From patchwork Mon Oct 16 22:47:36 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Alex Williamson X-Patchwork-Id: 153791 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:a05:612c:2908:b0:403:3b70:6f57 with SMTP id ib8csp3767862vqb; Mon, 16 Oct 2023 15:49:19 -0700 (PDT) X-Google-Smtp-Source: AGHT+IEisGMU0iiVTwbn8HpgnjYeaIpNZhpKWKnoHpPtCl0d4Hdbr9FrM+4REs3zxxeX8vXTKGUW X-Received: by 2002:a17:90b:3eca:b0:263:730b:f568 with SMTP id rm10-20020a17090b3eca00b00263730bf568mr546363pjb.3.1697496559005; Mon, 16 Oct 2023 15:49:19 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1697496558; cv=none; d=google.com; s=arc-20160816; b=NPbSRRvm6N3AACXZdCwGSVTHOY17biXvumKjuOT+XpgOoVN843a0P9KXoWrqXwkkrN xn+6hMULkhl8QE2Kd6wx42PA/aOA9cLaSgc8tu9HxEseUOVT2Pv92KHGmFTw9eNPclLc ad9HvZp78l90gbZXqbfKMt+KaRJ+nLiv1hBaDF7qRBm5MCvQwFJHE/oUoq1W3yJ9vYTD i2avHzU/ebul3CQXghGtJY9TvTCMhZHU8C/a52QoXUgbzHn2g4FgtqgzMXMUjHe2KF16 vQSnX+VNpgRXNGxCaQvKVSJUAAfh0G2boypbaDbuqWNbOrQToXo9F4LGabwUW2S9a730 Dthw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from :dkim-signature; bh=3yNgIozFXELpNAiObOFXYlIiTLpsdxEj30ygNyGFBA0=; fh=+Cb2XQ2PA67VLAGJa+jxW1LjaBXcHfLinB2fMRnx8lg=; b=DGr0K9tvR/0Wmv/hH+yjOthPQzppDJubTNJyGT12weQlwQNOBCVK13tI4YtKnsI2u+ 2mtKLMqsOKS5Nh3JHZN5YYo6lNhsdFrJSw9FzWjCk0pGet/6dY0u9Cy4cTPX04Zs7Eqa c593AJPJxwK1RiQ4/8GvrAx+Fc6YJOPaka9MkhGu1O+9eSRTUGhIZNlUp00XwMYcQigl sSdUW8Bm5L97xF0jvdGnNhek68UaifeBXUALVutvuGJ7uoYW/CD9I/bK1EmgQSmME9M6 b5w8LczfkPOH293jxmvskZfRtmWnhTe3C6IeWYuu/d/ZgDNO88vb9tnlCUqRda30qFTX MjKQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@redhat.com header.s=mimecast20190719 header.b=TwUiiSiW; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=redhat.com Received: from snail.vger.email (snail.vger.email. [23.128.96.37]) by mx.google.com with ESMTPS id ob4-20020a17090b390400b00274a22e6364si7666487pjb.92.2023.10.16.15.49.18 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 16 Oct 2023 15:49:18 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37; Authentication-Results: mx.google.com; dkim=pass header.i=@redhat.com header.s=mimecast20190719 header.b=TwUiiSiW; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=redhat.com Received: from out1.vger.email (depot.vger.email [IPv6:2620:137:e000::3:0]) by snail.vger.email (Postfix) with ESMTP id 256F38026AD2; Mon, 16 Oct 2023 15:49:18 -0700 (PDT) X-Virus-Status: Clean X-Virus-Scanned: clamav-milter 0.103.10 at snail.vger.email Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234185AbjJPWsl (ORCPT + 18 others); Mon, 16 Oct 2023 18:48:41 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47800 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233399AbjJPWsf (ORCPT ); Mon, 16 Oct 2023 18:48:35 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7B4B195 for ; Mon, 16 Oct 2023 15:47:46 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1697496465; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=3yNgIozFXELpNAiObOFXYlIiTLpsdxEj30ygNyGFBA0=; b=TwUiiSiWHjg9wrWwRSpyGmQA2UEsQ4Eb1PL7layD7n7KDXiqFe2Gnjll94/TlcFqyo+d0w Oq9XOTONYG1eX5YxTcE/hFMfkQq5DxEgbIzFAHUpdkaPyMGZk6/z9P/KEFMIiix1bz2i/W uFdu73Li4oV9KntRaBmT3rKrSE17YQ0= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-380-034ApOKCOEO9aHZasGem2Q-1; Mon, 16 Oct 2023 18:47:42 -0400 X-MC-Unique: 034ApOKCOEO9aHZasGem2Q-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.rdu2.redhat.com [10.11.54.1]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 1185E800B23; Mon, 16 Oct 2023 22:47:42 +0000 (UTC) Received: from omen.home.shazbot.org (unknown [10.22.10.53]) by