Merge tag 'migration-20230206-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request

In this try
- rebase to latest upstream
- same than previous patch
- fix compilation on non linux (userfaultfd.h) (me)
- query-migrationthreads (jiang)
- fix race on reading MultiFDPages_t.block (zhenzhong)
- fix flush of zero copy page send reuest  (zhenzhong)

Please apply.

Previous try:
It includes:
- David Hildenbrand fixes for virtio-men
- David Gilbert canary to detect problems
- Fix for rdma return values (Fiona)
- Peter Xu uffd_open fixes
- Peter Xu show right downtime for postcopy
- manish.mishra msg fix fixes
- my vfio changes.

Please apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmPhobYACgkQ9IfvGFhy
# 1yMNaA/9EHDPqrI1HL/VkJG4nNOOsQR7RbburXEberZOzvLjnqpjUD3Ls9qV6rx+
# ieHa5T4imYJFk72Wa5vx4r1/dCjtJD2W6jg5+/0nTvYAHrs1U1VRqpuTr0HiXdbJ
# ZLLCnW5eDyO3eMaOX0MUkgHgL0FNkc/Lq5ViCTFsMu9O9xMuDLLdAC3cdvslKuOu
# X1gKByr9jT817Y9e36amYmRaJKC6Cr/PIekNVFu12HBW79pPusLX8KWEf4RBw4HR
# sPwTvMCR/BwZ0+2Lppan60G5rt/ZxDu40oU7y+RHlfWqevl4hDM84/nhjMvEgzc5
# a4Ahe2ERGLwwnC8z3l7v9+pEzSGzDoPcnRGvZcpUpk68wTDtxd5Bdq8CwmNUfL07
# VzWcYpH0yvmwjBba9jfn9fAVgnG5rVp558XcYLIII3wEToty3UDtm43wSdj2CGr6
# cu+IPAp+n/I5G9SRYBTU9ozJz45ttnEe0hxUtZ4I3MuhzHi1VEDAqTWM/X0LyS41
# TB3Y5B2KKpJYbPyZEH4nyTeetR2k7alTFzahCgKqVfOgL0nJx54petjS1K+B1P72
# g6lhP9WnQ33W+M8S7J/aGEaDJd1lFyFB2Rdjn2ZZnASH/fR9j0mFmXWvulXtjFNp
# Sfim3887+Iv4Uzw4VWEe3mM5Ypi/Ba2CmuTjy/pM08Ey8X1Qs5o=
# =ZQbR
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 07 Feb 2023 00:56:22 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-20230206-pull-request' of https://gitlab.com/juan.quintela/qemu: (30 commits)
  migration: save/delete migration thread info
  migration: Introduce interface query-migrationthreads
  multifd: Fix flush of zero copy page send request
  multifd: Fix a race on reading MultiFDPages_t.block
  migration: check magic value for deciding the mapping of channels
  io: Add support for MSG_PEEK for socket channel
  migration/dirtyrate: Show sample pages only in page-sampling mode
  migration: Perform vmsd structure check during tests
  migration: Add canary to VMSTATE_END_OF_LIST
  migration/rdma: fix return value for qio_channel_rdma_{readv,writev}
  migration: Show downtime during postcopy phase
  virtio-mem: Proper support for preallocation with migration
  virtio-mem: Migrate immutable properties early
  virtio-mem: Fail if a memory backend with "prealloc=on" is specified
  migration/ram: Factor out check for advised postcopy
  migration/vmstate: Introduce VMSTATE_WITH_TMP_TEST() and VMSTATE_BITMAP_TEST()
  migration/savevm: Allow immutable device state to be migrated early (i.e., before RAM)
  migration/savevm: Prepare vmdesc json writer in qemu_savevm_state_setup()
  migration/savevm: Move more savevm handling into vmstate_save()
  migration/ram: Optimize ram_write_tracking_start() for RamDiscardManager
  ...

