[PATCH 0/1] gro: decrease size of CB

[PATCH 0/1] gro: decrease size of CB

[Richard Gobert]

This patch frees up space in the GRO CB, which is currently at its maximum
size. This patch was submitted and reviewed previously in a patch series,
but is now reposted as a standalone patch, as suggested by Paolo.
(https://lore.kernel.org/netdev/889f2dc5e646992033e0d9b0951d5a42f1907e07.camel@redhat.com/)

Richard Gobert (1):
  gro: decrease size of CB

 include/net/gro.h | 26 ++++++++++++++++----------
 net/core/gro.c    | 18 +++++++++++-------
 2 files changed, 27 insertions(+), 17 deletions(-)

-- 
2.36.1

[PATCH 1/1] gro: decrease size of CB

[Richard Gobert]

The GRO control block (NAPI_GRO_CB) is currently at its maximum size.
This commit reduces its size by putting two groups of fields that are
used only at different times into a union.

Specifically, the fields frag0 and frag0_len are the fields that make up
the frag0 optimisation mechanism, which is used during the initial
parsing of the SKB.

The fields last and age are used after the initial parsing, while the
SKB is stored in the GRO list, waiting for other packets to arrive.

There was one location in dev_gro_receive that modified the frag0 fields
after setting last and age. I changed this accordingly without altering
the code behaviour.

Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
---
 include/net/gro.h | 26 ++++++++++++++++----------
 net/core/gro.c    | 18 +++++++++++-------
 2 files changed, 27 insertions(+), 17 deletions(-)

diff --git a/include/net/gro.h b/include/net/gro.h
index a4fab706240d..7b47dd6ce94f 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -11,11 +11,23 @@
 #include <net/udp.h>
 
 struct napi_gro_cb {
-	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
-	void	*frag0;
+	union {
+		struct {
+			/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
+			void	*frag0;
 
-	/* Length of frag0. */
-	unsigned int frag0_len;
+			/* Length of frag0. */
+			unsigned int frag0_len;
+		};
+
+		struct {
+			/* used in skb_gro_receive() slow path */
+			struct sk_buff *last;
+
+			/* jiffies when first packet was created/queued */
+			unsigned long age;
+		};
+	};
 
 	/* This indicates where we are processing relative to skb->data. */
 	int	data_offset;
@@ -32,9 +44,6 @@ struct napi_gro_cb {
 	/* Used in ipv6_gro_receive() and foo-over-udp */
 	u16	proto;
 
-	/* jiffies when first packet was created/queued */
-	unsigned long age;
-
 /* Used in napi_gro_cb::free */
 #define NAPI_GRO_FREE             1
 #define NAPI_GRO_FREE_STOLEN_HEAD 2
@@ -77,9 +86,6 @@ struct napi_gro_cb {
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
-
-	/* used in skb_gro_receive() slow path */
-	struct sk_buff *last;
 };
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
diff --git a/net/core/gro.c b/net/core/gro.c
index 2d84165cb4f1..91454176a6d8 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -460,6 +460,14 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 	}
 }
 
+static inline void gro_try_pull_from_frag0(struct sk_buff *skb)
+{
+	int grow = skb_gro_offset(skb) - skb_headlen(skb);
+
+	if (grow > 0)
+		gro_pull_from_frag0(skb, grow);
+}
+
 static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
 {
 	struct sk_buff *oldest;
@@ -489,7 +497,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	struct sk_buff *pp = NULL;
 	enum gro_result ret;
 	int same_flow;
-	int grow;
 
 	if (netif_elide_gro(skb->dev))
 		goto normal;
@@ -564,17 +571,13 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	else
 		gro_list->count++;
 
+	gro_try_pull_from_frag0(skb);
 	NAPI_GRO_CB(skb)->age = jiffies;
 	NAPI_GRO_CB(skb)->last = skb;
 	if (!skb_is_gso(skb))
 		skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	list_add(&skb->list, &gro_list->list);
 	ret = GRO_HELD;
-
-pull:
-	grow = skb_gro_offset(skb) - skb_headlen(skb);
-	if (grow > 0)
-		gro_pull_from_frag0(skb, grow);
 ok:
 	if (gro_list->count) {
 		if (!test_bit(bucket, &napi->gro_bitmask))
@@ -587,7 +590,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 normal:
 	ret = GRO_NORMAL;
-	goto pull;
+	gro_try_pull_from_frag0(skb);
+	goto ok;
 }
 
 struct packet_offload *gro_find_receive_by_type(__be16 type)
-- 
2.36.1

Re: [PATCH 1/1] gro: decrease size of CB

[Simon Horman]

On Mon, May 29, 2023 at 06:12:42PM +0200, Richard Gobert wrote:
> The GRO control block (NAPI_GRO_CB) is currently at its maximum size.
> This commit reduces its size by putting two groups of fields that are
> used only at different times into a union.
> 
> Specifically, the fields frag0 and frag0_len are the fields that make up
> the frag0 optimisation mechanism, which is used during the initial
> parsing of the SKB.
> 
> The fields last and age are used after the initial parsing, while the
> SKB is stored in the GRO list, waiting for other packets to arrive.
> 
> There was one location in dev_gro_receive that modified the frag0 fields
> after setting last and age. I changed this accordingly without altering
> the code behaviour.
> 
> Signed-off-by: Richard Gobert <richardbgobert@gmail.com>

...

> diff --git a/net/core/gro.c b/net/core/gro.c
> index 2d84165cb4f1..91454176a6d8 100644
> --- a/net/core/gro.c
> +++ b/net/core/gro.c
> @@ -460,6 +460,14 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
>  	}
>  }
>  
> +static inline void gro_try_pull_from_frag0(struct sk_buff *skb)

Hi Richard,

In general it is preferred not to use the inline keyword in C files,
but rather let the compiler do it's thing.

Unless you think the compiler isn't doing it's thing very well
in this case, please consider removing the inline keyword.

> +{
> +	int grow = skb_gro_offset(skb) - skb_headlen(skb);
> +
> +	if (grow > 0)
> +		gro_pull_from_frag0(skb, grow);
> +}
> +
>  static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
>  {
>  	struct sk_buff *oldest;

...