| Message ID | 1433783045-8002-7-git-send-email-marc.zyngier@arm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Hi, On 06/08/2015 06:04 PM, Marc Zyngier wrote: > In order to be able to feed physical interrupts to a guest, we need > to be able to establish the virtual-physical mapping between the two > worlds. > > The mapping is kept in a rbtree, indexed by virtual interrupts. > > Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> > --- > include/kvm/arm_vgic.h | 18 ++++++++ > virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 128 insertions(+) > > diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h > index 4f9fa1d..33d121a 100644 > --- a/include/kvm/arm_vgic.h > +++ b/include/kvm/arm_vgic.h > @@ -159,6 +159,14 @@ struct vgic_io_device { > struct kvm_io_device dev; > }; > > +struct irq_phys_map { > + struct rb_node node; > + u32 virt_irq; > + u32 phys_irq; > + u32 irq; Can you add comments explaining the different IRQ types here? So I take it that phys_irq is the actual SPI number (hwirq in irqchip lingo), virt_irq is the guest's virtual IRQ number and irq is Linux' notion of the IRQ number (the first column in /proc/interrupts)? Would renaming help? (phys_irq to hwirq? virt_irq to guest_irq?) > + bool active; > +}; > + > struct vgic_dist { > spinlock_t lock; > bool in_kernel; > @@ -256,6 +264,10 @@ struct vgic_dist { > struct vgic_vm_ops vm_ops; > struct vgic_io_device dist_iodev; > struct vgic_io_device *redist_iodevs; > + > + /* Virtual irq to hwirq mapping */ > + spinlock_t irq_phys_map_lock; > + struct rb_root irq_phys_map; > }; > > struct vgic_v2_cpu_if { > @@ -307,6 +319,9 @@ struct vgic_cpu { > struct vgic_v2_cpu_if vgic_v2; > struct vgic_v3_cpu_if vgic_v3; > }; > + > + /* Protected by the distributor's irq_phys_map_lock */ > + struct rb_root irq_phys_map; > }; > > #define LR_EMPTY 0xff > @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, > 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); > > #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) > #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) > diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c > index 59ed7a3..c6604f2 100644 > --- a/virt/kvm/arm/vgic.c > +++ b/virt/kvm/arm/vgic.c > @@ -24,6 +24,7 @@ > #include <linux/of.h> > #include <linux/of_address.h> > #include <linux/of_irq.h> > +#include <linux/rbtree.h> > #include <linux/uaccess.h> > > #include <linux/irqchip/arm-gic.h> > @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); > static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); > static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); > static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); > +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > + int virt_irq); > > static const struct vgic_ops *vgic_ops; > static const struct vgic_params *vgic; > @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) > return IRQ_HANDLED; > } > > +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, > + int virt_irq) > +{ > + if (virt_irq < VGIC_NR_PRIVATE_IRQS) > + return &vcpu->arch.vgic_cpu.irq_phys_map; > + else > + return &vcpu->kvm->arch.vgic.irq_phys_map; > +} > + > +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, > + int virt_irq, int irq) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > + struct rb_node **new = &root->rb_node, *parent = NULL; > + struct irq_phys_map *new_map; > + struct irq_desc *desc; > + struct irq_data *data; > + int phys_irq; > + > + desc = irq_to_desc(irq); > + if (!desc) { > + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); I guess kvm_arch_timer: is a left-over of the original user? > + return NULL; > + } > + > + data = irq_desc_get_irq_data(desc); > + while (data->parent_data) > + data = data->parent_data; > + > + phys_irq = data->hwirq; So if I get this correctly we "cache" hwirq/phys_irq in this map to get a cheaper access to it, but actually it is redundant since we have Linux' irq number, isn't it? Are we sure that the irqdomain mapping of irq and phys_irq never will change while this map entry is valid? This is probably true for the timer, but does that still hold in the future with other devices? (see also the next email for more rationale) Cheers, Andre. > + > + spin_lock(&dist->irq_phys_map_lock); > + > + /* Boilerplate rb_tree code */ > + while (*new) { > + struct irq_phys_map *this; > + > + this = container_of(*new, struct irq_phys_map, node); > + parent = *new; > + if (this->virt_irq < virt_irq) > + new = &(*new)->rb_left; > + else if (this->virt_irq > virt_irq) > + new = &(*new)->rb_right; > + else { > + new_map = this; > + goto out; > + } > + } > + > + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); > + if (!new_map) > + goto out; > + > + new_map->virt_irq = virt_irq; > + new_map->phys_irq = phys_irq; > + new_map->irq = irq; > + > + rb_link_node(&new_map->node, parent, new); > + rb_insert_color(&new_map->node, root); > + > +out: > + spin_unlock(&dist->irq_phys_map_lock); > + return new_map; > +} > + > +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > + int virt_irq) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > + struct rb_node *node = root->rb_node; > + struct irq_phys_map *this = NULL; > + > + spin_lock(&dist->irq_phys_map_lock); > + > + while (node) { > + this = container_of(node, struct irq_phys_map, node); > + > + if (this->virt_irq < virt_irq) > + node = node->rb_left; > + else if (this->virt_irq > virt_irq) > + node = node->rb_right; > + else > + break; > + } > + > + spin_unlock(&dist->irq_phys_map_lock); > + return this; > +} > + > +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + > + if (!map) > + return -EINVAL; > + > + spin_lock(&dist->irq_phys_map_lock); > + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); > + spin_unlock(&dist->irq_phys_map_lock); > + > + kfree(map); > + return 0; > +} > + > void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) > { > struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; > @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) > goto out_unlock; > > spin_lock_init(&kvm->arch.vgic.lock); > + spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock); > kvm->arch.vgic.in_kernel = true; > kvm->arch.vgic.vgic_model = type; > kvm->arch.vgic.vctrl_base = vgic->vctrl_base; > -- IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you. ARM