posted_intr.c File Reference

#include <linux/kvm_host.h>
#include <asm/irq_remapping.h>
#include <asm/cpu.h>
#include "lapic.h"
#include "irq.h"
#include "posted_intr.h"
#include "trace.h"
#include "vmx.h"

Include dependency graph for posted_intr.c:

Go to the source code of this file.

Macros
#define	pr_fmt(fmt)   KBUILD_MODNAME ": " fmt

Functions
static	DEFINE_PER_CPU (struct list_head, wakeup_vcpus_on_cpu)
static	DEFINE_PER_CPU (raw_spinlock_t, wakeup_vcpus_on_cpu_lock)
static struct pi_desc *	vcpu_to_pi_desc (struct kvm_vcpu *vcpu)
static int	pi_try_set_control (struct pi_desc *pi_desc, u64 *pold, u64 new)
void	vmx_vcpu_pi_load (struct kvm_vcpu *vcpu, int cpu)
static bool	vmx_can_use_vtd_pi (struct kvm *kvm)
static void	pi_enable_wakeup_handler (struct kvm_vcpu *vcpu)
static bool	vmx_needs_pi_wakeup (struct kvm_vcpu *vcpu)
void	vmx_vcpu_pi_put (struct kvm_vcpu *vcpu)
void	pi_wakeup_handler (void)
void __init	pi_init_cpu (int cpu)
bool	pi_has_pending_interrupt (struct kvm_vcpu *vcpu)
void	vmx_pi_start_assignment (struct kvm *kvm)
int	vmx_pi_update_irte (struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set)

Macro Definition Documentation

pr_fmt

#define pr_fmt

(

fmt

)

KBUILD_MODNAME ": " fmt

Definition at line 2 of file posted_intr.c.

Function Documentation

DEFINE_PER_CPU() [1/2]

static DEFINE_PER_CPU ( raw_spinlock_t  , wakeup_vcpus_on_cpu_lock    )

static

DEFINE_PER_CPU() [2/2]

static DEFINE_PER_CPU ( struct list_head  , wakeup_vcpus_on_cpu    )

static

pi_enable_wakeup_handler()

static void pi_enable_wakeup_handler ( struct kvm_vcpu *  vcpu )

static

Definition at line 146 of file posted_intr.c.

{
    struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
    struct vcpu_vmx *vmx = to_vmx(vcpu);
    struct pi_desc old, new;
    unsigned long flags;
 
    local_irq_save(flags);
 
    raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
    list_add_tail(&vmx->pi_wakeup_list,
              &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
    raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 
    WARN(pi_desc->sn, "PI descriptor SN field set before blocking");
 
    old.control = READ_ONCE(pi_desc->control);
    do {
        /* set 'NV' to 'wakeup vector' */
        new.control = old.control;
        new.nv = POSTED_INTR_WAKEUP_VECTOR;
    } while (pi_try_set_control(pi_desc, &old.control, new.control));
 
    /*
     * Send a wakeup IPI to this CPU if an interrupt may have been posted
     * before the notification vector was updated, in which case the IRQ
     * will arrive on the non-wakeup vector.  An IPI is needed as calling
     * try_to_wake_up() from ->sched_out() isn't allowed (IRQs are not
     * enabled until it is safe to call try_to_wake_up() on the task being
     * scheduled out).
     */
    if (pi_test_on(&new))
        __apic_send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
 
    local_irq_restore(flags);
}

Here is the call graph for this function:

Here is the caller graph for this function:

pi_has_pending_interrupt()

bool pi_has_pending_interrupt

(

struct kvm_vcpu *

vcpu

)

Definition at line 240 of file posted_intr.c.

{
    struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
    return pi_test_on(pi_desc) ||
        (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
}

Here is the call graph for this function:

pi_init_cpu()

void __init pi_init_cpu

(

int

cpu

)

Definition at line 234 of file posted_intr.c.

{
    INIT_LIST_HEAD(&per_cpu(wakeup_vcpus_on_cpu, cpu));
    raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
}

Here is the caller graph for this function:

pi_try_set_control()

static int pi_try_set_control ( struct pi_desc *  pi_desc, u64 *  pold, u64  new  )

static

Definition at line 39 of file posted_intr.c.

