From: Jeff Guo <jia.guo@intel.com>
To: jingjing.wu@intel.com, qi.z.zhang@intel.com,
beilei.xing@intel.com, haiyue.wang@intel.com,
qiming.yang@intel.com
Cc: dev@dpdk.org, ferruh.yigit@intel.com, mb@smartsharesystems.com,
stephen@networkplumber.org, barbette@kth.se,
Feifei.wang2@arm.com, bruce.richardson@intel.com,
jia.guo@intel.com, helin.zhang@intel.com
Subject: [dpdk-dev] [PATCH v5 2/5] net/i40e: fix vector rx burst for i40e
Date: Fri, 16 Oct 2020 17:44:28 +0800 [thread overview]
Message-ID: <20201016094431.96889-3-jia.guo@intel.com> (raw)
In-Reply-To: <20201016094431.96889-1-jia.guo@intel.com>
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.
Bugzilla ID: 516
Fixes: 5b463eda8d26 ("net/i40e: make vector driver filenames consistent")
Fixes: ae0eb310f253 ("net/i40e: implement vector PMD for ARM")
Fixes: c3def6a8724c ("net/i40e: implement vector PMD for altivec")
Signed-off-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
---
drivers/net/i40e/i40e_rxtx_vec_altivec.c | 59 +++++++++++++++++-------
drivers/net/i40e/i40e_rxtx_vec_neon.c | 48 ++++++++++++++-----
drivers/net/i40e/i40e_rxtx_vec_sse.c | 48 ++++++++++++++-----
3 files changed, 114 insertions(+), 41 deletions(-)
diff --git a/drivers/net/i40e/i40e_rxtx_vec_altivec.c b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
index 6862a017e1..d3238bfb6a 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);
@@ -459,15 +458,15 @@ 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 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(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 +499,32 @@ 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_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index 543ecadb07..f094de69ae 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);
@@ -439,15 +437,15 @@ 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
+/**
+ * vPMD receive routine that reassembles single burst of 32 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)
+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 +480,32 @@ 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 240ce478ab..4b2b6a28fc 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);
@@ -605,15 +603,15 @@ 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
+/**
+ * vPMD receive routine that reassembles single burst of 32 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)
+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 +646,32 @@ 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
next prev parent reply other threads:[~2020-10-16 9:51 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-27 7:54 [dpdk-dev] [PATCH v1 0/4] maximize vector rx burst for PMDs Jeff Guo
2020-08-27 7:54 ` [dpdk-dev] [PATCH v1 1/4] net/ixgbe: maximize vector rx burst for ixgbe Jeff Guo
2020-08-27 7:54 ` [dpdk-dev] [PATCH v1 2/4] net/i40e: maximize vector rx burst for i40e Jeff Guo
2020-08-27 7:54 ` [dpdk-dev] [PATCH v1 3/4] net/ice: maximize vector rx burst for ice Jeff Guo
2020-08-27 7:54 ` [dpdk-dev] [PATCH v1 4/4] net/iavf: maximize vector rx burst for iavf Jeff Guo
2020-08-27 8:40 ` [dpdk-dev] [RFC] ethdev: rte_eth_rx_burst() requirements for nb_pkts Morten Brørup
