[PATCH V6 13/27] cpr: preserve extra state

[Steve Sistare <steven.sistare@oracle.com>]

cpr must save state that is needed after qemu is restarted, when devices are
realized.  Thus the extra state cannot be saved in the cpr-load vmstate file,
as objects must already exist before that file can be loaded.  Instead,
define auxilliary state structures and vmstate descriptions, not associated
with any registered object, and serialize the aux state to a memfd file.
Deserialize after qemu restarts, before devices are realized.

Currently file descriptors comprise the only such state, but more could
be added in the future.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 MAINTAINERS             |   2 +
 include/migration/cpr.h |  11 +++
 migration/cpr-state.c   | 215 ++++++++++++++++++++++++++++++++++++++++++++++++
 migration/meson.build   |   1 +
 migration/trace-events  |   5 ++
 stubs/cpr-state.c       |  15 ++++
 stubs/meson.build       |   1 +
 7 files changed, 250 insertions(+)
 create mode 100644 migration/cpr-state.c
 create mode 100644 stubs/cpr-state.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 2611ca6..a9d2ed8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2907,6 +2907,8 @@ S: Maintained
 F: include/migration/cpr.h
 F: migration/cpr.c
 F: qapi/cpr.json
+F: migration/cpr-state.c
+F: stubs/cpr-state.c
 
 Record/replay
 M: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
diff --git a/include/migration/cpr.h b/include/migration/cpr.h
index a76429a..83f69c9 100644
--- a/include/migration/cpr.h
+++ b/include/migration/cpr.h
@@ -14,4 +14,15 @@
 
 CprMode cpr_mode(void);
 
+typedef int (*cpr_walk_fd_cb)(const char *name, int id, int fd, void *opaque);
+
+void cpr_save_fd(const char *name, int id, int fd);
+void cpr_delete_fd(const char *name, int id);
+int cpr_find_fd(const char *name, int id);
+int cpr_walk_fd(cpr_walk_fd_cb cb, void *handle);
+int cpr_state_save(Error **errp);
+int cpr_state_load(Error **errp);
+CprMode cpr_state_mode(void);
+void cpr_state_print(void);
+
 #endif
diff --git a/migration/cpr-state.c b/migration/cpr-state.c
new file mode 100644
index 0000000..003b449
--- /dev/null
+++ b/migration/cpr-state.c
@@ -0,0 +1,215 @@
+#include "qemu/osdep.h"
+#include "qemu/cutils.h"
+#include "qemu/queue.h"
+#include "qemu/memfd.h"
+#include "qapi/error.h"
+#include "migration/vmstate.h"
+#include "migration/cpr.h"
+#include "migration/qemu-file.h"
+#include "migration/qemu-file-channel.h"
+#include "trace.h"
+
+/*************************************************************************/
+/* cpr state container for all information to be saved. */
+
+typedef QLIST_HEAD(CprNameList, CprName) CprNameList;
+
+typedef struct CprState {
+    CprMode mode;
+    CprNameList fds;            /* list of CprFd */
+} CprState;
+
+static CprState cpr_state;
+
+/*************************************************************************/
+/* Generic list of names. */
+
+typedef struct CprName {
+    char *name;
+    unsigned int namelen;
+    int id;
+    QLIST_ENTRY(CprName) next;
+} CprName;
+
+static const VMStateDescription vmstate_cpr_name = {
+    .name = "cpr name",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(namelen, CprName),
+        VMSTATE_VBUFFER_ALLOC_UINT32(name, CprName, 0, NULL, namelen),
+        VMSTATE_INT32(id, CprName),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void
+add_name(CprNameList *head, const char *name, int id, CprName *elem)
+{
+    elem->name = g_strdup(name);
+    elem->namelen = strlen(name) + 1;
+    elem->id = id;
+    QLIST_INSERT_HEAD(head, elem, next);
+}
+
+static CprName *find_name(CprNameList *head, const char *name, int id)
+{
+    CprName *elem;
+
+    QLIST_FOREACH(elem, head, next) {
+        if (!strcmp(elem->name, name) && elem->id == id) {
+            return elem;
+        }
+    }
+    return NULL;
+}
+
+static void delete_name(CprNameList *head, const char *name, int id)
+{
+    CprName *elem = find_name(head, name, id);
+
+    if (elem) {
+        QLIST_REMOVE(elem, next);
+        g_free(elem->name);
+        g_free(elem);
+    }
+}
+
+/****************************************************************************/
+/* Lists of named things.  The first field of each entry must be a CprName. */
+
+typedef struct CprFd {
+    CprName name;               /* must be first */
+    int fd;
+} CprFd;
+
+static const VMStateDescription vmstate_cpr_fd = {
+    .name = "cpr fd",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT(name, CprFd, 1, vmstate_cpr_name, CprName),
+        VMSTATE_INT32(fd, CprFd),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define CPR_FD(elem)        ((CprFd *)(elem))
+#define CPR_FD_FD(elem)     (CPR_FD(elem)->fd)
+
+void cpr_save_fd(const char *name, int id, int fd)
+{
+    CprFd *elem = g_new0(CprFd, 1);
+
+    trace_cpr_save_fd(name, id, fd);
+    elem->fd = fd;
+    add_name(&cpr_state.fds, name, id, &elem->name);
+}
+
+void cpr_delete_fd(const char *name, int id)
+{
+    trace_cpr_delete_fd(name, id);
+    delete_name(&cpr_state.fds, name, id);
+}
+
+int cpr_find_fd(const char *name, int id)
+{
+    CprName *elem = find_name(&cpr_state.fds, name, id);
+    int fd = elem ? CPR_FD_FD(elem) : -1;
+
+    trace_cpr_find_fd(name, id, fd);
+    return fd;
+}
+
+int cpr_walk_fd(cpr_walk_fd_cb cb, void *opaque)
+{
+    CprName *elem;
+
+    QLIST_FOREACH(elem, &cpr_state.fds, next) {
+        if (cb(elem->name, elem->id, CPR_FD_FD(elem), opaque)) {
+            return 1;
+        }
+    }
+    return 0;
+}
+
+/*************************************************************************/
+/* cpr state container interface and implementation. */
+
+#define CPR_STATE_NAME "QEMU_CPR_STATE"
+
+static const VMStateDescription vmstate_cpr_state = {
+    .name = CPR_STATE_NAME,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(mode, CprState),
+        VMSTATE_QLIST_V(fds, CprState, 1, vmstate_cpr_fd, CprFd, name.next),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+int cpr_state_save(Error **errp)
+{
+    int ret, mfd;
+    QEMUFile *f;
+    char val[16];
+
+    mfd = memfd_create(CPR_STATE_NAME, 0);
+    if (mfd < 0) {
+        error_setg_errno(errp, errno, "memfd_create failed");
+        return -1;
+    }
+    qemu_clear_cloexec(mfd);
+    f = qemu_fd_open(mfd, true, CPR_STATE_NAME);
+
+    ret = vmstate_save_state(f, &vmstate_cpr_state, &cpr_state, 0);
+    if (ret) {
+        error_setg(errp, "vmstate_save_state error %d", ret);
+        return ret;
+    }
+
+    /* Do not close f, as mfd must remain open. */
+    qemu_fflush(f);
+    lseek(mfd, 0, SEEK_SET);
+
+    /* Remember mfd for post-exec cpr_state_load */
+    snprintf(val, sizeof(val), "%d", mfd);
+    g_setenv(CPR_STATE_NAME, val, 1);
+
+    return 0;
+}
+
+int cpr_state_load(Error **errp)
+{
+    int ret, mfd;
+    QEMUFile *f;
+    const char *val = g_getenv(CPR_STATE_NAME);
+
+    if (!val) {
+        return 0;
+    }
+    g_unsetenv(CPR_STATE_NAME);
+    if (qemu_strtoi(val, NULL, 10, &mfd)) {
+        error_setg(errp, "Bad %s env value %s", CPR_STATE_NAME, val);
+        return 1;
+    }
+    f = qemu_fd_open(mfd, false, CPR_STATE_NAME);
+    ret = vmstate_load_state(f, &vmstate_cpr_state, &cpr_state, 1);
+    qemu_fclose(f);
+    return ret;
+}
+
+CprMode cpr_state_mode(void)
+{
+    return cpr_state.mode;
+}
+
+void cpr_state_print(void)
+{
+    CprName *elem;
+
+    QLIST_FOREACH(elem, &cpr_state.fds, next) {
+        printf("%s %d : %d\n", elem->name, elem->id, CPR_FD_FD(elem));
+    }
+}
diff --git a/migration/meson.build b/migration/meson.build
index fd59281..b79d02c 100644
--- a/migration/meson.build
+++ b/migration/meson.build
@@ -16,6 +16,7 @@ softmmu_ss.add(files(
   'colo-failover.c',
   'colo.c',
   'cpr.c',
+  'cpr-state.c',
   'exec.c',
   'fd.c',
   'global_state.c',
diff --git a/migration/trace-events b/migration/trace-events
index a1c0f03..e3149b6 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -310,6 +310,11 @@ colo_receive_message(const char *msg) "Receive '%s' message"
 # colo-failover.c
 colo_failover_set_state(const char *new_state) "new state %s"
 
