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>

8 files changed, 866 insertions, 2 deletions

diff --git a/Makefile.objs b/Makefile.objs
index 50b91e8..1860152 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -20,7 +20,7 @@ block-obj-$(CONFIG_LINUX_AIO) += linux-aio.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 += qed.o
+block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
 block-nested-$(CONFIG_POSIX) += raw-posix.o
diff --git a/block/qed-cluster.c b/block/qed-cluster.c
new file mode 100644
index 0000000..0ec864b
--- /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);
+}
diff --git a/block/qed-gencb.c b/block/qed-gencb.c
new file mode 100644
index 0000000..1513dc6
--- /dev/null
+++ b/block/qed-gencb.c
@@ -0,0 +1,32 @@
+/*
+ * QEMU Enhanced Disk Format
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ *  Stefan Hajnoczi   <stefanha@linux.vnet.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"
+
+void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque)
+{
+    GenericCB *gencb = qemu_malloc(len);
+    gencb->cb = cb;
+    gencb->opaque = opaque;
+    return gencb;
+}
+
+void gencb_complete(void *opaque, int ret)
+{
+    GenericCB *gencb = opaque;
+    BlockDriverCompletionFunc *cb = gencb->cb;
+    void *user_opaque = gencb->opaque;
+
+    qemu_free(gencb);
+    cb(user_opaque, ret);
+}
diff --git a/block/qed-l2-cache.c b/block/qed-l2-cache.c
new file mode 100644
index 0000000..57518a4
--- /dev/null
+++ b/block/qed-l2-cache.c
@@ -0,0 +1,173 @@
+/*
+ * QEMU Enhanced Disk Format L2 Cache
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ *  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.
+ *
+ */
+
+/*
+ * L2 table cache usage is as follows:
+ *
+ * An open image has one L2 table cache that is used to avoid accessing the
+ * image file for recently referenced L2 tables.
+ *
+ * Cluster offset lookup translates the logical offset within the block device
+ * to a cluster offset within the image file.  This is done by indexing into
+ * the L1 and L2 tables which store cluster offsets.  It is here where the L2
+ * table cache serves up recently referenced L2 tables.
+ *
+ * If there is a cache miss, that L2 table is read from the image file and
+ * committed to the cache.  Subsequent accesses to that L2 table will be served
+ * from the cache until the table is evicted from the cache.
+ *
+ * L2 tables are also committed to the cache when new L2 tables are allocated
+ * in the image file.  Since the L2 table cache is write-through, the new L2
+ * table is first written out to the image file and then committed to the
+ * cache.
+ *
+ * Multiple I/O requests may be using an L2 table cache entry at any given
+ * time.  That means an entry may be in use across several requests and
+ * reference counting is needed to free the entry at the correct time.  In
+ * particular, an entry evicted from the cache will only be freed once all
+ * references are dropped.
+ *
+ * An in-flight I/O request will hold a reference to a L2 table cache entry for
+ * the period during which it needs to access the L2 table.  This includes
+ * cluster offset lookup, L2 table allocation, and L2 table update when a new
+ * data cluster has been allocated.
+ *
+ * An interesting case occurs when two requests need to access an L2 table that
+ * is not in the cache.  Since the operation to read the table from the image
+ * file takes some time to complete, both requests may see a cache miss and
+ * start reading the L2 table from the image file.  The first to finish will
+ * commit its L2 table into the cache.  When the second tries to commit its
+ * table will be deleted in favor of the existing cache entry.
+ */
+
+#include "trace.h"
+#include "qed.h"
+
+/* Each L2 holds 2GB so this let's us fully cache a 100GB disk */
+#define MAX_L2_CACHE_SIZE 50
+
+/**
+ * Initialize the L2 cache
+ */
+void qed_init_l2_cache(L2TableCache *l2_cache)
+{
+    QTAILQ_INIT(&l2_cache->entries);
+    l2_cache->n_entries = 0;
+}
+
+/**
+ * Free the L2 cache
+ */
+void qed_free_l2_cache(L2TableCache *l2_cache)
+{
+    CachedL2Table *entry, *next_entry;
