[Qemu-devel] [PULL 0/9] Block patches

[Qemu-devel] [PULL 0/9] Block patches

[Kevin Wolf]

The following changes since commit cc015e9a5dde2f03f123357fa060acbdfcd570a4:

  add Win32 IPI service (2011-03-13 14:44:22 +0000)

are available in the git repository at:
  git://repo.or.cz/qemu/kevin.git for-anthony

Brian Wheeler (1):
      Fix ATA SMART and CHECK POWER MODE

Feiran Zheng (1):
      hw/xen_disk: aio_inflight not released in handling ioreq when nr_segments==0

Jes Sorensen (1):
      Improve error handling in do_snapshot_blkdev()

Kevin Wolf (3):
      Add error message for loading snapshot without VM state
      tools: Use real async.c instead of stubs
      Add qcow2 documentation

Ryan Harper (1):
      Don't allow multiwrites against a block device without underlying medium

Stefan Weil (2):
      block/vdi: Don't ignore immediate read/write failures
      block/qcow: Don't ignore immediate read/write and other failures

 Makefile.objs        |    4 +-
 block.c              |    8 ++
 block/qcow.c         |   16 +++-
 block/vdi.c          |    5 +
 blockdev.c           |   23 ++++-
 docs/specs/qcow2.txt |  260 ++++++++++++++++++++++++++++++++++++++++++++++++++
 hw/ide/core.c        |   41 ++++++---
 hw/xen_disk.c        |    2 +-
 qemu-tool.c          |   47 +--------
 savevm.c             |    2 +
 10 files changed, 339 insertions(+), 69 deletions(-)
 create mode 100644 docs/specs/qcow2.txt

[Qemu-devel] [PATCH 1/9] block/vdi: Don't ignore immediate read/write failures

[Kevin Wolf]

From: Stefan Weil <weil@mail.berlios.de>

This patch is similar to 171e3d6b9997c98a97d0c525867f7cd9b640cadd
which fixed qcow2:

Returning -EIO is far from optimal, but at least it's an error code.

Cc: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/vdi.c |    5 +++++
 1 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/block/vdi.c b/block/vdi.c
index 116b25b..9054079 100644
--- a/block/vdi.c
+++ b/block/vdi.c
@@ -610,6 +610,7 @@ static void vdi_aio_read_cb(void *opaque, int ret)
         acb->hd_aiocb = bdrv_aio_readv(bs->file, offset, &acb->hd_qiov,
                                        n_sectors, vdi_aio_read_cb, acb);
         if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
             goto done;
         }
     }
@@ -673,6 +674,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
             acb->hd_aiocb = bdrv_aio_writev(bs->file, 0, &acb->hd_qiov, 1,
                                             vdi_aio_write_cb, acb);
             if (acb->hd_aiocb == NULL) {
+                ret = -EIO;
                 goto done;
             }
             return;
@@ -702,6 +704,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
             acb->hd_aiocb = bdrv_aio_writev(bs->file, offset, &acb->hd_qiov,
                                             n_sectors, vdi_aio_write_cb, acb);
             if (acb->hd_aiocb == NULL) {
+                ret = -EIO;
                 goto done;
             }
             return;
@@ -752,6 +755,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
                                         &acb->hd_qiov, s->block_sectors,
                                         vdi_aio_write_cb, acb);
         if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
             goto done;
         }
     } else {
@@ -764,6 +768,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
         acb->hd_aiocb = bdrv_aio_writev(bs->file, offset, &acb->hd_qiov,
                                         n_sectors, vdi_aio_write_cb, acb);
         if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
             goto done;
         }
     }
-- 
1.7.2.3

[Qemu-devel] [PATCH 2/9] block/qcow: Don't ignore immediate read/write and other failures

[Kevin Wolf]

From: Stefan Weil <weil@mail.berlios.de>

This patch is similar to 171e3d6b9997c98a97d0c525867f7cd9b640cadd
which fixed qcow2:

Returning -EIO is far from optimal, but at least it's an error code.

In addition to read/write failures, -EIO is also returned when
decompress_cluster failed.

Cc: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/qcow.c |   16 ++++++++++++----
 1 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/block/qcow.c b/block/qcow.c
index f67d3d3..a26c886 100644
--- a/block/qcow.c
+++ b/block/qcow.c
@@ -589,8 +589,10 @@ static void qcow_aio_read_cb(void *opaque, int ret)
             qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
             acb->hd_aiocb = bdrv_aio_readv(bs->backing_hd, acb->sector_num,
                 &acb->hd_qiov, acb->n, qcow_aio_read_cb, acb);
-            if (acb->hd_aiocb == NULL)
+            if (acb->hd_aiocb == NULL) {
+                ret = -EIO;
                 goto done;
+            }
         } else {
             /* Note: in this case, no need to wait */
             memset(acb->buf, 0, 512 * acb->n);
@@ -598,8 +600,10 @@ static void qcow_aio_read_cb(void *opaque, int ret)
         }
     } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
         /* add AIO support for compressed blocks ? */
-        if (decompress_cluster(bs, acb->cluster_offset) < 0)
+        if (decompress_cluster(bs, acb->cluster_offset) < 0) {
+            ret = -EIO;
             goto done;
+        }
         memcpy(acb->buf,
                s->cluster_cache + index_in_cluster * 512, 512 * acb->n);
         goto redo;
@@ -614,8 +618,10 @@ static void qcow_aio_read_cb(void *opaque, int ret)
         acb->hd_aiocb = bdrv_aio_readv(bs->file,
                             (acb->cluster_offset >> 9) + index_in_cluster,
                             &acb->hd_qiov, acb->n, qcow_aio_read_cb, acb);
-        if (acb->hd_aiocb == NULL)
+        if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
             goto done;
+        }
     }
 
     return;
@@ -700,8 +706,10 @@ static void qcow_aio_write_cb(void *opaque, int ret)
                                     (cluster_offset >> 9) + index_in_cluster,
                                     &acb->hd_qiov, acb->n,
                                     qcow_aio_write_cb, acb);
-    if (acb->hd_aiocb == NULL)
+    if (acb->hd_aiocb == NULL) {
+        ret = -EIO;
         goto done;
+    }
     return;
 
 done:
-- 
1.7.2.3

[Qemu-devel] [PATCH 3/9] Add error message for loading snapshot without VM state

[Kevin Wolf]

