{"id":556363,"date":"2022-03-06T05:42:15","date_gmt":"2022-03-05T21:42:15","guid":{"rendered":"http:\/\/4563.org\/?p=556363"},"modified":"2022-03-06T05:42:15","modified_gmt":"2022-03-05T21:42:15","slug":"%e4%bd%bf%e7%94%a8-linux-vfio-%e5%b0%86-nvidia-gpu-%e9%80%8f%e4%bc%a0%e7%bb%99-qemu-%e8%99%9a%e6%8b%9f%e6%9c%ba-33","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=556363","title":{"rendered":"\u4f7f\u7528 Linux vfio \u5c06 Nvidia GPU \u900f\u4f20\u7ed9 QEMU \u865a\u62df\u673a"},"content":{"rendered":"<div>\n<div>\n<div>\n<h1> \u4f7f\u7528 Linux vfio \u5c06 Nvidia GPU \u900f\u4f20\u7ed9 QEMU \u865a\u62df\u673a <\/h1>\n<p> <\/p>\n<div>\n<div> <span>\u8cc7\u6df1\u5927\u4f6c : Cloudpods <\/span>  <span><i><\/i> 72<\/span> <\/div>\n<div> <\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<div isfirst=\"1\"> <\/p>\n<p>Linux \u4e0a\u865a\u62df\u673a GPU \u900f\u4f20\u9700\u8981\u4f7f\u7528 vfio \u7684\u65b9\u5f0f\u3002\u4e3b\u8981\u662f\u56e0\u4e3a\u5728 vfio \u65b9\u5f0f\u4e0b\u5bf9\u865a\u62df\u8bbe\u5907\u7684\u6743\u9650\u548c DMA \u9694\u79bb\u4e0a\u505a\u7684\u66f4\u597d\u3002\u4f46\u662f\u8fd9\u4e48\u505a\u4e5f\u6709\u4e2a\u7f3a\u70b9\uff0c\u8fd9\u4e2a\u7269\u7406\u8bbe\u5907\u5728\u4e3b\u673a\u548c\u5176\u4ed6\u865a\u62df\u673a\u90fd\u4e0d\u80fd\u4f7f\u7528\u4e86\u3002<\/p>\n<p>qemu \u76f4\u63a5\u4f7f\u7528\u7269\u7406\u8bbe\u5907\u672c\u8eab\u547d\u4ee4\u884c\u662f\u5f88\u7b80\u5355\u7684\uff0c\u5173\u952e\u5728\u4e8e\u4e8b\u5148\u5728\u4e3b\u673a\u4e0a\u5bf9\u7cfb\u7edf\u3001\u5185\u6838\u548c\u7269\u7406\u8bbe\u5907\u7684\u4e00\u4e9b\u914d\u7f6e\u3002<\/p>\n<p>\u5355\u7eaf\u4ece qemu \u7684\u547d\u4ee4\u884c\u6765\u770b\uff0c\u5176\u5b9e\u548c\u666e\u901a\u865a\u62df\u673a\u542f\u52a8\u5c31\u5dee\u4e86\u6700\u540e\u90a3\u4e2a <code>-device<\/code> \u7684\u9009\u9879\u3002\u8fd9\u4e2a\u9009\u9879\u4e5f\u6bd4\u8f83\u5bb9\u6613\u7406\u89e3\uff0c\u5c31\u662f\u628a\u4e3b\u673a\u4e0a\u7684\u8bbe\u5907 0000:00:01.0 \u4f20\u7ed9\u4e86\u865a\u62df\u673a\u4f7f\u7528\u3002<\/p>\n<pre><code>$ qemu-system-x86_64 -m 4096 -smp 4 --enable-kvm    -drive file=~\/guest\/fedora.img    -device vfio-pci,host=0000:00:01.0 <\/code><\/pre>\n<h2>\u7cfb\u7edf\u53ca\u786c\u4ef6\u51c6\u5907<\/h2>\n<h3>BIOS \u4e2d\u6253\u5f00 IOMMU<\/h3>\n<p>\u8bbe\u5907\u76f4\u901a\u5728 x86 \u5e73\u53f0\u4e0a\u9700\u8981\u6253\u5f00 iommu \u529f\u80fd\u3002\u8fd9\u662f Intel \u865a\u62df\u6280\u672f VT-d(Virtualization Technology for Device IO) \u4e2d\u7684\u4e00\u4e2a\u90e8\u5206\u3002\u6709\u65f6\u5019\u8fd9\u90e8\u5206\u7684\u529f\u80fd\u6ca1\u6709\u88ab\u6253\u5f00\u3002<\/p>\n<p>\u6253\u5f00\u7684\u65b9\u5f0f\u5728 BIOS \u8bbe\u7f6e\u4e2d Security-&gt;Virtualization-&gt;VT-d \u8fd9\u4e2a\u4f4d\u7f6e\u3002\u5f53\u7136\u4e0d\u540c\u7684 BIOS \u4f4d\u7f6e\u53ef\u80fd\u4f1a\u7565\u6709\u4e0d\u540c\u3002\u8bb0\u5f97\u5728\u4f7f\u7528\u76f4\u901a\u8bbe\u5907\u524d\u8981\u5c06\u8fd9\u4e2a\u9009\u9879\u6253\u5f00\u3002<\/p>\n<h3>\u5185\u6838\u914d\u7f6e\u52fe\u9009 