Limited, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, Registered in England & Wales, Company No: 2557590 ARM Holdings plc, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, Registered in England & Wales, Company No: 2548782 -- 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 11/06/15 09:43, Andre Przywara wrote: > Hi, > > On 06/08/2015 06:04 PM, Marc Zyngier wrote: >> In order to be able to feed physical interrupts to a guest, we need >> to be able to establish the virtual-physical mapping between the two >> worlds. >> >> The mapping is kept in a rbtree, indexed by virtual interrupts. >> >> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> >> --- >> include/kvm/arm_vgic.h | 18 ++++++++ >> virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ >> 2 files changed, 128 insertions(+) >> >> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h >> index 4f9fa1d..33d121a 100644 >> --- a/include/kvm/arm_vgic.h >> +++ b/include/kvm/arm_vgic.h >> @@ -159,6 +159,14 @@ struct vgic_io_device { >> struct kvm_io_device dev; >> }; >> >> +struct irq_phys_map { >> + struct rb_node node; >> + u32 virt_irq; >> + u32 phys_irq; >> + u32 irq; > > Can you add comments explaining the different IRQ types here? > So I take it that phys_irq is the actual SPI number (hwirq in irqchip > lingo), virt_irq is the guest's virtual IRQ number and irq is Linux' > notion of the IRQ number (the first column in /proc/interrupts)? > Would renaming help? (phys_irq to hwirq? virt_irq to guest_irq?) Adding comments would probably help. Renaming, I'm not sure. The virt vs phys was clear enough for me. The ambiguous one would be "irq"... I'll try to work something out anyway. > >> + bool active; >> +}; >> + >> struct vgic_dist { >> spinlock_t lock; >> bool in_kernel; >> @@ -256,6 +264,10 @@ struct vgic_dist { >> struct vgic_vm_ops vm_ops; >> struct vgic_io_device dist_iodev; >> struct vgic_io_device *redist_iodevs; >> + >> + /* Virtual irq to hwirq mapping */ >> + spinlock_t irq_phys_map_lock; >> + struct rb_root irq_phys_map; >> }; >> >> struct vgic_v2_cpu_if { >> @@ -307,6 +319,9 @@ struct vgic_cpu { >> struct vgic_v2_cpu_if vgic_v2; >> struct vgic_v3_cpu_if vgic_v3; >> }; >> + >> + /* Protected by the distributor's irq_phys_map_lock */ >> + struct rb_root irq_phys_map; >> }; >> >> #define LR_EMPTY 0xff >> @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, >> 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); >> >> #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) >> #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) >> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c >> index 59ed7a3..c6604f2 100644 >> --- a/virt/kvm/arm/vgic.c >> +++ b/virt/kvm/arm/vgic.c >> @@ -24,6 +24,7 @@ >> #include <linux/of.h> >> #include <linux/of_address.h> >> #include <linux/of_irq.h> >> +#include <linux/rbtree.h> >> #include <linux/uaccess.h> >> >> #include <linux/irqchip/arm-gic.h> >> @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); >> static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); >> static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); >> static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); >> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >> + int virt_irq); >> >> static const struct vgic_ops *vgic_ops; >> static const struct vgic_params *vgic; >> @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) >> return IRQ_HANDLED; >> } >> >> +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, >> + int virt_irq) >> +{ >> + if (virt_irq < VGIC_NR_PRIVATE_IRQS) >> + return &vcpu->arch.vgic_cpu.irq_phys_map; >> + else >> + return &vcpu->kvm->arch.vgic.irq_phys_map; >> +} >> + >> +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >> + int virt_irq, int irq) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >> + struct rb_node **new = &root->rb_node, *parent = NULL; >> + struct irq_phys_map *new_map; >> + struct irq_desc *desc; >> + struct irq_data *data; >> + int phys_irq; >> + >> + desc = irq_to_desc(irq); >> + if (!desc) { >> + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); > > I guess kvm_arch_timer: is a left-over of the original user? > >> + return NULL; >> + } >> + >> + data = irq_desc_get_irq_data(desc); >> + while (data->parent_data) >> + data = data->parent_data; >> + >> + phys_irq = data->hwirq; > > So if I get this correctly we "cache" hwirq/phys_irq in this map to get > a cheaper access to it, but actually it is redundant since we have > Linux' irq number, isn't it? Define what you call by redundant. Parsing the irq_data hierarchy can be arbitrarily long, and what we're after is the irq vs GIC view of the HW irq. > Are we sure that the irqdomain mapping of irq and phys_irq never will > change while this map entry is valid? This is probably true for the > timer, but does that still hold in the future with other devices? > (see also the next email for more rationale) How could such a mapping change? We have done a request_irq on this IRQ line. If it was to change, we'd get notifier when *another device* is interrupting us. That would simply defeat the whole purpose of having separate interrupts. M.
Hi Marc, On 06/08/2015 07:04 PM, Marc Zyngier wrote: > In order to be able to feed physical interrupts to a guest, we need > to be able to establish the virtual-physical mapping between the two > worlds. > > The mapping is kept in a rbtree, indexed by virtual interrupts. > > Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> > --- > include/kvm/arm_vgic.h | 18 ++++++++ > virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 128 insertions(+) > > diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h > index 4f9fa1d..33d121a 100644 > --- a/include/kvm/arm_vgic.h > +++ b/include/kvm/arm_vgic.h > @@ -159,6 +159,14 @@ struct vgic_io_device { > struct kvm_io_device dev; > }; > > +struct irq_phys_map { > + struct rb_node node; > + u32 virt_irq; > + u32 phys_irq; > + u32 irq; > + bool active; > +}; > + > struct vgic_dist { > spinlock_t lock; > bool in_kernel; > @@ -256,6 +264,10 @@ struct vgic_dist { > struct vgic_vm_ops vm_ops; > struct vgic_io_device dist_iodev; > struct vgic_io_device *redist_iodevs; > + > + /* Virtual irq to hwirq mapping */ > + spinlock_t irq_phys_map_lock; > + struct rb_root irq_phys_map; > }; > > struct vgic_v2_cpu_if { > @@ -307,6 +319,9 @@ struct vgic_cpu { > struct vgic_v2_cpu_if vgic_v2; > struct vgic_v3_cpu_if vgic_v3; > }; > + > + /* Protected by the distributor's irq_phys_map_lock */ > + struct rb_root irq_phys_map; > }; > > #define LR_EMPTY 0xff > @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, > 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); > > #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) > #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) > diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c > index 59ed7a3..c6604f2 100644 > --- a/virt/kvm/arm/vgic.c > +++ b/virt/kvm/arm/vgic.c > @@ -24,6 +24,7 @@ > #include <linux/of.h> > #include <linux/of_address.h> > #include <linux/of_irq.h> > +#include <linux/rbtree.h> > #include <linux/uaccess.h> > > #include <linux/irqchip/arm-gic.h> > @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); > static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); > static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); > static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); > +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > + int virt_irq); > > static const struct vgic_ops *vgic_ops; > static const struct vgic_params *vgic; > @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) > return IRQ_HANDLED; > } > > +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, > + int virt_irq) > +{ > + if (virt_irq < VGIC_NR_PRIVATE_IRQS) > + return &vcpu->arch.vgic_cpu.irq_phys_map; > + else > + return &vcpu->kvm->arch.vgic.irq_phys_map; > +} > + > +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, > + int virt_irq, int irq) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > + struct rb_node **new = &root->rb_node, *parent = NULL; > + struct irq_phys_map *new_map; > + struct irq_desc *desc; > + struct irq_data *data; > + int phys_irq; > + > + desc = irq_to_desc(irq); > + if (!desc) { > + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); > + return NULL; > + } > + > + data = irq_desc_get_irq_data(desc); > + while (data->parent_data) > + data = data->parent_data; > + > + phys_irq = data->hwirq; > + > + spin_lock(&dist->irq_phys_map_lock); > + > + /* Boilerplate rb_tree code */ > + while (*new) { > + struct irq_phys_map *this; > + > + this = container_of(*new, struct irq_phys_map, node); > + parent = *new; > + if (this->virt_irq < virt_irq) > + new = &(*new)->rb_left; > + else if (this->virt_irq > virt_irq) > + new = &(*new)->rb_right; > + else { > + new_map = this; in case the mapping already exists you don't update the mappping or return an error. Is it what you want here? > + goto out; > + } > + } > + > + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); > + if (!new_map) > + goto out; > + > + new_map->virt_irq = virt_irq; > + new_map->phys_irq = phys_irq; > + new_map->irq = irq; > + > + rb_link_node(&new_map->node, parent, new); > + rb_insert_color(&new_map->node, root); > + > +out: > + spin_unlock(&dist->irq_phys_map_lock); > + return new_map; > +} > + > +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > + int virt_irq) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > + struct rb_node *node = root->rb_node; > + struct irq_phys_map *this = NULL; > + > + spin_lock(&dist->irq_phys_map_lock); > + > + while (node) { > + this = container_of(node, struct irq_phys_map, node); > + > + if (this->virt_irq < virt_irq) > + node = node->rb_left; > + else if (this->virt_irq > virt_irq) > + node = node->rb_right; > + else > + break; > + } > + > + spin_unlock(&dist->irq_phys_map_lock); > + return this; > +} > + > +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + > + if (!map) > + return -EINVAL; > + > + spin_lock(&dist->irq_phys_map_lock); > + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); > + spin_unlock(&dist->irq_phys_map_lock); > + > + kfree(map); > + return 0; > +} > + > void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) > { > struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; > @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) > goto out_unlock; > > spin_lock_init(&kvm->arch.vgic.lock); Don't you deallocate the rbtree nodes here? Also in the future with EOI mode == 1 we will need to complete the physical IRQ in place of the guest. - Eric > + spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock); > kvm->arch.vgic.in_kernel = true; > kvm->arch.vgic.vgic_model = type; > kvm->arch.vgic.vctrl_base = vgic->vctrl_base; > -- 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
Hi Eric, On 15/06/15 16:44, Eric Auger wrote: > Hi Marc, > On 06/08/2015 07:04 PM, Marc Zyngier wrote: >> In order to be able to feed physical interrupts to a guest, we need >> to be able to establish the virtual-physical mapping between the two >> worlds. >> >> The mapping is kept in a rbtree, indexed by virtual interrupts. >> >> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> >> --- >> include/kvm/arm_vgic.h | 18 ++++++++ >> virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ >> 2 files changed, 128 insertions(+) >> >> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h >> index 4f9fa1d..33d121a 100644 >> --- a/include/kvm/arm_vgic.h >> +++ b/include/kvm/arm_vgic.h >> @@ -159,6 +159,14 @@ struct vgic_io_device { >> struct kvm_io_device dev; >> }; >> >> +struct irq_phys_map { >> + struct rb_node node; >> + u32 virt_irq; >> + u32 phys_irq; >> + u32 irq; >> + bool active; >> +}; >> + >> struct vgic_dist { >> spinlock_t lock; >> bool in_kernel; >> @@ -256,6 +264,10 @@ struct vgic_dist { >> struct vgic_vm_ops vm_ops; >> struct vgic_io_device dist_iodev; >> struct vgic_io_device *redist_iodevs; >> + >> + /* Virtual irq to hwirq mapping */ >> + spinlock_t irq_phys_map_lock; >> + struct rb_root irq_phys_map; >> }; >> >> struct vgic_v2_cpu_if { >> @@ -307,6 +319,9 @@ struct vgic_cpu { >> struct vgic_v2_cpu_if vgic_v2; >> struct vgic_v3_cpu_if vgic_v3; >> }; >> + >> + /* Protected by the distributor's irq_phys_map_lock */ >> + struct rb_root irq_phys_map; >> }; >> >> #define LR_EMPTY 0xff >> @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, >> 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); >> >> #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) >> #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) >> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c >> index 59ed7a3..c6604f2 100644 >> --- a/virt/kvm/arm/vgic.c >> +++ b/virt/kvm/arm/vgic.c >> @@ -24,6 +24,7 @@ >> #include <linux/of.h> >> #include <linux/of_address.h> >> #include <linux/of_irq.h> >> +#include <linux/rbtree.h> >> #include <linux/uaccess.h> >> >> #include <linux/irqchip/arm-gic.h> >> @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); >> static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); >> static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); >> static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); >> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >> + int virt_irq); >> >> static const struct vgic_ops *vgic_ops; >> static const struct vgic_params *vgic; >> @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) >> return IRQ_HANDLED; >> } >> >> +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, >> + int virt_irq) >> +{ >> + if (virt_irq < VGIC_NR_PRIVATE_IRQS) >> + return &vcpu->arch.vgic_cpu.irq_phys_map; >> + else >> + return &vcpu->kvm->arch.vgic.irq_phys_map; >> +} >> + >> +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >> + int virt_irq, int irq) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >> + struct rb_node **new = &root->rb_node, *parent = NULL; >> + struct irq_phys_map *new_map; >> + struct irq_desc *desc; >> + struct irq_data *data; >> + int phys_irq; >> + >> + desc = irq_to_desc(irq); >> + if (!desc) { >> + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); >> + return NULL; >> + } >> + >> + data = irq_desc_get_irq_data(desc); >> + while (data->parent_data) >> + data = data->parent_data; >> + >> + phys_irq = data->hwirq; >> + >> + spin_lock(&dist->irq_phys_map_lock); >> + >> + /* Boilerplate rb_tree code */ >> + while (*new) { >> + struct irq_phys_map *this; >> + >> + this = container_of(*new, struct irq_phys_map, node); >> + parent = *new; >> + if (this->virt_irq < virt_irq) >> + new = &(*new)->rb_left; >> + else if (this->virt_irq > virt_irq) >> + new = &(*new)->rb_right; >> + else { >> + new_map = this; > in case the mapping already exists you don't update the mappping or > return an error. Is it what you want here? Calling the map function several times is not necessarily a bad idea, as long as they result in the same mapping. Think of a reset function for a device that would perform the mapping (just like the timer does). It should be possible to perform that reset several times without seeing anything failing. Now, the code doesn't handle the case where you'd end up with a different mapping for the same IRQ, which would be an error (you'd need to go through an unmap first). I'll update the code to take care of this case. >> + goto out; >> + } >> + } >> + >> + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); >> + if (!new_map) >> + goto out; >> + >> + new_map->virt_irq = virt_irq; >> + new_map->phys_irq = phys_irq; >> + new_map->irq = irq; >> + >> + rb_link_node(&new_map->node, parent, new); >> + rb_insert_color(&new_map->node, root); >> + >> +out: >> + spin_unlock(&dist->irq_phys_map_lock); >> + return new_map; >> +} >> + >> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >> + int virt_irq) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >> + struct rb_node *node = root->rb_node; >> + struct irq_phys_map *this = NULL; >> + >> + spin_lock(&dist->irq_phys_map_lock); >> + >> + while (node) { >> + this = container_of(node, struct irq_phys_map, node); >> + >> + if (this->virt_irq < virt_irq) >> + node = node->rb_left; >> + else if (this->virt_irq > virt_irq) >> + node = node->rb_right; >> + else >> + break; >> + } >> + >> + spin_unlock(&dist->irq_phys_map_lock); >> + return this; >> +} >> + >> +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + >> + if (!map) >> + return -EINVAL; >> + >> + spin_lock(&dist->irq_phys_map_lock); >> + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); >> + spin_unlock(&dist->irq_phys_map_lock); >> + >> + kfree(map); >> + return 0; >> +} >> + >> void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) >> { >> struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; >> @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) >> goto out_unlock; >> >> spin_lock_init(&kvm->arch.vgic.lock); > Don't you deallocate the rbtree nodes here? Erm... Yes, indeed. Silly me. > Also in the future with EOI mode == 1 we will need to complete the > physical IRQ in place of the guest. That's one of the things I needed your input on. I can perform the deactivate here (clearing the active state is easy). But what will guarantee that the interrupt won't be screaming? Will the device be quiesced at that time? Thanks, M.
On 06/16/2015 10:28 AM, Marc Zyngier wrote: > Hi Eric, > > On 15/06/15 16:44, Eric Auger wrote: >> Hi Marc, >> On 06/08/2015 07:04 PM, Marc Zyngier wrote: >>> In order to be able to feed physical interrupts to a guest, we need >>> to be able to establish the virtual-physical mapping between the two >>> worlds. >>> >>> The mapping is kept in a rbtree, indexed by virtual interrupts. >>> >>> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> >>> --- >>> include/kvm/arm_vgic.h | 18 ++++++++ >>> virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ >>> 2 files changed, 128 insertions(+) >>> >>> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h >>> index 4f9fa1d..33d121a 100644 >>> --- a/include/kvm/arm_vgic.h >>> +++ b/include/kvm/arm_vgic.h >>> @@ -159,6 +159,14 @@ struct vgic_io_device { >>> struct kvm_io_device dev; >>> }; >>> >>> +struct irq_phys_map { >>> + struct rb_node node; >>> + u32 virt_irq; >>> + u32 phys_irq; >>> + u32 irq; >>> + bool active; >>> +}; >>> + >>> struct vgic_dist { >>> spinlock_t lock; >>> bool in_kernel; >>> @@ -256,6 +264,10 @@ struct vgic_dist { >>> struct vgic_vm_ops vm_ops; >>> struct vgic_io_device dist_iodev; >>> struct vgic_io_device *redist_iodevs; >>> + >>> + /* Virtual irq to hwirq mapping */ >>> + spinlock_t irq_phys_map_lock; >>> + struct rb_root irq_phys_map; >>> }; >>> >>> struct vgic_v2_cpu_if { >>> @@ -307,6 +319,9 @@ struct vgic_cpu { >>> struct vgic_v2_cpu_if vgic_v2; >>> struct vgic_v3_cpu_if vgic_v3; >>> }; >>> + >>> + /* Protected by the distributor's irq_phys_map_lock */ >>> + struct rb_root irq_phys_map; >>> }; >>> >>> #define LR_EMPTY 0xff >>> @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, >>> 