* [dpdk-dev] [PATCH v1 1/4] net/ixgbe: add VLAN stripping support for Arm
2020-11-18 6:29 [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Feifei Wang
@ 2020-11-18 6:29 ` Feifei Wang
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 2/4] net/ixgbe: support checksum flags for NEON vector Feifei Wang
` (3 subsequent siblings)
4 siblings, 0 replies; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 6:29 UTC (permalink / raw)
To: Jerin Jacob, Ruifeng Wang, Jeff Guo, Haiyue Wang; +Cc: dev, nd, Feifei Wang
Implemented PKT_RX_VLAN_STRIPPED for vector PMD on Arm platform.
Test Results:
NICs: 82599(igb)
Dirver: ixgbe(vector)
Packet: vlan-id=1
$:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i --port-topology=chained \
to enable vlan stripping: --enable-hw-vlan-strip
test-pmd> set fwd rxonly
test-pmd> set verbose 1
test-pmd> start
With this patch:
%enable vlan stripping:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1 - VLAN tci=0x1
ol_flags: PKT_RX_VLAN PKT_RX_VLAN_STRIPPED
%disable vlan stripping:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x8100 - length=74 - nb_segs=1 - VLAN tci=0x0
ol_flags: PKT_RX_VLAN
_________________________
Without this patch:
%enable vlan stripping:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1 - VLAN tci=0x1
ol_flags: PKT_RX_VLAN
%disable vlan stripping:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x8100 - length=74 - nb_segs=1 - VLAN tci=0x0
ol_flags: PKT_RX_VLAN
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 36 ++++++++++++++++---------
1 file changed, 23 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index 4c81ae9dc..e6d877af9 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -81,11 +81,9 @@ ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, rx_id);
}
-#define VTAG_SHIFT (3)
-
static inline void
desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
- uint8x16_t staterr, struct rte_mbuf **rx_pkts)
+ uint8x16_t staterr, uint8_t vlan_flags, struct rte_mbuf **rx_pkts)
{
uint8x16_t ptype;
uint8x16_t vtag;
@@ -95,13 +93,6 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
uint32_t word;
} vol;
- const uint8x16_t pkttype_msk = {
- PKT_RX_VLAN, PKT_RX_VLAN,
- PKT_RX_VLAN, PKT_RX_VLAN,
- 0x00, 0x00, 0x00, 0x00,
- 0x00, 0x00, 0x00, 0x00,
- 0x00, 0x00, 0x00, 0x00};
-
const uint8x16_t rsstype_msk = {
0x0F, 0x0F, 0x0F, 0x0F,
0x00, 0x00, 0x00, 0x00,
@@ -114,12 +105,26 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
PKT_RX_RSS_HASH, 0, 0, 0,
0, 0, 0, PKT_RX_FDIR};
+ const uint8x16_t vlan_msk = {
+ IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
+ IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0};
+
+ const uint8x16_t vlan_map = {
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ vlan_flags, 0, 0, 0,
+ 0, 0, 0, 0};
+
ptype = vzipq_u8(sterr_tmp1.val[0], sterr_tmp2.val[0]).val[0];
ptype = vandq_u8(ptype, rsstype_msk);
ptype = vqtbl1q_u8(rss_flags, ptype);
- vtag = vshrq_n_u8(staterr, VTAG_SHIFT);
- vtag = vandq_u8(vtag, pkttype_msk);
+ /* extract vlan_flags from IXGBE_RXD_STAT_VP bits of staterr */
+ vtag = vandq_u8(staterr, vlan_msk);
+ vtag = vqtbl1q_u8(vlan_map, vtag);
vtag = vorrq_u8(ptype, vtag);
vol.word = vgetq_lane_u32(vreinterpretq_u32_u8(vtag), 0);
@@ -221,6 +226,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
};
uint16x8_t crc_adjust = {0, 0, rxq->crc_len, 0,
rxq->crc_len, 0, 0, 0};
+ uint8_t vlan_flags;
/* nb_pkts has to be floor-aligned to RTE_IXGBE_DESCS_PER_LOOP */
nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, RTE_IXGBE_DESCS_PER_LOOP);
@@ -250,6 +256,10 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
*/
sw_ring = &rxq->sw_ring[rxq->rx_tail];
+ /* ensure these 2 flags are in the lower 8 bits */
