From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: Dietmar Maurer Date: Mon, 6 Apr 2020 12:16:57 +0200 Subject: [PATCH] PVE-Backup: add vma backup format code --- Makefile | 3 +- Makefile.objs | 1 + vma-reader.c | 857 ++++++++++++++++++++++++++++++++++++++++++++++++++ vma-writer.c | 790 ++++++++++++++++++++++++++++++++++++++++++++++ vma.c | 839 ++++++++++++++++++++++++++++++++++++++++++++++++ vma.h | 150 +++++++++ 6 files changed, 2639 insertions(+), 1 deletion(-) create mode 100644 vma-reader.c create mode 100644 vma-writer.c create mode 100644 vma.c create mode 100644 vma.h diff --git a/Makefile b/Makefile index 13dd708c4a..7b8c17ce2d 100644 --- a/Makefile +++ b/Makefile @@ -479,7 +479,7 @@ dummy := $(call unnest-vars,, \ include $(SRC_PATH)/tests/Makefile.include -all: $(DOCS) $(if $(BUILD_DOCS),sphinxdocs) $(TOOLS) $(HELPERS-y) recurse-all modules $(vhost-user-json-y) +all: $(DOCS) $(if $(BUILD_DOCS),sphinxdocs) $(TOOLS) vma$(EXESUF) $(HELPERS-y) recurse-all modules $(vhost-user-json-y) qemu-version.h: FORCE $(call quiet-command, \ @@ -602,6 +602,7 @@ qemu-img$(EXESUF): qemu-img.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io qemu-nbd$(EXESUF): qemu-nbd.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS) qemu-io$(EXESUF): qemu-io.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS) qemu-storage-daemon$(EXESUF): qemu-storage-daemon.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(chardev-obj-y) $(io-obj-y) $(qom-obj-y) $(storage-daemon-obj-y) $(COMMON_LDADDS) +vma$(EXESUF): vma.o vma-reader.o $(authz-obj-y) $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS) qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o $(COMMON_LDADDS) diff --git a/Makefile.objs b/Makefile.objs index a1307c12a8..ade7b17a69 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -17,6 +17,7 @@ block-obj-y = block/ nbd/ scsi/ block-obj-y += block.o blockjob.o job.o block-obj-y += qemu-io-cmds.o block-obj-$(CONFIG_REPLICATION) += replication.o +block-obj-y += vma-writer.o block-obj-m = block/ diff --git a/vma-reader.c b/vma-reader.c new file mode 100644 index 0000000000..2b1d1cdab3 --- /dev/null +++ b/vma-reader.c @@ -0,0 +1,857 @@ +/* + * VMA: Virtual Machine Archive + * + * Copyright (C) 2012 Proxmox Server Solutions + * + * Authors: + * Dietmar Maurer (dietmar@proxmox.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 +#include + +#include "qemu-common.h" +#include "qemu/timer.h" +#include "qemu/ratelimit.h" +#include "vma.h" +#include "block/block.h" +#include "sysemu/block-backend.h" + +static unsigned char zero_vma_block[VMA_BLOCK_SIZE]; + +typedef struct VmaRestoreState { + BlockBackend *target; + bool write_zeroes; + unsigned long *bitmap; + int bitmap_size; +} VmaRestoreState; + +struct VmaReader { + int fd; + GChecksum *md5csum; + GHashTable *blob_hash; + unsigned char *head_data; + VmaDeviceInfo devinfo[256]; + VmaRestoreState rstate[256]; + GList *cdata_list; + guint8 vmstate_stream; + uint32_t vmstate_clusters; + /* to show restore percentage if run with -v */ + time_t start_time; + int64_t cluster_count; + int64_t clusters_read; + int64_t zero_cluster_data; + int64_t partial_zero_cluster_data; + int clusters_read_per; +}; + +static guint +g_int32_hash(gconstpointer v) +{ + return *(const uint32_t *)v; +} + +static gboolean +g_int32_equal(gconstpointer v1, gconstpointer v2) +{ + return *((const uint32_t *)v1) == *((const uint32_t *)v2); +} + +static int vma_reader_get_bitmap(VmaRestoreState *rstate, int64_t cluster_num) +{ + assert(rstate); + assert(rstate->bitmap); + + unsigned long val, idx, bit; + + idx = cluster_num / BITS_PER_LONG; + + assert(rstate->bitmap_size > idx); + + bit = cluster_num % BITS_PER_LONG; + val = rstate->bitmap[idx]; + + return !!(val & (1UL << bit)); +} + +static void vma_reader_set_bitmap(VmaRestoreState *rstate, int64_t cluster_num, + int dirty) +{ + assert(rstate); + assert(rstate->bitmap); + + unsigned long val, idx, bit; + + idx = cluster_num / BITS_PER_LONG; + + assert(rstate->bitmap_size > idx); + + bit = cluster_num % BITS_PER_LONG; + val = rstate->bitmap[idx]; + if (dirty) { + if (!(val & (1UL << bit))) { + val |= 1UL << bit; + } + } else { + if (val & (1UL << bit)) { + val &= ~(1UL << bit); + } + } + rstate->bitmap[idx] = val; +} + +typedef struct VmaBlob { + uint32_t start; + uint32_t len; + void *data; +} VmaBlob; + +static const VmaBlob *get_header_blob(VmaReader *vmar, uint32_t pos) +{ + assert(vmar); + assert(vmar->blob_hash); + + return g_hash_table_lookup(vmar->blob_hash, &pos); +} + +static const char *get_header_str(VmaReader *vmar, uint32_t pos) +{ + const VmaBlob *blob = get_header_blob(vmar, pos); + if (!blob) { + return NULL; + } + const char *res = (char *)blob->data; + if (res[blob->len-1] != '\0') { + return NULL; + } + return res; +} + +static ssize_t +safe_read(int fd, unsigned char *buf, size_t count) +{ + ssize_t n; + + do { + n = read(fd, buf, count); + } while (n < 0 && errno == EINTR); + + return n; +} + +static ssize_t +full_read(int fd, unsigned char *buf, size_t len) +{ + ssize_t n; + size_t total; + + total = 0; + + while (len > 0) { + n = safe_read(fd, buf, len); + + if (n == 0) { + return total; + } + + if (n <= 0) { + break; + } + + buf += n; + total += n; + len -= n; + } + + if (len) { + return -1; + } + + return total; +} + +void vma_reader_destroy(VmaReader *vmar) +{ + assert(vmar); + + if (vmar->fd >= 0) { + close(vmar->fd); + } + + if (vmar->cdata_list) { + g_list_free(vmar->cdata_list); + } + + int i; + for (i = 1; i < 256; i++) { + if (vmar->rstate[i].bitmap) { + g_free(vmar->rstate[i].bitmap); + } + } + + if (vmar->md5csum) { + g_checksum_free(vmar->md5csum); + } + + if (vmar->blob_hash) { + g_hash_table_destroy(vmar->blob_hash); + } + + if (vmar->head_data) { + g_free(vmar->head_data); + } + + g_free(vmar); + +}; + +static int vma_reader_read_head(VmaReader *vmar, Error **errp) +{ + assert(vmar); + assert(errp); + assert(*errp == NULL); + + unsigned char md5sum[16]; + int i; + int ret = 0; + + vmar->head_data = g_malloc(sizeof(VmaHeader)); + + if (full_read(vmar->fd, vmar->head_data, sizeof(VmaHeader)) != + sizeof(VmaHeader)) { + error_setg(errp, "can't read vma header - %s", + errno ? g_strerror(errno) : "got EOF"); + return -1; + } + + VmaHeader *h = (VmaHeader *)vmar->head_data; + + if (h->magic != VMA_MAGIC) { + error_setg(errp, "not a vma file - wrong magic number"); + return -1; + } + + uint32_t header_size = GUINT32_FROM_BE(h->header_size); + int need = header_size - sizeof(VmaHeader); + if (need <= 0) { + error_setg(errp, "wrong vma header size %d", header_size); + return -1; + } + + vmar->head_data = g_realloc(vmar->head_data, header_size); + h = (VmaHeader *)vmar->head_data; + + if (full_read(vmar->fd, vmar->head_data + sizeof(VmaHeader), need) != + need) { + error_setg(errp, "can't read vma header data - %s", + errno ? g_strerror(errno) : "got EOF"); + return -1; + } + + memcpy(md5sum, h->md5sum, 16); + memset(h->md5sum, 0, 16); + + g_checksum_reset(vmar->md5csum); + g_checksum_update(vmar->md5csum, vmar->head_data, header_size); + gsize csize = 16; + g_checksum_get_digest(vmar->md5csum, (guint8 *)(h->md5sum), &csize); + + if (memcmp(md5sum, h->md5sum, 16) != 0) { + error_setg(errp, "wrong vma header chechsum"); + return -1; + } + + /* we can modify header data after checksum verify */ + h->header_size = header_size; + + h->version = GUINT32_FROM_BE(h->version); + if (h->version != 1) { + error_setg(errp, "wrong vma version %d", h->version); + return -1; + } + + h->ctime = GUINT64_FROM_BE(h->ctime); + h->blob_buffer_offset = GUINT32_FROM_BE(h->blob_buffer_offset); + h->blob_buffer_size = GUINT32_FROM_BE(h->blob_buffer_size); + + uint32_t bstart = h->blob_buffer_offset + 1; + uint32_t bend = h->blob_buffer_offset + h->blob_buffer_size; + + if (bstart <= sizeof(VmaHeader)) { + error_setg(errp, "wrong vma blob buffer offset %d", + h->blob_buffer_offset); + return -1; + } + + if (bend > header_size) { + error_setg(errp, "wrong vma blob buffer size %d/%d", + h->blob_buffer_offset, h->blob_buffer_size); + return -1; + } + + while ((bstart + 2) <= bend) { + uint32_t size = vmar->head_data[bstart] + + (vmar->head_data[bstart+1] << 8); + if ((bstart + size + 2) <= bend) { + VmaBlob *blob = g_new0(VmaBlob, 1); + blob->start = bstart - h->blob_buffer_offset; + blob->len = size; + blob->data = vmar->head_data + bstart + 2; + g_hash_table_insert(vmar->blob_hash, &blob->start, blob); + } + bstart += size + 2; + } + + + int count = 0; + for (i = 1; i < 256; i++) { + VmaDeviceInfoHeader *dih = &h->dev_info[i]; + uint32_t devname_ptr = GUINT32_FROM_BE(dih->devname_ptr); + uint64_t size = GUINT64_FROM_BE(dih->size); + const char *devname = get_header_str(vmar, devname_ptr); + + if (size && devname) { + count++; + vmar->devinfo[i].size = size; + vmar->devinfo[i].devname = devname; + + if (strcmp(devname, "vmstate") == 0) { + vmar->vmstate_stream = i; + } + } + } + + for (i = 0; i < VMA_MAX_CONFIGS; i++) { + uint32_t name_ptr = GUINT32_FROM_BE(h->config_names[i]); + uint32_t data_ptr = GUINT32_FROM_BE(h->config_data[i]); + + if (!(name_ptr && data_ptr)) { + continue; + } + const char *name = get_header_str(vmar, name_ptr); + const VmaBlob *blob = get_header_blob(vmar, data_ptr); + + if (!(name && blob)) { + error_setg(errp, "vma contains invalid data pointers"); + return -1; + } + + VmaConfigData *cdata = g_new0(VmaConfigData, 1); + cdata->name = name; + cdata->data = blob->data; + cdata->len = blob->len; + + vmar->cdata_list = g_list_append(vmar->cdata_list, cdata); + } + + return ret; +}; + +VmaReader *vma_reader_create(const char *filename, Error **errp) +{ + assert(filename); + assert(errp); + + VmaReader *vmar = g_new0(VmaReader, 1); + + if (strcmp(filename, "-") == 0) { + vmar->fd = dup(0); + } else { + vmar->fd = open(filename, O_RDONLY); + } + + if (vmar->fd < 0) { + error_setg(errp, "can't open file %s - %s\n", filename, + g_strerror(errno)); + goto err; + } + + vmar->md5csum = g_checksum_new(G_CHECKSUM_MD5); + if (!vmar->md5csum) { + error_setg(errp, "can't allocate cmsum\n"); + goto err; + } + + vmar->blob_hash = g_hash_table_new_full(g_int32_hash, g_int32_equal, + NULL, g_free); + + if (vma_reader_read_head(vmar, errp) < 0) { + goto err; + } + + return vmar; + +err: + if (vmar) { + vma_reader_destroy(vmar); + } + + return NULL; +} + +VmaHeader *vma_reader_get_header(VmaReader *vmar) +{ + assert(vmar); + assert(vmar->head_data); + + return (VmaHeader *)(vmar->head_data); +} + +GList *vma_reader_get_config_data(VmaReader *vmar) +{ + assert(vmar); + assert(vmar->head_data); + + return vmar->cdata_list; +} + +VmaDeviceInfo *vma_reader_get_device_info(VmaReader *vmar, guint8 dev_id) +{ + assert(vmar); + assert(dev_id); + + if (vmar->devinfo[dev_id].size && vmar->devinfo[dev_id].devname) { + return &vmar->devinfo[dev_id]; + } + + return NULL; +} + +static void allocate_rstate(VmaReader *vmar, guint8 dev_id, + BlockBackend *target, bool write_zeroes) +{ + assert(vmar); + assert(dev_id); + + vmar->rstate[dev_id].target = target; + vmar->rstate[dev_id].write_zeroes = write_zeroes; + + int64_t size = vmar->devinfo[dev_id].size; + + int64_t bitmap_size = (size/BDRV_SECTOR_SIZE) + + (VMA_CLUSTER_SIZE/BDRV_SECTOR_SIZE) * BITS_PER_LONG - 1; + bitmap_size /= (VMA_CLUSTER_SIZE/BDRV_SECTOR_SIZE) * BITS_PER_LONG; + + vmar->rstate[dev_id].bitmap_size = bitmap_size; + vmar->rstate[dev_id].bitmap = g_new0(unsigned long, bitmap_size); + + vmar->cluster_count += size/VMA_CLUSTER_SIZE; +} + +int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id, BlockBackend *target, + bool write_zeroes, Error **errp) +{ + assert(vmar); + assert(target != NULL); + assert(dev_id); + assert(vmar->rstate[dev_id].target == NULL); + + int64_t size = blk_getlength(target); + int64_t size_diff = size - vmar->devinfo[dev_id].size; + + /* storage types can have different size restrictions, so it + * is not always possible to create an image with exact size. + * So we tolerate a size difference up to 4MB. + */ + if ((size_diff < 0) || (size_diff > 4*1024*1024)) { + error_setg(errp, "vma_reader_register_bs for stream %s failed - " + "unexpected size %zd != %zd", vmar->devinfo[dev_id].devname, + size, vmar->devinfo[dev_id].size); + return -1; + } + + allocate_rstate(vmar, dev_id, target, write_zeroes); + + return 0; +} + +static ssize_t safe_write(int fd, void *buf, size_t count) +{ + ssize_t n; + + do { + n = write(fd, buf, count); + } while (n < 0 && errno == EINTR); + + return n; +} + +static size_t full_write(int fd, void *buf, size_t len) +{ + ssize_t n; + size_t total; + + total = 0; + + while (len > 0) { + n = safe_write(fd, buf, len); + if (n < 0) { + return n; + } + buf += n; + total += n; + len -= n; + } + + if (len) { + /* incomplete write ? */ + return -1; + } + + return total; +} + +static int restore_write_data(VmaReader *vmar, guint8 dev_id, + BlockBackend *target, int vmstate_fd, + unsigned char *buf, int64_t sector_num, + int nb_sectors, Error **errp) +{ + assert(vmar); + + if (dev_id == vmar->vmstate_stream) { + if (vmstate_fd >= 0) { + int len = nb_sectors * BDRV_SECTOR_SIZE; + int res = full_write(vmstate_fd, buf, len); + if (res < 0) { + error_setg(errp, "write vmstate failed %d", res); + return -1; + } + } + } else { + int res = blk_pwrite(target, sector_num * BDRV_SECTOR_SIZE, buf, nb_sectors * BDRV_SECTOR_SIZE, 0); + if (res < 0) { + error_setg(errp, "blk_pwrite to %s failed (%d)", + bdrv_get_device_name(blk_bs(target)), res); + return -1; + } + } + return 0; +} + +static int restore_extent(VmaReader *vmar, unsigned char *buf, + int extent_size, int vmstate_fd, + bool verbose, bool verify, Error **errp) +{ + assert(vmar); + assert(buf); + + VmaExtentHeader *ehead = (VmaExtentHeader *)buf; + int start = VMA_EXTENT_HEADER_SIZE; + int i; + + for (i = 0; i < VMA_BLOCKS_PER_EXTENT; i++) { + uint64_t block_info = GUINT64_FROM_BE(ehead->blockinfo[i]); + uint64_t cluster_num = block_info & 0xffffffff; + uint8_t dev_id = (block_info >> 32) & 0xff; + uint16_t mask = block_info >> (32+16); + int64_t max_sector; + + if (!dev_id) { + continue; + } + + VmaRestoreState *rstate = &vmar->rstate[dev_id]; + BlockBackend *target = NULL; + + if (dev_id != vmar->vmstate_stream) { + target = rstate->target; + if (!verify && !target) { + error_setg(errp, "got wrong dev id %d", dev_id); + return -1; + } + + if (vma_reader_get_bitmap(rstate, cluster_num)) { + error_setg(errp, "found duplicated cluster %zd for stream %s", + cluster_num, vmar->devinfo[dev_id].devname); + return -1; + } + vma_reader_set_bitmap(rstate, cluster_num, 1); + + max_sector = vmar->devinfo[dev_id].size/BDRV_SECTOR_SIZE; + } else { + max_sector = G_MAXINT64; + if (cluster_num != vmar->vmstate_clusters) { + error_setg(errp, "found out of order