| Message ID | 1433783045-8002-11-git-send-email-marc.zyngier@arm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Hi Marc, On 06/08/2015 07:04 PM, Marc Zyngier wrote: > So far, the only use of the HW interrupt facility is the timer, > implying that the active state is context-switched for each vcpu, > as the device is is shared across all vcpus. s/is// > > This does not work for a device that has been assigned to a VM, > as the guest is entierely in control of that device (the HW is entirely? > not shared). In that case, it makes sense to bypass the whole > active state srtwitchint, and only track the deactivation of the switching > interrupt. > > Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> > --- > include/kvm/arm_vgic.h | 5 +++-- > virt/kvm/arm/arch_timer.c | 2 +- > virt/kvm/arm/vgic.c | 37 ++++++++++++++++++++++++------------- > 3 files changed, 28 insertions(+), 16 deletions(-) > > diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h > index 1c653c1..5d47d60 100644 > --- a/include/kvm/arm_vgic.h > +++ b/include/kvm/arm_vgic.h > @@ -164,7 +164,8 @@ struct irq_phys_map { > u32 virt_irq; > u32 phys_irq; > u32 irq; > - bool active; > + bool shared; > + bool active; /* Only valid if shared */ > }; > > struct vgic_dist { > @@ -347,7 +348,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); > int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); > int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); > struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, > - int virt_irq, int irq); > + int virt_irq, int irq, bool shared); > int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); > bool vgic_get_phys_irq_active(struct irq_phys_map *map); > void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active); > diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c > index b9fff78..9544d79 100644 > --- a/virt/kvm/arm/arch_timer.c > +++ b/virt/kvm/arm/arch_timer.c > @@ -202,7 +202,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, > * Tell the VGIC that the virtual interrupt is tied to a > * physical interrupt. We do that once per VCPU. > */ > - timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq); > + timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq, true); > WARN_ON(!timer->map); > } > > diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c > index f376b56..4223166 100644 > --- a/virt/kvm/arm/vgic.c > +++ b/virt/kvm/arm/vgic.c > @@ -1125,18 +1125,21 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, > map = vgic_irq_map_search(vcpu, irq); > > if (map) { > - int ret; > - > - BUG_ON(!map->active); > vlr.hwirq = map->phys_irq; > vlr.state |= LR_HW; > vlr.state &= ~LR_EOI_INT; > > - ret = irq_set_irqchip_state(map->irq, > - IRQCHIP_STATE_ACTIVE, > - true); > vgic_irq_set_queued(vcpu, irq); the queued state is set again in vgic_queue_hwirq for level_sensitive IRQs although not harmful. > - WARN_ON(ret); > + > + if (map->shared) { > + int ret; > + > + BUG_ON(!map->active); > + ret = irq_set_irqchip_state(map->irq, > + IRQCHIP_STATE_ACTIVE, > + true); > + WARN_ON(ret); > + } > } > } > > @@ -1368,21 +1371,28 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) > static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) > { > struct irq_phys_map *map; > + bool active; > int ret; > > if (!(vlr.state & LR_HW)) > return 0; > > map = vgic_irq_map_search(vcpu, vlr.irq); > - BUG_ON(!map || !map->active); > + BUG_ON(!map); > + BUG_ON(map->shared && !map->active); > > ret = irq_get_irqchip_state(map->irq, > IRQCHIP_STATE_ACTIVE, > - &map->active); > + &active); > In case of non shared and EOIMode = 1 - I know this is not your current interest here though ;-) - , once the guest EOIs its virtual IRQ and GIC deactivates the physical one, a new phys IRQ can hit immediatly, the physical handler can be entered and the state is seen as active here. The queued state is never reset in such a case and the system gets stuck since the can_sample fails I think. What I mean here is sounds the state machine as is does not work for my VFIO case. So some adaptations still are needed I think. Do you share my diagnosis? Eric > > - if (map->active) { > + if (!map->shared) > + return !active; > + > + map->active = active; > + > + if (active) { > ret = irq_set_irqchip_state(map->irq, > IRQCHIP_STATE_ACTIVE, > false); > @@ -1663,7 +1673,7 @@ static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, > } > > struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, > - int virt_irq, int irq) > + int virt_irq, int irq, bool shared) > { > struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > @@ -1710,6 +1720,7 @@ struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, > new_map->virt_irq = virt_irq; > new_map->phys_irq = phys_irq; > new_map->irq = irq; > + new_map->shared = shared; > > rb_link_node(&new_map->node, parent, new); > rb_insert_color(&new_map->node, root); > @@ -1746,13 +1757,13 @@ static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > > bool vgic_get_phys_irq_active(struct irq_phys_map *map) > { > - BUG_ON(!map); > + BUG_ON(!map || !map->shared); > return map->active; > } > > void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active) > { > - BUG_ON(!map); > + BUG_ON(!map || !map->shared); > map->active = active; > } > > -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 17/06/15 16:11, Eric Auger wrote: > Hi Marc, > On 06/08/2015 07:04 PM, Marc Zyngier wrote: >> So far, the only use of the HW interrupt facility is the timer, >> implying that the active state is context-switched for each vcpu, >> as the device is is shared across all vcpus. > s/is// >> >> This does not work for a device that has been assigned to a VM, >> as the guest is entierely in control of that device (the HW is > entirely? >> not shared). In that case, it makes sense to bypass the whole >> active state srtwitchint, and only track the deactivation of the > switching Congratulations, I think you're now ready to try deciphering my handwriting... ;-) >> interrupt. >> >> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> >> --- >> include/kvm/arm_vgic.h | 5 +++-- >> virt/kvm/arm/arch_timer.c | 2 +- >> virt/kvm/arm/vgic.c | 37 ++++++++++++++++++++++++------------- >> 3 files changed, 28 insertions(+), 16 deletions(-) >> >> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h >> index 1c653c1..5d47d60 100644 >> --- a/include/kvm/arm_vgic.h >> +++ b/include/kvm/arm_vgic.h >> @@ -164,7 +164,8 @@ struct irq_phys_map { >> u32 virt_irq; >> u32 phys_irq; >> u32 irq; >> - bool active; >> + bool shared; >> + bool active; /* Only valid if shared */ >> }; >> >> struct vgic_dist { >> @@ -347,7 +348,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); >> int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); >> int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); >> struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >> - int virt_irq, int irq); >> + int virt_irq, int irq, bool shared); >> int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); >> bool vgic_get_phys_irq_active(struct irq_phys_map *map); >> void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active); >> diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c >> index b9fff78..9544d79 100644 >> --- a/virt/kvm/arm/arch_timer.c >> +++ b/virt/kvm/arm/arch_timer.c >> @@ -202,7 +202,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, >> * Tell the VGIC that the virtual interrupt is tied to a >> * physical interrupt. We do that once per VCPU. >> */ >> - timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq); >> + timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq, true); >> WARN_ON(!timer->map); >> } >> >> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c >> index f376b56..4223166 100644 >> --- a/virt/kvm/arm/vgic.c >> +++ b/virt/kvm/arm/vgic.c >> @@ -1125,18 +1125,21 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, >> map = vgic_irq_map_search(vcpu, irq); >> >> if (map) { >> - int ret; >> - >> - BUG_ON(!map->active); >> vlr.hwirq = map->phys_irq; >> vlr.state |= LR_HW; >> vlr.state &= ~LR_EOI_INT; >> >> - ret = irq_set_irqchip_state(map->irq, >> - IRQCHIP_STATE_ACTIVE, >> - true); >> vgic_irq_set_queued(vcpu, irq); > > the queued state is set again in vgic_queue_hwirq for level_sensitive > IRQs although not harmful. Indeed. We still need it for edge interrupts though. I'll try to find a nicer way... >> - WARN_ON(ret); >> + >> + if (map->shared) { >> + int ret; >> + >> + BUG_ON(!map->active); >> + ret = irq_set_irqchip_state(map->irq, >> + IRQCHIP_STATE_ACTIVE, >> + true); >> + WARN_ON(ret); >> + } >> } >> } >> >> @@ -1368,21 +1371,28 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) >> static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) >> { >> struct irq_phys_map *map; >> + bool active; >> int ret; >> >> if (!