Merge branch 'abstract-page-from-net-stack'

Mina Almasry says:

====================
Abstract page from net stack

This series is a prerequisite to the devmem TCP series. For a full
snapshot of the code which includes these changes, feel free to check:

https://github.com/mina/linux/commits/tcpdevmem-rfcv5/

Currently these components in the net stack use the struct page
directly:

1. Drivers.
2. Page pool.
3. skb_frag_t.

To add support for new (non struct page) memory types to the net stack, we
must first abstract the current memory type.

Originally the plan was to reuse struct page* for the new memory types,
and to set the LSB on the page* to indicate it's not really a page.
However, for safe compiler type checking we need to introduce a new type.

struct netmem is introduced to abstract the underlying memory type.
Currently it's a no-op abstraction that is always a struct page underneath.
In parallel there is an undergoing effort to add support for devmem to the
net stack:

https://lore.kernel.org/netdev/20231208005250.2910004-1-almasrymina@google.com/

Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yunsheng Lin <linyunsheng@huawei.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
====================

Link: https://lore.kernel.org/r/20240214223405.1972973-1-almasrymina@google.comSigned-off-by: Paolo Abeni <pabeni@redhat.com>

include/linux/skbuff.h

@@ -37,6 +37,7 @@
 #endif
 #include <net/net_debug.h>
 #include <net/dropreason-core.h>
+#include <net/netmem.h>
 
 /**
  * DOC: skb checksums
@@ -359,7 +360,11 @@ extern int sysctl_max_skb_frags;
  */
 #define GSO_BY_FRAGS	0xFFFF
 
-typedef struct bio_vec skb_frag_t;
+typedef struct skb_frag {
+	netmem_ref netmem;
+	unsigned int len;
+	unsigned int offset;
+} skb_frag_t;
 
 /**
  * skb_frag_size() - Returns the size of a skb fragment
@@ -367,7 +372,7 @@ typedef struct bio_vec skb_frag_t;
  */
 static inline unsigned int skb_frag_size(const skb_frag_t *frag)
 {
-	return frag->bv_len;
+	return frag->len;
 }
 
 /**
@@ -377,7 +382,7 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag)
  */
 static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size)
 {
-	frag->bv_len = size;
+	frag->len = size;
 }
 
 /**
@@ -387,7 +392,7 @@ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size)
  */
 static inline void skb_frag_size_add(skb_frag_t *frag, int delta)
 {
-	frag->bv_len += delta;
+	frag->len += delta;
 }
 
 /**
@@ -397,7 +402,7 @@ static inline void skb_frag_size_add(skb_frag_t *frag, int delta)
  */
 static inline void skb_frag_size_sub(skb_frag_t *frag, int delta)
 {
-	frag->bv_len -= delta;
+	frag->len -= delta;
 }
 
 /**
@@ -417,7 +422,7 @@ static inline bool skb_frag_must_loop(struct page *p)
  *	skb_frag_foreach_page - loop over pages in a fragment
  *
  *	@f:		skb frag to operate on
- *	@f_off:		offset from start of f->bv_page
+ *	@f_off:		offset from start of f->netmem
  *	@f_len:		length from f_off to loop over
  *	@p:		(temp var) current page
  *	@p_off:		(temp var) offset from start of current page,
@@ -2429,22 +2434,37 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb)
 	return skb_headlen(skb) + __skb_pagelen(skb);
 }
 
+static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag,
+					     netmem_ref netmem, int off,
+					     int size)
+{
+	frag->netmem = netmem;
+	frag->offset = off;
+	skb_frag_size_set(frag, size);
+}
+
 static inline void skb_frag_fill_page_desc(skb_frag_t *frag,
 					   struct page *page,
 					   int off, int size)
 {
-	frag->bv_page = page;
-	frag->bv_offset = off;
-	skb_frag_size_set(frag, size);
+	skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size);
+}
+
+static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo,
+						int i, netmem_ref netmem,
+						int off, int size)
+{
+	skb_frag_t *frag = &shinfo->frags[i];
+
+	skb_frag_fill_netmem_desc(frag, netmem, off, size);
 }
 
 static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo,
 					      int i, struct page *page,
 					      int off, int size)
 {
-	skb_frag_t *frag = &shinfo->frags[i];
-
-	skb_frag_fill_page_desc(frag, page, off, size);
+	__skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off,
+				     size);
 }
 
 /**
@@ -2460,10 +2480,10 @@ static inline void skb_len_add(struct sk_buff *skb, int delta)
 }
 
