diff --git a/Makefile b/Makefile index cbf252d547..fc1f8bb934 100644 --- a/Makefile +++ b/Makefile @@ -151,6 +151,8 @@ dummy := $(call unnest-vars,, \ stub-obj-y \ util-obj-y \ qga-obj-y \ + ivshmem-client-obj-y \ + ivshmem-server-obj-y \ qga-vss-dll-obj-y \ block-obj-y \ block-obj-m \ @@ -323,6 +325,11 @@ ifneq ($(EXESUF),) qemu-ga: qemu-ga$(EXESUF) $(QGA_VSS_PROVIDER) $(QEMU_GA_MSI) endif +ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) + $(call LINK, $^) +ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) libqemuutil.a libqemustub.a + $(call LINK, $^) + clean: # avoid old build problems by removing potentially incorrect old files rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h diff --git a/Makefile.objs b/Makefile.objs index ecfe03c195..fe02ee2cf4 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -104,3 +104,8 @@ target-obj-y += trace/ # by libqemuutil.a. These should be moved to a separate .json schema. qga-obj-y = qga/ qga-vss-dll-obj-y = qga/ + +###################################################################### +# contrib +ivshmem-client-obj-y = contrib/ivshmem-client/ +ivshmem-server-obj-y = contrib/ivshmem-server/ diff --git a/configure b/configure index 2a129bb6de..7a1d08dc4a 100755 --- a/configure +++ b/configure @@ -4508,6 +4508,7 @@ if test "$want_tools" = "yes" ; then tools="qemu-img\$(EXESUF) qemu-io\$(EXESUF) $tools" if [ "$linux" = "yes" -o "$bsd" = "yes" -o "$solaris" = "yes" ] ; then tools="qemu-nbd\$(EXESUF) $tools" + tools="ivshmem-client\$(EXESUF) ivshmem-server\$(EXESUF) $tools" fi fi if test "$softmmu" = yes ; then diff --git a/contrib/ivshmem-client/Makefile.objs b/contrib/ivshmem-client/Makefile.objs new file mode 100644 index 0000000000..bfab2d20dd --- /dev/null +++ b/contrib/ivshmem-client/Makefile.objs @@ -0,0 +1 @@ +ivshmem-client-obj-y = ivshmem-client.o main.o diff --git a/contrib/ivshmem-client/ivshmem-client.c b/contrib/ivshmem-client/ivshmem-client.c new file mode 100644 index 0000000000..31619d80e9 --- /dev/null +++ b/contrib/ivshmem-client/ivshmem-client.c @@ -0,0 +1,446 @@ +/* + * Copyright 6WIND S.A., 2014 + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include +#include +#include + +#include "qemu-common.h" +#include "qemu/queue.h" + +#include "ivshmem-client.h" + +/* log a message on stdout if verbose=1 */ +#define IVSHMEM_CLIENT_DEBUG(client, fmt, ...) do { \ + if ((client)->verbose) { \ + printf(fmt, ## __VA_ARGS__); \ + } \ + } while (0) + +/* read message from the unix socket */ +static int +ivshmem_client_read_one_msg(IvshmemClient *client, int64_t *index, int *fd) +{ + int ret; + struct msghdr msg; + struct iovec iov[1]; + union { + struct cmsghdr cmsg; + char control[CMSG_SPACE(sizeof(int))]; + } msg_control; + struct cmsghdr *cmsg; + + iov[0].iov_base = index; + iov[0].iov_len = sizeof(*index); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = &msg_control; + msg.msg_controllen = sizeof(msg_control); + + ret = recvmsg(client->sock_fd, &msg, 0); + if (ret < sizeof(*index)) { + IVSHMEM_CLIENT_DEBUG(client, "cannot read message: %s\n", + strerror(errno)); + return -1; + } + if (ret == 0) { + IVSHMEM_CLIENT_DEBUG(client, "lost connection to server\n"); + return -1; + } + + *index = GINT64_FROM_LE(*index); + *fd = -1; + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)) || + cmsg->cmsg_level != SOL_SOCKET || + cmsg->cmsg_type != SCM_RIGHTS) { + continue; + } + + memcpy(fd, CMSG_DATA(cmsg), sizeof(*fd)); + } + + return 0; +} + +/* free a peer when the server advertises a disconnection or when the + * client is freed */ +static void +ivshmem_client_free_peer(IvshmemClient *client, IvshmemClientPeer *peer) +{ + unsigned vector; + + QTAILQ_REMOVE(&client->peer_list, peer, next); + for (vector = 0; vector < peer->vectors_count; vector++) { + close(peer->vectors[vector]); + } + + g_free(peer); +} + +/* handle message coming from server (new peer, new vectors) */ +static int +ivshmem_client_handle_server_msg(IvshmemClient *client) +{ + IvshmemClientPeer *peer; + int64_t peer_id; + int ret, fd; + + ret = ivshmem_client_read_one_msg(client, &peer_id, &fd); + if (ret < 0) { + return -1; + } + + /* can return a peer or the local client */ + peer = ivshmem_client_search_peer(client, peer_id); + + /* delete peer */ + if (fd == -1) { + + if (peer == NULL || peer == &client->local) { + IVSHMEM_CLIENT_DEBUG(client, "receive delete for invalid " + "peer %" PRId64 "\n", peer_id); + return -1; + } + + IVSHMEM_CLIENT_DEBUG(client, "delete peer id = %" PRId64 "\n", peer_id); + ivshmem_client_free_peer(client, peer); + return 0; + } + + /* new peer */ + if (peer == NULL) { + peer = g_malloc0(sizeof(*peer)); + peer->id = peer_id; + peer->vectors_count = 0; + QTAILQ_INSERT_TAIL(&client->peer_list, peer, next); + IVSHMEM_CLIENT_DEBUG(client, "new peer id = %" PRId64 "\n", peer_id); + } + + /* new vector */ + IVSHMEM_CLIENT_DEBUG(client, " new vector %d (fd=%d) for peer id %" + PRId64 "\n", peer->vectors_count, fd, peer->id); + if (peer->vectors_count >= G_N_ELEMENTS(peer->vectors)) { + IVSHMEM_CLIENT_DEBUG(client, "Too many vectors received, failing"); + return -1; + } + + peer->vectors[peer->vectors_count] = fd; + peer->vectors_count++; + + return 0; +} + +/* init a new ivshmem client */ +int +ivshmem_client_init(IvshmemClient *client, const char *unix_sock_path, + IvshmemClientNotifCb notif_cb, void *notif_arg, + bool verbose) +{ + int ret; + unsigned i; + + memset(client, 0, sizeof(*client)); + + ret = snprintf(client->unix_sock_path, sizeof(client->unix_sock_path), + "%s", unix_sock_path); + + if (ret < 0 || ret >= sizeof(client->unix_sock_path)) { + IVSHMEM_CLIENT_DEBUG(client, "could not copy unix socket path\n"); + return -1; + } + + for (i = 0; i < IVSHMEM_CLIENT_MAX_VECTORS; i++) { + client->local.vectors[i] = -1; + } + + QTAILQ_INIT(&client->peer_list); + client->local.id = -1; + + client->notif_cb = notif_cb; + client->notif_arg = notif_arg; + client->verbose = verbose; + client->shm_fd = -1; + client->sock_fd = -1; + + return 0; +} + +/* create and connect to the unix socket */ +int +ivshmem_client_connect(IvshmemClient *client) +{ + struct sockaddr_un sun; + int fd, ret; + int64_t tmp; + + IVSHMEM_CLIENT_DEBUG(client, "connect to client %s\n", + client->unix_sock_path); + + client->sock_fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (client->sock_fd < 0) { + IVSHMEM_CLIENT_DEBUG(client, "cannot create socket: %s\n", + strerror(errno)); + return -1; + } + + sun.sun_family = AF_UNIX; + ret = snprintf(sun.sun_path, sizeof(sun.sun_path), "%s", + client->unix_sock_path); + if (ret < 0 || ret >= sizeof(sun.sun_path)) { + IVSHMEM_CLIENT_DEBUG(client, "could not copy unix socket path\n"); + goto err_close; + } + + if (connect(client->sock_fd, (struct sockaddr *)&sun, sizeof(sun)) < 0) { + IVSHMEM_CLIENT_DEBUG(client, "cannot connect to %s: %s\n", sun.sun_path, + strerror(errno)); + goto err_close; + } + + /* first, we expect a protocol version */ + if (ivshmem_client_read_one_msg(client, &tmp, &fd) < 0 || + (tmp != IVSHMEM_PROTOCOL_VERSION) || fd != -1) { + IVSHMEM_CLIENT_DEBUG(client, "cannot read from server\n"); + goto err_close; + } + + /* then, we expect our index + a fd == -1 */ + if (ivshmem_client_read_one_msg(client, &client->local.id, &fd) < 0 || + client->local.id < 0 || fd != -1) { + IVSHMEM_CLIENT_DEBUG(client, "cannot read from server (2)\n"); + goto err_close; + } + IVSHMEM_CLIENT_DEBUG(client, "our_id=%" PRId64 "\n", client->local.id); + + /* now, we expect shared mem fd + a -1 index, note that shm fd + * is not used */ + if (ivshmem_client_read_one_msg(client, &tmp, &fd) < 0 || + tmp != -1 || fd < 0) { + if (fd >= 0) { + close(fd); + } + IVSHMEM_CLIENT_DEBUG(client, "cannot read from server (3)\n"); + goto err_close; + } + client->shm_fd = fd; + IVSHMEM_CLIENT_DEBUG(client, "shm_fd=%d\n", fd); + + return 0; + +err_close: + close(client->sock_fd); + client->sock_fd = -1; + return -1; +} + +/* close connection to the server, and free all peer structures */ +void +ivshmem_client_close(IvshmemClient *client) +{ + IvshmemClientPeer *peer; + unsigned i; + + IVSHMEM_CLIENT_DEBUG(client, "close client\n"); + + while ((peer = QTAILQ_FIRST(&client->peer_list)) != NULL) { + ivshmem_client_free_peer(client, peer); + } + + close(client->shm_fd); + client->shm_fd = -1; + close(client->sock_fd); + client->sock_fd = -1; + client->local.id = -1; + for (i = 0; i < IVSHMEM_CLIENT_MAX_VECTORS; i++) { + close(client->local.vectors[i]); + client->local.vectors[i] = -1; + } + client->local.vectors_count = 0; +} + +/* get the fd_set according to the unix socket and peer list */ +void +ivshmem_client_get_fds(const IvshmemClient *client, fd_set *fds, int *maxfd) +{ + int fd; + unsigned vector; + + FD_SET(client->sock_fd, fds); + if (client->sock_fd >= *maxfd) { + *maxfd = client->sock_fd + 1; + } + + for (vector = 0; vector < client->local.vectors_count; vector++) { + fd = client->local.vectors[vector]; + FD_SET(fd, fds); + if (fd >= *maxfd) { + *maxfd = fd + 1; + } + } +} + +/* handle events from eventfd: just print a message on notification */ +static int +ivshmem_client_handle_event(IvshmemClient *client, const fd_set *cur, int maxfd) +{ + IvshmemClientPeer *peer; + uint64_t kick; + unsigned i; + int ret; + + peer = &client->local; + + for (i = 0; i < peer->vectors_count; i++) { + if (peer->vectors[i] >= maxfd || !FD_ISSET(peer->vectors[i], cur)) { + continue; + } + + ret = read(peer->vectors[i], &kick, sizeof(kick)); + if (ret < 0) { + return ret; + } + if (ret != sizeof(kick)) { + IVSHMEM_CLIENT_DEBUG(client, "invalid read size = %d\n", ret); + errno = EINVAL; + return -1; + } + IVSHMEM_CLIENT_DEBUG(client, "received event on fd %d vector %d: %" + PRIu64 "\n", peer->vectors[i], i, kick); + if (client->notif_cb != NULL) { + client->notif_cb(client, peer, i, client->notif_arg); + } + } + + return 0; +} + +/* read and handle new messages on the given fd_set */ +int +ivshmem_client_handle_fds(IvshmemClient *client, fd_set *fds, int maxfd) +{ + if (client->sock_fd < maxfd && FD_ISSET(client->sock_fd, fds) && + ivshmem_client_handle_server_msg(client) < 0 && errno != EINTR) { + IVSHMEM_CLIENT_DEBUG(client, "ivshmem_client_handle_server_msg() " + "failed\n"); + return -1; + } else if (ivshmem_client_handle_event(client, fds, maxfd) < 0 && + errno != EINTR) { + IVSHMEM_CLIENT_DEBUG(client, "ivshmem_client_handle_event() failed\n"); + return -1; + } + + return 0; +} + +/* send a notification on a vector of a peer */ +int +ivshmem_client_notify(const IvshmemClient *client, + const IvshmemClientPeer *peer, unsigned vector) +{ + uint64_t kick; + int fd; + + if (vector >= peer->vectors_count) { + IVSHMEM_CLIENT_DEBUG(client, "invalid vector %u on peer %" PRId64 "\n", + vector, peer->id); + return -1; + } + fd = peer->vectors[vector]; + IVSHMEM_CLIENT_DEBUG(client, "notify peer %" PRId64 + " on vector %d, fd %d\n", peer->id, vector, fd); + + kick = 1; + if (write(fd, &kick, sizeof(kick)) != sizeof(kick)) { + fprintf(stderr, "could not write to %d: %s\n", peer->vectors[vector], + strerror(errno)); + return -1; + } + return 0; +} + +/* send a notification to all vectors of a peer */ +int +ivshmem_client_notify_all_vects(const IvshmemClient *client, + const IvshmemClientPeer *peer) +{ + unsigned vector; + int ret = 0; + + for (vector = 0; vector < peer->vectors_count; vector++) { + if (ivshmem_client_notify(client, peer, vector) < 0) { + ret = -1; + } + } + + return ret; +} + +/* send a notification to all peers */ +int +ivshmem_client_notify_broadcast(const IvshmemClient *client) +{ + IvshmemClientPeer *peer; + int ret = 0; + + QTAILQ_FOREACH(peer, &client->peer_list, next) { + if (ivshmem_client_notify_all_vects(client, peer) < 0) { + ret = -1; + } + } + + return ret; +} + +/* lookup peer from its id */ +IvshmemClientPeer * +ivshmem_client_search_peer(IvshmemClient *client, int64_t peer_id) +{ + IvshmemClientPeer *peer; + + if (peer_id == client->local.id) { + return &client->local; + } + + QTAILQ_FOREACH(peer, &client->peer_list, next) { + if (peer->id == peer_id) { + return peer; + } + } + return NULL; +} + +/* dump our info, the list of peers their vectors on stdout */ +void +ivshmem_client_dump(const IvshmemClient *client) +{ + const IvshmemClientPeer *peer; + unsigned vector; + + /* dump local infos */ + peer = &client->local; + printf("our_id = %" PRId64 "\n", peer->id); + for (vector = 0; vector < peer->vectors_count; vector++) { + printf(" vector %d is enabled (fd=%d)\n", vector, + peer->vectors[vector]); + } + + /* dump peers */ + QTAILQ_FOREACH(peer, &client->peer_list, next) { + printf("peer_id = %" PRId64 "\n", peer->id); + + for (vector = 0; vector < peer->vectors_count; vector++) { + printf(" vector %d is enabled (fd=%d)\n", vector, + peer->vectors[vector]); + } + } +} diff --git a/contrib/ivshmem-client/ivshmem-client.h b/contrib/ivshmem-client/ivshmem-client.h new file mode 100644 index 0000000000..3a4f809682 --- /dev/null +++ b/contrib/ivshmem-client/ivshmem-client.h @@ -0,0 +1,213 @@ +/* + * Copyright 6WIND S.A., 2014 + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#ifndef _IVSHMEM_CLIENT_H_ +#define _IVSHMEM_CLIENT_H_ + +/** + * This file provides helper to implement an ivshmem client. It is used + * on the host to ask QEMU to send an interrupt to an ivshmem PCI device in a + * guest. QEMU also implements an ivshmem client similar to this one, they both + * connect to an ivshmem server. + * + * A standalone ivshmem client based on this file is provided for debug/test + * purposes. + */ + +#include +#include + +#include "qemu/queue.h" +#include "hw/misc/ivshmem.h" + +/** + * Maximum number of notification vectors supported by the client + */ +#define IVSHMEM_CLIENT_MAX_VECTORS 64 + +/** + * Structure storing a peer + * + * Each time a client connects to an ivshmem server, it is advertised to + * all connected clients through the unix socket. When our ivshmem + * client receives a notification, it creates a IvshmemClientPeer + * structure to store the infos of this peer. + * + * This structure is also used to store the information of our own + * client in (IvshmemClient)->local. + */ +typedef struct