Add VT-d Posted-Interrupts support
Subsystems (4)
v5 cover Add VT-d Posted-Interrupts support
VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt. With VT-d Posted-Interrupts enabled, external interrupts from direct-assigned devices can be delivered to guests without VMM intervention when guest is running in non-root mode.
You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/vt-directed-io-spec.html
This series was part of http://thread.gmane.org/gmane.linux.kernel.iommu/7708. To make things clear, send out IOMMU part here.
This patch-set is based on the lastest x86/apic branch of tip tree.
Divide the whole series which contain multiple components into three parts:
- Prerequisite changes to irq subsystem (already merged)
- IOMMU part (already merged)
- KVM and VFIO parts (this series)
v5:
- Based on Alex and Eric's irq bypass manager:
https://lkml.org/lkml/2015/7/10/663
- Reuse some common patch from Eric
Eric Auger (3):
KVM: create kvm_irqfd.h
KVM: eventfd: add irq bypass information in irqfd
KVM: eventfd: add irq bypass consumer management
Feng Wu (16):
KVM: Extend struct pi_desc for VT-d Posted-Interrupts
KVM: Add some helper functions for Posted-Interrupts
KVM: Define a new interface kvm_intr_is_single_vcpu()
KVM: Get Posted-Interrupts descriptor address from struct kvm_vcpu
KVM: Add interfaces to control PI outside vmx
KVM: Make struct kvm_irq_routing_table accessible
KVM: make kvm_set_msi_irq() public
vfio: Select IRQ_BYPASS_MANAGER for vfio PCI devices
vfio: Register/unregister irq_bypass_producer
KVM, x86: Select IRQ_BYPASS_MANAGER for KVM_INTEL
KVM: x86: Update IRTE for posted-interrupts
KVM: x86: Add arch specific routines for irqbypass manager
KVM: Add an arch specific hooks in 'struct kvm_kernel_irqfd'
KVM: Update Posted-Interrupts Descriptor when vCPU is preempted
KVM: Update Posted-Interrupts Descriptor when vCPU is blocked
KVM: Warn if 'SN' is set during posting interrupts by software
arch/x86/include/asm/kvm_host.h | 15 ++ arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/irq_comm.c | 28 +++- arch/x86/kvm/vmx.c | 278 +++++++++++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 160 +++++++++++++++++++-- drivers/vfio/pci/Kconfig | 1 + drivers/vfio/pci/vfio_pci_intrs.c | 19 +++ drivers/vfio/pci/vfio_pci_private.h | 2 + include/linux/kvm_host.h | 23 +++ include/linux/kvm_irqfd.h | 74 ++++++++++ virt/kvm/eventfd.c | 115 ++++++--------- virt/kvm/irqchip.c | 11 -- virt/kvm/kvm_main.c | 3 + 13 files changed, 632 insertions(+), 98 deletions(-) create mode 100644 include/linux/kvm_irqfd.h
Signature · 1 line
2.1.0
PATCH v5 1/19 KVM: Extend struct pi_desc for VT-d Posted-Interrupts
Extend struct pi_desc for VT-d Posted-Interrupts.
--- arch/x86/kvm/vmx.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)
arch/x86/kvm/vmx.c +18 -2
@@ -445,8 +445,24 @@ struct nested_vmx {/* Posted-Interrupt Descriptor */ struct pi_desc {u32 pir[8 ];/* Posted interrupt requested */ -u32 control;/* bit 0 of control is outstanding notification bit */ -u32 rsvd[7 ]; +union { +struct { +/* bit 256 - Outstanding Notification */ +u16 on :1 , +/* bit 257 - Suppress Notification */ + sn :1 , +/* bit 271:258 - Reserved */ + rsvd_1 :14 ; +/* bit 279:272 - Notification Vector */ +u8 nv; +/* bit 287:280 - Reserved */ +u8 rsvd_2; +/* bit 319:288 - Notification Destination */ +u32 ndst; + }; +u64 control; + }; +u32 rsvd[6 ]; }__aligned(64) ;static bool pi_test_and_set_on (struct pi_desc *pi_desc)
Signature · 1 line
2.1.0
PATCH v5 2/19 KVM: Add some helper functions for Posted-Interrupts
In reply to Feng WuThis patch adds some helper functions to manipulate the Posted-Interrupts Descriptor.
--- arch/x86/kvm/vmx.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)
arch/x86/kvm/vmx.c +26 -0
@@ -442,6 +442,8 @@ struct nested_vmx { };#define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 +/* Posted-Interrupt Descriptor */ struct pi_desc {u32 pir[8 ];/* Posted interrupt requested */
@@ -482,6 +484,30 @@ static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)return test_and_set_bit (vector, (unsigned long *)pi_desc->pir); } +static void pi_clear_sn (struct pi_desc *pi_desc) +{ +return clear_bit (POSTED_INTR_SN , + (unsigned long *)&pi_desc->control); +} + +static void pi_set_sn (struct pi_desc *pi_desc) +{ +return set_bit (POSTED_INTR_SN , + (unsigned long *)&pi_desc->control); +} + +static int pi_test_on (struct pi_desc *pi_desc) +{ +return test_bit (POSTED_INTR_ON , + (unsigned long *)&pi_desc->control); +} + +static int pi_test_sn (struct pi_desc *pi_desc) +{ +return test_bit (POSTED_INTR_SN , + (unsigned long *)&pi_desc->control); +} +struct vcpu_vmx {struct kvm_vcpu vcpu;unsigned long host_rsp;
Signature · 1 line
2.1.0
PATCH v5 3/19 KVM: Define a new interface kvm_intr_is_single_vcpu()
In reply to Feng WuThis patch defines a new interface kvm_intr_is_single_vcpu(), which can returns whether the interrupt is for single-CPU or not.
It is used by VT-d PI, since now we only support single-CPU interrupts, For lowest-priority interrupts, if user configures it via /proc/irq or uses irqbalance to make it single-CPU, we can use PI to deliver the interrupts to it. Full functionality of lowest-priority support will be added later.
--- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/irq_comm.c | 24 ++++++++++++++++++++++++ 2 files changed, 26 insertions(+)
arch/x86/include/asm/kvm_host.h +2 -0
@@ -1180,4 +1180,6 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);void kvm_handle_pmu_event (struct kvm_vcpu *vcpu);void kvm_deliver_pmi (struct kvm_vcpu *vcpu); +bool kvm_intr_is_single_vcpu (struct kvm *kvm,struct kvm_lapic_irq *irq, +struct kvm_vcpu **dest_vcpu);#endif /* _ASM_X86_KVM_HOST_H */
arch/x86/kvm/irq_comm.c +24 -0
@@ -299,6 +299,30 @@ out:return r; } +bool kvm_intr_is_single_vcpu (struct kvm *kvm,struct kvm_lapic_irq *irq, +struct kvm_vcpu **dest_vcpu) +{ +int i, r =0 ; +struct kvm_vcpu *vcpu; + +kvm_for_each_vcpu (i, vcpu, kvm) { +if (!kvm_apic_present (vcpu)) +continue ; + +if (!kvm_apic_match_dest (vcpu,NULL , irq->shorthand, + irq->dest_id, irq->dest_mode)) +continue ; + + r++; + *dest_vcpu = vcpu; + } + +if (r ==1 ) +return true; +else +return false; +} +#define IOAPIC_ROUTING_ENTRY (irq) \ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
Signature · 1 line
2.1.0
PATCH v5 4/19 KVM: Get Posted-Interrupts descriptor address from struct kvm_vcpu
In reply to Feng WuDefine an interface to get PI descriptor address from the vCPU structure.
--- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/vmx.c | 11 +++++++++++ 2 files changed, 13 insertions(+)
arch/x86/include/asm/kvm_host.h +2 -0
@@ -836,6 +836,8 @@ struct kvm_x86_ops {void (*enable_log_dirty_pt_masked)(struct kvm *kvm,struct kvm_memory_slot *slot,gfn_t offset,unsigned long mask); + +u64 (*get_pi_desc_addr)(struct kvm_vcpu *vcpu); };struct kvm_arch_async_pf {
arch/x86/kvm/vmx.c +11 -0
@@ -609,6 +609,10 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)#define FIELD64 (number, name) [number] = VMCS12_OFFSET(name), \ [number##_HIGH] = VMCS12_OFFSET(name)+4 +struct pi_desc *vcpu_to_pi_desc (struct kvm_vcpu *vcpu) +{ +return &(to_vmx (vcpu)->pi_desc); +}static unsigned long shadow_read_only_fields[] = {/*
@@ -4494,6 +4498,11 @@ static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu)return ; } +static u64 vmx_get_pi_desc_addr (struct kvm_vcpu *vcpu) +{ +return __pa ((u64 )vcpu_to_pi_desc (vcpu)); +} +/* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest.
@@ -10296,6 +10305,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .slot_disable_log_dirty = vmx_slot_disable_log_dirty, .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + + .get_pi_desc_addr = vmx_get_pi_desc_addr, };static int __init vmx_init (void )
Signature · 1 line
2.1.0
PATCH v5 5/19 KVM: Add interfaces to control PI outside vmx
In reply to Feng WuThis patch adds pi_clear_sn and pi_set_sn to struct kvm_x86_ops, so we can set/clear SN outside vmx.
--- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/vmx.c | 13 +++++++++++++ 2 files changed, 16 insertions(+)
arch/x86/include/asm/kvm_host.h +3 -0
@@ -838,6 +838,9 @@ struct kvm_x86_ops { gfn_t offset, unsigned long mask);u64 (*get_pi_desc_addr)(struct kvm_vcpu *vcpu); + +void (*pi_clear_sn)(struct kvm_vcpu *vcpu); +void (*pi_set_sn)(struct kvm_vcpu *vcpu); };struct kvm_arch_async_pf {
arch/x86/kvm/vmx.c +13 -0
@@ -614,6 +614,16 @@ struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)return &(to_vmx (vcpu)->pi_desc); } +static void vmx_pi_clear_sn (struct kvm_vcpu *vcpu) +{ +pi_clear_sn (vcpu_to_pi_desc (vcpu)); +} + +static void vmx_pi_set_sn (struct kvm_vcpu *vcpu) +{ +pi_set_sn (vcpu_to_pi_desc (vcpu)); +} +static unsigned long shadow_read_only_fields[] = {/* * We do NOT shadow fields that are modified when L0
@@ -10307,6 +10317,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, .get_pi_desc_addr = vmx_get_pi_desc_addr, + + .pi_clear_sn = vmx_pi_clear_sn, + .pi_set_sn = vmx_pi_set_sn, };static int __init vmx_init (void )
Signature · 1 line
2.1.0
PATCH v5 6/19 KVM: Make struct kvm_irq_routing_table accessible
In reply to Feng WuMove struct kvm_irq_routing_table from irqchip.c to kvm_host.h, so we can use it outside of irqchip.c.
--- include/linux/kvm_host.h | 15 +++++++++++++++ virt/kvm/irqchip.c | 11 ----------- 2 files changed, 15 insertions(+), 11 deletions(-)
include/linux/kvm_host.h +15 -0
@@ -321,6 +321,21 @@ struct kvm_kernel_irq_routing_entry {struct hlist_node link; }; +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING + +struct kvm_irq_routing_table { +int chip[KVM_NR_IRQCHIPS ][KVM_IRQCHIP_NUM_PINS ]; +struct kvm_kernel_irq_routing_entry *rt_entries; +u32 nr_rt_entries; +/* +* Array indexed by gsi. Each entry contains list of irq chips +* the gsi is connected to. +*/ +struct hlist_head map[0 ]; +}; + +#endif +#ifndef KVM_PRIVATE_MEM_SLOTS #define KVM_PRIVATE_MEM_SLOTS 0#endif
virt/kvm/irqchip.c +0 -11
@@ -31,17 +31,6 @@#include <trace/events/kvm.h> #include "irq.h" -struct kvm_irq_routing_table { -int chip[KVM_NR_IRQCHIPS ][KVM_IRQCHIP_NUM_PINS ]; -struct kvm_kernel_irq_routing_entry *rt_entries; -u32 nr_rt_entries; -/* -* Array indexed by gsi. Each entry contains list of irq chips -* the gsi is connected to. -*/ -struct hlist_head map[0 ]; -}; -int kvm_irq_map_gsi (struct kvm *kvm,struct kvm_kernel_irq_routing_entry *entries,int gsi) {
Signature · 1 line
2.1.0
PATCH v5 7/19 KVM: make kvm_set_msi_irq() public
In reply to Feng WuMake kvm_set_msi_irq() public, we can use this function outside.
--- arch/x86/include/asm/kvm_host.h | 4 ++++ arch/x86/kvm/irq_comm.c | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-)
arch/x86/include/asm/kvm_host.h +4 -0
@@ -175,6 +175,8 @@ enum {*/ #define KVM_APIC_PV_EOI_PENDING 1 +struct kvm_kernel_irq_routing_entry ; +/* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache.
@@ -1187,4 +1189,6 @@ void kvm_deliver_pmi(struct kvm_vcpu *vcpu);bool kvm_intr_is_single_vcpu (struct kvm *kvm,struct kvm_lapic_irq *irq,struct kvm_vcpu **dest_vcpu); +void kvm_set_msi_irq (struct kvm_kernel_irq_routing_entry *e, +struct kvm_lapic_irq *irq);#endif /* _ASM_X86_KVM_HOST_H */
arch/x86/kvm/irq_comm.c +2 -2
@@ -94,8 +94,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,return r; } -static inline void kvm_set_msi_irq (struct kvm_kernel_irq_routing_entry *e, -struct kvm_lapic_irq *irq) +void kvm_set_msi_irq (struct kvm_kernel_irq_routing_entry *e, +struct kvm_lapic_irq *irq) {trace_kvm_msi_set_irq (e->msi.address_lo, e->msi.data);
Signature · 1 line
2.1.0
PATCH v5 8/19 vfio: Select IRQ_BYPASS_MANAGER for vfio PCI devices
In reply to Feng WuEnable irq bypass manager for vfio PCI devices.
--- drivers/vfio/pci/Kconfig | 1 + 1 file changed, 1 insertion(+)
drivers/vfio/pci/Kconfig +1 -0
@@ -2,6 +2,7 @@ config VFIO_PCI tristate "VFIO support for PCI devices" depends on VFIO && PCI && EVENTFD select VFIO_VIRQFD + select IRQ_BYPASS_MANAGER help Support for the PCI VFIO bus driver. This is required to make use of PCI drivers using the VFIO framework.
Signature · 1 line
2.1.0
PATCH v5 9/19 vfio: Register/unregister irq_bypass_producer
In reply to Feng WuThis patch adds the registration/unregistration of an irq_bypass_producer for MSI/MSIx on vfio pci devices.
