1 files changed, 149 insertions, 39 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 570269c477..4096e679f6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -69,6 +69,7 @@
 #include <net/sock.h>
 #include <net/checksum.h>
 #include <net/gso.h>
+#include <net/hotdata.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 #include <net/mpls.h>
@@ -88,15 +89,10 @@
 #include "dev.h"
 #include "sock_destructor.h"
 
-struct kmem_cache *skbuff_cache __ro_after_init;
-static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
 #ifdef CONFIG_SKB_EXTENSIONS
 static struct kmem_cache *skbuff_ext_cache __ro_after_init;
 #endif
 
-
-static struct kmem_cache *skb_small_head_cache __ro_after_init;
-
 #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER)
 
 /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two.
@@ -115,6 +111,24 @@ 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[] = {
@@ -297,7 +311,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
-	return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
+	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
+				       align_mask);
 }
 EXPORT_SYMBOL(__napi_alloc_frag_align);
 
@@ -309,13 +324,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 	if (in_hardirq() || irqs_disabled()) {
 		struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
 
-		data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask);
+		data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC,
+					       align_mask);
 	} else {
 		struct napi_alloc_cache *nc;
 
 		local_bh_disable();
 		nc = this_cpu_ptr(&napi_alloc_cache);
-		data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
+		data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
+					       align_mask);
 		local_bh_enable();
 	}
 	return data;
@@ -328,7 +345,7 @@ static struct sk_buff *napi_skb_cache_get(void)
 	struct sk_buff *skb;
 
 	if (unlikely(!nc->skb_count)) {
-		nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache,
+		nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
 						      GFP_ATOMIC,
 						      NAPI_SKB_CACHE_BULK,
 						      nc->skb_cache);
@@ -337,7 +354,7 @@ static struct sk_buff *napi_skb_cache_get(void)
 	}
 
 	skb = nc->skb_cache[--nc->skb_count];
-	kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache));
+	kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache));
 
 	return skb;
 }
@@ -395,7 +412,7 @@ struct sk_buff *slab_build_skb(void *data)
 	struct sk_buff *skb;
 	unsigned int size;
 
-	skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
+	skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -446,7 +463,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct sk_buff *skb;
 
-	skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
+	skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -557,7 +574,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 	obj_size = SKB_HEAD_ALIGN(*size);
 	if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
 	    !(flags & KMALLOC_NOT_NORMAL_BITS)) {
-		obj = kmem_cache_alloc_node(skb_small_head_cache,
+		obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache,
 				flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
 				node);
 		*size = SKB_SMALL_HEAD_CACHE_SIZE;
@@ -565,7 +582,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 			goto out;
 		/* Try again but now we are using pfmemalloc reserves */
 		ret_pfmemalloc = true;
-		obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node);
+		obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node);
 		goto out;
 	}
 
@@ -628,7 +645,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	u8 *data;
 
 	cache = (flags & SKB_ALLOC_FCLONE)
-		? skbuff_fclone_cache : skbuff_cache;
+		? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache;
 
 	if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
 		gfp_mask |= __GFP_MEMALLOC;
@@ -845,17 +862,17 @@ skb_fail:
 }
 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)
@@ -895,6 +912,98 @@ static bool is_pp_page(struct page *page)
 	return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
 }
 
+int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
+		    unsigned int headroom)
+{
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+	u32 size, truesize, len, max_head_size, off;
+	struct sk_buff *skb = *pskb, *nskb;
+	int err, i, head_off;
+	void *data;
+
+	/* XDP does not support fraglist so we need to linearize
+	 * the skb.
+	 */
+	if (skb_has_frag_list(skb))
+		return -EOPNOTSUPP;
+
+	max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom);
+	if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE)
+		return -ENOMEM;
+
+	size = min_t(u32, skb->len, max_head_size);
+	truesize = SKB_HEAD_ALIGN(size) + headroom;
+	data = page_pool_dev_alloc_va(pool, &truesize);
+	if (!data)
+		return -ENOMEM;
+
+	nskb = napi_build_skb(data, truesize);
+	if (!nskb) {
+		page_pool_free_va(pool, data, true);
+		return -ENOMEM;
+	}
+
+	skb_reserve(nskb, headroom);
+	skb_copy_header(nskb, skb);
+	skb_mark_for_recycle(nskb);
+
+	err = skb_copy_bits(skb, 0, nskb->data, size);
+	if (err) {
+		consume_skb(nskb);
+		return err;
+	}
+	skb_put(nskb, size);
+
+	head_off = skb_headroom(nskb) - skb_headroom(skb);
+	skb_headers_offset_update(nskb, head_off);
+
+	off = size;
+	len = skb->len - off;
+	for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
+		struct page *page;
+		u32 page_off;
+
+		size = min_t(u32, len, PAGE_SIZE);
+		truesize = size;
+
+		page = page_pool_dev_alloc(pool, &page_off, &truesize);
+		if (!page) {
+			consume_skb(nskb);
+			return -ENOMEM;
+		}
+
+		skb_add_rx_frag(nskb, i, page, page_off, size, truesize);
+		err = skb_copy_bits(skb, off, page_address(page) + page_off,
+				    size);
+		if (err) {
+			consume_skb(nskb);
+			return err;
+		}
+
+		len -= size;
+		off += size;
+	}
+
+	consume_skb(skb);
+	*pskb = nskb;
+
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+EXPORT_SYMBOL(skb_pp_cow_data);
+
+int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
+			 struct bpf_prog *prog)
+{
+	if (!prog->aux->xdp_has_frags)
+		return -EINVAL;
+
+	return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM);
+}
+EXPORT_SYMBOL(skb_cow_data_for_xdp);
+
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 bool napi_pp_put_page(struct page *page, bool napi_safe)
 {
@@ -923,9 +1032,10 @@ bool napi_pp_put_page(struct page *page, bool napi_safe)
 	 */
 	if (napi_safe || in_softirq()) {
 		const struct napi_struct *napi = READ_ONCE(pp->p.napi);
+		unsigned int cpuid = smp_processor_id();
 
