From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:50376) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yi4Hh-0007et-0G for qemu-devel@nongnu.org; Tue, 14 Apr 2015 13:06:05 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Yi4Hf-00032w-OA for qemu-devel@nongnu.org; Tue, 14 Apr 2015 13:06:00 -0400 Received: from mx1.redhat.com ([209.132.183.28]:55043) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Yi4Hf-00032r-BG for qemu-devel@nongnu.org; Tue, 14 Apr 2015 13:05:59 -0400 From: "Dr. David Alan Gilbert (git)" Date: Tue, 14 Apr 2015 18:04:09 +0100 Message-Id: <1429031053-4454-44-git-send-email-dgilbert@redhat.com> In-Reply-To: <1429031053-4454-1-git-send-email-dgilbert@redhat.com> References: <1429031053-4454-1-git-send-email-dgilbert@redhat.com> Subject: [Qemu-devel] [PATCH v6 43/47] Start up a postcopy/listener thread ready for incoming page data List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: aarcange@redhat.com, yamahata@private.email.ne.jp, quintela@redhat.com, amit.shah@redhat.com, pbonzini@redhat.com, david@gibson.dropbear.id.au, yayanghy@cn.fujitsu.com From: "Dr. David Alan Gilbert" The loading of a device state (during postcopy) may access guest memory that's still on the source machine and thus might need a page fill; split off a separate thread that handles the incoming page data so that the original incoming migration code can finish off the device data. Signed-off-by: Dr. David Alan Gilbert --- include/migration/migration.h | 4 +++ migration/migration.c | 6 ++++ savevm.c | 79 ++++++++++++++++++++++++++++++++++++++++++- trace-events | 2 ++ 4 files changed, 90 insertions(+), 1 deletion(-) diff --git a/include/migration/migration.h b/include/migration/migration.h index 4d6f33a..cce4c50 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -79,6 +79,10 @@ struct MigrationIncomingState { QemuThread fault_thread; QemuSemaphore fault_thread_sem; + bool have_listen_thread; + QemuThread listen_thread; + QemuSemaphore listen_thread_sem; + /* For the kernel to send us notifications */ int userfault_fd; /* To tell the fault_thread to quit */ diff --git a/migration/migration.c b/migration/migration.c index 2509798..6537d23 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1082,6 +1082,12 @@ static int postcopy_start(MigrationState *ms, bool *old_vm_running) goto fail; } + /* + * Make sure the receiver can get incoming pages before we send the rest + * of the state + */ + qemu_savevm_send_postcopy_listen(fb); + qemu_savevm_state_complete_precopy(fb); qemu_savevm_send_ping(fb, 3); diff --git a/savevm.c b/savevm.c index f606ce8..ce8c3b5 100644 --- a/savevm.c +++ b/savevm.c @@ -1261,6 +1261,65 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, return 0; } +/* + * Triggered by a postcopy_listen command; this thread takes over reading + * the input stream, leaving the main thread free to carry on loading the rest + * of the device state (from RAM). + * (TODO:This could do with being in a postcopy file - but there again it's + * just another input loop, not that postcopy specific) + */ +static void *postcopy_ram_listen_thread(void *opaque) +{ + QEMUFile *f = opaque; + MigrationIncomingState *mis = migration_incoming_get_current(); + int load_res; + + qemu_sem_post(&mis->listen_thread_sem); + trace_postcopy_ram_listen_thread_start(); + + /* + * Because we're a thread and not a coroutine we can't yield + * in qemu_file, and thus we must be blocking now. + */ + qemu_file_change_blocking(f, true); + load_res = qemu_loadvm_state_main(f, mis); + /* And non-blocking again so we don't block in any cleanup */ + qemu_file_change_blocking(f, false); + + trace_postcopy_ram_listen_thread_exit(); + if (load_res < 0) { + error_report("%s: loadvm failed: %d", __func__, load_res); + qemu_file_set_error(f, load_res); + } else { + /* + * This looks good, but it's possible that the device loading in the + * main thread hasn't finished yet, and so we might not be in 'RUN' + * state yet; wait for the end of the main thread. + */ + qemu_event_wait(&mis->main_thread_load_event); + } + postcopy_ram_incoming_cleanup(mis); + /* + * If everything has worked fine, then the main thread has waited + * for us to start, and we're the last use of the mis. + * (If something broke then qemu will have to exit anyway since it's + * got a bad migration state). + */ + migration_incoming_state_destroy(); + + if (load_res < 0) { + /* + * If something went wrong then we have a bad state so exit; + * depending how far we got it might be possible at this point + * to leave the guest running and fire MCEs for pages that never + * arrived as a desperate recovery step. + */ + exit(EXIT_FAILURE); + } + + return NULL; +} + /* After this message we must be able to immediately receive postcopy data */ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) { @@ -1280,7 +1339,20 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) return -1; } - /* TODO start up the postcopy listening thread */ + if (mis->have_listen_thread) { + error_report("CMD_POSTCOPY_RAM_LISTEN already has a listen thread"); + return -1; + } + + mis->have_listen_thread = true; + /* Start up the listening thread and wait for it to signal ready */ + qemu_sem_init(&mis->listen_thread_sem, 0); + qemu_thread_create(&mis->listen_thread, "postcopy/listen", + postcopy_ram_listen_thread, mis->file, + QEMU_THREAD_JOINABLE); + qemu_sem_wait(&mis->listen_thread_sem); + qemu_sem_destroy(&mis->listen_thread_sem); + return 0; } @@ -1597,6 +1669,11 @@ int qemu_loadvm_state(QEMUFile *f) qemu_event_set(&mis->main_thread_load_event); trace_qemu_loadvm_state_post_main(ret); + if (mis->have_listen_thread) { + /* Listen thread still going, can't clean up yet */ + return ret; + } + if (ret == 0) { int file_error_after_eof = qemu_file_get_error(f); diff --git a/trace-events b/trace-events index 72a65fa..2f50cc4 100644 --- a/trace-events +++ b/trace-events @@ -1187,6 +1187,8 @@ loadvm_postcopy_ram_handle_discard_end(void) "" loadvm_postcopy_ram_handle_discard_header(const char *ramid, uint16_t len) "%s: %ud" loadvm_process_command(uint16_t com, uint16_t len) "com=0x%x len=%d" loadvm_process_command_ping(uint32_t val) "%x" +postcopy_ram_listen_thread_exit(void) "" +postcopy_ram_listen_thread_start(void) "" qemu_savevm_send_postcopy_advise(void) "" qemu_savevm_send_postcopy_ram_discard(const char *id, uint16_t len) "%s: %ud" savevm_section_start(const char *id, unsigned int section_id) "%s, section_id %u" -- 2.1.0