diff options
168 files changed, 3247 insertions, 1350 deletions
@@ -1,5 +1,5 @@ -QEMU ---- + QEMU README + =========== QEMU is a generic and open source machine & userspace emulator and virtualizer. @@ -31,31 +31,31 @@ version 2. For full licensing details, consult the LICENSE file. Building ---- +======== QEMU is multi-platform software intended to be buildable on all modern Linux platforms, OS-X, Win32 (via the Mingw64 toolchain) and a variety of other UNIX targets. The simple steps to build QEMU are: - mkdir build - cd build - ../configure - make + mkdir build + cd build + ../configure + make Complete details of the process for building and configuring QEMU for all supported host platforms can be found in the qemu-tech.html file. Additional information can also be found online via the QEMU website: - http://qemu-project.org/Hosts/Linux - http://qemu-project.org/Hosts/W32 + http://qemu-project.org/Hosts/Linux + http://qemu-project.org/Hosts/W32 Submitting patches ---- +================== The QEMU source code is maintained under the GIT version control system. - git clone git://git.qemu-project.org/qemu.git + git clone git://git.qemu-project.org/qemu.git When submitting patches, the preferred approach is to use 'git format-patch' and/or 'git send-email' to format & send the mail to the @@ -66,18 +66,18 @@ guidelines set out in the HACKING and CODING_STYLE files. Additional information on submitting patches can be found online via the QEMU website - http://qemu-project.org/Contribute/SubmitAPatch - http://qemu-project.org/Contribute/TrivialPatches + http://qemu-project.org/Contribute/SubmitAPatch + http://qemu-project.org/Contribute/TrivialPatches Bug reporting ---- +============= The QEMU project uses Launchpad as its primary upstream bug tracker. Bugs found when running code built from QEMU git or upstream released sources should be reported via: - https://bugs.launchpad.net/qemu/ + https://bugs.launchpad.net/qemu/ If using QEMU via an operating system vendor pre-built binary package, it is preferable to report bugs to the vendor's own bug tracker first. If @@ -86,21 +86,22 @@ reported via launchpad. For additional information on bug reporting consult: - http://qemu-project.org/Contribute/ReportABug + http://qemu-project.org/Contribute/ReportABug Contact ---- +======= The QEMU community can be contacted in a number of ways, with the two main methods being email and IRC - - Mailing List: qemu-devel@nongnu.org - - Archives: http://lists.nongnu.org/mailman/listinfo/qemu-devel - - IRC: #qemu on irc.oftc.net + - qemu-devel@nongnu.org + http://lists.nongnu.org/mailman/listinfo/qemu-devel + - #qemu on irc.oftc.net Information on additional methods of contacting the community can be found online via the QEMU website: http://qemu-project.org/Contribute/StartHere +-- End @@ -2837,7 +2837,7 @@ bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs) { BlockDriverInfo bdi; - if (bs->backing || !(bs->open_flags & BDRV_O_UNMAP)) { + if (!(bs->open_flags & BDRV_O_UNMAP)) { return false; } diff --git a/block/blkreplay.c b/block/blkreplay.c index 3368c8c98d..30f9d5ff6c 100755 --- a/block/blkreplay.c +++ b/block/blkreplay.c @@ -114,11 +114,11 @@ static int coroutine_fn blkreplay_co_pwrite_zeroes(BlockDriverState *bs, return ret; } -static int coroutine_fn blkreplay_co_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors) +static int coroutine_fn blkreplay_co_pdiscard(BlockDriverState *bs, + int64_t offset, int count) { uint64_t reqid = request_id++; - int ret = bdrv_co_discard(bs->file->bs, sector_num, nb_sectors); + int ret = bdrv_co_pdiscard(bs->file->bs, offset, count); block_request_create(reqid, bs, qemu_coroutine_self()); qemu_coroutine_yield(); @@ -148,7 +148,7 @@ static BlockDriver bdrv_blkreplay = { .bdrv_co_pwritev = blkreplay_co_pwritev, .bdrv_co_pwrite_zeroes = blkreplay_co_pwrite_zeroes, - .bdrv_co_discard = blkreplay_co_discard, + .bdrv_co_pdiscard = blkreplay_co_pdiscard, .bdrv_co_flush = blkreplay_co_flush, }; diff --git a/block/block-backend.c b/block/block-backend.c index f9cea1b304..effa038924 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -1065,16 +1065,16 @@ BlockAIOCB *blk_aio_flush(BlockBackend *blk, return bdrv_aio_flush(blk_bs(blk), cb, opaque); } -BlockAIOCB *blk_aio_discard(BlockBackend *blk, - int64_t sector_num, int nb_sectors, - BlockCompletionFunc *cb, void *opaque) +BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, + int64_t offset, int count, + BlockCompletionFunc *cb, void *opaque) { - int ret = blk_check_request(blk, sector_num, nb_sectors); + int ret = blk_check_byte_request(blk, offset, count); if (ret < 0) { return blk_abort_aio_request(blk, cb, opaque, ret); } - return bdrv_aio_discard(blk_bs(blk), sector_num, nb_sectors, cb, opaque); + return bdrv_aio_pdiscard(blk_bs(blk), offset, count, cb, opaque); } void blk_aio_cancel(BlockAIOCB *acb) @@ -1106,14 +1106,14 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf, return bdrv_aio_ioctl(blk_bs(blk), req, buf, cb, opaque); } -int blk_co_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors) +int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int count) { - int ret = blk_check_request(blk, sector_num, nb_sectors); + int ret = blk_check_byte_request(blk, offset, count); if (ret < 0) { return ret; } - return bdrv_co_discard(blk_bs(blk), sector_num, nb_sectors); + return bdrv_co_pdiscard(blk_bs(blk), offset, count); } int blk_co_flush(BlockBackend *blk) @@ -1504,14 +1504,14 @@ int blk_truncate(BlockBackend *blk, int64_t offset) return bdrv_truncate(blk_bs(blk), offset); } -int blk_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors) +int blk_pdiscard(BlockBackend *blk, int64_t offset, int count) { - int ret = blk_check_request(blk, sector_num, nb_sectors); + int ret = blk_check_byte_request(blk, offset, count); if (ret < 0) { return ret; } - return bdrv_discard(blk_bs(blk), sector_num, nb_sectors); + return bdrv_pdiscard(blk_bs(blk), offset, count); } int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index 4902ca557f..f2bfdcfdea 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -326,14 +326,14 @@ void bdrv_dirty_iter_init(BdrvDirtyBitmap *bitmap, HBitmapIter *hbi) } void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int nr_sectors) + int64_t cur_sector, int64_t nr_sectors) { assert(bdrv_dirty_bitmap_enabled(bitmap)); hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors); } void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int nr_sectors) + int64_t cur_sector, int64_t nr_sectors) { assert(bdrv_dirty_bitmap_enabled(bitmap)); hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors); @@ -361,7 +361,7 @@ void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in) } void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, - int nr_sectors) + int64_t nr_sectors) { BdrvDirtyBitmap *bitmap; QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) { diff --git a/block/gluster.c b/block/gluster.c index 406c1e6357..01b479fbb9 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -11,7 +11,27 @@ #include <glusterfs/api/glfs.h> #include "block/block_int.h" #include "qapi/error.h" +#include "qapi/qmp/qerror.h" #include "qemu/uri.h" +#include "qemu/error-report.h" + +#define GLUSTER_OPT_FILENAME "filename" +#define GLUSTER_OPT_VOLUME "volume" +#define GLUSTER_OPT_PATH "path" +#define GLUSTER_OPT_TYPE "type" +#define GLUSTER_OPT_SERVER_PATTERN "server." +#define GLUSTER_OPT_HOST "host" +#define GLUSTER_OPT_PORT "port" +#define GLUSTER_OPT_TO "to" +#define GLUSTER_OPT_IPV4 "ipv4" +#define GLUSTER_OPT_IPV6 "ipv6" +#define GLUSTER_OPT_SOCKET "socket" +#define GLUSTER_OPT_DEBUG "debug" +#define GLUSTER_DEFAULT_PORT 24007 +#define GLUSTER_DEBUG_DEFAULT 4 +#define GLUSTER_DEBUG_MAX 9 + +#define GERR_INDEX_HINT "hint: check in 'server' array index '%d'\n" typedef struct GlusterAIOCB { int64_t size; @@ -28,27 +48,141 @@ typedef struct BDRVGlusterState { int debug_level; } BDRVGlusterState; -typedef struct GlusterConf { - char *server; - int port; - char *volname; - char *image; - char *transport; - int debug_level; -} GlusterConf; +typedef struct BDRVGlusterReopenState { + struct glfs *glfs; + struct glfs_fd *fd; +} BDRVGlusterReopenState; -static void qemu_gluster_gconf_free(GlusterConf *gconf) -{ - if (gconf) { - g_free(gconf->server); - g_free(gconf->volname); - g_free(gconf->image); - g_free(gconf->transport); - g_free(gconf); + +static QemuOptsList qemu_gluster_create_opts = { + .name = "qemu-gluster-create-opts", + .head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head), + .desc = { + { + .name = BLOCK_OPT_SIZE, + .type = QEMU_OPT_SIZE, + .help = "Virtual disk size" + }, + { + .name = BLOCK_OPT_PREALLOC, + .type = QEMU_OPT_STRING, + .help = "Preallocation mode (allowed values: off, full)" + }, + { + .name = GLUSTER_OPT_DEBUG, + .type = QEMU_OPT_NUMBER, + .help = "Gluster log level, valid range is 0-9", + }, + { /* end of list */ } } -} +}; + +static QemuOptsList runtime_opts = { + .name = "gluster", + .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), + .desc = { + { + .name = GLUSTER_OPT_FILENAME, + .type = QEMU_OPT_STRING, + .help = "URL to the gluster image", + }, + { + .name = GLUSTER_OPT_DEBUG, + .type = QEMU_OPT_NUMBER, + .help = "Gluster log level, valid range is 0-9", + }, + { /* end of list */ } + }, +}; + +static QemuOptsList runtime_json_opts = { + .name = "gluster_json", + .head = QTAILQ_HEAD_INITIALIZER(runtime_json_opts.head), + .desc = { + { + .name = GLUSTER_OPT_VOLUME, + .type = QEMU_OPT_STRING, + .help = "name of gluster volume where VM image resides", + }, + { + .name = GLUSTER_OPT_PATH, + .type = QEMU_OPT_STRING, + .help = "absolute path to image file in gluster volume", + }, + { + .name = GLUSTER_OPT_DEBUG, + .type = QEMU_OPT_NUMBER, + .help = "Gluster log level, valid range is 0-9", + }, + { /* end of list */ } + }, +}; + +static QemuOptsList runtime_type_opts = { + .name = "gluster_type", + .head = QTAILQ_HEAD_INITIALIZER(runtime_type_opts.head), + .desc = { + { + .name = GLUSTER_OPT_TYPE, + .type = QEMU_OPT_STRING, + .help = "tcp|unix", + }, + { /* end of list */ } + }, +}; + +static QemuOptsList runtime_unix_opts = { + .name = "gluster_unix", + .head = QTAILQ_HEAD_INITIALIZER(runtime_unix_opts.head), + .desc = { + { + .name = GLUSTER_OPT_SOCKET, + .type = QEMU_OPT_STRING, + .help = "socket file path)", + }, + { /* end of list */ } + }, +}; + +static QemuOptsList runtime_tcp_opts = { + .name = "gluster_tcp", + .head = QTAILQ_HEAD_INITIALIZER(runtime_tcp_opts.head), + .desc = { + { + .name = GLUSTER_OPT_TYPE, + .type = QEMU_OPT_STRING, + .help = "tcp|unix", + }, + { + .name = GLUSTER_OPT_HOST, + .type = QEMU_OPT_STRING, + .help = "host address (hostname/ipv4/ipv6 addresses)", + }, + { + .name = GLUSTER_OPT_PORT, + .type = QEMU_OPT_NUMBER, + .help = "port number on which glusterd is listening (default 24007)", + }, + { + .name = "to", + .type = QEMU_OPT_NUMBER, + .help = "max port number, not supported by gluster", + }, + { + .name = "ipv4", + .type = QEMU_OPT_BOOL, + .help = "ipv4 bool value, not supported by gluster", + }, + { + .name = "ipv6", + .type = QEMU_OPT_BOOL, + .help = "ipv6 bool value, not supported by gluster", + }, + { /* end of list */ } + }, +}; -static int parse_volume_options(GlusterConf *gconf, char *path) +static int parse_volume_options(BlockdevOptionsGluster *gconf, char *path) { char *p, *q; @@ -62,31 +196,29 @@ static int parse_volume_options(GlusterConf *gconf, char *path) if (*p == '\0') { return -EINVAL; } - gconf->volname = g_strndup(q, p - q); + gconf->volume = g_strndup(q, p - q); - /* image */ + /* path */ p += strspn(p, "/"); if (*p == '\0') { return -EINVAL; } - gconf->image = g_strdup(p); + gconf->path = g_strdup(p); return 0; } /* - * file=gluster[+transport]://[server[:port]]/volname/image[?socket=...] + * file=gluster[+transport]://[host[:port]]/volume/path[?socket=...] * * 'gluster' is the protocol. * * 'transport' specifies the transport type used to connect to gluster * management daemon (glusterd). Valid transport types are - * tcp, unix and rdma. If a transport type isn't specified, then tcp - * type is assumed. + * tcp or unix. If a transport type isn't specified, then tcp type is assumed. * - * 'server' specifies the server where the volume file specification for - * the given volume resides. This can be either hostname, ipv4 address - * or ipv6 address. ipv6 address needs to be within square brackets [ ]. - * If transport type is 'unix', then 'server' field should not be specified. + * 'host' specifies the host where the volume file specification for + * the given volume resides. This can be either hostname or ipv4 address. + * If transport type is 'unix', then 'host' field should not be specified. * The 'socket' field needs to be populated with the path to unix domain * socket. * @@ -95,23 +227,22 @@ static int parse_volume_options(GlusterConf *gconf, char *path) * default port. If the transport type is unix, then 'port' should not be * specified. * - * 'volname' is the name of the gluster volume which contains the VM image. + * 'volume' is the name of the gluster volume which contains the VM image. * - * 'image' is the path to the actual VM image that resides on gluster volume. + * 'path' is the path to the actual VM image that resides on gluster volume. * * Examples: * * file=gluster://1.2.3.4/testvol/a.img * file=gluster+tcp://1.2.3.4/testvol/a.img * file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img - * file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img - * file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img - * file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img + * file=gluster+tcp://host.domain.com:24007/testvol/dir/a.img * file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket - * file=gluster+rdma://1.2.3.4:24007/testvol/a.img */ -static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename) +static int qemu_gluster_parse_uri(BlockdevOptionsGluster *gconf, + const char *filename) { + GlusterServer *gsconf; URI *uri; QueryParams *qp = NULL; bool is_unix = false; @@ -122,16 +253,21 @@ static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename) return -EINVAL; } + gconf->server = g_new0(GlusterServerList, 1); + gconf->server->value = gsconf = g_new0(GlusterServer, 1); + /* transport */ if (!uri->scheme || !strcmp(uri->scheme, "gluster")) { - gconf->transport = g_strdup("tcp"); + gsconf->type = GLUSTER_TRANSPORT_TCP; } else if (!strcmp(uri->scheme, "gluster+tcp")) { - gconf->transport = g_strdup("tcp"); + gsconf->type = GLUSTER_TRANSPORT_TCP; } else if (!strcmp(uri->scheme, "gluster+unix")) { - gconf->transport = g_strdup("unix"); + gsconf->type = GLUSTER_TRANSPORT_UNIX; is_unix = true; } else if (!strcmp(uri->scheme, "gluster+rdma")) { - gconf->transport = g_strdup("rdma"); + gsconf->type = GLUSTER_TRANSPORT_TCP; + error_report("Warning: rdma feature is not supported, falling " + "back to tcp"); } else { ret = -EINVAL; goto out; @@ -157,10 +293,14 @@ static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename) ret = -EINVAL; goto out; } - gconf->server = g_strdup(qp->p[0].value); + gsconf->u.q_unix.path = g_strdup(qp->p[0].value); } else { - gconf->server = g_strdup(uri->server ? uri->server : "localhost"); - gconf->port = uri->port; + gsconf->u.tcp.host = g_strdup(uri->server ? uri->server : "localhost"); + if (uri->port) { + gsconf->u.tcp.port = g_strdup_printf("%d", uri->port); + } else { + gsconf->u.tcp.port = g_strdup_printf("%d", GLUSTER_DEFAULT_PORT); + } } out: @@ -171,30 +311,34 @@ out: return ret; } -static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename, - Error **errp) +static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf, + Error **errp) { - struct glfs *glfs = NULL; + struct glfs *glfs; int ret; int old_errno; + GlusterServerList *server; - ret = qemu_gluster_parseuri(gconf, filename); - if (ret < 0) { - error_setg(errp, "Usage: file=gluster[+transport]://[server[:port]]/" - "volname/image[?socket=...]"); - errno = -ret; - goto out; - } - - glfs = glfs_new(gconf->volname); + glfs = glfs_new(gconf->volume); if (!glfs) { goto out; } - ret = glfs_set_volfile_server(glfs, gconf->transport, gconf->server, - gconf->port); - if (ret < 0) { - goto out; + for (server = gconf->server; server; server = server->next) { + if (server->value->type == GLUSTER_TRANSPORT_UNIX) { + ret = glfs_set_volfile_server(glfs, + GlusterTransport_lookup[server->value->type], + server->value->u.q_unix.path, 0); + } else { + ret = glfs_set_volfile_server(glfs, + GlusterTransport_lookup[server->value->type], + server->value->u.tcp.host, + atoi(server->value->u.tcp.port)); + } + + if (ret < 0) { + goto out; + } } ret = glfs_set_logging(glfs, "-", gconf->debug_level); @@ -204,15 +348,25 @@ static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename, ret = glfs_init(glfs); if (ret) { - error_setg_errno(errp, errno, - "Gluster connection failed for server=%s port=%d " - "volume=%s image=%s transport=%s", gconf->server, - gconf->port, gconf->volname, gconf->image, - gconf->transport); + error_setg(errp, "Gluster connection for volume %s, path %s failed" + " to connect", gconf->volume, gconf->path); + for (server = gconf->server; server; server = server->next) { + if (server->value->type == GLUSTER_TRANSPORT_UNIX) { + error_append_hint(errp, "hint: failed on socket %s ", + server->value->u.q_unix.path); + } else { + error_append_hint(errp, "hint: failed on host %s and port %s ", + server->value->u.tcp.host, + server->value->u.tcp.port); + } + } + + error_append_hint(errp, "Please refer to gluster logs for more info\n"); /* glfs_init sometimes doesn't set errno although docs suggest that */ - if (errno == 0) + if (errno == 0) { errno = EINVAL; + } goto out; } @@ -227,6 +381,226 @@ out: return NULL; } +static int qapi_enum_parse(const char *opt) +{ + int i; + + if (!opt) { + return GLUSTER_TRANSPORT__MAX; + } + + for (i = 0; i < GLUSTER_TRANSPORT__MAX; i++) { + if (!strcmp(opt, GlusterTransport_lookup[i])) { + return i; + } + } + + return i; +} + +/* + * Convert the json formatted command line into qapi. +*/ +static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf, + QDict *options, Error **errp) +{ + QemuOpts *opts; + GlusterServer *gsconf; + GlusterServerList *curr = NULL; + QDict *backing_options = NULL; + Error *local_err = NULL; + char *str = NULL; + const char *ptr; + size_t num_servers; + int i; + + /* create opts info from runtime_json_opts list */ + opts = qemu_opts_create(&runtime_json_opts, NULL, 0, &error_abort); + qemu_opts_absorb_qdict(opts, options, &local_err); + if (local_err) { + goto out; + } + + num_servers = qdict_array_entries(options, GLUSTER_OPT_SERVER_PATTERN); + if (num_servers < 1) { + error_setg(&local_err, QERR_MISSING_PARAMETER, "server"); + goto out; + } + + ptr = qemu_opt_get(opts, GLUSTER_OPT_VOLUME); + if (!ptr) { + error_setg(&local_err, QERR_MISSING_PARAMETER, GLUSTER_OPT_VOLUME); + goto out; + } + gconf->volume = g_strdup(ptr); + + ptr = qemu_opt_get(opts, GLUSTER_OPT_PATH); + if (!ptr) { + error_setg(&local_err, QERR_MISSING_PARAMETER, GLUSTER_OPT_PATH); + goto out; + } + gconf->path = g_strdup(ptr); + qemu_opts_del(opts); + + for (i = 0; i < num_servers; i++) { + str = g_strdup_printf(GLUSTER_OPT_SERVER_PATTERN"%d.", i); + qdict_extract_subqdict(options, &backing_options, str); + + /* create opts info from runtime_type_opts list */ + opts = qemu_opts_create(&runtime_type_opts, NULL, 0, &error_abort); + qemu_opts_absorb_qdict(opts, backing_options, &local_err); + if (local_err) { + goto out; + } + + ptr = qemu_opt_get(opts, GLUSTER_OPT_TYPE); + gsconf = g_new0(GlusterServer, 1); + gsconf->type = qapi_enum_parse(ptr); + if (!ptr) { + error_setg(&local_err, QERR_MISSING_PARAMETER, GLUSTER_OPT_TYPE); + error_append_hint(&local_err, GERR_INDEX_HINT, i); + goto out; + + } + if (gsconf->type == GLUSTER_TRANSPORT__MAX) { + error_setg(&local_err, QERR_INVALID_PARAMETER_VALUE, + GLUSTER_OPT_TYPE, "tcp or unix"); + error_append_hint(&local_err, GERR_INDEX_HINT, i); + goto out; + } + qemu_opts_del(opts); + + if (gsconf->type == GLUSTER_TRANSPORT_TCP) { + /* create opts info from runtime_tcp_opts list */ + opts = qemu_opts_create(&runtime_tcp_opts, NULL, 0, &error_abort); + qemu_opts_absorb_qdict(opts, backing_options, &local_err); + if (local_err) { + goto out; + } + + ptr = qemu_opt_get(opts, GLUSTER_OPT_HOST); + if (!ptr) { + error_setg(&local_err, QERR_MISSING_PARAMETER, + GLUSTER_OPT_HOST); + error_append_hint(&local_err, GERR_INDEX_HINT, i); + goto out; + } + gsconf->u.tcp.host = g_strdup(ptr); + ptr = qemu_opt_get(opts, GLUSTER_OPT_PORT); + if (!ptr) { + error_setg(&local_err, QERR_MISSING_PARAMETER, + GLUSTER_OPT_PORT); + error_append_hint(&local_err, GERR_INDEX_HINT, i); + goto out; + } + gsconf->u.tcp.port = g_strdup(ptr); + + /* defend for unsupported fields in InetSocketAddress, + * i.e. @ipv4, @ipv6 and @to + */ + ptr = qemu_opt_get(opts, GLUSTER_OPT_TO); + if (ptr) { + gsconf->u.tcp.has_to = true; + } + ptr = qemu_opt_get(opts, GLUSTER_OPT_IPV4); + if (ptr) { + gsconf->u.tcp.has_ipv4 = true; + } + ptr = qemu_opt_get(opts, GLUSTER_OPT_IPV6); + if (ptr) { + gsconf->u.tcp.has_ipv6 = true; + } + if (gsconf->u.tcp.has_to) { + error_setg(&local_err, "Parameter 'to' not supported"); + goto out; + } + if (gsconf->u.tcp.has_ipv4 || gsconf->u.tcp.has_ipv6) { + error_setg(&local_err, "Parameters 'ipv4/ipv6' not supported"); + goto out; + } + qemu_opts_del(opts); + } else { + /* create opts info from runtime_unix_opts list */ + opts = qemu_opts_create(&runtime_unix_opts, NULL, 0, &error_abort); + qemu_opts_absorb_qdict(opts, backing_options, &local_err); + if (local_err) { + goto out; + } + + ptr = qemu_opt_get(opts, GLUSTER_OPT_SOCKET); + if (!ptr) { + error_setg(&local_err, QERR_MISSING_PARAMETER, + GLUSTER_OPT_SOCKET); + error_append_hint(&local_err, GERR_INDEX_HINT, i); + goto out; + } + gsconf->u.q_unix.path = g_strdup(ptr); + qemu_opts_del(opts); + } + + if (gconf->server == NULL) { + gconf->server = g_new0(GlusterServerList, 1); + gconf->server->value = gsconf; + curr = gconf->server; + } else { + curr->next = g_new0(GlusterServerList, 1); + curr->next->value = gsconf; + curr = curr->next; + } + + qdict_del(backing_options, str); + g_free(str); + str = NULL; + } + + return 0; + +out: + error_propagate(errp, local_err); + qemu_opts_del(opts); + if (str) { + qdict_del(backing_options, str); + g_free(str); + } + errno = EINVAL; + return -errno; +} + +static struct glfs *qemu_gluster_init(BlockdevOptionsGluster *gconf, + const char *filename, + QDict *options, Error **errp) +{ + int ret; + if (filename) { + ret = qemu_gluster_parse_uri(gconf, filename); + if (ret < 0) { + error_setg(errp, "invalid URI"); + error_append_hint(errp, "Usage: file=gluster[+transport]://" + "[host[:port]]/volume/path[?socket=...]\n"); + errno = -ret; + return NULL; + } + } else { + ret = qemu_gluster_parse_json(gconf, options, errp); + if (ret < 0) { + error_append_hint(errp, "Usage: " + "-drive driver=qcow2,file.driver=gluster," + "file.volume=testvol,file.path=/path/a.qcow2" + "[,file.debug=9],file.server.0.type=tcp," + "file.server.0.host=1.2.3.4," + "file.server.0.port=24007," + "file.server.1.transport=unix," + "file.server.1.socket=/var/run/glusterd.socket ..." + "\n"); + errno = -ret; + return NULL; + } + + } + + return qemu_gluster_glfs_init(gconf, errp); +} + static void qemu_gluster_complete_aio(void *opaque) { GlusterAIOCB *acb = (GlusterAIOCB *)opaque; @@ -255,30 +629,6 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg) qemu_bh_schedule(acb->bh); } -#define GLUSTER_OPT_FILENAME "filename" -#define GLUSTER_OPT_DEBUG "debug" -#define GLUSTER_DEBUG_DEFAULT 4 -#define GLUSTER_DEBUG_MAX 9 - -/* TODO Convert to fine grained options */ -static QemuOptsList runtime_opts = { - .name = "gluster", - .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), - .desc = { - { - .name = GLUSTER_OPT_FILENAME, - .type = QEMU_OPT_STRING, - .help = "URL to the gluster image", - }, - { - .name = GLUSTER_OPT_DEBUG, - .type = QEMU_OPT_NUMBER, - .help = "Gluster log level, valid range is 0-9", - }, - { /* end of list */ } - }, -}; - static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags) { assert(open_flags != NULL); @@ -324,7 +674,7 @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options, BDRVGlusterState *s = bs->opaque; int open_flags = 0; int ret = 0; - GlusterConf *gconf = g_new0(GlusterConf, 1); + BlockdevOptionsGluster *gconf = NULL; QemuOpts *opts; Error *local_err = NULL; const char *filename; @@ -347,8 +697,10 @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options, s->debug_level = GLUSTER_DEBUG_MAX; } + gconf = g_new0(BlockdevOptionsGluster, 1); gconf->debug_level = s->debug_level; - s->glfs = qemu_gluster_init(gconf, filename, errp); + gconf->has_debug_level = true; + s->glfs = qemu_gluster_init(gconf, filename, options, errp); if (!s->glfs) { ret = -errno; goto out; @@ -373,7 +725,7 @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options, qemu_gluster_parse_flags(bdrv_flags, &open_flags); - s->fd = glfs_open(s->glfs, gconf->image, open_flags); + s->fd = glfs_open(s->glfs, gconf->path, open_flags); if (!s->fd) { ret = -errno; } @@ -382,7 +734,7 @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options, out: qemu_opts_del(opts); - qemu_gluster_gconf_free(gconf); + qapi_free_BlockdevOptionsGluster(gconf); if (!ret) { return ret; } @@ -395,19 +747,13 @@ out: return ret; } -typedef struct BDRVGlusterReopenState { - struct glfs *glfs; - struct glfs_fd *fd; -} BDRVGlusterReopenState; - - static int qemu_gluster_reopen_prepare(BDRVReopenState *state, BlockReopenQueue *queue, Error **errp) { int ret = 0; BDRVGlusterState *s; BDRVGlusterReopenState *reop_s; - GlusterConf *gconf = NULL; + BlockdevOptionsGluster *gconf; int open_flags = 0; assert(state != NULL); @@ -420,10 +766,10 @@ static int qemu_gluster_reopen_prepare(BDRVReopenState *state, qemu_gluster_parse_flags(state->flags, &open_flags); - gconf = g_new0(GlusterConf, 1); - + gconf = g_new0(BlockdevOptionsGluster, 1); gconf->debug_level = s->debug_level; - reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, errp); + gconf->has_debug_level = true; + reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, NULL, errp); if (reop_s->glfs == NULL) { ret = -errno; goto exit; @@ -439,7 +785,7 @@ static int qemu_gluster_reopen_prepare(BDRVReopenState *state, } #endif - reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags); + reop_s->fd = glfs_open(reop_s->glfs, gconf->path, open_flags); if (reop_s->fd == NULL) { /* reops->glfs will be cleaned up in _abort */ ret = -errno; @@ -448,7 +794,7 @@ static int qemu_gluster_reopen_prepare(BDRVReopenState *state, exit: /* state->opaque will be freed in either the _abort or _commit */ - qemu_gluster_gconf_free(gconf); + qapi_free_BlockdevOptionsGluster(gconf); return ret; } @@ -501,7 +847,9 @@ static void qemu_gluster_reopen_abort(BDRVReopenState *state) #ifdef CONFIG_GLUSTERFS_ZEROFILL static coroutine_fn int qemu_gluster_co_pwrite_zeroes(BlockDriverState *bs, - int64_t offset, int size, BdrvRequestFlags flags) + int64_t offset, + int size, + BdrvRequestFlags flags) { int ret; GlusterAIOCB acb; @@ -527,7 +875,7 @@ static inline bool gluster_supports_zerofill(void) } static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset, - int64_t size) + int64_t size) { return glfs_zerofill(fd, offset, size); } @@ -539,7 +887,7 @@ static inline bool gluster_supports_zerofill(void) } static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset, - int64_t size) + int64_t size) { return 0; } @@ -548,14 +896,15 @@ static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset, static int qemu_gluster_create(const char *filename, QemuOpts *opts, Error **errp) { + BlockdevOptionsGluster *gconf; struct glfs *glfs; struct glfs_fd *fd; int ret = 0; int prealloc = 0; int64_t total_size = 0; char *tmp = NULL; - GlusterConf *gconf = g_new0(GlusterConf, 1); + gconf = g_new0(BlockdevOptionsGluster, 1); gconf->debug_level = qemu_opt_get_number_del(opts, GLUSTER_OPT_DEBUG, GLUSTER_DEBUG_DEFAULT); if (gconf->debug_level < 0) { @@ -563,8 +912,9 @@ static int qemu_gluster_create(const char *filename, } else if (gconf->debug_level > GLUSTER_DEBUG_MAX) { gconf->debug_level = GLUSTER_DEBUG_MAX; } + gconf->has_debug_level = true; - glfs = qemu_gluster_init(gconf, filename, errp); + glfs = qemu_gluster_init(gconf, filename, NULL, errp); if (!glfs) { ret = -errno; goto out; @@ -576,19 +926,17 @@ static int qemu_gluster_create(const char *filename, tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC); if (!tmp || !strcmp(tmp, "off")) { prealloc = 0; - } else if (!strcmp(tmp, "full") && - gluster_supports_zerofill()) { + } else if (!strcmp(tmp, "full") && gluster_supports_zerofill()) { prealloc = 1; } else { error_setg(errp, "Invalid preallocation mode: '%s'" - " or GlusterFS doesn't support zerofill API", - tmp); + " or GlusterFS doesn't support zerofill API", tmp); ret = -EINVAL; goto out; } - fd = glfs_creat(glfs, gconf->image, - O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR); + fd = glfs_creat(glfs, gconf->path, + O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR); if (!fd) { ret = -errno; } else { @@ -606,7 +954,7 @@ static int qemu_gluster_create(const char *filename, } out: g_free(tmp); - qemu_gluster_gconf_free(gconf); + qapi_free_BlockdevOptionsGluster(gconf); if (glfs) { glfs_fini(glfs); } @@ -614,7 +962,8 @@ out: } static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int write) + int64_t sector_num, int nb_sectors, + QEMUIOVector *qiov, int write) { int ret; GlusterAIOCB acb; @@ -629,10 +978,10 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs, if (write) { ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0, - gluster_finish_aiocb, &acb); + gluster_finish_aiocb, &acb); } else { ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0, - gluster_finish_aiocb, &acb); + gluster_finish_aiocb, &acb); } if (ret < 0) { @@ -657,13 +1006,17 @@ static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset) } static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) + int64_t sector_num, + int nb_sectors, + QEMUIOVector *qiov) { return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 0); } static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) + int64_t sector_num, + int nb_sectors, + QEMUIOVector *qiov) { return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1); } @@ -724,14 +1077,12 @@ error: } #ifdef CONFIG_GLUSTERFS_DISCARD -static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors) +static coroutine_fn int qemu_gluster_co_pdiscard(BlockDriverState *bs, + int64_t offset, int size) { int ret; GlusterAIOCB acb; BDRVGlusterState *s = bs->opaque; - size_t size = nb_sectors * BDRV_SECTOR_SIZE; - off_t offset = sector_num * BDRV_SECTOR_SIZE; acb.size = 0; acb.ret = 0; @@ -934,34 +1285,11 @@ static int64_t coroutine_fn qemu_gluster_co_get_block_status( } -static QemuOptsList qemu_gluster_create_opts = { - .name = "qemu-gluster-create-opts", - .head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head), - .desc = { - { - .name = BLOCK_OPT_SIZE, - .type = QEMU_OPT_SIZE, - .help = "Virtual disk size" - }, - { - .name = BLOCK_OPT_PREALLOC, - .type = QEMU_OPT_STRING, - .help = "Preallocation mode (allowed values: off, full)" - }, - { - .name = GLUSTER_OPT_DEBUG, - .type = QEMU_OPT_NUMBER, - .help = "Gluster log level, valid range is 0-9", - }, - { /* end of list */ } - } -}; - static BlockDriver bdrv_gluster = { .format_name = "gluster", .protocol_name = "gluster", .instance_size = sizeof(BDRVGlusterState), - .bdrv_needs_filename = true, + .bdrv_needs_filename = false, .bdrv_file_open = qemu_gluster_open, .bdrv_reopen_prepare = qemu_gluster_reopen_prepare, .bdrv_reopen_commit = qemu_gluster_reopen_commit, @@ -976,7 +1304,7 @@ static BlockDriver bdrv_gluster = { .bdrv_co_flush_to_disk = qemu_gluster_co_flush_to_disk, .bdrv_has_zero_init = qemu_gluster_has_zero_init, #ifdef CONFIG_GLUSTERFS_DISCARD - .bdrv_co_discard = qemu_gluster_co_discard, + .bdrv_co_pdiscard = qemu_gluster_co_pdiscard, #endif #ifdef CONFIG_GLUSTERFS_ZEROFILL .bdrv_co_pwrite_zeroes = qemu_gluster_co_pwrite_zeroes, @@ -989,7 +1317,7 @@ static BlockDriver bdrv_gluster_tcp = { .format_name = "gluster", .protocol_name = "gluster+tcp", .instance_size = sizeof(BDRVGlusterState), - .bdrv_needs_filename = true, + .bdrv_needs_filename = false, .bdrv_file_open = qemu_gluster_open, .bdrv_reopen_prepare = qemu_gluster_reopen_prepare, .bdrv_reopen_commit = qemu_gluster_reopen_commit, @@ -1004,7 +1332,7 @@ static BlockDriver bdrv_gluster_tcp = { .bdrv_co_flush_to_disk = qemu_gluster_co_flush_to_disk, .bdrv_has_zero_init = qemu_gluster_has_zero_init, #ifdef CONFIG_GLUSTERFS_DISCARD - .bdrv_co_discard = qemu_gluster_co_discard, + .bdrv_co_pdiscard = qemu_gluster_co_pdiscard, #endif #ifdef CONFIG_GLUSTERFS_ZEROFILL .bdrv_co_pwrite_zeroes = qemu_gluster_co_pwrite_zeroes, @@ -1032,7 +1360,7 @@ static BlockDriver bdrv_gluster_unix = { .bdrv_co_flush_to_disk = qemu_gluster_co_flush_to_disk, .bdrv_has_zero_init = qemu_gluster_has_zero_init, #ifdef CONFIG_GLUSTERFS_DISCARD - .bdrv_co_discard = qemu_gluster_co_discard, + .bdrv_co_pdiscard = qemu_gluster_co_pdiscard, #endif #ifdef CONFIG_GLUSTERFS_ZEROFILL .bdrv_co_pwrite_zeroes = qemu_gluster_co_pwrite_zeroes, @@ -1041,6 +1369,12 @@ static BlockDriver bdrv_gluster_unix = { .create_opts = &qemu_gluster_create_opts, }; +/* rdma is deprecated (actually never supported for volfile fetch). + * Let's maintain it for the protocol compatibility, to make sure things + * won't break immediately. For now, gluster+rdma will fall back to gluster+tcp + * protocol with a warning. + * TODO: remove gluster+rdma interface support + */ static BlockDriver bdrv_gluster_rdma = { .format_name = "gluster", .protocol_name = "gluster+rdma", @@ -1060,7 +1394,7 @@ static BlockDriver bdrv_gluster_rdma = { .bdrv_co_flush_to_disk = qemu_gluster_co_flush_to_disk, .bdrv_has_zero_init = qemu_gluster_has_zero_init, #ifdef CONFIG_GLUSTERFS_DISCARD - .bdrv_co_discard = qemu_gluster_co_discard, + .bdrv_co_pdiscard = qemu_gluster_co_pdiscard, #endif #ifdef CONFIG_GLUSTERFS_ZEROFILL .bdrv_co_pwrite_zeroes = qemu_gluster_co_pwrite_zeroes, diff --git a/block/io.c b/block/io.c index cfda7148d8..7323f0fb7b 100644 --- a/block/io.c +++ b/block/io.c @@ -33,14 +33,13 @@ #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */ -static BlockAIOCB *bdrv_co_aio_rw_vector(BdrvChild *child, - int64_t sector_num, - QEMUIOVector *qiov, - int nb_sectors, - BdrvRequestFlags flags, - BlockCompletionFunc *cb, - void *opaque, - bool is_write); +static BlockAIOCB *bdrv_co_aio_prw_vector(BdrvChild *child, + int64_t offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags, + BlockCompletionFunc *cb, + void *opaque, + bool is_write); static void coroutine_fn bdrv_co_do_rw(void *opaque); static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int count, BdrvRequestFlags flags); @@ -971,21 +970,25 @@ err: /* * Forwards an already correctly aligned request to the BlockDriver. This - * handles copy on read and zeroing after EOF; any other features must be - * implemented by the caller. + * handles copy on read, zeroing after EOF, and fragmentation of large + * reads; any other features must be implemented by the caller. */ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, BdrvTrackedRequest *req, int64_t offset, unsigned int bytes, int64_t align, QEMUIOVector *qiov, int flags) { int64_t total_bytes, max_bytes; - int ret; + int ret = 0; + uint64_t bytes_remaining = bytes; + int max_transfer; assert(is_power_of_2(align)); assert((offset & (align - 1)) == 0); assert((bytes & (align - 1)) == 0); assert(!qiov || bytes == qiov->size); assert((bs->open_flags & BDRV_O_NO_IO) == 0); + max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX), + align); /* TODO: We would need a per-BDS .supported_read_flags and * potential fallback support, if we ever implement any read flags @@ -1024,7 +1027,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, } } - /* Forward the request to the BlockDriver */ + /* Forward the request to the BlockDriver, possibly fragmenting it */ total_bytes = bdrv_getlength(bs); if (total_bytes < 0) { ret = total_bytes; @@ -1032,30 +1035,39 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, } max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align); - if (bytes <= max_bytes) { + if (bytes <= max_bytes && bytes <= max_transfer) { ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0); - } else if (max_bytes > 0) { - QEMUIOVector local_qiov; + goto out; + } - qemu_iovec_init(&local_qiov, qiov->niov); - qemu_iovec_concat(&local_qiov, qiov, 0, max_bytes); + while (bytes_remaining) { + int num; - ret = bdrv_driver_preadv(bs, offset, max_bytes, &local_qiov, 0); + if (max_bytes) { + QEMUIOVector local_qiov; - qemu_iovec_destroy(&local_qiov); - } else { - ret = 0; - } + num = MIN(bytes_remaining, MIN(max_bytes, max_transfer)); + assert(num); + qemu_iovec_init(&local_qiov, qiov->niov); + qemu_iovec_concat(&local_qiov, qiov, bytes - bytes_remaining, num); - /* Reading beyond end of file is supposed to produce zeroes */ - if (ret == 0 && total_bytes < offset + bytes) { - uint64_t zero_offset = MAX(0, total_bytes - offset); - uint64_t zero_bytes = offset + bytes - zero_offset; - qemu_iovec_memset(qiov, zero_offset, 0, zero_bytes); + ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining, + num, &local_qiov, 0); + max_bytes -= num; + qemu_iovec_destroy(&local_qiov); + } else { + num = bytes_remaining; + ret = qemu_iovec_memset(qiov, bytes - bytes_remaining, 0, + bytes_remaining); + } + if (ret < 0) { + goto out; + } + bytes_remaining -= num; } out: - return ret; + return ret < 0 ? ret : 0; } /* @@ -1256,7 +1268,8 @@ fail: } /* - * Forwards an already correctly aligned write request to the BlockDriver. + * Forwards an already correctly aligned write request to the BlockDriver, + * after possibly fragmenting it. */ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, BdrvTrackedRequest *req, int64_t offset, unsigned int bytes, @@ -1268,6 +1281,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, int64_t start_sector = offset >> BDRV_SECTOR_BITS; int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); + uint64_t bytes_remaining = bytes; + int max_transfer; assert(is_power_of_2(align)); assert((offset & (align - 1)) == 0); @@ -1275,6 +1290,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, assert(!qiov || bytes == qiov->size); assert((bs->open_flags & BDRV_O_NO_IO) == 0); assert(!