From: Kumara Parameshwaran <kumaraparamesh92@gmail.com>
To: jiayu.hu@intel.com
Cc: dev@dpdk.org, Kumara Parameshwaran <kumaraparamesh92@gmail.com>
Subject: [PATCH v11 1/2] gro : refactor IPv4 to add GRO support for IPv6
Date: Wed, 21 Jun 2023 14:08:35 +0530 [thread overview]
Message-ID: <20230621083836.63060-1-kumaraparamesh92@gmail.com> (raw)
In-Reply-To: <20221020181425.48006-1-kumaraparmesh92@gmail.com>
Refactor the existing code to reuse data strutures and functions
to add support for IPv6 GRO
Signed-off-by: Kumara Parameshwaran <kumaraparamesh92@gmail.com>
---
v1:
* Changes to support GRO for TCP/ipv6 packets. This does not include
vxlan changes.
* The GRO is performed only for ipv6 packets that does not contain
extension headers.
* The logic for the TCP coalescing remains the same, in ipv6 header
the source address, destination address, flow label, version fields
are expected to be the same.
* Re-organised the code to reuse certain tcp functions for both ipv4 and
ipv6 flows.
v2:
* Fix comments in gro_tcp6.h header file.
v3:
* Adderess review comments to fix code duplication for v4 and v6
v4:
* Addresses review comments for v3, do not use callbacks
v5:
* Address review comments
v6:
* Fix warning and coding style issues
v7:
* Fix build compilation issue
v8:
* Use gro_tcp_internal.h for functions used for gro_tcp4 and gro_tcp6 and use
gro_tcp.h for data structures and functions used across gro_vxlan_tcp4
v9:
* Resolve merge conflict and add gro_tcp.h in proper path
v10:
* Refactor the code to contain 2 patches. This patch contains code/data strcuture changes
in ipv4 code that can be reused.
lib/gro/gro_tcp.h | 190 +++++++++++++++++++++++++++++++++++++
lib/gro/gro_tcp4.c | 177 ++++++++--------------------------
lib/gro/gro_tcp4.h | 170 ++-------------------------------
lib/gro/gro_tcp_internal.h | 128 +++++++++++++++++++++++++
lib/gro/gro_vxlan_tcp4.c | 22 ++---
lib/gro/gro_vxlan_tcp4.h | 2 +-
lib/gro/rte_gro.c | 2 +-
7 files changed, 373 insertions(+), 318 deletions(-)
create mode 100644 lib/gro/gro_tcp.h
create mode 100644 lib/gro/gro_tcp_internal.h
diff --git a/lib/gro/gro_tcp.h b/lib/gro/gro_tcp.h
new file mode 100644
index 0000000000..d926c4b8cc
--- /dev/null
+++ b/lib/gro/gro_tcp.h
@@ -0,0 +1,190 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2023 Intel Corporation
+ */
+#ifndef _GRO_TCP_H_
+#define _GRO_TCP_H_
+
+#define INVALID_ARRAY_INDEX 0xffffffffUL
+
+#include <rte_tcp.h>
+
+/*
+ * The max length of a IPv4 packet, which includes the length of the L3
+ * header, the L4 header and the data payload.
+ */
+#define MAX_IP_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))
+
+struct cmn_tcp_key {
+ struct rte_ether_addr eth_saddr;
+ struct rte_ether_addr eth_daddr;
+ uint32_t recv_ack;
+ uint16_t src_port;
+ uint16_t dst_port;
+};
+
+#define ASSIGN_COMMON_TCP_KEY(k1, k2) \
+ do {\
+ rte_ether_addr_copy(&(k1->eth_saddr), &(k2->eth_saddr)); \
+ rte_ether_addr_copy(&(k1->eth_daddr), &(k2->eth_daddr)); \
+ k2->recv_ack = k1->recv_ack; \
+ k2->src_port = k1->src_port; \
+ k2->dst_port = k1->dst_port; \
+ } while (0)
+
+struct gro_tcp_item {
+ /*
+ * The first MBUF segment of the packet. If the value
+ * is NULL, it means the item is empty.
