KVM: x86/xen: Add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery (14243b38) · Commits · EulixOS / Software / Kernel

Documentation/virt/kvm/api.rst

+21 −0

Original line number	Diff line number	Diff line
		@@ -1799,6 +1799,7 @@ No flags are specified so far, the corresponding field must be set to zero.
		struct kvm_irq_routing_msi msi;
		struct kvm_irq_routing_s390_adapter adapter;
		struct kvm_irq_routing_hv_sint hv_sint;
		struct kvm_irq_routing_xen_evtchn xen_evtchn;
		__u32 pad[8];
		} u;
		};
		@@ -1808,6 +1809,7 @@ No flags are specified so far, the corresponding field must be set to zero.
		#define KVM_IRQ_ROUTING_MSI 2
		#define KVM_IRQ_ROUTING_S390_ADAPTER 3
		#define KVM_IRQ_ROUTING_HV_SINT 4
		#define KVM_IRQ_ROUTING_XEN_EVTCHN 5

		flags:

		@@ -1859,6 +1861,20 @@ address_hi must be zero.
		__u32 sint;
		};

		struct kvm_irq_routing_xen_evtchn {
		__u32 port;
		__u32 vcpu;
		__u32 priority;
		};


		When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL bit
		in its indication of supported features, routing to Xen event channels
		is supported. Although the priority field is present, only the value
		KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported, which means delivery by
		2 level event channels. FIFO event channel support may be added in
		the future.


		4.55 KVM_SET_TSC_KHZ
		--------------------
		@@ -7413,6 +7429,7 @@ PVHVM guests. Valid flags are::
		#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
		#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
		#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 2)
		#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 3)

		The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
		ioctl is available, for the guest to set its hypercall page.
		@@ -7432,6 +7449,10 @@ The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related
		features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are
		supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls.

		The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries
		of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority
		field set to indicate 2 level event channel delivery.

		8.31 KVM_CAP_PPC_MULTITCE
		-------------------------

arch/x86/include/asm/kvm_host.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -610,6 +610,7 @@ struct kvm_vcpu_xen {
		u64 last_steal;
		u64 runstate_entry_time;
		u64 runstate_times[4];
		unsigned long evtchn_pending_sel;
		};

		struct kvm_vcpu_arch {

arch/x86/kvm/irq_comm.c

+12 −0

Original line number	Diff line number	Diff line
		@@ -24,6 +24,7 @@

		#include "hyperv.h"
		#include "x86.h"
		#include "xen.h"

		static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
		struct kvm *kvm, int irq_source_id, int level,
		@@ -175,6 +176,13 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
		return r;
		break;

		#ifdef CONFIG_KVM_XEN
		case KVM_IRQ_ROUTING_XEN_EVTCHN:
		if (!level)
		return -1;

		return kvm_xen_set_evtchn_fast(e, kvm);
		#endif
		default:
		break;
		}
		@@ -310,6 +318,10 @@ int kvm_set_routing_entry(struct kvm *kvm,
		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
		e->hv_sint.sint = ue->u.hv_sint.sint;
		break;
		#ifdef CONFIG_KVM_XEN
		case KVM_IRQ_ROUTING_XEN_EVTCHN:
		return kvm_xen_setup_evtchn(kvm, e, ue);
		#endif
		default:
		return -EINVAL;
		}

arch/x86/kvm/x86.c

+2 −1

Original line number	Diff line number	Diff line
		@@ -4188,7 +4188,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
		case KVM_CAP_XEN_HVM:
		r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR \|
		KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL \|
		KVM_XEN_HVM_CONFIG_SHARED_INFO;
		KVM_XEN_HVM_CONFIG_SHARED_INFO \|
		KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL;
		if (sched_info_on())
		r \|= KVM_XEN_HVM_CONFIG_RUNSTATE;
		break;

arch/x86/kvm/xen.c

+257 −5

Original line number	Diff line number	Diff line
		@@ -16,6 +16,7 @@
		#include <trace/events/kvm.h>
		#include <xen/interface/xen.h>
		#include <xen/interface/vcpu.h>
		#include <xen/interface/event_channel.h>

		#include "trace.h"

		@@ -195,6 +196,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)

		int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
		{
		unsigned long evtchn_pending_sel = READ_ONCE(v->arch.xen.evtchn_pending_sel);
		bool atomic = in_atomic() \|\| !task_is_running(current);
		int err;
		u8 rc = 0;

		@@ -204,6 +207,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
		*/
		struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache;
		struct kvm_memslots *slots = kvm_memslots(v->kvm);
		bool ghc_valid = slots->generation == ghc->generation &&
		!kvm_is_error_hva(ghc->hva) && ghc->memslot;

		unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending);

