All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Woodhouse <dwmw2@infradead.org>
To: kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Joao Martins <joao.m.martins@oracle.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Metin Kaya <metikaya@amazon.co.uk>,
	Paul Durrant <pdurrant@amazon.co.uk>
Subject: [PATCH v0 02/15] KVM: x86/xen: Use gfn_to_pfn_cache for runstate area
Date: Thu, 10 Feb 2022 00:27:08 +0000	[thread overview]
Message-ID: <20220210002721.273608-3-dwmw2@infradead.org> (raw)
In-Reply-To: <20220210002721.273608-1-dwmw2@infradead.org>

From: David Woodhouse <dwmw@amazon.co.uk>

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 arch/x86/include/asm/kvm_host.h |   3 +-
 arch/x86/kvm/x86.c              |   1 +
 arch/x86/kvm/xen.c              | 111 ++++++++++++++++----------------
 arch/x86/kvm/xen.h              |   6 +-
 4 files changed, 62 insertions(+), 59 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6e7c545bc7ee..1e73053fd2bf 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -603,10 +603,9 @@ struct kvm_vcpu_xen {
 	u32 current_runstate;
 	bool vcpu_info_set;
 	bool vcpu_time_info_set;
-	bool runstate_set;
 	struct gfn_to_hva_cache vcpu_info_cache;
 	struct gfn_to_hva_cache vcpu_time_info_cache;
-	struct gfn_to_hva_cache runstate_cache;
+	struct gfn_to_pfn_cache runstate_cache;
 	u64 last_steal;
 	u64 runstate_entry_time;
 	u64 runstate_times[4];
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 74b53a16f38a..5d0191bf30b3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11195,6 +11195,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
 
+	kvm_xen_destroy_vcpu(vcpu);
 	kvm_hv_vcpu_uninit(vcpu);
 	kvm_pmu_destroy(vcpu);
 	kfree(vcpu->arch.mce_banks);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 39b319f428bc..5d40d6521440 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -133,27 +133,37 @@ static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state)
 void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 {
 	struct kvm_vcpu_xen *vx = &v->arch.xen;
-	struct gfn_to_hva_cache *ghc = &vx->runstate_cache;
-	struct kvm_memslots *slots = kvm_memslots(v->kvm);
-	bool atomic = (state == RUNSTATE_runnable);
-	uint64_t state_entry_time;
-	int __user *user_state;
-	uint64_t __user *user_times;
+	struct gfn_to_pfn_cache *gpc = &vx->runstate_cache;
+	uint64_t *user_times;
+	unsigned long flags;
+	size_t user_len;
+	int *user_state;
 
 	kvm_xen_update_runstate(v, state);
 
-	if (!vx->runstate_set)
+	if (!vx->runstate_cache.active)
 		return;
 
-	if (unlikely(slots->generation != ghc->generation || kvm_is_error_hva(ghc->hva)) &&
-	    kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len))
-		return;
+	if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode)
+		user_len = sizeof(struct vcpu_runstate_info);
+	else
+		user_len = sizeof(struct compat_vcpu_runstate_info);
 
-	/* We made sure it fits in a single page */
-	BUG_ON(!ghc->memslot);
+	read_lock_irqsave(&gpc->lock, flags);
+	while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa,
+					   user_len)) {
+		read_unlock_irqrestore(&gpc->lock, flags);
 
-	if (atomic)
-		pagefault_disable();
+		/* When invoked from kvm_sched_out() we cannot sleep */
+		if (state == RUNSTATE_runnable)
+			return;
+
+		if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa,
+						 user_len, false))
+			return;
+
+		read_lock_irqsave(&gpc->lock, flags);
+	}
 
 	/*
 	 * The only difference between 32-bit and 64-bit versions of the
@@ -167,37 +177,32 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	 */
 	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0);
 	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0);
-	user_state = (int __user *)ghc->hva;
-
 	BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c);
-
-	user_times = (uint64_t __user *)(ghc->hva +
-					 offsetof(struct compat_vcpu_runstate_info,
-						  state_entry_time));
 #ifdef CONFIG_X86_64
 	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) !=
 		     offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4);
 	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) !=
 		     offsetof(struct compat_vcpu_runstate_info, time) + 4);
-
-	if (v->kvm->arch.xen.long_mode)
-		user_times = (uint64_t __user *)(ghc->hva +
-						 offsetof(struct vcpu_runstate_info,
-							  state_entry_time));
 #endif
+
+	user_state = gpc->khva;
+
+	if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode)
+		user_times = gpc->khva + offsetof(struct vcpu_runstate_info,
+						  state_entry_time);
+	else
+		user_times = gpc->khva + offsetof(struct compat_vcpu_runstate_info,
+						  state_entry_time);
+
 	/*
 	 * First write the updated state_entry_time to the guest area.
 	 */
-	state_entry_time = vx->runstate_entry_time;
-	state_entry_time |= XEN_RUNSTATE_UPDATE;
-
 	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
-		     sizeof(state_entry_time));
+		     sizeof(user_times[0]));
 	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
-		     sizeof(state_entry_time));
+		     sizeof(user_times[0]));
 
-	if (__put_user(state_entry_time, user_times))
-		goto out;
+	user_times[0] = vx->runstate_entry_time | XEN_RUNSTATE_UPDATE;
 	smp_wmb();
 
 	/*
@@ -209,8 +214,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
 
-	if (__put_user(vx->current_runstate, user_state))
-		goto out;
+	*user_state = vx->current_runstate;
 
 	/*
 	 * Write the actual runstate times immediately after the
@@ -225,23 +229,19 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
 		     sizeof(vx->runstate_times));
 