+ */
+ struct rte_mbuf *firstseg;
+ /* The last MBUF segment of the packet */
+ struct rte_mbuf *lastseg;
+ /*
+ * 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;
+ /*
+ * 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;
+ /* TCP sequence number of the packet */
+ uint32_t sent_seq;
+ union {
+ /* IPv4 ID of the packet */
+ uint16_t ip_id;
+ /* Unused field for IPv6 */
+ uint16_t unused;
+ } l3;
+ /* the number of merged packets */
+ uint16_t nb_merged;
+ /* Indicate if IPv4 ID can be ignored */
+ uint8_t is_atomic;
+};
+
+/*
+ * Merge two TCP 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_tcp_packets(struct gro_tcp_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_IP_PKT_LENGTH))
+ return 0;
+
+ if (unlikely(pkt_head->nb_segs >= 20))
+ 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->l3.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->l3.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 packets are neighbors.
+ */
+static inline int
+check_seq_option(struct gro_tcp_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;
+ char *iph_orig;
+ struct rte_tcp_hdr *tcph_orig;
+ uint16_t len, tcp_hl_orig;
+
+ iph_orig = (char *)(rte_pktmbuf_mtod(pkt_orig, char *) +
+ l2_offset + pkt_orig->l2_len);
+ tcph_orig = (struct rte_tcp_hdr *)(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->l3.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->l3.ip_id)))
+ /* pre-pend the new packet */
+ return -1;
+
+ return 0;
+}
+
+static inline int
+is_same_common_tcp_key(struct cmn_tcp_key *k1, struct cmn_tcp_key *k2)
+{
+ return (!memcmp(k1, k2, sizeof(struct cmn_tcp_key)));
+}
+
+#endif
diff --git a/lib/gro/gro_tcp4.c b/lib/gro/gro_tcp4.c
index 0014096e63..6645de592b 100644
--- a/lib/gro/gro_tcp4.c
+++ b/lib/gro/gro_tcp4.c
@@ -7,6 +7,7 @@
#include <rte_ethdev.h>
#include "gro_tcp4.h"
+#include "gro_tcp_internal.h"
void *
gro_tcp4_tbl_create(uint16_t socket_id,
@@ -30,7 +31,7 @@ gro_tcp4_tbl_create(uint16_t socket_id,
if (tbl == NULL)
return NULL;
- size = sizeof(struct gro_tcp4_item) * entries_num;
+ size = sizeof(struct gro_tcp_item) * entries_num;
tbl->items = rte_zmalloc_socket(__func__,
size,
RTE_CACHE_LINE_SIZE,
@@ -71,18 +72,6 @@ gro_tcp4_tbl_destroy(void *tbl)
rte_free(tcp_tbl);
}
-static inline uint32_t
-find_an_empty_item(struct gro_tcp4_tbl *tbl)
-{
- uint32_t i;
- uint32_t max_item_num = tbl->max_item_num;
-
- for (i = 0; i < max_item_num; i++)
- if (tbl->items[i].firstseg == NULL)
- return i;
- return INVALID_ARRAY_INDEX;
-}
-
static inline uint32_t
find_an_empty_flow(struct gro_tcp4_tbl *tbl)
{
@@ -95,56 +84,6 @@ find_an_empty_flow(struct gro_tcp4_tbl *tbl)
return INVALID_ARRAY_INDEX;
}
-static inline uint32_t
-insert_new_item(struct gro_tcp4_tbl *tbl,
- struct rte_mbuf *pkt,
- uint64_t start_time,
- uint32_t prev_idx,
- uint32_t sent_seq,
- uint16_t ip_id,
- uint8_t is_atomic)
-{
- uint32_t item_idx;
-
- item_idx = find_an_empty_item(tbl);
- if (item_idx == INVALID_ARRAY_INDEX)
