Merge tag 'migration-20230215-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request

This pull request contains:

* Add qemu_file_get_to_fd() a.k.a. make vfio happy(Avihai)
* migration/block is now DPRINTF() free zone (Philippe)
* remove res_compat and improve docs (me)

Please apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmPtOxgACgkQ9IfvGFhy
# 1yM+8w/+Nrm40o8B+0M1X/2O8SPaXE0Oxll5qk5AgfC+2Ef/n5661ZzOM1xQcqzv
# CN3bj3g7dKN05nGhqW5ZFrEZliJCGksx2FBKMq9H6R5YBSMo/+GHT4ugPqsujudl
# RBafIHzp4h4nTh/4aJ4Kr2Vn/bVQzGVyv5c6yUdUhKhE1QfCLu9AMC5vN1hfWxBz
# IQBvMkLNXXhWOTdkVAElVlFOM6GZzWb1UYDkBaQHjjw/dN0MdCFFj7tIaBIyU2Eb
# KyQCoYeJjjWrljsrfzfCucrW+mbVGmCe1TiCEnaAmmgzOI0NwARmUcdYdCyZ4Nhh
# flNjpqQB6H4/ekI0mus2YPMPEkHyVgBMuF8fHV3YDwxcQ25U39RLymVfAoKPNg88
# S1EcQ9h2QVqdML7bR9vTmPOZKk5vD25H7B8LQIJpT8PHVg3ZzzRaOIR8UHmmFXx/
# PSL1rGfPcCLJ3P1XlVjwBApebMHyid9c+Sohda9L9HPer0jlB+mGQUEV8J67DJiT
# xlffFgJmYu3+AJu9BoqrG0AUW6zA78jSs4Tbp78qbIVA4uzGkWI9JvROMfG9Qcc7
# vruuL0sUXHVUhzW2F+0M+b1rVhaHHQYvFo3mIqdHrd5mGicdgh1HUbaJuEJxeJnh
# oFt6SZbIx3N/pllcvMsxQa+rFI/po+FEkRwIF02SzTRWYHB0qos=
# =KpKO
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 15 Feb 2023 20:05:44 GMT
# 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-20230215-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: Rename res_{postcopy,precopy}_only
  migration: Remove unused res_compatible
  migration: In case of postcopy, the memory ends in res_postcopy_only
  migration/block: Convert remaining DPRINTF() debug macro to trace events
  migration/qemu-file: Add qemu_file_get_to_fd()

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

hw/s390x/s390-stattrib.c

@@ -182,17 +182,15 @@ static int cmma_save_setup(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void cmma_state_pending(void *opaque,
-                               uint64_t *res_precopy_only,
-                               uint64_t *res_compatible,
-                               uint64_t *res_postcopy_only)
+static void cmma_state_pending(void *opaque, uint64_t *must_precopy,
+                               uint64_t *can_postcopy)
 {
     S390StAttribState *sas = S390_STATTRIB(opaque);
     S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
     long long res = sac->get_dirtycount(sas);
 
     if (res >= 0) {
-        *res_precopy_only += res;
+        *must_precopy += res;
     }
 }
 

hw/vfio/migration.c

@@ -456,10 +456,8 @@ static void vfio_save_cleanup(void *opaque)
     trace_vfio_save_cleanup(vbasedev->name);
 }
 
-static void vfio_state_pending(void *opaque,
-                               uint64_t *res_precopy_only,
-                               uint64_t *res_compatible,
-                               uint64_t *res_postcopy_only)
+static void vfio_state_pending(void *opaque, uint64_t *must_precopy,
+                               uint64_t *can_postcopy)
 {
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
@@ -470,10 +468,9 @@ static void vfio_state_pending(void *opaque,
         return;
     }
 
-    *res_precopy_only += migration->pending_bytes;
+    *must_precopy += migration->pending_bytes;
 
