Re: [Xen-devel] (v2) VT-d Posted-interrupt (PI) design for XEN

[Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>]

On Thu, Mar 19, 2015 at 03:03:55AM +0000, Wu, Feng wrote:
> Thanks for the comments!
> 
> > -----Original Message-----
> > From: Konrad Rzeszutek Wilk [mailto:konrad.wilk@xxxxxxxxxx]
> > Sent: Thursday, March 19, 2015 12:10 AM
> > To: Wu, Feng
> > Cc: xen-devel@xxxxxxxxxxxxx; Zhang, Yang Z; Tian, Kevin; Keir Fraser
> > (keir@xxxxxxx); Jan Beulich (JBeulich@xxxxxxxx)
> > Subject: Re: [Xen-devel] (v2) VT-d Posted-interrupt (PI) design for XEN
> > 
> > On Wed, Mar 18, 2015 at 12:44:21PM +0000, Wu, Feng wrote:
> > > VT-d Posted-interrupt (PI) design for XEN
> > >
> > > Background
> > > ==========
> > > With the development of virtualization, there are more and more device
> > > assignment requirements. However, today when a VM is running with
> > > assigned devices (such as, NIC), external interrupt handling for the 
> > > assigned
> > > devices always needs VMM intervention.
> > >
> > > VT-d Posted-interrupt is a more enhanced method to handle interrupts
> > > in the virtualization environment. Interrupt posting is the process by
> > > which an interrupt request is recorded in a memory-resident
> > > posted-interrupt-descriptor structure by the root-complex, followed by
> > > an optional notification event issued to the CPU complex.
> > >
> > > With VT-d Posted-interrupt we can get the following advantages:
> > > - Direct delivery of external interrupts to running vCPUs without VMM
> > > intervention
> > 
> > 
> > I hadn't digged deep in what Xen has currently - but I would assume that
> > this is exactly what we have now in Xen?
> 
> Here is what Xen currently does for external interrupts from assigned devices:
> 
> When a VM is running and an external interrupts from an assigned devices 
> occurs
> for it. VM-EXIT happens, then:
> 
> vmx_do_extint() --> do_IRQ() --> __do_IRQ_guest() --> hvm_do_IRQ_dpci() --> 
> raise_softirq_for(pirq_dpci) --> raise_softirq(HVM_DPCI_SOFTIRQ)
> 
> softirq HVM_DPCI_SOFTIRQ is bound to dpci_softirq()
> 
> dpci_softirq() --> hvm_dirq_assist() --> vmsi_deliver_pirq() --> 
> vmsi_deliver() -->
> vmsi_inj_irq() --> vlapic_set_irq()

<nods> This would be fantastic to put in the design document to help
people make sure that their expectations are in line.

> 
> vlapic_set_irq() does the following things:
> 1. If CPU-side posted-interrupt is supported (I think it is supported from 
> Xen 4.3, or Xen 4.4,
> sorry, not quite remember the exact version), call vmx_deliver_posted_intr() 
> to deliver
> the virtual interrupt via posted-interrupt infrastructure.

The benefit is that if an interrupt comes for VCPU0 instead of
VCPU1 we can inject the interrupt in the VCPU1 without having it
do an VMEXIT.

However if we pin the vCPUs, then CPU-side posted interrupt do not
help - we still have to process the interrupt in Xen hypervisor.

> 2. Else If CPU-side posted-interrupt is not supported, set the related vIRR 
> in vLAPIC
> page and call vcpu_kick() to kick the related vCPU. Before VM-Entry, 
> vmx_intr_assist()
> will help to inject the interrupt to guests.
> 
> However, after VT-d PI is supported, when a guest is running in non-root and 
> an
> external interrupt from an assigned device occurs for it. _no_ VM-Exit is 
> needed,
> the guest can handle this totally in non-root mode, thus avoiding all the 
> above
> code flow.

<nods> However it does require for Linux PVHVM guests to not use the
vector callback mechanism - or rather - not use the event mechanism.

What you require for this to work on the Linux side is for the PCIe
device to use the 'baremetal' mechanism to setup MSIs (program the
IOAPIC, etc). It would be worth mentioning this in the document too.