- return INVALID_ARRAY_INDEX;
-
- tbl->items[item_idx].firstseg = pkt;
- tbl->items[item_idx].lastseg = rte_pktmbuf_lastseg(pkt);
- tbl->items[item_idx].start_time = start_time;
- tbl->items[item_idx].next_pkt_idx = INVALID_ARRAY_INDEX;
- tbl->items[item_idx].sent_seq = sent_seq;
- tbl->items[item_idx].ip_id = ip_id;
- tbl->items[item_idx].nb_merged = 1;
- tbl->items[item_idx].is_atomic = is_atomic;
- tbl->item_num++;
-
- /* if the previous packet exists, chain them together. */
- if (prev_idx != INVALID_ARRAY_INDEX) {
- tbl->items[item_idx].next_pkt_idx =
- tbl->items[prev_idx].next_pkt_idx;
- tbl->items[prev_idx].next_pkt_idx = item_idx;
- }
-
- return item_idx;
-}
-
-static inline uint32_t
-delete_item(struct gro_tcp4_tbl *tbl, uint32_t item_idx,
- uint32_t prev_item_idx)
-{
- uint32_t next_idx = tbl->items[item_idx].next_pkt_idx;
-
- /* NULL indicates an empty item */
- tbl->items[item_idx].firstseg = NULL;
- tbl->item_num--;
- if (prev_item_idx != INVALID_ARRAY_INDEX)
- tbl->items[prev_item_idx].next_pkt_idx = next_idx;
-
- return next_idx;
-}
-
static inline uint32_t
insert_new_flow(struct gro_tcp4_tbl *tbl,
struct tcp4_flow_key *src,
@@ -159,13 +98,10 @@ insert_new_flow(struct gro_tcp4_tbl *tbl,
dst = &(tbl->flows[flow_idx].key);
- rte_ether_addr_copy(&(src->eth_saddr), &(dst->eth_saddr));
- rte_ether_addr_copy(&(src->eth_daddr), &(dst->eth_daddr));
+ ASSIGN_COMMON_TCP_KEY((&src->cmn_key), (&dst->cmn_key));
+
dst->ip_src_addr = src->ip_src_addr;
dst->ip_dst_addr = src->ip_dst_addr;
- dst->recv_ack = src->recv_ack;
- dst->src_port = src->src_port;
- dst->dst_port = src->dst_port;
tbl->flows[flow_idx].start_index = item_idx;
tbl->flow_num++;
@@ -173,21 +109,6 @@ insert_new_flow(struct gro_tcp4_tbl *tbl,
return flow_idx;
}
-/*
- * update the packet length for the flushed packet.
- */
-static inline void
-update_header(struct gro_tcp4_item *item)
-{
- struct rte_ipv4_hdr *ipv4_hdr;
- struct rte_mbuf *pkt = item->firstseg;
-
- ipv4_hdr = (struct rte_ipv4_hdr *)(rte_pktmbuf_mtod(pkt, char *) +
- pkt->l2_len);
- ipv4_hdr->total_length = rte_cpu_to_be_16(pkt->pkt_len -
- pkt->l2_len);
-}
-
int32_t
gro_tcp4_reassemble(struct rte_mbuf *pkt,
struct gro_tcp4_tbl *tbl,
@@ -202,9 +123,8 @@ gro_tcp4_reassemble(struct rte_mbuf *pkt,
uint8_t is_atomic;
struct tcp4_flow_key key;
- uint32_t cur_idx, prev_idx, item_idx;
+ uint32_t item_idx;
uint32_t i, max_flow_num, remaining_flow_num;
- int cmp;
uint8_t find;
/*
@@ -239,6 +159,14 @@ gro_tcp4_reassemble(struct rte_mbuf *pkt,
if (tcp_dl <= 0)
return -1;
+ rte_ether_addr_copy(&(eth_hdr->src_addr), &(key.cmn_key.eth_saddr));
+ rte_ether_addr_copy(&(eth_hdr->dst_addr), &(key.cmn_key.eth_daddr));
+ key.ip_src_addr = ipv4_hdr->src_addr;
+ key.ip_dst_addr = ipv4_hdr->dst_addr;
+ key.cmn_key.src_port = tcp_hdr->src_port;
+ key.cmn_key.dst_port = tcp_hdr->dst_port;
+ key.cmn_key.recv_ack = tcp_hdr->recv_ack;
+
/*
* Save IPv4 ID for the packet whose DF bit is 0. For the packet
* whose DF bit is 1, IPv4 ID is ignored.