vmstate data"); + return -1; + } + vmar->vmstate_clusters++; + } + + vmar->clusters_read++; + + if (verbose) { + time_t duration = time(NULL) - vmar->start_time; + int percent = (vmar->clusters_read*100)/vmar->cluster_count; + if (percent != vmar->clusters_read_per) { + printf("progress %d%% (read %zd bytes, duration %zd sec)\n", + percent, vmar->clusters_read*VMA_CLUSTER_SIZE, + duration); + fflush(stdout); + vmar->clusters_read_per = percent; + } + } + + /* try to write whole clusters to speedup restore */ + if (mask == 0xffff) { + if ((start + VMA_CLUSTER_SIZE) > extent_size) { + error_setg(errp, "short vma extent - too many blocks"); + return -1; + } + int64_t sector_num = (cluster_num * VMA_CLUSTER_SIZE) / + BDRV_SECTOR_SIZE; + int64_t end_sector = sector_num + + VMA_CLUSTER_SIZE/BDRV_SECTOR_SIZE; + + if (end_sector > max_sector) { + end_sector = max_sector; + } + + if (end_sector <= sector_num) { + error_setg(errp, "got wrong block address - write beyond end"); + return -1; + } + + if (!verify) { + int nb_sectors = end_sector - sector_num; + if (restore_write_data(vmar, dev_id, target, vmstate_fd, + buf + start, sector_num, nb_sectors, + errp) < 0) { + return -1; + } + } + + start += VMA_CLUSTER_SIZE; + } else { + int j; + int bit = 1; + + for (j = 0; j < 16; j++) { + int64_t sector_num = (cluster_num*VMA_CLUSTER_SIZE + + j*VMA_BLOCK_SIZE)/BDRV_SECTOR_SIZE; + + int64_t end_sector = sector_num + + VMA_BLOCK_SIZE/BDRV_SECTOR_SIZE; + if (end_sector > max_sector) { + end_sector = max_sector; + } + + if (mask & bit) { + if ((start + VMA_BLOCK_SIZE) > extent_size) { + error_setg(errp, "short vma extent - too many blocks"); + return -1; + } + + if (end_sector <= sector_num) { + error_setg(errp, "got wrong block address - " + "write beyond end"); + return -1; + } + + if (!verify) { + int nb_sectors = end_sector - sector_num; + if (restore_write_data(vmar, dev_id, target, vmstate_fd, + buf + start, sector_num, + nb_sectors, errp) < 0) { + return -1; + } + } + + start += VMA_BLOCK_SIZE; + + } else { + + + if (end_sector > sector_num) { + /* Todo: use bdrv_co_write_zeroes (but that need to + * be run inside coroutine?) + */ + int nb_sectors = end_sector - sector_num; + int zero_size = BDRV_SECTOR_SIZE*nb_sectors; + vmar->zero_cluster_data += zero_size; + if (mask != 0) { + vmar->partial_zero_cluster_data += zero_size; + } + + if (rstate->write_zeroes && !verify) { + if (restore_write_data(vmar, dev_id, target, vmstate_fd, + zero_vma_block, sector_num, + nb_sectors, errp) < 0) { + return -1; + } + } + } + } + + bit = bit << 1; + } + } + } + + if (start != extent_size) { + error_setg(errp, "vma extent error - missing blocks"); + return -1; + } + + return 0; +} + +static int vma_reader_restore_full(VmaReader *vmar, int vmstate_fd, + bool verbose, bool verify, + Error **errp) +{ + assert(vmar); + assert(vmar->head_data); + + int ret = 0; + unsigned char buf[VMA_MAX_EXTENT_SIZE]; + int buf_pos = 0; + unsigned char md5sum[16]; + VmaHeader *h = (VmaHeader *)vmar->head_data; + + vmar->start_time = time(NULL); + + while (1) { + int bytes = full_read(vmar->fd, buf + buf_pos, sizeof(buf) - buf_pos); + if (bytes < 0) { + error_setg(errp, "read failed - %s", g_strerror(errno)); + return -1; + } + + buf_pos += bytes; + + if (!buf_pos) { + break; /* EOF */ + } + + if (buf_pos < VMA_EXTENT_HEADER_SIZE) { + error_setg(errp, "read short extent (%d bytes)", buf_pos); + return -1; + } + + VmaExtentHeader *ehead = (VmaExtentHeader *)buf; + + /* extract md5sum */ + memcpy(md5sum, ehead->md5sum, sizeof(ehead->md5sum)); + memset(ehead->md5sum, 0, sizeof(ehead->md5sum)); + + g_checksum_reset(vmar->md5csum); + g_checksum_update(vmar->md5csum, buf, VMA_EXTENT_HEADER_SIZE); + gsize csize = 16; + g_checksum_get_digest(vmar->md5csum, ehead->md5sum, &csize); + + if (memcmp(md5sum, ehead->md5sum, 16) != 0) { + error_setg(errp, "wrong vma extent header chechsum"); + return -1; + } + + if (memcmp(h->uuid, ehead->uuid, sizeof(ehead->uuid)) != 0) { + error_setg(errp, "wrong vma extent uuid"); + return -1; + } + + if (ehead->magic != VMA_EXTENT_MAGIC || ehead->reserved1 != 0) { + error_setg(errp, "wrong vma extent header magic"); + return -1; + } + + int block_count = GUINT16_FROM_BE(ehead->block_count); + int extent_size = VMA_EXTENT_HEADER_SIZE + block_count*VMA_BLOCK_SIZE; + + if (buf_pos < extent_size) { + error_setg(errp, "short vma extent (%d < %d)", buf_pos, + extent_size); + return -1; + } + + if (restore_extent(vmar, buf, extent_size, vmstate_fd, verbose, + verify, errp) < 0) { + return -1; + } + + if (buf_pos > extent_size) { + memmove(buf, buf + extent_size, buf_pos - extent_size); + buf_pos = buf_pos - extent_size; + } else { + buf_pos = 0; + } + } + + bdrv_drain_all(); + + int i; + for (i = 1; i < 256; i++) { + VmaRestoreState *rstate = &vmar->rstate[i]; + if (!rstate->target) { + continue; + } + + if (blk_flush(rstate->target) < 0) { + error_setg(errp, "vma blk_flush %s failed", + vmar->devinfo[i].devname); + return -1; + } + + if (vmar->devinfo[i].size && + (strcmp(vmar->devinfo[i].devname, "vmstate") != 0)) { + assert(rstate->bitmap); + + int64_t cluster_num, end; + + end = (vmar->devinfo[i].size + VMA_CLUSTER_SIZE - 1) / + VMA_CLUSTER_SIZE; + + for (cluster_num = 0; cluster_num < end; cluster_num++) { + if (!vma_reader_get_bitmap(rstate, cluster_num)) { + error_setg(errp, "detected missing cluster %zd " + "for stream %s", cluster_num, + vmar->devinfo[i].devname); + return -1; + } + } + } + } + + if (verbose) { + if (vmar->clusters_read) { + printf("total bytes read %zd, sparse bytes %zd (%.3g%%)\n", + vmar->clusters_read*VMA_CLUSTER_SIZE, + vmar->zero_cluster_data, + (double)(100.0*vmar->zero_cluster_data)/ + (vmar->clusters_read*VMA_CLUSTER_SIZE)); + + int64_t datasize = vmar->clusters_read*VMA_CLUSTER_SIZE-vmar->zero_cluster_data; + if (datasize) { // this does not make sense for empty files + printf("space reduction due to 4K zero blocks %.3g%%\n", + (double)(100.0*vmar->partial_zero_cluster_data) / datasize); + } + } else { + printf("vma archive contains no image data\n"); + } + } + return ret; +} + +int vma_reader_restore(VmaReader *vmar, int vmstate_fd, bool verbose, + Error **errp) +{ + return vma_reader_restore_full(vmar, vmstate_fd, verbose, false, errp); +} + +int vma_reader_verify(VmaReader *vmar, bool verbose, Error **errp) +{ + guint8 dev_id; + + for (dev_id = 1; dev_id < 255; dev_id++) { + if (vma_reader_get_device_info(vmar, dev_id)) { + allocate_rstate(vmar, dev_id, NULL, false); + } + } + + return vma_reader_restore_full(vmar, -1, verbose, true, errp); +} + diff --git a/vma-writer.c b/vma-writer.c new file mode 100644 index 0000000000..f5d2c5d23c --- /dev/null +++ b/vma-writer.c @@ -0,0 +1,790 @@ +/* + * VMA: Virtual Machine Archive + * + * Copyright (C) 2012 Proxmox Server Solutions + * + * Authors: + * Dietmar Maurer (dietmar@proxmox.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 +#include + +#include "vma.h" +#include "block/block.h" +#include "monitor/monitor.h" +#include "qemu/main-loop.h" +#include "qemu/coroutine.h" +#include "qemu/cutils.h" + +#define DEBUG_VMA 0 + +#define DPRINTF(fmt, ...)