+ RTE_BUILD_BUG_ON((PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED) > UINT8_MAX);
+ vlan_flags = rxq->vlan_flags & UINT8_MAX;
+
/* A. load 4 packet in one loop
* B. copy 4 mbuf point from swring to rx_pkts
* C. calc the number of DD bits among the 4 packets
@@ -311,7 +321,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
staterr = vzipq_u8(sterr_tmp1.val[1], sterr_tmp2.val[1]).val[0];
/* set ol_flags with vlan packet type */
- desc_to_olflags_v(sterr_tmp1, sterr_tmp2, staterr,
+ desc_to_olflags_v(sterr_tmp1, sterr_tmp2, staterr, vlan_flags,
&rx_pkts[pos]);
/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
--
2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* [dpdk-dev] [PATCH v1 2/4] net/ixgbe: support checksum flags for NEON vector
2020-11-18 6:29 [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Feifei Wang
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 1/4] net/ixgbe: add VLAN stripping support for Arm Feifei Wang
@ 2020-11-18 6:29 ` Feifei Wang
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag " Feifei Wang
` (2 subsequent siblings)
4 siblings, 0 replies; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 6:29 UTC (permalink / raw)
To: Jerin Jacob, Ruifeng Wang, Jeff Guo, Haiyue Wang; +Cc: dev, nd, Feifei Wang
Updated desc_to_olflags_v() to support PKT_RX_IP_CKSUM_BAD and
PKT_RX_L4_CKSUM_BAD in the ol_flags of the mbuf for Arm neon vector
Rx function.
Test Results:
NICs: 82599(igb)
Dirver: ixgbe(vector)
Packet: IPv4_checksum = 0xee && UDP_checksum = 0xee
$:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i --port-topology=chained
test-pmd> set fwd rxonly
test-pmd> set verbose 1
test-pmd> start
With this patch:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
ol_flags: PKT_RX_L4_CKSUM_BAD PKT_RX_IP_CKSUM_BAD
Without this patch:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 47 +++++++++++++++++++------
1 file changed, 36 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index e6d877af9..4d6f057e7 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -87,6 +87,8 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
{
uint8x16_t ptype;
uint8x16_t vtag;
+ uint8x16_t temp_csum;
+ uint32x4_t csum = {0, 0, 0, 0};
union {
uint8_t e[4];
@@ -105,26 +107,51 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
PKT_RX_RSS_HASH, 0, 0, 0,
0, 0, 0, PKT_RX_FDIR};
- const uint8x16_t vlan_msk = {
+ /* mask everything except vlan present and l4/ip csum error */
+ const uint8x16_t vlan_csum_msk = {
IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
0, 0, 0, 0,
0, 0, 0, 0,
- 0, 0, 0, 0};
-
- const uint8x16_t vlan_map = {
+ (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 24,
+ (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 24,
+ (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 24,
+ (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 24};
+
+ /* map vlan present (0x8), IPE (0x2), L4E (0x1) to ol_flags */
+ const uint8x16_t vlan_csum_map = {
+ 0,
+ PKT_RX_L4_CKSUM_BAD,
+ PKT_RX_IP_CKSUM_BAD,
+ PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
0, 0, 0, 0,
- 0, 0, 0, 0,
- vlan_flags, 0, 0, 0,
+ vlan_flags,
+ vlan_flags | PKT_RX_L4_CKSUM_BAD,
+ vlan_flags | PKT_RX_IP_CKSUM_BAD,
+ vlan_flags | PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
0, 0, 0, 0};
ptype = vzipq_u8(sterr_tmp1.val[0], sterr_tmp2.val[0]).val[0];
ptype = vandq_u8(ptype, rsstype_msk);
ptype = vqtbl1q_u8(rss_flags, ptype);
- /* extract vlan_flags from IXGBE_RXD_STAT_VP bits of staterr */
- vtag = vandq_u8(staterr, vlan_msk);
- vtag = vqtbl1q_u8(vlan_map, vtag);
+ /* extract vlan_flags and csum_error from staterr */
+ vtag = vandq_u8(staterr, vlan_csum_msk);
+
+ /* csum bits are in the most significant, to use shuffle we need to
+ * shift them. Change mask from 0xc0 to 0x03.