@@ -246,15 +174,6 @@ gro_tcp4_reassemble(struct rte_mbuf *pkt,
frag_off = rte_be_to_cpu_16(ipv4_hdr->fragment_offset);
is_atomic = (frag_off & RTE_IPV4_HDR_DF_FLAG) == RTE_IPV4_HDR_DF_FLAG;
ip_id = is_atomic ? 0 : rte_be_to_cpu_16(ipv4_hdr->packet_id);
- sent_seq = rte_be_to_cpu_32(tcp_hdr->sent_seq);
-
- rte_ether_addr_copy(&(eth_hdr->src_addr), &(key.eth_saddr));
- rte_ether_addr_copy(&(eth_hdr->dst_addr), &(key.eth_daddr));
- key.ip_src_addr = ipv4_hdr->src_addr;
- key.ip_dst_addr = ipv4_hdr->dst_addr;
- key.src_port = tcp_hdr->src_port;
- key.dst_port = tcp_hdr->dst_port;
- key.recv_ack = tcp_hdr->recv_ack;
/* Search for a matched flow. */
max_flow_num = tbl->max_flow_num;
@@ -270,63 +189,44 @@ gro_tcp4_reassemble(struct rte_mbuf *pkt,
}
}
- /*
- * Fail to find a matched flow. Insert a new flow and store the
- * packet into the flow.
- */
if (find == 0) {
- item_idx = insert_new_item(tbl, pkt, start_time,
- INVALID_ARRAY_INDEX, sent_seq, ip_id,
- is_atomic);
+ sent_seq = rte_be_to_cpu_32(tcp_hdr->sent_seq);
+ item_idx = insert_new_tcp_item(pkt, tbl->items, &tbl->item_num,
+ tbl->max_item_num, start_time,
+ INVALID_ARRAY_INDEX, sent_seq, ip_id,
+ is_atomic);
if (item_idx == INVALID_ARRAY_INDEX)
return -1;
if (insert_new_flow(tbl, &key, item_idx) ==
- INVALID_ARRAY_INDEX) {
+ INVALID_ARRAY_INDEX) {
/*
* Fail to insert a new flow, so delete the
* stored packet.
- */
- delete_item(tbl, item_idx, INVALID_ARRAY_INDEX);
+ */
+ delete_tcp_item(tbl->items, item_idx, &tbl->item_num, INVALID_ARRAY_INDEX);
return -1;
}
return 0;
}
- /*
- * Check all packets in the flow and try to find a neighbor for
- * the input packet.
- */
- cur_idx = tbl->flows[i].start_index;
- prev_idx = cur_idx;
- do {
- cmp = check_seq_option(&(tbl->items[cur_idx]), tcp_hdr,
- sent_seq, ip_id, pkt->l4_len, tcp_dl, 0,
- is_atomic);
- if (cmp) {
- if (merge_two_tcp4_packets(&(tbl->items[cur_idx]),
- pkt, cmp, sent_seq, ip_id, 0))
- return 1;
- /*
- * Fail to merge the two packets, as the packet
- * length is greater than the max value. Store
- * the packet into the flow.
- */
- if (insert_new_item(tbl, pkt, start_time, cur_idx,
- sent_seq, ip_id, is_atomic) ==
- INVALID_ARRAY_INDEX)
- return -1;
- return 0;
- }
- prev_idx = cur_idx;
- cur_idx = tbl->items[cur_idx].next_pkt_idx;
- } while (cur_idx != INVALID_ARRAY_INDEX);
+ return process_tcp_item(pkt, tcp_hdr, tcp_dl, tbl->items, tbl->flows[i].start_index,
+ &tbl->item_num, tbl->max_item_num,
+ ip_id, is_atomic, start_time);
+}
- /* Fail to find a neighbor, so store the packet into the flow. */
- if (insert_new_item(tbl, pkt, start_time, prev_idx, sent_seq,
- ip_id, is_atomic) == INVALID_ARRAY_INDEX)
- return -1;
+/*
+ * update the packet length for the flushed packet.
