A preparation patch for non-uniform folio split, which always split a
folio into half iteratively, and minimal xarray entry split.
Currently, xas_split_alloc() and xas_split() always split all slots from a
multi-index entry. They cost the same number of xa_node as the
to-be-split slots. For example, to split an order-9 entry, which takes
2^(9-6)=8 slots, assuming XA_CHUNK_SHIFT is 6 (!CONFIG_BASE_SMALL), 8
xa_node are needed. Instead xas_try_split() is intended to be used
iteratively to split the order-9 entry into 2 order-8 entries, then split
one order-8 entry, based on the given index, to 2 order-7 entries, ...,
and split one order-1 entry to 2 order-0 entries. When splitting the
order-6 entry and a new xa_node is needed, xas_try_split() will try to
allocate one if possible. As a result, xas_try_split() would only need
one xa_node instead of 8.
When a new xa_node is needed during the split, xas_try_split() can try to
allocate one but no more. -ENOMEM will be return if a node cannot be
allocated. -EINVAL will be return if a sibling node is split or cascade
split happens, where two or more new nodes are needed, and these are not
supported by xas_try_split().
xas_split_alloc() and xas_split() split an order-9 to order-0:
---------------------------------
| | | | | | | | |
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
| | | | | | | | |
---------------------------------
| | | |
------- --- --- -------
| | ... | |
V V V V
----------- ----------- ----------- -----------
| xa_node | | xa_node | ... | xa_node | | xa_node |
----------- ----------- ----------- -----------
xas_try_split() splits an order-9 to order-0:
---------------------------------
| | | | | | | | |
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
| | | | | | | | |
---------------------------------
|
|
V
-----------
| xa_node |
-----------
Signed-off-by: Zi Yan <z...@nvidia.com>
Cc: Baolin Wang <baolin.w...@linux.alibaba.com>
Cc: David Hildenbrand <da...@redhat.com>
Cc: Hugh Dickins <hu...@google.com>
Cc: John Hubbard <jhubb...@nvidia.com>
Cc: Kefeng Wang <wangkefeng.w...@huawei.com>
Cc: Kirill A. Shuemov <kirill.shute...@linux.intel.com>
Cc: Miaohe Lin <linmia...@huawei.com>
Cc: Matthew Wilcox <wi...@infradead.org>
Cc: Ryan Roberts <ryan.robe...@arm.com>
Cc: Yang Shi <y...@os.amperecomputing.com>
Cc: Yu Zhao <yuz...@google.com>
Cc: Zi Yan <z...@nvidia.com>
Cc: Kairui Song <kas...@tencent.com>
---
Documentation/core-api/xarray.rst | 14 +++-
include/linux/xarray.h | 6 ++
lib/test_xarray.c | 52 ++++++++++++
lib/xarray.c | 131 +++++++++++++++++++++++++++---
tools/testing/radix-tree/Makefile | 1 +
5 files changed, 191 insertions(+), 13 deletions(-)
diff --git a/Documentation/core-api/xarray.rst
b/Documentation/core-api/xarray.rst
index f6a3eef4fe7f..c6c91cbd0c3c 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -489,7 +489,19 @@ Storing ``NULL`` into any index of a multi-index entry
will set the
entry at every index to ``NULL`` and dissolve the tie. A multi-index
entry can be split into entries occupying smaller ranges by calling
xas_split_alloc() without the xa_lock held, followed by taking the lock
-and calling xas_split().
+and calling xas_split() or calling xas_try_split() with xa_lock. The
+difference between xas_split_alloc()+xas_split() and xas_try_alloc() is
+that xas_split_alloc() + xas_split() split the entry from the original
+order to the new order in one shot uniformly, whereas xas_try_split()
+iteratively splits the entry containing the index non-uniformly.
+For example, to split an order-9 entry, which takes 2^(9-6)=8 slots,
+assuming ``XA_CHUNK_SHIFT`` is 6, xas_split_alloc() + xas_split() need
+8 xa_node. xas_try_split() splits the order-9 entry into
+2 order-8 entries, then split one order-8 entry, based on the given index,
+to 2 order-7 entries, ..., and split one order-1 entry to 2 order-0 entries.
+When splitting the order-6 entry and a new xa_node is needed, xas_try_split()
+will try to allocate one if possible. As a result, xas_try_split() would only
+need 1 xa_node instead of 8.