It already fails, but it didn't tell the user why.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
---
 savevm.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/savevm.c b/savevm.c
index 60d2f2a..d1b9b4a 100644
--- a/savevm.c
+++ b/savevm.c
@@ -2021,6 +2021,8 @@ int load_vmstate(const char *name)
     if (ret < 0) {
         return ret;
     } else if (sn.vm_state_size == 0) {
+        error_report("This is a disk-only snapshot. Revert to it offline "
+            "using qemu-img.");
         return -EINVAL;
     }
 
-- 
1.7.2.3

[Qemu-devel] [PATCH 4/9] tools: Use real async.c instead of stubs

[Kevin Wolf]

It's wrong to call BHs directly, even in tools. The only operations that
schedule BHs are called in a loop that (indirectly) contains a call to
qemu_bh_poll anyway, so we're not losing the scheduled BHs: Tools either use
synchronous functions, which are guaranteed to have completed (including any
BHs) when they return; or if they use asynchronous functions, they need to call
qemu_aio_wait() or similar functions already today.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
---
 Makefile.objs |    4 ++--
 qemu-tool.c   |   47 ++++-------------------------------------------
 2 files changed, 6 insertions(+), 45 deletions(-)

diff --git a/Makefile.objs b/Makefile.objs
index a52f42f..167ccc2 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -13,7 +13,7 @@ oslib-obj-$(CONFIG_POSIX) += oslib-posix.o
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y = cutils.o cache-utils.o qemu-malloc.o qemu-option.o module.o
+block-obj-y = cutils.o cache-utils.o qemu-malloc.o qemu-option.o module.o async.o
 block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o
 block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
@@ -63,7 +63,7 @@ common-obj-y = $(block-obj-y) blockdev.o
 common-obj-y += $(net-obj-y)
 common-obj-y += $(qobject-obj-y)
 common-obj-$(CONFIG_LINUX) += $(fsdev-obj-$(CONFIG_LINUX))
-common-obj-y += readline.o console.o cursor.o async.o qemu-error.o
+common-obj-y += readline.o console.o cursor.o qemu-error.o
 common-obj-y += $(oslib-obj-y)
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o
diff --git a/qemu-tool.c b/qemu-tool.c
index 392e1c9..d45840d 100644
--- a/qemu-tool.c
+++ b/qemu-tool.c
@@ -56,53 +56,10 @@ void monitor_print_filename(Monitor *mon, const char *filename)
 {
 }
 
-void async_context_push(void)
-{
-}
-
-void async_context_pop(void)
-{
-}
-
-int get_async_context_id(void)
-{
-    return 0;
-}
-
 void monitor_protocol_event(MonitorEvent event, QObject *data)
 {
 }
 
-QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
-{
-    QEMUBH *bh;
-
-    bh = qemu_malloc(sizeof(*bh));
-    bh->cb = cb;
-    bh->opaque = opaque;
-
-    return bh;
-}
-
-int qemu_bh_poll(void)
-{
-    return 0;
-}
-
-void qemu_bh_schedule(QEMUBH *bh)
-{
-    bh->cb(bh->opaque);
-}
-
-void qemu_bh_cancel(QEMUBH *bh)
-{
-}
-
-void qemu_bh_delete(QEMUBH *bh)
-{
-    qemu_free(bh);
-}
-
 int qemu_set_fd_handler2(int fd,
                          IOCanReadHandler *fd_read_poll,
                          IOHandler *fd_read,
@@ -111,3 +68,7 @@ int qemu_set_fd_handler2(int fd,
 {
     return 0;
 }
+
+void qemu_notify_event(void)
+{
+}
-- 
1.7.2.3

[Qemu-devel] [PATCH 5/9] Don't allow multiwrites against a block device without underlying medium

[Kevin Wolf]

From: Ryan Harper <ryanh@us.ibm.com>

If the block device has been closed, we no longer have a medium to submit
IO against, check for this before submitting io.  This prevents a segfault
further in the code where we dereference elements of the block driver.

Signed-off-by: Ryan Harper <ryanh@us.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block.c |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/block.c b/block.c
index 0559d83..c8e2f97 100644
--- a/block.c
+++ b/block.c
@@ -2398,6 +2398,14 @@ int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs, int num_reqs)
     MultiwriteCB *mcb;
     int i;
 
+    /* don't submit writes if we don't have a medium */
+    if (bs->drv == NULL) {
+        for (i = 0; i < num_reqs; i++) {
+            reqs[i].error = -ENOMEDIUM;
+        }
+        return -1;
+    }
+
     if (num_reqs == 0) {
         return 0;
     }
-- 
1.7.2.3

[Qemu-devel] [PATCH 6/9] Fix ATA SMART and CHECK POWER MODE

[Kevin Wolf]

From: Brian Wheeler <bdwheele@indiana.edu>

This patch fixes two things:

 1) CHECK POWER MODE

The error return value wasn't always zero, so it would show up as
offline.  Error is now explicitly set to zero.

