From patchwork Mon Oct 22 05:18:35 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Bharata B Rao X-Patchwork-Id: 987512 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=kvm-ppc-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=linux.ibm.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 42dlDj2Tz1z9sDB for ; Mon, 22 Oct 2018 16:19:01 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727411AbeJVNf4 (ORCPT ); Mon, 22 Oct 2018 09:35:56 -0400 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:53700 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726784AbeJVNf4 (ORCPT ); Mon, 22 Oct 2018 09:35:56 -0400 Received: from pps.filterd (m0098419.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.0.22/8.16.0.22) with SMTP id w9M59TS5133170 for ; Mon, 22 Oct 2018 01:18:59 -0400 Received: from e06smtp02.uk.ibm.com (e06smtp02.uk.ibm.com [195.75.94.98]) by mx0b-001b2d01.pphosted.com with ESMTP id 2n9315rvwn-1 (version=TLSv1.2 cipher=AES256-GCM-SHA384 bits=256 verify=NOT) for ; Mon, 22 Oct 2018 01:18:59 -0400 Received: from localhost by e06smtp02.uk.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Mon, 22 Oct 2018 06:18:57 +0100 Received: from b06cxnps4076.portsmouth.uk.ibm.com (9.149.109.198) by e06smtp02.uk.ibm.com (192.168.101.132) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; (version=TLSv1/SSLv3 cipher=AES256-GCM-SHA384 bits=256/256) Mon, 22 Oct 2018 06:18:54 +0100 Received: from d06av26.portsmouth.uk.ibm.com (d06av26.portsmouth.uk.ibm.com [9.149.105.62]) by b06cxnps4076.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id w9M5Irhi1769772 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=FAIL); Mon, 22 Oct 2018 05:18:53 GMT Received: from d06av26.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 06E28AE04D; Mon, 22 Oct 2018 05:18:53 +0000 (GMT) Received: from d06av26.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 64B13AE045; Mon, 22 Oct 2018 05:18:51 +0000 (GMT) Received: from bharata.in.ibm.com (unknown [9.124.35.126]) by d06av26.portsmouth.uk.ibm.com (Postfix) with ESMTP; Mon, 22 Oct 2018 05:18:51 +0000 (GMT) From: Bharata B Rao To: linuxppc-dev@lists.ozlabs.org Cc: kvm-ppc@vger.kernel.org, linux-mm@kvack.org, paulus@au1.ibm.com, benh@linux.ibm.com, aneesh.kumar@linux.vnet.ibm.com, jglisse@redhat.com, linuxram@us.ibm.com, Bharata B Rao Subject: [RFC PATCH v1 2/4] kvmppc: Add support for shared pages in HMM driver Date: Mon, 22 Oct 2018 10:48:35 +0530 X-Mailer: git-send-email 2.17.1 In-Reply-To: <20181022051837.1165-1-bharata@linux.ibm.com> References: <20181022051837.1165-1-bharata@linux.ibm.com> X-TM-AS-GCONF: 00 x-cbid: 18102205-0008-0000-0000-0000028318EA X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 18102205-0009-0000-0000-000021EC95F0 Message-Id: <20181022051837.1165-3-bharata@linux.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:, , definitions=2018-10-21_14:, , signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 priorityscore=1501 malwarescore=0 suspectscore=1 phishscore=0 bulkscore=0 spamscore=0 clxscore=1015 lowpriorityscore=0 mlxscore=0 impostorscore=0 mlxlogscore=546 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1807170000 definitions=main-1810220049 Sender: kvm-ppc-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm-ppc@vger.kernel.org A secure guest will share some of its pages with hypervisor (Eg. virtio bounce buffers etc). Support shared pages in HMM driver. Signed-off-by: Bharata B Rao --- arch/powerpc/kvm/book3s_hv_hmm.c | 69 ++++++++++++++++++++++++++++++-- 1 file changed, 65 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_hmm.c b/arch/powerpc/kvm/book3s_hv_hmm.c index a2ee3163a312..09b8e19b7605 100644 --- a/arch/powerpc/kvm/book3s_hv_hmm.c +++ b/arch/powerpc/kvm/book3s_hv_hmm.c @@ -50,6 +50,7 @@ struct kvmppc_hmm_page_pvt { struct hlist_head *hmm_hash; unsigned int lpid; unsigned long gpa; + bool skip_page_out; }; struct kvmppc_hmm_migrate_args { @@ -278,6 +279,65 @@ static unsigned long kvmppc_gpa_to_hva(struct kvm *kvm, unsigned long gpa, return hva; } +/* + * Shares the page with HV, thus making it a normal page. + * + * - If the page is already secure, then provision a new page and share + * - If the page is a normal page, share the existing page + * + * In the former case, uses the HMM fault handler to release the HMM page. + */ +static unsigned long +kvmppc_share_page(struct kvm *kvm, unsigned long gpa, + unsigned long addr, unsigned long page_shift) +{ + + int ret; + struct hlist_head *list, *hmm_hash; + unsigned int lpid = kvm->arch.lpid; + unsigned long flags; + struct kvmppc_hmm_pfn_entry *p; + struct page *hmm_page, *page; + struct kvmppc_hmm_page_pvt *pvt; + unsigned long pfn; + + /* + * First check if the requested page has already been given to + * UV as a secure page. If so, ensure that we don't issue a + * UV_PAGE_OUT but instead directly send the page + */ + spin_lock_irqsave(&kvmppc_hmm_lock, flags); + hmm_hash = kvm->arch.hmm_hash; + list = &hmm_hash[kvmppc_hmm_pfn_hash_fn(gpa)]; + hlist_for_each_entry(p, list, hlist) { + if (p->addr == gpa) { + hmm_page = pfn_to_page(p->hmm_pfn); + get_page(hmm_page); /* TODO: Necessary ? */ + pvt = (struct kvmppc_hmm_page_pvt *) + hmm_devmem_page_get_drvdata(hmm_page); + pvt->skip_page_out = true; + put_page(hmm_page); + break; + } + } + spin_unlock_irqrestore(&kvmppc_hmm_lock, flags); + + ret = get_user_pages_fast(addr, 1, 0, &page); + if (ret != 1) + return H_PARAMETER; + + pfn = page_to_pfn(page); + if (is_zero_pfn(pfn)) { + put_page(page); + return H_SUCCESS; + } + + ret = uv_page_in(lpid, pfn << page_shift, gpa, 0, page_shift); + put_page(page); + + return (ret == U_SUCCESS) ? H_SUCCESS : H_PARAMETER; +} + /* * Move page from normal memory to secure memory. */ @@ -300,8 +360,8 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, return H_PARAMETER; end = addr + (1UL << page_shift); - if (flags) - return H_P2; + if (flags & H_PAGE_IN_SHARED) + return kvmppc_share_page(kvm, gpa, addr, page_shift); args.hmm_hash = kvm->arch.hmm_hash; args.lpid = kvm->arch.lpid; @@ -349,8 +409,9 @@ kvmppc_hmm_fault_migrate_alloc_and_copy(struct vm_area_struct *vma, hmm_devmem_page_get_drvdata(spage); pfn = page_to_pfn(dpage); - ret = uv_page_out(pvt->lpid, pfn << PAGE_SHIFT, - pvt->gpa, 0, PAGE_SHIFT); + if (!pvt->skip_page_out) + ret = uv_page_out(pvt->lpid, pfn << PAGE_SHIFT, + pvt->gpa, 0, PAGE_SHIFT); if (ret == U_SUCCESS) *dst_pfn = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; }