[Qemu-devel] [PATCH, RFC] block: separate raw images from the file protocol

[Christoph Hellwig]

We're running into various problems because the "raw" file access, which
is used internally by the various image formats is entangled with the
"raw" image format, which maps the VM view 1:1 to a file system.

This patch renames the raw file backends to the file protocol which
is treated like other protocols (e.g. nbd and http) and adds a new
"raw" image format which is just a wrapper around calls to the underlying
protocol.

The patch is surprisingly simple, besides changing the probing logical
in block.c to only look for image formats when using bdrv_open and
renaming of the old raw protocols to file there's almost nothing in there.

One thing that looks suspicious in the patch is moving the actual
posix file creation from raw-posix into the new raw image.  This is
a layering violation, but exactly the same as done by all other image
formats implementing the create operations, and not easily fixable
without a major API change in this area.

The only issues still open are in the handling of the host devices.
Firstly in current qemu we can specifiy the host* format names
on various command line acceping images, but the new code can't
do that without adding some translation.  Second the layering breaks
the no_zero_init flag in the BlockDriver used by qemu-img.  I'm not
happy how this is done per-driver instead of per-state so I'll
prepare a separate patch to clean this up.

There's some more cleanup opportunity after this patch, e.g. using
separate lists and registration functions for image formats vs
protocols and maybe even host drivers, but this can be done at a
later stage.

Also there's a check for protocol in bdrv_open for the BDRV_O_SNAPSHOT
case that I don't quite understand, but which I fear won't work as
expected - possibly even before this patch.

Note that this patch requires various recent block patches from Kevin
and me, which should all be in his block queue.

Signed-off-by: Christoph Hellwig <address@hidden>

Index: qemu/Makefile.objs
===================================================================
--- qemu.orig/Makefile.objs     2010-04-07 13:56:27.429254145 +0200
+++ qemu/Makefile.objs  2010-04-07 22:01:24.974284455 +0200
@@ -12,7 +12,7 @@ block-obj-y += nbd.o block.o aio.o aes.o
 block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 
-block-nested-y += cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
+block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o 
vvfat.o
 block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o
 block-nested-y += parallels.o nbd.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
Index: qemu/block.c
===================================================================
--- qemu.orig/block.c   2010-04-07 13:56:27.435254284 +0200
+++ qemu/block.c        2010-04-07 22:21:25.803256099 +0200
@@ -248,6 +248,28 @@ int is_windows_drive(const char *filenam
 }
 #endif
 
+/*
+ * Detect host devices. By convention, /dev/cdrom[N] is always
+ * recognized as a host CDROM.
+ */
+static BlockDriver *find_hdev_driver(const char *filename)
+{
+    int score_max = 0, score;
+    BlockDriver *drv = NULL, *d;
+
+    for (d = first_drv; d; d = d->next) {
+        if (d->bdrv_probe_device) {
+            score = d->bdrv_probe_device(filename);
+            if (score > score_max) {
+                score_max = score;
+                drv = d;
+            }
+        }
+    }
+
+    return drv;
+}
+
 static BlockDriver *find_protocol(const char *filename)
 {
     BlockDriver *drv1;
@@ -258,11 +280,16 @@ static BlockDriver *find_protocol(const
 #ifdef _WIN32
     if (is_windows_drive(filename) ||
         is_windows_drive_prefix(filename))
-        return bdrv_find_format("raw");
+        return bdrv_find_format("file");
 #endif
     p = strchr(filename, ':');
-    if (!p)
-        return bdrv_find_format("raw");
+    if (!p) {
+        drv1 = find_hdev_driver(filename);
+        if (!drv1) {
+            drv1 = bdrv_find_format("file");
+        }
+        return drv1;
+    }
     len = p - filename;
     if (len > sizeof(protocol) - 1)
         len = sizeof(protocol) - 1;
@@ -276,28 +303,6 @@ static BlockDriver *find_protocol(const
     return NULL;
 }
 