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

5 files changed, 162 insertions, 19 deletions

diff --git a/hw/core/machine.c b/hw/core/machine.c
index f7761ba..b5cd42c 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -41,7 +41,9 @@
 #include "hw/virtio/virtio-pci.h"
 #include "qom/object_interfaces.h"
 
-GlobalProperty hw_compat_7_2[] = {};
+GlobalProperty hw_compat_7_2[] = {
+    { "virtio-mem", "x-early-migration", "false" },
+};
 const size_t hw_compat_7_2_len = G_N_ELEMENTS(hw_compat_7_2);
 
 GlobalProperty hw_compat_7_1[] = {
diff --git a/hw/s390x/s390-stattrib.c b/hw/s390x/s390-stattrib.c
index 9eda1c3..3e32002 100644
--- a/hw/s390x/s390-stattrib.c
+++ b/hw/s390x/s390-stattrib.c
@@ -182,10 +182,10 @@ static int cmma_save_setup(QEMUFile *f, void *opaque)
     return 0;
 }
 
-static void cmma_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
-                              uint64_t *res_precopy_only,
-                              uint64_t *res_compatible,
-                              uint64_t *res_postcopy_only)
+static void cmma_state_pending(void *opaque,
+                               uint64_t *res_precopy_only,
+                               uint64_t *res_compatible,
+                               uint64_t *res_postcopy_only)
 {
     S390StAttribState *sas = S390_STATTRIB(opaque);
     S390StAttribClass *sac = S390_STATTRIB_GET_CLASS(sas);
@@ -371,7 +371,8 @@ static SaveVMHandlers savevm_s390_stattrib_handlers = {
     .save_setup = cmma_save_setup,
     .save_live_iterate = cmma_save_iterate,
     .save_live_complete_precopy = cmma_save_complete,
-    .save_live_pending = cmma_save_pending,
+    .state_pending_exact = cmma_state_pending,
+    .state_pending_estimate = cmma_state_pending,
     .save_cleanup = cmma_save_cleanup,
     .load_state = cmma_load,
     .is_active = cmma_active,
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index c74453e..b3318f0 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -456,11 +456,10 @@ static void vfio_save_cleanup(void *opaque)
     trace_vfio_save_cleanup(vbasedev->name);
 }
 
-static void vfio_save_pending(QEMUFile *f, void *opaque,
-                              uint64_t threshold_size,
-                              uint64_t *res_precopy_only,
-                              uint64_t *res_compatible,
-                              uint64_t *res_postcopy_only)
+static void vfio_state_pending(void *opaque,
+                               uint64_t *res_precopy_only,
+                               uint64_t *res_compatible,
+                               uint64_t *res_postcopy_only)
 {
     VFIODevice *vbasedev = opaque;
     VFIOMigration *migration = vbasedev->migration;
@@ -473,7 +472,7 @@ static void vfio_save_pending(QEMUFile *f, void *opaque,
 
     *res_precopy_only += migration->pending_bytes;
 
-    trace_vfio_save_pending(vbasedev->name, *res_precopy_only,
+    trace_vfio_state_pending(vbasedev->name, *res_precopy_only,
                             *res_postcopy_only, *res_compatible);
 }
 
@@ -515,9 +514,9 @@ static int vfio_save_iterate(QEMUFile *f, void *opaque)
     }
 
     /*
-     * Reset pending_bytes as .save_live_pending is not called during savevm or
-     * snapshot case, in such case vfio_update_pending() at the start of this
-     * function updates pending_bytes.
+     * Reset pending_bytes as state_pending* are not called during
+     * savevm or snapshot case, in such case vfio_update_pending() at
+     * the start of this function updates pending_bytes.
      */
     migration->pending_bytes = 0;
     trace_vfio_save_iterate(vbasedev->name, data_size);
@@ -685,7 +684,8 @@ static int vfio_load_state(QEMUFile *f, void *opaque, int version_id)
 static SaveVMHandlers savevm_vfio_handlers = {
     .save_setup = vfio_save_setup,
     .save_cleanup = vfio_save_cleanup,
-    .save_live_pending = vfio_save_pending,
+    .state_pending_exact = vfio_state_pending,
+    .state_pending_estimate = vfio_state_pending,
     .save_live_iterate = vfio_save_iterate,
     .save_live_complete_precopy = vfio_save_complete_precopy,
     .save_state = vfio_save_state,
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 73dffe9..52de1c8 100644
--- a/hw/vfio/trace-events
+++ b/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_save_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, uint64_t compatible) " (%s) precopy 0x%"PRIx64" postcopy 0x%"PRIx64" compatible 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)"
diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index 1ed1f5a..957fe77 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -31,6 +31,8 @@
 #include CONFIG_DEVICES
 #include "trace.h"
 