smtp.corp.redhat.com (Postfix) with ESMTP id A938325C9; Mon, 16 Oct 2023 22:47:41 +0000 (UTC) From: Alex Williamson To: alex.williamson@redhat.com Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, clg@redhat.com Subject: [PATCH v2 2/2] vfio/mtty: Enable migration support Date: Mon, 16 Oct 2023 16:47:36 -0600 Message-Id: <20231016224736.2575718-3-alex.williamson@redhat.com> In-Reply-To: <20231016224736.2575718-1-alex.williamson@redhat.com> References: <20231016224736.2575718-1-alex.williamson@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.1 X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H3,RCVD_IN_MSPIKE_WL,SPF_HELO_NONE,SPF_NONE autolearn=unavailable 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: X-Mailing-List: linux-kernel@vger.kernel.org X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (snail.vger.email [0.0.0.0]); Mon, 16 Oct 2023 15:49:18 -0700 (PDT) X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: 1779954151910327016 X-GMAIL-MSGID: 1779954151910327016 The mtty driver exposes a PCI serial device to userspace and therefore makes an easy target for a sample device supporting migration. The device does not make use of DMA, therefore we can easily claim support for the migration P2P states, as well as dirty logging. This implementation also makes use of PRE_COPY support in order to provide migration stream compatibility testing, which should generally be considered good practice. Signed-off-by: Alex Williamson Reviewed-by: Cédric Le Goater --- samples/vfio-mdev/mtty.c | 590 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 590 insertions(+) diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index 245db52bedf2..69ba0281f9e0 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -29,6 +29,8 @@ #include #include #include +#include + /* * #defines */ @@ -124,6 +126,29 @@ struct serial_port { u8 intr_trigger_level; /* interrupt trigger level */ }; +struct mtty_data { + u64 magic; +#define MTTY_MAGIC 0x7e9d09898c3e2c4e /* Nothing clever, just random */ + u32 major_ver; +#define MTTY_MAJOR_VER 1 + u32 minor_ver; +#define MTTY_MINOR_VER 0 + u32 nr_ports; + u32 flags; + struct serial_port ports[2]; +}; + +struct mdev_state; + +struct mtty_migration_file { + struct file *filp; + struct mutex lock; + struct mdev_state *mdev_state; + struct mtty_data data; + ssize_t filled_size; + u8 disabled:1; +}; + /* State of each mdev device */ struct mdev_state { struct vfio_device vdev; @@ -140,6 +165,12 @@ struct mdev_state { struct mutex rxtx_lock; struct vfio_device_info dev_info; int nr_ports; + enum vfio_device_mig_state state; + struct mutex state_mutex; + struct mutex reset_mutex; + struct mtty_migration_file *saving_migf; + struct mtty_migration_file *resuming_migf; + u8 deferred_reset:1; u8 intx_mask:1; }; @@ -743,6 +774,543 @@ static ssize_t mdev_access(struct mdev_state *mdev_state, u8 *buf, size_t count, return ret; } +static size_t mtty_data_size(struct mdev_state *mdev_state) +{ + return offsetof(struct mtty_data, ports) + + (mdev_state->nr_ports * sizeof(struct serial_port)); +} + +static void mtty_disable_file(struct mtty_migration_file *migf) +{ + mutex_lock(&migf->lock); + migf->disabled = true; + migf->filled_size = 0; + migf->filp->f_pos = 0; + mutex_unlock(&migf->lock); +} + +static void mtty_disable_files(struct mdev_state *mdev_state) +{ + if (mdev_state->saving_migf) { + mtty_disable_file(mdev_state->saving_migf); + fput(mdev_state->saving_migf->filp); + mdev_state->saving_migf = NULL; + } + + if (mdev_state->resuming_migf) { + mtty_disable_file(mdev_state->resuming_migf); + fput(mdev_state->resuming_migf->filp); + mdev_state->resuming_migf = NULL; + } +} + +static void mtty_state_mutex_unlock(struct mdev_state *mdev_state) +{ +again: + mutex_lock(&mdev_state->reset_mutex); + if (mdev_state->deferred_reset) { + mdev_state->deferred_reset = false; + mutex_unlock(&mdev_state->reset_mutex); + mdev_state->state = VFIO_DEVICE_STATE_RUNNING; + mtty_disable_files(mdev_state); + goto again; + } + mutex_unlock(&mdev_state->state_mutex); + mutex_unlock(&mdev_state->reset_mutex); +} + +static int mtty_release_migf(struct inode *inode, struct file *filp) +{ + struct mtty_migration_file *migf = filp->private_data; + + mtty_disable_file(migf); + mutex_destroy(&migf->lock); + kfree(migf); + + return 0; +} + +static long mtty_precopy_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct mtty_migration_file *migf = filp->private_data; + struct mdev_state *mdev_state = migf->mdev_state; + loff_t *pos = &filp->f_pos; + struct vfio_precopy_info info = {}; + unsigned long minsz; + int ret; + + if (cmd != VFIO_MIG_GET_PRECOPY_INFO) + return -ENOTTY; + + minsz = offsetofend(struct vfio_precopy_info, dirty_bytes); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + if (info.argsz < minsz) + return -EINVAL; + + mutex_lock(&mdev_state->state_mutex); + if (mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY && + mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY_P2P) { + ret = -EINVAL; + goto unlock; + } + + mutex_lock(&migf->lock); + + if (migf->disabled) { + mutex_unlock(&migf->lock); + ret = -ENODEV; + goto unlock; + } + + if (*pos > migf->filled_size) { + mutex_unlock(&migf->lock); + ret = -EINVAL; + goto unlock; + } + + info.dirty_bytes = 0; + info.initial_bytes = migf->filled_size - *pos; + mutex_unlock(&migf->lock); + + ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; +unlock: + mtty_state_mutex_unlock(mdev_state); + return ret; +} + +static ssize_t mtty_save_read(struct file *filp, char __user *buf, + size_t len, loff_t *pos) +{ + struct mtty_migration_file *migf = filp->private_data; + ssize_t ret = 0; + + if (pos) + return -ESPIPE; + + pos = &filp->f_pos; + + mutex_lock(&migf->lock); + + dev_dbg(migf->mdev_state->vdev.dev, "%s ask %zu\n", __func__, len); + + if (migf->disabled) { + ret = -ENODEV; + goto out_unlock; + } + + if (*pos > migf->filled_size) { + ret = -EINVAL; + goto out_unlock; + } + + len = min_t(size_t, migf->filled_size - *pos, len); + if (len) { + if (copy_to_user(buf, (void *)&migf->data + *pos, len)) { + ret = -EFAULT; + goto out_unlock; + } + *pos += len; + ret = len; + } +out_unlock: + dev_dbg(migf->mdev_state->vdev.dev, "%s read %zu\n", __func__, ret); + mutex_unlock(&migf->lock); + return ret; +} + +static const struct file_operations mtty_save_fops = { + .owner = THIS_MODULE, + .read = mtty_save_read, + .unlocked_ioctl = mtty_precopy_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .release = mtty_release_migf, + .llseek = no_llseek, +}; + +static void mtty_save_state(struct mdev_state *mdev_state) +{ + struct mtty_migration_file *migf = mdev_state->saving_migf; + int i; + + mutex_lock(&migf->lock); + for (i = 0; i < mdev_state->nr_ports; i++) { + memcpy(&migf->data.ports[i], + &mdev_state->s[i], sizeof(struct serial_port)); + migf->filled_size += sizeof(struct serial_port); + } + dev_dbg(mdev_state->vdev.dev, + "%s filled to %zu\n", __func__, migf->filled_size); + mutex_unlock(&migf->lock); +} + +static int mtty_load_state(struct mdev_state *mdev_state) +{ + struct mtty_migration_file *migf = mdev_state->resuming_migf; + int i; + + mutex_lock(&migf->lock); + /* magic and version already tested by resume write fn */ + if (migf->filled_size < mtty_data_size(mdev_state)) { + dev_dbg(mdev_state->vdev.dev, "%s expected %zu, got %zu\n", + __func__, mtty_data_size(mdev_state), + migf->filled_size); + mutex_unlock(&migf->lock); + return -EINVAL; + } + + for (i = 0; i < mdev_state->nr_ports; i++) + memcpy(&mdev_state->s[i], + &migf->data.ports[i], sizeof(struct serial_port)); + + mutex_unlock(&migf->lock); + return 0; +} + +static struct mtty_migration_file * +mtty_save_device_data(struct mdev_state *mdev_state, + enum vfio_device_mig_state state) +{ + struct mtty_migration_file *migf = mdev_state->saving_migf; + struct mtty_migration_file *ret = NULL; + + if (migf) { + if (state == VFIO_DEVICE_STATE_STOP_COPY) + goto fill_data; + return ret; + } + + migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT); + if (!migf) + return ERR_PTR(-ENOMEM); + + migf->filp = anon_inode_getfile("mtty_mig", &mtty_save_fops, + migf, O_RDONLY); + if (IS_ERR(migf->filp)) { + int rc = PTR_ERR(migf->filp); + + kfree(migf); + return ERR_PTR(rc); + } + + stream_open(migf->filp->f_inode, migf->filp); + mutex_init(&migf->lock); + migf->mdev_state = mdev_state; + + migf->data.magic = MTTY_MAGIC; + migf->data.major_ver = MTTY_MAJOR_VER; + migf->data.minor_ver = MTTY_MINOR_VER; + migf->data.nr_ports = mdev_state->nr_ports; + + migf->filled_size = offsetof(struct mtty_data, ports); + + dev_dbg(mdev_state->vdev.dev, "%s filled header to %zu\n", + __func__, migf->filled_size); + + ret = mdev_state->saving_migf = migf; + +fill_data: + if (state == VFIO_DEVICE_STATE_STOP_COPY) + mtty_save_state(mdev_state); + + return ret; +} + +static ssize_t mtty_resume_write(struct file *filp, const char __user *buf, + size_t len, loff_t *pos) +{ + struct mtty_migration_file *migf = filp->private_data; + struct mdev_state *mdev_state = migf->mdev_state; + loff_t requested_length; + ssize_t ret = 0; + + if (pos) + return -ESPIPE; + + pos = &filp->f_pos; + + if (*pos < 0 || + check_add_overflow((loff_t)len, *pos, &requested_length)) + return -EINVAL; + + if (requested_length > mtty_data_size(mdev_state)) + return -ENOMEM; + + mutex_lock(&migf->lock); + + if (migf->disabled) { + ret = -ENODEV; + goto out_unlock; + } + + if (copy_from_user((void *)&migf->data + *pos, buf, len)) { + ret = -EFAULT; + goto out_unlock; + } + + *pos += len; + ret = len; + + dev_dbg(migf->mdev_state->vdev.dev, "%s received %zu, total %zu\n", + __func__, len, migf->filled_size + len); + + if (migf->filled_size < offsetof(struct mtty_data, ports) && + migf->filled_size + len >= offsetof(struct mtty_data, ports)) { + if (migf->data.magic != MTTY_MAGIC || migf->data.flags || + migf->data.major_ver != MTTY_MAJOR_VER || + migf->data.minor_ver != MTTY_MINOR_VER || + migf->data.nr_ports != mdev_state->nr_ports) { + dev_dbg(migf->mdev_state->vdev.dev, + "%s failed validation\n", __func__); + ret = -EFAULT; + } else { + dev_dbg(migf->mdev_state->vdev.dev, + "%s header validated\n", __func__); + } + } + + migf->filled_size += len; + +out_unlock: + mutex_unlock(&migf->lock); + return ret; +} + +static const struct file_operations mtty_resume_fops = { + .owner = THIS_MODULE, + .write = mtty_resume_write, + .release = mtty_release_migf, + .llseek = no_llseek, +}; + +static struct mtty_migration_file * +mtty_resume_device_data(struct mdev_state *mdev_state) +{ + struct mtty_migration_file *migf; + int ret; + + migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT); + if (!migf) + return ERR_PTR(-ENOMEM); + + migf->filp = anon_inode_getfile("mtty_mig", &mtty_resume_fops, + migf, O_WRONLY); + if (IS_ERR(migf->filp)) { + ret = PTR_ERR(migf->filp); + kfree(migf); + return ERR_PTR(ret); + } + + stream_open(migf->filp->f_inode, migf->filp); + mutex_init(&migf->lock); + migf->mdev_state = mdev_state; + + mdev_state->resuming_migf = migf; + + return migf; +} + +static struct file *mtty_step_state(struct mdev_state *mdev_state, + enum vfio_device_mig_state new) +{ + enum vfio_device_mig_state cur = mdev_state->state; + + dev_dbg(mdev_state->vdev.dev, "%s: %d -> %d\n", __func__, cur, new); + + /* + * The following state transitions are no-op considering + * mtty does not do DMA nor require any explicit start/stop. + * + * RUNNING -> RUNNING_P2P + * RUNNING_P2P -> RUNNING + * RUNNING_P2P -> STOP + * PRE_COPY -> PRE_COPY_P2P + * PRE_COPY_P2P -> PRE_COPY + * STOP -> RUNNING_P2P + */ + if ((cur == VFIO_DEVICE_STATE_RUNNING && + new == VFIO_DEVICE_STATE_RUNNING_P2P) || + (cur == VFIO_DEVICE_STATE_RUNNING_P2P && + (new == VFIO_DEVICE_STATE_RUNNING || + new == VFIO_DEVICE_STATE_STOP)) || + (cur == VFIO_DEVICE_STATE_PRE_COPY && + new == VFIO_DEVICE_STATE_PRE_COPY_P2P) || + (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && + new == VFIO_DEVICE_STATE_PRE_COPY) || + (cur == VFIO_DEVICE_STATE_STOP && + new == VFIO_DEVICE_STATE_RUNNING_P2P)) + return NULL; + + /* + * The following state transitions simply close migration files, + * with the exception of RESUMING -> STOP, which needs to load + * the state first. + * + * RESUMING -> STOP + * PRE_COPY -> RUNNING + * PRE_COPY_P2P -> RUNNING_P2P + * STOP_COPY -> STOP + */ + if (cur == VFIO_DEVICE_STATE_RESUMING && + new == VFIO_DEVICE_STATE_STOP) { + int ret; + + ret = mtty_load_state(mdev_state); + if (ret) + return ERR_PTR(ret); + mtty_disable_files(mdev_state); + return NULL; + } + + if ((cur == VFIO_DEVICE_STATE_PRE_COPY && + new == VFIO_DEVICE_STATE_RUNNING) || + (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && + new == VFIO_DEVICE_STATE_RUNNING_P2P) || + (cur == VFIO_DEVICE_STATE_STOP_COPY && + new == VFIO_DEVICE_STATE_STOP)) { + mtty_disable_files(mdev_state); + return NULL; + } + + /* + * The following state transitions return migration files. + * + * RUNNING -> PRE_COPY + * RUNNING_P2P -> PRE_COPY_P2P + * STOP -> STOP_COPY + * STOP -> RESUMING + * PRE_COPY_P2P -> STOP_COPY + */ + if ((cur == VFIO_DEVICE_STATE_RUNNING && + new == VFIO_DEVICE_STATE_PRE_COPY) || + (cur == VFIO_DEVICE_STATE_RUNNING_P2P && + new == VFIO_DEVICE_STATE_PRE_COPY_P2P) || + (cur == VFIO_DEVICE_STATE_STOP && + new == VFIO_DEVICE_STATE_STOP_COPY) || + (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && + new == VFIO_DEVICE_STATE_STOP_COPY)) { + struct mtty_migration_file *migf; + + migf = mtty_save_device_data(mdev_state, new); + if (IS_ERR(migf)) + return ERR_CAST(migf); + + if (migf) { + get_file(migf->filp); + + return migf->filp; + } + return NULL; + } + + if (cur == VFIO_DEVICE_STATE_STOP && + new == VFIO_DEVICE_STATE_RESUMING) { + struct mtty_migration_file *migf; + + migf = mtty_resume_device_data(mdev_state); + if (IS_ERR(migf)) + return ERR_CAST(migf); + + get_file(migf->filp); + + return migf->filp; + } + + /* vfio_mig_get_next_state() does not use arcs other than the above */ + WARN_ON(true); + return ERR_PTR(-EINVAL); +} + +static struct file *mtty_set_state(struct vfio_device *vdev, + enum vfio_device_mig_state new_state) +{ + struct mdev_state *mdev_state = + container_of(vdev, struct mdev_state, vdev); + struct file *ret = NULL; + + dev_dbg(vdev->dev, "%s -> %d\n", __func__, new_state); + + mutex_lock(&mdev_state->state_mutex); + while (mdev_state->state != new_state) { + enum vfio_device_mig_state next_state; + int rc = vfio_mig_get_next_state(vdev, mdev_state->state, + new_state, &next_state); + if (rc) { + ret = ERR_PTR(rc); + break; + } + + ret = mtty_step_state(mdev_state, next_state); + if (IS_ERR(ret)) + break; + + mdev_state->state = next_state; + + if (WARN_ON(ret && new_state != next_state)) { + fput(ret); + ret = ERR_PTR(-EINVAL); + break; + } + } + mtty_state_mutex_unlock(mdev_state); + return ret; +} + +static int mtty_get_state(struct vfio_device *vdev, + enum vfio_device_mig_state *current_state) +{ + struct mdev_state *mdev_state = + container_of(vdev, struct mdev_state, vdev); + + mutex_lock(&mdev_state->state_mutex); + *current_state = mdev_state->state; + mtty_state_mutex_unlock(mdev_state); + return 0; +} + +static int mtty_get_data_size(struct vfio_device *vdev, + unsigned long *stop_copy_length) +{ + struct mdev_state *mdev_state = + container_of(vdev, struct mdev_state, vdev); + + *stop_copy_length = mtty_data_size(mdev_state); + return 0; +} + +static const struct vfio_migration_ops mtty_migration_ops = { + .migration_set_state = mtty_set_state, + .migration_get_state = mtty_get_state, + .migration_get_data_size = mtty_get_data_size, +}; + +static int mtty_log_start(struct vfio_device *vdev, + struct rb_root_cached *ranges, + u32 nnodes, u64 *page_size) +{ + return 0; +} + +static int mtty_log_stop(struct vfio_device *vdev) +{ + return 0; +} + +static int mtty_log_read_and_clear(struct vfio_device *vdev, + unsigned long iova, unsigned long length, + struct iova_bitmap *dirty) +{ + return 0; +} + +static const struct vfio_log_ops mtty_log_ops = { + .log_start = mtty_log_start, + .log_stop = mtty_log_stop, + .log_read_and_clear = mtty_log_read_and_clear, +}; + static int mtty_init_dev(struct vfio_device *vdev) { struct mdev_state *mdev_state = @@ -775,6 +1343,16 @@ static int mtty_init_dev(struct vfio_device *vdev) mutex_init(&mdev_state->ops_lock); mdev_state->mdev = mdev; mtty_create_config_space(mdev_state); + + mutex_init(&mdev_state->state_mutex); + mutex_init(&mdev_state->reset_mutex); + vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | + VFIO_MIGRATION_P2P | + VFIO_MIGRATION_PRE_COPY; + vdev->mig_ops = &mtty_migration_ops; + vdev->log_ops = &mtty_log_ops; + mdev_state->state = VFIO_DEVICE_STATE_RUNNING; + return 0; err_nr_ports: @@ -808,6 +1386,8 @@ static void mtty_release_dev(struct vfio_device *vdev) struct mdev_state *mdev_state = container_of(vdev, struct mdev_state, vdev); + mutex_destroy(&mdev_state->reset_mutex); + mutex_destroy(&mdev_state->state_mutex); atomic_add(mdev_state->nr_ports, &mdev_avail_ports); kfree(mdev_state->vconfig); } @@ -824,6 +1404,15 @@ static int mtty_reset(struct mdev_state *mdev_state) { pr_info("%s: called\n", __func__); + mutex_lock(&mdev_state->reset_mutex); + mdev_state->deferred_reset = true; + if (!mutex_trylock(&mdev_state->state_mutex)) { + mutex_unlock(&mdev_state->reset_mutex); + return 0; + } + mutex_unlock(&mdev_state->reset_mutex); + mtty_state_mutex_unlock(mdev_state); + return 0; } @@ -1350,6 +1939,7 @@ static void mtty_close(struct vfio_device *vdev) struct mdev_state *mdev_state = container_of(vdev, struct mdev_state, vdev); + mtty_disable_files(mdev_state); mtty_disable_intx(mdev_state); mtty_disable_msi(mdev_state); }