LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Joao Martins <joao.m.martins@oracle.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: "Ankur Arora" <ankur.a.arora@oracle.com>,
	"Boris Ostrovsky" <boris.ostrovsky@oracle.com>,
	"Joao Martins" <joao.m.martins@oracle.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Radim Krčmář" <rkrcmar@redhat.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Ingo Molnar" <mingo@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"H. Peter Anvin" <hpa@zytor.com>,
	x86@kernel.org
Subject: [PATCH RFC 15/39] KVM: x86/xen: handle PV spinlocks slowpath
Date: Wed, 20 Feb 2019 20:15:45 +0000	[thread overview]
Message-ID: <20190220201609.28290-16-joao.m.martins@oracle.com> (raw)
In-Reply-To: <20190220201609.28290-1-joao.m.martins@oracle.com>

From: Boris Ostrovsky <boris.ostrovsky@oracle.com>

Add support for SCHEDOP_poll hypercall.

This implementation is optimized for polling for a single channel, which
is what Linux does. Polling for multiple channels is not especially
efficient (and has not been tested).

PV spinlocks slow path uses this hypercall, and explicitly crash if it's
not supported.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/include/asm/kvm_host.h |   3 ++
 arch/x86/kvm/xen.c              | 108 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 111 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7fcc81dbb688..c629fedb2e21 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -554,6 +554,8 @@ struct kvm_vcpu_xen {
 	unsigned int virq_to_port[KVM_XEN_NR_VIRQS];
 	struct hrtimer timer;
 	atomic_t timer_pending;
+	wait_queue_head_t sched_waitq;
+	int poll_evtchn;
 };
 
 struct kvm_vcpu_arch {
@@ -865,6 +867,7 @@ struct kvm_xen {
 	struct shared_info *shinfo;
 
 	struct idr port_to_evt;
+	unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 	struct mutex xen_lock;
 };
 
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 753a6d2c11cd..07066402737d 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -563,6 +563,16 @@ static int kvm_xen_evtchn_set_pending(struct kvm_vcpu *svcpu,
 					     evfd->port);
 }
 
+static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port)
+{
+	struct kvm_vcpu_xen *vcpu_xen = vcpu_to_xen_vcpu(vcpu);
+
+	if ((vcpu_xen->poll_evtchn == port ||
+	     vcpu_xen->poll_evtchn == -1) &&
+	    test_and_clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.xen.poll_mask))
+		wake_up(&vcpu_xen->sched_waitq);
+}
+
 static int kvm_xen_evtchn_send(struct kvm_vcpu *vcpu, int port)
 {
 	struct eventfd_ctx *eventfd;
@@ -581,6 +591,8 @@ static int kvm_xen_evtchn_send(struct kvm_vcpu *vcpu, int port)
 			eventfd_signal(eventfd, 1);
 	}
 
+	kvm_xen_check_poller(kvm_get_vcpu(vcpu->kvm, evtchnfd->vcpu), port);
+
 	return 0;
 }
 
@@ -669,6 +681,94 @@ static int kvm_xen_hcall_set_timer_op(struct kvm_vcpu *vcpu, uint64_t timeout)
 	return 0;
 }
 
