net: netmem: document netmem and memory provider design in comments

Clarify the netmem, memory provider, page_pool, and skb fragment design
principles in header and code comments:

- Memory providers allocate struct net_iov or struct page, cast them to
  netmem_ref, and pass them to page_pool; page_pool, drivers, and the
  core stack operate on netmem_ref and must not downcast to page or
  net_iov outside dedicated netmem helpers.
- While current memory providers supply struct net_iov, they are not
  architecturally restricted to net_iov and may supply page-backed
  netmems.
- While current net_iov types are CPU-unreadable, net_iov has no
  inherent restrictions and may be readable or unreadable.
- New code should generalize existing limitations as much as possible to
  match these design principles.
- Per-provider logic belongs in memory_provider_ops, and per-netmem-type
  logic belongs in netmem helpers.
- All frags in an skb must either all be struct page-backed or all
  belong to the same memory provider instance; mixing them (including
  via coalescing) is not allowed.

Cc: Luigi Rizzo <lrizzo@google.com>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20261010033630.1171692-2-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/skbuff.h

@@ -358,6 +358,12 @@ struct sk_buff;
  */
 #define GSO_BY_FRAGS	0xFFFF
 
+/* All frags in an skb must either all be struct page-backed or all belong to
+ * the same memory provider instance (e.g. the same devmem binding or io_uring
+ * area). Mixing page and memory-provider frags, or mixing frags from different
+ * memory providers within a single skb (including via coalescing), is not
+ * allowed.
+ */
 typedef struct skb_frag {
 	netmem_ref netmem;
 	unsigned int len;

include/net/netmem.h

@@ -70,16 +70,18 @@ enum net_iov_type {
 	NET_IOV_IOURING,
 };
 
-/* 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.
+/* A memory descriptor representing abstract networking I/O vectors.
  *
  * 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.
+ * Examples include imported dmabuf memory and imported io_uring memory. See
+ * net_iov_type for all the supported types. While current net_iov types are
+ * unreadable by the CPU, net_iov has no inherent restrictions and may be
+ * CPU-readable or unreadable. New code must not assume net_iov implies
+ * unreadable memory (check readability via netmem_address() or
+ * skb_frags_readable() instead) and should, as much as possible, generalize
+ * existing limitations to match the design principles.
  *
  * @pp_magic:	pp field, similar to the one in struct page/struct
  *		netmem_desc.
@@ -131,8 +133,17 @@ static inline void net_iov_init(struct net_iov *niov,
  * network memory.
  *
  * A netmem_ref can be a struct page* or a struct net_iov* underneath.
+ * Memory providers (or the default page_pool allocator) allocate struct
+ * net_iov or struct page, cast them to netmem_ref, and hand them to
+ * page_pool.
  *
- * Use the supplied helpers to obtain the underlying memory pointer and fields.
+ * The page_pool, drivers, and core networking stack should operate on
+ * netmem_ref rather than struct page or struct net_iov. Downcasting
+ * netmem_ref via netmem_to_page() or netmem_to_net_iov() in callers is
+ * not allowed unless a code path strictly requires a specific backing
+ * type (e.g., kmap_local_page()). In such cases, add a netmem helper here
+ * that handles both page and net_iov cases and returns an error if the
+ * underlying type cannot support the operation.
  */
 typedef unsigned long __bitwise netmem_ref;
 
@@ -297,9 +308,8 @@ static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem)
 
 static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid)
 {
-	/* NUMA node preference only makes sense if we're allocating
-	 * system memory. Memory providers (which give us net_iovs)
-	 * choose for us.
+	/* NUMA node preference only applies to struct page; net_iovs are
+	 * managed by their memory provider.
 	 */
 	if (netmem_is_net_iov(netmem))
 		return true;

include/net/page_pool/helpers.h

@@ -8,12 +8,20 @@
 /**
  * DOC: page_pool allocator
  *
- * The page_pool allocator is optimized for recycling page or page fragment used
- * by skb packet and xdp frame.
+ * The page_pool allocator is optimized for recycling network memory
+ * (netmem_ref) or fragments used by skb packets and xdp frames.
  *
- * Basic use involves replacing any alloc_pages() calls with page_pool_alloc(),
- * which allocate memory with or without page splitting depending on the
- * requested memory size.
+ * page_pool natively operates on netmem_ref, which abstracts the underlying
+ * memory type (struct page or struct net_iov) supplied by the page allocator
+ * or a memory provider. Drivers and core networking code should use the
+ * netmem-based APIs (e.g. page_pool_alloc_netmem(), page_pool_put_netmem()).
+ * The struct page-based APIs (e.g. page_pool_alloc(), page_pool_alloc_pages(),
+ * page_pool_put_page()) are legacy compatibility wrappers for drivers not yet
+ * converted to netmem.
+ *
+ * Basic use involves replacing any alloc_pages() calls with
+ * page_pool_alloc_netmem() (or legacy page_pool_alloc()), which allocate memory
+ * with or without splitting depending on the requested memory size.
  *
  * If the driver knows that it always requires full pages or its allocations are
  * always smaller than half a page, it can use one of the more specific API

include/net/page_pool/memory_provider.h

@@ -9,6 +9,16 @@ struct netdev_rx_queue;
 struct netlink_ext_ack;
 struct sk_buff;
 
+/* Memory providers allocate underlying memory (struct net_iov or struct page),
+ * cast it to netmem_ref, and supply it to page_pool. While current memory
+ * providers only return struct net_iov, they are not architecturally limited to
+ * net_iov; a provider returning page-backed netmems is allowed. New code must
+ * not assume a memory provider implies net_iov and should, as much as possible,
+ * generalize existing limitations to match the design principles.
+ *
+ * Per-provider custom logic must be delegated to memory_provider_ops rather
+ * than handled directly in page_pool core code.
+ */
 struct memory_provider_ops {
 	netmem_ref (*alloc_netmems)(struct page_pool *pool, gfp_t gfp);
 	bool (*release_netmem)(struct page_pool *pool, netmem_ref netmem);

include/net/page_pool/types.h

@@ -22,9 +22,9 @@
 					*/
 #define PP_FLAG_SYSTEM_POOL	BIT(2) /* Global system page_pool */
 
-/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting
- * this must be able to support unreadable netmem, where netmem_address() would
- * return NULL. This flag should not be set for header page_pools.
+/* Allow unreadable netmem in this page_pool. Drivers setting this must be able
+ * to support unreadable netmem, where netmem_address() returns NULL. This flag
+ * should not be set for header page_pools.
  *
  * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set
  * page_pool_params.slow.queue_idx.

net/core/skbuff.c

@@ -6214,6 +6214,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (to->pp_recycle != from->pp_recycle)
 		return false;
 
+	/* All frags in an skb must either all be struct page-backed or all
+	 * belong to the same memory provider instance; do not coalesce skbs
+	 * that would mix them.
+	 */
 	if (skb_frags_readable(from) != skb_frags_readable(to))
 		return false;