(flags & ~BDRV_REQ_MASK)); + max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX), + align); waited = wait_serialising_requests(req); assert(!waited || !req->serialising); @@ -1297,9 +1314,34 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, } else if (flags & BDRV_REQ_ZERO_WRITE) { bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO); ret = bdrv_co_do_pwrite_zeroes(bs, offset, bytes, flags); - } else { + } else if (bytes <= max_transfer) { bdrv_debug_event(bs, BLKDBG_PWRITEV); ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, flags); + } else { + bdrv_debug_event(bs, BLKDBG_PWRITEV); + while (bytes_remaining) { + int num = MIN(bytes_remaining, max_transfer); + QEMUIOVector local_qiov; + int local_flags = flags; + + assert(num); + if (num < bytes_remaining && (flags & BDRV_REQ_FUA) && + !(bs->supported_write_flags & BDRV_REQ_FUA)) { + /* If FUA is going to be emulated by flush, we only + * need to flush on the last iteration */ + local_flags &= ~BDRV_REQ_FUA; + } + qemu_iovec_init(&local_qiov, qiov->niov); + qemu_iovec_concat(&local_qiov, qiov, bytes - bytes_remaining, num); + + ret = bdrv_driver_pwritev(bs, offset + bytes - bytes_remaining, + num, &local_qiov, local_flags); + qemu_iovec_destroy(&local_qiov); + if (ret < 0) { + break; + } + bytes_remaining -= num; + } } bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE); @@ -1312,6 +1354,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, if (ret >= 0) { bs->total_sectors = MAX(bs->total_sectors, end_sector); + ret = 0; } return ret; @@ -1971,8 +2014,9 @@ BlockAIOCB *bdrv_aio_readv(BdrvChild *child, int64_t sector_num, { trace_bdrv_aio_readv(child->bs, sector_num, nb_sectors, opaque); - return bdrv_co_aio_rw_vector(child, sector_num, qiov, nb_sectors, 0, - cb, opaque, false); + assert(nb_sectors << BDRV_SECTOR_BITS == qiov->size); + return bdrv_co_aio_prw_vector(child, sector_num << BDRV_SECTOR_BITS, qiov, + 0, cb, opaque, false); } BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num, @@ -1981,8 +2025,9 @@ BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num, { trace_bdrv_aio_writev(child->bs, sector_num, nb_sectors, opaque); - return bdrv_co_aio_rw_vector(child, sector_num, qiov, nb_sectors, 0, - cb, opaque, true); + assert(nb_sectors << BDRV_SECTOR_BITS == qiov->size); + return bdrv_co_aio_prw_vector(child, sector_num << BDRV_SECTOR_BITS, qiov, + 0, cb, opaque, true); } void bdrv_aio_cancel(BlockAIOCB *acb) @@ -2018,8 +2063,8 @@ typedef struct BlockRequest { union { /* Used during read, write, trim */ struct { - int64_t sector; - int nb_sectors; + int64_t offset; + int bytes; int flags; QEMUIOVector *qiov; }; @@ -2083,24 +2128,23 @@ static void coroutine_fn bdrv_co_do_rw(void *opaque) BlockAIOCBCoroutine *acb = opaque; if (!acb->is_write) { - acb->req.error = bdrv_co_do_readv(acb->child, acb->req.sector, - acb->req.nb_sectors, acb->req.qiov, acb->req.flags); + acb->req.error = bdrv_co_preadv(acb->child, acb->req.offset, + acb->req.qiov->size, acb->req.qiov, acb->req.flags); } else { - acb->req.error = bdrv_co_do_writev(acb->child, acb->req.sector, - acb->req.nb_sectors, acb->req.qiov, acb->req.flags); + acb->req.error = bdrv_co_pwritev(acb->child, acb->req.offset, + acb->req.qiov->size, acb->req.qiov, acb->req.flags); } bdrv_co_complete(acb); } -static BlockAIOCB *bdrv_co_aio_rw_vector(BdrvChild *child, - int64_t sector_num, - QEMUIOVector *qiov, - int nb_sectors, - BdrvRequestFlags flags, - BlockCompletionFunc *cb, - void *opaque, - bool is_write) +static BlockAIOCB *bdrv_co_aio_prw_vector(BdrvChild *child, + int64_t offset, + QEMUIOVector *qiov, + BdrvRequestFlags flags, + BlockCompletionFunc *cb, + void *opaque, + bool is_write) { Coroutine *co; BlockAIOCBCoroutine *acb; @@ -2109,8 +2153,7 @@ static BlockAIOCB *bdrv_co_aio_rw_vector(BdrvChild *child, acb->child = child; acb->need_bh = true; acb->req.error = -EINPROGRESS; - acb->req.sector = sector_num; - acb->req.nb_sectors = nb_sectors; + acb->req.offset = offset; acb->req.qiov = qiov; acb->req.flags = flags; acb->is_write = is_write; @@ -2150,30 +2193,29 @@ BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs, return &acb->common; } -static void coroutine_fn bdrv_aio_discard_co_entry(void *opaque) +static void coroutine_fn bdrv_aio_pdiscard_co_entry(void *opaque) { BlockAIOCBCoroutine *acb = opaque; BlockDriverState *bs = acb->common.bs; - acb->req.error = bdrv_co_discard(bs, acb->req.sector, acb->req.nb_sectors); + acb->req.error = bdrv_co_pdiscard(bs, acb->req.offset, acb->req.bytes); bdrv_co_complete(acb); } -BlockAIOCB *bdrv_aio_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, - BlockCompletionFunc *cb, void *opaque) +BlockAIOCB *bdrv_aio_pdiscard(BlockDriverState *bs, int64_t offset, int count, + BlockCompletionFunc *cb, void *opaque) { Coroutine *co; BlockAIOCBCoroutine *acb; - trace_bdrv_aio_discard(bs, sector_num, nb_sectors, opaque); + trace_bdrv_aio_pdiscard(bs, offset, count, opaque); acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque); acb->need_bh = true; acb->req.error = -EINPROGRESS; - acb->req.sector = sector_num; - acb->req.nb_sectors = nb_sectors; - co = qemu_coroutine_create(bdrv_aio_discard_co_entry, acb); + acb->req.offset = offset; + acb->req.bytes = count; + co = qemu_coroutine_create(bdrv_aio_pdiscard_co_entry, acb); qemu_coroutine_enter(co); bdrv_co_maybe_schedule_bh(acb); @@ -2346,28 +2388,29 @@ int bdrv_flush(BlockDriverState *bs) typedef struct DiscardCo { BlockDriverState *bs; - int64_t sector_num; - int nb_sectors; + int64_t offset; + int count; int ret; } DiscardCo; -static void coroutine_fn bdrv_discard_co_entry(void *opaque) +static void coroutine_fn bdrv_pdiscard_co_entry(void *opaque) { DiscardCo *rwco = opaque; - rwco->ret = bdrv_co_discard(rwco->bs, rwco->sector_num, rwco->nb_sectors); + rwco->ret = bdrv_co_pdiscard(rwco->bs, rwco->offset, rwco->count); } -int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, - int nb_sectors) +int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset, + int count) { BdrvTrackedRequest req; - int max_discard, ret; + int max_pdiscard, ret; + int head, align; if (!bs->drv) { return -ENOMEDIUM; } - ret = bdrv_check_request(bs, sector_num, nb_sectors); + ret = bdrv_check_byte_request(bs, offset, count); if (ret < 0) { return ret; } else if (bs->read_only) { @@ -2380,50 +2423,47 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, return 0; } - if (!bs->drv->bdrv_co_discard && !bs->drv->bdrv_aio_discard) { + if (!bs->drv->bdrv_co_pdiscard && !bs->drv->bdrv_aio_pdiscard) { + return 0; + } + + /* Discard is advisory, so ignore any unaligned head or tail */ + align = MAX(bs->bl.pdiscard_alignment, bs->bl.request_alignment); + assert(is_power_of_2(align)); + head = MIN(count, -offset & (align - 1)); + if (head) { + count -= head; + offset += head; + } + count = QEMU_ALIGN_DOWN(count, align); + if (!count) { return 0; } - tracked_request_begin(&req, bs, sector_num << BDRV_SECTOR_BITS, - nb_sectors << BDRV_SECTOR_BITS, BDRV_TRACKED_DISCARD); + tracked_request_begin(&req, bs, offset, count, BDRV_TRACKED_DISCARD); ret = notifier_with_return_list_notify(&bs->before_write_notifiers, &req); if (ret < 0) { goto out; } - max_discard = MIN_NON_ZERO(bs->bl.max_pdiscard >> BDRV_SECTOR_BITS, - BDRV_REQUEST_MAX_SECTORS); - while (nb_sectors > 0) { - int ret; - int num = nb_sectors; - int discard_alignment = bs->bl.pdiscard_alignment >> BDRV_SECTOR_BITS; - - /* align request */ - if (discard_alignment && - num >= discard_alignment && - sector_num % discard_alignment) { - if (num > discard_alignment) { - num = discard_alignment; - } - num -= sector_num % discard_alignment; - } + max_pdiscard = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_pdiscard, INT_MAX), + align); - /* limit request size */ - if (num > max_discard) { - num = max_discard; - } + while (count > 0) { + int ret; + int num = MIN(count, max_pdiscard); - if (bs->drv->bdrv_co_discard) { - ret = bs->drv->bdrv_co_discard(bs, sector_num, num); + if (bs->drv->bdrv_co_pdiscard) { + ret = bs->drv->bdrv_co_pdiscard(bs, offset, num); } else { BlockAIOCB *acb; CoroutineIOCompletion co = { .coroutine = qemu_coroutine_self(), }; - acb = bs->drv->bdrv_aio_discard(bs, sector_num, nb_sectors, - bdrv_co_io_em_complete, &co); + acb = bs->drv->bdrv_aio_pdiscard(bs, offset, num, + bdrv_co_io_em_complete, &co); if (acb == NULL) { ret = -EIO; goto out; @@ -2436,8 +2476,8 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, goto out; } - sector_num += num; - nb_sectors -= num; + offset += num; + count -= num; } ret = 0; out: @@ -2448,23 +2488,23 @@ out: return ret; } -int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors) +int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count) { Coroutine *co; DiscardCo rwco = { .bs = bs, - .sector_num = sector_num, - .nb_sectors = nb_sectors, + .offset = offset, + .count = count, .ret = NOT_DONE, }; if (qemu_in_coroutine()) { /* Fast-path if already in coroutine context */ - bdrv_discard_co_entry(&rwco); + bdrv_pdiscard_co_entry(&rwco); } else { AioContext *aio_context = bdrv_get_aio_context(bs); - co = qemu_coroutine_create(bdrv_discard_co_entry, &rwco); + co = qemu_coroutine_create(bdrv_pdiscard_co_entry, &rwco); qemu_coroutine_enter(co); while (rwco.ret == NOT_DONE) { aio_poll(aio_context, true); diff --git a/block/iscsi.c b/block/iscsi.c index 129c3afa68..95ce9e139e 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -586,11 +586,8 @@ iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors, return -EINVAL; } - if (bs->bl.max_transfer && - nb_sectors << BDRV_SECTOR_BITS > bs->bl.max_transfer) { - error_report("iSCSI Error: Write of %d sectors exceeds max_xfer_len " - "of %" PRIu32 " bytes", nb_sectors, bs->bl.max_transfer); - return -EINVAL; + if (bs->bl.max_transfer) { + assert(nb_sectors << BDRV_SECTOR_BITS <= bs->bl.max_transfer); } lba = sector_qemu2lun(sector_num, iscsilun); @@ -754,11 +751,8 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs, return -EINVAL; } - if (bs->bl.max_transfer && - nb_sectors << BDRV_SECTOR_BITS > bs->bl.max_transfer) { - error_report("iSCSI Error: Read of %d sectors exceeds max_xfer_len " - "of %" PRIu32 " bytes", nb_sectors, bs->bl.max_transfer); - return -EINVAL; + if (bs->bl.max_transfer) { + assert(nb_sectors << BDRV_SECTOR_BITS <= bs->bl.max_transfer); } /* if cache.direct is off and we have a valid entry in our allocation map @@ -1048,29 +1042,26 @@ iscsi_getlength(BlockDriverState *bs) } static int -coroutine_fn iscsi_co_discard(BlockDriverState *bs, int64_t sector_num, - int nb_sectors) +coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count) { IscsiLun *iscsilun = bs->opaque; struct IscsiTask iTask; struct unmap_list list; - if (!is_sector_request_lun_aligned(sector_num, nb_sectors, iscsilun)) { - return -EINVAL; - } + assert(is_byte_request_lun_aligned(offset, count, iscsilun)); if (!iscsilun->lbp.lbpu) { /* UNMAP is not supported by the target */ return 0; } - list.lba = sector_qemu2lun(sector_num, iscsilun); - list.num = sector_qemu2lun(nb_sectors, iscsilun); + list.lba = offset / iscsilun->block_size; + list.num = count / iscsilun->block_size; iscsi_co_init_iscsitask(iscsilun, &iTask); retry: if (iscsi_unmap_task(iscsilun->iscsi, iscsilun->lun, 0, 0, &list, 1, - iscsi_co_generic_cb, &iTask) == NULL) { + iscsi_co_generic_cb, &iTask) == NULL) { return -ENOMEM; } @@ -1100,7 +1091,8 @@ retry: return iTask.err_code; } - iscsi_allocmap_set_invalid(iscsilun, sector_num, nb_sectors); + iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS, + count >> BDRV_SECTOR_BITS); return 0; } @@ -2004,7 +1996,7 @@ static BlockDriver bdrv_iscsi = { .bdrv_refresh_limits = iscsi_refresh_limits, .bdrv_co_get_block_status = iscsi_co_get_block_status, - .bdrv_co_discard = iscsi_co_discard, + .bdrv_co_pdiscard = iscsi_co_pdiscard, .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes, .bdrv_co_readv = iscsi_co_readv, .bdrv_co_writev_flags = iscsi_co_writev_flags, diff --git a/block/mirror.c b/block/mirror.c index 9ae11e5276..69a1a7cc96 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -58,9 +58,10 @@ typedef struct MirrorBlockJob { QSIMPLEQ_HEAD(, MirrorBuffer) buf_free; int buf_free_count; + uint64_t last_pause_ns; unsigned long *in_flight_bitmap; int in_flight; - int sectors_in_flight; + int64_t sectors_in_flight; int ret; bool unmap; bool waiting_for_io; @@ -303,8 +304,9 @@ static void mirror_do_zero_or_discard(MirrorBlockJob *s, s->in_flight++; s->sectors_in_flight += nb_sectors; if (is_discard) { - blk_aio_discard(s->target, sector_num, op->nb_sectors, - mirror_write_complete, op); + blk_aio_pdiscard(s->target, sector_num << BDRV_SECTOR_BITS, + op->nb_sectors << BDRV_SECTOR_BITS, + mirror_write_complete, op); } else { blk_aio_pwrite_zeroes(s->target, sector_num * BDRV_SECTOR_SIZE, op->nb_sectors * BDRV_SECTOR_SIZE, @@ -322,6 +324,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) int nb_chunks = 1; int64_t end = s->bdev_length / BDRV_SECTOR_SIZE; int sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS; + bool write_zeroes_ok = bdrv_can_write_zeroes_with_unmap(blk_bs(s->target)); sector_num = hbitmap_iter_next(&s->hbi); if (sector_num < 0) { @@ -372,7 +375,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) bitmap_set(s->in_flight_bitmap, sector_num / sectors_per_chunk, nb_chunks); while (nb_chunks > 0 && sector_num < end) { int ret; - int io_sectors; + int io_sectors, io_sectors_acct; BlockDriverState *file; enum MirrorMethod { MIRROR_METHOD_COPY, @@ -405,16 +408,26 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) } } + while (s->in_flight >= MAX_IN_FLIGHT) { + trace_mirror_yield_in_flight(s, sector_num, s->in_flight); + mirror_wait_for_io(s); + } + mirror_clip_sectors(s, sector_num, &io_sectors); switch (mirror_method) { case MIRROR_METHOD_COPY: io_sectors = mirror_do_read(s, sector_num, io_sectors); + io_sectors_acct = io_sectors; break; case MIRROR_METHOD_ZERO: - mirror_do_zero_or_discard(s, sector_num, io_sectors, false); - break; case MIRROR_METHOD_DISCARD: - mirror_do_zero_or_discard(s, sector_num, io_sectors, true); + mirror_do_zero_or_discard(s, sector_num, io_sectors, + mirror_method == MIRROR_METHOD_DISCARD); + if (write_zeroes_ok) { + io_sectors_acct = 0; + } else { + io_sectors_acct = io_sectors; + } break; default: abort(); @@ -423,7 +436,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) sector_num += io_sectors; nb_chunks -= DIV_ROUND_UP(io_sectors, sectors_per_chunk); if (s->common.speed) { - delay_ns = ratelimit_calculate_delay(&s->limit, io_sectors); + delay_ns = ratelimit_calculate_delay(&s->limit, io_sectors_acct); } } return delay_ns; @@ -511,19 +524,94 @@ static void mirror_exit(BlockJob *job, void *opaque) bdrv_unref(src); } +static void mirror_throttle(MirrorBlockJob *s) +{ + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); + + if (now - s->last_pause_ns > SLICE_TIME) { + s->last_pause_ns = now; + block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0); + } else { + block_job_pause_point(&s->common); + } +} + +static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) +{ + int64_t sector_num, end; + BlockDriverState *base = s->base; + BlockDriverState *bs = blk_bs(s->common.blk); + BlockDriverState *target_bs = blk_bs(s->target); + int ret, n; + + end = s->bdev_length / BDRV_SECTOR_SIZE; + + if (base == NULL && !bdrv_has_zero_init(target_bs)) { + if (!bdrv_can_write_zeroes_with_unmap(target_bs)) { + bdrv_set_dirty_bitmap(s->dirty_bitmap, 0, end); + return 0; + } + + for (sector_num = 0; sector_num < end; ) { + int nb_sectors = MIN(end - sector_num, + QEMU_ALIGN_DOWN(INT_MAX, s->granularity) >> BDRV_SECTOR_BITS); + + mirror_throttle(s); + + if (block_job_is_cancelled(&s->common)) { + return 0; + } + + if (s->in_flight >= MAX_IN_FLIGHT) { + trace_mirror_yield(s, s->in_flight, s->buf_free_count, -1); + mirror_wait_for_io(s); + continue; + } + + mirror_do_zero_or_discard(s, sector_num, nb_sectors, false); + sector_num += nb_sectors; + } + + mirror_drain(s); + } + + /* First part, loop on the sectors and initialize the dirty bitmap. */ + for (sector_num = 0; sector_num < end; ) { + /* Just to make sure we are not exceeding int limit. */ + int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS, + end - sector_num); + + mirror_throttle(s); + + if (block_job_is_cancelled(&s->common)) { + return 0; + } + + ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n); + if (ret < 0) { + return ret; + } + + assert(n > 0); + if (ret == 1) { + bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n); + } + sector_num += n; + } + return 0; +} + static void coroutine_fn mirror_run(void *opaque) { MirrorBlockJob *s = opaque; MirrorExitData *data; BlockDriverState *bs = blk_bs(s->common.blk); BlockDriverState *target_bs = blk_bs(s->target); - int64_t sector_num, end, length; - uint64_t last_pause_ns; + int64_t length; BlockDriverInfo bdi; char backing_filename[2]; /* we only need 2 characters because we are only checking for a NULL string */ int ret = 0; - int n; int target_cluster_size = BDRV_SECTOR_SIZE; if (block_job_is_cancelled(&s->common)) { @@ -565,7 +653,6 @@ static void coroutine_fn mirror_run(void *opaque) s->target_cluster_sectors = target_cluster_size >> BDRV_SECTOR_BITS; s->max_iov = MIN(bs->bl.max_iov, target_bs->bl.max_iov); - end = s->bdev_length / BDRV_SECTOR_SIZE; s->buf = qemu_try_blockalign(bs, s->buf_size); if (s->buf == NULL) { ret = -ENOMEM; @@ -574,47 +661,18 @@ static void coroutine_fn mirror_run(void *opaque) mirror_free_init(s); - last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); + s->last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); if (!s->is_none_mode) { - /* First part, loop on the sectors and initialize the dirty bitmap. */ - BlockDriverState *base = s->base; - bool mark_all_dirty = s->base == NULL && !bdrv_has_zero_init(target_bs); - - for (sector_num = 0; sector_num < end; ) { - /* Just to make sure we are not exceeding int limit. */ - int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS, - end - sector_num); - int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); - - if (now - last_pause_ns > SLICE_TIME) { - last_pause_ns = now; - block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0); - } else { - block_job_pause_point(&s->common); - } - - if (block_job_is_cancelled(&s->common)) { - goto immediate_exit; - } - - ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n); - - if (ret < 0) { - goto immediate_exit; - } - - assert(n > 0); - if (ret == 1 || mark_all_dirty) { - bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n); - } - sector_num += n; + ret = mirror_dirty_init(s); + if (ret < 0 || block_job_is_cancelled(&s->common)) { + goto immediate_exit; } } bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi); for (;;) { uint64_t delay_ns = 0; - int64_t cnt; + int64_t cnt, delta; bool should_complete; if (s->ret < 0) { @@ -637,9 +695,10 @@ static void coroutine_fn mirror_run(void *opaque) * We do so every SLICE_TIME nanoseconds, or when there is an error, * or when the source is clean, whichever comes first. */ - if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - last_pause_ns < SLICE_TIME && + delta = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - s->last_pause_ns; + if (delta < SLICE_TIME && s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) { - if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 || + if (s->in_flight >= MAX_IN_FLIGHT || s->buf_free_count == 0 || (cnt == 0 && s->in_flight > 0)) { trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt); mirror_wait_for_io(s); @@ -707,7 +766,7 @@ static void coroutine_fn mirror_run(void *opaque) s->common.cancelled = false; break; } - last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); + s->last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); } immediate_exit: diff --git a/block/nbd-client.c b/block/nbd-client.c index 4cc408d206..2cf3237ef3 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -116,7 +116,7 @@ static void nbd_restart_write(void *opaque) static int nbd_co_send_request(BlockDriverState *bs, struct nbd_request *request, - QEMUIOVector *qiov, int offset) + QEMUIOVector *qiov) { NbdClientSession *s = nbd_get_client_session(bs); AioContext *aio_context; @@ -149,8 +149,8 @@ static int nbd_co_send_request(BlockDriverState *bs, qio_channel_set_cork(s->ioc, true); rc = nbd_send_request(s->ioc, request); if (rc >= 0) { - ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov, - offset, request->len, 0); + ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov, request->len, + false); if (ret != request->len) { rc = -EIO; } @@ -167,8 +167,9 @@ static int nbd_co_send_request(BlockDriverState *bs, } static void nbd_co_receive_reply(NbdClientSession *s, - struct nbd_request *request, struct nbd_reply *reply, - QEMUIOVector *qiov, int offset) + struct nbd_request *request, + struct nbd_reply *reply, + QEMUIOVector *qiov) { int ret; @@ -181,8 +182,8 @@ static void nbd_co_receive_reply(NbdClientSession *s, reply->error = EIO; } else { if (qiov && reply->error == 0) { - ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov, - offset, request->len, 1); + ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov, request->len, + true); if (ret != request->len) { reply->error = EIO; } @@ -217,36 +218,41 @@ static void nbd_coroutine_end(NbdClientSession *s, } } -static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov, - int offset) +int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, int flags) { NbdClientSession *client = nbd_get_client_session(bs); - struct nbd_request request = { .type = NBD_CMD_READ }; + struct nbd_request request = { + .type = NBD_CMD_READ, + .from = offset, + .len = bytes, + }; struct nbd_reply reply; ssize_t ret; - request.from = sector_num * 512; - request.len = nb_sectors * 512; + assert(bytes <= NBD_MAX_BUFFER_SIZE); + assert(!flags); nbd_coroutine_start(client, &request); - ret = nbd_co_send_request(bs, &request, NULL, 0); + ret = nbd_co_send_request(bs, &request, NULL); if (ret < 0) { reply.error = -ret; } else { - nbd_co_receive_reply(client, &request, &reply, qiov, offset); + nbd_co_receive_reply(client, &request, &reply, qiov); } nbd_coroutine_end(client, &request); return -reply.error; - } -static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov, - int offset, int flags) +int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, int flags) { NbdClientSession *client = nbd_get_client_session(bs); - struct nbd_request request = { .type = NBD_CMD_WRITE }; + struct nbd_request request = { + .type = NBD_CMD_WRITE, + .from = offset, + .len = bytes, + }; struct nbd_reply reply; ssize_t ret; @@ -255,55 +261,19 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num, request.type |= NBD_CMD_FLAG_FUA; } - request.from = sector_num * 512; - request.len = nb_sectors * 512; + assert(bytes <= NBD_MAX_BUFFER_SIZE); nbd_coroutine_start(client, &request); - ret = nbd_co_send_request(bs, &request, qiov, offset); + ret = nbd_co_send_request(bs, &request, qiov); if (ret < 0) { reply.error = -ret; } else { - nbd_co_receive_reply(client, &request, &reply, NULL, 0); + nbd_co_receive_reply(client, &request, &reply, NULL); } nbd_coroutine_end(client, &request); return -reply.error; } -int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov) -{ - int offset = 0; - int ret; - while (nb_sectors > NBD_MAX_SECTORS) { - ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset); - if (ret < 0) { - return ret; - } - offset += NBD_MAX_SECTORS * 512; - sector_num += NBD_MAX_SECTORS; - nb_sectors -= NBD_MAX_SECTORS; - } - return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset); -} - -int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov, int flags) -{ - int offset = 0; - int ret; - while (nb_sectors > NBD_MAX_SECTORS) { - ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset, - flags); - if (ret < 0) { - return ret; - } - offset += NBD_MAX_SECTORS * 512; - sector_num += NBD_MAX_SECTORS; - nb_sectors -= NBD_MAX_SECTORS; - } - return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset, flags); -} - int nbd_client_co_flush(BlockDriverState *bs) { NbdClientSession *client = nbd_get_client_session(bs); @@ -319,36 +289,37 @@ int nbd_client_co_flush(BlockDriverState *bs) request.len = 0; nbd_coroutine_start(client, &request); - ret = nbd_co_send_request(bs, &request, NULL, 0); + ret = nbd_co_send_request(bs, &request, NULL); if (ret < 0) { reply.error = -ret; } else { - nbd_co_receive_reply(client, &request, &reply, NULL, 0); + nbd_co_receive_reply(client, &request, &reply, NULL); } nbd_coroutine_end(client, &request); return -reply.error; } -int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num, - int nb_sectors) +int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count) { NbdClientSession *client = nbd_get_client_session(bs); - struct nbd_request request = { .type = NBD_CMD_TRIM }; + struct nbd_request request = { + .type = NBD_CMD_TRIM, + .from = offset, + .len = count, + }; struct nbd_reply reply; ssize_t ret; if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) { return 0; } - request.from = sector_num * 512; - request.len = nb_sectors * 512; nbd_coroutine_start(client, &request); - ret = nbd_co_send_request(bs, &request, NULL, 0); + ret = nbd_co_send_request(bs, &request, NULL); if (ret < 0) { reply.error = -ret; } else { - nbd_co_receive_reply(client, &request, &reply, NULL, 0); + nbd_co_receive_reply(client, &request, &reply, NULL); } nbd_coroutine_end(client, &request); return -reply.error; diff --git a/block/nbd-client.h b/block/nbd-client.h index c618dadc39..fa9817b7d7 100644 --- a/block/nbd-client.h +++ b/block/nbd-client.h @@ -44,13 +44,12 @@ int nbd_client_init(BlockDriverState *bs, Error **errp); void nbd_client_close(BlockDriverState *bs); -int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num, - int nb_sectors); +int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count); int nbd_client_co_flush(BlockDriverState *bs); -int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov, int flags); -int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov); +int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, int flags); +int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, int flags); void nbd_client_detach_aio_context(BlockDriverState *bs); void nbd_client_attach_aio_context(BlockDriverState *bs, diff --git a/block/nbd.c b/block/nbd.c index 08e5b67b2f..8d57220f18 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -349,12 +349,6 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags, return ret; } -static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov) -{ - return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov); -} - static int nbd_co_flush(BlockDriverState *bs) { return nbd_client_co_flush(bs); @@ -366,12 +360,6 @@ static void nbd_refresh_limits(BlockDriverState *bs, Error **errp) bs->bl.max_transfer = NBD_MAX_BUFFER_SIZE; } -static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num, - int nb_sectors) -{ - return nbd_client_co_discard(bs, sector_num, nb_sectors); -} - static void nbd_close(BlockDriverState *bs) { nbd_client_close(bs); @@ -450,11 +438,11 @@ static BlockDriver bdrv_nbd = { .instance_size = sizeof(BDRVNBDState), .bdrv_parse_filename = nbd_parse_filename, .bdrv_file_open = nbd_open, - .bdrv_co_readv = nbd_co_readv, - .bdrv_co_writev_flags = nbd_client_co_writev, + .bdrv_co_preadv = nbd_client_co_preadv, + .bdrv_co_pwritev = nbd_client_co_pwritev, .bdrv_close = nbd_close, .bdrv_co_flush_to_os = nbd_co_flush, - .bdrv_co_discard = nbd_co_discard, + .bdrv_co_pdiscard = nbd_client_co_pdiscard, .bdrv_refresh_limits = nbd_refresh_limits, .bdrv_getlength = nbd_getlength, .bdrv_detach_aio_context = nbd_detach_aio_context, @@ -468,11 +456,11 @@ static BlockDriver bdrv_nbd_tcp = { .instance_size = sizeof(BDRVNBDState), .bdrv_parse_filename = nbd_parse_filename, .bdrv_file_open = nbd_open, - .bdrv_co_readv = nbd_co_readv, - .bdrv_co_writev_flags = nbd_client_co_writev, + .bdrv_co_preadv = nbd_client_co_preadv, + .bdrv_co_pwritev = nbd_client_co_pwritev, .bdrv_close = nbd_close, .bdrv_co_flush_to_os = nbd_co_flush, - .bdrv_co_discard = nbd_co_discard, + .bdrv_co_pdiscard = nbd_client_co_pdiscard, .bdrv_refresh_limits = nbd_refresh_limits, .bdrv_getlength = nbd_getlength, .bdrv_detach_aio_context = nbd_detach_aio_context, @@ -486,11 +474,11 @@ static BlockDriver bdrv_nbd_unix = { .instance_size = sizeof(BDRVNBDState), .bdrv_parse_filename = nbd_parse_filename, .bdrv_file_open = nbd_open, - .bdrv_co_readv = nbd_co_readv, - .bdrv_co_writev_flags = nbd_client_co_writev, + .bdrv_co_preadv = nbd_client_co_preadv, + .bdrv_co_pwritev = nbd_client_co_pwritev, .bdrv_close = nbd_close, .bdrv_co_flush_to_os = nbd_co_flush, - .bdrv_co_discard = nbd_co_discard, + .bdrv_co_pdiscard = nbd_client_co_pdiscard, .bdrv_refresh_limits = nbd_refresh_limits, .bdrv_getlength = nbd_getlength, .bdrv_detach_aio_context = nbd_detach_aio_context, diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index 49b6ce6bfd..cbfb3fe064 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -615,9 +615,7 @@ void qcow2_process_discards(BlockDriverState *bs, int ret) /* Discard is optional, ignore the return value */ if (ret >= 0) { - bdrv_discard(bs->file->bs, - d->offset >> BDRV_SECTOR_BITS, - d->bytes >> BDRV_SECTOR_BITS); + bdrv_pdiscard(bs->file->bs, d->offset, d->bytes); } g_free(d); diff --git a/block/qcow2.c b/block/qcow2.c index a6bca735e5..d620d0a85b 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2479,15 +2479,15 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, return ret; } -static coroutine_fn int qcow2_co_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors) +static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs, + int64_t offset, int count) { int ret; BDRVQcow2State *s = bs->opaque; qemu_co_mutex_lock(&s->lock); - ret = qcow2_discard_clusters(bs, sector_num << BDRV_SECTOR_BITS, - nb_sectors, QCOW2_DISCARD_REQUEST, false); + ret = qcow2_discard_clusters(bs, offset, count >> BDRV_SECTOR_BITS, + QCOW2_DISCARD_REQUEST, false); qemu_co_mutex_unlock(&s->lock); return ret; } @@ -3410,7 +3410,7 @@ BlockDriver bdrv_qcow2 = { .bdrv_co_flush_to_os = qcow2_co_flush_to_os, .bdrv_co_pwrite_zeroes = qcow2_co_pwrite_zeroes, - .bdrv_co_discard = qcow2_co_discard, + .bdrv_co_pdiscard = qcow2_co_pdiscard, .bdrv_truncate = qcow2_truncate, .bdrv_write_compressed = qcow2_write_compressed, .bdrv_make_empty = qcow2_make_empty, diff --git a/block/raw-posix.c b/block/raw-posix.c index 20f4d7aa8d..6ed7547392 100644 --- a/block/raw-posix.c +++ b/block/raw-posix.c @@ -1214,7 +1214,7 @@ static int paio_submit_co(BlockDriverState *bs, int fd, } static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd, - int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, + int64_t offset, QEMUIOVector *qiov, int count, BlockCompletionFunc *cb, void *opaque, int type) { RawPosixAIOData *acb = g_new(RawPosixAIOData, 1); @@ -1224,8 +1224,8 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd, acb->aio_type = type; acb->aio_fildes = fd; - acb->aio_nbytes = nb_sectors * BDRV_SECTOR_SIZE; - acb->aio_offset = sector_num * BDRV_SECTOR_SIZE; + acb->aio_nbytes = count; + acb->aio_offset = offset; if (qiov) { acb->aio_iov = qiov->iov; @@ -1233,7 +1233,7 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd, assert(qiov->size == acb->aio_nbytes); } - trace_paio_submit(acb, opaque, sector_num, nb_sectors, type); + trace_paio_submit(acb, opaque, offset, count, type); pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque); } @@ -1786,13 +1786,13 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs, return ret | BDRV_BLOCK_OFFSET_VALID | start; } -static coroutine_fn BlockAIOCB *raw_aio_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, +static coroutine_fn BlockAIOCB *raw_aio_pdiscard(BlockDriverState *bs, + int64_t offset, int count, BlockCompletionFunc *cb, void *opaque) { BDRVRawState *s = bs->opaque; - return paio_submit(bs, s->fd, sector_num, NULL, nb_sectors, + return paio_submit(bs, s->fd, offset, NULL, count, cb, opaque, QEMU_AIO_DISCARD); } @@ -1864,7 +1864,7 @@ BlockDriver bdrv_file = { .bdrv_co_preadv = raw_co_preadv, .bdrv_co_pwritev = raw_co_pwritev, .bdrv_aio_flush = raw_aio_flush, - .bdrv_aio_discard = raw_aio_discard, + .bdrv_aio_pdiscard = raw_aio_pdiscard, .bdrv_refresh_limits = raw_refresh_limits, .bdrv_io_plug = raw_aio_plug, .bdrv_io_unplug = raw_aio_unplug, @@ -2203,8 +2203,8 @@ static int fd_open(BlockDriverState *bs) return -EIO; } -static coroutine_fn BlockAIOCB *hdev_aio_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, +static coroutine_fn BlockAIOCB *hdev_aio_pdiscard(BlockDriverState *bs, + int64_t offset, int count, BlockCompletionFunc *cb, void *opaque) { BDRVRawState *s = bs->opaque; @@ -2212,7 +2212,7 @@ static coroutine_fn BlockAIOCB *hdev_aio_discard(BlockDriverState *bs, if (fd_open(bs) < 0) { return NULL; } - return paio_submit(bs, s->fd, sector_num, NULL, nb_sectors, + return paio_submit(bs, s->fd, offset, NULL, count, cb, opaque, QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV); } @@ -2307,7 +2307,7 @@ static BlockDriver bdrv_host_device = { .bdrv_co_preadv = raw_co_preadv, .bdrv_co_pwritev = raw_co_pwritev, .bdrv_aio_flush = raw_aio_flush, - .bdrv_aio_discard = hdev_aio_discard, + .bdrv_aio_pdiscard = hdev_aio_pdiscard, .bdrv_refresh_limits = raw_refresh_limits, .bdrv_io_plug = raw_aio_plug, .bdrv_io_unplug = raw_aio_unplug, diff --git a/block/raw-win32.c b/block/raw-win32.c index 9b813d99ae..56f45fea9e 100644 --- a/block/raw-win32.c +++ b/block/raw-win32.c @@ -142,7 +142,7 @@ static int aio_worker(void *arg) } static BlockAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile, - int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, + int64_t offset, QEMUIOVector *qiov, int count, BlockCompletionFunc *cb, void *opaque, int type) { RawWin32AIOData *acb = g_new(RawWin32AIOData, 1); @@ -155,11 +155,12 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile, if (qiov) { acb->aio_iov = qiov->iov; acb->aio_niov = qiov->niov; + assert(qiov->size == count); } - acb->aio_nbytes = nb_sectors * 512; - acb->aio_offset = sector_num * 512; + acb->aio_nbytes = count; + acb->aio_offset = offset; - trace_paio_submit(acb, opaque, sector_num, nb_sectors, type); + trace_paio_submit(acb, opaque, offset, count, type); pool = aio_get_thread_pool(bdrv_get_aio_context(bs)); return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque); } @@ -378,9 +379,10 @@ static BlockAIOCB *raw_aio_readv(BlockDriverState *bs, BDRVRawState *s = bs->opaque; if (s->aio) { return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov, - nb_sectors, cb, opaque, QEMU_AIO_READ); + nb_sectors, cb, opaque, QEMU_AIO_READ); } else { - return paio_submit(bs, s->hfile, sector_num, qiov, nb_sectors, + return paio_submit(bs, s->hfile, sector_num << BDRV_SECTOR_BITS, qiov, + nb_sectors << BDRV_SECTOR_BITS, cb, opaque, QEMU_AIO_READ); } } @@ -392,9 +394,10 @@ static BlockAIOCB *raw_aio_writev(BlockDriverState *bs, BDRVRawState *s = bs->opaque; if (s->aio) { return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov, - nb_sectors, cb, opaque, QEMU_AIO_WRITE); + nb_sectors, cb, opaque, QEMU_AIO_WRITE); } else { - return paio_submit(bs, s->hfile, sector_num, qiov, nb_sectors, + return paio_submit(bs, s->hfile, sector_num << BDRV_SECTOR_BITS, qiov, + nb_sectors << BDRV_SECTOR_BITS, cb, opaque, QEMU_AIO_WRITE); } } diff --git a/block/raw_bsd.c b/block/raw_bsd.c index 5f9dd299a6..588d4080f9 100644 --- a/block/raw_bsd.c +++ b/block/raw_bsd.c @@ -50,33 +50,30 @@ static int raw_reopen_prepare(BDRVReopenState *reopen_state, return 0; } -static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov) +static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + int flags) { BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); - return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov); + return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags); } -static int coroutine_fn -raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors, - QEMUIOVector *qiov, int flags) +static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + int flags) { void *buf = NULL; BlockDriver *drv; QEMUIOVector local_qiov; int ret; - if (bs->probed && sector_num == 0) { - /* As long as these conditions are true, we can't get partial writes to - * the probe buffer and can just directly check the request. */ + if (bs->probed && offset < BLOCK_PROBE_BUF_SIZE && bytes) { + /* Handling partial writes would be a pain - so we just + * require that guests have 512-byte request alignment if + * probing occurred */ QEMU_BUILD_BUG_ON(BLOCK_PROBE_BUF_SIZE != 512); QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != 512); - - if (nb_sectors == 0) { - /* qemu_iovec_to_buf() would fail, but we want to return success - * instead of -EINVAL in this case. */ - return 0; - } + assert(offset == 0 && bytes >= BLOCK_PROBE_BUF_SIZE); buf = qemu_try_blockalign(bs->file->bs, 512); if (!buf) { @@ -105,8 +102,7 @@ raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors, } BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); - ret = bdrv_co_pwritev(bs->file, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, qiov, flags); + ret = bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags); fail: if (qiov == &local_qiov) { @@ -134,10 +130,10 @@ static int coroutine_fn raw_co_pwrite_zeroes(BlockDriverState *bs, return bdrv_co_pwrite_zeroes(bs->file, offset, count, flags); } -static int coroutine_fn raw_co_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors) +static int coroutine_fn raw_co_pdiscard(BlockDriverState *bs, + int64_t offset, int count) { - return bdrv_co_discard(bs->file->bs, sector_num, nb_sectors); + return bdrv_co_pdiscard(bs->file->bs, offset, count); } static int64_t raw_getlength(BlockDriverState *bs) @@ -150,6 +146,16 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) return bdrv_get_info(bs->file->bs, bdi); } +static void raw_refresh_limits(BlockDriverState *bs, Error **errp) +{ + if (bs->probed) { + /* To make it easier to protect the first sector, any probed + * image is restricted to read-modify-write on sub-sector + * operations. */ + bs->bl.request_alignment = BDRV_SECTOR_SIZE; + } +} + static int raw_truncate(BlockDriverState *bs, int64_t offset) { return bdrv_truncate(bs->file->bs, offset); @@ -192,8 +198,10 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { bs->sg = bs->file->bs->sg; - bs->supported_write_flags = BDRV_REQ_FUA; - bs->supported_zero_flags = BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP; + bs->supported_write_flags = BDRV_REQ_FUA & + bs->file->bs->supported_write_flags; + bs->supported_zero_flags = (BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP) & + bs->file->bs->supported_zero_flags; if (bs->probed && !bdrv_is_read_only(bs)) { fprintf(stderr, @@ -238,15 +246,16 @@ BlockDriver bdrv_raw = { .bdrv_open = &raw_open, .bdrv_close = &raw_close, .bdrv_create = &raw_create, - .bdrv_co_readv = &raw_co_readv, - .bdrv_co_writev_flags = &raw_co_writev_flags, + .bdrv_co_preadv = &raw_co_preadv, + .bdrv_co_pwritev = &raw_co_pwritev, .bdrv_co_pwrite_zeroes = &raw_co_pwrite_zeroes, - .bdrv_co_discard = &raw_co_discard, + .bdrv_co_pdiscard = &raw_co_pdiscard, .bdrv_co_get_block_status = &raw_co_get_block_status, .bdrv_truncate = &raw_truncate, .bdrv_getlength = &raw_getlength, .has_variable_length = true, .bdrv_get_info = &raw_get_info, + .bdrv_refresh_limits = &raw_refresh_limits, .bdrv_probe_blocksizes = &raw_probe_blocksizes, .bdrv_probe_geometry = &raw_probe_geometry, .bdrv_media_changed = &raw_media_changed, diff --git a/block/rbd.c b/block/rbd.c index 0a5840d08b..0106fea45f 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -649,9 +649,9 @@ static int rbd_aio_flush_wrapper(rbd_image_t image, } static BlockAIOCB *rbd_start_aio(BlockDriverState *bs, - int64_t sector_num, + int64_t off, QEMUIOVector *qiov, - int nb_sectors, + int64_t size, BlockCompletionFunc *cb, void *opaque, RBDAIOCmd cmd) @@ -659,7 +659,6 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs, RBDAIOCB *acb; RADOSCB *rcb = NULL; rbd_completion_t c; - int64_t off, size; char *buf; int r; @@ -668,6 +667,7 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs, acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque); acb->cmd = cmd; acb->qiov = qiov; + assert(!qiov || qiov->size == size); if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) { acb->bounce = NULL; } else { @@ -687,9 +687,6 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs, buf = acb->bounce; - off = sector_num * BDRV_SECTOR_SIZE; - size = nb_sectors * BDRV_SECTOR_SIZE; - rcb = g_new(RADOSCB, 1); rcb->acb = acb; rcb->buf = buf; @@ -739,7 +736,8 @@ static BlockAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque) { - return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque, + return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov, + nb_sectors << BDRV_SECTOR_BITS, cb, opaque, RBD_AIO_READ); } @@ -750,7 +748,8 @@ static BlockAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque) { - return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque, + return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov, + nb_sectors << BDRV_SECTOR_BITS, cb, opaque, RBD_AIO_WRITE); } @@ -931,13 +930,13 @@ static int qemu_rbd_snap_list(BlockDriverState *bs, } #ifdef LIBRBD_SUPPORTS_DISCARD -static BlockAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs, - int64_t sector_num, - int nb_sectors, - BlockCompletionFunc *cb, - void *opaque) +static BlockAIOCB *qemu_rbd_aio_pdiscard(BlockDriverState *bs, + int64_t offset, + int count, + BlockCompletionFunc *cb, + void *opaque) { - return rbd_start_aio(bs, sector_num, NULL, nb_sectors, cb, opaque, + return rbd_start_aio(bs, offset, NULL, count, cb, opaque, RBD_AIO_DISCARD); } #endif @@ -1001,7 +1000,7 @@ static BlockDriver bdrv_rbd = { #endif #ifdef LIBRBD_SUPPORTS_DISCARD - .bdrv_aio_discard = qemu_rbd_aio_discard, + .bdrv_aio_pdiscard = qemu_rbd_aio_pdiscard, #endif .bdrv_snapshot_create = qemu_rbd_snap_create, diff --git a/block/sheepdog.c b/block/sheepdog.c index e739c56f08..66e1cb2b2d 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -2800,8 +2800,8 @@ static int sd_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, } -static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num, - int nb_sectors) +static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset, + int count) { SheepdogAIOCB *acb; BDRVSheepdogState *s = bs->opaque; @@ -2811,7 +2811,7 @@ static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num, uint32_t zero = 0; if (!s->discard_supported) { - return 0; + return 0; } memset(&discard_iov, 0, sizeof(discard_iov)); @@ -2820,7 +2820,10 @@ static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num, iov.iov_len = sizeof(zero); discard_iov.iov = &iov; discard_iov.niov = 1; - acb = sd_aio_setup(bs, &discard_iov, sector_num, nb_sectors); + assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0); + assert((count & (BDRV_SECTOR_SIZE - 1)) == 0); + acb = sd_aio_setup(bs, &discard_iov, offset >> BDRV_SECTOR_BITS, + count >> BDRV_SECTOR_BITS); acb->aiocb_type = AIOCB_DISCARD_OBJ; acb->aio_done_func = sd_finish_aiocb; @@ -2954,7 +2957,7 @@ static BlockDriver bdrv_sheepdog = { .bdrv_co_readv = sd_co_readv, .bdrv_co_writev = sd_co_writev, .bdrv_co_flush_to_disk = sd_co_flush_to_disk, - .bdrv_co_discard = sd_co_discard, + .bdrv_co_pdiscard = sd_co_pdiscard, .bdrv_co_get_block_status = sd_co_get_block_status, .bdrv_snapshot_create = sd_snapshot_create, @@ -2990,7 +2993,7 @@ static BlockDriver bdrv_sheepdog_tcp = { .bdrv_co_readv = sd_co_readv, .bdrv_co_writev = sd_co_writev, .bdrv_co_flush_to_disk = sd_co_flush_to_disk, - .bdrv_co_discard = sd_co_discard, + .bdrv_co_pdiscard = sd_co_pdiscard, .bdrv_co_get_block_status = sd_co_get_block_status, .bdrv_snapshot_create = sd_snapshot_create, @@ -3026,7 +3029,7 @@ static BlockDriver bdrv_sheepdog_unix = { .bdrv_co_readv = sd_co_readv, .bdrv_co_writev = sd_co_writev, .bdrv_co_flush_to_disk = sd_co_flush_to_disk, - .bdrv_co_discard = sd_co_discard, + .bdrv_co_pdiscard = sd_co_pdiscard, .bdrv_co_get_block_status = sd_co_get_block_status, .bdrv_snapshot_create = sd_snapshot_create, diff --git a/block/trace-events b/block/trace-events index 354967eacb..978ef4f02a 100644 --- a/block/trace-events +++ b/block/trace-events @@ -9,7 +9,7 @@ blk_co_preadv(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags blk_co_pwritev(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags) "blk %p bs %p offset %"PRId64" bytes %u flags %x" # block/io.c -bdrv_aio_discard(void *bs, int64_t sector_num, int nb_sectors, void *opaque) "bs %p sector_num %"PRId64" nb_sectors %d opaque %p" +bdrv_aio_pdiscard(void *bs, int64_t offset, int count, void *opaque) "bs %p offset %"PRId64" count %d opaque %p" bdrv_aio_flush(void *bs, void *opaque) "bs %p opaque %p" bdrv_aio_readv(void *bs, int64_t sector_num, int nb_sectors, void *opaque) "bs %p sector_num %"PRId64" nb_sectors %d opaque %p" bdrv_aio_writev(void *bs, int64_t sector_num, int nb_sectors, void *opaque) "bs %p sector_num %"PRId64" nb_sectors %d opaque %p" @@ -58,7 +58,7 @@ qmp_block_stream(void *bs, void *job) "bs %p job %p" # block/raw-win32.c # block/raw-posix.c paio_submit_co(int64_t offset, int count, int type) "offset %"PRId64" count %d type %d" -paio_submit(void *acb, void *opaque, int64_t sector_num, int nb_sectors, int type) "acb %p opaque %p sector_num %"PRId64" nb_sectors %d type %d" +paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d" # block/qcow2.c qcow2_writev_start_req(void *co, int64_t offset, int bytes) "co %p offset %" PRIx64 " bytes %d" diff --git a/blockdev.c b/blockdev.c index 384ad3bba6..eafeba96d0 100644 --- a/blockdev.c +++ b/blockdev.c @@ -2634,49 +2634,17 @@ fail: } /* throttling disk I/O limits */ -void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd, - int64_t bps_wr, - int64_t iops, - int64_t iops_rd, - int64_t iops_wr, - bool has_bps_max, - int64_t bps_max, - bool has_bps_rd_max, - int64_t bps_rd_max, - bool has_bps_wr_max, - int64_t bps_wr_max, - bool has_iops_max, - int64_t iops_max, - bool has_iops_rd_max, - int64_t iops_rd_max, - bool has_iops_wr_max, - int64_t iops_wr_max, - bool has_bps_max_length, - int64_t bps_max_length, - bool has_bps_rd_max_length, - int64_t bps_rd_max_length, - bool has_bps_wr_max_length, - int64_t bps_wr_max_length, - bool has_iops_max_length, - int64_t iops_max_length, - bool has_iops_rd_max_length, - int64_t iops_rd_max_length, - bool has_iops_wr_max_length, - int64_t iops_wr_max_length, - bool has_iops_size, - int64_t iops_size, - bool has_group, - const char *group, Error **errp) +void qmp_block_set_io_throttle(BlockIOThrottle *arg, Error **errp) { ThrottleConfig cfg; BlockDriverState *bs; BlockBackend *blk; AioContext *aio_context; - blk = blk_by_name(device); + blk = blk_by_name(arg->device); if (!blk) { error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, - "Device '%s' not found", device); + "Device '%s' not found", arg->device); return; } @@ -2685,59 +2653,59 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd, bs = blk_bs(blk); if (!bs) { - error_setg(errp, "Device '%s' has no medium", device); + error_setg(errp, "Device '%s' has no medium", arg->device); goto out; } throttle_config_init(&cfg); - cfg.buckets[THROTTLE_BPS_TOTAL].avg = bps; - cfg.buckets[THROTTLE_BPS_READ].avg = bps_rd; - cfg.buckets[THROTTLE_BPS_WRITE].avg = bps_wr; + cfg.buckets[THROTTLE_BPS_TOTAL].avg = arg->bps; + cfg.buckets[THROTTLE_BPS_READ].avg = arg->bps_rd; + cfg.buckets[THROTTLE_BPS_WRITE].avg = arg->bps_wr; - cfg.buckets[THROTTLE_OPS_TOTAL].avg = iops; - cfg.buckets[THROTTLE_OPS_READ].avg = iops_rd; - cfg.buckets[THROTTLE_OPS_WRITE].avg = iops_wr; + cfg.buckets[THROTTLE_OPS_TOTAL].avg = arg->iops; + cfg.buckets[THROTTLE_OPS_READ].avg = arg->iops_rd; + cfg.buckets[THROTTLE_OPS_WRITE].avg = arg->iops_wr; - if (has_bps_max) { - cfg.buckets[THROTTLE_BPS_TOTAL].max = bps_max; + if (arg->has_bps_max) { + cfg.buckets[THROTTLE_BPS_TOTAL].max = arg->bps_max; } - if (has_bps_rd_max) { - cfg.buckets[THROTTLE_BPS_READ].max = bps_rd_max; + if (arg->has_bps_rd_max) { + cfg.buckets[THROTTLE_BPS_READ].max = arg->bps_rd_max; } - if (has_bps_wr_max) { - cfg.buckets[THROTTLE_BPS_WRITE].max = bps_wr_max; + if (arg->has_bps_wr_max) { + cfg.buckets[THROTTLE_BPS_WRITE].max = arg->bps_wr_max; } - if (has_iops_max) { - cfg.buckets[THROTTLE_OPS_TOTAL].max = iops_max; + if (arg->has_iops_max) { + cfg.buckets[THROTTLE_OPS_TOTAL].max = arg->iops_max; } - if (has_iops_rd_max) { - cfg.buckets[THROTTLE_OPS_READ].max = iops_rd_max; + if (arg->has_iops_rd_max) { + cfg.buckets[THROTTLE_OPS_READ].max = arg->iops_rd_max; } - if (has_iops_wr_max) { - cfg.buckets[THROTTLE_OPS_WRITE].max = iops_wr_max; + if (arg->has_iops_wr_max) { + cfg.buckets[THROTTLE_OPS_WRITE].max = arg->iops_wr_max; } - if (has_bps_max_length) { - cfg.buckets[THROTTLE_BPS_TOTAL].burst_length = bps_max_length; + if (arg->has_bps_max_length) { + cfg.buckets[THROTTLE_BPS_TOTAL].burst_length = arg->bps_max_length; } - if (has_bps_rd_max_length) { - cfg.buckets[THROTTLE_BPS_READ].burst_length = bps_rd_max_length; + if (arg->has_bps_rd_max_length) { + cfg.buckets[THROTTLE_BPS_READ].burst_length = arg->bps_rd_max_length; } - if (has_bps_wr_max_length) { - cfg.buckets[THROTTLE_BPS_WRITE].burst_length = bps_wr_max_length; + if (arg->has_bps_wr_max_length) { + cfg.buckets[THROTTLE_BPS_WRITE].burst_length = arg->bps_wr_max_length; } - if (has_iops_max_length) { - cfg.buckets[THROTTLE_OPS_TOTAL].burst_length = iops_max_length; + if (arg->has_iops_max_length) { + cfg.buckets[THROTTLE_OPS_TOTAL].burst_length = arg->iops_max_length; } - if (has_iops_rd_max_length) { - cfg.buckets[THROTTLE_OPS_READ].burst_length = iops_rd_max_length; + if (arg->has_iops_rd_max_length) { + cfg.buckets[THROTTLE_OPS_READ].burst_length = arg->iops_rd_max_length; } - if (has_iops_wr_max_length) { - cfg.buckets[THROTTLE_OPS_WRITE].burst_length = iops_wr_max_length; + if (arg->has_iops_wr_max_length) { + cfg.buckets[THROTTLE_OPS_WRITE].burst_length = arg->iops_wr_max_length; } - if (has_iops_size) { - cfg.op_size = iops_size; + if (arg->has_iops_size) { + cfg.op_size = arg->iops_size; } if (!throttle_is_valid(&cfg, errp)) { @@ -2748,9 +2716,10 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd, /* Enable I/O limits if they're not enabled yet, otherwise * just update the throttling group. */ if (!blk_get_public(blk)->throttle_state) { - blk_io_limits_enable(blk, has_group ? group : device); - } else if (has_group) { - blk_io_limits_update_group(blk, group); + blk_io_limits_enable(blk, + arg->has_group ? arg->group : arg->device); + } else if (arg->has_group) { + blk_io_limits_update_group(blk, arg->group); } /* Set the new throttling configuration */ blk_set_io_limits(blk, &cfg); @@ -3497,19 +3466,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs, block_job_cb, bs, errp); } -void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, - const char *target, bool has_format, const char *format, - bool has_node_name, const char *node_name, - bool has_replaces, const char *replaces, - enum MirrorSyncMode sync, - bool has_mode, enum NewImageMode mode, - bool has_speed, int64_t speed, - bool has_granularity, uint32_t granularity, - bool has_buf_size, int64_t buf_size, - bool has_on_source_error, BlockdevOnError on_source_error, - bool has_on_target_error, BlockdevOnError on_target_error, - bool has_unmap, bool unmap, - Error **errp) +void qmp_drive_mirror(DriveMirror *arg, Error **errp) { BlockDriverState *bs; BlockBackend *blk; @@ -3520,11 +3477,12 @@ void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, QDict *options = NULL; int flags; int64_t size; + const char *format = arg->format; - blk = blk_by_name(device); + blk = blk_by_name(arg->device); if (!blk) { error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, - "Device '%s' not found", device); + "Device '%s' not found", arg->device); return; } @@ -3532,24 +3490,25 @@ void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, aio_context_acquire(aio_context); if (!blk_is_available(blk)) { - error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, device); + error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, arg->device); goto out; } bs = blk_bs(blk); - if (!has_mode) { - mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS; + if (!arg->has_mode) { + arg->mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS; } - if (!has_format) { - format = mode == NEW_IMAGE_MODE_EXISTING ? NULL : bs->drv->format_name; + if (!arg->has_format) { + format = (arg->mode == NEW_IMAGE_MODE_EXISTING + ? NULL : bs->drv->format_name); } flags = bs->open_flags | BDRV_O_RDWR; source = backing_bs(bs); - if (!source && sync == MIRROR_SYNC_MODE_TOP) { - sync = MIRROR_SYNC_MODE_FULL; + if (!source && arg->sync == MIRROR_SYNC_MODE_TOP) { + arg->sync = MIRROR_SYNC_MODE_FULL; } - if (sync == MIRROR_SYNC_MODE_NONE) { + if (arg->sync == MIRROR_SYNC_MODE_NONE) { source = bs; } @@ -3559,18 +3518,18 @@ void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, goto out; } - if (has_replaces) { + if (arg->has_replaces) { BlockDriverState *to_replace_bs; AioContext *replace_aio_context; int64_t replace_size; - if (!has_node_name) { + if (!arg->has_node_name) { error_setg(errp, "a node-name must be provided when replacing a" " named node of the graph"); goto out; } - to_replace_bs = check_to_replace_node(bs, replaces, &local_err); + to_replace_bs = check_to_replace_node(bs, arg->replaces, &local_err); if (!to_replace_bs) { error_propagate(errp, local_err); @@ -3589,26 +3548,26 @@ void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, } } - if (mode == NEW_IMAGE_MODE_ABSOLUTE_PATHS) { + if (arg->mode == NEW_IMAGE_MODE_ABSOLUTE_PATHS) { backing_mode = MIRROR_SOURCE_BACKING_CHAIN; } else { backing_mode = MIRROR_OPEN_BACKING_CHAIN; } - if ((sync == MIRROR_SYNC_MODE_FULL || !source) - && mode != NEW_IMAGE_MODE_EXISTING) + if ((arg->sync == MIRROR_SYNC_MODE_FULL || !source) + && arg->mode != NEW_IMAGE_MODE_EXISTING) { /* create new image w/o backing file */ assert(format); - bdrv_img_create(target, format, + bdrv_img_create(arg->target, format, NULL, NULL, NULL, size, flags, &local_err, false); } else { - switch (mode) { + switch (arg->mode) { case NEW_IMAGE_MODE_EXISTING: break; case NEW_IMAGE_MODE_ABSOLUTE_PATHS: /* create new image with backing file */ - bdrv_img_create(target, format, + bdrv_img_create(arg->target, format, source->filename, source->drv->format_name, NULL, size, flags, &local_err, false); @@ -3624,8 +3583,8 @@ void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, } options = qdict_new(); - if (has_node_name) { - qdict_put(options, "node-name", qstring_from_str(node_name)); + if (arg->has_node_name) { + qdict_put(options, "node-name", qstring_from_str(arg->node_name)); } if (format) { qdict_put(options, "driver", qstring_from_str(format)); @@ -3634,22 +3593,22 @@ void qmp_drive_mirror(bool has_job_id, const char *job_id, const char *device, /* Mirroring takes care of copy-on-write using the source's backing * file. */ - target_bs = bdrv_open(target, NULL, options, flags | BDRV_O_NO_BACKING, - errp); + target_bs = bdrv_open(arg->target, NULL, options, + flags | BDRV_O_NO_BACKING, errp); if (!target_bs) { goto out; } bdrv_set_aio_context(target_bs, aio_context); - blockdev_mirror_common(has_job_id ? job_id : NULL, bs, target_bs, - has_replaces, replaces, sync, backing_mode, - has_speed, speed, - has_granularity, granularity, - has_buf_size, buf_size, - has_on_source_error, on_source_error, - has_on_target_error, on_target_error, - has_unmap, unmap, + blockdev_mirror_common(arg->has_job_id ? arg->job_id : NULL, bs, target_bs, + arg->has_replaces, arg->replaces, arg->sync, + backing_mode, arg->has_speed, arg->speed, + arg->has_granularity, arg->granularity, + arg->has_buf_size, arg->buf_size, + arg->has_on_source_error, arg->on_source_error, + arg->has_on_target_error, arg->on_target_error, + arg->has_unmap, arg->unmap, &local_err); bdrv_unref(target_bs); error_propagate(errp, local_err); diff --git a/crypto/Makefile.objs b/crypto/Makefile.objs index 1f86f4f07f..a36d2d9bdf 100644 --- a/crypto/Makefile.objs +++ b/crypto/Makefile.objs @@ -2,6 +2,7 @@ crypto-obj-y = init.o crypto-obj-y += hash.o crypto-obj-$(CONFIG_NETTLE) += hash-nettle.o crypto-obj-$(if $(CONFIG_NETTLE),n,$(CONFIG_GCRYPT)) += hash-gcrypt.o +crypto-obj-$(if $(CONFIG_NETTLE),n,$(if $(CONFIG_GCRYPT),n,y)) += hash-glib.o crypto-obj-y += aes.o crypto-obj-y += desrfb.o crypto-obj-y += cipher.o @@ -12,6 +13,7 @@ crypto-obj-y += tlssession.o crypto-obj-y += secret.o crypto-obj-$(CONFIG_GCRYPT) += random-gcrypt.o crypto-obj-$(if $(CONFIG_GCRYPT),n,$(CONFIG_GNUTLS_RND)) += random-gnutls.o +crypto-obj-$(if $(CONFIG_GCRYPT),n,$(if $(CONFIG_GNUTLS_RND),n,y)) += random-platform.o crypto-obj-y += pbkdf.o crypto-obj-$(CONFIG_NETTLE_KDF) += pbkdf-nettle.o crypto-obj-$(if $(CONFIG_NETTLE_KDF),n,$(CONFIG_GCRYPT_KDF)) += pbkdf-gcrypt.o @@ -28,6 +30,4 @@ crypto-obj-y += block-luks.o # Let the userspace emulators avoid linking gnutls/etc crypto-aes-obj-y = aes.o -stub-obj-y += random-stub.o stub-obj-y += pbkdf-stub.o -stub-obj-y += hash-stub.o diff --git a/crypto/hash-gcrypt.c b/crypto/hash-gcrypt.c index ed6f842461..7690690f70 100644 --- a/crypto/hash-gcrypt.c +++ b/crypto/hash-gcrypt.c @@ -55,8 +55,7 @@ int qcrypto_hash_bytesv(QCryptoHashAlgorithm alg, gcry_md_hd_t md; unsigned char *digest; - if (alg >= G_N_ELEMENTS(qcrypto_hash_alg_map) || - qcrypto_hash_alg_map[alg] == GCRY_MD_NONE) { + if (!qcrypto_hash_supports(alg)) { error_setg(errp, "Unknown hash algorithm %d", alg); diff --git a/crypto/hash-glib.c b/crypto/hash-glib.c new file mode 100644 index 0000000000..ec99ac9df9 --- /dev/null +++ b/crypto/hash-glib.c @@ -0,0 +1,97 @@ +/* + * QEMU Crypto hash algorithms + * + * Copyright (c) 2016 Red Hat, Inc. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + * + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "crypto/hash.h" + + +static int qcrypto_hash_alg_map[QCRYPTO_HASH_ALG__MAX] = { + [QCRYPTO_HASH_ALG_MD5] = G_CHECKSUM_MD5, + [QCRYPTO_HASH_ALG_SHA1] = G_CHECKSUM_SHA1, + [QCRYPTO_HASH_ALG_SHA224] = -1, + [QCRYPTO_HASH_ALG_SHA256] = G_CHECKSUM_SHA256, + [QCRYPTO_HASH_ALG_SHA384] = -1, +#if GLIB_CHECK_VERSION(2, 36, 0) + [QCRYPTO_HASH_ALG_SHA512] = G_CHECKSUM_SHA512, +#else + [QCRYPTO_HASH_ALG_SHA512] = -1, +#endif + [QCRYPTO_HASH_ALG_RIPEMD160] = -1, +}; + +gboolean qcrypto_hash_supports(QCryptoHashAlgorithm alg) +{ + if (alg < G_N_ELEMENTS(qcrypto_hash_alg_map) && + qcrypto_hash_alg_map[alg] != -1) { + return true; + } + return false; +} + + +int qcrypto_hash_bytesv(QCryptoHashAlgorithm alg, + const struct iovec *iov, + size_t niov, + uint8_t **result, + size_t *resultlen, + Error **errp) +{ + int i, ret; + GChecksum *cs; + + if (!qcrypto_hash_supports(alg)) { + error_setg(errp, + "Unknown hash algorithm %d", + alg); + return -1; + } + + cs = g_checksum_new(qcrypto_hash_alg_map[alg]); + + for (i = 0; i < niov; i++) { + g_checksum_update(cs, iov[i].iov_base, iov[i].iov_len); + } + + ret = g_checksum_type_get_length(qcrypto_hash_alg_map[alg]); + if (ret < 0) { + error_setg(errp, "%s", + "Unable to get hash length"); + goto error; + } + if (*resultlen == 0) { + *resultlen = ret; + *result = g_new0(uint8_t, *resultlen); + } else if (*resultlen != ret) { + error_setg(errp, + "Result buffer size %zu is smaller than hash %d", + *resultlen, ret); + goto error; + } + + g_checksum_get_digest(cs, *result, resultlen); + + g_checksum_free(cs); + return 0; + + error: + g_checksum_free(cs); + return -1; +} diff --git a/crypto/hash-nettle.c b/crypto/hash-nettle.c index 4c6f50b65d..6a206dcb18 100644 --- a/crypto/hash-nettle.c +++ b/crypto/hash-nettle.c @@ -113,8 +113,7 @@ int qcrypto_hash_bytesv(QCryptoHashAlgorithm alg, int i; union qcrypto_hash_ctx ctx; - if (alg >= G_N_ELEMENTS(qcrypto_hash_alg_map) || - qcrypto_hash_alg_map[alg].init == NULL) { + if (!qcrypto_hash_supports(alg)) { error_setg(errp, "Unknown hash algorithm %d", alg); diff --git a/crypto/hash-stub.c b/crypto/hash-stub.c deleted file mode 100644 index 8a9b8d4c09..0000000000 --- a/crypto/hash-stub.c +++ /dev/null @@ -1,41 +0,0 @@ -/* - * QEMU Crypto hash algorithms - * - * Copyright (c) 2016 Red Hat, Inc. - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - * - */ - -#include "qemu/osdep.h" -#include "qapi/error.h" -#include "crypto/hash.h" - -gboolean qcrypto_hash_supports(QCryptoHashAlgorithm alg G_GNUC_UNUSED) -{ - return false; -} - -int qcrypto_hash_bytesv(QCryptoHashAlgorithm alg, - const struct iovec *iov G_GNUC_UNUSED, - size_t niov G_GNUC_UNUSED, - uint8_t **result G_GNUC_UNUSED, - size_t *resultlen G_GNUC_UNUSED, - Error **errp) -{ - error_setg(errp, - "Hash algorithm %d not supported without GNUTLS", - alg); - return -1; -} diff --git a/crypto/random-stub.c b/crypto/random-platform.c index 63bbf41473..82b755afad 100644 --- a/crypto/random-stub.c +++ b/crypto/random-platform.c @@ -26,6 +26,39 @@ int qcrypto_random_bytes(uint8_t *buf G_GNUC_UNUSED, size_t buflen G_GNUC_UNUSED, Error **errp) { - error_setg(errp, "No random byte source provided in this build"); - return -1; + int fd; + int ret = -1; + int got; + + /* TBD perhaps also add support for BSD getentropy / Linux + * getrandom syscalls directly */ + fd = open("/dev/urandom", O_RDONLY); + if (fd == -1 && errno == ENOENT) { + fd = open("/dev/random", O_RDONLY); + } + + if (fd < 0) { + error_setg(errp, "No /dev/urandom or /dev/random found"); + return -1; + } + + while (buflen > 0) { + got = read(fd, buf, buflen); + if (got < 0) { + error_setg_errno(errp, errno, + "Unable to read random bytes"); + goto cleanup; + } else if (!got) { + error_setg(errp, + "Unexpected EOF reading random bytes"); + goto cleanup; + } + buflen -= got; + buf += got; + } + + ret = 0; + cleanup: + close(fd); + return ret; } diff --git a/docs/qapi-code-gen.txt b/docs/qapi-code-gen.txt index 48b0b31f2e..de298dcaec 100644 --- a/docs/qapi-code-gen.txt +++ b/docs/qapi-code-gen.txt @@ -410,7 +410,7 @@ following example objects: === Commands === Usage: { 'command': STRING, '*data': COMPLEX-TYPE-NAME-OR-DICT, - '*returns': TYPE-NAME, + '*returns': TYPE-NAME, '*boxed': true, '*gen': false, '*success-response': false } Commands are defined by using a dictionary containing several members, @@ -461,6 +461,20 @@ which would validate this Client JSON Protocol transaction: => { "execute": "my-second-command" } <= { "return": [ { "value": "one" }, { } ] } +The generator emits a prototype for the user's function implementing +the command. Normally, 'data' is a dictionary for an anonymous type, +or names a struct type (possibly empty, but not a union), and its +members are passed as separate arguments to this function. If the +command definition includes a key 'boxed' with the boolean value true, +then 'data' is instead the name of any non-empty complex type +(struct, union, or alternate), and a pointer to that QAPI type is +passed as a single argument. + +The generator also emits a marshalling function that extracts +arguments for the user's function out of an input QDict, calls the +user's function, and if it succeeded, builds an output QObject from +its return value. + In rare cases, QAPI cannot express a type-safe representation of a corresponding Client JSON Protocol command. You then have to suppress generation of a marshalling function by including a key 'gen' with @@ -484,7 +498,8 @@ use of this member. === Events === -Usage: { 'event': STRING, '*data': COMPLEX-TYPE-NAME-OR-DICT } +Usage: { 'event': STRING, '*data': COMPLEX-TYPE-NAME-OR-DICT, + '*boxed': true } Events are defined with the keyword 'event'. It is not allowed to name an event 'MAX', since the generator also produces a C enumeration @@ -505,6 +520,14 @@ Resulting in this JSON object: "data": { "b": "test string" }, "timestamp": { "seconds": 1267020223, "microseconds": 435656 } } +The generator emits a function to send the event. Normally, 'data' is +a dictionary for an anonymous type, or names a struct type (possibly +empty, but not a union), and its members are passed as separate +arguments to this function. If the event definition includes a key +'boxed' with the boolean value true, then 'data' is instead the name of +any non-empty complex type (struct, union, or alternate), and a +pointer to that QAPI type is passed as a single argument. + == Client JSON Protocol introspection == @@ -1077,31 +1077,28 @@ void hmp_block_resize(Monitor *mon, const QDict *qdict) void hmp_drive_mirror(Monitor *mon, const QDict *qdict) { - const char *device = qdict_get_str(qdict, "device"); const char *filename = qdict_get_str(qdict, "target"); const char *format = qdict_get_try_str(qdict, "format"); bool reuse = qdict_get_try_bool(qdict, "reuse", false); bool full = qdict_get_try_bool(qdict, "full", false); - enum NewImageMode mode; Error *err = NULL; + DriveMirror mirror = { + .device = (char *)qdict_get_str(qdict, "device"), + .target = (char *)filename, + .has_format = !!format, + .format = (char *)format, + .sync = full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP, + .has_mode = true, + .mode = reuse ? NEW_IMAGE_MODE_EXISTING : NEW_IMAGE_MODE_ABSOLUTE_PATHS, + .unmap = true, + }; if (!filename) { error_setg(&err, QERR_MISSING_PARAMETER, "target"); hmp_handle_error(mon, &err); return; } - - if (reuse) { - mode = NEW_IMAGE_MODE_EXISTING; - } else { - mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS; - } - - qmp_drive_mirror(false, NULL, device, filename, !!format, format, - false, NULL, false, NULL, - full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP, - true, mode, false, 0, false, 0, false, 0, - false, 0, false, 0, false, true, &err); + qmp_drive_mirror(&mirror, &err); hmp_handle_error(mon, &err); } @@ -1439,42 +1436,17 @@ void hmp_change(Monitor *mon, const QDict *qdict) void hmp_block_set_io_throttle(Monitor *mon, const QDict *qdict) { Error *err = NULL; + BlockIOThrottle throttle = { + .device = (char *) qdict_get_str(qdict, "device"), + .bps = qdict_get_int(qdict, "bps"), + .bps_rd = qdict_get_int(qdict, "bps_rd"), + .bps_wr = qdict_get_int(qdict, "bps_wr"), + .iops = qdict_get_int(qdict, "iops"), + .iops_rd = qdict_get_int(qdict, "iops_rd"), + .iops_wr = qdict_get_int(qdict, "iops_wr"), + }; - qmp_block_set_io_throttle(qdict_get_str(qdict, "device"), - qdict_get_int(qdict, "bps"), - qdict_get_int(qdict, "bps_rd"), - qdict_get_int(qdict, "bps_wr"), - qdict_get_int(qdict, "iops"), - qdict_get_int(qdict, "iops_rd"), - qdict_get_int(qdict, "iops_wr"), - false, /* no burst max via HMP */ - 0, - false, - 0, - false, - 0, - false, - 0, - false, - 0, - false, - 0, - false, /* no burst length via HMP */ - 0, - false, - 0, - false, - 0, - false, - 0, - false, - 0, - false, - 0, - false, /* No default I/O size */ - 0, - false, - NULL, &err); + qmp_block_set_io_throttle(&throttle, &err); hmp_handle_error(mon, &err); } diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index 7a4cc07dd5..cc50ace13d 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -378,7 +378,7 @@ static void eth_cleanup(NetClientState *nc) } static NetClientInfo net_mv88w8618_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = eth_receive, .cleanup = eth_cleanup, diff --git a/hw/block/xen_disk.c b/hw/block/xen_disk.c index 90aca73121..3b8ad33fc5 100644 --- a/hw/block/xen_disk.c +++ b/hw/block/xen_disk.c @@ -574,9 +574,10 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq) { struct blkif_request_discard *discard_req = (void *)&ioreq->req; ioreq->aio_inflight++; - blk_aio_discard(blkdev->blk, - discard_req->sector_number, discard_req->nr_sectors, - qemu_aio_complete, ioreq); + blk_aio_pdiscard(blkdev->blk, + discard_req->sector_number << BDRV_SECTOR_BITS, + discard_req->nr_sectors << BDRV_SECTOR_BITS, + qemu_aio_complete, ioreq); break; } default: diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index ab1bc5e945..2ba2504ea0 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -247,7 +247,7 @@ static void set_netdev(Object *obj, Visitor *v, const char *name, } queues = qemu_find_net_clients_except(str, peers, - NET_CLIENT_OPTIONS_KIND_NIC, + NET_CLIENT_DRIVER_NIC, MAX_QUEUE_NUM); if (queues == 0) { err = -ENOENT; diff --git a/hw/display/qxl.c b/hw/display/qxl.c index 46cc86690c..0e2682d28b 100644 --- a/hw/display/qxl.c +++ b/hw/display/qxl.c @@ -1816,16 +1816,17 @@ static void qxl_hw_update(void *opaque) static void qxl_dirty_one_surface(PCIQXLDevice *qxl, QXLPHYSICAL pqxl, uint32_t height, int32_t stride) { - uint64_t offset; - uint32_t slot, size; + uint64_t offset, size; + uint32_t slot; bool rc; rc = qxl_get_check_slot_offset(qxl, pqxl, &slot, &offset); assert(rc == true); - size = height * abs(stride); - trace_qxl_surfaces_dirty(qxl->id, (int)offset, size); + size = (uint64_t)height * abs(stride); + trace_qxl_surfaces_dirty(qxl->id, offset, size); qxl_set_dirty(qxl->guest_slots[slot].mr, - qxl->guest_slots[slot].offset + offset, size); + qxl->guest_slots[slot].offset + offset, + qxl->guest_slots[slot].offset + offset + size); } static void qxl_dirty_surfaces(PCIQXLDevice *qxl) diff --git a/hw/display/trace-events b/hw/display/trace-events index 9dd82cecde..78f04657a0 100644 --- a/hw/display/trace-events +++ b/hw/display/trace-events @@ -105,7 +105,7 @@ qxl_spice_reset_image_cache(int qid) "%d" qxl_spice_reset_memslots(int qid) "%d" qxl_spice_update_area(int qid, uint32_t surface_id, uint32_t left, uint32_t right, uint32_t top, uint32_t bottom) "%d sid=%d [%d,%d,%d,%d]" qxl_spice_update_area_rest(int qid, uint32_t num_dirty_rects, uint32_t clear_dirty_region) "%d #d=%d clear=%d" -qxl_surfaces_dirty(int qid, int offset, int size) "%d offset=%d size=%d" +qxl_surfaces_dirty(int qid, uint64_t offset, uint64_t size) "%d offset=0x%"PRIx64" size=0x%"PRIx64 qxl_send_events(int qid, uint32_t events) "%d %d" qxl_send_events_vm_stopped(int qid, uint32_t events) "%d %d" qxl_set_guest_bug(int qid) "%d" diff --git a/hw/i386/kvm/apic.c b/hw/i386/kvm/apic.c index c5983c79be..2bd0de82b4 100644 --- a/hw/i386/kvm/apic.c +++ b/hw/i386/kvm/apic.c @@ -184,19 +184,24 @@ static void kvm_apic_realize(DeviceState *dev, Error **errp) { APICCommonState *s = APIC_COMMON(dev); - memory_region_init_io(&s->io_memory, NULL, &kvm_apic_io_ops, s, "kvm-apic-msi", - APIC_SPACE_SIZE); + memory_region_init_io(&s->io_memory, OBJECT(s), &kvm_apic_io_ops, s, + "kvm-apic-msi", APIC_SPACE_SIZE); if (kvm_has_gsi_routing()) { msi_nonbroken = true; } } +static void kvm_apic_unrealize(DeviceState *dev, Error **errp) +{ +} + static void kvm_apic_class_init(ObjectClass *klass, void *data) { APICCommonClass *k = APIC_COMMON_CLASS(klass); k->realize = kvm_apic_realize; + k->unrealize = kvm_apic_unrealize; k->reset = kvm_apic_reset; k->set_base = kvm_apic_set_base; k->set_tpr = kvm_apic_set_tpr; diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 979f36d99f..9e3c70fb23 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -471,9 +471,6 @@ void pc_cmos_init(PCMachineState *pcms, rtc_set_memory(s, 0x5c, val >> 8); rtc_set_memory(s, 0x5d, val >> 16); - /* set the number of CPU */ - rtc_set_memory(s, 0x5f, smp_cpus - 1); - object_property_add_link(OBJECT(pcms), "rtc_state", TYPE_ISA_DEVICE, (Object **)&pcms->rtc, @@ -1090,6 +1087,17 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level) } } +static int pc_present_cpus_count(PCMachineState *pcms) +{ + int i, boot_cpus = 0; + for (i = 0; i < pcms->possible_cpus->len; i++) { + if (pcms->possible_cpus->cpus[i].cpu) { + boot_cpus++; + } + } + return boot_cpus; +} + static X86CPU *pc_new_cpu(const char *typename, int64_t apic_id, Error **errp) { @@ -1122,18 +1130,6 @@ void pc_hot_add_cpu(const int64_t id, Error **errp) return; } - if (cpu_exists(apic_id)) { - error_setg(errp, "Unable to add CPU: %" PRIi64 - ", it already exists", id); - return; - } - - if (id >= max_cpus) { - error_setg(errp, "Unable to add CPU: %" PRIi64 - ", max allowed: %d", id, max_cpus - 1); - return; - } - if (apic_id >= ACPI_CPU_HOTPLUG_ID_LIMIT) { error_setg(errp, "Unable to add CPU: %" PRIi64 ", resulting APIC ID (%" PRIi64 ") is too large", @@ -1208,7 +1204,6 @@ void pc_cpus_init(PCMachineState *pcms) if (i < smp_cpus) { cpu = pc_new_cpu(typename, x86_cpu_apic_id_from_index(i), &error_fatal); - pcms->possible_cpus->cpus[i].cpu = CPU(cpu); object_unref(OBJECT(cpu)); } } @@ -1252,6 +1247,9 @@ void pc_machine_done(Notifier *notifier, void *data) PCMachineState, machine_done); PCIBus *bus = pcms->bus; + /* set the number of CPUs */ + rtc_set_memory(pcms->rtc, 0x5f, pc_present_cpus_count(pcms) - 1); + if (bus) { int extra_hosts = 0; @@ -1759,39 +1757,48 @@ static int pc_apic_cmp(const void *a, const void *b) return apic_a->arch_id - apic_b->arch_id; } +/* returns pointer to CPUArchId descriptor that matches CPU's apic_id + * in pcms->possible_cpus->cpus, if pcms->possible_cpus->cpus has no + * entry correponding to CPU's apic_id returns NULL. + */ +static CPUArchId *pc_find_cpu_slot(PCMachineState *pcms, CPUState *cpu, + int *idx) +{ + CPUClass *cc = CPU_GET_CLASS(cpu); + CPUArchId apic_id, *found_cpu; + + apic_id.arch_id = cc->get_arch_id(CPU(cpu)); + found_cpu = bsearch(&apic_id, pcms->possible_cpus->cpus, + pcms->possible_cpus->len, sizeof(*pcms->possible_cpus->cpus), + pc_apic_cmp); + if (found_cpu && idx) { + *idx = found_cpu - pcms->possible_cpus->cpus; + } + return found_cpu; +} + static void pc_cpu_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - CPUClass *cc = CPU_GET_CLASS(dev); - CPUArchId apic_id, *found_cpu; + CPUArchId *found_cpu; HotplugHandlerClass *hhc; Error *local_err = NULL; PCMachineState *pcms = PC_MACHINE(hotplug_dev); - if (!dev->hotplugged) { - goto out; - } - - if (!pcms->acpi_dev) { - error_setg(&local_err, - "cpu hotplug is not enabled: missing acpi device"); - goto out; + if (pcms->acpi_dev) { + hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev); + hhc->plug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err); + if (local_err) { + goto out; + } } - hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev); - hhc->plug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err); - if (local_err) { - goto out; + if (dev->hotplugged) { + /* increment the number of CPUs */ + rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) + 1); } - /* increment the number of CPUs */ - rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) + 1); - - apic_id.arch_id = cc->get_arch_id(CPU(dev)); - found_cpu = bsearch(&apic_id, pcms->possible_cpus->cpus, - pcms->possible_cpus->len, sizeof(*pcms->possible_cpus->cpus), - pc_apic_cmp); - assert(found_cpu); + found_cpu = pc_find_cpu_slot(pcms, CPU(dev), NULL); found_cpu->cpu = CPU(dev); out: error_propagate(errp, local_err); @@ -1799,10 +1806,35 @@ out: static void pc_cpu_unplug_request_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { + int idx = -1; HotplugHandlerClass *hhc; Error *local_err = NULL; PCMachineState *pcms = PC_MACHINE(hotplug_dev); + pc_find_cpu_slot(pcms, CPU(dev), &idx); + assert(idx != -1); + if (idx == 0) { + error_setg(&local_err, "Boot CPU is unpluggable"); + goto out; + } + + if (idx < pcms->possible_cpus->len - 1 && + pcms->possible_cpus->cpus[idx + 1].cpu != NULL) { + X86CPU *cpu; + + for (idx = pcms->possible_cpus->len - 1; + pcms->possible_cpus->cpus[idx].cpu == NULL; idx--) { + ;; + } + + cpu = X86_CPU(pcms->possible_cpus->cpus[idx].cpu); + error_setg(&local_err, "CPU [socket-id: %u, core-id: %u," + " thread-id: %u] should be removed first", + cpu->socket_id, cpu->core_id, cpu->thread_id); + goto out; + + } + hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev); hhc->unplug_request(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err); @@ -1818,6 +1850,7 @@ static void pc_cpu_unplug_request_cb(HotplugHandler *hotplug_dev, static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { + CPUArchId *found_cpu; HotplugHandlerClass *hhc; Error *local_err = NULL; PCMachineState *pcms = PC_MACHINE(hotplug_dev); @@ -1829,17 +1862,129 @@ static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev, goto out; } - /* - * TODO: enable unplug once generic CPU remove bits land - * for now guest will be able to eject CPU ACPI wise but - * it will come back again on machine reset. - */ - /* object_unparent(OBJECT(dev)); */ + found_cpu = pc_find_cpu_slot(pcms, CPU(dev), NULL); + found_cpu->cpu = NULL; + object_unparent(OBJECT(dev)); + rtc_set_memory(pcms->rtc, 0x5f, rtc_get_memory(pcms->rtc, 0x5f) - 1); out: error_propagate(errp, local_err); } +static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + int idx; + CPUArchId *cpu_slot; + X86CPUTopoInfo topo; + X86CPU *cpu = X86_CPU(dev); + PCMachineState *pcms = PC_MACHINE(hotplug_dev); + + /* if APIC ID is not set, set it based on socket/core/thread properties */ + if (cpu->apic_id == UNASSIGNED_APIC_ID) { + int max_socket = (max_cpus - 1) / smp_threads / smp_cores; + + if (cpu->socket_id < 0) { + error_setg(errp, "CPU socket-id is not set"); + return; + } else if (cpu->socket_id > max_socket) { + error_setg(errp, "Invalid CPU socket-id: %u must be in range 0:%u", + cpu->socket_id, max_socket); + return; + } + if (cpu->core_id < 0) { + error_setg(errp, "CPU core-id is not set"); + return; + } else if (cpu->core_id > (smp_cores - 1)) { + error_setg(errp, "Invalid CPU core-id: %u must be in range 0:%u", + cpu->core_id, smp_cores - 1); + return; + } + if (cpu->thread_id < 0) { + error_setg(errp, "CPU thread-id is not set"); + return; + } else if (cpu->thread_id > (smp_threads - 1)) { + error_setg(errp, "Invalid CPU thread-id: %u must be in range 0:%u", + cpu->thread_id, smp_threads - 1); + return; + } + + topo.pkg_id = cpu->socket_id; + topo.core_id = cpu->core_id; + topo.smt_id = cpu->thread_id; + cpu->apic_id = apicid_from_topo_ids(smp_cores, smp_threads, &topo); + } + + cpu_slot = pc_find_cpu_slot(pcms, CPU(dev), &idx); + if (!cpu_slot) { + x86_topo_ids_from_apicid(cpu->apic_id, smp_cores, smp_threads, &topo); + error_setg(errp, "Invalid CPU [socket: %u, core: %u, thread: %u] with" + " APIC ID %" PRIu32 ", valid index range 0:%d", + topo.pkg_id, topo.core_id, topo.smt_id, cpu->apic_id, + pcms->possible_cpus->len - 1); + return; + } + + if (cpu_slot->cpu) { + error_setg(errp, "CPU[%d] with APIC ID %" PRIu32 " exists", + idx, cpu->apic_id); + return; + } + + if (idx != 0 && pcms->possible_cpus->cpus[idx - 1].cpu == NULL) { + PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms); + + for (idx = 1; pcms->possible_cpus->cpus[idx].cpu != NULL; idx++) { + ;; + } + + x86_topo_ids_from_apicid(pcms->possible_cpus->cpus[idx].arch_id, + smp_cores, smp_threads, &topo); + + if (!pcmc->legacy_cpu_hotplug) { + error_setg(errp, "CPU [socket: %u, core: %u, thread: %u] should be" + " added first", topo.pkg_id, topo.core_id, topo.smt_id); + return; + } + } + + /* if 'address' properties socket-id/core-id/thread-id are not set, set them + * so that query_hotpluggable_cpus would show correct values + */ + /* TODO: move socket_id/core_id/thread_id checks into x86_cpu_realizefn() + * once -smp refactoring is complete and there will be CPU private + * CPUState::nr_cores and CPUState::nr_threads fields instead of globals */ + x86_topo_ids_from_apicid(cpu->apic_id, smp_cores, smp_threads, &topo); + if (cpu->socket_id != -1 && cpu->socket_id != topo.pkg_id) { + error_setg(errp, "property socket-id: %u doesn't match set apic-id:" + " 0x%x (socket-id: %u)", cpu->socket_id, cpu->apic_id, topo.pkg_id); + return; + } + cpu->socket_id = topo.pkg_id; + + if (cpu->core_id != -1 && cpu->core_id != topo.core_id) { + error_setg(errp, "property core-id: %u doesn't match set apic-id:" + " 0x%x (core-id: %u)", cpu->core_id, cpu->apic_id, topo.core_id); + return; + } + cpu->core_id = topo.core_id; + + if (cpu->thread_id != -1 && cpu->thread_id != topo.smt_id) { + error_setg(errp, "property thread-id: %u doesn't match set apic-id:" + " 0x%x (thread-id: %u)", cpu->thread_id, cpu->apic_id, topo.smt_id); + return; + } + cpu->thread_id = topo.smt_id; +} + +static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { + pc_cpu_pre_plug(hotplug_dev, dev, errp); + } +} + static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { @@ -2093,6 +2238,50 @@ static CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *machine) return list; } +static HotpluggableCPUList *pc_query_hotpluggable_cpus(MachineState *machine) +{ + int i; + CPUState *cpu; + HotpluggableCPUList *head = NULL; + PCMachineState *pcms = PC_MACHINE(machine); + const char *cpu_type; + + cpu = pcms->possible_cpus->cpus[0].cpu; + assert(cpu); /* BSP is always present */ + cpu_type = object_class_get_name(OBJECT_CLASS(CPU_GET_CLASS(cpu))); + + for (i = 0; i < pcms->possible_cpus->len; i++) { + X86CPUTopoInfo topo; + HotpluggableCPUList *list_item = g_new0(typeof(*list_item), 1); + HotpluggableCPU *cpu_item = g_new0(typeof(*cpu_item), 1); + CpuInstanceProperties *cpu_props = g_new0(typeof(*cpu_props), 1); + const uint32_t apic_id = pcms->possible_cpus->cpus[i].arch_id; + + x86_topo_ids_from_apicid(apic_id, smp_cores, smp_threads, &topo); + + cpu_item->type = g_strdup(cpu_type); + cpu_item->vcpus_count = 1; + cpu_props->has_socket_id = true; + cpu_props->socket_id = topo.pkg_id; + cpu_props->has_core_id = true; + cpu_props->core_id = topo.core_id; + cpu_props->has_thread_id = true; + cpu_props->thread_id = topo.smt_id; + cpu_item->props = cpu_props; + + cpu = pcms->possible_cpus->cpus[i].cpu; + if (cpu) { + cpu_item->has_qom_path = true; + cpu_item->qom_path = object_get_canonical_path(OBJECT(cpu)); + } + + list_item->value = cpu_item; + list_item->next = head; + head = list_item; + } + return head; +} + static void x86_nmi(NMIState *n, int cpu_index, Error **errp) { /* cpu index isn't used */ @@ -2133,10 +2322,12 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) mc->get_hotplug_handler = pc_get_hotpug_handler; mc->cpu_index_to_socket_id = pc_cpu_index_to_socket_id; mc->possible_cpu_arch_ids = pc_possible_cpu_arch_ids; + mc->query_hotpluggable_cpus = pc_query_hotpluggable_cpus; mc->default_boot_order = "cad"; mc->hot_add_cpu = pc_hot_add_cpu; mc->max_cpus = 255; mc->reset = pc_machine_reset; + hc->pre_plug = pc_machine_device_pre_plug_cb; hc->plug = pc_machine_device_plug_cb; hc->unplug_request = pc_machine_device_unplug_request_cb; hc->unplug = pc_machine_device_unplug_cb; diff --git a/hw/ide/core.c b/hw/ide/core.c index b1daf967d6..081c9eb765 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -423,8 +423,10 @@ static void ide_issue_trim_cb(void *opaque, int ret) } /* Got an entry! Submit and exit. */ - iocb->aiocb = blk_aio_discard(iocb->blk, sector, count, - ide_issue_trim_cb, opaque); + iocb->aiocb = blk_aio_pdiscard(iocb->blk, + sector << BDRV_SECTOR_BITS, + count << BDRV_SECTOR_BITS, + ide_issue_trim_cb, opaque); return; } diff --git a/hw/intc/apic.c b/hw/intc/apic.c index e1ab9354c6..45887d99c0 100644 --- a/hw/intc/apic.c +++ b/hw/intc/apic.c @@ -28,7 +28,9 @@ #include "trace.h" #include "hw/i386/pc.h" #include "hw/i386/apic-msidef.h" +#include "qapi/error.h" +#define MAX_APICS 255 #define MAX_APIC_WORDS 8 #define SYNC_FROM_VAPIC 0x1 @@ -419,7 +421,7 @@ static int apic_find_dest(uint8_t dest) int i; if (apic && apic->id == dest) - return dest; /* shortcut in case apic->id == apic->idx */ + return dest; /* shortcut in case apic->id == local_apics[dest]->id */ for (i = 0; i < MAX_APICS; i++) { apic = local_apics[i]; @@ -502,14 +504,14 @@ static void apic_deliver(DeviceState *dev, uint8_t dest, uint8_t dest_mode, break; case 1: memset(deliver_bitmask, 0x00, sizeof(deliver_bitmask)); - apic_set_bit(deliver_bitmask, s->idx); + apic_set_bit(deliver_bitmask, s->id); break; case 2: memset(deliver_bitmask, 0xff, sizeof(deliver_bitmask)); break; case 3: memset(deliver_bitmask, 0xff, sizeof(deliver_bitmask)); - apic_reset_bit(deliver_bitmask, s->idx); + apic_reset_bit(deliver_bitmask, s->id); break; } @@ -870,20 +872,36 @@ static void apic_realize(DeviceState *dev, Error **errp) { APICCommonState *s = APIC_COMMON(dev); + if (s->id >= MAX_APICS) { + error_setg(errp, "%s initialization failed. APIC ID %d is invalid", + object_get_typename(OBJECT(dev)), s->id); + return; + } + memory_region_init_io(&s->io_memory, OBJECT(s), &apic_io_ops, s, "apic-msi", APIC_SPACE_SIZE); s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, apic_timer, s); - local_apics[s->idx] = s; + local_apics[s->id] = s; msi_nonbroken = true; } +static void apic_unrealize(DeviceState *dev, Error **errp) +{ + APICCommonState *s = APIC_COMMON(dev); + + timer_del(s->timer); + timer_free(s->timer); + local_apics[s->id] = NULL; +} + static void apic_class_init(ObjectClass *klass, void *data) { APICCommonClass *k = APIC_COMMON_CLASS(klass); k->realize = apic_realize; + k->unrealize = apic_unrealize; k->set_base = apic_set_base; k->set_tpr = apic_set_tpr; k->get_tpr = apic_get_tpr; diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c index e6eb694de0..14ac43c186 100644 --- a/hw/intc/apic_common.c +++ b/hw/intc/apic_common.c @@ -294,19 +294,14 @@ static int apic_load_old(QEMUFile *f, void *opaque, int version_id) return 0; } +static const VMStateDescription vmstate_apic_common; + static void apic_common_realize(DeviceState *dev, Error **errp) { APICCommonState *s = APIC_COMMON(dev); APICCommonClass *info; static DeviceState *vapic; - static int apic_no; - - if (apic_no >= MAX_APICS) { - error_setg(errp, "%s initialization failed.", - object_get_typename(OBJECT(dev))); - return; - } - s->idx = apic_no++; + int instance_id = s->id; info = APIC_COMMON_GET_CLASS(s); info->realize(dev, errp); @@ -321,6 +316,24 @@ static void apic_common_realize(DeviceState *dev, Error **errp) info->enable_tpr_reporting(s, true); } + if (s->legacy_instance_id) { + instance_id = -1; + } + vmstate_register_with_alias_id(NULL, instance_id, &vmstate_apic_common, + s, -1, 0); +} + +static void apic_common_unrealize(DeviceState *dev, Error **errp) +{ + APICCommonState *s = APIC_COMMON(dev); + APICCommonClass *info = APIC_COMMON_GET_CLASS(s); + + vmstate_unregister(NULL, &vmstate_apic_common, s); + info->unrealize(dev, errp); + + if (apic_report_tpr_access && info->enable_tpr_reporting) { + info->enable_tpr_reporting(s, false); + } } static int apic_pre_load(void *opaque) @@ -418,6 +431,8 @@ static Property apic_properties_common[] = { DEFINE_PROP_UINT8("version", APICCommonState, version, 0x14), DEFINE_PROP_BIT("vapic", APICCommonState, vapic_control, VAPIC_ENABLE_BIT, true), + DEFINE_PROP_BOOL("legacy-instance-id", APICCommonState, legacy_instance_id, + false), DEFINE_PROP_END_OF_LIST(), }; @@ -425,10 +440,10 @@ static void apic_common_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); - dc->vmsd = &vmstate_apic_common; dc->reset = apic_reset_common; dc->props = apic_properties_common; dc->realize = apic_common_realize; + dc->unrealize = apic_common_unrealize; /* * Reason: APIC and CPU need to be wired up by * x86_cpu_apic_create() diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index 2f60096e6e..77e5cfa327 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -420,6 +420,8 @@ MemTxResult gicv3_redist_read(void *opaque, hwaddr offset, uint64_t *data, MemTxResult r; int cpuidx; + assert((offset & (size - 1)) == 0); + /* This region covers all the redistributor pages; there are * (for GICv3) two 64K pages per CPU. At the moment they are * all contiguous (ie in this one region), though we might later @@ -468,6 +470,8 @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, MemTxResult r; int cpuidx; + assert((offset & (size - 1)) == 0); + /* This region covers all the redistributor pages; there are * (for GICv3) two 64K pages per CPU. At the moment they are * all contiguous (ie in this one region), though we might later diff --git a/hw/net/allwinner_emac.c b/hw/net/allwinner_emac.c index d57502300c..50e8361e52 100644 --- a/hw/net/allwinner_emac.c +++ b/hw/net/allwinner_emac.c @@ -424,7 +424,7 @@ static const MemoryRegionOps aw_emac_mem_ops = { }; static NetClientInfo net_aw_emac_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = aw_emac_can_receive, .receive = aw_emac_receive, diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index 8a4be1e667..db1b301e7f 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -1207,7 +1207,7 @@ static void gem_set_link(NetClientState *nc) } static NetClientInfo net_gem_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = gem_can_receive, .receive = gem_receive, diff --git a/hw/net/dp8393x.c b/hw/net/dp8393x.c index 0fa652c392..17f0338d1c 100644 --- a/hw/net/dp8393x.c +++ b/hw/net/dp8393x.c @@ -812,7 +812,7 @@ static void dp8393x_reset(DeviceState *dev) } static NetClientInfo net_dp83932_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = dp8393x_can_receive, .receive = dp8393x_receive, diff --git a/hw/net/e1000.c b/hw/net/e1000.c index 06ca7b2638..93249497f4 100644 --- a/hw/net/e1000.c +++ b/hw/net/e1000.c @@ -1563,7 +1563,7 @@ pci_e1000_uninit(PCIDevice *dev) } static NetClientInfo net_e1000_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = e1000_can_receive, .receive = e1000_receive, diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c index b4758bc441..d001c96668 100644 --- a/hw/net/e1000e.c +++ b/hw/net/e1000e.c @@ -225,7 +225,7 @@ e1000e_set_link_status(NetClientState *nc) } static NetClientInfo net_e1000e_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = e1000e_nc_can_receive, .receive = e1000e_nc_receive, diff --git a/hw/net/eepro100.c b/hw/net/eepro100.c index b10c419838..bab4dbfc98 100644 --- a/hw/net/eepro100.c +++ b/hw/net/eepro100.c @@ -1848,7 +1848,7 @@ static void pci_nic_uninit(PCIDevice *pci_dev) } static NetClientInfo net_eepro100_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = nic_receive, }; diff --git a/hw/net/etraxfs_eth.c b/hw/net/etraxfs_eth.c index 05495ec405..efaa49faae 100644 --- a/hw/net/etraxfs_eth.c +++ b/hw/net/etraxfs_eth.c @@ -578,7 +578,7 @@ static const MemoryRegionOps eth_ops = { }; static NetClientInfo net_etraxfs_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = eth_receive, .link_status_changed = eth_set_link, diff --git a/hw/net/fsl_etsec/etsec.c b/hw/net/fsl_etsec/etsec.c index 98250e0591..b5c777fbf6 100644 --- a/hw/net/fsl_etsec/etsec.c +++ b/hw/net/fsl_etsec/etsec.c @@ -371,7 +371,7 @@ static void etsec_set_link_status(NetClientState *nc) } static NetClientInfo net_etsec_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = etsec_receive, .link_status_changed = etsec_set_link_status, diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index d91e029382..1c415ab3b1 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -1147,7 +1147,7 @@ static void imx_eth_cleanup(NetClientState *nc) } static NetClientInfo imx_eth_net_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = imx_eth_can_receive, .receive = imx_eth_receive, diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c index 205207356c..4615d873b1 100644 --- a/hw/net/lan9118.c +++ b/hw/net/lan9118.c @@ -1313,7 +1313,7 @@ static const MemoryRegionOps lan9118_16bit_mem_ops = { }; static NetClientInfo net_lan9118_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = lan9118_receive, .link_status_changed = lan9118_set_link, diff --git a/hw/net/lance.c b/hw/net/lance.c index 6253d2103d..573d724bcf 100644 --- a/hw/net/lance.c +++ b/hw/net/lance.c @@ -93,7 +93,7 @@ static const MemoryRegionOps lance_mem_ops = { }; static NetClientInfo net_lance_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = pcnet_receive, .link_status_changed = pcnet_set_link_status, diff --git a/hw/net/mcf_fec.c b/hw/net/mcf_fec.c index 7c0398ed99..0ee8ad9d66 100644 --- a/hw/net/mcf_fec.c +++ b/hw/net/mcf_fec.c @@ -507,7 +507,7 @@ static const MemoryRegionOps mcf_fec_ops = { }; static NetClientInfo net_mcf_fec_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = mcf_fec_receive, }; diff --git a/hw/net/milkymist-minimac2.c b/hw/net/milkymist-minimac2.c index 1e147c33c5..c3a12e1197 100644 --- a/hw/net/milkymist-minimac2.c +++ b/hw/net/milkymist-minimac2.c @@ -447,7 +447,7 @@ static void milkymist_minimac2_reset(DeviceState *d) } static NetClientInfo net_milkymist_minimac2_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = minimac2_rx, }; diff --git a/hw/net/mipsnet.c b/hw/net/mipsnet.c index 5115adcaea..5a63df7ccb 100644 --- a/hw/net/mipsnet.c +++ b/hw/net/mipsnet.c @@ -224,7 +224,7 @@ static const VMStateDescription vmstate_mipsnet = { }; static NetClientInfo net_mipsnet_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = mipsnet_receive, }; diff --git a/hw/net/ne2000-isa.c b/hw/net/ne2000-isa.c index 8fab7ae2ec..f3455339ee 100644 --- a/hw/net/ne2000-isa.c +++ b/hw/net/ne2000-isa.c @@ -44,7 +44,7 @@ typedef struct ISANE2000State { } ISANE2000State; static NetClientInfo net_ne2000_isa_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = ne2000_receive, }; diff --git a/hw/net/ne2000.c b/hw/net/ne2000.c index f0feaf96b0..798d681e25 100644 --- a/hw/net/ne2000.c +++ b/hw/net/ne2000.c @@ -712,7 +712,7 @@ void ne2000_setup_io(NE2000State *s, DeviceState *dev, unsigned size) } static NetClientInfo net_ne2000_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = ne2000_receive, }; diff --git a/hw/net/opencores_eth.c b/hw/net/opencores_eth.c index 484d113eb6..268d6a7892 100644 --- a/hw/net/opencores_eth.c +++ b/hw/net/opencores_eth.c @@ -473,7 +473,7 @@ static ssize_t open_eth_receive(NetClientState *nc, } static NetClientInfo net_open_eth_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = open_eth_can_receive, .receive = open_eth_receive, diff --git a/hw/net/pcnet-pci.c b/hw/net/pcnet-pci.c index 595439a65b..0acf8a4879 100644 --- a/hw/net/pcnet-pci.c +++ b/hw/net/pcnet-pci.c @@ -272,7 +272,7 @@ static void pci_pcnet_uninit(PCIDevice *dev) } static NetClientInfo net_pci_pcnet_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = pcnet_receive, .link_status_changed = pcnet_set_link_status, diff --git a/hw/net/rocker/rocker_fp.c b/hw/net/rocker/rocker_fp.c index 0149899c62..1305ac36cc 100644 --- a/hw/net/rocker/rocker_fp.c +++ b/hw/net/rocker/rocker_fp.c @@ -167,7 +167,7 @@ static void fp_port_set_link_status(NetClientState *nc) } static NetClientInfo fp_port_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = fp_port_receive, .receive_iov = fp_port_receive_iov, diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c index 07297cb78f..3345bc6b5e 100644 --- a/hw/net/rtl8139.c +++ b/hw/net/rtl8139.c @@ -3393,7 +3393,7 @@ static void rtl8139_set_link_status(NetClientState *nc) } static NetClientInfo net_rtl8139_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = rtl8139_can_receive, .receive = rtl8139_receive, diff --git a/hw/net/smc91c111.c b/hw/net/smc91c111.c index 21c1b8f54b..3b16dcf5a1 100644 --- a/hw/net/smc91c111.c +++ b/hw/net/smc91c111.c @@ -755,7 +755,7 @@ static const MemoryRegionOps smc91c111_mem_ops = { }; static NetClientInfo net_smc91c111_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = smc91c111_can_receive_nc, .receive = smc91c111_receive, diff --git a/hw/net/spapr_llan.c b/hw/net/spapr_llan.c index 8b2eebd4e3..b273eda933 100644 --- a/hw/net/spapr_llan.c +++ b/hw/net/spapr_llan.c @@ -278,7 +278,7 @@ static ssize_t spapr_vlan_receive(NetClientState *nc, const uint8_t *buf, } static NetClientInfo net_spapr_vlan_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = spapr_vlan_can_receive, .receive = spapr_vlan_receive, diff --git a/hw/net/stellaris_enet.c b/hw/net/stellaris_enet.c index 6880894945..957730e023 100644 --- a/hw/net/stellaris_enet.c +++ b/hw/net/stellaris_enet.c @@ -460,7 +460,7 @@ static void stellaris_enet_reset(stellaris_enet_state *s) } static NetClientInfo net_stellaris_enet_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = stellaris_enet_receive, }; diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 11fabc0b0a..f92d3f829e 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -88,10 +88,10 @@ static const int *vhost_net_get_feature_bits(struct vhost_net *net) const int *feature_bits = 0; switch (net->nc->info->type) { - case NET_CLIENT_OPTIONS_KIND_TAP: + case NET_CLIENT_DRIVER_TAP: feature_bits = kernel_feature_bits; break; - case NET_CLIENT_OPTIONS_KIND_VHOST_USER: + case NET_CLIENT_DRIVER_VHOST_USER: feature_bits = user_feature_bits; break; default: @@ -128,7 +128,7 @@ uint64_t vhost_net_get_acked_features(VHostNetState *net) static int vhost_net_get_fd(NetClientState *backend) { switch (backend->info->type) { - case NET_CLIENT_OPTIONS_KIND_TAP: + case NET_CLIENT_DRIVER_TAP: return tap_get_fd(backend); default: fprintf(stderr, "vhost-net requires tap backend\n"); @@ -191,7 +191,7 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options) } /* Set sane init value. Override when guest acks. */ - if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + if (net->nc->info->type == NET_CLIENT_DRIVER_VHOST_USER) { features = vhost_user_get_acked_features(net->nc); if (~net->dev.features & features) { fprintf(stderr, "vhost lacks feature mask %" PRIu64 @@ -238,7 +238,7 @@ static int vhost_net_start_one(struct vhost_net *net, net->nc->info->poll(net->nc, false); } - if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP) { + if (net->nc->info->type == NET_CLIENT_DRIVER_TAP) { qemu_set_fd_handler(net->backend, NULL, NULL, NULL); file.fd = net->backend; for (file.index = 0; file.index < net->dev.nvqs; ++file.index) { @@ -253,7 +253,7 @@ static int vhost_net_start_one(struct vhost_net *net, return 0; fail: file.fd = -1; - if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP) { + if (net->nc->info->type == NET_CLIENT_DRIVER_TAP) { while (file.index-- > 0) { const VhostOps *vhost_ops = net->dev.vhost_ops; int r = vhost_ops->vhost_net_set_backend(&net->dev, &file); @@ -275,7 +275,7 @@ static void vhost_net_stop_one(struct vhost_net *net, { struct vhost_vring_file file = { .fd = -1 }; - if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP) { + if (net->nc->info->type == NET_CLIENT_DRIVER_TAP) { for (file.index = 0; file.index < net->dev.nvqs; ++file.index) { const VhostOps *vhost_ops = net->dev.vhost_ops; int r = vhost_ops->vhost_net_set_backend(&net->dev, &file); @@ -312,7 +312,7 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, * because vhost user doesn't interrupt masking/unmasking * properly. */ - if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + if (net->nc->info->type == NET_CLIENT_DRIVER_VHOST_USER) { dev->use_guest_notifier_mask = false; } } @@ -413,10 +413,10 @@ VHostNetState *get_vhost_net(NetClientState *nc) } switch (nc->info->type) { - case NET_CLIENT_OPTIONS_KIND_TAP: + case NET_CLIENT_DRIVER_TAP: vhost_net = tap_get_vhost_net(nc); break; - case NET_CLIENT_OPTIONS_KIND_VHOST_USER: + case NET_CLIENT_DRIVER_VHOST_USER: vhost_net = vhost_user_get_vhost_net(nc); break; default: diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index bb311c4587..01f1351554 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -468,11 +468,11 @@ static int peer_attach(VirtIONet *n, int index) return 0; } - if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_USER) { vhost_set_vring_enable(nc->peer, 1); } - if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) { + if (nc->peer->info->type != NET_CLIENT_DRIVER_TAP) { return 0; } @@ -487,11 +487,11 @@ static int peer_detach(VirtIONet *n, int index) return 0; } - if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + if (nc->peer->info->type == NET_CLIENT_DRIVER_VHOST_USER) { vhost_set_vring_enable(nc->peer, 0); } - if (nc->peer->info->type != NET_CLIENT_OPTIONS_KIND_TAP) { + if (nc->peer->info->type != NET_CLIENT_DRIVER_TAP) { return 0; } @@ -1658,7 +1658,7 @@ static int virtio_net_load_device(VirtIODevice *vdev, QEMUFile *f, } static NetClientInfo net_virtio_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = virtio_net_can_receive, .receive = virtio_net_receive, diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c index e767fc64b8..bbf44adbcc 100644 --- a/hw/net/vmxnet3.c +++ b/hw/net/vmxnet3.c @@ -2087,7 +2087,7 @@ static void vmxnet3_set_link_status(NetClientState *nc) } static NetClientInfo net_vmxnet3_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = vmxnet3_receive, .link_status_changed = vmxnet3_set_link_status, diff --git a/hw/net/xen_nic.c b/hw/net/xen_nic.c index 0b4ddae48c..6856b52999 100644 --- a/hw/net/xen_nic.c +++ b/hw/net/xen_nic.c @@ -269,7 +269,7 @@ static ssize_t net_rx_packet(NetClientState *nc, const uint8_t *buf, size_t size /* ------------------------------------------------------------- */ static NetClientInfo net_xen_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = net_rx_packet, }; diff --git a/hw/net/xgmac.c b/hw/net/xgmac.c index 0c5f793bd2..46b1aa17fa 100644 --- a/hw/net/xgmac.c +++ b/hw/net/xgmac.c @@ -371,7 +371,7 @@ out: } static NetClientInfo net_xgmac_enet_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = eth_rx, }; diff --git a/hw/net/xilinx_axienet.c b/hw/net/xilinx_axienet.c index de23ab5dcd..b6701844d3 100644 --- a/hw/net/xilinx_axienet.c +++ b/hw/net/xilinx_axienet.c @@ -935,7 +935,7 @@ xilinx_axienet_data_stream_push(StreamSlave *obj, uint8_t *buf, size_t size) } static NetClientInfo net_xilinx_enet_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = eth_rx, }; diff --git a/hw/net/xilinx_ethlite.c b/hw/net/xilinx_ethlite.c index bc846e7096..54db2b83bd 100644 --- a/hw/net/xilinx_ethlite.c +++ b/hw/net/xilinx_ethlite.c @@ -217,7 +217,7 @@ static void xilinx_ethlite_reset(DeviceState *dev) } static NetClientInfo net_xilinx_ethlite_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .can_receive = eth_can_rx, .receive = eth_rx, diff --git a/hw/s390x/css-bridge.c b/hw/s390x/css-bridge.c index e4c24e21f3..9a7f7ee60c 100644 --- a/hw/s390x/css-bridge.c +++ b/hw/s390x/css-bridge.c @@ -59,11 +59,28 @@ static void virtual_css_bus_reset(BusState *qbus) css_reset(); } +static char *virtual_css_bus_get_dev_path(DeviceState *dev) +{ + CcwDevice *ccw_dev = CCW_DEVICE(dev); + SubchDev *sch = ccw_dev->sch; + VirtualCssBridge *bridge = + VIRTUAL_CSS_BRIDGE(qdev_get_parent_bus(dev)->parent); + + /* + * We can't provide a dev path for backward compatibility on + * older machines, as it is visible in the migration stream. + */ + return bridge->css_dev_path ? + g_strdup_printf("/%02x.%1x.%04x", sch->cssid, sch->ssid, sch->devno) : + NULL; +} + static void virtual_css_bus_class_init(ObjectClass *klass, void *data) { BusClass *k = BUS_CLASS(klass); k->reset = virtual_css_bus_reset; + k->get_dev_path = virtual_css_bus_get_dev_path; } static const TypeInfo virtual_css_bus_info = { @@ -95,6 +112,12 @@ VirtualCssBus *virtual_css_bus_init(void) /***************** Virtual-css Bus Bridge Device ********************/ +static Property virtual_css_bridge_properties[] = { + DEFINE_PROP_BOOL("css_dev_path", VirtualCssBridge, css_dev_path, + true), + DEFINE_PROP_END_OF_LIST(), +}; + static void virtual_css_bridge_class_init(ObjectClass *klass, void *data) { HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass); @@ -102,12 +125,13 @@ static void virtual_css_bridge_class_init(ObjectClass *klass, void *data) hc->unplug = ccw_device_unplug; set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + dc->props = virtual_css_bridge_properties; } static const TypeInfo virtual_css_bridge_info = { .name = TYPE_VIRTUAL_CSS_BRIDGE, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(SysBusDevice), + .instance_size = sizeof(VirtualCssBridge), .class_init = virtual_css_bridge_class_init, .interfaces = (InterfaceInfo[]) { { TYPE_HOTPLUG_HANDLER }, diff --git a/hw/s390x/css.c b/hw/s390x/css.c index aa61773885..bb8e4be339 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -511,6 +511,7 @@ static void sch_handle_start_func(SubchDev *sch, ORB *orb) path = 0x80; if (!(s->ctrl & SCSW_ACTL_SUSP)) { + /* Start Function triggered via ssch, i.e. we have an ORB */ s->cstat = 0; s->dstat = 0; /* Look at the orb and try to execute the channel program. */ @@ -524,9 +525,12 @@ static void sch_handle_start_func(SubchDev *sch, ORB *orb) return; } sch->ccw_fmt_1 = !!(orb->ctrl0 & ORB_CTRL0_MASK_FMT); + s->flags |= (sch->ccw_fmt_1) ? SCSW_FLAGS_MASK_FMT : 0; sch->ccw_no_data_cnt = 0; suspend_allowed = !!