		/* No need for compat handling here */
		@@ -219,8 +225,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
		* cache in kvm_read_guest_offset_cached(), but just uses
		* __get_user() instead. And falls back to the slow path.
		*/
		if (likely(slots->generation == ghc->generation &&
		!kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
		if (!evtchn_pending_sel && ghc_valid) {
		/* Fast path */
		pagefault_disable();
		err = __get_user(rc, (u8 __user *)ghc->hva + offset);
		@@ -239,11 +244,82 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
		* and we'll end up getting called again from a context where we can
		* fault in the page and wait for it.
		*/
		if (in_atomic() \|\| !task_is_running(current))
		if (atomic)
		return 1;

		kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
		sizeof(rc));
		if (!ghc_valid) {
		err = kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len);
		if (err \|\| !ghc->memslot) {
		/*
		* If this failed, userspace has screwed up the
		* vcpu_info mapping. No interrupts for you.
		*/
		return 0;
		}
		}

		/*
		* Now we have a valid (protected by srcu) userspace HVA in
		* ghc->hva which points to the struct vcpu_info. If there
		* are any bits in the in-kernel evtchn_pending_sel then
		* we need to write those to the guest vcpu_info and set
		* its evtchn_upcall_pending flag. If there aren't any bits
		* to add, we only want to check evtchn_upcall_pending.
		*/
		if (evtchn_pending_sel) {
		bool long_mode = v->kvm->arch.xen.long_mode;

		if (!user_access_begin((void __user *)ghc->hva, sizeof(struct vcpu_info)))
		return 0;

		if (IS_ENABLED(CONFIG_64BIT) && long_mode) {
		struct vcpu_info __user vi = (void __user )ghc->hva;

		/* Attempt to set the evtchn_pending_sel bits in the
		* guest, and if that succeeds then clear the same
		* bits in the in-kernel version. */
		asm volatile("1:\t" LOCK_PREFIX "orq %0, %1\n"
		"\tnotq %0\n"
		"\t" LOCK_PREFIX "andq %0, %2\n"
		"2:\n"
		"\t.section .fixup,\"ax\"\n"
		"3:\tjmp\t2b\n"
		"\t.previous\n"
		_ASM_EXTABLE_UA(1b, 3b)
		: "=r" (evtchn_pending_sel),
		"+m" (vi->evtchn_pending_sel),
		"+m" (v->arch.xen.evtchn_pending_sel)
		: "0" (evtchn_pending_sel));
		} else {
		struct compat_vcpu_info __user vi = (void __user )ghc->hva;
		u32 evtchn_pending_sel32 = evtchn_pending_sel;

		/* Attempt to set the evtchn_pending_sel bits in the
		* guest, and if that succeeds then clear the same
		* bits in the in-kernel version. */
		asm volatile("1:\t" LOCK_PREFIX "orl %0, %1\n"
		"\tnotl %0\n"
		"\t" LOCK_PREFIX "andl %0, %2\n"
		"2:\n"
		"\t.section .fixup,\"ax\"\n"
		"3:\tjmp\t2b\n"
		"\t.previous\n"
		_ASM_EXTABLE_UA(1b, 3b)
		: "=r" (evtchn_pending_sel32),
		"+m" (vi->evtchn_pending_sel),
		"+m" (v->arch.xen.evtchn_pending_sel)
		: "0" (evtchn_pending_sel32));
		}
		rc = 1;
		unsafe_put_user(rc, (u8 __user *)ghc->hva + offset, err);

		err:
		user_access_end();

		mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT);
		} else {
		__get_user(rc, (u8 __user *)ghc->hva + offset);
		}

		return rc;
		}
		@@ -740,3 +816,179 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)

		return 0;
		}

		static inline int max_evtchn_port(struct kvm *kvm)
		{
		if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
		return EVTCHN_2L_NR_CHANNELS;
		else
		return COMPAT_EVTCHN_2L_NR_CHANNELS;
		}

		/*
		* This follows the kvm_set_irq() API, so it returns:
		* < 0 Interrupt was ignored (masked or not delivered for other reasons)
		* = 0 Interrupt was coalesced (previous irq is still pending)
		* > 0 Number of CPUs interrupt was delivered to
		*/
		int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
		struct kvm *kvm)
		{
		struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
		struct kvm_vcpu *vcpu;
		unsigned long pending_bits, mask_bits;
		unsigned long flags;
		int port_word_bit;
		bool kick_vcpu = false;
		int idx;
		int rc;

		vcpu = kvm_get_vcpu_by_id(kvm, e->xen_evtchn.vcpu);
		if (!vcpu)
		return -1;