+static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports,
+			       evtchn_port_t *ports)
+{
+	int i;
+	struct shared_info *shared_info =
+		(struct shared_info *)vcpu->kvm->arch.xen.shinfo;
+
+	for (i = 0; i < nr_ports; i++)
+		if (test_bit(ports[i],
+			     (unsigned long *)shared_info->evtchn_pending))
+			return true;
+
+	return false;
+}
+
+static int kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, gpa_t gpa)
+{
+	struct kvm_vcpu_xen *vcpu_xen = vcpu_to_xen_vcpu(vcpu);
+	int idx, i;
+	struct sched_poll sched_poll;
+	evtchn_port_t port, *ports;
+	struct shared_info *shared_info;
+	struct evtchnfd *evtchnfd;
+	int ret = 0;
+
+	if (kvm_vcpu_read_guest(vcpu, gpa,
+				&sched_poll, sizeof(sched_poll)))
+		return -EFAULT;
+
+	shared_info = (struct shared_info *)vcpu->kvm->arch.xen.shinfo;
+
+	if (unlikely(sched_poll.nr_ports > 1)) {
+		/* Xen (unofficially) limits number of pollers to 128 */
+		if (sched_poll.nr_ports > 128)
+			return -EINVAL;
+
+		ports = kmalloc_array(sched_poll.nr_ports,
+				      sizeof(*ports), GFP_KERNEL);
+		if (!ports)
+			return -ENOMEM;
+	} else
+		ports = &port;
+
+	set_bit(vcpu->vcpu_id, vcpu->kvm->arch.xen.poll_mask);
+
+	for (i = 0; i < sched_poll.nr_ports; i++) {
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		gpa = kvm_mmu_gva_to_gpa_system(vcpu,
+						(gva_t)(sched_poll.ports + i),
+						NULL);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+		if (!gpa || kvm_vcpu_read_guest(vcpu, gpa,
+						&ports[i], sizeof(port))) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		evtchnfd = idr_find(&vcpu->kvm->arch.xen.port_to_evt,
+				    ports[i]);
+		if (!evtchnfd) {
+			ret = -ENOENT;
+			goto out;
+		}
+	}
+
+	if (sched_poll.nr_ports == 1)
+		vcpu_xen->poll_evtchn = port;
+	else
+		vcpu_xen->poll_evtchn = -1;
+
+	if (!wait_pending_event(vcpu, sched_poll.nr_ports, ports))
+		wait_event_interruptible_timeout(
+			 vcpu_xen->sched_waitq,
+			 wait_pending_event(vcpu, sched_poll.nr_ports, ports),
+			 sched_poll.timeout ?: KTIME_MAX);
+
+	vcpu_xen->poll_evtchn = 0;
+
+out:
+	/* Really, this is only needed in case of timeout */
+	clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.xen.poll_mask);
+
+	if (unlikely(sched_poll.nr_ports > 1))
+		kfree(ports);
+	return ret;
+}
+
 static int kvm_xen_hcall_sched_op(struct kvm_vcpu *vcpu, int cmd, u64 param)
 {
 	int ret = -ENOSYS;
@@ -687,6 +787,9 @@ static int kvm_xen_hcall_sched_op(struct kvm_vcpu *vcpu, int cmd, u64 param)
 		kvm_vcpu_on_spin(vcpu, true);
 		ret = 0;
 		break;
+	case SCHEDOP_poll:
+		ret = kvm_xen_schedop_poll(vcpu, gpa);
+		break;
 	default:
 		break;
 	}
@@ -744,6 +847,9 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 		r = kvm_xen_hcall_sched_op(vcpu, params[0], params[1]);
 		if (!r)
 			goto hcall_success;
+		else if (params[0] == SCHEDOP_poll)
+			/* SCHEDOP_poll should be handled in kernel */
+			return r;
 		break;
 	/* fallthrough */
 	default:
@@ -770,6 +876,8 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 
 void kvm_xen_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	init_waitqueue_head(&vcpu->arch.xen.sched_waitq);
+	vcpu->arch.xen.poll_evtchn = 0;
 }
 
 void kvm_xen_vcpu_uninit(struct kvm_vcpu *vcpu)
-- 
2.11.0


  parent reply	other threads:[~2019-02-20 20:18 UTC|newest]

Thread overview: 126+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-20 20:15 [PATCH RFC 00/39] x86/KVM: Xen HVM guest support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 01/39] KVM: x86: fix Xen hypercall page msr handling Joao Martins
2019-02-22  1:30   ` Sean Christopherson
2019-02-22 11:47     ` Joao Martins
2019-02-22 12:51     ` Paolo Bonzini
2020-11-30 10:39       ` David Woodhouse
2020-11-30 11:03         ` Paolo Bonzini
2020-11-30 11:27           ` David Woodhouse
2019-02-20 20:15 ` [PATCH RFC 02/39] KVM: x86/xen: intercept xen hypercalls if enabled Joao Martins
2019-02-21 18:29   ` Sean Christopherson
2019-02-21 20:56     ` Joao Martins
2019-02-22  0:30       ` Sean Christopherson
2019-02-22 12:50         ` Paolo Bonzini
2020-12-01  9:48   ` David Woodhouse
2020-12-01 11:19     ` David Woodhouse
2020-12-02 11:17       ` Joao Martins
2020-12-02 12:12         ` David Woodhouse
2020-12-02  5:19     ` Ankur Arora
2020-12-02  8:03       ` David Woodhouse
2020-12-02 18:20         ` Ankur Arora
2019-02-20 20:15 ` [PATCH RFC 03/39] KVM: x86/xen: register shared_info page Joao Martins
2020-12-01 13:07   ` David Woodhouse
2020-12-02  0:40     ` Ankur Arora
2020-12-02  1:26       ` David Woodhouse
2020-12-02  5:17         ` Ankur Arora
2020-12-02 10:50           ` Joao Martins
2020-12-02 10:44       ` Joao Martins
2020-12-02 12:20         ` David Woodhouse
2020-12-02 20:32           ` Ankur Arora
2020-12-03 10:16             ` David Woodhouse
2020-12-04 17:30               ` Sean Christopherson
2020-12-02 20:33         ` Ankur Arora
2020-12-12 12:07       ` David Woodhouse
2019-02-20 20:15 ` [PATCH RFC 04/39] KVM: x86/xen: setup pvclock updates Joao Martins
2019-02-20 20:15 ` [PATCH RFC 05/39] KVM: x86/xen: update wallclock region Joao Martins
2019-02-20 20:15 ` [PATCH RFC 06/39] KVM: x86/xen: register vcpu info Joao Martins
2019-02-20 20:15 ` [PATCH RFC 07/39] KVM: x86/xen: register vcpu time info region Joao Martins
2019-02-20 20:15 ` [PATCH RFC 08/39] KVM: x86/xen: register steal clock Joao Martins
2019-02-20 20:15 ` [PATCH RFC 09/39] KVM: x86: declare Xen HVM guest capability Joao Martins
2019-02-20 20:15 ` [PATCH RFC 10/39] KVM: x86/xen: support upcall vector Joao Martins
2020-12-02 11:17   ` David Woodhouse
2020-12-02 13:12     ` Joao Martins
2020-12-02 16:47       ` David Woodhouse
2020-12-02 18:34         ` Joao Martins
2020-12-02 19:02           ` David Woodhouse
2020-12-02 20:12             ` Joao Martins
2020-12-02 20:37               ` David Woodhouse
2020-12-03  1:08             ` Ankur Arora
2020-12-08 16:08             ` David Woodhouse
2020-12-09  6:35               ` Ankur Arora
2020-12-09 10:27                 ` David Woodhouse
2020-12-09 10:51                   ` Joao Martins
2020-12-09 11:39                     ` David Woodhouse
2020-12-09 13:26                       ` Joao Martins
2020-12-09 15:41                         ` David Woodhouse
2020-12-09 16:12                           ` Joao Martins
2021-01-01 14:33           ` David Woodhouse
2021-01-05 12:11             ` Joao Martins
2021-01-05 13:23               ` David Woodhouse
2019-02-20 20:15 ` [PATCH RFC 11/39] KVM: x86/xen: evtchn signaling via eventfd Joao Martins
2020-11-30  9:41   ` David Woodhouse
2020-11-30 12:17     ` Joao Martins
2020-11-30 12:55       ` David Woodhouse
2020-11-30 15:08         ` Joao Martins
2020-11-30 16:48           ` David Woodhouse
2020-11-30 17:15             ` Joao Martins
2020-11-30 18:01               ` David Woodhouse
2020-11-30 18:41                 ` Joao Martins
2020-11-30 19:04                   ` David Woodhouse
2020-11-30 19:25                     ` Joao Martins
2021-11-23 13:15           ` David Woodhouse
2019-02-20 20:15 ` [PATCH RFC 12/39] KVM: x86/xen: store virq when assigning evtchn Joao Martins
     [not found]   ` <b750291466f3c89e0a393e48079c087704b217a5.camel@amazon.co.uk>
2022-02-10 12:17     ` Joao Martins
2022-02-10 15:23       ` [EXTERNAL] " David Woodhouse
2019-02-20 20:15 ` [PATCH RFC 13/39] KVM: x86/xen: handle PV timers oneshot mode Joao Martins
2019-02-20 20:15 ` [PATCH RFC 14/39] KVM: x86/xen: handle PV IPI vcpu yield Joao Martins
2019-02-20 20:15 ` Joao Martins [this message]
2022-02-08 12:36   ` [PATCH RFC 15/39] KVM: x86/xen: handle PV spinlocks slowpath David Woodhouse
2022-02-10 12:17     ` Joao Martins
2022-02-10 14:11       ` David Woodhouse
2019-02-20 20:15 ` [PATCH RFC 16/39] KVM: x86: declare Xen HVM evtchn offload capability Joao Martins
2019-02-20 20:15 ` [PATCH RFC 17/39] x86/xen: export vcpu_info and shared_info Joao Martins
2019-02-20 20:15 ` [PATCH RFC 18/39] x86/xen: make hypercall_page generic Joao Martins
2019-02-20 20:15 ` [PATCH RFC 19/39] xen/xenbus: xenbus uninit support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 20/39] xen-blkback: module_exit support Joao Martins
2019-02-25 18:57   ` Konrad Rzeszutek Wilk
2019-02-26 11:20     ` Joao Martins
2019-02-20 20:15 ` [PATCH RFC 21/39] KVM: x86/xen: domid allocation Joao Martins
2019-02-20 20:15 ` [PATCH RFC 22/39] KVM: x86/xen: grant table init Joao Martins
2019-02-20 20:15 ` [PATCH RFC 23/39] KVM: x86/xen: grant table grow support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 24/39] KVM: x86/xen: backend hypercall support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 25/39] KVM: x86/xen: grant map support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 26/39] KVM: x86/xen: grant unmap support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 27/39] KVM: x86/xen: grant copy support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 28/39] KVM: x86/xen: interdomain evtchn support Joao Martins
2019-02-20 20:15 ` [PATCH RFC 29/39] KVM: x86/xen: evtchn unmask support Joao Martins
2019-02-20 20:16 ` [PATCH RFC 30/39] KVM: x86/xen: add additional evtchn ops Joao Martins
2019-02-20 20:16 ` [PATCH RFC 31/39] xen-shim: introduce shim domain driver Joao Martins
2019-02-20 20:16 ` [PATCH RFC 32/39] xen/balloon: xen_shim_domain() support Joao Martins
2019-02-20 20:16 ` [PATCH RFC 33/39] xen/grant-table: " Joao Martins
2019-02-20 20:16 ` [PATCH RFC 34/39] xen/gntdev: " Joao Martins
2019-02-20 20:16 ` [PATCH RFC 35/39] xen/xenbus: " Joao Martins
2019-02-20 20:16 ` [PATCH RFC 36/39] drivers/xen: " Joao Martins
2019-02-20 20:16 ` [PATCH RFC 37/39] xen-netback: " Joao Martins
2019-02-20 20:16 ` [PATCH RFC 38/39] xen-blkback: " Joao Martins
2019-02-20 20:16 ` [PATCH RFC 39/39] KVM: x86: declare Xen HVM Dom0 capability Joao Martins
2019-02-20 21:09 ` [PATCH RFC 00/39] x86/KVM: Xen HVM guest support Paolo Bonzini
2019-02-21  0:29   ` Ankur Arora
2019-02-21 11:45   ` Joao Martins
2019-02-22 16:59     ` Paolo Bonzini
2019-03-12 17:14       ` Joao Martins
2019-04-08  6:44         ` Juergen Gross
2019-04-08 10:36           ` Joao Martins
2019-04-08 10:42             ` Juergen Gross
2019-04-08 17:31               ` Joao Martins
2019-04-09  0:35                 ` Stefano Stabellini
2019-04-10  5:50                   ` [Xen-devel] " Ankur Arora
2019-04-10 20:45                     ` Stefano Stabellini
2019-04-09  5:04                 ` Juergen Gross
2019-04-10  6:55                   ` Ankur Arora
2019-04-10  7:14                     ` Juergen Gross
2019-02-20 23:39 ` [Xen-devel] " Marek Marczykowski-Górecki
2019-02-21  0:31   ` Ankur Arora
2019-02-21  7:57   ` Juergen Gross
2019-02-21 12:00     ` Joao Martins
2019-02-21 11:55   ` Joao Martins

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=20190220201609.28290-16-joao.m.martins@oracle.com \
    --to=joao.m.martins@oracle.com \
    --cc=ankur.a.arora@oracle.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=hpa@zytor.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=rkrcmar@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH RFC 15/39] KVM: x86/xen: handle PV spinlocks slowpath' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).