diff options
Diffstat (limited to 'nbd/server.c')
| -rw-r--r-- | nbd/server.c | 309 |
1 files changed, 131 insertions, 178 deletions
diff --git a/nbd/server.c b/nbd/server.c index 982de67816..f74766add7 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -18,6 +18,8 @@ */ #include "qemu/osdep.h" + +#include "block/export.h" #include "qapi/error.h" #include "qemu/queue.h" #include "trace.h" @@ -80,20 +82,15 @@ struct NBDRequestData { }; struct NBDExport { - int refcount; - void (*close)(NBDExport *exp); + BlockExport common; - BlockBackend *blk; char *name; char *description; - uint64_t dev_offset; uint64_t size; uint16_t nbdflags; QTAILQ_HEAD(, NBDClient) clients; QTAILQ_ENTRY(NBDExport) next; - AioContext *ctx; - BlockBackend *eject_notifier_blk; Notifier eject_notifier; @@ -102,8 +99,6 @@ struct NBDExport { }; static QTAILQ_HEAD(, NBDExport) exports = QTAILQ_HEAD_INITIALIZER(exports); -static QTAILQ_HEAD(, NBDExport) closed_exports = - QTAILQ_HEAD_INITIALIZER(closed_exports); /* NBDExportMetaContexts represents a list of contexts to be exported, * as selected by NBD_OPT_SET_META_CONTEXT. Also used for @@ -498,7 +493,7 @@ static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes, } QTAILQ_INSERT_TAIL(&client->exp->clients, client, next); - nbd_export_get(client->exp); + blk_exp_ref(&client->exp->common); nbd_check_meta_export(client); return 0; @@ -647,7 +642,7 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp) * whether this is OPT_INFO or OPT_GO. */ /* minimum - 1 for back-compat, or actual if client will obey it. */ if (client->opt == NBD_OPT_INFO || blocksize) { - check_align = sizes[0] = blk_get_request_alignment(exp->blk); + check_align = sizes[0] = blk_get_request_alignment(exp->common.blk); } else { sizes[0] = 1; } @@ -656,7 +651,7 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp) * TODO: is blk_bs(blk)->bl.opt_transfer appropriate? */ sizes[1] = MAX(4096, sizes[0]); /* maximum - At most 32M, but smaller as appropriate. */ - sizes[2] = MIN(blk_get_max_transfer(exp->blk), NBD_MAX_BUFFER_SIZE); + sizes[2] = MIN(blk_get_max_transfer(exp->common.blk), NBD_MAX_BUFFER_SIZE); trace_nbd_negotiate_handle_info_block_size(sizes[0], sizes[1], sizes[2]); sizes[0] = cpu_to_be32(sizes[0]); sizes[1] = cpu_to_be32(sizes[1]); @@ -688,7 +683,7 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp) * tolerate all clients, regardless of alignments. */ if (client->opt == NBD_OPT_INFO && !blocksize && - blk_get_request_alignment(exp->blk) > 1) { + blk_get_request_alignment(exp->common.blk) > 1) { return nbd_negotiate_send_rep_err(client, NBD_REP_ERR_BLOCK_SIZE_REQD, errp, @@ -706,7 +701,7 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp) client->exp = exp; client->check_align = check_align; QTAILQ_INSERT_TAIL(&client->exp->clients, client, next); - nbd_export_get(client->exp); + blk_exp_ref(&client->exp->common); nbd_check_meta_export(client); rc = 1; } @@ -1333,8 +1328,8 @@ static coroutine_fn int nbd_negotiate(NBDClient *client, Error **errp) } /* Attach the channel to the same AioContext as the export */ - if (client->exp && client->exp->ctx) { - qio_channel_attach_aio_context(client->ioc, client->exp->ctx); + if (client->exp && client->exp->common.ctx) { + qio_channel_attach_aio_context(client->ioc, client->exp->common.ctx); } assert(!client->optlen); @@ -1405,7 +1400,7 @@ void nbd_client_put(NBDClient *client) g_free(client->tlsauthz); if (client->exp) { QTAILQ_REMOVE(&client->exp->clients, client, next); - nbd_export_put(client->exp); + blk_exp_unref(&client->exp->common); } g_free(client); } @@ -1466,7 +1461,7 @@ static void blk_aio_attached(AioContext *ctx, void *opaque) trace_nbd_blk_aio_attached(exp->name, ctx); - exp->ctx = ctx; + exp->common.ctx = ctx; QTAILQ_FOREACH(client, &exp->clients, next) { qio_channel_attach_aio_context(client->ioc, ctx); @@ -1484,72 +1479,92 @@ static void blk_aio_detach(void *opaque) NBDExport *exp = opaque; NBDClient *client; - trace_nbd_blk_aio_detach(exp->name, exp->ctx); + trace_nbd_blk_aio_detach(exp->name, exp->common.ctx); QTAILQ_FOREACH(client, &exp->clients, next) { qio_channel_detach_aio_context(client->ioc); } - exp->ctx = NULL; + exp->common.ctx = NULL; } static void nbd_eject_notifier(Notifier *n, void *data) { NBDExport *exp = container_of(n, NBDExport, eject_notifier); - AioContext *aio_context; - aio_context = exp->ctx; - aio_context_acquire(aio_context); - nbd_export_close(exp); - aio_context_release(aio_context); + blk_exp_request_shutdown(&exp->common); +} + +void nbd_export_set_on_eject_blk(BlockExport *exp, BlockBackend *blk) +{ + NBDExport *nbd_exp = container_of(exp, NBDExport, common); + assert(exp->drv == &blk_exp_nbd); + assert(nbd_exp->eject_notifier_blk == NULL); + + blk_ref(blk); + nbd_exp->eject_notifier_blk = blk; + nbd_exp->eject_notifier.notify = nbd_eject_notifier; + blk_add_remove_bs_notifier(blk, &nbd_exp->eject_notifier); } -NBDExport *nbd_export_new(BlockDriverState *bs, uint64_t dev_offset, - uint64_t size, const char *name, const char *desc, - const char *bitmap, bool readonly, bool shared, - void (*close)(NBDExport *), bool writethrough, - BlockBackend *on_eject_blk, Error **errp) +static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, + Error **errp) { - AioContext *ctx; - BlockBackend *blk; - NBDExport *exp = g_new0(NBDExport, 1); - uint64_t perm; + NBDExport *exp = container_of(blk_exp, NBDExport, common); + BlockExportOptionsNbd *arg = &exp_args->u.nbd; + BlockBackend *blk = blk_exp->blk; + int64_t size; + uint64_t perm, shared_perm; + bool readonly = !exp_args->writable; + bool shared = !exp_args->writable; int ret; - /* - * NBD exports are used for non-shared storage migration. Make sure - * that BDRV_O_INACTIVE is cleared and the image is ready for write - * access since the export could be available before migration handover. - * ctx was acquired in the caller. - */ - assert(name && strlen(name) <= NBD_MAX_STRING_SIZE); - ctx = bdrv_get_aio_context(bs); - bdrv_invalidate_cache(bs, NULL); + assert(exp_args->type == BLOCK_EXPORT_TYPE_NBD); + + if (!nbd_server_is_running()) { + error_setg(errp, "NBD server not running"); + return -EINVAL; + } + + if (!arg->has_name) { + arg->name = exp_args->node_name; + } + + if (strlen(arg->name) > NBD_MAX_STRING_SIZE) { + error_setg(errp, "export name '%s' too long", arg->name); + return -EINVAL; + } + + if (arg->description && strlen(arg->description) > NBD_MAX_STRING_SIZE) { + error_setg(errp, "description '%s' too long", arg->description); + return -EINVAL; + } + + if (nbd_export_find(arg->name)) { + error_setg(errp, "NBD server already has export named '%s'", arg->name); + return -EEXIST; + } + + size = blk_getlength(blk); + if (size < 0) { + error_setg_errno(errp, -size, + "Failed to determine the NBD export's length"); + return size; + } /* Don't allow resize while the NBD server is running, otherwise we don't * care what happens with the node. */ - perm = BLK_PERM_CONSISTENT_READ; - if (!readonly) { - perm |= BLK_PERM_WRITE; - } - blk = blk_new(ctx, perm, - BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | - BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD); - ret = blk_insert_bs(blk, bs, errp); + blk_get_perm(blk, &perm, &shared_perm); + ret = blk_set_perm(blk, perm, shared_perm & ~BLK_PERM_RESIZE, errp); if (ret < 0) { - goto fail; + return ret; } - blk_set_enable_write_cache(blk, !writethrough); + blk_set_allow_aio_context_change(blk, true); - exp->refcount = 1; QTAILQ_INIT(&exp->clients); - exp->blk = blk; - assert(dev_offset <= INT64_MAX); - exp->dev_offset = dev_offset; - exp->name = g_strdup(name); - assert(!desc || strlen(desc) <= NBD_MAX_STRING_SIZE); - exp->description = g_strdup(desc); + exp->name = g_strdup(arg->name); + exp->description = g_strdup(arg->description); exp->nbdflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA | NBD_FLAG_SEND_CACHE); if (readonly) { @@ -1561,14 +1576,14 @@ NBDExport *nbd_export_new(BlockDriverState *bs, uint64_t dev_offset, exp->nbdflags |= (NBD_FLAG_SEND_TRIM | NBD_FLAG_SEND_WRITE_ZEROES | NBD_FLAG_SEND_FAST_ZERO); } - assert(size <= INT64_MAX - dev_offset); exp->size = QEMU_ALIGN_DOWN(size, BDRV_SECTOR_SIZE); - if (bitmap) { + if (arg->bitmap) { + BlockDriverState *bs = blk_bs(blk); BdrvDirtyBitmap *bm = NULL; while (bs) { - bm = bdrv_find_dirty_bitmap(bs, bitmap); + bm = bdrv_find_dirty_bitmap(bs, arg->bitmap); if (bm != NULL) { break; } @@ -1577,50 +1592,43 @@ NBDExport *nbd_export_new(BlockDriverState *bs, uint64_t dev_offset, } if (bm == NULL) { - error_setg(errp, "Bitmap '%s' is not found", bitmap); + ret = -ENOENT; + error_setg(errp, "Bitmap '%s' is not found", arg->bitmap); goto fail; } if (bdrv_dirty_bitmap_check(bm, BDRV_BITMAP_ALLOW_RO, errp)) { + ret = -EINVAL; goto fail; } if (readonly && bdrv_is_writable(bs) && bdrv_dirty_bitmap_enabled(bm)) { + ret = -EINVAL; error_setg(errp, "Enabled bitmap '%s' incompatible with readonly export", - bitmap); + arg->bitmap); goto fail; } bdrv_dirty_bitmap_set_busy(bm, true); exp->export_bitmap = bm; - assert(strlen(bitmap) <= BDRV_BITMAP_MAX_NAME_SIZE); + assert(strlen(arg->bitmap) <= BDRV_BITMAP_MAX_NAME_SIZE); exp->export_bitmap_context = g_strdup_printf("qemu:dirty-bitmap:%s", - bitmap); + arg->bitmap); assert(strlen(exp->export_bitmap_context) < NBD_MAX_STRING_SIZE); } - exp->close = close; - exp->ctx = ctx; blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp); - if (on_eject_blk) { - blk_ref(on_eject_blk); - exp->eject_notifier_blk = on_eject_blk; - exp->eject_notifier.notify = nbd_eject_notifier; - blk_add_remove_bs_notifier(on_eject_blk, &exp->eject_notifier); - } QTAILQ_INSERT_TAIL(&exports, exp, next); - nbd_export_get(exp); - return exp; + + return 0; fail: - blk_unref(blk); g_free(exp->name); g_free(exp->description); - g_free(exp); - return NULL; + return ret; } NBDExport *nbd_export_find(const char *name) @@ -1638,14 +1646,15 @@ NBDExport *nbd_export_find(const char *name) AioContext * nbd_export_aio_context(NBDExport *exp) { - return exp->ctx; + return exp->common.ctx; } -void nbd_export_close(NBDExport *exp) +static void nbd_export_request_shutdown(BlockExport *blk_exp) { + NBDExport *exp = container_of(blk_exp, NBDExport, common); NBDClient *client, *next; - nbd_export_get(exp); + blk_exp_ref(&exp->common); /* * TODO: Should we expand QMP NbdServerRemoveNode enum to allow a * close mode that stops advertising the export to new clients but @@ -1657,101 +1666,46 @@ void nbd_export_close(NBDExport *exp) client_close(client, true); } if (exp->name) { - nbd_export_put(exp); g_free(exp->name); exp->name = NULL; QTAILQ_REMOVE(&exports, exp, next); - QTAILQ_INSERT_TAIL(&closed_exports, exp, next); } - g_free(exp->description); - exp->description = NULL; - nbd_export_put(exp); -} - -void nbd_export_remove(NBDExport *exp, NbdServerRemoveMode mode, Error **errp) -{ - ERRP_GUARD(); - if (mode == NBD_SERVER_REMOVE_MODE_HARD || QTAILQ_EMPTY(&exp->clients)) { - nbd_export_close(exp); - return; - } - - assert(mode == NBD_SERVER_REMOVE_MODE_SAFE); - - error_setg(errp, "export '%s' still in use", exp->name); - error_append_hint(errp, "Use mode='hard' to force client disconnect\n"); -} - -void nbd_export_get(NBDExport *exp) -{ - assert(exp->refcount > 0); - exp->refcount++; + blk_exp_unref(&exp->common); } -void nbd_export_put(NBDExport *exp) +static void nbd_export_delete(BlockExport *blk_exp) { - assert(exp->refcount > 0); - if (exp->refcount == 1) { - nbd_export_close(exp); - } + NBDExport *exp = container_of(blk_exp, NBDExport, common); - /* nbd_export_close() may theoretically reduce refcount to 0. It may happen - * if someone calls nbd_export_put() on named export not through - * nbd_export_set_name() when refcount is 1. So, let's assert that - * it is > 0. - */ - assert(exp->refcount > 0); - if (--exp->refcount == 0) { - assert(exp->name == NULL); - assert(exp->description == NULL); + assert(exp->name == NULL); + assert(QTAILQ_EMPTY(&exp->clients)); - if (exp->close) { - exp->close(exp); - } - - if (exp->blk) { - if (exp->eject_notifier_blk) { - notifier_remove(&exp->eject_notifier); - blk_unref(exp->eject_notifier_blk); - } - blk_remove_aio_context_notifier(exp->blk, blk_aio_attached, - blk_aio_detach, exp); - blk_unref(exp->blk); - exp->blk = NULL; - } + g_free(exp->description); + exp->description = NULL; - if (exp->export_bitmap) { - bdrv_dirty_bitmap_set_busy(exp->export_bitmap, false); - g_free(exp->export_bitmap_context); + if (exp->common.blk) { + if (exp->eject_notifier_blk) { + notifier_remove(&exp->eject_notifier); + blk_unref(exp->eject_notifier_blk); } - - QTAILQ_REMOVE(&closed_exports, exp, next); - g_free(exp); - aio_wait_kick(); + blk_remove_aio_context_notifier(exp->common.blk, blk_aio_attached, + blk_aio_detach, exp); } -} -BlockBackend *nbd_export_get_blockdev(NBDExport *exp) -{ - return exp->blk; -} - -void nbd_export_close_all(void) -{ - NBDExport *exp, *next; - AioContext *aio_context; - - QTAILQ_FOREACH_SAFE(exp, &exports, next, next) { - aio_context = exp->ctx; - aio_context_acquire(aio_context); - nbd_export_close(exp); - aio_context_release(aio_context); + if (exp->export_bitmap) { + bdrv_dirty_bitmap_set_busy(exp->export_bitmap, false); + g_free(exp->export_bitmap_context); } - - AIO_WAIT_WHILE(NULL, !(QTAILQ_EMPTY(&exports) && - QTAILQ_EMPTY(&closed_exports))); } +const BlockExportDriver blk_exp_nbd = { + .type = BLOCK_EXPORT_TYPE_NBD, + .instance_size = sizeof(NBDExport), + .create = nbd_export_create, + .delete = nbd_export_delete, + .request_shutdown = nbd_export_request_shutdown, +}; + static int coroutine_fn nbd_co_send_iov(NBDClient *client, struct iovec *iov, unsigned niov, Error **errp) { @@ -1888,7 +1842,7 @@ static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client, while (progress < size) { int64_t pnum; - int status = bdrv_block_status_above(blk_bs(exp->blk), NULL, + int status = bdrv_block_status_above(blk_bs(exp->common.blk), NULL, offset + progress, size - progress, &pnum, NULL, NULL); @@ -1920,7 +1874,7 @@ static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client, stl_be_p(&chunk.length, pnum); ret = nbd_co_send_iov(client, iov, 1, errp); } else { - ret = blk_pread(exp->blk, offset + progress + exp->dev_offset, + ret = blk_pread(exp->common.blk, offset + progress, data + progress, pnum); if (ret < 0) { error_setg_errno(errp, -ret, "reading from file failed"); @@ -2185,7 +2139,8 @@ static int nbd_co_receive_request(NBDRequestData *req, NBDRequest *request, } if (request->type != NBD_CMD_CACHE) { - req->data = blk_try_blockalign(client->exp->blk, request->len); + req->data = blk_try_blockalign(client->exp->common.blk, + request->len); if (req->data == NULL) { error_setg(errp, "No memory"); return -ENOMEM; @@ -2281,7 +2236,7 @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request, /* XXX: NBD Protocol only documents use of FUA with WRITE */ if (request->flags & NBD_CMD_FLAG_FUA) { - ret = blk_co_flush(exp->blk); + ret = blk_co_flush(exp->common.blk); if (ret < 0) { return nbd_send_generic_reply(client, request->handle, ret, "flush failed", errp); @@ -2295,8 +2250,7 @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request, data, request->len, errp); } - ret = blk_pread(exp->blk, request->from + exp->dev_offset, data, - request->len); + ret = blk_pread(exp->common.blk, request->from, data, request->len); if (ret < 0) { return nbd_send_generic_reply(client, request->handle, ret, "reading from file failed", errp); @@ -2331,7 +2285,7 @@ static coroutine_fn int nbd_do_cmd_cache(NBDClient *client, NBDRequest *request, assert(request->type == NBD_CMD_CACHE); - ret = blk_co_preadv(exp->blk, request->from + exp->dev_offset, request->len, + ret = blk_co_preadv(exp->common.blk, request->from, request->len, NULL, BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH); return nbd_send_generic_reply(client, request->handle, ret, @@ -2362,8 +2316,8 @@ static coroutine_fn int nbd_handle_request(NBDClient *client, if (request->flags & NBD_CMD_FLAG_FUA) { flags |= BDRV_REQ_FUA; } - ret = blk_pwrite(exp->blk, request->from + exp->dev_offset, - data, request->len, flags); + ret = blk_pwrite(exp->common.blk, request->from, data, request->len, + flags); return nbd_send_generic_reply(client, request->handle, ret, "writing to file failed", errp); @@ -2384,8 +2338,7 @@ static coroutine_fn int nbd_handle_request(NBDClient *client, int align = client->check_align ?: 1; int len = MIN(request->len, QEMU_ALIGN_DOWN(BDRV_REQUEST_MAX_BYTES, align)); - ret = blk_pwrite_zeroes(exp->blk, request->from + exp->dev_offset, - len, flags); + ret = blk_pwrite_zeroes(exp->common.blk, request->from, len, flags); request->len -= len; request->from += len; } @@ -2397,7 +2350,7 @@ static coroutine_fn int nbd_handle_request(NBDClient *client, abort(); case NBD_CMD_FLUSH: - ret = blk_co_flush(exp->blk); + ret = blk_co_flush(exp->common.blk); return nbd_send_generic_reply(client, request->handle, ret, "flush failed", errp); @@ -2408,13 +2361,12 @@ static coroutine_fn int nbd_handle_request(NBDClient *client, int align = client->check_align ?: 1; int len = MIN(request->len, QEMU_ALIGN_DOWN(BDRV_REQUEST_MAX_BYTES, align)); - ret = blk_co_pdiscard(exp->blk, request->from + exp->dev_offset, - len); + ret = blk_co_pdiscard(exp->common.blk, request->from, len); request->len -= len; request->from += len; } if (ret >= 0 && request->flags & NBD_CMD_FLAG_FUA) { - ret = blk_co_flush(exp->blk); + ret = blk_co_flush(exp->common.blk); } return nbd_send_generic_reply(client, request->handle, ret, "discard failed", errp); @@ -2432,7 +2384,8 @@ static coroutine_fn int nbd_handle_request(NBDClient *client, if (client->export_meta.base_allocation) { ret = nbd_co_send_block_status(client, request->handle, - blk_bs(exp->blk), request->from, + blk_bs(exp->common.blk), + request->from, request->len, dont_fragment, !client->export_meta.bitmap, NBD_META_ID_BASE_ALLOCATION, @@ -2546,7 +2499,7 @@ static void nbd_client_receive_next_request(NBDClient *client) if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS) { nbd_client_get(client); client->recv_coroutine = qemu_coroutine_create(nbd_trip, client); - aio_co_schedule(client->exp->ctx, client->recv_coroutine); + aio_co_schedule(client->exp->common.ctx, client->recv_coroutine); } } |