block: add basic backup support to block driver

backup_start() creates a block job that copies a point-in-time snapshot
of a block device to a target block device.

We call backup_do_cow() for each write during backup. That function
reads the original data from the block device before it gets
overwritten.  The data is then written to the target device.

Currently backup cluster size is hardcoded to 65536 bytes.

[I made a number of changes to Dietmar's original patch and folded them
in to make code review easy.  Here is the full list:

 * Drop BackupDumpFunc interface in favor of a target block device
 * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes()
 * Use 0 delay instead of 1us, like other block jobs
 * Unify creation/start functions into backup_start()
 * Simplify cleanup, free bitmap in backup_run() instead of cb
 * function
 * Use HBitmap to avoid duplicating bitmap code
 * Use bdrv_getlength() instead of accessing ->total_sectors
 * directly
 * Delete the backup.h header file, it is no longer necessary
 * Move ./backup.c to block/backup.c
 * Remove #ifdefed out code
 * Coding style and whitespace cleanups
 * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks
 * Keep our own in-flight CowRequest list instead of using block.c
   tracked requests.  This means a little code duplication but is much
   simpler than trying to share the tracked requests list and use the
   backup block size.
 * Add on_source_error and on_target_error error handling.
 * Use trace events instead of DPRINTF()

-- stefanha]

Signed-off-by: Dietmar Maurer <dietmar@proxmox.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

4 files changed, 369 insertions, 0 deletions

diff --git a/block/Makefile.objs b/block/Makefile.objs
index 2981654846..4cf9aa499f 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -21,5 +21,6 @@ endif
 common-obj-y += stream.o
 common-obj-y += commit.o
 common-obj-y += mirror.o
+common-obj-y += backup.o
 
