1 files changed, 58 insertions, 41 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2170bea2c7de..ba2f38246f07 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -70,6 +70,7 @@
 #include <net/xfrm.h>
 #include <net/mpls.h>
 #include <net/mptcp.h>
+#include <net/mctp.h>
 #include <net/page_pool.h>
 
 #include <linux/uaccess.h>
@@ -80,6 +81,7 @@
 #include <linux/indirect_call_wrapper.h>
 
 #include "datagram.h"
+#include "sock_destructor.h"
 
 struct kmem_cache *skbuff_head_cache __ro_after_init;
 static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
@@ -134,34 +136,31 @@ struct napi_alloc_cache {
 static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
 static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
 
-static void *__alloc_frag_align(unsigned int fragsz, gfp_t gfp_mask,
-				unsigned int align_mask)
+void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
-	return page_frag_alloc_align(&nc->page, fragsz, gfp_mask, align_mask);
-}
-
-void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
-{
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
-	return __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask);
+	return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
 }
 EXPORT_SYMBOL(__napi_alloc_frag_align);
 
 void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 {
-	struct page_frag_cache *nc;
 	void *data;
 
 	fragsz = SKB_DATA_ALIGN(fragsz);
 	if (in_hardirq() || irqs_disabled()) {
-		nc = this_cpu_ptr(&netdev_alloc_cache);
+		struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
+
 		data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask);
 	} else {
+		struct napi_alloc_cache *nc;
+
 		local_bh_disable();
-		data = __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask);
+		nc = this_cpu_ptr(&napi_alloc_cache);
+		data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
 		local_bh_enable();
 	}
 	return data;
@@ -397,8 +396,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 {
 	struct kmem_cache *cache;
 	struct sk_buff *skb;
-	u8 *data;
+	unsigned int osize;
 	bool pfmemalloc;
+	u8 *data;
 
 	cache = (flags & SKB_ALLOC_FCLONE)
 		? skbuff_fclone_cache : skbuff_head_cache;
@@ -430,7 +430,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 * Put skb_shared_info exactly at the end of allocated zone,
 	 * to allow max possible filling before reallocation.
 	 */
-	size = SKB_WITH_OVERHEAD(ksize(data));
+	osize = ksize(data);
+	size = SKB_WITH_OVERHEAD(osize);
 	prefetchw(data + size);
 
 	/*
@@ -439,7 +440,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 * the tail pointer in struct sk_buff!
 	 */
 	memset(skb, 0, offsetof(struct sk_buff, tail));
-	__build_skb_around(skb, data, 0);
+	__build_skb_around(skb, data, osize);
 	skb->pfmemalloc = pfmemalloc;
 
 	if (flags & SKB_ALLOC_FCLONE) {
@@ -1804,30 +1805,39 @@ EXPORT_SYMBOL(skb_realloc_headroom);
 struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
 {
 	int delta = headroom - skb_headroom(skb);
+	int osize = skb_end_offset(skb);
+	struct sock *sk = skb->sk;
 
 	if (WARN_ONCE(delta <= 0,
 		      "%s is expecting an increase in the headroom", __func__))
 		return skb;
 
-	/* pskb_expand_head() might crash, if skb is shared */
-	if (skb_shared(skb)) {
+	delta = SKB_DATA_ALIGN(delta);
+	/* pskb_expand_head() might crash, if skb is shared. */
+	if (skb_shared(skb) || !is_skb_wmem(skb)) {
 		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
 
-		if (likely(nskb)) {
-			if (skb->sk)
-				skb_set_owner_w(nskb, skb->sk);
-			consume_skb(skb);
-		} else {
-			kfree_skb(skb);
-		}
+		if (unlikely(!nskb))
+			goto fail;
+
+		if (sk)
+			skb_set_owner_w(nskb, sk);
+		consume_skb(skb);
 		skb = nskb;
 	}
-	if (skb &&
-	    pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
-		kfree_skb(skb);
-		skb = NULL;
+	if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
+		goto fail;
+
+	if (sk && is_skb_wmem(skb)) {
+		delta = skb_end_offset(skb) - osize;
+		refcount_add(delta, &sk->sk_wmem_alloc);
+		skb->truesize += delta;
 	}
 	return skb;
+
+fail:
+	kfree_skb(skb);
+	return NULL;
 }
 EXPORT_SYMBOL(skb_expand_head);
 
@@ -3423,8 +3433,9 @@ static inline void skb_split_no_header(struct sk_buff *skb,
 void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
 {
 	int pos = skb_headlen(skb);
+	const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY;
 
-	skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG;
+	skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags;
 	skb_zerocopy_clone(skb1, skb, 0);
 	if (len < pos)	/* Split line is inside header. */
 		skb_split_inside_header(skb, skb1, len, pos);
@@ -3439,19 +3450,7 @@ EXPORT_SYMBOL(skb_split);
  */
 static int skb_prepare_for_shift(struct sk_buff *skb)
 {
-	int ret = 0;
-
-	if (skb_cloned(skb)) {
-		/* Save and restore truesize: pskb_expand_head() may reallocate
-		 * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we
-		 * cannot change truesize at this point.
-		 */
-		unsigned int save_truesize = skb->truesize;
-
-		ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
-		skb->truesize = save_truesize;
-	}
-	return ret;
+	return skb_unclone_keeptruesize(skb, GFP_ATOMIC);
 }
 
 /**
@@ -4431,6 +4430,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_MPTCP)
 	[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
 #endif
+#if IS_ENABLED(CONFIG_MCTP_FLOWS)
+	[SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -4448,6 +4450,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 #if IS_ENABLED(CONFIG_MPTCP)
 		skb_ext_type_len[SKB_EXT_MPTCP] +
 #endif
+#if IS_ENABLED(CONFIG_MCTP_FLOWS)
+		skb_ext_type_len[SKB_EXT_MCTP] +
+#endif
 		0;
 }
 
@@ -6520,6 +6525,14 @@ static void skb_ext_put_sp(struct sec_path *sp)
 }
 #endif
 
+#ifdef CONFIG_MCTP_FLOWS
+static void skb_ext_put_mctp(struct mctp_flow *flow)
+{
+	if (flow->key)
+		mctp_key_unref(flow->key);
+}
+#endif
+
 void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
 {
 	struct skb_ext *ext = skb->extensions;
@@ -6555,6 +6568,10 @@ free_now:
 	if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
 		skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH));
 #endif
+#ifdef CONFIG_MCTP_FLOWS
+	if (__skb_ext_exist(ext, SKB_EXT_MCTP))
+		skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP));
+#endif
 
 	kmem_cache_free(skbuff_ext_cache, ext);
 }