\ + do { if (DEBUG_VMA) { printf("vma: " fmt, ## __VA_ARGS__); } } while (0) + +#define WRITE_BUFFERS 5 +#define HEADER_CLUSTERS 8 +#define HEADERBUF_SIZE (VMA_CLUSTER_SIZE*HEADER_CLUSTERS) + +struct VmaWriter { + int fd; + FILE *cmd; + int status; + char errmsg[8192]; + uuid_t uuid; + bool header_written; + bool closed; + + /* we always write extents */ + unsigned char *outbuf; + int outbuf_pos; /* in bytes */ + int outbuf_count; /* in VMA_BLOCKS */ + uint64_t outbuf_block_info[VMA_BLOCKS_PER_EXTENT]; + + unsigned char *headerbuf; + + GChecksum *md5csum; + CoMutex flush_lock; + Coroutine *co_writer; + + /* drive informations */ + VmaStreamInfo stream_info[256]; + guint stream_count; + + guint8 vmstate_stream; + uint32_t vmstate_clusters; + + /* header blob table */ + char *header_blob_table; + uint32_t header_blob_table_size; + uint32_t header_blob_table_pos; + + /* store for config blobs */ + uint32_t config_names[VMA_MAX_CONFIGS]; /* offset into blob_buffer table */ + uint32_t config_data[VMA_MAX_CONFIGS]; /* offset into blob_buffer table */ + uint32_t config_count; +}; + +void vma_writer_set_error(VmaWriter *vmaw, const char *fmt, ...) +{ + va_list ap; + + if (vmaw->status < 0) { + return; + } + + vmaw->status = -1; + + va_start(ap, fmt); + g_vsnprintf(vmaw->errmsg, sizeof(vmaw->errmsg), fmt, ap); + va_end(ap); + + DPRINTF("vma_writer_set_error: %s\n", vmaw->errmsg); +} + +static uint32_t allocate_header_blob(VmaWriter *vmaw, const char *data, + size_t len) +{ + if (len > 65535) { + return 0; + } + + if (!vmaw->header_blob_table || + (vmaw->header_blob_table_size < + (vmaw->header_blob_table_pos + len + 2))) { + int newsize = vmaw->header_blob_table_size + ((len + 2 + 511)/512)*512; + + vmaw->header_blob_table = g_realloc(vmaw->header_blob_table, newsize); + memset(vmaw->header_blob_table + vmaw->header_blob_table_size, + 0, newsize - vmaw->header_blob_table_size); + vmaw->header_blob_table_size = newsize; + } + + uint32_t cpos = vmaw->header_blob_table_pos; + vmaw->header_blob_table[cpos] = len & 255; + vmaw->header_blob_table[cpos+1] = (len >> 8) & 255; + memcpy(vmaw->header_blob_table + cpos + 2, data, len); + vmaw->header_blob_table_pos += len + 2; + return cpos; +} + +static uint32_t allocate_header_string(VmaWriter *vmaw, const char *str) +{ + assert(vmaw); + + size_t len = strlen(str) + 1; + + return allocate_header_blob(vmaw, str, len); +} + +int vma_writer_add_config(VmaWriter *vmaw, const char *name, gpointer data, + gsize len) +{ + assert(vmaw); + assert(!vmaw->header_written); + assert(vmaw->config_count < VMA_MAX_CONFIGS); + assert(name); + assert(data); + + gchar *basename = g_path_get_basename(name); + uint32_t name_ptr = allocate_header_string(vmaw, basename); + g_free(basename); + + if (!name_ptr) { + return -1; + } + + uint32_t data_ptr = allocate_header_blob(vmaw, data, len); + if (!data_ptr) { + return -1; + } + + vmaw->config_names[vmaw->config_count] = name_ptr; + vmaw->config_data[vmaw->config_count] = data_ptr; + + vmaw->config_count++; + + return 0; +} + +int vma_writer_register_stream(VmaWriter *vmaw, const char *devname, + size_t size) +{ + assert(vmaw); + assert(devname); + assert(!vmaw->status); + + if (vmaw->header_written) { + vma_writer_set_error(vmaw, "vma_writer_register_stream: header " + "already written"); + return -1; + } + + guint n = vmaw->stream_count + 1; + + /* we can have dev_ids form 1 to 255 (0 reserved) + * 255(-1) reseverd for safety + */ + if (n > 254) { + vma_writer_set_error(vmaw, "vma_writer_register_stream: " + "too many drives"); + return -1; + } + + if (size <= 0) { + vma_writer_set_error(vmaw, "vma_writer_register_stream: " + "got strange size %zd", size); + return -1; + } + + DPRINTF("vma_writer_register_stream %s %zu %d\n", devname, size, n); + + vmaw->stream_info[n].devname = g_strdup(devname); + vmaw->stream_info[n].size = size; + + vmaw->stream_info[n].cluster_count = (size + VMA_CLUSTER_SIZE - 1) / + VMA_CLUSTER_SIZE; + + vmaw->stream_count = n; + + if (strcmp(devname, "vmstate") == 0) { + vmaw->vmstate_stream = n; + } + + return n; +} + +static void coroutine_fn yield_until_fd_writable(int fd) +{ + assert(qemu_in_coroutine()); + AioContext *ctx = qemu_get_current_aio_context(); + aio_set_fd_handler(ctx, fd, false, NULL, (IOHandler *)qemu_coroutine_enter, + NULL, qemu_coroutine_self()); + qemu_coroutine_yield(); + aio_set_fd_handler(ctx, fd, false, NULL, NULL, NULL, NULL); +} + +static ssize_t coroutine_fn +vma_queue_write(VmaWriter *vmaw, const void *buf, size_t bytes) +{ + DPRINTF("vma_queue_write enter %zd\n", bytes); + + assert(vmaw); + assert(buf); + assert(bytes <= VMA_MAX_EXTENT_SIZE); + + size_t done = 0; + ssize_t ret; + + assert(vmaw->co_writer == NULL); + + vmaw->co_writer = qemu_coroutine_self(); + + while (done < bytes) { + if (vmaw->status < 0) { + DPRINTF("vma_queue_write detected canceled backup\n"); + done = -1; + break; + } + yield_until_fd_writable(vmaw->fd); + ret = write(vmaw->fd, buf + done, bytes - done); + if (ret > 0) { + done += ret; + DPRINTF("vma_queue_write written %zd %zd\n", done, ret); + } else if (ret < 0) { + if (errno == EAGAIN || errno == EWOULDBLOCK) { + /* try again */ + } else { + vma_writer_set_error(vmaw, "vma_queue_write: write error - %s", + g_strerror(errno)); + done = -1; /* always return failure for partial writes */ + break; + } + } else if (ret == 0) { + /* should not happen - simply try again */ + } + } + + vmaw->co_writer = NULL; + + return (done == bytes) ? bytes : -1; +} + +VmaWriter *vma_writer_create(const char *filename, uuid_t uuid, Error **errp) +{ + const char *p; + + assert(sizeof(VmaHeader) == (4096 + 8192)); + assert(G_STRUCT_OFFSET(VmaHeader, config_names) == 2044); + assert(G_STRUCT_OFFSET(VmaHeader, config_data) == 3068); + assert(G_STRUCT_OFFSET(VmaHeader, dev_info) == 4096); + assert(sizeof(VmaExtentHeader) == 512); + + VmaWriter *vmaw = g_new0(VmaWriter, 1); + vmaw->fd = -1; + + vmaw->md5csum = g_checksum_new(G_CHECKSUM_MD5); + if (!vmaw->md5csum) { + error_setg(errp, "can't allocate cmsum\n"); + goto err; + } + + if (strstart(filename, "exec:", &p)) { + vmaw->cmd = popen(p, "w"); + if (vmaw->cmd == NULL) { + error_setg(errp, "can't popen command '%s' - %s\n", p, + g_strerror(errno)); + goto err; + } + vmaw->fd = fileno(vmaw->cmd); + + /* try to use O_NONBLOCK */ + fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_NONBLOCK); + + } else { + struct stat st; + int oflags; + const char *tmp_id_str; + + if ((stat(filename, &st) == 0) && S_ISFIFO(st.st_mode)) { + oflags = O_NONBLOCK|O_WRONLY; + vmaw->fd = qemu_open(filename, oflags, 0644); + } else if (strstart(filename, "/dev/fdset/", &tmp_id_str)) { + oflags = O_NONBLOCK|O_WRONLY; + vmaw->fd = qemu_open(filename, oflags, 0644); + } else if (strstart(filename, "/dev/fdname/", &tmp_id_str)) { + vmaw->fd = monitor_get_fd(cur_mon, tmp_id_str, errp); + if (vmaw->fd < 0) { + goto err; + } + /* try to use O_NONBLOCK */ + fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_NONBLOCK); + } else { + oflags = O_NONBLOCK|O_DIRECT|O_WRONLY|O_CREAT|O_EXCL; + vmaw->fd = qemu_open(filename, oflags, 0644); + } + + if (vmaw->fd < 0) { + error_setg(errp, "can't open file %s - %s\n", filename, + g_strerror(errno)); + goto err; + } + } + + /* we use O_DIRECT, so we need to align IO buffers */ + + vmaw->outbuf = qemu_memalign(512, VMA_MAX_EXTENT_SIZE); + vmaw->headerbuf = qemu_memalign(512, HEADERBUF_SIZE); + + vmaw->outbuf_count = 0; + vmaw->outbuf_pos = VMA_EXTENT_HEADER_SIZE; + + vmaw->header_blob_table_pos = 1; /* start at pos 1 */ + + qemu_co_mutex_init(&vmaw->flush_lock); + + uuid_copy(vmaw->uuid, uuid); + + return