IvshmemClientPeer { + QTAILQ_ENTRY(IvshmemClientPeer) next; /**< next in list*/ + int64_t id; /**< the id of the peer */ + int vectors[IVSHMEM_CLIENT_MAX_VECTORS]; /**< one fd per vector */ + unsigned vectors_count; /**< number of vectors */ +} IvshmemClientPeer; +QTAILQ_HEAD(IvshmemClientPeerList, IvshmemClientPeer); + +typedef struct IvshmemClientPeerList IvshmemClientPeerList; +typedef struct IvshmemClient IvshmemClient; + +/** + * Typedef of callback function used when our IvshmemClient receives a + * notification from a peer. + */ +typedef void (*IvshmemClientNotifCb)( + const IvshmemClient *client, + const IvshmemClientPeer *peer, + unsigned vect, void *arg); + +/** + * Structure describing an ivshmem client + * + * This structure stores all information related to our client: the name + * of the server unix socket, the list of peers advertised by the + * server, our own client information, and a pointer the notification + * callback function used when we receive a notification from a peer. + */ +struct IvshmemClient { + char unix_sock_path[PATH_MAX]; /**< path to unix sock */ + int sock_fd; /**< unix sock filedesc */ + int shm_fd; /**< shm file descriptor */ + + IvshmemClientPeerList peer_list; /**< list of peers */ + IvshmemClientPeer local; /**< our own infos */ + + IvshmemClientNotifCb notif_cb; /**< notification callback */ + void *notif_arg; /**< notification argument */ + + bool verbose; /**< true to enable debug */ +}; + +/** + * Initialize an ivshmem client + * + * @client: A pointer to an uninitialized IvshmemClient structure + * @unix_sock_path: The pointer to the unix socket file name + * @notif_cb: If not NULL, the pointer to the function to be called when + * our IvshmemClient receives a notification from a peer + * @notif_arg: Opaque pointer given as-is to the notification callback + * function + * @verbose: True to enable debug + * + * Returns: 0 on success, or a negative value on error + */ +int ivshmem_client_init(IvshmemClient *client, const char *unix_sock_path, + IvshmemClientNotifCb notif_cb, void *notif_arg, + bool verbose); + +/** + * Connect to the server + * + * Connect to the server unix socket, and read the first initial + * messages sent by the server, giving the ID of the client and the file + * descriptor of the shared memory. + * + * @client: The ivshmem client + * + * Returns: 0 on success, or a negative value on error + */ +int ivshmem_client_connect(IvshmemClient *client); + +/** + * Close connection to the server and free all peer structures + * + * @client: The ivshmem client + */ +void ivshmem_client_close(IvshmemClient *client); + +/** + * Fill a fd_set with file descriptors to be monitored + * + * This function will fill a fd_set with all file descriptors + * that must be polled (unix server socket and peers eventfd). The + * function will not initialize the fd_set, it is up to the caller + * to do this. + * + * @client: The ivshmem client + * @fds: The fd_set to be updated + * @maxfd: Must be set to the max file descriptor + 1 in fd_set. This value is + * updated if this function adds a greater fd in fd_set. + */ +void ivshmem_client_get_fds(const IvshmemClient *client, fd_set *fds, + int *maxfd); + +/** + * Read and handle new messages + * + * Given a fd_set filled by select(), handle incoming messages from + * server or peers. + * + * @client: The ivshmem client + * @fds: The fd_set containing the file descriptors to be checked. Note + * that file descriptors that are not related to our client are + * ignored. + * @maxfd: The maximum fd in fd_set, plus one. + * + * Returns: 0 on success, or a negative value on error + */ +int ivshmem_client_handle_fds(IvshmemClient *client, fd_set *fds, int maxfd); + +/** + * Send a notification to a vector of a peer + * + * @client: The ivshmem client + * @peer: The peer to be notified + * @vector: The number of the vector + * + * Returns: 0 on success, or a negative value on error + */ +int ivshmem_client_notify(const IvshmemClient *client, + const IvshmemClientPeer *peer, unsigned vector); + +/** + * Send a notification to all vectors of a peer + * + * @client: The ivshmem client + * @peer: The peer to be notified + * + * Returns: 0 on success, or a negative value on error (at least one + * notification failed) + */ +int ivshmem_client_notify_all_vects(const IvshmemClient *client, + const IvshmemClientPeer *peer); + +/** + * Broadcat a notification to all vectors of all peers + * + * @client: The ivshmem client + * + * Returns: 0 on success, or a negative value on error (at least one + * notification failed) + */ +int ivshmem_client_notify_broadcast(const IvshmemClient *client); + +/** + * Search a peer from its identifier + * + * Return the peer structure from its peer_id. If the given peer_id is + * the local id, the function returns the local peer structure. + * + * @client: The ivshmem client + * @peer_id: The identifier of the peer structure + * + * Returns: The peer structure, or NULL if not found + */ +IvshmemClientPeer * +ivshmem_client_search_peer(IvshmemClient *client, int64_t peer_id); + +/** + * Dump information of this ivshmem client on stdout + * + * Dump the id and the vectors of the given ivshmem client and the list + * of its peers and their vectors on stdout. + * + * @client: The ivshmem client + */ +void ivshmem_client_dump(const IvshmemClient *client); + +#endif /* _IVSHMEM_CLIENT_H_ */ diff --git a/contrib/ivshmem-client/main.c b/contrib/ivshmem-client/main.c new file mode 100644 index 0000000000..c004870ae3 --- /dev/null +++ b/contrib/ivshmem-client/main.c @@ -0,0 +1,240 @@ +/* + * Copyright 6WIND S.A., 2014 + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu-common.h" + +#include "ivshmem-client.h" + +#define IVSHMEM_CLIENT_DEFAULT_VERBOSE 0 +#define IVSHMEM_CLIENT_DEFAULT_UNIX_SOCK_PATH "/tmp/ivshmem_socket" + +typedef struct IvshmemClientArgs { + bool verbose; + const char *unix_sock_path; +} IvshmemClientArgs; + +/* show ivshmem_client_usage and exit with given error code */ +static void +ivshmem_client_usage(const char *name, int code) +{ + fprintf(stderr, "%s [opts]\n", name); + fprintf(stderr, " -h: show this help\n"); + fprintf(stderr, " -v: verbose mode\n"); + fprintf(stderr, " -S : path to the unix socket\n" + " to connect to.\n" + " default=%s\n", IVSHMEM_CLIENT_DEFAULT_UNIX_SOCK_PATH); + exit(code); +} + +/* parse the program arguments, exit on error */ +static void +ivshmem_client_parse_args(IvshmemClientArgs *args, int argc, char *argv[]) +{ + int c; + + while ((c = getopt(argc, argv, + "h" /* help */ + "v" /* verbose */ + "S:" /* unix_sock_path */ + )) != -1) { + + switch (c) { + case 'h': /* help */ + ivshmem_client_usage(argv[0], 0); + break; + + case 'v': /* verbose */ + args->verbose = 1; + break; + + case 'S': /* unix_sock_path */ + args->unix_sock_path = optarg; + break; + + default: + ivshmem_client_usage(argv[0], 1); + break; + } + } +} + +/* show command line help */ +static void +ivshmem_client_cmdline_help(void) +{ + printf("dump: dump peers (including us)\n" + "int : notify one vector on a peer\n" + "int all: notify all vectors of a peer\n" + "int all: notify all vectors of all peers (excepting us)\n"); +} + +/* read stdin and handle commands */ +static int +ivshmem_client_handle_stdin_command(IvshmemClient *client) +{ + IvshmemClientPeer *peer; + char buf[128]; + char *s, *token; + int ret; + int peer_id, vector; + + memset(buf, 0, sizeof(buf)); + ret = read(0, buf, sizeof(buf) - 1); + if (ret < 0) { + return -1; + } + + s = buf; + while ((token = strsep(&s, "\n\r;")) != NULL) { + if (!strcmp(token, "")) { + continue; + } + if (!strcmp(token, "?")) { + ivshmem_client_cmdline_help(); + } + if (!strcmp(token, "help")) { + ivshmem_client_cmdline_help(); + } else if (!strcmp(token, "dump")) { + ivshmem_client_dump(client); + } else if (!strcmp(token, "int all")) { + ivshmem_client_notify_broadcast(client); + } else if (sscanf(token, "int %d %d", &peer_id, &vector) == 2) { + peer = ivshmem_client_search_peer(client, peer_id); + if (peer == NULL) { + printf("cannot find peer_id = %d\n", peer_id); + continue; + } + ivshmem_client_notify(client, peer, vector); + } else if (sscanf(token, "int %d all", &peer_id) == 1) { + peer = ivshmem_client_search_peer(client, peer_id); + if (peer == NULL) { + printf("cannot find peer_id = %d\n", peer_id); + continue; + } + ivshmem_client_notify_all_vects(client, peer); + } else { + printf("invalid command, type help\n"); + } + } + + printf("cmd> "); + fflush(stdout); + return 0; +} + +/* listen on stdin (command line), on unix socket (notifications of new + * and dead peers), and on eventfd (IRQ request) */ +static int +ivshmem_client_poll_events(IvshmemClient *client) +{ + fd_set fds; + int ret, maxfd; + + while (1) { + + FD_ZERO(&fds); + FD_SET(0, &fds); /* add stdin in fd_set */ + maxfd = 1; + + ivshmem_client_get_fds(client, &fds, &maxfd); + + ret = select(maxfd, &fds, NULL, NULL, NULL); + if (ret < 0) { + if (errno == EINTR) { + continue; + } + + fprintf(stderr, "select error: %s\n", strerror(errno)); + break; + } + if (ret == 0) { + continue; + } + + if (FD_ISSET(0, &fds) && + ivshmem_client_handle_stdin_command(client) < 0 && errno != EINTR) { + fprintf(stderr, "ivshmem_client_handle_stdin_command() failed\n"); + break; + } + + if (ivshmem_client_handle_fds(client, &fds, maxfd) < 0) { + fprintf(stderr, "ivshmem_client_handle_fds() failed\n"); + break; + } + } + + return ret; +} + +/* callback when we receive a notification (just display it) */ +static void +ivshmem_client_notification_cb(const IvshmemClient *client, + const IvshmemClientPeer *peer, + unsigned vect, void *arg) +{ + (void)client; + (void)arg; + printf("receive notification from peer_id=%" PRId64 " vector=%u\n", + peer->id, vect); +} + +int +main(int argc, char *argv[]) +{ + struct sigaction sa; + IvshmemClient client; + IvshmemClientArgs args = { + .verbose = IVSHMEM_CLIENT_DEFAULT_VERBOSE, + .unix_sock_path = IVSHMEM_CLIENT_DEFAULT_UNIX_SOCK_PATH, + }; + + /* parse arguments, will exit on error */ + ivshmem_client_parse_args(&args, argc, argv); + + /* Ignore SIGPIPE, see this link for more info: + * http://www.mail-archive.com/libevent-users@monkey.org/msg01606.html */ + sa.sa_handler = SIG_IGN; + sa.sa_flags = 0; + if (sigemptyset(&sa.sa_mask) == -1 || + sigaction(SIGPIPE, &sa, 0) == -1) { + perror("failed to ignore SIGPIPE; sigaction"); + return 1; + } + + ivshmem_client_cmdline_help(); + printf("cmd> "); + fflush(stdout); + + if (ivshmem_client_init(&client, args.unix_sock_path, + ivshmem_client_notification_cb, NULL, + args.verbose) < 0) { + fprintf(stderr, "cannot init client\n"); + return 1; + } + + while (1) { + if (ivshmem_client_connect(&client) < 0) { + fprintf(stderr, "cannot connect to server, retry in 1 second\n"); + sleep(1); + continue; + } + + fprintf(stdout, "listen on server socket %d\n", client.sock_fd); + + if (ivshmem_client_poll_events(&client) == 0) { + continue; + } + + /* disconnected from server, reset all peers */ + fprintf(stdout, "disconnected from server\n"); + + ivshmem_client_close(&client); + } + + return 0; +} diff --git a/contrib/ivshmem-server/Makefile.objs b/contrib/ivshmem-server/Makefile.objs new file mode 100644 index 0000000000..c060dd3698 --- /dev/null +++ b/contrib/ivshmem-server/Makefile.objs @@ -0,0 +1 @@ +ivshmem-server-obj-y = ivshmem-server.o main.o diff --git a/contrib/ivshmem-server/ivshmem-server.c b/contrib/ivshmem-server/ivshmem-server.c new file mode 100644 index 0000000000..5e5239ce45 --- /dev/null +++ b/contrib/ivshmem-server/ivshmem-server.c @@ -0,0 +1,491 @@ +/* + * Copyright 6WIND S.A., 2014 + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ +#include "qemu-common.h" +#include "qemu/sockets.h" + +#include +#include +#include +#include +#ifdef CONFIG_LINUX +#include +#endif + +#include "ivshmem-server.h" + +/* log a message on stdout if verbose=1 */ +#define IVSHMEM_SERVER_DEBUG(server, fmt, ...) do { \ + if ((server)->verbose) { \ + printf(fmt, ## __VA_ARGS__); \ + } \ + } while (0) + +/** maximum size of a huge page, used by ivshmem_server_ftruncate() */ +#define IVSHMEM_SERVER_MAX_HUGEPAGE_SIZE (1024 * 1024 * 1024) + +/** default listen backlog (number of sockets not accepted) */ +#define IVSHMEM_SERVER_LISTEN_BACKLOG 10 + +/* send message to a client unix socket */ +static int +ivshmem_server_send_one_msg(int sock_fd, int64_t peer_id, int fd) +{ + int ret; + struct msghdr msg; + struct iovec iov[1]; + union { + struct cmsghdr cmsg; + char control[CMSG_SPACE(sizeof(int))]; + } msg_control; + struct cmsghdr *cmsg; + + peer_id = GINT64_TO_LE(peer_id); + iov[0].iov_base = &peer_id; + iov[0].iov_len = sizeof(peer_id); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = iov; + msg.msg_iovlen = 1; + + /* if fd is specified, add it in a cmsg */ + if (fd >= 0) { + memset(&msg_control, 0, sizeof(msg_control)); + msg.msg_control = &msg_control; + msg.msg_controllen = sizeof(msg_control); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + memcpy(CMSG_DATA(cmsg), &fd, sizeof(fd)); + } + + ret = sendmsg(sock_fd, &msg, 0); + if (ret <= 0) { + return -1; + } + + return 0; +} + +/* free a peer when the server advertises a disconnection or when the + * server is freed */ +static void +ivshmem_server_free_peer(IvshmemServer *server, IvshmemServerPeer *peer) +{ + unsigned vector; + IvshmemServerPeer *other_peer; + + IVSHMEM_SERVER_DEBUG(server, "free peer %" PRId64 "\n", peer->id); + close(peer->sock_fd); + QTAILQ_REMOVE(&server->peer_list, peer, next); + + /* advertise the deletion to other peers */ + QTAILQ_FOREACH(other_peer, &server->peer_list, next) { + ivshmem_server_send_one_msg(other_peer->sock_fd, peer->id, -1); + } + + for (vector = 0; vector < peer->vectors_count; vector++) { + event_notifier_cleanup(&peer->vectors[vector]); + } + + g_free(peer); +} + +/* send the peer id and the shm_fd just after a new client connection */ +static int +ivshmem_server_send_initial_info(IvshmemServer *server, IvshmemServerPeer *peer) +{ + int ret; + + /* send our protocol version first */ + ret = ivshmem_server_send_one_msg(peer->sock_fd, IVSHMEM_PROTOCOL_VERSION, + -1); + if (ret < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot send version: %s\n", + strerror(errno)); + return -1; + } + + /* send the peer id to the client */ + ret = ivshmem_server_send_one_msg(peer->sock_fd, peer->id, -1); + if (ret < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot send peer id: %s\n", + strerror(errno)); + return -1; + } + + /* send the shm_fd */ + ret = ivshmem_server_send_one_msg(peer->sock_fd, -1, server->shm_fd); + if (ret < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot send shm fd: %s\n", + strerror(errno)); + return -1; + } + + return 0; +} + +/* handle message on listening unix socket (new client connection) */ +static int +ivshmem_server_handle_new_conn(IvshmemServer *server) +{ + IvshmemServerPeer *peer, *other_peer; + struct sockaddr_un unaddr; + socklen_t unaddr_len; + int newfd; + unsigned i; + + /* accept the incoming connection */ + unaddr_len = sizeof(unaddr); + newfd = qemu_accept(server->sock_fd, + (struct sockaddr *)&unaddr, &unaddr_len); + + if (newfd < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot accept() %s\n", strerror(errno)); + return -1; + } + + qemu_set_nonblock(newfd); + IVSHMEM_SERVER_DEBUG(server, "accept()=%d\n", newfd); + + /* allocate new structure for this peer */ + peer = g_malloc0(sizeof(*peer)); + peer->sock_fd = newfd; + + /* get an unused peer id */ + /* XXX: this could use id allocation such as Linux IDA, or simply + * a free-list */ + for (i = 0; i < G_MAXUINT16; i++) { + if (ivshmem_server_search_peer(server, server->cur_id) == NULL) { + break; + } + server->cur_id++; + } + if (i == G_MAXUINT16) { + IVSHMEM_SERVER_DEBUG(server, "cannot allocate new client id\n"); + goto fail; + } + peer->id = server->cur_id++; + + /* create eventfd, one per vector */ + peer->vectors_count = server->n_vectors; + for (i = 0; i < peer->vectors_count; i++) { + if (event_notifier_init(&peer->vectors[i], FALSE) < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot create eventfd\n"); + goto fail; + } + } + + /* send peer id and shm fd */ + if (ivshmem_server_send_initial_info(server, peer) < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot send initial info\n"); + goto fail; + } + + /* advertise the new peer to others */ + QTAILQ_FOREACH(other_peer, &server->peer_list, next) { + for (i = 0; i < peer->vectors_count; i++) { + ivshmem_server_send_one_msg(other_peer->sock_fd, peer->id, + peer->vectors[i].wfd); + } + } + + /* advertise the other peers to the new one */ + QTAILQ_FOREACH(other_peer, &server->peer_list, next) { + for (i = 0; i < peer->vectors_count; i++) { + ivshmem_server_send_one_msg(peer->sock_fd, other_peer->id, + other_peer->vectors[i].wfd); + } + } + + /* advertise the new peer to itself */ + for (i = 0; i < peer->vectors_count; i++) { + ivshmem_server_send_one_msg(peer->sock_fd, peer->id, + event_notifier_get_fd(&peer->vectors[i])); + } + + QTAILQ_INSERT_TAIL(&server->peer_list, peer, next); + IVSHMEM_SERVER_DEBUG(server, "new peer id = %" PRId64 "\n", + peer->id); + return 0; + +fail: + while (i--) { + event_notifier_cleanup(&peer->vectors[i]); + } + close(newfd); + g_free(peer); + return -1; +} + +/* Try to ftruncate a file to next power of 2 of shmsize. + * If it fails; all power of 2 above shmsize are tested until + * we reach the maximum huge page size. This is useful + * if the shm file is in a hugetlbfs that cannot be truncated to the + * shm_size value. */ +static int +ivshmem_server_ftruncate(int fd, unsigned shmsize) +{ + int ret; + struct stat mapstat; + + /* align shmsize to next power of 2 */ + shmsize = pow2ceil(shmsize); + + if (fstat(fd, &mapstat) != -1 && mapstat.st_size == shmsize) { + return 0; + } + + while (shmsize <= IVSHMEM_SERVER_MAX_HUGEPAGE_SIZE) { + ret = ftruncate(fd, shmsize); + if (ret == 0) { + return ret; + } + shmsize *= 2; + } + + return -1; +} + +/* Init a new ivshmem server */ +int +ivshmem_server_init(IvshmemServer *server, const char *unix_sock_path, + const char *shm_path, size_t shm_size, unsigned n_vectors, + bool verbose) +{ + int ret; + + memset(server, 0, sizeof(*server)); + server->verbose = verbose; + + ret = snprintf(server->unix_sock_path, sizeof(server->unix_sock_path), + "%s", unix_sock_path); + if (ret < 0 || ret >= sizeof(server->unix_sock_path)) { + IVSHMEM_SERVER_DEBUG(server, "could not copy unix socket path\n"); + return -1; + } + ret = snprintf(server->shm_path, sizeof(server->shm_path), + "%s", shm_path); + if (ret < 0 || ret >= sizeof(server->shm_path)) { + IVSHMEM_SERVER_DEBUG(server, "could not copy shm path\n"); + return -1; + } + + server->shm_size = shm_size; + server->n_vectors = n_vectors; + + QTAILQ_INIT(&server->peer_list); + + return 0; +} + +#ifdef CONFIG_LINUX + +#define HUGETLBFS_MAGIC 0x958458f6 + +static long gethugepagesize(const char *path) +{ + struct statfs fs; + int ret; + + do { + ret = statfs(path, &fs); + } while (ret != 0 && errno == EINTR); + + if (ret != 0) { + return -1; + } + + if (fs.f_type != HUGETLBFS_MAGIC) { + return -1; + } + + return fs.f_bsize; +} +#endif + +/* open shm, create and bind to the unix socket */ +int +ivshmem_server_start(IvshmemServer *server) +{ + struct sockaddr_un sun; + int shm_fd, sock_fd, ret; + + /* open shm file */ +#ifdef CONFIG_LINUX + long hpagesize; + + hpagesize = gethugepagesize(server->shm_path); + if (hpagesize < 0 && errno != ENOENT) { + IVSHMEM_SERVER_DEBUG(server, "cannot stat shm file %s: %s\n", + server->shm_path, strerror(errno)); + } + + if (hpagesize > 0) { + gchar *filename = g_strdup_printf("%s/ivshmem.XXXXXX", server->shm_path); + IVSHMEM_SERVER_DEBUG(server, "Using hugepages: %s\n", server->shm_path); + shm_fd = mkstemp(filename); + unlink(filename); + g_free(filename); + } else +#endif + { + IVSHMEM_SERVER_DEBUG(server, "Using POSIX shared memory: %s\n", + server->shm_path); + shm_fd = shm_open(server->shm_path, O_CREAT|O_RDWR, S_IRWXU); + } + + if (shm_fd < 0) { + fprintf(stderr, "cannot open shm file %s: %s\n", server->shm_path, + strerror(errno)); + return -1; + } + if (ivshmem_server_ftruncate(shm_fd, server->shm_size) < 0) { + fprintf(stderr, "ftruncate(%s) failed: %s\n", server->shm_path, + strerror(errno)); + goto err_close_shm; + } + + IVSHMEM_SERVER_DEBUG(server, "create & bind socket %s\n", + server->unix_sock_path); + + /* create the unix listening socket */ + sock_fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (sock_fd < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot create socket: %s\n", + strerror(errno)); + goto err_close_shm; + } + + sun.sun_family = AF_UNIX; + ret = snprintf(sun.sun_path, sizeof(sun.sun_path), "%s", + server->unix_sock_path); + if (ret < 0 || ret >= sizeof(sun.sun_path)) { + IVSHMEM_SERVER_DEBUG(server, "could not copy unix socket path\n"); + goto err_close_sock; + } + if (bind(sock_fd, (struct sockaddr *)&sun, sizeof(sun)) < 0) { + IVSHMEM_SERVER_DEBUG(server, "cannot connect to %s: %s\n", sun.sun_path, + strerror(errno)); + goto err_close_sock; + } + + if (listen(sock_fd, IVSHMEM_SERVER_LISTEN_BACKLOG) < 0) { + IVSHMEM_SERVER_DEBUG(server, "listen() failed: %s\n", strerror(errno)); + goto err_close_sock; + } + + server->sock_fd = sock_fd; + server->shm_fd = shm_fd; + + return 0; + +err_close_sock: + close(sock_fd); +err_close_shm: + close(shm_fd); + return -1; +} + +/* close connections to clients, the unix socket and the shm fd */ +void +ivshmem_server_close(IvshmemServer *server) +{ + IvshmemServerPeer *peer, *npeer; + + IVSHMEM_SERVER_DEBUG(server, "close server\n"); + + QTAILQ_FOREACH_SAFE(peer, &server->peer_list, next, npeer) { + ivshmem_server_free_peer(server, peer); + } + + unlink(server->unix_sock_path); + close(server->sock_fd); + close(server->shm_fd); + server->sock_fd = -1; + server->shm_fd = -1; +} + +/* get the fd_set according to the unix socket and the peer list */ +void +ivshmem_server_get_fds(const IvshmemServer *server, fd_set *fds, int *maxfd) +{ + IvshmemServerPeer *peer; + + if (server->sock_fd == -1) { + return; + } + + FD_SET(server->sock_fd, fds); + if (server->sock_fd >= *maxfd) { + *maxfd = server->sock_fd + 1; + } + + QTAILQ_FOREACH(peer, &server->peer_list, next) { + FD_SET(peer->sock_fd, fds); + if (peer->sock_fd >= *maxfd) { + *maxfd = peer->sock_fd + 1; + } + } +} + +/* process incoming messages on the sockets in fd_set */ +int +ivshmem_server_handle_fds(IvshmemServer *server, fd_set *fds, int maxfd) +{ + IvshmemServerPeer *peer, *peer_next; + + if (server->sock_fd < maxfd && FD_ISSET(server->sock_fd, fds) && + ivshmem_server_handle_new_conn(server) < 0 && errno != EINTR) { + IVSHMEM_SERVER_DEBUG(server, "ivshmem_server_handle_new_conn() " + "failed\n"); + return -1; + } + + QTAILQ_FOREACH_SAFE(peer, &server->peer_list, next, peer_next) { + /* any message from a peer socket result in a close() */ + IVSHMEM_SERVER_DEBUG(server, "peer->sock_fd=%d\n", peer->sock_fd); + if (peer->sock_fd < maxfd && FD_ISSET(peer->sock_fd, fds)) { + ivshmem_server_free_peer(server, peer); + } + } + + return 0; +} + +/* lookup peer from its id */ +IvshmemServerPeer * +ivshmem_server_search_peer(IvshmemServer *server, int64_t peer_id) +{ + IvshmemServerPeer *peer; + + QTAILQ_FOREACH(peer, &server->peer_list, next) { + if (peer->id == peer_id) { + return peer; + } + } + return NULL; +} + +/* dump our info, the list of peers their vectors on stdout */ +void +ivshmem_server_dump(const IvshmemServer *server) +{ + const IvshmemServerPeer *peer; + unsigned vector; + + /* dump peers */ + QTAILQ_FOREACH(peer, &server->peer_list, next) { + printf("peer_id = %" PRId64 "\n", peer->id); + + for (vector = 0; vector < peer->vectors_count; vector++) { + printf(" vector %d is enabled (fd=%d)\n", vector, + event_notifier_get_fd(&peer->vectors[vector])); + } + } +} diff --git a/contrib/ivshmem-server/ivshmem-server.h b/contrib/ivshmem-server/ivshmem-server.h new file mode 100644 index 0000000000..c9359a0a8a --- /dev/null +++ b/contrib/ivshmem-server/ivshmem-server.h @@ -0,0 +1,167 @@ +/* + * Copyright 6WIND S.A., 2014 + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#ifndef _IVSHMEM_SERVER_H_ +#define _IVSHMEM_SERVER_H_ + +/** + * The ivshmem server is a daemon that creates a unix socket in listen + * mode. The ivshmem clients (qemu or ivshmem-client) connect to this + * unix socket. For each client, the server will create some eventfd + * (see EVENTFD(2)), one per vector. These fd are transmitted to all + * clients using the SCM_RIGHTS cmsg message. Therefore, each client is + * able to send a notification to another client without beeing + * "profixied" by the server. + * + * We use this mechanism to send interruptions between guests. + * qemu is able to transform an event on a eventfd into a PCI MSI-x + * interruption in the guest. + * + * The ivshmem server is also able to share the file descriptor + * associated to the ivshmem shared memory. + */ + +#include +#include +#include +#include + +#include "qemu/event_notifier.h" +#include "qemu/queue.h" +#include "hw/misc/ivshmem.h" + +/** + * Maximum number of notification vectors supported by the server + */ +#define IVSHMEM_SERVER_MAX_VECTORS 64 + +/** + * Structure storing a peer + * + * Each time a client connects to an ivshmem server, a new + * IvshmemServerPeer structure is created. This peer and all its + * vectors are advertised to all connected clients through the connected + * unix sockets. + */ +typedef struct IvshmemServerPeer { + QTAILQ_ENTRY(IvshmemServerPeer) next; /**< next in list*/ + int sock_fd; /**< connected unix sock */ + int64_t id; /**< the id of the peer */ + EventNotifier vectors[IVSHMEM_SERVER_MAX_VECTORS]; /**< one per vector */ + unsigned vectors_count; /**< number of vectors */ +} IvshmemServerPeer; +QTAILQ_HEAD(IvshmemServerPeerList, IvshmemServerPeer); + +typedef struct IvshmemServerPeerList IvshmemServerPeerList; + +/** + * Structure describing an ivshmem server + * + * This structure stores all information related to our server: the name + * of the server unix socket and the list of connected peers. + */ +typedef struct IvshmemServer { + char unix_sock_path[PATH_MAX]; /**< path to unix socket */ + int sock_fd; /**< unix sock file descriptor */ + char shm_path[PATH_MAX]; /**< path to shm */ + size_t shm_size; /**< size of shm */ + int shm_fd; /**< shm file descriptor */ + unsigned n_vectors; /**< number of vectors */ + uint16_t cur_id; /**< id to be given to next client */ + bool verbose; /**< true in verbose mode */ + IvshmemServerPeerList peer_list; /**< list of peers */ +} IvshmemServer; + +/** + * Initialize an ivshmem server + * + * @server: A pointer to an uninitialized IvshmemServer structure + * @unix_sock_path: The pointer to the unix socket file name + * @shm_path: Path to the shared memory. The path corresponds to a POSIX + * shm name or a hugetlbfs mount point. + * @shm_size: Size of shared memory + * @n_vectors: Number of interrupt vectors per client + * @verbose: True to enable verbose mode + * + * Returns: 0 on success, or a negative value on error + */ +int +ivshmem_server_init(IvshmemServer *server, const char *unix_sock_path, + const char *shm_path, size_t shm_size, unsigned n_vectors, + bool verbose); + +/** + * Open the shm, then create and bind to the unix socket + * + * @server: The pointer to the initialized IvshmemServer structure + * + * Returns: 0 on success, or a negative value on error + */ +int ivshmem_server_start(IvshmemServer *server); + +/** + * Close the server + * + * Close connections to all clients, close the unix socket and the + * shared memory file descriptor. The structure remains initialized, so + * it is possible to call ivshmem_server_start() again after a call to + * ivshmem_server_close(). + * + * @server: The ivshmem server + */ +void ivshmem_server_close(IvshmemServer *server); + +/** + * Fill a fd_set with file descriptors to be monitored + * + * This function will fill a fd_set with all file descriptors that must + * be polled (unix server socket and peers unix socket). The function + * will not initialize the fd_set, it is up to the caller to do it. + * + * @server: The ivshmem server + * @fds: The fd_set to be updated + * @maxfd: Must be set to the max file descriptor + 1 in fd_set. This value is + * updated