Re: [Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
On 12/22/16 18:38, Jan Beulich wrote: On 19.09.16 at 07:52,wrote: Suravee Suthikulpanit (9): x86/HVM: Introduce struct hvm_pi_ops x86/vLAPIC: Declare vlapic_read_aligned() and vlapic_reg_write() as non-static x86/HVM: Call vlapic_destroy after vcpu_destroy x86/SVM: Modify VMCB fields to add AVIC support x86/HVM/SVM: Add AVIC initialization code x86/SVM: Add AVIC vmexit handlers x86/SVM: Add vcpu scheduling support for AVIC x86/SVM: Add interrupt management code via AVIC x86/SVM: Hook up miscellaneous AVIC functions Apart from the small comments on the individual patches I've just given, there are a number of cosmetic issues which will need dealing with, like coding style, use of plain int when unsigned int is meant, use of bool_t (or even plain int) when elsewhere you already properly use bool, and perhaps some constification. And I'm sorry for it having taken so long to get to look over this series. Jan Thanks for your review comment. I know you are busy. Your time is greatly appreciated. Konrad has also pointed out several styling issue which I have been making changes. I'll test and send out the V2. S ___ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
Re: [Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
>>> On 19.09.16 at 07:52,wrote: > Suravee Suthikulpanit (9): > x86/HVM: Introduce struct hvm_pi_ops > x86/vLAPIC: Declare vlapic_read_aligned() and vlapic_reg_write() as > non-static > x86/HVM: Call vlapic_destroy after vcpu_destroy > x86/SVM: Modify VMCB fields to add AVIC support > x86/HVM/SVM: Add AVIC initialization code > x86/SVM: Add AVIC vmexit handlers > x86/SVM: Add vcpu scheduling support for AVIC > x86/SVM: Add interrupt management code via AVIC > x86/SVM: Hook up miscellaneous AVIC functions Apart from the small comments on the individual patches I've just given, there are a number of cosmetic issues which will need dealing with, like coding style, use of plain int when unsigned int is meant, use of bool_t (or even plain int) when elsewhere you already properly use bool, and perhaps some constification. And I'm sorry for it having taken so long to get to look over this series. Jan ___ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
Re: [Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
Boris, On 9/20/16 21:34, Boris Ostrovsky wrote: BENCHMARK 1: HACKBENCH > == > > For measuring IPI performance used for scheduling workload, I have collected > some performance number on 2 and 3 CPU running hackbech with the following > detail: > > hackbench -p -l 10 > Running in process mode with 10 groups using 40 file descriptors each (== 400 tasks) > Each sender will pass 10 messages of 100 bytes > >| 2 vcpus (sec) | 3 vcpus (sec) > > No AVIC w/o evtchn | 299.57 |337.779 > No AVIC w/ evtchn | 270.37 |419.6064 >AVIC w/ evtchn | 181.46 |171.7957 >AVIC w/o evtchn | 171.81 |169.0858 > > Note: In "w/o evtchn" case, the Linux guest is built w/o > Xen guest support. Enlightened Linux tries to avoid using event channels for APIC accesses if XEN_HVM_CPUID_APIC_ACCESS_VIRT or XEN_HVM_CPUID_X2APIC_VIRT is set. I didn't notice either of these two bits set in the series. Should they be (probably the first one)? Or is this something you are planning for the second part? -boris Thanks for pointing this out. The XEN_HVM_CPUID_APIC_ACCESS_VIRT would likely be needed. Since it is related to MSI, this will be covered in the second part of this patch series. Thanks, Suravee ___ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
Re: [Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