(orb->ctrl0 & ORB_CTRL0_MASK_SPND); } else { + /* Start Function resumed via rsch, i.e. we don't have an + * ORB */ s->ctrl &= ~(SCSW_ACTL_SUSP | SCSW_ACTL_RESUME_PEND); /* The channel program had been suspended before. */ suspend_allowed = true; @@ -609,6 +613,7 @@ static void do_subchannel_work(SubchDev *sch, ORB *orb) } else if (s->ctrl & SCSW_FCTL_HALT_FUNC) { sch_handle_halt_func(sch); } else if (s->ctrl & SCSW_FCTL_START_FUNC) { + /* Triggered by both ssch and rsch. */ sch_handle_start_func(sch, orb); } else { /* Cannot happen. */ diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index caf0a682a7..91d9cefbb5 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -322,6 +322,10 @@ static const TypeInfo ccw_machine_info = { .driver = TYPE_S390_IPL,\ .property = "iplbext_migration",\ .value = "off",\ + }, {\ + .driver = TYPE_VIRTUAL_CSS_BRIDGE,\ + .property = "css_dev_path",\ + .value = "off",\ }, #define CCW_COMPAT_2_5 \ diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index 8dbfc10b78..836a1553ed 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -1609,10 +1609,10 @@ static void scsi_unmap_complete_noio(UnmapCBData *data, int ret) goto done; } - r->req.aiocb = blk_aio_discard(s->qdev.conf.blk, - sector_num * (s->qdev.blocksize / 512), - nb_sectors * (s->qdev.blocksize / 512), - scsi_unmap_complete, data); + r->req.aiocb = blk_aio_pdiscard(s->qdev.conf.blk, + sector_num * s->qdev.blocksize, + nb_sectors * s->qdev.blocksize, + scsi_unmap_complete, data); data->count--; data->inbuf += 16; return; diff --git a/hw/usb/dev-network.c b/hw/usb/dev-network.c index 5c18198f55..c0f1193ba9 100644 --- a/hw/usb/dev-network.c +++ b/hw/usb/dev-network.c @@ -1334,7 +1334,7 @@ static void usb_net_handle_destroy(USBDevice *dev) } static NetClientInfo net_usbnet_info = { - .type = NET_CLIENT_OPTIONS_KIND_NIC, + .type = NET_CLIENT_DRIVER_NIC, .size = sizeof(NICState), .receive = usbnet_receive, .cleanup = usbnet_cleanup, @@ -1396,7 +1396,7 @@ static USBDevice *usb_net_init(USBBus *bus, const char *cmdline) qemu_opt_set(opts, "type", "nic", &error_abort); qemu_opt_set(opts, "model", "usb", &error_abort); - idx = net_client_init(opts, 0, &local_err); + idx = net_client_init(opts, false, &local_err); if (local_err) { error_report_err(local_err); return NULL; diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c index 976bfb0659..188f95416a 100644 --- a/hw/usb/hcd-xhci.c +++ b/hw/usb/hcd-xhci.c @@ -2201,7 +2201,9 @@ static void xhci_kick_ep(XHCIState *xhci, unsigned int slotid, xfer->trb_count = length; for (i = 0; i < length; i++) { - assert(xhci_ring_fetch(xhci, ring, &xfer->trbs[i], NULL)); + TRBType type; + type = xhci_ring_fetch(xhci, ring, &xfer->trbs[i], NULL); + assert(type); } xfer->streamid = streamid; diff --git a/hw/usb/redirect.c b/hw/usb/redirect.c index 8ec8484349..444672a000 100644 --- a/hw/usb/redirect.c +++ b/hw/usb/redirect.c @@ -109,6 +109,7 @@ struct USBRedirDevice { uint8_t debug; char *filter_str; int32_t bootindex; + bool enable_streams; /* Data passed from chardev the fd_read cb to the usbredirparser read cb */ const uint8_t *read_buf; int read_buf_size; @@ -1229,7 +1230,9 @@ static void usbredir_create_parser(USBRedirDevice *dev) usbredirparser_caps_set_cap(caps, usb_redir_cap_32bits_bulk_length); usbredirparser_caps_set_cap(caps, usb_redir_cap_bulk_receiving); #if USBREDIR_VERSION >= 0x000700 - usbredirparser_caps_set_cap(caps, usb_redir_cap_bulk_streams); + if (dev->enable_streams) { + usbredirparser_caps_set_cap(caps, usb_redir_cap_bulk_streams); + } #endif if (runstate_check(RUN_STATE_INMIGRATE)) { @@ -2476,6 +2479,7 @@ static Property usbredir_properties[] = { DEFINE_PROP_CHR("chardev", USBRedirDevice, cs), DEFINE_PROP_UINT8("debug", USBRedirDevice, debug, usbredirparser_warning), DEFINE_PROP_STRING("filter", USBRedirDevice, filter_str), + DEFINE_PROP_BOOL("streams", USBRedirDevice, enable_streams, true), DEFINE_PROP_END_OF_LIST(), }; diff --git a/include/block/block.h b/include/block/block.h index 616d8b9f12..11c162d594 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -316,9 +316,9 @@ BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num, BlockCompletionFunc *cb, void *opaque); BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque); -BlockAIOCB *bdrv_aio_discard(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, - BlockCompletionFunc *cb, void *opaque); +BlockAIOCB *bdrv_aio_pdiscard(BlockDriverState *bs, + int64_t offset, int count, + BlockCompletionFunc *cb, void *opaque); void bdrv_aio_cancel(BlockAIOCB *acb); void bdrv_aio_cancel_async(BlockAIOCB *acb); @@ -341,8 +341,8 @@ void bdrv_drain(BlockDriverState *bs); void coroutine_fn bdrv_co_drain(BlockDriverState *bs); void bdrv_drain_all(void); -int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors); -int bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors); +int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count); +int bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset, int count); int bdrv_has_zero_init_1(BlockDriverState *bs); int bdrv_has_zero_init(BlockDriverState *bs); bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs); diff --git a/include/block/block_int.h b/include/block/block_int.h index a6b13adb45..1fe0fd9ff6 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -142,8 +142,8 @@ struct BlockDriver { BlockCompletionFunc *cb, void *opaque); BlockAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque); - BlockAIOCB *(*bdrv_aio_discard)(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, + BlockAIOCB *(*bdrv_aio_pdiscard)(BlockDriverState *bs, + int64_t offset, int count, BlockCompletionFunc *cb, void *opaque); int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs, @@ -165,8 +165,8 @@ struct BlockDriver { */ int coroutine_fn (*bdrv_co_pwrite_zeroes)(BlockDriverState *bs, int64_t offset, int count, BdrvRequestFlags flags); - int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs, - int64_t sector_num, int nb_sectors); + int coroutine_fn (*bdrv_co_pdiscard)(BlockDriverState *bs, + int64_t offset, int count); int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file); @@ -783,7 +783,7 @@ void blk_dev_eject_request(BlockBackend *blk, bool force); bool blk_dev_is_tray_open(BlockBackend *blk); bool blk_dev_is_medium_locked(BlockBackend *blk); -void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors); +void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int64_t nr_sect); bool bdrv_requests_pending(BlockDriverState *bs); void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out); diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index 80afe603f6..ee3388f90d 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -33,9 +33,9 @@ DirtyBitmapStatus bdrv_dirty_bitmap_status(BdrvDirtyBitmap *bitmap); int bdrv_get_dirty(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, int64_t sector); void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int nr_sectors); + int64_t cur_sector, int64_t nr_sectors); void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int nr_sectors); + int64_t cur_sector, int64_t nr_sectors); void bdrv_dirty_iter_init(BdrvDirtyBitmap *bitmap, struct HBitmapIter *hbi); void bdrv_set_dirty_iter(struct HBitmapIter *hbi, int64_t offset); int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap); diff --git a/include/block/nbd.h b/include/block/nbd.h index eeda3ebdf7..cb91820f38 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -77,7 +77,6 @@ enum { /* Maximum size of a single READ/WRITE data buffer */ #define NBD_MAX_BUFFER_SIZE (32 * 1024 * 1024) -#define NBD_MAX_SECTORS (NBD_MAX_BUFFER_SIZE / BDRV_SECTOR_SIZE) /* Maximum size of an export name. The NBD spec requires 256 and * suggests that servers support up to 4096, but we stick to only the @@ -89,7 +88,6 @@ enum { ssize_t nbd_wr_syncv(QIOChannel *ioc, struct iovec *iov, size_t niov, - size_t offset, size_t length, bool do_read); int nbd_receive_negotiate(QIOChannel *ioc, const char *name, uint32_t *flags, diff --git a/include/hw/i386/apic_internal.h b/include/hw/i386/apic_internal.h index 73ce71674f..06c4e9f6f9 100644 --- a/include/hw/i386/apic_internal.h +++ b/include/hw/i386/apic_internal.h @@ -121,8 +121,6 @@ #define VAPIC_ENABLE_BIT 0 #define VAPIC_ENABLE_MASK (1 << VAPIC_ENABLE_BIT) -#define MAX_APICS 255 - typedef struct APICCommonState APICCommonState; #define TYPE_APIC_COMMON "apic-common" @@ -138,6 +136,7 @@ typedef struct APICCommonClass DeviceClass parent_class; DeviceRealize realize; + DeviceUnrealize unrealize; void (*set_base)(APICCommonState *s, uint64_t val); void (*set_tpr)(APICCommonState *s, uint8_t val); uint8_t (*get_tpr)(APICCommonState *s); @@ -176,7 +175,6 @@ struct APICCommonState { uint32_t initial_count; int64_t initial_count_load_time; int64_t next_time; - int idx; QEMUTimer *timer; int64_t timer_expiry; int sipi_vector; @@ -185,6 +183,7 @@ struct APICCommonState { uint32_t vapic_control; DeviceState *vapic; hwaddr vapic_paddr; /* note: persistence via kvmvapic */ + bool legacy_instance_id; }; typedef struct VAPICState { diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 9811125492..c87c5c1eec 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -381,6 +381,16 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .driver = "vmxnet3",\ .property = "romfile",\ .value = "",\ + },\ + {\ + .driver = TYPE_X86_CPU,\ + .property = "fill-mtrr-mask",\ + .value = "off",\ + },\ + {\ + .driver = "apic",\ + .property = "legacy-instance-id",\ + .value = "on",\ }, #define PC_COMPAT_2_5 \ diff --git a/include/hw/i386/topology.h b/include/hw/i386/topology.h index fc95572394..1ebaee0f76 100644 --- a/include/hw/i386/topology.h +++ b/include/hw/i386/topology.h @@ -117,6 +117,21 @@ static inline void x86_topo_ids_from_idx(unsigned nr_cores, topo->pkg_id = core_index / nr_cores; } +/* Calculate thread/core/package IDs for a specific topology, + * based on APIC ID + */ +static inline void x86_topo_ids_from_apicid(apic_id_t apicid, + unsigned nr_cores, + unsigned nr_threads, + X86CPUTopoInfo *topo) +{ + topo->smt_id = apicid & + ~(0xFFFFFFFFUL << apicid_smt_width(nr_cores, nr_threads)); + topo->core_id = (apicid >> apicid_core_offset(nr_cores, nr_threads)) & + ~(0xFFFFFFFFUL << apicid_core_width(nr_cores, nr_threads)); + topo->pkg_id = apicid >> apicid_pkg_offset(nr_cores, nr_threads); +} + /* Make APIC ID for the CPU 'cpu_index' * * 'cpu_index' is a sequential, contiguous ID for the CPU. diff --git a/include/hw/s390x/css-bridge.h b/include/hw/s390x/css-bridge.h index ad73c1faf6..5a0203be5f 100644 --- a/include/hw/s390x/css-bridge.h +++ b/include/hw/s390x/css-bridge.h @@ -16,7 +16,14 @@ #include "hw/qdev-core.h" /* virtual css bridge */ +typedef struct VirtualCssBridge { + SysBusDevice sysbus_dev; + bool css_dev_path; +} VirtualCssBridge; + #define TYPE_VIRTUAL_CSS_BRIDGE "virtual-css-bridge" +#define VIRTUAL_CSS_BRIDGE(obj) \ + OBJECT_CHECK(VirtualCssBridge, (obj), TYPE_VIRTUAL_CSS_BRIDGE) /* virtual css bus type */ typedef struct VirtualCssBus { diff --git a/include/net/net.h b/include/net/net.h index a5c5095154..e8d9e9e4e9 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -66,7 +66,7 @@ typedef struct SocketReadState SocketReadState; typedef void (SocketReadStateFinalize)(SocketReadState *rs); typedef struct NetClientInfo { - NetClientOptionsKind type; + NetClientDriver type; size_t size; NetReceive *receive; NetReceive *receive_raw; @@ -122,7 +122,7 @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size); char *qemu_mac_strdup_printf(const uint8_t *macaddr); NetClientState *qemu_find_netdev(const char *id); int qemu_find_net_clients_except(const char *id, NetClientState **ncs, - NetClientOptionsKind type, int max); + NetClientDriver type, int max); NetClientState *qemu_new_net_client(NetClientInfo *info, NetClientState *peer, const char *model, @@ -203,7 +203,7 @@ extern const char *host_net_devices[]; extern const char *legacy_tftp_prefix; extern const char *legacy_bootp_filename; -int net_client_init(QemuOpts *opts, int is_netdev, Error **errp); +int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp); int net_client_parse(QemuOptsList *opts_list, const char *str); int net_init_clients(void); void net_check_clients(void); diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index 3c3e82f05d..2da4905d18 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -139,15 +139,14 @@ BlockAIOCB *blk_aio_pwritev(BlockBackend *blk, int64_t offset, BlockCompletionFunc *cb, void *opaque); BlockAIOCB *blk_aio_flush(BlockBackend *blk, BlockCompletionFunc *cb, void *opaque); -BlockAIOCB *blk_aio_discard(BlockBackend *blk, - int64_t sector_num, int nb_sectors, - BlockCompletionFunc *cb, void *opaque); +BlockAIOCB *blk_aio_pdiscard(BlockBackend *blk, int64_t offset, int count, + BlockCompletionFunc *cb, void *opaque); void blk_aio_cancel(BlockAIOCB *acb); void blk_aio_cancel_async(BlockAIOCB *acb); int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf); BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf, BlockCompletionFunc *cb, void *opaque); -int blk_co_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors); +int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int count); int blk_co_flush(BlockBackend *blk); int blk_flush(BlockBackend *blk); int blk_flush_all(void); @@ -207,7 +206,7 @@ int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, int blk_write_compressed(BlockBackend *blk, int64_t sector_num, const uint8_t *buf, int nb_sectors); int blk_truncate(BlockBackend *blk, int64_t offset); -int blk_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors); +int blk_pdiscard(BlockBackend *blk, int64_t offset, int count); int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, int64_t pos, int size); int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size); diff --git a/linux-user/aarch64/syscall_nr.h b/linux-user/aarch64/syscall_nr.h index 59511d855d..a3c9a3b679 100644 --- a/linux-user/aarch64/syscall_nr.h +++ b/linux-user/aarch64/syscall_nr.h @@ -86,8 +86,7 @@ #define TARGET_NR_sync 81 #define TARGET_NR_fsync 82 #define TARGET_NR_fdatasync 83 -#define TARGET_NR_sync_file_range2 84 -/* #define TARGET_NR_sync_file_range 84 */ +#define TARGET_NR_sync_file_range 84 #define TARGET_NR_timerfd_create 85 #define TARGET_NR_timerfd_settime 86 #define TARGET_NR_timerfd_gettime 87 diff --git a/linux-user/ioctls.h b/linux-user/ioctls.h index e672655100..7e2c133ba1 100644 --- a/linux-user/ioctls.h +++ b/linux-user/ioctls.h @@ -76,10 +76,39 @@ IOCTL(BLKFLSBUF, 0, TYPE_NULL) IOCTL(BLKRASET, 0, TYPE_INT) IOCTL(BLKRAGET, IOC_R, MK_PTR(TYPE_LONG)) - IOCTL(BLKSSZGET, IOC_R, MK_PTR(TYPE_LONG)) + IOCTL(BLKSSZGET, IOC_R, MK_PTR(TYPE_INT)) IOCTL(BLKBSZGET, IOC_R, MK_PTR(TYPE_INT)) IOCTL_SPECIAL(BLKPG, IOC_W, do_ioctl_blkpg, MK_PTR(MK_STRUCT(STRUCT_blkpg_ioctl_arg))) + +#ifdef BLKDISCARD + IOCTL(BLKDISCARD, IOC_W, MK_PTR(MK_ARRAY(TYPE_ULONGLONG, 2))) +#endif +#ifdef BLKIOMIN + IOCTL(BLKIOMIN, IOC_R, MK_PTR(TYPE_INT)) +#endif +#ifdef BLKIOOPT + IOCTL(BLKIOOPT, IOC_R, MK_PTR(TYPE_INT)) +#endif +#ifdef BLKALIGNOFF + IOCTL(BLKALIGNOFF, IOC_R, MK_PTR(TYPE_INT)) +#endif +#ifdef BLKPBSZGET + IOCTL(BLKPBSZGET, IOC_R, MK_PTR(TYPE_INT)) +#endif +#ifdef BLKDISCARDZEROES + IOCTL(BLKDISCARDZEROES, IOC_R, MK_PTR(TYPE_INT)) +#endif +#ifdef BLKSECDISCARD + IOCTL(BLKSECDISCARD, IOC_W, MK_PTR(MK_ARRAY(TYPE_ULONGLONG, 2))) +#endif +#ifdef BLKROTATIONAL + IOCTL(BLKROTATIONAL, IOC_R, MK_PTR(TYPE_SHORT)) +#endif +#ifdef BLKZEROOUT + IOCTL(BLKZEROOUT, IOC_W, MK_PTR(MK_ARRAY(TYPE_ULONGLONG, 2))) +#endif + #ifdef FIBMAP IOCTL(FIBMAP, IOC_W | IOC_R, MK_PTR(TYPE_LONG)) #endif @@ -91,7 +120,7 @@ MK_PTR(MK_STRUCT(STRUCT_fiemap))) #endif - IOCTL(SIOCATMARK, 0, TYPE_NULL) + IOCTL(SIOCATMARK, IOC_R, MK_PTR(TYPE_INT)) IOCTL(SIOCGIFNAME, IOC_RW, MK_PTR(TYPE_INT)) IOCTL(SIOCGIFFLAGS, IOC_W | IOC_R, MK_PTR(MK_STRUCT(STRUCT_short_ifreq))) IOCTL(SIOCSIFFLAGS, IOC_W, MK_PTR(MK_STRUCT(STRUCT_short_ifreq))) @@ -322,11 +351,15 @@ IOCTL(LOOP_SET_FD, 0, TYPE_INT) IOCTL(LOOP_CLR_FD, 0, TYPE_INT) IOCTL(LOOP_SET_STATUS, IOC_W, MK_PTR(MK_STRUCT(STRUCT_loop_info))) - IOCTL(LOOP_GET_STATUS, IOC_W, MK_PTR(MK_STRUCT(STRUCT_loop_info))) + IOCTL(LOOP_GET_STATUS, IOC_R, MK_PTR(MK_STRUCT(STRUCT_loop_info))) IOCTL(LOOP_SET_STATUS64, IOC_W, MK_PTR(MK_STRUCT(STRUCT_loop_info64))) - IOCTL(LOOP_GET_STATUS64, IOC_W, MK_PTR(MK_STRUCT(STRUCT_loop_info64))) + IOCTL(LOOP_GET_STATUS64, IOC_R, MK_PTR(MK_STRUCT(STRUCT_loop_info64))) IOCTL(LOOP_CHANGE_FD, 0, TYPE_INT) + IOCTL(LOOP_CTL_ADD, 0, TYPE_INT) + IOCTL(LOOP_CTL_REMOVE, 0, TYPE_INT) + IOCTL(LOOP_CTL_GET_FREE, 0, TYPE_NULL) + IOCTL(MTIOCTOP, IOC_W, MK_PTR(MK_STRUCT(STRUCT_mtop))) IOCTL(MTIOCGET, IOC_R, MK_PTR(MK_STRUCT(STRUCT_mtget))) IOCTL(MTIOCPOS, IOC_R, MK_PTR(MK_STRUCT(STRUCT_mtpos))) diff --git a/linux-user/linux_loop.h b/linux-user/linux_loop.h index 1f52403814..c69fea11e4 100644 --- a/linux-user/linux_loop.h +++ b/linux-user/linux_loop.h @@ -1,4 +1,6 @@ -/* Copied from 2.6.25 kernel headers to avoid problems on older hosts. */ +/* Copied from 2.6.25 kernel headers to avoid problems on older hosts, + * and subsequently updated to match newer additions to the API. + */ #ifndef LINUX_LOOP_H #define LINUX_LOOP_H @@ -92,5 +94,12 @@ struct loop_info64 { #define LOOP_SET_STATUS64 0x4C04 #define LOOP_GET_STATUS64 0x4C05 #define LOOP_CHANGE_FD 0x4C06 +#define LOOP_SET_CAPACITY 0x4C07 +#define LOOP_SET_DIRECT_IO 0x4C08 + +/* /dev/loop-control interface */ +#define LOOP_CTL_ADD 0x4C80 +#define LOOP_CTL_REMOVE 0x4C81 +#define LOOP_CTL_GET_FREE 0x4C82 #endif diff --git a/linux-user/signal.c b/linux-user/signal.c index 9d980456ec..9a4d894e3a 100644 --- a/linux-user/signal.c +++ b/linux-user/signal.c @@ -5826,7 +5826,8 @@ long do_rt_sigreturn(CPUArchState *env) #endif -static void handle_pending_signal(CPUArchState *cpu_env, int sig) +static void handle_pending_signal(CPUArchState *cpu_env, int sig, + struct emulated_sigtable *k) { CPUState *cpu = ENV_GET_CPU(cpu_env); abi_ulong handler; @@ -5834,7 +5835,6 @@ static void handle_pending_signal(CPUArchState *cpu_env, int sig) target_sigset_t target_old_set; struct target_sigaction *sa; TaskState *ts = cpu->opaque; - struct emulated_sigtable *k = &ts->sigtab[sig - 1]; trace_user_handle_signal(cpu_env, sig); /* dequeue signal */ @@ -5937,7 +5937,7 @@ void process_pending_signals(CPUArchState *cpu_env) sigact_table[sig - 1]._sa_handler = TARGET_SIG_DFL; } - handle_pending_signal(cpu_env, sig); + handle_pending_signal(cpu_env, sig, &ts->sync_signal); } for (sig = 1; sig <= TARGET_NSIG; sig++) { @@ -5947,7 +5947,7 @@ void process_pending_signals(CPUArchState *cpu_env) if (ts->sigtab[sig - 1].pending && (!sigismember(blocked_set, target_to_host_signal_table[sig]))) { - handle_pending_signal(cpu_env, sig); + handle_pending_signal(cpu_env, sig, &ts->sigtab[sig - 1]); /* Restart scan from the beginning */ sig = 1; } diff --git a/linux-user/sparc/syscall_nr.h b/linux-user/sparc/syscall_nr.h index 732b1052a4..e713c9d5f4 100644 --- a/linux-user/sparc/syscall_nr.h +++ b/linux-user/sparc/syscall_nr.h @@ -179,6 +179,9 @@ #define TARGET_NR_readahead 205 /* Linux Specific */ #define TARGET_NR_socketcall 206 /* Linux Specific */ #define TARGET_NR_syslog 207 /* Linux Specific */ +#define TARGET_NR_lookup_dcookie 208 /* Linux Specific */ +#define TARGET_NR_fadvise64 209 /* Linux Specific */ +#define TARGET_NR_fadvise64_64 210 /* Linux Specific */ #define TARGET_NR_tgkill 211 /* Linux Specific */ #define TARGET_NR_waitpid 212 /* Linux Specific */ #define TARGET_NR_swapoff 213 /* Linux Specific */ diff --git a/linux-user/syscall.c b/linux-user/syscall.c index 8bf6205dc2..ca6a2b495a 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -100,9 +100,11 @@ int __clone2(int (*fn)(void *), void *child_stack_base, #include <linux/route.h> #include <linux/filter.h> #include <linux/blkpg.h> +#include <netpacket/packet.h> #include <linux/netlink.h> #ifdef CONFIG_RTNETLINK #include <linux/rtnetlink.h> +#include <linux/if_bridge.h> #endif #include <linux/audit.h> #include "linux_loop.h" @@ -1374,15 +1376,26 @@ static inline abi_long host_to_target_sockaddr(abi_ulong target_addr, { struct target_sockaddr *target_saddr; + if (len == 0) { + return 0; + } + target_saddr = lock_user(VERIFY_WRITE, target_addr, len, 0); if (!target_saddr) return -TARGET_EFAULT; memcpy(target_saddr, addr, len); - target_saddr->sa_family = tswap16(addr->sa_family); - if (addr->sa_family == AF_NETLINK) { + if (len >= offsetof(struct target_sockaddr, sa_family) + + sizeof(target_saddr->sa_family)) { + target_saddr->sa_family = tswap16(addr->sa_family); + } + if (addr->sa_family == AF_NETLINK && len >= sizeof(struct sockaddr_nl)) { struct sockaddr_nl *target_nl = (struct sockaddr_nl *)target_saddr; target_nl->nl_pid = tswap32(target_nl->nl_pid); target_nl->nl_groups = tswap32(target_nl->nl_groups); + } else if (addr->sa_family == AF_PACKET) { + struct sockaddr_ll *target_ll = (struct sockaddr_ll *)target_saddr; + target_ll->sll_ifindex = tswap32(target_ll->sll_ifindex); + target_ll->sll_hatype = tswap16(target_ll->sll_hatype); } unlock_user(target_saddr, target_addr, len); @@ -1707,6 +1720,33 @@ static abi_long target_to_host_for_each_nlmsg(struct nlmsghdr *nlh, } #ifdef CONFIG_RTNETLINK +static abi_long host_to_target_for_each_nlattr(struct nlattr *nlattr, + size_t len, void *context, + abi_long (*host_to_target_nlattr) + (struct nlattr *, + void *context)) +{ + unsigned short nla_len; + abi_long ret; + + while (len > sizeof(struct nlattr)) { + nla_len = nlattr->nla_len; + if (nla_len < sizeof(struct nlattr) || + nla_len > len) { + break; + } + ret = host_to_target_nlattr(nlattr, context); + nlattr->nla_len = tswap16(nlattr->nla_len); + nlattr->nla_type = tswap16(nlattr->nla_type); + if (ret < 0) { + return ret; + } + len -= NLA_ALIGN(nla_len); + nlattr = (struct nlattr *)(((char *)nlattr) + NLA_ALIGN(nla_len)); + } + return 0; +} + static abi_long host_to_target_for_each_rtattr(struct rtattr *rtattr, size_t len, abi_long (*host_to_target_rtattr) @@ -1733,12 +1773,292 @@ static abi_long host_to_target_for_each_rtattr(struct rtattr *rtattr, return 0; } +#define NLA_DATA(nla) ((void *)((char *)(nla)) + NLA_HDRLEN) + +static abi_long host_to_target_data_bridge_nlattr(struct nlattr *nlattr, + void *context) +{ + uint16_t *u16; + uint32_t *u32; + uint64_t *u64; + + switch (nlattr->nla_type) { + /* no data */ + case IFLA_BR_FDB_FLUSH: + break; + /* binary */ + case IFLA_BR_GROUP_ADDR: + break; + /* uint8_t */ + case IFLA_BR_VLAN_FILTERING: + case IFLA_BR_TOPOLOGY_CHANGE: + case IFLA_BR_TOPOLOGY_CHANGE_DETECTED: + case IFLA_BR_MCAST_ROUTER: + case IFLA_BR_MCAST_SNOOPING: + case IFLA_BR_MCAST_QUERY_USE_IFADDR: + case IFLA_BR_MCAST_QUERIER: + case IFLA_BR_NF_CALL_IPTABLES: + case IFLA_BR_NF_CALL_IP6TABLES: + case IFLA_BR_NF_CALL_ARPTABLES: + break; + /* uint16_t */ + case IFLA_BR_PRIORITY: + case IFLA_BR_VLAN_PROTOCOL: + case IFLA_BR_GROUP_FWD_MASK: + case IFLA_BR_ROOT_PORT: + case IFLA_BR_VLAN_DEFAULT_PVID: + u16 = NLA_DATA(nlattr); + *u16 = tswap16(*u16); + break; + /* uint32_t */ + case IFLA_BR_FORWARD_DELAY: + case IFLA_BR_HELLO_TIME: + case IFLA_BR_MAX_AGE: + case IFLA_BR_AGEING_TIME: + case IFLA_BR_STP_STATE: + case IFLA_BR_ROOT_PATH_COST: + case IFLA_BR_MCAST_HASH_ELASTICITY: + case IFLA_BR_MCAST_HASH_MAX: + case IFLA_BR_MCAST_LAST_MEMBER_CNT: + case IFLA_BR_MCAST_STARTUP_QUERY_CNT: + u32 = NLA_DATA(nlattr); + *u32 = tswap32(*u32); + break; + /* uint64_t */ + case IFLA_BR_HELLO_TIMER: + case IFLA_BR_TCN_TIMER: + case IFLA_BR_GC_TIMER: + case IFLA_BR_TOPOLOGY_CHANGE_TIMER: + case IFLA_BR_MCAST_LAST_MEMBER_INTVL: + case IFLA_BR_MCAST_MEMBERSHIP_INTVL: + case IFLA_BR_MCAST_QUERIER_INTVL: + case IFLA_BR_MCAST_QUERY_INTVL: + case IFLA_BR_MCAST_QUERY_RESPONSE_INTVL: + case IFLA_BR_MCAST_STARTUP_QUERY_INTVL: + u64 = NLA_DATA(nlattr); + *u64 = tswap64(*u64); + break; + /* ifla_bridge_id: uin8_t[] */ + case IFLA_BR_ROOT_ID: + case IFLA_BR_BRIDGE_ID: + break; + default: + gemu_log("Unknown IFLA_BR type %d\n", nlattr->nla_type); + break; + } + return 0; +} + +static abi_long host_to_target_slave_data_bridge_nlattr(struct nlattr *nlattr, + void *context) +{ + uint16_t *u16; + uint32_t *u32; + uint64_t *u64; + + switch (nlattr->nla_type) { + /* uint8_t */ + case IFLA_BRPORT_STATE: + case IFLA_BRPORT_MODE: + case IFLA_BRPORT_GUARD: + case IFLA_BRPORT_PROTECT: + case IFLA_BRPORT_FAST_LEAVE: + case IFLA_BRPORT_LEARNING: + case IFLA_BRPORT_UNICAST_FLOOD: + case IFLA_BRPORT_PROXYARP: + case IFLA_BRPORT_LEARNING_SYNC: + case IFLA_BRPORT_PROXYARP_WIFI: + case IFLA_BRPORT_TOPOLOGY_CHANGE_ACK: + case IFLA_BRPORT_CONFIG_PENDING: + case IFLA_BRPORT_MULTICAST_ROUTER: + break; + /* uint16_t */ + case IFLA_BRPORT_PRIORITY: + case IFLA_BRPORT_DESIGNATED_PORT: + case IFLA_BRPORT_DESIGNATED_COST: + case IFLA_BRPORT_ID: + case IFLA_BRPORT_NO: + u16 = NLA_DATA(nlattr); + *u16 = tswap16(*u16); + break; + /* uin32_t */ + case IFLA_BRPORT_COST: + u32 = NLA_DATA(nlattr); + *u32 = tswap32(*u32); + break; + /* uint64_t */ + case IFLA_BRPORT_MESSAGE_AGE_TIMER: + case IFLA_BRPORT_FORWARD_DELAY_TIMER: + case IFLA_BRPORT_HOLD_TIMER: + u64 = NLA_DATA(nlattr); + *u64 = tswap64(*u64); + break; + /* ifla_bridge_id: uint8_t[] */ + case IFLA_BRPORT_ROOT_ID: + case IFLA_BRPORT_BRIDGE_ID: + break; + default: + gemu_log("Unknown IFLA_BRPORT type %d\n", nlattr->nla_type); + break; + } + return 0; +} + +struct linkinfo_context { + int len; + char *name; + int slave_len; + char *slave_name; +}; + +static abi_long host_to_target_data_linkinfo_nlattr(struct nlattr *nlattr, + void *context) +{ + struct linkinfo_context *li_context = context; + + switch (nlattr->nla_type) { + /* string */ + case IFLA_INFO_KIND: + li_context->name = NLA_DATA(nlattr); + li_context->len = nlattr->nla_len - NLA_HDRLEN; + break; + case IFLA_INFO_SLAVE_KIND: + li_context->slave_name = NLA_DATA(nlattr); + li_context->slave_len = nlattr->nla_len - NLA_HDRLEN; + break; + /* stats */ + case IFLA_INFO_XSTATS: + /* FIXME: only used by CAN */ + break; + /* nested */ + case IFLA_INFO_DATA: + if (strncmp(li_context->name, "bridge", + li_context->len) == 0) { + return host_to_target_for_each_nlattr(NLA_DATA(nlattr), + nlattr->nla_len, + NULL, + host_to_target_data_bridge_nlattr); + } else { + gemu_log("Unknown IFLA_INFO_KIND %s\n", li_context->name); + } + break; + case IFLA_INFO_SLAVE_DATA: + if (strncmp(li_context->slave_name, "bridge", + li_context->slave_len) == 0) { + return host_to_target_for_each_nlattr(NLA_DATA(nlattr), + nlattr->nla_len, + NULL, + host_to_target_slave_data_bridge_nlattr); + } else { + gemu_log("Unknown IFLA_INFO_SLAVE_KIND %s\n", + li_context->slave_name); + } + break; + default: + gemu_log("Unknown host IFLA_INFO type: %d\n", nlattr->nla_type); + break; + } + + return 0; +} + +static abi_long host_to_target_data_inet_nlattr(struct nlattr *nlattr, + void *context) +{ + uint32_t *u32; + int i; + + switch (nlattr->nla_type) { + case IFLA_INET_CONF: + u32 = NLA_DATA(nlattr); + for (i = 0; i < (nlattr->nla_len - NLA_HDRLEN) / sizeof(*u32); + i++) { + u32[i] = tswap32(u32[i]); + } + break; + default: + gemu_log("Unknown host AF_INET type: %d\n", nlattr->nla_type); + } + return 0; +} + +static abi_long host_to_target_data_inet6_nlattr(struct nlattr *nlattr, + void *context) +{ + uint32_t *u32; + uint64_t *u64; + struct ifla_cacheinfo *ci; + int i; + + switch (nlattr->nla_type) { + /* binaries */ + case IFLA_INET6_TOKEN: + break; + /* uint8_t */ + case IFLA_INET6_ADDR_GEN_MODE: + break; + /* uint32_t */ + case IFLA_INET6_FLAGS: + u32 = NLA_DATA(nlattr); + *u32 = tswap32(*u32); + break; + /* uint32_t[] */ + case IFLA_INET6_CONF: + u32 = NLA_DATA(nlattr); + for (i = 0; i < (nlattr->nla_len - NLA_HDRLEN) / sizeof(*u32); + i++) { + u32[i] = tswap32(u32[i]); + } + break; + /* ifla_cacheinfo */ + case IFLA_INET6_CACHEINFO: + ci = NLA_DATA(nlattr); + ci->max_reasm_len = tswap32(ci->max_reasm_len); + ci->tstamp = tswap32(ci->tstamp); + ci->reachable_time = tswap32(ci->reachable_time); + ci->retrans_time = tswap32(ci->retrans_time); + break; + /* uint64_t[] */ + case IFLA_INET6_STATS: + case IFLA_INET6_ICMP6STATS: + u64 = NLA_DATA(nlattr); + for (i = 0; i < (nlattr->nla_len - NLA_HDRLEN) / sizeof(*u64); + i++) { + u64[i] = tswap64(u64[i]); + } + break; + default: + gemu_log("Unknown host AF_INET6 type: %d\n", nlattr->nla_type); + } + return 0; +} + +static abi_long host_to_target_data_spec_nlattr(struct nlattr *nlattr, + void *context) +{ + switch (nlattr->nla_type) { + case AF_INET: + return host_to_target_for_each_nlattr(NLA_DATA(nlattr), nlattr->nla_len, + NULL, + host_to_target_data_inet_nlattr); + case AF_INET6: + return host_to_target_for_each_nlattr(NLA_DATA(nlattr), nlattr->nla_len, + NULL, + host_to_target_data_inet6_nlattr); + default: + gemu_log("Unknown host AF_SPEC type: %d\n", nlattr->nla_type); + break; + } + return 0; +} + static abi_long host_to_target_data_link_rtattr(struct rtattr *rtattr) { uint32_t *u32; struct rtnl_link_stats *st; struct rtnl_link_stats64 *st64; struct rtnl_link_ifmap *map; + struct linkinfo_context li_context; switch (rtattr->rta_type) { /* binary stream */ @@ -1846,11 +2166,15 @@ static abi_long host_to_target_data_link_rtattr(struct rtattr *rtattr) map->irq = tswap16(map->irq); break; /* nested */ - case IFLA_AF_SPEC: case IFLA_LINKINFO: - /* FIXME: implement nested type */ - gemu_log("Unimplemented nested type %d\n", rtattr->rta_type); - break; + memset(&li_context, 0, sizeof(li_context)); + return host_to_target_for_each_nlattr(RTA_DATA(rtattr), rtattr->rta_len, + &li_context, + host_to_target_data_linkinfo_nlattr); + case IFLA_AF_SPEC: + return host_to_target_for_each_nlattr(RTA_DATA(rtattr), rtattr->rta_len, + NULL, + host_to_target_data_spec_nlattr); default: gemu_log("Unknown host IFLA type: %d\n", rtattr->rta_type); break; @@ -2826,12 +3150,26 @@ static TargetFdTrans target_packet_trans = { #ifdef CONFIG_RTNETLINK static abi_long netlink_route_target_to_host(void *buf, size_t len) { - return target_to_host_nlmsg_route(buf, len); + abi_long ret; + + ret = target_to_host_nlmsg_route(buf, len); + if (ret < 0) { + return ret; + } + + return len; } static abi_long netlink_route_host_to_target(void *buf, size_t len) { - return host_to_target_nlmsg_route(buf, len); + abi_long ret; + + ret = host_to_target_nlmsg_route(buf, len); + if (ret < 0) { + return ret; + } + + return len; } static TargetFdTrans target_netlink_route_trans = { @@ -2842,12 +3180,26 @@ static TargetFdTrans target_netlink_route_trans = { static abi_long netlink_audit_target_to_host(void *buf, size_t len) { - return target_to_host_nlmsg_audit(buf, len); + abi_long ret; + + ret = target_to_host_nlmsg_audit(buf, len); + if (ret < 0) { + return ret; + } + + return len; } static abi_long netlink_audit_host_to_target(void *buf, size_t len) { - return host_to_target_nlmsg_audit(buf, len); + abi_long ret; + + ret = host_to_target_nlmsg_audit(buf, len); + if (ret < 0) { + return ret; + } + + return len; } static TargetFdTrans target_netlink_audit_trans = { @@ -2989,13 +3341,22 @@ static abi_long do_sendrecvmsg_locked(int fd, struct target_msghdr *msgp, if (send) { if (fd_trans_target_to_host_data(fd)) { - ret = fd_trans_target_to_host_data(fd)(msg.msg_iov->iov_base, + void *host_msg; + + host_msg = g_malloc(msg.msg_iov->iov_len); + memcpy(host_msg, msg.msg_iov->iov_base, msg.msg_iov->iov_len); + ret = fd_trans_target_to_host_data(fd)(host_msg, msg.msg_iov->iov_len); + if (ret >= 0) { + msg.msg_iov->iov_base = host_msg; + ret = get_errno(safe_sendmsg(fd, &msg, flags)); + } + g_free(host_msg); } else { ret = target_to_host_cmsg(&msg, msgp); - } - if (ret == 0) { - ret = get_errno(safe_sendmsg(fd, &msg, flags)); + if (ret == 0) { + ret = get_errno(safe_sendmsg(fd, &msg, flags)); + } } } else { ret = get_errno(safe_recvmsg(fd, &msg, flags)); @@ -3211,6 +3572,7 @@ static abi_long do_sendto(int fd, abi_ulong msg, size_t len, int flags, { void *addr; void *host_msg; + void *copy_msg = NULL; abi_long ret; if ((int)addrlen < 0) { @@ -3221,23 +3583,29 @@ static abi_long do_sendto(int fd, abi_ulong msg, size_t len, int flags, if (!host_msg) return -TARGET_EFAULT; if (fd_trans_target_to_host_data(fd)) { + copy_msg = host_msg; + host_msg = g_malloc(len); + memcpy(host_msg, copy_msg, len); ret = fd_trans_target_to_host_data(fd)(host_msg, len); if (ret < 0) { - unlock_user(host_msg, msg, 0); - return ret; + goto fail; } } if (target_addr) { addr = alloca(addrlen+1); ret = target_to_host_sockaddr(fd, addr, target_addr, addrlen); if (ret) { - unlock_user(host_msg, msg, 0); - return ret; + goto fail; } ret = get_errno(safe_sendto(fd, host_msg, len, flags, addr, addrlen)); } else { ret = get_errno(safe_sendto(fd, host_msg, len, flags, NULL, 0)); } +fail: + if (copy_msg) { + g_free(host_msg); + host_msg = copy_msg; + } unlock_user(host_msg, msg, 0); return ret; } @@ -3272,6 +3640,9 @@ static abi_long do_recvfrom(int fd, abi_ulong msg, size_t len, int flags, ret = get_errno(safe_recvfrom(fd, host_msg, len, flags, NULL, 0)); } if (!is_error(ret)) { + if (fd_trans_host_to_target_data(fd)) { + ret = fd_trans_host_to_target_data(fd)(host_msg, ret); + } if (target_addr) { host_to_target_sockaddr(target_addr, addr, addrlen); if (put_user_u32(addrlen, target_addrlen)) { @@ -7614,7 +7985,11 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, #if defined(TARGET_ALPHA) struct target_sigaction act, oact, *pact = 0; struct target_rt_sigaction *rt_act; - /* ??? arg4 == sizeof(sigset_t). */ + + if (arg4 != sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } if (arg2) { if (!lock_user_struct(VERIFY_READ, rt_act, arg2, 1)) goto efault; @@ -7638,6 +8013,10 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, struct target_sigaction *act; struct target_sigaction *oact; + if (arg4 != sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } if (arg2) { if (!lock_user_struct(VERIFY_READ, act, arg2, 1)) goto efault; @@ -7769,6 +8148,11 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, int how = arg1; sigset_t set, oldset, *set_ptr; + if (arg4 != sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } + if (arg2) { switch(how) { case TARGET_SIG_BLOCK: @@ -7819,6 +8203,17 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, case TARGET_NR_rt_sigpending: { sigset_t set; + + /* Yes, this check is >, not != like most. We follow the kernel's + * logic and it does it like this because it implements + * NR_sigpending through the same code path, and in that case + * the old_sigset_t is smaller in size. + */ + if (arg2 > sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } + ret = get_errno(sigpending(&set)); if (!is_error(ret)) { if (!(p = lock_user(VERIFY_WRITE, arg1, sizeof(target_sigset_t), 0))) @@ -7852,6 +8247,11 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, case TARGET_NR_rt_sigsuspend: { TaskState *ts = cpu->opaque; + + if (arg2 != sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } if (!(p = lock_user(VERIFY_READ, arg1, sizeof(target_sigset_t), 1))) goto efault; target_to_host_sigset(&ts->sigsuspend_mask, p); @@ -7869,6 +8269,11 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, struct timespec uts, *puts; siginfo_t uinfo; + if (arg4 != sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } + if (!