Merge tag 'migration-20230530-pull-request' of https://gitlab.com/jua…

…n.quintela/qemu into staging

Migration 20230530 Pull request (take 2)

Hi

Resend last PULL request, this time it compiles when CONFIG_RDMA is
not configured in.

[take 1]
On this PULL request:

- Set vmstate migration failure right (vladimir)
- Migration QEMUFileHook removal (juan)
- Migration Atomic counters (juan)

Please apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmR2P48ACgkQ9IfvGFhy
# 1yN/EhAA1HAg2YPcUxNFJw/4apv782KrtMgtZW+HiYkKn51/VthHEP/V2OQSpUuc
# dv4QBH+lZXPDb5xkQM8kVfcUCB16yd38w9b6zvRCG6JN2IxyOMN6810pxV3PqTq9
# 86+/W1yly0XkR95kH7wqAjlbkEe6yAKTvabiJfRLUs48E794U1ok5p+O0L3rDEbI
# Og8Z/jvcaU4tSVmWH4+tI0wZY4iSwo2u2XO2tyxEh7PrAlql1wCvfD6szs7rDTtT
# i8TsWJ8mtx0VTLx1QBwDsU02kTmUTptJZrxbn5bY7vfLNz5ztZD4Mv4g9aNFuJ5B
# xumSl5T6HHBfxdl7NAzBBM6v0GmN21gfNXoB4WKDIVlCXgYyTeQHfrJBmrkZJwj8
# by8NHhtWDkc5M0em6ZwW9reDRXa80fQAhrVAE2+5wK0qI/1xm/tHroZm37X1v88j
# wvbDAnurdo7V8QC/kbIX+691lS2krB9IC2qiA40egS2UxzaNxIy7ohc+cnr4dzjP
# ofAKjJOTw7c/Vl6npBoJ/eJpa1/f3fVVvYBOkcyJezHwUJJUq0SXEhzoz4y6IpvR
# 4ZqbmQoUW8nilNN9NabdewwHCjGhXHBtyQMSUINaIFDyI/bcS5W6I2NblM9CBuYd
# gm6dXhTwNXmgh4aO48OVxmnyLgw7qSDz2yhIhy4MR+Yueh8Zifs=
# =lRhq
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 30 May 2023 11:25:19 AM PDT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [undefined]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20230530-pull-request' of https://gitlab.com/juan.quintela/qemu: (21 commits)
  migration/rdma: Check sooner if we are in postcopy for save_page()
  migration/rdma: Remove qemu_ prefix from exported functions
  migration/rdma: Move rdma constants from qemu-file.h to rdma.h
  qemu-file: Remove QEMUFileHooks
  migration/rdma: Create rdma_control_save_page()
  migration/rdma: Unfold hook_ram_load()
  migration/rdma: Remove all uses of RAM_CONTROL_HOOK
  migration/rdma: Unfold ram_control_after_iterate()
  migration/rdma: Unfold ram_control_before_iterate()
  migration: Create migrate_rdma()
  migration/rdma: Simplify the function that saves a page
  migration: Remove unused qemu_file_credit_transfer()
  migration/rdma: Don't use imaginary transfers
  migration/rdma: Remove QEMUFile parameter when not used
  migration/RDMA: It is accounting for zero/normal pages in two places
  migration: Don't abuse qemu_file transferred for RDMA
  migration: restore vmstate on migration failure
  migration: switch from .vm_was_running to .vm_old_state
  runstate: drop unused runstate_store()
  migration: never fail in global_state_store()
  ...

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

include/migration/global_state.h

@@ -16,7 +16,7 @@
 #include "qapi/qapi-types-run-state.h"
 
 void register_global_state(void);
-int global_state_store(void);
+void global_state_store(void);
 void global_state_store_running(void);
 bool global_state_received(void);
 RunState global_state_get_runstate(void);

include/sysemu/runstate.h

@@ -6,9 +6,9 @@
 
 bool runstate_check(RunState state);
 void runstate_set(RunState new_state);
+RunState runstate_get(void);
 bool runstate_is_running(void);
 bool runstate_needs_reset(void);
-bool runstate_store(char *str, size_t size);
 
 typedef void VMChangeStateHandler(void *opaque, bool running, RunState state);
 

migration/global_state.c

@@ -29,23 +29,22 @@ typedef struct {
 
 static GlobalState global_state;
 
