int dm_array_get_value(struct dm_array_info *info, dm_block_t root,
uint32_t index, void *value_le)
{
int r;
struct dm_block *block;
struct array_block *ab;
size_t size_of_block;
unsigned entry, max_entries;
size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm));
max_entries = calc_max_entries(info->value_type.size, size_of_block);
r = lookup_ablock(info, root, index / max_entries, &block, &ab);
if (r)
return r;
entry = index % max_entries;
if (entry >= le32_to_cpu(ab->nr_entries))
r = -ENODATA;
else
memcpy(value_le, element_at(info, ab, entry),
info->value_type.size);
unlock_ablock(info, block);
return r;
}
static int array_resize(struct dm_array_info *info, dm_block_t root,
uint32_t old_size, uint32_t new_size,
const void *value, dm_block_t *new_root)
{
int r;
struct resize resize;
if (old_size == new_size)
return 0;
resize.info = info;
resize.root = root;
resize.size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm));
resize.max_entries = calc_max_entries(info->value_type.size,
resize.size_of_block);
resize.old_nr_full_blocks = old_size / resize.max_entries;
resize.old_nr_entries_in_last_block = old_size % resize.max_entries;
resize.new_nr_full_blocks = new_size / resize.max_entries;
resize.new_nr_entries_in_last_block = new_size % resize.max_entries;
resize.value = value;
r = ((new_size > old_size) ? grow : shrink)(&resize);
if (r)
return r;
*new_root = resize.root;
return 0;
}
int dm_btree_empty(struct dm_btree_info *info, dm_block_t *root)
{
int r;
struct dm_block *b;
struct btree_node *n;
size_t block_size;
uint32_t max_entries;
r = new_block(info, &b);
if (r < 0)
return r;
block_size = dm_bm_block_size(dm_tm_get_bm(info->tm));
max_entries = calc_max_entries(info->value_type.size, block_size);
n = dm_block_data(b);
memset(n, 0, block_size);
n->header.flags = cpu_to_le32(LEAF_NODE);
n->header.nr_entries = cpu_to_le32(0);
n->header.max_entries = cpu_to_le32(max_entries);
n->header.value_size = cpu_to_le32(info->value_type.size);
*root = dm_block_location(b);
return unlock_block(info, b);
}
static void prefetch_children(struct del_stack *s, struct frame *f)
{
unsigned i;
struct dm_block_manager *bm = dm_tm_get_bm(s->tm);
for (i = 0; i < f->nr_children; i++)
dm_bm_prefetch(bm, value64(f->n, i));
}
static int rebalance_children(struct shadow_spine *s,
struct dm_btree_info *info,
struct dm_btree_value_type *vt, uint64_t key)
{
int i, r, has_left_sibling, has_right_sibling;
uint32_t child_entries;
struct btree_node *n;
n = dm_block_data(shadow_current(s));
if (le32_to_cpu(n->header.nr_entries) == 1) {
struct dm_block *child;
dm_block_t b = value64(n, 0);
r = dm_tm_read_lock(info->tm, b, &btree_node_validator, &child);
if (r)
return r;
memcpy(n, dm_block_data(child),
dm_bm_block_size(dm_tm_get_bm(info->tm)));
r = dm_tm_unlock(info->tm, child);
if (r)
return r;
dm_tm_dec(info->tm, dm_block_location(child));
return 0;
}
i = lower_bound(n, key);
if (i < 0)
return -ENODATA;
r = get_nr_entries(info->tm, value64(n, i), &child_entries);
if (r)
return r;
has_left_sibling = i > 0;
has_right_sibling = i < (le32_to_cpu(n->header.nr_entries) - 1);
if (!has_left_sibling)
r = rebalance2(s, info, vt, i);
else if (!has_right_sibling)
r = rebalance2(s, info, vt, i - 1);
else
r = rebalance3(s, info, vt, i - 1);
return r;
}
static int array_set_value(struct dm_array_info *info, dm_block_t root,
uint32_t index, const void *value, dm_block_t *new_root)
{
int r;
struct dm_block *block;
struct array_block *ab;
size_t size_of_block;
unsigned max_entries;
unsigned entry;
void *old_value;
struct dm_btree_value_type *vt = &info->value_type;
size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm));
max_entries = calc_max_entries(info->value_type.size, size_of_block);
r = shadow_ablock(info, &root, index / max_entries, &block, &ab);
if (r)
return r;
*new_root = root;
entry = index % max_entries;
if (entry >= le32_to_cpu(ab->nr_entries)) {
r = -ENODATA;
goto out;
}
old_value = element_at(info, ab, entry);
if (vt->dec &&
(!vt->equal || !vt->equal(vt->context, old_value, value))) {
vt->dec(vt->context, old_value);
if (vt->inc)
vt->inc(vt->context, value);
}
memcpy(old_value, value, info->value_type.size);
out:
unlock_ablock(info, block);
return r;
}
/*
* Splits a node by creating two new children beneath the given node.
*
* Before:
* +----------+
* | A ++++++ |
* +----------+
*
*
* After:
* +------------+
* | A (shadow) |
* +------------+
* | |
* +------+ +----+
* | |
* v v
* +-------+ +-------+
* | B +++ | | C +++ |
* +-------+ +-------+
*/
static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
{
int r;
size_t size;
unsigned nr_left, nr_right;
struct dm_block *left, *right, *new_parent;
struct btree_node *pn, *ln, *rn;
__le64 val;
new_parent = shadow_current(s);
r = new_block(s->info, &left);
if (r < 0)
return r;
r = new_block(s->info, &right);
if (r < 0) {
/* FIXME: put left */
return r;
}
pn = dm_block_data(new_parent);
ln = dm_block_data(left);
rn = dm_block_data(right);
nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left;
ln->header.flags = pn->header.flags;
ln->header.nr_entries = cpu_to_le32(nr_left);
ln->header.max_entries = pn->header.max_entries;
ln->header.value_size = pn->header.value_size;
rn->header.flags = pn->header.flags;
rn->header.nr_entries = cpu_to_le32(nr_right);
rn->header.max_entries = pn->header.max_entries;
rn->header.value_size = pn->header.value_size;
memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0]));
size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
sizeof(__le64) : s->info->value_type.size;
memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left),
nr_right * size);
/* new_parent should just point to l and r now */
pn->header.flags = cpu_to_le32(INTERNAL_NODE);
pn->header.nr_entries = cpu_to_le32(2);
pn->header.max_entries = cpu_to_le32(
calc_max_entries(sizeof(__le64),
dm_bm_block_size(
dm_tm_get_bm(s->info->tm))));
pn->header.value_size = cpu_to_le32(sizeof(__le64));
val = cpu_to_le64(dm_block_location(left));
__dm_bless_for_disk(&val);
pn->keys[0] = ln->keys[0];
memcpy_disk(value_ptr(pn, 0), &val, sizeof(__le64));
val = cpu_to_le64(dm_block_location(right));
__dm_bless_for_disk(&val);
pn->keys[1] = rn->keys[0];
memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
/*
* rejig the spine. This is ugly, since it knows too
* much about the spine
*/
if (s->nodes[0] != new_parent) {
unlock_block(s->info, s->nodes[0]);
s->nodes[0] = new_parent;
}
if (key < le64_to_cpu(rn->keys[0])) {
unlock_block(s->info, right);
s->nodes[1] = left;
} else {
unlock_block(s->info, left);
s->nodes[1] = right;
}
s->count = 2;
return 0;
}