-    trace_vfio_state_pending(vbasedev->name, *res_precopy_only,
-                            *res_postcopy_only, *res_compatible);
+    trace_vfio_state_pending(vbasedev->name, *must_precopy, *can_postcopy);
 }
 
 static int vfio_save_iterate(QEMUFile *f, void *opaque)

hw/vfio/trace-events

@@ -157,7 +157,7 @@ vfio_save_cleanup(const char *name) " (%s)"
 vfio_save_buffer(const char *name, uint64_t data_offset, uint64_t data_size, uint64_t pending) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64" pending 0x%"PRIx64
 vfio_update_pending(const char *name, uint64_t pending) " (%s) pending 0x%"PRIx64
 vfio_save_device_config_state(const char *name) " (%s)"
-vfio_state_pending(const char *name, uint64_t precopy, uint64_t postcopy, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 0x%"PRIx64
+vfio_state_pending(const char *name, uint64_t precopy, uint64_t postcopy) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64
 vfio_save_iterate(const char *name, int data_size) " (%s) data_size %d"
 vfio_save_complete_precopy(const char *name) " (%s)"
 vfio_load_device_config_state(const char *name) " (%s)"

include/migration/register.h

@@ -47,25 +47,25 @@ typedef struct SaveVMHandlers {
     /* This runs outside the iothread lock!  */
     int (*save_setup)(QEMUFile *f, void *opaque);
     /* Note for save_live_pending:
-     * - res_precopy_only is for data which must be migrated in precopy phase
-     *     or in stopped state, in other words - before target vm start
-     * - res_compatible is for data which may be migrated in any phase
-     * - res_postcopy_only is for data which must be migrated in postcopy phase
-     *     or in stopped state, in other words - after source vm stop
+     * must_precopy:
+     * - must be migrated in precopy or in stopped state
+     * - i.e. must be migrated before target start
      *
-     * Sum of res_postcopy_only, res_compatible and res_postcopy_only is the
-     * whole amount of pending data.
+     * can_postcopy:
+     * - can migrate in postcopy or in stopped state
+     * - i.e. can migrate after target start
+     * - some can also be migrated during precopy (RAM)
+     * - some must be migrated after source stops (block-dirty-bitmap)
+     *
+     * Sum of can_postcopy and must_postcopy is the whole amount of
+     * pending data.
      */
     /* This estimates the remaining data to transfer */
-    void (*state_pending_estimate)(void *opaque,
-                                   uint64_t *res_precopy_only,
-                                   uint64_t *res_compatible,
-                                   uint64_t *res_postcopy_only);
+    void (*state_pending_estimate)(void *opaque, uint64_t *must_precopy,
+                                   uint64_t *can_postcopy);
     /* This calculate the exact remaining data to transfer */
-    void (*state_pending_exact)(void *opaque,
-                                uint64_t *res_precopy_only,
-                                uint64_t *res_compatible,
-                                uint64_t *res_postcopy_only);
+    void (*state_pending_exact)(void *opaque, uint64_t *must_precopy,
+                                uint64_t *can_postcopy);
     LoadStateHandler *load_state;
     int (*load_setup)(QEMUFile *f, void *opaque);
     int (*load_cleanup)(void *opaque);

migration/block-dirty-bitmap.c

@@ -763,9 +763,8 @@ static int dirty_bitmap_save_complete(QEMUFile *f, void *opaque)
 }
 
 static void dirty_bitmap_state_pending(void *opaque,
-                                       uint64_t *res_precopy_only,
-                                       uint64_t *res_compatible,
-                                       uint64_t *res_postcopy_only)
+                                       uint64_t *must_precopy,
+                                       uint64_t *can_postcopy)
 {
     DBMSaveState *s = &((DBMState *)opaque)->save;
     SaveBitmapState *dbms;
@@ -785,7 +784,7 @@ static void dirty_bitmap_state_pending(void *opaque,
 
     trace_dirty_bitmap_state_pending(pending);
 