vmaw; + +err: + if (vmaw) { + if (vmaw->cmd) { + pclose(vmaw->cmd); + } else if (vmaw->fd >= 0) { + close(vmaw->fd); + } + + if (vmaw->md5csum) { + g_checksum_free(vmaw->md5csum); + } + + g_free(vmaw); + } + + return NULL; +} + +static int coroutine_fn vma_write_header(VmaWriter *vmaw) +{ + assert(vmaw); + unsigned char *buf = vmaw->headerbuf; + VmaHeader *head = (VmaHeader *)buf; + + int i; + + DPRINTF("VMA WRITE HEADER\n"); + + if (vmaw->status < 0) { + return vmaw->status; + } + + memset(buf, 0, HEADERBUF_SIZE); + + head->magic = VMA_MAGIC; + head->version = GUINT32_TO_BE(1); /* v1 */ + memcpy(head->uuid, vmaw->uuid, 16); + + time_t ctime = time(NULL); + head->ctime = GUINT64_TO_BE(ctime); + + for (i = 0; i < VMA_MAX_CONFIGS; i++) { + head->config_names[i] = GUINT32_TO_BE(vmaw->config_names[i]); + head->config_data[i] = GUINT32_TO_BE(vmaw->config_data[i]); + } + + /* 32 bytes per device (12 used currently) = 8192 bytes max */ + for (i = 1; i <= 254; i++) { + VmaStreamInfo *si = &vmaw->stream_info[i]; + if (si->size) { + assert(si->devname); + uint32_t devname_ptr = allocate_header_string(vmaw, si->devname); + if (!devname_ptr) { + return -1; + } + head->dev_info[i].devname_ptr = GUINT32_TO_BE(devname_ptr); + head->dev_info[i].size = GUINT64_TO_BE(si->size); + } + } + + uint32_t header_size = sizeof(VmaHeader) + vmaw->header_blob_table_size; + head->header_size = GUINT32_TO_BE(header_size); + + if (header_size > HEADERBUF_SIZE) { + return -1; /* just to be sure */ + } + + uint32_t blob_buffer_offset = sizeof(VmaHeader); + memcpy(buf + blob_buffer_offset, vmaw->header_blob_table, + vmaw->header_blob_table_size); + head->blob_buffer_offset = GUINT32_TO_BE(blob_buffer_offset); + head->blob_buffer_size = GUINT32_TO_BE(vmaw->header_blob_table_pos); + + g_checksum_reset(vmaw->md5csum); + g_checksum_update(vmaw->md5csum, (const guchar *)buf, header_size); + gsize csize = 16; + g_checksum_get_digest(vmaw->md5csum, (guint8 *)(head->md5sum), &csize); + + return vma_queue_write(vmaw, buf, header_size); +} + +static int coroutine_fn vma_writer_flush(VmaWriter *vmaw) +{ + assert(vmaw); + + int ret; + int i; + + if (vmaw->status < 0) { + return vmaw->status; + } + + if (!vmaw->header_written) { + vmaw->header_written = true; + ret = vma_write_header(vmaw); + if (ret < 0) { + vma_writer_set_error(vmaw, "vma_writer_flush: write header failed"); + return ret; + } + } + + DPRINTF("VMA WRITE FLUSH %d %d\n", vmaw->outbuf_count, vmaw->outbuf_pos); + + + VmaExtentHeader *ehead = (VmaExtentHeader *)vmaw->outbuf; + + ehead->magic = VMA_EXTENT_MAGIC; + ehead->reserved1 = 0; + + for (i = 0; i < VMA_BLOCKS_PER_EXTENT; i++) { + ehead->blockinfo[i] = GUINT64_TO_BE(vmaw->outbuf_block_info[i]); + } + + guint16 block_count = (vmaw->outbuf_pos - VMA_EXTENT_HEADER_SIZE) / + VMA_BLOCK_SIZE; + + ehead->block_count = GUINT16_TO_BE(block_count); + + memcpy(ehead->uuid, vmaw->uuid, sizeof(ehead->uuid)); + memset(ehead->md5sum, 0, sizeof(ehead->md5sum)); + + g_checksum_reset(vmaw->md5csum); + g_checksum_update(vmaw->md5csum, vmaw->outbuf, VMA_EXTENT_HEADER_SIZE); + gsize csize = 16; + g_checksum_get_digest(vmaw->md5csum, ehead->md5sum, &csize); + + int bytes = vmaw->outbuf_pos; + ret = vma_queue_write(vmaw, vmaw->outbuf, bytes); + if (ret != bytes) { + vma_writer_set_error(vmaw, "vma_writer_flush: failed write"); + } + + vmaw->outbuf_count = 0; + vmaw->outbuf_pos = VMA_EXTENT_HEADER_SIZE; + + for (i = 0; i < VMA_BLOCKS_PER_EXTENT; i++) { + vmaw->outbuf_block_info[i] = 0; + } + + return vmaw->status; +} + +static int vma_count_open_streams(VmaWriter *vmaw) +{ + g_assert(vmaw != NULL); + + int i; + int open_drives = 0; + for (i = 0; i <= 255; i++) { + if (vmaw->stream_info[i].size && !vmaw->stream_info[i].finished) { + open_drives++; + } + } + + return open_drives; +} + + +/** + * You need to call this if the vma archive does not contain + * any data stream. + */ +int coroutine_fn +vma_writer_flush_output(VmaWriter *vmaw) +{ + qemu_co_mutex_lock(&vmaw->flush_lock); + int ret = vma_writer_flush(vmaw); + qemu_co_mutex_unlock(&vmaw->flush_lock); + if (ret < 0) { + vma_writer_set_error(vmaw, "vma_writer_flush_header failed"); + } + return ret; +} + +/** + * all jobs should call this when there is no more data + * Returns: number of remaining stream (0 ==> finished) + */ +int coroutine_fn +vma_writer_close_stream(VmaWriter *vmaw, uint8_t dev_id) +{ + g_assert(vmaw != NULL); + + DPRINTF("vma_writer_set_status %d\n", dev_id); + if (!vmaw->stream_info[dev_id].size) { + vma_writer_set_error(vmaw, "vma_writer_close_stream: " + "no such stream %d", dev_id); + return -1; + } + if (vmaw->stream_info[dev_id].finished) { + vma_writer_set_error(vmaw, "vma_writer_close_stream: " + "stream already closed %d", dev_id); + return -1; + } + + vmaw->stream_info[dev_id].finished = true; + + int open_drives = vma_count_open_streams(vmaw); + + if (open_drives <= 0) { + DPRINTF("vma_writer_set_status all drives completed\n"); + vma_writer_flush_output(vmaw); + } + + return open_drives; +} + +int vma_writer_get_status(VmaWriter *vmaw, VmaStatus *status) +{ + int i; + + g_assert(vmaw != NULL); + + if (status) { + status->status = vmaw->status; + g_strlcpy(status->errmsg, vmaw->errmsg, sizeof(status->errmsg)); + for (i = 0; i <= 255; i++) { + status->stream_info[i] = vmaw->stream_info[i]; + } + + uuid_unparse_lower(vmaw->uuid, status->uuid_str); + } + + status->closed = vmaw->closed; + + return vmaw->status; +} + +static int vma_writer_get_buffer(VmaWriter *vmaw) +{ + int ret = 0; + + qemu_co_mutex_lock(&vmaw->flush_lock); + + /* wait until buffer is available */ + while (vmaw->outbuf_count >= (VMA_BLOCKS_PER_EXTENT - 1)) { + ret = vma_writer_flush(vmaw); + if (ret < 0) { + vma_writer_set_error(vmaw, "vma_writer_get_buffer: flush failed"); + break; + } + } + + qemu_co_mutex_unlock(&vmaw->flush_lock); + + return ret; +} + + +int64_t coroutine_fn +vma_writer_write(VmaWriter *vmaw, uint8_t dev_id, int64_t cluster_num, + const unsigned char *buf, size_t *zero_bytes) +{ + g_assert(vmaw != NULL); + g_assert(zero_bytes != NULL); + + *zero_bytes = 0; + + if (vmaw->status < 0) { + return vmaw->status; + } + + if (!dev_id || !vmaw->stream_info[dev_id].size) { + vma_writer_set_error(vmaw, "vma_writer_write: " + "no such stream %d", dev_id); + return -1; + } + + if (vmaw->stream_info[dev_id].finished) { + vma_writer_set_error(vmaw, "vma_writer_write: " + "stream already closed %d", dev_id); + return -1; + } + + + if (cluster_num >= (((uint64_t)1)<<32)) { + vma_writer_set_error(vmaw, "vma_writer_write: " + "cluster number out of range"); + return -1; + } + + if (dev_id == vmaw->vmstate_stream) { + if (cluster_num != vmaw->vmstate_clusters) { + vma_writer_set_error(vmaw, "vma_writer_write: " + "non sequential vmstate write"); + } + vmaw->vmstate_clusters++; + } else if (cluster_num >= vmaw->stream_info[dev_id].cluster_count) { + vma_writer_set_error(vmaw, "vma_writer_write: cluster number too big"); + return -1; + } + + /* wait until buffer is available */ + if (vma_writer_get_buffer(vmaw) < 0) { + vma_writer_set_error(vmaw, "vma_writer_write: " + "vma_writer_get_buffer failed"); + return -1; + } + + DPRINTF("VMA WRITE %d %zd\n", dev_id, cluster_num); + + uint64_t dev_size = vmaw->stream_info[dev_id].size; + uint16_t mask = 0; + + if (buf) { + int i; + int bit = 1; + uint64_t byte_offset = cluster_num * VMA_CLUSTER_SIZE; + for (i = 0; i < 16; i++) { + const unsigned char *vmablock = buf + (i*VMA_BLOCK_SIZE); + + // Note: If the source is not 64k-aligned, we might reach 4k blocks + // after the end of the device. Always mark these as zero in the + // mask, so the restore handles them correctly. + if (byte_offset < dev_size && + !buffer_is_zero(vmablock, VMA_BLOCK_SIZE)) + { + mask |= bit; + memcpy(vmaw->outbuf + vmaw->outbuf_pos, vmablock, + VMA_BLOCK_SIZE); + + // prevent memory leakage on unaligned last block + if (byte_offset + VMA_BLOCK_SIZE > dev_size) { + uint64_t real_data_in_block = dev_size - byte_offset; + memset(vmaw->outbuf + vmaw->outbuf_pos + real_data_in_block, + 0, VMA_BLOCK_SIZE - real_data_in_block); + } + + vmaw->outbuf_pos += VMA_BLOCK_SIZE; + } else { + DPRINTF("VMA WRITE %zd ZERO BLOCK %d\n", cluster_num, i); + vmaw->stream_info[dev_id].zero_bytes += VMA_BLOCK_SIZE; + *zero_bytes += VMA_BLOCK_SIZE; + } + + byte_offset += VMA_BLOCK_SIZE; + bit = bit << 1; + } + } else { + DPRINTF("VMA WRITE %zd ZERO CLUSTER\n", cluster_num); + vmaw->stream_info[dev_id].zero_bytes += VMA_CLUSTER_SIZE; + *zero_bytes += VMA_CLUSTER_SIZE; + } + + uint64_t block_info = ((uint64_t)mask) << (32+16); + block_info |= ((uint64_t)dev_id) << 32; + block_info |= (cluster_num & 0xffffffff); + vmaw->outbuf_block_info[vmaw->outbuf_count] = block_info; + + DPRINTF("VMA WRITE MASK %zd %zx\n", cluster_num, block_info); + + vmaw->outbuf_count++; + + /** NOTE: We allways write whole clusters, but we correctly set + * transferred bytes. So transferred == size when when everything + * went OK. + */ + size_t transferred = VMA_CLUSTER_SIZE; + + if (dev_id != vmaw->vmstate_stream) { + uint64_t last = (cluster_num + 1) * VMA_CLUSTER_SIZE; + if (last > dev_size) { + uint64_t diff = last - dev_size; + if (diff >= VMA_CLUSTER_SIZE) { + vma_writer_set_error(vmaw, "vma_writer_write: " + "read after last cluster"); + return -1; + } + transferred -= diff; + } + } + + vmaw->stream_info[dev_id].transferred += transferred; + + return transferred; +} + +void vma_writer_error_propagate(VmaWriter *vmaw, Error **errp) +{ + if (vmaw->status < 0 && *errp == NULL) { + error_setg(errp, "%s", vmaw->errmsg); + } +} + +int vma_writer_close(VmaWriter *vmaw, Error **errp) +{ + g_assert(vmaw != NULL); + + int i; + + qemu_co_mutex_lock(&vmaw->flush_lock); // wait for pending writes + + assert(vmaw->co_writer == NULL); + + if (vmaw->cmd) { + if (pclose(vmaw->cmd) < 0) { + vma_writer_set_error(vmaw, "vma_writer_close: " + "pclose failed - %s", g_strerror(errno)); + } + } else { + if (close(vmaw->fd) < 0) { + vma_writer_set_error(vmaw, "vma_writer_close: " + "close failed - %s", g_strerror(errno)); + } + } + + for (i = 0; i <= 255; i++) { + VmaStreamInfo *si = &vmaw->stream_info[i]; + if (si->size) { + if (!si->finished) { + vma_writer_set_error(vmaw, "vma_writer_close: " + "detected open stream '%s'", si->devname); + } else if ((si->transferred != si->size) && + (i != vmaw->vmstate_stream)) { + vma_writer_set_error(vmaw, "vma_writer_close: " + "incomplete stream '%s' (%zd != %zd)", + si->devname, si->transferred, si->size); + } + } + } + + for (i = 0; i <= 255; i++) { + vmaw->stream_info[i].finished = 1; /* mark as closed */ + } + + vmaw->closed = 1; + + if (vmaw->status < 0 && *errp == NULL) { + error_setg(errp, "%s", vmaw->errmsg); + } + + qemu_co_mutex_unlock(&vmaw->flush_lock); + + return vmaw->status; +} + +void vma_writer_destroy(VmaWriter *vmaw) +{ + assert(vmaw); + + int i; + + for (i = 0; i <= 255; i++) { + if (vmaw->stream_info[i].devname) { + g_free(vmaw->stream_info[i].devname); + } + } + + if (vmaw->md5csum) { + g_checksum_free(vmaw->md5csum); + } + + qemu_vfree(vmaw->headerbuf); + qemu_vfree(vmaw->outbuf); + g_free(vmaw); +} diff --git a/vma.c b/vma.c new file mode 100644 index 0000000000..2eea2fc281 --- /dev/null +++ b/vma.c @@ -0,0 +1,839 @@ +/* + * VMA: Virtual Machine Archive + * + * Copyright (C) 2012-2013 Proxmox Server Solutions + * + * Authors: + * Dietmar Maurer (dietmar@proxmox.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 + +#include "vma.h" +#include "qemu-common.h" +#include "qemu/module.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "qemu/cutils.h" +#include "qapi/qmp/qdict.h" +#include "sysemu/block-backend.h" + +static void help(void) +{ + const char *help_msg = + "usage: vma command [command options]\n" + "\n" + "vma list \n" + "vma config [-c config]\n" + "vma create [-c config] pathname ...\n" + "vma extract [-r ] \n" + "vma verify [-v]\n" + ; + + printf("%s", help_msg); + exit(1); +} + +static const char *extract_devname(const char *path, char **devname, int index) +{ + assert(path); + + const char *sep = strchr(path, '='); + + if (sep) { + *devname = g_strndup(path, sep - path); + path = sep + 1; + } else { + if (index >= 0) { + *devname = g_strdup_printf("disk%d", index); + } else { + *devname = NULL; + } + } + + return path; +} + +static void print_content(VmaReader *vmar) +{ + assert(vmar); + + VmaHeader *head = vma_reader_get_header(vmar); + + GList *l = vma_reader_get_config_data(vmar); + while (l && l->data) { + VmaConfigData *cdata = (VmaConfigData *)l->data; + l = g_list_next(l); + printf("CFG: size: %d name: %s\n", cdata->len, cdata->name); + } + + int i; + VmaDeviceInfo *di; + for (i = 1; i < 255; i++) { + di = vma_reader_get_device_info(vmar, i); + if (di) { + if (strcmp(di->devname, "vmstate") == 0) { + printf("VMSTATE: dev_id=%d memory: %zd\n", i, di->size); + } else { + printf("DEV: dev_id=%d size: %zd devname: %s\n", + i, di->size, di->devname); + } + } + } + /* ctime is the last entry we print */ + printf("CTIME: %s", ctime(&head->ctime)); + fflush(stdout); +} + +static int list_content(int argc, char **argv) +{ + int c, ret = 0; + const char *filename; + + for (;;) { + c = getopt(argc, argv, "h"); + if (c == -1) { + break; + } + switch (c) { + case '?': + case 'h': + help(); + break; + default: + g_assert_not_reached(); + } + } + + /* Get the filename */ + if ((optind + 1) != argc) { + help(); + } + filename = argv[optind++]; + + Error *errp = NULL; + VmaReader *vmar = vma_reader_create(filename, &errp); + + if (!vmar) { + g_error("%s", error_get_pretty(errp)); + } + + print_content(vmar); + + vma_reader_destroy(vmar); + + return ret; +} + +typedef struct RestoreMap { + char *devname; + char *path; + char *format; + uint64_t throttling_bps; + char *throttling_group; + char *cache; + bool write_zero; +} RestoreMap; + +static bool try_parse_option(char **line, const char *optname, char **out, const char *inbuf) { + size_t optlen = strlen(optname); + if (strncmp(*line, optname, optlen) != 0 || (*line)[optlen] != '=') { + return false; + } + if (*out) { + g_error("read map failed - duplicate value for option '%s'", optname); + } + char *value = (*line) + optlen + 1; /* including a '=' */ + char *colon = strchr(value, ':'); + if (!colon) { + g_error("read map failed - option '%s' not terminated ('%s')", + optname, inbuf); + } + *line = colon+1; + *out = g_strndup(value, colon - value); + return true; +} + +static uint64_t verify_u64(const char *text) { + uint64_t value; + const char *endptr = NULL; + if (qemu_strtou64(text, &endptr, 0, &value) != 0 || !endptr || *endptr) { + g_error("read map failed - not a number: %s", text); + } + return value; +} + +static int extract_content(int argc, char **argv) +{ + int c, ret = 0; + int