Merge tag 'migration-20231102-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request (20231102)

Hi

In this pull request:

- migration reboot mode (steve)
  * I disabled the test because our CI don't like programs using so
    much shared memory.  Searching for a fix.
- test for postcopy recover (fabiano)
- MigrateAddress QAPI (het)
- better return path error handling (peter)
- traces for downtime (peter)
- vmstate_register() check for duplicates (juan)
  thomas find better solutions for s390x and ipmi.
  now also works on s390x

Please, apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmVDipMACgkQ9IfvGFhy
# 1yNYnQ/9E5Cywsoqljqa/9FiKBSII2qMrmkfu6JLKqePnsh5pFZiukbudYRuJCCe
# ZTDEmD0NmKRJbDx2xRU1qx/e6gKJy+gz37KP89Buuh/WwZHPboPYtxQpGvCSiH26
# J3i+1+TgaqmkLzcO35wa8tp6gneQclWeAwKgMvdb4cm2pJEhgWRKI62ccyLzxeve
# UCzFQn60t55ETyVZGnRD4YwdTQvGKH+DPlyTuJOLR3DePuvZd8EdH+ypvB4RLAy7
# 3+CuQOxmF5LRXPbpJuAeOsudbmhhHzrO/yL7ZmsiKQTthsJv+SzC1bO94jhQrawZ
# Q7GCii5KpGq0KnRTRKZRGk6XKwxcYRduXMX3R5tXuVmDmCZsjhXzziU8yEdftph8
# 5TJdk1o0Gb043EFu81mrsQYS+9yJqe6sy6m3PTJaec54cAty5ln+c17WOvpAOaSV
# +1phe05ftuVPmQ3KWhbIR/tCmavNLwEZxpVIfyaKJx04bFbtQ9gRpRyURORX4KXc
# s4WXvNirQEohxYBnP4TPvA09xBTW3V08pk/wRDwt0YDXnLiqCltOuxD8r05K8K4B
# MkCLcWj0g7he2tBkF60oz1KSIE0oTB81um9AzLIv5F2YSYLaJM5BIcoC437MR2f4
# MOR7drR1fP5GsRu/SeU5BWvhVq3IvdOxR7G2MLNRJJvl7ZtGXDc=
# =uaqL
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 02 Nov 2023 19:40:03 HKT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20231102-pull-request' of https://gitlab.com/juan.quintela/qemu: (40 commits)
  migration: modify test_multifd_tcp_none() to use new QAPI syntax.
  migration: Implement MigrateChannelList to hmp migration flow.
  migration: Implement MigrateChannelList to qmp migration flow.
  migration: modify migration_channels_and_uri_compatible() for new QAPI syntax
  migration: New migrate and migrate-incoming argument 'channels'
  migration: Convert the file backend to the new QAPI syntax
  migration: convert exec backend to accept MigrateAddress.
  migration: convert rdma backend to accept MigrateAddress
  migration: convert socket backend to accept MigrateAddress
  migration: convert migration 'uri' into 'MigrateAddress'
  migration: New QAPI type 'MigrateAddress'
  migration: Change ram_dirty_bitmap_reload() retval to bool
  tests/migration-test: Add a test for postcopy hangs during RECOVER
  migration: Allow network to fail even during recovery
  migration: Refactor error handling in source return path
  tests/qtest: migration: add reboot mode test
  cpr: reboot mode
  cpr: relax vhost migration blockers
  cpr: relax blockdev migration blockers
  migration: per-mode blockers
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 32 insertions, 29 deletions

diff --git a/migration/ram.c b/migration/ram.c
index 34724e8fe8..a0f3b86663 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1898,7 +1898,8 @@ static void migration_page_queue_free(RAMState *rs)
  * @start: starting address from the start of the RAMBlock
  * @len: length (in bytes) to send
  */
-int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
+int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len,
+                         Error **errp)
 {
     RAMBlock *ramblock;
     RAMState *rs = ram_state;
@@ -1915,7 +1916,7 @@ int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
              * Shouldn't happen, we can't reuse the last RAMBlock if
              * it's the 1st request.
              */
-            error_report("ram_save_queue_pages no previous block");
+            error_setg(errp, "MIG_RP_MSG_REQ_PAGES has no previous block");
             return -1;
         }
     } else {
@@ -1923,16 +1924,17 @@ int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
 
         if (!ramblock) {
             /* We shouldn't be asked for a non-existent RAMBlock */
-            error_report("ram_save_queue_pages no block '%s'", rbname);
+            error_setg(errp, "MIG_RP_MSG_REQ_PAGES has no block '%s'", rbname);
             return -1;
         }
         rs->last_req_rb = ramblock;
     }
     trace_ram_save_queue_pages(ramblock->idstr, start, len);
     if (!offset_in_ramblock(ramblock, start + len - 1)) {
-        error_report("%s request overrun start=" RAM_ADDR_FMT " len="
-                     RAM_ADDR_FMT " blocklen=" RAM_ADDR_FMT,
-                     __func__, start, len, ramblock->used_length);
+        error_setg(errp, "MIG_RP_MSG_REQ_PAGES request overrun, "
+                   "start=" RAM_ADDR_FMT " len="
+                   RAM_ADDR_FMT " blocklen=" RAM_ADDR_FMT,
+                   start, len, ramblock->used_length);
         return -1;
     }
 