+
+    QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next_entry) {
+        qemu_vfree(entry->table);
+        qemu_free(entry);
+    }
+}
+
+/**
+ * Allocate an uninitialized entry from the cache
+ *
+ * The returned entry has a reference count of 1 and is owned by the caller.
+ * The caller must allocate the actual table field for this entry and it must
+ * be freeable using qemu_vfree().
+ */
+CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache)
+{
+    CachedL2Table *entry;
+
+    entry = qemu_mallocz(sizeof(*entry));
+    entry->ref++;
+
+    trace_qed_alloc_l2_cache_entry(l2_cache, entry);
+
+    return entry;
+}
+
+/**
+ * Decrease an entry's reference count and free if necessary when the reference
+ * count drops to zero.
+ */
+void qed_unref_l2_cache_entry(CachedL2Table *entry)
+{
+    if (!entry) {
+        return;
+    }
+
+    entry->ref--;
+    trace_qed_unref_l2_cache_entry(entry, entry->ref);
+    if (entry->ref == 0) {
+        qemu_vfree(entry->table);
+        qemu_free(entry);
+    }
+}
+
+/**
+ * Find an entry in the L2 cache.  This may return NULL and it's up to the
+ * caller to satisfy the cache miss.
+ *
+ * For a cached entry, this function increases the reference count and returns
+ * the entry.
+ */
+CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset)
+{
+    CachedL2Table *entry;
+
+    QTAILQ_FOREACH(entry, &l2_cache->entries, node) {
+        if (entry->offset == offset) {
+            trace_qed_find_l2_cache_entry(l2_cache, entry, offset, entry->ref);
+            entry->ref++;
+            return entry;
+        }
+    }
+    return NULL;
+}
+
+/**
+ * Commit an L2 cache entry into the cache.  This is meant to be used as part of
+ * the process to satisfy a cache miss.  A caller would allocate an entry which
+ * is not actually in the L2 cache and then once the entry was valid and
+ * present on disk, the entry can be committed into the cache.
+ *
+ * Since the cache is write-through, it's important that this function is not
+ * called until the entry is present on disk and the L1 has been updated to
+ * point to the entry.
+ *
+ * N.B. This function steals a reference to the l2_table from the caller so the
+ * caller must obtain a new reference by issuing a call to
+ * qed_find_l2_cache_entry().
+ */
+void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table)
+{
+    CachedL2Table *entry;
+
+    entry = qed_find_l2_cache_entry(l2_cache, l2_table->offset);
+    if (entry) {
+        qed_unref_l2_cache_entry(entry);
+        qed_unref_l2_cache_entry(l2_table);
+        return;
+    }
+
+    if (l2_cache->n_entries >= MAX_L2_CACHE_SIZE) {
+        entry = QTAILQ_FIRST(&l2_cache->entries);
+        QTAILQ_REMOVE(&l2_cache->entries, entry, node);
+        l2_cache->n_entries--;
+        qed_unref_l2_cache_entry(entry);
+    }
+
+    l2_cache->n_entries++;
+    QTAILQ_INSERT_TAIL(&l2_cache->entries, l2_table, node);
+}
diff --git a/block/qed-table.c b/block/qed-table.c
new file mode 100644
index 0000000..d38c673
--- /dev/null
+++ b/block/qed-table.c
@@ -0,0 +1,319 @@
+/*
+ * QEMU Enhanced Disk Format Table I/O
+ *
+ * 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 "trace.h"
+#include "qemu_socket.h" /* for EINPROGRESS on Windows */
+#include "qed.h"
+
+typedef struct {
+    GenericCB gencb;
+    BDRVQEDState *s;
+    QEDTable *table;
+
+    struct iovec iov;
+    QEMUIOVector qiov;
+} QEDReadTableCB;
+
+static void qed_read_table_cb(void *opaque, int ret)
+{
+    QEDReadTableCB *read_table_cb = opaque;
+    QEDTable *table = read_table_cb->table;
+    int noffsets = read_table_cb->iov.iov_len / sizeof(uint64_t);
+    int i;
+
+    /* Handle I/O error */
+    if (ret) {
+        goto out;
+    }
+
+    /* Byteswap offsets */
+    for (i = 0; i < noffsets; i++) {
+        table->offsets[i] = le64_to_cpu(table->offsets[i]);
+    }
+
+out:
+    /* Completion */
+    trace_qed_read_table_cb(read_table_cb->s, read_table_cb->table, ret);
+    gencb_complete(&read_table_cb->gencb, ret);
+}
+
+static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