		if (!vcpu->arch.xen.vcpu_info_set)
		return -1;

		if (e->xen_evtchn.port >= max_evtchn_port(kvm))
		return -1;

		rc = -EWOULDBLOCK;
		read_lock_irqsave(&gpc->lock, flags);

		idx = srcu_read_lock(&kvm->srcu);
		if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, PAGE_SIZE))
		goto out_rcu;

		if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) {
		struct shared_info *shinfo = gpc->khva;
		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
		mask_bits = (unsigned long *)&shinfo->evtchn_mask;
		port_word_bit = e->xen_evtchn.port / 64;
		} else {
		struct compat_shared_info *shinfo = gpc->khva;
		pending_bits = (unsigned long *)&shinfo->evtchn_pending;
		mask_bits = (unsigned long *)&shinfo->evtchn_mask;
		port_word_bit = e->xen_evtchn.port / 32;
		}

		/*
		* If this port wasn't already set, and if it isn't masked, then
		* we try to set the corresponding bit in the in-kernel shadow of
		* evtchn_pending_sel for the target vCPU. And if that wasn't
		* already set, then we kick the vCPU in question to write to the
		* real evtchn_pending_sel in its own guest vcpu_info struct.
		*/
		if (test_and_set_bit(e->xen_evtchn.port, pending_bits)) {
		rc = 0; /* It was already raised */
		} else if (test_bit(e->xen_evtchn.port, mask_bits)) {
		rc = -1; /* Masked */
		} else {
		rc = 1; /* Delivered. But was the vCPU waking already? */
		if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel))
		kick_vcpu = true;
		}

		out_rcu:
		srcu_read_unlock(&kvm->srcu, idx);
		read_unlock_irqrestore(&gpc->lock, flags);

		if (kick_vcpu) {
		kvm_make_request(KVM_REQ_EVENT, vcpu);
		kvm_vcpu_kick(vcpu);
		}

		return rc;
		}

		/* This is the version called from kvm_set_irq() as the .set function */
		static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry e, struct kvm kvm,
		int irq_source_id, int level, bool line_status)
		{
		bool mm_borrowed = false;
		int rc;

		if (!level)
		return -1;

		rc = kvm_xen_set_evtchn_fast(e, kvm);
		if (rc != -EWOULDBLOCK)
		return rc;

		if (current->mm != kvm->mm) {
		/*
		* If not on a thread which already belongs to this KVM,
		* we'd better be in the irqfd workqueue.
		*/
		if (WARN_ON_ONCE(current->mm))
		return -EINVAL;

		kthread_use_mm(kvm->mm);
		mm_borrowed = true;
		}

		/*
		* For the irqfd workqueue, using the main kvm->lock mutex is
		* fine since this function is invoked from kvm_set_irq() with
		* no other lock held, no srcu. In future if it will be called
		* directly from a vCPU thread (e.g. on hypercall for an IPI)
		* then it may need to switch to using a leaf-node mutex for
		* serializing the shared_info mapping.
		*/
		mutex_lock(&kvm->lock);

		/*
		* It is theoretically possible for the page to be unmapped
		* and the MMU notifier to invalidate the shared_info before
		* we even get to use it. In that case, this looks like an
		* infinite loop. It was tempting to do it via the userspace
		* HVA instead... but that just hides the fact that it's
		* an infinite loop, because if a fault occurs and it waits
		* for the page to come back, it can still immediately
		* fault and have to wait again, repeatedly.
		*
		* Conversely, the page could also have been reinstated by
		* another thread before we even obtain the mutex above, so
		* check again first before remapping it.
		*/
		do {
		struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache;
		int idx;

		rc = kvm_xen_set_evtchn_fast(e, kvm);
		if (rc != -EWOULDBLOCK)
		break;

		idx = srcu_read_lock(&kvm->srcu);
		rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa,
		PAGE_SIZE, false);
		srcu_read_unlock(&kvm->srcu, idx);
		} while(!rc);

		mutex_unlock(&kvm->lock);

		if (mm_borrowed)
		kthread_unuse_mm(kvm->mm);

		return rc;
		}

		int kvm_xen_setup_evtchn(struct kvm *kvm,
		struct kvm_kernel_irq_routing_entry *e,
		const struct kvm_irq_routing_entry *ue)

		{
		if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
		return -EINVAL;

		/* We only support 2 level event channels for now */
		if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
		return -EINVAL;

		e->xen_evtchn.port = ue->u.xen_evtchn.port;
		e->xen_evtchn.vcpu = ue->u.xen_evtchn.vcpu;
		e->xen_evtchn.priority = ue->u.xen_evtchn.priority;
		e->set = evtchn_set_fn;

		return 0;
		}