 $(obj)/curl.o: QEMU_CFLAGS+=$(CURL_CFLAGS)
diff --git a/block/backup.c b/block/backup.c
new file mode 100644
index 0000000000..16105d40b1
--- /dev/null
+++ b/block/backup.c
@@ -0,0 +1,341 @@
+/*
+ * QEMU backup
+ *
+ * Copyright (C) 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 <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+
+#include "trace.h"
+#include "block/block.h"
+#include "block/block_int.h"
+#include "block/blockjob.h"
+#include "qemu/ratelimit.h"
+
+#define BACKUP_CLUSTER_BITS 16
+#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
+#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
+
+#define SLICE_TIME 100000000ULL /* ns */
+
+typedef struct CowRequest {
+    int64_t start;
+    int64_t end;
+    QLIST_ENTRY(CowRequest) list;
+    CoQueue wait_queue; /* coroutines blocked on this request */
+} CowRequest;
+
+typedef struct BackupBlockJob {
+    BlockJob common;
+    BlockDriverState *target;
+    RateLimit limit;
+    BlockdevOnError on_source_error;
+    BlockdevOnError on_target_error;
+    CoRwlock flush_rwlock;
+    uint64_t sectors_read;
+    HBitmap *bitmap;
+    QLIST_HEAD(, CowRequest) inflight_reqs;
+} BackupBlockJob;
+
+/* See if in-flight requests overlap and wait for them to complete */
+static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
+                                                       int64_t start,
+                                                       int64_t end)
+{
+    CowRequest *req;
+    bool retry;
+
+    do {
+        retry = false;
+        QLIST_FOREACH(req, &job->inflight_reqs, list) {
+            if (end > req->start && start < req->end) {
+                qemu_co_queue_wait(&req->wait_queue);
+                retry = true;
+                break;
+            }
+        }
+    } while (retry);
+}
+
+/* Keep track of an in-flight request */
+static void cow_request_begin(CowRequest *req, BackupBlockJob *job,
+                                     int64_t start, int64_t end)
+{
+    req->start = start;
+    req->end = end;
+    qemu_co_queue_init(&req->wait_queue);
+    QLIST_INSERT_HEAD(&job->inflight_reqs, req, list);
+}
+
+/* Forget about a completed request */
+static void cow_request_end(CowRequest *req)
+{
+    QLIST_REMOVE(req, list);
+    qemu_co_queue_restart_all(&req->wait_queue);
+}
+
+static int coroutine_fn backup_do_cow(BlockDriverState *bs,
+                                      int64_t sector_num, int nb_sectors,
+                                      bool *error_is_read)
+{
+    BackupBlockJob *job = (BackupBlockJob *)bs->job;
+    CowRequest cow_request;
+    struct iovec iov;
+    QEMUIOVector bounce_qiov;
+    void *bounce_buffer = NULL;
+    int ret = 0;
+    int64_t start, end;
+    int n;
+
+    qemu_co_rwlock_rdlock(&job->flush_rwlock);
+
+    start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
+    end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
+
+    trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
+
+    wait_for_overlapping_requests(job, start, end);
+    cow_request_begin(&cow_request, job, start, end);
+
+    for (; start < end; start++) {
+        if (hbitmap_get(job->bitmap, start)) {
+            trace_backup_do_cow_skip(job, start);
+            continue; /* already copied */
+        }
+
+        trace_backup_do_cow_process(job, start);
+
+        n = MIN(BACKUP_SECTORS_PER_CLUSTER,
+                job->common.len / BDRV_SECTOR_SIZE -
+                start * BACKUP_SECTORS_PER_CLUSTER);
+
+        if (!bounce_buffer) {
+            bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
+        }
+        iov.iov_base = bounce_buffer;
+        iov.iov_len = n * BDRV_SECTOR_SIZE;
+        qemu_iovec_init_external(&bounce_qiov, &iov, 1);
+
+        ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
+                            &bounce_qiov);
+        if (ret < 0) {
+            trace_backup_do_cow_read_fail(job, start, ret);
+            if (error_is_read) {
+                *error_is_read = true;
+            }
+            goto out;
+        }
+
+        if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
+            ret = bdrv_co_write_zeroes(job->target,
+                                       start * BACKUP_SECTORS_PER_CLUSTER, n);
+        } else {
+            ret = bdrv_co_writev(job->target,
+                                 start * BACKUP_SECTORS_PER_CLUSTER, n,
+                                 &bounce_qiov);
+        }
+        if (ret < 0) {
+            trace_backup_do_cow_write_fail(job, start, ret);
+            if (error_is_read) {
+                *error_is_read = false;
+            }
+            goto out;
+        }
+
+        hbitmap_set(job->bitmap, start, 1);
+
+        /* Publish progress, guest I/O counts as progress too.  Note that the
+         * offset field is an opaque progress value, it is not a disk offset.
+         */
+        job->sectors_read += n;
+        job->common.offset += n * BDRV_SECTOR_SIZE;
+    }
+
+out:
+    if (bounce_buffer) {
+        qemu_vfree(bounce_buffer);
+    }
+
+    cow_request_end(&cow_request);
+
+    trace_backup_do_cow_return(job, sector_num, nb_sectors, ret);
+
+    qemu_co_rwlock_unlock(&job->flush_rwlock);
+
+    return ret;
+}
+
+static int coroutine_fn backup_before_write_notify(
+        NotifierWithReturn *notifier,
+        void *opaque)
+{
+    BdrvTrackedRequest *req = opaque;
+
+    return backup_do_cow(req->bs, req->sector_num, req->nb_sectors, NULL);
+}
+
+static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+    if (speed < 0) {
+        error_set(errp, QERR_INVALID_PARAMETER, "speed");
+        return;
+    }
+    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
+}
+
+static void backup_iostatus_reset(BlockJob *job)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+    bdrv_iostatus_reset(s->target);
+}
+
+static const BlockJobType backup_job_type = {
+    .instance_size  = sizeof(BackupBlockJob),
+    .job_type       = "backup",
+    .set_speed      = backup_set_speed,
+    .iostatus_reset = backup_iostatus_reset,
+};
+
+static BlockErrorAction backup_error_action(BackupBlockJob *job,
+                                            bool read, int error)
+{
+    if (read) {
+        return block_job_error_action(&job->common, job->common.bs,
+                                      job->on_source_error, true, error);
+    } else {
+        return block_job_error_action(&job->common, job->target,
+                                      job->on_target_error, false, error);
+    }
+}
+
+static void coroutine_fn backup_run(void *opaque)
+{
+    BackupBlockJob *job = opaque;
+    BlockDriverState *bs = job->common.bs;
+    BlockDriverState *target = job->target;
+    BlockdevOnError on_target_error = job->on_target_error;
+    NotifierWithReturn before_write = {
+        .notify = backup_before_write_notify,
+    };
+    int64_t start, end;
+    int ret = 0;
+
+    QLIST_INIT(&job->inflight_reqs);
+    qemu_co_rwlock_init(&job->flush_rwlock);
+
+    start = 0;
+    end = DIV_ROUND_UP(job->common.len / BDRV_SECTOR_SIZE,
+                       BACKUP_SECTORS_PER_CLUSTER);
+
+    job->bitmap = hbitmap_alloc(end, 0);
+
+    bdrv_set_enable_write_cache(target, true);
+    bdrv_set_on_error(target, on_target_error, on_target_error);
+    bdrv_iostatus_enable(target);
+
+    bdrv_add_before_write_notifier(bs, &before_write);
+
+    for (; start < end; start++) {
+        bool error_is_read;
+
+        if (block_job_is_cancelled(&job->common)) {
+            break;
+        }
+
+        /* we need to yield so that qemu_aio_flush() returns.
+         * (without, VM does not reboot)
+         */
+        if (job->common.speed) {
+            uint64_t delay_ns = ratelimit_calculate_delay(
+                &job->limit, job->sectors_read);
+            job->sectors_read = 0;
+            block_job_sleep_ns(&job->common, rt_clock, delay_ns);
+        } else {
+            block_job_sleep_ns(&job->common, rt_clock, 0);
+        }
+
+        if (block_job_is_cancelled(&job->common)) {
+            break;
+        }
+
+        ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
+                            BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
+        if (ret < 0) {
+            /* Depending on error action, fail now or retry cluster */
+            BlockErrorAction action =
+                backup_error_action(job, error_is_read, -ret);
+            if (action == BDRV_ACTION_REPORT) {
+                break;
+            } else {
+                start--;
+                continue;
+            }
+        }
+    }
+
+    notifier_with_return_remove(&before_write);
+
+    /* wait until pending backup_do_cow() calls have completed */
+    qemu_co_rwlock_wrlock(&job->flush_rwlock);
+    qemu_co_rwlock_unlock(&job->flush_rwlock);
+
+    hbitmap_free(job->bitmap);
+
+    bdrv_iostatus_disable(target);
+    bdrv_delete(target);
+
+    block_job_completed(&job->common, ret);
+}
+
+void backup_start(BlockDriverState *bs, BlockDriverState *target,
+                  int64_t speed,
+                  BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
+                  BlockDriverCompletionFunc *cb, void *opaque,
+                  Error **errp)
+{
+    int64_t len;
+
+    assert(bs);
+    assert(target);
+    assert(cb);
+
+    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
+         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
+        !bdrv_iostatus_is_enabled(bs)) {
+        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
+        return;
+    }
+
+    len = bdrv_getlength(bs);
+    if (len < 0) {
+        error_setg_errno(errp, -len, "unable to get length for '%s'",
+                         bdrv_get_device_name(bs));
+        return;
+    }
+
+    BackupBlockJob *job = block_job_create(&backup_job_type, bs, speed,
+                                           cb, opaque, errp);
+    if (!job) {
+        return;
+    }
+
+    job->on_source_error = on_source_error;
+    job->on_target_error = on_target_error;
+    job->target = target;
+    job->common.len = len;
+    job->common.co = qemu_coroutine_create(backup_run);
+    qemu_coroutine_enter(job->common.co, job);
+}
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 2d009556b0..c6ac871e21 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -399,4 +399,23 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp);
 