> 
> > 
> > Hm, actually we seem to be still invoking the hypervisor on the
> > interrupts  -except that if we need to dispatch it to another CPU
> > using an normal vector to do so - which would still cause the
> > hypervisor to be invoked? Or does it actually go straight in the
> > guest?
> > 
> 
> Like what I mentioned above, If the guest is running, we don't need invoke 
> hypervisor.
> 
> > So what kind of support do we currently have in Xen from posted
> > interrupt? Could you add a bit about this in the background please?
> 
> Good suggestion.
> 
> Currently, Xen only supports the CPU-side posted-interrupt. Like what I 
> mentioned above,
> function vlapic_set_irq() can use this to deliver virtual interrupts, 
> basically there are several
> methods to deliver virtual interrupts to guests:
> - Event delivery before VM-Entry via __vmx_inject_exception(), this is the 
> oldest way.
> - After APICv was enabled, we had hardware support for virtual interrupt 
> delivery, virtual
> interrupts are stored in virtual LAPIC page, after VM-Entry, guests can 
> evaluate these
> virtual interrupt and handle them in non-root mode.
> - As an enhancement to APICv, CPU-side posted-interrupt was introduced, like 
> above comments,
> with this new feature, we don't need to kick the vCPU and deliver the virtual 
> interrupts
> direct to it.
> 
> About APICv and CPU-side Posted-interrupt, please refer to Chapter 29, and 
> Section 29.6 in the Intel SDM: 
> http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-software-developer-manual-325462.pdf
> 
> > 
> > > - Decrease the interrupt migration complexity. On vCPU migration, software
> > > can atomically co-migrate all interrupts targeting the migrating vCPU. For
> > > virtual machines with assigned devices, migrating a vCPU across pCPUs
> > > either incur the overhead of forwarding interrupts in software (e.g. via 
> > > VMM
> > > generated IPIS), or complexity to independently migrate each interrupt
> > targeting
> > > the vCPU to the new pCPU. However, after enabling VT-d PI, the destination
> > vCPU
> > > of an external interrupt from assigned devices is stored in the IRTE (i.e.
> > > Posted-interrupt Descriptor Address), when vCPU is migrated to another
> > pCPU,
> > > we will set this new pCPU in the 'NDST' filed of Posted-interrupt 
> > > descriptor,
> > this
> > > make the interrupt migration automatic.
> > >
> > >
> > > Posted-interrupt Introduction
> > > ========================
> > > There are two components to the Posted-interrupt architecture:
> > > Processor Support and Root-Complex Support
> > >
> > > - Processor Support
> > > Posted-interrupt processing is a feature by which a processor processes
> > > the virtual interrupts by recording them as pending on the virtual-APIC
> > > page.
> > >
> > > Posted-interrupt processing is enabled by setting the "process posted
> > > interrupts" VM-execution control. The processing is performed in response
> > > to the arrival of an interrupt with the posted-interrupt notification 
> > > vector.
> > > In response to such an interrupt, the processor processes virtual 
> > > interrupts
> > > recorded in a data structure called a posted-interrupt descriptor.
> > >
> > > More information about APICv and CPU-side Posted-interrupt, please refer
> > > to Chapter 29, and Section 29.6 in the Intel SDM:
> > >
> > http://www.intel.com/content/dam/www/public/us/en/documents/manuals/6
> > 4-ia-32-architectures-software-developer-manual-325462.pdf
> > >
> > > - Root-Complex Support
> > > Interrupt posting is the process by which an interrupt request (from 
> > > IOAPIC
> > > or MSI/MSIx capable sources) is recorded in a memory-resident
> > > posted-interrupt-descriptor structure by the root-complex, followed by
> > > an optional notification event issued to the CPU complex. The interrupt
> > > request arriving at the root-complex carry the identity of the interrupt
> > > request source and a 'remapping-index'. The remapping-index is used to
> > > look-up an entry from the memory-resident interrupt-remap-table. Unlike
> > > with interrupt-remapping, the interrupt-remap-table-entry for a posted-
> > > interrupt, specifies a virtual-vector and a pointer to the 
> > > posted-interrupt
> > > descriptor. The virtual-vector specifies the vector of the interrupt to be
> > > recorded in the posted-interrupt descriptor. The posted-interrupt 
> > > descriptor
> > > hosts storage for the virtual-vectors and contains the attributes of the
> > > notification event (interrupt) to be issued to the CPU complex to inform
> > > CPU/software about pending interrupts recorded in the posted-interrupt
> > > descriptor.
> > >
> > > More information about VT-d PI, please refer to
> > >
> > http://www.intel.com/content/www/us/en/intelligent-systems/intel-technolog
> > y/vt-directed-io-spec.html
> > >
> > > Important Definitions
> > > ==================
> > > There are some changes to IRTE and posted-interrupt descriptor after
> > > VT-d PI is introduced:
> > 
> > s/is/was/
> > 
> > > IRTE:
> > > Posted-interrupt Descriptor Address: the address of the posted-interrupt
> > descriptor
> > > Virtual Vector: the guest vector of the interrupt
> > > URG: indicates if the interrupt is urgent
> > >
> > > Posted-interrupt descriptor:
> > > The Posted Interrupt Descriptor hosts the following fields:
> > > Posted Interrupt Request (PIR): Provide storage for posting (recording)
> > interrupts (one bit
> > > per vector, for up to 256 vectors).
> > >
> > > Outstanding Notification (ON): Indicate if there is a notification event
> > outstanding (not
> > > processed by processor or software) for this Posted Interrupt Descriptor.
> > When this field is 0,