if this function adds a greater fd in fd_set. + */ +void +ivshmem_server_get_fds(const IvshmemServer *server, fd_set *fds, int *maxfd); + +/** + * Read and handle new messages + * + * Given a fd_set (for instance filled by a call to select()), handle + * incoming messages from peers. + * + * @server: The ivshmem server + * @fds: The fd_set containing the file descriptors to be checked. Note that + * file descriptors that are not related to our server are ignored. + * @maxfd: The maximum fd in fd_set, plus one. + * + * Returns: 0 on success, or a negative value on error + */ +int ivshmem_server_handle_fds(IvshmemServer *server, fd_set *fds, int maxfd); + +/** + * Search a peer from its identifier + * + * @server: The ivshmem server + * @peer_id: The identifier of the peer structure + * + * Returns: The peer structure, or NULL if not found + */ +IvshmemServerPeer * +ivshmem_server_search_peer(IvshmemServer *server, int64_t peer_id); + +/** + * Dump information of this ivshmem server and its peers on stdout + * + * @server: The ivshmem server + */ +void ivshmem_server_dump(const IvshmemServer *server); + +#endif /* _IVSHMEM_SERVER_H_ */ diff --git a/contrib/ivshmem-server/main.c b/contrib/ivshmem-server/main.c new file mode 100644 index 0000000000..54ff001c23 --- /dev/null +++ b/contrib/ivshmem-server/main.c @@ -0,0 +1,263 @@ +/* + * Copyright 6WIND S.A., 2014 + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu-common.h" + +#include "ivshmem-server.h" + +#define IVSHMEM_SERVER_DEFAULT_VERBOSE 0 +#define IVSHMEM_SERVER_DEFAULT_FOREGROUND 0 +#define IVSHMEM_SERVER_DEFAULT_PID_FILE "/var/run/ivshmem-server.pid" +#define IVSHMEM_SERVER_DEFAULT_UNIX_SOCK_PATH "/tmp/ivshmem_socket" +#define IVSHMEM_SERVER_DEFAULT_SHM_PATH "ivshmem" +#define IVSHMEM_SERVER_DEFAULT_SHM_SIZE (4*1024*1024) +#define IVSHMEM_SERVER_DEFAULT_N_VECTORS 1 + +/* used to quit on signal SIGTERM */ +static int ivshmem_server_quit; + +/* arguments given by the user */ +typedef struct IvshmemServerArgs { + bool verbose; + bool foreground; + const char *pid_file; + const char *unix_socket_path; + const char *shm_path; + uint64_t shm_size; + unsigned n_vectors; +} IvshmemServerArgs; + +/* show ivshmem_server_usage and exit with given error code */ +static void +ivshmem_server_usage(const char *name, int code) +{ + fprintf(stderr, "%s [opts]\n", name); + fprintf(stderr, " -h: show this help\n"); + fprintf(stderr, " -v: verbose mode\n"); + fprintf(stderr, " -F: foreground mode (default is to daemonize)\n"); + fprintf(stderr, " -p : path to the PID file (used in daemon\n" + " mode only).\n" + " Default=%s\n", IVSHMEM_SERVER_DEFAULT_SHM_PATH); + fprintf(stderr, " -S : path to the unix socket\n" + " to listen to.\n" + " Default=%s\n", IVSHMEM_SERVER_DEFAULT_UNIX_SOCK_PATH); + fprintf(stderr, " -m : path to the shared memory.\n" + " The path corresponds to a POSIX shm name or a\n" + " hugetlbfs mount point.\n" + " default=%s\n", IVSHMEM_SERVER_DEFAULT_SHM_PATH); + fprintf(stderr, " -l : size of shared memory in bytes. The suffix\n" + " K, M and G can be used (ex: 1K means 1024).\n" + " default=%u\n", IVSHMEM_SERVER_DEFAULT_SHM_SIZE); + fprintf(stderr, " -n : number of vectors.\n" + " default=%u\n", IVSHMEM_SERVER_DEFAULT_N_VECTORS); + + exit(code); +} + +/* parse the program arguments, exit on error */ +static void +ivshmem_server_parse_args(IvshmemServerArgs *args, int argc, char *argv[]) +{ + int c; + unsigned long long v; + Error *errp = NULL; + + while ((c = getopt(argc, argv, + "h" /* help */ + "v" /* verbose */ + "F" /* foreground */ + "p:" /* pid_file */ + "S:" /* unix_socket_path */ + "m:" /* shm_path */ + "l:" /* shm_size */ + "n:" /* n_vectors */ + )) != -1) { + + switch (c) { + case 'h': /* help */ + ivshmem_server_usage(argv[0], 0); + break; + + case 'v': /* verbose */ + args->verbose = 1; + break; + + case 'F': /* foreground */ + args->foreground = 1; + break; + + case 'p': /* pid_file */ + args->pid_file = optarg; + break; + + case 'S': /* unix_socket_path */ + args->unix_socket_path = optarg; + break; + + case 'm': /* shm_path */ + args->shm_path = optarg; + break; + + case 'l': /* shm_size */ + parse_option_size("shm_size", optarg, &args->shm_size, &errp); + if (errp) { + fprintf(stderr, "cannot parse shm size: %s\n", + error_get_pretty(errp)); + error_free(errp); + ivshmem_server_usage(argv[0], 1); + } + break; + + case 'n': /* n_vectors */ + if (parse_uint_full(optarg, &v, 0) < 0) { + fprintf(stderr, "cannot parse n_vectors\n"); + ivshmem_server_usage(argv[0], 1); + } + args->n_vectors = v; + break; + + default: + ivshmem_server_usage(argv[0], 1); + break; + } + } + + if (args->n_vectors > IVSHMEM_SERVER_MAX_VECTORS) { + fprintf(stderr, "too many requested vectors (max is %d)\n", + IVSHMEM_SERVER_MAX_VECTORS); + ivshmem_server_usage(argv[0], 1); + } + + if (args->verbose == 1 && args->foreground == 0) { + fprintf(stderr, "cannot use verbose in daemon mode\n"); + ivshmem_server_usage(argv[0], 1); + } +} + +/* wait for events on listening server unix socket and connected client + * sockets */ +static int +ivshmem_server_poll_events(IvshmemServer *server) +{ + fd_set fds; + int ret = 0, maxfd; + + while (!ivshmem_server_quit) { + + FD_ZERO(&fds); + maxfd = 0; + ivshmem_server_get_fds(server, &fds, &maxfd); + + ret = select(maxfd, &fds, NULL, NULL, NULL); + + if (ret < 0) { + if (errno == EINTR) { + continue; + } + + fprintf(stderr, "select error: %s\n", strerror(errno)); + break; + } + if (ret == 0) { + continue; + } + + if (ivshmem_server_handle_fds(server, &fds, maxfd) < 0) { + fprintf(stderr, "ivshmem_server_handle_fds() failed\n"); + break; + } + } + + return ret; +} + +static void +ivshmem_server_quit_cb(int signum) +{ + ivshmem_server_quit = 1; +} + +int +main(int argc, char *argv[]) +{ + IvshmemServer server; + struct sigaction sa, sa_quit; + IvshmemServerArgs args = { + .verbose = IVSHMEM_SERVER_DEFAULT_VERBOSE, + .foreground = IVSHMEM_SERVER_DEFAULT_FOREGROUND, + .pid_file = IVSHMEM_SERVER_DEFAULT_PID_FILE, + .unix_socket_path = IVSHMEM_SERVER_DEFAULT_UNIX_SOCK_PATH, + .shm_path = IVSHMEM_SERVER_DEFAULT_SHM_PATH, + .shm_size = IVSHMEM_SERVER_DEFAULT_SHM_SIZE, + .n_vectors = IVSHMEM_SERVER_DEFAULT_N_VECTORS, + }; + int ret = 1; + + /* parse arguments, will exit on error */ + ivshmem_server_parse_args(&args, argc, argv); + + /* Ignore SIGPIPE, see this link for more info: + * http://www.mail-archive.com/libevent-users@monkey.org/msg01606.html */ + sa.sa_handler = SIG_IGN; + sa.sa_flags = 0; + if (sigemptyset(&sa.sa_mask) == -1 || + sigaction(SIGPIPE, &sa, 0) == -1) { + perror("failed to ignore SIGPIPE; sigaction"); + goto err; + } + + sa_quit.sa_handler = ivshmem_server_quit_cb; + sa_quit.sa_flags = 0; + if (sigemptyset(&sa_quit.sa_mask) == -1 || + sigaction(SIGTERM, &sa_quit, 0) == -1) { + perror("failed to add SIGTERM handler; sigaction"); + goto err; + } + + /* init the ivshms structure */ + if (ivshmem_server_init(&server, args.unix_socket_path, args.shm_path, + args.shm_size, args.n_vectors, args.verbose) < 0) { + fprintf(stderr, "cannot init server\n"); + goto err; + } + + /* start the ivshmem server (open shm & unix socket) */ + if (ivshmem_server_start(&server) < 0) { + fprintf(stderr, "cannot bind\n"); + goto err; + } + + /* daemonize if asked to */ + if (!args.foreground) { + FILE *fp; + + if (qemu_daemon(1, 1) < 0) { + fprintf(stderr, "cannot daemonize: %s\n", strerror(errno)); + goto err_close; + } + + /* write pid file */ + fp = fopen(args.pid_file, "w"); + if (fp == NULL) { + fprintf(stderr, "cannot write pid file: %s\n", strerror(errno)); + goto err_close; + } + + fprintf(fp, "%d\n", (int) getpid()); + fclose(fp); + } + + ivshmem_server_poll_events(&server); + fprintf(stdout, "server disconnected\n"); + ret = 0; + +err_close: + ivshmem_server_close(&server); +err: + return ret; +} diff --git a/default-configs/pci.mak b/default-configs/pci.mak index 7e10903baa..f250119e1b 100644 --- a/default-configs/pci.mak +++ b/default-configs/pci.mak @@ -35,5 +35,5 @@ CONFIG_SDHCI=y CONFIG_EDU=y CONFIG_VGA=y CONFIG_VGA_PCI=y -CONFIG_IVSHMEM=$(CONFIG_KVM) +CONFIG_IVSHMEM=$(CONFIG_POSIX) CONFIG_ROCKER=y diff --git a/docs/specs/ivshmem_device_spec.txt b/docs/specs/ivshmem_device_spec.txt index 667a8628f0..d318d65c32 100644 --- a/docs/specs/ivshmem_device_spec.txt +++ b/docs/specs/ivshmem_device_spec.txt @@ -2,30 +2,106 @@ Device Specification for Inter-VM shared memory device ------------------------------------------------------ -The Inter-VM shared memory device is designed to share a region of memory to -userspace in multiple virtual guests. The memory region does not belong to any -guest, but is a POSIX memory object on the host. Optionally, the device may -support sending interrupts to other guests sharing the same memory region. +The Inter-VM shared memory device is designed to share a memory region (created +on the host via the POSIX shared memory API) between multiple QEMU processes +running different guests. In order for all guests to be able to pick up the +shared memory area, it is modeled by QEMU as a PCI device exposing said memory +to the guest as a PCI BAR. +The memory region does not belong to any guest, but is a POSIX memory object on +the host. The host can access this shared memory if needed. + +The device also provides an optional communication mechanism between guests +sharing the same memory object. More details about that in the section 'Guest to +guest communication' section. The Inter-VM PCI device ----------------------- -*BARs* +From the VM point of view, the ivshmem PCI device supports three BARs. -The device supports three BARs. BAR0 is a 1 Kbyte MMIO region to support -registers. BAR1 is used for MSI-X when it is enabled in the device. BAR2 is -used to map the shared memory object from the host. The size of BAR2 is -specified when the guest is started and must be a power of 2 in size. +- BAR0 is a 1 Kbyte MMIO region to support registers and interrupts when MSI is + not used. +- BAR1 is used for MSI-X when it is enabled in the device. +- BAR2 is used to access the shared memory object. -*Registers* +It is your choice how to use the device but you must choose between two +behaviors : -The device currently supports 4 registers of 32-bits each. Registers -are used for synchronization between guests sharing the same memory object when -interrupts are supported (this requires using the shared memory server). +- basically, if you only need the shared memory part, you will map BAR2. + This way, you have access to the shared memory in guest and can use it as you + see fit (memnic, for example, uses it in userland + http://dpdk.org/browse/memnic). -The server assigns each VM an ID number and sends this ID number to the QEMU -process when the guest starts. +- BAR0 and BAR1 are used to implement an optional communication mechanism + through interrupts in the guests. If you need an event mechanism between the + guests accessing the shared memory, you will most likely want to write a + kernel driver that will handle interrupts. See details in the section 'Guest + to guest communication' section. + +The behavior is chosen when starting your QEMU processes: +- no communication mechanism needed, the first QEMU to start creates the shared + memory on the host, subsequent QEMU processes will use it. + +- communication mechanism needed, an ivshmem server must be started before any + QEMU processes, then each QEMU process connects to the server unix socket. + +For more details on the QEMU ivshmem parameters, see qemu-doc documentation. + + +Guest to guest communication +---------------------------- + +This section details the communication mechanism between the guests accessing +the ivhsmem shared memory. + +*ivshmem server* + +This server code is available in qemu.git/contrib/ivshmem-server. + +The server must be started on the host before any guest. +It creates a shared memory object then waits for clients to connect on a unix +socket. All the messages are little-endian int64_t integer. + +For each client (QEMU process) that connects to the server: +- the server sends a protocol version, if client does not support it, the client + closes the communication, +- the server assigns an ID for this client and sends this ID to him as the first + message, +- the server sends a fd to the shared memory object to this client, +- the server creates a new set of host eventfds associated to the new client and + sends this set to all already connected clients, +- finally, the server sends all the eventfds sets for all clients to the new + client. + +The server signals all clients when one of them disconnects. + +The client IDs are limited to 16 bits because of the current implementation (see +Doorbell register in 'PCI device registers' subsection). Hence only 65536 +clients are supported. + +All the file descriptors (fd to the shared memory, eventfds for each client) +are passed to clients using SCM_RIGHTS over the server unix socket. + +Apart from the current ivshmem implementation in QEMU, an ivshmem client has +been provided in qemu.git/contrib/ivshmem-client for debug. + +*QEMU as an ivshmem client* + +At initialisation, when creating the ivshmem device, QEMU first receives a +protocol version and closes communication with server if it does not match. +Then, QEMU gets its ID from the server then makes it available through BAR0 +IVPosition register for the VM to use (see 'PCI device registers' subsection). +QEMU then uses the fd to the shared memory to map it to BAR2. +eventfds for all other clients received from the server are stored to implement +BAR0 Doorbell register (see 'PCI device registers' subsection). +Finally, eventfds assigned to this QEMU process are used to send interrupts in +this VM. + +*PCI device registers* + +From the VM point of view, the ivshmem PCI device supports 4 registers of +32-bits each. enum ivshmem_registers { IntrMask = 0, @@ -49,8 +125,8 @@ bit to 0 and unmasked by setting the first bit to 1. IVPosition Register: The IVPosition register is read-only and reports the guest's ID number. The guest IDs are non-negative integers. When using the server, since the server is a