-int global_state_store(void)
+static void global_state_do_store(RunState state)
 {
-    if (!runstate_store((char *)global_state.runstate,
-                        sizeof(global_state.runstate))) {
-        error_report("runstate name too big: %s", global_state.runstate);
-        trace_migrate_state_too_big();
-        return -EINVAL;
-    }
-    return 0;
+    const char *state_str = RunState_str(state);
+    assert(strlen(state_str) < sizeof(global_state.runstate));
+    strpadcpy((char *)global_state.runstate, sizeof(global_state.runstate),
+              state_str, '\0');
+}
+
+void global_state_store(void)
+{
+    global_state_do_store(runstate_get());
 }
 
 void global_state_store_running(void)
 {
-    const char *state = RunState_str(RUN_STATE_RUNNING);
-    assert(strlen(state) < sizeof(global_state.runstate));
-    strpadcpy((char *)global_state.runstate, sizeof(global_state.runstate),
-              state, '\0');
+    global_state_do_store(RUN_STATE_RUNNING);
 }
 
 bool global_state_received(void)

migration/migration-stats.c

@@ -61,8 +61,9 @@ void migration_rate_reset(QEMUFile *f)
 uint64_t migration_transferred_bytes(QEMUFile *f)
 {
     uint64_t multifd = stat64_get(&mig_stats.multifd_bytes);
+    uint64_t rdma = stat64_get(&mig_stats.rdma_bytes);
     uint64_t qemu_file = qemu_file_transferred(f);
 
-    trace_migration_transferred_bytes(qemu_file, multifd);
-    return qemu_file + multifd;
+    trace_migration_transferred_bytes(qemu_file, multifd, rdma);
+    return qemu_file + multifd + rdma;
 }

migration/migration-stats.h

@@ -89,6 +89,10 @@ typedef struct {
      * Maximum amount of data we can send in a cycle.
      */
     Stat64 rate_limit_max;
+    /*
+     * Number of bytes sent through RDMA.
+     */
+    Stat64 rdma_bytes;
     /*
      * Total number of bytes transferred.
      */

migration/migration.c

@@ -1402,9 +1402,10 @@ void migrate_init(MigrationState *s)
 
     s->start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     s->total_time = 0;
-    s->vm_was_running = false;
+    s->vm_old_state = -1;
     s->iteration_initial_bytes = 0;
     s->threshold_size = 0;
+    s->rdma_migration = false;
 }
 
 int migrate_add_blocker_internal(Error *reason, Error **errp)
@@ -2287,28 +2288,28 @@ static void migration_completion(MigrationState *s)
         qemu_mutex_lock_iothread();
         s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
         qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-        s->vm_was_running = runstate_is_running();
-        ret = global_state_store();
-
-        if (!ret) {
-            ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
-            trace_migration_completion_vm_stop(ret);
-            if (ret >= 0) {
-                ret = migration_maybe_pause(s, &current_active_state,
-                                            MIGRATION_STATUS_DEVICE);
-            }
-            if (ret >= 0) {
-                /*
-                 * Inactivate disks except in COLO, and track that we
-                 * have done so in order to remember to reactivate
-                 * them if migration fails or is cancelled.
-                 */
-                s->block_inactive = !migrate_colo();
-                migration_rate_set(RATE_LIMIT_DISABLED);
-                ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
-                                                         s->block_inactive);
-            }
+
+        s->vm_old_state = runstate_get();
+        global_state_store();
+
+        ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
+        trace_migration_completion_vm_stop(ret);
+        if (ret >= 0) {
+            ret = migration_maybe_pause(s, &current_active_state,
+                                        MIGRATION_STATUS_DEVICE);
         }
+        if (ret >= 0) {
+            /*
+             * Inactivate disks except in COLO, and track that we
+             * have done so in order to remember to reactivate
+             * them if migration fails or is cancelled.
+             */
+            s->block_inactive = !migrate_colo();
+            migration_rate_set(RATE_LIMIT_DISABLED);
+            ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
+                                                     s->block_inactive);
+        }
+
         qemu_mutex_unlock_iothread();
 
         if (ret < 0) {
@@ -2761,18 +2762,18 @@ static void migration_iteration_finish(MigrationState *s)
     case MIGRATION_STATUS_COLO:
         assert(migrate_colo());
         migrate_start_colo_process(s);
-        s->vm_was_running = true;
+        s->vm_old_state = RUN_STATE_RUNNING;
         /* Fallthrough */
     case MIGRATION_STATUS_FAILED:
     case MIGRATION_STATUS_CANCELLED:
     case MIGRATION_STATUS_CANCELLING:
-        if (s->vm_was_running) {
+        if (s->vm_old_state == RUN_STATE_RUNNING) {
             if (!runstate_check(RUN_STATE_SHUTDOWN)) {
                 vm_start();
             }
         } else {
             if (runstate_check(RUN_STATE_FINISH_MIGRATE)) {
-                runstate_set(RUN_STATE_POSTMIGRATE);
+                runstate_set(s->vm_old_state);
             }
         }
         break;
@@ -3086,11 +3087,9 @@ static void *bg_migration_thread(void *opaque)
      * transition in vm_stop_force_state() we need to wakeup it up.
      */
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-    s->vm_was_running = runstate_is_running();
+    s->vm_old_state = runstate_get();
 
-    if (global_state_store()) {
-        goto fail;
-    }
+    global_state_store();
     /* Forcibly stop VM before saving state of vCPUs and devices */
     if (vm_stop_force_state(RUN_STATE_PAUSED)) {
         goto fail;

migration/migration.h

@@ -25,6 +25,7 @@
 #include "net/announce.h"
 #include "qom/object.h"
 #include "postcopy-ram.h"
+#include "sysemu/runstate.h"
 
 struct PostcopyBlocktimeContext;
 