@@ -1964,9 +1966,9 @@ int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
         assert(len % page_size == 0);
         while (len) {
             if (ram_save_host_page_urgent(pss)) {
-                error_report("%s: ram_save_host_page_urgent() failed: "
-                             "ramblock=%s, start_addr=0x"RAM_ADDR_FMT,
-                             __func__, ramblock->idstr, start);
+                error_setg(errp, "ram_save_host_page_urgent() failed: "
+                           "ramblock=%s, start_addr=0x"RAM_ADDR_FMT,
+                           ramblock->idstr, start);
                 ret = -1;
                 break;
             }
@@ -4097,7 +4099,9 @@ static int ram_dirty_bitmap_sync_all(MigrationState *s, RAMState *rs)
 
     /* Wait until all the ramblocks' dirty bitmap synced */
     while (qatomic_read(&rs->postcopy_bmap_sync_requested)) {
-        migration_rp_wait(s);
+        if (migration_rp_wait(s)) {
+            return -1;
+        }
     }
 
     trace_ram_dirty_bitmap_sync_complete();
@@ -4109,10 +4113,11 @@ static int ram_dirty_bitmap_sync_all(MigrationState *s, RAMState *rs)
  * Read the received bitmap, revert it as the initial dirty bitmap.
  * This is only used when the postcopy migration is paused but wants
  * to resume from a middle point.
+ *
+ * Returns true if succeeded, false for errors.
  */
-int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
+bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block, Error **errp)
 {
-    int ret = -EINVAL;
     /* from_dst_file is always valid because we're within rp_thread */
     QEMUFile *file = s->rp_state.from_dst_file;
     g_autofree unsigned long *le_bitmap = NULL;
@@ -4124,9 +4129,9 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
     trace_ram_dirty_bitmap_reload_begin(block->idstr);
 
     if (s->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
-        error_report("%s: incorrect state %s", __func__,
-                     MigrationStatus_str(s->state));
-        return -EINVAL;
+        error_setg(errp, "Reload bitmap in incorrect state %s",
+                   MigrationStatus_str(s->state));
+        return false;
     }
 
     /*
@@ -4142,27 +4147,25 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
 
     /* The size of the bitmap should match with our ramblock */
     if (size != local_size) {
-        error_report("%s: ramblock '%s' bitmap size mismatch "
-                     "(0x%"PRIx64" != 0x%"PRIx64")", __func__,
-                     block->idstr, size, local_size);
-        return -EINVAL;
+        error_setg(errp, "ramblock '%s' bitmap size mismatch (0x%"PRIx64
+                   " != 0x%"PRIx64")", block->idstr, size, local_size);
+        return false;
     }
 
     size = qemu_get_buffer(file, (uint8_t *)le_bitmap, local_size);
     end_mark = qemu_get_be64(file);
 
-    ret = qemu_file_get_error(file);
-    if (ret || size != local_size) {
-        error_report("%s: read bitmap failed for ramblock '%s': %d"
-                     " (size 0x%"PRIx64", got: 0x%"PRIx64")",
-                     __func__, block->idstr, ret, local_size, size);
-        return -EIO;
+    if (qemu_file_get_error(file) || size != local_size) {
+        error_setg(errp, "read bitmap failed for ramblock '%s': "
+                   "(size 0x%"PRIx64", got: 0x%"PRIx64")",
+                   block->idstr, local_size, size);
+        return false;
     }
 
     if (end_mark != RAMBLOCK_RECV_BITMAP_ENDING) {
-        error_report("%s: ramblock '%s' end mark incorrect: 0x%"PRIx64,
-                     __func__, block->idstr, end_mark);
-        return -EINVAL;
+        error_setg(errp, "ramblock '%s' end mark incorrect: 0x%"PRIx64,
+                   block->idstr, end_mark);
+        return false;
     }
 
     /*
@@ -4194,7 +4197,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
      */
     migration_rp_kick(s);
 
-    return 0;
+    return true;
 }
 
 static int ram_resume_prepare(MigrationState *s, void *opaque)