separate process, the VM ID will only be set when -the device is ready (shared memory is received from the server and accessible via -the device). If the device is not ready, the IVPosition will return -1. +the device is ready (shared memory is received from the server and accessible +via the device). If the device is not ready, the IVPosition will return -1. Applications should ensure that they have a valid VM ID before accessing the shared memory. @@ -59,8 +135,8 @@ Doorbell register. The doorbell register is 32-bits, logically divided into two 16-bit fields. The high 16-bits are the guest ID to interrupt and the low 16-bits are the interrupt vector to trigger. The semantics of the value written to the doorbell depends on whether the device is using MSI or a regular -pin-based interrupt. In short, MSI uses vectors while regular interrupts set the -status register. +pin-based interrupt. In short, MSI uses vectors while regular interrupts set +the status register. Regular Interrupts @@ -71,7 +147,7 @@ interrupt in the destination guest. Message Signalled Interrupts -A ivshmem device may support multiple MSI vectors. If so, the lower 16-bits +An ivshmem device may support multiple MSI vectors. If so, the lower 16-bits written to the Doorbell register must be between 0 and the maximum number of vectors the guest supports. The lower 16 bits written to the doorbell is the MSI vector that will be raised in the destination guest. The number of MSI @@ -83,14 +159,3 @@ interrupt itself should be communicated via the shared memory region. Devices supporting multiple MSI vectors can use different vectors to indicate different events have occurred. The semantics of interrupt vectors are left to the user's discretion. - - -Usage in the Guest ------------------- - -The shared memory device is intended to be used with the provided UIO driver. -Very little configuration is needed. The guest should map BAR0 to access the -registers (an array of 32-bit ints allows simple writing) and map BAR2 to -access the shared memory region itself. The size of the shared memory region -is specified when the guest (or shared memory server) is started. A guest may -map the whole shared memory region or only part of it. diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index cc76989a39..83d7bd3e5f 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -19,6 +19,7 @@ #include "hw/hw.h" #include "hw/i386/pc.h" #include "hw/pci/pci.h" +#include "hw/pci/msi.h" #include "hw/pci/msix.h" #include "sysemu/kvm.h" #include "migration/migration.h" @@ -26,6 +27,10 @@ #include "qemu/event_notifier.h" #include "qemu/fifo8.h" #include "sysemu/char.h" +#include "sysemu/hostmem.h" +#include "qapi/visitor.h" + +#include "hw/misc/ivshmem.h" #include #include @@ -34,6 +39,7 @@ #define PCI_VENDOR_ID_IVSHMEM PCI_VENDOR_ID_REDHAT_QUMRANET #define PCI_DEVICE_ID_IVSHMEM 0x1110 +#define IVSHMEM_MAX_PEERS G_MAXUINT16 #define IVSHMEM_IOEVENTFD 0 #define IVSHMEM_MSI 1 @@ -54,24 +60,26 @@ #define IVSHMEM(obj) \ OBJECT_CHECK(IVShmemState, (obj), TYPE_IVSHMEM) +#define IVSHMEM_MEMDEV_PROP "memdev" + typedef struct Peer { int nb_eventfds; EventNotifier *eventfds; } Peer; -typedef struct EventfdEntry { +typedef struct MSIVector { PCIDevice *pdev; - int vector; -} EventfdEntry; + int virq; +} MSIVector; typedef struct IVShmemState { /*< private >*/ PCIDevice parent_obj; /*< public >*/ + HostMemoryBackend *hostmem; uint32_t intrmask; uint32_t intrstatus; - uint32_t doorbell; CharDriverState **eventfd_chr; CharDriverState *server_chr; @@ -85,18 +93,15 @@ typedef struct IVShmemState { MemoryRegion bar; MemoryRegion ivshmem; uint64_t ivshmem_size; /* size of shared memory region */ - uint32_t ivshmem_attr; uint32_t ivshmem_64bit; - int shm_fd; /* shared memory file descriptor */ Peer *peers; - int nb_peers; /* how many guests we have space for */ - int max_peer; /* maximum numbered peer */ + int nb_peers; /* how many peers we have space for */ int vm_id; uint32_t vectors; uint32_t features; - EventfdEntry *eventfd_table; + MSIVector *msi_vectors; Error *migration_blocker; @@ -119,12 +124,8 @@ static inline uint32_t ivshmem_has_feature(IVShmemState *ivs, return (ivs->features & (1 << feature)); } -static inline bool is_power_of_two(uint64_t x) { - return (x & (x - 1)) == 0; -} - /* accessing registers - based on rtl8139 */ -static void ivshmem_update_irq(IVShmemState *s, int val) +static void ivshmem_update_irq(IVShmemState *s) { PCIDevice *d = PCI_DEVICE(s); int isr; @@ -145,7 +146,7 @@ static void ivshmem_IntrMask_write(IVShmemState *s, uint32_t val) s->intrmask = val; - ivshmem_update_irq(s, val); + ivshmem_update_irq(s); } static uint32_t ivshmem_IntrMask_read(IVShmemState *s) @@ -163,7 +164,7 @@ static void ivshmem_IntrStatus_write(IVShmemState *s, uint32_t val) s->intrstatus = val; - ivshmem_update_irq(s, val); + ivshmem_update_irq(s); } static uint32_t ivshmem_IntrStatus_read(IVShmemState *s) @@ -173,7 +174,7 @@ static uint32_t ivshmem_IntrStatus_read(IVShmemState *s) /* reading ISR clears all interrupts */ s->intrstatus = 0; - ivshmem_update_irq(s, 0); + ivshmem_update_irq(s); return ret; } @@ -201,7 +202,7 @@ static void ivshmem_io_write(void *opaque, hwaddr addr, case DOORBELL: /* check that dest VM ID is reasonable */ - if (dest > s->max_peer) { + if (dest >= s->nb_peers) { IVSHMEM_DPRINTF("Invalid destination VM ID (%d)\n", dest); break; } @@ -210,10 +211,13 @@ static void ivshmem_io_write(void *opaque, hwaddr addr, if (vector < s->peers[dest].nb_eventfds) { IVSHMEM_DPRINTF("Notifying VM %d on vector %d\n", dest, vector); event_notifier_set(&s->peers[dest].eventfds[vector]); + } else { + IVSHMEM_DPRINTF("Invalid destination vector %d on VM %d\n", + vector, dest); } break; default: - IVSHMEM_DPRINTF("Invalid VM Doorbell VM %d\n", dest); + IVSHMEM_DPRINTF("Unhandled write " TARGET_FMT_plx "\n", addr); } } @@ -236,7 +240,7 @@ static uint64_t ivshmem_io_read(void *opaque, hwaddr addr, case IVPOSITION: /* return my VM ID if the memory is mapped */ - if (s->shm_fd > 0) { + if (memory_region_is_mapped(&s->ivshmem)) { ret = s->vm_id; } else { ret = -1; @@ -265,14 +269,14 @@ static void ivshmem_receive(void *opaque, const uint8_t *buf, int size) { IVShmemState *s = opaque; - ivshmem_IntrStatus_write(s, *buf); + IVSHMEM_DPRINTF("ivshmem_receive 0x%02x size: %d\n", *buf, size); - IVSHMEM_DPRINTF("ivshmem_receive 0x%02x\n", *buf); + ivshmem_IntrStatus_write(s, *buf); } static int ivshmem_can_receive(void * opaque) { - return 8; + return sizeof(int64_t); } static void ivshmem_event(void *opaque, int event) @@ -282,11 +286,70 @@ static void ivshmem_event(void *opaque, int event) static void fake_irqfd(void *opaque, const uint8_t *buf, int size) { - EventfdEntry *entry = opaque; + MSIVector *entry = opaque; PCIDevice *pdev = entry->pdev; + IVShmemState *s = IVSHMEM(pdev); + int vector = entry - s->msi_vectors; - IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, entry->vector); - msix_notify(pdev, entry->vector); + IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, vector); + msix_notify(pdev, vector); +} + +static int ivshmem_vector_unmask(PCIDevice *dev, unsigned vector, + MSIMessage msg) +{ + IVShmemState *s = IVSHMEM(dev); + EventNotifier *n = &s->peers[s->vm_id].eventfds[vector]; + MSIVector *v = &s->msi_vectors[vector]; + int ret; + + IVSHMEM_DPRINTF("vector unmask %p %d\n", dev, vector); + + ret = kvm_irqchip_update_msi_route(kvm_state, v->virq, msg, dev); + if (ret < 0) { + return ret; + } + + return kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL, v->virq); +} + +static void ivshmem_vector_mask(PCIDevice *dev, unsigned vector) +{ + IVShmemState *s = IVSHMEM(dev); + EventNotifier *n = &s->peers[s->vm_id].eventfds[vector]; + int ret; + + IVSHMEM_DPRINTF("vector mask %p %d\n", dev, vector); + + ret = kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, n, + s->msi_vectors[vector].virq); + if (ret != 0) { + error_report("remove_irqfd_notifier_gsi failed"); + } +} + +static void ivshmem_vector_poll(PCIDevice *dev, + unsigned int vector_start, + unsigned int vector_end) +{ + IVShmemState *s = IVSHMEM(dev); + unsigned int vector; + + IVSHMEM_DPRINTF("vector poll %p %d-%d\n", dev, vector_start, vector_end); + + vector_end = MIN(vector_end, s->vectors); + + for (vector = vector_start; vector < vector_end; vector++) { + EventNotifier *notifier = &s->peers[s->vm_id].eventfds[vector]; + + if (!msix_is_masked(dev, vector)) { + continue; + } + + if (event_notifier_test_and_clear(notifier)) { + msix_set_pending(dev, vector); + } + } } static CharDriverState* create_eventfd_chr_device(void * opaque, EventNotifier *n, @@ -294,24 +357,26 @@ static CharDriverState* create_eventfd_chr_device(void * opaque, EventNotifier * { /* create a event character device based on the passed eventfd */ IVShmemState *s = opaque; - CharDriverState * chr; + PCIDevice *pdev = PCI_DEVICE(s); int eventfd = event_notifier_get_fd(n); + CharDriverState *chr; + + s->msi_vectors[vector].pdev = pdev; chr = qemu_chr_open_eventfd(eventfd); if (chr == NULL) { - error_report("creating eventfd for eventfd %d failed", eventfd); - exit(1); + error_report("creating chardriver for eventfd %d failed", eventfd); + return NULL; } qemu_chr_fe_claim_no_fail(chr); /* if MSI is supported we need multiple interrupts */ if (ivshmem_has_feature(s, IVSHMEM_MSI)) { - s->eventfd_table[vector].pdev = PCI_DEVICE(s); - s->eventfd_table[vector].vector = vector; + s->msi_vectors[vector].pdev = PCI_DEVICE(s); qemu_chr_add_handlers(chr, ivshmem_can_receive, fake_irqfd, - ivshmem_event, &s->eventfd_table[vector]); + ivshmem_event, &s->msi_vectors[vector]); } else { qemu_chr_add_handlers(chr, ivshmem_can_receive, ivshmem_receive, ivshmem_event, s); @@ -321,22 +386,23 @@ static CharDriverState* create_eventfd_chr_device(void * opaque, EventNotifier * } -static int check_shm_size(IVShmemState *s, int fd) { +static int check_shm_size(IVShmemState *s, int fd, Error **errp) +{ /* check that the guest isn't going to try and map more memory than the * the object has allocated return -1 to indicate error */ struct stat buf; if (fstat(fd, &buf) < 0) { - error_report("exiting: fstat on fd %d failed: %s", - fd, strerror(errno)); + error_setg(errp, "exiting: fstat on fd %d failed: %s", + fd, strerror(errno)); return -1; } if (s->ivshmem_size > buf.st_size) { - error_report("Requested memory size greater" - " than shared object size (%" PRIu64 " > %" PRIu64")", - s->ivshmem_size, (uint64_t)buf.st_size); + error_setg(errp, "Requested memory size greater" + " than shared object size (%" PRIu64 " > %" PRIu64")", + s->ivshmem_size, (uint64_t)buf.st_size); return -1; } else { return 0; @@ -345,13 +411,16 @@ static int check_shm_size(IVShmemState *s, int fd) { /* create the shared memory BAR when we are not using the server, so we can * create the BAR and map the memory immediately */ -static void create_shared_memory_BAR(IVShmemState *s, int fd) { - +static int create_shared_memory_BAR(IVShmemState *s, int fd, uint8_t attr, + Error **errp) +{ void * ptr; - s->shm_fd = fd; - ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); + if (ptr == MAP_FAILED) { + error_setg_errno(errp, errno, "Failed to mmap shared memory"); + return -1; + } memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s), "ivshmem.bar2", s->ivshmem_size, ptr); @@ -359,7 +428,9 @@ static void create_shared_memory_BAR(IVShmemState *s, int fd) { memory_region_add_subregion(&s->bar, 0, &s->ivshmem); /* region for shared memory */ - pci_register_bar(PCI_DEVICE(s), 2, s->ivshmem_attr, &s->bar); + pci_register_bar(PCI_DEVICE(s), 2, attr, &s->bar); + + return 0; } static void ivshmem_add_eventfd(IVShmemState *s, int posn, int i) @@ -382,25 +453,26 @@ static void ivshmem_del_eventfd(IVShmemState *s, int posn, int i) &s->peers[posn].eventfds[i]); } -static void close_guest_eventfds(IVShmemState *s, int posn) +static void close_peer_eventfds(IVShmemState *s, int posn) { - int i, guest_curr_max; + int i, n; if (!ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) { return; } if (posn < 0 || posn >= s->nb_peers) { + error_report("invalid peer %d", posn); return; } - guest_curr_max = s->peers[posn].nb_eventfds; + n = s->peers[posn].nb_eventfds; memory_region_transaction_begin(); - for (i = 0; i < guest_curr_max; i++) { + for (i = 0; i < n; i++) { ivshmem_del_eventfd(s, posn, i); } memory_region_transaction_commit(); - for (i = 0; i < guest_curr_max; i++) { + for (i = 0; i < n; i++) { event_notifier_cleanup(&s->peers[posn].eventfds[i]); } @@ -409,125 +481,207 @@ static void close_guest_eventfds(IVShmemState *s, int posn) } /* this function increase the dynamic storage need to store data about other - * guests */ -static int increase_dynamic_storage(IVShmemState *s, int new_min_size) + * peers */ +static int resize_peers(IVShmemState *s, int new_min_size) { - int j, old_nb_alloc; + int j, old_size; - /* check for integer overflow */ - if (new_min_size >= INT_MAX / sizeof(Peer) - 1 || new_min_size <= 0) { + /* limit number of max peers */ + if (new_min_size <= 0 || new_min_size > IVSHMEM_MAX_PEERS) { return -1; } - - old_nb_alloc = s->nb_peers; - - if (new_min_size >= s->nb_peers) { - /* +1 because #new_min_size is used as last array index */ - s->nb_peers = new_min_size + 1; - } else { + if (new_min_size <= s->nb_peers) { return 0; } - IVSHMEM_DPRINTF("bumping storage to %d guests\n", s->nb_peers); + old_size = s->nb_peers; + s->nb_peers = new_min_size; + + IVSHMEM_DPRINTF("bumping storage to %d peers\n", s->nb_peers); + s->peers = g_realloc(s->peers, s->nb_peers * sizeof(Peer)); - /* zero out new pointers */ - for (j = old_nb_alloc; j < s->nb_peers; j++) { - s->peers[j].eventfds = NULL; + for (j = old_size; j < s->nb_peers; j++) { + s->peers[j].eventfds = g_new0(EventNotifier, s->vectors); s->peers[j].nb_eventfds = 0; } return 0; } +static bool fifo_update_and_get(IVShmemState *s, const uint8_t *buf, int size, + void *data, size_t len) +{ + const uint8_t *p; + uint32_t num; + + assert(len <= sizeof(int64_t)); /* limitation of the fifo */ + if (fifo8_is_empty(&s->incoming_fifo) && size == len) { + memcpy(data, buf, size); + return true; + } + + IVSHMEM_DPRINTF("short