net: Add function for parsing the header length out of linear ethernet frames
This patch updates some of the flow_dissector api so that it can be used to
parse the length of ethernet buffers stored in fragments. Most of the
changes needed were to __skb_get_poff as it needed to be updated to support
sending a linear buffer instead of a skb.
I have split __skb_get_poff into two functions, the first is skb_get_poff
and it retains the functionality of the original __skb_get_poff. The other
function is __skb_get_poff which now works much like __skb_flow_dissect in
relation to skb_flow_dissect in that it provides the same functionality but
works with just a data buffer and hlen instead of needing an skb.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 9c5529d..733980f 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -29,6 +29,7 @@
#include <asm/bitsperlong.h>
#ifdef __KERNEL__
+u32 eth_get_headlen(void *data, unsigned int max_len);
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
extern const struct header_ops eth_header_ops;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1cf0cfa..07c9fdd 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3218,7 +3218,9 @@
int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
-u32 __skb_get_poff(const struct sk_buff *skb);
+u32 skb_get_poff(const struct sk_buff *skb);
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+ const struct flow_keys *keys, int hlen);
/**
* skb_head_is_locked - Determine if the skb->head is locked down
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 9a03f73..7ee2df0 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -40,4 +40,6 @@
return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
}
u32 flow_hash_from_keys(struct flow_keys *keys);
+unsigned int flow_get_hlen(const unsigned char *data, unsigned int max_len,
+ __be16 protocol);
#endif
diff --git a/net/core/filter.c b/net/core/filter.c
index 37f8eb0..fa5b7d0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -113,7 +113,7 @@
static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
{
- return __skb_get_poff((struct sk_buff *)(unsigned long) ctx);
+ return skb_get_poff((struct sk_buff *)(unsigned long) ctx);
}
static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 12f48ca..8560dea 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -13,6 +13,7 @@
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
#include <net/flow_keys.h>
+#include <scsi/fc/fc_fcoe.h>
/* copy saddr & daddr, possibly using 64bit load/store
* Equivalent to : flow->src = iph->saddr;
@@ -117,6 +118,13 @@
flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
nhoff += sizeof(struct ipv6hdr);
+ /* skip the flow label processing if skb is NULL. The
+ * assumption here is that if there is no skb we are not
+ * looking for flow info as much as we are length.
+ */
+ if (!skb)
+ break;
+
flow_label = ip6_flowlabel(iph);
if (flow_label) {
/* Awesome, IPv6 packet has a flow label so we can
@@ -165,6 +173,9 @@
return false;
}
}
+ case htons(ETH_P_FCOE):
+ flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+ /* fall through */
default:
return false;
}
@@ -316,26 +327,18 @@
}
EXPORT_SYMBOL(__skb_tx_hash);
-/* __skb_get_poff() returns the offset to the payload as far as it could
- * be dissected. The main user is currently BPF, so that we can dynamically
- * truncate packets without needing to push actual payload to the user
- * space and can analyze headers only, instead.
- */
-u32 __skb_get_poff(const struct sk_buff *skb)
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+ const struct flow_keys *keys, int hlen)
{
- struct flow_keys keys;
- u32 poff = 0;
+ u32 poff = keys->thoff;
- if (!skb_flow_dissect(skb, &keys))
- return 0;
-
- poff += keys.thoff;
- switch (keys.ip_proto) {
+ switch (keys->ip_proto) {
case IPPROTO_TCP: {
const struct tcphdr *tcph;
struct tcphdr _tcph;
- tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
+ tcph = __skb_header_pointer(skb, poff, sizeof(_tcph),
+ data, hlen, &_tcph);
if (!tcph)
return poff;
@@ -369,6 +372,21 @@
return poff;
}
+/* skb_get_poff() returns the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
+ * truncate packets without needing to push actual payload to the user
+ * space and can analyze headers only, instead.
+ */
+u32 skb_get_poff(const struct sk_buff *skb)
+{
+ struct flow_keys keys;
+
+ if (!skb_flow_dissect(skb, &keys))
+ return 0;
+
+ return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
+}
+
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 5cebca1..33a140e 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -146,6 +146,33 @@
EXPORT_SYMBOL(eth_rebuild_header);
/**
+ * eth_get_headlen - determine the the length of header for an ethernet frame
+ * @data: pointer to start of frame
+ * @len: total length of frame
+ *
+ * Make a best effort attempt to pull the length for all of the headers for
+ * a given frame in a linear buffer.
+ */
+u32 eth_get_headlen(void *data, unsigned int len)
+{
+ const struct ethhdr *eth = (const struct ethhdr *)data;
+ struct flow_keys keys;
+
+ /* this should never happen, but better safe than sorry */
+ if (len < sizeof(*eth))
+ return len;
+
+ /* parse any remaining L2/L3 headers, check for L4 */
+ if (!__skb_flow_dissect(NULL, &keys, data,
+ eth->h_proto, sizeof(*eth), len))
+ return max_t(u32, keys.thoff, sizeof(*eth));
+
+ /* parse for any L4 headers */
+ return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
+}
+EXPORT_SYMBOL(eth_get_headlen);
+
+/**
* eth_type_trans - determine the packet's protocol ID.
* @skb: received socket data
* @dev: receiving network device