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); >>> >>> #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) >>> #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) >>> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c >>> index 59ed7a3..c6604f2 100644 >>> --- a/virt/kvm/arm/vgic.c >>> +++ b/virt/kvm/arm/vgic.c >>> @@ -24,6 +24,7 @@ >>> #include <linux/of.h> >>> #include <linux/of_address.h> >>> #include <linux/of_irq.h> >>> +#include <linux/rbtree.h> >>> #include <linux/uaccess.h> >>> >>> #include <linux/irqchip/arm-gic.h> >>> @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); >>> static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); >>> static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); >>> static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); >>> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >>> + int virt_irq); >>> >>> static const struct vgic_ops *vgic_ops; >>> static const struct vgic_params *vgic; >>> @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) >>> return IRQ_HANDLED; >>> } >>> >>> +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, >>> + int virt_irq) >>> +{ >>> + if (virt_irq < VGIC_NR_PRIVATE_IRQS) >>> + return &vcpu->arch.vgic_cpu.irq_phys_map; >>> + else >>> + return &vcpu->kvm->arch.vgic.irq_phys_map; >>> +} >>> + >>> +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >>> + int virt_irq, int irq) >>> +{ >>> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >>> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >>> + struct rb_node **new = &root->rb_node, *parent = NULL; >>> + struct irq_phys_map *new_map; >>> + struct irq_desc *desc; >>> + struct irq_data *data; >>> + int phys_irq; >>> + >>> + desc = irq_to_desc(irq); >>> + if (!desc) { >>> + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); >>> + return NULL; >>> + } >>> + >>> + data = irq_desc_get_irq_data(desc); >>> + while (data->parent_data) >>> + data = data->parent_data; >>> + >>> + phys_irq = data->hwirq; >>> + >>> + spin_lock(&dist->irq_phys_map_lock); >>> + >>> + /* Boilerplate rb_tree code */ >>> + while (*new) { >>> + struct irq_phys_map *this; >>> + >>> + this = container_of(*new, struct irq_phys_map, node); >>> + parent = *new; >>> + if (this->virt_irq < virt_irq) >>> + new = &(*new)->rb_left; >>> + else if (this->virt_irq > virt_irq) >>> + new = &(*new)->rb_right; >>> + else { >>> + new_map = this; >> in case the mapping already exists you don't update the mappping or >> return an error. Is it what you want here? > > Calling the map function several times is not necessarily a bad idea, as > long as they result in the same mapping. Think of a reset function for a > device that would perform the mapping (just like the timer does). It > should be possible to perform that reset several times without seeing > anything failing. > > Now, the code doesn't handle the case where you'd end up with a > different mapping for the same IRQ, which would be an error (you'd need > to go through an unmap first). > > I'll update the code to take care of this case. > >>> + goto out; >>> + } >>> + } >>> + >>> + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); >>> + if (!new_map) >>> + goto out; >>> + >>> + new_map->virt_irq = virt_irq; >>> + new_map->phys_irq = phys_irq; >>> + new_map->irq = irq; >>> + >>> + rb_link_node(&new_map->node, parent, new); >>> + rb_insert_color(&new_map->node, root); >>> + >>> +out: >>> + spin_unlock(&dist->irq_phys_map_lock); >>> + return new_map; >>> +} >>> + >>> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >>> + int virt_irq) >>> +{ >>> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >>> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >>> + struct rb_node *node = root->rb_node; >>> + struct irq_phys_map *this = NULL; >>> + >>> + spin_lock(&dist->irq_phys_map_lock); >>> + >>> + while (node) { >>> + this = container_of(node, struct irq_phys_map, node); >>> + >>> + if (this->virt_irq < virt_irq) >>> + node = node->rb_left; >>> + else if (this->virt_irq > virt_irq) >>> + node = node->rb_right; >>> + else >>> + break; >>> + } >>> + >>> + spin_unlock(&dist->irq_phys_map_lock); >>> + return this; >>> +} >>> + >>> +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) >>> +{ >>> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >>> + >>> + if (!map) >>> + return -EINVAL; >>> + >>> + spin_lock(&dist->irq_phys_map_lock); >>> + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); >>> + spin_unlock(&dist->irq_phys_map_lock); >>> + >>> + kfree(map); >>> + return 0; >>> +} >>> + >>> void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) >>> { >>> struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; >>> @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) >>> goto out_unlock; >>> >>> spin_lock_init(&kvm->arch.vgic.lock); >> Don't you deallocate the rbtree nodes here? > > Erm... Yes, indeed. Silly me. > >> Also in the future with EOI mode == 1 we will need to complete the >> physical IRQ in place of the guest. > > That's one of the things I needed your input on. I can perform the > deactivate here (clearing the active state is easy). But what will > guarantee that the interrupt won't be screaming? Will the device be > quiesced at that time? In my VFIO use case what does happen is that the guest might be killed without being able to handle and deactivate the vIRQ/pIRQ properly. In such a case when you restart a new guest using the same forwarded physical IRQ, the physical IRQ still is active and you cannot restart properly. This is why it is mandated to take care of the deactivation, at some point, in case the guest failed to do it. When killing the guest the device is not necessarily quiescent, ie IRQ might still be issued. This depends on the availability of a vfio reset module whose job consists in stopping DMA accesses and IRQ (https://lkml.org/lkml/2015/6/15/123). In //lkml.org/lkml/2014/11/23/120 I cleared the unforwarded state before doing the deactivate so if a new IRQ hits, it is completed by the host and not injected. Hope it helps Eric > > Thanks, > > M. > -- 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 06:04:01PM +0100, Marc Zyngier wrote: > In order to be able to feed physical interrupts to a guest, we need > to be able to establish the virtual-physical mapping between the two > worlds. > > The mapping is kept in a rbtree, indexed by virtual interrupts. how