The limitation of burst size in vector rx was removed, since it should
retrieve as much received packets as possible. And also the scattered
receive path should use a wrapper function to achieve the goal of
burst maximizing.
Signed-off-by: Jeff Guo <jia....@intel.com>
---
drivers/net/i40e/i40e_rxtx_vec_altivec.c | 61 +++++++++++++++---------
drivers/net/i40e/i40e_rxtx_vec_avx2.c | 13 +----
drivers/net/i40e/i40e_rxtx_vec_neon.c | 55 +++++++++++++--------
drivers/net/i40e/i40e_rxtx_vec_sse.c | 55 +++++++++++++--------
4 files changed, 111 insertions(+), 73 deletions(-)
diff --git a/drivers/net/i40e/i40e_rxtx_vec_altivec.c
b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
index 6862a017e..2eb45d5a5 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_altivec.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
@@ -188,11 +188,13 @@ desc_to_ptype_v(vector unsigned long descs[4], struct
rte_mbuf **rx_pkts,
ptype_tbl[(*(vector unsigned char *)&ptype1)[8]];
}
- /* Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
- */
+/**
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_I40E_DESCS_PER_LOOP)
+ *
+ * Notice:
+ * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
+ * - floor align nb_pkts to a RTE_I40E_DESCS_PER_LOOP power-of-two
+ */
static inline uint16_t
_recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts, uint8_t *split_packet)
@@ -214,9 +216,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
};
vector unsigned long dd_check, eop_check;
- /* nb_pkts shall be less equal than RTE_I40E_MAX_RX_BURST */
- nb_pkts = RTE_MIN(nb_pkts, RTE_I40E_MAX_RX_BURST);
-
/* nb_pkts has to be floor-aligned to RTE_I40E_DESCS_PER_LOOP */
nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_I40E_DESCS_PER_LOOP);
@@ -447,11 +446,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
return nb_pkts_recd;
}
- /* Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
- */
uint16_t
i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts)
@@ -459,15 +453,12 @@ i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf
**rx_pkts,
return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
}
- /* vPMD receive routine that reassembles scattered packets
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
- */
-uint16_t
-i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+/**
+ * vPMD receive routine that reassembles scattered packets
+ */
+static uint16_t
+i40e_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
{
struct i40e_rx_queue *rxq = rx_queue;
uint8_t split_flags[RTE_I40E_VPMD_RX_BURST] = {0};
@@ -500,6 +491,32 @@ i40e_recv_scattered_pkts_vec(void *rx_queue, struct
rte_mbuf **rx_pkts,
&split_flags[i]);
}
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > RTE_I40E_VPMD_RX_BURST) {
+ uint16_t burst;
+
+ burst = i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ RTE_I40E_VPMD_RX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < RTE_I40E_VPMD_RX_BURST)
+ return retval;
+ }
+
+ return retval + i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ nb_pkts);
+}
+
static inline void
vtx1(volatile struct i40e_tx_desc *txdp,
struct rte_mbuf *pkt, uint64_t flags)
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
index 3bcef1363..690d3d2ba 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
@@ -729,10 +729,6 @@ _recv_raw_pkts_vec_avx2(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
return received;
}
-/*
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- */
uint16_t
i40e_recv_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts)
@@ -740,10 +736,8 @@ i40e_recv_pkts_vec_avx2(void *rx_queue, struct rte_mbuf
**rx_pkts,
return _recv_raw_pkts_vec_avx2(rx_queue, rx_pkts, nb_pkts, NULL);
}
-/*
+/**
* vPMD receive routine that reassembles single burst of 32 scattered packets
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
*/
static uint16_t
i40e_recv_scattered_burst_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
@@ -781,11 +775,8 @@ i40e_recv_scattered_burst_vec_avx2(void *rx_queue, struct
rte_mbuf **rx_pkts,
&split_flags[i]);
}
-/*
+/**
* vPMD receive routine that reassembles scattered packets.