(p = lock_user(VERIFY_READ, arg1, sizeof(target_sigset_t), 1))) goto efault; target_to_host_sigset(&set, p); @@ -9120,6 +9525,12 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, } if (arg4) { + if (arg5 != sizeof(target_sigset_t)) { + unlock_user(target_pfd, arg1, 0); + ret = -TARGET_EINVAL; + break; + } + target_set = lock_user(VERIFY_READ, arg4, sizeof(target_sigset_t), 1); if (!target_set) { unlock_user(target_pfd, arg1, 0); @@ -10939,6 +11350,11 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, sigset_t _set, *set = &_set; if (arg5) { + if (arg6 != sizeof(target_sigset_t)) { + ret = -TARGET_EINVAL; + break; + } + target_set = lock_user(VERIFY_READ, arg5, sizeof(target_sigset_t), 1); if (!target_set) { diff --git a/linux-user/syscall_defs.h b/linux-user/syscall_defs.h index b43966ece0..783565463f 100644 --- a/linux-user/syscall_defs.h +++ b/linux-user/syscall_defs.h @@ -985,6 +985,17 @@ struct target_pollfd { #define TARGET_BLKGETSIZE64 TARGET_IOR(0x12,114,abi_ulong) /* return device size in bytes (u64 *arg) */ + +#define TARGET_BLKDISCARD TARGET_IO(0x12, 119) +#define TARGET_BLKIOMIN TARGET_IO(0x12, 120) +#define TARGET_BLKIOOPT TARGET_IO(0x12, 121) +#define TARGET_BLKALIGNOFF TARGET_IO(0x12, 122) +#define TARGET_BLKPBSZGET TARGET_IO(0x12, 123) +#define TARGET_BLKDISCARDZEROES TARGET_IO(0x12, 124) +#define TARGET_BLKSECDISCARD TARGET_IO(0x12, 125) +#define TARGET_BLKROTATIONAL TARGET_IO(0x12, 126) +#define TARGET_BLKZEROOUT TARGET_IO(0x12, 127) + #define TARGET_FIBMAP TARGET_IO(0x00,1) /* bmap access */ #define TARGET_FIGETBSZ TARGET_IO(0x00,2) /* get the block size used for bmap */ #define TARGET_FS_IOC_FIEMAP TARGET_IOWR('f',11,struct fiemap) @@ -1117,6 +1128,10 @@ struct target_pollfd { #define TARGET_LOOP_GET_STATUS64 0x4C05 #define TARGET_LOOP_CHANGE_FD 0x4C06 +#define TARGET_LOOP_CTL_ADD 0x4C80 +#define TARGET_LOOP_CTL_REMOVE 0x4C81 +#define TARGET_LOOP_CTL_GET_FREE 0x4C82 + /* fb ioctls */ #define TARGET_FBIOGET_VSCREENINFO 0x4600 #define TARGET_FBIOPUT_VSCREENINFO 0x4601 diff --git a/linux-user/syscall_types.h b/linux-user/syscall_types.h index 1fd4ee0bfd..af79fbf1de 100644 --- a/linux-user/syscall_types.h +++ b/linux-user/syscall_types.h @@ -103,10 +103,11 @@ STRUCT(loop_info64, TYPE_ULONGLONG, /* lo_inode */ TYPE_ULONGLONG, /* lo_rdevice */ TYPE_ULONGLONG, /* lo_offset */ - TYPE_ULONG, /* lo_number */ - TYPE_ULONG, /* lo_encrypt_type */ - TYPE_ULONG, /* lo_encrypt_key_size */ - TYPE_ULONG, /* lo_flags */ + TYPE_ULONGLONG, /* lo_sizelimit */ + TYPE_INT, /* lo_number */ + TYPE_INT, /* lo_encrypt_type */ + TYPE_INT, /* lo_encrypt_key_size */ + TYPE_INT, /* lo_flags */ MK_ARRAY(TYPE_CHAR, 64), /* lo_name */ MK_ARRAY(TYPE_CHAR, 64), /* lo_crypt_name */ MK_ARRAY(TYPE_CHAR, 32), /* lo_encrypt_key */ diff --git a/linux-user/x86_64/termbits.h b/linux-user/x86_64/termbits.h index 1c3445c6a2..387e742592 100644 --- a/linux-user/x86_64/termbits.h +++ b/linux-user/x86_64/termbits.h @@ -209,12 +209,12 @@ struct target_termios { #define TARGET_TIOCSBRK 0x5427 /* BSD compatibility */ #define TARGET_TIOCCBRK 0x5428 /* BSD compatibility */ #define TARGET_TIOCGSID 0x5429 /* Return the session ID of FD */ -#define TARGET_TCGETS2 _IOR('T',0x2A, struct termios2) -#define TARGET_TCSETS2 _IOW('T',0x2B, struct termios2) -#define TARGET_TCSETSW2 _IOW('T',0x2C, struct termios2) -#define TARGET_TCSETSF2 _IOW('T',0x2D, struct termios2) -#define TARGET_TIOCGPTN _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ -#define TARGET_TIOCSPTLCK _IOW('T',0x31, int) /* Lock/unlock Pty */ +#define TARGET_TCGETS2 TARGET_IOR('T',0x2A, struct termios2) +#define TARGET_TCSETS2 TARGET_IOW('T',0x2B, struct termios2) +#define TARGET_TCSETSW2 TARGET_IOW('T',0x2C, struct termios2) +#define TARGET_TCSETSF2 TARGET_IOW('T',0x2D, struct termios2) +#define TARGET_TIOCGPTN TARGET_IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ +#define TARGET_TIOCSPTLCK TARGET_IOW('T',0x31, int) /* Lock/unlock Pty */ #define TARGET_FIONCLEX 0x5450 /* these numbers need to be adjusted. */ #define TARGET_FIOCLEX 0x5451 @@ -3080,8 +3080,8 @@ void netdev_add_completion(ReadLineState *rs, int nb_args, const char *str) } len = strlen(str); readline_set_completion_index(rs, len); - for (i = 0; NetClientOptionsKind_lookup[i]; i++) { - add_completion_option(rs, str, NetClientOptionsKind_lookup[i]); + for (i = 0; NetClientDriver_lookup[i]; i++) { + add_completion_option(rs, str, NetClientDriver_lookup[i]); } } @@ -3281,7 +3281,7 @@ void set_link_completion(ReadLineState *rs, int nb_args, const char *str) NetClientState *ncs[MAX_QUEUE_NUM]; int count, i; count = qemu_find_net_clients_except(NULL, ncs, - NET_CLIENT_OPTIONS_KIND_NONE, + NET_CLIENT_DRIVER_NONE, MAX_QUEUE_NUM); for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) { const char *name = ncs[i]->name; @@ -3306,7 +3306,7 @@ void netdev_del_completion(ReadLineState *rs, int nb_args, const char *str) len = strlen(str); readline_set_completion_index(rs, len); - count = qemu_find_net_clients_except(NULL, ncs, NET_CLIENT_OPTIONS_KIND_NIC, + count = qemu_find_net_clients_except(NULL, ncs, NET_CLIENT_DRIVER_NIC, MAX_QUEUE_NUM); for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) { QemuOpts *opts; @@ -3435,7 +3435,7 @@ void host_net_remove_completion(ReadLineState *rs, int nb_args, const char *str) readline_set_completion_index(rs, len); if (nb_args == 2) { count = qemu_find_net_clients_except(NULL, ncs, - NET_CLIENT_OPTIONS_KIND_NONE, + NET_CLIENT_DRIVER_NONE, MAX_QUEUE_NUM); for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) { int id; @@ -3452,13 +3452,13 @@ void host_net_remove_completion(ReadLineState *rs, int nb_args, const char *str) return; } else if (nb_args == 3) { count = qemu_find_net_clients_except(NULL, ncs, - NET_CLIENT_OPTIONS_KIND_NIC, + NET_CLIENT_DRIVER_NIC, MAX_QUEUE_NUM); for (i = 0; i < MIN(count, MAX_QUEUE_NUM); i++) { int id; const char *name; - if (ncs[i]->info->type == NET_CLIENT_OPTIONS_KIND_HUBPORT || + if (ncs[i]->info->type == NET_CLIENT_DRIVER_HUBPORT || net_hub_id_for_client(ncs[i], &id)) { continue; } diff --git a/nbd/common.c b/nbd/common.c index 8ddb2dd2f0..b583a4f4cf 100644 --- a/nbd/common.c +++ b/nbd/common.c @@ -23,7 +23,6 @@ ssize_t nbd_wr_syncv(QIOChannel *ioc, struct iovec *iov, size_t niov, - size_t offset, size_t length, bool do_read) { @@ -33,9 +32,7 @@ ssize_t nbd_wr_syncv(QIOChannel *ioc, struct iovec *local_iov_head = local_iov; unsigned int nlocal_iov = niov; - nlocal_iov = iov_copy(local_iov, nlocal_iov, - iov, niov, - offset, length); + nlocal_iov = iov_copy(local_iov, nlocal_iov, iov, niov, 0, length); while (nlocal_iov > 0) { ssize_t len; diff --git a/nbd/nbd-internal.h b/nbd/nbd-internal.h index 26a9f4d9fd..93a6ca8549 100644 --- a/nbd/nbd-internal.h +++ b/nbd/nbd-internal.h @@ -101,14 +101,14 @@ static inline ssize_t read_sync(QIOChannel *ioc, void *buffer, size_t size) * our request/reply. Synchronization is done with recv_coroutine, so * that this is coroutine-safe. */ - return nbd_wr_syncv(ioc, &iov, 1, 0, size, true); + return nbd_wr_syncv(ioc, &iov, 1, size, true); } static inline ssize_t write_sync(QIOChannel *ioc, void *buffer, size_t size) { struct iovec iov = { .iov_base = buffer, .iov_len = size }; - return nbd_wr_syncv(ioc, &iov, 1, 0, size, false); + return nbd_wr_syncv(ioc, &iov, 1, size, false); } struct NBDTLSHandshakeData { diff --git a/nbd/server.c b/nbd/server.c index fbc82de932..29e2099b5e 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -1182,20 +1182,11 @@ static void nbd_trip(void *opaque) break; case NBD_CMD_TRIM: TRACE("Request type is TRIM"); - /* Ignore unaligned head or tail, until block layer adds byte - * interface */ - if (request.len >= BDRV_SECTOR_SIZE) { - request.len -= (request.from + request.len) % BDRV_SECTOR_SIZE; - ret = blk_co_discard(exp->blk, - DIV_ROUND_UP(request.from + exp->dev_offset, - BDRV_SECTOR_SIZE), - request.len / BDRV_SECTOR_SIZE); - if (ret < 0) { - LOG("discard failed"); - reply.error = -ret; - } - } else { - TRACE("trim request too small, ignoring"); + ret = blk_co_pdiscard(exp->blk, request.from + exp->dev_offset, + request.len); + if (ret < 0) { + LOG("discard failed"); + reply.error = -ret; } if (nbd_co_send_reply(req, &reply, 0) < 0) { goto out; diff --git a/net/clients.h b/net/clients.h index d47530e82f..5cae479730 100644 --- a/net/clients.h +++ b/net/clients.h @@ -27,39 +27,39 @@ #include "net/net.h" #include "qapi-types.h" -int net_init_dump(const NetClientOptions *opts, const char *name, +int net_init_dump(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); #ifdef CONFIG_SLIRP -int net_init_slirp(const NetClientOptions *opts, const char *name, +int net_init_slirp(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); #endif -int net_init_hubport(const NetClientOptions *opts, const char *name, +int net_init_hubport(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); -int net_init_socket(const NetClientOptions *opts, const char *name, +int net_init_socket(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); -int net_init_tap(const NetClientOptions *opts, const char *name, +int net_init_tap(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); -int net_init_bridge(const NetClientOptions *opts, const char *name, +int net_init_bridge(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); -int net_init_l2tpv3(const NetClientOptions *opts, const char *name, +int net_init_l2tpv3(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); #ifdef CONFIG_VDE -int net_init_vde(const NetClientOptions *opts, const char *name, +int net_init_vde(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); #endif #ifdef CONFIG_NETMAP -int net_init_netmap(const NetClientOptions *opts, const char *name, +int net_init_netmap(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); #endif -int net_init_vhost_user(const NetClientOptions *opts, const char *name, +int net_init_vhost_user(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp); #endif /* QEMU_NET_CLIENTS_H */ diff --git a/net/dump.c b/net/dump.c index 41f7673efd..89a149b5dd 100644 --- a/net/dump.c +++ b/net/dump.c @@ -172,14 +172,14 @@ static void dumpclient_cleanup(NetClientState *nc) } static NetClientInfo net_dump_info = { - .type = NET_CLIENT_OPTIONS_KIND_DUMP, + .type = NET_CLIENT_DRIVER_DUMP, .size = sizeof(DumpNetClient), .receive = dumpclient_receive, .receive_iov = dumpclient_receive_iov, .cleanup = dumpclient_cleanup, }; -int net_init_dump(const NetClientOptions *opts, const char *name, +int net_init_dump(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { int len, rc; @@ -189,8 +189,8 @@ int net_init_dump(const NetClientOptions *opts, const char *name, NetClientState *nc; DumpNetClient *dnc; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_DUMP); - dump = opts->u.dump.data; + assert(netdev->type == NET_CLIENT_DRIVER_DUMP); + dump = &netdev->u.dump; assert(peer); diff --git a/net/filter.c b/net/filter.c index 8ac79f3b7b..888fe6dd93 100644 --- a/net/filter.c +++ b/net/filter.c @@ -201,7 +201,7 @@ static void netfilter_complete(UserCreatable *uc, Error **errp) } queues = qemu_find_net_clients_except(nf->netdev_id, ncs, - NET_CLIENT_OPTIONS_KIND_NIC, + NET_CLIENT_DRIVER_NIC, MAX_QUEUE_NUM); if (queues < 1) { error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "netdev", @@ -131,7 +131,7 @@ static void net_hub_port_cleanup(NetClientState *nc) } static NetClientInfo net_hub_port_info = { - .type = NET_CLIENT_OPTIONS_KIND_HUBPORT, + .type = NET_CLIENT_DRIVER_HUBPORT, .size = sizeof(NetHubPort), .can_receive = net_hub_port_can_receive, .receive = net_hub_port_receive, @@ -266,10 +266,10 @@ int net_hub_id_for_client(NetClientState *nc, int *id) { NetHubPort *port; - if (nc->info->type == NET_CLIENT_OPTIONS_KIND_HUBPORT) { + if (nc->info->type == NET_CLIENT_DRIVER_HUBPORT) { port = DO_UPCAST(NetHubPort, nc, nc); } else if (nc->peer != NULL && nc->peer->info->type == - NET_CLIENT_OPTIONS_KIND_HUBPORT) { + NET_CLIENT_DRIVER_HUBPORT) { port = DO_UPCAST(NetHubPort, nc, nc->peer); } else { return -ENOENT; @@ -281,14 +281,14 @@ int net_hub_id_for_client(NetClientState *nc, int *id) return 0; } -int net_init_hubport(const NetClientOptions *opts, const char *name, +int net_init_hubport(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { const NetdevHubPortOptions *hubport; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_HUBPORT); + assert(netdev->type == NET_CLIENT_DRIVER_HUBPORT); assert(!peer); - hubport = opts->u.hubport.data; + hubport = &netdev->u.hubport; net_hub_add_port(hubport->hubid, name); return 0; @@ -315,14 +315,14 @@ void net_hub_check_clients(void) } switch (peer->info->type) { - case NET_CLIENT_OPTIONS_KIND_NIC: + case NET_CLIENT_DRIVER_NIC: has_nic = 1; break; - case NET_CLIENT_OPTIONS_KIND_USER: - case NET_CLIENT_OPTIONS_KIND_TAP: - case NET_CLIENT_OPTIONS_KIND_SOCKET: - case NET_CLIENT_OPTIONS_KIND_VDE: - case NET_CLIENT_OPTIONS_KIND_VHOST_USER: + case NET_CLIENT_DRIVER_USER: + case NET_CLIENT_DRIVER_TAP: + case NET_CLIENT_DRIVER_SOCKET: + case NET_CLIENT_DRIVER_VDE: + case NET_CLIENT_DRIVER_VHOST_USER: has_host_dev = 1; break; default: diff --git a/net/l2tpv3.c b/net/l2tpv3.c index 5c668f7376..6745b78990 100644 --- a/net/l2tpv3.c +++ b/net/l2tpv3.c @@ -516,7 +516,7 @@ static void net_l2tpv3_cleanup(NetClientState *nc) } static NetClientInfo net_l2tpv3_info = { - .type = NET_CLIENT_OPTIONS_KIND_L2TPV3, + .type = NET_CLIENT_DRIVER_L2TPV3, .size = sizeof(NetL2TPV3State), .receive = net_l2tpv3_receive_dgram, .receive_iov = net_l2tpv3_receive_dgram_iov, @@ -524,7 +524,7 @@ static NetClientInfo net_l2tpv3_info = { .cleanup = net_l2tpv3_cleanup, }; -int net_init_l2tpv3(const NetClientOptions *opts, +int net_init_l2tpv3(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { @@ -545,8 +545,8 @@ int net_init_l2tpv3(const NetClientOptions *opts, s->queue_tail = 0; s->header_mismatch = false; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_L2TPV3); - l2tpv3 = opts->u.l2tpv3.data; + assert(netdev->type == NET_CLIENT_DRIVER_L2TPV3); + l2tpv3 = &netdev->u.l2tpv3; if (l2tpv3->has_ipv6 && l2tpv3->ipv6) { s->ipv6 = l2tpv3->ipv6; @@ -289,7 +289,7 @@ NICState *qemu_new_nic(NetClientInfo *info, NICState *nic; int i, queues = MAX(1, conf->peers.queues); - assert(info->type == NET_CLIENT_OPTIONS_KIND_NIC); + assert(info->type == NET_CLIENT_DRIVER_NIC); assert(info->size >= sizeof(NICState)); nic = g_malloc0(info->size + sizeof(NetClientState) * queues); @@ -360,13 +360,13 @@ void qemu_del_net_client(NetClientState *nc) int queues, i; NetFilterState *nf, *next; - assert(nc->info->type != NET_CLIENT_OPTIONS_KIND_NIC); + assert(nc->info->type != NET_CLIENT_DRIVER_NIC); /* If the NetClientState belongs to a multiqueue backend, we will change all * other NetClientStates also. */ queues = qemu_find_net_clients_except(nc->name, ncs, - NET_CLIENT_OPTIONS_KIND_NIC, + NET_CLIENT_DRIVER_NIC, MAX_QUEUE_NUM); assert(queues != 0); @@ -375,7 +375,7 @@ void qemu_del_net_client(NetClientState *nc) } /* If there is a peer NIC, delete and cleanup client, but do not free. */ - if (nc->peer && nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_NIC) { NICState *nic = qemu_get_nic(nc->peer); if (nic->peer_deleted) { return; @@ -431,7 +431,7 @@ void qemu_foreach_nic(qemu_nic_foreach func, void *opaque) NetClientState *nc; QTAILQ_FOREACH(nc, &net_clients, next) { - if (nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (nc->info->type == NET_CLIENT_DRIVER_NIC) { if (nc->queue_index == 0) { func(qemu_get_nic(nc), opaque); } @@ -603,7 +603,7 @@ void qemu_flush_or_purge_queued_packets(NetClientState *nc, bool purge) { nc->receive_disabled = 0; - if (nc->peer && nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_HUBPORT) { + if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_HUBPORT) { if (net_hub_flush(nc->peer)) { qemu_notify_event(); } @@ -777,7 +777,7 @@ NetClientState *qemu_find_netdev(const char *id) NetClientState *nc; QTAILQ_FOREACH(nc, &net_clients, next) { - if (nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) + if (nc->info->type == NET_CLIENT_DRIVER_NIC) continue; if (!strcmp(nc->name, id)) { return nc; @@ -788,7 +788,7 @@ NetClientState *qemu_find_netdev(const char *id) } int qemu_find_net_clients_except(const char *id, NetClientState **ncs, - NetClientOptionsKind type, int max) + NetClientDriver type, int max) { NetClientState *nc; int ret = 0; @@ -862,15 +862,15 @@ int qemu_find_nic_model(NICInfo *nd, const char * const *models, return -1; } -static int net_init_nic(const NetClientOptions *opts, const char *name, +static int net_init_nic(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { int idx; NICInfo *nd; const NetLegacyNicOptions *nic; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_NIC); - nic = opts->u.nic.data; + assert(netdev->type == NET_CLIENT_DRIVER_NIC); + nic = &netdev->u.nic; idx = nic_get_free_idx(); if (idx == -1 || nb_nics >= MAX_NICS) { @@ -930,70 +930,111 @@ static int net_init_nic(const NetClientOptions *opts, const char *name, } -static int (* const net_client_init_fun[NET_CLIENT_OPTIONS_KIND__MAX])( - const NetClientOptions *opts, +static int (* const net_client_init_fun[NET_CLIENT_DRIVER__MAX])( + const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) = { - [NET_CLIENT_OPTIONS_KIND_NIC] = net_init_nic, + [NET_CLIENT_DRIVER_NIC] = net_init_nic, #ifdef CONFIG_SLIRP - [NET_CLIENT_OPTIONS_KIND_USER] = net_init_slirp, + [NET_CLIENT_DRIVER_USER] = net_init_slirp, #endif - [NET_CLIENT_OPTIONS_KIND_TAP] = net_init_tap, - [NET_CLIENT_OPTIONS_KIND_SOCKET] = net_init_socket, + [NET_CLIENT_DRIVER_TAP] = net_init_tap, + [NET_CLIENT_DRIVER_SOCKET] = net_init_socket, #ifdef CONFIG_VDE - [NET_CLIENT_OPTIONS_KIND_VDE] = net_init_vde, + [NET_CLIENT_DRIVER_VDE] = net_init_vde, #endif #ifdef CONFIG_NETMAP - [NET_CLIENT_OPTIONS_KIND_NETMAP] = net_init_netmap, + [NET_CLIENT_DRIVER_NETMAP] = net_init_netmap, #endif - [NET_CLIENT_OPTIONS_KIND_DUMP] = net_init_dump, + [NET_CLIENT_DRIVER_DUMP] = net_init_dump, #ifdef CONFIG_NET_BRIDGE - [NET_CLIENT_OPTIONS_KIND_BRIDGE] = net_init_bridge, + [NET_CLIENT_DRIVER_BRIDGE] = net_init_bridge, #endif - [NET_CLIENT_OPTIONS_KIND_HUBPORT] = net_init_hubport, + [NET_CLIENT_DRIVER_HUBPORT] = net_init_hubport, #ifdef CONFIG_VHOST_NET_USED - [NET_CLIENT_OPTIONS_KIND_VHOST_USER] = net_init_vhost_user, + [NET_CLIENT_DRIVER_VHOST_USER] = net_init_vhost_user, #endif #ifdef CONFIG_L2TPV3 - [NET_CLIENT_OPTIONS_KIND_L2TPV3] = net_init_l2tpv3, + [NET_CLIENT_DRIVER_L2TPV3] = net_init_l2tpv3, #endif }; -static int net_client_init1(const void *object, int is_netdev, Error **errp) +static int net_client_init1(const void *object, bool is_netdev, Error **errp) { - const NetClientOptions *opts; + Netdev legacy = {0}; + const Netdev *netdev; const char *name; NetClientState *peer = NULL; if (is_netdev) { - const Netdev *netdev = object; - opts = netdev->opts; + netdev = object; name = netdev->id; - if (opts->type == NET_CLIENT_OPTIONS_KIND_DUMP || - opts->type == NET_CLIENT_OPTIONS_KIND_NIC || - !net_client_init_fun[opts->type]) { + if (netdev->type == NET_CLIENT_DRIVER_DUMP || + netdev->type == NET_CLIENT_DRIVER_NIC || + !net_client_init_fun[netdev->type]) { error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type", "a netdev backend type"); return -1; } } else { const NetLegacy *net = object; - opts = net->opts; + const NetLegacyOptions *opts = net->opts; + legacy.id = net->id; + netdev = &legacy; /* missing optional values have been initialized to "all bits zero" */ name = net->has_id ? net->id : net->name; - if (opts->type == NET_CLIENT_OPTIONS_KIND_NONE) { + /* Map the old options to the new flat type */ + switch (opts->type) { + case NET_LEGACY_OPTIONS_KIND_NONE: return 0; /* nothing to do */ - } - if (opts->type == NET_CLIENT_OPTIONS_KIND_HUBPORT) { - error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type", - "a net type"); - return -1; + case NET_LEGACY_OPTIONS_KIND_NIC: + legacy.type = NET_CLIENT_DRIVER_NIC; + legacy.u.nic = *opts->u.nic.data; + break; + case NET_LEGACY_OPTIONS_KIND_USER: + legacy.type = NET_CLIENT_DRIVER_USER; + legacy.u.user = *opts->u.user.data; + break; + case NET_LEGACY_OPTIONS_KIND_TAP: + legacy.type = NET_CLIENT_DRIVER_TAP; + legacy.u.tap = *opts->u.tap.data; + break; + case NET_LEGACY_OPTIONS_KIND_L2TPV3: + legacy.type = NET_CLIENT_DRIVER_L2TPV3; + legacy.u.l2tpv3 = *opts->u.l2tpv3.data; + break; + case NET_LEGACY_OPTIONS_KIND_SOCKET: + legacy.type = NET_CLIENT_DRIVER_SOCKET; + legacy.u.socket = *opts->u.socket.data; + break; + case NET_LEGACY_OPTIONS_KIND_VDE: + legacy.type = NET_CLIENT_DRIVER_VDE; + legacy.u.vde = *opts->u.vde.data; + break; + case NET_LEGACY_OPTIONS_KIND_DUMP: + legacy.type = NET_CLIENT_DRIVER_DUMP; + legacy.u.dump = *opts->u.dump.data; + break; + case NET_LEGACY_OPTIONS_KIND_BRIDGE: + legacy.type = NET_CLIENT_DRIVER_BRIDGE; + legacy.u.bridge = *opts->u.bridge.data; + break; + case NET_LEGACY_OPTIONS_KIND_NETMAP: + legacy.type = NET_CLIENT_DRIVER_NETMAP; + legacy.u.netmap = *opts->u.netmap.data; + break; + case NET_LEGACY_OPTIONS_KIND_VHOST_USER: + legacy.type = NET_CLIENT_DRIVER_VHOST_USER; + legacy.u.vhost_user = *opts->u.vhost_user.data; + break; + default: + abort(); } - if (!net_client_init_fun[opts->type]) { + if (!net_client_init_fun[netdev->type]) { error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "type", "a net backend type (maybe it is not compiled " "into this binary)"); @@ -1001,17 +1042,17 @@ static int net_client_init1(const void *object, int is_netdev, Error **errp) } /* Do not add to a vlan if it's a nic with a netdev= parameter. */ - if (opts->type != NET_CLIENT_OPTIONS_KIND_NIC || + if (netdev->type != NET_CLIENT_DRIVER_NIC || !opts->u.nic.data->has_netdev) { peer = net_hub_add_port(net->has_vlan ? net->vlan : 0, NULL); } } - if (net_client_init_fun[opts->type](opts, name, peer, errp) < 0) { + if (net_client_init_fun[netdev->type](netdev, name, peer, errp) < 0) { /* FIXME drop when all init functions store an Error */ if (errp && !*errp) { error_setg(errp, QERR_DEVICE_INIT_FAILED, - NetClientOptionsKind_lookup[opts->type]); + NetClientDriver_lookup[netdev->type]); } return -1; } @@ -1019,7 +1060,7 @@ static int net_client_init1(const void *object, int is_netdev, Error **errp) } -int net_client_init(QemuOpts *opts, int is_netdev, Error **errp) +int net_client_init(QemuOpts *opts, bool is_netdev, Error **errp) { void *object = NULL; Error *err = NULL; @@ -1112,7 +1153,7 @@ void hmp_host_net_add(Monitor *mon, const QDict *qdict) qemu_opt_set(opts, "type", device, &error_abort); - net_client_init(opts, 0, &local_err); + net_client_init(opts, false, &local_err); if (local_err) { error_report_err(local_err); monitor_printf(mon, "adding host network device %s failed\n", device); @@ -1131,7 +1172,7 @@ void hmp_host_net_remove(Monitor *mon, const QDict *qdict) device, vlan_id); return; } - if (nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (nc->info->type == NET_CLIENT_DRIVER_NIC) { error_report("invalid host network device '%s'", device); return; } @@ -1142,7 +1183,7 @@ void hmp_host_net_remove(Monitor *mon, const QDict *qdict) void netdev_add(QemuOpts *opts, Error **errp) { - net_client_init(opts, 1, errp); + net_client_init(opts, true, errp); } void qmp_netdev_add(QDict *qdict, QObject **ret, Error **errp) @@ -1222,7 +1263,7 @@ void print_net_client(Monitor *mon, NetClientState *nc) monitor_printf(mon, "%s: index=%d,type=%s,%s\n", nc->name, nc->queue_index, - NetClientOptionsKind_lookup[nc->info->type], + NetClientDriver_lookup[nc->info->type], nc->info_str); if (!QTAILQ_EMPTY(&nc->filters)) { monitor_printf(mon, "filters:\n"); @@ -1252,7 +1293,7 @@ RxFilterInfoList *qmp_query_rx_filter(bool has_name, const char *name, } /* only query rx-filter information of NIC */ - if (nc->info->type != NET_CLIENT_OPTIONS_KIND_NIC) { + if (nc->info->type != NET_CLIENT_DRIVER_NIC) { if (has_name) { error_setg(errp, "net client(%s) isn't a NIC", name); return NULL; @@ -1298,7 +1339,7 @@ RxFilterInfoList *qmp_query_rx_filter(bool has_name, const char *name, void hmp_info_network(Monitor *mon, const QDict *qdict) { NetClientState *nc, *peer; - NetClientOptionsKind type; + NetClientDriver type; net_hub_info(mon); @@ -1311,10 +1352,10 @@ void hmp_info_network(Monitor *mon, const QDict *qdict) continue; } - if (!peer || type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (!peer || type == NET_CLIENT_DRIVER_NIC) { print_net_client(mon, nc); } /* else it's a netdev connected to a NIC, printed with the NIC */ - if (peer && type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (peer && type == NET_CLIENT_DRIVER_NIC) { monitor_printf(mon, " \\ "); print_net_client(mon, peer); } @@ -1328,7 +1369,7 @@ void qmp_set_link(const char *name, bool up, Error **errp) int queues, i; queues = qemu_find_net_clients_except(name, ncs, - NET_CLIENT_OPTIONS_KIND__MAX, + NET_CLIENT_DRIVER__MAX, MAX_QUEUE_NUM); if (queues == 0) { @@ -1355,7 +1396,7 @@ void qmp_set_link(const char *name, bool up, Error **errp) * multiple clients that can still communicate with each other in * disconnected mode. For now maintain this compatibility. */ - if (nc->peer->info->type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (nc->peer->info->type == NET_CLIENT_DRIVER_NIC) { for (i = 0; i < queues; i++) { ncs[i]->peer->link_down = !up; } @@ -1396,7 +1437,7 @@ void net_cleanup(void) */ while (!QTAILQ_EMPTY(&net_clients)) { nc = QTAILQ_FIRST(&net_clients); - if (nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC) { + if (nc->info->type == NET_CLIENT_DRIVER_NIC) { qemu_del_nic(qemu_get_nic(nc)); } else { qemu_del_net_client(nc); @@ -1416,7 +1457,7 @@ void net_check_clients(void) QTAILQ_FOREACH(nc, &net_clients, next) { if (!nc->peer) { fprintf(stderr, "Warning: %s %s has no peer\n", - nc->info->type == NET_CLIENT_OPTIONS_KIND_NIC ? + nc->info->type == NET_CLIENT_DRIVER_NIC ? "nic" : "netdev", nc->name); } } @@ -1440,7 +1481,7 @@ static int net_init_client(void *dummy, QemuOpts *opts, Error **errp) { Error *local_err = NULL; - net_client_init(opts, 0, &local_err); + net_client_init(opts, false, &local_err); if (local_err) { error_report_err(local_err); return -1; @@ -1454,7 +1495,7 @@ static int net_init_netdev(void *dummy, QemuOpts *opts, Error **errp) Error *local_err = NULL; int ret; - ret = net_client_init(opts, 1, &local_err); + ret = net_client_init(opts, true, &local_err); if (local_err) { error_report_err(local_err); return -1; diff --git a/net/netmap.c b/net/netmap.c index 64967b947e..2d11a8f4be 100644 --- a/net/netmap.c +++ b/net/netmap.c @@ -400,7 +400,7 @@ static void netmap_set_offload(NetClientState *nc, int csum, int tso4, int tso6, /* NetClientInfo methods */ static NetClientInfo net_netmap_info = { - .type = NET_CLIENT_OPTIONS_KIND_NETMAP, + .type = NET_CLIENT_DRIVER_NETMAP, .size = sizeof(NetmapState), .receive = netmap_receive, .receive_iov = netmap_receive_iov, @@ -418,10 +418,10 @@ static NetClientInfo net_netmap_info = { * * ... -net netmap,ifname="..." */ -int net_init_netmap(const NetClientOptions *opts, +int net_init_netmap(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { - const NetdevNetmapOptions *netmap_opts = opts->u.netmap.data; + const NetdevNetmapOptions *netmap_opts = &netdev->u.netmap; struct nm_desc *nmd; NetClientState *nc; Error *err = NULL; diff --git a/net/slirp.c b/net/slirp.c index 28207b6614..facc30ed18 100644 --- a/net/slirp.c +++ b/net/slirp.c @@ -137,7 +137,7 @@ static void net_slirp_cleanup(NetClientState *nc) } static NetClientInfo net_slirp_info = { - .type = NET_CLIENT_OPTIONS_KIND_USER, + .type = NET_CLIENT_DRIVER_USER, .size = sizeof(SlirpState), .receive = net_slirp_receive, .cleanup = net_slirp_cleanup, @@ -828,7 +828,7 @@ static const char **slirp_dnssearch(const StringList *dnsname) return ret; } -int net_init_slirp(const NetClientOptions *opts, const char *name, +int net_init_slirp(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { /* FIXME error_setg(errp, ...) on failure */ @@ -839,8 +839,8 @@ int net_init_slirp(const NetClientOptions *opts, const char *name, const char **dnssearch; bool ipv4 = true, ipv6 = true; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_USER); - user = opts->u.user.data; + assert(netdev->type == NET_CLIENT_DRIVER_USER); + user = &netdev->u.user; if ((user->has_ipv6 && user->ipv6 && !user->has_ipv4) || (user->has_ipv4 && !user->ipv4)) { diff --git a/net/socket.c b/net/socket.c index ae6f92101d..17e635de20 100644 --- a/net/socket.c +++ b/net/socket.c @@ -311,7 +311,7 @@ static void net_socket_cleanup(NetClientState *nc) } static NetClientInfo net_dgram_socket_info = { - .type = NET_CLIENT_OPTIONS_KIND_SOCKET, + .type = NET_CLIENT_DRIVER_SOCKET, .size = sizeof(NetSocketState), .receive = net_socket_receive_dgram, .cleanup = net_socket_cleanup, @@ -395,7 +395,7 @@ static void net_socket_connect(void *opaque) } static NetClientInfo net_socket_info = { - .type = NET_CLIENT_OPTIONS_KIND_SOCKET, + .type = NET_CLIENT_DRIVER_SOCKET, .size = sizeof(NetSocketState), .receive = net_socket_receive, .cleanup = net_socket_cleanup, @@ -663,15 +663,15 @@ static int net_socket_udp_init(NetClientState *peer, return 0; } -int net_init_socket(const NetClientOptions *opts, const char *name, +int net_init_socket(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { /* FIXME error_setg(errp, ...) on failure */ Error *err = NULL; const NetdevSocketOptions *sock; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_SOCKET); - sock = opts->u.socket.data; + assert(netdev->type == NET_CLIENT_DRIVER_SOCKET); + sock = &netdev->u.socket; if (sock->has_fd + sock->has_listen + sock->has_connect + sock->has_mcast + sock->has_udp != 1) { diff --git a/net/tap-win32.c b/net/tap-win32.c index f1e142ace6..662f9b63e1 100644 --- a/net/tap-win32.c +++ b/net/tap-win32.c @@ -750,7 +750,7 @@ static void tap_set_vnet_hdr_len(NetClientState *nc, int len) } static NetClientInfo net_tap_win32_info = { - .type = NET_CLIENT_OPTIONS_KIND_TAP, + .type = NET_CLIENT_DRIVER_TAP, .size = sizeof(TAPState), .receive = tap_receive, .cleanup = tap_cleanup, @@ -788,14 +788,14 @@ static int tap_win32_init(NetClientState *peer, const char *model, return 0; } -int net_init_tap(const NetClientOptions *opts, const char *name, +int net_init_tap(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { /* FIXME error_setg(errp, ...) on failure */ const NetdevTapOptions *tap; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_TAP); - tap = opts->u.tap.data; + assert(netdev->type == NET_CLIENT_DRIVER_TAP); + tap = &netdev->u.tap; if (!tap->has_ifname) { error_report("tap: no interface name"); @@ -223,7 +223,7 @@ static bool tap_has_ufo(NetClientState *nc) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); return s->has_ufo; } @@ -232,7 +232,7 @@ static bool tap_has_vnet_hdr(NetClientState *nc) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); return !!s->host_vnet_hdr_len; } @@ -241,7 +241,7 @@ static bool tap_has_vnet_hdr_len(NetClientState *nc, int len) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); return !!tap_probe_vnet_hdr_len(s->fd, len); } @@ -250,7 +250,7 @@ static void tap_set_vnet_hdr_len(NetClientState *nc, int len) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); assert(len == sizeof(struct virtio_net_hdr_mrg_rxbuf) || len == sizeof(struct virtio_net_hdr)); @@ -262,7 +262,7 @@ static void tap_using_vnet_hdr(NetClientState *nc, bool using_vnet_hdr) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); assert(!!s->host_vnet_hdr_len == using_vnet_hdr); s->using_vnet_hdr = using_vnet_hdr; @@ -336,14 +336,14 @@ static void tap_poll(NetClientState *nc, bool enable) int tap_get_fd(NetClientState *nc) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); return s->fd; } /* fd support */ static NetClientInfo net_tap_info = { - .type = NET_CLIENT_OPTIONS_KIND_TAP, + .type = NET_CLIENT_DRIVER_TAP, .size = sizeof(TAPState), .receive = tap_receive, .receive_raw = tap_receive_raw, @@ -571,7 +571,7 @@ static int net_bridge_run_helper(const char *helper, const char *bridge, } } -int net_init_bridge(const NetClientOptions *opts, const char *name, +int net_init_bridge(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { const NetdevBridgeOptions *bridge; @@ -579,8 +579,8 @@ int net_init_bridge(const NetClientOptions *opts, const char *name, TAPState *s; int fd, vnet_hdr; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_BRIDGE); - bridge = opts->u.bridge.data; + assert(netdev->type == NET_CLIENT_DRIVER_BRIDGE); + bridge = &netdev->u.bridge; helper = bridge->has_helper ? bridge->helper : DEFAULT_BRIDGE_HELPER; br = bridge->has_br ? bridge->br : DEFAULT_BRIDGE_INTERFACE; @@ -735,7 +735,7 @@ static int get_fds(char *str, char *fds[], int max) return i; } -int net_init_tap(const NetClientOptions *opts, const char *name, +int net_init_tap(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { const NetdevTapOptions *tap; @@ -747,8 +747,8 @@ int net_init_tap(const NetClientOptions *opts, const char *name, const char *vhostfdname; char ifname[128]; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_TAP); - tap = opts->u.tap.data; + assert(netdev->type == NET_CLIENT_DRIVER_TAP); + tap = &netdev->u.tap; queues = tap->has_queues ? tap->queues : 1; vhostfdname = tap->has_vhostfd ? tap->vhostfd : NULL; @@ -921,7 +921,7 @@ free_fail: VHostNetState *tap_get_vhost_net(NetClientState *nc) { TAPState *s = DO_UPCAST(TAPState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_TAP); + assert(nc->info->type == NET_CLIENT_DRIVER_TAP); return s->vhost_net; } @@ -68,7 +68,7 @@ static void vde_cleanup(NetClientState *nc) } static NetClientInfo net_vde_info = { - .type = NET_CLIENT_OPTIONS_KIND_VDE, + .type = NET_CLIENT_DRIVER_VDE, .size = sizeof(VDEState), .receive = vde_receive, .cleanup = vde_cleanup, @@ -109,14 +109,14 @@ static int net_vde_init(NetClientState *peer, const char *model, return 0; } -int net_init_vde(const NetClientOptions *opts, const char *name, +int net_init_vde(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { /* FIXME error_setg(errp, ...) on failure */ const NetdevVdeOptions *vde; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_VDE); - vde = opts->u.vde.data; + assert(netdev->type == NET_CLIENT_DRIVER_VDE); + vde = &netdev->u.vde; /* missing optional values have been initialized to "all bits zero" */ if (net_vde_init(peer, "vde", name, vde->sock, vde->port, vde->group, diff --git a/net/vhost-user.c b/net/vhost-user.c index a88dfe0655..c4d63e05eb 100644 --- a/net/vhost-user.c +++ b/net/vhost-user.c @@ -34,14 +34,14 @@ typedef struct VhostUserChardevProps { VHostNetState *vhost_user_get_vhost_net(NetClientState *nc) { VhostUserState *s = DO_UPCAST(VhostUserState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER); return s->vhost_net; } uint64_t vhost_user_get_acked_features(NetClientState *nc) { VhostUserState *s = DO_UPCAST(VhostUserState, nc, nc); - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER); return s->acked_features; } @@ -56,7 +56,7 @@ static void vhost_user_stop(int queues, NetClientState *ncs[]) int i; for (i = 0; i < queues; i++) { - assert (ncs[i]->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + assert(ncs[i]->info->type == NET_CLIENT_DRIVER_VHOST_USER); s = DO_UPCAST(VhostUserState, nc, ncs[i]); if (!vhost_user_running(s)) { @@ -82,7 +82,7 @@ static int vhost_user_start(int queues, NetClientState *ncs[]) options.backend_type = VHOST_BACKEND_TYPE_USER; for (i = 0; i < queues; i++) { - assert (ncs[i]->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + assert(ncs[i]->info->type == NET_CLIENT_DRIVER_VHOST_USER); s = DO_UPCAST(VhostUserState, nc, ncs[i]); if (vhost_user_running(s)) { @@ -163,20 +163,20 @@ static void vhost_user_cleanup(NetClientState *nc) static bool vhost_user_has_vnet_hdr(NetClientState *nc) { - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER); return true; } static bool vhost_user_has_ufo(NetClientState *nc) { - assert(nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); + assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_USER); return true; } static NetClientInfo net_vhost_user_info = { - .type = NET_CLIENT_OPTIONS_KIND_VHOST_USER, + .type = NET_CLIENT_DRIVER_VHOST_USER, .size = sizeof(VhostUserState), .receive = vhost_user_receive, .cleanup = vhost_user_cleanup, @@ -207,7 +207,7 @@ static void net_vhost_user_event(void *opaque, int event) int queues; queues = qemu_find_net_clients_except(name, ncs, - NET_CLIENT_OPTIONS_KIND_NIC, + NET_CLIENT_DRIVER_NIC, MAX_QUEUE_NUM); assert(queues < MAX_QUEUE_NUM); @@ -334,15 +334,15 @@ static int net_vhost_check_net(void *opaque, QemuOpts *opts, Error **errp) return 0; } -int net_init_vhost_user(const NetClientOptions *opts, const char *name, +int net_init_vhost_user(const Netdev *netdev, const char *name, NetClientState *peer, Error **errp) { int queues; const NetdevVhostUserOptions *vhost_user_opts; CharDriverState *chr; - assert(opts->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER); - vhost_user_opts = opts->u.vhost_user.data; + assert(netdev->type == NET_CLIENT_DRIVER_VHOST_USER); + vhost_user_opts = &netdev->u.vhost_user; chr = net_vhost_parse_chardev(vhost_user_opts, errp); if (!chr) { diff --git a/qapi-schema.json b/qapi-schema.json index d2d650673b..5658723b37 100644 --- a/qapi-schema.json +++ b/qapi-schema.json @@ -2809,16 +2809,32 @@ '*queues': 'int' } } ## -# @NetClientOptions +# @NetClientDriver # -# A discriminated record of network device traits. +# Available netdev drivers. +# +# Since 2.7 +## +{ 'enum': 'NetClientDriver', + 'data': [ 'none', 'nic', 'user', 'tap', 'l2tpv3', 'socket', 'vde', 'dump', + 'bridge', 'hubport', 'netmap', 'vhost-user' ] } + +## +# @Netdev +# +# Captures the configuration of a network device. +# +# @id: identifier for monitor commands. +# +# @type: Specify the driver used for interpreting remaining arguments. # # Since 1.2 # # 'l2tpv3' - since 2.1 -# ## -{ 'union': 'NetClientOptions', +{ 'union': 'Netdev', + 'base': { 'id': 'str', 'type': 'NetClientDriver' }, + 'discriminator': 'type', 'data': { 'none': 'NetdevNoneOptions', 'nic': 'NetLegacyNicOptions', @@ -2853,23 +2869,28 @@ '*vlan': 'int32', '*id': 'str', '*name': 'str', - 'opts': 'NetClientOptions' } } + 'opts': 'NetLegacyOptions' } } ## -# @Netdev +# @NetLegacyOptions # -# Captures the configuration of a network device. -# -# @id: identifier for monitor commands. -# -# @opts: device type specific properties +# Like Netdev, but for use only by the legacy command line options # # Since 1.2 ## -{ 'struct': 'Netdev', +{ 'union': 'NetLegacyOptions', 'data': { - 'id': 'str', - 'opts': 'NetClientOptions' } } + 'none': 'NetdevNoneOptions', + 'nic': 'NetLegacyNicOptions', + 'user': 'NetdevUserOptions', + 'tap': 'NetdevTapOptions', + 'l2tpv3': 'NetdevL2TPv3Options', + 'socket': 'NetdevSocketOptions', + 'vde': 'NetdevVdeOptions', + 'dump': 'NetdevDumpOptions', + 'bridge': 'NetdevBridgeOptions', + 'netmap': 'NetdevNetmapOptions', + 'vhost-user': 'NetdevVhostUserOptions' } } ## # @NetFilterDirection diff --git a/qapi/block-core.json b/qapi/block-core.json index 3444a9bc3e..f462345ca3 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -1120,6 +1120,21 @@ # # Start mirroring a block device's writes to a new destination. # +# See DriveMirror for parameter descriptions +# +# Returns: nothing on success +# If @device is not a valid block device, DeviceNotFound +# +# Since 1.3 +## +{ 'command': 'drive-mirror', 'boxed': true, + 'data': 'DriveMirror' } + +## +# DriveMirror +# +# A set of parameters describing drive mirror setup. +# # @job-id: #optional identifier