From 437fd90c0250dee670290f9b714253671a990160 Mon Sep 17 00:00:00 2001 From: José Pekkarinen Date: Wed, 18 May 2016 13:18:31 +0300 Subject: These changes are the raw update to qemu-2.6. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Collission happened in the following patches: migration: do cleanup operation after completion(738df5b9) Bug fix.(1750c932f86) kvmclock: add a new function to update env->tsc.(b52baab2) The code provided by the patches was already in the upstreamed version. Change-Id: I3cc11841a6a76ae20887b2e245710199e1ea7f9a Signed-off-by: José Pekkarinen --- qemu/nbd/Makefile.objs | 1 + qemu/nbd/client.c | 745 +++++++++++++++++++++++++++ qemu/nbd/common.c | 96 ++++ qemu/nbd/nbd-internal.h | 124 +++++ qemu/nbd/server.c | 1290 +++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 2256 insertions(+) create mode 100644 qemu/nbd/Makefile.objs create mode 100644 qemu/nbd/client.c create mode 100644 qemu/nbd/common.c create mode 100644 qemu/nbd/nbd-internal.h create mode 100644 qemu/nbd/server.c (limited to 'qemu/nbd') diff --git a/qemu/nbd/Makefile.objs b/qemu/nbd/Makefile.objs new file mode 100644 index 000000000..eb3dd4461 --- /dev/null +++ b/qemu/nbd/Makefile.objs @@ -0,0 +1 @@ +block-obj-y += server.o client.o common.o diff --git a/qemu/nbd/client.c b/qemu/nbd/client.c new file mode 100644 index 000000000..48f2a21f3 --- /dev/null +++ b/qemu/nbd/client.c @@ -0,0 +1,745 @@ +/* + * Copyright (C) 2005 Anthony Liguori + * + * Network Block Device Client Side + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; under version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "nbd-internal.h" + +static int nbd_errno_to_system_errno(int err) +{ + switch (err) { + case NBD_SUCCESS: + return 0; + case NBD_EPERM: + return EPERM; + case NBD_EIO: + return EIO; + case NBD_ENOMEM: + return ENOMEM; + case NBD_ENOSPC: + return ENOSPC; + case NBD_EINVAL: + default: + return EINVAL; + } +} + +/* Definitions for opaque data types */ + +static QTAILQ_HEAD(, NBDExport) exports = QTAILQ_HEAD_INITIALIZER(exports); + +/* That's all folks */ + +/* Basic flow for negotiation + + Server Client + Negotiate + + or + + Server Client + Negotiate #1 + Option + Negotiate #2 + + ---- + + followed by + + Server Client + Request + Response + Request + Response + ... + ... + Request (type == 2) + +*/ + + +/* If type represents success, return 1 without further action. + * If type represents an error reply, consume the rest of the packet on ioc. + * Then return 0 for unsupported (so the client can fall back to + * other approaches), or -1 with errp set for other errors. + */ +static int nbd_handle_reply_err(QIOChannel *ioc, uint32_t opt, uint32_t type, + Error **errp) +{ + uint32_t len; + char *msg = NULL; + int result = -1; + + if (!(type & (1 << 31))) { + return 1; + } + + if (read_sync(ioc, &len, sizeof(len)) != sizeof(len)) { + error_setg(errp, "failed to read option length"); + return -1; + } + len = be32_to_cpu(len); + if (len) { + if (len > NBD_MAX_BUFFER_SIZE) { + error_setg(errp, "server's error message is too long"); + goto cleanup; + } + msg = g_malloc(len + 1); + if (read_sync(ioc, msg, len) != len) { + error_setg(errp, "failed to read option error message"); + goto cleanup; + } + msg[len] = '\0'; + } + + switch (type) { + case NBD_REP_ERR_UNSUP: + TRACE("server doesn't understand request %d, attempting fallback", + opt); + result = 0; + goto cleanup; + + case NBD_REP_ERR_POLICY: + error_setg(errp, "Denied by server for option %x", opt); + break; + + case NBD_REP_ERR_INVALID: + error_setg(errp, "Invalid data length for option %x", opt); + break; + + case NBD_REP_ERR_TLS_REQD: + error_setg(errp, "TLS negotiation required before option %x", opt); + break; + + default: + error_setg(errp, "Unknown error code when asking for option %x", opt); + break; + } + + if (msg) { + error_append_hint(errp, "%s\n", msg); + } + + cleanup: + g_free(msg); + return result; +} + +static int nbd_receive_list(QIOChannel *ioc, char **name, Error **errp) +{ + uint64_t magic; + uint32_t opt; + uint32_t type; + uint32_t len; + uint32_t namelen; + int error; + + *name = NULL; + if (read_sync(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + error_setg(errp, "failed to read list option magic"); + return -1; + } + magic = be64_to_cpu(magic); + if (magic != NBD_REP_MAGIC) { + error_setg(errp, "Unexpected option list magic"); + return -1; + } + if (read_sync(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + error_setg(errp, "failed to read list option"); + return -1; + } + opt = be32_to_cpu(opt); + if (opt != NBD_OPT_LIST) { + error_setg(errp, "Unexpected option type %x expected %x", + opt, NBD_OPT_LIST); + return -1; + } + + if (read_sync(ioc, &type, sizeof(type)) != sizeof(type)) { + error_setg(errp, "failed to read list option type"); + return -1; + } + type = be32_to_cpu(type); + error = nbd_handle_reply_err(ioc, opt, type, errp); + if (error <= 0) { + return error; + } + + if (read_sync(ioc, &len, sizeof(len)) != sizeof(len)) { + error_setg(errp, "failed to read option length"); + return -1; + } + len = be32_to_cpu(len); + + if (type == NBD_REP_ACK) { + if (len != 0) { + error_setg(errp, "length too long for option end"); + return -1; + } + } else if (type == NBD_REP_SERVER) { + if (len < sizeof(namelen) || len > NBD_MAX_BUFFER_SIZE) { + error_setg(errp, "incorrect option length"); + return -1; + } + if (read_sync(ioc, &namelen, sizeof(namelen)) != sizeof(namelen)) { + error_setg(errp, "failed to read option name length"); + return -1; + } + namelen = be32_to_cpu(namelen); + len -= sizeof(namelen); + if (len < namelen) { + error_setg(errp, "incorrect option name length"); + return -1; + } + if (namelen > 255) { + error_setg(errp, "export name length too long %d", namelen); + return -1; + } + + *name = g_new0(char, namelen + 1); + if (read_sync(ioc, *name, namelen) != namelen) { + error_setg(errp, "failed to read export name"); + g_free(*name); + *name = NULL; + return -1; + } + (*name)[namelen] = '\0'; + len -= namelen; + if (len) { + char *buf = g_malloc(len + 1); + if (read_sync(ioc, buf, len) != len) { + error_setg(errp, "failed to read export description"); + g_free(*name); + g_free(buf); + *name = NULL; + return -1; + } + buf[len] = '\0'; + TRACE("Ignoring export description: %s", buf); + g_free(buf); + } + } else { + error_setg(errp, "Unexpected reply type %x expected %x", + type, NBD_REP_SERVER); + return -1; + } + return 1; +} + + +static int nbd_receive_query_exports(QIOChannel *ioc, + const char *wantname, + Error **errp) +{ + uint64_t magic = cpu_to_be64(NBD_OPTS_MAGIC); + uint32_t opt = cpu_to_be32(NBD_OPT_LIST); + uint32_t length = 0; + bool foundExport = false; + + TRACE("Querying export list"); + if (write_sync(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + error_setg(errp, "Failed to send list option magic"); + return -1; + } + + if (write_sync(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + error_setg(errp, "Failed to send list option number"); + return -1; + } + + if (write_sync(ioc, &length, sizeof(length)) != sizeof(length)) { + error_setg(errp, "Failed to send list option length"); + return -1; + } + + TRACE("Reading available export names"); + while (1) { + char *name = NULL; + int ret = nbd_receive_list(ioc, &name, errp); + + if (ret < 0) { + g_free(name); + name = NULL; + return -1; + } + if (ret == 0) { + /* Server doesn't support export listing, so + * we will just assume an export with our + * wanted name exists */ + foundExport = true; + break; + } + if (name == NULL) { + TRACE("End of export name list"); + break; + } + if (g_str_equal(name, wantname)) { + foundExport = true; + TRACE("Found desired export name '%s'", name); + } else { + TRACE("Ignored export name '%s'", name); + } + g_free(name); + } + + if (!foundExport) { + error_setg(errp, "No export with name '%s' available", wantname); + return -1; + } + + return 0; +} + +static QIOChannel *nbd_receive_starttls(QIOChannel *ioc, + QCryptoTLSCreds *tlscreds, + const char *hostname, Error **errp) +{ + uint64_t magic = cpu_to_be64(NBD_OPTS_MAGIC); + uint32_t opt = cpu_to_be32(NBD_OPT_STARTTLS); + uint32_t length = 0; + uint32_t type; + QIOChannelTLS *tioc; + struct NBDTLSHandshakeData data = { 0 }; + + TRACE("Requesting TLS from server"); + if (write_sync(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + error_setg(errp, "Failed to send option magic"); + return NULL; + } + + if (write_sync(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + error_setg(errp, "Failed to send option number"); + return NULL; + } + + if (write_sync(ioc, &length, sizeof(length)) != sizeof(length)) { + error_setg(errp, "Failed to send option length"); + return NULL; + } + + TRACE("Getting TLS reply from server1"); + if (read_sync(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + error_setg(errp, "failed to read option magic"); + return NULL; + } + magic = be64_to_cpu(magic); + if (magic != NBD_REP_MAGIC) { + error_setg(errp, "Unexpected option magic"); + return NULL; + } + TRACE("Getting TLS reply from server2"); + if (read_sync(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + error_setg(errp, "failed to read option"); + return NULL; + } + opt = be32_to_cpu(opt); + if (opt != NBD_OPT_STARTTLS) { + error_setg(errp, "Unexpected option type %x expected %x", + opt, NBD_OPT_STARTTLS); + return NULL; + } + + TRACE("Getting TLS reply from server"); + if (read_sync(ioc, &type, sizeof(type)) != sizeof(type)) { + error_setg(errp, "failed to read option type"); + return NULL; + } + type = be32_to_cpu(type); + if (type != NBD_REP_ACK) { + error_setg(errp, "Server rejected request to start TLS %x", + type); + return NULL; + } + + TRACE("Getting TLS reply from server"); + if (read_sync(ioc, &length, sizeof(length)) != sizeof(length)) { + error_setg(errp, "failed to read option length"); + return NULL; + } + length = be32_to_cpu(length); + if (length != 0) { + error_setg(errp, "Start TLS reponse was not zero %x", + length); + return NULL; + } + + TRACE("TLS request approved, setting up TLS"); + tioc = qio_channel_tls_new_client(ioc, tlscreds, hostname, errp); + if (!tioc) { + return NULL; + } + data.loop = g_main_loop_new(g_main_context_default(), FALSE); + TRACE("Starting TLS hanshake"); + qio_channel_tls_handshake(tioc, + nbd_tls_handshake, + &data, + NULL); + + if (!data.complete) { + g_main_loop_run(data.loop); + } + g_main_loop_unref(data.loop); + if (data.error) { + error_propagate(errp, data.error); + object_unref(OBJECT(tioc)); + return NULL; + } + + return QIO_CHANNEL(tioc); +} + + +int nbd_receive_negotiate(QIOChannel *ioc, const char *name, uint32_t *flags, + QCryptoTLSCreds *tlscreds, const char *hostname, + QIOChannel **outioc, + off_t *size, Error **errp) +{ + char buf[256]; + uint64_t magic, s; + int rc; + + TRACE("Receiving negotiation tlscreds=%p hostname=%s.", + tlscreds, hostname ? hostname : ""); + + rc = -EINVAL; + + if (outioc) { + *outioc = NULL; + } + if (tlscreds && !outioc) { + error_setg(errp, "Output I/O channel required for TLS"); + goto fail; + } + + if (read_sync(ioc, buf, 8) != 8) { + error_setg(errp, "Failed to read data"); + goto fail; + } + + buf[8] = '\0'; + if (strlen(buf) == 0) { + error_setg(errp, "Server connection closed unexpectedly"); + goto fail; + } + + TRACE("Magic is %c%c%c%c%c%c%c%c", + qemu_isprint(buf[0]) ? buf[0] : '.', + qemu_isprint(buf[1]) ? buf[1] : '.', + qemu_isprint(buf[2]) ? buf[2] : '.', + qemu_isprint(buf[3]) ? buf[3] : '.', + qemu_isprint(buf[4]) ? buf[4] : '.', + qemu_isprint(buf[5]) ? buf[5] : '.', + qemu_isprint(buf[6]) ? buf[6] : '.', + qemu_isprint(buf[7]) ? buf[7] : '.'); + + if (memcmp(buf, "NBDMAGIC", 8) != 0) { + error_setg(errp, "Invalid magic received"); + goto fail; + } + + if (read_sync(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + error_setg(errp, "Failed to read magic"); + goto fail; + } + magic = be64_to_cpu(magic); + TRACE("Magic is 0x%" PRIx64, magic); + + if (magic == NBD_OPTS_MAGIC) { + uint32_t clientflags = 0; + uint32_t opt; + uint32_t namesize; + uint16_t globalflags; + uint16_t exportflags; + bool fixedNewStyle = false; + + if (read_sync(ioc, &globalflags, sizeof(globalflags)) != + sizeof(globalflags)) { + error_setg(errp, "Failed to read server flags"); + goto fail; + } + globalflags = be16_to_cpu(globalflags); + *flags = globalflags << 16; + TRACE("Global flags are %x", globalflags); + if (globalflags & NBD_FLAG_FIXED_NEWSTYLE) { + fixedNewStyle = true; + TRACE("Server supports fixed new style"); + clientflags |= NBD_FLAG_C_FIXED_NEWSTYLE; + } + /* client requested flags */ + clientflags = cpu_to_be32(clientflags); + if (write_sync(ioc, &clientflags, sizeof(clientflags)) != + sizeof(clientflags)) { + error_setg(errp, "Failed to send clientflags field"); + goto fail; + } + if (tlscreds) { + if (fixedNewStyle) { + *outioc = nbd_receive_starttls(ioc, tlscreds, hostname, errp); + if (!