Merge tag 'migration-20240311-pull-request' of https://gitlab.com/peterx/qemu into staging

Migration pull request

- Avihai's fix to allow vmstate iterators to not starve for VFIO
- Maksim's fix on additional check on precopy load error
- Fabiano's fix on fdatasync() hang in mapped-ram
- Jonathan's fix on vring cached access over MMIO regions
- Cedric's cleanup patches 1-4 out of his error report series
- Yu's fix for RDMA migration (which used to be broken even for 8.2)
- Anthony's small cleanup/fix on err message
- Steve's patches on privatize migration.h
- Xiang's patchset to enable zero page detections in multifd threads

# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZe9+uBIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wamaQD/SvmpMEcuRndT9LPSxzXowAGDZTBpYUfv
# 5XAbx80dS9IBAO8PJJgQJIBHBeacyLBjHP9CsdVtgw5/VW+wCsbfV4AB
# =xavb
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 11 Mar 2024 21:59:20 GMT
# gpg:                using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg:                issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [marginal]
# gpg:                 aka "Peter Xu <peterx@redhat.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: B918 4DC2 0CC4 57DA CF7D  D1A9 3B5F CCCD F3AB D706

* tag 'migration-20240311-pull-request' of https://gitlab.com/peterx/qemu: (34 commits)
  migration/multifd: Add new migration test cases for legacy zero page checking.
  migration/multifd: Enable multifd zero page checking by default.
  migration/multifd: Implement ram_save_target_page_multifd to handle multifd version of MigrationOps::ram_save_target_page.
  migration/multifd: Implement zero page transmission on the multifd thread.
  migration/multifd: Add new migration option zero-page-detection.
  migration/multifd: Allow clearing of the file_bmap from multifd
  migration/multifd: Allow zero pages in file migration
  migration: purge MigrationState from public interface
  migration: delete unused accessors
  migration: privatize colo interfaces
  migration: migration_file_set_error
  migration: migration_is_device
  migration: migration_thread_is_self
  migration: export vcpu_dirty_limit_period
  migration: export migration_is_running
  migration: export migration_is_active
  migration: export migration_is_setup_or_active
  migration: remove migration.h references
  migration: export fewer options
  migration: Fix format in error message
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 47 insertions, 15 deletions

diff --git a/migration/ram.c b/migration/ram.c
index 003c28e133..8deb84984f 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1140,6 +1140,10 @@ static int save_zero_page(RAMState *rs, PageSearchStatus *pss,
     QEMUFile *file = pss->pss_channel;
     int len = 0;
 
+    if (migrate_zero_page_detection() == ZERO_PAGE_DETECTION_NONE) {
+        return 0;
+    }
+
     if (!buffer_is_zero(p, TARGET_PAGE_SIZE)) {
         return 0;
     }
@@ -1284,7 +1288,6 @@ static int ram_save_multifd_page(RAMBlock *block, ram_addr_t offset)
     if (!multifd_queue_page(block, offset)) {
         return -1;
     }
-    stat64_add(&mig_stats.normal_pages, 1);
 
     return 1;
 }
@@ -2076,7 +2079,6 @@ static bool save_compress_page(RAMState *rs, PageSearchStatus *pss,
  */
 static int ram_save_target_page_legacy(RAMState *rs, PageSearchStatus *pss)
 {
-    RAMBlock *block = pss->block;
     ram_addr_t offset = ((ram_addr_t)pss->page) << TARGET_PAGE_BITS;
     int res;
 
@@ -2092,17 +2094,33 @@ static int ram_save_target_page_legacy(RAMState *rs, PageSearchStatus *pss)
         return 1;
     }
 
+    return ram_save_page(rs, pss);
+}
+
+/**
+ * ram_save_target_page_multifd: send one target page to multifd workers
+ *
+ * Returns 1 if the page was queued, -1 otherwise.
+ *
+ * @rs: current RAM state
+ * @pss: data about the page we want to send
+ */
+static int ram_save_target_page_multifd(RAMState *rs, PageSearchStatus *pss)
+{
+    RAMBlock *block = pss->block;
+    ram_addr_t offset = ((ram_addr_t)pss->page) << TARGET_PAGE_BITS;
+
     /*
-     * Do not use multifd in postcopy as one whole host page should be
-     * placed.  Meanwhile postcopy requires atomic update of pages, so even
-     * if host page size == guest page size the dest guest during run may
-     * still see partially copied pages which is data corruption.
+     * While using multifd live migration, we still need to handle zero
+     * page checking on the migration main thread.
      */
-    if (migrate_multifd() && !migration_in_postcopy()) {
-        return ram_save_multifd_page(block, offset);
+    if (migrate_zero_page_detection() == ZERO_PAGE_DETECTION_LEGACY) {
+        if (save_zero_page(rs, pss, offset)) {
+            return 1;
+        }
     }
 
-    return ram_save_page(rs, pss);
+    return ram_save_multifd_page(block, offset);
 }
 
 /* Should be called before sending a host page */
@@ -2909,10 +2927,9 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
     RAMBlock *block;
     ram_addr_t offset;
     size_t used_len, start, npages;
-    MigrationState *s = migrate_get_current();
 
     /* This function is currently expected to be used during live migration */
-    if (!migration_is_setup_or_active(s->state)) {
+    if (!migration_is_setup_or_active()) {
         return;
     }
 
@@ -3110,7 +3127,12 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     }
 
     migration_ops = g_malloc0(sizeof(MigrationOps));
-    migration_ops->ram_save_target_page = ram_save_target_page_legacy;
+
+    if (migrate_multifd()) {
+        migration_ops->ram_save_target_page = ram_save_target_page_multifd;
+    } else {
+        migration_ops->ram_save_target_page = ram_save_target_page_legacy;
+    }
 
     bql_unlock();
     ret = multifd_send_sync_main();
@@ -3150,9 +3172,13 @@ static void ram_save_file_bmap(QEMUFile *f)
     }
 }
 
-void ramblock_set_file_bmap_atomic(RAMBlock *block, ram_addr_t offset)
+void ramblock_set_file_bmap_atomic(RAMBlock *block, ram_addr_t offset, bool set)
 {
-    set_bit_atomic(offset >> TARGET_PAGE_BITS, block->file_bmap);
+    if (set) {
+        set_bit_atomic(offset >> TARGET_PAGE_BITS, block->file_bmap);
+    } else {
+        clear_bit_atomic(offset >> TARGET_PAGE_BITS, block->file_bmap);
+    }
 }
 
 /**
@@ -3263,7 +3289,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
 
 out:
     if (ret >= 0
-        && migration_is_setup_or_active(migrate_get_current()->state)) {
+        && migration_is_setup_or_active()) {
         if (migrate_multifd() && migrate_multifd_flush_after_each_section() &&
             !migrate_mapped_ram()) {
             ret = multifd_send_sync_main();
@@ -4214,6 +4240,12 @@ static int ram_load_precopy(QEMUFile *f)
         i++;
 
         addr = qemu_get_be64(f);
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            error_report("Getting RAM address failed");
+            break;
+        }
+
         flags = addr & ~TARGET_PAGE_MASK;
         addr &= TARGET_PAGE_MASK;