[pve-devel] [PATCH qemu] fix #1534: vma: Add extract filter for disk images

[pve-devel] [PATCH qemu] fix #1534: vma: Add extract filter for disk images

[Filip Schauer]

Add a filter to the "vma extract" command. A wildcard can be passed with
"-f" to match disk images that should be extracted.

Example to extract all IDE drives from vzdump.vma:

vma extract vzdump.vma -f "drive-ide*" extractdir

Signed-off-by: Filip Schauer <f.schauer@proxmox.com>
---
 ...VE-Backup-add-vma-backup-format-code.patch | 27 ++++++++++++++-----
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/debian/patches/pve/0027-PVE-Backup-add-vma-backup-format-code.patch b/debian/patches/pve/0027-PVE-Backup-add-vma-backup-format-code.patch
index 8471a6f..b29d348 100644
--- a/debian/patches/pve/0027-PVE-Backup-add-vma-backup-format-code.patch
+++ b/debian/patches/pve/0027-PVE-Backup-add-vma-backup-format-code.patch
@@ -1738,7 +1738,7 @@ new file mode 100644
 index 0000000000..304f02bc84
 --- /dev/null
 +++ b/vma.c
-@@ -0,0 +1,878 @@
+@@ -0,0 +1,893 @@
 +/*
 + * VMA: Virtual Machine Archive
 + *
@@ -1753,6 +1753,7 @@ index 0000000000..304f02bc84
 + */
 +
 +#include "qemu/osdep.h"
++#include <fnmatch.h>
 +#include <glib.h>
 +
 +#include "vma.h"
@@ -1772,7 +1773,7 @@ index 0000000000..304f02bc84
 +        "vma list <filename>\n"
 +        "vma config <filename> [-c config]\n"
 +        "vma create <filename> [-c config] pathname ...\n"
-+        "vma extract <filename> [-r <fifo>] <targetdir>\n"
++        "vma extract <filename> [-f <filter>] [-r <fifo>] <targetdir>\n"
 +        "vma verify <filename> [-v]\n"
 +        ;
 +
@@ -1917,9 +1918,10 @@ index 0000000000..304f02bc84
 +    const char *filename;
 +    const char *dirname;
 +    const char *readmap = NULL;
++    const char *filter = NULL;
 +
 +    for (;;) {
-+        c = getopt(argc, argv, "hvr:");
++        c = getopt(argc, argv, "hvf:r:");
 +        if (c == -1) {
 +            break;
 +        }
@@ -1928,6 +1930,9 @@ index 0000000000..304f02bc84
 +        case 'h':
 +            help();
 +            break;
++        case 'f':
++            filter = optarg;
++            break;
 +        case 'r':
 +            readmap = optarg;
 +            break;
@@ -2064,12 +2069,12 @@ index 0000000000..304f02bc84
 +
 +    int i;
 +    int vmstate_fd = -1;
-+    guint8 vmstate_stream = 0;
++    uint8_t filter_bitmap[256 / 8];
++    memset(filter_bitmap, 0, sizeof(filter_bitmap));
 +
 +    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) {
@@ -2078,6 +2083,16 @@ index 0000000000..304f02bc84
 +            }
 +            g_free(statefn);
 +        } else if (di) {
++            if (filter && (fnmatch(filter, di->devname, 0) != 0)) {
++                if (vma_reader_register_bs(vmar, i, NULL, true, true, &errp) < 0) {
++                    g_error("%s", error_get_pretty(errp));
++                }
++
++                continue;
++            }
++
++            filter_bitmap[i / 8] |= 1 << (i % 8);
++
 +            char *devfn = NULL;
 +            const char *format = NULL;
 +            uint64_t throttling_bps = 0;
@@ -2190,7 +2205,7 @@ index 0000000000..304f02bc84
 +    if (!readmap) {
 +        for (i = 1; i < 255; i++) {
 +            VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i);
-+            if (di && (i != vmstate_stream)) {
++            if (di && (filter_bitmap[i / 8] & (1 << (i % 8)))) {
 +                char *tmpfn = g_strdup_printf("%s/tmp-disk-%s.raw",
 +                                              dirname, di->devname);
 +                char *fn = g_strdup_printf("%s/disk-%s.raw",
-- 
2.39.2

Re: [pve-devel] [PATCH qemu] fix #1534: vma: Add extract filter for disk images

[Fiona Ebner]

Am 07.08.23 um 12:08 schrieb Filip Schauer:
> Add a filter to the "vma extract" command. A wildcard can be passed with
> "-f" to match disk images that should be extracted.

The bug report doesn't mention wildcards, but a list of image names.
Restoring drive-ide2 and drive-scsi0 becomes awkward with a single
pattern and I don't see why a list of just the names shouldn't suffice.
Cases with many disks are rather rare and even in extreme cases it won't
be more than ~30 disks or so. And if users request patterns, we can
still add it on top.

> @@ -2064,12 +2069,12 @@ index 0000000000..304f02bc84
>  +
>  +    int i;
>  +    int vmstate_fd = -1;
> -+    guint8 vmstate_stream = 0;
> ++    uint8_t filter_bitmap[256 / 8];

I'd rather use a bool array (if the compiler optimizes it to a bitmap
great, otherwise it's still easier to read), but...

> ++    memset(filter_bitmap, 0, sizeof(filter_bitmap));
>  +
>  +    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) {
> @@ -2078,6 +2083,16 @@ index 0000000000..304f02bc84
>  +            }
>  +            g_free(statefn);
>  +        } else if (di) {
> ++            if (filter && (fnmatch(filter, di->devname, 0) != 0)) {
> ++                if (vma_reader_register_bs(vmar, i, NULL, true, true, &errp) < 0) {
> ++                    g_error("%s", error_get_pretty(errp));
> ++                }
> ++
> ++                continue;
> ++            }

...instead of doing this, you could also just make sure not to allocate
an image when the name is not included and set the skip flag when
calling vma_reader_register_bs(), re-using the existing mechanism for
partial restore.

Does not registering all even work? I thought vma was written in such a
way that it would read everything, which is why the skip logic was
necessary IIRC. Peeking at the code, doesn't restore_write_data() call
restore_write_data() with a dev_id from the backup we didn't register
the stream for at some point otherwise?