read of %d bytes\n", size); + + num = MIN(size, sizeof(int64_t) - fifo8_num_used(&s->incoming_fifo)); + fifo8_push_all(&s->incoming_fifo, buf, num); + + if (fifo8_num_used(&s->incoming_fifo) < len) { + assert(num == 0); + return false; + } + + size -= num; + buf += num; + p = fifo8_pop_buf(&s->incoming_fifo, len, &num); + assert(num == len); + + memcpy(data, p, len); + + if (size > 0) { + fifo8_push_all(&s->incoming_fifo, buf, size); + } + + return true; +} + +static bool fifo_update_and_get_i64(IVShmemState *s, + const uint8_t *buf, int size, int64_t *i64) +{ + if (fifo_update_and_get(s, buf, size, i64, sizeof(*i64))) { + *i64 = GINT64_FROM_LE(*i64); + return true; + } + + return false; +} + +static int ivshmem_add_kvm_msi_virq(IVShmemState *s, int vector) +{ + PCIDevice *pdev = PCI_DEVICE(s); + MSIMessage msg = msix_get_message(pdev, vector); + int ret; + + IVSHMEM_DPRINTF("ivshmem_add_kvm_msi_virq vector:%d\n", vector); + + if (s->msi_vectors[vector].pdev != NULL) { + return 0; + } + + ret = kvm_irqchip_add_msi_route(kvm_state, msg, pdev); + if (ret < 0) { + error_report("ivshmem: kvm_irqchip_add_msi_route failed"); + return -1; + } + + s->msi_vectors[vector].virq = ret; + s->msi_vectors[vector].pdev = pdev; + + return 0; +} + +static void setup_interrupt(IVShmemState *s, int vector) +{ + EventNotifier *n = &s->peers[s->vm_id].eventfds[vector]; + bool with_irqfd = kvm_msi_via_irqfd_enabled() && + ivshmem_has_feature(s, IVSHMEM_MSI); + PCIDevice *pdev = PCI_DEVICE(s); + + IVSHMEM_DPRINTF("setting up interrupt for vector: %d\n", vector); + + if (!with_irqfd) { + IVSHMEM_DPRINTF("with eventfd"); + s->eventfd_chr[vector] = create_eventfd_chr_device(s, n, vector); + } else if (msix_enabled(pdev)) { + IVSHMEM_DPRINTF("with irqfd"); + if (ivshmem_add_kvm_msi_virq(s, vector) < 0) { + return; + } + + if (!msix_is_masked(pdev, vector)) { + kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL, + s->msi_vectors[vector].virq); + } + } else { + /* it will be delayed until msix is enabled, in write_config */ + IVSHMEM_DPRINTF("with irqfd, delayed until msix enabled"); + } +} + static void ivshmem_read(void *opaque, const uint8_t *buf, int size) { IVShmemState *s = opaque; - int incoming_fd, tmp_fd; - int guest_max_eventfd; - long incoming_posn; + int incoming_fd; + int new_eventfd; + int64_t incoming_posn; + Error *err = NULL; + Peer *peer; - if (fifo8_is_empty(&s->incoming_fifo) && size == sizeof(incoming_posn)) { - memcpy(&incoming_posn, buf, size); - } else { - const uint8_t *p; - uint32_t num; - - IVSHMEM_DPRINTF("short read of %d bytes\n", size); - num = MAX(size, sizeof(long) - fifo8_num_used(&s->incoming_fifo)); - fifo8_push_all(&s->incoming_fifo, buf, num); - if (fifo8_num_used(&s->incoming_fifo) < sizeof(incoming_posn)) { - return; - } - size -= num; - buf += num; - p = fifo8_pop_buf(&s->incoming_fifo, sizeof(incoming_posn), &num); - g_assert(num == sizeof(incoming_posn)); - memcpy(&incoming_posn, p, sizeof(incoming_posn)); - if (size > 0) { - fifo8_push_all(&s->incoming_fifo, buf, size); - } + if (!fifo_update_and_get_i64(s, buf, size, &incoming_posn)) { + return; } if (incoming_posn < -1) { - IVSHMEM_DPRINTF("invalid incoming_posn %ld\n", incoming_posn); + IVSHMEM_DPRINTF("invalid incoming_posn %" PRId64 "\n", incoming_posn); return; } /* pick off s->server_chr->msgfd and store it, posn should accompany msg */ - tmp_fd = qemu_chr_fe_get_msgfd(s->server_chr); - IVSHMEM_DPRINTF("posn is %ld, fd is %d\n", incoming_posn, tmp_fd); + incoming_fd = qemu_chr_fe_get_msgfd(s->server_chr); + IVSHMEM_DPRINTF("posn is %" PRId64 ", fd is %d\n", + incoming_posn, incoming_fd); - /* make sure we have enough space for this guest */ + /* make sure we have enough space for this peer */ if (incoming_posn >= s->nb_peers) { - if (increase_dynamic_storage(s, incoming_posn) < 0) { - error_report("increase_dynamic_storage() failed"); - if (tmp_fd != -1) { - close(tmp_fd); + if (resize_peers(s, incoming_posn + 1) < 0) { + error_report("failed to resize peers array"); + if (incoming_fd != -1) { + close(incoming_fd); } return; } } - if (tmp_fd == -1) { - /* if posn is positive and unseen before then this is our posn*/ - if ((incoming_posn >= 0) && - (s->peers[incoming_posn].eventfds == NULL)) { - /* receive our posn */ - s->vm_id = incoming_posn; - return; - } else { - /* otherwise an fd == -1 means an existing guest has gone away */ - IVSHMEM_DPRINTF("posn %ld has gone away\n", incoming_posn); - close_guest_eventfds(s, incoming_posn); - return; - } - } - - /* because of the implementation of get_msgfd, we need a dup */ - incoming_fd = dup(tmp_fd); + peer = &s->peers[incoming_posn]; if (incoming_fd == -1) { - error_report("could not allocate file descriptor %s", strerror(errno)); - close(tmp_fd); + /* if posn is positive and unseen before then this is our posn*/ + if (incoming_posn >= 0 && s->vm_id == -1) { + /* receive our posn */ + s->vm_id = incoming_posn; + } else { + /* otherwise an fd == -1 means an existing peer has gone away */ + IVSHMEM_DPRINTF("posn %" PRId64 " has gone away\n", incoming_posn); + close_peer_eventfds(s, incoming_posn); + } return; } /* if the position is -1, then it's shared memory region fd */ if (incoming_posn == -1) { - void * map_ptr; - s->max_peer = 0; + if (memory_region_is_mapped(&s->ivshmem)) { + error_report("shm already initialized"); + close(incoming_fd); + return; + } - if (check_shm_size(s, incoming_fd) == -1) { - exit(1); + if (check_shm_size(s, incoming_fd, &err) == -1) { + error_report_err(err); + close(incoming_fd); + return; } /* mmap the region and map into the BAR2 */ map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, incoming_fd, 0); + if (map_ptr == MAP_FAILED) { + error_report("Failed to mmap shared memory %s", strerror(errno)); + close(incoming_fd); + return; + } memory_region_init_ram_ptr(&s->ivshmem, OBJECT(s), "ivshmem.bar2", s->ivshmem_size, map_ptr); vmstate_register_ram(&s->ivshmem, DEVICE(s)); @@ -537,46 +691,61 @@ static void ivshmem_read(void *opaque, const uint8_t *buf, int size) memory_region_add_subregion(&s->bar, 0, &s->ivshmem); - /* only store the fd if it is successfully mapped */ - s->shm_fd = incoming_fd; - + close(incoming_fd); return; } - /* each guest has an array of eventfds, and we keep track of how many - * guests for each VM */ - guest_max_eventfd = s->peers[incoming_posn].nb_eventfds; - - if (guest_max_eventfd == 0) { - /* one eventfd per MSI vector */ - s->peers[incoming_posn].eventfds = g_new(EventNotifier, s->vectors); + /* each peer has an associated array of eventfds, and we keep + * track of how many eventfds received so far */ + /* get a new eventfd: */ + if (peer->nb_eventfds >= s->vectors) { + error_report("Too many eventfd received, device has %d vectors", + s->vectors); + close(incoming_fd); + return; } - /* this is an eventfd for a particular guest VM */ - IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn, - guest_max_eventfd, incoming_fd); - event_notifier_init_fd(&s->peers[incoming_posn].eventfds[guest_max_eventfd], - incoming_fd); + new_eventfd = peer->nb_eventfds++; - /* increment count for particular guest */ - s->peers[incoming_posn].nb_eventfds++; - - /* keep track of the maximum VM ID */ - if (incoming_posn > s->max_peer) { - s->max_peer = incoming_posn; - } + /* this is an eventfd for a particular peer VM */ + IVSHMEM_DPRINTF("eventfds[%" PRId64 "][%d] = %d\n", incoming_posn, + new_eventfd, incoming_fd); + event_notifier_init_fd(&peer->eventfds[new_eventfd], incoming_fd); + fcntl_setfl(incoming_fd, O_NONBLOCK); /* msix/irqfd poll non block */ if (incoming_posn == s->vm_id) { - s->eventfd_chr[guest_max_eventfd] = create_eventfd_chr_device(s, - &s->peers[s->vm_id].eventfds[guest_max_eventfd], - guest_max_eventfd); + setup_interrupt(s, new_eventfd); } if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) { - ivshmem_add_eventfd(s, incoming_posn, guest_max_eventfd); + ivshmem_add_eventfd(s, incoming_posn, new_eventfd); } } +static void ivshmem_check_version(void *opaque, const uint8_t * buf, int size) +{ + IVShmemState *s = opaque; + int tmp; + int64_t version; + + if (!fifo_update_and_get_i64(s, buf, size, &version)) { + return; + } + + tmp = qemu_chr_fe_get_msgfd(s->server_chr); + if (tmp != -1 || version != IVSHMEM_PROTOCOL_VERSION) { + fprintf(stderr, "incompatible version, you are connecting to a ivshmem-" + "server using a different protocol please check your setup\n"); + qemu_chr_delete(s->server_chr); + s->server_chr = NULL; + return; + } + + IVSHMEM_DPRINTF("version check ok, switch to real chardev handler\n"); + qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, ivshmem_read, + ivshmem_event, s); +} + /* Select the MSI-X vectors used by device. * ivshmem maps events to vectors statically, so * we just enable all vectors on init and after reset. */ @@ -585,6 +754,7 @@ static void ivshmem_use_msix(IVShmemState * s) PCIDevice *d = PCI_DEVICE(s); int i; + IVSHMEM_DPRINTF("%s, msix present: %d\n", __func__, msix_present(d)); if (!msix_present(d)) { return; } @@ -599,128 +769,127 @@ static void ivshmem_reset(DeviceState *d) IVShmemState *s = IVSHMEM(d); s->intrstatus = 0; + s->intrmask = 0; ivshmem_use_msix(s); } -static uint64_t ivshmem_get_size(IVShmemState * s) { - - uint64_t value; - char *ptr; - - value = strtoull(s->sizearg, &ptr, 10); - switch (*ptr) { - case 0: case 'M': case 'm': - value <<= 20; - break; - case 'G': case 'g': - value <<= 30; - break; - default: - error_report("invalid ram size: %s", s->sizearg); - exit(1); - } - - /* BARs must be a power of 2 */ - if (!is_power_of_two(value)) { - error_report("size must be power of 2"); - exit(1); - } - - return value; -} - -static void ivshmem_setup_msi(IVShmemState * s) +static int ivshmem_setup_msi(IVShmemState * s) { if (msix_init_exclusive_bar(PCI_DEVICE(s), s->vectors, 1)) { - IVSHMEM_DPRINTF("msix initialization failed\n"); - exit(1); + return -1; } IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors); /* allocate QEMU char devices for receiving interrupts */ - s->eventfd_table = g_malloc0(s->vectors * sizeof(EventfdEntry)); + s->msi_vectors = g_malloc0(s->vectors * sizeof(MSIVector)); ivshmem_use_msix(s); -} - -static void ivshmem_save(QEMUFile* f, void *opaque) -{ - IVShmemState *proxy = opaque; - PCIDevice *pci_dev = PCI_DEVICE(proxy); - - IVSHMEM_DPRINTF("ivshmem_save\n"); - pci_device_save(pci_dev, f); - - if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) { - msix_save(pci_dev, f); - } else { - qemu_put_be32(f, proxy->intrstatus); - qemu_put_be32(f, proxy->intrmask); - } - -} - -static int ivshmem_load(QEMUFile* f, void *opaque, int version_id) -{ - IVSHMEM_DPRINTF("ivshmem_load\n"); - - IVShmemState *proxy = opaque; - PCIDevice *pci_dev = PCI_DEVICE(proxy); - int ret; - - if (version_id > 0) { - return -EINVAL; - } - - if (proxy->role_val == IVSHMEM_PEER) { - error_report("'peer' devices are not migratable"); - return -EINVAL; - } - - ret = pci_device_load(pci_dev, f); - if (ret) { - return ret; - } - - if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) { - msix_load(pci_dev, f); - ivshmem_use_msix(proxy); - } else { - proxy->intrstatus = qemu_get_be32(f); - proxy->intrmask = qemu_get_be32(f); - } - return 0; } -static void ivshmem_write_config(PCIDevice *pci_dev, uint32_t address, - uint32_t val, int len) +static void ivshmem_enable_irqfd(IVShmemState *s) { - pci_default_write_config(pci_dev, address, val, len); + PCIDevice *pdev = PCI_DEVICE(s); + int i; + + for (i = 0; i < s->peers[s->vm_id].nb_eventfds; i++) { + ivshmem_add_kvm_msi_virq(s, i); + } + + if (msix_set_vector_notifiers(pdev, + ivshmem_vector_unmask, + ivshmem_vector_mask, + ivshmem_vector_poll)) { + error_report("ivshmem: msix_set_vector_notifiers failed"); + } } -static int pci_ivshmem_init(PCIDevice *dev) +static void ivshmem_remove_kvm_msi_virq(IVShmemState *s, int vector) +{ + IVSHMEM_DPRINTF("ivshmem_remove_kvm_msi_virq vector:%d\n", vector); + + if (s->msi_vectors[vector].pdev == NULL) { + return; + } + + /* it was cleaned when masked in the frontend. */ + kvm_irqchip_release_virq(kvm_state, s->msi_vectors[vector].virq); + + s->msi_vectors[vector].pdev = NULL; +} + +static void ivshmem_disable_irqfd(IVShmemState *s) +{ + PCIDevice *pdev = PCI_DEVICE(s); + int i; + + for (i = 0; i < s->peers[s->vm_id].nb_eventfds; i++) { + ivshmem_remove_kvm_msi_virq(s, i); + } + + msix_unset_vector_notifiers(pdev); +} + +static void ivshmem_write_config(PCIDevice *pdev, uint32_t address, + uint32_t val, int len) +{ + IVShmemState *s = IVSHMEM(pdev); + int is_enabled, was_enabled = msix_enabled(pdev); + + pci_default_write_config(pdev, address, val, len); + is_enabled = msix_enabled(pdev); + + if (kvm_msi_via_irqfd_enabled() && s->vm_id != -1) { + if (!was_enabled && is_enabled) { + ivshmem_enable_irqfd(s); + } else if (was_enabled && !is_enabled) { + ivshmem_disable_irqfd(s); + } + } +} + +static void pci_ivshmem_realize(PCIDevice *dev, Error **errp) { IVShmemState *s = IVSHMEM(dev); uint8_t *pci_conf; + uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY | + PCI_BASE_ADDRESS_MEM_PREFETCH; - if (s->sizearg == NULL) - s->ivshmem_size = 4 << 20; /* 4 MB default */ - else { - s->ivshmem_size = ivshmem_get_size(s); + if (!!s->server_chr + !!s->shmobj + !!s->hostmem != 1) { + error_setg(errp, "You must specify either a shmobj, a chardev" + " or a hostmem"); + return; } - fifo8_create(&s->incoming_fifo, sizeof(long)); + if (s->hostmem) { + MemoryRegion *mr; - register_savevm(DEVICE(dev), "ivshmem", 0, 0, ivshmem_save, ivshmem_load, - dev); + if (s->sizearg) { + g_warning("size argument ignored with hostmem"); + } + + mr = host_memory_backend_get_memory(s->hostmem, errp); + s->ivshmem_size = memory_region_size(mr); + } else if (s->sizearg == NULL) { + s->ivshmem_size = 4 << 20; /* 4 MB default */ + } else { + char *end; + int64_t size = qemu_strtosz(s->sizearg, &end); + if (size < 0 || *end != '\0' || !is_power_of_2(size)) { + error_setg(errp, "Invalid size %s", s->sizearg); + return; + } + s->ivshmem_size = size; + } + + fifo8_create(&s->incoming_fifo, sizeof(int64_t)); /* IRQFD requires MSI */ if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) && !ivshmem_has_feature(s, IVSHMEM_MSI)) { - error_report("ioeventfd/irqfd requires MSI"); - exit(1); + error_setg(errp, "ioeventfd/irqfd requires MSI"); + return; } /* check that role is reasonable */ @@ -730,8 +899,8 @@ static int pci_ivshmem_init(PCIDevice *dev) } else if (strncmp(s->role, "master", 7) == 0) { s->role_val = IVSHMEM_MASTER; } else { - error_report("'role' must be 'peer' or 'master'"); - exit(1); + error_setg(errp, "'role' must be 'peer' or 'master'"); + return; } } else { s->role_val = IVSHMEM_MASTER; /* default */ @@ -748,8 +917,6 @@ static int pci_ivshmem_init(PCIDevice *dev) pci_config_set_interrupt_pin(pci_conf, 1); - s->shm_fd = 0; - memory_region_init_io(&s->ivshmem_mmio, OBJECT(s), &ivshmem_mmio_ops, s, "ivshmem-mmio", IVSHMEM_REG_BAR_SIZE); @@ -758,51 +925,51 @@ static int pci_ivshmem_init(PCIDevice *dev) &s->ivshmem_mmio); memory_region_init(&s->bar, OBJECT(s), "ivshmem-bar2-container", s->ivshmem_size); - s->ivshmem_attr = PCI_BASE_ADDRESS_SPACE_MEMORY | - PCI_BASE_ADDRESS_MEM_PREFETCH; if (s->ivshmem_64bit) { - s->ivshmem_attr |= PCI_BASE_ADDRESS_MEM_TYPE_64; + attr |= PCI_BASE_ADDRESS_MEM_TYPE_64; } - if ((s->server_chr != NULL) && - (strncmp(s->server_chr->filename, "unix:", 5) == 0)) { + if (s->hostmem != NULL) { + MemoryRegion *mr; + + IVSHMEM_DPRINTF("using hostmem\n"); + + mr = host_memory_backend_get_memory(MEMORY_BACKEND(s->hostmem), errp); + vmstate_register_ram(mr, DEVICE(s)); + memory_region_add_subregion(&s->bar, 0, mr); + pci_register_bar(PCI_DEVICE(s), 2, attr, &s->bar); + } else if (s->server_chr != NULL) { + if (strncmp(s->server_chr->filename, "unix:", 5)) { + error_setg(errp, "chardev is not a unix client socket"); + return; + } + /* if we get a UNIX socket as the parameter we will talk * to the ivshmem server to receive the memory region */ - if (s->shmobj != NULL) { - error_report("WARNING: do not specify both 'chardev' " - "and 'shm' with ivshmem"); - } - IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n", s->server_chr->filename); - if (ivshmem_has_feature(s, IVSHMEM_MSI)) { - ivshmem_setup_msi(s); + if (ivshmem_has_feature(s, IVSHMEM_MSI) && + ivshmem_setup_msi(s)) { + error_setg(errp, "msix initialization failed"); + return; } - /* we allocate enough space for 16 guests and grow as needed */ - s->nb_peers = 16; + /* we allocate enough space for 16 peers and grow as needed */ + resize_peers(s, 16); s->vm_id = -1; - /* allocate/initialize space for interrupt handling */ - s->peers = g_malloc0(s->nb_peers * sizeof(Peer)); - - pci_register_bar(dev, 2, s->ivshmem_attr, &s->bar); + pci_register_bar(dev, 2, attr, &s->bar); s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *)); - qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, ivshmem_read, - ivshmem_event, s); + qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, + ivshmem_check_version, ivshmem_event, s); } else { /* just map the file immediately, we're not using a server */ int fd; - if (s->shmobj == NULL) { - error_report("Must specify 'chardev' or 'shm' to ivshmem"); - exit(1); - } - IVSHMEM_DPRINTF("using shm_open (shm object = %s)\n", s->shmobj); /* try opening with O_EXCL and if it succeeds zero the memory @@ -816,39 +983,155 @@ static int pci_ivshmem_init(PCIDevice *dev) } else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR, S_IRWXU|S_IRWXG|S_IRWXO)) < 0) { - error_report("could not open shared file"); - exit(1); - + error_setg(errp, "could not open shared file"); + return; } - if (check_shm_size(s, fd) == -1) { - exit(1); + if (check_shm_size(s, fd, errp) == -1) { + return; } - create_shared_memory_BAR(s, fd); - + create_shared_memory_BAR(s, fd, attr, errp); + close(fd); } - - dev->config_write = ivshmem_write_config; - - return 0; } -static void pci_ivshmem_uninit(PCIDevice *dev) +static void pci_ivshmem_exit(PCIDevice *dev) { IVShmemState *s = IVSHMEM(dev); + int i; + + fifo8_destroy(&s->incoming_fifo); if (s->migration_blocker) { migrate_del_blocker(s->migration_blocker); error_free(s->migration_blocker); } - memory_region_del_subregion(&s->bar, &s->ivshmem); - vmstate_unregister_ram(&s->ivshmem, DEVICE(dev)); - unregister_savevm(DEVICE(dev), "ivshmem", s); - fifo8_destroy(&s->incoming_fifo); + if (memory_region_is_mapped(&s->ivshmem)) { + if (!s->hostmem) { + void *addr = memory_region_get_ram_ptr(&s->ivshmem); + + if (munmap(addr, s->ivshmem_size) == -1) { + error_report("Failed to munmap shared memory %s", + strerror(errno)); + } + } + + vmstate_unregister_ram(&s->ivshmem, DEVICE(dev)); + memory_region_del_subregion(&s->bar, &s->ivshmem); + } + + if (s->eventfd_chr) { + for (i = 0; i < s->vectors; i++) { + if (s->eventfd_chr[i]) { + qemu_chr_free(s->eventfd_chr[i]); + } + } + g_free(s->eventfd_chr); + } + + if (s->peers) { + for (i = 0; i < s->nb_peers; i++) { + close_peer_eventfds(s, i); + } + g_free(s->peers); + } + + if (ivshmem_has_feature(s, IVSHMEM_MSI)) { + msix_uninit_exclusive_bar(dev); + } + + g_free(s->msi_vectors); } +static bool test_msix(void *opaque, int version_id) +{ + IVShmemState *s = opaque; + + return ivshmem_has_feature(s, IVSHMEM_MSI); +} + +static bool test_no_msix(void *opaque, int version_id) +{ + return !test_msix(opaque, version_id); +} + +static int ivshmem_pre_load(void *opaque) +{ + IVShmemState *s = opaque; + + if (s->role_val == IVSHMEM_PEER) { + error_report("'peer' devices are not migratable"); + return -EINVAL; + } + + return 0; +} + +static int ivshmem_post_load(void *opaque, int version_id) +{ + IVShmemState *s = opaque; + + if (ivshmem_has_feature(s, IVSHMEM_MSI)) { + ivshmem_use_msix(s); + } + + return 0; +} + +static int ivshmem_load_old(QEMUFile *f, void *opaque, int version_id) +{ + IVShmemState *s = opaque; + PCIDevice *pdev = PCI_DEVICE(s); + int ret; + + IVSHMEM_DPRINTF("ivshmem_load_old\n"); + + if (version_id != 0) { + return -EINVAL; + } + + if (s->role_val == IVSHMEM_PEER) { + error_report("'peer' devices are not migratable"); + return -EINVAL; + } + + ret = pci_device_load(pdev, f); + if (ret) { + return ret; + } + + if (ivshmem_has_feature(s, IVSHMEM_MSI)) { + msix_load(pdev, f); + ivshmem_use_msix(s); + } else { + s->intrstatus = qemu_get_be32(f); + s->intrmask = qemu_get_be32(f); + } + + return 0; +} + +static const VMStateDescription ivshmem_vmsd = { + .name = "ivshmem", + .version_id = 1, + .minimum_version_id = 1, + .pre_load = ivshmem_pre_load, + .post_load = ivshmem_post_load, + .fields = (VMStateField[]) { + VMSTATE_PCI_DEVICE(parent_obj, IVShmemState), + + VMSTATE_MSIX_TEST(parent_obj, IVShmemState, test_msix), + VMSTATE_UINT32_TEST(intrstatus, IVShmemState, test_no_msix), + VMSTATE_UINT32_TEST(intrmask, IVShmemState, test_no_msix), + + VMSTATE_END_OF_LIST() + }, + .load_state_old = ivshmem_load_old, + .minimum_version_id_old = 0 +}; + static Property ivshmem_properties[] = { DEFINE_PROP_CHR("chardev", IVShmemState, server_chr), DEFINE_PROP_STRING("size", IVShmemState, sizearg), @@ -866,20 +1149,50 @@ static void ivshmem_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - k->init = pci_ivshmem_init; - k->exit = pci_ivshmem_uninit; + k->realize = pci_ivshmem_realize; + k->exit = pci_ivshmem_exit; + k->config_write = ivshmem_write_config; k->vendor_id = PCI_VENDOR_ID_IVSHMEM; k->device_id = PCI_DEVICE_ID_IVSHMEM; k->class_id = PCI_CLASS_MEMORY_RAM; dc->reset = ivshmem_reset; dc->props = ivshmem_properties; + dc->vmsd = &ivshmem_vmsd; set_bit(DEVICE_CATEGORY_MISC, dc->categories); + dc->desc = "Inter-VM shared memory"; +} + +static void ivshmem_check_memdev_is_busy(Object *obj, const char *name, + Object *val, Error **errp) +{ + MemoryRegion *mr; + + mr = host_memory_backend_get_memory(MEMORY_BACKEND(val), errp); + if (memory_region_is_mapped(mr)) { + char *path = object_get_canonical_path_component(val); + error_setg(errp, "can't use already busy memdev: %s", path); + g_free(path); + } else { + qdev_prop_allow_set_link_before_realize(obj, name, val, errp); + } +} + +static void ivshmem_init(Object *obj) +{ + IVShmemState *s = IVSHMEM(obj); + + object_property_add_link(obj, IVSHMEM_MEMDEV_PROP, TYPE_MEMORY_BACKEND, + (Object **)&s->hostmem, + ivshmem_check_memdev_is_busy, + OBJ_PROP_LINK_UNREF_ON_RELEASE, + &error_abort); } static const TypeInfo ivshmem_info = { .name = TYPE_IVSHMEM, .parent = TYPE_PCI_DEVICE, .instance_size = sizeof(IVShmemState), + .instance_init = ivshmem_init, .class_init = ivshmem_class_init, }; diff --git a/hw/pci/msix.c b/hw/pci/msix.c index 2fdada4e8f..64c93d83d6 100644 --- a/hw/pci/msix.c +++ b/hw/pci/msix.c @@ -200,8 +200,14 @@ static uint64_t msix_pba_mmio_read(void *opaque, hwaddr addr, return pci_get_long(dev->msix_pba + addr); } +static void msix_pba_mmio_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ +} + static const MemoryRegionOps msix_pba_mmio_ops = { .read = msix_pba_mmio_read, + .write = msix_pba_mmio_write, .endianness = DEVICE_LITTLE_ENDIAN, .valid = { .min_access_size = 4, diff --git a/include/hw/misc/ivshmem.h b/include/hw/misc/ivshmem.h new file mode 100644 index 0000000000..433ef53d79 --- /dev/null +++ b/include/hw/misc/ivshmem.h @@ -0,0 +1,25 @@ + +/* + * Inter-VM Shared Memory PCI device. + * + * Author: + * Cam Macdonell + * + * Based On: cirrus_vga.c + * Copyright (c) 2004 Fabrice Bellard + * Copyright (c) 2004 Makoto Suzuki (suzu) + * + * and rtl8139.c + * Copyright (c) 2006 Igor Kovalenko + * + * This code is licensed under the GNU GPL v2. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ +#ifndef IVSHMEM_H +#define IVSHMEM_H + +#define IVSHMEM_PROTOCOL_VERSION 0 + +#endif /* IVSHMEM_H */ diff --git a/include/hw/pci/msix.h b/include/hw/pci/msix.h index 954d82b350..72e5f931c5 100644 --- a/include/hw/pci/msix.h +++ b/include/hw/pci/msix.h @@ -46,12 +46,16 @@ void msix_unset_vector_notifiers(PCIDevice *dev); extern const VMStateDescription vmstate_msix; -#define VMSTATE_MSIX(_field, _state) { \ - .name = (stringify(_field)), \ - .size = sizeof(PCIDevice), \ - .vmsd = &vmstate_msix, \ - .flags = VMS_STRUCT, \ - .offset = vmstate_offset_value(_state, _field, PCIDevice), \ +#define VMSTATE_MSIX_TEST(_field, _state, _test) { \ + .name = (stringify(_field)), \ + .size = sizeof(PCIDevice), \ + .vmsd = &vmstate_msix, \ + .flags = VMS_STRUCT, \ + .offset = vmstate_offset_value(_state, _field, PCIDevice), \ + .field_exists = (_test) \ } +#define VMSTATE_MSIX(_f, _s) \ + VMSTATE_MSIX_TEST(_f, _s, NULL) + #endif diff --git a/include/qemu/event_notifier.h b/include/qemu/event_notifier.h index 88b57af7ce..a8f28540c9 100644 --- a/include/qemu/event_notifier.h +++ b/include/qemu/event_notifier.h @@ -38,7 +38,7 @@ int event_notifier_set_handler(EventNotifier *, EventNotifierHandler *); #ifdef CONFIG_POSIX void event_notifier_init_fd(EventNotifier *, int fd); -int event_notifier_get_fd(EventNotifier *); +int event_notifier_get_fd(const EventNotifier *); #else HANDLE event_notifier_get_handle(EventNotifier *); #endif diff --git a/include/sysemu/char.h b/include/sysemu/char.h index edf76693d9..aff193f080 100644 --- a/include/sysemu/char.h +++ b/include/sysemu/char.h @@ -128,10 +128,18 @@ CharDriverState *qemu_chr_new(const char *label, const char *filename, /** * @qemu_chr_delete: * - * Destroy a character backend. + * Destroy a character backend and remove it from the list of + * identified character backends. */ void qemu_chr_delete(CharDriverState *chr); +/** + * @qemu_chr_free: + * + * Destroy a character backend. + */ +void qemu_chr_free(CharDriverState *chr); + /** * @qemu_chr_fe_set_echo: * diff --git a/qemu-char.c b/qemu-char.c index 908e7124eb..c4eb4eea31 100644 --- a/qemu-char.c +++ b/qemu-char.c @@ -3876,9 +3876,8 @@ void qemu_chr_fe_release(CharDriverState *s) s->avail_connections++; } -void qemu_chr_delete(CharDriverState *chr) +void qemu_chr_free(CharDriverState *chr) { - QTAILQ_REMOVE(&chardevs, chr, next); if (chr->chr_close) { chr->chr_close(chr); } @@ -3888,6 +3887,12 @@ void qemu_chr_delete(CharDriverState *chr) g_free(chr); } +void qemu_chr_delete(CharDriverState *chr) +{ + QTAILQ_REMOVE(&chardevs, chr, next); + qemu_chr_free(chr); +} + ChardevInfoList *qmp_query_chardev(Error **errp) { ChardevInfoList *chr_list = NULL; diff --git a/qemu-doc.texi b/qemu-doc.texi index 5b81aa052d..3126abdcd3 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -1266,9 +1266,13 @@ is qemu.git/contrib/ivshmem-server. An example syntax when using the shared memory server is: @example -qemu-system-i386 -device ivshmem,size=[,chardev=] - [,msi=on][,ioeventfd=on][,vectors=n][,role=peer|master] -qemu-system-i386 -chardev socket,path=,id= +# First start the ivshmem server once and for all +ivshmem-server -p -S -m -l -n + +# Then start your qemu instances with matching arguments +qemu-system-i386 -device ivshmem,size=,vectors=,chardev= + [,msi=on][,ioeventfd=on][,role=peer|master] + -chardev socket,path=,id= @end example When using the server, the guest will be assigned a VM ID (>=0) that allows guests @@ -1289,6 +1293,19 @@ copy the shared memory on migration to the destination host. With With the @option{peer} case, the device should be detached and then reattached after migration using the PCI hotplug support. +@subsubsection ivshmem and hugepages + +Instead of specifying the using POSIX shm, you may specify +a memory backend that has hugepage support: + +@example +qemu-system-i386 -object memory-backend-file,size=1G,mem-path=/mnt/hugepages,id=mb1 + -device ivshmem,memdev=mb1 +@end example + +ivshmem-server also supports hugepages mount points with the +@option{-m} memory path argument. + @node direct_linux_boot @section Direct Linux Boot diff --git a/tests/Makefile b/tests/Makefile index 9341498d42..1c57e39c53 100644 --- a/tests/Makefile +++ b/tests/Makefile @@ -150,6 +150,8 @@ gcov-files-pci-y += hw/display/virtio-gpu-pci.c gcov-files-pci-$(CONFIG_VIRTIO_VGA) += hw/display/virtio-vga.c check-qtest-pci-y += tests/intel-hda-test$(EXESUF) gcov-files-pci-y += hw/audio/intel-hda.c hw/audio/hda-codec.c +check-qtest-pci-$(CONFIG_POSIX) += tests/ivshmem-test$(EXESUF) +gcov-files-pci-y += hw/misc/ivshmem.c check-qtest-i386-y = tests/endianness-test$(EXESUF) check-qtest-i386-y += tests/fdc-test$(EXESUF) @@ -522,6 +524,7 @@ tests/qemu-iotests/socket_scm_helper$(EXESUF): tests/qemu-iotests/socket_scm_hel tests/test-qemu-opts$(EXESUF): tests/test-qemu-opts.o $(test-util-obj-y) tests/test-write-threshold$(EXESUF): tests/test-write-threshold.o $(test-block-obj-y) tests/test-netfilter$(EXESUF): tests/test-netfilter.o $(qtest-obj-y) +tests/ivshmem-test$(EXESUF): tests/ivshmem-test.o contrib/ivshmem-server/ivshmem-server.o $(libqos-pc-obj-y) ifeq ($(CONFIG_POSIX),y) LIBS += -lutil diff --git a/tests/ivshmem-test.c b/tests/ivshmem-test.c new file mode 100644 index 0000000000..c8f0cf0f70 --- /dev/null +++ b/tests/ivshmem-test.c @@ -0,0 +1,491 @@ +/* + * QTest testcase for ivshmem + * + * Copyright (c) 2014 SUSE LINUX Products GmbH + * Copyright (c) 2015 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. + */ + +#include +#include +#include +#include +#include +#include +#include +#include "contrib/ivshmem-server/ivshmem-server.h" +#include "libqos/pci-pc.h" +#include "libqtest.h" +#include "qemu/osdep.h" +#include "qemu-common.h" + +#define TMPSHMSIZE (1 << 20) +static char *tmpshm; +static void *tmpshmem; +static char *tmpdir; +static char *tmpserver; + +static void save_fn(QPCIDevice *dev, int devfn, void *data) +{ + QPCIDevice **pdev = (QPCIDevice **) data; + + *pdev = dev; +} + +static QPCIDevice *get_device(void) +{ + QPCIDevice *dev; + QPCIBus *pcibus; + + pcibus = qpci_init_pc(); + qpci_device_foreach(pcibus, 0x1af4, 0x1110, save_fn, &dev); + g_assert(dev != NULL); + + return dev; +} + +typedef struct _IVState { + QTestState *qtest; + void *reg_base, *mem_base; + QPCIDevice *dev; +} IVState; + +enum Reg { + INTRMASK = 0, + INTRSTATUS = 4, + IVPOSITION = 8, + DOORBELL = 12, +}; + +static const char* reg2str(enum Reg reg) { + switch (reg) { + case INTRMASK: + return "IntrMask"; + case INTRSTATUS: + return "IntrStatus"; + case IVPOSITION: + return "IVPosition"; + case DOORBELL: + return "DoorBell"; + default: + return NULL; + } +} + +static inline unsigned in_reg(IVState *s, enum Reg reg) +{ + const char *name = reg2str(reg); + QTestState *qtest = global_qtest; + unsigned res; + + global_qtest = s->qtest; + res = qpci_io_readl(s->dev, s->reg_base + reg); + g_test_message("*%s -> %x\n", name, res); + global_qtest = qtest; + + return res; +} + +static inline void out_reg(IVState *s, enum Reg reg, unsigned v) +{ + const char *name = reg2str(reg); + QTestState *qtest = global_qtest; + + global_qtest = s->qtest; + g_test_message("%x -> *%s\n", v, name); + qpci_io_writel(s->dev, s->reg_base + reg, v); + global_qtest = qtest; +} + +static void setup_vm_cmd(IVState *s, const char *cmd, bool msix) +{ + uint64_t barsize; + + s->qtest = qtest_start(cmd); + + s->dev = get_device(); + + /* FIXME: other bar order fails, mappings changes */ + s->mem_base = qpci_iomap(s->dev, 2, &barsize); + g_assert_nonnull(s->mem_base); + g_assert_cmpuint(barsize, ==, TMPSHMSIZE); + + if (msix) { + qpci_msix_enable(s->dev); + } + + s->reg_base = qpci_iomap(s->dev, 0, &barsize); + g_assert_nonnull(s->reg_base); + g_assert_cmpuint(barsize, ==, 256); + + qpci_device_enable(s->dev); +} + +static void setup_vm(IVState *s) +{ + char *cmd = g_strdup_printf("-device ivshmem,shm=%s,size=1M", tmpshm); + + setup_vm_cmd(s, cmd, false); + + g_free(cmd); +} + +static void test_ivshmem_single(void) +{ + IVState state, *s; + uint32_t data[1024]; + int i; + + setup_vm(&state); + s = &state; + + /* valid io */ + out_reg(s, INTRMASK, 0); + in_reg(s, INTRSTATUS); + in_reg(s, IVPOSITION); + + out_reg(s, INTRMASK, 0xffffffff); + g_assert_cmpuint(in_reg(s, INTRMASK), ==, 0xffffffff); + out_reg(s, INTRSTATUS, 1); + /* XXX: intercept IRQ, not seen in resp */ + g_assert_cmpuint(in_reg(s, INTRSTATUS), ==, 1); + + /* invalid io */ + out_reg(s, IVPOSITION, 1); + out_reg(s, DOORBELL, 8 << 16); + + for (i = 0; i < G_N_ELEMENTS(data); i++) { + data[i] = i; + } + qtest_memwrite(s->qtest, (uintptr_t)s->mem_base, data, sizeof(data)); + + for (i = 0; i < G_N_ELEMENTS(data); i++) { + g_assert_cmpuint(((uint32_t *)tmpshmem)[i], ==, i); + } + + memset(data, 0, sizeof(data)); + + qtest_memread(s->qtest, (uintptr_t)s->mem_base, data, sizeof(data)); + for (i = 0; i < G_N_ELEMENTS(data); i++) { + g_assert_cmpuint(data[i], ==, i); + } + + qtest_quit(s->qtest); +} + +static void test_ivshmem_pair(void) +{ + IVState state1, state2, *s1, *s2; + char *data; + int i; + + setup_vm(&state1); + s1 = &state1; + setup_vm(&state2); + s2 = &state2; + + data = g_malloc0(TMPSHMSIZE); + + /* host write, guest 1 & 2 read */ + memset(tmpshmem, 0x42, TMPSHMSIZE); + qtest_memread(s1->qtest, (uintptr_t)s1->mem_base, data, TMPSHMSIZE); + for (i = 0; i < TMPSHMSIZE; i++) { + g_assert_cmpuint(data[i], ==, 0x42); + } + qtest_memread(s2->qtest, (uintptr_t)s2->mem_base, data, TMPSHMSIZE); + for (i = 0; i < TMPSHMSIZE; i++) { + g_assert_cmpuint(data[i], ==, 0x42); + } + + /* guest 1 write, guest 2 read */ + memset(data, 0x43, TMPSHMSIZE); + qtest_memwrite(s1->qtest, (uintptr_t)s1->mem_base, data, TMPSHMSIZE); + memset(data, 0, TMPSHMSIZE); + qtest_memread(s2->qtest, (uintptr_t)s2->mem_base, data, TMPSHMSIZE); + for (i = 0; i < TMPSHMSIZE; i++) { + g_assert_cmpuint(data[i], ==, 0x43); + } + + /* guest 2 write, guest 1 read */ + memset(data, 0x44, TMPSHMSIZE); + qtest_memwrite(s2->qtest, (uintptr_t)s2->mem_base, data, TMPSHMSIZE); + memset(data, 0, TMPSHMSIZE); + qtest_memread(s1->qtest, (uintptr_t)s2->mem_base, data, TMPSHMSIZE); + for (i = 0; i < TMPSHMSIZE; i++) { + g_assert_cmpuint(data[i], ==, 0x44); + } + + qtest_quit(s1->qtest); + qtest_quit(s2->qtest); + g_free(data); +} + +typedef struct ServerThread { + GThread *thread; + IvshmemServer *server; + int pipe[2]; /* to handle quit */ +} ServerThread; + +static void *server_thread(void *data) +{ + ServerThread *t = data; + IvshmemServer *server = t->server; + + while (true) { + fd_set fds; + int maxfd, ret; + + FD_ZERO(&fds); + FD_SET(t->pipe[0], &fds); + maxfd = t->pipe[0] + 1; + + ivshmem_server_get_fds(server, &fds, &maxfd); + + ret = select(maxfd, &fds, NULL, NULL, NULL); + + if (ret < 0) { + if (errno == EINTR) { + continue; + } + + g_critical("select error: %s\n", strerror(errno)); + break; + } + if (ret == 0) { + continue; + } + + if (FD_ISSET(t->pipe[0], &fds)) { + break; + } + + if (ivshmem_server_handle_fds(server, &fds, maxfd) < 0) { + g_critical("ivshmem_server_handle_fds() failed\n"); + break; + } + } + + return NULL; +} + +static void setup_vm_with_server(IVState *s, int nvectors) +{ + char *cmd = g_strdup_printf("-chardev socket,id=chr0,path=%s,nowait " + "-device ivshmem,size=1M,chardev=chr0,vectors=%d", + tmpserver, nvectors); + + setup_vm_cmd(s, cmd, true); + + g_free(cmd); +} + +static void test_ivshmem_server(void) +{ + IVState state1, state2, *s1, *s2; + ServerThread thread; + IvshmemServer server; + int ret, vm1, vm2; + int nvectors = 2; + guint64 end_time = g_get_monotonic_time() + 5 * G_TIME_SPAN_SECOND; + + memset(tmpshmem, 0x42, TMPSHMSIZE); + ret = ivshmem_server_init(&server, tmpserver, tmpshm, + TMPSHMSIZE, nvectors, + g_test_verbose()); + g_assert_cmpint(ret, ==, 0); + + ret = ivshmem_server_start(&server); + g_assert_cmpint(ret, ==, 0); + + setup_vm_with_server(&state1, nvectors); + s1 = &state1; + setup_vm_with_server(&state2, nvectors); + s2 = &state2; + + g_assert_cmpuint(in_reg(s1, IVPOSITION), ==, 0xffffffff); + g_assert_cmpuint(in_reg(s2, IVPOSITION), ==, 0xffffffff); + + g_assert_cmpuint(qtest_readb(s1->qtest, (uintptr_t)s1->mem_base), ==, 0x00); + + thread.server = &server; + ret = pipe(thread.pipe); + g_assert_cmpint(ret, ==, 0); + thread.thread = g_thread_new("ivshmem-server", server_thread, &thread); + g_assert(thread.thread != NULL); + + /* waiting until mapping is done */ + while (g_get_monotonic_time() < end_time) { + g_usleep(1000); + + if (qtest_readb(s1->qtest, (uintptr_t)s1->mem_base) == 0x42 && + qtest_readb(s2->qtest, (uintptr_t)s2->mem_base) == 0x42) { + break; + } + } + + /* check got different VM ids */ + vm1 = in_reg(s1, IVPOSITION); + vm2 = in_reg(s2, IVPOSITION); + g_assert_cmpuint(vm1, !=, vm2); + + global_qtest = s1->qtest; + ret = qpci_msix_table_size(s1->dev); + g_assert_cmpuint(ret, ==, nvectors); + + /* ping vm2 -> vm1 */ + ret = qpci_msix_pending(s1->dev, 0); + g_assert_cmpuint(ret, ==, 0); + out_reg(s2, DOORBELL, vm1 << 16); + do { + g_usleep(10000); + ret = qpci_msix_pending(s1->dev, 0); + } while (ret == 0 && g_get_monotonic_time() < end_time); + g_assert_cmpuint(ret, !=, 0); + + /* ping vm1 -> vm2 */ + global_qtest = s2->qtest; + ret = qpci_msix_pending(s2->dev, 0); + g_assert_cmpuint(ret, ==, 0); + out_reg(s1, DOORBELL, vm2 << 16); + do { + g_usleep(10000); + ret = qpci_msix_pending(s2->dev, 0); + } while (ret == 0 && g_get_monotonic_time() < end_time); + g_assert_cmpuint(ret, !=, 0); + + qtest_quit(s2->qtest); + qtest_quit(s1->qtest); + + if (qemu_write_full(thread.pipe[1], "q", 1) != 1) { + g_error("qemu_write_full: %s", g_strerror(errno)); + } + + g_thread_join(thread.thread); + + ivshmem_server_close(&server); + close(thread.pipe[1]); + close(thread.pipe[0]); +} + +#define PCI_SLOT_HP 0x06 + +static void test_ivshmem_hotplug(void) +{ + gchar *opts; + + qtest_start(""); + + opts = g_strdup_printf("'shm': '%s', 'size': '1M'", tmpshm); + + qpci_plug_device_test("ivshmem", "iv1", PCI_SLOT_HP, opts); + qpci_unplug_acpi_device_test("iv1", PCI_SLOT_HP); + + qtest_end(); + g_free(opts); +} + +static void test_ivshmem_memdev(void) +{ + IVState state; + + /* just for the sake of checking memory-backend property */ + setup_vm_cmd(&state, "-object memory-backend-ram,size=1M,id=mb1" + " -device ivshmem,memdev=mb1", false); + + qtest_quit(state.qtest); +} + +static void cleanup(void) +{ + if (tmpshmem) { + munmap(tmpshmem, TMPSHMSIZE); + tmpshmem = NULL; + } + + if (tmpshm) { + shm_unlink(tmpshm); + g_free(tmpshm); + tmpshm = NULL; + } + + if (tmpserver) { + g_unlink(tmpserver); + g_free(tmpserver); + tmpserver = NULL; + } + + if (tmpdir) { + g_rmdir(tmpdir); + tmpdir = NULL; + } +} + +static void abrt_handler(void *data) +{ + cleanup(); +} + +static gchar *mktempshm(int size, int *fd) +{ + while (true) { + gchar *name; + + name = g_strdup_printf("/qtest-%u-%u", getpid(), g_random_int()); + *fd = shm_open(name, O_CREAT|O_RDWR|O_EXCL, + S_IRWXU|S_IRWXG|S_IRWXO); + if (*fd > 0) { + g_assert(ftruncate(*fd, size) == 0); + return name; + } + + g_free(name); + + if (errno != EEXIST) { + perror("shm_open"); + return NULL; + } + } +} + +int main(int argc, char **argv) +{ + int ret, fd; + gchar dir[] = "/tmp/ivshmem-test.XXXXXX"; + +#if !GLIB_CHECK_VERSION(2, 31, 0) + if (!g_thread_supported()) { + g_thread_init(NULL); + } +#endif + + g_test_init(&argc, &argv, NULL); + + qtest_add_abrt_handler(abrt_handler, NULL); + /* shm */ + tmpshm = mktempshm(TMPSHMSIZE, &fd); + if (!tmpshm) { + return 0; + } + tmpshmem = mmap(0, TMPSHMSIZE, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); + g_assert(tmpshmem != MAP_FAILED); + /* server */ + if (mkdtemp(dir) == NULL) { + g_error("mkdtemp: %s", g_strerror(errno)); + } + tmpdir = dir; + tmpserver = g_strconcat(tmpdir, "/server", NULL); + + qtest_add_func("/ivshmem/single", test_ivshmem_single); + qtest_add_func("/ivshmem/pair", test_ivshmem_pair); + qtest_add_func("/ivshmem/server", test_ivshmem_server); + qtest_add_func("/ivshmem/hotplug", test_ivshmem_hotplug); + qtest_add_func("/ivshmem/memdev", test_ivshmem_memdev); + + ret = g_test_run(); + + cleanup(); + + return ret; +} diff --git a/tests/libqtest.c b/tests/libqtest.c index b6d700c606..f6f3d7a950 100644 --- a/tests/libqtest.c +++ b/tests/libqtest.c @@ -48,6 +48,7 @@ struct QTestState pid_t qemu_pid; /* our child QEMU process */ }; +static GHookList abrt_hooks; static GList *qtest_instances; static struct sigaction sigact_old; @@ -111,10 +112,7 @@ static void kill_qemu(QTestState *s) static void sigabrt_handler(int signo) { - GList *elem; - for (elem = qtest_instances; elem; elem = elem->next) { - kill_qemu(elem->data); - } + g_hook_list_invoke(&abrt_hooks, FALSE); } static void setup_sigabrt_handler(void) @@ -135,6 +133,23 @@ static void cleanup_sigabrt_handler(void) sigaction(SIGABRT, &sigact_old, NULL); } +void qtest_add_abrt_handler(void (*fn), const void *data) +{ + GHook *hook; + + /* Only install SIGABRT handler once */ + if (!abrt_hooks.is_setup) { + g_hook_list_init(&abrt_hooks, sizeof(GHook)); + setup_sigabrt_handler(); + } + + hook = g_hook_alloc(&abrt_hooks); + hook->func = fn; + hook->data = (void *)data; + + g_hook_prepend(&abrt_hooks, hook); +} + QTestState *qtest_init(const char *extra_args) { QTestState *s; @@ -155,12 +170,7 @@ QTestState *qtest_init(const char *extra_args) sock = init_socket(socket_path); qmpsock = init_socket(qmp_socket_path); - /* Only install SIGABRT handler once */ - if (!qtest_instances) { - setup_sigabrt_handler(); - } - - qtest_instances = g_list_prepend(qtest_instances, s); + qtest_add_abrt_handler(kill_qemu, s); s->qemu_pid = fork(); if (s->qemu_pid == 0) { @@ -208,13 +218,14 @@ QTestState *qtest_init(const char *extra_args) void qtest_quit(QTestState *s) { + qtest_instances = g_list_remove(qtest_instances, s); + g_hook_destroy_link(&abrt_hooks, g_hook_find_data(&abrt_hooks, TRUE, s)); + /* Uninstall SIGABRT handler on last instance */ - if (qtest_instances && !qtest_instances->next) { + if (!qtest_instances) { cleanup_sigabrt_handler(); } - qtest_instances = g_list_remove(qtest_instances, s); - kill_qemu(s); close(s->fd); close(s->qmp_fd); diff --git a/tests/libqtest.h b/tests/libqtest.h index 9818ef712d..df087452ee 100644 --- a/tests/libqtest.h +++ b/tests/libqtest.h @@ -450,6 +450,8 @@ void qtest_add_data_func(const char *str, const void *data, void (*fn)); g_free(path); \ } while (0) +void qtest_add_abrt_handler(void (*fn), const void *data); + /** * qtest_start: * @args: other arguments to pass to QEMU diff --git a/util/event_notifier-posix.c b/util/event_notifier-posix.c index ed4ca2b01e..d4a0c63e12 100644 --- a/util/event_notifier-posix.c +++ b/util/event_notifier-posix.c @@ -77,7 +77,7 @@ void event_notifier_cleanup(EventNotifier *e) close(e->wfd); } -int event_notifier_get_fd(EventNotifier *e) +int event_notifier_get_fd(const EventNotifier *e) { return e->rfd; }