IOMMU<\/h3>\n<pre><code>INTEL_IOMMU \u2502 Location: \u2502 \u2502 -&gt; Device Drivers \u2502 \u2502 (2) -&gt; IOMMU Hardware Support (IOMMU_SUPPORT [=y]) <\/code><\/pre>\n<h3>\u5185\u6838\u542f\u52a8\u53c2\u6570 enable IOMMU<\/h3>\n<p>BIOS \u4e2d\u6253\u5f00\uff0c\u5185\u6838\u7f16\u8bd1\u9009\u9879\u52fe\u9009\u8fd8\u4e0d\u591f\u3002\u8fd8\u9700\u8981\u5728\u5f15\u5bfc\u7a0b\u5e8f\u4e2d\u6dfb\u52a0\u4e0a\u5185\u6838\u542f\u52a8\u53c2\u6570<\/p>\n<pre><code># \u5bf9\u5e94\u7f16\u8f91 \/etc\/default\/grub, \u8bbe\u7f6e GRUB_CMDLINE_LINUX= $ cat \/etc\/default\/grub ... GRUB_CMDLINE_LINUX=\"intel_iommu=on iommu=pt vfio_iommu_type1.allow_unsafe_interrupts=1 rdblacklist=nouveau nouveau.modeset=0\" ...   # \u91cd\u65b0\u751f\u6210 grub \u5f15\u5bfc\u914d\u7f6e\u6587\u4ef6 $ grub2-mkconfig -o \/boot\/grub2\/grub.cfg   # \u5c06 vfio \u76f8\u5173 module \u8bbe\u7f6e\u4e3a\u5f00\u673a load $ cat \/etc\/modules-load.d\/vfio.conf vfio vfio_iommu_type1 vfio_pci vfio_virqfd <\/code><\/pre>\n<p>Setting up IOMMU Kernel parameters<\/p>\n<h3>\u627e\u5230 nvidia GPU BusID<\/h3>\n<p>record PCI addresses and hardware IDs of the GPU<\/p>\n<pre><code>$ lspci -k | grep -i nvidia -A 3                    41:00.0 VGA compatible controller: NVIDIA Corporation GP107 [GeForce GTX 1050 Ti] (rev a1)         Subsystem: Device 1b4c:11bf         Kernel driver in use: vfio-pci         Kernel modules: nouveau 41:00.1 Audio device: NVIDIA Corporation GP107GL High Definition Audio Controller (rev a1)         Subsystem: Device 1b4c:11bf         Kernel driver in use: snd_hda_intel         Kernel modules: snd_hda_intel # pci address =&gt; 41:00.0,41:00.1 # device id =&gt; 1b4c:11bf   # \u8fd9\u91cc\u627e\u5230\u4e86\u4e24\u5f20 nvidia \u5361\uff0c\u5b83\u4eec\u7684 device id \u90fd\u662f 1b4c:11bf, \u4e00\u5f20\u662f Audio device # \u8fd9\u6837\u662f\u4e0d\u80fd passthrough \u8fdb\u53bb\u7684\uff0c\u56e0\u4e3a: # vfio-pci use your vendor and device id pair to identify which device they need to bind to at boot, # if you have two GPUs sharing such an ID pair you will not be able to get your passthough driver to bind with just one of them # \u4f7f\u7528\u4e0b\u9762\u7684\u811a\u672c\u89e3\u51b3\u8fd9\u79cd\u60c5\u51b5\uff1a   $ cat \/usr\/bin\/vfio-pci-override.sh #!\/bin\/sh   for i in $(find \/sys\/devices\/pci* -name boot_vga); do     if [ $(cat \"$i\") -eq 0 ]; then         GPU=\"${i%\/boot_vga}\"         AUDIO=\"$(echo \"$GPU\" | sed -e \"s\/0$\/1\/\")\"         echo \"vfio-pci\" &gt; \"$GPU\/driver_override\"         if [ -d \"$AUDIO\" ]; then             echo \"vfio-pci\" &gt; \"$AUDIO\/driver_override\"         fi     fi done   modprobe -i vfio-pci   # \u628a\u811a\u672c\u4f20\u5165 \/etc\/modprobe.d\/vfio.conf $ cat \/etc\/modprobe.d\/vfio.conf install vfio-pci \/usr\/bin\/vfio-pci-override.sh options vfio-pci ids=10de:1c82 disable_vga=1 <\/code><\/pre>\n<h3>\u4f7f\u7528 vfio \u7ba1\u7406 GPU<\/h3>\n<pre><code># \/etc\/modprobe.d\/vfio.conf, ids \u4e3a lspci \u627e\u5230\u7684 hardware id, \u591a\u4e2a\u8bbe\u5907\u7684\u8bdd\u7528','\u5206\u5272 $ cat \/etc\/modprobe.d\/vfio.conf options vfio-pci ids=10de:134d disable_vga=1   # \u7981\u7528 NVIDIA nouveau \u5f00\u6e90\u9a71\u52a8, \/etc\/modprobe.d\/blacklist.conf $ cat \/etc\/modprobe.d\/blacklist.conf blacklist nouveau   # kvm \u6a21\u5757\u914d\u7f6e, \/etc\/modprobe.d\/kvm.conf $ cat \/etc\/modprobe.d\/kvm.conf options kvm ignore_msrs=1 <\/code><\/pre>\n<p>\u91cd\u542f\u7cfb\u7edf\uff0c\u542f\u52a8\u5b8c\u6210\u540e\u67e5\u770b\u5f53\u524d\u7684 nvidia GPU \u662f\u5426\u88ab vfio-pci \u6a21\u5757\u4f7f\u7528, \u786e\u8ba4 IOMMU \u529f\u80fd\u786e\u5b9e\u6253\u5f00\u3002<\/p>\n<pre><code>$ dmesg | grep -e DMAR -e IOMMU | grep enabled   # \u5982\u679c\u80fd\u641c\u7d22\u5230 DMAR: IOMMU enabled # \u8868\u793a\u4e0a\u8ff0\u914d\u7f6e\u6210\u529f\u3002   # \u67e5\u770b GPU \u662f\u5426\u88ab vfio-pci \u4f7f\u7528 # \u53e6\u5916\u6ce8\u610f\u68c0\u67e5\u770b\u770b 41:00.1 Audio device \u662f\u5426\u4e5f\u88ab vfio-pci \u4f7f\u7528 $ lspci -k | grep -i -e nvidia -A 3 41:00.0 VGA compatible controller: NVIDIA Corporation GP107 [GeForce GTX 1050 Ti] (rev a1)     Subsystem: Device 1b4c:11bf     Kernel driver in use: vfio-pci # GTX 1050 Ti GPU \u88ab vfio-pci \u4f7f\u7528     Kernel modules: nouveau 41:00.1 Audio device: NVIDIA Corporation GP107GL High Definition Audio Controller (rev a1)     Subsystem: Device 1b4c:11bf     Kernel driver in use: vfio-pci # \u53d1\u73b0 Audio device \u4e5f\u88ab vfio-pci \u4f7f\u7528\u4e86     Kernel modules: snd_hda_intel ... <\/code><\/pre>\n<pre><code># list GPU IOMMU group $ find \/sys\/kernel\/iommu_groups\/ -type l | grep 41:00 \/sys\/kernel\/iommu_groups\/27\/devices\/0000:41:00.0 \/sys\/kernel\/iommu_groups\/27\/devices\/0000:41:00.1   # \u627e\u5230 IOMMU Group \u7ba1\u7406\u7684 PCI \u8bbe\u5907 #!\/bin\/bash shopt -s nullglob for d in \/sys\/kernel\/iommu_groups\/*\/devices\/*; do   n=${d#*\/iommu_groups\/*}; n=${n%%\/*}   printf 'IOMMU Group %s ' \"$n\"   lspci -nns \"${d##*\/}\" done <\/code><\/pre>\n<h3>\u4f7f\u7528 qemu \u900f\u4f20 nvidia GPU<\/h3>\n<p>\u51c6\u5907\u597d centos7 \u955c\u50cf\uff0c\u7136\u540e\u5728\u865a\u62df\u673a\u91cc\u9762\u5b89\u88c5 nvidia \u5b98\u65b9\u95ed\u6e90\u9a71\u52a8\u548c cuda SDK<\/p>\n<pre><code># \u6211\u4ece\u670d\u52a1\u5668\u4e0a\u62f7\u8d1d\u8fc7\u6765\u7684\u662f vmdk \u7684\u955c\u50cf\uff0c\u5148\u628a\u5b83\u8f6c\u6362\u6210 qcow2 \u7684\u683c\u5f0f $ \/usr\/local\/qemu-2.9.0\/bin\/qemu-img convert -f vmdk -O qcow2 centos-7.3.1611-20180104.vmdk centos-7.3.1611-20180104.qcow2   # \u4f7f\u7528 qemu \u542f\u52a8\uff0c\u6ce8\u610f-cpu \u9700\u8981 kvm=off \u53c2\u6570 # kvm=off will hide the kvm hypervisor signature, this is required for NVIDIA cards # since its driver will refuse to work on an hypervisor and result in Code 43 on windows $ cat startvm.sh #!