 2) SMART

The smart values that were returned were invalid and tools like skdump
would not recognize that the smart data was actually valid and would
dump weird output.  The data has been fixed up and raw value support
was added.  Tools like skdump and palimpsest work as expected.

Signed-off-by: Brian Wheeler <bdwheele@indiana.edu>
Acked-by: Ryan Harper <ryanh@us.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 hw/ide/core.c |   41 ++++++++++++++++++++++++++++-------------
 1 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/hw/ide/core.c b/hw/ide/core.c
index 9c91a49..1ffca56 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -34,13 +34,26 @@
 
 #include <hw/ide/internal.h>
 
-static const int smart_attributes[][5] = {
-    /* id,  flags, val, wrst, thrsh */
-    { 0x01, 0x03, 0x64, 0x64, 0x06}, /* raw read */
-    { 0x03, 0x03, 0x64, 0x64, 0x46}, /* spin up */
-    { 0x04, 0x02, 0x64, 0x64, 0x14}, /* start stop count */
-    { 0x05, 0x03, 0x64, 0x64, 0x36}, /* remapped sectors */
-    { 0x00, 0x00, 0x00, 0x00, 0x00}
+/* These values were based on a Seagate ST3500418AS but have been modified
+   to make more sense in QEMU */
+static const int smart_attributes[][12] = {
+    /* id,  flags, hflags, val, wrst, raw (6 bytes), threshold */
+    /* raw read error rate*/
+    { 0x01, 0x03, 0x00, 0x64, 0x64, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06},
+    /* spin up */
+    { 0x03, 0x03, 0x00, 0x64, 0x64, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00},
+    /* start stop count */
+    { 0x04, 0x02, 0x00, 0x64, 0x64, 0x64, 0x00, 0x00, 0x00, 0x00, 0x00, 0x14},
+    /* remapped sectors */
+    { 0x05, 0x03, 0x00, 0x64, 0x64, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x24},
+    /* power on hours */
+    { 0x09, 0x03, 0x00, 0x64, 0x64, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00},
+    /* power cycle count */
+    { 0x0c, 0x03, 0x00, 0x64, 0x64, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00},
+    /* airflow-temperature-celsius */
+    { 190,  0x03, 0x00, 0x45, 0x45, 0x1f, 0x00, 0x1f, 0x1f, 0x00, 0x00, 0x32},
+    /* end of list */
+    { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}
 };
 
 /* XXX: DVDs that could fit on a CD will be reported as a CD */
@@ -1843,6 +1856,7 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
         break;
     case WIN_CHECKPOWERMODE1:
     case WIN_CHECKPOWERMODE2:
+        s->error = 0;
         s->nsector = 0xff; /* device active or idle */
         s->status = READY_STAT | SEEK_STAT;
         ide_set_irq(s->bus);
@@ -2097,7 +2111,7 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
 		if (smart_attributes[n][0] == 0)
 			break;
 		s->io_buffer[2+0+(n*12)] = smart_attributes[n][0];
-		s->io_buffer[2+1+(n*12)] = smart_attributes[n][4];
+		s->io_buffer[2+1+(n*12)] = smart_attributes[n][11];
 		}
 		for (n=0; n<511; n++) /* checksum */
 		s->io_buffer[511] += s->io_buffer[n];
@@ -2110,12 +2124,13 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
 		memset(s->io_buffer, 0, 0x200);
 		s->io_buffer[0] = 0x01; /* smart struct version */
 		for (n=0; n<30; n++) {
-		if (smart_attributes[n][0] == 0)
+		    if (smart_attributes[n][0] == 0) {
 			break;
-		s->io_buffer[2+0+(n*12)] = smart_attributes[n][0];
-		s->io_buffer[2+1+(n*12)] = smart_attributes[n][1];
-		s->io_buffer[2+3+(n*12)] = smart_attributes[n][2];
-		s->io_buffer[2+4+(n*12)] = smart_attributes[n][3];
+		    }
+		    int i;
+		    for(i = 0; i < 11; i++) {
+			s->io_buffer[2+i+(n*12)] = smart_attributes[n][i];
+		    }
 		}
 		s->io_buffer[362] = 0x02 | (s->smart_autosave?0x80:0x00);
 		if (s->smart_selftest_count == 0) {
-- 
1.7.2.3

[Qemu-devel] [PATCH 7/9] Improve error handling in do_snapshot_blkdev()

[Kevin Wolf]

From: Jes Sorensen <Jes.Sorensen@redhat.com>

In case we cannot open the newly created snapshot image, try to fall
back to the original image file and continue running on that, which
should prevent the guest from aborting.

This is a corner case which can happen if the admin by mistake
specifies the snapshot file on a virtual file system which does not
support O_DIRECT. bdrv_create() does not use O_DIRECT, but the
following open in bdrv_open() does and will then fail.

Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 blockdev.c |   23 +++++++++++++++++------
 1 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/blockdev.c b/blockdev.c
index 0690cc8..ecf2252 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -574,9 +574,10 @@ int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data)
     const char *filename = qdict_get_try_str(qdict, "snapshot_file");
     const char *format = qdict_get_try_str(qdict, "format");
     BlockDriverState *bs;
-    BlockDriver *drv, *proto_drv;
+    BlockDriver *drv, *old_drv, *proto_drv;
     int ret = 0;
     int flags;
+    char old_filename[1024];
 
     if (!filename) {
         qerror_report(QERR_MISSING_PARAMETER, "snapshot_file");
@@ -591,6 +592,11 @@ int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data)
         goto out;
     }
 
