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----- 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>
2023-02-07 15:16:51 +00:00 · 2023-02-07 15:16:51 +00:00 · b86307ecef
commit b86307ecef
parent 285ee77f5b 1b1f4ab69c
53 changed files with 2135 additions and 234 deletions
--- a/include/hw/virtio/virtio-mem.h
+++ b/include/hw/virtio/virtio-mem.h
@ -31,6 +31,7 @@ OBJECT_DECLARE_TYPE(VirtIOMEM, VirtIOMEMClass,
 #define VIRTIO_MEM_BLOCK_SIZE_PROP "block-size"
 #define VIRTIO_MEM_ADDR_PROP "memaddr"
 #define VIRTIO_MEM_UNPLUGGED_INACCESSIBLE_PROP "unplugged-inaccessible"
+#define VIRTIO_MEM_EARLY_MIGRATION_PROP "x-early-migration"
 #define VIRTIO_MEM_PREALLOC_PROP "prealloc"

 struct VirtIOMEM {
@ -74,6 +75,13 @@ struct VirtIOMEM {
    /* whether to prealloc memory when plugging new blocks */
    bool prealloc;

+    /*
+     * Whether we migrate properties that are immutable while migration is
+     * active early, before state of other devices and especially, before
+     * migrating any RAM content.
+     */
+    bool early_migration;
+
    /* notifiers to notify when "size" changes */
    NotifierList size_change_notifiers;

--- a/include/io/channel.h
+++ b/include/io/channel.h
@ -34,6 +34,8 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,

 #define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1

+#define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1
+
 typedef enum QIOChannelFeature QIOChannelFeature;

 enum QIOChannelFeature {
@ -41,6 +43,7 @@ enum QIOChannelFeature {
    QIO_CHANNEL_FEATURE_SHUTDOWN,
    QIO_CHANNEL_FEATURE_LISTEN,
    QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
+    QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
 };


@ -114,6 +117,7 @@ struct QIOChannelClass {
                        size_t niov,
                        int **fds,
                        size_t *nfds,
+                        int flags,
                        Error **errp);
    int (*io_close)(QIOChannel *ioc,
                    Error **errp);
@ -188,6 +192,7 @@ void qio_channel_set_name(QIOChannel *ioc,
 * @niov: the length of the @iov array
 * @fds: pointer to an array that will received file handles
 * @nfds: pointer filled with number of elements in @fds on return
+ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*)
 * @errp: pointer to a NULL-initialized error object
 *
 * Read data from the IO channel, storing it in the
@ -224,6 +229,7 @@ ssize_t qio_channel_readv_full(QIOChannel *ioc,
                               size_t niov,
                               int **fds,
                               size_t *nfds,
+                               int flags,
                               Error **errp);


--- a/include/migration/misc.h
+++ b/include/migration/misc.h
@ -67,8 +67,10 @@ bool migration_has_failed(MigrationState *);
 /* ...and after the device transmission */
 bool migration_in_postcopy_after_devices(MigrationState *);
 void migration_global_dump(Monitor *mon);
-/* True if incomming migration entered POSTCOPY_INCOMING_DISCARD */
+/* True if incoming migration entered POSTCOPY_INCOMING_DISCARD */
 bool migration_in_incoming_postcopy(void);
+/* True if incoming migration entered POSTCOPY_INCOMING_ADVISE */
+bool migration_incoming_postcopy_advised(void);
 /* True if background snapshot is active */
 bool migration_in_bg_snapshot(void);

--- a/include/migration/register.h
+++ b/include/migration/register.h
@ -46,11 +46,6 @@ typedef struct SaveVMHandlers {

    /* This runs outside the iothread lock!  */
    int (*save_setup)(QEMUFile *f, void *opaque);
-    void (*save_live_pending)(QEMUFile *f, void *opaque,
-                              uint64_t threshold_size,
-                              uint64_t *res_precopy_only,
-                              uint64_t *res_compatible,
-                              uint64_t *res_postcopy_only);
    /* 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
@ -61,8 +56,16 @@ typedef struct SaveVMHandlers {
     * Sum of res_postcopy_only, res_compatible and res_postcopy_only 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);
+    /* 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);
    LoadStateHandler *load_state;
    int (*load_setup)(QEMUFile *f, void *opaque);
    int (*load_cleanup)(void *opaque);
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@ -147,6 +147,9 @@ enum VMStateFlags {
     * VMStateField.struct_version_id to tell which version of the
     * structure we are referencing to use. */
    VMS_VSTRUCT           = 0x8000,
+
+    /* Marker for end of list */
+    VMS_END = 0x10000
 };