+                           BlockDriverCompletionFunc *cb, void *opaque)
+{
+    QEDReadTableCB *read_table_cb = gencb_alloc(sizeof(*read_table_cb),
+                                                cb, opaque);
+    QEMUIOVector *qiov = &read_table_cb->qiov;
+    BlockDriverAIOCB *aiocb;
+
+    trace_qed_read_table(s, offset, table);
+
+    read_table_cb->s = s;
+    read_table_cb->table = table;
+    read_table_cb->iov.iov_base = table->offsets,
+    read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size,
+
+    qemu_iovec_init_external(qiov, &read_table_cb->iov, 1);
+    aiocb = bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov,
+                           read_table_cb->iov.iov_len / BDRV_SECTOR_SIZE,
+                           qed_read_table_cb, read_table_cb);
+    if (!aiocb) {
+        qed_read_table_cb(read_table_cb, -EIO);
+    }
+}
+
+typedef struct {
+    GenericCB gencb;
+    BDRVQEDState *s;
+    QEDTable *orig_table;
+    QEDTable *table;
+    bool flush;             /* flush after write? */
+
+    struct iovec iov;
+    QEMUIOVector qiov;
+} QEDWriteTableCB;
+
+static void qed_write_table_cb(void *opaque, int ret)
+{
+    QEDWriteTableCB *write_table_cb = opaque;
+
+    trace_qed_write_table_cb(write_table_cb->s,
+                             write_table_cb->orig_table,
+                             write_table_cb->flush,
+                             ret);
+
+    if (ret) {
+        goto out;
+    }
+
+    if (write_table_cb->flush) {
+        /* We still need to flush first */
+        write_table_cb->flush = false;
+        bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb,
+                       write_table_cb);
+        return;
+    }
+
+out:
+    qemu_vfree(write_table_cb->table);
+    gencb_complete(&write_table_cb->gencb, ret);
+    return;
+}
+
+/**
+ * Write out an updated part or all of a table
+ *
+ * @s:          QED state
+ * @offset:     Offset of table in image file, in bytes
+ * @table:      Table
+ * @index:      Index of first element
+ * @n:          Number of elements
+ * @flush:      Whether or not to sync to disk
+ * @cb:         Completion function
+ * @opaque:     Argument for completion function
+ */
+static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
+                            unsigned int index, unsigned int n, bool flush,
+                            BlockDriverCompletionFunc *cb, void *opaque)
+{
+    QEDWriteTableCB *write_table_cb;
+    BlockDriverAIOCB *aiocb;
+    unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1;
+    unsigned int start, end, i;
+    size_t len_bytes;
+
+    trace_qed_write_table(s, offset, table, index, n);
+
+    /* Calculate indices of the first and one after last elements */
+    start = index & ~sector_mask;
+    end = (index + n + sector_mask) & ~sector_mask;
+
+    len_bytes = (end - start) * sizeof(uint64_t);
+
+    write_table_cb = gencb_alloc(sizeof(*write_table_cb), cb, opaque);
+    write_table_cb->s = s;
+    write_table_cb->orig_table = table;
+    write_table_cb->flush = flush;
+    write_table_cb->table = qemu_blockalign(s->bs, len_bytes);
+    write_table_cb->iov.iov_base = write_table_cb->table->offsets;
+    write_table_cb->iov.iov_len = len_bytes;
+    qemu_iovec_init_external(&write_table_cb->qiov, &write_table_cb->iov, 1);
+
+    /* Byteswap table */
+    for (i = start; i < end; i++) {
+        uint64_t le_offset = cpu_to_le64(table->offsets[i]);
+        write_table_cb->table->offsets[i - start] = le_offset;
+    }
+
+    /* Adjust for offset into table */
+    offset += start * sizeof(uint64_t);
+
+    aiocb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
+                            &write_table_cb->qiov,
+                            write_table_cb->iov.iov_len / BDRV_SECTOR_SIZE,
+                            qed_write_table_cb, write_table_cb);
+    if (!aiocb) {
+        qed_write_table_cb(write_table_cb, -EIO);
+    }
+}
+
+/**
+ * Propagate return value from async callback
+ */
+static void qed_sync_cb(void *opaque, int ret)
+{
+    *(int *)opaque = ret;
+}
+
+int qed_read_l1_table_sync(BDRVQEDState *s)
