X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_gro%2Fgro_tcp4.h;h=bb875a5ef061133e45f9e2552f88e5058ea1ab7a;hb=986f2134c336a086054980903e819308dcfd43ce;hp=d12952393ce90b2499c0c60808165068d9cbda0e;hpb=369991d997e4abdee355e19ffbb41a4d246cafa2;p=dpdk.git

diff --git a/lib/librte_gro/gro_tcp4.h b/lib/librte_gro/gro_tcp4.h
index d12952393c..bb875a5ef0 100644
--- a/lib/librte_gro/gro_tcp4.h
+++ b/lib/librte_gro/gro_tcp4.h
@@ -5,19 +5,28 @@
 #ifndef _GRO_TCP4_H_
 #define _GRO_TCP4_H_
 
+#include <rte_ip.h>
+#include <rte_tcp.h>
+#include <rte_vxlan.h>
+
 #define INVALID_ARRAY_INDEX 0xffffffffUL
 #define GRO_TCP4_TBL_MAX_ITEM_NUM (1024UL * 1024UL)
 
 /*
- * the max L3 length of a TCP/IPv4 packet. The L3 length
- * is the sum of ipv4 header, tcp header and L4 payload.
+ * The max length of a IPv4 packet, which includes the length of the L3
+ * header, the L4 header and the data payload.
  */
-#define TCP4_MAX_L3_LENGTH UINT16_MAX
+#define MAX_IPV4_PKT_LENGTH UINT16_MAX
+
+/* The maximum TCP header length */
+#define MAX_TCP_HLEN 60
+#define INVALID_TCP_HDRLEN(len) \
+	(((len) < sizeof(struct rte_tcp_hdr)) || ((len) > MAX_TCP_HLEN))
 
-/* criteria of mergeing packets */
-struct tcp4_key {
-	struct ether_addr eth_saddr;
-	struct ether_addr eth_daddr;
+/* Header fields representing a TCP/IPv4 flow */
+struct tcp4_flow_key {
+	struct rte_ether_addr eth_saddr;
+	struct rte_ether_addr eth_daddr;
 	uint32_t ip_src_addr;
 	uint32_t ip_dst_addr;
 
@@ -26,44 +35,43 @@ struct tcp4_key {
 	uint16_t dst_port;
 };
 
-struct gro_tcp4_key {
-	struct tcp4_key key;
+struct gro_tcp4_flow {
+	struct tcp4_flow_key key;
 	/*
-	 * the index of the first packet in the item group.
-	 * If the value is INVALID_ARRAY_INDEX, it means
-	 * the key is empty.
+	 * The index of the first packet in the flow.
+	 * INVALID_ARRAY_INDEX indicates an empty flow.
 	 */
 	uint32_t start_index;
 };
 
 struct gro_tcp4_item {
 	/*
-	 * first segment of the packet. If the value
+	 * The first MBUF segment of the packet. If the value
 	 * is NULL, it means the item is empty.
 	 */
 	struct rte_mbuf *firstseg;
-	/* last segment of the packet */
+	/* The last MBUF segment of the packet */
 	struct rte_mbuf *lastseg;
 	/*
-	 * the time when the first packet is inserted
-	 * into the table. If a packet in the table is
-	 * merged with an incoming packet, this value
-	 * won't be updated. We set this value only
-	 * when the first packet is inserted into the
-	 * table.
+	 * The time when the first packet is inserted into the table.
+	 * This value won't be updated, even if the packet is merged
+	 * with other packets.
 	 */
 	uint64_t start_time;
 	/*
-	 * we use next_pkt_idx to chain the packets that
-	 * have same key value but can't be merged together.
+	 * next_pkt_idx is used to chain the packets that
+	 * are in the same flow but can't be merged together
+	 * (e.g. caused by packet reordering).
 	 */
 	uint32_t next_pkt_idx;
-	/* the sequence number of the packet */
+	/* TCP sequence number of the packet */
 	uint32_t sent_seq;
-	/* the IP ID of the packet */
+	/* IPv4 ID of the packet */
 	uint16_t ip_id;
 	/* the number of merged packets */
 	uint16_t nb_merged;
+	/* Indicate if IPv4 ID can be ignored */
+	uint8_t is_atomic;
 };
 
 /*
@@ -72,31 +80,31 @@ struct gro_tcp4_item {
 struct gro_tcp4_tbl {
 	/* item array */
 	struct gro_tcp4_item *items;
-	/* key array */
-	struct gro_tcp4_key *keys;
+	/* flow array */
+	struct gro_tcp4_flow *flows;
 	/* current item number */
 	uint32_t item_num;
-	/* current key num */
-	uint32_t key_num;
+	/* current flow num */
+	uint32_t flow_num;
 	/* item array size */
 	uint32_t max_item_num;
-	/* key array size */
-	uint32_t max_key_num;
+	/* flow array size */
+	uint32_t max_flow_num;
 };
 