*outioc) { + goto fail; + } + ioc = *outioc; + } else { + error_setg(errp, "Server does not support STARTTLS"); + goto fail; + } + } + if (!name) { + TRACE("Using default NBD export name \"\""); + name = ""; + } + if (fixedNewStyle) { + /* Check our desired export is present in the + * server export list. Since NBD_OPT_EXPORT_NAME + * cannot return an error message, running this + * query gives us good error reporting if the + * server required TLS + */ + if (nbd_receive_query_exports(ioc, name, errp) < 0) { + goto fail; + } + } + /* write the export name */ + magic = cpu_to_be64(magic); + if (write_sync(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + error_setg(errp, "Failed to send export name magic"); + goto fail; + } + opt = cpu_to_be32(NBD_OPT_EXPORT_NAME); + if (write_sync(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + error_setg(errp, "Failed to send export name option number"); + goto fail; + } + namesize = cpu_to_be32(strlen(name)); + if (write_sync(ioc, &namesize, sizeof(namesize)) != + sizeof(namesize)) { + error_setg(errp, "Failed to send export name length"); + goto fail; + } + if (write_sync(ioc, (char *)name, strlen(name)) != strlen(name)) { + error_setg(errp, "Failed to send export name"); + goto fail; + } + + if (read_sync(ioc, &s, sizeof(s)) != sizeof(s)) { + error_setg(errp, "Failed to read export length"); + goto fail; + } + *size = be64_to_cpu(s); + TRACE("Size is %" PRIu64, *size); + + if (read_sync(ioc, &exportflags, sizeof(exportflags)) != + sizeof(exportflags)) { + error_setg(errp, "Failed to read export flags"); + goto fail; + } + exportflags = be16_to_cpu(exportflags); + *flags |= exportflags; + TRACE("Export flags are %x", exportflags); + } else if (magic == NBD_CLIENT_MAGIC) { + if (name) { + error_setg(errp, "Server does not support export names"); + goto fail; + } + if (tlscreds) { + error_setg(errp, "Server does not support STARTTLS"); + goto fail; + } + + if (read_sync(ioc, &s, sizeof(s)) != sizeof(s)) { + error_setg(errp, "Failed to read export length"); + goto fail; + } + *size = be64_to_cpu(s); + TRACE("Size is %" PRIu64, *size); + + if (read_sync(ioc, flags, sizeof(*flags)) != sizeof(*flags)) { + error_setg(errp, "Failed to read export flags"); + goto fail; + } + *flags = be32_to_cpup(flags); + } else { + error_setg(errp, "Bad magic received"); + goto fail; + } + + if (read_sync(ioc, &buf, 124) != 124) { + error_setg(errp, "Failed to read reserved block"); + goto fail; + } + rc = 0; + +fail: + return rc; +} + +#ifdef __linux__ +int nbd_init(int fd, QIOChannelSocket *sioc, uint32_t flags, off_t size) +{ + TRACE("Setting NBD socket"); + + if (ioctl(fd, NBD_SET_SOCK, sioc->fd) < 0) { + int serrno = errno; + LOG("Failed to set NBD socket"); + return -serrno; + } + + TRACE("Setting block size to %lu", (unsigned long)BDRV_SECTOR_SIZE); + + if (ioctl(fd, NBD_SET_BLKSIZE, (size_t)BDRV_SECTOR_SIZE) < 0) { + int serrno = errno; + LOG("Failed setting NBD block size"); + return -serrno; + } + + TRACE("Setting size to %zd block(s)", (size_t)(size / BDRV_SECTOR_SIZE)); + + if (ioctl(fd, NBD_SET_SIZE_BLOCKS, (size_t)(size / BDRV_SECTOR_SIZE)) < 0) { + int serrno = errno; + LOG("Failed setting size (in blocks)"); + return -serrno; + } + + if (ioctl(fd, NBD_SET_FLAGS, flags) < 0) { + if (errno == ENOTTY) { + int read_only = (flags & NBD_FLAG_READ_ONLY) != 0; + TRACE("Setting readonly attribute"); + + if (ioctl(fd, BLKROSET, (unsigned long) &read_only) < 0) { + int serrno = errno; + LOG("Failed setting read-only attribute"); + return -serrno; + } + } else { + int serrno = errno; + LOG("Failed setting flags"); + return -serrno; + } + } + + TRACE("Negotiation ended"); + + return 0; +} + +int nbd_client(int fd) +{ + int ret; + int serrno; + + TRACE("Doing NBD loop"); + + ret = ioctl(fd, NBD_DO_IT); + if (ret < 0 && errno == EPIPE) { + /* NBD_DO_IT normally returns EPIPE when someone has disconnected + * the socket via NBD_DISCONNECT. We do not want to return 1 in + * that case. + */ + ret = 0; + } + serrno = errno; + + TRACE("NBD loop returned %d: %s", ret, strerror(serrno)); + + TRACE("Clearing NBD queue"); + ioctl(fd, NBD_CLEAR_QUE); + + TRACE("Clearing NBD socket"); + ioctl(fd, NBD_CLEAR_SOCK); + + errno = serrno; + return ret; +} +#else +int nbd_init(int fd, QIOChannelSocket *ioc, uint32_t flags, off_t size) +{ + return -ENOTSUP; +} + +int nbd_client(int fd) +{ + return -ENOTSUP; +} +#endif + +ssize_t nbd_send_request(QIOChannel *ioc, struct nbd_request *request) +{ + uint8_t buf[NBD_REQUEST_SIZE]; + ssize_t ret; + + TRACE("Sending request to server: " + "{ .from = %" PRIu64", .len = %u, .handle = %" PRIu64", .type=%i}", + request->from, request->len, request->handle, request->type); + + cpu_to_be32w((uint32_t*)buf, NBD_REQUEST_MAGIC); + cpu_to_be32w((uint32_t*)(buf + 4), request->type); + cpu_to_be64w((uint64_t*)(buf + 8), request->handle); + cpu_to_be64w((uint64_t*)(buf + 16), request->from); + cpu_to_be32w((uint32_t*)(buf + 24), request->len); + + ret = write_sync(ioc, buf, sizeof(buf)); + if (ret < 0) { + return ret; + } + + if (ret != sizeof(buf)) { + LOG("writing to socket failed"); + return -EINVAL; + } + return 0; +} + +ssize_t nbd_receive_reply(QIOChannel *ioc, struct nbd_reply *reply) +{ + uint8_t buf[NBD_REPLY_SIZE]; + uint32_t magic; + ssize_t ret; + + ret = read_sync(ioc, buf, sizeof(buf)); + if (ret < 0) { + return ret; + } + + if (ret != sizeof(buf)) { + LOG("read failed"); + return -EINVAL; + } + + /* Reply + [ 0 .. 3] magic (NBD_REPLY_MAGIC) + [ 4 .. 7] error (0 == no error) + [ 7 .. 15] handle + */ + + magic = be32_to_cpup((uint32_t*)buf); + reply->error = be32_to_cpup((uint32_t*)(buf + 4)); + reply->handle = be64_to_cpup((uint64_t*)(buf + 8)); + + reply->error = nbd_errno_to_system_errno(reply->error); + + TRACE("Got reply: " + "{ magic = 0x%x, .error = %d, handle = %" PRIu64" }", + magic, reply->error, reply->handle); + + if (magic != NBD_REPLY_MAGIC) { + LOG("invalid magic (got 0x%x)", magic); + return -EINVAL; + } + return 0; +} + diff --git a/qemu/nbd/common.c b/qemu/nbd/common.c new file mode 100644 index 000000000..8ddb2dd2f --- /dev/null +++ b/qemu/nbd/common.c @@ -0,0 +1,96 @@ +/* + * Copyright (C) 2005 Anthony Liguori + * + * Network Block Device Common Code + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; under version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "nbd-internal.h" + +ssize_t nbd_wr_syncv(QIOChannel *ioc, + struct iovec *iov, + size_t niov, + size_t offset, + size_t length, + bool do_read) +{ + ssize_t done = 0; + Error *local_err = NULL; + struct iovec *local_iov = g_new(struct iovec, niov); + struct iovec *local_iov_head = local_iov; + unsigned int nlocal_iov = niov; + + nlocal_iov = iov_copy(local_iov, nlocal_iov, + iov, niov, + offset, length); + + while (nlocal_iov > 0) { + ssize_t len; + if (do_read) { + len = qio_channel_readv(ioc, local_iov, nlocal_iov, &local_err); + } else { + len = qio_channel_writev(ioc, local_iov, nlocal_iov, &local_err); + } + if (len == QIO_CHANNEL_ERR_BLOCK) { + if (qemu_in_coroutine()) { + /* XXX figure out if we can create a variant on + * qio_channel_yield() that works with AIO contexts + * and consider using that in this branch */ + qemu_coroutine_yield(); + } else if (done) { + /* XXX this is needed by nbd_reply_ready. */ + qio_channel_wait(ioc, + do_read ? G_IO_IN : G_IO_OUT); + } else { + return -EAGAIN; + } + continue; + } + if (len < 0) { + TRACE("I/O error: %s", error_get_pretty(local_err)); + error_free(local_err); + /* XXX handle Error objects */ + done = -EIO; + goto cleanup; + } + + if (do_read && len == 0) { + break; + } + + iov_discard_front(&local_iov, &nlocal_iov, len); + done += len; + } + + cleanup: + g_free(local_iov_head); + return done; +} + + +void nbd_tls_handshake(Object *src, + Error *err, + void *opaque) +{ + struct NBDTLSHandshakeData *data = opaque; + + if (err) { + TRACE("TLS failed %s", error_get_pretty(err)); + data->error = error_copy(err); + } + data->complete = true; + g_main_loop_quit(data->loop); +} diff --git a/qemu/nbd/nbd-internal.h b/qemu/nbd/nbd-internal.h new file mode 100644 index 000000000..379153561 --- /dev/null +++ b/qemu/nbd/nbd-internal.h @@ -0,0 +1,124 @@ +/* + * NBD Internal Declarations + * + * Copyright (C) 2016 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef NBD_INTERNAL_H +#define NBD_INTERNAL_H +#include "block/nbd.h" +#include "sysemu/block-backend.h" +#include "io/channel-tls.h" + +#include "qemu/coroutine.h" +#include "qemu/iov.h" + +#ifndef _WIN32 +#include +#endif +#if defined(__sun__) || defined(__HAIKU__) +#include +#endif + +#ifdef __linux__ +#include +#endif + +#include "qemu/queue.h" +#include "qemu/main-loop.h" + +/* #define DEBUG_NBD */ + +#ifdef DEBUG_NBD +#define DEBUG_NBD_PRINT 1 +#else +#define DEBUG_NBD_PRINT 0 +#endif + +#define TRACE(msg, ...) do { \ + if (DEBUG_NBD_PRINT) { \ + LOG(msg, ## __VA_ARGS__); \ + } \ +} while (0) + +#define LOG(msg, ...) do { \ + fprintf(stderr, "%s:%s():L%d: " msg "\n", \ + __FILE__, __FUNCTION__, __LINE__, ## __VA_ARGS__); \ +} while (0) + +/* This is all part of the "official" NBD API. + * + * The most up-to-date documentation is available at: + * https://github.com/yoe/nbd/blob/master/doc/proto.txt + */ + +#define NBD_REQUEST_SIZE (4 + 4 + 8 + 8 + 4) +#define NBD_REPLY_SIZE (4 + 4 + 8) +#define NBD_REQUEST_MAGIC 0x25609513 +#define NBD_REPLY_MAGIC 0x67446698 +#define NBD_OPTS_MAGIC 0x49484156454F5054LL +#define NBD_CLIENT_MAGIC 0x0000420281861253LL +#define NBD_REP_MAGIC 0x3e889045565a9LL + +#define NBD_SET_SOCK _IO(0xab, 0) +#define NBD_SET_BLKSIZE _IO(0xab, 1) +#define NBD_SET_SIZE _IO(0xab, 2) +#define NBD_DO_IT _IO(0xab, 3) +#define NBD_CLEAR_SOCK _IO(0xab, 4) +#define NBD_CLEAR_QUE _IO(0xab, 5) +#define NBD_PRINT_DEBUG _IO(0xab, 6) +#define NBD_SET_SIZE_BLOCKS _IO(0xab, 7) +#define NBD_DISCONNECT _IO(0xab, 8) +#define NBD_SET_TIMEOUT _IO(0xab, 9) +#define NBD_SET_FLAGS _IO(0xab, 10) + +#define NBD_OPT_EXPORT_NAME (1) +#define NBD_OPT_ABORT (2) +#define NBD_OPT_LIST (3) +#define NBD_OPT_PEEK_EXPORT (4) +#define NBD_OPT_STARTTLS (5) + +/* NBD errors are based on errno numbers, so there is a 1:1 mapping, + * but only a limited set of errno values is specified in the protocol. + * Everything else is squashed to EINVAL. + */ +#define NBD_SUCCESS 0 +#define NBD_EPERM 1 +#define NBD_EIO 5 +#define NBD_ENOMEM 12 +#define NBD_EINVAL 22 +#define NBD_ENOSPC 28 + +static inline ssize_t read_sync(QIOChannel *ioc, void *buffer, size_t size) +{ + struct iovec iov = { .iov_base = buffer, .iov_len = size }; + /* Sockets are kept in blocking mode in the negotiation phase. After + * that, a non-readable socket simply means that another thread stole + * our request/reply. Synchronization is done with recv_coroutine, so + * that this is coroutine-safe. + */ + return nbd_wr_syncv(ioc, &iov, 1, 0, size, true); +} + +static inline ssize_t write_sync(QIOChannel *ioc, void *buffer, size_t size) +{ + struct iovec iov = { .iov_base = buffer, .iov_len = size }; + + return nbd_wr_syncv(ioc, &iov, 1, 0, size, false); +} + +struct NBDTLSHandshakeData { + GMainLoop *loop; + bool complete; + Error *error; +}; + + +void nbd_tls_handshake(Object *src, + Error *err, + void *opaque); + +#endif diff --git a/qemu/nbd/server.c b/qemu/nbd/server.c new file mode 100644 index 000000000..2184c64fe --- /dev/null +++ b/qemu/nbd/server.c @@ -0,0 +1,1290 @@ +/* + * Copyright (C) 2005 Anthony Liguori + * + * Network Block Device Server Side + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; under version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "nbd-internal.h" + +static int system_errno_to_nbd_errno(int err) +{ + switch (err) { + case 0: + return NBD_SUCCESS; + case EPERM: + case EROFS: + return NBD_EPERM; + case EIO: + return NBD_EIO; + case ENOMEM: + return NBD_ENOMEM; +#ifdef EDQUOT + case EDQUOT: +#endif + case EFBIG: + case ENOSPC: + return NBD_ENOSPC; + case EINVAL: + default: + return NBD_EINVAL; + } +} + +/* Definitions for opaque data types */ + +typedef struct NBDRequest NBDRequest; + +struct NBDRequest { + QSIMPLEQ_ENTRY(NBDRequest) entry; + NBDClient *client; + uint8_t *data; +}; + +struct NBDExport { + int refcount; + void (*close)(NBDExport *exp); + + BlockBackend *blk; + char *name; + off_t dev_offset; + off_t size; + uint32_t nbdflags; + QTAILQ_HEAD(, NBDClient) clients; + QTAILQ_ENTRY(NBDExport) next; + + AioContext *ctx; + + Notifier eject_notifier; +}; + +static QTAILQ_HEAD(, NBDExport) exports = QTAILQ_HEAD_INITIALIZER(exports); + +struct NBDClient { + int refcount; + void (*close)(NBDClient *client); + + NBDExport *exp; + QCryptoTLSCreds *tlscreds; + char *tlsaclname; + QIOChannelSocket *sioc; /* The underlying data channel */ + QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */ + + Coroutine *recv_coroutine; + + CoMutex send_lock; + Coroutine *send_coroutine; + + bool can_read; + + QTAILQ_ENTRY(NBDClient) next; + int nb_requests; + bool closing; +}; + +/* That's all folks */ + +static void nbd_set_handlers(NBDClient *client); +static void nbd_unset_handlers(NBDClient *client); +static void nbd_update_can_read(NBDClient *client); + +static gboolean nbd_negotiate_continue(QIOChannel *ioc, + GIOCondition condition, + void *opaque) +{ + qemu_coroutine_enter(opaque, NULL); + return TRUE; +} + +static ssize_t nbd_negotiate_read(QIOChannel *ioc, void *buffer, size_t size) +{ + ssize_t ret; + guint watch; + + assert(qemu_in_coroutine()); + /* Negotiation are always in main loop. */ + watch = qio_channel_add_watch(ioc, + G_IO_IN, + nbd_negotiate_continue, + qemu_coroutine_self(), + NULL); + ret = read_sync(ioc, buffer, size); + g_source_remove(watch); + return ret; + +} + +static ssize_t nbd_negotiate_write(QIOChannel *ioc, void *buffer, size_t size) +{ + ssize_t ret; + guint watch; + + assert(qemu_in_coroutine()); + /* Negotiation are always in main loop. */ + watch = qio_channel_add_watch(ioc, + G_IO_OUT, + nbd_negotiate_continue, + qemu_coroutine_self(), + NULL); + ret = write_sync(ioc, buffer, size); + g_source_remove(watch); + return ret; +} + +static ssize_t nbd_negotiate_drop_sync(QIOChannel *ioc, size_t size) +{ + ssize_t ret, dropped = size; + uint8_t *buffer = g_malloc(MIN(65536, size)); + + while (size > 0) { + ret = nbd_negotiate_read(ioc, buffer, MIN(65536, size)); + if (ret < 0) { + g_free(buffer); + return ret; + } + + assert(ret <= size); + size -= ret; + } + + g_free(buffer); + return dropped; +} + +/* Basic flow for negotiation + + Server Client + Negotiate + + or + + Server Client + Negotiate #1 + Option + Negotiate #2 + + ---- + + followed by + + Server Client + Request + Response + Request + Response + ... + ... + Request (type == 2) + +*/ + +static int nbd_negotiate_send_rep(QIOChannel *ioc, uint32_t type, uint32_t opt) +{ + uint64_t magic; + uint32_t len; + + TRACE("Reply opt=%x type=%x", type, opt); + + magic = cpu_to_be64(NBD_REP_MAGIC); + if (nbd_negotiate_write(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + LOG("write failed (rep magic)"); + return -EINVAL; + } + opt = cpu_to_be32(opt); + if (nbd_negotiate_write(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + LOG("write failed (rep opt)"); + return -EINVAL; + } + type = cpu_to_be32(type); + if (nbd_negotiate_write(ioc, &type, sizeof(type)) != sizeof(type)) { + LOG("write failed (rep type)"); + return -EINVAL; + } + len = cpu_to_be32(0); + if (nbd_negotiate_write(ioc, &len, sizeof(len)) != sizeof(len)) { + LOG("write failed (rep data length)"); + return -EINVAL; + } + return 0; +} + +static int nbd_negotiate_send_rep_list(QIOChannel *ioc, NBDExport *exp) +{ + uint64_t magic, name_len; + uint32_t opt, type, len; + + TRACE("Advertizing export name '%s'", exp->name ? exp->name : ""); + name_len = strlen(exp->name); + magic = cpu_to_be64(NBD_REP_MAGIC); + if (nbd_negotiate_write(ioc, &magic, sizeof(magic)) != sizeof(magic)) { + LOG("write failed (magic)"); + return -EINVAL; + } + opt = cpu_to_be32(NBD_OPT_LIST); + if (nbd_negotiate_write(ioc, &opt, sizeof(opt)) != sizeof(opt)) { + LOG("write failed (opt)"); + return -EINVAL; + } + type = cpu_to_be32(NBD_REP_SERVER); + if (nbd_negotiate_write(ioc, &type, sizeof(type)) != sizeof(type)) { + LOG("write failed (reply type)"); + return -EINVAL; + } + len = cpu_to_be32(name_len + sizeof(len)); + if (nbd_negotiate_write(ioc, &len, sizeof(len)) != sizeof(len)) { + LOG("write failed (length)"); + return -EINVAL; + } + len = cpu_to_be32(name_len); + if (nbd_negotiate_write(ioc, &len, sizeof(len)) != sizeof(len)) { + LOG("write failed (length)"); + return -EINVAL; + } + if (nbd_negotiate_write(ioc, exp->name, name_len) != name_len) { + LOG("write failed (buffer)"); + return -EINVAL; + } + return 0; +} + +static int nbd_negotiate_handle_list(NBDClient *client, uint32_t length) +{ + NBDExport *exp; + + if (length) { + if (nbd_negotiate_drop_sync(client->ioc, length) != length) { + return -EIO; + } + return nbd_negotiate_send_rep(client->ioc, + NBD_REP_ERR_INVALID, NBD_OPT_LIST); + } + + /* For each export, send a NBD_REP_SERVER reply. */ + QTAILQ_FOREACH(exp, &exports, next) { + if (nbd_negotiate_send_rep_list(client->ioc, exp)) { + return -EINVAL; + } + } + /* Finish with a NBD_REP_ACK. */ + return nbd_negotiate_send_rep(client->ioc, NBD_REP_ACK, NBD_OPT_LIST); +} + +static int nbd_negotiate_handle_export_name(NBDClient *client, uint32_t length) +{ + int rc = -EINVAL; + char name[256]; + + /* Client sends: + [20 .. xx] export name (length bytes) + */ + TRACE("Checking length"); + if (length > 255) { + LOG("Bad length received"); + goto fail; + } + if (nbd_negotiate_read(client->ioc, name, length) != length) { + LOG("read failed"); + goto fail; + } + name[length] = '\0'; + + TRACE("Client requested export '%s'", name); + + client->exp = nbd_export_find(name); + if (!client->exp) { + LOG("export not found"); + goto fail; + } + + QTAILQ_INSERT_TAIL(&client->exp->clients, client, next); + nbd_export_get(client->exp); + rc = 0; +fail: + return rc; +} + + +static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client, + uint32_t length) +{ + QIOChannel *ioc; + QIOChannelTLS *tioc; + struct NBDTLSHandshakeData data = { 0 }; + + TRACE("Setting up TLS"); + ioc = client->ioc; + if (length) { + if (nbd_negotiate_drop_sync(ioc, length) != length) { + return NULL; + } + nbd_negotiate_send_rep(ioc, NBD_REP_ERR_INVALID, NBD_OPT_STARTTLS); + return NULL; + } + + nbd_negotiate_send_rep(client->ioc, NBD_REP_ACK, NBD_OPT_STARTTLS); + + tioc = qio_channel_tls_new_server(ioc, + client->tlscreds, + client->tlsaclname, + NULL); + if (!tioc) { + return NULL; + } + + TRACE("Starting TLS handshake"); + data.loop = g_main_loop_new(g_main_context_default(), FALSE); + qio_channel_tls_handshake(tioc, + nbd_tls_handshake, + &data, + NULL); + + if (!data.complete) { + g_main_loop_run(data.loop); + } + g_main_loop_unref(data.loop); + if (data.error) { + object_unref(OBJECT(tioc)); + error_free(data.error); + return NULL; + } + + return QIO_CHANNEL(tioc); +} + + +static int nbd_negotiate_options(NBDClient *client) +{ + uint32_t flags; + bool fixedNewstyle = false; + + /* Client sends: + [ 0 .. 3] client flags + + [ 0 .. 7] NBD_OPTS_MAGIC + [ 8 .. 11] NBD option + [12 .. 15] Data length + ... Rest of request + + [ 0 .. 7] NBD_OPTS_MAGIC + [ 8 .. 11] Second NBD option + [12 .. 15] Data length + ... Rest of request + */ + + if (nbd_negotiate_read(client->ioc, &flags, sizeof(flags)) != + sizeof(flags)) { + LOG("read failed"); + return -EIO; + } + TRACE("Checking client flags"); + be32_to_cpus(&flags); + if (flags & NBD_FLAG_C_FIXED_NEWSTYLE) { + TRACE("Support supports fixed newstyle handshake"); + fixedNewstyle = true; + flags &= ~NBD_FLAG_C_FIXED_NEWSTYLE; + } + if (flags != 0) { + TRACE("Unknown client flags 0x%x received", flags); + return -EIO; + } + + while (1) { + int ret; + uint32_t clientflags, length; + uint64_t magic; + + if (nbd_negotiate_read(client->ioc, &magic, sizeof(magic)) != + sizeof(magic)) { + LOG("read failed"); + return -EINVAL; + } + TRACE("Checking opts magic"); + if (magic != be64_to_cpu(NBD_OPTS_MAGIC)) { + LOG("Bad magic received"); + return -EINVAL; + } + + if (nbd_negotiate_read(client->ioc, &clientflags, + sizeof(clientflags)) != sizeof(clientflags)) { + LOG("read failed"); + return -EINVAL; + } + clientflags = be32_to_cpu(clientflags); + + if (nbd_negotiate_read(client->ioc, &length, sizeof(length)) != + sizeof(length)) { + LOG("read failed"); + return -EINVAL; + } + length = be32_to_cpu(length); + + TRACE("Checking option 0x%x", clientflags); + if (client->tlscreds && + client->ioc == (QIOChannel *)client->sioc) { + QIOChannel *tioc; + if (!fixedNewstyle) { + TRACE("Unsupported option 0x%x", clientflags); + return -EINVAL; + } + switch (clientflags) { + case NBD_OPT_STARTTLS: + tioc = nbd_negotiate_handle_starttls(client, length); + if (!tioc) { + return -EIO; + } + object_unref(OBJECT(client->ioc)); + client->ioc = QIO_CHANNEL(tioc); + break; + + case NBD_OPT_EXPORT_NAME: + /* No way to return an error to client, so drop connection */ + TRACE("Option 0x%x not permitted before TLS", clientflags); + return -EINVAL; + + default: + TRACE("Option 0x%x not permitted before TLS", clientflags); + if (nbd_negotiate_drop_sync(client->ioc, length) != length) { + return -EIO; + } + nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_TLS_REQD, + clientflags); + break; + } + } else if (fixedNewstyle) { + switch (clientflags) { + case NBD_OPT_LIST: + ret = nbd_negotiate_handle_list(client, length); + if (ret < 0) { + return ret; + } + break; + + case NBD_OPT_ABORT: + return -EINVAL; + + case NBD_OPT_EXPORT_NAME: + return nbd_negotiate_handle_export_name(client, length); + + case NBD_OPT_STARTTLS: + if (nbd_negotiate_drop_sync(client->ioc, length) != length) { + return -EIO; + } + if (client->tlscreds) { + TRACE("TLS already enabled"); + nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_INVALID, + clientflags); + } else { + TRACE("TLS not configured"); + nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_POLICY, + clientflags); + } + break; + default: + TRACE("Unsupported option 0x%x", clientflags); + if (nbd_negotiate_drop_sync(client->ioc, length) != length) { + return -EIO; + } + nbd_negotiate_send_rep(client->ioc, NBD_REP_ERR_UNSUP, + clientflags); + break; + } + } else { + /* + * If broken new-style we should drop the connection + * for anything except NBD_OPT_EXPORT_NAME + */ + switch (clientflags) { + case NBD_OPT_EXPORT_NAME: + return nbd_negotiate_handle_export_name(client, length); + + default: + TRACE("Unsupported option 0x%x", clientflags); + return -EINVAL; + } + } + } +} + +typedef struct { + NBDClient *client; + Coroutine *co; +} NBDClientNewData; + +static coroutine_fn int nbd_negotiate(NBDClientNewData *data) +{ + NBDClient *client = data->client; + char buf[8 + 8 + 8 + 128]; + int rc; + const int myflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_TRIM | + NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA); + bool oldStyle; + + /* Old style negotiation header without options + [ 0 .. 7] passwd ("NBDMAGIC") + [ 8 .. 15] magic (NBD_CLIENT_MAGIC) + [16 .. 23] size + [24 .. 25] server flags (0) + [26 .. 27] export flags + [28 .. 151] reserved (0) + + New style negotiation header with options + [ 0 .. 7] passwd ("NBDMAGIC") + [ 8 .. 15] magic (NBD_OPTS_MAGIC) + [16 .. 17] server flags (0) + ....options sent.... + [18 .. 25] size + [26 .. 27] export flags + [28 .. 151] reserved (0) + */ + + qio_channel_set_blocking(client->ioc, false, NULL); + rc = -EINVAL; + + TRACE("Beginning negotiation."); + memset(buf, 0, sizeof(buf)); + memcpy(buf, "NBDMAGIC", 8); + + oldStyle = client->exp != NULL && !client->tlscreds; + if (oldStyle) { + assert ((client->exp->nbdflags & ~65535) == 0); + stq_be_p(buf + 8, NBD_CLIENT_MAGIC); + stq_be_p(buf + 16, client->exp->size); + stw_be_p(buf + 26, client->exp->nbdflags | myflags); + } else { + stq_be_p(buf + 8, NBD_OPTS_MAGIC); + stw_be_p(buf + 16, NBD_FLAG_FIXED_NEWSTYLE); + } + + if (oldStyle) { + if (client->tlscreds) { + TRACE("TLS cannot be enabled with oldstyle protocol"); + goto fail; + } + if (nbd_negotiate_write(client->ioc, buf, sizeof(buf)) != sizeof(buf)) { + LOG("write failed"); + goto fail; + } + } else { + if (nbd_negotiate_write(client->ioc, buf, 18) != 18) { + LOG("write failed"); + goto fail; + } + rc = nbd_negotiate_options(client); + if (rc != 0) { + LOG("option negotiation failed"); + goto fail; + } + + assert ((client->exp->nbdflags & ~65535) == 0); + stq_be_p(buf + 18, client->exp->size); + stw_be_p(buf + 26, client->exp->nbdflags | myflags); + if (nbd_negotiate_write(client->ioc, buf + 18, sizeof(buf) - 18) != + sizeof(buf) - 18) { + LOG("write failed"); + goto fail; + } + } + + TRACE("Negotiation succeeded."); + rc = 0; +fail: + return rc; +} + +#ifdef __linux__ + +int nbd_disconnect(int fd) +{ + ioctl(fd, NBD_CLEAR_QUE); + ioctl(fd, NBD_DISCONNECT); + ioctl(fd, NBD_CLEAR_SOCK); + return 0; +} + +#else + +int nbd_disconnect(int fd) +{ + return -ENOTSUP; +} +#endif + +static ssize_t nbd_receive_request(QIOChannel *ioc, struct nbd_request *request) +{ + uint8_t buf[NBD_REQUEST_SIZE]; + uint32_t magic; + ssize_t ret; + + ret = read_sync(ioc, buf, sizeof(buf)); + if (ret < 0) { + return ret; + } + + if (ret != sizeof(buf)) { + LOG("read failed"); + return -EINVAL; + } + + /* Request + [ 0 .. 3] magic (NBD_REQUEST_MAGIC) + [ 4 .. 7] type (0 == READ, 1 == WRITE) + [ 8 .. 15] handle + [16 .. 23] from + [24 .. 27] len + */ + + magic = be32_to_cpup((uint32_t*)buf); + request->type = be32_to_cpup((uint32_t*)(buf + 4)); + request->handle = be64_to_cpup((uint64_t*)(buf + 8)); + request->from = be64_to_cpup((uint64_t*)(buf + 16)); + request->len = be32_to_cpup((uint32_t*)(buf + 24)); + + TRACE("Got request: " + "{ magic = 0x%x, .type = %d, from = %" PRIu64" , len = %u }", + magic, request->type, request->from, request->len); + + if (magic != NBD_REQUEST_MAGIC) { + LOG("invalid magic (got 0x%x)", magic); + return -EINVAL; + } + return 0; +} + +static ssize_t nbd_send_reply(QIOChannel *ioc, struct nbd_reply *reply) +{ + uint8_t buf[NBD_REPLY_SIZE]; + ssize_t ret; + + reply->error = system_errno_to_nbd_errno(reply->error); + + TRACE("Sending response to client: { .error = %d, handle = %" PRIu64 " }", + reply->error, reply->handle); + + /* Reply + [ 0 .. 3] magic (NBD_REPLY_MAGIC) + [ 4 .. 7] error (0 == no error) + [ 7 .. 15] handle + */ + stl_be_p(buf, NBD_REPLY_MAGIC); + stl_be_p(buf + 4, reply->error); + stq_be_p(buf + 8, reply->handle); + + ret = write_sync(ioc, buf, sizeof(buf)); + if (ret < 0) { + return ret; + } + + if (ret != sizeof(buf)) { + LOG("writing to socket failed"); + return -EINVAL; + } + return 0; +} + +#define MAX_NBD_REQUESTS 16 + +void nbd_client_get(NBDClient *client) +{ + client->refcount++; +} + +void nbd_client_put(NBDClient *client) +{ + if (--client->refcount == 0) { + /* The last reference should be dropped by client->close, + * which is called by client_close. + */ + assert(client->closing); + + nbd_unset_handlers(client); + object_unref(OBJECT(client->sioc)); + object_unref(OBJECT(client->ioc)); + if (client->tlscreds) { + object_unref(OBJECT(client->tlscreds)); + } + g_free(client->tlsaclname); + if (client->exp) { + QTAILQ_REMOVE(&client->exp->clients, client, next); + nbd_export_put(client->exp); + } + g_free(client); + } +} + +static void client_close(NBDClient *client) +{ + if (client->closing) { + return; + } + + client->closing = true; + + /* Force requests to finish. They will drop their own references, + * then we'll close the socket and free the NBDClient. + */ + qio_channel_shutdown(client->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, + NULL); + + /* Also tell the client, so that they release their reference. */ + if (client->close) { + client->close(client); + } +} + +static NBDRequest *nbd_request_get(NBDClient *client) +{ + NBDRequest *req; + + assert(client->nb_requests <= MAX_NBD_REQUESTS - 1); + client->nb_requests++; + nbd_update_can_read(client); + + req = g_new0(NBDRequest, 1); + nbd_client_get(client); + req->client = client; + return req; +} + +static void nbd_request_put(NBDRequest *req) +{ + NBDClient *client = req->client; + + if (req->data) { + qemu_vfree(req->data); + } + g_free(req); + + client->nb_requests--; + nbd_update_can_read(client); + nbd_client_put(client); +} + +static void blk_aio_attached(AioContext *ctx, void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; + + TRACE("Export %s: Attaching clients to AIO context %p\n", exp->name, ctx); + + exp->ctx = ctx; + + QTAILQ_FOREACH(client, &exp->clients, next) { + nbd_set_handlers(client); + } +} + +static void blk_aio_detach(void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; + + TRACE("Export %s: Detaching clients from AIO context %p\n", exp->name, exp->ctx); + + QTAILQ_FOREACH(client, &exp->clients, next) { + nbd_unset_handlers(client); + } + + exp->ctx = NULL; +} + +static void nbd_eject_notifier(Notifier *n, void *data) +{ + NBDExport *exp = container_of(n, NBDExport, eject_notifier); + nbd_export_close(exp); +} + +NBDExport *nbd_export_new(BlockBackend *blk, off_t dev_offset, off_t size, + uint32_t nbdflags, void (*close)(NBDExport *), + Error **errp) +{ + NBDExport *exp = g_malloc0(sizeof(NBDExport)); + exp->refcount = 1; + QTAILQ_INIT(&exp->clients); + exp->blk = blk; + exp->dev_offset = dev_offset; + exp->nbdflags = nbdflags; + exp->size = size < 0 ? blk_getlength(blk) : size; + if (exp->size < 0) { + error_setg_errno(errp, -exp->size, + "Failed to determine the NBD export's length"); + goto fail; + } + exp->size -= exp->size % BDRV_SECTOR_SIZE; + + exp->close = close; + exp->ctx = blk_get_aio_context(blk); + blk_ref(blk); + blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp); + + exp->eject_notifier.notify = nbd_eject_notifier; + blk_add_remove_bs_notifier(blk, &exp->eject_notifier); + + /* + * NBD exports are used for non-shared storage migration. Make sure + * that BDRV_O_INACTIVE is cleared and the image is ready for write + * access since the export could be available before migration handover. + */ + aio_context_acquire(exp->ctx); + blk_invalidate_cache(blk, NULL); + aio_context_release(exp->ctx); + return exp; + +fail: + g_free(exp); + return NULL; +} + +NBDExport *nbd_export_find(const char *name) +{ + NBDExport *exp; + QTAILQ_FOREACH(exp, &exports, next) { + if (strcmp(name, exp->name) == 0) { + return exp; + } + } + + return NULL; +} + +void nbd_export_set_name(NBDExport *exp, const char *name) +{ + if (exp->name == name) { + return; + } + + nbd_export_get(exp); + if (exp->name != NULL) { + g_free(exp->name); + exp->name = NULL; + QTAILQ_REMOVE(&exports, exp, next); + nbd_export_put(exp); + } + if (name != NULL) { + nbd_export_get(exp); + exp->name = g_strdup(name); + QTAILQ_INSERT_TAIL(&exports, exp, next); + } + nbd_export_put(exp); +} + +void nbd_export_close(NBDExport *exp) +{ + NBDClient *client, *next; + + nbd_export_get(exp); + QTAILQ_FOREACH_SAFE(client, &exp->clients, next, next) { + client_close(client); + } + nbd_export_set_name(exp, NULL); + nbd_export_put(exp); +} + +void nbd_export_get(NBDExport *exp) +{ + assert(exp->refcount > 0); + exp->refcount++; +} + +void nbd_export_put(NBDExport *exp) +{ + assert(exp->refcount > 0); + if (exp->refcount == 1) { + nbd_export_close(exp); + } + + if (--exp->refcount == 0) { + assert(exp->name == NULL); + + if (exp->close) { + exp->close(exp); + } + + if (exp->blk) { + notifier_remove(&exp->eject_notifier); + blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, + blk_aio_detach, exp); + blk_unref(exp->blk); + exp->blk = NULL; + } + + g_free(exp); + } +} + +BlockBackend *nbd_export_get_blockdev(NBDExport *exp) +{ + return exp->blk; +} + +void nbd_export_close_all(void) +{ + NBDExport *exp, *next; + + QTAILQ_FOREACH_SAFE(exp, &exports, next, next) { + nbd_export_close(exp); + } +} + +static ssize_t nbd_co_send_reply(NBDRequest *req, struct nbd_reply *reply, + int len) +{ + NBDClient *client = req->client; + ssize_t rc, ret; + + g_assert(qemu_in_coroutine()); + qemu_co_mutex_lock(&client->send_lock); + client->send_coroutine = qemu_coroutine_self(); + nbd_set_handlers(client); + + if (!len) { + rc = nbd_send_reply(client->ioc, reply); + } else { + qio_channel_set_cork(client->ioc, true); + rc = nbd_send_reply(client->ioc, reply); + if (rc >= 0) { + ret = write_sync(client->ioc, req->data, len); + if (ret != len) { + rc = -EIO; + } + } + qio_channel_set_cork(client->ioc, false); + } + + client->send_coroutine = NULL; + nbd_set_handlers(client); + qemu_co_mutex_unlock(&client->send_lock); + return rc; +} + +static ssize_t nbd_co_receive_request(NBDRequest *req, struct nbd_request *request) +{ + NBDClient *client = req->client; + uint32_t command; + ssize_t rc; + + g_assert(qemu_in_coroutine()); + client->recv_coroutine = qemu_coroutine_self(); + nbd_update_can_read(client); + + rc = nbd_receive_request(client->ioc, request); + if (rc < 0) { + if (rc != -EAGAIN) { + rc = -EIO; + } + goto out; + } + + if ((request->from + request->len) < request->from) { + LOG("integer overflow detected! " + "you're probably being attacked"); + rc = -EINVAL; + goto out; + } + + TRACE("Decoding type"); + + command = request->type & NBD_CMD_MASK_COMMAND; + if (command == NBD_CMD_READ || command == NBD_CMD_WRITE) { + if (request->len > NBD_MAX_BUFFER_SIZE) { + LOG("len (%u) is larger than max len (%u)", + request->len, NBD_MAX_BUFFER_SIZE); + rc = -EINVAL; + goto out; + } + + req->data = blk_try_blockalign(client->exp->blk, request->len); + if (req->data == NULL) { + rc = -ENOMEM; + goto out; + } + } + if (command == NBD_CMD_WRITE) { + TRACE("Reading %u byte(s)", request->len); + + if (read_sync(client->ioc, req->data, request->len) != request->len) { + LOG("reading from socket failed"); + rc = -EIO; + goto out; + } + } + rc = 0; + +out: + client->recv_coroutine = NULL; + nbd_update_can_read(client); + + return rc; +} + +static void nbd_trip(void *opaque) +{ + NBDClient *client = opaque; + NBDExport *exp = client->exp; + NBDRequest *req; + struct nbd_request request; + struct nbd_reply reply; + ssize_t ret; + uint32_t command; + + TRACE("Reading request."); + if (client->closing) { + return; + } + + req = nbd_request_get(client); + ret = nbd_co_receive_request(req, &request); + if (ret == -EAGAIN) { + goto done; + } + if (ret == -EIO) { + goto out; + } + + reply.handle = request.handle; + reply.error = 0; + + if (ret < 0) { + reply.error = -ret; + goto error_reply; + } + command = request.type & NBD_CMD_MASK_COMMAND; + if (command != NBD_CMD_DISC && (request.from + request.len) > exp->size) { + LOG("From: %" PRIu64 ", Len: %u, Size: %" PRIu64 + ", Offset: %" PRIu64 "\n", + request.from, request.len, + (uint64_t)exp->size, (uint64_t)exp->dev_offset); + LOG("requested operation past EOF--bad client?"); + goto invalid_request; + } + + if (client->closing) { + /* + * The client may be closed when we are blocked in + * nbd_co_receive_request() + */ + goto done; + } + + switch (command) { + case NBD_CMD_READ: + TRACE("Request type is READ"); + + if (request.type & NBD_CMD_FLAG_FUA) { + ret = blk_co_flush(exp->blk); + if (ret < 0) { + LOG("flush failed"); + reply.error = -ret; + goto error_reply; + } + } + + ret = blk_pread(exp->blk, request.from + exp->dev_offset, + req->data, request.len); + if (ret < 0) { + LOG("reading from file failed"); + reply.error = -ret; + goto error_reply; + } + + TRACE("Read %u byte(s)", request.len); + if (nbd_co_send_reply(req, &reply, request.len) < 0) + goto out; + break; + case NBD_CMD_WRITE: + TRACE("Request type is WRITE"); + + if (exp->nbdflags & NBD_FLAG_READ_ONLY) { + TRACE("Server is read-only, return error"); + reply.error = EROFS; + goto error_reply; + } + + TRACE("Writing to device"); + + ret = blk_pwrite(exp->blk, request.from + exp->dev_offset, + req->data, request.len); + if (ret < 0) { + LOG("writing to file failed"); + reply.error = -ret; + goto error_reply; + } + + if (request.type & NBD_CMD_FLAG_FUA) { + ret = blk_co_flush(exp->blk); + if (ret < 0) { + LOG("flush failed"); + reply.error = -ret; + goto error_reply; + } + } + + if (nbd_co_send_reply(req, &reply, 0) < 0) { + goto out; + } + break; + case NBD_CMD_DISC: + TRACE("Request type is DISCONNECT"); + errno = 0; + goto out; + case NBD_CMD_FLUSH: + TRACE("Request type is FLUSH"); + + ret = blk_co_flush(exp->blk); + if (ret < 0) { + LOG("flush failed"); + reply.error = -ret; + } + if (nbd_co_send_reply(req, &reply, 0) < 0) { + goto out; + } + break; + case NBD_CMD_TRIM: + TRACE("Request type is TRIM"); + ret = blk_co_discard(exp->blk, (request.from + exp->dev_offset) + / BDRV_SECTOR_SIZE, + request.len / BDRV_SECTOR_SIZE); + if (ret < 0) { + LOG("discard failed"); + reply.error = -ret; + } + if (nbd_co_send_reply(req, &reply, 0) < 0) { + goto out; + } + break; + default: + LOG("invalid request type (%u) received", request.type); + invalid_request: + reply.error = EINVAL; + error_reply: + if (nbd_co_send_reply(req, &reply, 0) < 0) { + goto out; + } + break; + } + + TRACE("Request/Reply complete"); + +done: + nbd_request_put(req); + return; + +out: + nbd_request_put(req); + client_close(client); +} + +static void nbd_read(void *opaque) +{ + NBDClient *client = opaque; + + if (client->recv_coroutine) { + qemu_coroutine_enter(client->recv_coroutine, NULL); + } else { + qemu_coroutine_enter(qemu_coroutine_create(nbd_trip), client); + } +} + +static void nbd_restart_write(void *opaque) +{ + NBDClient *client = opaque; + + qemu_coroutine_enter(client->send_coroutine, NULL); +} + +static void nbd_set_handlers(NBDClient *client) +{ + if (client->exp && client->exp->ctx) { + aio_set_fd_handler(client->exp->ctx, client->sioc->fd, + true, + client->can_read ? nbd_read : NULL, + client->send_coroutine ? nbd_restart_write : NULL, + client); + } +} + +static void nbd_unset_handlers(NBDClient *client) +{ + if (client->exp && client->exp->ctx) { + aio_set_fd_handler(client->exp->ctx, client->sioc->fd, + true, NULL, NULL, NULL); + } +} + +static void nbd_update_can_read(NBDClient *client) +{ + bool can_read = client->recv_coroutine || + client->nb_requests < MAX_NBD_REQUESTS; + + if (can_read != client->can_read) { + client->can_read = can_read; + nbd_set_handlers(client); + + /* There is no need to invoke aio_notify(), since aio_set_fd_handler() + * in nbd_set_handlers() will have taken care of that */ + } +} + +static coroutine_fn void nbd_co_client_start(void *opaque) +{ + NBDClientNewData *data = opaque; + NBDClient *client = data->client; + NBDExport *exp = client->exp; + + if (exp) { + nbd_export_get(exp); + } + if (nbd_negotiate(data)) { + client_close(client); + goto out; + } + qemu_co_mutex_init(&client->send_lock); + nbd_set_handlers(client); + + if (exp) { + QTAILQ_INSERT_TAIL(&exp->clients, client, next); + } +out: + g_free(data); +} + +void nbd_client_new(NBDExport *exp, + QIOChannelSocket *sioc, + QCryptoTLSCreds *tlscreds, + const char *tlsaclname, + void (*close_fn)(NBDClient *)) +{ + NBDClient *client; + NBDClientNewData *data = g_new(NBDClientNewData, 1); + + client = g_malloc0(sizeof(NBDClient)); + client->refcount = 1; + client->exp = exp; + client->tlscreds = tlscreds; + if (tlscreds) { + object_ref(OBJECT(client->tlscreds)); + } + client->tlsaclname = g_strdup(tlsaclname); + client->sioc = sioc; + object_ref(OBJECT(client->sioc)); + client->ioc = QIO_CHANNEL(sioc); + object_ref(OBJECT(client->ioc)); + client->can_read = true; + client->close = close_fn; + + data->client = client; + data->co = qemu_coroutine_create(nbd_co_client_start); + qemu_coroutine_enter(data->co, data); +} -- cgit 1.2.3-korg