+{
+    int ret = -EINPROGRESS;
+
+    async_context_push();
+
+    qed_read_table(s, s->header.l1_table_offset,
+                   s->l1_table, qed_sync_cb, &ret);
+    while (ret == -EINPROGRESS) {
+        qemu_aio_wait();
+    }
+
+    async_context_pop();
+
+    return ret;
+}
+
+void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
+                        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE);
+    qed_write_table(s, s->header.l1_table_offset,
+                    s->l1_table, index, n, false, cb, opaque);
+}
+
+int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
+                            unsigned int n)
+{
+    int ret = -EINPROGRESS;
+
+    async_context_push();
+
+    qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
+    while (ret == -EINPROGRESS) {
+        qemu_aio_wait();
+    }
+
+    async_context_pop();
+
+    return ret;
+}
+
+typedef struct {
+    GenericCB gencb;
+    BDRVQEDState *s;
+    uint64_t l2_offset;
+    QEDRequest *request;
+} QEDReadL2TableCB;
+
+static void qed_read_l2_table_cb(void *opaque, int ret)
+{
+    QEDReadL2TableCB *read_l2_table_cb = opaque;
+    QEDRequest *request = read_l2_table_cb->request;
+    BDRVQEDState *s = read_l2_table_cb->s;
+    CachedL2Table *l2_table = request->l2_table;
+
+    if (ret) {
+        /* can't trust loaded L2 table anymore */
+        qed_unref_l2_cache_entry(l2_table);
+        request->l2_table = NULL;
+    } else {
+        l2_table->offset = read_l2_table_cb->l2_offset;
+
+        qed_commit_l2_cache_entry(&s->l2_cache, l2_table);
+
+        /* This is guaranteed to succeed because we just committed the entry
+         * to the cache.
+         */
+        request->l2_table = qed_find_l2_cache_entry(&s->l2_cache,
+                                                    l2_table->offset);
+        assert(request->l2_table != NULL);
+    }
+
+    gencb_complete(&read_l2_table_cb->gencb, ret);
+}
+
+void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
+                       BlockDriverCompletionFunc *cb, void *opaque)
+{
+    QEDReadL2TableCB *read_l2_table_cb;
+
+    qed_unref_l2_cache_entry(request->l2_table);
+
+    /* Check for cached L2 entry */
+    request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset);
+    if (request->l2_table) {
+        cb(opaque, 0);
+        return;
+    }
+
+    request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
+    request->l2_table->table = qed_alloc_table(s);
+
+    read_l2_table_cb = gencb_alloc(sizeof(*read_l2_table_cb), cb, opaque);
+    read_l2_table_cb->s = s;
+    read_l2_table_cb->l2_offset = offset;
+    read_l2_table_cb->request = request;
+
+    BLKDBG_EVENT(s->bs->file, BLKDBG_L2_LOAD);
+    qed_read_table(s, offset, request->l2_table->table,
+                   qed_read_l2_table_cb, read_l2_table_cb);
+}
+
+int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset)
+{
+    int ret = -EINPROGRESS;
+
+    async_context_push();
+
+    qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
+    while (ret == -EINPROGRESS) {
+        qemu_aio_wait();
+    }
+
+    async_context_pop();
+    return ret;
+}
+
+void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
+                        unsigned int index, unsigned int n, bool flush,
+                        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE);
+    qed_write_table(s, request->l2_table->offset,
+                    request->l2_table->table, index, n, flush, cb, opaque);
+}
+
+int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
+                            unsigned int index, unsigned int n, bool flush)
+{
+    int ret = -EINPROGRESS;
+
+    async_context_push();
+
+    qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
+    while (ret == -EINPROGRESS) {
+        qemu_aio_wait();
+    }
+
+    async_context_pop();
+    return ret;
+}
diff --git a/block/qed.c b/block/qed.c
index 1436ac4..cd1bead 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -155,6 +155,13 @@ static int qed_read_string(BlockDriverState *file, uint64_t offset, size_t n,
     return 0;
 }
 
