Re: [PATCH V1 06/26] migration: precreate vmstate for exec

[Fabiano Rosas <farosas@suse.de>]

Steven Sistare <steven.sistare@oracle.com> writes:

> On 5/6/2024 7:34 PM, Fabiano Rosas wrote:
>> Steve Sistare <steven.sistare@oracle.com> writes:
>> 
>>> Provide migration_precreate_save for saving precreate vmstate across exec.
>>> Create a memfd, save its value in the environment, and serialize state
>>> to it.  Reverse the process in migration_precreate_load.
>>>
>>> Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
>>> ---
>>>   include/migration/misc.h |   5 ++
>>>   migration/meson.build    |   1 +
>>>   migration/precreate.c    | 139 +++++++++++++++++++++++++++++++++++++++++++++++
>>>   3 files changed, 145 insertions(+)
>>>   create mode 100644 migration/precreate.c
>>>
>>> diff --git a/include/migration/misc.h b/include/migration/misc.h
>>> index c9e200f..cf30351 100644
>>> --- a/include/migration/misc.h
>>> +++ b/include/migration/misc.h
>>> @@ -56,6 +56,11 @@ AnnounceParameters *migrate_announce_params(void);
>>>   
>>>   void dump_vmstate_json_to_file(FILE *out_fp);
>>>   
>>> +/* migration/precreate.c */
>>> +int migration_precreate_save(Error **errp);
>>> +void migration_precreate_unsave(void);
>>> +int migration_precreate_load(Error **errp);
>>> +
>>>   /* migration/migration.c */
>>>   void migration_object_init(void);
>>>   void migration_shutdown(void);
>>> diff --git a/migration/meson.build b/migration/meson.build
>>> index f76b1ba..50e7cb2 100644
>>> --- a/migration/meson.build
>>> +++ b/migration/meson.build
>>> @@ -26,6 +26,7 @@ system_ss.add(files(
>>>     'ram-compress.c',
>>>     'options.c',
>>>     'postcopy-ram.c',
>>> +  'precreate.c',
>>>     'savevm.c',
>>>     'socket.c',
>>>     'tls.c',
>>> diff --git a/migration/precreate.c b/migration/precreate.c
>>> new file mode 100644
>>> index 0000000..0bf5e1f
>>> --- /dev/null
>>> +++ b/migration/precreate.c
>>> @@ -0,0 +1,139 @@
>>> +/*
>>> + * Copyright (c) 2022, 2024 Oracle and/or its affiliates.
>>> + *
>>> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
>>> + * See the COPYING file in the top-level directory.
>>> + */
>>> +
>>> +#include "qemu/osdep.h"
>>> +#include "qemu/cutils.h"
>>> +#include "qemu/memfd.h"
>>> +#include "qapi/error.h"
>>> +#include "io/channel-file.h"
>>> +#include "migration/misc.h"
>>> +#include "migration/qemu-file.h"
>>> +#include "migration/savevm.h"
>>> +
>>> +#define PRECREATE_STATE_NAME "QEMU_PRECREATE_STATE"
>>> +
>>> +static QEMUFile *qemu_file_new_fd_input(int fd, const char *name)
>>> +{
>>> +    g_autoptr(QIOChannelFile) fioc = qio_channel_file_new_fd(fd);
>>> +    QIOChannel *ioc = QIO_CHANNEL(fioc);
>>> +    qio_channel_set_name(ioc, name);
>>> +    return qemu_file_new_input(ioc);
>>> +}
>>> +
>>> +static QEMUFile *qemu_file_new_fd_output(int fd, const char *name)
>>> +{
>>> +    g_autoptr(QIOChannelFile) fioc = qio_channel_file_new_fd(fd);
>>> +    QIOChannel *ioc = QIO_CHANNEL(fioc);
>>> +    qio_channel_set_name(ioc, name);
>>> +    return qemu_file_new_output(ioc);
>>> +}
>>> +
>>> +static int memfd_create_named(const char *name, Error **errp)
>>> +{
>>> +    int mfd;
>>> +    char val[16];
>>> +
>>> +    mfd = memfd_create(name, 0);
>>> +    if (mfd < 0) {
>>> +        error_setg_errno(errp, errno, "memfd_create failed");
>>> +        return -1;
>>> +    }
>>> +
>>> +    /* Remember mfd in environment for post-exec load */
>>> +    qemu_clear_cloexec(mfd);
>>> +    snprintf(val, sizeof(val), "%d", mfd);
>>> +    g_setenv(name, val, 1);
>>> +
>>> +    return mfd;
>>> +}
>>> +
>>> +static int memfd_find_named(const char *name, int *mfd_p, Error **errp)
>>> +{
>>> +    const char *val = g_getenv(name);
>>> +
>>> +    if (!val) {
>>> +        *mfd_p = -1;
>>> +        return 0;       /* No memfd was created, not an error */
>>> +    }
>>> +    g_unsetenv(name);
>>> +    if (qemu_strtoi(val, NULL, 10, mfd_p)) {
>>> +        error_setg(errp, "Bad %s env value %s", PRECREATE_STATE_NAME, val);
>>> +        return -1;
>>> +    }
>>> +    lseek(*mfd_p, 0, SEEK_SET);
>>> +    return 0;
>>> +}
>>> +
>>> +static void memfd_delete_named(const char *name)
>>> +{
>>> +    int mfd;
>>> +    const char *val = g_getenv(name);
>>> +
>>> +    if (val) {
>>> +        g_unsetenv(name);
>>> +        if (!qemu_strtoi(val, NULL, 10, &mfd)) {
>>> +            close(mfd);
>>> +        }
>>> +    }
>>> +}
>>> +
>>> +static QEMUFile *qemu_file_new_memfd_output(const char *name, Error **errp)
>>> +{
>>> +    int mfd = memfd_create_named(name, errp);
>>> +
>>> +    if (mfd < 0) {
>>> +        return NULL;
>>> +    }
>>> +
>>> +    return qemu_file_new_fd_output(mfd, name);
>>> +}
>>> +
>>> +static QEMUFile *qemu_file_new_memfd_input(const char *name, Error **errp)
>>> +{
>>> +    int ret, mfd;
>>> +
>>> +    ret = memfd_find_named(name, &mfd, errp);
>>> +    if (ret || mfd < 0) {
>>> +        return NULL;
>>> +    }
>>> +
>>> +    return qemu_file_new_fd_input(mfd, name);
>>> +}
>>> +
>>> +int migration_precreate_save(Error **errp)
>>> +{
>>> +    QEMUFile *f = qemu_file_new_memfd_output(PRECREATE_STATE_NAME, errp);
>>> +
>>> +    if (!f) {
>>> +        return -1;
>>> +    } else if (qemu_savevm_precreate_save(f, errp)) {
>>> +        memfd_delete_named(PRECREATE_STATE_NAME);
>>> +        return -1;
>>> +    } else {
>>> +        /* Do not close f, as mfd must remain open. */
>>> +        return 0;
>>> +    }
>>> +}
>>> +
>>> +void migration_precreate_unsave(void)
>>> +{
>>> +    memfd_delete_named(PRECREATE_STATE_NAME);
>>> +}
>>> +
>>> +int migration_precreate_load(Error **errp)
>>> +{
>>> +    int ret;
>>> +    QEMUFile *f = qemu_file_new_memfd_input(PRECREATE_STATE_NAME, errp);
>> 
>> Can we avoid the QEMUFile? I don't see it being exported from this file.
>
> It is not exported, but within this file, it is the basis for all read and
> write operations, via the existing functions qemu_file_new_input() and 
> qemu_file_new_output()

Right, that's the easy part, we could just use the QIOChannel
directly. But I missed the fact that you also need to interop with the
existing code that needs the QEMUFile.

Reviewed-by: Fabiano Rosas <farosas@suse.de>