\/bin\/sh \/usr\/local\/qemu-2.9.0\/bin\/qemu-system-x86_64 -enable-kvm  -m 4096 -cpu host,kvm=off -smp 4,sockets=1,cores=4,threads=1  -drive file=.\/centos-7.3.1611-20180104.qcow2  -device vfio-pci,host=41:00.0,multifunction=on,addr=0x16  -device vfio-pci,host=41:00.1  -net nic,model=e1000 -net user,hostfwd=tcp::5022-:22  -vnc :1   # \u8fd9\u53f0\u865a\u62df\u673a\u5f00\u4e86 vnc \u548c ssh \u7aef\u53e3\u8f6c\u53d1\uff0c\u53ef\u4ee5\u4f7f\u7528 vnc \u6216\u8005 ssh \u8bbf\u95ee   # \u4ece host \u8fdb\u5165\u865a\u62df\u673a $ ssh 127.0.0.1 -p 5022   # \u67e5\u770b\u865a\u62df\u673a\u900f\u4f20\u8fdb\u6765\u7684\u663e\u5361 $ lspci -k | grep -i nvidia -A 3 00:04.0 Audio device: NVIDIA Corporation Device 0fb9 (rev a1)     Subsystem: Device 1b4c:11bf     Kernel driver in use: snd_hda_intel     Kernel modules: snd_hda_intel 00:16.0 VGA compatible controller: NVIDIA Corporation GP107 (rev a1)     Subsystem: Device 1b4c:11bf     Kernel modules: nouveau <\/code><\/pre>\n<h2>\u5b89\u88c5 nvidia \u9a71\u52a8\u548c Cuda<\/h2>\n<p>nvidia \u9a71\u52a8\u9700\u8981\u4ece\u5b98\u65b9\u4e0b\u8f7d\uff0c\u5982\u679c\u5148\u5b89\u88c5 cuda \u7684\u8bdd\u4f1a\u4e00\u540c\u5b89\u88c5 nvidia \u9a71\u52a8\u3002 \u63a5\u4e0b\u6765\u91c7\u7528\u865a\u62df\u673a\u5148\u5b89\u88c5\u9a71\u52a8\u518d\u5b89\u88c5 cuda \u7684\u6b65\u9aa4\u3002<\/p>\n<p>\u53c2\u8003\uff1a installing-nvidia-drivers-centos-7 NVIDIA CUDA GETTINGS STARTED GUIDE FOR LINUX<\/p>\n<h3>\u5b89\u88c5 nvidia \u9a71\u52a8<\/h3>\n<p>\u4e0b\u8f7d\u5730\u5740\uff1a http:\/\/www.nvidia.com\/object\/unix.html<\/p>\n<pre><code># update \u540e\u5982\u679c\u66f4\u65b0\u5185\u6838\uff0c\u9700\u8981\u91cd\u542f $ yum -y update   # \u5b89\u88c5 gcc \u3001make \u3001glibc \u7b49\u5de5\u5177\u548c\u5e93 $ yum -y groupinstall \"Development Tools\" $ yum -y install kernel-devel   # Download the latest NVIDIA driver for unix. $ wget http:\/\/us.download.nvidia.com\/XFree86\/Linux-x86_64\/390.42\/NVIDIA-Linux-x86_64-390.42.run $ yum -y install epel-release $ yum -y install dkms   # Edit \/etc\/default\/grub. Append the following  to \u201cGRUB_CMDLINE_LINUX\u201d rd.driver.blacklist=nouveau nouveau.modeset=0   # Generate a new grub configuration to include the above changes. $ grub2-mkconfig -o \/boot\/grub2\/grub.cfg   # Edit\/create \/etc\/modprobe.d\/blacklist.conf and append: blacklist nouveau   # Backup your old initramfs and then build a new one $ mv \/boot\/initramfs-$(uname -r).img \/boot\/initramfs-$(uname -r)-nouveau.img $ dracut \/boot\/initramfs-$(uname -r).img $(uname -r)   # \u91cd\u542f again   # Run the NVIDIA driver installer and enter yes to all options. $ sh NVIDIA-Linux-x86_64-*.run   # \u88c5\u597d\u540e\u518d\u4e00\u6b21\u91cd\u542f\uff0clspci -k \u770b\u4e0b gpu \u4f7f\u7528\u7684\u9a71\u52a8\u662f\u5426\u662f nvidia $ lspci -k | grep -i nvidia -A 3 00:04.0 Audio device: NVIDIA Corporation GP107GL High Definition Audio Controller (rev a1) 00:16.0 VGA compatible controller: NVIDIA Corporation GP107 [GeForce GTX 1050 Ti] (rev a1)     Kernel driver in use: nvidia # \u53d1\u73b0\u5df2\u7ecf\u4f7f\u7528 nvidia \u9a71\u52a8     Kernel modules: nouveau, nvidia_drm, nvidia   # \u6267\u884c nvidia-smi \u770b\u4e0b\u8f93\u51fa\u548c\u6e29\u5ea6 $ nvidia-smi Thu Mar 15 01:31:09 2018       +-----------------------------------------------------------------------------+ | NVIDIA-SMI 390.42                 Driver Version: 390.42                    | |-------------------------------+----------------------+----------------------+ | GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC | | Fan  Temp  Perf  Pwr:Usage\/Cap|         Memory-Usage | GPU-Util  Compute M. | |===============================+======================+======================| |   0  GeForce GTX 105...  Off  | 00000000:00:16.0 Off |                  N\/A | | 40%   32C    P0    N\/A \/ 100W |      0MiB \/  4040MiB |      0%      Default | +-------------------------------+----------------------+----------------------+   +-----------------------------------------------------------------------------+ | Processes:                                                       GPU Memory | |  GPU       PID   Type   Process name                             Usage      | |=============================================================================| |  No running processes found                                                 | +-----------------------------------------------------------------------------+   $ nvidia-smi -q -d TEMPERATURE   ==============NVSMI LOG==============   Timestamp                           : Thu Mar 15 01:32:42 2018 Driver Version                      : 390.42   Attached GPUs                       : 1 GPU 00000000:00:16.0     Temperature         GPU Current Temp            : 32 C         GPU Shutdown Temp           : 102 C         GPU Slowdown Temp           : 99 C         GPU Max Operating Temp      : N\/A         Memory Current Temp         : N\/A         Memory Max Operating Temp   : N\/A <\/code><\/pre>\n<h3>\u5b89\u88c5 cuda<\/h3>\n<p>\u4e0b\u8f7d\u5730\u5740\uff1a https:\/\/developer.nvidia.com\/cuda-downloads \u8fd9\u91cc\u9009\u62e9 runfile \uff0c\u4ee5\u540e\u4e3a\u4e86\u65b9\u4fbf\u4e5f\u53ef\u4ee5\u9009\u62e9 rpm(network)\u7684\u65b9\u5f0f\uff0c\u4f1a\u81ea\u52a8\u5e2e\u6211\u4eec\u5b89\u88c5 nvidia \u9a71\u52a8<\/p>\n<pre><code>$ wget https:\/\/developer.nvidia.com\/compute\/cuda\/9.1\/Prod\/local_installers\/cuda_9.1.85_387.26_linux   # Say no to installing the NVIDIA driver. # The standalone driver you already installed is typically newer than what is packaged with CUDA. # Use the default option for all other choices. $ sh cuda_*.run   # \u6dfb\u52a0 CUDA \u76f8\u5173\u7684\u73af\u5883\u53d8\u91cf export PATH=$PATH:\/usr\/local\/cuda\/bin export LD_LIBRARY_PATH=\/usr\/local\/cuda\/lib64:$LD_LIBRARY_PATH   # make samples $ cd ~\/NVIDIA_CUDA-9.1_Samples; make -j 4 $ cd bin\/x86_64\/linux\/release $ .