+QEDTable *qed_alloc_table(BDRVQEDState *s)
+{
+    /* Honor O_DIRECT memory alignment requirements */
+    return qemu_blockalign(s->bs,
+                           s->header.cluster_size * s->header.table_size);
+}
+
 static int bdrv_qed_open(BlockDriverState *bs, int flags)
 {
     BDRVQEDState *s = bs->opaque;
@@ -244,11 +251,23 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
         bdrv_flush(bs->file);
     }
 
+    s->l1_table = qed_alloc_table(s);
+    qed_init_l2_cache(&s->l2_cache);
+
+    ret = qed_read_l1_table_sync(s);
+    if (ret) {
+        qed_free_l2_cache(&s->l2_cache);
+        qemu_vfree(s->l1_table);
+    }
     return ret;
 }
 
 static void bdrv_qed_close(BlockDriverState *bs)
 {
+    BDRVQEDState *s = bs->opaque;
+
+    qed_free_l2_cache(&s->l2_cache);
+    qemu_vfree(s->l1_table);
 }
 
 static int bdrv_qed_flush(BlockDriverState *bs)
@@ -368,10 +387,43 @@ static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options)
                       backing_file, backing_fmt);
 }
 
+typedef struct {
+    int is_allocated;
+    int *pnum;
+} QEDIsAllocatedCB;
+
+static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len)
+{
+    QEDIsAllocatedCB *cb = opaque;
+    *cb->pnum = len / BDRV_SECTOR_SIZE;
+    cb->is_allocated = ret == QED_CLUSTER_FOUND;
+}
+
 static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num,
                                   int nb_sectors, int *pnum)
 {
-    return -ENOTSUP;
+    BDRVQEDState *s = bs->opaque;
+    uint64_t pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
+    size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE;
+    QEDIsAllocatedCB cb = {
+        .is_allocated = -1,
+        .pnum = pnum,
+    };
+    QEDRequest request = { .l2_table = NULL };
+
+    async_context_push();
+
+    qed_find_cluster(s, &request, pos, len, qed_is_allocated_cb, &cb);
+
+    while (cb.is_allocated == -1) {
+        qemu_aio_wait();
+    }
+
+    async_context_pop();
+
+    qed_unref_l2_cache_entry(request.l2_table);
+
+    return cb.is_allocated;
 }
 
 static int bdrv_qed_make_empty(BlockDriverState *bs)
diff --git a/block/qed.h b/block/qed.h
index 1f8a125..6d49a4d 100644
--- a/block/qed.h
+++ b/block/qed.h
@@ -96,16 +96,118 @@ typedef struct {
 } QEDHeader;
 
 typedef struct {
+    uint64_t offsets[0];            /* in bytes */
+} QEDTable;
+
+/* The L2 cache is a simple write-through cache for L2 structures */
+typedef struct CachedL2Table {
+    QEDTable *table;
+    uint64_t offset;    /* offset=0 indicates an invalidate entry */
+    QTAILQ_ENTRY(CachedL2Table) node;
+    int ref;
+} CachedL2Table;
+
+typedef struct {
+    QTAILQ_HEAD(, CachedL2Table) entries;
+    unsigned int n_entries;
+} L2TableCache;
+
+typedef struct QEDRequest {
+    CachedL2Table *l2_table;
+} QEDRequest;
+
+typedef struct {
     BlockDriverState *bs;           /* device */
     uint64_t file_size;             /* length of image file, in bytes */
 
     QEDHeader header;               /* always cpu-endian */
+    QEDTable *l1_table;
+    L2TableCache l2_cache;          /* l2 table cache */
     uint32_t table_nelems;
     uint32_t l1_shift;
     uint32_t l2_shift;
     uint32_t l2_mask;
 } BDRVQEDState;
 