(vlr.state & LR_HW)) >> return 0; >> >> map = vgic_irq_map_search(vcpu, vlr.irq); >> - BUG_ON(!map || !map->active); >> + BUG_ON(!map); >> + BUG_ON(map->shared && !map->active); >> >> ret = irq_get_irqchip_state(map->irq, >> IRQCHIP_STATE_ACTIVE, >> - &map->active); >> + &active); >> > In case of non shared and EOIMode = 1 - I know this is not your current > interest here though ;-) - , once the guest EOIs its virtual IRQ and GIC > deactivates the physical one, a new phys IRQ can hit immediatly, the > physical handler can be entered and the state is seen as active here. > The queued state is never reset in such a case and the system gets stuck > since the can_sample fails I think. What I mean here is sounds the state > machine as is does not work for my VFIO case. So some adaptations still > are needed I think. Do you share my diagnosis? Yup, there is something that doesn't quite work here. I think the mistake is to sample the distributor active state. I wonder if I can simply rely on the LR state. If it is neither pending nor active, it means that we have done the deactivation, and we can then reset the queued state. As a bonus, it would save a read from MMIO, which is often dog slow. Thoughts? M. > > Eric >> >> - if (map->active) { >> + if (!map->shared) >> + return !active; >> + >> + map->active = active; >> + >> + if (active) { >> ret = irq_set_irqchip_state(map->irq, >> IRQCHIP_STATE_ACTIVE, >> false); >> @@ -1663,7 +1673,7 @@ static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, >> } >> >> struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >> - int virt_irq, int irq) >> + int virt_irq, int irq, bool shared) >> { >> struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >> @@ -1710,6 +1720,7 @@ struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >> new_map->virt_irq = virt_irq; >> new_map->phys_irq = phys_irq; >> new_map->irq = irq; >> + new_map->shared = shared; >> >> rb_link_node(&new_map->node, parent, new); >> rb_insert_color(&new_map->node, root); >> @@ -1746,13 +1757,13 @@ static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >> >> bool vgic_get_phys_irq_active(struct irq_phys_map *map) >> { >> - BUG_ON(!map); >> + BUG_ON(!map || !map->shared); >> return map->active; >> } >> >> void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active) >> { >> - BUG_ON(!map); >> + BUG_ON(!map || !map->shared); >> map->active = active; >> } >> >> >
On 06/17/2015 05:37 PM, Marc Zyngier wrote: > On 17/06/15 16:11, Eric Auger wrote: >> Hi Marc, >> On 06/08/2015 07:04 PM, Marc Zyngier wrote: >>> So far, the only use of the HW interrupt facility is the timer, >>> implying that the active state is context-switched for each vcpu, >>> as the device is is shared across all vcpus. >> s/is// >>> >>> This does not work for a device that has been assigned to a VM, >>> as the guest is entierely in control of that device (the HW is >> entirely? >>> not shared). In that case, it makes sense to bypass the whole >>> active state srtwitchint, and only track the deactivation of the >> switching > > Congratulations, I think you're now ready to try deciphering my > handwriting... ;-) good to see you're not a machine or maybe you do it on purpose some times ;-) > >>> interrupt. >>> >>> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> >>> --- >>> include/kvm/arm_vgic.h | 5 +++-- >>> virt/kvm/arm/arch_timer.c | 2 +- >>> virt/kvm/arm/vgic.c | 37 ++++++++++++++++++++++++------------- >>> 3 files changed, 28 insertions(+), 16 deletions(-) >>> >>> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h >>> index 1c653c1..5d47d60 100644 >>> --- a/include/kvm/arm_vgic.h >>> +++ b/include/kvm/arm_vgic.h >>> @@ -164,7 +164,8 @@ struct irq_phys_map { >>> u32 virt_irq; >>> u32 phys_irq; >>> u32 irq; >>> - bool active; >>> + bool shared; >>> + bool active; /* Only valid if shared */ >>> }; >>> >>> struct vgic_dist { >>> @@ -347,7 +348,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); >>> int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); >>> int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); >>> struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >>> - int virt_irq, int irq); >>> + int virt_irq, int irq, bool shared); >>> int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); >>> bool vgic_get_phys_irq_active(struct irq_phys_map *map); >>> void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active); >>> diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c >>> index b9fff78..9544d79 100644 >>> --- a/virt/kvm/arm/arch_timer.c >>> +++ b/virt/kvm/arm/arch_timer.c >>> @@ -202,7 +202,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, >>> * Tell the VGIC that the virtual interrupt is tied to a >>> * physical interrupt. We do that once per VCPU. >>> */ >>> - timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq); >>> + timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq, true); >>> WARN_ON(!timer->map); >>> } >>> >>> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c >>> index f376b56..4223166 100644 >>> --- a/virt/kvm/arm/vgic.c >>> +++ b/virt/kvm/arm/vgic.c >>> @@ -1125,18 +1125,21 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, >>> map = vgic_irq_map_search(vcpu, irq); >>> >>> if (map) { >>> - int ret; >>> - >>> - BUG_ON(!map->active); >>> vlr.hwirq = map->phys_irq; >>> vlr.state |= LR_HW; >>> vlr.state &= ~LR_EOI_INT; >>> >>> - ret = irq_set_irqchip_state(map->irq, >>> - IRQCHIP_STATE_ACTIVE, >>> - true); >>> vgic_irq_set_queued(vcpu, irq); >> >> the queued state is set again in vgic_queue_hwirq for level_sensitive >> IRQs although not harmful. > > Indeed. We still need it for edge interrupts though. I'll try to find a > nicer way... > >>> - WARN_ON(ret); >>> + >>> + if (map->shared) { >>> + int ret; >>> + >>> + BUG_ON(!map->active); >>> + ret = irq_set_irqchip_state(map->irq, >>> + IRQCHIP_STATE_ACTIVE, >>> + true); >>> + WARN_ON(ret); >>> + } >>> } >>> } >>> >>> @@ -1368,21 +1371,28 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) >>> static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) >>> { >>> struct irq_phys_map *map; >>> + bool active; >>> int ret; >>> >>> if (!(vlr.state & LR_HW)) >>> return 0; >>> >>> map = vgic_irq_map_search(vcpu, vlr.irq); >>> - BUG_ON(!map || !map->active); >>> + BUG_ON(!map); >>> + BUG_ON(map->shared && !map->active); >>> >>> ret = irq_get_irqchip_state(map->irq, >>> IRQCHIP_STATE_ACTIVE, >>> - &map->active); >>> + &active); >>> >> In case of non shared and EOIMode = 1 - I know this is not your current >> interest here though ;-) - , once the guest EOIs its virtual IRQ and GIC >> deactivates the physical one, a new phys IRQ can hit immediatly, the >> physical handler can be entered and the state is seen as active here. >> The queued state is never reset in such a case and the system gets stuck >> since the can_sample fails I think. What I mean here is sounds the state >> machine as is does not work for my VFIO case. So some adaptations still >> are needed I think. Do you share my diagnosis? > > Yup, there is something that doesn't quite work here. > > I think the mistake is to sample the distributor active state. I wonder > if I can simply rely on the LR state. If it is neither pending nor > active, it means that we have done the deactivation, and we can then > reset the queued state. I tried to use the LR in the past - it was also Christoffer's will - but it was not working. I observed injection before seeing the LR voided. This is why I resorted to using the pending state instead and treated forwarded IRQ as edge in vgic_queue_hwirq. sampling could be done only if the IRQ was pending. Eric > > As a bonus, it would save a read from MMIO, which is often dog slow. > > Thoughts? > > M. >> >> Eric >>> >>> - if (map->active) { >>> + if (!map->shared) >>> + return !active; >>> + >>> + map->active = active; >>> + >>> + if (active) { >>> ret = irq_set_irqchip_state(map->irq, >>> IRQCHIP_STATE_ACTIVE, >>> false); >>> @@ -1663,7 +1673,7 @@ static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, >>> } >>> >>> struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >>> - int virt_irq, int irq) >>> + int virt_irq, int irq, bool shared) >>> { >>> struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >>> struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >>> @@ -1710,6 +1720,7 @@ struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >>> new_map->virt_irq = virt_irq; >>> new_map->phys_irq = phys_irq; >>> new_map->irq = irq; >>> + new_map->shared = shared; >>> >>> rb_link_node(&new_map->node, parent, new); >>> rb_insert_color(&new_map->node, root); >>> @@ -1746,13 +1757,13 @@ static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >>> >>> bool vgic_get_phys_irq_active(struct irq_phys_map *map) >>> { >>> - BUG_ON(!map); >>> + BUG_ON(!map || !map->shared); >>> return map->active; >>> } >>> >>> void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active) >>> { >>> - BUG_ON(!map); >>> + BUG_ON(!map || !map->shared); >>> map->active = active; >>> } >>> >>> >> > > -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Jun 08, 2015 at 06:04:05PM +0100, Marc Zyngier wrote: > So far, the only use of the HW interrupt facility is the timer, > implying that the active state is context-switched for each vcpu, > as the device is is shared across all vcpus. > > This does not work for a device that has been assigned to a VM, > as the guest is entierely in control of that device (the HW is > not shared). In that case, it makes sense to bypass the whole > active state switchint, and only track the deactivation of the > interrupt. > The discinction here between shared and non-shared feels a bit arbitrary (it may not be, but just feel that way) and I can't easily convince myself that this is the logical/correct/all-encompassing word to describe the nature of the two devices. Meh, not the most productive comment, I know... -Christoffer -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 30/06/15 21:19, Christoffer Dall wrote: > On Mon, Jun 08, 2015 at 06:04:05PM +0100, Marc Zyngier wrote: >> So far, the only use of the HW interrupt facility is the timer, >> implying that the active state is context-switched for each vcpu, >> as the device is is shared across all vcpus. >> >> This does not work for a device that has been assigned to a VM, >> as the guest is entierely in control of that device (the HW is >> not shared). In that case, it makes sense to bypass the whole >> active state switchint, and only track the deactivation of the >> interrupt. >> > The discinction here between shared and non-shared feels a bit arbitrary > (it may not be, but just feel that way) and I can't easily convince > myself that this is the logical/correct/all-encompassing word to > describe the nature of the two devices. Does the idea of global vs private resource feel more correct? M.
On Wed, Jul 01, 2015 at 09:26:59AM +0100, Marc Zyngier wrote: > On 30/06/15 21:19, Christoffer Dall wrote: > > On Mon, Jun 08, 2015 at 06:04:05PM +0100, Marc Zyngier wrote: > >> So far, the only use of the HW interrupt facility is the timer, > >> implying that the active state is context-switched for each vcpu, > >> as the device is is shared across all vcpus. > >> > >> This does not work for a device that has been assigned to a VM, > >> as the guest is entierely in control of that device (the HW is > >> not shared). In that case, it makes sense to bypass the whole > >> active state switchint, and only track the deactivation of the > >> interrupt. > >> > > The discinction here between shared and non-shared feels a bit arbitrary > > (it may not be, but just feel that way) and I can't easily convince > > myself that this is the logical/correct/all-encompassing word to > > describe the nature of the two devices. > > Does the idea of global vs private resource feel more correct? > I think shared covers that equally well. This feels like one of