many of these do you expect there will be? Is the extra code and complexity of an rbtree really warranted? I would assume that you'll have one PPI for each CPU in the default case plus potentially a few more for an assigned network adapter, let's say a couple of handfulls. Am I missing something obvious or is this optimization of traversing a list of 10-12 mappings in the typical case not likely to be measurable? I would actually be more concerned about the additional locking and would look at RCU for protecting a list instead. Can you protect an rbtree with RCU easily? Thanks, -Christoffer > > Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> > --- > include/kvm/arm_vgic.h | 18 ++++++++ > virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 128 insertions(+) > > diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h > index 4f9fa1d..33d121a 100644 > --- a/include/kvm/arm_vgic.h > +++ b/include/kvm/arm_vgic.h > @@ -159,6 +159,14 @@ struct vgic_io_device { > struct kvm_io_device dev; > }; > > +struct irq_phys_map { > + struct rb_node node; > + u32 virt_irq; > + u32 phys_irq; > + u32 irq; > + bool active; > +}; > + > struct vgic_dist { > spinlock_t lock; > bool in_kernel; > @@ -256,6 +264,10 @@ struct vgic_dist { > struct vgic_vm_ops vm_ops; > struct vgic_io_device dist_iodev; > struct vgic_io_device *redist_iodevs; > + > + /* Virtual irq to hwirq mapping */ > + spinlock_t irq_phys_map_lock; why do we need a separate lock here? > + struct rb_root irq_phys_map; > }; > > struct vgic_v2_cpu_if { > @@ -307,6 +319,9 @@ struct vgic_cpu { > struct vgic_v2_cpu_if vgic_v2; > struct vgic_v3_cpu_if vgic_v3; > }; > + > + /* Protected by the distributor's irq_phys_map_lock */ > + struct rb_root irq_phys_map; > }; > > #define LR_EMPTY 0xff > @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, > 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); > > #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) > #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) > diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c > index 59ed7a3..c6604f2 100644 > --- a/virt/kvm/arm/vgic.c > +++ b/virt/kvm/arm/vgic.c > @@ -24,6 +24,7 @@ > #include <linux/of.h> > #include <linux/of_address.h> > #include <linux/of_irq.h> > +#include <linux/rbtree.h> > #include <linux/uaccess.h> > > #include <linux/irqchip/arm-gic.h> > @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); > static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); > static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); > static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); > +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > + int virt_irq); > > static const struct vgic_ops *vgic_ops; > static const struct vgic_params *vgic; > @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) > return IRQ_HANDLED; > } > > +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, > + int virt_irq) > +{ > + if (virt_irq < VGIC_NR_PRIVATE_IRQS) > + return &vcpu->arch.vgic_cpu.irq_phys_map; > + else > + return &vcpu->kvm->arch.vgic.irq_phys_map; > +} > + > +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, > + int virt_irq, int irq) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > + struct rb_node **new = &root->rb_node, *parent = NULL; > + struct irq_phys_map *new_map; > + struct irq_desc *desc; > + struct irq_data *data; > + int phys_irq; > + > + desc = irq_to_desc(irq); > + if (!desc) { > + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); > + return NULL; > + } > + > + data = irq_desc_get_irq_data(desc); > + while (data->parent_data) > + data = data->parent_data; > + > + phys_irq = data->hwirq; > + > + spin_lock(&dist->irq_phys_map_lock); > + > + /* Boilerplate rb_tree code */ > + while (*new) { > + struct irq_phys_map *this; > + > + this = container_of(*new, struct irq_phys_map, node); > + parent = *new; > + if (this->virt_irq < virt_irq) > + new = &(*new)->rb_left; > + else if (this->virt_irq > virt_irq) > + new = &(*new)->rb_right; > + else { > + new_map = this; > + goto out; > + } > + } > + > + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); > + if (!new_map) > + goto out; > + > + new_map->virt_irq = virt_irq; > + new_map->phys_irq = phys_irq; > + new_map->irq = irq; > + > + rb_link_node(&new_map->node, parent, new); > + rb_insert_color(&new_map->node, root); > + > +out: > + spin_unlock(&dist->irq_phys_map_lock); > + return new_map; > +} > + > +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, > + int virt_irq) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); > + struct rb_node *node = root->rb_node; > + struct irq_phys_map *this = NULL; > + > + spin_lock(&dist->irq_phys_map_lock); > + > + while (node) { > + this = container_of(node, struct irq_phys_map, node); > + > + if (this->virt_irq < virt_irq) > + node = node->rb_left; > + else if (this->virt_irq > virt_irq) > + node = node->rb_right; > + else > + break; > + } > + > + spin_unlock(&dist->irq_phys_map_lock); > + return this; > +} > + > +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) > +{ > + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; > + > + if (!map) > + return -EINVAL; > + > + spin_lock(&dist->irq_phys_map_lock); > + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); > + spin_unlock(&dist->irq_phys_map_lock); > + > + kfree(map); > + return 0; > +} > + > void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) > { > struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; > @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) > goto out_unlock; > > spin_lock_init(&kvm->arch.vgic.lock); > + spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock); > kvm->arch.vgic.in_kernel = true; > kvm->arch.vgic.vgic_model = type; > kvm->arch.vgic.vctrl_base = vgic->vctrl_base; > -- > 2.1.4 > -- 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 06:04:01PM +0100, Marc Zyngier wrote: >> In order to be able to feed physical interrupts to a guest, we need >> to be able to establish the virtual-physical mapping between the two >> worlds. >> >> The mapping is kept in a rbtree, indexed by virtual interrupts. > > how many of these do you expect there will be? Is the extra code and > complexity of an rbtree really warranted? > > I would assume that you'll have one PPI for each CPU in the default case > plus potentially a few more