 /**
- * __skb_fill_page_desc - initialise a paged fragment in an skb
+ * __skb_fill_netmem_desc - initialise a fragment in an skb
  * @skb: buffer containing fragment to be initialised
- * @i: paged fragment index to initialise
- * @page: the page to use for this fragment
+ * @i: fragment index to initialise
+ * @netmem: the netmem to use for this fragment
  * @off: the offset to the data with @page
  * @size: the length of the data
  *
@@ -2472,10 +2492,12 @@ static inline void skb_len_add(struct sk_buff *skb, int delta)
  *
  * Does not take any additional reference on the fragment.
  */
-static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
-					struct page *page, int off, int size)
+static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i,
+					  netmem_ref netmem, int off, int size)
 {
-	__skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size);
+	struct page *page = netmem_to_page(netmem);
+
+	__skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size);
 
 	/* Propagate page pfmemalloc to the skb if we can. The problem is
 	 * that not all callers have unique ownership of the page but rely
@@ -2483,7 +2505,20 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 	 */
 	page = compound_head(page);
 	if (page_is_pfmemalloc(page))
-		skb->pfmemalloc	= true;
+		skb->pfmemalloc = true;
+}
+
+static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
+					struct page *page, int off, int size)
+{
+	__skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size);
+}
+
+static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i,
+					netmem_ref netmem, int off, int size)
+{
+	__skb_fill_netmem_desc(skb, i, netmem, off, size);
+	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
 /**
@@ -2503,8 +2538,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 				      struct page *page, int off, int size)
 {
-	__skb_fill_page_desc(skb, i, page, off, size);
-	skb_shinfo(skb)->nr_frags = i + 1;
+	skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size);
 }
 
 /**
@@ -2528,8 +2562,16 @@ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i,
 	shinfo->nr_frags = i + 1;
 }
 
-void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
-		     int size, unsigned int truesize);
+void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem,
+			    int off, int size, unsigned int truesize);
+
+static inline void skb_add_rx_frag(struct sk_buff *skb, int i,
+				   struct page *page, int off, int size,
+				   unsigned int truesize)
+{
+	skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size,
+			       truesize);
+}
 
 void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
 			  unsigned int truesize);
@@ -3378,7 +3420,7 @@ static inline void skb_propagate_pfmemalloc(const struct page *page,
  */
 static inline unsigned int skb_frag_off(const skb_frag_t *frag)
 {
-	return frag->bv_offset;
+	return frag->offset;
 }
 
 /**
@@ -3388,7 +3430,7 @@ static inline unsigned int skb_frag_off(const skb_frag_t *frag)
  */
 static inline void skb_frag_off_add(skb_frag_t *frag, int delta)
 {
-	frag->bv_offset += delta;
+	frag->offset += delta;
 }
 
 /**
@@ -3398,7 +3440,7 @@ static inline void skb_frag_off_add(skb_frag_t *frag, int delta)
  */
 static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset)
 {
-	frag->bv_offset = offset;
+	frag->offset = offset;
 }
 
 /**
@@ -3409,7 +3451,7 @@ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset)
 static inline void skb_frag_off_copy(skb_frag_t *fragto,
 				     const skb_frag_t *fragfrom)
 {
-	fragto->bv_offset = fragfrom->bv_offset;
+	fragto->offset = fragfrom->offset;
 }
 
 /**
@@ -3420,7 +3462,7 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto,
  */
 static inline struct page *skb_frag_page(const skb_frag_t *frag)
 {
-	return frag->bv_page;
+	return netmem_to_page(frag->netmem);
 }
 
 /**
@@ -3528,7 +3570,7 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag)
 static inline void skb_frag_page_copy(skb_frag_t *fragto,
 				      const skb_frag_t *fragfrom)
 {
-	fragto->bv_page = fragfrom->bv_page;
+	fragto->netmem = fragfrom->netmem;
 }
 
 bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio);