On 09/19/2016 01:52 AM, Suravee Suthikulpanit wrote: > GITHUB > == > Latest git tree can be found at: > http://github.com/ssuthiku/xen.gitxen_avic_part1_v1 > > OVERVIEW > > This patch set is the first of the two-part patch series to introduce > the new AMD Advance Virtual Interrupt Controller (AVIC) support. > > Basically, SVM AVIC hardware virtualizes local APIC registers of each > vCPU via the virtual APIC (vAPIC) backing page. This allows guest access > to certain APIC registers without the need to emulate the hardware behavior > in the hypervisor. More information about AVIC can be found in the > AMD64 Architecture Programmer’s Manual Volume 2 - System Programming. > > http://support.amd.com/TechDocs/24593.pdf > > For SVM AVIC, we extend the existing kvm_amd driver to: > * Check CPUID to detect AVIC support in the processor > * Program new fields in VMCB to enable AVIC > * Introduce new AVIC data structures and add code to manage them > * Handle two new AVIC #VMEXITs > * Add new interrupt injection code using vAPIC backing page > instead of the existing V_IRQ, V_INTR_PRIO, V_INTR_VECTOR, > and V_IGN_TPR fields > > Currently, this patch series does not enable AVIC by default. > Users can enable SVM AVIC by specifying Xen parameter svm-avic=1. > > Later, in part 2, we will introduce the IOMMU AVIC support, which > provides speed up for PCI device pass-through use case by allowing > the IOMMU hardware to inject interrupt directly into the guest via > the vAPIC backing page. > > OVERALL PERFORMANCE > === > Currently, AVIC is available on the AMD family 15h models 6Xh > (Carrizo) processors and newer. Here, the Carizzo is used to collect > performance data shown below. > > Generally, SVM AVIC alone (w/o IOMMU AVIC) should provide overall speed up > for HVM guest since it does not require #vmexit into the hypervisor to > emulate certain guest accesses to local APIC registers. > > It should also improve performance when hypervisor wants to inject > interrupts into a running vcpu by setting the corresponded IRR > bit in the vAPIC backing page and trigger AVIC_DOORBELL MSR. > > For sending IPI interrupts between running vcpus in Linux guest, > Xen is default to using event channel. However, in case of > non-paravirtualize guest, AVIC can also provide performance > improvements for sending IPI. > > BENCHMARK 1: HACKBENCH > == > > For measuring IPI performance used for scheduling workload, I have collected > some performance number on 2 and 3 CPU running hackbech with the following > detail: > > hackbench -p -l 10 > Running in process mode with 10 groups using 40 file descriptors each (== > 400 tasks) > Each sender will pass 10 messages of 100 bytes > >| 2 vcpus (sec) | 3 vcpus (sec) > > No AVIC w/o evtchn | 299.57 |337.779 > No AVIC w/ evtchn | 270.37 |419.6064 >AVIC w/ evtchn | 181.46 |171.7957 >AVIC w/o evtchn | 171.81 |169.0858 > > Note: In "w/o evtchn" case, the Linux guest is built w/o > Xen guest support. Enlightened Linux tries to avoid using event channels for APIC accesses if XEN_HVM_CPUID_APIC_ACCESS_VIRT or XEN_HVM_CPUID_X2APIC_VIRT is set. I didn't notice either of these two bits set in the series. Should they be (probably the first one)? Or is this something you are planning for the second part? -boris > > CURRENT UNTESTED USE-CASES > === > - Nested VM > > Any feedback and comments are very much appreciated. > > Thank you, > Suravee > > Suravee Suthikulpanit (9): > x86/HVM: Introduce struct hvm_pi_ops > x86/vLAPIC: Declare vlapic_read_aligned() and vlapic_reg_write() as > non-static > x86/HVM: Call vlapic_destroy after vcpu_destroy > x86/SVM: Modify VMCB fields to add AVIC support > x86/HVM/SVM: Add AVIC initialization code > x86/SVM: Add AVIC vmexit handlers > x86/SVM: Add vcpu scheduling support for AVIC > x86/SVM: Add interrupt management code via AVIC > x86/SVM: Hook up miscellaneous AVIC functions > > xen/arch/x86/hvm/hvm.c | 4 +- > xen/arch/x86/hvm/svm/Makefile | 1 + > xen/arch/x86/hvm/svm/avic.c| 609 > + > xen/arch/x86/hvm/svm/intr.c| 4 + > xen/arch/x86/hvm/svm/svm.c | 57 +++- > xen/arch/x86/hvm/svm/vmcb.c| 9 +- > xen/arch/x86/hvm/vlapic.c | 5 +- > xen/arch/x86/hvm/vmx/vmx.c | 32 +- > xen/include/asm-x86/hvm/domain.h | 63 > xen/include/asm-x86/hvm/hvm.h | 4 +- > xen/include/asm-x86/hvm/svm/avic.h | 49 +++ > xen/include/asm-x86/hvm/svm/svm.h | 2 + > xen/include/asm-x86/hvm/svm/vmcb.h | 35 ++- > xen/include/asm-x86/hvm/vlapic.h | 4 + > xen/include/asm-x86/hvm/vmx/vmcs.h | 59 > 15 files changed, 843 insertions(+), 94
Re: [Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
On 9/19/16 20:09, Konrad Rzeszutek Wilk wrote: On Mon, Sep 19, 2016 at 12:52:39AM -0500, Suravee Suthikulpanit wrote: GITHUB == Latest git tree can be found at: http://github.com/ssuthiku/xen.gitxen_avic_part1_v1 OVERVIEW This patch set is the first of the two-part patch series to introduce the new AMD Advance Virtual Interrupt Controller (AVIC) support. Basically, SVM AVIC hardware virtualizes local APIC registers of each vCPU via the virtual APIC (vAPIC) backing page. This allows guest access to certain APIC registers without the need to emulate the hardware behavior in the hypervisor. More information about AVIC can be found in the AMD64 Architecture Programmer’s Manual Volume 2 - System Programming. http://support.amd.com/TechDocs/24593.pdf For SVM AVIC, we extend the existing kvm_amd driver to: kvm_amd ?, heheh Ooops. hehehe .. snip.. Note: In "w/o evtchn" case, the Linux guest is built w/o Xen guest support. You can also just boot Linux with 'xen_nopv' parameter which would do the same thing. Ok, Thanks for the tips. Suravee ___ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
Re: [Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
On Mon, Sep 19, 2016 at 12:52:39AM -0500, Suravee Suthikulpanit wrote: > GITHUB > == > Latest git tree can be found at: > http://github.com/ssuthiku/xen.gitxen_avic_part1_v1 > > OVERVIEW > > This patch set is the first of the two-part patch series to introduce > the new AMD Advance Virtual Interrupt Controller (AVIC) support. > > Basically, SVM AVIC hardware virtualizes local APIC registers of each > vCPU via the virtual APIC (vAPIC) backing page. This allows guest access > to certain APIC registers without the need to emulate the hardware behavior > in the hypervisor. More information about AVIC can be found in the > AMD64 Architecture Programmer’s Manual Volume 2 - System Programming. > > http://support.amd.com/TechDocs/24593.pdf > > For SVM AVIC, we extend the existing kvm_amd driver to: kvm_amd ?, heheh .. snip.. > Note: In "w/o evtchn" case, the Linux guest is built w/o > Xen guest support. You can also just boot Linux with 'xen_nopv' parameter which would do the same thing. ___ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
[Xen-devel] [RFC PATCH 0/9] Introduce AMD SVM AVIC