+/*
+ * backup_start:
+ * @bs: Block device to operate on.
+ * @target: Block device to write to.
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ *
+ * Start a backup operation on @bs.  Clusters in @bs are written to @target
+ * until the job is cancelled or manually completed.
+ */
+void backup_start(BlockDriverState *bs, BlockDriverState *target,
+                  int64_t speed, BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
+                  BlockDriverCompletionFunc *cb, void *opaque,
+                  Error **errp);
+
 #endif /* BLOCK_INT_H */
diff --git a/trace-events b/trace-events
index c5f1ccb96d..0acce7b350 100644
--- a/trace-events
+++ b/trace-events
@@ -92,6 +92,14 @@ mirror_yield_in_flight(void *s, int64_t sector_num, int in_flight) "s %p sector_
 mirror_yield_buf_busy(void *s, int nb_chunks, int in_flight) "s %p requested chunks %d in_flight %d"
 mirror_break_buf_busy(void *s, int nb_chunks, int in_flight) "s %p requested chunks %d in_flight %d"
 
+# block/backup.c
+backup_do_cow_enter(void *job, int64_t start, int64_t sector_num, int nb_sectors) "job %p start %"PRId64" sector_num %"PRId64" nb_sectors %d"
+backup_do_cow_return(void *job, int64_t sector_num, int nb_sectors, int ret) "job %p sector_num %"PRId64" nb_sectors %d ret %d"
+backup_do_cow_skip(void *job, int64_t start) "job %p start %"PRId64
+backup_do_cow_process(void *job, int64_t start) "job %p start %"PRId64
+backup_do_cow_read_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
+backup_do_cow_write_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
+
 # blockdev.c
 qmp_block_job_cancel(void *job) "job %p"
 qmp_block_job_pause(void *job) "job %p"