-/*
- * Detect host devices. By convention, /dev/cdrom[N] is always
- * recognized as a host CDROM.
- */
-static BlockDriver *find_hdev_driver(const char *filename)
-{
-    int score_max = 0, score;
-    BlockDriver *drv = NULL, *d;
-
-    for (d = first_drv; d; d = d->next) {
-        if (d->bdrv_probe_device) {
-            score = d->bdrv_probe_device(filename);
-            if (score > score_max) {
-                score_max = score;
-                drv = d;
-            }
-        }
-    }
-
-    return drv;
-}
-
 static BlockDriver *find_image_format(const char *filename)
 {
     int ret, score, score_max;
@@ -320,6 +325,7 @@ static BlockDriver *find_image_format(co
     }
 
     score_max = 0;
+    drv = NULL;
     for(drv1 = first_drv; drv1 != NULL; drv1 = drv1->next) {
         if (drv1->bdrv_probe) {
             score = drv1->bdrv_probe(buf, ret, filename);
@@ -424,10 +430,7 @@ int bdrv_open(BlockDriverState *bs, cons
     pstrcpy(bs->filename, sizeof(bs->filename), filename);
 
     if (!drv) {
-        drv = find_hdev_driver(filename);
-        if (!drv) {
-            drv = find_image_format(filename);
-        }
+        drv = find_image_format(filename);
     }
 
     if (!drv) {
Index: qemu/block/raw-posix.c
===================================================================
--- qemu.orig/block/raw-posix.c 2010-04-07 13:56:27.446254494 +0200
+++ qemu/block/raw-posix.c      2010-04-07 22:21:01.012006275 +0200
@@ -723,60 +723,21 @@ static int64_t raw_getlength(BlockDriver
 }
 #endif
 
-static int raw_create(const char *filename, QEMUOptionParameter *options)
-{
-    int fd;
-    int result = 0;
-    int64_t total_size = 0;
-
-    /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n / 512;
-        }
-        options++;
-    }
-
-    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
-              0644);
-    if (fd < 0) {
-        result = -errno;
-    } else {
-        if (ftruncate(fd, total_size * 512) != 0) {
-            result = -errno;
-        }
-        if (close(fd) != 0) {
-            result = -errno;
-        }
-    }
-    return result;
-}
-
 static void raw_flush(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
     qemu_fdatasync(s->fd);
 }
 
-
-static QEMUOptionParameter raw_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
-};
-
-static BlockDriver bdrv_raw = {
-    .format_name = "raw",
+static BlockDriver bdrv_file = {
+    .format_name = "file",
+    .protocol_name = "file",
     .instance_size = sizeof(BDRVRawState),
     .bdrv_probe = NULL, /* no probe for protocols */
     .bdrv_open = raw_open,
     .bdrv_read = raw_read,
     .bdrv_write = raw_write,
     .bdrv_close = raw_close,
-    .bdrv_create = raw_create,
     .bdrv_flush = raw_flush,
 
     .bdrv_aio_readv = raw_aio_readv,
@@ -785,8 +746,6 @@ static BlockDriver bdrv_raw = {
 
     .bdrv_truncate = raw_truncate,
     .bdrv_getlength = raw_getlength,
-
-    .create_options = raw_create_options,
 };
 
 /***********************************************/
@@ -1026,12 +985,12 @@ static int hdev_create(const char *filen
 
 static BlockDriver bdrv_host_device = {
     .format_name        = "host_device",
+    .protocol_name        = "host_device",
     .instance_size      = sizeof(BDRVRawState),
     .bdrv_probe_device  = hdev_probe_device,
     .bdrv_open          = hdev_open,
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
     .no_zero_init       = 1,
     .bdrv_flush         = raw_flush,
 
@@ -1140,12 +1099,12 @@ static int floppy_eject(BlockDriverState
 
 static BlockDriver bdrv_host_floppy = {
     .format_name        = "host_floppy",
+    .protocol_name      = "host_floppy",
     .instance_size      = sizeof(BDRVRawState),
     .bdrv_probe_device = floppy_probe_device,
     .bdrv_open          = floppy_open,
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
     .no_zero_init       = 1,
     .bdrv_flush         = raw_flush,
 