include/net/netmem.h

+/* SPDX-License-Identifier: GPL-2.0
+ *
+ *	Network memory
+ *
+ *	Author:	Mina Almasry <almasrymina@google.com>
+ */
+
+#ifndef _NET_NETMEM_H
+#define _NET_NETMEM_H
+
+/**
+ * typedef netmem_ref - a nonexistent type marking a reference to generic
+ * network memory.
+ *
+ * A netmem_ref currently is always a reference to a struct page. This
+ * abstraction is introduced so support for new memory types can be added.
+ *
+ * Use the supplied helpers to obtain the underlying memory pointer and fields.
+ */
+typedef unsigned long __bitwise netmem_ref;
+
+/* This conversion fails (returns NULL) if the netmem_ref is not struct page
+ * backed.
+ *
+ * Currently struct page is the only possible netmem, and this helper never
+ * fails.
+ */
+static inline struct page *netmem_to_page(netmem_ref netmem)
+{
+	return (__force struct page *)netmem;
+}
+
+/* Converting from page to netmem is always safe, because a page can always be
+ * a netmem.
+ */
+static inline netmem_ref page_to_netmem(struct page *page)
+{
+	return (__force netmem_ref)page;
+}
+
+#endif /* _NET_NETMEM_H */

net/core/skbuff.c

@@ -115,6 +115,24 @@ static struct kmem_cache *skb_small_head_cache __ro_after_init;
 int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
 EXPORT_SYMBOL(sysctl_max_skb_frags);
 
+/* kcm_write_msgs() relies on casting paged frags to bio_vec to use
+ * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the
+ * netmem is a page.
+ */
+static_assert(offsetof(struct bio_vec, bv_page) ==
+	      offsetof(skb_frag_t, netmem));
+static_assert(sizeof_field(struct bio_vec, bv_page) ==
+	      sizeof_field(skb_frag_t, netmem));
+
+static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len));
+static_assert(sizeof_field(struct bio_vec, bv_len) ==
+	      sizeof_field(skb_frag_t, len));
+
+static_assert(offsetof(struct bio_vec, bv_offset) ==
+	      offsetof(skb_frag_t, offset));
+static_assert(sizeof_field(struct bio_vec, bv_offset) ==
+	      sizeof_field(skb_frag_t, offset));
+
 #undef FN
 #define FN(reason) [SKB_DROP_REASON_##reason] = #reason,
 static const char * const drop_reasons[] = {
@@ -845,17 +863,17 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 }
 EXPORT_SYMBOL(__napi_alloc_skb);
 
-void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
-		     int size, unsigned int truesize)
+void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem,
+			    int off, int size, unsigned int truesize)
 {
 	DEBUG_NET_WARN_ON_ONCE(size > truesize);
 
-	skb_fill_page_desc(skb, i, page, off, size);
+	skb_fill_netmem_desc(skb, i, netmem, off, size);
 	skb->len += size;
 	skb->data_len += size;
 	skb->truesize += truesize;
 }
-EXPORT_SYMBOL(skb_add_rx_frag);
+EXPORT_SYMBOL(skb_add_rx_frag_netmem);
 
 void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
 			  unsigned int truesize)
@@ -1999,10 +2017,11 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 
 	/* skb frags point to kernel buffers */
 	for (i = 0; i < new_frags - 1; i++) {
-		__skb_fill_page_desc(skb, i, head, 0, psize);
+		__skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize);
 		head = (struct page *)page_private(head);
 	}
-	__skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
+	__skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0,
+			       d_off);
 	skb_shinfo(skb)->nr_frags = new_frags;
 
 release:
@@ -3740,7 +3759,8 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
 		if (plen) {
 			page = virt_to_head_page(from->head);
 			offset = from->data - (unsigned char *)page_address(page);
-			__skb_fill_page_desc(to, 0, page, offset, plen);
+			__skb_fill_netmem_desc(to, 0, page_to_netmem(page),
+					       offset, plen);
 			get_page(page);
 			j = 1;
 			len -= plen;

net/kcm/kcmsock.c

@@ -627,7 +627,8 @@ static int kcm_write_msgs(struct kcm_sock *kcm)
 			skb = txm->frag_skb;
 		}
 
-		if (WARN_ON(!skb_shinfo(skb)->nr_frags)) {
+		if (WARN_ON(!skb_shinfo(skb)->nr_frags) ||
+		    WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
 			ret = -EINVAL;
 			goto out;
 		}
@@ -637,8 +638,8 @@ static int kcm_write_msgs(struct kcm_sock *kcm)
 			msize += skb_frag_size(&skb_shinfo(skb)->frags[i]);
 
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE,
-			      skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags,
-			      msize);
+			      (const struct bio_vec *)skb_shinfo(skb)->frags,
+			      skb_shinfo(skb)->nr_frags, msize);
 		iov_iter_advance(&msg.msg_iter, txm->frag_offset);
 
 		do {