-		allow_direct = napi &&
-			READ_ONCE(napi->list_owner) == smp_processor_id();
+		allow_direct = napi && READ_ONCE(napi->list_owner) == cpuid;
+		allow_direct |= READ_ONCE(pp->cpuid) == cpuid;
 	}
 
 	/* Driver set this to memory recycling info. Reset it on recycle.
@@ -981,7 +1091,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
 	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
-		kmem_cache_free(skb_small_head_cache, head);
+		kmem_cache_free(net_hotdata.skb_small_head_cache, head);
 	else
 		kfree(head);
 }
@@ -1005,9 +1115,7 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason,
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	int i;
 
-	if (skb->cloned &&
-	    atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
-			      &shinfo->dataref))
+	if (!skb_data_unref(skb, shinfo))
 		goto exit;
 
 	if (skb_zcopy(skb)) {
@@ -1048,7 +1156,7 @@ static void kfree_skbmem(struct sk_buff *skb)
 
 	switch (skb->fclone) {
 	case SKB_FCLONE_UNAVAILABLE:
-		kmem_cache_free(skbuff_cache, skb);
+		kmem_cache_free(net_hotdata.skbuff_cache, skb);
 		return;
 
 	case SKB_FCLONE_ORIG:
@@ -1069,7 +1177,7 @@ static void kfree_skbmem(struct sk_buff *skb)
 	if (!refcount_dec_and_test(&fclones->fclone_ref))
 		return;
 fastpath:
-	kmem_cache_free(skbuff_fclone_cache, fclones);
+	kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones);
 }
 
 void skb_release_head_state(struct sk_buff *skb)
@@ -1166,7 +1274,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb,
 	sa->skb_array[sa->skb_count++] = skb;
 
 	if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) {
-		kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE,
+		kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE,
 				     sa->skb_array);
 		sa->skb_count = 0;
 	}
@@ -1191,7 +1299,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason)
 	}
 
 	if (sa.skb_count)
-		kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array);
+		kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array);
 }
 EXPORT_SYMBOL(kfree_skb_list_reason);
 
@@ -1353,9 +1461,9 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
 		for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
 			kasan_mempool_unpoison_object(nc->skb_cache[i],
-						kmem_cache_size(skbuff_cache));
+						kmem_cache_size(net_hotdata.skbuff_cache));
 
-		kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF,
+		kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF,
 				     nc->skb_cache + NAPI_SKB_CACHE_HALF);
 		nc->skb_count = NAPI_SKB_CACHE_HALF;
 	}
@@ -1906,10 +2014,11 @@ 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:
@@ -1951,7 +2060,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 		if (skb_pfmemalloc(skb))
 			gfp_mask |= __GFP_MEMALLOC;
 
-		n = kmem_cache_alloc(skbuff_cache, gfp_mask);
+		n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask);
 		if (!n)
 			return NULL;
 
@@ -3658,7 +3767,8 @@ 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;
@@ -4900,7 +5010,7 @@ static void skb_extensions_init(void) {}
 
 void __init skb_init(void)
 {
-	skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
+	net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
 					      sizeof(struct sk_buff),
 					      0,
 					      SLAB_HWCACHE_ALIGN|SLAB_PANIC|
@@ -4908,7 +5018,7 @@ void __init skb_init(void)
 					      offsetof(struct sk_buff, cb),
 					      sizeof_field(struct sk_buff, cb),
 					      NULL);
-	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
+	net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
 						sizeof(struct sk_buff_fclones),
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
@@ -4917,7 +5027,7 @@ void __init skb_init(void)
 	 * struct skb_shared_info is located at the end of skb->head,
 	 * and should not be copied to/from user.
 	 */
-	skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head",
+	net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head",
 						SKB_SMALL_HEAD_CACHE_SIZE,
 						0,
 						SLAB_HWCACHE_ALIGN | SLAB_PANIC,
@@ -5790,7 +5900,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen)
 {
 	if (head_stolen) {
 		skb_release_head_state(skb);
-		kmem_cache_free(skbuff_cache, skb);
+		kmem_cache_free(net_hotdata.skbuff_cache, skb);
 	} else {
 		__kfree_skb(skb);
 	}