+enum {
+    QED_CLUSTER_FOUND,         /* cluster found */
+    QED_CLUSTER_L2,            /* cluster missing in L2 */
+    QED_CLUSTER_L1,            /* cluster missing in L1 */
+};
+
+/**
+ * qed_find_cluster() completion callback
+ *
+ * @opaque:     User data for completion callback
+ * @ret:        QED_CLUSTER_FOUND   Success
+ *              QED_CLUSTER_L2      Data cluster unallocated in L2
+ *              QED_CLUSTER_L1      L2 unallocated in L1
+ *              -errno              POSIX error occurred
+ * @offset:     Data cluster offset
+ * @len:        Contiguous bytes starting from cluster offset
+ *
+ * This function is invoked when qed_find_cluster() completes.
+ *
+ * On success ret is QED_CLUSTER_FOUND and offset/len are a contiguous range
+ * in the image file.
+ *
+ * On failure ret is QED_CLUSTER_L2 or QED_CLUSTER_L1 for missing L2 or L1
+ * table offset, respectively.  len is number of contiguous unallocated bytes.
+ */
+typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len);
+
+/**
+ * Generic callback for chaining async callbacks
+ */
+typedef struct {
+    BlockDriverCompletionFunc *cb;
+    void *opaque;
+} GenericCB;
+
+void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque);
+void gencb_complete(void *opaque, int ret);
+
+/**
+ * L2 cache functions
+ */
+void qed_init_l2_cache(L2TableCache *l2_cache);
+void qed_free_l2_cache(L2TableCache *l2_cache);
+CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache);
+void qed_unref_l2_cache_entry(CachedL2Table *entry);
+CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset);
+void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table);
+
+/**
+ * Table I/O functions
+ */
+int qed_read_l1_table_sync(BDRVQEDState *s);
+void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
+                        BlockDriverCompletionFunc *cb, void *opaque);
+int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
+                            unsigned int n);
+int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
+                           uint64_t offset);
+void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
+                       BlockDriverCompletionFunc *cb, void *opaque);
+void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
+                        unsigned int index, unsigned int n, bool flush,
+                        BlockDriverCompletionFunc *cb, void *opaque);
+int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
+                            unsigned int index, unsigned int n, bool flush);
+
+/**
+ * Cluster functions
+ */
+void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
+                      size_t len, QEDFindClusterFunc *cb, void *opaque);
+
+/**
+ * Consistency check
+ */
+int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix);
+
+QEDTable *qed_alloc_table(BDRVQEDState *s);
+
 /**
  * Round down to the start of a cluster
  */
@@ -114,6 +216,27 @@ static inline uint64_t qed_start_of_cluster(BDRVQEDState *s, uint64_t offset)
     return offset & ~(uint64_t)(s->header.cluster_size - 1);
 }
 
+static inline uint64_t qed_offset_into_cluster(BDRVQEDState *s, uint64_t offset)
+{
+    return offset & (s->header.cluster_size - 1);
+}
+
+static inline unsigned int qed_bytes_to_clusters(BDRVQEDState *s, size_t bytes)
+{
+    return qed_start_of_cluster(s, bytes + (s->header.cluster_size - 1)) /
+           (s->header.cluster_size - 1);
+}
+
+static inline unsigned int qed_l1_index(BDRVQEDState *s, uint64_t pos)
+{
+    return pos >> s->l1_shift;
+}
+
+static inline unsigned int qed_l2_index(BDRVQEDState *s, uint64_t pos)
+{
+    return (pos >> s->l2_shift) & s->l2_mask;
+}
+
 /**
  * Test if a cluster offset is valid
  */
diff --git a/trace-events b/trace-events
index da03d4b..59f97a2 100644
--- a/trace-events
+++ b/trace-events
@@ -192,3 +192,14 @@ disable sun4m_iommu_bad_addr(uint64_t addr) "bad addr %"PRIx64""
 
 # vl.c
 disable vm_state_notify(int running, int reason) "running %d reason %d"
+
+# block/qed-l2-cache.c
+disable qed_alloc_l2_cache_entry(void *l2_cache, void *entry) "l2_cache %p entry %p"
+disable qed_unref_l2_cache_entry(void *entry, int ref) "entry %p ref %d"
+disable qed_find_l2_cache_entry(void *l2_cache, void *entry, uint64_t offset, int ref) "l2_cache %p entry %p offset %"PRIu64" ref %d"
+
+# block/qed-table.c
+disable qed_read_table(void *s, uint64_t offset, void *table) "s %p offset %"PRIu64" table %p"
+disable qed_read_table_cb(void *s, void *table, int ret) "s %p table %p ret %d"
+disable qed_write_table(void *s, uint64_t offset, void *table, unsigned int index, unsigned int n) "s %p offset %"PRIu64" table %p index %u n %u"
+disable qed_write_table_cb(void *s, void *table, int flush, int ret) "s %p table %p flush %d ret %d"