-    *res_postcopy_only += pending;
+    *can_postcopy += pending;
 }
 
 /* First occurrence of this bitmap. It should be created if doesn't exist */

migration/block.c

@@ -42,16 +42,6 @@
 #define MAX_IO_BUFFERS 512
 #define MAX_PARALLEL_IO 16
 
-/* #define DEBUG_BLK_MIGRATION */
-
-#ifdef DEBUG_BLK_MIGRATION
-#define DPRINTF(fmt, ...) \
-    do { printf("blk_migration: " fmt, ## __VA_ARGS__); } while (0)
-#else
-#define DPRINTF(fmt, ...) \
-    do { } while (0)
-#endif
-
 typedef struct BlkMigDevState {
     /* Written during setup phase.  Can be read without a lock.  */
     BlockBackend *blk;
@@ -502,7 +492,7 @@ static int blk_mig_save_bulked_block(QEMUFile *f)
         block_mig_state.prev_progress = progress;
         qemu_put_be64(f, (progress << BDRV_SECTOR_BITS)
                          | BLK_MIG_FLAG_PROGRESS);
-        DPRINTF("Completed %d %%\r", progress);
+        trace_migration_block_progression(progress);
     }
 
     return ret;
@@ -863,10 +853,8 @@ static int block_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void block_state_pending(void *opaque,
-                                uint64_t *res_precopy_only,
-                                uint64_t *res_compatible,
-                                uint64_t *res_postcopy_only)
+static void block_state_pending(void *opaque, uint64_t *must_precopy,
+                                uint64_t *can_postcopy)
 {
     /* Estimate pending number of bytes to send */
     uint64_t pending;
@@ -887,7 +875,7 @@ static void block_state_pending(void *opaque,
 
     trace_migration_block_state_pending(pending);
     /* We don't do postcopy */
-    *res_precopy_only += pending;
+    *must_precopy += pending;
 }
 
 static int block_load(QEMUFile *f, void *opaque, int version_id)

migration/migration.c

@@ -3863,20 +3863,18 @@ typedef enum {
  */
 static MigIterateState migration_iteration_run(MigrationState *s)
 {
-    uint64_t pend_pre, pend_compat, pend_post;
+    uint64_t must_precopy, can_postcopy;
     bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE;
 
-    qemu_savevm_state_pending_estimate(&pend_pre, &pend_compat, &pend_post);
-    uint64_t pending_size = pend_pre + pend_compat + pend_post;
+    qemu_savevm_state_pending_estimate(&must_precopy, &can_postcopy);
+    uint64_t pending_size = must_precopy + can_postcopy;
 
-    trace_migrate_pending_estimate(pending_size,
-                                   pend_pre, pend_compat, pend_post);
+    trace_migrate_pending_estimate(pending_size, must_precopy, can_postcopy);
 
-    if (pend_pre + pend_compat <= s->threshold_size) {
-        qemu_savevm_state_pending_exact(&pend_pre, &pend_compat, &pend_post);
-        pending_size = pend_pre + pend_compat + pend_post;
-        trace_migrate_pending_exact(pending_size,
-                                    pend_pre, pend_compat, pend_post);
+    if (must_precopy <= s->threshold_size) {
+        qemu_savevm_state_pending_exact(&must_precopy, &can_postcopy);
+        pending_size = must_precopy + can_postcopy;
+        trace_migrate_pending_exact(pending_size, must_precopy, can_postcopy);
     }
 
     if (!pending_size || pending_size < s->threshold_size) {
@@ -3886,7 +3884,7 @@ static MigIterateState migration_iteration_run(MigrationState *s)
     }
 
     /* Still a significant amount to transfer */
-    if (!in_postcopy && pend_pre <= s->threshold_size &&
+    if (!in_postcopy && must_precopy <= s->threshold_size &&
         qatomic_read(&s->start_postcopy)) {
         if (postcopy_start(s)) {
             error_report("%s: postcopy failed to start", __func__);