+ */
+ temp_csum = vshrq_n_u8(vtag, 6);
+
+ /* 'OR' the most significant 32 bits containing the checksum
+ * flags with the vlan present flags
+ * Then bits layout of each lane(8bits) will be 'xxxx,VP,x,IPE,L4E'
+ */
+ csum = vsetq_lane_u32(vgetq_lane_u32(vreinterpretq_u32_u8(temp_csum), 3), csum, 0);
+ vtag = vorrq_u8(vreinterpretq_u8_u32(csum), vtag);
+
+ /* convert VP, IPE, L4E to ol_flags */
+ vtag = vqtbl1q_u8(vlan_csum_map, vtag);
vtag = vorrq_u8(ptype, vtag);
vol.word = vgetq_lane_u32(vreinterpretq_u32_u8(vtag), 0);
@@ -391,7 +418,6 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
* Notice:
* - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
* - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
- * - don't support ol_flags for rss and csum err
*/
uint16_t
ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
@@ -404,7 +430,6 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
* vPMD receive routine that reassembles scattered packets
*
* Notice:
- * - don't support ol_flags for rss and csum err
* - nb_pkts < RTE_IXGBE_DESCS_PER_LOOP, just return no packet
* - floor align nb_pkts to a RTE_IXGBE_DESC_PER_LOOP power-of-two
*/
--
2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
2020-11-18 6:29 [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Feifei Wang
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 1/4] net/ixgbe: add VLAN stripping support for Arm Feifei Wang
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 2/4] net/ixgbe: support checksum flags for NEON vector Feifei Wang
@ 2020-11-18 6:29 ` Feifei Wang
2020-11-18 7:21 ` Wang, Haiyue
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 4/4] net/ixgbe: enable IXGBE NEON vector PMD when CHECKSUM is set Feifei Wang
2020-12-11 1:52 ` [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Zhang, Qi Z
4 siblings, 1 reply; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 6:29 UTC (permalink / raw)
To: Jerin Jacob, Ruifeng Wang, Jeff Guo, Haiyue Wang; +Cc: dev, nd, feiwan02
From: feiwan02 <feifei.wang2@arm.com>
Add CKSUM_GOOD flag to distinguish a good checksum from an unknown one
in neon vertor RX function.
Test Results:
NICs: 82599(igb)
Dirver: ixgbe(vector)
Packet: IPv4_checksum = correct value && UDP_checksum = correct value
$:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i --port-topology=chained
test-pmd> set fwd rxonly
test-pmd> set verbose 1
test-pmd> start
With this patch:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD
Without this patch:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 37 +++++++++++++++++--------
1 file changed, 25 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index 4d6f057e7..b2bee2228 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -86,13 +86,13 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
uint8x16_t staterr, uint8_t vlan_flags, struct rte_mbuf **rx_pkts)
{
uint8x16_t ptype;
- uint8x16_t vtag;
+ uint8x16_t vtag_lo, vtag_hi, vtag;
uint8x16_t temp_csum;
uint32x4_t csum = {0, 0, 0, 0};
union {
- uint8_t e[4];
- uint32_t word;
+ uint16_t e[4];
+ uint64_t word;
} vol;
const uint8x16_t rsstype_msk = {
@@ -119,18 +119,26 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
(IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 24};
/* map vlan present (0x8), IPE (0x2), L4E (0x1) to ol_flags */
- const uint8x16_t vlan_csum_map = {
- 0,
- PKT_RX_L4_CKSUM_BAD,
+ const uint8x16_t vlan_csum_map_lo = {
+ PKT_RX_IP_CKSUM_GOOD,
+ PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD,
PKT_RX_IP_CKSUM_BAD,
PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
0, 0, 0, 0,
