net:Add sysctl_max_skb_frags

[ Upstream commit 5f74f82ea34c0da80ea0b49192bb5ea06e063593 ]

Devices may have limits on the number of fragments in an skb they support.
Current codebase uses a constant as maximum for number of fragments one
skb can hold and use.
When enabling scatter/gather and running traffic with many small messages
the codebase uses the maximum number of fragments and may thereby violate
the max for certain devices.
The patch introduces a global variable as max number of fragments.

Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9147f9f34cbe460eec9f782cb226095006f07b11..75f136a22a5ebf378b3e0ddec8493effc8b72d36 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -219,6 +219,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2df375ec9c2173a8132b8efa1c3062f0510284b..5bf88f58bee7405ff65f80487a64339b92a91bcb 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *     skb_panic - private function for out-of-line support

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 95b6139d710c46825d1e43f825188d81fcb70f60..a6beb7b6ae556dff501413d6661d9c4655502e36 100644 (file)
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,7 @@ static int zero = 0;
 static int one = 1;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;       /* Unused, but still a sysctl */
 
@@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec
        },
+       {
+               .procname       = "max_skb_frags",
+               .data           = &sysctl_max_skb_frags,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec_minmax,
+               .extra1         = &one,
+               .extra2         = &max_skb_frags,
+       },
        { }
 };
 

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9c1241e3230d15efb5917ab726bef8960fdebb0a..036a76ba2ac293bcf6e33655cbc7508e74f7cf8f 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -939,7 +939,7 @@ new_segment:
 
                i = skb_shinfo(skb)->nr_frags;
                can_coalesce = skb_can_coalesce(skb, i, page, offset);
-               if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+               if (!can_coalesce && i >= sysctl_max_skb_frags) {
                        tcp_mark_push(tp, skb);
                        goto new_segment;
                }
@@ -1212,7 +1212,7 @@ new_segment:
 
                        if (!skb_can_coalesce(skb, i, pfrag->page,
                                              pfrag->offset)) {
-                               if (i == MAX_SKB_FRAGS || !sg) {
+                               if (i == sysctl_max_skb_frags || !sg) {
                                        tcp_mark_push(tp, skb);
                                        goto new_segment;
                                }