qcow2: Metadata overlap checks

Two new functions are added; the first one checks a given range in the
image file for overlaps with metadata (main header, L1 tables, L2
tables, refcount table and blocks).

The second one should be used immediately before writing to the image
file as it calls the first function and, upon collision, marks the
image as corrupt and makes the BDS unusable, thereby preventing
further access.

Both functions take a bitmask argument specifying the structures which
should be checked for overlaps, making it possible to also check
metadata writes against colliding with other structures.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

4 files changed, 213 insertions, 0 deletions

diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index a61224a414..8ee2f13604 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -25,6 +25,8 @@
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
+#include "qemu/range.h"
+#include "qapi/qmp/types.h"
 
 static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
@@ -1390,3 +1392,173 @@ fail:
     return ret;
 }
 
+#define overlaps_with(ofs, sz) \
+    ranges_overlap(offset, size, ofs, sz)
+
+/*
+ * Checks if the given offset into the image file is actually free to use by
+ * looking for overlaps with important metadata sections (L1/L2 tables etc.),
+ * i.e. a sanity check without relying on the refcount tables.
+ *
+ * The chk parameter specifies exactly what checks to perform (being a bitmask
+ * of QCow2MetadataOverlap values).
+ *
+ * Returns:
+ * - 0 if writing to this offset will not affect the mentioned metadata
+ * - a positive QCow2MetadataOverlap value indicating one overlapping section
+ * - a negative value (-errno) indicating an error while performing a check,
+ *   e.g. when bdrv_read failed on QCOW2_OL_INACTIVE_L2
+ */
+int qcow2_check_metadata_overlap(BlockDriverState *bs, int chk, int64_t offset,
+                                 int64_t size)
+{
+    BDRVQcowState *s = bs->opaque;
+    int i, j;
+
+    if (!size) {
+        return 0;
+    }
+
+    if (chk & QCOW2_OL_MAIN_HEADER) {
+        if (offset < s->cluster_size) {
+            return QCOW2_OL_MAIN_HEADER;
+        }
+    }
+
+    /* align range to test to cluster boundaries */
+    size = align_offset(offset_into_cluster(s, offset) + size, s->cluster_size);
+    offset = start_of_cluster(s, offset);
+
+    if ((chk & QCOW2_OL_ACTIVE_L1) && s->l1_size) {
+        if (overlaps_with(s->l1_table_offset, s->l1_size * sizeof(uint64_t))) {
+            return QCOW2_OL_ACTIVE_L1;
+        }
+    }
+
+    if ((chk & QCOW2_OL_REFCOUNT_TABLE) && s->refcount_table_size) {
+        if (overlaps_with(s->refcount_table_offset,
+            s->refcount_table_size * sizeof(uint64_t))) {
+            return QCOW2_OL_REFCOUNT_TABLE;
+        }
+    }
+
+    if ((chk & QCOW2_OL_SNAPSHOT_TABLE) && s->snapshots_size) {
+        if (overlaps_with(s->snapshots_offset, s->snapshots_size)) {
+            return QCOW2_OL_SNAPSHOT_TABLE;
+        }
+    }
+
+    if ((chk & QCOW2_OL_INACTIVE_L1) && s->snapshots) {
+        for (i = 0; i < s->nb_snapshots; i++) {
+            if (s->snapshots[i].l1_size &&
+                overlaps_with(s->snapshots[i].l1_table_offset,
+                s->snapshots[i].l1_size * sizeof(uint64_t))) {
+                return QCOW2_OL_INACTIVE_L1;
+            }
+        }
+    }
+
+    if ((chk & QCOW2_OL_ACTIVE_L2) && s->l1_table) {
+        for (i = 0; i < s->l1_size; i++) {
+            if ((s->l1_table[i] & L1E_OFFSET_MASK) &&
+                overlaps_with(s->l1_table[i] & L1E_OFFSET_MASK,
+                s->cluster_size)) {
+                return QCOW2_OL_ACTIVE_L2;
+            }
+        }
+    }
+
+    if ((chk & QCOW2_OL_REFCOUNT_BLOCK) && s->refcount_table) {
+        for (i = 0; i < s->refcount_table_size; i++) {
+            if ((s->refcount_table[i] & REFT_OFFSET_MASK) &&
+                overlaps_with(s->refcount_table[i] & REFT_OFFSET_MASK,
+                s->cluster_size)) {
+                return QCOW2_OL_REFCOUNT_BLOCK;
+            }
+        }
+    }
+
+    if ((chk & QCOW2_OL_INACTIVE_L2) && s->snapshots) {
+        for (i = 0; i < s->nb_snapshots; i++) {
+            uint64_t l1_ofs = s->snapshots[i].l1_table_offset;
+            uint32_t l1_sz  = s->snapshots[i].l1_size;
+            uint64_t *l1 = g_malloc(l1_sz * sizeof(uint64_t));
+            int ret;
+
+            ret = bdrv_read(bs->file, l1_ofs / BDRV_SECTOR_SIZE, (uint8_t *)l1,
+                            l1_sz * sizeof(uint64_t) / BDRV_SECTOR_SIZE);
+
+            if (ret < 0) {
+                g_free(l1);
+                return ret;
+            }
+
+            for (j = 0; j < l1_sz; j++) {
+                if ((l1[j] & L1E_OFFSET_MASK) &&
+                    overlaps_with(l1[j] & L1E_OFFSET_MASK, s->cluster_size)) {
+                    g_free(l1);
+                    return QCOW2_OL_INACTIVE_L2;
+                }
+            }
+
+            g_free(l1);
+        }
+    }
+
+    return 0;
+}
+
+static const char *metadata_ol_names[] = {
+    [QCOW2_OL_MAIN_HEADER_BITNR]    = "qcow2_header",
+    [QCOW2_OL_ACTIVE_L1_BITNR]      = "active L1 table",
+    [QCOW2_OL_ACTIVE_L2_BITNR]      = "active L2 table",
+    [QCOW2_OL_REFCOUNT_TABLE_BITNR] = "refcount table",
+    [QCOW2_OL_REFCOUNT_BLOCK_BITNR] = "refcount block",
+    [QCOW2_OL_SNAPSHOT_TABLE_BITNR] = "snapshot table",
+    [QCOW2_OL_INACTIVE_L1_BITNR]    = "inactive L1 table",
+    [QCOW2_OL_INACTIVE_L2_BITNR]    = "inactive L2 table",
+};
+
+/*
+ * First performs a check for metadata overlaps (through
+ * qcow2_check_metadata_overlap); if that fails with a negative value (error
+ * while performing a check), that value is returned. If an impending overlap
+ * is detected, the BDS will be made unusable, the qcow2 file marked corrupt
+ * and -EIO returned.
+ *
+ * Returns 0 if there were neither overlaps nor errors while checking for
+ * overlaps; or a negative value (-errno) on error.
+ */
+int qcow2_pre_write_overlap_check(BlockDriverState *bs, int chk, int64_t offset,
+                                  int64_t size)
+{
+    int ret = qcow2_check_metadata_overlap(bs, chk, offset, size);
+
+    if (ret < 0) {
+        return ret;
+    } else if (ret > 0) {
+        int metadata_ol_bitnr = ffs(ret) - 1;
+        char *message;
+        QObject *data;
+
+        assert(metadata_ol_bitnr < QCOW2_OL_MAX_BITNR);
+
+        fprintf(stderr, "qcow2: Preventing invalid write on metadata (overlaps "
+                "with %s); image marked as corrupt.\n",
+                metadata_ol_names[metadata_ol_bitnr]);
+        message = g_strdup_printf("Prevented %s overwrite",
+                metadata_ol_names[metadata_ol_bitnr]);
+        data = qobject_from_jsonf("{ 'device': %s, 'msg': %s, 'offset': %"
+                PRId64 ", 'size': %" PRId64 " }", bs->device_name, message,
+                offset, size);
+        monitor_protocol_event(QEVENT_BLOCK_IMAGE_CORRUPTED, data);
+        g_free(message);
+        qobject_decref(data);
+
+        qcow2_mark_corrupt(bs);
+        bs->drv = NULL; /* make BDS unusable */
+        return -EIO;
+    }
+
+    return 0;
+}
diff --git a/block/qcow2.h b/block/qcow2.h
index 32ecb338ab..d4448c6350 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -289,6 +289,40 @@ enum {
     QCOW2_CLUSTER_ZERO
 };
 
+typedef enum QCow2MetadataOverlap {
+    QCOW2_OL_MAIN_HEADER_BITNR    = 0,
+    QCOW2_OL_ACTIVE_L1_BITNR      = 1,
+    QCOW2_OL_ACTIVE_L2_BITNR      = 2,
+    QCOW2_OL_REFCOUNT_TABLE_BITNR = 3,
+    QCOW2_OL_REFCOUNT_BLOCK_BITNR = 4,
+    QCOW2_OL_SNAPSHOT_TABLE_BITNR = 5,
+    QCOW2_OL_INACTIVE_L1_BITNR    = 6,
+    QCOW2_OL_INACTIVE_L2_BITNR    = 7,
+
+    QCOW2_OL_MAX_BITNR            = 8,
+
+    QCOW2_OL_NONE           = 0,
+    QCOW2_OL_MAIN_HEADER    = (1 << QCOW2_OL_MAIN_HEADER_BITNR),
+    QCOW2_OL_ACTIVE_L1      = (1 << QCOW2_OL_ACTIVE_L1_BITNR),
+    QCOW2_OL_ACTIVE_L2      = (1 << QCOW2_OL_ACTIVE_L2_BITNR),
+    QCOW2_OL_REFCOUNT_TABLE = (1 << QCOW2_OL_REFCOUNT_TABLE_BITNR),
+    QCOW2_OL_REFCOUNT_BLOCK = (1 << QCOW2_OL_REFCOUNT_BLOCK_BITNR),
+    QCOW2_OL_SNAPSHOT_TABLE = (1 << QCOW2_OL_SNAPSHOT_TABLE_BITNR),
+    QCOW2_OL_INACTIVE_L1    = (1 << QCOW2_OL_INACTIVE_L1_BITNR),
+    /* NOTE: Checking overlaps with inactive L2 tables will result in bdrv
+     * reads. */
+    QCOW2_OL_INACTIVE_L2    = (1 << QCOW2_OL_INACTIVE_L2_BITNR),
+} QCow2MetadataOverlap;
+
+/* Perform all overlap checks which don't require disk access */
+#define QCOW2_OL_CACHED \
+    (QCOW2_OL_MAIN_HEADER | QCOW2_OL_ACTIVE_L1 | QCOW2_OL_ACTIVE_L2 | \
+     QCOW2_OL_REFCOUNT_TABLE | QCOW2_OL_REFCOUNT_BLOCK | \
+     QCOW2_OL_SNAPSHOT_TABLE | QCOW2_OL_INACTIVE_L1)
+
+/* The default checks to perform */
+#define QCOW2_OL_DEFAULT QCOW2_OL_CACHED
+
 #define L1E_OFFSET_MASK 0x00ffffffffffff00ULL
 #define L2E_OFFSET_MASK 0x00ffffffffffff00ULL
 #define L2E_COMPRESSED_OFFSET_SIZE_MASK 0x3fffffffffffffffULL
@@ -390,6 +424,11 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
 
 void qcow2_process_discards(BlockDriverState *bs, int ret);
 
+int qcow2_check_metadata_overlap(BlockDriverState *bs, int chk, int64_t offset,
+                                 int64_t size);
+int qcow2_pre_write_overlap_check(BlockDriverState *bs, int chk, int64_t offset,
+                                  int64_t size);
+
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
                         bool exact_size);
diff --git a/include/monitor/monitor.h b/include/monitor/monitor.h
index 1942cc42fe..10fa0e390c 100644
--- a/include/monitor/monitor.h
+++ b/include/monitor/monitor.h
@@ -48,6 +48,7 @@ typedef enum MonitorEvent {
     QEVENT_BALLOON_CHANGE,
     QEVENT_SPICE_MIGRATE_COMPLETED,
     QEVENT_GUEST_PANICKED,
+    QEVENT_BLOCK_IMAGE_CORRUPTED,
 
     /* Add to 'monitor_event_names' array in monitor.c when
      * defining new events here */
diff --git a/monitor.c b/monitor.c
index ee9744cfb6..2c542e1bca 100644
--- a/monitor.c
+++ b/monitor.c
@@ -504,6 +504,7 @@ static const char *monitor_event_names[] = {
     [QEVENT_BALLOON_CHANGE] = "BALLOON_CHANGE",
     [QEVENT_SPICE_MIGRATE_COMPLETED] = "SPICE_MIGRATE_COMPLETED",
     [QEVENT_GUEST_PANICKED] = "GUEST_PANICKED",
+    [QEVENT_BLOCK_IMAGE_CORRUPTED] = "BLOCK_IMAGE_CORRUPTED",
 };
 QEMU_BUILD_BUG_ON(ARRAY_SIZE(monitor_event_names) != QEVENT_MAX)