+ */
+static inline void
+update_header(struct gro_tcp_item *item)
+{
+ struct rte_ipv4_hdr *ipv4_hdr;
+ struct rte_mbuf *pkt = item->firstseg;
- return 0;
+ ipv4_hdr = (struct rte_ipv4_hdr *)(rte_pktmbuf_mtod(pkt, char *) +
+ pkt->l2_len);
+ ipv4_hdr->total_length = rte_cpu_to_be_16(pkt->pkt_len -
+ pkt->l2_len);
}
uint16_t
@@ -353,7 +253,8 @@ gro_tcp4_tbl_timeout_flush(struct gro_tcp4_tbl *tbl,
* Delete the packet and get the next
* packet in the flow.
*/
- j = delete_item(tbl, j, INVALID_ARRAY_INDEX);
+ j = delete_tcp_item(tbl->items, j,
+ &tbl->item_num, INVALID_ARRAY_INDEX);
tbl->flows[i].start_index = j;
if (j == INVALID_ARRAY_INDEX)
tbl->flow_num--;
diff --git a/lib/gro/gro_tcp4.h b/lib/gro/gro_tcp4.h
index 212f97a042..245e5da486 100644
--- a/lib/gro/gro_tcp4.h
+++ b/lib/gro/gro_tcp4.h
@@ -5,32 +5,15 @@
#ifndef _GRO_TCP4_H_
#define _GRO_TCP4_H_
-#include <rte_tcp.h>
+#include "gro_tcp.h"
-#define INVALID_ARRAY_INDEX 0xffffffffUL
#define GRO_TCP4_TBL_MAX_ITEM_NUM (1024UL * 1024UL)
-/*
- * The max length of a IPv4 packet, which includes the length of the L3
- * header, the L4 header and the data payload.
- */
-#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))
-
-/* Header fields representing a TCP/IPv4 flow */
+/* Header fields representing common fields in TCP flow */
struct tcp4_flow_key {
- struct rte_ether_addr eth_saddr;
- struct rte_ether_addr eth_daddr;
+ struct cmn_tcp_key cmn_key;
uint32_t ip_src_addr;
uint32_t ip_dst_addr;
-
- uint32_t recv_ack;
- uint16_t src_port;
- uint16_t dst_port;
};
struct gro_tcp4_flow {
@@ -42,42 +25,12 @@ struct gro_tcp4_flow {
uint32_t start_index;
};
-struct gro_tcp4_item {
- /*
- * The first MBUF segment of the packet. If the value
- * is NULL, it means the item is empty.
- */
- struct rte_mbuf *firstseg;
- /* The last MBUF segment of the packet */
- struct rte_mbuf *lastseg;
- /*
- * 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;
- /*
- * 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;
- /* TCP sequence number of the packet */
- uint32_t sent_seq;
- /* 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;
-};
-
/*
* TCP/IPv4 reassembly table structure.
*/
struct gro_tcp4_tbl {
/* item array */
- struct gro_tcp4_item *items;
+ struct gro_tcp_item *items;
/* flow array */
struct gro_tcp4_flow *flows;
/* current item number */
@@ -186,120 +139,9 @@ uint32_t gro_tcp4_tbl_pkt_count(void *tbl);
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) &&
+ return ((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));
+ is_same_common_tcp_key(&k1.cmn_key, &k2.cmn_key));
}
-/*
- * 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
diff --git a/lib/gro/gro_tcp_internal.h b/lib/gro/gro_tcp_internal.h
new file mode 100644
index 0000000000..cc84abeaeb
