[PATCH] KVM: PPC: Book3S HV: rework secure mem slot dropping

[Laurent Dufour]

When a secure memslot is dropped, all the pages backed in the secure
device (aka really backed by secure memory by the Ultravisor)
should be paged out to a normal page. Previously, this was
achieved by triggering the page fault mechanism which is calling
kvmppc_svm_page_out() on each pages.

This can't work when hot unplugging a memory slot because the memory
slot is flagged as invalid and gfn_to_pfn() is then not trying to access
the page, so the page fault mechanism is not triggered.

Since the final goal is to make a call to kvmppc_svm_page_out() it seems
simpler to call directly instead of triggering such a mechanism. This
way kvmppc_uvmem_drop_pages() can be called even when hot unplugging a
memslot.

Since kvmppc_uvmem_drop_pages() is already holding kvm->arch.uvmem_lock,
the call to __kvmppc_svm_page_out() is made.  As
__kvmppc_svm_page_out needs the vma pointer to migrate the pages,
the VMA is fetched in a lazy way, to not trigger find_vma() all
the time. In addition, the mmap_sem is held in read mode during
that time, not in write mode since the virual memory layout is not
impacted, and kvm->arch.uvmem_lock prevents concurrent operation
on the secure device.

Cc: Ram Pai <linuxram at us.ibm.com>
Cc: Bharata B Rao <bharata at linux.ibm.com>
Cc: Paul Mackerras <paulus at ozlabs.org>
Signed-off-by: Ram Pai <linuxram at us.ibm.com>
	[modified the changelog description]
Signed-off-by: Laurent Dufour <ldufour at linux.ibm.com>
        [modified check on the VMA in kvmppc_uvmem_drop_pages]
---
 arch/powerpc/kvm/book3s_hv_uvmem.c | 53 ++++++++++++++++++++----------
 1 file changed, 36 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index c772e921f769..5dd3e9acdcab 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -632,35 +632,54 @@ static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
  * fault on them, do fault time migration to replace the device PTEs in
  * QEMU page table with normal PTEs from newly allocated pages.
  */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr, end;
+
+	mmap_read_lock(kvm->mm);
+
+	addr = slot->userspace_addr;
+	end = addr + (slot->npages * PAGE_SIZE);
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || addr >= vma->vm_end) {
+			vma = find_vma_intersection(kvm->mm, addr, addr+1);
+			if (!vma) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+				break;
+			}
+		}
 
 		mutex_lock(&kvm->arch.uvmem_lock);
-		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+
+		if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			uvmem_page = pfn_to_page(uvmem_pfn);
+			pvt = uvmem_page->zone_device_data;
+			pvt->skip_page_out = skip_page_out;
+			pvt->remove_gfn = true;
+
+			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
+						  PAGE_SHIFT, kvm, pvt->gpa))
+				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
+				       pvt->gpa, addr);
+		} else {
+			/* Remove the shared flag if any */
 			kvmppc_gfn_remove(gfn, kvm);
-			mutex_unlock(&kvm->arch.uvmem_lock);
-			continue;
 		}
 
-		uvmem_page = pfn_to_page(uvmem_pfn);
-		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = skip_page_out;
-		pvt->remove_gfn = true;
 		mutex_unlock(&kvm->arch.uvmem_lock);
-
-		pfn = gfn_to_pfn(kvm, gfn);
-		if (is_error_noslot_pfn(pfn))
-			continue;
-		kvm_release_pfn_clean(pfn);
 	}
+
+	mmap_read_unlock(kvm->mm);
 }
 
 unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
-- 
2.27.0