From nobody Thu Nov 6 08:15:02 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1540206664818254.82257870819797; Mon, 22 Oct 2018 04:11:04 -0700 (PDT) Received: from localhost ([::1]:34218 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gEY6x-0001jE-Kz for importer@patchew.org; Mon, 22 Oct 2018 07:11:03 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43699) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gEY5c-00013K-Hf for qemu-devel@nongnu.org; Mon, 22 Oct 2018 07:09:41 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gEY5Y-00016C-Fx for qemu-devel@nongnu.org; Mon, 22 Oct 2018 07:09:40 -0400 Received: from smtp.nue.novell.com ([195.135.221.5]:59286) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gEY5W-0000wp-Mf for qemu-devel@nongnu.org; Mon, 22 Oct 2018 07:09:36 -0400 Received: from localhost.localdomain ([45.122.156.254]) by smtp.nue.novell.com with ESMTP (NOT encrypted); Mon, 22 Oct 2018 13:09:20 +0200 From: Fei Li To: qemu-devel@nongnu.org Date: Mon, 22 Oct 2018 19:08:53 +0800 Message-Id: <20181022110854.10284-2-fli@suse.com> X-Mailer: git-send-email 2.13.7 In-Reply-To: <20181022110854.10284-1-fli@suse.com> References: <20181022110854.10284-1-fli@suse.com> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 195.135.221.5 Subject: [Qemu-devel] [PATCH RFC 1/2] migration: fix the multifd code X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: dgilbert@redhat.com, peterx@redhat.com, quintela@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" When multifd is used during migration, if there is an error before the destination receives all new channels, the destination does not exit but keeps waiting in our current code. However, a segmentaion fault will occur in the source when multifd_save_cleanup() is called again as the multifd_send_state has been freed earlier in the first error handling. This can happen when migrate_fd_connect() fails and multifd_fd_cleanup() is called, and then multifd_new_send_channel_ async() fails and multifd_save_cleanup() is called again. If the QIOChannel *c of multifd_recv_state->params[i] (p->c) is not initialized, there is no need to close the channel. Or else a segmentation fault will occur in multifd_recv_terminate_threads() when multifd_recv_initial_packet() fails. Signed-off-by: Fei Li --- migration/ram.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/migration/ram.c b/migration/ram.c index 7e7deec4d8..2dd873ba35 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -907,6 +907,11 @@ static void multifd_send_terminate_threads(Error *err) } } =20 + /* in case multifd_send_state has been freed earlier */ + if (!multifd_send_state) { + return; + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { MultiFDSendParams *p =3D &multifd_send_state->params[i]; =20 @@ -922,7 +927,7 @@ int multifd_save_cleanup(Error **errp) int i; int ret =3D 0; =20 - if (!migrate_use_multifd()) { + if (!migrate_use_multifd() || !multifd_send_state) { return 0; } multifd_send_terminate_threads(NULL); @@ -1070,6 +1075,10 @@ static void multifd_new_send_channel_async(QIOTask *= task, gpointer opaque) QIOChannel *sioc =3D QIO_CHANNEL(qio_task_get_source(task)); Error *local_err =3D NULL; =20 + if (!multifd_send_state) { + return; + } + if (qio_task_propagate_error(task, &local_err)) { if (multifd_save_cleanup(&local_err) !=3D 0) { migrate_set_error(migrate_get_current(), local_err); @@ -1131,7 +1140,7 @@ struct { uint64_t packet_num; } *multifd_recv_state; =20 -static void multifd_recv_terminate_threads(Error *err) +static void multifd_recv_terminate_threads(Error *err, bool channel) { int i; =20 @@ -1145,6 +1154,11 @@ static void multifd_recv_terminate_threads(Error *er= r) } } =20 + /* in case p->c is not initialized */ + if (!channel) { + return; + } + for (i =3D 0; i < migrate_multifd_channels(); i++) { MultiFDRecvParams *p =3D &multifd_recv_state->params[i]; =20 @@ -1166,7 +1180,7 @@ int multifd_load_cleanup(Error **errp) if (!migrate_use_multifd()) { return 0; } - multifd_recv_terminate_threads(NULL); + multifd_recv_terminate_threads(NULL, true); for (i =3D 0; i < migrate_multifd_channels(); i++) { MultiFDRecvParams *p =3D &multifd_recv_state->params[i]; =20 @@ -1269,7 +1283,7 @@ static void *multifd_recv_thread(void *opaque) } =20 if (local_err) { - multifd_recv_terminate_threads(local_err); + multifd_recv_terminate_threads(local_err, true); } qemu_mutex_lock(&p->mutex); p->running =3D false; @@ -1331,7 +1345,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc) =20 id =3D multifd_recv_initial_packet(ioc, &local_err); if (id < 0) { - multifd_recv_terminate_threads(local_err); + multifd_recv_terminate_threads(local_err, false); return false; } =20 @@ -1339,7 +1353,7 @@ bool multifd_recv_new_channel(QIOChannel *ioc) if (p->c !