Hi Zi,
On 2025/2/19 07:50, Zi Yan wrote:
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 <ziy@xxxxxxxxxx>
Cc: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Kirill A. Shuemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Yang Shi <yang@xxxxxxxxxxxxxxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Zi Yan <ziy@xxxxxxxxxx>
---
Documentation/core-api/xarray.rst | 14 ++-
include/linux/xarray.h | 7 ++
lib/test_xarray.c | 47 ++++++++++
lib/xarray.c | 138 ++++++++++++++++++++++++++----
tools/testing/radix-tree/Makefile | 1 +
5 files changed, 190 insertions(+), 17 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..9eb8c7425090 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1555,6 +1555,8 @@ 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,
+ gfp_t gfp);
#else
static inline int xa_get_order(struct xarray *xa, unsigned long index)
{
@@ -1576,6 +1578,11 @@ 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, gfp_t gfp)
+{
+}
#endif
/**
[snip]
diff --git a/lib/xarray.c b/lib/xarray.c
index 116e9286c64e..b9a63d7fbd58 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1007,6 +1007,31 @@ static void node_set_marks(struct xa_node *node, unsigned int offset,
}
}
+static struct xa_node *__xas_alloc_node_for_split(struct xa_state *xas,
+ void *entry, gfp_t gfp)
+{
+ unsigned int i;
+ void *sibling = NULL;
+ struct xa_node *node;
+ unsigned int mask = xas->xa_sibs;
+
+ node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp);
+ if (!node)
+ return NULL;
+ 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);
+ }
+ }
+ RCU_INIT_POINTER(node->parent, xas->xa_alloc);
+
+ return node;
+}
+
/**
* xas_split_alloc() - Allocate memory for splitting an entry.
* @xas: XArray operation state.
@@ -1025,7 +1050,6 @@ 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))
@@ -1034,23 +1058,9 @@ 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);
+ struct xa_node *node = __xas_alloc_node_for_split(xas, entry, 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);
- }
- }
- RCU_INIT_POINTER(node->parent, xas->xa_alloc);
xas->xa_alloc = node;
} while (sibs-- > 0);
@@ -1122,6 +1132,102 @@ 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.
+ * @gfp: Memory allocation flags.
+ *
+ * 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 xa_node needs to
+ * be allocated, the function will use @gfp to get one. If more 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,
+ gfp_t gfp)
The xas_try_split() may sleep if ‘gfp’ flags permit while holding the
xa_lock, which can cause issues. So can we add a check for the ‘gfp’ or
only use GFP_NOWAIT?