> > > hardware modifies it from 0 to 1 when generating a notification event, and
> > the entity receiving
> > > the notification event (processor or software) resets it as part of posted
> > interrupt processing.
> > >
> > > Suppress Notification (SN): Indicate if a notification event is to be 
> > > suppressed
> > (not
> > > generated) for non-urgent interrupt requests (interrupts processed through
> > an IRTE with
> > > URG=0).
> > >
> > > Notification Vector (NV): Specify the vector for notification event 
> > > (interrupt).
> > >
> > > Notification Destination (NDST): Specify the physical APIC-ID of the
> > destination logical
> > > processor for the notification event.
> > >
> > > Design Overview
> > > ==============
> > > In this design, we will cover the following items:
> > > 1. Add a variable to control whether enable VT-d posted-interrupt or not.
> > > 2. VT-d PI feature detection.
> > > 3. Extend posted-interrupt descriptor structure to cover VT-d PI specific 
> > > stuff.
> > 
> > stuff? Perhaps features?
> > > 4. Extend IRTE structure to support VT-d PI.
> > > 5. Introduce a new global vector which is used for waking up the blocked
> > vCPU.
> > > 6. Update IRTE when guest modifies the interrupt configuration (MSI/MSIx
> > configuration).
> > > 7. Update posted-interrupt descriptor during vCPU scheduling (when the
> > state
> > > of the vCPU is transmitted among RUNSTATE_running / RUNSTATE_blocked/
> > > RUNSTATE_runnable / RUNSTATE_offline).
> > > 8. How to wakeup blocked vCPU when an interrupt is posted for it (wakeup
> > notification handler).
> > > 9. New boot command line for Xen, which controls VT-d PI feature by user.
> > > 10. Multicast/broadcast and lowest priority interrupts consideration.
> > >
> > >
> > > Implementation details
> > > ===================
> > > - New variable to control VT-d PI
> > >
> > > Like variable 'iommu_intremap' for interrupt remapping, it is very
> > straightforward
> > > to add a new one 'iommu_intpost' for posted-interrupt. 'iommu_intpost' is
> > set
> > > only when interrupt remapping and VT-d posted-interrupt are both enabled.
> > >
> > > - VT-d PI feature detection.
> > > Bit 59 in VT-d Capability Register is used to report VT-d Posted-interrupt
> > support.
> > >
> > > - Extend posted-interrupt descriptor structure to cover VT-d PI specific 
> > > stuff.
> > > Here is the new structure for posted-interrupt descriptor:
> > >
> > > struct pi_desc {
> > >      DECLARE_BITMAP(pir, NR_VECTORS);
> > >      union {
> > >         struct
> > >         {
> > >         u64 on     : 1,
> > >             sn     : 1,
> > >             rsvd_1 : 13,
> > >             ndm    : 1,
> > >             nv     : 8,
> > >             rsvd_2 : 8,
> > >             ndst   : 32;
> > >         };
> > >         u64 control;
> > >     };
> > >     u32 rsvd[6];
> > >  } __attribute__ ((aligned (64)));
> > >
> > > - Extend IRTE structure to support VT-d PI.
> > >
> > > Here is the new structure for IRTE:
> > > /* interrupt remap entry */
> > > struct iremap_entry {
> > >   union {
> > >     u64 lo_val;
> > >     struct {
> > >         u64 p       : 1,
> > >             fpd     : 1,
> > >             dm      : 1,
> > >             rh      : 1,
> > >             tm      : 1,
> > >             dlm     : 3,
> > >             avail   : 4,
> > >             res_1   : 4,
> > >             vector  : 8,
> > >             res_2   : 8,
> > >             dst     : 32;
> > >     }lo;
> > >     struct {
> > >         u64 p       : 1,
> > >             fpd     : 1,
> > >             res_1   : 6,
> > >             avail   : 4,
> > >             res_2   : 2,
> > >             urg     : 1,
> > >             im      : 1,
> > >             vector  : 8,
> > >             res_3   : 14,
> > >             pda_l   : 26;
> > >     }lo_intpost;
> > >   };
> > >   union {
> > >     u64 hi_val;
> > >     struct {
> > >         u64 sid     : 16,
> > >             sq      : 2,
> > >             svt     : 2,
> > >             res_1   : 44;
> > >     }hi;
> > >     struct {
> > >         u64 sid     : 16,
> > >             sq      : 2,
> > >             svt     : 2,
> > >             res_1   : 12,
> > >             pda_h   : 32;
> > >     }hi_intpost;
> > >   };
> > > };
> > >
> > > - Introduce a new global vector which is used to wake up the blocked vCPU.
> > >
> > > Currently, there is a global vector 'posted_intr_vector', which is used 
> > > as the
> > 
> > s/Currently/In Xen 4.6 and earlier/
> > > global notification vector for all vCPUs in the system. This vector is 
> > > stored in
> > > VMCS and CPU considers it as a _special_ vector, uses it to notify the 
> > > related
> > > pCPU when an interrupt is recorded in the posted-interrupt descriptor.
> > >
> > > This existing global vector is a _special_ vector to CPU, CPU handle it 
> > > in a
> > > _special_ way compared to normal vectors, please refer to 29.6 in Intel 
> > > SDM
> > >
> > http://www.intel.com/content/dam/www/public/us/en/documents/manuals/6
> > 4-ia-32-architectures-software-developer-manual-325462.pdf
> > > for more information about how CPU handles it.
> > >
> > > After having VT-d PI, VT-d engine can issue notification event when the
> > > assigned devices issue interrupts. We need add a new global vector to
> > > wakeup the blocked vCPU, please refer to later section in this design for
> > > how to use this new global vector.
> > 
> > Ah, so this is what Xen has right now - and the changes that this design
> > outlines are here  deal with an blocked guests.
> 
> No, this is what I add for enabling VT-d PI. We discussed a lot about this
> new global vector and its usage scenario after posting version 1 of this
> design. Do you have any question about this?