=3D NULL) { error_setg(&local_err, "multifd: received id '%d' already setup'", id); - multifd_recv_terminate_threads(local_err); + multifd_recv_terminate_threads(local_err, true); return false; } p->c =3D ioc; --=20 2.13.7 From nobody Thu Nov 6 08:15:02 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1540206748338887.5540350709496; Mon, 22 Oct 2018 04:12:28 -0700 (PDT) Received: from localhost ([::1]:34223 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gEY8J-0002dM-Ck for importer@patchew.org; Mon, 22 Oct 2018 07:12:27 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43700) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gEY5c-00013L-He for qemu-devel@nongnu.org; Mon, 22 Oct 2018 07:09:41 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gEY5Y-000166-FC for qemu-devel@nongnu.org; Mon, 22 Oct 2018 07:09:40 -0400 Received: from smtp.nue.novell.com ([195.135.221.5]:37152) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gEY5W-0000yi-Mf for qemu-devel@nongnu.org; Mon, 22 Oct 2018 07:09:36 -0400 Received: from localhost.localdomain ([45.122.156.254]) by smtp.nue.novell.com with ESMTP (NOT encrypted); Mon, 22 Oct 2018 13:09:22 +0200 From: Fei Li To: qemu-devel@nongnu.org Date: Mon, 22 Oct 2018 19:08:54 +0800 Message-Id: <20181022110854.10284-3-fli@suse.com> X-Mailer: git-send-email 2.13.7 In-Reply-To: <20181022110854.10284-1-fli@suse.com> References: <20181022110854.10284-1-fli@suse.com> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 195.135.221.5 Subject: [Qemu-devel] [PATCH RFC 2/2] migration: fix some error handling X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: dgilbert@redhat.com, peterx@redhat.com, quintela@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Add error handling for qemu_ram_foreach_migratable_block() when it fails. Always call migrate_set_error() to set the error state without relying on whether multifd_save_cleanup() succeeds. As the passed &local_err is never used in multifd_save_cleanup(), remove it. Signed-off-by: Fei Li --- migration/migration.c | 5 +---- migration/postcopy-ram.c | 3 +++ migration/ram.c | 7 +++---- migration/ram.h | 2 +- 4 files changed, 8 insertions(+), 9 deletions(-) diff --git a/migration/migration.c b/migration/migration.c index 7696729340..ca07c243be 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1372,7 +1372,6 @@ static void migrate_fd_cleanup(void *opaque) qemu_savevm_state_cleanup(); =20 if (s->to_dst_file) { - Error *local_err =3D NULL; QEMUFile *tmp; =20 trace_migrate_fd_cleanup(); @@ -1383,9 +1382,7 @@ static void migrate_fd_cleanup(void *opaque) } qemu_mutex_lock_iothread(); =20 - if (multifd_save_cleanup(&local_err) !=3D 0) { - error_report_err(local_err); - } + multifd_save_cleanup(); qemu_mutex_lock(&s->qemu_file_lock); tmp =3D s->to_dst_file; s->to_dst_file =3D NULL; diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index e5c02a32c5..4ca2bc02b3 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -1117,6 +1117,9 @@ int postcopy_ram_enable_notify(MigrationIncomingState= *mis) =20 /* Mark so that we get notified of accesses to unwritten areas */ if (qemu_ram_foreach_migratable_block(ram_block_enable_notify, mis)) { + error_report("ram_block_enable_notify failed"); + close(mis->userfault_event_fd); + close(mis->userfault_fd); return -1; } =20 diff --git a/migration/ram.c b/migration/ram.c index 2dd873ba35..e7c8ccb38a 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -922,7 +922,7 @@ static void multifd_send_terminate_threads(Error *err) } } =20 -int multifd_save_cleanup(Error **errp) +int multifd_save_cleanup(void) { int i; int ret =3D 0; @@ -1080,9 +1080,8 @@ static void multifd_new_send_channel_async(QIOTask *t= ask, gpointer opaque) } =20 if (qio_task_propagate_error(task, &local_err)) { - if (multifd_save_cleanup(&local_err) !=3D 0) { - migrate_set_error(migrate_get_current(), local_err); - } + multifd_save_cleanup(); + migrate_set_error(migrate_get_current(), local_err); } else { p->c =3D QIO_CHANNEL(sioc); qio_channel_set_delay(p->c, false); diff --git a/migration/ram.h b/migration/ram.h index 83ff1bc11a..c4fafea368 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -43,7 +43,7 @@ uint64_t ram_bytes_remaining(void); uint64_t ram_bytes_total(void); =20 int multifd_save_setup(void); -int multifd_save_cleanup(Error **errp); +int multifd_save_cleanup(void); int multifd_load_setup(void); int multifd_load_cleanup(Error **errp); bool multifd_recv_all_channels_created(void); --=20 2.13.7