 /**
  * This function creates a TCP/IPv4 reassembly table.
  *
  * @param socket_id
- *  socket index for allocating TCP/IPv4 reassemble table
+ *  Socket index for allocating the TCP/IPv4 reassemble table
  * @param max_flow_num
- *  the maximum number of flows in the TCP/IPv4 GRO table
+ *  The maximum number of flows in the TCP/IPv4 GRO table
  * @param max_item_per_flow
- *  the maximum packet number per flow.
+ *  The maximum number of packets per flow
  *
  * @return
- *  if create successfully, return a pointer which points to the
- *  created TCP/IPv4 GRO table. Otherwise, return NULL.
+ *  - Return the table pointer on success.
+ *  - Return NULL on failure.
  */
 void *gro_tcp4_tbl_create(uint16_t socket_id,
 		uint16_t max_flow_num,
@@ -106,62 +114,56 @@ void *gro_tcp4_tbl_create(uint16_t socket_id,
  * This function destroys a TCP/IPv4 reassembly table.
  *
  * @param tbl
- *  a pointer points to the TCP/IPv4 reassembly table.
+ *  Pointer pointing to the TCP/IPv4 reassembly table.
  */
 void gro_tcp4_tbl_destroy(void *tbl);
 
 /**
- * This function searches for a packet in the TCP/IPv4 reassembly table
- * to merge with the inputted one. To merge two packets is to chain them
- * together and update packet headers. Packets, whose SYN, FIN, RST, PSH
- * CWR, ECE or URG bit is set, are returned immediately. Packets which
- * only have packet headers (i.e. without data) are also returned
- * immediately. Otherwise, the packet is either merged, or inserted into
- * the table. Besides, if there is no available space to insert the
- * packet, this function returns immediately too.
+ * This function merges a TCP/IPv4 packet. It doesn't process the packet,
+ * which has SYN, FIN, RST, PSH, CWR, ECE or URG set, or doesn't have
+ * payload.
  *
- * This function assumes the inputted packet is with correct IPv4 and
- * TCP checksums. And if two packets are merged, it won't re-calculate
- * IPv4 and TCP checksums. Besides, if the inputted packet is IP
- * fragmented, it assumes the packet is complete (with TCP header).
+ * This function doesn't check if the packet has correct checksums and
+ * doesn't re-calculate checksums for the merged packet. Additionally,
+ * it assumes the packets are complete (i.e., MF==0 && frag_off==0),
+ * when IP fragmentation is possible (i.e., DF==0). It returns the
+ * packet, if the packet has invalid parameters (e.g. SYN bit is set)
+ * or there is no available space in the table.
  *
  * @param pkt
- *  packet to reassemble.
+ *  Packet to reassemble
  * @param tbl
- *  a pointer that points to a TCP/IPv4 reassembly table.
+ *  Pointer pointing to the TCP/IPv4 reassembly table
  * @start_time
- *  the start time that the packet is inserted into the table
+ *  The time when the packet is inserted into the table
  *
  * @return
- *  if the packet doesn't have data, or SYN, FIN, RST, PSH, CWR, ECE
- *  or URG bit is set, or there is no available space in the table to
- *  insert a new item or a new key, return a negative value. If the
- *  packet is merged successfully, return an positive value. If the
- *  packet is inserted into the table, return 0.
+ *  - Return a positive value if the packet is merged.
+ *  - Return zero if the packet isn't merged but stored in the table.
+ *  - Return a negative value for invalid parameters or no available
+ *    space in the table.
  */
 int32_t gro_tcp4_reassemble(struct rte_mbuf *pkt,
 		struct gro_tcp4_tbl *tbl,
 		uint64_t start_time);
 