Functions and structures
========================
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 0b618ec04115..4010195201c9 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1555,6 +1555,7 @@ int xa_get_order(struct xarray *, unsigned long index);
int xas_get_order(struct xa_state *xas);
void xas_split(struct xa_state *, void *entry, unsigned int order);
void xas_split_alloc(struct xa_state *, void *entry, unsigned int order,
gfp_t);
+void xas_try_split(struct xa_state *xas, void *entry, unsigned int order);
#else
static inline int xa_get_order(struct xarray *xa, unsigned long index)
{
@@ -1576,6 +1577,11 @@ static inline void xas_split_alloc(struct xa_state *xas,
void *entry,
unsigned int order, gfp_t gfp)
{
}
+
+static inline void xas_try_split(struct xa_state *xas, void *entry,
+ unsigned int order)
+{
+}
#endif
/**
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 0e865bab4a10..080a39d22e73 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1858,6 +1858,54 @@ static void check_split_1(struct xarray *xa, unsigned
long index,
xa_destroy(xa);
}
+static void check_split_2(struct xarray *xa, unsigned long index,
+ unsigned int order, unsigned int new_order)
+{
+ XA_STATE_ORDER(xas, xa, index, new_order);
+ unsigned int i, found;
+ void *entry;
+
+ xa_store_order(xa, index, order, xa, GFP_KERNEL);
+ xa_set_mark(xa, index, XA_MARK_1);
+
+ /* allocate a node for xas_try_split() */
+ xas_set_err(&xas, -ENOMEM);
+ XA_BUG_ON(xa, !xas_nomem(&xas, GFP_KERNEL));
+
+ xas_lock(&xas);
+ xas_try_split(&xas, xa, order);
+ if (((new_order / XA_CHUNK_SHIFT) < (order / XA_CHUNK_SHIFT)) &&
+ new_order < order - 1) {
+ XA_BUG_ON(xa, !xas_error(&xas) || xas_error(&xas) != -EINVAL);
+ xas_unlock(&xas);
+ goto out;
+ }
+ for (i = 0; i < (1 << order); i += (1 << new_order))
+ __xa_store(xa, index + i, xa_mk_index(index + i), 0);
+ xas_unlock(&xas);
+
+ for (i = 0; i < (1 << order); i++) {
+ unsigned int val = index + (i & ~((1 << new_order) - 1));
+ XA_BUG_ON(xa, xa_load(xa, index + i) != xa_mk_index(val));
+ }
+
+ xa_set_mark(xa, index, XA_MARK_0);
+ XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
+
+ xas_set_order(&xas, index, 0);
+ found = 0;
+ rcu_read_lock();
+ xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_1) {
+ found++;
+ XA_BUG_ON(xa, xa_is_internal(entry));
+ }
+ rcu_read_unlock();
+ XA_BUG_ON(xa, found != 1 << (order - new_order));
+out:
+ xas_destroy(&xas);
+ xa_destroy(xa);
+}
+
static noinline void check_split(struct xarray *xa)
{
unsigned int order, new_order;
@@ -1869,6 +1917,10 @@ static noinline void check_split(struct xarray *xa)
check_split_1(xa, 0, order, new_order);
check_split_1(xa, 1UL << order, order, new_order);
check_split_1(xa, 3UL << order, order, new_order);
+
+ check_split_2(xa, 0, order, new_order);
+ check_split_2(xa, 1UL << order, order, new_order);
+ check_split_2(xa, 3UL << order, order, new_order);
}
}
}
diff --git a/lib/xarray.c b/lib/xarray.c
index 116e9286c64e..bc197c96d171 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1007,6 +1007,26 @@ static void node_set_marks(struct xa_node *node,
unsigned int offset,
}
}
+static void __xas_init_node_for_split(struct xa_state *xas,
+ struct xa_node *node, void *entry)
+{
+ unsigned int i;
+ void *sibling = NULL;
+ unsigned int mask = xas->xa_sibs;
+
+ if (!node)
+ return;
+ node->array = xas->xa;
+ for (i = 0; i < XA_CHUNK_SIZE; i++) {
+ if ((i & mask) == 0) {
+ RCU_INIT_POINTER(node->slots[i], entry);
+ sibling = xa_mk_sibling(i);
+ } else {
+ RCU_INIT_POINTER(node->slots[i], sibling);
+ }
+ }
+}
+
/**
* xas_split_alloc() - Allocate memory for splitting an entry.
* @xas: XArray operation state.
