diff options
Diffstat (limited to 'include/migration')
| -rw-r--r-- | include/migration/migration.h | 121 | ||||
| -rw-r--r-- | include/migration/postcopy-ram.h | 99 | ||||
| -rw-r--r-- | include/migration/qemu-file.h | 10 | ||||
| -rw-r--r-- | include/migration/vmstate.h | 8 |
4 files changed, 233 insertions, 5 deletions
diff --git a/include/migration/migration.h b/include/migration/migration.h index 83346210b1..fd018b74a2 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -35,6 +35,7 @@ #define QEMU_VM_SUBSECTION 0x05 #define QEMU_VM_VMDESCRIPTION 0x06 #define QEMU_VM_CONFIGURATION 0x07 +#define QEMU_VM_COMMAND 0x08 #define QEMU_VM_SECTION_FOOTER 0x7e struct MigrationParams { @@ -42,13 +43,67 @@ struct MigrationParams { bool shared; }; -typedef struct MigrationState MigrationState; +/* Messages sent on the return path from destination to source */ +enum mig_rp_message_type { + MIG_RP_MSG_INVALID = 0, /* Must be 0 */ + MIG_RP_MSG_SHUT, /* sibling will not send any more RP messages */ + MIG_RP_MSG_PONG, /* Response to a PING; data (seq: be32 ) */ + + MIG_RP_MSG_REQ_PAGES_ID, /* data (start: be64, len: be32, id: string) */ + MIG_RP_MSG_REQ_PAGES, /* data (start: be64, len: be32) */ + + MIG_RP_MSG_MAX +}; typedef QLIST_HEAD(, LoadStateEntry) LoadStateEntry_Head; +/* The current postcopy state is read/set by postcopy_state_get/set + * which update it atomically. + * The state is updated as postcopy messages are received, and + * in general only one thread should be writing to the state at any one + * time, initially the main thread and then the listen thread; + * Corner cases are where either thread finishes early and/or errors. + * The state is checked as messages are received to ensure that + * the source is sending us messages in the correct order. + * The state is also used by the RAM reception code to know if it + * has to place pages atomically, and the cleanup code at the end of + * the main thread to know if it has to delay cleanup until the end + * of postcopy. + */ +typedef enum { + POSTCOPY_INCOMING_NONE = 0, /* Initial state - no postcopy */ + POSTCOPY_INCOMING_ADVISE, + POSTCOPY_INCOMING_DISCARD, + POSTCOPY_INCOMING_LISTENING, + POSTCOPY_INCOMING_RUNNING, + POSTCOPY_INCOMING_END +} PostcopyState; + /* State for the incoming migration */ struct MigrationIncomingState { - QEMUFile *file; + QEMUFile *from_src_file; + + /* + * Free at the start of the main state load, set as the main thread finishes + * loading state. + */ + QemuEvent main_thread_load_event; + + bool have_fault_thread; + QemuThread fault_thread; + QemuSemaphore fault_thread_sem; + + bool have_listen_thread; + QemuThread listen_thread; + QemuSemaphore listen_thread_sem; + + /* For the kernel to send us notifications */ + int userfault_fd; + /* To tell the fault_thread to quit */ + int userfault_quit_fd; + QEMUFile *to_src_file; + QemuMutex rp_mutex; /* We send replies from multiple threads */ + void *postcopy_tmp_page; /* See savevm.c */ LoadStateEntry_Head loadvm_handlers; @@ -58,6 +113,18 @@ MigrationIncomingState *migration_incoming_get_current(void); MigrationIncomingState *migration_incoming_state_new(QEMUFile *f); void migration_incoming_state_destroy(void); +/* + * An outstanding page request, on the source, having been received + * and queued + */ +struct MigrationSrcPageRequest { + RAMBlock *rb; + hwaddr offset; + hwaddr len; + + QSIMPLEQ_ENTRY(MigrationSrcPageRequest) next_req; +}; + struct MigrationState { int64_t bandwidth_limit; @@ -70,6 +137,14 @@ struct MigrationState int state; MigrationParams params; + + /* State related to return path */ + struct { + QEMUFile *from_dst_file; + QemuThread rp_thread; + bool error; + } rp_state; + double mbps; int64_t total_time; int64_t downtime; @@ -80,6 +155,18 @@ struct MigrationState int64_t xbzrle_cache_size; int64_t setup_time; int64_t dirty_sync_count; + + /* Flag set once the migration has been asked to enter postcopy */ + bool start_postcopy; + + /* Flag set once the migration thread is running (and needs joining) */ + bool migration_thread_running; + + /* Queue of outstanding page requests from the destination */ + QemuMutex src_page_req_mutex; + QSIMPLEQ_HEAD(src_page_requests, MigrationSrcPageRequest) src_page_requests; + /* The RAMBlock used in the last src_page_request */ + RAMBlock *last_req_rb; }; void process_incoming_migration(QEMUFile *f); @@ -116,9 +203,12 @@ int migrate_fd_close(MigrationState *s); void add_migration_state_change_notifier(Notifier *notify); void remove_migration_state_change_notifier(Notifier *notify); +MigrationState *migrate_init(const MigrationParams *params); bool migration_in_setup(MigrationState *); bool migration_has_finished(MigrationState *); bool migration_has_failed(MigrationState *); +/* True if outgoing migration has entered postcopy phase */ +bool migration_in_postcopy(MigrationState *); MigrationState *migrate_get_current(void); void migrate_compress_threads_create(void); @@ -145,6 +235,13 @@ uint64_t xbzrle_mig_pages_cache_miss(void); double xbzrle_mig_cache_miss_rate(void); void ram_handle_compressed(void *host, uint8_t ch, uint64_t size); +void ram_debug_dump_bitmap(unsigned long *todump, bool expected); +/* For outgoing discard bitmap */ +int ram_postcopy_send_discard_bitmap(MigrationState *ms); +/* For incoming postcopy discard */ +int ram_discard_range(MigrationIncomingState *mis, const char *block_name, + uint64_t start, size_t length); +int ram_postcopy_incoming_init(MigrationIncomingState *mis); /** * @migrate_add_blocker - prevent migration from proceeding @@ -160,6 +257,7 @@ void migrate_add_blocker(Error *reason); */ void migrate_del_blocker(Error *reason); +bool migrate_postcopy_ram(void); bool migrate_zero_blocks(void); bool migrate_auto_converge(void); @@ -179,6 +277,17 @@ int migrate_compress_threads(void); int migrate_decompress_threads(void); bool migrate_use_events(void); +/* Sending on the return path - generic and then for each message type */ +void migrate_send_rp_message(MigrationIncomingState *mis, + enum mig_rp_message_type message_type, + uint16_t len, void *data); +void migrate_send_rp_shut(MigrationIncomingState *mis, + uint32_t value); +void migrate_send_rp_pong(MigrationIncomingState *mis, + uint32_t value); +void migrate_send_rp_req_pages(MigrationIncomingState *mis, const char* rbname, + ram_addr_t start, size_t len); + void ram_control_before_iterate(QEMUFile *f, uint64_t flags); void ram_control_after_iterate(QEMUFile *f, uint64_t flags); void ram_control_load_hook(QEMUFile *f, uint64_t flags, void *data); @@ -204,4 +313,12 @@ void global_state_set_optional(void); void savevm_skip_configuration(void); int global_state_store(void); void global_state_store_running(void); + +void flush_page_queue(MigrationState *ms); +int ram_save_queue_pages(MigrationState *ms, const char *rbname, + ram_addr_t start, ram_addr_t len); + +PostcopyState postcopy_state_get(void); +/* Set the state and return the old state */ +PostcopyState postcopy_state_set(PostcopyState new_state); #endif diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h new file mode 100644 index 0000000000..b6a7491f2d --- /dev/null +++ b/include/migration/postcopy-ram.h @@ -0,0 +1,99 @@ +/* + * Postcopy migration for RAM + * + * Copyright 2013 Red Hat, Inc. and/or its affiliates + * + * Authors: + * Dave Gilbert <dgilbert@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ +#ifndef QEMU_POSTCOPY_RAM_H +#define QEMU_POSTCOPY_RAM_H + +/* Return true if the host supports everything we need to do postcopy-ram */ +bool postcopy_ram_supported_by_host(void); + +/* + * Make all of RAM sensitive to accesses to areas that haven't yet been written + * and wire up anything necessary to deal with it. + */ +int postcopy_ram_enable_notify(MigrationIncomingState *mis); + +/* + * Initialise postcopy-ram, setting the RAM to a state where we can go into + * postcopy later; must be called prior to any precopy. + * called from ram.c's similarly named ram_postcopy_incoming_init + */ +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages); + +/* + * At the end of a migration where postcopy_ram_incoming_init was called. + */ +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis); + +/* + * Discard the contents of 'length' bytes from 'start' + * We can assume that if we've been called postcopy_ram_hosttest returned true + */ +int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start, + size_t length); + +/* + * Userfault requires us to mark RAM as NOHUGEPAGE prior to discard + * however leaving it until after precopy means that most of the