migration/qemu-file.c

@@ -940,3 +940,37 @@ QIOChannel *qemu_file_get_ioc(QEMUFile *file)
 {
     return file->ioc;
 }
+
+/*
+ * Read size bytes from QEMUFile f and write them to fd.
+ */
+int qemu_file_get_to_fd(QEMUFile *f, int fd, size_t size)
+{
+    while (size) {
+        size_t pending = f->buf_size - f->buf_index;
+        ssize_t rc;
+
+        if (!pending) {
+            rc = qemu_fill_buffer(f);
+            if (rc < 0) {
+                return rc;
+            }
+            if (rc == 0) {
+                return -EIO;
+            }
+            continue;
+        }
+
+        rc = write(fd, f->buf + f->buf_index, MIN(pending, size));
+        if (rc < 0) {
+            return -errno;
+        }
+        if (rc == 0) {
+            return -EIO;
+        }
+        f->buf_index += rc;
+        size -= rc;
+    }
+
+    return 0;
+}

migration/qemu-file.h

@@ -148,6 +148,7 @@ int qemu_file_shutdown(QEMUFile *f);
 QEMUFile *qemu_file_get_return_path(QEMUFile *f);
 void qemu_fflush(QEMUFile *f);
 void qemu_file_set_blocking(QEMUFile *f, bool block);
+int qemu_file_get_to_fd(QEMUFile *f, int fd, size_t size);
 
 void ram_control_before_iterate(QEMUFile *f, uint64_t flags);
 void ram_control_after_iterate(QEMUFile *f, uint64_t flags);

migration/ram.c

@@ -3489,10 +3489,8 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void ram_state_pending_estimate(void *opaque,
-                                       uint64_t *res_precopy_only,
-                                       uint64_t *res_compatible,
-                                       uint64_t *res_postcopy_only)
+static void ram_state_pending_estimate(void *opaque, uint64_t *must_precopy,
+                                       uint64_t *can_postcopy)
 {
     RAMState **temp = opaque;
     RAMState *rs = *temp;
@@ -3501,16 +3499,14 @@ static void ram_state_pending_estimate(void *opaque,
 
     if (migrate_postcopy_ram()) {
         /* We can do postcopy, and all the data is postcopiable */
-        *res_postcopy_only += remaining_size;
+        *can_postcopy += remaining_size;
     } else {
-        *res_precopy_only += remaining_size;
+        *must_precopy += remaining_size;
     }
 }
 
-static void ram_state_pending_exact(void *opaque,
-                                    uint64_t *res_precopy_only,
-                                    uint64_t *res_compatible,
-                                    uint64_t *res_postcopy_only)
+static void ram_state_pending_exact(void *opaque, uint64_t *must_precopy,
+                                    uint64_t *can_postcopy)
 {
     RAMState **temp = opaque;
     RAMState *rs = *temp;
@@ -3528,9 +3524,9 @@ static void ram_state_pending_exact(void *opaque,
 
     if (migrate_postcopy_ram()) {
         /* We can do postcopy, and all the data is postcopiable */
-        *res_compatible += remaining_size;
+        *can_postcopy += remaining_size;
     } else {
-        *res_precopy_only += remaining_size;
+        *must_precopy += remaining_size;
     }
 }
 

migration/savevm.c

@@ -1541,15 +1541,13 @@ flush:
  * the result is split into the amount for units that can and
  * for units that can't do postcopy.
  */
-void qemu_savevm_state_pending_estimate(uint64_t *res_precopy_only,
-                                        uint64_t *res_compatible,
-                                        uint64_t *res_postcopy_only)
+void qemu_savevm_state_pending_estimate(uint64_t *must_precopy,
+                                        uint64_t *can_postcopy)
 {
     SaveStateEntry *se;
 
-    *res_precopy_only = 0;
-    *res_compatible = 0;
-    *res_postcopy_only = 0;
+    *must_precopy = 0;
+    *can_postcopy = 0;
 
     QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
         if (!se->ops || !se->ops->state_pending_estimate) {
@@ -1560,21 +1558,17 @@ void qemu_savevm_state_pending_estimate(uint64_t *res_precopy_only,
                 continue;
             }
         }
-        se->ops->state_pending_estimate(se->opaque,
-                                        res_precopy_only, res_compatible,
-                                        res_postcopy_only);
+        se->ops->state_pending_estimate(se->opaque, must_precopy, can_postcopy);
     }
 }
 
