From patchwork Tue Sep 22 16:04:01 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stefan Hajnoczi X-Patchwork-Id: 304750 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.8 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI, MIME_BASE64_TEXT,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 35E4FC4363D for ; Tue, 22 Sep 2020 16:13:28 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id A9C1222206 for ; Tue, 22 Sep 2020 16:13:27 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="LOJBk6JV" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org A9C1222206 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=redhat.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:40010 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1kKkv0-00049B-Lo for qemu-devel@archiver.kernel.org; Tue, 22 Sep 2020 12:13:26 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:46946) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kKkmg-0003Qs-AF for qemu-devel@nongnu.org; Tue, 22 Sep 2020 12:04:50 -0400 Received: from us-smtp-delivery-124.mimecast.com ([63.128.21.124]:47901) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.90_1) (envelope-from ) id 1kKkmb-0005g3-FQ for qemu-devel@nongnu.org; Tue, 22 Sep 2020 12:04:49 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1600790684; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=BN0mDWS0Jks4TTWCUyAWyxyS9BNNtn+o/qsNSIbuj10=; b=LOJBk6JVxzepnirfZ2G2EgkUeRIS+iAdF72+3SR+nVe2+tbxz320cJp4qNE9wkCq0kdIt7 haELs0itz9YbCcacb5aAk3C4Xb+sLdFte+aDDqVFsPoQXzVjr9o8QnhSHfBb7leG+zGdhC s5JXRvJgK6vcKuRI39mU815UcP6Uicw= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-488-1AACv8jUOZq1g5PwrpJ_uw-1; Tue, 22 Sep 2020 12:04:42 -0400 X-MC-Unique: 1AACv8jUOZq1g5PwrpJ_uw-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 4CC75802EA5; Tue, 22 Sep 2020 16:04:41 +0000 (UTC) Received: from localhost (ovpn-115-55.ams2.redhat.com [10.36.115.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id 943765C1A3; Tue, 22 Sep 2020 16:04:40 +0000 (UTC) From: Stefan Hajnoczi To: qemu-devel@nongnu.org Subject: [PATCH 11/11] block/export: convert vhost-user-blk server to block export API Date: Tue, 22 Sep 2020 17:04:01 +0100 Message-Id: <20200922160401.294055-12-stefanha@redhat.com> In-Reply-To: <20200922160401.294055-1-stefanha@redhat.com> References: <20200922160401.294055-1-stefanha@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=stefanha@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Received-SPF: pass client-ip=63.128.21.124; envelope-from=stefanha@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/09/22 02:07:04 X-ACL-Warn: Detected OS = Linux 2.2.x-3.x [generic] [fuzzy] X-Spam_score_int: -17 X-Spam_score: -1.8 X-Spam_bar: - X-Spam_report: (-1.8 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-1.455, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, MIME_BASE64_TEXT=1.741, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H5=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=unavailable autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Kevin Wolf , qemu-block@nongnu.org, Markus Armbruster , Coiby Xu , mreitz@redhat.com, Stefan Hajnoczi Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Use the new QAPI block exports API instead of defining our own QOM objects. This is a large change because the lifecycle of VuBlockDev needs to follow BlockExportDriver. QOM properties are replaced by QAPI options objects. VuBlockDev is renamed VuBlkExport and contains a BlockExport field. Several fields can be dropped since BlockExport already has equivalents. The file names and meson build integration will be adjusted in a future patch. libvhost-user should probably be built as a static library that is linked into QEMU instead of as a .c file that results in duplicate compilation. The new command-line syntax is: $ qemu-storage-daemon \ --blockdev file,node-name=drive0,filename=test.img \ --export vhost-user-blk,node-name=drive0,id=export0,unix-socket=/tmp/vhost-user-blk.sock Note that unix-socket is optional because we may wish to accept chardevs too in the future. Signed-off-by: Stefan Hajnoczi --- qapi/block-export.json | 19 +- block/export/vhost-user-blk-server.h | 23 +- block/export/export.c | 8 +- block/export/vhost-user-blk-server.c | 461 ++++++++------------------- block/export/meson.build | 1 + block/meson.build | 1 - 6 files changed, 156 insertions(+), 357 deletions(-) diff --git a/qapi/block-export.json b/qapi/block-export.json index ace0d66e17..840dcbe833 100644 --- a/qapi/block-export.json +++ b/qapi/block-export.json @@ -84,6 +84,19 @@ 'data': { '*name': 'str', '*description': 'str', '*bitmap': 'str' } } +## +# @BlockExportOptionsVhostUserBlk: +# +# A vhost-user-blk block export. +# +# @unix-socket: Path where the vhost-user UNIX domain socket will be created. +# @logical-block-size: Logical block size in bytes. +# +# Since: 5.2 +## +{ 'struct': 'BlockExportOptionsVhostUserBlk', + 'data': { '*unix-socket': 'str', '*logical-block-size': 'size' } } + ## # @NbdServerAddOptions: # @@ -180,11 +193,12 @@ # An enumeration of block export types # # @nbd: NBD export +# @vhost-user-blk: vhost-user-blk export (since 5.2) # # Since: 4.2 ## { 'enum': 'BlockExportType', - 'data': [ 'nbd' ] } + 'data': [ 'nbd', 'vhost-user-blk' ] } ## # @BlockExportOptions: @@ -213,7 +227,8 @@ '*writethrough': 'bool' }, 'discriminator': 'type', 'data': { - 'nbd': 'BlockExportOptionsNbd' + 'nbd': 'BlockExportOptionsNbd', + 'vhost-user-blk': 'BlockExportOptionsVhostUserBlk' } } ## diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h index f06f37c4c8..fcf46fc8a5 100644 --- a/block/export/vhost-user-blk-server.h +++ b/block/export/vhost-user-blk-server.h @@ -10,27 +10,10 @@ #ifndef VHOST_USER_BLK_SERVER_H #define VHOST_USER_BLK_SERVER_H -#include "util/vhost-user-server.h" -typedef struct VuBlockDev VuBlockDev; -#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server" -#define VHOST_USER_BLK_SERVER(obj) \ - OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER) +#include "block/export.h" -/* vhost user block device */ -struct VuBlockDev { - Object parent_obj; - char *node_name; - SocketAddress *addr; - AioContext *ctx; - VuServer vu_server; - bool running; - uint32_t blk_size; - BlockBackend *backend; - QIOChannelSocket *sioc; - QTAILQ_ENTRY(VuBlockDev) next; - struct virtio_blk_config blkcfg; - bool writable; -}; +/* For block/export/export.c */ +extern const BlockExportDriver blk_exp_vhost_user_blk; #endif /* VHOST_USER_BLK_SERVER_H */ diff --git a/block/export/export.c b/block/export/export.c index 87516d1e05..d0c7590911 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -17,6 +17,9 @@ #include "sysemu/block-backend.h" #include "block/export.h" #include "block/nbd.h" +#if CONFIG_LINUX +#include "block/export/vhost-user-blk-server.h" +#endif #include "qapi/error.h" #include "qapi/qapi-commands-block-export.h" #include "qapi/qapi-events-block-export.h" @@ -24,6 +27,9 @@ static const BlockExportDriver *blk_exp_drivers[] = { &blk_exp_nbd, +#if CONFIG_LINUX + &blk_exp_vhost_user_blk, +#endif }; /* Only accessed from the main thread */ @@ -123,7 +129,7 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) assert(drv->instance_size >= sizeof(BlockExport)); exp = g_malloc0(drv->instance_size); *exp = (BlockExport) { - .drv = &blk_exp_nbd, + .drv = drv, .refcount = 1, .user_owned = true, .id = g_strdup(export->id), diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c index 44d3c45fa2..9908b3287e 100644 --- a/block/export/vhost-user-blk-server.c +++ b/block/export/vhost-user-blk-server.c @@ -11,6 +11,9 @@ */ #include "qemu/osdep.h" #include "block/block.h" +#include "contrib/libvhost-user/libvhost-user.h" +#include "standard-headers/linux/virtio_blk.h" +#include "util/vhost-user-server.h" #include "vhost-user-blk-server.h" #include "qapi/error.h" #include "qom/object_interfaces.h" @@ -24,7 +27,7 @@ struct virtio_blk_inhdr { unsigned char status; }; -typedef struct VuBlockReq { +typedef struct VuBlkReq { VuVirtqElement elem; int64_t sector_num; size_t size; @@ -32,9 +35,19 @@ typedef struct VuBlockReq { struct virtio_blk_outhdr out; VuServer *server; struct VuVirtq *vq; -} VuBlockReq; +} VuBlkReq; -static void vu_block_req_complete(VuBlockReq *req) +/* vhost user block device */ +typedef struct { + BlockExport export; + VuServer vu_server; + uint32_t blk_size; + QIOChannelSocket *sioc; + struct virtio_blk_config blkcfg; + bool writable; +} VuBlkExport; + +static void vu_blk_req_complete(VuBlkReq *req) { VuDev *vu_dev = &req->server->vu_dev; @@ -45,14 +58,9 @@ static void vu_block_req_complete(VuBlockReq *req) free(req); } -static VuBlockDev *get_vu_block_device_by_server(VuServer *server) -{ - return container_of(server, VuBlockDev, vu_server); -} - static int coroutine_fn -vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, - uint32_t iovcnt, uint32_t type) +vu_blk_discard_write_zeroes(BlockBackend *blk, struct iovec *iov, + uint32_t iovcnt, uint32_t type) { struct virtio_blk_discard_write_zeroes desc; ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc)); @@ -61,16 +69,14 @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); uint64_t range[2] = { le64_to_cpu(desc.sector) << 9, le32_to_cpu(desc.num_sectors) << 9 }; if (type == VIRTIO_BLK_T_DISCARD) { - if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) { + if (blk_co_pdiscard(blk, range[0], range[1]) == 0) { return 0; } } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) { - if (blk_co_pwrite_zeroes(vdev_blk->backend, - range[0], range[1], 0) == 0) { + if (blk_co_pwrite_zeroes(blk, range[0], range[1], 0) == 0) { return 0; } } @@ -78,22 +84,15 @@ vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov, return -EINVAL; } -static int coroutine_fn vu_block_flush(VuBlockReq *req) +static void coroutine_fn vu_blk_virtio_process_req(void *opaque) { - VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server); - BlockBackend *backend = vdev_blk->backend; - return blk_co_flush(backend); -} - -static void coroutine_fn vu_block_virtio_process_req(void *opaque) -{ - VuBlockReq *req = opaque; + VuBlkReq *req = opaque; VuServer *server = req->server; VuVirtqElement *elem = &req->elem; uint32_t type; - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - BlockBackend *backend = vdev_blk->backend; + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + BlockBackend *blk = vexp->export.blk; struct iovec *in_iov = elem->in_sg; struct iovec *out_iov = elem->out_sg; @@ -133,16 +132,19 @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) bool is_write = type & VIRTIO_BLK_T_OUT; req->sector_num = le64_to_cpu(req->out.sector); - int64_t offset = req->sector_num * vdev_blk->blk_size; + if (is_write && !vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + int64_t offset = req->sector_num * vexp->blk_size; QEMUIOVector qiov; if (is_write) { qemu_iovec_init_external(&qiov, out_iov, out_num); - ret = blk_co_pwritev(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_pwritev(blk, offset, qiov.size, &qiov, 0); } else { qemu_iovec_init_external(&qiov, in_iov, in_num); - ret = blk_co_preadv(backend, offset, qiov.size, - &qiov, 0); + ret = blk_co_preadv(blk, offset, qiov.size, &qiov, 0); } if (ret >= 0) { req->in->status = VIRTIO_BLK_S_OK; @@ -152,7 +154,7 @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } case VIRTIO_BLK_T_FLUSH: - if (vu_block_flush(req) == 0) { + if (blk_co_flush(blk) == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { req->in->status = VIRTIO_BLK_S_IOERR; @@ -169,8 +171,13 @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) case VIRTIO_BLK_T_DISCARD: case VIRTIO_BLK_T_WRITE_ZEROES: { int rc; - rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1], - out_num, type); + + if (!vexp->writable) { + req->in->status = VIRTIO_BLK_S_IOERR; + break; + } + + rc = vu_blk_discard_write_zeroes(blk, &elem->out_sg[1], out_num, type); if (rc == 0) { req->in->status = VIRTIO_BLK_S_OK; } else { @@ -183,22 +190,22 @@ static void coroutine_fn vu_block_virtio_process_req(void *opaque) break; } - vu_block_req_complete(req); + vu_blk_req_complete(req); return; err: - free(elem); + free(req); } -static void vu_block_process_vq(VuDev *vu_dev, int idx) +static void vu_blk_process_vq(VuDev *vu_dev, int idx) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); VuVirtq *vq = vu_get_queue(vu_dev, idx); while (1) { - VuBlockReq *req; + VuBlkReq *req; - req = vu_queue_pop(vu_dev, vq, sizeof(VuBlockReq)); + req = vu_queue_pop(vu_dev, vq, sizeof(VuBlkReq)); if (!req) { break; } @@ -207,26 +214,26 @@ static void vu_block_process_vq(VuDev *vu_dev, int idx) req->vq = vq; Coroutine *co = - qemu_coroutine_create(vu_block_virtio_process_req, req); + qemu_coroutine_create(vu_blk_virtio_process_req, req); qemu_coroutine_enter(co); } } -static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started) +static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started) { VuVirtq *vq; assert(vu_dev); vq = vu_get_queue(vu_dev, idx); - vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL); + vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL); } -static uint64_t vu_block_get_features(VuDev *dev) +static uint64_t vu_blk_get_features(VuDev *dev) { uint64_t features; VuServer *server = container_of(dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); features = 1ull << VIRTIO_BLK_F_SIZE_MAX | 1ull << VIRTIO_BLK_F_SEG_MAX | 1ull << VIRTIO_BLK_F_TOPOLOGY | @@ -240,35 +247,35 @@ static uint64_t vu_block_get_features(VuDev *dev) 1ull << VIRTIO_RING_F_EVENT_IDX | 1ull << VHOST_USER_F_PROTOCOL_FEATURES; - if (!vdev_blk->writable) { + if (!vexp->writable) { features |= 1ull << VIRTIO_BLK_F_RO; } return features; } -static uint64_t vu_block_get_protocol_features(VuDev *dev) +static uint64_t vu_blk_get_protocol_features(VuDev *dev) { return 1ull << VHOST_USER_PROTOCOL_F_CONFIG | 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD; } static int -vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) +vu_blk_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len) { + /* TODO blkcfg must be little-endian for VIRTIO 1.0 */ VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); - memcpy(config, &vdev_blk->blkcfg, len); - + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); + memcpy(config, &vexp->blkcfg, len); return 0; } static int -vu_block_set_config(VuDev *vu_dev, const uint8_t *data, +vu_blk_set_config(VuDev *vu_dev, const uint8_t *data, uint32_t offset, uint32_t size, uint32_t flags) { VuServer *server = container_of(vu_dev, VuServer, vu_dev); - VuBlockDev *vdev_blk = get_vu_block_device_by_server(server); + VuBlkExport *vexp = container_of(server, VuBlkExport, vu_server); uint8_t wce; /* don't support live migration */ @@ -282,8 +289,8 @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, } wce = *data; - vdev_blk->blkcfg.wce = wce; - blk_set_enable_write_cache(vdev_blk->backend, wce); + vexp->blkcfg.wce = wce; + blk_set_enable_write_cache(vexp->export.blk, wce); return 0; } @@ -295,7 +302,7 @@ vu_block_set_config(VuDev *vu_dev, const uint8_t *data, * of vu_process_message. * */ -static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) +static int vu_blk_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) { if (vmsg->request == VHOST_USER_NONE) { dev->panic(dev, "disconnect"); @@ -304,29 +311,29 @@ static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply) return false; } -static const VuDevIface vu_block_iface = { - .get_features = vu_block_get_features, - .queue_set_started = vu_block_queue_set_started, - .get_protocol_features = vu_block_get_protocol_features, - .get_config = vu_block_get_config, - .set_config = vu_block_set_config, - .process_msg = vu_block_process_msg, +static const VuDevIface vu_blk_iface = { + .get_features = vu_blk_get_features, + .queue_set_started = vu_blk_queue_set_started, + .get_protocol_features = vu_blk_get_protocol_features, + .get_config = vu_blk_get_config, + .set_config = vu_blk_set_config, + .process_msg = vu_blk_process_msg, }; static void blk_aio_attached(AioContext *ctx, void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_attach_aio_context(&vub_dev->vu_server, ctx); + VuBlkExport *vexp = opaque; + vhost_user_server_attach_aio_context(&vexp->vu_server, ctx); } static void blk_aio_detach(void *opaque) { - VuBlockDev *vub_dev = opaque; - vhost_user_server_detach_aio_context(&vub_dev->vu_server); + VuBlkExport *vexp = opaque; + vhost_user_server_detach_aio_context(&vexp->vu_server); } static void -vu_block_initialize_config(BlockDriverState *bs, +vu_blk_initialize_config(BlockDriverState *bs, struct virtio_blk_config *config, uint32_t blk_size) { config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS; @@ -343,290 +350,78 @@ vu_block_initialize_config(BlockDriverState *bs, config->max_write_zeroes_seg = 1; } -static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp) +static void vu_blk_exp_request_shutdown(BlockExport *exp) { + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - BlockBackend *blk; - Error *local_error = NULL; - const char *node_name = vu_block_device->node_name; - bool writable = vu_block_device->writable; - uint64_t perm = BLK_PERM_CONSISTENT_READ; - int ret; - - AioContext *ctx; - - BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error); - - if (!bs) { - error_propagate(errp, local_error); - return NULL; - } - - if (bdrv_is_read_only(bs)) { - writable = false; - } - - if (writable) { - perm |= BLK_PERM_WRITE; - } - - ctx = bdrv_get_aio_context(bs); - aio_context_acquire(ctx); - bdrv_invalidate_cache(bs, NULL); - aio_context_release(ctx); - - /* - * Don't allow resize while the vhost user server is running, - * otherwise we don't care what happens with the node. - */ - blk = blk_new(bdrv_get_aio_context(bs), perm, - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | - BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); - ret = blk_insert_bs(blk, bs, errp); - - if (ret < 0) { - goto fail; - } - - blk_set_enable_write_cache(blk, false); - - blk_set_allow_aio_context_change(blk, true); - - vu_block_device->blkcfg.wce = 0; - vu_block_device->backend = blk; - if (!vu_block_device->blk_size) { - vu_block_device->blk_size = BDRV_SECTOR_SIZE; - } - vu_block_device->blkcfg.blk_size = vu_block_device->blk_size; - blk_set_guest_block_size(blk, vu_block_device->blk_size); - vu_block_initialize_config(bs, &vu_block_device->blkcfg, - vu_block_device->blk_size); - return vu_block_device; - -fail: - blk_unref(blk); - return NULL; -} - -static void vu_block_deinit(VuBlockDev *vu_block_device) -{ - if (vu_block_device->backend) { - blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - } - - blk_unref(vu_block_device->backend); -} - -static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device) -{ - vhost_user_server_stop(&vu_block_device->vu_server); - vu_block_deinit(vu_block_device); -} - -static void vhost_user_blk_server_start(VuBlockDev *vu_block_device, - Error **errp) -{ - AioContext *ctx; - SocketAddress *addr = vu_block_device->addr; - - if (!vu_block_init(vu_block_device, errp)) { - return; - } - - ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend)); - - if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx, - VHOST_USER_BLK_MAX_QUEUES, &vu_block_iface, - errp)) { - goto error; - } - - blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached, - blk_aio_detach, vu_block_device); - vu_block_device->running = true; - return; - - error: - vu_block_deinit(vu_block_device); -} - -static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp) -{ - if (vus->running) { - error_setg(errp, "The property can't be modified " - "while the server is running"); - return false; - } - return true; -} - -static void vu_set_node_name(Object *obj, const char *value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->node_name) { - g_free(vus->node_name); - } - - vus->node_name = g_strdup(value); -} - -static char *vu_get_node_name(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->node_name); -} - -static void free_socket_addr(SocketAddress *addr) -{ - g_free(addr->u.q_unix.path); - g_free(addr); -} - -static void vu_set_unix_socket(Object *obj, const char *value, - Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - if (vus->addr) { - free_socket_addr(vus->addr); - } - - SocketAddress *addr = g_new0(SocketAddress, 1); - addr->type = SOCKET_ADDRESS_TYPE_UNIX; - addr->u.q_unix.path = g_strdup(value); - vus->addr = addr; + vhost_user_server_stop(&vexp->vu_server); } -static char *vu_get_unix_socket(Object *obj, Error **errp) +static int vu_blk_exp_create(BlockExport *exp, BlockExportOptions *opts, + Error **errp) { - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return g_strdup(vus->addr->u.q_unix.path); -} - -static bool vu_get_block_writable(Object *obj, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - return vus->writable; -} - -static void vu_set_block_writable(Object *obj, bool value, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - - if (!vu_prop_modifiable(vus, errp)) { - return; - } - - vus->writable = value; -} - -static void vu_get_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - uint32_t value = vus->blk_size; - - visit_type_uint32(v, name, &value, errp); -} - -static void vu_set_blk_size(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj); - + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); + BlockExportOptionsVhostUserBlk *vu_opts = &opts->u.vhost_user_blk; + SocketAddress addr = { + .type = SOCKET_ADDRESS_TYPE_UNIX, + .u.q_unix.path = vu_opts->has_unix_socket ? + vu_opts->unix_socket : + NULL, + }; Error *local_err = NULL; - uint32_t value; + uint64_t logical_block_size; - if (!vu_prop_modifiable(vus, errp)) { - return; + if (!vu_opts->has_unix_socket) { + error_setg(errp, "Missing unix-socket path to listen on"); + return -EINVAL; } - visit_type_uint32(v, name, &value, &local_err); - if (local_err) { - goto out; - } + vexp->writable = opts->writable; + vexp->blkcfg.wce = 0; - check_block_size(object_get_typename(obj), name, value, &local_err); + if (vu_opts->has_logical_block_size) { + logical_block_size = vu_opts->logical_block_size; + } else { + logical_block_size = BDRV_SECTOR_SIZE; + } + check_block_size(exp->id, "logical-block-size", logical_block_size, + &local_err); if (local_err) { - goto out; + error_propagate(errp, local_err); + return -EINVAL; + } + vexp->blk_size = logical_block_size; + blk_set_guest_block_size(exp->blk, logical_block_size); + vu_blk_initialize_config(blk_bs(exp->blk), &vexp->blkcfg, + logical_block_size); + + blk_set_allow_aio_context_change(exp->blk, true); + blk_add_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); + + if (!vhost_user_server_start(&vexp->vu_server, &addr, exp->ctx, + VHOST_USER_BLK_MAX_QUEUES, &vu_blk_iface, + errp)) { + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, + blk_aio_detach, vexp); + return -EADDRNOTAVAIL; } - vus->blk_size = value; - -out: - error_propagate(errp, local_err); -} - -static void vhost_user_blk_server_instance_finalize(Object *obj) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_stop(vub); - - /* - * Unlike object_property_add_str, object_class_property_add_str - * doesn't have a release method. Thus manual memory freeing is - * needed. - */ - free_socket_addr(vub->addr); - g_free(vub->node_name); -} - -static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp) -{ - VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj); - - vhost_user_blk_server_start(vub, errp); + return 0; } -static void vhost_user_blk_server_class_init(ObjectClass *klass, - void *class_data) +static void vu_blk_exp_delete(BlockExport *exp) { - UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass); - ucc->complete = vhost_user_blk_server_complete; - - object_class_property_add_bool(klass, "writable", - vu_get_block_writable, - vu_set_block_writable); - - object_class_property_add_str(klass, "node-name", - vu_get_node_name, - vu_set_node_name); - - object_class_property_add_str(klass, "unix-socket", - vu_get_unix_socket, - vu_set_unix_socket); + VuBlkExport *vexp = container_of(exp, VuBlkExport, export); - object_class_property_add(klass, "logical-block-size", "uint32", - vu_get_blk_size, vu_set_blk_size, - NULL, NULL); + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, blk_aio_detach, + vexp); } -static const TypeInfo vhost_user_blk_server_info = { - .name = TYPE_VHOST_USER_BLK_SERVER, - .parent = TYPE_OBJECT, - .instance_size = sizeof(VuBlockDev), - .instance_finalize = vhost_user_blk_server_instance_finalize, - .class_init = vhost_user_blk_server_class_init, - .interfaces = (InterfaceInfo[]) { - {TYPE_USER_CREATABLE}, - {} - }, +const BlockExportDriver blk_exp_vhost_user_blk = { + .type = BLOCK_EXPORT_TYPE_VHOST_USER_BLK, + .instance_size = sizeof(VuBlkExport), + .create = vu_blk_exp_create, + .delete = vu_blk_exp_delete, + .request_shutdown = vu_blk_exp_request_shutdown, }; - -static void vhost_user_blk_server_register_types(void) -{ - type_register_static(&vhost_user_blk_server_info); -} - -type_init(vhost_user_blk_server_register_types) diff --git a/block/export/meson.build b/block/export/meson.build index 558ef35d38..ef3a9576f7 100644 --- a/block/export/meson.build +++ b/block/export/meson.build @@ -1 +1,2 @@ block_ss.add(files('export.c')) +block_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-server.c', '../../contrib/libvhost-user/libvhost-user.c')) diff --git a/block/meson.build b/block/meson.build index cd52104c84..0b38dc36f7 100644 --- a/block/meson.build +++ b/block/meson.build @@ -60,7 +60,6 @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c') block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit]) block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c')) block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c')) -block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c')) block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c')) block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c')) block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c'))