Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri, 11 Aug 2023 14:18:44 -0300
From:   Jason Gunthorpe <jgg@nvidia.com>
To:     Sean Christopherson <seanjc@google.com>
Cc:     Yan Zhao <yan.y.zhao@intel.com>, bibo mao <maobibo@loongson.cn>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        kvm@vger.kernel.org, pbonzini@redhat.com, mike.kravetz@oracle.com,
        apopple@nvidia.com, rppt@kernel.org, akpm@linux-foundation.org,
        kevin.tian@intel.com, david@redhat.com
Subject: Re: [RFC PATCH v2 5/5] KVM: Unmap pages only when it's indeed
 protected for NUMA migration
Message-ID: <ZNZtdKXslPlKYRWY@nvidia.com>
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <ZNZshVZI5bRq4mZQ@google.com>
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?sxmH2pOeS2O/JhSsU7dKglxDOfK5Q0j0OEON2h3pFTPNq0pNSVd24e6fp9vf?=
 =?us-ascii?Q?4ylD8hl/qSk0ZaHligq4sm5/5WXQX2R8mG8NuDqfggr7uH5Hjlm8DNZzYn0v?=
 =?us-ascii?Q?Y7lyt7W6wf+2fiG4VH6Y0cQqBhJCMzwPYwHz4F+s6noiz54zUKC/d4X7nL8r?=
 =?us-ascii?Q?FwO8TMpoCwOSRCOEVLJUuePzKItv9ueFjqQvuD/zaqxpAmiPp7dKzKHwAZN8?=
 =?us-ascii?Q?jvS+2kJe4mpEX01cS/BSg13BPEbNZz2WpHpG4MOa08g6YXZkzCgugpzz8l7a?=
 =?us-ascii?Q?mceRpXPB+1GM/VjsOgf9uh580eJaeGcfQ819oU8J5qKUp7Q4Uk91OFiVuKiE?=
 =?us-ascii?Q?79dJbZI72H3xsayjfRFuVWG732V5ZUQWF1dwKT4GVXhMM8Wb4X2F7llCZ1uM?=
 =?us-ascii?Q?PCWxVd+GY9nfDU+0rVzIirf94US2xNChA4fVFXWQFeEILyDj43rpkHM83L7t?=
 =?us-ascii?Q?NnVLHzUOitf4WXKVjTHsCDzgWaazCpyaP7n7ApQSv/olAsp6O4b2IN5g2CSW?=
 =?us-ascii?Q?h6/B5HJI4nV10epIiTeiTfSc1Mssk4dfBTCyqiIXfUmflU1lTy7Bk3uzdv2o?=
 =?us-ascii?Q?axbi05rRB5i/NV4xYLLkEPcqp5ZqufWvBikO7PL2iOvKuO/1nobFaeU8yTsu?=
 =?us-ascii?Q?7uGnUoIWQ75xKDMkQBPTq76dhVlwWNObVWH7hMbzPjkriG8hiIWGWhbVYmVM?=
 =?us-ascii?Q?6MoWIcop9U0fuzAIacNRwyc/tmtt6qPVbyCwgK9giL/rvj+nWgen3A5g8MpO?=
 =?us-ascii?Q?CyefCoD/JADSH1Ntl2Vhm59AzoRnUDx7wy810iKWHge+l0cDxwC8V1zoLJZo?=
 =?us-ascii?Q?Cp+R+TuwiKBGNfHfuRWYuCFOmIRtMymaRHrQqTDu+kMpx+eoCWZfz7iWwRgg?=
 =?us-ascii?Q?zyKo1bSG8RMjDIuE4p/54GZKeb+RaaC8157WidwJ9eDTEZs9Qqeg3O81/cRU?=
 =?us-ascii?Q?75nC6xkH7U9YMmFtboeVtB8Shnn0kF3AJYdnFPXDYTFMadGDFvk4oc2o0f63?=
 =?us-ascii?Q?cbqmgYfY9kQzphsEwpXKOilfZMET2U6cXWhsqAvGk8xWBhaF5odE4QU32r9y?=
 =?us-ascii?Q?6VW9oBNK6jRuf2KiXUzzUgLpZuBxrrABsPqv0Y1CxbgeNA8snkJvzXI4BLdx?=
 =?us-ascii?Q?3okl2fFtntO1SVPfBSnrds+2b1h2m2KmCrYe79naP3LHrTB+K7tsW3J3xJ/r?=
 =?us-ascii?Q?S2s2lYB5mFG2zF7btkc7JkCdBHuxU8dzQfi/ibcyyULZ0QApF4WTvgbcLLQk?=
 =?us-ascii?Q?KLv0OY/0rA3XSDi/PIElvglt/zHwHOWx348c1dDXh5uxhBMEaz8NBPIkffUg?=
 =?us-ascii?Q?ERVI33YS+P5qRDi7FdU+mOxL+4h3jO1P4urGKeyzBEkf15lodBsxi9uT1Edp?=
 =?us-ascii?Q?RlKpLX5y0zh0Ie/58lQm+PXXcgOClxheJ/HpGVeLqLaMSxeQufNpVcB6Kj7q?=
 =?us-ascii?Q?KmMelAP2RHVwAJ7mnwUPBYBlhyKxOH+zorxsNNwkcHII0lSRLyKFwykcl7FD?=
 =?us-ascii?Q?zJ1gWrVe4xZWbaFSpsaT7dofJZE/P3786HnTWlz6nYvlGVed9qUOMpkh1lvb?=
 =?us-ascii?Q?ACQCNDOUKcL+VGGCJ8zM9QsN8E1YhRINYGrHE76Y?=
X-OriginatorOrg: Nvidia.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 7a098585-2acc-45fb-9441-08db9a8f0595
X-MS-Exchange-CrossTenant-AuthSource: LV2PR12MB5869.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 11 Aug 2023 17:18:46.9227
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: T461Xfy+2gWZ1kaA+U//ML/vIJxcnrYF1gj35oWIbeP37DsSfRp3Plgr2hWaV5vE
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DS0PR12MB7996
X-Spam-Status: No, score=-1.1 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH,
        DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,
        RCVD_IN_DNSWL_BLOCKED,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE,
        URIBL_BLOCKED autolearn=no autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

> However, *if* it's ok to invoke MMU notifiers while holding PMD/PTE locks, then
> I think we can achieve what you want without losing batching, and without changing
> secondary MMUs.

No, this is not legal.

> +void change_pmd_range_notify_secondary_mmus(unsigned long addr,
> +					    struct mmu_notifier_range *range)
> +{
> +	if (range->start)
> +		return;
> +
> +	VM_WARN_ON(addr >= range->end);
> +	range->start = addr;
> +	mmu_notifier_invalidate_range_start_nonblock(range);
> +}

The 'nonblock' entry point is advisory, if it fails the caller must
not change the mm.

Jason