aboutsummaryrefslogtreecommitdiffstats
path: root/examples/l3fwd/l3fwd_sse.h
diff options
context:
space:
mode:
Diffstat (limited to 'examples/l3fwd/l3fwd_sse.h')
-rw-r--r--examples/l3fwd/l3fwd_sse.h261
1 files changed, 8 insertions, 253 deletions
diff --git a/examples/l3fwd/l3fwd_sse.h b/examples/l3fwd/l3fwd_sse.h
index 1afa1f00..831760f0 100644
--- a/examples/l3fwd/l3fwd_sse.h
+++ b/examples/l3fwd/l3fwd_sse.h
@@ -32,53 +32,11 @@
*/
-#ifndef _L3FWD_COMMON_H_
-#define _L3FWD_COMMON_H_
+#ifndef _L3FWD_SSE_H_
+#define _L3FWD_SSE_H_
#include "l3fwd.h"
-
-#ifdef DO_RFC_1812_CHECKS
-
-#define IPV4_MIN_VER_IHL 0x45
-#define IPV4_MAX_VER_IHL 0x4f
-#define IPV4_MAX_VER_IHL_DIFF (IPV4_MAX_VER_IHL - IPV4_MIN_VER_IHL)
-
-/* Minimum value of IPV4 total length (20B) in network byte order. */
-#define IPV4_MIN_LEN_BE (sizeof(struct ipv4_hdr) << 8)
-
-/*
- * From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2:
- * - The IP version number must be 4.
- * - The IP header length field must be large enough to hold the
- * minimum length legal IP datagram (20 bytes = 5 words).
- * - The IP total length field must be large enough to hold the IP
- * datagram header, whose length is specified in the IP header length
- * field.
- * If we encounter invalid IPV4 packet, then set destination port for it
- * to BAD_PORT value.
- */
-static inline __attribute__((always_inline)) void
-rfc1812_process(struct ipv4_hdr *ipv4_hdr, uint16_t *dp, uint32_t ptype)
-{
- uint8_t ihl;
-
- if (RTE_ETH_IS_IPV4_HDR(ptype)) {
- ihl = ipv4_hdr->version_ihl - IPV4_MIN_VER_IHL;
-
- ipv4_hdr->time_to_live--;
- ipv4_hdr->hdr_checksum++;
-
- if (ihl > IPV4_MAX_VER_IHL_DIFF ||
- ((uint8_t)ipv4_hdr->total_length == 0 &&
- ipv4_hdr->total_length < IPV4_MIN_LEN_BE))
- dp[0] = BAD_PORT;
-
- }
-}
-
-#else
-#define rfc1812_process(mb, dp, ptype) do { } while (0)
-#endif /* DO_RFC_1812_CHECKS */
+#include "l3fwd_common.h"
/*
* Update source and destination MAC addresses in the ethernet header.
@@ -130,143 +88,16 @@ processx4_step3(struct rte_mbuf *pkt[FWDSTEP], uint16_t dst_port[FWDSTEP])
}
/*
- * We group consecutive packets with the same destionation port into one burst.
- * To avoid extra latency this is done together with some other packet
- * processing, but after we made a final decision about packet's destination.
- * To do this we maintain:
- * pnum - array of number of consecutive packets with the same dest port for
- * each packet in the input burst.
- * lp - pointer to the last updated element in the pnum.
- * dlp - dest port value lp corresponds to.
- */
-
-#define GRPSZ (1 << FWDSTEP)
-#define GRPMSK (GRPSZ - 1)
-
-#define GROUP_PORT_STEP(dlp, dcp, lp, pn, idx) do { \
- if (likely((dlp) == (dcp)[(idx)])) { \
- (lp)[0]++; \
- } else { \
- (dlp) = (dcp)[idx]; \
- (lp) = (pn) + (idx); \
- (lp)[0] = 1; \
- } \
-} while (0)
-
-/*
* Group consecutive packets with the same destination port in bursts of 4.
* Suppose we have array of destionation ports:
* dst_port[] = {a, b, c, d,, e, ... }
* dp1 should contain: <a, b, c, d>, dp2: <b, c, d, e>.
- * We doing 4 comparisions at once and the result is 4 bit mask.
+ * We doing 4 comparisons at once and the result is 4 bit mask.
* This mask is used as an index into prebuild array of pnum values.