@@ -1025,7 +1045,6 @@ void xas_split_alloc(struct xa_state *xas, void *entry,
unsigned int order,
gfp_t gfp)
{
unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
- unsigned int mask = xas->xa_sibs;
/* XXX: no support for splitting really large entries yet */
if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT <= order))
@@ -1034,22 +1053,13 @@ void xas_split_alloc(struct xa_state *xas, void *entry,
unsigned int order,
return;
do {
- unsigned int i;
- void *sibling = NULL;
struct xa_node *node;
node = kmem_cache_alloc_lru(radix_tree_node_cachep,
xas->xa_lru, gfp);
if (!node)
goto nomem;
- node->array = xas->xa;
- for (i = 0; i < XA_CHUNK_SIZE; i++) {
- if ((i & mask) == 0) {
- RCU_INIT_POINTER(node->slots[i], entry);
- sibling = xa_mk_sibling(i);
- } else {
- RCU_INIT_POINTER(node->slots[i], sibling);
- }
- }
+
+ __xas_init_node_for_split(xas, node, entry);
RCU_INIT_POINTER(node->parent, xas->xa_alloc);
xas->xa_alloc = node;
} while (sibs-- > 0);
@@ -1122,6 +1132,103 @@ void xas_split(struct xa_state *xas, void *entry,
unsigned int order)
xas_update(xas, node);
}
EXPORT_SYMBOL_GPL(xas_split);
+
+/**
+ * xas_try_split() - Try to split a multi-index entry.
+ * @xas: XArray operation state.
+ * @entry: New entry to store in the array.
+ * @order: Current entry order.
+ *
+ * The size of the new entries is set in @xas. The value in @entry is
+ * copied to all the replacement entries. If and only if one new xa_node is
+ * needed, the function will use GFP_NOWAIT to get one if xas->xa_alloc is
+ * NULL. If more new xa_node are needed, the function gives EINVAL error.
+ *
+ * Context: Any context. The caller should hold the xa_lock.
+ */
+void xas_try_split(struct xa_state *xas, void *entry, unsigned int order)
+{
+ unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+ unsigned int offset, marks;
+ struct xa_node *node;
+ void *curr = xas_load(xas);
+ int values = 0;
+ gfp_t gfp = GFP_NOWAIT;
+
+ node = xas->xa_node;
+ if (xas_top(node))
+ return;
+
+ if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT)
+ gfp |= __GFP_ACCOUNT;
+
+ marks = node_get_marks(node, xas->xa_offset);
+
+ offset = xas->xa_offset + sibs;
+
+ if (xas->xa_shift < node->shift) {
+ struct xa_node *child = xas->xa_alloc;
+ unsigned int expected_sibs =
+ (1 << ((order - 1) % XA_CHUNK_SHIFT)) - 1;
+
+ /*
+ * No support for splitting sibling entries
+ * (horizontally) or cascade split (vertically), which
+ * requires two or more new xa_nodes.
+ * Since if one xa_node allocation fails,
+ * it is hard to free the prior allocations.
+ */
+ if (sibs || xas->xa_sibs != expected_sibs) {
+ xas_destroy(xas);
+ xas_set_err(xas, -EINVAL);
+ return;
+ }
+
+ if (!child) {
+ child = kmem_cache_alloc_lru(radix_tree_node_cachep,
+ xas->xa_lru, gfp);
+ if (!child) {
+ xas_destroy(xas);
+ xas_set_err(xas, -ENOMEM);
+ return;
+ }
+ RCU_INIT_POINTER(child->parent, xas->xa_alloc);
+ }
+ __xas_init_node_for_split(xas, child, entry);
+
+ xas->xa_alloc = rcu_dereference_raw(child->parent);
+ child->shift = node->shift - XA_CHUNK_SHIFT;
+ child->offset = offset;
+ child->count = XA_CHUNK_SIZE;
+ child->nr_values = xa_is_value(entry) ?
+ XA_CHUNK_SIZE : 0;
+ RCU_INIT_POINTER(child->parent, node);
+ node_set_marks(node, offset, child, xas->xa_sibs,
+ marks);
+ rcu_assign_pointer(node->slots[offset],
+ xa_mk_node(child));
+ if (xa_is_value(curr))
+ values--;
+ xas_update(xas, child);
+
+ } else {
+ do {
+ unsigned int canon = offset - xas->xa_sibs;
+
+ node_set_marks(node, canon, NULL, 0, marks);
+ rcu_assign_pointer(node->slots[canon], entry);
+ while (offset > canon)
+ rcu_assign_pointer(node->slots[offset--],
+ xa_mk_sibling(canon));
+ values += (xa_is_value(entry) - xa_is_value(curr)) *
+ (xas->xa_sibs + 1);
+ } while (offset-- > xas->xa_offset);
+ }
+
+ node->nr_values += values;
+ xas_update(xas, node);
+}
+EXPORT_SYMBOL_GPL(xas_try_split);
#endif
/**
diff --git a/tools/testing/radix-tree/Makefile
b/tools/testing/radix-tree/Makefile
index 8b3591a51e1f..b2a6660bbd92 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -14,6 +14,7 @@ include ../shared/shared.mk
main: $(OFILES)
+xarray.o: ../../../lib/test_xarray.c
idr-test.o: ../../../lib/test_ida.c
idr-test: idr-test.o $(CORE_OFILES)
--
2.47.2