precopy + * data is still THPd + */ +int postcopy_ram_prepare_discard(MigrationIncomingState *mis); + +/* + * Called at the start of each RAMBlock by the bitmap code. + * 'offset' is the bitmap offset of the named RAMBlock in the migration + * bitmap. + * Returns a new PDS + */ +PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms, + unsigned long offset, + const char *name); + +/* + * Called by the bitmap code for each chunk to discard. + * May send a discard message, may just leave it queued to + * be sent later. + * @start,@length: a range of pages in the migration bitmap in the + * RAM block passed to postcopy_discard_send_init() (length=1 is one page) + */ +void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds, + unsigned long start, unsigned long length); + +/* + * Called at the end of each RAMBlock by the bitmap code. + * Sends any outstanding discard messages, frees the PDS. + */ +void postcopy_discard_send_finish(MigrationState *ms, + PostcopyDiscardState *pds); + +/* + * Place a page (from) at (host) efficiently + * There are restrictions on how 'from' must be mapped, in general best + * to use other postcopy_ routines to allocate. + * returns 0 on success + */ +int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from); + +/* + * Place a zero page at (host) atomically + * returns 0 on success + */ +int postcopy_place_page_zero(MigrationIncomingState *mis, void *host); + +/* + * Allocate a page of memory that can be mapped at a later point in time + * using postcopy_place_page + * Returns: Pointer to allocated page + */ +void *postcopy_get_tmp_page(MigrationIncomingState *mis); + +#endif diff --git a/include/migration/qemu-file.h b/include/migration/qemu-file.h index 29a338d0a9..b5d08d217d 100644 --- a/include/migration/qemu-file.h +++ b/include/migration/qemu-file.h @@ -89,6 +89,11 @@ typedef size_t (QEMURamSaveFunc)(QEMUFile *f, void *opaque, uint64_t *bytes_sent); /* + * Return a QEMUFile for comms in the opposite direction + */ +typedef QEMUFile *(QEMURetPathFunc)(void *opaque); + +/* * Stop any read or write (depending on flags) on the underlying * transport on the QEMUFile. * Existing blocking reads/writes must be woken @@ -106,6 +111,7 @@ typedef struct QEMUFileOps { QEMURamHookFunc *after_ram_iterate; QEMURamHookFunc *hook_ram_load; QEMURamSaveFunc *save_page; + QEMURetPathFunc *get_return_path; QEMUFileShutdownFunc *shut_down; } QEMUFileOps; @@ -163,9 +169,11 @@ void qemu_put_be32(QEMUFile *f, unsigned int v); void qemu_put_be64(QEMUFile *f, uint64_t v); size_t qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t size, size_t offset); size_t qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size); +size_t qemu_get_buffer_in_place(QEMUFile *f, uint8_t **buf, size_t size); ssize_t qemu_put_compression_data(QEMUFile *f, const uint8_t *p, size_t size, int level); int qemu_put_qemu_file(QEMUFile *f_des, QEMUFile *f_src); + /* * Note that you can only peek continuous bytes from where the current pointer * is; you aren't guaranteed to be able to peak to +n bytes unless you've @@ -194,7 +202,9 @@ int64_t qemu_file_get_rate_limit(QEMUFile *f); int qemu_file_get_error(QEMUFile *f); void qemu_file_set_error(QEMUFile *f, int ret); 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); static inline void qemu_put_be64s(QEMUFile *f, const uint64_t *pv) { diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index d173b565f5..7267e38c1f 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -40,7 +40,8 @@ typedef struct SaveVMHandlers { SaveStateHandler *save_state; void (*cleanup)(void *opaque); - int (*save_live_complete)(QEMUFile *f, void *opaque); + int (*save_live_complete_postcopy)(QEMUFile *f, void *opaque); + int (*save_live_complete_precopy)(QEMUFile *f, void *opaque); /* This runs both outside and inside the iothread lock. */ bool (*is_active)(void *opaque); @@ -54,8 +55,9 @@ typedef struct SaveVMHandlers { /* This runs outside the iothread lock! */ int (*save_live_setup)(QEMUFile *f, void *opaque); - uint64_t (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t max_size); - + void (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t max_size, + uint64_t *non_postcopiable_pending, + uint64_t *postcopiable_pending); LoadStateHandler *load_state; } SaveVMHandlers; |