No, you clarified it in your answers to my questions! thank you.
> 
> > >
> > > - Update IRTE when guest modifies the interrupt configuration (MSI/MSIx
> > configuration).
> > > After VT-d PI is introduced, the format of IRTE is changed as follows:
> > >   Descriptor Address: the address of the posted-interrupt descriptor
> > >   Virtual Vector: the guest vector of the interrupt
> > >   URG: indicates if the interrupt is urgent
> > >   Other fields continue to have the same meaning
> > >
> > > 'Descriptor Address' tells the destination vCPU of this interrupt, since
> > > each vCPU has a dedicated posted-interrupt descriptor.
> > >
> > > 'Virtual Vector' tells the guest vector of the interrupt.
> > >
> > > When guest changes the configuration of the interrupts, such as, the
> > > cpu affinity, or the vector, we need to update the associated IRTE 
> > > accordingly.
> > >
> > > - Update posted-interrupt descriptor during vCPU scheduling
> > >
> > > The basic idea here is:
> > > 1. When vCPU's state is RUNSTATE_running,
> > >         - Set 'NV' to 'posted_intr_vector'.
> > >         - Clear 'SN' to accept posted-interrupts.
> > >         - Set 'NDST' to the pCPU on which the vCPU will be running.
> > > 2. When vCPU's state is RUNSTATE_blocked,
> > >         - Set 'NV' to ' pi_wakeup_vector ', so we can wake up the
> > >           related vCPU when posted-interrupt happens for it.
> > >           Please refer to the above section about the new global vector.
> > >         - Clear 'SN' to accept posted-interrupts
> > > 3. When vCPU's state is RUNSTATE_runnable/RUNSTATE_offline,
> > >         - Set 'SN' to suppress non-urgent interrupts
> > >           (Current, we only support non-urgent interrupts)
> > >          When vCPU is in RUNSTATE_runnable or RUNSTATE_offline,
> > >          It is not needed to accept posted-interrupt notification event,
> > >          since we don't change the behavior of scheduler when the
> > interrupt
> > >          occurs, we still need wait the next scheduling of the vCPU.
> > 
> > still need to wait for the next..
> > >          When external interrupts from assigned devices occur, the
> > interrupts
> > >          are recorded in PIR, and will be synced to IRR before VM-Entry.
> > >         - Set 'NV' to 'posted_intr_vector'.
> > >
> > > - How to wakeup blocked vCPU when an interrupt is posted for it (wakeup
> > notification handler).
> > >
> > > Here is the scenario for the usage of the new global vector:
> > >
> > > 1. vCPU0 is running on pCPU0
> > > 2. vCPU0 is blocked and vCPU1 is currently running on pCPU0
> > > 3. An external interrupt from an assigned device occurs for vCPU0, if we
> > > still use 'posted_intr_vector' as the notification vector for vCPU0, the
> > > notification event for vCPU0 (the event will go to pCPU1) will be consumed
> > > by vCPU1 incorrectly (remember this is a special vector to CPU). The worst
> > > case is that vCPU0 will never be woken up again since the wakeup event
> > > for it is always consumed by other vCPUs incorrectly. So we need introduce
> > > another global vector, naming 'pi_wakeup_vector' to wake up the blocked
> > vCPU.
> > >
> > > After using 'pi_wakeup_vector' for vCPU0, VT-d engine will issue 
> > > notification
> > > event using this new vector. Since this new vector is not a SPECIAL one to
> > CPU,
> > > it is just a normal vector. To cpu, it just receives an normal external 
> > > interrupt,
> > > then we can get control in the handler of this new vector. In this case,
> > hypervisor
> > > can do something in it, such as wakeup the blocked vCPU.
> > >
> > > Here are what we do for the blocked vCPU:
> > > 1. Define a per-cpu list 'blocked_vcpu_on_cpu', which stored the blocked
> > > vCPU on the pCPU.
> > > 2. When the vCPU's state is changed to RUNSTATE_blocked, insert the vCPU
> > > to the per-cpu list belonging to the pCPU it was running.
> > > 3. When the vCPU is unblocked, remove the vCPU from the related pCPU list.
> > >
> > > In the handler of 'pi_wakeup_vector', we do:
> > > 1. Get the physical CPU.
> > > 2. Iterate the list 'blocked_vcpu_on_cpu' of the current pCPU, if 'ON' is 
> > > set,
> > > we unblock the associated vCPU.
> > >
> > > - New boot command line for Xen, which controls VT-d PI feature by user.
> > >
> > > Like 'intremap' for interrupt remapping, we add a new boot command line
> > > 'intpost' for posted-interrupts.
> > 
> > Earlier you mentioned "iommu_intpost" ?
> 
> 'intpost' is a Xen command line parameter, while 'iommu_intpost' is a variable
> In the Code, just like 'intremap' and 'iommu_intremap'.

