netmem: introduce struct netmem_desc mirroring struct page

To simplify struct page, the page pool members of struct page should be
moved to other, allowing these members to be removed from struct page.

Introduce a network memory descriptor to store the members, struct
netmem_desc, and make it union'ed with the existing fields in struct
net_iov, allowing to organize the fields of struct net_iov.

Signed-off-by: Byungchul Park <byungchul@sk.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20250721021835.63939-2-byungchul@sk.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 95 insertions, 21 deletions

diff --git a/include/net/netmem.h b/include/net/netmem.h
index de1d95f04076..535cf17b9134 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -12,6 +12,50 @@
 #include <linux/mm.h>
 #include <net/net_debug.h>
 
+/* These fields in struct page are used by the page_pool and net stack:
+ *
+ *        struct {
+ *                unsigned long pp_magic;
+ *                struct page_pool *pp;
+ *                unsigned long _pp_mapping_pad;
+ *                unsigned long dma_addr;
+ *                atomic_long_t pp_ref_count;
+ *        };
+ *
+ * We mirror the page_pool fields here so the page_pool can access these
+ * fields without worrying whether the underlying fields belong to a
+ * page or netmem_desc.
+ *
+ * CAUTION: Do not update the fields in netmem_desc without also
+ * updating the anonymous aliasing union in struct net_iov.
+ */
+struct netmem_desc {
+	unsigned long _flags;
+	unsigned long pp_magic;
+	struct page_pool *pp;
+	unsigned long _pp_mapping_pad;
+	unsigned long dma_addr;
+	atomic_long_t pp_ref_count;
+};
+
+#define NETMEM_DESC_ASSERT_OFFSET(pg, desc)        \
+	static_assert(offsetof(struct page, pg) == \
+		      offsetof(struct netmem_desc, desc))
+NETMEM_DESC_ASSERT_OFFSET(flags, _flags);
+NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic);
+NETMEM_DESC_ASSERT_OFFSET(pp, pp);
+NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
+NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr);
+NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
+#undef NETMEM_DESC_ASSERT_OFFSET
+
+/*
+ * Since struct netmem_desc uses the space in struct page, the size
+ * should be checked, until struct netmem_desc has its own instance from
+ * slab, to avoid conflicting with other members within struct page.
+ */
+static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount));
+
 /* net_iov */
 
 DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
@@ -30,13 +74,48 @@ enum net_iov_type {
 	NET_IOV_MAX = ULONG_MAX
 };
 
+/* A memory descriptor representing abstract networking I/O vectors,
+ * generally for non-pages memory that doesn't have its corresponding
+ * struct page and needs to be explicitly allocated through slab.
+ *
+ * net_iovs are allocated and used by networking code, and the size of
+ * the chunk is PAGE_SIZE.
+ *
+ * This memory can be any form of non-struct paged memory.  Examples
+ * include imported dmabuf memory and imported io_uring memory.  See
+ * net_iov_type for all the supported types.
+ *
+ * @pp_magic:	pp field, similar to the one in struct page/struct
+ *		netmem_desc.
+ * @pp:		the pp this net_iov belongs to, if any.
+ * @dma_addr:	the dma addrs of the net_iov. Needed for the network
+ *		card to send/receive this net_iov.
+ * @pp_ref_count: the pp ref count of this net_iov, exactly the same
+ *		usage as struct page/struct netmem_desc.
+ * @owner:	the net_iov_area this net_iov belongs to, if any.
+ * @type:	the type of the memory.  Different types of net_iovs are
+ *		supported.
+ */
 struct net_iov {
-	enum net_iov_type type;
-	unsigned long pp_magic;
-	struct page_pool *pp;
+	union {
+		struct netmem_desc desc;
+
+		/* XXX: The following part should be removed once all
+		 * the references to them are converted so as to be
+		 * accessed via netmem_desc e.g. niov->desc.pp instead
+		 * of niov->pp.
+		 */
+		struct {
+			unsigned long _flags;
+			unsigned long pp_magic;
+			struct page_pool *pp;
+			unsigned long _pp_mapping_pad;
+			unsigned long dma_addr;
+			atomic_long_t pp_ref_count;
+		};
+	};
 	struct net_iov_area *owner;
-	unsigned long dma_addr;
-	atomic_long_t pp_ref_count;
+	enum net_iov_type type;
 };
 
 struct net_iov_area {
@@ -48,27 +127,22 @@ struct net_iov_area {
 	unsigned long base_virtual;
 };
 
-/* These fields in struct page are used by the page_pool and net stack:
+/* net_iov is union'ed with struct netmem_desc mirroring struct page, so
+ * the page_pool can access these fields without worrying whether the
+ * underlying fields are accessed via netmem_desc or directly via
+ * net_iov, until all the references to them are converted so as to be
+ * accessed via netmem_desc e.g. niov->desc.pp instead of niov->pp.
  *
- *        struct {
- *                unsigned long pp_magic;
- *                struct page_pool *pp;
- *                unsigned long _pp_mapping_pad;
- *                unsigned long dma_addr;
- *                atomic_long_t pp_ref_count;
- *        };
- *
- * We mirror the page_pool fields here so the page_pool can access these fields
- * without worrying whether the underlying fields belong to a page or net_iov.
- *
- * The non-net stack fields of struct page are private to the mm stack and must
- * never be mirrored to net_iov.
+ * The non-net stack fields of struct page are private to the mm stack
+ * and must never be mirrored to net_iov.
  */
-#define NET_IOV_ASSERT_OFFSET(pg, iov)             \
-	static_assert(offsetof(struct page, pg) == \
+#define NET_IOV_ASSERT_OFFSET(desc, iov)                    \
+	static_assert(offsetof(struct netmem_desc, desc) == \
 		      offsetof(struct net_iov, iov))
+NET_IOV_ASSERT_OFFSET(_flags, _flags);
 NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic);
 NET_IOV_ASSERT_OFFSET(pp, pp);
+NET_IOV_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
 NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
 NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
 #undef NET_IOV_ASSERT_OFFSET