Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20201026a' into staging

migration pull: 2020-10-26

Another go at Peter's postcopy fixes

Cleanups from Bihong Yu and Peter Maydell.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

# gpg: Signature made Mon 26 Oct 2020 16:17:03 GMT
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20201026a:
  migration-test: Only hide error if !QTEST_LOG
  migration/postcopy: Release fd before going into 'postcopy-pause'
  migration: Sync requested pages after postcopy recovery
  migration: Maintain postcopy faulted addresses
  migration: Introduce migrate_send_rp_message_req_pages()
  migration: Pass incoming state into qemu_ufd_copy_ioctl()
  migration: using trace_ to replace DPRINTF
  migration: Delete redundant spaces
  migration: Open brace '{' following function declarations go on the next line
  migration: Do not initialise statics and globals to 0 or NULL
  migration: Add braces {} for if statement
  migration: Open brace '{' following struct go on the same line
  migration: Add spaces around operator
  migration: Don't use '#' flag of printf format
  migration: Do not use C99 // comments
  migration: Drop unused VMSTATE_FLOAT64 support

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

1 files changed, 52 insertions, 7 deletions

diff --git a/migration/migration.c b/migration/migration.c
index deb6005..9bb4fee 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -143,6 +143,13 @@ static int migration_maybe_pause(MigrationState *s,
                                  int new_state);
 static void migrate_fd_cancel(MigrationState *s);
 
+static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp)
+{
+    uintptr_t a = (uintptr_t) ap, b = (uintptr_t) bp;
+
+    return (a > b) - (a < b);
+}
+
 void migration_object_init(void)
 {
     Error *err = NULL;
@@ -164,6 +171,8 @@ void migration_object_init(void)
     qemu_event_init(&current_incoming->main_thread_load_event, false);
     qemu_sem_init(&current_incoming->postcopy_pause_sem_dst, 0);
     qemu_sem_init(&current_incoming->postcopy_pause_sem_fault, 0);
+    qemu_mutex_init(&current_incoming->page_request_mutex);
+    current_incoming->page_requested = g_tree_new(page_request_addr_cmp);
 
     if (!migration_object_check(current_migration, &err)) {
         error_report_err(err);
@@ -230,6 +239,11 @@ void migration_incoming_state_destroy(void)
 
     qemu_event_reset(&mis->main_thread_load_event);
 
+    if (mis->page_requested) {
+        g_tree_destroy(mis->page_requested);
+        mis->page_requested = NULL;
+    }
+
     if (mis->socket_address_list) {
         qapi_free_SocketAddressList(mis->socket_address_list);
         mis->socket_address_list = NULL;
@@ -306,8 +320,8 @@ error:
  *   Start: Address offset within the RB
  *   Len: Length in bytes required - must be a multiple of pagesize
  */
-int migrate_send_rp_req_pages(MigrationIncomingState *mis, RAMBlock *rb,
-                              ram_addr_t start)
+int migrate_send_rp_message_req_pages(MigrationIncomingState *mis,
+                                      RAMBlock *rb, ram_addr_t start)
 {
     uint8_t bufc[12 + 1 + 255]; /* start (8), len (4), rbname up to 256 */
     size_t msglen = 12; /* start + len */
@@ -343,6 +357,37 @@ int migrate_send_rp_req_pages(MigrationIncomingState *mis, RAMBlock *rb,
     return migrate_send_rp_message(mis, msg_type, msglen, bufc);
 }
 
+int migrate_send_rp_req_pages(MigrationIncomingState *mis,
+                              RAMBlock *rb, ram_addr_t start, uint64_t haddr)
+{
+    void *aligned = (void *)(uintptr_t)(haddr & (-qemu_ram_pagesize(rb)));
+    bool received;
+
+    WITH_QEMU_LOCK_GUARD(&mis->page_request_mutex) {
+        received = ramblock_recv_bitmap_test_byte_offset(rb, start);
+        if (!received && !g_tree_lookup(mis->page_requested, aligned)) {
+            /*
+             * The page has not been received, and it's not yet in the page
+             * request list.  Queue it.  Set the value of element to 1, so that
+             * things like g_tree_lookup() will return TRUE (1) when found.
+             */
+            g_tree_insert(mis->page_requested, aligned, (gpointer)1);
+            mis->page_requested_count++;
+            trace_postcopy_page_req_add(aligned, mis->page_requested_count);
+        }
+    }
+
+    /*
+     * If the page is there, skip sending the message.  We don't even need the
+     * lock because as long as the page arrived, it'll be there forever.
+     */
+    if (received) {
+        return 0;
+    }
+
+    return migrate_send_rp_message_req_pages(mis, rb, start);
+}
+
 static bool migration_colo_enabled;
 bool migration_incoming_colo_enabled(void)
 {
@@ -2468,8 +2513,8 @@ static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
      * Since we currently insist on matching page sizes, just sanity check
      * we're being asked for whole host pages.
      */
-    if (start & (our_host_ps-1) ||
-       (len & (our_host_ps-1))) {
+    if (start & (our_host_ps - 1) ||
+       (len & (our_host_ps - 1))) {
         error_report("%s: Misaligned page request, start: " RAM_ADDR_FMT
                      " len: %zd", __func__, start, len);
         mark_source_rp_bad(ms);
@@ -3123,9 +3168,6 @@ static MigThrError postcopy_pause(MigrationState *s)
     while (true) {
         QEMUFile *file;
 
-        migrate_set_state(&s->state, s->state,
-                          MIGRATION_STATUS_POSTCOPY_PAUSED);
-
         /* Current channel is possibly broken. Release it. */
         assert(s->to_dst_file);
         qemu_mutex_lock(&s->qemu_file_lock);
@@ -3136,6 +3178,9 @@ static MigThrError postcopy_pause(MigrationState *s)
         qemu_file_shutdown(file);
         qemu_fclose(file);
 
+        migrate_set_state(&s->state, s->state,
+                          MIGRATION_STATUS_POSTCOPY_PAUSED);
+
         error_report("Detected IO failure for postcopy. "
                      "Migration paused.");