--- /dev/null
+++ b/lib/gro/gro_tcp_internal.h
@@ -0,0 +1,128 @@
+
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2023 Intel Corporation
+ */
+
+#ifndef _GRO_TCP_INTERNAL_H_
+#define _GRO_TCP_INTERNAL_H_
+
+static inline uint32_t
+find_an_empty_item(struct gro_tcp_item *items,
+ uint32_t max_item_num)
+{
+ uint32_t i;
+
+ for (i = 0; i < max_item_num; i++)
+ if (items[i].firstseg == NULL)
+ return i;
+ return INVALID_ARRAY_INDEX;
+}
+
+static inline uint32_t
+insert_new_tcp_item(struct rte_mbuf *pkt,
+ struct gro_tcp_item *items,
+ uint32_t *item_num,
+ uint32_t max_item_num,
+ uint64_t start_time,
+ uint32_t prev_idx,
+ uint32_t sent_seq,
+ uint16_t ip_id,
+ uint8_t is_atomic)
+{
+ uint32_t item_idx;
+
+ item_idx = find_an_empty_item(items, max_item_num);
+ if (item_idx == INVALID_ARRAY_INDEX)
+ return INVALID_ARRAY_INDEX;
+
+ items[item_idx].firstseg = pkt;
+ items[item_idx].lastseg = rte_pktmbuf_lastseg(pkt);
+ items[item_idx].start_time = start_time;
+ items[item_idx].next_pkt_idx = INVALID_ARRAY_INDEX;
+ items[item_idx].sent_seq = sent_seq;
+ items[item_idx].l3.ip_id = ip_id;
+ items[item_idx].nb_merged = 1;
+ items[item_idx].is_atomic = is_atomic;
+ (*item_num) += 1;
+
+ /* if the previous packet exists, chain them together. */
+ if (prev_idx != INVALID_ARRAY_INDEX) {
+ items[item_idx].next_pkt_idx =
+ items[prev_idx].next_pkt_idx;
+ items[prev_idx].next_pkt_idx = item_idx;
+ }
+
+ return item_idx;
+}
+
+static inline uint32_t
+delete_tcp_item(struct gro_tcp_item *items, uint32_t item_idx,
+ uint32_t *item_num,
+ uint32_t prev_item_idx)
+{
+ uint32_t next_idx = items[item_idx].next_pkt_idx;
+
+ /* NULL indicates an empty item */
+ items[item_idx].firstseg = NULL;
+ (*item_num) -= 1;
+ if (prev_item_idx != INVALID_ARRAY_INDEX)
+ items[prev_item_idx].next_pkt_idx = next_idx;
+
+ return next_idx;
+}
+
+static inline int32_t
+process_tcp_item(struct rte_mbuf *pkt,
+ struct rte_tcp_hdr *tcp_hdr,
+ int32_t tcp_dl,
+ struct gro_tcp_item *items,
+ uint32_t item_idx,
+ uint32_t *item_num,
+ uint32_t max_item_num,
+ uint16_t ip_id,
+ uint8_t is_atomic,
+ uint64_t start_time)
+{
+ uint32_t cur_idx;
+ uint32_t prev_idx;
+ int cmp;
+ uint32_t sent_seq;
+
+ sent_seq = rte_be_to_cpu_32(tcp_hdr->sent_seq);
+ /*
+ * Check all packets in the flow and try to find a neighbor for
+ * the input packet.
+ */
+ cur_idx = item_idx;
+ prev_idx = cur_idx;
+ do {
+ cmp = check_seq_option(&items[cur_idx], tcp_hdr,
+ sent_seq, ip_id, pkt->l4_len, tcp_dl, 0,
+ is_atomic);
+ if (cmp) {
+ if (merge_two_tcp_packets(&items[cur_idx],
+ pkt, cmp, sent_seq, ip_id, 0))
+ return 1;
+ /*
+ * Fail to merge the two packets, as the packet
+ * length is greater than the max value. Store
+ * the packet into the flow.