--- drivers/vfio/pci/vfio_pci_intrs.c | 19 +++++++++++++++++++ drivers/vfio/pci/vfio_pci_private.h | 2 ++ 2 files changed, 21 insertions(+)
drivers/vfio/pci/vfio_pci_intrs.c +19 -0
@@ -305,6 +305,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)return 0 ; } +void vfio_pci_add_consumer (struct irq_bypass_producer *prod, +struct irq_bypass_consumer *cons) +{ +} + +void vfio_pci_del_consumer (struct irq_bypass_producer *prod, +struct irq_bypass_consumer *cons) +{ +} +static int vfio_msi_set_vector_signal (struct vfio_pci_device *vdev,int vector,int fd,bool msix) {
@@ -319,6 +329,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,if (vdev->ctx[vector].trigger) {free_irq (irq, vdev->ctx[vector].trigger); +irq_bypass_unregister_producer (&vdev->ctx[vector].producer);kfree (vdev->ctx[vector].name);eventfd_ctx_put (vdev->ctx[vector].trigger); vdev->ctx[vector].trigger =NULL ;
@@ -360,6 +371,14 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,return ret; } +INIT_LIST_HEAD (&vdev->ctx[vector].producer.node); + vdev->ctx[vector].producer.token = trigger; + vdev->ctx[vector].producer.irq = irq; + vdev->ctx[vector].producer.add_consumer = vfio_pci_add_consumer; + vdev->ctx[vector].producer.del_consumer = vfio_pci_del_consumer; + ret =irq_bypass_register_producer (&vdev->ctx[vector].producer); +WARN_ON (ret); + vdev->ctx[vector].trigger = trigger;return 0 ;
drivers/vfio/pci/vfio_pci_private.h +2 -0
@@ -13,6 +13,7 @@#include <linux/mutex.h> #include <linux/pci.h> +#include <linux/irqbypass.h> #ifndef VFIO_PCI_PRIVATE_H #define VFIO_PCI_PRIVATE_H
@@ -29,6 +30,7 @@ struct vfio_pci_irq_ctx {struct virqfd *mask;char *name;bool masked; +struct irq_bypass_producer producer; };struct vfio_pci_device {
Signature · 1 line
2.1.0
Re: [v5 09/19] vfio: Register/unregister irq_bypass_producer
Hi Feng,
Quoted 2 lines · Feng Wu
This patch adds the registration/unregistration of an
irq_bypass_producerfor MSI/MSIx on vfio pci devices.
may be worth mentioning this is a dummy producer with callbacks not yet implemented.
Quoted 12 lines
Signed-off-by Feng Wu <[email protected]>--- drivers/vfio/pci/vfio_pci_intrs.c | 19 +++++++++++++++++++ drivers/vfio/pci/vfio_pci_private.h | 2 ++ 2 files changed, 21 insertions(+)drivers/vfio/pci/vfio_pci_intrs.c +0
-0
drivers/vfio/pci/vfio_pci_intrs.c static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) · line 309
Quoted 5 lines
drivers/vfio/pci/vfio_pci_intrs.c +2
-0@@ -305,6 +305,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)return 0 ; } +void vfio_pci_add_consumer (struct irq_bypass_producer *prod, +struct irq_bypass_consumer *cons)
static?
Also Paolo encouraged me to use vfio_pci_irq_bypass_add_consumer naming. Same below.
drivers/vfio/pci/vfio_pci_intrs.c static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) · line 314
Quoted 5 lines
drivers/vfio/pci/vfio_pci_intrs.c +5
-0+{ +} + +void vfio_pci_del_consumer (struct irq_bypass_producer *prod, +struct irq_bypass_consumer *cons)
static?
Eric
Quoted 50 lines
drivers/vfio/pci/vfio_pci_intrs.c +12
-0+{ +} +static int vfio_msi_set_vector_signal (struct vfio_pci_device *vdev,int vector,int fd,bool msix) {@@ -319,6 +329,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,if (vdev->ctx[vector].trigger) {free_irq (irq, vdev->ctx[vector].trigger); +irq_bypass_unregister_producer (&vdev->ctx[vector].producer);kfree (vdev->ctx[vector].name);eventfd_ctx_put (vdev->ctx[vector].trigger); vdev->ctx[vector].trigger =NULL ;@@ -360,6 +371,14 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,return ret; } +INIT_LIST_HEAD (&vdev->ctx[vector].producer.node); + vdev->ctx[vector].producer.token = trigger; + vdev->ctx[vector].producer.irq = irq; + vdev->ctx[vector].producer.add_consumer = vfio_pci_add_consumer; + vdev->ctx[vector].producer.del_consumer = vfio_pci_del_consumer; + ret =irq_bypass_register_producer (&vdev->ctx[vector].producer); +WARN_ON (ret); + vdev->ctx[vector].trigger = trigger;return 0 ;drivers/vfio/pci/vfio_pci_private.h +2
-0@@ -13,6 +13,7 @@#include <linux/mutex.h> #include <linux/pci.h> +#include <linux/irqbypass.h> #ifndef VFIO_PCI_PRIVATE_H #define VFIO_PCI_PRIVATE_H @@ -29,6 +30,7 @@ struct vfio_pci_irq_ctx {struct virqfd *mask;char *name;bool masked; +struct irq_bypass_producer producer; };struct vfio_pci_device {
Re: [v5 09/19] vfio: Register/unregister irq_bypass_producer
In reply to Feng WuQuoted 17 lines · Feng Wu
This patch adds the registration/unregistration of an
irq_bypass_producerfor MSI/MSIx on vfio pci devices.Signed-off-by Feng Wu <[email protected]>--- drivers/vfio/pci/vfio_pci_intrs.c | 19 +++++++++++++++++++ drivers/vfio/pci/vfio_pci_private.h | 2 ++ 2 files changed, 21 insertions(+)drivers/vfio/pci/vfio_pci_intrs.c +0
-0@@ -305,6 +305,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)return 0 ; }
drivers/vfio/pci/vfio_pci_intrs.c static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) · line 317
Quoted 10 lines
drivers/vfio/pci/vfio_pci_intrs.c +10
-0+void vfio_pci_add_consumer (struct irq_bypass_producer *prod, +struct irq_bypass_consumer *cons) +{ +} + +void vfio_pci_del_consumer (struct irq_bypass_producer *prod, +struct irq_bypass_consumer *cons) +{ +} +
Yes, as Eric says, these should be static
Quoted 12 lines
drivers/vfio/pci/vfio_pci_intrs.c +1
-0static int vfio_msi_set_vector_signal (struct vfio_pci_device *vdev,int vector,int fd,bool msix) {@@ -319,6 +329,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,if (vdev->ctx[vector].trigger) {free_irq (irq, vdev->ctx[vector].trigger); +irq_bypass_unregister_producer (&vdev->ctx[vector].producer);kfree (vdev->ctx[vector].name);eventfd_ctx_put (vdev->ctx[vector].trigger); vdev->ctx[vector].trigger =NULL ;
drivers/vfio/pci/vfio_pci_intrs.c static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, · line 374
Quoted 4 lines
drivers/vfio/pci/vfio_pci_intrs.c +1
-0@@ -360,6 +371,14 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,return ret; } +INIT_LIST_HEAD (&vdev->ctx[vector].producer.node);
nit, INIT_LIST_HEAD isn't really needed, irq-bypass-manager shouldn't trust incoming data here anyway.
drivers/vfio/pci/vfio_pci_intrs.c static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, · line 380
Quoted 6 lines
drivers/vfio/pci/vfio_pci_intrs.c +6
-0+ vdev->ctx[vector].producer.token = trigger; + vdev->ctx[vector].producer.irq = irq; + vdev->ctx[vector].producer.add_consumer = vfio_pci_add_consumer; + vdev->ctx[vector].producer.del_consumer = vfio_pci_del_consumer; + ret =irq_bypass_register_producer (&vdev->ctx[vector].producer); +WARN_ON (ret);
This is only an acceleration path, so a dev_dbg() or dev_info() is probably more appropriate. Same for kvm side.
Quoted 24 lines
drivers/vfio/pci/vfio_pci_intrs.c +1
-0+ vdev->ctx[vector].trigger = trigger;return 0 ;drivers/vfio/pci/vfio_pci_private.h +2
-0@@ -13,6 +13,7 @@#include <linux/mutex.h> #include <linux/pci.h> +#include <linux/irqbypass.h> #ifndef VFIO_PCI_PRIVATE_H #define VFIO_PCI_PRIVATE_H @@ -29,6 +30,7 @@ struct vfio_pci_irq_ctx {struct virqfd *mask;char *name;bool masked; +struct irq_bypass_producer producer; };struct vfio_pci_device {
PATCH v5 10/19 KVM, x86: Select IRQ_BYPASS_MANAGER for KVM_INTEL
In reply to Feng WuEnable irq bypass manager for kvm-intel.
