diff options
Diffstat (limited to 'migration/multifd-nocomp.c')
| -rw-r--r-- | migration/multifd-nocomp.c | 394 |
1 files changed, 394 insertions, 0 deletions
diff --git a/migration/multifd-nocomp.c b/migration/multifd-nocomp.c new file mode 100644 index 0000000000..53ea9f9c83 --- /dev/null +++ b/migration/multifd-nocomp.c @@ -0,0 +1,394 @@ +/* + * Multifd RAM migration without compression + * + * Copyright (c) 2019-2020 Red Hat Inc + * + * Authors: + * Juan Quintela <quintela@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. + */ + +#include "qemu/osdep.h" +#include "exec/ramblock.h" +#include "exec/target_page.h" +#include "file.h" +#include "multifd.h" +#include "options.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "trace.h" + +static MultiFDSendData *multifd_ram_send; + +size_t multifd_ram_payload_size(void) +{ + uint32_t n = multifd_ram_page_count(); + + /* + * We keep an array of page offsets at the end of MultiFDPages_t, + * add space for it in the allocation. + */ + return sizeof(MultiFDPages_t) + n * sizeof(ram_addr_t); +} + +void multifd_ram_save_setup(void) +{ + multifd_ram_send = multifd_send_data_alloc(); +} + +void multifd_ram_save_cleanup(void) +{ + g_free(multifd_ram_send); + multifd_ram_send = NULL; +} + +static void multifd_set_file_bitmap(MultiFDSendParams *p) +{ + MultiFDPages_t *pages = &p->data->u.ram; + + assert(pages->block); + + for (int i = 0; i < pages->normal_num; i++) { + ramblock_set_file_bmap_atomic(pages->block, pages->offset[i], true); + } + + for (int i = pages->normal_num; i < pages->num; i++) { + ramblock_set_file_bmap_atomic(pages->block, pages->offset[i], false); + } +} + +static int multifd_nocomp_send_setup(MultiFDSendParams *p, Error **errp) +{ + uint32_t page_count = multifd_ram_page_count(); + + if (migrate_zero_copy_send()) { + p->write_flags |= QIO_CHANNEL_WRITE_FLAG_ZERO_COPY; + } + + if (!migrate_mapped_ram()) { + /* We need one extra place for the packet header */ + p->iov = g_new0(struct iovec, page_count + 1); + } else { + p->iov = g_new0(struct iovec, page_count); + } + + return 0; +} + +static void multifd_nocomp_send_cleanup(MultiFDSendParams *p, Error **errp) +{ + g_free(p->iov); + p->iov = NULL; + return; +} + +static void multifd_send_prepare_iovs(MultiFDSendParams *p) +{ + MultiFDPages_t *pages = &p->data->u.ram; + uint32_t page_size = multifd_ram_page_size(); + + for (int i = 0; i < pages->normal_num; i++) { + p->iov[p->iovs_num].iov_base = pages->block->host + pages->offset[i]; + p->iov[p->iovs_num].iov_len = page_size; + p->iovs_num++; + } + + p->next_packet_size = pages->normal_num * page_size; +} + +static int multifd_nocomp_send_prepare(MultiFDSendParams *p, Error **errp) +{ + bool use_zero_copy_send = migrate_zero_copy_send(); + int ret; + + multifd_send_zero_page_detect(p); + + if (migrate_mapped_ram()) { + multifd_send_prepare_iovs(p); + multifd_set_file_bitmap(p); + + return 0; + } + + if (!use_zero_copy_send) { + /* + * Only !zerocopy needs the header in IOV; zerocopy will + * send it separately. + */ + multifd_send_prepare_header(p); + } + + multifd_send_prepare_iovs(p); + p->flags |= MULTIFD_FLAG_NOCOMP; + + multifd_send_fill_packet(p); + + if (use_zero_copy_send) { + /* Send header first, without zerocopy */ + ret = qio_channel_write_all(p->c, (void *)p->packet, + p->packet_len, errp); + if (ret != 0) { + return -1; + } + } + + return 0; +} + +static int multifd_nocomp_recv_setup(MultiFDRecvParams *p, Error **errp) +{ + p->iov = g_new0(struct iovec, multifd_ram_page_count()); + return 0; +} + +static void multifd_nocomp_recv_cleanup(MultiFDRecvParams *p) +{ + g_free(p->iov); + p->iov = NULL; +} + +static int multifd_nocomp_recv(MultiFDRecvParams *p, Error **errp) +{ + uint32_t flags; + + if (migrate_mapped_ram()) { + return multifd_file_recv_data(p, errp); + } + + flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK; + + if (flags != MULTIFD_FLAG_NOCOMP) { + error_setg(errp, "multifd %u: flags received %x flags expected %x", + p->id, flags, MULTIFD_FLAG_NOCOMP); + return -1; + } + + multifd_recv_zero_page_process(p); + + if (!p->normal_num) { + return 0; + } + + for (int i = 0; i < p->normal_num; i++) { + p->iov[i].iov_base = p->host + p->normal[i]; + p->iov[i].iov_len = multifd_ram_page_size(); + ramblock_recv_bitmap_set_offset(p->block, p->normal[i]); + } + return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp); +} + +static void multifd_pages_reset(MultiFDPages_t *pages) +{ + /* + * We don't need to touch offset[] array, because it will be + * overwritten later when reused. + */ + pages->num = 0; + pages->normal_num = 0; + pages->block = NULL; +} + +void multifd_ram_fill_packet(MultiFDSendParams *p) +{ + MultiFDPacket_t *packet = p->packet; + MultiFDPages_t *pages = &p->data->u.ram; + uint32_t zero_num = pages->num - pages->normal_num; + + packet->pages_alloc = cpu_to_be32(multifd_ram_page_count()); + packet->normal_pages = cpu_to_be32(pages->normal_num); + packet->zero_pages = cpu_to_be32(zero_num); + + if (pages->block) { + strncpy(packet->ramblock, pages->block->idstr, 256); + } + + for (int i = 0; i < pages->num; i++) { + /* there are architectures where ram_addr_t is 32 bit */ + uint64_t temp = pages->offset[i]; + + packet->offset[i] = cpu_to_be64(temp); + } + + trace_multifd_send_ram_fill(p->id, pages->normal_num, + zero_num); +} + +int multifd_ram_unfill_packet(MultiFDRecvParams *p, Error **errp) +{ + MultiFDPacket_t *packet = p->packet; + uint32_t page_count = multifd_ram_page_count(); + uint32_t page_size = multifd_ram_page_size(); + int i; + + packet->pages_alloc = be32_to_cpu(packet->pages_alloc); + /* + * If we received a packet that is 100 times bigger than expected + * just stop migration. It is a magic number. + */ + if (packet->pages_alloc > page_count) { + error_setg(errp, "multifd: received packet " + "with size %u and expected a size of %u", + packet->pages_alloc, page_count) ; + return -1; + } + + p->normal_num = be32_to_cpu(packet->normal_pages); + if (p->normal_num > packet->pages_alloc) { + error_setg(errp, "multifd: received packet " + "with %u normal pages and expected maximum pages are %u", + p->normal_num, packet->pages_alloc) ; + return -1; + } + + p->zero_num = be32_to_cpu(packet->zero_pages); + if (p->zero_num > packet->pages_alloc - p->normal_num) { + error_setg(errp, "multifd: received packet " + "with %u zero pages and expected maximum zero pages are %u", + p->zero_num, packet->pages_alloc - p->normal_num) ; + return -1; + } + + if (p->normal_num == 0 && p->zero_num == 0) { + return 0; + } + + /* make sure that ramblock is 0 terminated */ + packet->ramblock[255] = 0; + p->block = qemu_ram_block_by_name(packet->ramblock); + if (!p->block) { + error_setg(errp, "multifd: unknown ram block %s", + packet->ramblock); + return -1; + } + + p->host = p->block->host; + for (i = 0; i < p->normal_num; i++) { + uint64_t offset = be64_to_cpu(packet->offset[i]); + + if (offset > (p->block->used_length - page_size)) { + error_setg(errp, "multifd: offset too long %" PRIu64 + " (max " RAM_ADDR_FMT ")", + offset, p->block->used_length); + return -1; + } + p->normal[i] = offset; + } + + for (i = 0; i < p->zero_num; i++) { + uint64_t offset = be64_to_cpu(packet->offset[p->normal_num + i]); + + if (offset > (p->block->used_length - page_size)) { + error_setg(errp, "multifd: offset too long %" PRIu64 + " (max " RAM_ADDR_FMT ")", + offset, p->block->used_length); + return -1; + } + p->zero[i] = offset; + } + + return 0; +} + +static inline bool multifd_queue_empty(MultiFDPages_t *pages) +{ + return pages->num == 0; +} + +static inline bool multifd_queue_full(MultiFDPages_t *pages) +{ + return pages->num == multifd_ram_page_count(); +} + +static inline void multifd_enqueue(MultiFDPages_t *pages, ram_addr_t offset) +{ + pages->offset[pages->num++] = offset; +} + +/* Returns true if enqueue successful, false otherwise */ +bool multifd_queue_page(RAMBlock *block, ram_addr_t offset) +{ + MultiFDPages_t *pages; + +retry: + pages = &multifd_ram_send->u.ram; + + if (multifd_payload_empty(multifd_ram_send)) { + multifd_pages_reset(pages); + multifd_set_payload_type(multifd_ram_send, MULTIFD_PAYLOAD_RAM); + } + + /* If the queue is empty, we can already enqueue now */ + if (multifd_queue_empty(pages)) { + pages->block = block; + multifd_enqueue(pages, offset); + return true; + } + + /* + * Not empty, meanwhile we need a flush. It can because of either: + * + * (1) The page is not on the same ramblock of previous ones, or, + * (2) The queue is full. + * + * After flush, always retry. + */ + if (pages->block != block || multifd_queue_full(pages)) { + if (!multifd_send(&multifd_ram_send)) { + return false; + } + goto retry; + } + + /* Not empty, and we still have space, do it! */ + multifd_enqueue(pages, offset); + return true; +} + +int multifd_ram_flush_and_sync(void) +{ + if (!migrate_multifd()) { + return 0; + } + + if (!multifd_payload_empty(multifd_ram_send)) { + if (!multifd_send(&multifd_ram_send)) { + error_report("%s: multifd_send fail", __func__); + return -1; + } + } + + return multifd_send_sync_main(); +} + +bool multifd_send_prepare_common(MultiFDSendParams *p) +{ + MultiFDPages_t *pages = &p->data->u.ram; + multifd_send_zero_page_detect(p); + + if (!pages->normal_num) { + p->next_packet_size = 0; + return false; + } + + multifd_send_prepare_header(p); + + return true; +} + +static MultiFDMethods multifd_nocomp_ops = { + .send_setup = multifd_nocomp_send_setup, + .send_cleanup = multifd_nocomp_send_cleanup, + .send_prepare = multifd_nocomp_send_prepare, + .recv_setup = multifd_nocomp_recv_setup, + .recv_cleanup = multifd_nocomp_recv_cleanup, + .recv = multifd_nocomp_recv +}; + +static void multifd_nocomp_register(void) +{ + multifd_register_ops(MULTIFD_COMPRESSION_NONE, &multifd_nocomp_ops); +} + +migration_init(multifd_nocomp_register); |