\/deviceQuery # \u67e5\u8be2 gpu \u4fe1\u606f .\/deviceQuery Starting...    CUDA Device Query (Runtime API) version (CUDART static linking)   Detected 1 CUDA Capable device(s)   Device 0: \"GeForce GTX 1050 Ti\"   CUDA Driver Version \/ Runtime Version          9.1 \/ 9.1   CUDA Capability Major\/Minor version number:    6.1   Total amount of global memory:                 4040 MBytes (4236312576 bytes)   ( 6) Multiprocessors, (128) CUDA Cores\/MP:     768 CUDA Cores   GPU Max Clock rate:                            1481 MHz (1.48 GHz)   Memory Clock rate:                             3504 Mhz   Memory Bus Width:                              128-bit   L2 Cache Size:                                 1048576 bytes ...   $ .\/bandwidtTest # \u4f7f\u7528 cuda \u6d4b\u8bd5 gpu bandwidth Running on...    Device 0: GeForce GTX 1050 Ti  Quick Mode    Host to Device Bandwidth, 1 Device(s)  PINNED Memory Transfers    Transfer Size (Bytes)    Bandwidth(MB\/s)    33554432            9719.0    Device to Host Bandwidth, 1 Device(s)  PINNED Memory Transfers    Transfer Size (Bytes)    Bandwidth(MB\/s)    33554432            9215.8    Device to Device Bandwidth, 1 Device(s)  PINNED Memory Transfers    Transfer Size (Bytes)    Bandwidth(MB\/s)    33554432            95525.1   Result = PASS   NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled. <\/code><\/pre>\n<p><strong>\u4f5c\u8005:<\/strong> \u4e91\u8054\u58f9\u4e91\u674e\u6cfd\u73ba<\/p>\n<p><strong>GitHub:<\/strong> https:\/\/github.com\/yunionio\/cloudpods<\/p>\n<p><strong>\u5f00\u6e90\u5730\u5740\uff1a<\/strong> https:\/\/www.cloudpods.org\/<\/p>\n<p><strong>Cloudpods \u662f\u4e00\u4e2a\u5f00\u6e90\u7684 Golang \u5b9e\u73b0\u7684\u4e91\u539f\u751f\u7684\u591a\u4e91\u548c\u6df7\u5408\u4e91\u878d\u5408\u5e73\u53f0\u3002Cloudpods \u4e0d\u4ec5\u53ef\u4ee5\u7ba1\u7406\u672c\u5730\u7684\u865a\u62df\u673a\u548c\u7269\u7406\u673a\u8d44\u6e90\uff0c\u8fd8\u53ef\u4ee5\u7ba1\u7406\u5176\u4ed6\u516c\u6709\u4e91\u548c\u79c1\u6709\u4e91\u5e73\u53f0\u7684\u8d44\u6e90\u3002<\/strong><\/p>\n<\/p><\/div>\n<div> <b>\u5927\u4f6c\u6709\u8a71\u8aaa<\/b> (<span>0<\/span>) <\/div>\n<div> <\/div>\n<\/p><\/div>\n<\/p><\/div>\n<ul>\n<li>\n","protected":false},"excerpt":{"rendered":"<p>\u4f7f\u7528 Linux vfio \u5c06 N&hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/556363"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=556363"}],"version-history":[{"count":0,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/556363\/revisions"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=556363"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=556363"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=556363"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}