--- arch/x86/kvm/Kconfig | 1 + 1 file changed, 1 insertion(+)
arch/x86/kvm/Kconfig +1 -0
@@ -61,6 +61,7 @@ config KVM_INTEL depends on KVM # for perf_guest_get_msrs(): depends on CPU_SUP_INTEL + select IRQ_BYPASS_MANAGER ---help--- Provides support for KVM on Intel processors equipped with the VT extensions.
Signature · 1 line
2.1.0
PATCH v5 11/19 KVM: create kvm_irqfd.h
In reply to Feng WuFrom: Eric Auger <[email protected]>
Move _irqfd_resampler and _irqfd struct declarations in a new public header: kvm_irqfd.h. They are respectively renamed into kvm_kernel_irqfd_resampler and kvm_kernel_irqfd. Those datatypes will be used by architecture specific code, in the context of IRQ bypass manager integration.
--- include/linux/kvm_irqfd.h | 69 ++++++++++++++++++++++++++++++++++ virt/kvm/eventfd.c | 95 ++++++++++++----------------------------------- 2 files changed, 92 insertions(+), 72 deletions(-) create mode 100644 include/linux/kvm_irqfd.h
include/linux/kvm_irqfd.h new file +69 -0
@@ -0,0 +1,69 @@ +/* +* This program is free software; you can redistribute it and/or modify +* it under the terms of the GNU General Public License as published by +* the Free Software Foundation; either version 2 of the License. +* +* This program is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU General Public License for more details. +* +* irqfd: Allows an fd to be used to inject an interrupt to the guest +* Credit goes to Avi Kivity for the original idea. +*/ + +#ifndef __LINUX_KVM_IRQFD_H +#define __LINUX_KVM_IRQFD_H + +#include <linux/kvm_host.h> +#include <linux/poll.h> + +/* +* Resampling irqfds are a special variety of irqfds used to emulate +* level triggered interrupts. The interrupt is asserted on eventfd +* trigger. On acknowledgment through the irq ack notifier, the +* interrupt is de-asserted and userspace is notified through the +* resamplefd. All resamplers on the same gsi are de-asserted +* together, so we don't need to track the state of each individual +* user. We can also therefore share the same irq source ID. +*/ +struct kvm_kernel_irqfd_resampler { +struct kvm *kvm; +/* +* List of resampling struct _irqfd objects sharing this gsi. +* RCU list modified under kvm->irqfds.resampler_lock +*/ +struct list_head list; +struct kvm_irq_ack_notifier notifier; +/* +* Entry in list of kvm->irqfd.resampler_list. Use for sharing +* resamplers among irqfds on the same gsi. +* Accessed and modified under kvm->irqfds.resampler_lock +*/ +struct list_head link; +}; + +struct kvm_kernel_irqfd { +/* Used for MSI fast-path */ +struct kvm *kvm; +wait_queue_t wait; +/* Update side is protected by irqfds.lock */ +struct kvm_kernel_irq_routing_entry irq_entry; +seqcount_t irq_entry_sc; +/* Used for level IRQ fast-path */ +int gsi; +struct work_struct inject; +/* The resampler used by this irqfd (resampler-only) */ +struct kvm_kernel_irqfd_resampler *resampler; +/* Eventfd notified on resample (resampler-only) */ +struct eventfd_ctx *resamplefd; +/* Entry in list of irqfds for a resampler (resampler-only) */ +struct list_head resampler_link; +/* Used for setup/shutdown */ +struct eventfd_ctx *eventfd; +struct list_head list; +poll_table pt; +struct work_struct shutdown; +}; + +#endif /* __LINUX_KVM_IRQFD_H */
virt/kvm/eventfd.c +23 -72
193 lines not on this page · raw message
Signature · 1 line
2.1.0
PATCH v5 12/19 KVM: eventfd: add irq bypass information in irqfd
In reply to Feng WuFrom: Eric Auger <[email protected]>
This patch adds the following new members in 'struct kvm_kernel_irqfd'
- struct irq_bypass_consumer consumer
- struct irq_bypass_producer *producer
--- include/linux/kvm_irqfd.h | 3 +++ 1 file changed, 3 insertions(+)
include/linux/kvm_irqfd.h +3 -0
@@ -17,6 +17,7 @@#include <linux/kvm_host.h> #include <linux/poll.h> +#include <linux/irqbypass.h> /* * Resampling irqfds are a special variety of irqfds used to emulate
@@ -64,6 +65,8 @@ struct kvm_kernel_irqfd {struct list_head list;poll_table pt;struct work_struct shutdown; +struct irq_bypass_consumer consumer; + struct irq_bypass_producer *producer; };#endif /* __LINUX_KVM_IRQFD_H */
Signature · 1 line
2.1.0
PATCH v5 13/19 KVM: x86: Update IRTE for posted-interrupts
In reply to Feng WuThis patch adds the routine to update IRTE for posted-interrupts when guest changes the interrupt configuration.
--- arch/x86/kvm/x86.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+)
arch/x86/kvm/x86.c +73 -0
@@ -63,6 +63,7 @@#include <asm/fpu/internal.h> /* Ugh! */ #include <asm/pvclock.h> #include <asm/div64.h> +#include <asm/irq_remapping.h> #define MAX_IO_MSRS 256#define KVM_MAX_MCE_BANKS 32
@@ -7950,6 +7951,78 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) }EXPORT_SYMBOL_GPL (kvm_arch_has_noncoherent_dma); +/* +* kvm_arch_update_pi_irte - set IRTE for Posted-Interrupts +* +* @kvm: kvm +* @host_irq: host irq of the interrupt +* @guest_irq: gsi of the interrupt +* @set: set or unset PI +* returns 0 on success, < 0 on failure +*/ +int kvm_arch_update_pi_irte (struct kvm *kvm,unsigned int host_irq, +uint32_t guest_irq,bool set) +{ +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 = -EINVAL ; + +if (!irq_remapping_cap (IRQ_POSTING_CAP )) +return 0 ; + + idx =srcu_read_lock (&kvm->irq_srcu); + irq_rt =srcu_dereference (kvm->irq_routing, &kvm->irq_srcu); +BUG_ON (guest_irq >= irq_rt->nr_rt_entries); + +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. +* +*/ + +kvm_set_msi_irq (e, &irq); +if (!kvm_intr_is_single_vcpu (kvm, &irq, &vcpu)) +continue ; + + vcpu_info.pi_desc_addr = kvm_x86_ops->get_pi_desc_addr (vcpu); + vcpu_info.vector = irq.vector; + +if (set) + ret =irq_set_vcpu_affinity (host_irq, &vcpu_info); +else { +/* suppress notification event before unposting */ + kvm_x86_ops->pi_set_sn (vcpu); + ret =irq_set_vcpu_affinity (host_irq,NULL ); + kvm_x86_ops->pi_clear_sn (vcpu); + } + +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; +} +EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_exit);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_inj_virq);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_page_fault);
Signature · 1 line
2.1.0
PATCH v5 14/19 KVM: x86: Add arch specific routines for irqbypass manager
In reply to Feng WuAdd the following x86 specific routines for irqbypass manger:
- kvm_arch_irq_bypass_add_producer
- kvm_arch_irq_bypass_del_producer
--- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 2 ++ 3 files changed, 43 insertions(+)
arch/x86/include/asm/kvm_host.h +1 -0
@@ -24,6 +24,7 @@#include <linux/perf_event.h> #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> +#include <linux/irqbypass.h> #include <asm/pvclock-abi.h> #include <asm/desc.h>
arch/x86/kvm/x86.c +40 -0
@@ -49,6 +49,8 @@#include <linux/pci.h> #include <linux/timekeeper_internal.h> #include <linux/pvclock_gtod.h> +#include <linux/kvm_irqfd.h> +#include <linux/irqbypass.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS
@@ -8023,6 +8025,44 @@ out:return ret; } +void kvm_arch_irq_bypass_add_producer (struct irq_bypass_consumer *cons, +struct irq_bypass_producer *prod) +{ +int ret; +struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + irqfd->producer = prod; + + ret =kvm_arch_update_pi_irte (irqfd->kvm, prod->irq, irqfd->gsi,1 ); +WARN_ON (ret); +} + +void kvm_arch_irq_bypass_del_producer (struct irq_bypass_consumer *cons, +struct irq_bypass_producer *prod) +{ +int ret; +struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + irqfd->producer =NULL ; + +/* +* When producer of consumer is unregistered, we change back to +* remapped mode, so we can re-use the current implementation +* when the irq is masked/disabed or the consumer side (KVM +* int this case doesn't want to receive the interrupts. +*/ + ret =kvm_arch_update_pi_irte (irqfd->kvm, prod->irq, irqfd->gsi,0 ); +WARN_ON (ret); +} + +void kvm_arch_irq_consumer_init (struct irq_bypass_consumer *cons) +{ + cons->add_producer = kvm_arch_irq_bypass_add_producer; + cons->del_producer = kvm_arch_irq_bypass_del_producer; +} +EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_exit);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_inj_virq);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_page_fault);
include/linux/kvm_host.h +2 -0
@@ -1073,6 +1073,8 @@ extern struct kvm_device_ops kvm_xics_ops;extern struct kvm_device_ops kvm_arm_vgic_v2_ops;extern struct kvm_device_ops kvm_arm_vgic_v3_ops; +void kvm_arch_irq_consumer_init (struct irq_bypass_consumer *cons); +#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop (struct kvm_vcpu *vcpu,bool val)
Signature · 1 line
2.1.0
Re: [v5 14/19] KVM: x86: Add arch specific routines for irqbypass manager
Quoted 38 lines · Feng Wu
Add the following x86 specific routines for irqbypass manger:
-
kvm_arch_irq_bypass_add_producer
-kvm_arch_irq_bypass_del_producerSigned-off-by Feng Wu <[email protected]>--- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 2 ++ 3 files changed, 43 insertions(+)arch/x86/include/asm/kvm_host.h +1
-0@@ -24,6 +24,7 @@#include <linux/perf_event.h> #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> +#include <linux/irqbypass.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> arch/x86/kvm/x86.c +2
-0@@ -49,6 +49,8 @@#include <linux/pci.h> #include <linux/timekeeper_internal.h> #include <linux/pvclock_gtod.h> +#include <linux/kvm_irqfd.h> +#include <linux/irqbypass.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS
arch/x86/kvm/x86.c out: · line 8029
Quoted 5 lines
arch/x86/kvm/x86.c +2
-0@@ -8023,6 +8025,44 @@ out:return ret; } +void kvm_arch_irq_bypass_add_producer (struct irq_bypass_consumer *cons, +struct irq_bypass_producer *prod)
static?
Quoted 4 lines
arch/x86/kvm/x86.c +4
-0+{ +int ret; +struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer);
arch/x86/kvm/x86.c out: · line 8043
Quoted 10 lines
arch/x86/kvm/x86.c +10
-0+ + irqfd->producer = prod; + + ret =kvm_arch_update_pi_irte (irqfd->kvm, prod->irq, irqfd->gsi,1 ); +WARN_ON (ret); +} + +void kvm_arch_irq_bypass_del_producer (struct irq_bypass_consumer *cons, +struct irq_bypass_producer *prod) +{
static?
Since those 2 functions are not exposed to generic code anymore, why this kvm_arch naming?
Eric
Quoted 39 lines
arch/x86/kvm/x86.c +22
-0+int ret; +struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + irqfd->producer =NULL ; + +/* +* When producer of consumer is unregistered, we change back to +* remapped mode, so we can re-use the current implementation +* when the irq is masked/disabed or the consumer side (KVM +* int this case doesn't want to receive the interrupts. +*/ + ret =kvm_arch_update_pi_irte (irqfd->kvm, prod->irq, irqfd->gsi,0 ); +WARN_ON (ret); +} + +void kvm_arch_irq_consumer_init (struct irq_bypass_consumer *cons) +{ + cons->add_producer = kvm_arch_irq_bypass_add_producer; + cons->del_producer = kvm_arch_irq_bypass_del_producer; +} +EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_exit);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_inj_virq);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_page_fault);include/linux/kvm_host.h +2
-0@@ -1073,6 +1073,8 @@ extern struct kvm_device_ops kvm_xics_ops;extern struct kvm_device_ops kvm_arm_vgic_v2_ops;extern struct kvm_device_ops kvm_arm_vgic_v3_ops; +void kvm_arch_irq_consumer_init (struct irq_bypass_consumer *cons); +#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop (struct kvm_vcpu *vcpu,bool val)
PATCH v5 15/19 KVM: eventfd: add irq bypass consumer management
In reply to Feng WuFrom: Eric Auger <[email protected]>
This patch adds the registration/unregistration of an irq_bypass_consumer on irqfd assignment/deassignment.
--- virt/kvm/eventfd.c | 7 +++++++ 1 file changed, 7 insertions(+)
virt/kvm/eventfd.c +7 -0
@@ -35,6 +35,7 @@#include <linux/srcu.h> #include <linux/slab.h> #include <linux/seqlock.h> +#include <linux/irqbypass.h> #include <trace/events/kvm.h> #include <kvm/iodev.h>
@@ -140,6 +141,7 @@ irqfd_shutdown(struct work_struct *work)/* * It is now safe to release the object's resources */ +irq_bypass_unregister_consumer (&irqfd->consumer);eventfd_ctx_put (irqfd->eventfd);kfree (irqfd); }
@@ -380,6 +382,11 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)*/ fdput (f); + irqfd->consumer.token = (void *)irqfd->eventfd; +kvm_arch_irq_consumer_init (&irqfd->consumer); + ret =irq_bypass_register_consumer (&irqfd->consumer); +WARN_ON (ret); +return 0 ; fail:
Signature · 1 line
2.1.0
Re: [v5 15/19] KVM: eventfd: add irq bypass consumer management
Hi Feng,
Quoted 32 lines · Feng Wu
From: Eric Auger <[email protected]>
This patch adds the registration/unregistration of an
irq_bypass_consumeron irqfd assignment/deassignment.Signed-off-by Eric Auger <[email protected]>Signed-off-by Feng Wu <[email protected]>--- virt/kvm/eventfd.c | 7 +++++++ 1 file changed, 7 insertions(+)virt/kvm/eventfd.c +2
-0@@ -35,6 +35,7 @@#include <linux/srcu.h> #include <linux/slab.h> #include <linux/seqlock.h> +#include <linux/irqbypass.h> #include <trace/events/kvm.h> #include <kvm/iodev.h> @@ -140,6 +141,7 @@ irqfd_shutdown(struct work_struct *work)/* * It is now safe to release the object's resources */ +irq_bypass_unregister_consumer (&irqfd->consumer);eventfd_ctx_put (irqfd->eventfd);kfree (irqfd); }
virt/kvm/eventfd.c kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) · line 386
Quoted 5 lines
virt/kvm/eventfd.c +2
-0@@ -380,6 +382,11 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)*/ fdput (f); + irqfd->consumer.token = (void *)irqfd->eventfd; +kvm_arch_irq_consumer_init (&irqfd->consumer);
what if the architecture does not implement kvm_arch_irq_consumer_init?
Also you are using here this single function kvm_arch_irq_consumer_init to do some irq bypass manager settings + attaching your irqfd->arch_update cb which does not really relate to IRQ bypass manager. I think I preferred the approach where start/top/add/del were exposed separately ([RFC v2 5/6] KVM: introduce kvm_arch functions for IRQ bypass).
Why not adding another kvm_arch_irq_routing_update then, not necessarily linked to irq bypass manager.
Best Regards
Eric
Quoted 7 lines
virt/kvm/eventfd.c +3
-0+ ret =irq_bypass_register_consumer (&irqfd->consumer); +WARN_ON (ret); +return 0 ; fail:
Paolo Bonzini
maintainerRe: [v5 15/19] KVM: eventfd: add irq bypass consumer management
Quoted 12 lines · Eric Auger
Quoted 3 lines
virt/kvm/eventfd.c kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) · line 386
Quoted 3 lines
virt/kvm/eventfd.c +2
-0+ irqfd->consumer.token = (void *)irqfd->eventfd; +kvm_arch_irq_consumer_init (&irqfd->consumer);what if the architecture does not implement
kvm_arch_irq_consumer_init?Also you are using here this single function
kvm_arch_irq_consumer_initto do some irq bypass manager settings + attaching yourirqfd->arch_updatecb which does not really relate to IRQ bypass manager. I think I preferred the approach where start/top/add/del were exposed separately ([RFC v2 5/6] KVM: introducekvm_archfunctions for IRQ bypass).
Quoted 2 lines
Why not adding another
kvm_arch_irq_routing_updatethen, not necessarily linked to irq bypass manager.
Yes, I also preferred the dummy kvm_arch_* functions to this approach with an init function. You'd have to add dummy init functions anyway for non-ARM, non-x86 architectures.
Paolo
RE: [v5 15/19] KVM: eventfd: add irq bypass consumer management
Quoted 22 lines
-----Original Message-----
From: Paolo Bonzini [mailto:[email protected]]
Sent: Monday, July 13, 2015 9:47 PM
To: Eric Auger; Wu, Feng; [email protected]; [email protected]
Cc: [email protected]; [email protected]
Subject: Re: [v5 15/19] KVM: eventfd: add irq bypass consumer managementQuoted 12 lines · Eric Auger
Quoted 3 lines
virt/kvm/eventfd.c kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) · line 386
Quoted 3 lines
virt/kvm/eventfd.c +2
-0+ irqfd->consumer.token = (void *)irqfd->eventfd; +kvm_arch_irq_consumer_init (&irqfd->consumer);what if the architecture does not implement
kvm_arch_irq_consumer_init?Also you are using here this single function
kvm_arch_irq_consumer_initto do some irq bypass manager settings + attaching yourirqfd->arch_updatecb which does not really relate to IRQ bypass manager. I think I preferred the approach where start/top/add/del were exposed separately ([RFC v2 5/6] KVM: introducekvm_archfunctions for IRQ bypass).
Quoted 6 lines
Quoted 2 lines
Why not adding another
kvm_arch_irq_routing_updatethen, not necessarily linked to irq bypass manager.Yes, I also preferred the dummy kvm_arch_* functions to this approach with an init function. You'd have to add dummy init functions anyway for non-ARM, non-x86 architectures.
I think dummy kvm_arch_* is okay for me. However, my point is that currently 'add_producer ' and 'del_producer ' are mandatory, other callbacks are optional. In patch "[RFC v2 5/6] KVM: introduce kvm_arch functions for IRQ bypass " and "[RFC v2 6/6] KVM: eventfd: add irq bypass consumer management ", it provides all the callbacks, which means we need to implement dummy arch specific functions no matter it is necessary. In that case, seems it is pointless to make some of the callbacks optional. Anyway, if you guys are fine with the dummy approach, I am good! :)
Thanks,
Feng
Quoted 2 lines
Paolo
PATCH v5 16/19 KVM: Add an arch specific hooks in 'struct kvm_kernel_irqfd'
In reply to Feng WuThis patch adds an arch specific hooks 'arch_update' in 'struct kvm_kernel_irqfd'. On Intel side, it is used to update the IRTE when VT-d posted-interrupts is used.
--- arch/x86/kvm/x86.c | 5 +++++ include/linux/kvm_host.h | 3 +++ include/linux/kvm_irqfd.h | 2 ++ virt/kvm/eventfd.c | 13 ++++++++++++- 4 files changed, 22 insertions(+), 1 deletion(-)
arch/x86/kvm/x86.c +5 -0
@@ -8063,6 +8063,11 @@ void kvm_arch_irq_consumer_init(struct irq_bypass_consumer *cons) cons->del_producer = kvm_arch_irq_bypass_del_producer; } +void kvm_arch_irqfd_init (struct kvm_kernel_irqfd *irqfd) +{ + irqfd->arch_update = kvm_arch_update_pi_irte; +} +EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_exit);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_inj_virq);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_page_fault);
include/linux/kvm_host.h +3 -0
@@ -33,6 +33,8 @@#include <asm/kvm_host.h> +struct kvm_kernel_irqfd ; +/* * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used * in kvm, other bits are visible for userspace which are defined in
@@ -1074,6 +1076,7 @@ extern struct kvm_device_ops kvm_arm_vgic_v2_ops;extern struct kvm_device_ops kvm_arm_vgic_v3_ops;void kvm_arch_irq_consumer_init (struct irq_bypass_consumer *cons); +void kvm_arch_irqfd_init (struct kvm_kernel_irqfd *irqfd);#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
include/linux/kvm_irqfd.h +2 -0
@@ -67,6 +67,8 @@ struct kvm_kernel_irqfd {struct work_struct shutdown;struct irq_bypass_consumer consumer;struct irq_bypass_producer *producer; +int (*arch_update)(struct kvm *kvm,unsigned int host_irq, + uint32_t guest_irq, bool set); };#endif /* __LINUX_KVM_IRQFD_H */
virt/kvm/eventfd.c +12 -1
@@ -276,6 +276,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)INIT_LIST_HEAD (&irqfd->list);INIT_WORK (&irqfd->inject, irqfd_inject);INIT_WORK (&irqfd->shutdown, irqfd_shutdown); +kvm_arch_irqfd_init (irqfd);seqcount_init (&irqfd->irq_entry_sc); f =fdget (args->fd);
@@ -562,13 +563,23 @@ kvm_irqfd_release(struct kvm *kvm)*/ void kvm_irq_routing_update (struct kvm *kvm) { +int ret;struct kvm_kernel_irqfd *irqfd;spin_lock_irq (&kvm->irqfds.lock); -list_for_each_entry (irqfd, &kvm->irqfds.items, list) +list_for_each_entry (irqfd, &kvm->irqfds.items, list) {irqfd_update (kvm, irqfd); +if (irqfd->arch_update) { +BUG_ON (!irqfd->producer); + ret = irqfd->arch_update ( + irqfd->kvm, irqfd->producer->irq, + irqfd->gsi,1 ); +WARN_ON (ret); + } + } +spin_unlock_irq (&kvm->irqfds.lock); }
Signature · 1 line
2.1.0
Re: [v5 16/19] KVM: Add an arch specific hooks in 'struct kvm_kernel_irqfd'
Quoted 42 lines · Feng Wu
This patch adds an arch specific hooks '
arch_update' in 'structkvm_kernel_irqfd'. On Intel side, it is used to update the IRTE when VT-d posted-interrupts is used.Signed-off-by Feng Wu <[email protected]>--- arch/x86/kvm/x86.c | 5 +++++ include/linux/kvm_host.h | 3 +++ include/linux/kvm_irqfd.h | 2 ++ virt/kvm/eventfd.c | 13 ++++++++++++- 4 files changed, 22 insertions(+), 1 deletion(-)arch/x86/kvm/x86.c +5
-0@@ -8063,6 +8063,11 @@ void kvm_arch_irq_consumer_init(struct irq_bypass_consumer *cons) cons->del_producer = kvm_arch_irq_bypass_del_producer; } +void kvm_arch_irqfd_init (struct kvm_kernel_irqfd *irqfd) +{ + irqfd->arch_update = kvm_arch_update_pi_irte; +} +EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_exit);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_inj_virq);EXPORT_TRACEPOINT_SYMBOL_GPL (kvm_page_fault);include/linux/kvm_host.h +2
-0@@ -33,6 +33,8 @@#include <asm/kvm_host.h> +struct kvm_kernel_irqfd ; +/* * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used * in kvm, other bits are visible for userspace which are defined in
include/linux/kvm_host.h extern struct kvm_device_ops kvm_arm_vgic_v2_ops; · line 1079
Quoted 4 lines
include/linux/kvm_host.h +1
-0@@ -1074,6 +1076,7 @@ extern struct kvm_device_ops kvm_arm_vgic_v2_ops;extern struct kvm_device_ops kvm_arm_vgic_v3_ops;void kvm_arch_irq_consumer_init (struct irq_bypass_consumer *cons); +void kvm_arch_irqfd_init (struct kvm_kernel_irqfd *irqfd);
need to handle the case this is not implemented by the arch?