+ */
+ if (insert_new_tcp_item(pkt, items, item_num, max_item_num,
+ start_time, cur_idx, sent_seq, ip_id, is_atomic) ==
+ INVALID_ARRAY_INDEX)
+ return -1;
+ return 0;
+ }
+ prev_idx = cur_idx;
+ cur_idx = items[cur_idx].next_pkt_idx;
+ } while (cur_idx != INVALID_ARRAY_INDEX);
+
+ /* Fail to find a neighbor, so store the packet into the flow. */
+ if (insert_new_tcp_item(pkt, items, item_num, max_item_num, start_time, prev_idx, sent_seq,
+ ip_id, is_atomic) == INVALID_ARRAY_INDEX)
+ return -1;
+
+ return 0;
+}
+#endif
diff --git a/lib/gro/gro_vxlan_tcp4.c b/lib/gro/gro_vxlan_tcp4.c
index 3be4deb7c7..6ab7001922 100644
--- a/lib/gro/gro_vxlan_tcp4.c
+++ b/lib/gro/gro_vxlan_tcp4.c
@@ -116,7 +116,7 @@ insert_new_item(struct gro_vxlan_tcp4_tbl *tbl,
tbl->items[item_idx].inner_item.start_time = start_time;
tbl->items[item_idx].inner_item.next_pkt_idx = INVALID_ARRAY_INDEX;
tbl->items[item_idx].inner_item.sent_seq = sent_seq;
- tbl->items[item_idx].inner_item.ip_id = ip_id;
+ tbl->items[item_idx].inner_item.l3.ip_id = ip_id;
tbl->items[item_idx].inner_item.nb_merged = 1;
tbl->items[item_idx].inner_item.is_atomic = is_atomic;
tbl->items[item_idx].outer_ip_id = outer_ip_id;
@@ -163,15 +163,9 @@ insert_new_flow(struct gro_vxlan_tcp4_tbl *tbl,
dst = &(tbl->flows[flow_idx].key);
- rte_ether_addr_copy(&(src->inner_key.eth_saddr),
- &(dst->inner_key.eth_saddr));
- rte_ether_addr_copy(&(src->inner_key.eth_daddr),
- &(dst->inner_key.eth_daddr));
+ ASSIGN_COMMON_TCP_KEY((&(src->inner_key.cmn_key)), (&(dst->inner_key.cmn_key)));
dst->inner_key.ip_src_addr = src->inner_key.ip_src_addr;
dst->inner_key.ip_dst_addr = src->inner_key.ip_dst_addr;
- dst->inner_key.recv_ack = src->inner_key.recv_ack;
- dst->inner_key.src_port = src->inner_key.src_port;
- dst->inner_key.dst_port = src->inner_key.dst_port;
dst->vxlan_hdr.vx_flags = src->vxlan_hdr.vx_flags;
dst->vxlan_hdr.vx_vni = src->vxlan_hdr.vx_vni;
@@ -248,7 +242,7 @@ merge_two_vxlan_tcp4_packets(struct gro_vxlan_tcp4_item *item,
uint16_t outer_ip_id,
uint16_t ip_id)
{
- if (merge_two_tcp4_packets(&item->inner_item, pkt, cmp, sent_seq,
+ if (merge_two_tcp_packets(&item->inner_item, pkt, cmp, sent_seq,
ip_id, pkt->outer_l2_len +
pkt->outer_l3_len)) {
/* Update the outer IPv4 ID to the large value. */
@@ -357,13 +351,13 @@ gro_vxlan_tcp4_reassemble(struct rte_mbuf *pkt,
sent_seq = rte_be_to_cpu_32(tcp_hdr->sent_seq);
- rte_ether_addr_copy(&(eth_hdr->src_addr), &(key.inner_key.eth_saddr));
- rte_ether_addr_copy(&(eth_hdr->dst_addr), &(key.inner_key.eth_daddr));
+ rte_ether_addr_copy(&(eth_hdr->src_addr), &(key.inner_key.cmn_key.eth_saddr));
+ rte_ether_addr_copy(&(eth_hdr->dst_addr), &(key.inner_key.cmn_key.eth_daddr));
key.inner_key.ip_src_addr = ipv4_hdr->src_addr;
key.inner_key.ip_dst_addr = ipv4_hdr->dst_addr;
- key.inner_key.recv_ack = tcp_hdr->recv_ack;
- key.inner_key.src_port = tcp_hdr->src_port;
- key.inner_key.dst_port = tcp_hdr->dst_port;
+ key.inner_key.cmn_key.recv_ack = tcp_hdr->recv_ack;
+ key.inner_key.cmn_key.src_port = tcp_hdr->src_port;
+ key.inner_key.cmn_key.dst_port = tcp_hdr->dst_port;