@@ -1239,12 +1198,12 @@ static int cdrom_set_locked(BlockDriverS
 
 static BlockDriver bdrv_host_cdrom = {
     .format_name        = "host_cdrom",
+    .protocol_name      = "host_cdrom",
     .instance_size      = sizeof(BDRVRawState),
     .bdrv_probe_device = cdrom_probe_device,
     .bdrv_open          = cdrom_open,
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
     .no_zero_init       = 1,
     .bdrv_flush         = raw_flush,
 
@@ -1361,12 +1320,12 @@ static int cdrom_set_locked(BlockDriverS
 
 static BlockDriver bdrv_host_cdrom = {
     .format_name        = "host_cdrom",
+    .protocol_name      = "host_cdrom",
     .instance_size      = sizeof(BDRVRawState),
     .bdrv_probe_device = cdrom_probe_device,
     .bdrv_open          = cdrom_open,
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
     .no_zero_init       = 1,
     .bdrv_flush         = raw_flush,
 
@@ -1385,13 +1344,13 @@ static BlockDriver bdrv_host_cdrom = {
 };
 #endif /* __FreeBSD__ */
 
-static void bdrv_raw_init(void)
+static void bdrv_file_init(void)
 {
     /*
      * Register all the drivers.  Note that order is important, the driver
      * registered last will get probed first.
      */
-    bdrv_register(&bdrv_raw);
+    bdrv_register(&bdrv_file);
     bdrv_register(&bdrv_host_device);
 #ifdef __linux__
     bdrv_register(&bdrv_host_floppy);
@@ -1402,4 +1361,4 @@ static void bdrv_raw_init(void)
 #endif
 }
 
-block_init(bdrv_raw_init);
+block_init(bdrv_file_init);
Index: qemu/block/raw-win32.c
===================================================================
--- qemu.orig/block/raw-win32.c 2010-04-07 13:56:27.458254284 +0200
+++ qemu/block/raw-win32.c      2010-04-07 22:20:15.295005645 +0200
@@ -238,8 +238,9 @@ static QEMUOptionParameter raw_create_op
     { NULL }
 };
 
-static BlockDriver bdrv_raw = {
-    .format_name       = "raw",
+static BlockDriver bdrv_file = {
+    .format_name       = "file",
+    .protocol_name     = "file",
     .instance_size     = sizeof(BDRVRawState),
     .bdrv_open         = raw_open,
     .bdrv_close                = raw_close,
@@ -395,6 +396,7 @@ static int raw_set_locked(BlockDriverSta
 
 static BlockDriver bdrv_host_device = {
     .format_name       = "host_device",
+    .protocol_name     = "host_device",
     .instance_size     = sizeof(BDRVRawState),
     .bdrv_probe_device = hdev_probe_device,
     .bdrv_open         = hdev_open,
@@ -406,10 +408,10 @@ static BlockDriver bdrv_host_device = {
     .bdrv_getlength    = raw_getlength,
 };
 
-static void bdrv_raw_init(void)
+static void bdrv_file_init(void)
 {
-    bdrv_register(&bdrv_raw);
+    bdrv_register(&bdrv_file);
     bdrv_register(&bdrv_host_device);
 }
 
-block_init(bdrv_raw_init);
+block_init(bdrv_file_init);
Index: qemu/block/raw.c
===================================================================
--- /dev/null   1970-01-01 00:00:00.000000000 +0000
+++ qemu/block/raw.c    2010-04-07 22:07:49.054255891 +0200
@@ -0,0 +1,195 @@
+
+#include "qemu-common.h"
+#include "block_int.h"
+#include "module.h"
+
+typedef struct RAWState {
+    BlockDriverState *hd;
+} RAWState;
+
+static int raw_open(BlockDriverState *bs, const char *filename, int flags)
+{
+    RAWState *s = bs->opaque;
+    int ret;
+
+    ret = bdrv_file_open(&s->hd, filename, flags);
+    if (!ret) {
+        bs->sg = s->hd->sg;
+    }
+
+    return ret;
+}
+
+static int raw_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_read(s->hd, sector_num, buf, nb_sectors);
+}
+
+static int raw_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_write(s->hd, sector_num, buf, nb_sectors);
+}
+
+static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    RAWState *s = bs->opaque;
+
+    return bdrv_aio_readv(s->hd, sector_num, qiov, nb_sectors, cb, opaque);
+}
+
+static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    RAWState *s = bs->opaque;
+
+    return bdrv_aio_writev(s->hd, sector_num, qiov, nb_sectors, cb, opaque);
+}
+
+static void raw_close(BlockDriverState *bs)
+{
+    RAWState *s = bs->opaque;
+    bdrv_delete(s->hd);
+}
+
+static void raw_flush(BlockDriverState *bs)
+{
+    RAWState *s = bs->opaque;
+    bdrv_flush(s->hd);
+}
+
+static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_aio_flush(s->hd, cb, opaque);
+}
+
+static int64_t raw_getlength(BlockDriverState *bs)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_getlength(s->hd);
+}
+
+static int raw_truncate(BlockDriverState *bs, int64_t offset)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_truncate(s->hd, offset);
+}
+
+static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
+{
+   return 1; /* everything can be opened as raw image */
+}
+
+static int raw_is_inserted(BlockDriverState *bs)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_is_inserted(s->hd);
+}
+
+static int raw_eject(BlockDriverState *bs, int eject_flag)
+{
+    RAWState *s = bs->opaque;
+    return bdrv_eject(s->hd, eject_flag);
+}
+
+static int raw_set_locked(BlockDriverState *bs, int locked)
+{
+    RAWState *s = bs->opaque;
+    bdrv_set_locked(s->hd, locked);
+    return 0;
+}
+
+static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+{
+   RAWState *s = bs->opaque;
+   return bdrv_ioctl(s->hd, req, buf);
+}
+
+static BlockDriverAIOCB *raw_aio_ioctl(BlockDriverState *bs,
+        unsigned long int req, void *buf,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+   RAWState *s = bs->opaque;
+   return bdrv_aio_ioctl(s->hd, req, buf, cb, opaque);
+}
+
+static int raw_create(const char *filename, QEMUOptionParameter *options)
+{
+    int fd;
+    int result = 0;
+    int64_t total_size = 0;
+
+    /* Read out options */
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n / 512;
+        }
+        options++;
+    }
+
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+              0644);
+    if (fd < 0) {
+        result = -errno;
+    } else {
+        if (ftruncate(fd, total_size * 512) != 0) {
+            result = -errno;
+        }
+        if (close(fd) != 0) {
+            result = -errno;
+        }
+    }
+    return result;
+}
+
+static QEMUOptionParameter raw_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    { NULL }
+};
+
+static BlockDriver bdrv_raw = {
+    .format_name        = "raw",
+
+    .instance_size      = sizeof(RAWState),
+
+    .bdrv_open          = raw_open,
+    .bdrv_close         = raw_close,
+    .bdrv_read          = raw_read,
+    .bdrv_write         = raw_write,
+    .bdrv_flush         = raw_flush,
+    .bdrv_probe         = raw_probe,
+    .bdrv_getlength     = raw_getlength,
+    .bdrv_truncate      = raw_truncate,
+
+    .bdrv_aio_readv     = raw_aio_readv,
+    .bdrv_aio_writev    = raw_aio_writev,
+    .bdrv_aio_flush     = raw_aio_flush,
+
+    .bdrv_is_inserted   = raw_is_inserted,
+    .bdrv_eject         = raw_eject,
+    .bdrv_set_locked    = raw_set_locked,
+    .bdrv_ioctl         = raw_ioctl,
+    .bdrv_aio_ioctl     = raw_aio_ioctl,
+
+    .bdrv_create        = raw_create,
+    .create_options     = raw_create_options,
+};
+
+static void bdrv_raw_init(void)
+{
+    bdrv_register(&bdrv_raw);
+}
+
+block_init(bdrv_raw_init);