summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2011-11-14 06:03:34 +0000
committerDavid S. Miller <davem@davemloft.net>2011-11-14 14:13:30 -0500
commitb2b5ce9d1ccf1c45f8ac68e5d901112ab76ba199 (patch)
tree60839b87de74c617f417eaccbbac98c770c9fc90 /net
parentc3e072f8a6c5625028531c40ec65f7e301531be2 (diff)
net: introduce build_skb()
One of the thing we discussed during netdev 2011 conference was the idea to change some network drivers to allocate/populate their skb at RX completion time, right before feeding the skb to network stack. In old days, we allocated skbs when populating the RX ring. This means bringing into cpu cache sk_buff and skb_shared_info cache lines (since we clear/initialize them), then 'queue' skb->data to NIC. By the time NIC fills a frame in skb->data buffer and host can process it, cpu probably threw away the cache lines from its caches, because lot of things happened between the allocation and final use. So the deal would be to allocate only the data buffer for the NIC to populate its RX ring buffer. And use build_skb() at RX completion to attach a data buffer (now filled with an ethernet frame) to a new skb, initialize the skb_shared_info portion, and give the hot skb to network stack. build_skb() is the function to allocate an skb, caller providing the data buffer that should be attached to it. Drivers are expected to call skb_reserve() right after build_skb() to adjust skb->data to the Ethernet frame (usually skipping NET_SKB_PAD and NET_IP_ALIGN, but some drivers might add a hardware provided alignment) Data provided to build_skb() MUST have been allocated by a prior kmalloc() call, with enough room to add SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) bytes at the end of the data without corrupting incoming frame. data = kmalloc(NET_SKB_PAD + NET_IP_ALIGN + 1536 + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), GFP_ATOMIC); ... skb = build_skb(data); if (!skb) { recycle_data(data); } else { skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); ... } Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Eilon Greenstein <eilong@broadcom.com> CC: Ben Hutchings <bhutchings@solarflare.com> CC: Tom Herbert <therbert@google.com> CC: Jamal Hadi Salim <hadi@mojatatu.com> CC: Stephen Hemminger <shemminger@vyatta.com> CC: Thomas Graf <tgraf@infradead.org> CC: Herbert Xu <herbert@gondor.apana.org.au> CC: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/core/skbuff.c49
1 files changed, 49 insertions, 0 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 18a3cebb753d..8d2c5b32f172 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -245,6 +245,55 @@ nodata:
EXPORT_SYMBOL(__alloc_skb);
/**
+ * build_skb - build a network buffer
+ * @data: data buffer provided by caller
+ *
+ * Allocate a new &sk_buff. Caller provides space holding head and
+ * skb_shared_info. @data must have been allocated by kmalloc()
+ * The return is the new skb buffer.
+ * On a failure the return is %NULL, and @data is not freed.
+ * Notes :
+ * Before IO, driver allocates only data buffer where NIC put incoming frame
+ * Driver should add room at head (NET_SKB_PAD) and
+ * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info))
+ * After IO, driver calls build_skb(), to allocate sk_buff and populate it
+ * before giving packet to stack.
+ * RX rings only contains data buffers, not full skbs.
+ */
+struct sk_buff *build_skb(void *data)
+{
+ struct skb_shared_info *shinfo;
+ struct sk_buff *skb;
+ unsigned int size;
+
+ skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ memset(skb, 0, offsetof(struct sk_buff, tail));
+ skb->truesize = SKB_TRUESIZE(size);
+ atomic_set(&skb->users, 1);
+ skb->head = data;
+ skb->data = data;
+ skb_reset_tail_pointer(skb);
+ skb->end = skb->tail + size;
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ skb->mac_header = ~0U;
+#endif
+
+ /* make sure we initialize shinfo sequentially */
+ shinfo = skb_shinfo(skb);
+ memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+ atomic_set(&shinfo->dataref, 1);
+ kmemcheck_annotate_variable(shinfo->destructor_arg);
+
+ return skb;
+}
+EXPORT_SYMBOL(build_skb);
+
+/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
* @length: length to allocate