verbose = 0; + const char *filename; + const char *dirname; + const char *readmap = NULL; + + for (;;) { + c = getopt(argc, argv, "hvr:"); + if (c == -1) { + break; + } + switch (c) { + case '?': + case 'h': + help(); + break; + case 'r': + readmap = optarg; + break; + case 'v': + verbose = 1; + break; + default: + help(); + } + } + + /* Get the filename */ + if ((optind + 2) != argc) { + help(); + } + filename = argv[optind++]; + dirname = argv[optind++]; + + Error *errp = NULL; + VmaReader *vmar = vma_reader_create(filename, &errp); + + if (!vmar) { + g_error("%s", error_get_pretty(errp)); + } + + if (mkdir(dirname, 0777) < 0) { + g_error("unable to create target directory %s - %s", + dirname, g_strerror(errno)); + } + + GList *l = vma_reader_get_config_data(vmar); + while (l && l->data) { + VmaConfigData *cdata = (VmaConfigData *)l->data; + l = g_list_next(l); + char *cfgfn = g_strdup_printf("%s/%s", dirname, cdata->name); + GError *err = NULL; + if (!g_file_set_contents(cfgfn, (gchar *)cdata->data, cdata->len, + &err)) { + g_error("unable to write file: %s", err->message); + } + } + + GHashTable *devmap = g_hash_table_new(g_str_hash, g_str_equal); + + if (readmap) { + print_content(vmar); + + FILE *map = fopen(readmap, "r"); + if (!map) { + g_error("unable to open fifo %s - %s", readmap, g_strerror(errno)); + } + + while (1) { + char inbuf[8192]; + char *line = fgets(inbuf, sizeof(inbuf), map); + char *format = NULL; + char *bps = NULL; + char *group = NULL; + char *cache = NULL; + if (!line || line[0] == '\0' || !strcmp(line, "done\n")) { + break; + } + int len = strlen(line); + if (line[len - 1] == '\n') { + line[len - 1] = '\0'; + if (len == 1) { + break; + } + } + + while (1) { + if (!try_parse_option(&line, "format", &format, inbuf) && + !try_parse_option(&line, "throttling.bps", &bps, inbuf) && + !try_parse_option(&line, "throttling.group", &group, inbuf) && + !try_parse_option(&line, "cache", &cache, inbuf)) + { + break; + } + } + + uint64_t bps_value = 0; + if (bps) { + bps_value = verify_u64(bps); + g_free(bps); + } + + const char *path; + bool write_zero; + if (line[0] == '0' && line[1] == ':') { + path = line + 2; + write_zero = false; + } else if (line[0] == '1' && line[1] == ':') { + path = line + 2; + write_zero = true; + } else { + g_error("read map failed - parse error ('%s')", inbuf); + } + + char *devname = NULL; + path = extract_devname(path, &devname, -1); + if (!devname) { + g_error("read map failed - no dev name specified ('%s')", + inbuf); + } + + RestoreMap *map = g_new0(RestoreMap, 1); + map->devname = g_strdup(devname); + map->path = g_strdup(path); + map->format = format; + map->throttling_bps = bps_value; + map->throttling_group = group; + map->cache = cache; + map->write_zero = write_zero; + + g_hash_table_insert(devmap, map->devname, map); + + }; + } + + int i; + int vmstate_fd = -1; + guint8 vmstate_stream = 0; + + BlockBackend *blk = NULL; + + for (i = 1; i < 255; i++) { + VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i); + if (di && (strcmp(di->devname, "vmstate") == 0)) { + vmstate_stream = i; + char *statefn = g_strdup_printf("%s/vmstate.bin", dirname); + vmstate_fd = open(statefn, O_WRONLY|O_CREAT|O_EXCL, 0644); + if (vmstate_fd < 0) { + g_error("create vmstate file '%s' failed - %s", statefn, + g_strerror(errno)); + } + g_free(statefn); + } else if (di) { + char *devfn = NULL; + const char *format = NULL; + uint64_t throttling_bps = 0; + const char *throttling_group = NULL; + const char *cache = NULL; + int flags = BDRV_O_RDWR; + bool write_zero = true; + + if (readmap) { + RestoreMap *map; + map = (RestoreMap *)g_hash_table_lookup(devmap, di->devname); + if (map == NULL) { + g_error("no device name mapping for %s", di->devname); + } + devfn = map->path; + format = map->format; + throttling_bps = map->throttling_bps; + throttling_group = map->throttling_group; + cache = map->cache; + write_zero = map->write_zero; + } else { + devfn = g_strdup_printf("%s/tmp-disk-%s.raw", + dirname, di->devname); + printf("DEVINFO %s %zd\n", devfn, di->size); + + bdrv_img_create(devfn, "raw", NULL, NULL, NULL, di->size, + flags, true, &errp); + if (errp) { + g_error("can't create file %s: %s", devfn, + error_get_pretty(errp)); + } + + /* Note: we created an empty file above, so there is no + * need to write zeroes (so we generate a sparse file) + */ + write_zero = false; + } + + size_t devlen = strlen(devfn); + QDict *options = NULL; + bool writethrough; + if (format) { + /* explicit format from commandline */ + options = qdict_new(); + qdict_put_str(options, "driver", format); + } else if ((devlen > 4 && strcmp(devfn+devlen-4, ".raw") == 0) || + strncmp(devfn, "/dev/", 5) == 0) + { + /* This part is now deprecated for PVE as well (just as qemu + * deprecated not specifying an explicit raw format, too. + */ + /* explicit raw format */ + options = qdict_new(); + qdict_put_str(options, "driver", "raw"); + } + if (cache && bdrv_parse_cache_mode(cache, &flags, &writethrough)) { + g_error("invalid cache option: %s\n", cache); + } + + if (errp || !(blk = blk_new_open(devfn, NULL, options, flags, &errp))) { + g_error("can't open file %s - %s", devfn, + error_get_pretty(errp)); + } + + if (cache) { + blk_set_enable_write_cache(blk, !writethrough); + } + + if (throttling_group) { + blk_io_limits_enable(blk, throttling_group); + } + + if (throttling_bps) { + if (!throttling_group) { + blk_io_limits_enable(blk, devfn); + } + + ThrottleConfig cfg; + throttle_config_init(&cfg); + cfg.buckets[THROTTLE_BPS_WRITE].avg = throttling_bps; + Error *err = NULL; + if (!throttle_is_valid(&cfg, &err)) { + error_report_err(err); + g_error("failed to apply throttling"); + } + blk_set_io_limits(blk, &cfg); + } + + if (vma_reader_register_bs(vmar, i, blk, write_zero, &errp) < 0) { + g_error("%s", error_get_pretty(errp)); + } + + if (!readmap) { + g_free(devfn); + } + } + } + + if (vma_reader_restore(vmar, vmstate_fd, verbose, &errp) < 0) { + g_error("restore failed - %s", error_get_pretty(errp)); + } + + if (!readmap) { + for (i = 1; i < 255; i++) { + VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i); + if (di && (i != vmstate_stream)) { + char *tmpfn = g_strdup_printf("%s/tmp-disk-%s.raw", + dirname, di->devname); + char *fn = g_strdup_printf("%s/disk-%s.raw", + dirname, di->devname); + if (rename(tmpfn, fn) != 0) { + g_error("rename %s to %s failed - %s", + tmpfn, fn, g_strerror(errno)); + } + } + } + } + + vma_reader_destroy(vmar); + + blk_unref(blk); + + bdrv_close_all(); + + return ret; +} + +static int verify_content(int argc, char **argv) +{ + int c, ret = 0; + int verbose = 0; + const char *filename; + + for (;;) { + c = getopt(argc, argv, "hv"); + if (c == -1) { + break; + } + switch (c) { + case '?': + case 'h': + help(); + break; + case 'v': + verbose = 1; + break; + default: + help(); + } + } + + /* Get the filename */ + if ((optind + 1) != argc) { + help(); + } + filename = argv[optind++]; + + Error *errp = NULL; + VmaReader *vmar = vma_reader_create(filename, &errp); + + if (!vmar) { + g_error("%s", error_get_pretty(errp)); + } + + if (verbose) { + print_content(vmar); + } + + if (vma_reader_verify(vmar, verbose, &errp) < 0) { + g_error("verify failed - %s", error_get_pretty(errp)); + } + + vma_reader_destroy(vmar); + + bdrv_close_all(); + + return ret; +} + +typedef struct BackupJob { + BlockBackend *target; + int64_t len; + VmaWriter *vmaw; + uint8_t dev_id; +} BackupJob; + +#define BACKUP_SECTORS_PER_CLUSTER (VMA_CLUSTER_SIZE / BDRV_SECTOR_SIZE) + +static void coroutine_fn backup_run_empty(void *opaque) +{ + VmaWriter *vmaw = (VmaWriter *)opaque; + + vma_writer_flush_output(vmaw); + + Error *err = NULL; + if (vma_writer_close(vmaw, &err) != 0) { + g_warning("vma_writer_close failed %s", error_get_pretty(err)); + } +} + +static void coroutine_fn backup_run(void *opaque) +{ + BackupJob *job = (BackupJob *)opaque; + struct iovec iov; + QEMUIOVector qiov; + + int64_t start, end; + int ret = 0; + + unsigned char *buf = blk_blockalign(job->target, VMA_CLUSTER_SIZE); + + start = 0; + end = DIV_ROUND_UP(job->len / BDRV_SECTOR_SIZE, + BACKUP_SECTORS_PER_CLUSTER); + + for (; start < end; start++) { + iov.iov_base = buf; + iov.iov_len = VMA_CLUSTER_SIZE; + qemu_iovec_init_external(&qiov, &iov, 1); + + ret = blk_co_preadv(job->target, start * VMA_CLUSTER_SIZE, + VMA_CLUSTER_SIZE, &qiov, 0); + if (ret < 0) { + vma_writer_set_error(job->vmaw, "read error", -1); + goto out; + } + + size_t zb = 0; + if (vma_writer_write(job->vmaw, job->dev_id, start, buf, &zb) < 0) { + vma_writer_set_error(job->vmaw, "backup_dump_cb vma_writer_write failed", -1); + goto out; + } + } + + +out: + if (vma_writer_close_stream(job->vmaw, job->dev_id) <= 0) { + Error *err = NULL; + if (vma_writer_close(job->vmaw, &err) != 0) { + g_warning("vma_writer_close failed %s", error_get_pretty(err)); + } + } + qemu_vfree(buf); +} + +static int create_archive(int argc, char **argv) +{ + int i, c; + int verbose = 0; + const char *archivename; + GList *config_files = NULL; + + for (;;) { + c = getopt(argc, argv, "hvc:"); + if (c == -1) { + break; + } + switch (c) { + case '?': + case 'h': + help(); + break; + case 'c': + config_files = g_list_append(config_files, optarg); + break; + case 'v': + verbose = 1; + break; + default: + g_assert_not_reached(); + } + } + + + /* make sure we an archive name */ + if ((optind + 1) > argc) { + help(); + } + + archivename = argv[optind++]; + + uuid_t uuid; + uuid_generate(uuid); + + Error *local_err = NULL; + VmaWriter *vmaw = vma_writer_create(archivename, uuid, &local_err); + + if (vmaw == NULL) { + g_error("%s", error_get_pretty(local_err)); + } + + GList *l = config_files; + while (l && l->data) { + char *name = l->data; + char *cdata = NULL; + gsize clen = 0; + GError *err = NULL; + if (!g_file_get_contents(name, &cdata, &clen, &err)) { + unlink(archivename); + g_error("Unable to read file: %s", err->message); + } + + if (vma_writer_add_config(vmaw, name, cdata, clen) != 0) { + unlink(archivename); + g_error("Unable to append config data %s (len = %zd)", + name, clen); + } + l = g_list_next(l); + } + + int devcount = 0; + while (optind < argc) { + const char *path = argv[optind++]; + char *devname = NULL; + path = extract_devname(path, &devname, devcount++); + + Error *errp = NULL; + BlockBackend *target; + + target = blk_new_open(path, NULL, NULL, 0, &errp); + if (!target) { + unlink(archivename); + g_error("bdrv_open '%s' failed - %s", path, error_get_pretty(errp)); + } + int64_t size = blk_getlength(target); + int dev_id = vma_writer_register_stream(vmaw, devname, size); + if (dev_id <= 0) { + unlink(archivename); + g_error("vma_writer_register_stream '%s' failed", devname); + } + + BackupJob *job = g_new0(BackupJob, 1); + job->len = size; + job->target = target; + job->vmaw = vmaw; + job->dev_id = dev_id; + + Coroutine *co = qemu_coroutine_create(backup_run, job); + qemu_coroutine_enter(co); + } + + VmaStatus vmastat; + int percent = 0; + int last_percent = -1; + + if (devcount) { + while (1) { + main_loop_wait(false); + vma_writer_get_status(vmaw, &vmastat); + + if (verbose) { + + uint64_t total = 0; + uint64_t transferred = 0; + uint64_t zero_bytes = 0; + + int i; + for (i = 0; i < 256; i++) { + if (vmastat.stream_info[i].size) { + total += vmastat.stream_info[i].size; + transferred += vmastat.stream_info[i].transferred; + zero_bytes += vmastat.stream_info[i].zero_bytes; + } + } + percent = (transferred*100)/total; + if (percent != last_percent) { + fprintf(stderr, "progress %d%% %zd/%zd %zd\n", percent, + transferred, total, zero_bytes); + fflush(stderr); + + last_percent = percent; + } + } + + if (vmastat.closed) { + break; + } + } + } else { + Coroutine *co = qemu_coroutine_create(backup_run_empty, vmaw); + qemu_coroutine_enter(co); + while (1) { + main_loop_wait(false); + vma_writer_get_status(vmaw, &vmastat); + if (vmastat.closed) { + break; + } + } + } + + bdrv_drain_all(); + + vma_writer_get_status(vmaw, &vmastat); + + if (verbose) { + for (i = 0; i < 256; i++) { + VmaStreamInfo *si = &vmastat.stream_info[i]; + if (si->size) { + fprintf(stderr, "image %s: size=%zd zeros=%zd saved=%zd\n", + si->devname, si->size, si->zero_bytes, + si->size - si->zero_bytes); + } + } + } + + if (vmastat.status < 0) { + unlink(archivename); + g_error("creating vma archive failed"); + } + + vma_writer_destroy(vmaw); + return 0; +} + +static int dump_config(int argc, char **argv) +{ + int c, ret = 0; + const char *filename; + const char *config_name = "qemu-server.conf"; + + for (;;) { + c = getopt(argc, argv, "hc:"); + if (c == -1) { + break; + } + switch (c) { + case '?': + case 'h': + help(); + break; + case 'c': + config_name = optarg; + break; + default: + help(); + } + } + + /* Get the filename */ + if ((optind + 1) != argc) { + help(); + } + filename = argv[optind++]; + + Error *errp = NULL; + VmaReader *vmar = vma_reader_create(filename, &errp); + + if (!vmar) { + g_error("%s", error_get_pretty(errp)); + } + + int found = 0; + GList *l = vma_reader_get_config_data(vmar); + while (l && l->data) { + VmaConfigData *cdata = (VmaConfigData *)l->data; + l = g_list_next(l); + if (strcmp(cdata->name, config_name) == 0) { + found = 1; + fwrite(cdata->data, cdata->len, 1, stdout); + break; + } + } + + vma_reader_destroy(vmar); + + bdrv_close_all(); + + if (!found) { + fprintf(stderr, "unable to find configuration data '%s'\n", config_name); + return -1; + } + + return ret; +} + +int main(int argc, char **argv) +{ + const char *cmdname; + Error *main_loop_err = NULL; + + error_init(argv[0]); + module_call_init(MODULE_INIT_TRACE); + qemu_init_exec_dir(argv[0]); + + if (qemu_init_main_loop(&main_loop_err)) { + g_error("%s", error_get_pretty(main_loop_err)); + } + + bdrv_init(); + module_call_init(MODULE_INIT_QOM); + + if (argc < 2) { + help(); + } + + cmdname = argv[1]; + argc--; argv++; + + + if (!strcmp(cmdname, "list")) { + return list_content(argc, argv); + } else if (!strcmp(cmdname, "create")) { + return create_archive(argc, argv); + } else if (!strcmp(cmdname, "extract")) { + return extract_content(argc, argv); + } else if (!strcmp(cmdname, "verify")) { + return verify_content(argc, argv); + } else if (!strcmp(cmdname, "config")) { + return dump_config(argc, argv); + } + + help(); + return 0; +} diff --git a/vma.h b/vma.h new file mode 100644 index 0000000000..c895c97f6d --- /dev/null +++ b/vma.h @@ -0,0 +1,150 @@ +/* + * VMA: Virtual Machine Archive + * + * Copyright (C) Proxmox Server Solutions + * + * Authors: + * Dietmar Maurer (dietmar@proxmox.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 BACKUP_VMA_H +#define BACKUP_VMA_H + +#include +#include "qapi/error.h" +#include "block/block.h" + +#define VMA_BLOCK_BITS 12 +#define VMA_BLOCK_SIZE (1<