[PATCH 18/19] KVM: PPC: Book3S HV: add passthrough support

[Cédric Le Goater]

Clear the ESB pages from the VMA of the IRQ being pass through to the
guest and let the fault handler repopulate the VMA when the ESB pages
are accessed for an EOI or for a trigger.

Storing the VMA under the KVM XIVE device is a little ugly.

Signed-off-by: Cédric Le Goater <clg at kaod.org>
---
 arch/powerpc/kvm/book3s_xive.h        |  8 +++++++
 arch/powerpc/kvm/book3s_xive.c        | 15 ++++++++++++++
 arch/powerpc/kvm/book3s_xive_native.c | 30 +++++++++++++++++++++++++++
 3 files changed, 53 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 31e598e62589..6e64d3496a2c 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -90,6 +90,11 @@ struct kvmppc_xive_src_block {
 	struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
 };
 
+struct kvmppc_xive;
+
+struct kvmppc_xive_ops {
+	int (*reset_mapped)(struct kvm *kvm, unsigned long guest_irq);
+};
 
 struct kvmppc_xive {
 	struct kvm *kvm;
@@ -131,6 +136,9 @@ struct kvmppc_xive {
 
 	/* VC base address for ESBs */
 	u64     vc_base;
+
+	struct kvmppc_xive_ops *ops;
+	struct vm_area_struct *vma;
 };
 
 #define KVMPPC_XIVE_Q_COUNT	8
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index e9f05d9c9ad5..9b4751713554 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -946,6 +946,13 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	/* Turn the IPI hard off */
 	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped)
+		xive->ops->reset_mapped(kvm, guest_irq);
+
 	/* Grab info about irq */
 	state->pt_number = hw_irq;
 	state->pt_data = irq_data_get_irq_handler_data(host_data);
@@ -1031,6 +1038,14 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 	state->pt_number = 0;
 	state->pt_data = NULL;
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped) {
+		xive->ops->reset_mapped(kvm, guest_irq);
+	}
+
 	/* Reconfigure the IPI */
 	xive_native_configure_irq(state->ipi_number,
 				  xive_vp(xive, state->act_server),
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 1aefb366df0b..12edac29995e 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -240,6 +240,32 @@ static int kvmppc_xive_native_get_vc_base(struct kvmppc_xive *xive, u64 addr)
 	return 0;
 }
 
+static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq)
+{
+	struct kvmppc_xive *xive = kvm->arch.xive;
+	struct mm_struct *mm = kvm->mm;
+	struct vm_area_struct *vma = xive->vma;
+	unsigned long address;
+
+	if (irq >= KVMPPC_XIVE_NR_IRQS)
+		return -EINVAL;
+
+	pr_debug("clearing esb pages for girq 0x%lx\n", irq);
+
+	down_read(&mm->mmap_sem);
+	/* TODO: can we clear the PTEs without keeping a VMA pointer ? */
+	if (vma) {
+		address = vma->vm_start + irq * (2ull << PAGE_SHIFT);
+		zap_vma_ptes(vma, address, 2ull << PAGE_SHIFT);
+	}
+	up_read(&mm->mmap_sem);
+	return 0;
+}
+
+static struct kvmppc_xive_ops kvmppc_xive_native_ops =  {
+	.reset_mapped = kvmppc_xive_native_reset_mapped,
+};
+
 static int xive_native_esb_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -292,6 +318,8 @@ static const struct vm_operations_struct xive_native_esb_vmops = {
 
 static int xive_native_esb_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct kvmppc_xive *xive = vma->vm_file->private_data;
+
 	/* There are two ESB pages (trigger and EOI) per IRQ */
 	if (vma_pages(vma) + vma->vm_pgoff > KVMPPC_XIVE_NR_IRQS * 2)
 		return -EINVAL;
@@ -299,6 +327,7 @@ static int xive_native_esb_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_IO | VM_PFNMAP;
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	vma->vm_ops = &xive_native_esb_vmops;
+	xive->vma = vma; /* TODO: get rid of the VMA pointer */
 	return 0;
 }
 
@@ -992,6 +1021,7 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
 	xive->vc_base = XIVE_VC_BASE;
 
 	xive->single_escalation = xive_native_has_single_escalation();
+	xive->ops = &kvmppc_xive_native_ops;
 
 	if (ret)
 		kfree(xive);
-- 
2.20.1