those things that just doesn't make intuitive sense on its own but when you think about the cases we are familiar with, then it fits for now. So what you have here is probably as good as it gets and hopefully it does cover all the cases we care about, i.e. shared and non-shared :) -Christoffer -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 1c653c1..5d47d60 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -164,7 +164,8 @@ struct irq_phys_map { u32 virt_irq; u32 phys_irq; u32 irq; - bool active; + bool shared; + bool active; /* Only valid if shared */ }; struct vgic_dist { @@ -347,7 +348,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, - int virt_irq, int irq); + int virt_irq, int irq, bool shared); int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); bool vgic_get_phys_irq_active(struct irq_phys_map *map); void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active); diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index b9fff78..9544d79 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -202,7 +202,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu, * Tell the VGIC that the virtual interrupt is tied to a * physical interrupt. We do that once per VCPU. */ - timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq); + timer->map = vgic_map_phys_irq(vcpu, irq->irq, host_vtimer_irq, true); WARN_ON(!timer->map); } diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index f376b56..4223166 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1125,18 +1125,21 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, map = vgic_irq_map_search(vcpu, irq); if (map) { - int ret; - - BUG_ON(!map->active); vlr.hwirq = map->phys_irq; vlr.state |= LR_HW; vlr.state &= ~LR_EOI_INT; - ret = irq_set_irqchip_state(map->irq, - IRQCHIP_STATE_ACTIVE, - true); vgic_irq_set_queued(vcpu, irq); - WARN_ON(ret); + + if (map->shared) { + int ret; + + BUG_ON(!map->active); + ret = irq_set_irqchip_state(map->irq, + IRQCHIP_STATE_ACTIVE, + true); + WARN_ON(ret); + } } } @@ -1368,21 +1371,28 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr) { struct irq_phys_map *map; + bool active; int ret; if (!(vlr.state & LR_HW)) return 0; map = vgic_irq_map_search(vcpu, vlr.irq); - BUG_ON(!map || !map->active); + BUG_ON(!map); + BUG_ON(map->shared && !map->active); ret = irq_get_irqchip_state(map->irq, IRQCHIP_STATE_ACTIVE, - &map->active); + &active); WARN_ON(ret); - if (map->active) { + if (!map->shared) + return !active; + + map->active = active; + + if (active) { ret = irq_set_irqchip_state(map->irq, IRQCHIP_STATE_ACTIVE, false); @@ -1663,7 +1673,7 @@ static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, } struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, - int virt_irq, int irq) + int virt_irq, int irq, bool shared) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); @@ -1710,6 +1720,7 @@ struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, new_map->virt_irq = virt_irq; new_map->phys_irq = phys_irq; new_map->irq = irq; + new_map->shared = shared; rb_link_node(&new_map->node, parent, new); rb_insert_color(&new_map->node, root); @@ -1746,13 +1757,13 @@ static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, bool vgic_get_phys_irq_active(struct irq_phys_map *map) { - BUG_ON(!map); + BUG_ON(!map || !map->shared); return map->active; } void vgic_set_phys_irq_active(struct irq_phys_map *map, bool active) { - BUG_ON(!map); + BUG_ON(!map || !map->shared); map->active = active; }
So far, the only use of the HW interrupt facility is the timer, implying that the active state is context-switched for each vcpu, as the device is is shared across all vcpus. This does not work for a device that has been assigned to a VM, as the guest is entierely in control of that device (the HW is not shared). In that case, it makes sense to bypass the whole active state switchint, and only track the deactivation of the interrupt. Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> --- include/kvm/arm_vgic.h | 5 +++-- virt/kvm/arm/arch_timer.c | 2 +- virt/kvm/arm/vgic.c | 37 ++++++++++++++++++++++++------------- 3 files changed, 28 insertions(+), 16 deletions(-)