 /**
- * This function flushes timeout packets in a TCP/IPv4 reassembly table
- * to applications, and without updating checksums for merged packets.
- * The max number of flushed timeout packets is the element number of
- * the array which is used to keep flushed packets.
+ * This function flushes timeout packets in a TCP/IPv4 reassembly table,
+ * and without updating checksums.
  *
  * @param tbl
- *  a pointer that points to a TCP GRO table.
+ *  TCP/IPv4 reassembly table pointer
  * @param flush_timestamp
- *  this function flushes packets which are inserted into the table
- *  before or at the flush_timestamp.
+ *  Flush packets which are inserted into the table before or at the
+ *  flush_timestamp.
  * @param out
- *  pointer array which is used to keep flushed packets.
+ *  Pointer array used to keep flushed packets
  * @param nb_out
- *  the element number of out. It's also the max number of timeout
+ *  The element number in 'out'. It also determines the maximum number of
  *  packets that can be flushed finally.
  *
  * @return
- *  the number of packets that are returned.
+ *  The number of flushed packets
  */
 uint16_t gro_tcp4_tbl_timeout_flush(struct gro_tcp4_tbl *tbl,
 		uint64_t flush_timestamp,
@@ -173,10 +175,133 @@ uint16_t gro_tcp4_tbl_timeout_flush(struct gro_tcp4_tbl *tbl,
  * reassembly table.
  *
  * @param tbl
- *  pointer points to a TCP/IPv4 reassembly table.
+ *  TCP/IPv4 reassembly table pointer
  *
  * @return
- *  the number of packets in the table
+ *  The number of packets in the table
  */
 uint32_t gro_tcp4_tbl_pkt_count(void *tbl);
+
+/*
+ * Check if two TCP/IPv4 packets belong to the same flow.
+ */
+static inline int
+is_same_tcp4_flow(struct tcp4_flow_key k1, struct tcp4_flow_key k2)
+{
+	return (rte_is_same_ether_addr(&k1.eth_saddr, &k2.eth_saddr) &&
+			rte_is_same_ether_addr(&k1.eth_daddr, &k2.eth_daddr) &&
+			(k1.ip_src_addr == k2.ip_src_addr) &&
+			(k1.ip_dst_addr == k2.ip_dst_addr) &&
+			(k1.recv_ack == k2.recv_ack) &&
+			(k1.src_port == k2.src_port) &&
+			(k1.dst_port == k2.dst_port));
+}
+
+/*
+ * Merge two TCP/IPv4 packets without updating checksums.
+ * If cmp is larger than 0, append the new packet to the
+ * original packet. Otherwise, pre-pend the new packet to
+ * the original packet.
+ */
+static inline int
+merge_two_tcp4_packets(struct gro_tcp4_item *item,
+		struct rte_mbuf *pkt,
+		int cmp,
+		uint32_t sent_seq,
+		uint16_t ip_id,
+		uint16_t l2_offset)
+{
+	struct rte_mbuf *pkt_head, *pkt_tail, *lastseg;
+	uint16_t hdr_len, l2_len;
+
+	if (cmp > 0) {
+		pkt_head = item->firstseg;
+		pkt_tail = pkt;
+	} else {
+		pkt_head = pkt;
+		pkt_tail = item->firstseg;
+	}
+
+	/* check if the IPv4 packet length is greater than the max value */
+	hdr_len = l2_offset + pkt_head->l2_len + pkt_head->l3_len +
+		pkt_head->l4_len;
+	l2_len = l2_offset > 0 ? pkt_head->outer_l2_len : pkt_head->l2_len;
+	if (unlikely(pkt_head->pkt_len - l2_len + pkt_tail->pkt_len -
+				hdr_len > MAX_IPV4_PKT_LENGTH))
+		return 0;
+
+	/* remove the packet header for the tail packet */
+	rte_pktmbuf_adj(pkt_tail, hdr_len);
+
+	/* chain two packets together */
+	if (cmp > 0) {
+		item->lastseg->next = pkt;
+		item->lastseg = rte_pktmbuf_lastseg(pkt);
+		/* update IP ID to the larger value */
+		item->ip_id = ip_id;
+	} else {
+		lastseg = rte_pktmbuf_lastseg(pkt);
+		lastseg->next = item->firstseg;
+		item->firstseg = pkt;
+		/* update sent_seq to the smaller value */
+		item->sent_seq = sent_seq;
+		item->ip_id = ip_id;
+	}
+	item->nb_merged++;
+
+	/* update MBUF metadata for the merged packet */
+	pkt_head->nb_segs += pkt_tail->nb_segs;
+	pkt_head->pkt_len += pkt_tail->pkt_len;
+
+	return 1;
+}
+
+/*
+ * Check if two TCP/IPv4 packets are neighbors.
+ */
+static inline int
+check_seq_option(struct gro_tcp4_item *item,
+		struct rte_tcp_hdr *tcph,
+		uint32_t sent_seq,
+		uint16_t ip_id,
+		uint16_t tcp_hl,
+		uint16_t tcp_dl,
+		uint16_t l2_offset,
+		uint8_t is_atomic)
+{
+	struct rte_mbuf *pkt_orig = item->firstseg;
+	struct rte_ipv4_hdr *iph_orig;
+	struct rte_tcp_hdr *tcph_orig;
+	uint16_t len, tcp_hl_orig;
+
+	iph_orig = (struct rte_ipv4_hdr *)(rte_pktmbuf_mtod(pkt_orig, char *) +
+			l2_offset + pkt_orig->l2_len);
+	tcph_orig = (struct rte_tcp_hdr *)((char *)iph_orig + pkt_orig->l3_len);
+	tcp_hl_orig = pkt_orig->l4_len;
+
+	/* Check if TCP option fields equal */
+	len = RTE_MAX(tcp_hl, tcp_hl_orig) - sizeof(struct rte_tcp_hdr);
+	if ((tcp_hl != tcp_hl_orig) || ((len > 0) &&
+				(memcmp(tcph + 1, tcph_orig + 1,
+					len) != 0)))
+		return 0;
+
+	/* Don't merge packets whose DF bits are different */
+	if (unlikely(item->is_atomic ^ is_atomic))
+		return 0;
+
+	/* check if the two packets are neighbors */
+	len = pkt_orig->pkt_len - l2_offset - pkt_orig->l2_len -
+		pkt_orig->l3_len - tcp_hl_orig;
+	if ((sent_seq == item->sent_seq + len) && (is_atomic ||
+				(ip_id == item->ip_id + 1)))
+		/* append the new packet */
+		return 1;
+	else if ((sent_seq + tcp_dl == item->sent_seq) && (is_atomic ||
+				(ip_id + item->nb_merged == item->ip_id)))
+		/* pre-pend the new packet */
+		return -1;
+
+	return 0;
+}
 #endif