2020-08-27 9:09 ` Bruce Richardson
2020-08-27 9:31 ` Morten Brørup
2020-08-27 9:43 ` Bruce Richardson
2020-08-27 10:13 ` [dpdk-dev] [RFC] ethdev: rte_eth_rx_burst() requirements fornb_pkts Morten Brørup
2020-08-27 11:41 ` Bruce Richardson
2020-08-28 9:03 ` Morten Brørup
2020-08-28 10:07 ` Bruce Richardson
2020-08-28 10:50 ` Morten Brørup
2020-08-29 10:15 ` Morten Brørup
2020-09-09 6:36 ` [dpdk-dev] [PATCH v3 0/5] fix vector rx burst for PMDs Jeff Guo
2020-09-09 6:36 ` [dpdk-dev] [PATCH v3 1/5] net/iavf: fix vector rx burst for iavf Jeff Guo
2020-09-09 6:36 ` [dpdk-dev] [PATCH v3 2/5] net/ixgbe: fix vector rx burst for ixgbe Jeff Guo
[not found] ` <VI1PR0802MB23518C6B517B6EAD8E018CD49E260@VI1PR0802MB2351.eurprd08.prod.outlook.com>
2020-09-09 9:54 ` [dpdk-dev] 回复: " Feifei Wang
2020-09-09 6:36 ` [dpdk-dev] [PATCH v3 3/5] net/i40e: fix vector rx burst for i40e Jeff Guo
2020-09-09 6:36 ` [dpdk-dev] [PATCH v3 4/5] net/ice: fix vector rx burst for ice Jeff Guo
2020-09-15 7:10 ` Han, YingyaX
2020-09-09 6:36 ` [dpdk-dev] [PATCH v3 5/5] net/fm10k: fix vector rx burst for fm10k Jeff Guo
2020-09-09 6:45 ` [dpdk-dev] [PATCH v3 0/5] fix vector rx burst for PMDs Wang, Haiyue
2020-09-09 7:03 ` Guo, Jia
2020-09-09 7:05 ` Wang, Haiyue
2020-09-09 7:43 ` Morten Brørup
2020-09-09 7:55 ` Wang, Haiyue
2020-09-09 8:01 ` Guo, Jia
2020-09-17 7:58 ` [dpdk-dev] [PATCH v4 " Jeff Guo
2020-09-17 7:58 ` [dpdk-dev] [PATCH v4 1/5] net/iavf: fix vector rx burst for iavf Jeff Guo
2020-09-17 7:58 ` [dpdk-dev] [PATCH v4 2/5] net/ixgbe: fix vector rx burst for ixgbe Jeff Guo
2020-09-17 7:58 ` [dpdk-dev] [PATCH v4 3/5] net/i40e: fix vector rx burst for i40e Jeff Guo
2020-09-17 7:58 ` [dpdk-dev] [PATCH v4 4/5] net/ice: fix vector rx burst for ice Jeff Guo
2020-09-17 11:03 ` Zhang, Qi Z
2020-09-18 3:20 ` Guo, Jia
2020-09-18 3:41 ` Zhang, Qi Z
2020-09-18 4:41 ` Guo, Jia
2020-09-18 5:39 ` Zhang, Qi Z
2020-09-17 7:58 ` [dpdk-dev] [PATCH v4 5/5] net/fm10k: fix vector rx burst for fm10k Jeff Guo
2020-10-16 9:44 ` [dpdk-dev] [PATCH v5 0/5] fix vector rx burst for PMDs Jeff Guo
2020-10-16 9:44 ` [dpdk-dev] [PATCH v5 1/5] net/ixgbe: fix vector rx burst for ixgbe Jeff Guo
2020-10-16 9:44 ` Jeff Guo [this message]
2020-10-16 9:44 ` [dpdk-dev] [PATCH v5 3/5] net/ice: fix vector rx burst for ice Jeff Guo
2020-10-16 9:44 ` [dpdk-dev] [PATCH v5 4/5] net/fm10k: fix vector rx burst for fm10k Jeff Guo
2020-10-16 9:44 ` [dpdk-dev] [PATCH v5 5/5] net/iavf: fix vector rx burst for iavf Jeff Guo
2020-10-23 5:09 ` Ling, WeiX
2020-10-23 10:11 ` [dpdk-dev] [PATCH v5 0/5] fix vector rx burst for PMDs Zhang, Qi Z
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=20201016094431.96889-3-jia.guo@intel.com \
--to=jia.guo@intel.com \
--cc=Feifei.wang2@arm.com \
--cc=barbette@kth.se \
--cc=beilei.xing@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=haiyue.wang@intel.com \
--cc=helin.zhang@intel.com \
--cc=jingjing.wu@intel.com \
--cc=mb@smartsharesystems.com \
--cc=qi.z.zhang@intel.com \
--cc=qiming.yang@intel.com \
--cc=stephen@networkplumber.org \
/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).