@@ -933,6 +933,8 @@ Return values
* H_UNSUPPORTED if called from the wrong context (e.g.
from an SVM or before an H_SVM_INIT_START
hypercall).
+ * H_STATE if the hypervisor could not successfully
+ transition the VM to Secure VM.
Description
~~~~~~~~~~~
@@ -339,6 +339,21 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
return false;
}
+/* return true, if the GFN is a shared-GFN, or a secure-GFN */
+bool kvmppc_gfn_has_transitioned(unsigned long gfn, struct kvm *kvm)
+{
+ struct kvmppc_uvmem_slot *p;
+
+ list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
+ if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
+ unsigned long index = gfn - p->base_pfn;
+
+ return (p->pfns[index] & KVMPPC_GFN_FLAG_MASK);
+ }
+ }
+ return false;
+}
+
unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
{
struct kvm_memslots *slots;
@@ -377,14 +392,152 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
return ret;
}
+static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm);
+
+/*
+ * Alloc a PFN from private device memory pool. If @pagein is true,
+ * copy page from normal memory to secure memory using UV_PAGE_IN uvcall.
+ */
+static int kvmppc_svm_migrate_page(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end, unsigned long gpa, struct kvm *kvm,
+ unsigned long page_shift,
+ bool pagein)
+{
+ unsigned long src_pfn, dst_pfn = 0;
+ struct migrate_vma mig;
+ struct page *dpage;
+ struct page *spage;
+ unsigned long pfn;
+ int ret = 0;
+
+ memset(&mig, 0, sizeof(mig));
+ mig.vma = vma;
+ mig.start = start;
+ mig.end = end;
+ mig.src = &src_pfn;
+ mig.dst = &dst_pfn;
+
+ ret = migrate_vma_setup(&mig);
+ if (ret)
+ return ret;
+
+ if (!(*mig.src & MIGRATE_PFN_MIGRATE)) {
+ ret = -1;
+ goto out_finalize;
+ }
+
+ dpage = kvmppc_uvmem_get_page(gpa, kvm);
+ if (!dpage) {
+ ret = -1;
+ goto out_finalize;
+ }
+
+ if (pagein) {
+ pfn = *mig.src >> MIGRATE_PFN_SHIFT;
+ spage = migrate_pfn_to_page(*mig.src);
+ if (spage) {
+ ret = uv_page_in(kvm->arch.lpid, pfn << page_shift,
+ gpa, 0, page_shift);
+ if (ret)
+ goto out_finalize;
+ }
+ }
+
+ *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
+ migrate_vma_pages(&mig);
+out_finalize:
+ migrate_vma_finalize(&mig);
+ return ret;
+}
+
+static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot)
+{
+ unsigned long gfn = memslot->base_gfn;
+ unsigned long end;
+ bool downgrade = false;
+ struct vm_area_struct *vma;
+ int i, ret = 0;
+ unsigned long start = gfn_to_hva(kvm, gfn);
+
+ if (kvm_is_error_hva(start))
+ return H_STATE;
+
+ end = start + (memslot->npages << PAGE_SHIFT);
+
+ down_write(&kvm->mm->mmap_sem);
+
+ mutex_lock(&kvm->arch.uvmem_lock);
+ vma = find_vma_intersection(kvm->mm, start, end);
+ if (!vma || vma->vm_start > start || vma->vm_end < end) {
+ ret = H_STATE;
+ goto out_unlock;
+ }
+
+ ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+ MADV_UNMERGEABLE, &vma->vm_flags);
+ downgrade_write(&kvm->mm->mmap_sem);
+ downgrade = true;
+ if (ret) {
+ ret = H_STATE;
+ goto out_unlock;
+ }
+
+ for (i = 0; i < memslot->npages; i++, ++gfn) {
+ /*
+ * skip GFNs that have already tranistioned.
+ * paged-in GFNs, shared GFNs, paged-in GFNs
+ * that were later paged-out.