+static const VMStateDescription vmstate_virtio_mem_device_early;
+
 /*
  * We only had legacy x86 guests that did not support
  * VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE. Other targets don't have legacy guests.
@@ -202,6 +204,30 @@ static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg,
     return ret;
 }
 
+static int virtio_mem_for_each_plugged_range(const VirtIOMEM *vmem, void *arg,
+                                             virtio_mem_range_cb cb)
+{
+    unsigned long first_bit, last_bit;
+    uint64_t offset, size;
+    int ret = 0;
+
+    first_bit = find_first_bit(vmem->bitmap, vmem->bitmap_size);
+    while (first_bit < vmem->bitmap_size) {
+        offset = first_bit * vmem->block_size;
+        last_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size,
+                                      first_bit + 1) - 1;
+        size = (last_bit - first_bit + 1) * vmem->block_size;
+
+        ret = cb(vmem, arg, offset, size);
+        if (ret) {
+            break;
+        }
+        first_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size,
+                                  last_bit + 2);
+    }
+    return ret;
+}
+
 /*
  * Adjust the memory section to cover the intersection with the given range.
  *
@@ -772,6 +798,12 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
         error_setg(errp, "'%s' property specifies an unsupported memdev",
                    VIRTIO_MEM_MEMDEV_PROP);
         return;
+    } else if (vmem->memdev->prealloc) {
+        error_setg(errp, "'%s' property specifies a memdev with preallocation"
+                   " enabled: %s. Instead, specify 'prealloc=on' for the"
+                   " virtio-mem device. ", VIRTIO_MEM_MEMDEV_PROP,
+                   object_get_canonical_path_component(OBJECT(vmem->memdev)));
+        return;
     }
 
     if ((nb_numa_nodes && vmem->node >= nb_numa_nodes) ||
@@ -872,6 +904,10 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
 
     host_memory_backend_set_mapped(vmem->memdev, true);
     vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem));
+    if (vmem->early_migration) {
+        vmstate_register(VMSTATE_IF(vmem), VMSTATE_INSTANCE_ID_ANY,
+                         &vmstate_virtio_mem_device_early, vmem);
+    }
     qemu_register_reset(virtio_mem_system_reset, vmem);
 
     /*
@@ -893,6 +929,10 @@ static void virtio_mem_device_unrealize(DeviceState *dev)
      */
     memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL);
     qemu_unregister_reset(virtio_mem_system_reset, vmem);
+    if (vmem->early_migration) {
+        vmstate_unregister(VMSTATE_IF(vmem), &vmstate_virtio_mem_device_early,
+                           vmem);
+    }
     vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem));
     host_memory_backend_set_mapped(vmem->memdev, false);
     virtio_del_queue(vdev, 0);
@@ -922,6 +962,10 @@ static int virtio_mem_post_load(void *opaque, int version_id)
     RamDiscardListener *rdl;
     int ret;
 
+    if (vmem->prealloc && !vmem->early_migration) {
+        warn_report("Proper preallocation with migration requires a newer QEMU machine");
+    }
+
     /*
      * We started out with all memory discarded and our memory region is mapped
      * into an address space. Replay, now that we updated the bitmap.
@@ -941,6 +985,64 @@ static int virtio_mem_post_load(void *opaque, int version_id)
     return virtio_mem_restore_unplugged(vmem);
 }
 
