diff mbox series

[net-next,5/6] skbuff: allow 'slow_gro' for skb carring sock reference

Message ID 4864c71049779d924c1cf9d2cd8a86b064f8fd17.1627405778.git.pabeni@redhat.com (mailing list archive)
State Accepted
Commit 5e10da5385d20c4bae587bc2921e5fdd9655d5fc
Delegated to: Netdev Maintainers
Headers show
Series sk_buff: optimize GRO for the common case | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 13 maintainers not CCed: linmiaohe@huawei.com jonathan.lemon@gmail.com gnault@redhat.com daniel@iogearbox.net cong.wang@bytedance.com ast@kernel.org ap420073@gmail.com willemb@google.com bjorn@kernel.org memxor@gmail.com alobakin@pm.me atenart@kernel.org weiwan@google.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 3051 this patch: 3051
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 85 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 3135 this patch: 3135
netdev/header_inline success Link

Commit Message

Paolo Abeni July 28, 2021, 4:24 p.m. UTC 
This change leverages the infrastructure introduced by the previous
patches to allow soft devices passing to the GRO engine owned skbs
without impacting the fast-path.

It's up to the GRO caller ensuring the slow_gro bit validity before
invoking the GRO engine. The new helper skb_prepare_for_gro() is
introduced for that goal.

On slow_gro, skbs are aggregated only with equal sk.
Additionally, skb truesize on GRO recycle and free is correctly
updated so that sk wmem is not changed by the GRO processing.

rfc-> v1:
 - fixed bad truesize on dev_gro_receive NAPI_FREE
 - use the existing state bit

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sock.h |  9 +++++++++
 net/core/dev.c     |  2 ++
 net/core/skbuff.c  | 17 +++++++++++++----
 3 files changed, 24 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/include/net/sock.h b/include/net/sock.h
index f23cb259b0e2..ff1be7e7e90b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2249,6 +2249,15 @@  static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struc
 	return false;
 }
 
+static inline void skb_prepare_for_gro(struct sk_buff *skb)
+{
+	if (skb->destructor != sock_wfree) {
+		skb_orphan(skb);
+		return;
+	}
+	skb->slow_gro = 1;
+}
+
 void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 		    unsigned long expires);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 19565f7497ee..dcc87fcd64ba 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6034,6 +6034,7 @@  static void gro_list_prepare(const struct list_head *head,
 			struct tc_skb_ext *p_ext;
 #endif
 
+			diffs |= p->sk != skb->sk;
 			diffs |= skb_metadata_dst_cmp(p, skb);
 			diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb);
 
@@ -6311,6 +6312,7 @@  static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 	if (unlikely(skb->slow_gro)) {
+		skb_orphan(skb);
 		skb_ext_reset(skb);
 		nf_reset_ct(skb);
 		skb->slow_gro = 0;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8231cbddb6ed..9510cb0807bc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -958,6 +958,7 @@  void napi_skb_free_stolen_head(struct sk_buff *skb)
 		nf_reset_ct(skb);
 		skb_dst_drop(skb);
 		skb_ext_put(skb);
+		skb_orphan(skb);
 		skb->slow_gro = 0;
 	}
 	napi_skb_cache_put(skb);
@@ -3898,6 +3899,9 @@  int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
 	NAPI_GRO_CB(p)->last = skb;
 	NAPI_GRO_CB(p)->count++;
 	p->data_len += skb->len;
+
+	/* sk owenrship - if any - completely transferred to the aggregated packet */
+	skb->destructor = NULL;
 	p->truesize += skb->truesize;
 	p->len += skb->len;
 
@@ -4265,6 +4269,7 @@  int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int headlen = skb_headlen(skb);
 	unsigned int len = skb_gro_len(skb);
 	unsigned int delta_truesize;
+	unsigned int new_truesize;
 	struct sk_buff *lp;
 
 	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
@@ -4296,10 +4301,10 @@  int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 		skb_frag_size_sub(frag, offset);
 
 		/* all fragments truesize : remove (head size + sk_buff) */
-		delta_truesize = skb->truesize -
-				 SKB_TRUESIZE(skb_end_offset(skb));
+		new_truesize = SKB_TRUESIZE(skb_end_offset(skb));
+		delta_truesize = skb->truesize - new_truesize;
 
-		skb->truesize -= skb->data_len;
+		skb->truesize = new_truesize;
 		skb->len -= skb->data_len;
 		skb->data_len = 0;
 
@@ -4328,12 +4333,16 @@  int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 		memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
 		/* We dont need to clear skbinfo->nr_frags here */
 
-		delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
+		new_truesize = SKB_TRUESIZE(sizeof(struct sk_buff));
+		delta_truesize = skb->truesize - new_truesize;
+		skb->truesize = new_truesize;
 		NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
 		goto done;
 	}
 
 merge:
+	/* sk owenrship - if any - completely transferred to the aggregated packet */
+	skb->destructor = NULL;
 	delta_truesize = skb->truesize;
 	if (offset > headlen) {
 		unsigned int eat = offset - headlen;