+ */
+ if (kvmppc_gfn_has_transitioned(gfn, kvm))
+ continue;
+
+ start = gfn_to_hva(kvm, gfn);
+ end = start + (1UL << PAGE_SHIFT);
+ ret = kvmppc_svm_migrate_page(vma, start, end,
+ (gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false);
+
+ if (ret)
+ goto out_unlock;
+ }
+
+out_unlock:
+ mutex_unlock(&kvm->arch.uvmem_lock);
+ if (downgrade)
+ up_read(&kvm->mm->mmap_sem);
+ else
+ up_write(&kvm->mm->mmap_sem);
+ return ret;
+}
+
unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int srcu_idx;
+ long ret = H_SUCCESS;
+
if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
return H_UNSUPPORTED;
+ /* migrate any unmoved normal pfn to device pfns*/
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(memslot, slots) {
+ ret = kvmppc_uv_migrate_mem_slot(kvm, memslot);
+ if (ret) {
+ ret = H_STATE;
+ goto out;
+ }
+ }
+
kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
pr_info("LPID %d went secure\n", kvm->arch.lpid);
- return H_SUCCESS;
+
+out:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ return ret;
}
/*
@@ -510,68 +663,6 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
}
/*
- * Alloc a PFN from private device memory pool and copy page from normal
- * memory to secure memory using UV_PAGE_IN uvcall.
- */
-static int kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, unsigned long gpa, struct kvm *kvm,
- unsigned long page_shift, bool *downgrade)
-{
- unsigned long src_pfn, dst_pfn = 0;
- struct migrate_vma mig;
- struct page *spage;
- unsigned long pfn;
- struct page *dpage;
- int ret = 0;
-
- memset(&mig, 0, sizeof(mig));
- mig.vma = vma;
- mig.start = start;
- mig.end = end;
- mig.src = &src_pfn;
- mig.dst = &dst_pfn;
-
- /*
- * We come here with mmap_sem write lock held just for
- * ksm_madvise(), otherwise we only need read mmap_sem.
- * Hence downgrade to read lock once ksm_madvise() is done.
- */
- ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
- MADV_UNMERGEABLE, &vma->vm_flags);
- downgrade_write(&kvm->mm->mmap_sem);
- *downgrade = true;
- if (ret)
- return ret;
-
- ret = migrate_vma_setup(&mig);
- if (ret)
- return ret;
-
- if (!(*mig.src & MIGRATE_PFN_MIGRATE)) {
- ret = -1;
- goto out_finalize;
- }
-
- dpage = kvmppc_uvmem_get_page(gpa, kvm);
- if (!dpage) {
- ret = -1;
- goto out_finalize;
- }
-
- pfn = *mig.src >> MIGRATE_PFN_SHIFT;
- spage = migrate_pfn_to_page(*mig.src);
- if (spage)
- uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
- page_shift);
-
- *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
- migrate_vma_pages(&mig);
-out_finalize:
- migrate_vma_finalize(&mig);
- return ret;
-}
-
-/*
* Shares the page with HV, thus making it a normal page.
*
* - If the page is already secure, then provision a new page and share
@@ -676,9 +767,21 @@ unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
if (!vma || vma->vm_start > start || vma->vm_end < end)
goto out_unlock;
- if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
- &downgrade))
- ret = H_SUCCESS;
+ ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+ MADV_UNMERGEABLE, &vma->vm_flags);
+ downgrade_write(&kvm->mm->mmap_sem);
+ downgrade = true;
+ if (ret) {
+ ret = H_PARAMETER;
+ goto out_unlock;
+ }
+
+ ret = H_PARAMETER;
+ if (kvmppc_svm_migrate_page(vma, start, end, gpa, kvm, page_shift,
+ true))
+ goto out_unlock;
+
+ ret = H_SUCCESS;
out_unlock:
mutex_unlock(&kvm->arch.uvmem_lock);
H_SVM_INIT_DONE incorrectly assumes that the Ultravisor has explicitly called H_SVM_PAGE_IN for all secure pages. These GFNs continue to be normal GFNs associated with normal PFNs; when infact, these GFNs should have been secure GFNs, associated with device PFNs. Move all the PFN associated with the SVM's GFNs, to secure-PFNs, in H_SVM_INIT_DONE. Skip the GFNs that are already Paged-in or Shared through H_SVM_PAGE_IN, or Paged-in followed by a Paged-out through UV_PAGE_OUT. Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Bharata B Rao <bharata@linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Claudio Carvalho <cclaudio@linux.ibm.com> Cc: kvm-ppc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Ram Pai <linuxram@us.ibm.com> --- Documentation/powerpc/ultravisor.rst | 2 + arch/powerpc/kvm/book3s_hv_uvmem.c | 235 +++++++++++++++++++++++++---------- 2 files changed, 171 insertions(+), 66 deletions(-)