for the newly-created block job. If # omitted, the device name will be used. (Since 2.7) # @@ -1169,12 +1184,9 @@ # written. Both will result in identical contents. # Default is true. (Since 2.4) # -# Returns: nothing on success -# If @device is not a valid block device, DeviceNotFound -# # Since 1.3 ## -{ 'command': 'drive-mirror', +{ 'struct': 'DriveMirror', 'data': { '*job-id': 'str', 'device': 'str', 'target': 'str', '*format': 'str', '*node-name': 'str', '*replaces': 'str', 'sync': 'MirrorSyncMode', '*mode': 'NewImageMode', @@ -1330,6 +1342,21 @@ # the device will be removed from its group and the rest of its # members will not be affected. The 'group' parameter is ignored. # +# See BlockIOThrottle for parameter descriptions. +# +# Returns: Nothing on success +# If @device is not a valid block device, DeviceNotFound +# +# Since: 1.1 +## +{ 'command': 'block_set_io_throttle', 'boxed': true, + 'data': 'BlockIOThrottle' } + +## +# BlockIOThrottle +# +# A set of parameters describing block throttling. +# # @device: The name of the device # # @bps: total throughput limit in bytes per second @@ -1396,12 +1423,9 @@ # # @group: #optional throttle group name (Since 2.4) # -# Returns: Nothing on success -# If @device is not a valid block device, DeviceNotFound -# # Since: 1.1 ## -{ 'command': 'block_set_io_throttle', +{ 'struct': 'BlockIOThrottle', 'data': { 'device': 'str', 'bps': 'int', 'bps_rd': 'int', 'bps_wr': 'int', 'iops': 'int', 'iops_rd': 'int', 'iops_wr': 'int', '*bps_max': 'int', '*bps_rd_max': 'int', @@ -1666,13 +1690,14 @@ # @host_device, @host_cdrom: Since 2.1 # # Since: 2.0 +# @gluster: Since 2.7 ## { 'enum': 'BlockdevDriver', 'data': [ 'archipelago', 'blkdebug', 'blkverify', 'bochs', 'cloop', - 'dmg', 'file', 'ftp', 'ftps', 'host_cdrom', 'host_device', - 'http', 'https', 'luks', 'null-aio', 'null-co', 'parallels', - 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'tftp', 'vdi', 'vhdx', - 'vmdk', 'vpc', 'vvfat' ] } + 'dmg', 'file', 'ftp', 'ftps', 'gluster', 'host_cdrom', + 'host_device', 'http', 'https', 'luks', 'null-aio', 'null-co', + 'parallels', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'tftp', + 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] } ## # @BlockdevOptionsFile @@ -2065,6 +2090,63 @@ '*read-pattern': 'QuorumReadPattern' } } ## +# @GlusterTransport +# +# An enumeration of Gluster transport types +# +# @tcp: TCP - Transmission Control Protocol +# +# @unix: UNIX - Unix domain socket +# +# Since: 2.7 +## +{ 'enum': 'GlusterTransport', + 'data': [ 'unix', 'tcp' ] } + + +## +# @GlusterServer +# +# Captures the address of a socket +# +# Details for connecting to a gluster server +# +# @type: Transport type used for gluster connection +# +# @unix: socket file +# +# @tcp: host address and port number +# +# Since: 2.7 +## +{ 'union': 'GlusterServer', + 'base': { 'type': 'GlusterTransport' }, + 'discriminator': 'type', + 'data': { 'unix': 'UnixSocketAddress', + 'tcp': 'InetSocketAddress' } } + +## +# @BlockdevOptionsGluster +# +# Driver specific block device options for Gluster +# +# @volume: name of gluster volume where VM image resides +# +# @path: absolute path to image file in gluster volume +# +# @server: gluster server description +# +# @debug-level: #optional libgfapi log level (default '4' which is Error) +# +# Since: 2.7 +## +{ 'struct': 'BlockdevOptionsGluster', + 'data': { 'volume': 'str', + 'path': 'str', + 'server': ['GlusterServer'], + '*debug_level': 'int' } } + +## # @BlockdevOptions # # Options for creating a block device. Many options are available for all @@ -2111,7 +2193,7 @@ 'file': 'BlockdevOptionsFile', 'ftp': 'BlockdevOptionsFile', 'ftps': 'BlockdevOptionsFile', -# TODO gluster: Wait for structured options + 'gluster': 'BlockdevOptionsGluster', 'host_cdrom': 'BlockdevOptionsFile', 'host_device':'BlockdevOptionsFile', 'http': 'BlockdevOptionsFile', diff --git a/qapi/qmp-input-visitor.c b/qapi/qmp-input-visitor.c index 21edb3928e..64dd392e6f 100644 --- a/qapi/qmp-input-visitor.c +++ b/qapi/qmp-input-visitor.c @@ -30,6 +30,8 @@ typedef struct StackObject GHashTable *h; /* If obj is dict: unvisited keys */ const QListEntry *entry; /* If obj is list: unvisited tail */ + + QSLIST_ENTRY(StackObject) node; } StackObject; struct QmpInputVisitor @@ -41,8 +43,7 @@ struct QmpInputVisitor /* Stack of objects being visited (all entries will be either * QDict or QList). */ - StackObject stack[QIV_STACK_SIZE]; - int nb_stack; + QSLIST_HEAD(, StackObject) stack; /* True to reject parse in visit_end_struct() if unvisited keys remain. */ bool strict; @@ -61,13 +62,13 @@ static QObject *qmp_input_get_object(QmpInputVisitor *qiv, QObject *qobj; QObject *ret; - if (!qiv->nb_stack) { + if (QSLIST_EMPTY(&qiv->stack)) { /* Starting at root, name is ignored. */ return qiv->root; } /* We are in a container; find the next element. */ - tos = &qiv->stack[qiv->nb_stack - 1]; + tos = QSLIST_FIRST(&qiv->stack); qobj = tos->obj; assert(qobj); @@ -100,18 +101,11 @@ static const QListEntry *qmp_input_push(QmpInputVisitor *qiv, QObject *obj, void *qapi, Error **errp) { GHashTable *h; - StackObject *tos = &qiv->stack[qiv->nb_stack]; + StackObject *tos = g_new0(StackObject, 1); assert(obj); - if (qiv->nb_stack >= QIV_STACK_SIZE) { - error_setg(errp, "An internal buffer overran"); - return NULL; - } - tos->obj = obj; tos->qapi = qapi; - assert(!tos->h); - assert(!tos->entry); if (qiv->strict && qobject_type(obj) == QTYPE_QDICT) { h = g_hash_table_new(g_str_hash, g_str_equal); @@ -121,7 +115,7 @@ static const QListEntry *qmp_input_push(QmpInputVisitor *qiv, QObject *obj, tos->entry = qlist_first(qobject_to_qlist(obj)); } - qiv->nb_stack++; + QSLIST_INSERT_HEAD(&qiv->stack, tos, node); return tos->entry; } @@ -129,10 +123,9 @@ static const QListEntry *qmp_input_push(QmpInputVisitor *qiv, QObject *obj, static void qmp_input_check_struct(Visitor *v, Error **errp) { QmpInputVisitor *qiv = to_qiv(v); - StackObject *tos = &qiv->stack[qiv->nb_stack - 1]; - - assert(qiv->nb_stack > 0); + StackObject *tos = QSLIST_FIRST(&qiv->stack); + assert(tos && !tos->entry); if (qiv->strict) { GHashTable *const top_ht = tos->h; if (top_ht) { @@ -147,23 +140,23 @@ static void qmp_input_check_struct(Visitor *v, Error **errp) } } -static void qmp_input_pop(Visitor *v, void **obj) +static void qmp_input_stack_object_free(StackObject *tos) { - QmpInputVisitor *qiv = to_qiv(v); - StackObject *tos = &qiv->stack[qiv->nb_stack - 1]; + if (tos->h) { + g_hash_table_unref(tos->h); + } - assert(qiv->nb_stack > 0); - assert(tos->qapi == obj); + g_free(tos); +} - if (qiv->strict) { - GHashTable * const top_ht = qiv->stack[qiv->nb_stack - 1].h; - if (top_ht) { - g_hash_table_unref(top_ht); - } - tos->h = NULL; - } +static void qmp_input_pop(Visitor *v, void **obj) +{ + QmpInputVisitor *qiv = to_qiv(v); + StackObject *tos = QSLIST_FIRST(&qiv->stack); - qiv->nb_stack--; + assert(tos && tos->qapi == obj); + QSLIST_REMOVE_HEAD(&qiv->stack, node); + qmp_input_stack_object_free(tos); } static void qmp_input_start_struct(Visitor *v, const char *name, void **obj, @@ -224,7 +217,7 @@ static GenericList *qmp_input_next_list(Visitor *v, GenericList *tail, size_t size) { QmpInputVisitor *qiv = to_qiv(v); - StackObject *so = &qiv->stack[qiv->nb_stack - 1]; + StackObject *so = QSLIST_FIRST(&qiv->stack); if (!so->entry) { return NULL; @@ -376,6 +369,12 @@ static void qmp_input_optional(Visitor *v, const char *name, bool *present) static void qmp_input_free(Visitor *v) { QmpInputVisitor *qiv = to_qiv(v); + while (!QSLIST_EMPTY(&qiv->stack)) { + StackObject *tos = QSLIST_FIRST(&qiv->stack); + + QSLIST_REMOVE_HEAD(&qiv->stack, node); + qmp_input_stack_object_free(tos); + } qobject_decref(qiv->root); g_free(qiv); diff --git a/qapi/qmp-output-visitor.c b/qapi/qmp-output-visitor.c index 0452056d42..9e3b67ce13 100644 --- a/qapi/qmp-output-visitor.c +++ b/qapi/qmp-output-visitor.c @@ -23,15 +23,13 @@ typedef struct QStackEntry { QObject *value; void *qapi; /* sanity check that caller uses same pointer */ - QTAILQ_ENTRY(QStackEntry) node; + QSLIST_ENTRY(QStackEntry) node; } QStackEntry; -typedef QTAILQ_HEAD(QStack, QStackEntry) QStack; - struct QmpOutputVisitor { Visitor visitor; - QStack stack; /* Stack of containers that haven't yet been finished */ + QSLIST_HEAD(, QStackEntry) stack; /* Stack of unfinished containers */ QObject *root; /* Root of the output visit */ QObject **result; /* User's storage location for result */ }; @@ -56,18 +54,18 @@ static void qmp_output_push_obj(QmpOutputVisitor *qov, QObject *value, assert(value); e->value = value; e->qapi = qapi; - QTAILQ_INSERT_HEAD(&qov->stack, e, node); + QSLIST_INSERT_HEAD(&qov->stack, e, node); } /* Pop a value off the stack of QObjects being built, and return it. */ static QObject *qmp_output_pop(QmpOutputVisitor *qov, void *qapi) { - QStackEntry *e = QTAILQ_FIRST(&qov->stack); + QStackEntry *e = QSLIST_FIRST(&qov->stack); QObject *value; assert(e); assert(e->qapi == qapi); - QTAILQ_REMOVE(&qov->stack, e, node); + QSLIST_REMOVE_HEAD(&qov->stack, node); value = e->value; assert(value); g_free(e); @@ -80,7 +78,7 @@ static QObject *qmp_output_pop(QmpOutputVisitor *qov, void *qapi) static void qmp_output_add_obj(QmpOutputVisitor *qov, const char *name, QObject *value) { - QStackEntry *e = QTAILQ_FIRST(&qov->stack); + QStackEntry *e = QSLIST_FIRST(&qov->stack); QObject *cur = e ? e->value : NULL; if (!cur) { @@ -206,7 +204,7 @@ static void qmp_output_complete(Visitor *v, void *opaque) QmpOutputVisitor *qov = to_qov(v); /* A visit must have occurred, with each start paired with end. */ - assert(qov->root && QTAILQ_EMPTY(&qov->stack)); + assert(qov->root && QSLIST_EMPTY(&qov->stack)); assert(opaque == qov->result); qobject_incref(qov->root); @@ -217,10 +215,11 @@ static void qmp_output_complete(Visitor *v, void *opaque) static void qmp_output_free(Visitor *v) { QmpOutputVisitor *qov = to_qov(v); - QStackEntry *e, *tmp; + QStackEntry *e; - QTAILQ_FOREACH_SAFE(e, &qov->stack, node, tmp) { - QTAILQ_REMOVE(&qov->stack, e, node); + while (!QSLIST_EMPTY(&qov->stack)) { + e = QSLIST_FIRST(&qov->stack); + QSLIST_REMOVE_HEAD(&qov->stack, node); g_free(e); } @@ -250,7 +249,6 @@ Visitor *qmp_output_visitor_new(QObject **result) v->visitor.complete = qmp_output_complete; v->visitor.free = qmp_output_free; - QTAILQ_INIT(&v->stack); *result = NULL; v->result = result; diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index 6e29edb1fd..25954f5634 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -1696,8 +1696,7 @@ static int discard_f(BlockBackend *blk, int argc, char **argv) } gettimeofday(&t1, NULL); - ret = blk_discard(blk, offset >> BDRV_SECTOR_BITS, - count >> BDRV_SECTOR_BITS); + ret = blk_pdiscard(blk, offset, count); gettimeofday(&t2, NULL); if (ret < 0) { diff --git a/qmp-commands.hx b/qmp-commands.hx index 496d73c275..c8d360ad36 100644 --- a/qmp-commands.hx +++ b/qmp-commands.hx @@ -5026,3 +5026,18 @@ Example for pseries machine type started with { "props": { "core-id": 0 }, "type": "POWER8-spapr-cpu-core", "vcpus-count": 1, "qom-path": "/machine/unattached/device[0]"} ]}' + +Example for pc machine type started with +-smp 1,maxcpus=2: + -> { "execute": "query-hotpluggable-cpus" } + <- {"return": [ + { + "type": "qemu64-x86_64-cpu", "vcpus-count": 1, + "props": {"core-id": 0, "socket-id": 1, "thread-id": 0} + }, + { + "qom-path": "/machine/unattached/device[0]", + "type": "qemu64-x86_64-cpu", "vcpus-count": 1, + "props": {"core-id": 0, "socket-id": 0, "thread-id": 0} + } + ]} diff --git a/scripts/qapi-commands.py b/scripts/qapi-commands.py index 34b6a3a07f..a06a2c4f9b 100644 --- a/scripts/qapi-commands.py +++ b/scripts/qapi-commands.py @@ -16,20 +16,23 @@ from qapi import * import re -def gen_command_decl(name, arg_type, ret_type): +def gen_command_decl(name, arg_type, boxed, ret_type): return mcgen(''' %(c_type)s qmp_%(c_name)s(%(params)s); ''', c_type=(ret_type and ret_type.c_type()) or 'void', c_name=c_name(name), - params=gen_params(arg_type, 'Error **errp')) + params=gen_params(arg_type, boxed, 'Error **errp')) -def gen_call(name, arg_type, ret_type): +def gen_call(name, arg_type, boxed, ret_type): ret = '' argstr = '' - if arg_type: + if boxed: + assert arg_type and not arg_type.is_empty() + argstr = '&arg, ' + elif arg_type: assert not arg_type.variants for memb in arg_type.members: if memb.optional: @@ -46,8 +49,10 @@ def gen_call(name, arg_type, ret_type): ''', c_name=c_name(name), args=argstr, lhs=lhs) if ret_type: - ret += gen_err_check() ret += mcgen(''' + if (err) { + goto out; + } qmp_marshal_output_%(c_name)s(retval, ret, &err); ''', @@ -92,7 +97,7 @@ def gen_marshal_decl(name): proto=gen_marshal_proto(name)) -def gen_marshal(name, arg_type, ret_type): +def gen_marshal(name, arg_type, boxed, ret_type): ret = mcgen(''' %(proto)s @@ -107,7 +112,7 @@ def gen_marshal(name, arg_type, ret_type): ''', c_type=ret_type.c_type()) - if arg_type and arg_type.members: + if arg_type and not arg_type.is_empty(): ret += mcgen(''' Visitor *v; %(c_name)s arg = {0}; @@ -134,10 +139,10 @@ def gen_marshal(name, arg_type, ret_type): (void)args; ''') - ret += gen_call(name, arg_type, ret_type) + ret += gen_call(name, arg_type, boxed, ret_type) # 'goto out' produced above for arg_type, and by gen_call() for ret_type - if (arg_type and arg_type.members) or ret_type: + if (arg_type and not arg_type.is_empty()) or ret_type: ret += mcgen(''' out: @@ -145,7 +150,7 @@ out: ret += mcgen(''' error_propagate(errp, err); ''') - if arg_type and arg_type.members: + if arg_type and not arg_type.is_empty(): ret += mcgen(''' visit_free(v); v = qapi_dealloc_visitor_new(); @@ -210,16 +215,16 @@ class QAPISchemaGenCommandVisitor(QAPISchemaVisitor): self._visited_ret_types = None def visit_command(self, name, info, arg_type, ret_type, - gen, success_response): + gen, success_response, boxed): if not gen: return - self.decl += gen_command_decl(name, arg_type, ret_type) + self.decl += gen_command_decl(name, arg_type, boxed, ret_type) if ret_type and ret_type not in self._visited_ret_types: self._visited_ret_types.add(ret_type) self.defn += gen_marshal_output(ret_type) if middle_mode: self.decl += gen_marshal_decl(name) - self.defn += gen_marshal(name, arg_type, ret_type) + self.defn += gen_marshal(name, arg_type, boxed, ret_type) if not middle_mode: self._regy += gen_register_command(name, success_response) diff --git a/scripts/qapi-event.py b/scripts/qapi-event.py index 9c88627c9f..38d82111ad 100644 --- a/scripts/qapi-event.py +++ b/scripts/qapi-event.py @@ -14,18 +14,18 @@ from qapi import * -def gen_event_send_proto(name, arg_type): +def gen_event_send_proto(name, arg_type, boxed): return 'void qapi_event_send_%(c_name)s(%(param)s)' % { 'c_name': c_name(name.lower()), - 'param': gen_params(arg_type, 'Error **errp')} + 'param': gen_params(arg_type, boxed, 'Error **errp')} -def gen_event_send_decl(name, arg_type): +def gen_event_send_decl(name, arg_type, boxed): return mcgen(''' %(proto)s; ''', - proto=gen_event_send_proto(name, arg_type)) + proto=gen_event_send_proto(name, arg_type, boxed)) # Declare and initialize an object 'qapi' using parameters from gen_params() @@ -49,10 +49,15 @@ def gen_param_var(typ): }; ''') + if not typ.is_implicit(): + ret += mcgen(''' + %(c_name)s *arg = ¶m; +''', + c_name=typ.c_name()) return ret -def gen_event_send(name, arg_type): +def gen_event_send(name, arg_type, boxed): # FIXME: Our declaration of local variables (and of 'errp' in the # parameter list) can collide with exploded members of the event's # data type passed in as parameters. If this collision ever hits in @@ -67,14 +72,17 @@ def gen_event_send(name, arg_type): Error *err = NULL; QMPEventFuncEmit emit; ''', - proto=gen_event_send_proto(name, arg_type)) + proto=gen_event_send_proto(name, arg_type, boxed)) - if arg_type and arg_type.members: + if arg_type and not arg_type.is_empty(): ret += mcgen(''' QObject *obj; Visitor *v; ''') - ret += gen_param_var(arg_type) + if not boxed: + ret += gen_param_var(arg_type) + else: + assert not boxed ret += mcgen(''' @@ -88,9 +96,17 @@ def gen_event_send(name, arg_type): ''', name=name) - if arg_type and arg_type.members: + if arg_type and not arg_type.is_empty(): ret += mcgen(''' v = qmp_output_visitor_new(&obj); +''') + if not arg_type.is_implicit(): + ret += mcgen(''' + visit_type_%(c_name)s(v, "%(name)s", &arg, &err); +''', + name=name, c_name=arg_type.c_name()) + else: + ret += mcgen(''' visit_start_struct(v, "%(name)s", NULL, 0, &err); if (err) { @@ -101,14 +117,16 @@ def gen_event_send(name, arg_type): visit_check_struct(v, &err); } visit_end_struct(v, NULL); +''', + name=name, c_name=arg_type.c_name()) + ret += mcgen(''' if (err) { goto out; } visit_complete(v, &obj); qdict_put_obj(qmp, "data", obj); -''', - name=name, c_name=arg_type.c_name()) +''') ret += mcgen(''' emit(%(c_enum)s, qmp, &err); @@ -116,7 +134,7 @@ def gen_event_send(name, arg_type): ''', c_enum=c_enum_const(event_enum_name, name)) - if arg_type and arg_type.members: + if arg_type and not arg_type.is_empty(): ret += mcgen(''' out: visit_free(v); @@ -145,9 +163,9 @@ class QAPISchemaGenEventVisitor(QAPISchemaVisitor): self.defn += gen_enum_lookup(event_enum_name, self._event_names) self._event_names = None - def visit_event(self, name, info, arg_type): - self.decl += gen_event_send_decl(name, arg_type) - self.defn += gen_event_send(name, arg_type) + def visit_event(self, name, info, arg_type, boxed): + self.decl += gen_event_send_decl(name, arg_type, boxed) + self.defn += gen_event_send(name, arg_type, boxed) self._event_names.append(name) diff --git a/scripts/qapi-introspect.py b/scripts/qapi-introspect.py index e0f926be04..541644e350 100644 --- a/scripts/qapi-introspect.py +++ b/scripts/qapi-introspect.py @@ -154,14 +154,14 @@ const char %(c_name)s[] = %(c_string)s; for m in variants.variants]}) def visit_command(self, name, info, arg_type, ret_type, - gen, success_response): + gen, success_response, boxed): arg_type = arg_type or self._schema.the_empty_object_type ret_type = ret_type or self._schema.the_empty_object_type self._gen_json(name, 'command', {'arg-type': self._use_type(arg_type), 'ret-type': self._use_type(ret_type)}) - def visit_event(self, name, info, arg_type): + def visit_event(self, name, info, arg_type, boxed): arg_type = arg_type or self._schema.the_empty_object_type self._gen_json(name, 'event', {'arg-type': self._use_type(arg_type)}) diff --git a/scripts/qapi-types.py b/scripts/qapi-types.py index 5ace2cf065..dabc42e047 100644 --- a/scripts/qapi-types.py +++ b/scripts/qapi-types.py @@ -91,7 +91,7 @@ struct %(c_name)s { # potential issues with attempting to malloc space for zero-length # structs in C, and also incompatibility with C++ (where an empty # struct is size 1). - if not (base and base.members) and not members and not variants: + if (not base or base.is_empty()) and not members and not variants: ret += mcgen(''' char qapi_dummy_for_empty_struct; ''') diff --git a/scripts/qapi-visit.py b/scripts/qapi-visit.py index 0b9e298bc4..96f2491c16 100644 --- a/scripts/qapi-visit.py +++ b/scripts/qapi-visit.py @@ -47,9 +47,11 @@ void visit_type_%(c_name)s_members(Visitor *v, %(c_name)s *obj, Error **errp) if base: ret += mcgen(''' visit_type_%(c_type)s_members(v, (%(c_type)s *)obj, &err); + if (err) { + goto out; + } ''', c_type=base.c_name()) - ret += gen_err_check() for memb in members: if memb.optional: @@ -60,10 +62,12 @@ void visit_type_%(c_name)s_members(Visitor *v, %(c_name)s *obj, Error **errp) push_indent() ret += mcgen(''' visit_type_%(c_type)s(v, "%(name)s", &obj->%(c_name)s, &err); + if (err) { + goto out; + } ''', c_type=memb.type.c_name(), name=memb.name, c_name=c_name(memb.name)) - ret += gen_err_check() if memb.optional: pop_indent() ret += mcgen(''' diff --git a/scripts/qapi.py b/scripts/qapi.py index b13ae47899..21bc32fda3 100644 --- a/scripts/qapi.py +++ b/scripts/qapi.py @@ -522,10 +522,14 @@ def check_type(expr_info, source, value, allow_array=False, def check_command(expr, expr_info): name = expr['command'] + boxed = expr.get('boxed', False) + args_meta = ['struct'] + if boxed: + args_meta += ['union', 'alternate'] check_type(expr_info, "'data' for command '%s'" % name, - expr.get('data'), allow_dict=True, allow_optional=True, - allow_metas=['struct']) + expr.get('data'), allow_dict=not boxed, allow_optional=True, + allow_metas=args_meta) returns_meta = ['union', 'struct'] if name in returns_whitelist: returns_meta += ['built-in', 'alternate', 'enum'] @@ -537,11 +541,15 @@ def check_command(expr, expr_info): def check_event(expr, expr_info): global events name = expr['event'] + boxed = expr.get('boxed', False) + meta = ['struct'] + if boxed: + meta += ['union', 'alternate'] events.append(name) check_type(expr_info, "'data' for event '%s'" % name, - expr.get('data'), allow_dict=True, allow_optional=True, - allow_metas=['struct']) + expr.get('data'), allow_dict=not boxed, allow_optional=True, + allow_metas=meta) def check_union(expr, expr_info): @@ -612,6 +620,14 @@ def check_union(expr, expr_info): "enum '%s'" % (key, enum_define["enum_name"])) + # If discriminator is user-defined, ensure all values are covered + if enum_define: + for value in enum_define['enum_values']: + if value not in members.keys(): + raise QAPIExprError(expr_info, + "Union '%s' data missing '%s' branch" + % (name, value)) + def check_alternate(expr, expr_info): name = expr['alternate'] @@ -686,6 +702,10 @@ def check_keys(expr_elem, meta, required, optional=[]): raise QAPIExprError(info, "'%s' of %s '%s' should only use false value" % (key, meta, name)) + if key == 'boxed' and value is not True: + raise QAPIExprError(info, + "'%s' of %s '%s' should only use true value" + % (key, meta, name)) for key in required: if key not in expr: raise QAPIExprError(info, @@ -717,10 +737,10 @@ def check_exprs(exprs): add_struct(expr, info) elif 'command' in expr: check_keys(expr_elem, 'command', [], - ['data', 'returns', 'gen', 'success-response']) + ['data', 'returns', 'gen', 'success-response', 'boxed']) add_name(expr['command'], info, 'command') elif 'event' in expr: - check_keys(expr_elem, 'event', [], ['data']) + check_keys(expr_elem, 'event', [], ['data', 'boxed']) add_name(expr['event'], info, 'event') else: raise QAPIExprError(expr_elem['info'], @@ -818,10 +838,10 @@ class QAPISchemaVisitor(object): pass def visit_command(self, name, info, arg_type, ret_type, - gen, success_response): + gen, success_response, boxed): pass - def visit_event(self, name, info, arg_type): + def visit_event(self, name, info, arg_type, boxed): pass @@ -991,7 +1011,12 @@ class QAPISchemaObjectType(QAPISchemaType): # _def_predefineds() return self.name.startswith('q_') + def is_empty(self): + assert self.members is not None + return not self.members and not self.variants + def c_name(self): + assert self.name != 'q_empty' return QAPISchemaType.c_name(self) def c_type(self): @@ -1084,7 +1109,7 @@ class QAPISchemaObjectTypeVariants(object): assert len(variants) > 0 for v in variants: assert isinstance(v, QAPISchemaObjectTypeVariant) - self.tag_name = tag_name + self._tag_name = tag_name self.tag_member = tag_member self.variants = variants @@ -1094,8 +1119,8 @@ class QAPISchemaObjectTypeVariants(object): def check(self, schema, seen): if not self.tag_member: # flat union - self.tag_member = seen[c_name(self.tag_name)] - assert self.tag_name == self.tag_member.name + self.tag_member = seen[c_name(self._tag_name)] + assert self._tag_name == self.tag_member.name assert isinstance(self.tag_member.type, QAPISchemaEnumType) for v in self.variants: v.check(schema) @@ -1125,7 +1150,7 @@ class QAPISchemaAlternateType(QAPISchemaType): def __init__(self, name, info, variants): QAPISchemaType.__init__(self, name, info) assert isinstance(variants, QAPISchemaObjectTypeVariants) - assert not variants.tag_name + assert variants.tag_member variants.set_owner(name) variants.tag_member.set_owner(self.name) self.variants = variants @@ -1150,9 +1175,13 @@ class QAPISchemaAlternateType(QAPISchemaType): def visit(self, visitor): visitor.visit_alternate_type(self.name, self.info, self.variants) + def is_empty(self): + return False + class QAPISchemaCommand(QAPISchemaEntity): - def __init__(self, name, info, arg_type, ret_type, gen, success_response): + def __init__(self, name, info, arg_type, ret_type, gen, success_response, + boxed): QAPISchemaEntity.__init__(self, name, info) assert not arg_type or isinstance(arg_type, str) assert not ret_type or isinstance(ret_type, str) @@ -1162,12 +1191,24 @@ class QAPISchemaCommand(QAPISchemaEntity): self.ret_type = None self.gen = gen self.success_response = success_response + self.boxed = boxed def check(self, schema): if self._arg_type_name: self.arg_type = schema.lookup_type(self._arg_type_name) - assert isinstance(self.arg_type, QAPISchemaObjectType) - assert not self.arg_type.variants # not implemented + assert (isinstance(self.arg_type, QAPISchemaObjectType) or + isinstance(self.arg_type, QAPISchemaAlternateType)) + self.arg_type.check(schema) + if self.boxed: + if self.arg_type.is_empty(): + raise QAPIExprError(self.info, + "Cannot use 'boxed' with empty type") + else: + assert not isinstance(self.arg_type, QAPISchemaAlternateType) + assert not self.arg_type.variants + elif self.boxed: + raise QAPIExprError(self.info, + "Use of 'boxed' requires 'data'") if self._ret_type_name: self.ret_type = schema.lookup_type(self._ret_type_name) assert isinstance(self.ret_type, QAPISchemaType) @@ -1175,24 +1216,36 @@ class QAPISchemaCommand(QAPISchemaEntity): def visit(self, visitor): visitor.visit_command(self.name, self.info, self.arg_type, self.ret_type, - self.gen, self.success_response) + self.gen, self.success_response, self.boxed) class QAPISchemaEvent(QAPISchemaEntity): - def __init__(self, name, info, arg_type): + def __init__(self, name, info, arg_type, boxed): QAPISchemaEntity.__init__(self, name, info) assert not arg_type or isinstance(arg_type, str) self._arg_type_name = arg_type self.arg_type = None + self.boxed = boxed def check(self, schema): if self._arg_type_name: self.arg_type = schema.lookup_type(self._arg_type_name) - assert isinstance(self.arg_type, QAPISchemaObjectType) - assert not self.arg_type.variants # not implemented + assert (isinstance(self.arg_type, QAPISchemaObjectType) or + isinstance(self.arg_type, QAPISchemaAlternateType)) + self.arg_type.check(schema) + if self.boxed: + if self.arg_type.is_empty(): + raise QAPIExprError(self.info, + "Cannot use 'boxed' with empty type") + else: + assert not isinstance(self.arg_type, QAPISchemaAlternateType) + assert not self.arg_type.variants + elif self.boxed: + raise QAPIExprError(self.info, + "Use of 'boxed' requires 'data'") def visit(self, visitor): - visitor.visit_event(self.name, self.info, self.arg_type) + visitor.visit_event(self.name, self.info, self.arg_type, self.boxed) class QAPISchema(object): @@ -1368,6 +1421,7 @@ class QAPISchema(object): rets = expr.get('returns') gen = expr.get('gen', True) success_response = expr.get('success-response', True) + boxed = expr.get('boxed', False) if isinstance(data, OrderedDict): data = self._make_implicit_object_type( name, info, 'arg', self._make_members(data, info)) @@ -1375,15 +1429,16 @@ class QAPISchema(object): assert len(rets) == 1 rets = self._make_array_type(rets[0], info) self._def_entity(QAPISchemaCommand(name, info, data, rets, gen, - success_response)) + success_response, boxed)) def _def_event(self, expr, info): name = expr['event'] data = expr.get('data') + boxed = expr.get('boxed', False) if isinstance(data, OrderedDict): data = self._make_implicit_object_type( name, info, 'arg', self._make_members(data, info)) - self._def_entity(QAPISchemaEvent(name, info, data)) + self._def_entity(QAPISchemaEvent(name, info, data, boxed)) def _def_exprs(self): for expr_elem in self.exprs: @@ -1626,31 +1681,29 @@ extern const char *const %(c_name)s_lookup[]; return ret -def gen_params(arg_type, extra): +def gen_params(arg_type, boxed, extra): if not arg_type: + assert not boxed return extra - assert not arg_type.variants ret = '' sep = '' - for memb in arg_type.members: - ret += sep + if boxed: + ret += '%s arg' % arg_type.c_param_type() sep = ', ' - if memb.optional: - ret += 'bool has_%s, ' % c_name(memb.name) - ret += '%s %s' % (memb.type.c_param_type(), c_name(memb.name)) + else: + assert not arg_type.variants + for memb in arg_type.members: + ret += sep + sep = ', ' + if memb.optional: + ret += 'bool has_%s, ' % c_name(memb.name) + ret += '%s %s' % (memb.type.c_param_type(), + c_name(memb.name)) if extra: ret += sep + extra return ret -def gen_err_check(): - return mcgen(''' - if (err) { - goto out; - } -''') - - # # Common command line parsing # diff --git a/target-arm/machine.c b/target-arm/machine.c index 2dbeb826cd..7a6ca31a8e 100644 --- a/target-arm/machine.c +++ b/target-arm/machine.c @@ -340,10 +340,9 @@ const char *gicv3_class_name(void) #else error_report("KVM GICv3 acceleration is not supported on this " "platform"); + exit(1); #endif } else { return "arm-gicv3"; } - - exit(1); } diff --git a/target-i386/cpu.c b/target-i386/cpu.c index 6e49e4ca82..6a1afab595 100644 --- a/target-i386/cpu.c +++ b/target-i386/cpu.c @@ -305,12 +305,12 @@ static const char *cpuid_7_0_ebx_feature_name[] = { }; static const char *cpuid_7_0_ecx_feature_name[] = { - NULL, NULL, NULL, "pku", + NULL, NULL, "umip", "pku", "ospke", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, + NULL, NULL, "rdpid", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; @@ -1893,50 +1893,6 @@ static void x86_cpuid_set_tsc_freq(Object *obj, Visitor *v, const char *name, cpu->env.tsc_khz = cpu->env.user_tsc_khz = value / 1000; } -static void x86_cpuid_get_apic_id(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - X86CPU *cpu = X86_CPU(obj); - int64_t value = cpu->apic_id; - - visit_type_int(v, name, &value, errp); -} - -static void x86_cpuid_set_apic_id(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - X86CPU *cpu = X86_CPU(obj); - DeviceState *dev = DEVICE(obj); - const int64_t min = 0; - const int64_t max = UINT32_MAX; - Error *error = NULL; - int64_t value; - - if (dev->realized) { - error_setg(errp, "Attempt to set property '%s' on '%s' after " - "it was realized", name, object_get_typename(obj)); - return; - } - - visit_type_int(v, name, &value, &error); - if (error) { - error_propagate(errp, error); - return; - } - if (value < min || value > max) { - error_setg(errp, "Property %s.%s doesn't take value %" PRId64 - " (minimum: %" PRId64 ", maximum: %" PRId64 ")" , - object_get_typename(obj), name, value, min, max); - return; - } - - if ((value != cpu->apic_id) && cpu_exists(value)) { - error_setg(errp, "CPU with APIC ID %" PRIi64 " exists", value); - return; - } - cpu->apic_id = value; -} - /* Generic getter for "feature-words" and "filtered-features" properties */ static void x86_cpu_get_feature_words(Object *obj, Visitor *v, const char *name, void *opaque, @@ -2641,17 +2597,13 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, break; case 0x80000008: /* virtual & phys address size in low 2 bytes. */ -/* XXX: This value must match the one used in the MMU code. */ if (env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) { - /* 64 bit processor */ -/* XXX: The physical address space is limited to 42 bits in exec.c. */ - *eax = 0x00003028; /* 48 bits virtual, 40 bits physical */ + /* 64 bit processor, 48 bits virtual, configurable + * physical bits. + */ + *eax = 0x00003000 + cpu->phys_bits; } else { - if (env->features[FEAT_1_EDX] & CPUID_PSE36) { - *eax = 0x00000024; /* 36 bits physical */ - } else { - *eax = 0x00000020; /* 32 bits physical */ - } + *eax = cpu->phys_bits; } *ebx = 0; *ecx = 0; @@ -2874,8 +2826,10 @@ static void x86_cpu_apic_create(X86CPU *cpu, Error **errp) cpu->apic_state = DEVICE(object_new(apic_type)); - object_property_add_child(OBJECT(cpu), "apic", - OBJECT(cpu->apic_state), NULL); + object_property_add_child(OBJECT(cpu), "lapic", + OBJECT(cpu->apic_state), &error_abort); + object_unref(OBJECT(cpu->apic_state)); + qdev_prop_set_uint8(cpu->apic_state, "id", cpu->apic_id); /* TODO: convert to link<> */ apic = APIC_COMMON(cpu->apic_state); @@ -2926,6 +2880,31 @@ static void x86_cpu_apic_realize(X86CPU *cpu, Error **errp) } #endif +/* Note: Only safe for use on x86(-64) hosts */ +static uint32_t x86_host_phys_bits(void) +{ + uint32_t eax; + uint32_t host_phys_bits; + + host_cpuid(0x80000000, 0, &eax, NULL, NULL, NULL); + if (eax >= 0x80000008) { + host_cpuid(0x80000008, 0, &eax, NULL, NULL, NULL); + /* Note: According to AMD doc 25481 rev 2.34 they have a field + * at 23:16 that can specify a maximum physical address bits for + * the guest that can override this value; but I've not seen + * anything with that set. + */ + host_phys_bits = eax & 0xff; + } else { + /* It's an odd 64 bit machine that doesn't have the leaf for + * physical address bits; fall back to 36 that's most older + * Intel. + */ + host_phys_bits = 36; + } + + return host_phys_bits; +} #define IS_INTEL_CPU(env) ((env)->cpuid_vendor1 == CPUID_VENDOR_INTEL_1 && \ (env)->cpuid_vendor2 == CPUID_VENDOR_INTEL_2 && \ @@ -2950,7 +2929,7 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) goto out; } - if (cpu->apic_id < 0) { + if (cpu->apic_id == UNASSIGNED_APIC_ID) { error_setg(errp, "apic-id property was not initialized properly"); return; } @@ -2993,7 +2972,70 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) & CPUID_EXT2_AMD_ALIASES); } + /* For 64bit systems think about the number of physical bits to present. + * ideally this should be the same as the host; anything other than matching + * the host can cause incorrect guest behaviour. + * QEMU used to pick the magic value of 40 bits that corresponds to + * consumer AMD devices but nothing else. + */ + if (env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) { + if (kvm_enabled()) { + uint32_t host_phys_bits = x86_host_phys_bits(); + static bool warned; + + if (cpu->host_phys_bits) { + /* The user asked for us to use the host physical bits */ + cpu->phys_bits = host_phys_bits; + } + + /* Print a warning if the user set it to a value that's not the + * host value. + */ + if (cpu->phys_bits != host_phys_bits && cpu->phys_bits != 0 && + !warned) { + error_report("Warning: Host physical bits (%u)" + " does not match phys-bits property (%u)", + host_phys_bits, cpu->phys_bits); + warned = true; + } + + if (cpu->phys_bits && + (cpu->phys_bits > TARGET_PHYS_ADDR_SPACE_BITS || + cpu->phys_bits < 32)) { + error_setg(errp, "phys-bits should be between 32 and %u " + " (but is %u)", + TARGET_PHYS_ADDR_SPACE_BITS, cpu->phys_bits); + return; + } + } else { + if (cpu->phys_bits && cpu->phys_bits != TCG_PHYS_ADDR_BITS) { + error_setg(errp, "TCG only supports phys-bits=%u", + TCG_PHYS_ADDR_BITS); + return; + } + } + /* 0 means it was not explicitly set by the user (or by machine + * compat_props or by the host code above). In this case, the default + * is the value used by TCG (40). + */ + if (cpu->phys_bits == 0) { + cpu->phys_bits = TCG_PHYS_ADDR_BITS; + } + } else { + /* For 32 bit systems don't use the user set value, but keep + * phys_bits consistent with what we tell the guest. + */ + if (cpu->phys_bits != 0) { + error_setg(errp, "phys-bits is not user-configurable in 32 bit"); + return; + } + if (env->features[FEAT_1_EDX] & CPUID_PSE36) { + cpu->phys_bits = 36; + } else { + cpu->phys_bits = 32; + } + } cpu_exec_init(cs, &error_abort); if (tcg_enabled()) { @@ -3072,6 +3114,21 @@ out: } } +static void x86_cpu_unrealizefn(DeviceState *dev, Error **errp) +{ + X86CPU *cpu = X86_CPU(dev); + +#ifndef CONFIG_USER_ONLY + cpu_remove_sync(CPU(dev)); + qemu_unregister_reset(x86_cpu_machine_reset_cb, dev); +#endif + + if (cpu->apic_state) { + object_unparent(OBJECT(cpu->apic_state)); + cpu->apic_state = NULL; + } +} + typedef struct BitProperty { uint32_t *ptr; uint32_t mask; @@ -3207,9 +3264,6 @@ static void x86_cpu_initfn(Object *obj) object_property_add(obj, "tsc-frequency", "int", x86_cpuid_get_tsc_freq, x86_cpuid_set_tsc_freq, NULL, NULL, NULL); - object_property_add(obj, "apic-id", "int", - x86_cpuid_get_apic_id, - x86_cpuid_set_apic_id, NULL, NULL, NULL); object_property_add(obj, "feature-words", "X86CPUFeatureWordInfo", x86_cpu_get_feature_words, NULL, NULL, (void *)env->features, NULL); @@ -3219,11 +3273,6 @@ static void x86_cpu_initfn(Object *obj) cpu->hyperv_spinlock_attempts = HYPERV_SPINLOCK_NEVER_RETRY; -#ifndef CONFIG_USER_ONLY - /* Any code creating new X86CPU objects have to set apic-id explicitly */ - cpu->apic_id = -1; -#endif - for (w = 0; w < FEATURE_WORDS; w++) { int bitnr; @@ -3280,6 +3329,18 @@ static bool x86_cpu_has_work(CPUState *cs) } static Property x86_cpu_properties[] = { +#ifdef CONFIG_USER_ONLY + /* apic_id = 0 by default for *-user, see commit 9886e834 */ + DEFINE_PROP_UINT32("apic-id", X86CPU, apic_id, 0), + DEFINE_PROP_INT32("thread-id", X86CPU, thread_id, 0), + DEFINE_PROP_INT32("core-id", X86CPU, core_id, 0), + DEFINE_PROP_INT32("socket-id", X86CPU, socket_id, 0), +#else + DEFINE_PROP_UINT32("apic-id", X86CPU, apic_id, UNASSIGNED_APIC_ID), + DEFINE_PROP_INT32("thread-id", X86CPU, thread_id, -1), + DEFINE_PROP_INT32("core-id", X86CPU, core_id, -1), + DEFINE_PROP_INT32("socket-id", X86CPU, socket_id, -1), +#endif DEFINE_PROP_BOOL("pmu", X86CPU, enable_pmu, false), { .name = "hv-spinlocks", .info = &qdev_prop_spinlocks }, DEFINE_PROP_BOOL("hv-relaxed", X86CPU, hyperv_relaxed_timing, false), @@ -3294,6 +3355,9 @@ static Property x86_cpu_properties[] = { DEFINE_PROP_BOOL("check", X86CPU, check_cpuid, true), DEFINE_PROP_BOOL("enforce", X86CPU, enforce_cpuid, false), DEFINE_PROP_BOOL("kvm", X86CPU, expose_kvm, true), + DEFINE_PROP_UINT32("phys-bits", X86CPU, phys_bits, 0), + DEFINE_PROP_BOOL("host-phys-bits", X86CPU, host_phys_bits, false), + DEFINE_PROP_BOOL("fill-mtrr-mask", X86CPU, fill_mtrr_mask, true), DEFINE_PROP_UINT32("level", X86CPU, env.cpuid_level, 0), DEFINE_PROP_UINT32("xlevel", X86CPU, env.cpuid_xlevel, 0), DEFINE_PROP_UINT32("xlevel2", X86CPU, env.cpuid_xlevel2, 0), @@ -3311,6 +3375,7 @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data) xcc->parent_realize = dc->realize; dc->realize = x86_cpu_realizefn; + dc->unrealize = x86_cpu_unrealizefn; dc->props = x86_cpu_properties; xcc->parent_reset = cc->reset; @@ -3347,6 +3412,7 @@ static void x86_cpu_common_class_init(ObjectClass *oc, void *data) cc->cpu_exec_enter = x86_cpu_exec_enter; cc->cpu_exec_exit = x86_cpu_exec_exit; + dc->cannot_instantiate_with_device_add_yet = false; /* * Reason: x86_cpu_initfn() calls cpu_exec_init(), which saves the * object in cpus -> dangling pointer after final object_unref(). diff --git a/target-i386/cpu.h b/target-i386/cpu.h index 5b14a72baa..65615c0f3b 100644 --- a/target-i386/cpu.h +++ b/target-i386/cpu.h @@ -616,8 +616,10 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS]; #define CPUID_7_0_EBX_AVX512ER (1U << 27) /* AVX-512 Exponential and Reciprocal */ #define CPUID_7_0_EBX_AVX512CD (1U << 28) /* AVX-512 Conflict Detection */ +#define CPUID_7_0_ECX_UMIP (1U << 2) #define CPUID_7_0_ECX_PKU (1U << 3) #define CPUID_7_0_ECX_OSPKE (1U << 4) +#define CPUID_7_0_ECX_RDPID (1U << 22) #define CPUID_XSAVE_XSAVEOPT (1U << 0) #define CPUID_XSAVE_XSAVEC (1U << 1) @@ -845,6 +847,11 @@ typedef struct { #define NB_OPMASK_REGS 8 +/* CPU can't have 0xFFFFFFFF APIC ID, use that value to distinguish + * that APIC ID hasn't been set yet + */ +#define UNASSIGNED_APIC_ID 0xFFFFFFFF + typedef union X86LegacyXSaveArea { struct { uint16_t fcw; @@ -1174,7 +1181,7 @@ struct X86CPU { bool expose_kvm; bool migratable; bool host_features; - int64_t apic_id; + uint32_t apic_id; /* if true the CPUID code directly forward host cache leaves to the guest */ bool cache_info_passthrough; @@ -1198,6 +1205,15 @@ struct X86CPU { /* Compatibility bits for old machine types: */ bool enable_cpuid_0xb; + /* if true fill the top bits of the MTRR_PHYSMASKn variable range */ + bool fill_mtrr_mask; + + /* if true override the phys_bits value with a value read from the host */ + bool host_phys_bits; + + /* Number of physical address bits supported */ + uint32_t phys_bits; + /* in order to simplify APIC support, we leave this pointer to the user */ struct DeviceState *apic_state; @@ -1205,6 +1221,10 @@ struct X86CPU { Notifier machine_done; struct kvm_msrs *kvm_msr_buf; + + int32_t socket_id; + int32_t core_id; + int32_t thread_id; }; static inline X86CPU *x86_env_get_cpu(CPUX86State *env) @@ -1419,11 +1439,13 @@ uint64_t cpu_get_tsc(CPUX86State *env); /* XXX: This value should match the one returned by CPUID * and in exec.c */ # if defined(TARGET_X86_64) -# define PHYS_ADDR_MASK 0xffffffffffLL +# define TCG_PHYS_ADDR_BITS 40 # else -# define PHYS_ADDR_MASK 0xfffffffffLL +# define TCG_PHYS_ADDR_BITS 36 # endif +#define PHYS_ADDR_MASK MAKE_64BIT_MASK(0, TCG_PHYS_ADDR_BITS) + #define cpu_init(cpu_model) CPU(cpu_x86_init(cpu_model)) #define cpu_signal_handler cpu_x86_signal_handler diff --git a/target-i386/kvm.c b/target-i386/kvm.c index 0a09be656e..9697e16fdd 100644 --- a/target-i386/kvm.c +++ b/target-i386/kvm.c @@ -1719,6 +1719,8 @@ static int kvm_put_msrs(X86CPU *cpu, int level) } } if (has_msr_mtrr) { + uint64_t phys_mask = MAKE_64BIT_MASK(0, cpu->phys_bits); + kvm_msr_entry_add(cpu, MSR_MTRRdefType, env->mtrr_deftype); kvm_msr_entry_add(cpu, MSR_MTRRfix64K_00000, env->mtrr_fixed[0]); kvm_msr_entry_add(cpu, MSR_MTRRfix16K_80000, env->mtrr_fixed[1]); @@ -1732,10 +1734,15 @@ static int kvm_put_msrs(X86CPU *cpu, int level) kvm_msr_entry_add(cpu, MSR_MTRRfix4K_F0000, env->mtrr_fixed[9]); kvm_msr_entry_add(cpu, MSR_MTRRfix4K_F8000, env->mtrr_fixed[10]); for (i = 0; i < MSR_MTRRcap_VCNT; i++) { + /* The CPU GPs if we write to a bit above the physical limit of + * the host CPU (and KVM emulates that) + */ + uint64_t mask = env->mtrr_var[i].mask; + mask &= phys_mask; + kvm_msr_entry_add(cpu, MSR_MTRRphysBase(i), env->mtrr_var[i].base); - kvm_msr_entry_add(cpu, MSR_MTRRphysMask(i), - env->mtrr_var[i].mask); + kvm_msr_entry_add(cpu, MSR_MTRRphysMask(i), mask); } } @@ -1973,6 +1980,7 @@ static int kvm_get_msrs(X86CPU *cpu) CPUX86State *env = &cpu->env; struct kvm_msr_entry *msrs = cpu->kvm_msr_buf->entries; int ret, i; + uint64_t mtrr_top_bits; kvm_msr_buf_reset(cpu); @@ -2125,6 +2133,30 @@ static int kvm_get_msrs(X86CPU *cpu) } assert(ret == cpu->kvm_msr_buf->nmsrs); + /* + * MTRR masks: Each mask consists of 5 parts + * a 10..0: must be zero + * b 11 : valid bit + * c n-1.12: actual mask bits + * d 51..n: reserved must be zero + * e 63.52: reserved must be zero + * + * 'n' is the number of physical bits supported by the CPU and is + * apparently always <= 52. We know our 'n' but don't know what + * the destinations 'n' is; it might be smaller, in which case + * it masks (c) on loading. It might be larger, in which case + * we fill 'd' so that d..c is consistent irrespetive of the 'n' + * we're migrating to. + */ + + if (cpu->fill_mtrr_mask) { + QEMU_BUILD_BUG_ON(TARGET_PHYS_ADDR_SPACE_BITS > 52); + assert(cpu->phys_bits <= TARGET_PHYS_ADDR_SPACE_BITS); + mtrr_top_bits = MAKE_64BIT_MASK(cpu->phys_bits, 52 - cpu->phys_bits); + } else { + mtrr_top_bits = 0; + } + for (i = 0; i < ret; i++) { uint32_t index = msrs[i].index; switch (index) { @@ -2323,7 +2355,8 @@ static int kvm_get_msrs(X86CPU *cpu) break; case MSR_MTRRphysBase(0) ... MSR_MTRRphysMask(MSR_MTRRcap_VCNT - 1): if (index & 1) { - env->mtrr_var[MSR_MTRRphysIndex(index)].mask = msrs[i].data; + env->mtrr_var[MSR_MTRRphysIndex(index)].mask = msrs[i].data | + mtrr_top_bits; } else { env->mtrr_var[MSR_MTRRphysIndex(index)].base = msrs[i].data; } diff --git a/tests/Makefile.include b/tests/Makefile.include index 2010b11b6c..e7e50d6bd9 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -284,6 +284,10 @@ qapi-schema += args-alternate.json qapi-schema += args-any.json qapi-schema += args-array-empty.json qapi-schema += args-array-unknown.json +qapi-schema += args-bad-boxed.json +qapi-schema += args-boxed-anon.json +qapi-schema += args-boxed-empty.json +qapi-schema += args-boxed-string.json qapi-schema += args-int.json qapi-schema += args-invalid.json qapi-schema += args-member-array-bad.json @@ -317,6 +321,7 @@ qapi-schema += enum-wrong-data.json qapi-schema += escape-outside-string.json qapi-schema += escape-too-big.json qapi-schema += escape-too-short.json +qapi-schema += event-boxed-empty.json qapi-schema += event-case.json qapi-schema += event-nest-struct.json qapi-schema += flat-union-array-branch.json @@ -326,6 +331,7 @@ qapi-schema += flat-union-base-any.json qapi-schema += flat-union-base-union.json qapi-schema += flat-union-clash-member.json qapi-schema += flat-union-empty.json +qapi-schema += flat-union-incomplete-branch.json qapi-schema += flat-union-inline.json qapi-schema += flat-union-int-branch.json qapi-schema += flat-union-invalid-branch-key.json diff --git a/tests/docker/Makefile.include b/tests/docker/Makefile.include index f88c0a7309..78af46837b 100644 --- a/tests/docker/Makefile.include +++ b/tests/docker/Makefile.include @@ -46,7 +46,8 @@ docker-image: ${DOCKER_TARGETS} docker-image-%: $(DOCKER_FILES_DIR)/%.docker $(call quiet-command,\ $(SRC_PATH)/tests/docker/docker.py build qemu:$* $< \ - $(if $V,,--quiet) $(if $(NOCACHE),--no-cache),\ + $(if $V,,--quiet) $(if $(NOCACHE),--no-cache) \ + $(if $(EXECUTABLE),--include-executable=$(EXECUTABLE)),\ " BUILD $*") # Expand all the pre-requistes for each docker image and test combination @@ -95,6 +96,7 @@ docker: @echo ' DEBUG=1 Stop and drop to shell in the created container' @echo ' before running the command.' @echo ' NOCACHE=1 Ignore cache when build images.' + @echo ' EXECUTABLE=<path> Include executable in image.' docker-run-%: CMD = $(shell echo '$@' | sed -e 's/docker-run-\([^@]*\)@\(.*\)/\1/') docker-run-%: IMAGE = $(shell echo '$@' | sed -e 's/docker-run-\([^@]*\)@\(.*\)/\2/') @@ -105,7 +107,10 @@ docker-run-%: docker-qemu-src fi $(if $(filter $(TESTS),$(CMD)),$(if $(filter $(IMAGES),$(IMAGE)), \ $(call quiet-command,\ - $(SRC_PATH)/tests/docker/docker.py run $(if $V,,--rm) \ + if $(SRC_PATH)/tests/docker/docker.py images \ + --format={{.Repository}}:{{.Tag}} | \ + grep -qx qemu:$(IMAGE); then \ + $(SRC_PATH)/tests/docker/docker.py run $(if $V,,--rm) \ -t \ $(if $(DEBUG),-i,--net=none) \ -e TARGET_LIST=$(TARGET_LIST) \ @@ -114,11 +119,10 @@ docker-run-%: docker-qemu-src -e CCACHE_DIR=/var/tmp/ccache \ -v $$(realpath $(DOCKER_SRC_COPY)):/var/tmp/qemu:z$(COMMA)ro \ -v $(DOCKER_CCACHE_DIR):/var/tmp/ccache:z \ - -w /var/tmp/qemu \ qemu:$(IMAGE) \ - $(if $V,/bin/bash -x ,) \ - ./run \ + /var/tmp/qemu/run \ $(CMD); \ + fi \ , " RUN $(CMD) in $(IMAGE)"))) docker-clean: diff --git a/tests/docker/docker.py b/tests/docker/docker.py index 0151362d17..222a1053fe 100755 --- a/tests/docker/docker.py +++ b/tests/docker/docker.py @@ -20,7 +20,10 @@ import atexit import uuid import argparse import tempfile -from shutil import copy +import re +from tarfile import TarFile, TarInfo +from StringIO import StringIO +from shutil import copy, rmtree def _text_checksum(text): """Calculate a digest string unique to the text content""" @@ -38,6 +41,54 @@ def _guess_docker_command(): raise Exception("Cannot find working docker command. Tried:\n%s" % \ commands_txt) +def _copy_with_mkdir(src, root_dir, sub_path): + """Copy src into root_dir, creating sub_path as needed.""" + dest_dir = os.path.normpath("%s/%s" % (root_dir, sub_path)) + try: + os.makedirs(dest_dir) + except OSError: + # we can safely ignore already created directories + pass + + dest_file = "%s/%s" % (dest_dir, os.path.basename(src)) + copy(src, dest_file) + + +def _get_so_libs(executable): + """Return a list of libraries associated with an executable. + + The paths may be symbolic links which would need to be resolved to + ensure theright data is copied.""" + + libs = [] + ldd_re = re.compile(r"(/.*/)(\S*)") + try: + ldd_output = subprocess.check_output(["ldd", executable]) + for line in ldd_output.split("\n"): + search = ldd_re.search(line) + if search and len(search.groups()) == 2: + so_path = search.groups()[0] + so_lib = search.groups()[1] + libs.append("%s/%s" % (so_path, so_lib)) + except subprocess.CalledProcessError: + print "%s had no associated libraries (static build?)" % (executable) + + return libs + +def _copy_binary_with_libs(src, dest_dir): + """Copy a binary executable and all its dependant libraries. + + This does rely on the host file-system being fairly multi-arch + aware so the file don't clash with the guests layout.""" + + _copy_with_mkdir(src, dest_dir, "/usr/bin") + + libs = _get_so_libs(src) + if libs: + for l in libs: + so_path = os.path.dirname(l) + _copy_with_mkdir(l , dest_dir, so_path) + class Docker(object): """ Running Docker commands """ def __init__(self): @@ -45,9 +96,11 @@ class Docker(object): self._instances = [] atexit.register(self._kill_instances) - def _do(self, cmd, quiet=True, **kwargs): + def _do(self, cmd, quiet=True, infile=None, **kwargs): if quiet: kwargs["stdout"] = subprocess.PIPE + if infile: + kwargs["stdin"] = infile return subprocess.call(self._command + cmd, **kwargs) def _do_kill_instances(self, only_known, only_active=True): @@ -87,22 +140,27 @@ class Docker(object): labels = json.loads(resp)[0]["Config"].get("Labels", {}) return labels.get("com.qemu.dockerfile-checksum", "") - def build_image(self, tag, dockerfile, df_path, quiet=True, argv=None): + def build_image(self, tag, docker_dir, dockerfile, quiet=True, argv=None): if argv == None: argv = [] - tmp_dir = tempfile.mkdtemp(prefix="docker_build") - tmp_df = tempfile.NamedTemporaryFile(dir=tmp_dir, suffix=".docker") + tmp_df = tempfile.NamedTemporaryFile(dir=docker_dir, suffix=".docker") tmp_df.write(dockerfile) tmp_df.write("\n") tmp_df.write("LABEL com.qemu.dockerfile-checksum=%s" % _text_checksum(dockerfile)) tmp_df.flush() + self._do(["build", "-t", tag, "-f", tmp_df.name] + argv + \ - [tmp_dir], + [docker_dir], quiet=quiet) + def update_image(self, tag, tarball, quiet=True): + "Update a tagged image using " + + self._do(["build", "-t", tag, "-"], quiet=quiet, infile=tarball) + def image_matches_dockerfile(self, tag, dockerfile): try: checksum = self.get_image_dockerfile_checksum(tag) @@ -121,6 +179,9 @@ class Docker(object): self._instances.remove(label) return ret + def command(self, cmd, argv, quiet): + return self._do([cmd] + argv, quiet=quiet) + class SubCommand(object): """A SubCommand template base class""" name = None # Subcommand name @@ -151,6 +212,10 @@ class BuildCommand(SubCommand): """ Build docker image out of a dockerfile. Arguments: <tag> <dockerfile>""" name = "build" def args(self, parser): + parser.add_argument("--include-executable", "-e", + help="""Specify a binary that will be copied to the + container together with all its dependent + libraries""") parser.add_argument("tag", help="Image Tag") parser.add_argument("dockerfile", @@ -164,10 +229,80 @@ class BuildCommand(SubCommand): if dkr.image_matches_dockerfile(tag, dockerfile): if not args.quiet: print "Image is up to date." - return 0 + else: + # Create a docker context directory for the build + docker_dir = tempfile.mkdtemp(prefix="docker_build") + + # Is there a .pre file to run in the build context? + docker_pre = os.path.splitext(args.dockerfile)[0]+".pre" + if os.path.exists(docker_pre): + rc = subprocess.call(os.path.realpath(docker_pre), + cwd=docker_dir) + if rc == 3: + print "Skip" + return 0 + elif rc != 0: + print "%s exited with code %d" % (docker_pre, rc) + return 1 + + # Do we include a extra binary? + if args.include_executable: + _copy_binary_with_libs(args.include_executable, + docker_dir) + + dkr.build_image(tag, docker_dir, dockerfile, + quiet=args.quiet, argv=argv) + + rmtree(docker_dir) + + return 0 + +class UpdateCommand(SubCommand): + """ Update a docker image with new executables. Arguments: <tag> <executable>""" + name = "update" + def args(self, parser): + parser.add_argument("tag", + help="Image Tag") + parser.add_argument("executable", + help="Executable to copy") + + def run(self, args, argv): + # Create a temporary tarball with our whole build context and + # dockerfile for the update + tmp = tempfile.NamedTemporaryFile(suffix="dckr.tar.gz") + tmp_tar = TarFile(fileobj=tmp, mode='w') + + # Add the executable to the tarball + bn = os.path.basename(args.executable) + ff = "/usr/bin/%s" % bn + tmp_tar.add(args.executable, arcname=ff) + + # Add any associated libraries + libs = _get_so_libs(args.executable) + if libs: + for l in libs: + tmp_tar.add(os.path.realpath(l), arcname=l) + + # Create a Docker buildfile + df = StringIO() + df.write("FROM %s\n" % args.tag) + df.write("ADD . /\n") + df.seek(0) + + df_tar = TarInfo(name="Dockerfile") + df_tar.size = len(df.buf) + tmp_tar.addfile(df_tar, fileobj=df) + + tmp_tar.close() + + # reset the file pointers + tmp.flush() + tmp.seek(0) + + # Run the build with our tarball context + dkr = Docker() + dkr.update_image(args.tag, tmp, quiet=args.quiet) - dkr.build_image(tag, dockerfile, args.dockerfile, - quiet=args.quiet, argv=argv) return 0 class CleanCommand(SubCommand): @@ -177,6 +312,12 @@ class CleanCommand(SubCommand): Docker().clean() return 0 +class ImagesCommand(SubCommand): + """Run "docker images" command""" + name = "images" + def run(self, args, argv): + return Docker().command("images", argv, args.quiet) + def main(): parser = argparse.ArgumentParser(description="A Docker helper", usage="%s <subcommand> ..." % os.path.basename(sys.argv[0])) diff --git a/tests/docker/dockerfiles/debian-bootstrap.docker b/tests/docker/dockerfiles/debian-bootstrap.docker new file mode 100644 index 0000000000..3a9125e497 --- /dev/null +++ b/tests/docker/dockerfiles/debian-bootstrap.docker @@ -0,0 +1,21 @@ +# Create Debian Bootstrap Image +# +# This is intended to be pre-poluated by: +# - a first stage debootstrap (see debian-bootstrap.pre) +# - a native qemu-$arch that binfmt_misc will run +FROM scratch + +# Add everything from the context into the container +ADD . / + +# Patch all mounts as docker already has stuff set up +RUN sed -i 's/in_target mount/echo not for docker in_target mount/g' /debootstrap/functions + +# Run stage 2 +RUN /debootstrap/debootstrap --second-stage + +# At this point we can install additional packages if we want +# Duplicate deb line as deb-src +RUN cat /etc/apt/sources.list | sed "s/deb/deb-src/" >> /etc/apt/sources.list +RUN apt-get update +RUN apt-get -y build-dep qemu diff --git a/tests/docker/dockerfiles/debian-bootstrap.pre b/tests/docker/dockerfiles/debian-bootstrap.pre new file mode 100755 index 0000000000..5d9c8d5ebc --- /dev/null +++ b/tests/docker/dockerfiles/debian-bootstrap.pre @@ -0,0 +1,87 @@ +#!/bin/sh +# +# Simple wrapper for debootstrap, run in the docker build context +# +FAKEROOT=`which fakeroot 2> /dev/null` + +exit_and_skip() +{ + exit 3 +} + +# +# fakeroot is needed to run the bootstrap stage +# +if [ -z $FAKEROOT ]; then + echo "Please install fakeroot to enable bootstraping" + exit_and_skip +fi + +# We check in order for +# +# - DEBOOTSTRAP_DIR pointing at a development checkout +# - PATH for the debootstrap script (installed) +# +# If neither option works then we checkout debootstrap from its +# upstream SCM and run it from there. +# + +if [ -z $DEBOOTSTRAP_DIR ]; then + DEBOOTSTRAP=`which debootstrap 2> /dev/null` + if [ -z $DEBOOTSTRAP ]; then + echo "No debootstrap installed, attempting to install from SCM" + DEBOOTSTRAP_SOURCE=https://anonscm.debian.org/git/d-i/debootstrap.git + git clone ${DEBOOTSTRAP_SOURCE} ./debootstrap.git + export DEBOOTSTRAP_DIR=./debootstrap.git + DEBOOTSTRAP=./debootstrap.git/debootstrap + fi +else + DEBOOTSTRAP=${DEBOOTSTRAP_DIR}/debootstrap + if [ ! -f $DEBOOTSTRAP ]; then + echo "Couldn't find script at ${DEBOOTSTRAP}" + exit_and_skip + fi +fi + +# +# Finally check to see if any qemu's are installed +# +BINFMT_DIR=/proc/sys/fs/binfmt_misc +if [ ! -e $BINFMT_DIR ]; then + echo "binfmt_misc needs enabling for a QEMU bootstrap to work" + exit_and_skip +else + # DEB_ARCH and QEMU arch names are not totally aligned + case "${DEB_ARCH}" in + amd64) + QEMU=qemu-i386 + ;; + armel|armhf) + QEMU=qemu-arm + ;; + arm64) + QEMU=qemu-aarch64 + ;; + powerpc) + QEMU=qemu-ppc + ;; + ppc64el) + QEMU=qemu-ppc64le + ;; + s390) + QEMU=qemu-s390x + ;; + *) + QEMU=qemu-${DEB_ARCH} + ;; + esac + if [ ! -e "${BINFMT_DIR}/$QEMU" ]; then + echo "No binfmt_misc rule to run $QEMU, can't bootstrap" + exit_and_skip + fi +fi + +echo "Building a rootfs using ${FAKEROOT} and ${DEBOOTSTRAP} ${DEB_ARCH}/${DEB_TYPE}" + +${FAKEROOT} ${DEBOOTSTRAP} --variant=buildd --foreign --arch=$DEB_ARCH $DEB_TYPE . http://httpredir.debian.org/debian || exit 1 +exit 0 diff --git a/tests/docker/run b/tests/docker/run index ec3d11934b..d85d49afc1 100755 --- a/tests/docker/run +++ b/tests/docker/run @@ -11,6 +11,14 @@ # or (at your option) any later version. See the COPYING file in # the top-level directory. +set -e + +if test -n "$V"; then + set -x +fi + +BASE="$(dirname $(readlink -e $0))" + # Prepare the environment . /etc/profile || true export PATH=/usr/lib/ccache:$PATH @@ -24,10 +32,10 @@ export TEST_DIR=/tmp/qemu-test mkdir -p $TEST_DIR/{src,build,install} # Extract the source tarballs -tar -C $TEST_DIR/src -xzf qemu.tgz +tar -C $TEST_DIR/src -xzf $BASE/qemu.tgz for p in dtc pixman; do - if test -f $p.tgz; then - tar -C $TEST_DIR/src/$p -xzf $p.tgz + if test -f $BASE/$p.tgz; then + tar -C $TEST_DIR/src/$p -xzf $BASE/$p.tgz export FEATURES="$FEATURES $p" fi done @@ -55,4 +63,6 @@ elif test -n "$DEBUG"; then echo # Force error after shell exits $SHELL && exit 1 +else + exit 1 fi diff --git a/tests/qapi-schema/args-bad-boxed.err b/tests/qapi-schema/args-bad-boxed.err new file mode 100644 index 0000000000..ad0d417321 --- /dev/null +++ b/tests/qapi-schema/args-bad-boxed.err @@ -0,0 +1 @@ +tests/qapi-schema/args-bad-boxed.json:2: 'boxed' of command 'foo' should only use true value diff --git a/tests/qapi-schema/args-bad-boxed.exit b/tests/qapi-schema/args-bad-boxed.exit new file mode 100644 index 0000000000..d00491fd7e --- /dev/null +++ b/tests/qapi-schema/args-bad-boxed.exit @@ -0,0 +1 @@ +1 diff --git a/tests/qapi-schema/args-bad-boxed.json b/tests/qapi-schema/args-bad-boxed.json new file mode 100644 index 0000000000..dea0cd0aa5 --- /dev/null +++ b/tests/qapi-schema/args-bad-boxed.json @@ -0,0 +1,2 @@ +# 'boxed' should only appear with value true +{ 'command': 'foo', 'boxed': false } diff --git a/tests/qapi-schema/args-bad-boxed.out b/tests/qapi-schema/args-bad-boxed.out new file mode 100644 index 0000000000..e69de29bb2 --- /dev/null +++ b/tests/qapi-schema/args-bad-boxed.out diff --git a/tests/qapi-schema/args-boxed-anon.err b/tests/qapi-schema/args-boxed-anon.err new file mode 100644 index 0000000000..f24f345218 --- /dev/null +++ b/tests/qapi-schema/args-boxed-anon.err @@ -0,0 +1 @@ +tests/qapi-schema/args-boxed-anon.json:2: 'data' for command 'foo' should be a type name diff --git a/tests/qapi-schema/args-boxed-anon.exit b/tests/qapi-schema/args-boxed-anon.exit new file mode 100644 index 0000000000..d00491fd7e --- /dev/null +++ b/tests/qapi-schema/args-boxed-anon.exit @@ -0,0 +1 @@ +1 diff --git a/tests/qapi-schema/args-boxed-anon.json b/tests/qapi-schema/args-boxed-anon.json new file mode 100644 index 0000000000..95f60da2ed --- /dev/null +++ b/tests/qapi-schema/args-boxed-anon.json @@ -0,0 +1,2 @@ +# 'boxed' can only be used with named types +{ 'command': 'foo', 'boxed': true, 'data': { 'string': 'str' } } diff --git a/tests/qapi-schema/args-boxed-anon.out b/tests/qapi-schema/args-boxed-anon.out new file mode 100644 index 0000000000..e69de29bb2 --- /dev/null +++ b/tests/qapi-schema/args-boxed-anon.out diff --git a/tests/qapi-schema/args-boxed-empty.err b/tests/qapi-schema/args-boxed-empty.err new file mode 100644 index 0000000000..039603e85c --- /dev/null +++ b/tests/qapi-schema/args-boxed-empty.err @@ -0,0 +1 @@ +tests/qapi-schema/args-boxed-empty.json:3: Cannot use 'boxed' with empty type diff --git a/tests/qapi-schema/args-boxed-empty.exit b/tests/qapi-schema/args-boxed-empty.exit new file mode 100644 index 0000000000..d00491fd7e --- /dev/null +++ b/tests/qapi-schema/args-boxed-empty.exit @@ -0,0 +1 @@ +1 diff --git a/tests/qapi-schema/args-boxed-empty.json b/tests/qapi-schema/args-boxed-empty.json new file mode 100644 index 0000000000..52717e065f --- /dev/null +++ b/tests/qapi-schema/args-boxed-empty.json @@ -0,0 +1,3 @@ +# 'boxed' requires a non-empty type +{ 'struct': 'Empty', 'data': {} } +{ 'command': 'foo', 'boxed': true, 'data': 'Empty' } diff --git a/tests/qapi-schema/args-boxed-empty.out b/tests/qapi-schema/args-boxed-empty.out new file mode 100644 index 0000000000..e69de29bb2 --- /dev/null +++ b/tests/qapi-schema/args-boxed-empty.out diff --git a/tests/qapi-schema/args-boxed-string.err b/tests/qapi-schema/args-boxed-string.err new file mode 100644 index 0000000000..d326b48aef --- /dev/null +++ b/tests/qapi-schema/args-boxed-string.err @@ -0,0 +1 @@ +tests/qapi-schema/args-boxed-string.json:2: 'data' for command 'foo' cannot use built-in type 'str' diff --git a/tests/qapi-schema/args-boxed-string.exit b/tests/qapi-schema/args-boxed-string.exit new file mode 100644 index 0000000000..d00491fd7e --- /dev/null +++ b/tests/qapi-schema/args-boxed-string.exit @@ -0,0 +1 @@ +1 diff --git a/tests/qapi-schema/args-boxed-string.json b/tests/qapi-schema/args-boxed-string.json new file mode 100644 index 0000000000..f91a1502e7 --- /dev/null +++ b/tests/qapi-schema/args-boxed-string.json @@ -0,0 +1,2 @@ +# 'boxed' requires a complex (not built-in) type +{ 'command': 'foo', 'boxed': true, 'data': 'str' } diff --git a/tests/qapi-schema/args-boxed-string.out b/tests/qapi-schema/args-boxed-string.out new file mode 100644 index 0000000000..e69de29bb2 --- /dev/null +++ b/tests/qapi-schema/args-boxed-string.out diff --git a/tests/qapi-schema/args-union.err b/tests/qapi-schema/args-union.err index 1d693d74da..f8ad223dde 100644 --- a/tests/qapi-schema/args-union.err +++ b/tests/qapi-schema/args-union.err @@ -1 +1 @@ -tests/qapi-schema/args-union.json:4: 'data' for command 'oops' cannot use union type 'Uni' +tests/qapi-schema/args-union.json:3: 'data' for command 'oops' cannot use union type 'Uni' diff --git a/tests/qapi-schema/args-union.json b/tests/qapi-schema/args-union.json index 7bdcbb7f08..2fcaeaae16 100644 --- a/tests/qapi-schema/args-union.json +++ b/tests/qapi-schema/args-union.json @@ -1,4 +1,3 @@ -# we do not allow union arguments -# TODO should we support this? +# use of union arguments requires 'boxed':true { 'union': 'Uni', 'data': { 'case1': 'int', 'case2': 'str' } } { 'command': 'oops', 'data': 'Uni' } diff --git a/tests/qapi-schema/event-boxed-empty.err b/tests/qapi-schema/event-boxed-empty.err new file mode 100644 index 0000000000..68ec6f2d2b --- /dev/null +++ b/tests/qapi-schema/event-boxed-empty.err @@ -0,0 +1 @@ +tests/qapi-schema/event-boxed-empty.json:2: Use of 'boxed' requires 'data' diff --git a/tests/qapi-schema/event-boxed-empty.exit b/tests/qapi-schema/event-boxed-empty.exit new file mode 100644 index 0000000000..d00491fd7e --- /dev/null +++ b/tests/qapi-schema/event-boxed-empty.exit @@ -0,0 +1 @@ +1 diff --git a/tests/qapi-schema/event-boxed-empty.json b/tests/qapi-schema/event-boxed-empty.json new file mode 100644 index 0000000000..cb145f1433 --- /dev/null +++ b/tests/qapi-schema/event-boxed-empty.json @@ -0,0 +1,2 @@ +# 'boxed' requires a non-empty type +{ 'event': 'FOO', 'boxed': true } diff --git a/tests/qapi-schema/event-boxed-empty.out b/tests/qapi-schema/event-boxed-empty.out new file mode 100644 index 0000000000..e69de29bb2 --- /dev/null +++ b/tests/qapi-schema/event-boxed-empty.out diff --git a/tests/qapi-schema/event-case.out b/tests/qapi-schema/event-case.out index b6b4134a80..5a0f2bf805 100644 --- a/tests/qapi-schema/event-case.out +++ b/tests/qapi-schema/event-case.out @@ -1,4 +1,5 @@ enum QType ['none', 'qnull', 'qint', 'qstring', 'qdict', 'qlist', 'qfloat', 'qbool'] prefix QTYPE event oops None + boxed=False object q_empty diff --git a/tests/qapi-schema/flat-union-incomplete-branch.err b/tests/qapi-schema/flat-union-incomplete-branch.err new file mode 100644 index 0000000000..e826bf0789 --- /dev/null +++ b/tests/qapi-schema/flat-union-incomplete-branch.err @@ -0,0 +1 @@ +tests/qapi-schema/flat-union-incomplete-branch.json:6: Union 'TestUnion' data missing 'value2' branch diff --git a/tests/qapi-schema/flat-union-incomplete-branch.exit b/tests/qapi-schema/flat-union-incomplete-branch.exit new file mode 100644 index 0000000000..d00491fd7e --- /dev/null +++ b/tests/qapi-schema/flat-union-incomplete-branch.exit @@ -0,0 +1 @@ +1 diff --git a/tests/qapi-schema/flat-union-incomplete-branch.json b/tests/qapi-schema/flat-union-incomplete-branch.json new file mode 100644 index 0000000000..25a411bc83 --- /dev/null +++ b/tests/qapi-schema/flat-union-incomplete-branch.json @@ -0,0 +1,9 @@ +# we require all branches of the union to be covered +{ 'enum': 'TestEnum', + 'data': [ 'value1', 'value2' ] } +{ 'struct': 'TestTypeA', + 'data': { 'string': 'str' } } +{ 'union': 'TestUnion', + 'base': { 'type': 'TestEnum' }, + 'discriminator': 'type', + 'data': { 'value1': 'TestTypeA' } } diff --git a/tests/qapi-schema/flat-union-incomplete-branch.out b/tests/qapi-schema/flat-union-incomplete-branch.out new file mode 100644 index 0000000000..e69de29bb2 --- /dev/null +++ b/tests/qapi-schema/flat-union-incomplete-branch.out diff --git a/tests/qapi-schema/ident-with-escape.out b/tests/qapi-schema/ident-with-escape.out index 382ce2fa27..1d2722c02e 100644 --- a/tests/qapi-schema/ident-with-escape.out +++ b/tests/qapi-schema/ident-with-escape.out @@ -1,7 +1,7 @@ enum QType ['none', 'qnull', 'qint', 'qstring', 'qdict', 'qlist', 'qfloat', 'qbool'] prefix QTYPE command fooA q_obj_fooA-arg -> None - gen=True success_response=True + gen=True success_response=True boxed=False object q_empty object q_obj_fooA-arg member bar1: str optional=False diff --git a/tests/qapi-schema/indented-expr.out b/tests/qapi-schema/indented-expr.out index ae3293a3ae..e8171c935f 100644 --- a/tests/qapi-schema/indented-expr.out +++ b/tests/qapi-schema/indented-expr.out @@ -1,7 +1,7 @@ enum QType ['none', 'qnull', 'qint', 'qstring', 'qdict', 'qlist', 'qfloat', 'qbool'] prefix QTYPE command eins None -> None - gen=True success_response=True + gen=True success_response=True boxed=False object q_empty command zwei None -> None - gen=True success_response=True + gen=True success_response=True boxed=False diff --git a/tests/qapi-schema/qapi-schema-test.json b/tests/qapi-schema/qapi-schema-test.json index f571e1bb34..17194637ba 100644 --- a/tests/qapi-schema/qapi-schema-test.json +++ b/tests/qapi-schema/qapi-schema-test.json @@ -127,6 +127,8 @@ { 'command': 'guest-get-time', 'data': {'a': 'int', '*b': 'int' }, 'returns': 'int' } { 'command': 'guest-sync', 'data': { 'arg': 'any' }, 'returns': 'any' } +{ 'command': 'boxed-struct', 'boxed': true, 'data': 'UserDefZero' } +{ 'command': 'boxed-union', 'data': 'UserDefNativeListUnion', 'boxed': true } # For testing integer range flattening in opts-visitor. The following schema # corresponds to the option format: @@ -154,6 +156,8 @@ 'data': { '*a': 'int', '*b': 'UserDefOne', 'c': 'str' } } { 'event': 'EVENT_D', 'data': { 'a' : 'EventStructOne', 'b' : 'str', '*c': 'str', '*enum3': 'EnumOne' } } +{ 'event': 'EVENT_E', 'boxed': true, 'data': 'UserDefZero' } +{ 'event': 'EVENT_F', 'boxed': true, 'data': 'UserDefAlternate' } # test that we correctly compile downstream extensions, as well as munge # ticklish names diff --git a/tests/qapi-schema/qapi-schema-test.out b/tests/qapi-schema/qapi-schema-test.out index 19cd214f6b..9d99c4eebb 100644 --- a/tests/qapi-schema/qapi-schema-test.out +++ b/tests/qapi-schema/qapi-schema-test.out @@ -1,25 +1,39 @@ alternate AltIntNum + tag type case i: int case n: number alternate AltNumInt + tag type case n: number case i: int alternate AltNumStr + tag type case n: number case s: str alternate AltStrBool + tag type case s: str case b: bool alternate AltStrInt + tag type case s: str case i: int alternate AltStrNum + tag type case s: str case n: number event EVENT_A None + boxed=False event EVENT_B None + boxed=False event EVENT_C q_obj_EVENT_C-arg + boxed=False event EVENT_D q_obj_EVENT_D-arg + boxed=False +event EVENT_E UserDefZero + boxed=True +event EVENT_F UserDefAlternate + boxed=True object Empty1 object Empty2 base Empty1 @@ -50,6 +64,7 @@ object UserDefA member boolean: bool optional=False member a_b: int optional=True alternate UserDefAlternate + tag type case udfu: UserDefFlatUnion case s: str case i: int @@ -72,6 +87,7 @@ object UserDefFlatUnion2 case value2: UserDefB object UserDefNativeListUnion member type: UserDefNativeListUnionKind optional=False + tag type case integer: q_obj_intList-wrapper case s8: q_obj_int8List-wrapper case s16: q_obj_int16List-wrapper @@ -116,7 +132,9 @@ object UserDefZero object WrapAlternate member alt: UserDefAlternate optional=False event __ORG.QEMU_X-EVENT __org.qemu_x-Struct + boxed=False alternate __org.qemu_x-Alt + tag type case __org.qemu_x-branch: str case b: __org.qemu_x-Base object __org.qemu_x-Base @@ -130,6 +148,7 @@ object __org.qemu_x-Struct2 member array: __org.qemu_x-Union1List optional=False object __org.qemu_x-Union1 member type: __org.qemu_x-Union1Kind optional=False + tag type case __org.qemu_x-branch: q_obj_str-wrapper enum __org.qemu_x-Union1Kind ['__org.qemu_x-branch'] object __org.qemu_x-Union2 @@ -137,11 +156,15 @@ object __org.qemu_x-Union2 tag __org.qemu_x-member1 case __org.qemu_x-value: __org.qemu_x-Struct2 command __org.qemu_x-command q_obj___org.qemu_x-command-arg -> __org.qemu_x-Union1 - gen=True success_response=True + gen=True success_response=True boxed=False +command boxed-struct UserDefZero -> None + gen=True success_response=True boxed=True +command boxed-union UserDefNativeListUnion -> None + gen=True success_response=True boxed=True command guest-get-time q_obj_guest-get-time-arg -> int - gen=True success_response=True + gen=True success_response=True boxed=False command guest-sync q_obj_guest-sync-arg -> any - gen=True success_response=True + gen=True success_response=True boxed=False object q_empty object q_obj_EVENT_C-arg member a: int optional=True @@ -202,10 +225,10 @@ object q_obj_user_def_cmd2-arg member ud1a: UserDefOne optional=False member ud1b: UserDefOne optional=True command user_def_cmd None -> None - gen=True success_response=True + gen=True success_response=True boxed=False command user_def_cmd0 Empty2 -> Empty2 - gen=True success_response=True + gen=True success_response=True boxed=False command user_def_cmd1 q_obj_user_def_cmd1-arg -> None - gen=True success_response=True + gen=True success_response=True boxed=False command user_def_cmd2 q_obj_user_def_cmd2-arg -> UserDefTwo - gen=True success_response=True + gen=True success_response=True boxed=False diff --git a/tests/qapi-schema/test-qapi.py b/tests/qapi-schema/test-qapi.py index 649677e017..ef74e2c4c8 100644 --- a/tests/qapi-schema/test-qapi.py +++ b/tests/qapi-schema/test-qapi.py @@ -36,19 +36,20 @@ class QAPISchemaTestVisitor(QAPISchemaVisitor): self._print_variants(variants) def visit_command(self, name, info, arg_type, ret_type, - gen, success_response): + gen, success_response, boxed): print 'command %s %s -> %s' % \ (name, arg_type and arg_type.name, ret_type and ret_type.name) - print ' gen=%s success_response=%s' % (gen, success_response) + print ' gen=%s success_response=%s boxed=%s' % \ + (gen, success_response, boxed) - def visit_event(self, name, info, arg_type): + def visit_event(self, name, info, arg_type, boxed): print 'event %s %s' % (name, arg_type and arg_type.name) + print ' boxed=%s' % boxed @staticmethod def _print_variants(variants): if variants: - if variants.tag_name: - print ' tag %s' % variants.tag_name + print ' tag %s' % variants.tag_member.name for v in variants.variants: print ' case %s: %s' % (v.name, v.type.name) diff --git a/tests/test-qmp-commands.c b/tests/test-qmp-commands.c index 8ffeb045cd..5af1a468b8 100644 --- a/tests/test-qmp-commands.c +++ b/tests/test-qmp-commands.c @@ -59,6 +59,14 @@ QObject *qmp_guest_sync(QObject *arg, Error **errp) return arg; } +void qmp_boxed_struct(UserDefZero *arg, Error **errp) +{ +} + +void qmp_boxed_union(UserDefNativeListUnion *arg, Error **errp) +{ +} + __org_qemu_x_Union1 *qmp___org_qemu_x_command(__org_qemu_x_EnumList *a, __org_qemu_x_StructList *b, __org_qemu_x_Union2 *c, |