for an assigned network adapter, let's say a > couple of handfulls. Am I missing something obvious or is this > optimization of traversing a list of 10-12 mappings in the typical case > not likely to be measurable? > > I would actually be more concerned about the additional locking and > would look at RCU for protecting a list instead. Can you protect an > rbtree with RCU easily? Not very easily. There was some work done a while ago for the dentry cache IIRC, but I doubt that's reusable directly, and probably overkill. RCU protected lists are, on the other hand, readily available. Bah. I'll switch to this. By the time it becomes the bottleneck, the world will have moved on. Or so I hope. M. > > Thanks, > -Christoffer > >> >> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> >> --- >> include/kvm/arm_vgic.h | 18 ++++++++ >> virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ >> 2 files changed, 128 insertions(+) >> >> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h >> index 4f9fa1d..33d121a 100644 >> --- a/include/kvm/arm_vgic.h >> +++ b/include/kvm/arm_vgic.h >> @@ -159,6 +159,14 @@ struct vgic_io_device { >> struct kvm_io_device dev; >> }; >> >> +struct irq_phys_map { >> + struct rb_node node; >> + u32 virt_irq; >> + u32 phys_irq; >> + u32 irq; >> + bool active; >> +}; >> + >> struct vgic_dist { >> spinlock_t lock; >> bool in_kernel; >> @@ -256,6 +264,10 @@ struct vgic_dist { >> struct vgic_vm_ops vm_ops; >> struct vgic_io_device dist_iodev; >> struct vgic_io_device *redist_iodevs; >> + >> + /* Virtual irq to hwirq mapping */ >> + spinlock_t irq_phys_map_lock; > > why do we need a separate lock here? > >> + struct rb_root irq_phys_map; >> }; >> >> struct vgic_v2_cpu_if { >> @@ -307,6 +319,9 @@ struct vgic_cpu { >> struct vgic_v2_cpu_if vgic_v2; >> struct vgic_v3_cpu_if vgic_v3; >> }; >> + >> + /* Protected by the distributor's irq_phys_map_lock */ >> + struct rb_root irq_phys_map; >> }; >> >> #define LR_EMPTY 0xff >> @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, >> 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); >> >> #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) >> #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) >> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c >> index 59ed7a3..c6604f2 100644 >> --- a/virt/kvm/arm/vgic.c >> +++ b/virt/kvm/arm/vgic.c >> @@ -24,6 +24,7 @@ >> #include <linux/of.h> >> #include <linux/of_address.h> >> #include <linux/of_irq.h> >> +#include <linux/rbtree.h> >> #include <linux/uaccess.h> >> >> #include <linux/irqchip/arm-gic.h> >> @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); >> static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); >> static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); >> static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); >> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >> + int virt_irq); >> >> static const struct vgic_ops *vgic_ops; >> static const struct vgic_params *vgic; >> @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) >> return IRQ_HANDLED; >> } >> >> +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, >> + int virt_irq) >> +{ >> + if (virt_irq < VGIC_NR_PRIVATE_IRQS) >> + return &vcpu->arch.vgic_cpu.irq_phys_map; >> + else >> + return &vcpu->kvm->arch.vgic.irq_phys_map; >> +} >> + >> +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, >> + int virt_irq, int irq) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >> + struct rb_node **new = &root->rb_node, *parent = NULL; >> + struct irq_phys_map *new_map; >> + struct irq_desc *desc; >> + struct irq_data *data; >> + int phys_irq; >> + >> + desc = irq_to_desc(irq); >> + if (!desc) { >> + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); >> + return NULL; >> + } >> + >> + data = irq_desc_get_irq_data(desc); >> + while (data->parent_data) >> + data = data->parent_data; >> + >> + phys_irq = data->hwirq; >> + >> + spin_lock(&dist->irq_phys_map_lock); >> + >> + /* Boilerplate rb_tree code */ >> + while (*new) { >> + struct irq_phys_map *this; >> + >> + this = container_of(*new, struct irq_phys_map, node); >> + parent = *new; >> + if (this->virt_irq < virt_irq) >> + new = &(*new)->rb_left; >> + else if (this->virt_irq > virt_irq) >> + new = &(*new)->rb_right; >> + else { >> + new_map = this; >> + goto out; >> + } >> + } >> + >> + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); >> + if (!new_map) >> + goto out; >> + >> + new_map->virt_irq = virt_irq; >> + new_map->phys_irq = phys_irq; >> + new_map->irq = irq; >> + >> + rb_link_node(&new_map->node, parent, new); >> + rb_insert_color(&new_map->node, root); >> + >> +out: >> + spin_unlock(&dist->irq_phys_map_lock); >> + return new_map; >> +} >> + >> +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, >> + int virt_irq) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); >> + struct rb_node *node = root->rb_node; >> + struct irq_phys_map *this = NULL; >> + >> + spin_lock(&dist->irq_phys_map_lock); >> + >> + while (node) { >> + this = container_of(node, struct irq_phys_map, node); >> + >> + if (this->virt_irq < virt_irq) >> + node = node->rb_left; >> + else if (this->virt_irq > virt_irq) >> + node = node->rb_right; >> + else >> + break; >> + } >> + >> + spin_unlock(&dist->irq_phys_map_lock); >> + return this; >> +} >> + >> +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) >> +{ >> + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; >> + >> + if (!map) >> + return -EINVAL; >> + >> + spin_lock(&dist->irq_phys_map_lock); >> + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); >> + spin_unlock(&dist->irq_phys_map_lock); >> + >> + kfree(map); >> + return 0; >> +} >> + >> void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) >> { >> struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; >> @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) >> goto out_unlock; >> >> spin_lock_init(&kvm->arch.vgic.lock); >> + spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock); >> kvm->arch.vgic.in_kernel = true; >> kvm->arch.vgic.vgic_model = type; >> kvm->arch.vgic.vctrl_base = vgic->vctrl_base; >> -- >> 2.1.4 >> >