{
    /*
     * PID.ON can be set at any time by a different vCPU or by hardware,
     * e.g. a device.  PID.control must be written atomically, and the
     * update must be retried with a fresh snapshot an ON change causes
     * the cmpxchg to fail.
     */
    if (!try_cmpxchg64(&pi_desc->control, pold, new))
        return -EBUSY;
 
    return 0;
}

Here is the caller graph for this function:

pi_wakeup_handler()

void pi_wakeup_handler

(

void

)

Definition at line 218 of file posted_intr.c.

{
    int cpu = smp_processor_id();
    struct list_head *wakeup_list = &per_cpu(wakeup_vcpus_on_cpu, cpu);
    raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, cpu);
    struct vcpu_vmx *vmx;
 
    raw_spin_lock(spinlock);
    list_for_each_entry(vmx, wakeup_list, pi_wakeup_list) {
 
        if (pi_test_on(&vmx->pi_desc))
            kvm_vcpu_wake_up(&vmx->vcpu);
    }
    raw_spin_unlock(spinlock);
}

Here is the call graph for this function:

Here is the caller graph for this function:

vcpu_to_pi_desc()

static struct pi_desc* vcpu_to_pi_desc ( struct kvm_vcpu *  vcpu )

inlinestatic

Definition at line 34 of file posted_intr.c.

{
    return &(to_vmx(vcpu)->pi_desc);
}

Here is the call graph for this function:

Here is the caller graph for this function:

vmx_can_use_vtd_pi()

static bool vmx_can_use_vtd_pi ( struct kvm *  kvm )

static

Definition at line 135 of file posted_intr.c.

{
    return irqchip_in_kernel(kvm) && enable_apicv &&
        kvm_arch_has_assigned_device(kvm) &&
        irq_remapping_cap(IRQ_POSTING_CAP);
}

Here is the call graph for this function:

Here is the caller graph for this function:

vmx_needs_pi_wakeup()

static bool vmx_needs_pi_wakeup ( struct kvm_vcpu *  vcpu )

static

Definition at line 183 of file posted_intr.c.

{
    /*
     * The default posted interrupt vector does nothing when
     * invoked outside guest mode.   Return whether a blocked vCPU
     * can be the target of posted interrupts, as is the case when
     * using either IPI virtualization or VT-d PI, so that the
     * notification vector is switched to the one that calls
     * back to the pi_wakeup_handler() function.
     */
    return vmx_can_use_ipiv(vcpu) || vmx_can_use_vtd_pi(vcpu->kvm);
}

Here is the call graph for this function:

Here is the caller graph for this function:

vmx_pi_start_assignment()

void vmx_pi_start_assignment

(

struct kvm *

kvm

)

Definition at line 255 of file posted_intr.c.

{
    if (!irq_remapping_cap(IRQ_POSTING_CAP))
        return;
 
    kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
}

Here is the call graph for this function:

vmx_pi_update_irte()

int vmx_pi_update_irte	(	struct kvm *	kvm,
		unsigned int	host_irq,
		uint32_t	guest_irq,
		bool	set
	)

Definition at line 272 of file posted_intr.c.

{
    struct kvm_kernel_irq_routing_entry *e;
    struct kvm_irq_routing_table *irq_rt;
    struct kvm_lapic_irq irq;
    struct kvm_vcpu *vcpu;
    struct vcpu_data vcpu_info;
    int idx, ret = 0;
 
    if (!vmx_can_use_vtd_pi(kvm))
        return 0;
 
    idx = srcu_read_lock(&kvm->irq_srcu);
    irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
    if (guest_irq >= irq_rt->nr_rt_entries ||
        hlist_empty(&irq_rt->map[guest_irq])) {
        pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
                 guest_irq, irq_rt->nr_rt_entries);
        goto out;
    }
 
    hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
        if (e->type != KVM_IRQ_ROUTING_MSI)
            continue;
        /*
         * VT-d PI cannot support posting multicast/broadcast
         * interrupts to a vCPU, we still use interrupt remapping
         * for these kind of interrupts.
         *
         * For lowest-priority interrupts, we only support
         * those with single CPU as the destination, e.g. user
         * configures the interrupts via /proc/irq or uses
         * irqbalance to make the interrupts single-CPU.
         *
         * We will support full lowest-priority interrupt later.
         *
         * In addition, we can only inject generic interrupts using
         * the PI mechanism, refuse to route others through it.
         */
 