@@ -317,12 +318,14 @@ struct MigrationState {
     int64_t expected_downtime;
     bool capabilities[MIGRATION_CAPABILITY__MAX];
     int64_t setup_time;
+
     /*
-     * Whether guest was running when we enter the completion stage.
+     * State before stopping the vm by vm_stop_force_state().
      * If migration is interrupted by any reason, we need to continue
-     * running the guest on source.
+     * running the guest on source if it was running or restore its stopped
+     * state.
      */
-    bool vm_was_running;
+    RunState vm_old_state;
 
     /* Flag set once the migration has been asked to enter postcopy */
     bool start_postcopy;
@@ -437,6 +440,9 @@ struct MigrationState {
 
     /* QEMU_VM_VMDESCRIPTION content filled for all non-iterable devices. */
     JSONWriter *vmdesc;
+
+    /* Is this a rdma migration */
+    bool rdma_migration;
 };
 
 void migrate_set_state(int *state, int old_state, int new_state);

migration/options.c

@@ -350,6 +350,13 @@ bool migrate_postcopy(void)
     return migrate_postcopy_ram() || migrate_dirty_bitmaps();
 }
 
+bool migrate_rdma(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return s->rdma_migration;
+}
+
 bool migrate_tls(void)
 {
     MigrationState *s = migrate_get_current();

migration/options.h

@@ -54,6 +54,7 @@ bool migrate_zero_copy_send(void);
 
 bool migrate_multifd_flush_after_each_section(void);
 bool migrate_postcopy(void);
+bool migrate_rdma(void);
 bool migrate_tls(void);
 
 /* capabilities helpers */

migration/qemu-file.c

@@ -32,12 +32,12 @@
 #include "trace.h"
 #include "options.h"
 #include "qapi/error.h"
+#include "rdma.h"
 
 #define IO_BUF_SIZE 32768
 #define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
 
 struct QEMUFile {
-    const QEMUFileHooks *hooks;
     QIOChannel *ioc;
     bool is_writable;
 
@@ -146,11 +146,6 @@ QEMUFile *qemu_file_new_input(QIOChannel *ioc)
     return qemu_file_new_impl(ioc, false);
 }
 
-void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks)
-{
-    f->hooks = hooks;
-}
-
 /*
  * Get last error for stream f with optional Error*
  *
@@ -302,63 +297,6 @@ void qemu_fflush(QEMUFile *f)
     f->iovcnt = 0;
 }
 
-void ram_control_before_iterate(QEMUFile *f, uint64_t flags)
-{
-    int ret = 0;
-
-    if (f->hooks && f->hooks->before_ram_iterate) {
-        ret = f->hooks->before_ram_iterate(f, flags, NULL);
-        if (ret < 0) {
-            qemu_file_set_error(f, ret);
-        }
-    }
-}
-
-void ram_control_after_iterate(QEMUFile *f, uint64_t flags)
-{
-    int ret = 0;
-
-    if (f->hooks && f->hooks->after_ram_iterate) {
-        ret = f->hooks->after_ram_iterate(f, flags, NULL);
-        if (ret < 0) {
-            qemu_file_set_error(f, ret);
-        }
-    }
-}
-
-void ram_control_load_hook(QEMUFile *f, uint64_t flags, void *data)
-{
-    if (f->hooks && f->hooks->hook_ram_load) {
-        int ret = f->hooks->hook_ram_load(f, flags, data);
-        if (ret < 0) {
-            qemu_file_set_error(f, ret);
-        }
-    }
-}
-
-size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
-                             ram_addr_t offset, size_t size,
-                             uint64_t *bytes_sent)
-{
-    if (f->hooks && f->hooks->save_page) {
-        int ret = f->hooks->save_page(f, block_offset,
-                                      offset, size, bytes_sent);
-
-        if (ret != RAM_SAVE_CONTROL_DELAYED &&
-            ret != RAM_SAVE_CONTROL_NOT_SUPP) {
-            if (bytes_sent && *bytes_sent > 0) {
-                qemu_file_credit_transfer(f, *bytes_sent);
-            } else if (ret < 0) {
-                qemu_file_set_error(f, ret);
-            }
-        }
-
-        return ret;
-    }
-
-    return RAM_SAVE_CONTROL_NOT_SUPP;
-}
-
 /*
  * Attempt to fill the buffer from the underlying file
  * Returns the number of bytes read, or negative value for an error.
@@ -414,11 +352,6 @@ static ssize_t coroutine_mixed_fn qemu_fill_buffer(QEMUFile *f)
     return len;
 }
 
-void qemu_file_credit_transfer(QEMUFile *f, size_t size)
-{
-    f->total_transferred += size;
-}
-
 /** Closes the file
  *
  * Returns negative error value if any error happened on previous operations or