- * Main receive routine that can handle arbitrary burst sizes
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
*/
uint16_t
i40e_recv_scattered_pkts_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts,
diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c
b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index 6f874e45b..68558826c 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -187,11 +187,12 @@ desc_to_ptype_v(uint64x2_t descs[4], struct rte_mbuf
**__rte_restrict rx_pkts,
}
- /*
+/**
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_I40E_DESCS_PER_LOOP)
+ *
* Notice:
* - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
+ * - floor align nb_pkts to a RTE_I40E_DESCS_PER_LOOP power-of-two
*/
static inline uint16_t
_recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict rxq,
@@ -230,9 +231,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict rxq,
0, 0, 0 /* ignore non-length fields */
};
- /* nb_pkts shall be less equal than RTE_I40E_MAX_RX_BURST */
- nb_pkts = RTE_MIN(nb_pkts, RTE_I40E_MAX_RX_BURST);
-
/* nb_pkts has to be floor-aligned to RTE_I40E_DESCS_PER_LOOP */
nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_I40E_DESCS_PER_LOOP);
@@ -426,12 +424,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *__rte_restrict
rxq,
return nb_pkts_recd;
}
- /*
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
- */
uint16_t
i40e_recv_pkts_vec(void *__rte_restrict rx_queue,
struct rte_mbuf **__rte_restrict rx_pkts, uint16_t nb_pkts)
@@ -439,15 +431,12 @@ i40e_recv_pkts_vec(void *__rte_restrict rx_queue,
return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
}
- /* vPMD receive routine that reassembles scattered packets
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
+/**
+ * vPMD receive routine that reassembles scattered packets
*/
-uint16_t
-i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+static uint16_t
+i40e_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
{
struct i40e_rx_queue *rxq = rx_queue;
@@ -482,6 +471,32 @@ i40e_recv_scattered_pkts_vec(void *rx_queue, struct
rte_mbuf **rx_pkts,
&split_flags[i]);
}
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > RTE_I40E_VPMD_RX_BURST) {
+ uint16_t burst;
+
+ burst = i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ RTE_I40E_VPMD_RX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < RTE_I40E_VPMD_RX_BURST)
+ return retval;
+ }
+
+ return retval + i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ nb_pkts);
+}
+
static inline void
vtx1(volatile struct i40e_tx_desc *txdp,
struct rte_mbuf *pkt, uint64_t flags)
diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c
b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index 698518349..d785a495c 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c
@@ -342,11 +342,12 @@ desc_to_ptype_v(__m128i descs[4], struct rte_mbuf
**rx_pkts,
rx_pkts[3]->packet_type = ptype_tbl[_mm_extract_epi8(ptype1, 8)];
}
- /*
+/**
+ * vPMD raw receive routine, only accept(nb_pkts >= RTE_I40E_DESCS_PER_LOOP)
+ *
* Notice:
* - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
+ * - floor align nb_pkts to a RTE_I40E_DESCS_PER_LOOP power-of-two
*/
static inline uint16_t
_recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
@@ -378,9 +379,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
__m128i dd_check, eop_check;
- /* nb_pkts shall be less equal than RTE_I40E_MAX_RX_BURST */
- nb_pkts = RTE_MIN(nb_pkts, RTE_I40E_MAX_RX_BURST);
-
/* nb_pkts has to be floor-aligned to RTE_I40E_DESCS_PER_LOOP */
nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_I40E_DESCS_PER_LOOP);
@@ -592,12 +590,6 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
return nb_pkts_recd;
}
- /*
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
- */
uint16_t
i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts)
@@ -605,15 +597,12 @@ i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf
**rx_pkts,
return _recv_raw_pkts_vec(rx_queue, rx_pkts, nb_pkts, NULL);
}
- /* vPMD receive routine that reassembles scattered packets
- * Notice:
- * - nb_pkts < RTE_I40E_DESCS_PER_LOOP, just return no packet
- * - nb_pkts > RTE_I40E_VPMD_RX_BURST, only scan RTE_I40E_VPMD_RX_BURST
- * numbers of DD bits
+/**
+ * vPMD receive routine that reassembles scattered packets
*/
-uint16_t
-i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
- uint16_t nb_pkts)
+static uint16_t
+i40e_recv_scattered_burst_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
{
struct i40e_rx_queue *rxq = rx_queue;
@@ -648,6 +637,32 @@ i40e_recv_scattered_pkts_vec(void *rx_queue, struct
rte_mbuf **rx_pkts,
&split_flags[i]);
}
+/**
+ * vPMD receive routine that reassembles scattered packets.
+ */
+uint16_t
+i40e_recv_scattered_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts)
+{
+ uint16_t retval = 0;
+
+ while (nb_pkts > RTE_I40E_VPMD_RX_BURST) {
+ uint16_t burst;
+
+ burst = i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ RTE_I40E_VPMD_RX_BURST);
+ retval += burst;
+ nb_pkts -= burst;
+ if (burst < RTE_I40E_VPMD_RX_BURST)
+ return retval;
+ }
+
+ return retval + i40e_recv_scattered_burst_vec(rx_queue,
+ rx_pkts + retval,
+ nb_pkts);
+}
+
static inline void
vtx1(volatile struct i40e_tx_desc *txdp,
struct rte_mbuf *pkt, uint64_t flags)
--
2.20.1