 typedef enum {
@ -178,7 +181,21 @@ struct VMStateField {

 struct VMStateDescription {
    const char *name;
-    int unmigratable;
+    bool unmigratable;
+    /*
+     * This VMSD describes something that should be sent during setup phase
+     * of migration. It plays similar role as save_setup() for explicitly
+     * registered vmstate entries, so it can be seen as a way to describe
+     * save_setup() in VMSD structures.
+     *
+     * Note that for now, a SaveStateEntry cannot have a VMSD and
+     * operations (e.g., save_setup()) set at the same time. Consequently,
+     * save_setup() and a VMSD with early_setup set to true are mutually
+     * exclusive. For this reason, also early_setup VMSDs are migrated in a
+     * QEMU_VM_SECTION_FULL section, while save_setup() data is migrated in
+     * a QEMU_VM_SECTION_START section.
+     */
+    bool early_setup;
    int version_id;
    int minimum_version_id;
    MigrationPriority priority;
@ -705,8 +722,9 @@ extern const VMStateInfo vmstate_info_qlist;
 *        '_state' type
 *    That the pointer is right at the start of _tmp_type.
 */
-#define VMSTATE_WITH_TMP(_state, _tmp_type, _vmsd) {                 \
+#define VMSTATE_WITH_TMP_TEST(_state, _test, _tmp_type, _vmsd) {     \
    .name         = "tmp",                                           \
+    .field_exists = (_test),                                         \
    .size         = sizeof(_tmp_type) +                              \
                    QEMU_BUILD_BUG_ON_ZERO(offsetof(_tmp_type, parent) != 0) + \
                    type_check_pointer(_state,                       \
@ -715,6 +733,9 @@ extern const VMStateInfo vmstate_info_qlist;
    .info         = &vmstate_info_tmp,                               \
 }

+#define VMSTATE_WITH_TMP(_state, _tmp_type, _vmsd) \
+    VMSTATE_WITH_TMP_TEST(_state, NULL, _tmp_type, _vmsd)
+
 #define VMSTATE_UNUSED_BUFFER(_test, _version, _size) {              \
    .name         = "unused",                                        \
    .field_exists = (_test),                                         \
@ -738,8 +759,9 @@ extern const VMStateInfo vmstate_info_qlist;
 /* _field_size should be a int32_t field in the _state struct giving the
 * size of the bitmap _field in bits.
 */
-#define VMSTATE_BITMAP(_field, _state, _version, _field_size) {      \
+#define VMSTATE_BITMAP_TEST(_field, _state, _test, _version, _field_size) { \
    .name         = (stringify(_field)),                             \
+    .field_exists = (_test),                                         \
    .version_id   = (_version),                                      \
    .size_offset  = vmstate_offset_value(_state, _field_size, int32_t),\
    .info         = &vmstate_info_bitmap,                            \
@ -747,6 +769,9 @@ extern const VMStateInfo vmstate_info_qlist;
    .offset       = offsetof(_state, _field),                        \
 }

+#define VMSTATE_BITMAP(_field, _state, _version, _field_size) \
+    VMSTATE_BITMAP_TEST(_field, _state, NULL, _version, _field_size)
+
 /* For migrating a QTAILQ.
 * Target QTAILQ needs be properly initialized.
 * _type: type of QTAILQ element
@ -1161,7 +1186,9 @@ extern const VMStateInfo vmstate_info_qlist;
    VMSTATE_UNUSED_BUFFER(_test, 0, _size)

 #define VMSTATE_END_OF_LIST()                                         \
-    {}
+    {                     \
+        .flags = VMS_END, \
+    }

 int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
                       void *opaque, int version_id);
--- a/include/qemu/userfaultfd.h
+++ b/include/qemu/userfaultfd.h
@ -13,10 +13,20 @@
 #ifndef USERFAULTFD_H
 #define USERFAULTFD_H

+#ifdef CONFIG_LINUX
+
 #include "qemu/osdep.h"
 #include "exec/hwaddr.h"
 #include <linux/userfaultfd.h>

+/**
+ * uffd_open(): Open an userfaultfd handle for current context.
+ *
+ * @flags: The flags we want to pass in when creating the handle.
+ *
+ * Returns: the uffd handle if >=0, or <0 if error happens.
+ */
+int uffd_open(int flags);
 int uffd_query_features(uint64_t *features);
 int uffd_create_fd(uint64_t features, bool non_blocking);
 void uffd_close_fd(int uffd_fd);
@ -32,4 +42,6 @@ int uffd_wakeup(int uffd_fd, void *addr, uint64_t length);
 int uffd_read_events(int uffd_fd, struct uffd_msg *msgs, int count);
 bool uffd_poll_events(int uffd_fd, int tmo);

+#endif /* CONFIG_LINUX */
+
 #endif /* USERFAULTFD_H */