+    pstrcpy(old_filename, sizeof(old_filename), bs->filename);
+
+    old_drv = bs->drv;
+    flags = bs->open_flags;
+
     if (!format) {
         format = "qcow2";
     }
@@ -610,7 +616,7 @@ int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data)
     }
 
     ret = bdrv_img_create(filename, format, bs->filename,
-                          bs->drv->format_name, NULL, -1, bs->open_flags);
+                          bs->drv->format_name, NULL, -1, flags);
     if (ret) {
         goto out;
     }
@@ -618,15 +624,20 @@ int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data)
     qemu_aio_flush();
     bdrv_flush(bs);
 
-    flags = bs->open_flags;
     bdrv_close(bs);
     ret = bdrv_open(bs, filename, flags, drv);
     /*
-     * If reopening the image file we just created fails, we really
-     * are in trouble :(
+     * If reopening the image file we just created fails, fall back
+     * and try to re-open the original image. If that fails too, we
+     * are in serious trouble.
      */
     if (ret != 0) {
-        abort();
+        ret = bdrv_open(bs, old_filename, flags, old_drv);
+        if (ret != 0) {
+            qerror_report(QERR_OPEN_FILE_FAILED, old_filename);
+        } else {
+            qerror_report(QERR_OPEN_FILE_FAILED, filename);
+        }
     }
 out:
     if (ret) {
-- 
1.7.2.3

[Qemu-devel] [PATCH 8/9] hw/xen_disk: aio_inflight not released in handling ioreq when nr_segments==0

[Kevin Wolf]

From: Feiran Zheng <famcool@gmail.com>

In hw/xen_disk.c, async writing ioreq is leaked when
ioreq->req.nr_segments==0, because `aio_inflight` flag is not released
properly (skipped by misplaced "break").

Signed-off-by: Feiran Zheng <famcool@gmail.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 hw/xen_disk.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/hw/xen_disk.c b/hw/xen_disk.c
index ed9e5eb..445bf03 100644
--- a/hw/xen_disk.c
+++ b/hw/xen_disk.c
@@ -408,9 +408,9 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
 	break;
     case BLKIF_OP_WRITE:
     case BLKIF_OP_WRITE_BARRIER:
-        ioreq->aio_inflight++;
         if (!ioreq->req.nr_segments)
             break;
+        ioreq->aio_inflight++;
         bdrv_aio_writev(blkdev->bs, ioreq->start / BLOCK_SIZE,
                         &ioreq->v, ioreq->v.size / BLOCK_SIZE,
                         qemu_aio_complete, ioreq);
-- 
1.7.2.3

[Qemu-devel] [PATCH 9/9] Add qcow2 documentation

[Kevin Wolf]

This adds a description of the qcow2 file format to the docs/ directory.
Besides documenting what's there, which is never wrong, the document should
provide a good basis for the discussion of format extensions (called "qcow3"
in previous discussions)

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
---
 docs/specs/qcow2.txt |  260 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 260 insertions(+), 0 deletions(-)
 create mode 100644 docs/specs/qcow2.txt