On Wed, Jul 01, 2015 at 11:20:45AM +0100, Marc Zyngier wrote: > On 30/06/15 21:19, Christoffer Dall wrote: > > On Mon, Jun 08, 2015 at 06:04:01PM +0100, Marc Zyngier wrote: > >> In order to be able to feed physical interrupts to a guest, we need > >> to be able to establish the virtual-physical mapping between the two > >> worlds. > >> > >> The mapping is kept in a rbtree, indexed by virtual interrupts. > > > > how many of these do you expect there will be? Is the extra code and > > complexity of an rbtree really warranted? > > > > I would assume that you'll have one PPI for each CPU in the default case > > plus potentially a few more for an assigned network adapter, let's say a > > couple of handfulls. Am I missing something obvious or is this > > optimization of traversing a list of 10-12 mappings in the typical case > > not likely to be measurable? > > > > I would actually be more concerned about the additional locking and > > would look at RCU for protecting a list instead. Can you protect an > > rbtree with RCU easily? > > Not very easily. There was some work done a while ago for the dentry > cache IIRC, but I doubt that's reusable directly, and probably overkill. > > RCU protected lists are, on the other hand, readily available. Bah. I'll > switch to this. By the time it becomes the bottleneck, the world will > have moved on. Or so I hope. > We can also move to RB trees if we have some data to show us it's worth the hassle later on, but I assume that since these structs are fairly small and overhead like this is mostly to show up on a hot path, a better optimization would be to allocate a bunch of these structures contiguously for cache locality, but again, I feel like this is all premature and we should measure the beast first. Thanks, -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 4f9fa1d..33d121a 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -159,6 +159,14 @@ struct vgic_io_device { struct kvm_io_device dev; }; +struct irq_phys_map { + struct rb_node node; + u32 virt_irq; + u32 phys_irq; + u32 irq; + bool active; +}; + struct vgic_dist { spinlock_t lock; bool in_kernel; @@ -256,6 +264,10 @@ struct vgic_dist { struct vgic_vm_ops vm_ops; struct vgic_io_device dist_iodev; struct vgic_io_device *redist_iodevs; + + /* Virtual irq to hwirq mapping */ + spinlock_t irq_phys_map_lock; + struct rb_root irq_phys_map; }; struct vgic_v2_cpu_if { @@ -307,6 +319,9 @@ struct vgic_cpu { struct vgic_v2_cpu_if vgic_v2; struct vgic_v3_cpu_if vgic_v3; }; + + /* Protected by the distributor's irq_phys_map_lock */ + struct rb_root irq_phys_map; }; #define LR_EMPTY 0xff @@ -331,6 +346,9 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, 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 vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 59ed7a3..c6604f2 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -24,6 +24,7 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/rbtree.h> #include <linux/uaccess.h> #include <linux/irqchip/arm-gic.h> @@ -84,6 +85,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu); static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu); static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr); static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc); +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, + int virt_irq); static const struct vgic_ops *vgic_ops; static const struct vgic_params *vgic; @@ -1585,6 +1588,112 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data) return IRQ_HANDLED; } +static struct rb_root *vgic_get_irq_phys_map(struct kvm_vcpu *vcpu, + int virt_irq) +{ + if (virt_irq < VGIC_NR_PRIVATE_IRQS) + return &vcpu->arch.vgic_cpu.irq_phys_map; + else + return &vcpu->kvm->arch.vgic.irq_phys_map; +} + +struct irq_phys_map *vgic_map_phys_irq(struct kvm_vcpu *vcpu, + int virt_irq, int irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); + struct rb_node **new = &root->rb_node, *parent = NULL; + struct irq_phys_map *new_map; + struct irq_desc *desc; + struct irq_data *data; + int phys_irq; + + desc = irq_to_desc(irq); + if (!desc) { + kvm_err("kvm_arch_timer: can't obtain interrupt descriptor\n"); + return NULL; + } + + data = irq_desc_get_irq_data(desc); + while (data->parent_data) + data = data->parent_data; + + phys_irq = data->hwirq; + + spin_lock(&dist->irq_phys_map_lock); + + /* Boilerplate rb_tree code */ + while (*new) { + struct irq_phys_map *this; + + this = container_of(*new, struct irq_phys_map, node); + parent = *new; + if (this->virt_irq < virt_irq) + new = &(*new)->rb_left; + else if (this->virt_irq > virt_irq) + new = &(*new)->rb_right; + else { + new_map = this; + goto out; + } + } + + new_map = kzalloc(sizeof(*new_map), GFP_KERNEL); + if (!new_map) + goto out; + + new_map->virt_irq = virt_irq; + new_map->phys_irq = phys_irq; + new_map->irq = irq; + + rb_link_node(&new_map->node, parent, new); + rb_insert_color(&new_map->node, root); + +out: + spin_unlock(&dist->irq_phys_map_lock); + return new_map; +} + +static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu, + int virt_irq) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + struct rb_root *root = vgic_get_irq_phys_map(vcpu, virt_irq); + struct rb_node *node = root->rb_node; + struct irq_phys_map *this = NULL; + + spin_lock(&dist->irq_phys_map_lock); + + while (node) { + this = container_of(node, struct irq_phys_map, node); + + if (this->virt_irq < virt_irq) + node = node->rb_left; + else if (this->virt_irq > virt_irq) + node = node->rb_right; + else + break; + } + + spin_unlock(&dist->irq_phys_map_lock); + return this; +} + +int vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + if (!map) + return -EINVAL; + + spin_lock(&dist->irq_phys_map_lock); + rb_erase(&map->node, vgic_get_irq_phys_map(vcpu, map->virt_irq)); + spin_unlock(&dist->irq_phys_map_lock); + + kfree(map); + return 0; +} + void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -1835,6 +1944,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) goto out_unlock; spin_lock_init(&kvm->arch.vgic.lock); + spin_lock_init(&kvm->arch.vgic.irq_phys_map_lock); kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
In order to be able to feed physical interrupts to a guest, we need to be able to establish the virtual-physical mapping between the two worlds. The mapping is kept in a rbtree, indexed by virtual interrupts. Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> --- include/kvm/arm_vgic.h | 18 ++++++++ virt/kvm/arm/vgic.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 128 insertions(+)