+# cpr-state.c
+cpr_save_fd(const char *name, int id, int fd) "%s, id %d, fd %d"
+cpr_delete_fd(const char *name, int id) "%s, id %d"
+cpr_find_fd(const char *name, int id, int fd) "%s, id %d returns %d"
+
 # block-dirty-bitmap.c
 send_bitmap_header_enter(void) ""
 send_bitmap_bits(uint32_t flags, uint64_t start_sector, uint32_t nr_sectors, uint64_t data_size) "flags: 0x%x, start_sector: %" PRIu64 ", nr_sectors: %" PRIu32 ", data_size: %" PRIu64
diff --git a/stubs/cpr-state.c b/stubs/cpr-state.c
new file mode 100644
index 0000000..24a9057
--- /dev/null
+++ b/stubs/cpr-state.c
@@ -0,0 +1,15 @@
+#include "qemu/osdep.h"
+#include "migration/cpr.h"
+
+void cpr_save_fd(const char *name, int id, int fd)
+{
+}
+
+void cpr_delete_fd(const char *name, int id)
+{
+}
+
+int cpr_find_fd(const char *name, int id)
+{
+    return -1;
+}
diff --git a/stubs/meson.build b/stubs/meson.build
index d3fa864..2748508 100644
--- a/stubs/meson.build
+++ b/stubs/meson.build
@@ -5,6 +5,7 @@ stub_ss.add(files('blk-exp-close-all.c'))
 stub_ss.add(files('blockdev-close-all-bdrv-states.c'))
 stub_ss.add(files('change-state-handler.c'))
 stub_ss.add(files('cmos.c'))
+stub_ss.add(files('cpr-state.c'))
 stub_ss.add(files('cpu-get-clock.c'))
 stub_ss.add(files('cpus-get-virtual-clock.c'))
 stub_ss.add(files('qemu-timer-notify-cb.c'))
-- 
1.8.3.1