+static int virtio_mem_prealloc_range_cb(const VirtIOMEM *vmem, void *arg,
+                                        uint64_t offset, uint64_t size)
+{
+    void *area = memory_region_get_ram_ptr(&vmem->memdev->mr) + offset;
+    int fd = memory_region_get_fd(&vmem->memdev->mr);
+    Error *local_err = NULL;
+
+    qemu_prealloc_mem(fd, area, size, 1, NULL, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -ENOMEM;
+    }
+    return 0;
+}
+
+static int virtio_mem_post_load_early(void *opaque, int version_id)
+{
+    VirtIOMEM *vmem = VIRTIO_MEM(opaque);
+    RAMBlock *rb = vmem->memdev->mr.ram_block;
+    int ret;
+
+    if (!vmem->prealloc) {
+        return 0;
+    }
+
+    /*
+     * We restored the bitmap and verified that the basic properties
+     * match on source and destination, so we can go ahead and preallocate
+     * memory for all plugged memory blocks, before actual RAM migration starts
+     * touching this memory.
+     */
+    ret = virtio_mem_for_each_plugged_range(vmem, NULL,
+                                            virtio_mem_prealloc_range_cb);
+    if (ret) {
+        return ret;
+    }
+
+    /*
+     * This is tricky: postcopy wants to start with a clean slate. On
+     * POSTCOPY_INCOMING_ADVISE, postcopy code discards all (ordinarily
+     * preallocated) RAM such that postcopy will work as expected later.
+     *
+     * However, we run after POSTCOPY_INCOMING_ADVISE -- but before actual
+     * RAM migration. So let's discard all memory again. This looks like an
+     * expensive NOP, but actually serves a purpose: we made sure that we
+     * were able to allocate all required backend memory once. We cannot
+     * guarantee that the backend memory we will free will remain free
+     * until we need it during postcopy, but at least we can catch the
+     * obvious setup issues this way.
+     */
+    if (migration_incoming_postcopy_advised()) {
+        if (ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb))) {
+            return -EBUSY;
+        }
+    }
+    return 0;
+}
+
 typedef struct VirtIOMEMMigSanityChecks {
     VirtIOMEM *parent;
     uint64_t addr;
@@ -1009,6 +1111,14 @@ static const VMStateDescription vmstate_virtio_mem_sanity_checks = {
     },
 };
 
+static bool virtio_mem_vmstate_field_exists(void *opaque, int version_id)
+{
+    const VirtIOMEM *vmem = VIRTIO_MEM(opaque);
+
+    /* With early migration, these fields were already migrated. */
+    return !vmem->early_migration;
+}
+
 static const VMStateDescription vmstate_virtio_mem_device = {
     .name = "virtio-mem-device",
     .minimum_version_id = 1,
@@ -1016,11 +1126,39 @@ static const VMStateDescription vmstate_virtio_mem_device = {
     .priority = MIG_PRI_VIRTIO_MEM,
     .post_load = virtio_mem_post_load,
     .fields = (VMStateField[]) {
+        VMSTATE_WITH_TMP_TEST(VirtIOMEM, virtio_mem_vmstate_field_exists,
+                              VirtIOMEMMigSanityChecks,
+                              vmstate_virtio_mem_sanity_checks),
+        VMSTATE_UINT64(usable_region_size, VirtIOMEM),
+        VMSTATE_UINT64_TEST(size, VirtIOMEM, virtio_mem_vmstate_field_exists),
+        VMSTATE_UINT64(requested_size, VirtIOMEM),
+        VMSTATE_BITMAP_TEST(bitmap, VirtIOMEM, virtio_mem_vmstate_field_exists,
+                            0, bitmap_size),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+/*
+ * Transfer properties that are immutable while migration is active early,
+ * such that we have have this information around before migrating any RAM
+ * content.
+ *
+ * Note that virtio_mem_is_busy() makes sure these properties can no longer
+ * change on the migration source until migration completed.
+ *
+ * With QEMU compat machines, we transmit these properties later, via
+ * vmstate_virtio_mem_device instead -- see virtio_mem_vmstate_field_exists().
+ */
+static const VMStateDescription vmstate_virtio_mem_device_early = {
+    .name = "virtio-mem-device-early",
+    .minimum_version_id = 1,
+    .version_id = 1,
+    .early_setup = true,
+    .post_load = virtio_mem_post_load_early,
+    .fields = (VMStateField[]) {
         VMSTATE_WITH_TMP(VirtIOMEM, VirtIOMEMMigSanityChecks,
                          vmstate_virtio_mem_sanity_checks),
-        VMSTATE_UINT64(usable_region_size, VirtIOMEM),
         VMSTATE_UINT64(size, VirtIOMEM),
-        VMSTATE_UINT64(requested_size, VirtIOMEM),
         VMSTATE_BITMAP(bitmap, VirtIOMEM, 0, bitmap_size),
         VMSTATE_END_OF_LIST()
     },
@@ -1205,6 +1343,8 @@ static Property virtio_mem_properties[] = {
     DEFINE_PROP_ON_OFF_AUTO(VIRTIO_MEM_UNPLUGGED_INACCESSIBLE_PROP, VirtIOMEM,
                             unplugged_inaccessible, ON_OFF_AUTO_AUTO),
 #endif
+    DEFINE_PROP_BOOL(VIRTIO_MEM_EARLY_MIGRATION_PROP, VirtIOMEM,
+                     early_migration, true),
     DEFINE_PROP_END_OF_LIST(),
 };