        kvm_set_msi_irq(kvm, e, &irq);
        if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
            !kvm_irq_is_postable(&irq)) {
            /*
             * Make sure the IRTE is in remapped mode if
             * we don't handle it in posted mode.
             */
            ret = irq_set_vcpu_affinity(host_irq, NULL);
            if (ret < 0) {
                printk(KERN_INFO
                   "failed to back to remapped mode, irq: %u\n",
                   host_irq);
                goto out;
            }
 
            continue;
        }
 
        vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
        vcpu_info.vector = irq.vector;
 
        trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
                vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
        if (set)
            ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
        else
            ret = irq_set_vcpu_affinity(host_irq, NULL);
 
        if (ret < 0) {
            printk(KERN_INFO "%s: failed to update PI IRTE\n",
                    __func__);
            goto out;
        }
    }
 
    ret = 0;
out:
    srcu_read_unlock(&kvm->irq_srcu, idx);
    return ret;
}

Here is the call graph for this function:

vmx_vcpu_pi_load()

void vmx_vcpu_pi_load	(	struct kvm_vcpu *	vcpu,
		int	cpu
	)

Definition at line 53 of file posted_intr.c.

{
    struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
    struct vcpu_vmx *vmx = to_vmx(vcpu);
    struct pi_desc old, new;
    unsigned long flags;
    unsigned int dest;
 
    /*
     * To simplify hot-plug and dynamic toggling of APICv, keep PI.NDST and
     * PI.SN up-to-date even if there is no assigned device or if APICv is
     * deactivated due to a dynamic inhibit bit, e.g. for Hyper-V's SyncIC.
     */
    if (!enable_apicv || !lapic_in_kernel(vcpu))
        return;
 
    /*
     * If the vCPU wasn't on the wakeup list and wasn't migrated, then the
     * full update can be skipped as neither the vector nor the destination
     * needs to be changed.
     */
    if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR && vcpu->cpu == cpu) {
        /*
         * Clear SN if it was set due to being preempted.  Again, do
         * this even if there is no assigned device for simplicity.
         */
        if (pi_test_and_clear_sn(pi_desc))
            goto after_clear_sn;
        return;
    }
 
    local_irq_save(flags);
 
    /*
     * If the vCPU was waiting for wakeup, remove the vCPU from the wakeup
     * list of the _previous_ pCPU, which will not be the same as the
     * current pCPU if the task was migrated.
     */
    if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
        raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
        list_del(&vmx->pi_wakeup_list);
        raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
    }
 
    dest = cpu_physical_id(cpu);
    if (!x2apic_mode)
        dest = (dest << 8) & 0xFF00;
 
    old.control = READ_ONCE(pi_desc->control);
    do {
        new.control = old.control;
 
        /*
         * Clear SN (as above) and refresh the destination APIC ID to
         * handle task migration (@cpu != vcpu->cpu).
         */
        new.ndst = dest;
        new.sn = 0;
 
        /*
         * Restore the notification vector; in the blocking case, the
         * descriptor was modified on "put" to use the wakeup vector.
         */
        new.nv = POSTED_INTR_VECTOR;
    } while (pi_try_set_control(pi_desc, &old.control, new.control));
 
    local_irq_restore(flags);
 
after_clear_sn:
 
    /*
     * Clear SN before reading the bitmap.  The VT-d firmware
     * writes the bitmap and reads SN atomically (5.2.3 in the
     * spec), so it doesn't really have a memory barrier that
     * pairs with this, but we cannot do that and we need one.
     */
    smp_mb__after_atomic();
 
    if (!pi_is_pir_empty(pi_desc))
        pi_set_on(pi_desc);
}

Here is the call graph for this function:

Here is the caller graph for this function:

vmx_vcpu_pi_put()

void vmx_vcpu_pi_put

(

struct kvm_vcpu *

vcpu

)

Definition at line 196 of file posted_intr.c.

{
    struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
    if (!vmx_needs_pi_wakeup(vcpu))
        return;
 
    if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu))
        pi_enable_wakeup_handler(vcpu);
 
    /*
     * Set SN when the vCPU is preempted.  Note, the vCPU can both be seen
     * as blocking and preempted, e.g. if it's preempted between setting
     * its wait state and manually scheduling out.
     */
    if (vcpu->preempted)
        pi_set_sn(pi_desc);
}

Here is the call graph for this function:

Here is the caller graph for this function: