diff options
Diffstat (limited to 'hw/vfio-user/proxy.c')
| -rw-r--r-- | hw/vfio-user/proxy.c | 515 |
1 files changed, 515 insertions, 0 deletions
diff --git a/hw/vfio-user/proxy.c b/hw/vfio-user/proxy.c index 349ea2b27c..874142e9e5 100644 --- a/hw/vfio-user/proxy.c +++ b/hw/vfio-user/proxy.c @@ -13,11 +13,15 @@ #include "hw/vfio-user/proxy.h" #include "hw/vfio-user/trace.h" #include "qapi/error.h" +#include "qobject/qdict.h" +#include "qobject/qjson.h" +#include "qobject/qnum.h" #include "qemu/error-report.h" #include "qemu/lockable.h" #include "qemu/main-loop.h" #include "system/iothread.h" +static int wait_time = 5000; /* wait up to 5 sec for busy servers */ static IOThread *vfio_user_iothread; static void vfio_user_shutdown(VFIOUserProxy *proxy); @@ -27,9 +31,12 @@ static VFIOUserFDs *vfio_user_getfds(int numfds); static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg); static void vfio_user_recv(void *opaque); +static void vfio_user_send(void *opaque); static void vfio_user_cb(void *opaque); static void vfio_user_request(void *opaque); +static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd, + uint32_t size, uint32_t flags); static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err) { @@ -48,6 +55,41 @@ static void vfio_user_shutdown(VFIOUserProxy *proxy) proxy->ctx, NULL, NULL); } +/* + * Same return values as qio_channel_writev_full(): + * + * QIO_CHANNEL_ERR_BLOCK: *errp not set + * -1: *errp will be populated + * otherwise: bytes written + */ +static ssize_t vfio_user_send_qio(VFIOUserProxy *proxy, VFIOUserMsg *msg, + Error **errp) +{ + VFIOUserFDs *fds = msg->fds; + struct iovec iov = { + .iov_base = msg->hdr, + .iov_len = msg->hdr->size, + }; + size_t numfds = 0; + int *fdp = NULL; + ssize_t ret; + + if (fds != NULL && fds->send_fds != 0) { + numfds = fds->send_fds; + fdp = fds->fds; + } + + ret = qio_channel_writev_full(proxy->ioc, &iov, 1, fdp, numfds, 0, errp); + + if (ret == -1) { + vfio_user_set_error(msg->hdr, EIO); + vfio_user_shutdown(proxy); + } + trace_vfio_user_send_write(msg->hdr->id, ret); + + return ret; +} + static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr, VFIOUserFDs *fds) { @@ -88,6 +130,7 @@ static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg) msg->hdr = NULL; msg->fds = NULL; msg->complete = false; + msg->pending = false; QTAILQ_INSERT_HEAD(&proxy->free, msg, next); } @@ -385,6 +428,62 @@ static void vfio_user_recv(void *opaque) } } +/* + * Send a single message, same return semantics as vfio_user_send_qio(). + * + * Sent async messages are freed, others are moved to pending queue. + */ +static ssize_t vfio_user_send_one(VFIOUserProxy *proxy, Error **errp) +{ + VFIOUserMsg *msg; + ssize_t ret; + + msg = QTAILQ_FIRST(&proxy->outgoing); + ret = vfio_user_send_qio(proxy, msg, errp); + if (ret < 0) { + return ret; + } + + QTAILQ_REMOVE(&proxy->outgoing, msg, next); + if (msg->type == VFIO_MSG_ASYNC) { + vfio_user_recycle(proxy, msg); + } else { + QTAILQ_INSERT_TAIL(&proxy->pending, msg, next); + msg->pending = true; + } + + return ret; +} + +/* + * Send messages from outgoing queue when the socket buffer has space. + * If we deplete 'outgoing', remove ourselves from the poll list. + */ +static void vfio_user_send(void *opaque) +{ + VFIOUserProxy *proxy = opaque; + + QEMU_LOCK_GUARD(&proxy->lock); + + if (proxy->state == VFIO_PROXY_CONNECTED) { + while (!QTAILQ_EMPTY(&proxy->outgoing)) { + Error *local_err = NULL; + int ret; + + ret = vfio_user_send_one(proxy, &local_err); + + if (ret == QIO_CHANNEL_ERR_BLOCK) { + return; + } else if (ret == -1) { + error_report_err(local_err); + return; + } + } + qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx, + vfio_user_recv, NULL, NULL, proxy); + } +} + static void vfio_user_cb(void *opaque) { VFIOUserProxy *proxy = opaque; @@ -446,6 +545,128 @@ static void vfio_user_request(void *opaque) } } +/* + * Messages are queued onto the proxy's outgoing list. + * + * It handles 3 types of messages: + * + * async messages - replies and posted writes + * + * There will be no reply from the server, so message + * buffers are freed after they're sent. + * + * nowait messages - map/unmap during address space transactions + * + * These are also sent async, but a reply is expected so that + * vfio_wait_reqs() can wait for the youngest nowait request. + * They transition from the outgoing list to the pending list + * when sent, and are freed when the reply is received. + * + * wait messages - all other requests + * + * The reply to these messages is waited for by their caller. + * They also transition from outgoing to pending when sent, but + * the message buffer is returned to the caller with the reply + * contents. The caller is responsible for freeing these messages. + * + * As an optimization, if the outgoing list and the socket send + * buffer are empty, the message is sent inline instead of being + * added to the outgoing list. The rest of the transitions are + * unchanged. + */ +static bool vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg, + Error **errp) +{ + int ret; + + /* + * Unsent outgoing msgs - add to tail + */ + if (!QTAILQ_EMPTY(&proxy->outgoing)) { + QTAILQ_INSERT_TAIL(&proxy->outgoing, msg, next); + return true; + } + + /* + * Try inline - if blocked, queue it and kick send poller + */ + if (proxy->flags & VFIO_PROXY_FORCE_QUEUED) { + ret = QIO_CHANNEL_ERR_BLOCK; + } else { + ret = vfio_user_send_qio(proxy, msg, errp); + } + + if (ret == QIO_CHANNEL_ERR_BLOCK) { + QTAILQ_INSERT_HEAD(&proxy->outgoing, msg, next); + qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx, + vfio_user_recv, proxy->ctx, + vfio_user_send, proxy); + return true; + } + if (ret == -1) { + return false; + } + + /* + * Sent - free async, add others to pending + */ + if (msg->type == VFIO_MSG_ASYNC) { + vfio_user_recycle(proxy, msg); + } else { + QTAILQ_INSERT_TAIL(&proxy->pending, msg, next); + msg->pending = true; + } + + return true; +} + +/* + * Returns false if we did not successfully receive a reply message, in which + * case @errp will be populated. + * + * In either case, the caller must free @hdr and @fds if needed. + */ +static bool vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr, + VFIOUserFDs *fds, int rsize, Error **errp) +{ + VFIOUserMsg *msg; + bool ok = false; + + if (hdr->flags & VFIO_USER_NO_REPLY) { + error_setg_errno(errp, EINVAL, "%s on NO_REPLY message", __func__); + return false; + } + + qemu_mutex_lock(&proxy->lock); + + msg = vfio_user_getmsg(proxy, hdr, fds); + msg->id = hdr->id; + msg->rsize = rsize ? rsize : hdr->size; + msg->type = VFIO_MSG_WAIT; + + ok = vfio_user_send_queued(proxy, msg, errp); + + if (ok) { + while (!msg->complete) { + if (!qemu_cond_timedwait(&msg->cv, &proxy->lock, wait_time)) { + VFIOUserMsgQ *list; + + list = msg->pending ? &proxy->pending : &proxy->outgoing; + QTAILQ_REMOVE(list, msg, next); + error_setg_errno(errp, ETIMEDOUT, + "timed out waiting for reply"); + ok = false; + break; + } + } + } + + vfio_user_recycle(proxy, msg); + + qemu_mutex_unlock(&proxy->lock); + + return ok; +} static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets = QLIST_HEAD_INITIALIZER(vfio_user_sockets); @@ -474,6 +695,15 @@ VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp) proxy = g_malloc0(sizeof(VFIOUserProxy)); proxy->sockname = g_strdup_printf("unix:%s", sockname); proxy->ioc = ioc; + + /* init defaults */ + proxy->max_xfer_size = VFIO_USER_DEF_MAX_XFER; + proxy->max_send_fds = VFIO_USER_DEF_MAX_FDS; + proxy->max_dma = VFIO_USER_DEF_MAP_MAX; + proxy->dma_pgsizes = VFIO_USER_DEF_PGSIZE; + proxy->max_bitmap = VFIO_USER_DEF_MAX_BITMAP; + proxy->migr_pgsize = VFIO_USER_DEF_PGSIZE; + proxy->flags = VFIO_PROXY_CLIENT; proxy->state = VFIO_PROXY_CONNECTED; @@ -571,3 +801,288 @@ void vfio_user_disconnect(VFIOUserProxy *proxy) g_free(proxy->sockname); g_free(proxy); } + +static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd, + uint32_t size, uint32_t flags) +{ + static uint16_t next_id; + + hdr->id = qatomic_fetch_inc(&next_id); + hdr->command = cmd; + hdr->size = size; + hdr->flags = (flags & ~VFIO_USER_TYPE) | VFIO_USER_REQUEST; + hdr->error_reply = 0; +} + +struct cap_entry { + const char *name; + bool (*check)(VFIOUserProxy *proxy, QObject *qobj, Error **errp); +}; + +static bool caps_parse(VFIOUserProxy *proxy, QDict *qdict, + struct cap_entry caps[], Error **errp) +{ + QObject *qobj; + struct cap_entry *p; + + for (p = caps; p->name != NULL; p++) { + qobj = qdict_get(qdict, p->name); + if (qobj != NULL) { + if (!p->check(proxy, qobj, errp)) { + return false; + } + qdict_del(qdict, p->name); + } + } + + /* warning, for now */ + if (qdict_size(qdict) != 0) { + warn_report("spurious capabilities"); + } + return true; +} + +static bool check_migr_pgsize(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QNum *qn = qobject_to(QNum, qobj); + uint64_t pgsize; + + if (qn == NULL || !qnum_get_try_uint(qn, &pgsize)) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_PGSIZE); + return false; + } + + /* must be larger than default */ + if (pgsize & (VFIO_USER_DEF_PGSIZE - 1)) { + error_setg(errp, "pgsize 0x%"PRIx64" too small", pgsize); + return false; + } + + proxy->migr_pgsize = pgsize; + return true; +} + +static bool check_bitmap(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QNum *qn = qobject_to(QNum, qobj); + uint64_t bitmap_size; + + if (qn == NULL || !qnum_get_try_uint(qn, &bitmap_size)) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_BITMAP); + return false; + } + + /* can only lower it */ + if (bitmap_size > VFIO_USER_DEF_MAX_BITMAP) { + error_setg(errp, "%s too large", VFIO_USER_CAP_MAX_BITMAP); + return false; + } + + proxy->max_bitmap = bitmap_size; + return true; +} + +static struct cap_entry caps_migr[] = { + { VFIO_USER_CAP_PGSIZE, check_migr_pgsize }, + { VFIO_USER_CAP_MAX_BITMAP, check_bitmap }, + { NULL } +}; + +static bool check_max_fds(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QNum *qn = qobject_to(QNum, qobj); + uint64_t max_send_fds; + + if (qn == NULL || !qnum_get_try_uint(qn, &max_send_fds) || + max_send_fds > VFIO_USER_MAX_MAX_FDS) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_FDS); + return false; + } + proxy->max_send_fds = max_send_fds; + return true; +} + +static bool check_max_xfer(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QNum *qn = qobject_to(QNum, qobj); + uint64_t max_xfer_size; + + if (qn == NULL || !qnum_get_try_uint(qn, &max_xfer_size) || + max_xfer_size > VFIO_USER_MAX_MAX_XFER) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_XFER); + return false; + } + proxy->max_xfer_size = max_xfer_size; + return true; +} + +static bool check_pgsizes(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QNum *qn = qobject_to(QNum, qobj); + uint64_t pgsizes; + + if (qn == NULL || !qnum_get_try_uint(qn, &pgsizes)) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_PGSIZES); + return false; + } + + /* must be larger than default */ + if (pgsizes & (VFIO_USER_DEF_PGSIZE - 1)) { + error_setg(errp, "pgsize 0x%"PRIx64" too small", pgsizes); + return false; + } + + proxy->dma_pgsizes = pgsizes; + return true; +} + +static bool check_max_dma(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QNum *qn = qobject_to(QNum, qobj); + uint64_t max_dma; + + if (qn == NULL || !qnum_get_try_uint(qn, &max_dma)) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_MAP_MAX); + return false; + } + + /* can only lower it */ + if (max_dma > VFIO_USER_DEF_MAP_MAX) { + error_setg(errp, "%s too large", VFIO_USER_CAP_MAP_MAX); + return false; + } + + proxy->max_dma = max_dma; + return true; +} + +static bool check_migr(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QDict *qdict = qobject_to(QDict, qobj); + + if (qdict == NULL) { + error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_FDS); + return true; + } + return caps_parse(proxy, qdict, caps_migr, errp); +} + +static struct cap_entry caps_cap[] = { + { VFIO_USER_CAP_MAX_FDS, check_max_fds }, + { VFIO_USER_CAP_MAX_XFER, check_max_xfer }, + { VFIO_USER_CAP_PGSIZES, check_pgsizes }, + { VFIO_USER_CAP_MAP_MAX, check_max_dma }, + { VFIO_USER_CAP_MIGR, check_migr }, + { NULL } +}; + +static bool check_cap(VFIOUserProxy *proxy, QObject *qobj, Error **errp) +{ + QDict *qdict = qobject_to(QDict, qobj); + + if (qdict == NULL) { + error_setg(errp, "malformed %s", VFIO_USER_CAP); + return false; + } + return caps_parse(proxy, qdict, caps_cap, errp); +} + +static struct cap_entry ver_0_0[] = { + { VFIO_USER_CAP, check_cap }, + { NULL } +}; + +static bool caps_check(VFIOUserProxy *proxy, int minor, const char *caps, + Error **errp) +{ + QObject *qobj; + QDict *qdict; + bool ret; + + qobj = qobject_from_json(caps, NULL); + if (qobj == NULL) { + error_setg(errp, "malformed capabilities %s", caps); + return false; + } + qdict = qobject_to(QDict, qobj); + if (qdict == NULL) { + error_setg(errp, "capabilities %s not an object", caps); + qobject_unref(qobj); + return false; + } + ret = caps_parse(proxy, qdict, ver_0_0, errp); + + qobject_unref(qobj); + return ret; +} + +static GString *caps_json(void) +{ + QDict *dict = qdict_new(); + QDict *capdict = qdict_new(); + QDict *migdict = qdict_new(); + GString *str; + + qdict_put_int(migdict, VFIO_USER_CAP_PGSIZE, VFIO_USER_DEF_PGSIZE); + qdict_put_int(migdict, VFIO_USER_CAP_MAX_BITMAP, VFIO_USER_DEF_MAX_BITMAP); + qdict_put_obj(capdict, VFIO_USER_CAP_MIGR, QOBJECT(migdict)); + + qdict_put_int(capdict, VFIO_USER_CAP_MAX_FDS, VFIO_USER_MAX_MAX_FDS); + qdict_put_int(capdict, VFIO_USER_CAP_MAX_XFER, VFIO_USER_DEF_MAX_XFER); + qdict_put_int(capdict, VFIO_USER_CAP_PGSIZES, VFIO_USER_DEF_PGSIZE); + qdict_put_int(capdict, VFIO_USER_CAP_MAP_MAX, VFIO_USER_DEF_MAP_MAX); + + qdict_put_obj(dict, VFIO_USER_CAP, QOBJECT(capdict)); + + str = qobject_to_json(QOBJECT(dict)); + qobject_unref(dict); + return str; +} + +bool vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp) +{ + g_autofree VFIOUserVersion *msgp = NULL; + GString *caps; + char *reply; + int size, caplen; + + caps = caps_json(); + caplen = caps->len + 1; + size = sizeof(*msgp) + caplen; + msgp = g_malloc0(size); + + vfio_user_request_msg(&msgp->hdr, VFIO_USER_VERSION, size, 0); + msgp->major = VFIO_USER_MAJOR_VER; + msgp->minor = VFIO_USER_MINOR_VER; + memcpy(&msgp->capabilities, caps->str, caplen); + g_string_free(caps, true); + trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities); + + if (!vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0, errp)) { + return false; + } + + if (msgp->hdr.flags & VFIO_USER_ERROR) { + error_setg_errno(errp, msgp->hdr.error_reply, "version reply"); + return false; + } + + if (msgp->major != VFIO_USER_MAJOR_VER || + msgp->minor > VFIO_USER_MINOR_VER) { + error_setg(errp, "incompatible server version"); + return false; + } + + reply = msgp->capabilities; + if (reply[msgp->hdr.size - sizeof(*msgp) - 1] != '\0') { + error_setg(errp, "corrupt version reply"); + return false; + } + + if (!caps_check(proxy, msgp->minor, reply, errp)) { + return false; + } + + trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities); + return true; +} |