include/linux/kvm_irqfd.h struct kvm_kernel_irqfd { · line 71
Quoted 13 lines
include/linux/kvm_host.h +0
-0#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT include/linux/kvm_irqfd.h +2
-0@@ -67,6 +67,8 @@ struct kvm_kernel_irqfd {struct work_struct shutdown;struct irq_bypass_consumer consumer;struct irq_bypass_producer *producer; +int (*arch_update)(struct kvm *kvm,unsigned int host_irq, +uint32_t guest_irq,bool set);
you must document this cb cannot sleep I think
Eric
Quoted 41 lines
include/linux/kvm_irqfd.h +0
-0};#endif /* __LINUX_KVM_IRQFD_H */ virt/kvm/eventfd.c +12
-1@@ -276,6 +276,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)INIT_LIST_HEAD (&irqfd->list);INIT_WORK (&irqfd->inject, irqfd_inject);INIT_WORK (&irqfd->shutdown, irqfd_shutdown); +kvm_arch_irqfd_init (irqfd);seqcount_init (&irqfd->irq_entry_sc); f =fdget (args->fd);@@ -562,13 +563,23 @@ kvm_irqfd_release(struct kvm *kvm)*/ void kvm_irq_routing_update (struct kvm *kvm) { +int ret;struct kvm_kernel_irqfd *irqfd;spin_lock_irq (&kvm->irqfds.lock); -list_for_each_entry (irqfd, &kvm->irqfds.items, list) +list_for_each_entry (irqfd, &kvm->irqfds.items, list) {irqfd_update (kvm, irqfd); +if (irqfd->arch_update) { +BUG_ON (!irqfd->producer); + ret = irqfd->arch_update ( + irqfd->kvm, irqfd->producer->irq, + irqfd->gsi,1 ); +WARN_ON (ret); + } + } +spin_unlock_irq (&kvm->irqfds.lock); }
PATCH v5 17/19 KVM: Update Posted-Interrupts Descriptor when vCPU is preempted
In reply to Feng WuThis patch updates the Posted-Interrupts Descriptor when vCPU is preempted.
sched out:
- Set 'SN' to suppress furture non-urgent interrupts posted for the vCPU.
sched in:
- Clear 'SN'
- Change NDST if vCPU is scheduled to a different CPU
- Set 'NV' to POSTED_INTR_VECTOR
--- arch/x86/kvm/vmx.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+)
arch/x86/kvm/vmx.c +34 -0
@@ -45,6 +45,7 @@#include <asm/debugreg.h> #include <asm/kexec.h> #include <asm/apic.h> +#include <asm/irq_remapping.h> #include "trace.h"
@@ -2000,10 +2001,43 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)vmcs_writel (HOST_IA32_SYSENTER_ESP , sysenter_esp);/* 22.2.3 */ vmx->loaded_vmcs->cpu = cpu; } + +if (irq_remapping_cap (IRQ_POSTING_CAP )) { +struct pi_desc *pi_desc =vcpu_to_pi_desc (vcpu); +struct pi_desc old, new; +unsigned int dest; + +do { + old.control = new.control = pi_desc->control; +if (vcpu->cpu != cpu) { + dest =cpu_physical_id (cpu); + +if (x2apic_enabled ()) + new.ndst = dest; +else + new.ndst = (dest <<8 ) &0xFF00 ; + } + +/* Allow posting non-urgent interrupts */ + new.sn =0 ; + +/* set 'NV' to 'notification vector' */ + new.nv =POSTED_INTR_VECTOR ; + }while (cmpxchg (&pi_desc->control, old.control, + new.control) != old.control); + } }static void vmx_vcpu_put (struct kvm_vcpu *vcpu) { +if (irq_remapping_cap (IRQ_POSTING_CAP )) { +struct pi_desc *pi_desc =vcpu_to_pi_desc (vcpu); + +/* Set SN when the vCPU is preempted */ +if (vcpu->preempted) +pi_set_sn (pi_desc); + } +__vmx_load_host_state (to_vmx (vcpu));if (!vmm_exclusive) {__loaded_vmcs_clear (to_vmx (vcpu)->loaded_vmcs);
Signature · 1 line
2.1.0
PATCH v5 18/19 KVM: Update Posted-Interrupts Descriptor when vCPU is blocked
In reply to Feng WuThis patch updates the Posted-Interrupts Descriptor when vCPU is blocked.
pre-block:
- Add the vCPU to the blocked per-CPU list
- Set 'NV' to POSTED_INTR_WAKEUP_VECTOR
post-block:
- Remove the vCPU from the per-CPU list
--- arch/x86/include/asm/kvm_host.h | 3 + arch/x86/kvm/vmx.c | 158 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 42 ++++++++--- include/linux/kvm_host.h | 3 + virt/kvm/kvm_main.c | 3 + 5 files changed, 199 insertions(+), 10 deletions(-)
arch/x86/include/asm/kvm_host.h +3 -0
@@ -844,6 +844,9 @@ struct kvm_x86_ops {void (*pi_clear_sn)(struct kvm_vcpu *vcpu);void (*pi_set_sn)(struct kvm_vcpu *vcpu); + +int (*pi_pre_block)(struct kvm_vcpu *vcpu); +void (*pi_post_block)(struct kvm_vcpu *vcpu); };struct kvm_arch_async_pf {
arch/x86/kvm/vmx.c +158 -0
194 lines not on this page · raw message
arch/x86/kvm/x86.c +32 -10
68 lines not on this page · raw message
include/linux/kvm_host.h +3 -0
@@ -227,6 +227,9 @@ struct kvm_vcpu {unsigned long requests;unsigned long guest_debug; +int pre_pcpu; +struct list_head blocked_vcpu_list; +struct mutex mutex;struct kvm_run *run;
virt/kvm/kvm_main.c +3 -0
@@ -221,6 +221,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)init_waitqueue_head (&vcpu->wq);kvm_async_pf_vcpu_init (vcpu); + vcpu->pre_pcpu =-1 ; +INIT_LIST_HEAD (&vcpu->blocked_vcpu_list); + page =alloc_page (GFP_KERNEL | __GFP_ZERO);if (!page) { r = -ENOMEM ;
Signature · 1 line
2.1.0
PATCH v5 19/19 KVM: Warn if 'SN' is set during posting interrupts by software
In reply to Feng WuCurrently, we don't support urgent interrupt, all interrupts are recognized as non-urgent interrupt, so we cannot post interrupts when 'SN' is set.
If the vcpu is in guest mode, it cannot have been scheduled out, and that's the only case when SN is set currently, warning if SN is set.
--- arch/x86/kvm/vmx.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
arch/x86/kvm/vmx.c +16 -0
@@ -4484,6 +4484,22 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) {#ifdef CONFIG_SMP if (vcpu->mode ==IN_GUEST_MODE ) { +struct vcpu_vmx *vmx =to_vmx (vcpu); + +/* +* Currently, we don't support urgent interrupt, +* all interrupts are recognized as non-urgent +* interrupt, so we cannot post interrupts when +* 'SN' is set. +* +* If the vcpu is in guest mode, it means it is +* running instead of being scheduled out and +* waiting in the run queue, and that's the only +* case when 'SN' is set currently, warning if +* 'SN' is set. +*/ +WARN_ON_ONCE (pi_test_sn (&vmx->pi_desc)); + apic->send_IPI_mask (get_cpu_mask (vcpu->cpu),POSTED_INTR_VECTOR );return true;
Signature · 1 line
2.1.0
Hi Feng,
Quoted 17 lines · Feng Wu
VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt. With VT-d Posted-Interrupts enabled, external interrupts from direct-assigned devices can be delivered to guests without VMM intervention when guest is running in non-root mode.
You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technology/vt-directed-io-spec.htmlThis series was part of http://thread.gmane.org/gmane.linux.kernel.iommu/7708. To make things clear, send out IOMMU part here.
This patch-set is based on the lastest x86/apic branch of tip tree.
Divide the whole series which contain multiple components into three parts:
- Prerequisite changes to irq subsystem (already merged)
- IOMMU part (already merged)
- KVM and VFIO parts (this series)
Quoted 4 lines
v5:
- Based on Alex and Eric's irq bypass manager:
https://lkml.org/lkml/2015/7/10/663
- Reuse some common patch from Eric
A comment about the overall structure. Previously you prefered to have 2 separate series, one usable by both of us and one with my forwarding stuff. Why did you change your mind?
Best Regards
Eric
Quoted 40 lines
Eric Auger (3):
KVM: createkvm_irqfd.h
KVM: eventfd: add irq bypass information in irqfd
KVM: eventfd: add irq bypass consumer managementFeng Wu (16):
KVM: Extend structpi_descfor VT-d Posted-Interrupts
KVM: Add some helper functions for Posted-Interrupts
KVM: Define a new interfacekvm_intr_is_single_vcpu()
KVM: Get Posted-Interrupts descriptor address from structkvm_vcpu
KVM: Add interfaces to control PI outside vmx
KVM: Make structkvm_irq_routing_tableaccessible
KVM: makekvm_set_msi_irq()public
vfio: SelectIRQ_BYPASS_MANAGERfor vfio PCI devices
vfio: Register/unregisterirq_bypass_producer
KVM, x86: SelectIRQ_BYPASS_MANAGERforKVM_INTEL
KVM: x86: Update IRTE for posted-interrupts
KVM: x86: Add arch specific routines for irqbypass manager
KVM: Add an arch specific hooks in 'structkvm_kernel_irqfd'
KVM: Update Posted-Interrupts Descriptor when vCPU is preempted
KVM: Update Posted-Interrupts Descriptor when vCPU is blocked
KVM: Warn if 'SN' is set during posting interrupts by softwarearch/x86/include/asm/kvm_host.h | 15 ++ arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/irq_comm.c | 28 +++- arch/x86/kvm/vmx.c | 278 +++++++++++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 160 +++++++++++++++++++-- drivers/vfio/pci/Kconfig | 1 + drivers/vfio/pci/vfio_pci_intrs.c | 19 +++ drivers/vfio/pci/vfio_pci_private.h | 2 + include/linux/kvm_host.h | 23 +++ include/linux/kvm_irqfd.h | 74 ++++++++++ virt/kvm/eventfd.c | 115 ++++++--------- virt/kvm/irqchip.c | 11 -- virt/kvm/kvm_main.c | 3 + 13 files changed, 632 insertions(+), 98 deletions(-) create mode 100644 include/linux/kvm_irqfd.h
Quoted 32 lines
-----Original Message-----
From: Eric Auger [mailto:[email protected]]
Sent: Monday, July 13, 2015 9:19 PM
To: Wu, Feng; [email protected]; [email protected]
Cc: [email protected]; [email protected]; [email protected]
Subject: Re: [v5 00/19] Add VT-d Posted-Interrupts supportHi Feng,
Quoted 7 lines · Feng Wu
VT-d Posted-Interrupts is an enhancement to CPU side Posted-Interrupt. With VT-d Posted-Interrupts enabled, external interrupts from direct-assigned devices can be delivered to guests without VMM intervention when guest is running in non-root mode.
You can find the VT-d Posted-Interrtups Spec. in the following URL:
http://www.intel.com/content/www/us/en/intelligent-systems/intel-technolog
y/vt-directed-io-spec.htmlQuoted 2 lines
This series was part of
http://thread.gmane.org/gmane.linux.kernel.iommu/7708. To make things clear, send out IOMMU part here.
Quoted 8 lines
This patch-set is based on the lastest x86/apic branch of tip tree.
Divide the whole series which contain multiple components into three parts:
- Prerequisite changes to irq subsystem (already merged)
- IOMMU part (already merged)
- KVM and VFIO parts (this series)
Quoted 8 lines
Quoted 4 lines
v5:
- Based on Alex and Eric's irq bypass manager:
https://lkml.org/lkml/2015/7/10/663
- Reuse some common patch from EricA comment about the overall structure. Previously you prefered to have 2 separate series, one usable by both of us and one with my forwarding stuff. Why did you change your mind?
I didn't change my mind, since alex sent out the latest irq bypass manger patch, in which, some callbacks are renamed and some are changed to optional, I feel there may need some changes to your patch below:
[RFC v2 0/6] IRQ bypass manager and irqfd consumer
So I integrate it here, sorry for the inconvenience. Could you please send Out a new version of this patch-set, then I can follow it. Thanks a lot!
Thanks,
Feng
Quoted 45 lines
Best Regards
Eric
Quoted 24 lines
Eric Auger (3):
KVM: createkvm_irqfd.h
KVM: eventfd: add irq bypass information in irqfd
KVM: eventfd: add irq bypass consumer managementFeng Wu (16):
KVM: Extend structpi_descfor VT-d Posted-Interrupts
KVM: Add some helper functions for Posted-Interrupts
KVM: Define a new interfacekvm_intr_is_single_vcpu()
KVM: Get Posted-Interrupts descriptor address from structkvm_vcpu
KVM: Add interfaces to control PI outside vmx
KVM: Make structkvm_irq_routing_tableaccessible
KVM: makekvm_set_msi_irq()public
vfio: SelectIRQ_BYPASS_MANAGERfor vfio PCI devices
vfio: Register/unregisterirq_bypass_producer
KVM, x86: SelectIRQ_BYPASS_MANAGERforKVM_INTEL
KVM: x86: Update IRTE for posted-interrupts
KVM: x86: Add arch specific routines for irqbypass manager
KVM: Add an arch specific hooks in 'structkvm_kernel_irqfd'
KVM: Update Posted-Interrupts Descriptor when vCPU is preempted
KVM: Update Posted-Interrupts Descriptor when vCPU is blocked
KVM: Warn if 'SN' is set during posting interrupts by softwareQuoted 4 lines
arch/x86/include/asm/kvm_host.h | 15 ++ arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/irq_comm.c | 28 +++- arch/x86/kvm/vmx.c | 278+++++++++++++++++++++++++++++++++++-
Quoted 12 lines
arch/x86/kvm/x86.c | 160 +++++++++++++++++++-- drivers/vfio/pci/Kconfig | 1 + drivers/vfio/pci/vfio_pci_intrs.c | 19 +++ drivers/vfio/pci/vfio_pci_private.h | 2 + include/linux/kvm_host.h | 23 +++ include/linux/kvm_irqfd.h | 74 ++++++++++ virt/kvm/eventfd.c | 115 ++++++--------- virt/kvm/irqchip.c | 11 -- virt/kvm/kvm_main.c | 3 + 13 files changed, 632 insertions(+), 98 deletions(-) create mode 100644 include/linux/kvm_irqfd.h