diff --git a/nbd/server.c b/nbd/server.c index 86a44a9b41..b60ebc3ab6 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -1513,6 +1513,11 @@ static void nbd_request_put(NBDRequestData *req) g_free(req); client->nb_requests--; + + if (client->quiescing && client->nb_requests == 0) { + aio_wait_kick(); + } + nbd_client_receive_next_request(client); nbd_client_put(client); @@ -1530,51 +1535,70 @@ static void blk_aio_attached(AioContext *ctx, void *opaque) QTAILQ_FOREACH(client, &exp->clients, next) { qio_channel_attach_aio_context(client->ioc, ctx); + assert(client->nb_requests == 0); assert(client->recv_coroutine == NULL); assert(client->send_coroutine == NULL); - - if (client->quiescing) { - client->quiescing = false; - nbd_client_receive_next_request(client); - } - } -} - -static void nbd_aio_detach_bh(void *opaque) -{ - NBDExport *exp = opaque; - NBDClient *client; - - QTAILQ_FOREACH(client, &exp->clients, next) { - qio_channel_detach_aio_context(client->ioc); - client->quiescing = true; - - if (client->recv_coroutine) { - if (client->read_yielding) { - qemu_aio_coroutine_enter(exp->common.ctx, - client->recv_coroutine); - } else { - AIO_WAIT_WHILE(exp->common.ctx, client->recv_coroutine != NULL); - } - } - - if (client->send_coroutine) { - AIO_WAIT_WHILE(exp->common.ctx, client->send_coroutine != NULL); - } } } static void blk_aio_detach(void *opaque) { NBDExport *exp = opaque; + NBDClient *client; trace_nbd_blk_aio_detach(exp->name, exp->common.ctx); - aio_wait_bh_oneshot(exp->common.ctx, nbd_aio_detach_bh, exp); + QTAILQ_FOREACH(client, &exp->clients, next) { + qio_channel_detach_aio_context(client->ioc); + } exp->common.ctx = NULL; } +static void nbd_drained_begin(void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; + + QTAILQ_FOREACH(client, &exp->clients, next) { + client->quiescing = true; + } +} + +static void nbd_drained_end(void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; + + QTAILQ_FOREACH(client, &exp->clients, next) { + client->quiescing = false; + nbd_client_receive_next_request(client); + } +} + +static bool nbd_drained_poll(void *opaque) +{ + NBDExport *exp = opaque; + NBDClient *client; + + QTAILQ_FOREACH(client, &exp->clients, next) { + if (client->nb_requests != 0) { + /* + * If there's a coroutine waiting for a request on nbd_read_eof() + * enter it here so we don't depend on the client to wake it up. + */ + if (client->recv_coroutine != NULL && client->read_yielding) { + qemu_aio_coroutine_enter(exp->common.ctx, + client->recv_coroutine); + } + + return true; + } + } + + return false; +} + static void nbd_eject_notifier(Notifier *n, void *data) { NBDExport *exp = container_of(n, NBDExport, eject_notifier); @@ -1594,6 +1618,12 @@ void nbd_export_set_on_eject_blk(BlockExport *exp, BlockBackend *blk) blk_add_remove_bs_notifier(blk, &nbd_exp->eject_notifier); } +static const BlockDevOps nbd_block_ops = { + .drained_begin = nbd_drained_begin, + .drained_end = nbd_drained_end, + .drained_poll = nbd_drained_poll, +}; + static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, Error **errp) { @@ -1715,8 +1745,17 @@ static int nbd_export_create(BlockExport *blk_exp, BlockExportOptions *exp_args, exp->allocation_depth = arg->allocation_depth; + /* + * We need to inhibit request queuing in the block layer to ensure we can + * be properly quiesced when entering a drained section, as our coroutines + * servicing pending requests might enter blk_pread(). + */ + blk_set_disable_request_queuing(blk, true); + blk_add_aio_context_notifier(blk, blk_aio_attached, blk_aio_detach, exp); + blk_set_dev_ops(blk, &nbd_block_ops, exp); + QTAILQ_INSERT_TAIL(&exports, exp, next); return 0; @@ -1788,6 +1827,7 @@ static void nbd_export_delete(BlockExport *blk_exp) } blk_remove_aio_context_notifier(exp->common.blk, blk_aio_attached, blk_aio_detach, exp); + blk_set_disable_request_queuing(exp->common.blk, false); } for (i = 0; i < exp->nr_export_bitmaps; i++) {