GITHUB == Latest git tree can be found at: http://github.com/ssuthiku/xen.gitxen_avic_part1_v1 OVERVIEW This patch set is the first of the two-part patch series to introduce the new AMD Advance Virtual Interrupt Controller (AVIC) support. Basically, SVM AVIC hardware virtualizes local APIC registers of each vCPU via the virtual APIC (vAPIC) backing page. This allows guest access to certain APIC registers without the need to emulate the hardware behavior in the hypervisor. More information about AVIC can be found in the AMD64 Architecture Programmer???s Manual Volume 2 - System Programming. http://support.amd.com/TechDocs/24593.pdf For SVM AVIC, we extend the existing kvm_amd driver to: * Check CPUID to detect AVIC support in the processor * Program new fields in VMCB to enable AVIC * Introduce new AVIC data structures and add code to manage them * Handle two new AVIC #VMEXITs * Add new interrupt injection code using vAPIC backing page instead of the existing V_IRQ, V_INTR_PRIO, V_INTR_VECTOR, and V_IGN_TPR fields Currently, this patch series does not enable AVIC by default. Users can enable SVM AVIC by specifying Xen parameter svm-avic=1. Later, in part 2, we will introduce the IOMMU AVIC support, which provides speed up for PCI device pass-through use case by allowing the IOMMU hardware to inject interrupt directly into the guest via the vAPIC backing page. OVERALL PERFORMANCE === Currently, AVIC is available on the AMD family 15h models 6Xh (Carrizo) processors and newer. Here, the Carizzo is used to collect performance data shown below. Generally, SVM AVIC alone (w/o IOMMU AVIC) should provide overall speed up for HVM guest since it does not require #vmexit into the hypervisor to emulate certain guest accesses to local APIC registers. It should also improve performance when hypervisor wants to inject interrupts into a running vcpu by setting the corresponded IRR bit in the vAPIC backing page and trigger AVIC_DOORBELL MSR. For sending IPI interrupts between running vcpus in Linux guest, Xen is default to using event channel. However, in case of non-paravirtualize guest, AVIC can also provide performance improvements for sending IPI. BENCHMARK 1: HACKBENCH == For measuring IPI performance used for scheduling workload, I have collected some performance number on 2 and 3 CPU running hackbech with the following detail: hackbench -p -l 10 Running in process mode with 10 groups using 40 file descriptors each (== 400 tasks) Each sender will pass 10 messages of 100 bytes | 2 vcpus (sec) | 3 vcpus (sec) No AVIC w/o evtchn | 299.57 |337.779 No AVIC w/ evtchn | 270.37 |419.6064 AVIC w/ evtchn | 181.46 |171.7957 AVIC w/o evtchn | 171.81 |169.0858 Note: In "w/o evtchn" case, the Linux guest is built w/o Xen guest support. CURRENT UNTESTED USE-CASES === - Nested VM Any feedback and comments are very much appreciated. Thank you, Suravee Suravee Suthikulpanit (9): x86/HVM: Introduce struct hvm_pi_ops x86/vLAPIC: Declare vlapic_read_aligned() and vlapic_reg_write() as non-static x86/HVM: Call vlapic_destroy after vcpu_destroy x86/SVM: Modify VMCB fields to add AVIC support x86/HVM/SVM: Add AVIC initialization code x86/SVM: Add AVIC vmexit handlers x86/SVM: Add vcpu scheduling support for AVIC x86/SVM: Add interrupt management code via AVIC x86/SVM: Hook up miscellaneous AVIC functions xen/arch/x86/hvm/hvm.c | 4 +- xen/arch/x86/hvm/svm/Makefile | 1 + xen/arch/x86/hvm/svm/avic.c| 609 + xen/arch/x86/hvm/svm/intr.c| 4 + xen/arch/x86/hvm/svm/svm.c | 57 +++- xen/arch/x86/hvm/svm/vmcb.c| 9 +- xen/arch/x86/hvm/vlapic.c | 5 +- xen/arch/x86/hvm/vmx/vmx.c | 32 +- xen/include/asm-x86/hvm/domain.h | 63 xen/include/asm-x86/hvm/hvm.h | 4 +- xen/include/asm-x86/hvm/svm/avic.h | 49 +++ xen/include/asm-x86/hvm/svm/svm.h | 2 + xen/include/asm-x86/hvm/svm/vmcb.h | 35 ++- xen/include/asm-x86/hvm/vlapic.h | 4 + xen/include/asm-x86/hvm/vmx/vmcs.h | 59 15 files changed, 843 insertions(+), 94 deletions(-) create mode 100644 xen/arch/x86/hvm/svm/avic.c create mode 100644 xen/include/asm-x86/hvm/svm/avic.h -- 1.9.1 ___ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel