aboutsummaryrefslogtreecommitdiff
path: root/block/qed-cluster.c
diff options
context:
space:
mode:
authorStefan Hajnoczi <stefanha@linux.vnet.ibm.com>2010-12-06 16:08:01 +0000
committerKevin Wolf <kwolf@redhat.com>2010-12-17 16:11:04 +0100
commit298800cae72eb2a549374189e87615b2b0b79262 (patch)
treefadedcd0842fa60989078a4aa8c1959a27adbbd0 /block/qed-cluster.c
parent75411d236d93d79d8052e0116c3eeebe23e2778b (diff)
qed: Table, L2 cache, and cluster functions
This patch adds code to look up data cluster offsets in the image via the L1/L2 tables. The L2 tables are writethrough cached in memory for performance (each read/write requires a lookup so it is essential to cache the tables). With cluster lookup code in place it is possible to implement bdrv_is_allocated() to query the number of contiguous allocated/unallocated clusters. Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Diffstat (limited to 'block/qed-cluster.c')
-rw-r--r--block/qed-cluster.c154
1 files changed, 154 insertions, 0 deletions
diff --git a/block/qed-cluster.c b/block/qed-cluster.c
new file mode 100644
index 0000000000..0ec864b14c
--- /dev/null
+++ b/block/qed-cluster.c
@@ -0,0 +1,154 @@
+/*
+ * QEMU Enhanced Disk Format Cluster functions
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qed.h"
+
+/**
+ * Count the number of contiguous data clusters
+ *
+ * @s: QED state
+ * @table: L2 table
+ * @index: First cluster index
+ * @n: Maximum number of clusters
+ * @offset: Set to first cluster offset
+ *
+ * This function scans tables for contiguous allocated or free clusters.
+ */
+static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s,
+ QEDTable *table,
+ unsigned int index,
+ unsigned int n,
+ uint64_t *offset)
+{
+ unsigned int end = MIN(index + n, s->table_nelems);
+ uint64_t last = table->offsets[index];
+ unsigned int i;
+
+ *offset = last;
+
+ for (i = index + 1; i < end; i++) {
+ if (last == 0) {
+ /* Counting free clusters */
+ if (table->offsets[i] != 0) {
+ break;
+ }
+ } else {
+ /* Counting allocated clusters */
+ if (table->offsets[i] != last + s->header.cluster_size) {
+ break;
+ }
+ last = table->offsets[i];
+ }
+ }
+ return i - index;
+}
+
+typedef struct {
+ BDRVQEDState *s;
+ uint64_t pos;
+ size_t len;
+
+ QEDRequest *request;
+
+ /* User callback */
+ QEDFindClusterFunc *cb;
+ void *opaque;
+} QEDFindClusterCB;
+
+static void qed_find_cluster_cb(void *opaque, int ret)
+{
+ QEDFindClusterCB *find_cluster_cb = opaque;
+ BDRVQEDState *s = find_cluster_cb->s;
+ QEDRequest *request = find_cluster_cb->request;
+ uint64_t offset = 0;
+ size_t len = 0;
+ unsigned int index;
+ unsigned int n;
+
+ if (ret) {
+ goto out;
+ }
+
+ index = qed_l2_index(s, find_cluster_cb->pos);
+ n = qed_bytes_to_clusters(s,
+ qed_offset_into_cluster(s, find_cluster_cb->pos) +
+ find_cluster_cb->len);
+ n = qed_count_contiguous_clusters(s, request->l2_table->table,
+ index, n, &offset);
+
+ ret = offset ? QED_CLUSTER_FOUND : QED_CLUSTER_L2;
+ len = MIN(find_cluster_cb->len, n * s->header.cluster_size -
+ qed_offset_into_cluster(s, find_cluster_cb->pos));
+
+ if (offset && !qed_check_cluster_offset(s, offset)) {
+ ret = -EINVAL;
+ }
+
+out:
+ find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len);
+ qemu_free(find_cluster_cb);
+}
+
+/**
+ * Find the offset of a data cluster
+ *
+ * @s: QED state
+ * @request: L2 cache entry
+ * @pos: Byte position in device
+ * @len: Number of bytes
+ * @cb: Completion function
+ * @opaque: User data for completion function
+ *
+ * This function translates a position in the block device to an offset in the
+ * image file. It invokes the cb completion callback to report back the
+ * translated offset or unallocated range in the image file.
+ *
+ * If the L2 table exists, request->l2_table points to the L2 table cache entry
+ * and the caller must free the reference when they are finished. The cache
+ * entry is exposed in this way to avoid callers having to read the L2 table
+ * again later during request processing. If request->l2_table is non-NULL it
+ * will be unreferenced before taking on the new cache entry.
+ */
+void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
+ size_t len, QEDFindClusterFunc *cb, void *opaque)
+{
+ QEDFindClusterCB *find_cluster_cb;
+ uint64_t l2_offset;
+
+ /* Limit length to L2 boundary. Requests are broken up at the L2 boundary
+ * so that a request acts on one L2 table at a time.
+ */
+ len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos);
+
+ l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)];
+ if (!l2_offset) {
+ cb(opaque, QED_CLUSTER_L1, 0, len);
+ return;
+ }
+ if (!qed_check_table_offset(s, l2_offset)) {
+ cb(opaque, -EINVAL, 0, 0);
+ return;
+ }
+
+ find_cluster_cb = qemu_malloc(sizeof(*find_cluster_cb));
+ find_cluster_cb->s = s;
+ find_cluster_cb->pos = pos;
+ find_cluster_cb->len = len;
+ find_cluster_cb->cb = cb;
+ find_cluster_cb->opaque = opaque;
+ find_cluster_cb->request = request;
+
+ qed_read_l2_table(s, request, l2_offset,
+ qed_find_cluster_cb, find_cluster_cb);
+}