Why not piggyback on 'iommu' ? It might be worth mentioning the
reasoning why you choose a new name instead of adding new options for
the 'iommu'.
> 
> Thanks,
> Feng
> 
> > 
> > >
> > > - Multicast/broadcast and lowest priority interrupts consideration.
> > >
> > > With VT-d PI, the destination vCPU information of an external interrupt
> > > from assigned devices is stored in IRTE, this makes the following
> > > consideration of the design:
> > > 1. Multicast/broadcast interrupts cannot be posted.
> > > 2. For lowest-priority interrupts, new Intel CPU/Chipset/root-complex
> > > (starting from Nehalem) ignore TPR value, and instead supported two other
> > > ways (configurable by BIOS) on how the handle lowest priority interrupts:
> > >   A) Round robin: In this method, the chipset simply delivers lowest 
> > > priority
> > > interrupts in a round-robin manner across all the available logical CPUs. 
> > > While
> > > this provides good load balancing, this was not the best thing to do 
> > > always as
> > > interrupts from the same device (like NIC) will start running on all the 
> > > CPUs
> > > thrashing caches and taking locks. This led to the next scheme.
> > >   B) Vector hashing: In this method, hardware would apply a hash function
> > > on the vector value in the interrupt request, and use that hash to pick a
> > logical
> > > CPU to route the lowest priority interrupt. This way, a given vector 
> > > always
> > goes
> > > to the same logical CPU, avoiding the thrashing problem above.
> > >
> > > So, gist of above is that, lowest priority interrupts has never been 
> > > delivered
> > as
> > > "lowest priority" in physical hardware.
> > >
> > > I will emulate vector hashing for posted-interrupt for XEN.
> > >
> > > ================================
> > >
> > > Any comments about this design are highly appreciated!
> > >
> > > Thanks,
> > > Feng
> > >
> > > _______________________________________________
> > > Xen-devel mailing list
> > > Xen-devel@xxxxxxxxxxxxx
> > > http://lists.xen.org/xen-devel

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel