Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Claudio Imbrenda <imbrenda@linux.ibm.com>
To:     kvm@vger.kernel.org
Cc:     borntraeger@de.ibm.com, frankja@linux.ibm.com, thuth@redhat.com,
        pasic@linux.ibm.com, david@redhat.com, linux-s390@vger.kernel.org,
        linux-kernel@vger.kernel.org, scgl@linux.ibm.com,
        mimu@linux.ibm.com, nrb@linux.ibm.com
Subject: [PATCH v10 15/19] KVM: s390: pv: asynchronous destroy for reboot
Date:   Thu, 14 Apr 2022 10:03:06 +0200
Message-Id: <20220414080311.1084834-16-imbrenda@linux.ibm.com>
In-Reply-To: <20220414080311.1084834-1-imbrenda@linux.ibm.com>
References: <20220414080311.1084834-1-imbrenda@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Until now, destroying a protected guest was an entirely synchronous
operation that could potentially take a very long time, depending on
the size of the guest, due to the time needed to clean up the address
space from protected pages.

This patch implements an asynchronous destroy mechanism, that allows a
protected guest to reboot significantly faster than previously.

This is achieved by clearing the pages of the old guest in background.
In case of reboot, the new guest will be able to run in the same
address space almost immediately.

The old protected guest is then only destroyed when all of its memory has
been destroyed or otherwise made non protected.

Two new PV commands are added for the KVM_S390_PV_COMMAND ioctl:

KVM_PV_ASYNC_DISABLE_PREPARE: prepares the current protected VM for
asynchronous teardown. The current VM will then continue immediately
as non-protected. If a protected VM had already been set aside without
starting the teardown process, this call will fail.

KVM_PV_ASYNC_DISABLE: tears down the protected VM previously set aside
for asynchronous teardown. This PV command should ideally be issued by
userspace from a separate thread. If a fatal signal is received (or the
process terminates naturally), the command will terminate immediately
without completing.

Leftover protected VMs are cleaned up when a KVM VM is torn down
normally (either via IOCTL or when the process terminates); this
cleanup has been implemented in a previous patch.

Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/kvm-s390.c |  24 ++++++++
 arch/s390/kvm/kvm-s390.h |   2 +
 arch/s390/kvm/pv.c       | 126 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/kvm.h |   2 +
 4 files changed, 154 insertions(+)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 05c976bf2438..e00283b48a47 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2292,6 +2292,30 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
 		set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
 		break;
 	}
+	case KVM_PV_ASYNC_DISABLE_PREPARE:
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm) || !lazy_destroy)
+			break;
+
+		r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc);
+		/*
+		 * If a CPU could not be destroyed, destroy VM will also fail.
+		 * There is no point in trying to destroy it. Instead return
+		 * the rc and rrc from the first CPU that failed destroying.
+		 */
+		if (r)
+			break;
+		r = kvm_s390_pv_deinit_vm_async_prepare(kvm, &cmd->rc, &cmd->rrc);
+
+		/* no need to block service interrupts any more */
+		clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
+		break;
+	case KVM_PV_ASYNC_DISABLE:
+		r = -EINVAL;
+		if (!kvm->arch.pv.async_deinit)
+			break;
+		r = kvm_s390_pv_deinit_vm_async(kvm, &cmd->rc, &cmd->rrc);
+		break;
 	case KVM_PV_DISABLE: {
 		r = -EINVAL;
 		if (!kvm_s390_pv_is_protected(kvm))
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index d3abedafa7a8..d296afb6041c 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -243,6 +243,8 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm)
 /* implemented in pv.c */
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
 int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
+int kvm_s390_pv_deinit_vm_async_prepare(struct kvm *kvm, u16 *rc, u16 *rrc);
+int kvm_s390_pv_deinit_vm_async(struct kvm *kvm, u16 *rc, u16 *rrc);
 int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc);
 int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc);
 int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index b20f2cbd43d9..36bc107bbd7d 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -262,6 +262,132 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	return cc ? -EIO : 0;
 }
 
+/**
+ * kvm_s390_clear_2g - Clear the first 2GB of guest memory.
+ * @kvm the VM whose memory is to be cleared.
+ * Clear the first 2GB of guest memory, to avoid prefix issues after reboot.
+ */
+static void kvm_s390_clear_2g(struct kvm *kvm)
+{
+	struct kvm_memory_slot *slot;
+	unsigned long lim;
+	int srcu_idx;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, 0);
+	/* Clear all slots that are completely below 2GB */
+	while (slot && slot->base_gfn + slot->npages < SZ_2G / PAGE_SIZE) {
+		lim = slot->userspace_addr + slot->npages * PAGE_SIZE;
+		s390_uv_destroy_range(kvm->mm, slot->userspace_addr, lim);
+		slot = gfn_to_memslot(kvm, slot->base_gfn + slot->npages);
+	}
+	/* Last slot crosses the 2G boundary, clear only up to 2GB */
+	if (slot && slot->base_gfn < SZ_2G / PAGE_SIZE) {
+		lim = slot->userspace_addr + SZ_2G - slot->base_gfn * PAGE_SIZE;
+		s390_uv_destroy_range(kvm->mm, slot->userspace_addr, lim);
+	}
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+}
+
+/**
+ * kvm_s390_pv_deinit_vm_async_prepare - Prepare a protected VM for
+ * asynchronous teardown.
+ * @kvm the VM
+ * @rc return value for the RC field of the UVCB
+ * @rrc return value for the RRC field of the UVCB
+ *
+ * Prepare the protected VM for asynchronous teardown. The VM will be able
+ * to continue immediately as a non-secure VM, and the information needed to
+ * properly tear down the protected VM is set aside. If another protected VM
+ * was already set aside without starting a teardown, the function will
+ * fail.
+ *
+ * Context: kvm->lock needs to be held
+ *
+ * Return: 0 in case of success, -EINVAL if another protected VM was already set
+ * aside, -ENOMEM if the system ran out of memory.
+ */
+int kvm_s390_pv_deinit_vm_async_prepare(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	struct deferred_priv *priv;
+
+	/*
+	 * If an asynchronous deinitialization is already pending, refuse.
+	 * A synchronous deinitialization has to be performed instead.
+	 */
+	if (kvm->arch.pv.async_deinit)
+		return -EINVAL;
+	priv = kmalloc(sizeof(*priv), GFP_KERNEL | __GFP_ZERO);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->stor_var = kvm->arch.pv.stor_var;
+	priv->stor_base = kvm->arch.pv.stor_base;
+	priv->handle = kvm_s390_pv_get_handle(kvm);
+	priv->old_table = (unsigned long)kvm->arch.gmap->table;
+	WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
+	if (s390_replace_asce(kvm->arch.gmap)) {
+		kfree(priv);
+		return -ENOMEM;
+	}
+
+	kvm_s390_clear_2g(kvm);
+	kvm_s390_clear_pv_state(kvm);
+	kvm->arch.pv.async_deinit = priv;
+
+	*rc = 1;
+	*rrc = 42;
+	return 0;
+}
+
+/**
+ * kvm_s390_pv_deinit_vm_async - Perform an asynchronous teardown of a
+ * protected VM.
+ * @kvm the VM previously associated with the protected VM
+ * @rc return value for the RC field of the UVCB
+ * @rrc return value for the RRC field of the UVCB
+ *
+ * Tear down the protected VM that had previously been set aside using
+ * kvm_s390_pv_deinit_vm_async_prepare.
+ *
+ * Context: kvm->lock needs to be held
+ *
+ * Return: 0 in case of success, -EINVAL if no protected VM had been
+ * prepared for asynchronous teardowm, -EIO in case of other errors.
+ */
+int kvm_s390_pv_deinit_vm_async(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	struct deferred_priv *p = kvm->arch.pv.async_deinit;
+	int ret = 0;
+
+	if (!p)
+		return -EINVAL;
+	kvm->arch.pv.async_deinit = NULL;
+	mutex_unlock(&kvm->lock);
+
+	/* When a fatal signal is received, stop immediately */
+	if (s390_uv_destroy_range_interruptible(kvm->mm, 0, TASK_SIZE_MAX))
+		goto done;
+	if (kvm_s390_pv_cleanup_deferred(kvm, p))
+		ret = -EIO;
+	else
+		atomic_dec(&kvm->mm->context.protected_count);
+	kfree(p);
+	p = NULL;
+done:
+	/* The caller expects the lock to be held */
+	mutex_lock(&kvm->lock);
+	/*
+	 * p is not NULL if we aborted because of a fatal signal, in which
+	 * case queue the leftover for later cleanup.
+	 */
+	if (p)
+		list_add(&p->list, &kvm->arch.pv.need_cleanup);
+	return ret;
+}
+
 static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription,
 					     struct mm_struct *mm)
 {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 91a6fe4e02c0..0abad46d5910 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1653,6 +1653,8 @@ enum pv_cmd_id {
 	KVM_PV_VERIFY,
 	KVM_PV_PREP_RESET,
 	KVM_PV_UNSHARE_ALL,
+	KVM_PV_ASYNC_DISABLE_PREPARE,
+	KVM_PV_ASYNC_DISABLE,
 };
 
 struct kvm_pv_cmd {
-- 
2.34.1