key.vxlan_hdr.vx_flags = vxlan_hdr->vx_flags;
key.vxlan_hdr.vx_vni = vxlan_hdr->vx_vni;
diff --git a/lib/gro/gro_vxlan_tcp4.h b/lib/gro/gro_vxlan_tcp4.h
index 7832942a68..662db01a88 100644
--- a/lib/gro/gro_vxlan_tcp4.h
+++ b/lib/gro/gro_vxlan_tcp4.h
@@ -36,7 +36,7 @@ struct gro_vxlan_tcp4_flow {
};
struct gro_vxlan_tcp4_item {
- struct gro_tcp4_item inner_item;
+ struct gro_tcp_item inner_item;
/* IPv4 ID in the outer IPv4 header */
uint16_t outer_ip_id;
/* Indicate if outer IPv4 ID can be ignored */
diff --git a/lib/gro/rte_gro.c b/lib/gro/rte_gro.c
index e35399fd42..ac3d1cdc94 100644
--- a/lib/gro/rte_gro.c
+++ b/lib/gro/rte_gro.c
@@ -147,7 +147,7 @@ rte_gro_reassemble_burst(struct rte_mbuf **pkts,
/* allocate a reassembly table for TCP/IPv4 GRO */
struct gro_tcp4_tbl tcp_tbl;
struct gro_tcp4_flow tcp_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
- struct gro_tcp4_item tcp_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {{0} };
+ struct gro_tcp_item tcp_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {{0} };
/* allocate a reassembly table for UDP/IPv4 GRO */
struct gro_udp4_tbl udp_tbl;
--
2.25.1
next prev parent reply other threads:[~2023-06-21 8:38 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-20 18:07 [PATCH] gro : ipv6 changes to support GRO for TCP/ipv6 Kumara Parameshwaran
2022-10-20 18:14 ` [PATCH v2] " Kumara Parameshwaran
2023-05-12 2:47 ` Hu, Jiayu
2023-05-16 9:28 ` kumaraparameshwaran rathinavel
2023-05-25 11:22 ` kumaraparameshwaran rathinavel
2023-05-31 8:20 ` Hu, Jiayu
2023-06-02 6:02 ` [PATCH v3] gro : ipv6-gro review comments to reduce code duplication across v4 and v6 Kumara Parameshwaran
2023-06-02 6:34 ` [PATCH v3] gro : ipv6 changes to support GRO for TCP/ipv6 Kumara Parameshwaran
2023-06-06 4:35 ` Hu, Jiayu
2023-06-06 9:31 ` kumaraparameshwaran rathinavel
2023-06-06 14:58 ` [PATCH v4] " Kumara Parameshwaran
2023-06-08 4:05 ` Hu, Jiayu
2023-06-08 16:52 ` kumaraparameshwaran rathinavel
2023-06-09 1:04 ` Hu, Jiayu
2023-06-12 11:05 ` [PATCH v5] " Kumara Parameshwaran
2023-06-12 11:23 ` [PATCH v6] " Kumara Parameshwaran
2023-06-12 11:31 ` [PATCH v7] " Kumara Parameshwaran
2023-06-12 12:04 ` kumaraparameshwaran rathinavel
2023-06-13 2:25 ` Hu, Jiayu
2023-06-14 3:43 ` kumaraparameshwaran rathinavel
2023-06-14 4:56 ` Hu, Jiayu
2023-06-15 5:40 ` [PATCH v8] " Kumara Parameshwaran
2023-06-15 6:20 ` [PATCH v9] " Kumara Parameshwaran
2023-06-15 6:30 ` kumaraparameshwaran rathinavel
2023-06-15 8:01 ` Hu, Jiayu
2023-06-15 9:16 ` kumaraparameshwaran rathinavel
2023-06-19 13:30 ` Thomas Monjalon
2023-06-21 8:25 ` [PATCH v10 1/2] gro : refactor IPv4 to add GRO support for IPv6 Kumara Parameshwaran
2023-06-21 8:25 ` [PATCH v10 2/2] gro : add support for IPv6 GRO Kumara Parameshwaran
2023-06-21 8:38 ` Kumara Parameshwaran [this message]
2023-06-21 8:38 ` [PATCH v11 " Kumara Parameshwaran
2023-06-27 15:47 ` Thomas Monjalon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230621083836.63060-1-kumaraparamesh92@gmail.com \
--to=kumaraparamesh92@gmail.com \
--cc=dev@dpdk.org \
--cc=jiayu.hu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).