*/
static inline uint16_t *
port_groupx4(uint16_t pn[FWDSTEP + 1], uint16_t *lp, __m128i dp1, __m128i dp2)
{
- static const struct {
- uint64_t pnum; /* prebuild 4 values for pnum[]. */
- int32_t idx; /* index for new last updated elemnet. */
- uint16_t lpv; /* add value to the last updated element. */
- } gptbl[GRPSZ] = {
- {
- /* 0: a != b, b != c, c != d, d != e */
- .pnum = UINT64_C(0x0001000100010001),
- .idx = 4,
- .lpv = 0,
- },
- {
- /* 1: a == b, b != c, c != d, d != e */
- .pnum = UINT64_C(0x0001000100010002),
- .idx = 4,
- .lpv = 1,
- },
- {
- /* 2: a != b, b == c, c != d, d != e */
- .pnum = UINT64_C(0x0001000100020001),
- .idx = 4,
- .lpv = 0,
- },
- {
- /* 3: a == b, b == c, c != d, d != e */
- .pnum = UINT64_C(0x0001000100020003),
- .idx = 4,
- .lpv = 2,
- },
- {
- /* 4: a != b, b != c, c == d, d != e */
- .pnum = UINT64_C(0x0001000200010001),
- .idx = 4,
- .lpv = 0,
- },
- {
- /* 5: a == b, b != c, c == d, d != e */
- .pnum = UINT64_C(0x0001000200010002),
- .idx = 4,
- .lpv = 1,
- },
- {
- /* 6: a != b, b == c, c == d, d != e */
- .pnum = UINT64_C(0x0001000200030001),
- .idx = 4,
- .lpv = 0,
- },
- {
- /* 7: a == b, b == c, c == d, d != e */
- .pnum = UINT64_C(0x0001000200030004),
- .idx = 4,
- .lpv = 3,
- },
- {
- /* 8: a != b, b != c, c != d, d == e */
- .pnum = UINT64_C(0x0002000100010001),
- .idx = 3,
- .lpv = 0,
- },
- {
- /* 9: a == b, b != c, c != d, d == e */
- .pnum = UINT64_C(0x0002000100010002),
- .idx = 3,
- .lpv = 1,
- },
- {
- /* 0xa: a != b, b == c, c != d, d == e */
- .pnum = UINT64_C(0x0002000100020001),
- .idx = 3,
- .lpv = 0,
- },
- {
- /* 0xb: a == b, b == c, c != d, d == e */
- .pnum = UINT64_C(0x0002000100020003),
- .idx = 3,
- .lpv = 2,
- },
- {
- /* 0xc: a != b, b != c, c == d, d == e */
- .pnum = UINT64_C(0x0002000300010001),
- .idx = 2,
- .lpv = 0,
- },
- {
- /* 0xd: a == b, b != c, c == d, d == e */
- .pnum = UINT64_C(0x0002000300010002),
- .idx = 2,
- .lpv = 1,
- },
- {
- /* 0xe: a != b, b == c, c == d, d == e */
- .pnum = UINT64_C(0x0002000300040001),
- .idx = 1,
- .lpv = 0,
- },
- {
- /* 0xf: a == b, b == c, c == d, d == e */
- .pnum = UINT64_C(0x0002000300040005),
- .idx = 0,
- .lpv = 4,
- },
- };
-
union {
uint16_t u16[FWDSTEP + 1];
uint64_t u64;
@@ -314,88 +145,10 @@ process_packet(struct rte_mbuf *pkt, uint16_t *dst_port)
_mm_storeu_si128((__m128i *)eth_hdr, te);
}
-static inline __attribute__((always_inline)) void
-send_packetsx4(struct lcore_conf *qconf, uint8_t port, struct rte_mbuf *m[],
- uint32_t num)
-{
- uint32_t len, j, n;
-
- len = qconf->tx_mbufs[port].len;
-
- /*
- * If TX buffer for that queue is empty, and we have enough packets,
- * then send them straightway.
- */
- if (num >= MAX_TX_BURST && len == 0) {
- n = rte_eth_tx_burst(port, qconf->tx_queue_id[port], m, num);
- if (unlikely(n < num)) {
- do {
- rte_pktmbuf_free(m[n]);
- } while (++n < num);
- }
- return;
- }
-
- /*
- * Put packets into TX buffer for that queue.
- */
-
- n = len + num;
- n = (n > MAX_PKT_BURST) ? MAX_PKT_BURST - len : num;
-
- j = 0;
- switch (n % FWDSTEP) {
- while (j < n) {
- case 0:
- qconf->tx_mbufs[port].m_table[len + j] = m[j];
- j++;
- case 3:
- qconf->tx_mbufs[port].m_table[len + j] = m[j];
- j++;
- case 2:
- qconf->tx_mbufs[port].m_table[len + j] = m[j];
- j++;
- case 1:
- qconf->tx_mbufs[port].m_table[len + j] = m[j];
- j++;
- }
- }
-
- len += n;
-
- /* enough pkts to be sent */
- if (unlikely(len == MAX_PKT_BURST)) {
-
- send_burst(qconf, MAX_PKT_BURST, port);
-
- /* copy rest of the packets into the TX buffer. */
- len = num - n;
- j = 0;
- switch (len % FWDSTEP) {
- while (j < len) {
- case 0:
- qconf->tx_mbufs[port].m_table[j] = m[n + j];
- j++;
- case 3:
- qconf->tx_mbufs[port].m_table[j] = m[n + j];
- j++;
- case 2:
- qconf->tx_mbufs[port].m_table[j] = m[n + j];
- j++;
- case 1:
- qconf->tx_mbufs[port].m_table[j] = m[n + j];
- j++;
- }
- }
- }
-
- qconf->tx_mbufs[port].len = len;
-}
-
/**
* Send packets burst from pkts_burst to the ports in dst_port array
*/
-static inline __attribute__((always_inline)) void
+static __rte_always_inline void
send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst,
uint16_t dst_port[MAX_PKT_BURST], int nb_rx)
{
@@ -464,10 +217,12 @@ send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst,
process_packet(pkts_burst[j], dst_port + j);
GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
j++;
+ /* fall-through */
case 2:
process_packet(pkts_burst[j], dst_port + j);
GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
j++;
+ /* fall-through */
case 1:
process_packet(pkts_burst[j], dst_port + j);
GROUP_PORT_STEP(dlp, dst_port, lp, pnum, j);
@@ -498,4 +253,4 @@ send_packets_multi(struct lcore_conf *qconf, struct rte_mbuf **pkts_burst,
}
}
-#endif /* _L3FWD_COMMON_H_ */
+#endif /* _L3FWD_SSE_H_ */