-void qemu_savevm_state_pending_exact(uint64_t *res_precopy_only,
-                                     uint64_t *res_compatible,
-                                     uint64_t *res_postcopy_only)
+void qemu_savevm_state_pending_exact(uint64_t *must_precopy,
+                                     uint64_t *can_postcopy)
 {
     SaveStateEntry *se;
 
-    *res_precopy_only = 0;
-    *res_compatible = 0;
-    *res_postcopy_only = 0;
+    *must_precopy = 0;
+    *can_postcopy = 0;
 
     QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
         if (!se->ops || !se->ops->state_pending_exact) {
@@ -1585,9 +1579,7 @@ void qemu_savevm_state_pending_exact(uint64_t *res_precopy_only,
                 continue;
             }
         }
-        se->ops->state_pending_exact(se->opaque,
-                                     res_precopy_only, res_compatible,
-                                     res_postcopy_only);
+        se->ops->state_pending_exact(se->opaque, must_precopy, can_postcopy);
     }
 }
 

migration/savevm.h

@@ -40,12 +40,10 @@ void qemu_savevm_state_cleanup(void);
 void qemu_savevm_state_complete_postcopy(QEMUFile *f);
 int qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only,
                                        bool inactivate_disks);
-void qemu_savevm_state_pending_exact(uint64_t *res_precopy_only,
-                                     uint64_t *res_compatible,
-                                     uint64_t *res_postcopy_only);
-void qemu_savevm_state_pending_estimate(uint64_t *res_precopy_only,
-                                        uint64_t *res_compatible,
-                                        uint64_t *res_postcopy_only);
+void qemu_savevm_state_pending_exact(uint64_t *must_precopy,
+                                     uint64_t *can_postcopy);
+void qemu_savevm_state_pending_estimate(uint64_t *must_precopy,
+                                        uint64_t *can_postcopy);
 void qemu_savevm_send_ping(QEMUFile *f, uint32_t value);
 void qemu_savevm_send_open_return_path(QEMUFile *f);
 int qemu_savevm_send_packaged(QEMUFile *f, const uint8_t *buf, size_t len);

migration/trace-events

@@ -150,8 +150,8 @@ migrate_fd_cleanup(void) ""
 migrate_fd_error(const char *error_desc) "error=%s"
 migrate_fd_cancel(void) ""
 migrate_handle_rp_req_pages(const char *rbname, size_t start, size_t len) "in %s at 0x%zx len 0x%zx"
-migrate_pending_exact(uint64_t size, uint64_t pre, uint64_t compat, uint64_t post) "exact pending size %" PRIu64 " (pre = %" PRIu64 " compat=%" PRIu64 " post=%" PRIu64 ")"
-migrate_pending_estimate(uint64_t size, uint64_t pre, uint64_t compat, uint64_t post) "estimate pending size %" PRIu64 " (pre = %" PRIu64 " compat=%" PRIu64 " post=%" PRIu64 ")"
+migrate_pending_exact(uint64_t size, uint64_t pre, uint64_t post) "exact pending size %" PRIu64 " (pre = %" PRIu64 " post=%" PRIu64 ")"
+migrate_pending_estimate(uint64_t size, uint64_t pre, uint64_t post) "estimate pending size %" PRIu64 " (pre = %" PRIu64 " post=%" PRIu64 ")"
 migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d"
 migrate_send_rp_recv_bitmap(char *name, int64_t size) "block '%s' size 0x%"PRIi64
 migration_completion_file_err(void) ""
@@ -357,6 +357,7 @@ migration_block_flush_blks(const char *action, int submitted, int read_done, int
 migration_block_save(const char *mig_stage, int submitted, int transferred) "Enter save live %s submitted %d transferred %d"
 migration_block_save_complete(void) "Block migration completed"
 migration_block_state_pending(uint64_t pending) "Enter save live pending  %" PRIu64
+migration_block_progression(unsigned percent) "Completed %u%%"
 
 # page_cache.c
 migration_pagecache_init(int64_t max_num_items) "Setting cache buckets to %" PRId64