Merge tag 'pull-migration-20220720c' of https://gitlab.com/dagrh/qemu into staging

Migration pull 2022-07-20

This replaces yesterdays pull and:
  a) Fixes some test build errors without TLS
  b) Reenabled the zlib acceleration on s390
     now that we have Ilya's fix

  Hyman's dirty page rate limit set
  Ilya's fix for zlib vs migration
  Peter's postcopy-preempt
  Cleanup from Dan
  zero-copy tidy ups from Leo
  multifd doc fix from Juan
  Revert disable of zlib acceleration on s390x

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

# gpg: Signature made Wed 20 Jul 2022 12:18:56 BST
# 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

* tag 'pull-migration-20220720c' of https://gitlab.com/dagrh/qemu: (30 commits)
  Revert "gitlab: disable accelerated zlib for s390x"
  migration: Avoid false-positive on non-supported scenarios for zero-copy-send
  multifd: Document the locking of MultiFD{Send/Recv}Params
  migration/multifd: Report to user when zerocopy not working
  Add dirty-sync-missed-zero-copy migration stat
  QIOChannelSocket: Fix zero-copy flush returning code 1 when nothing sent
  migration: remove unreachable code after reading data
  tests: Add postcopy preempt tests
  tests: Add postcopy tls recovery migration test
  tests: Add postcopy tls migration test
  tests: Move MigrateCommon upper
  migration: Respect postcopy request order in preemption mode
  migration: Enable TLS for preempt channel
  migration: Export tls-[creds|hostname|authz] params to cmdline too
  migration: Add helpers to detect TLS capability
  migration: Add property x-postcopy-preempt-break-huge
  migration: Create the postcopy preempt channel asynchronously
  migration: Postcopy recover with preempt enabled
  migration: Postcopy preemption enablement
  migration: Postcopy preemption preparation on channel creation
  ...

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

1 files changed, 43 insertions, 1 deletions

diff --git a/migration/migration.h b/migration/migration.h
index 485d58b95f..cdad8aceaa 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -23,6 +23,7 @@
 #include "io/channel-buffer.h"
 #include "net/announce.h"
 #include "qom/object.h"
+#include "postcopy-ram.h"
 
 struct PostcopyBlocktimeContext;
 
@@ -67,7 +68,7 @@ typedef struct {
 struct MigrationIncomingState {
     QEMUFile *from_src_file;
     /* Previously received RAM's RAMBlock pointer */
-    RAMBlock *last_recv_block;
+    RAMBlock *last_recv_block[RAM_CHANNEL_MAX];
     /* A hook to allow cleanup at the end of incoming migration */
     void *transport_data;
     void (*transport_cleanup)(void *data);
@@ -112,6 +113,23 @@ struct MigrationIncomingState {
      * enabled.
      */
     unsigned int postcopy_channels;
+    /* QEMUFile for postcopy only; it'll be handled by a separate thread */
+    QEMUFile *postcopy_qemufile_dst;
+    /* Postcopy priority thread is used to receive postcopy requested pages */
+    QemuThread postcopy_prio_thread;
+    bool postcopy_prio_thread_created;
+    /*
+     * Used to sync between the ram load main thread and the fast ram load
+     * thread.  It protects postcopy_qemufile_dst, which is the postcopy
+     * fast channel.
+     *
+     * The ram fast load thread will take it mostly for the whole lifecycle
+     * because it needs to continuously read data from the channel, and
+     * it'll only release this mutex if postcopy is interrupted, so that
+     * the ram load main thread will take this mutex over and properly
+     * release the broken channel.
+     */
+    QemuMutex postcopy_prio_thread_mutex;
     /*
      * An array of temp host huge pages to be used, one for each postcopy
      * channel.
@@ -141,6 +159,13 @@ struct MigrationIncomingState {
     /* notify PAUSED postcopy incoming migrations to try to continue */
     QemuSemaphore postcopy_pause_sem_dst;
     QemuSemaphore postcopy_pause_sem_fault;
+    /*
+     * This semaphore is used to allow the ram fast load thread (only when
+     * postcopy preempt is enabled) fall into sleep when there's network
+     * interruption detected.  When the recovery is done, the main load
+     * thread will kick the fast ram load thread using this semaphore.
+     */
+    QemuSemaphore postcopy_pause_sem_fast_load;
 
     /* List of listening socket addresses  */
     SocketAddressList *socket_address_list;
@@ -192,6 +217,15 @@ struct MigrationState {
     QEMUBH *cleanup_bh;
     /* Protected by qemu_file_lock */
     QEMUFile *to_dst_file;
+    /* Postcopy specific transfer channel */
+    QEMUFile *postcopy_qemufile_src;
+    /*
+     * It is posted when the preempt channel is established.  Note: this is
+     * used for both the start or recover of a postcopy migration.  We'll
+     * post to this sem every time a new preempt channel is created in the
+     * main thread, and we keep post() and wait() in pair.
+     */
+    QemuSemaphore postcopy_qemufile_src_sem;
     QIOChannelBuffer *bioc;
     /*
      * Protects to_dst_file/from_dst_file pointers.  We need to make sure we
@@ -306,6 +340,13 @@ struct MigrationState {
     bool send_configuration;
     /* Whether we send section footer during migration */
     bool send_section_footer;
+    /*
+     * Whether we allow break sending huge pages when postcopy preempt is
+     * enabled.  When disabled, we won't interrupt precopy within sending a
+     * host huge page, which is the old behavior of vanilla postcopy.
+     * NOTE: this parameter is ignored if postcopy preempt is not enabled.
+     */
+    bool postcopy_preempt_break_huge;
 
     /* Needed by postcopy-pause state */
     QemuSemaphore postcopy_pause_sem;
@@ -400,6 +441,7 @@ int migrate_decompress_threads(void);
 bool migrate_use_events(void);
 bool migrate_postcopy_blocktime(void);
 bool migrate_background_snapshot(void);
+bool migrate_postcopy_preempt(void);
 
 /* Sending on the return path - generic and then for each message type */
 void migrate_send_rp_shut(MigrationIncomingState *mis,