diff --git a/docs/specs/qcow2.txt b/docs/specs/qcow2.txt
new file mode 100644
index 0000000..8fc3cb2
--- /dev/null
+++ b/docs/specs/qcow2.txt
@@ -0,0 +1,260 @@
+== General ==
+
+A qcow2 image file is organized in units of constant size, which are called
+(host) clusters. A cluster is the unit in which all allocations are done,
+both for actual guest data and for image metadata.
+
+Likewise, the virtual disk as seen by the guest is divided into (guest)
+clusters of the same size.
+
+All numbers in qcow2 are stored in Big Endian byte order.
+
+
+== Header ==
+
+The first cluster of a qcow2 image contains the file header:
+
+    Byte  0 -  3:   magic
+                    QCOW magic string ("QFI\xfb")
+
+          4 -  7:   version
+                    Version number (only valid value is 2)
+
+          8 - 15:   backing_file_offset
+                    Offset into the image file at which the backing file name
+                    is stored (NB: The string is not null terminated). 0 if the
+                    image doesn't have a backing file.
+
+         16 - 19:   backing_file_size
+                    Length of the backing file name in bytes. Must not be
+                    longer than 1023 bytes. Undefined if the image doesn't have
+                    a backing file.
+
+         20 - 23:   cluster_bits
+                    Number of bits that are used for addressing an offset
+                    within a cluster (1 << cluster_bits is the cluster size).
+                    Must not be less than 9 (i.e. 512 byte clusters).
+
+                    Note: qemu as of today has an implementation limit of 2 MB
+                    as the maximum cluster size and won't be able to open images
+                    with larger cluster sizes.
+
+         24 - 31:   size
+                    Virtual disk size in bytes
+
+         32 - 35:   crypt_method
+                    0 for no encryption
+                    1 for AES encryption
+
+         36 - 39:   l1_size
+                    Number of entries in the active L1 table
+
+         40 - 47:   l1_table_offset
+                    Offset into the image file at which the active L1 table
+                    starts. Must be aligned to a cluster boundary.
+
+         48 - 55:   refcount_table_offset
+                    Offset into the image file at which the refcount table
+                    starts. Must be aligned to a cluster boundary.
+
+         56 - 59:   refcount_table_clusters
+                    Number of clusters that the refcount table occupies
+
+         60 - 63:   nb_snapshots
+                    Number of snapshots contained in the image
+
+         64 - 71:   snapshots_offset
+                    Offset into the image file at which the snapshot table
+                    starts. Must be aligned to a cluster boundary.
+
+Directly after the image header, optional sections called header extensions can
+be stored. Each extension has a structure like the following:
+
+    Byte  0 -  3:   Header extension type:
+                        0x00000000 - End of the header extension area
+                        0xE2792ACA - Backing file format name
+                        other      - Unknown header extension, can be safely
+                                     ignored
+
+          4 -  7:   Length of the header extension data
+
+          8 -  n:   Header extension data
+
+          n -  m:   Padding to round up the header extension size to the next
+                    multiple of 8.
+
+The remaining space between the end of the header extension area and the end of
+the first cluster can be used for other data. Usually, the backing file name is
+stored there.
+
+
+== Host cluster management ==
+
+qcow2 manages the allocation of host clusters by maintaining a reference count
+for each host cluster. A refcount of 0 means that the cluster is free, 1 means
+that it is used, and >= 2 means that it is used and any write access must
+perform a COW (copy on write) operation.
+
+The refcounts are managed in a two-level table. The first level is called
+refcount table and has a variable size (which is stored in the header). The
+refcount table can cover multiple clusters, however it needs to be contiguous
+in the image file.
+
+It contains pointers to the second level structures which are called refcount
+blocks and are exactly one cluster in size.
+
+Given a offset into the image file, the refcount of its cluster can be obtained
+as follows:
+
+    refcount_block_entries = (cluster_size / sizeof(uint16_t))
+
+    refcount_block_index = (offset / cluster_size) % refcount_table_entries
+    refcount_table_index = (offset / cluster_size) / refcount_table_entries
+
+    refcount_block = load_cluster(refcount_table[refcount_table_index]);
+    return refcount_block[refcount_block_index];
+
+Refcount table entry:
+
+    Bit  0 -  8:    Reserved (set to 0)
+
+         9 - 63:    Bits 9-63 of the offset into the image file at which the
+                    refcount block starts. Must be aligned to a cluster
+                    boundary.
+
+                    If this is 0, the corresponding refcount block has not yet
+                    been allocated. All refcounts managed by this refcount block
+                    are 0.
+
+Refcount block entry:
+
+    Bit  0 - 15:    Reference count of the cluster
+
+
+== Cluster mapping ==
+
+Just as for refcounts, qcow2 uses a two-level structure for the mapping of
+guest clusters to host clusters. They are called L1 and L2 table.
+
+The L1 table has a variable size (stored in the header) and may use multiple
+clusters, however it must be contiguous in the image file. L2 tables are
+exactly one cluster in size.
+
+Given a offset into the virtual disk, the offset into the image file can be
+obtained as follows:
+
+    l2_entries = (cluster_size / sizeof(uint64_t))
+
+    l2_index = (offset / cluster_size) % l2_entries
+    l1_index = (offset / cluster_size) / l2_entries
+
+    l2_table = load_cluster(l1_table[l1_index]);
+    cluster_offset = l2_table[l2_index];
+
+    return cluster_offset + (offset % cluster_size)
+
+L1 table entry:
+
+    Bit  0 -  8:    Reserved (set to 0)
+
+         9 - 55:    Bits 9-55 of the offset into the image file at which the L2
+                    table starts. Must be aligned to a cluster boundary. If the
+                    offset is 0, the L2 table and all clusters described by this
+                    L2 table are unallocated.
+
+        56 - 62:    Reserved (set to 0)
+
+             63:    0 for an L2 table that is unused or requires COW, 1 if its
+                    refcount is exactly one. This information is only accurate
+                    in the active L1 table.
+
+L2 table entry (for normal clusters):
+
+    Bit  0 -  8:    Reserved (set to 0)
+
+         9 - 55:    Bits 9-55 of host cluster offset. Must be aligned to a
+                    cluster boundary. If the offset is 0, the cluster is
+                    unallocated.
+
+        56 - 61:    Reserved (set to 0)
+
+             62:    0 (this cluster is not compressed)
+
+             63:    0 for a cluster that is unused or requires COW, 1 if its
+                    refcount is exactly one. This information is only accurate
+                    in L2 tables that are reachable from the the active L1
+                    table.
+
+L2 table entry (for compressed clusters; x = 62 - (cluster_size - 8)):
+
+    Bit  0 -  x:    Host cluster offset. This is usually _not_ aligned to a
+                    cluster boundary!
+
+       x+1 - 61:    Compressed size of the images in sectors of 512 bytes
+
+             62:    1 (this cluster is compressed using zlib)
+
+             63:    0 for a cluster that is unused or requires COW, 1 if its
+                    refcount is exactly one. This information is only accurate
+                    in L2 tables that are reachable from the the active L1
+                    table.
+
+If a cluster is unallocated, read requests shall read the data from the backing
+file. If there is no backing file or the backing file is smaller than the image,
+they shall read zeros for all parts that are not covered by the backing file.
+
+
+== Snapshots ==
+
+qcow2 supports internal snapshots. Their basic principle of operation is to
+switch the active L1 table, so that a different set of host clusters are
+exposed to the guest.
+
+When creating a snapshot, the L1 table should be copied and the refcount of all
+L2 tables and clusters reachable form this L1 table must be increased, so that
+a write causes a COW and isn't visible in other snapshots.
+
+When loading a snapshot, bit 63 of all entries in the new active L1 table and
+all L2 tables referenced by it must be reconstructed from the refcount table
+as it doesn't need to be accurate in inactive L1 tables.
+
+A directory of all snapshots is stored in the snapshot table, a contiguous area
+in the image file, whose starting offset and length are given by the header
+fields snapshots_offset and nb_snapshots. The entries of the snapshot table
+have variable length, depending on the length of ID, name and extra data.
+
+Snapshot table entry:
+
+    Byte 0 -  7:    Offset into the image file at which the L1 table for the
+                    snapshot starts. Must be aligned to a cluster boundary.
+
+         8 - 11:    Number of entries in the L1 table of the snapshots
+
+        12 - 13:    Length of the unique ID string describing the snapshot
+
+        14 - 15:    Length of the name of the snapshot
+
+        16 - 19:    Time at which the snapshot was taken in seconds since the
+                    Epoch
+
+        20 - 23:    Subsecond part of the time at which the snapshot was taken
+                    in nanoseconds
+
+        24 - 31:    Time that the guest was running until the snapshot was
+                    taken in nanoseconds
+
+        32 - 35:    Size of the VM state in bytes. 0 if no VM state is saved.
+                    If there is VM state, it starts at the first cluster
+                    described by first L1 table entry that doesn't describe a
+                    regular guest cluster (i.e. VM state is stored like guest
+                    disk content, except that it is stored at offsets that are
+                    larger than the virtual disk presented to the guest)
+
+        36 - 39:    Size of extra data in the table entry (used for future
+                    extensions of the format)
+
+        variable:   Extra data for future extensions. Must be ignored.
+
+        variable:   Unique ID string for the snapshot (not null terminated)
+
+        variable:   Name of the snapshot (not null terminated)
-- 
1.7.2.3

[Qemu-devel] Re: [PULL 0/9] Block patches

[Kevin Wolf]

Am 16.03.2011 11:47, schrieb Kevin Wolf:
> The following changes since commit cc015e9a5dde2f03f123357fa060acbdfcd570a4:
> 
>   add Win32 IPI service (2011-03-13 14:44:22 +0000)
> 
> are available in the git repository at:
>   git://repo.or.cz/qemu/kevin.git for-anthony
> 
> Brian Wheeler (1):
>       Fix ATA SMART and CHECK POWER MODE
> 
> Feiran Zheng (1):
>       hw/xen_disk: aio_inflight not released in handling ioreq when nr_segments==0
> 
> Jes Sorensen (1):
>       Improve error handling in do_snapshot_blkdev()
> 
> Kevin Wolf (3):
>       Add error message for loading snapshot without VM state
>       tools: Use real async.c instead of stubs
>       Add qcow2 documentation
> 
> Ryan Harper (1):
>       Don't allow multiwrites against a block device without underlying medium
> 
> Stefan Weil (2):
>       block/vdi: Don't ignore immediate read/write failures
>       block/qcow: Don't ignore immediate read/write and other failures

Ping?

Kevin

Re: [Qemu-devel] Re: [PULL 0/9] Block patches

[Aurelien Jarno]

On Mon, Mar 21, 2011 at 02:31:37PM +0100, Kevin Wolf wrote:
> Am 16.03.2011 11:47, schrieb Kevin Wolf:
> > The following changes since commit cc015e9a5dde2f03f123357fa060acbdfcd570a4:
> > 
> >   add Win32 IPI service (2011-03-13 14:44:22 +0000)
> > 
> > are available in the git repository at:
> >   git://repo.or.cz/qemu/kevin.git for-anthony
> > 
> > Brian Wheeler (1):
> >       Fix ATA SMART and CHECK POWER MODE
> > 
> > Feiran Zheng (1):
> >       hw/xen_disk: aio_inflight not released in handling ioreq when nr_segments==0
> > 
> > Jes Sorensen (1):
> >       Improve error handling in do_snapshot_blkdev()
> > 
> > Kevin Wolf (3):
> >       Add error message for loading snapshot without VM state
> >       tools: Use real async.c instead of stubs
> >       Add qcow2 documentation
> > 
> > Ryan Harper (1):
> >       Don't allow multiwrites against a block device without underlying medium
> > 
> > Stefan Weil (2):
> >       block/vdi: Don't ignore immediate read/write failures
> >       block/qcow: Don't ignore immediate read/write and other failures
> 
> Ping?
> 

Pulled.

-- 
Aurelien Jarno                          GPG: 1024D/F1BCDB73
aurelien@aurel32.net                 http://www.aurel32.net

[Qemu-devel] [PULL 0/9] Block patches

[Stefan Hajnoczi]

The following changes since commit 806f352d3d6f7b326b0ab3a49c622b124459dc8d:

  gen-icount.h: Rename gen_icount_start/end to gen_tb_start/end (2013-03-03 14:29:08 +0000)

are available in the git repository at:

  git://github.com/stefanha/qemu.git block

for you to fetch changes up to 272d2d8e1241b92ab9be87b2c8fb590fd84987a8:

  block: for HMP commit() operations on 'all', skip non-COW drives (2013-03-04 09:54:17 +0100)

----------------------------------------------------------------
Christian Borntraeger (1):
      virtio-blk: fix unplug + virsh reboot

Jeff Cody (1):
      block: for HMP commit() operations on 'all', skip non-COW drives

MORITA Kazutaka (5):
      slirp/tcp_subr.c: fix coding style in tcp_connect
      move socket_set_nodelay to osdep.c
      sheepdog: accept URIs
      sheepdog: use inet_connect to simplify connect code
      sheepdog: add support for connecting to unix domain socket

Mark Cave-Ayland (1):
      ide/macio: Fix macio DMA initialisation.

