From 81ab595ddd3c3036806b460526e1fbc5b271ff33 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Mon, 27 Jul 2020 12:24:29 -0700 Subject: [PATCH] KVM: PPC: Book3S HV: Rework secure mem slot dropping 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. Reviewed-by: Bharata B Rao Signed-off-by: Laurent Dufour [modified check on the VMA in kvmppc_uvmem_drop_pages] Signed-off-by: Ram Pai [modified the changelog description] Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv_uvmem.c | 56 ++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 565f24bbccf1..0d49e3425a12 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -594,35 +594,53 @@ 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; - for (i = free->npages; i; --i, ++gfn) { - struct page *uvmem_page; + mmap_read_lock(kvm->mm); - mutex_lock(&kvm->arch.uvmem_lock); - if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { - kvmppc_gfn_remove(gfn, kvm); - mutex_unlock(&kvm->arch.uvmem_lock); - continue; + addr = slot->userspace_addr; + + 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; + } } - 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); + mutex_lock(&kvm->arch.uvmem_lock); - pfn = gfn_to_pfn(kvm, gfn); - if (is_error_noslot_pfn(pfn)) - continue; - kvm_release_pfn_clean(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); } + + mmap_read_unlock(kvm->mm); } unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)