-	if (__copy_to_user(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times)))
-		goto out;
+	memcpy(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times));
 	smp_wmb();
 
 	/*
 	 * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's
 	 * runstate_entry_time field.
 	 */
-	state_entry_time &= ~XEN_RUNSTATE_UPDATE;
-	__put_user(state_entry_time, user_times);
+	user_times[0] &= ~XEN_RUNSTATE_UPDATE;
 	smp_wmb();
 
- out:
-	mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT);
+	read_unlock_irqrestore(&gpc->lock, flags);
 
-	if (atomic)
-		pagefault_enable();
+	mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
 }
 
 int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
@@ -504,24 +504,17 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 			break;
 		}
 		if (data->u.gpa == GPA_INVALID) {
-			vcpu->arch.xen.runstate_set = false;
+			kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
+						     &vcpu->arch.xen.runstate_cache);
 			r = 0;
 			break;
 		}
 
-		/* It must fit within a single page */
-		if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_runstate_info) > PAGE_SIZE) {
-			r = -EINVAL;
-			break;
-		}
-
-		r = kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
 					      &vcpu->arch.xen.runstate_cache,
-					      data->u.gpa,
-					      sizeof(struct vcpu_runstate_info));
-		if (!r) {
-			vcpu->arch.xen.runstate_set = true;
-		}
+					      NULL, false, true, data->u.gpa,
+					      sizeof(struct vcpu_runstate_info),
+					      false);
 		break;
 
 	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
@@ -656,7 +649,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 			r = -EOPNOTSUPP;
 			break;
 		}
-		if (vcpu->arch.xen.runstate_set) {
+		if (vcpu->arch.xen.runstate_cache.active) {
 			data->u.gpa = vcpu->arch.xen.runstate_cache.gpa;
 			r = 0;
 		}
@@ -1054,3 +1047,9 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
 
 	return 0;
 }
+
+void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
+{
+	kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
+				     &vcpu->arch.xen.runstate_cache);
+}
diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index adbcc9ed59db..54b2bf4c3001 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -23,7 +23,7 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data);
 int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc);
 void kvm_xen_init_vm(struct kvm *kvm);
 void kvm_xen_destroy_vm(struct kvm *kvm);
-
+void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu);
 int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e,
 			    struct kvm *kvm);
 int kvm_xen_setup_evtchn(struct kvm *kvm,
@@ -65,6 +65,10 @@ static inline void kvm_xen_destroy_vm(struct kvm *kvm)
 {
 }
 
+static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
+{
+}
+
 static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
 {
 	return false;
-- 
2.33.1


  parent reply	other threads:[~2022-02-10  2:09 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-10  0:27 [PATCH v0 00/15] KVM: Add Xen event channel acceleration David Woodhouse
2022-02-10  0:27 ` [PATCH v0 01/15] KVM: x86/xen: Fix runstate updates to be atomic when preempting vCPU David Woodhouse
2022-02-10  0:27 ` David Woodhouse [this message]
2022-02-18 19:57   ` [PATCH v0 02/15] KVM: x86/xen: Use gfn_to_pfn_cache for runstate area Sean Christopherson
2022-02-18 21:45     ` David Woodhouse
2022-02-10  0:27 ` [PATCH v0 03/15] KVM: x86: Use gfn_to_pfn_cache for pv_time David Woodhouse
2022-02-10  0:27 ` [PATCH v0 04/15] KVM: x86/xen: Use gfn_to_pfn_cache for vcpu_info David Woodhouse
2022-02-10  0:27 ` [PATCH v0 05/15] KVM: x86/xen: Use gfn_to_pfn_cache for vcpu_time_info David Woodhouse
2022-02-10  0:27 ` [PATCH v0 06/15] KVM: x86/xen: Make kvm_xen_set_evtchn() reusable from other places David Woodhouse
2022-02-10  0:27 ` [PATCH v0 07/15] KVM: x86/xen: Support direct injection of event channel events David Woodhouse
2022-02-10  0:27 ` [PATCH v0 08/15] KVM: x86/xen: intercept EVTCHNOP_send from guests David Woodhouse
2022-02-10  0:27 ` [PATCH v0 09/15] KVM: x86/xen: handle PV IPI vcpu yield David Woodhouse
2022-02-10  0:27 ` [PATCH v0 10/15] KVM: x86/xen: Add KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID David Woodhouse
2022-02-10  0:27 ` [PATCH v0 11/15] KVM: x86/xen: handle PV timers oneshot mode David Woodhouse
2022-02-10  0:27 ` [PATCH v0 12/15] KVM: x86/xen: Kernel acceleration for XENVER_version David Woodhouse
2022-02-10  0:27 ` [PATCH v0 13/15] KVM: x86/xen: Support per-vCPU event channel upcall via local APIC David Woodhouse
2022-02-10  0:27 ` [PATCH v0 14/15] KVM: x86/xen: Advertise and document KVM_XEN_HVM_CONFIG_EVTCHN_SEND David Woodhouse
2022-02-10  0:27 ` [PATCH v0 15/15] KVM: x86/xen: handle PV spinlocks slowpath David Woodhouse

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220210002721.273608-3-dwmw2@infradead.org \
    --to=dwmw2@infradead.org \
    --cc=boris.ostrovsky@oracle.com \
    --cc=jmattson@google.com \
    --cc=joao.m.martins@oracle.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=metikaya@amazon.co.uk \
    --cc=pbonzini@redhat.com \
    --cc=pdurrant@amazon.co.uk \
    --cc=seanjc@google.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.