Paolo Bonzini (1):
      dataplane: remove EventPoll in favor of AioContext

 block.c                    |   8 +-
 block/sheepdog.c           | 315 +++++++++++++++++++++++++++------------------
 gdbstub.c                  |   5 +-
 hw/dataplane/Makefile.objs |   2 +-
 hw/dataplane/event-poll.c  | 100 --------------
 hw/dataplane/event-poll.h  |  40 ------
 hw/dataplane/virtio-blk.c  |  48 ++++---
 hw/macio.c                 |   2 +-
 hw/virtio-blk.c            |   4 +-
 include/qemu/sockets.h     |   1 +
 qemu-char.c                |   6 -
 qemu-doc.texi              |  22 ++--
 qemu-options.hx            |  18 +--
 slirp/tcp_subr.c           | 139 ++++++++++----------
 util/osdep.c               |   6 +
 15 files changed, 328 insertions(+), 388 deletions(-)
 delete mode 100644 hw/dataplane/event-poll.c
 delete mode 100644 hw/dataplane/event-poll.h

-- 
1.8.1.4

[Qemu-devel] [PULL 0/9] Block patches

[Stefan Hajnoczi]

The following changes since commit 9fbee91a131a05e443d7108d7fbdf3ca91020290:

  Merge remote-tracking branch 'remotes/kvm/uq/master' into staging (2014-02-27 16:00:31 +0000)

are available in the git repository at:


  git://github.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to 3eba13ec25341ce473591ff338eab3196890a4eb:

  block/vmdk: do not report file offset for compressed extents (2014-02-28 18:59:07 +0100)

----------------------------------------------------------------
Block pull request

----------------------------------------------------------------
Amit Shah (1):
      block: use /var/tmp instead of /tmp for -snapshot

Benoît Canet (3):
      qmp: Fix BlockdevOptionQuorum.
      qmp: Make Quorum error events more palatable.
      qemu-io-test: Disable Quorum test when not compiled in.

Jeff Cody (2):
      block: gluster - code movements, state storage changes
      block: gluster - add reopen support.

Loic Dachary (1):
      discard rbd error output when not relevant in qemu-iotests

Paolo Bonzini (1):
      qemu-iotests: add more tests to the "quick" group

Peter Lieven (1):
      block/vmdk: do not report file offset for compressed extents

 block.c                      |   5 +-
 block/gluster.c              | 143 ++++++++++++++++++++++++++++++++++++++-----
 block/quorum.c               |   9 ++-
 block/vmdk.c                 |   2 +-
 docs/qmp/qmp-events.txt      |  75 ++++++++++++-----------
 qapi-schema.json             |   5 +-
 tests/qemu-iotests-quick.sh  |   1 +
 tests/qemu-iotests/081       |   3 +
 tests/qemu-iotests/081.out   |   2 +-
 tests/qemu-iotests/common.rc |   2 +-
 tests/qemu-iotests/group     |  34 +++++-----
 11 files changed, 203 insertions(+), 78 deletions(-)

-- 
1.8.5.3

Re: [Qemu-devel] [PULL 0/9] Block patches

[Peter Maydell]

On 28 February 2014 18:33, Stefan Hajnoczi <stefanha@redhat.com> wrote:
> The following changes since commit 9fbee91a131a05e443d7108d7fbdf3ca91020290:
>
>   Merge remote-tracking branch 'remotes/kvm/uq/master' into staging (2014-02-27 16:00:31 +0000)
>
> are available in the git repository at:
>
>
>   git://github.com/stefanha/qemu.git tags/block-pull-request
>
> for you to fetch changes up to 3eba13ec25341ce473591ff338eab3196890a4eb:
>
>   block/vmdk: do not report file offset for compressed extents (2014-02-28 18:59:07 +0100)

Applied, thanks.

-- PMM

[Qemu-devel] [PULL 0/9] Block patches

[Stefan Hajnoczi]

The following changes since commit fdc997ef54c5b2c3483969aee5f1d5f2a7587520:

  target-alpha: Avoid gcc 6.1 werror for linux-user (2016-06-27 21:03:58 +0100)

are available in the git repository at:

  git://github.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to 2f2705908fc4b7be868d45b7b02159fb243a8457:

  virtio-blk: add num-queues device property (2016-06-28 13:08:32 +0100)

----------------------------------------------------------------

----------------------------------------------------------------

Stefan Hajnoczi (9):
  Revert "virtio: sync the dataplane vring state to the virtqueue before
    virtio_save"
  dma-helpers: dma_blk_io() cancel support
  virtio-blk: add VirtIOBlockConf->num_queues
  virtio-blk: multiqueue batch notify
  virtio-blk: tell dataplane which vq to notify
  virtio-blk: associate request with a virtqueue
  virtio-blk: live migrate s->rq with multiqueue
  virtio-blk: dataplane multiqueue support
  virtio-blk: add num-queues device property

 dma-helpers.c                   |  7 ++++
 hw/block/dataplane/virtio-blk.c | 81 +++++++++++++++++++++++++++++------------
 hw/block/dataplane/virtio-blk.h |  2 +-
 hw/block/virtio-blk.c           | 57 +++++++++++++++++++++--------
 hw/scsi/virtio-scsi.c           |  5 ---
 include/hw/virtio/virtio-blk.h  |  6 ++-
 6 files changed, 112 insertions(+), 46 deletions(-)

-- 
2.7.4

Re: [Qemu-devel] [PULL 0/9] Block patches

[Peter Maydell]

On 28 June 2016 at 14:23, Stefan Hajnoczi <stefanha@redhat.com> wrote:
> The following changes since commit fdc997ef54c5b2c3483969aee5f1d5f2a7587520:
>
>   target-alpha: Avoid gcc 6.1 werror for linux-user (2016-06-27 21:03:58 +0100)
>
> are available in the git repository at:
>
>   git://github.com/stefanha/qemu.git tags/block-pull-request
>
> for you to fetch changes up to 2f2705908fc4b7be868d45b7b02159fb243a8457:
>
>   virtio-blk: add num-queues device property (2016-06-28 13:08:32 +0100)
>
> ----------------------------------------------------------------
>
> ----------------------------------------------------------------

Applied, thanks.

-- PMM

[Qemu-devel] [PULL 0/9] Block patches

[Jeff Cody]

The following changes since commit a1cf5fac2b929ffa2abd1285401f2535ff8c6fea:

  Merge remote-tracking branch 'remotes/armbru/tags/pull-block-2017-02-21' into staging (2017-02-21 13:58:50 +0000)

are available in the git repository at:

  git@github.com:codyprime/qemu-kvm-jtc.git tags/block-pull-request

for you to fetch changes up to 6135c5e12606b8413708384e3e7d43f6010c5941:

  qemu-options: Fix broken sheepdog URL (2017-02-21 10:38:09 -0500)

----------------------------------------------------------------
Block patches
----------------------------------------------------------------

Anton Nefedov (1):
  mirror: do not increase offset during initial zero_or_discard phase

Jeff Cody (1):
  QAPI: Fix blockdev-add example documentation

Kevin Wolf (6):
  iscsi: Split URL into individual options
  iscsi: Handle -iscsi user/password in bdrv_parse_filename()
  iscsi: Add initiator-name option
  iscsi: Add header-digest option
  iscsi: Add timeout option
  iscsi: Add blockdev-add support

Thomas Huth (1):
  qemu-options: Fix broken sheepdog URL

 block/iscsi.c        | 353 +++++++++++++++++++++++++++++++--------------------
 block/mirror.c       |   9 +-
 qapi/block-core.json | 125 +++++++++++++-----
 qemu-options.hx      |   2 +-
 4 files changed, 317 insertions(+), 172 deletions(-)

-- 
2.9.3

Re: [Qemu-devel] [PULL 0/9] Block patches

[Peter Maydell]

On 21 February 2017 at 15:40, Jeff Cody <jcody@redhat.com> wrote:
> The following changes since commit a1cf5fac2b929ffa2abd1285401f2535ff8c6fea:
>
>   Merge remote-tracking branch 'remotes/armbru/tags/pull-block-2017-02-21' into staging (2017-02-21 13:58:50 +0000)
>
> are available in the git repository at:
>
>   git@github.com:codyprime/qemu-kvm-jtc.git tags/block-pull-request
>
> for you to fetch changes up to 6135c5e12606b8413708384e3e7d43f6010c5941:
>
>   qemu-options: Fix broken sheepdog URL (2017-02-21 10:38:09 -0500)
>
> ----------------------------------------------------------------
> Block patches

Applied, thanks.

-- PMM

[Qemu-devel] [PULL 0/9] Block patches

[Stefan Hajnoczi]

The following changes since commit e47f81b617684c4546af286d307b69014a83538a:

  Merge remote-tracking branch 'remotes/thibault/tags/samuel-thibault' into staging (2019-02-07 18:53:25 +0000)

are available in the Git repository at:

  git://github.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to 55140166667bb555c5d05165b93b25557d2e6397:

  tests/virtio-blk: add test for WRITE_ZEROES command (2019-02-11 11:58:17 +0800)

----------------------------------------------------------------
Pull request

User-visible changes:

 * virtio-blk: DISCARD and WRITE_ZEROES support

----------------------------------------------------------------

Peter Xu (1):
  iothread: fix iothread hang when stop too soon

Stefano Garzarella (7):
  virtio-blk: cleanup using VirtIOBlock *s and VirtIODevice *vdev
  virtio-blk: add acct_failed param to virtio_blk_handle_rw_error()
  virtio-blk: add host_features field in VirtIOBlock
  virtio-blk: add "discard" and "write-zeroes" properties
  virtio-blk: add DISCARD and WRITE_ZEROES features
  tests/virtio-blk: change assert on data_size in virtio_blk_request()
  tests/virtio-blk: add test for WRITE_ZEROES command

Vladimir Sementsov-Ogievskiy (1):
  qemugdb/coroutine: fix arch_prctl has unknown return type

 include/hw/virtio/virtio-blk.h |   5 +-
 hw/block/virtio-blk.c          | 236 +++++++++++++++++++++++++++++----
 hw/core/machine.c              |   2 +
 iothread.c                     |   6 +-
 tests/virtio-blk-test.c        |  75 ++++++++++-
 scripts/qemugdb/coroutine.py   |   2 +-
 6 files changed, 297 insertions(+), 29 deletions(-)

-- 
2.20.1

Re: [Qemu-devel] [PULL 0/9] Block patches

[Peter Maydell]

On Mon, 11 Feb 2019 at 05:50, Stefan Hajnoczi <stefanha@redhat.com> wrote:
>
> The following changes since commit e47f81b617684c4546af286d307b69014a83538a:
>
>   Merge remote-tracking branch 'remotes/thibault/tags/samuel-thibault' into staging (2019-02-07 18:53:25 +0000)
>
> are available in the Git repository at:
>
>   git://github.com/stefanha/qemu.git tags/block-pull-request
>
> for you to fetch changes up to 55140166667bb555c5d05165b93b25557d2e6397:
>
>   tests/virtio-blk: add test for WRITE_ZEROES command (2019-02-11 11:58:17 +0800)
>
> ----------------------------------------------------------------
> Pull request
>
> User-visible changes:
>
>  * virtio-blk: DISCARD and WRITE_ZEROES support

Hi; this fails to pass "make check" (all platforms):

MALLOC_PERTURB_=${MALLOC_PERTURB_:-$(( ${RANDOM:-0} % 255 + 1))}
QTEST_QEMU_BINARY=arm-softmmu/qemu-system-arm QTEST_QEMU_IMG=qemu-img
tests/virtio-blk-test -m
=quick -k --tap < /dev/null | ./scripts/tap-driver.pl
--test-name="virtio-blk-test"
**
ERROR:/home/pm215/qemu/tests/virtio-blk-test.c:272:test_basic:
assertion failed (status == 0): (1 == 0)
ERROR - too few tests run (expected 1, got 0)

thanks
-- PMM