- vlan_flags,
- vlan_flags | PKT_RX_L4_CKSUM_BAD,
+ vlan_flags | PKT_RX_IP_CKSUM_GOOD,
+ vlan_flags | PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD,
vlan_flags | PKT_RX_IP_CKSUM_BAD,
vlan_flags | PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
0, 0, 0, 0};
+ const uint8x16_t vlan_csum_map_hi = {
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ 0, 0, 0, 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ 0, 0, 0, 0};
+
ptype = vzipq_u8(sterr_tmp1.val[0], sterr_tmp2.val[0]).val[0];
ptype = vandq_u8(ptype, rsstype_msk);
ptype = vqtbl1q_u8(rss_flags, ptype);
@@ -150,11 +158,16 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
csum = vsetq_lane_u32(vgetq_lane_u32(vreinterpretq_u32_u8(temp_csum), 3), csum, 0);
vtag = vorrq_u8(vreinterpretq_u8_u32(csum), vtag);
- /* convert VP, IPE, L4E to ol_flags */
- vtag = vqtbl1q_u8(vlan_csum_map, vtag);
- vtag = vorrq_u8(ptype, vtag);
+ /* convert L4 checksum correct type to vtag_hi */
+ vtag_hi = vqtbl1q_u8(vlan_csum_map_hi, vtag);
+ vtag_hi = vshrq_n_u8(vtag_hi, 7);
+
+ /* convert VP, IPE, L4E to vtag_lo */
+ vtag_lo = vqtbl1q_u8(vlan_csum_map_lo, vtag);
+ vtag_lo = vorrq_u8(ptype, vtag_lo);
- vol.word = vgetq_lane_u32(vreinterpretq_u32_u8(vtag), 0);
+ vtag = vzipq_u8(vtag_lo, vtag_hi).val[0];
+ vol.word = vgetq_lane_u64(vreinterpretq_u64_u8(vtag), 0);
rx_pkts[0]->ol_flags = vol.e[0];
rx_pkts[1]->ol_flags = vol.e[1];
--
2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag " Feifei Wang
@ 2020-11-18 7:21 ` Wang, Haiyue
2020-11-18 7:55 ` [dpdk-dev] 回复: " Feifei Wang
0 siblings, 1 reply; 11+ messages in thread
From: Wang, Haiyue @ 2020-11-18 7:21 UTC (permalink / raw)
To: Feifei Wang, Jerin Jacob, Ruifeng Wang, Guo, Jia; +Cc: dev, nd
> -----Original Message-----
> From: Feifei Wang <feifei.wang2@arm.com>
> Sent: Wednesday, November 18, 2020 14:29
> To: Jerin Jacob <jerinj@marvell.com>; Ruifeng Wang <ruifeng.wang@arm.com>; Guo, Jia
> <jia.guo@intel.com>; Wang, Haiyue <haiyue.wang@intel.com>
> Cc: dev@dpdk.org; nd@arm.com; feiwan02 <feifei.wang2@arm.com>
> Subject: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
>
> From: feiwan02 <feifei.wang2@arm.com>
>
> Add CKSUM_GOOD flag to distinguish a good checksum from an unknown one
> in neon vertor RX function.
>
> Test Results:
> NICs: 82599(igb)
> Dirver: ixgbe(vector)
> Packet: IPv4_checksum = correct value && UDP_checksum = correct value
>
> $:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i --port-topology=chained
> test-pmd> set fwd rxonly
> test-pmd> set verbose 1
> test-pmd> start
>
> With this patch:
> testpmd> port 0/queue 0: received 1 packets
> src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
> ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD
>
> Without this patch:
> testpmd> port 0/queue 0: received 1 packets
> src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
> ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
>
How about to merge "1 & 2" and "3 & 4"? Then you will have the above test result. ;-)
> Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> ---
> 2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* [dpdk-dev] 回复: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
2020-11-18 7:21 ` Wang, Haiyue
@ 2020-11-18 7:55 ` Feifei Wang
2020-11-18 8:15 ` [dpdk-dev] " Wang, Haiyue
0 siblings, 1 reply; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 7:55 UTC (permalink / raw)
To: Wang, Haiyue, jerinj, Ruifeng Wang, Guo, Jia; +Cc: dev, nd, nd
Hi, Haiyue
> -----邮件原件-----
> 发件人: Wang, Haiyue <haiyue.wang@intel.com>
> 发送时间: 2020年11月18日 15:22
> 收件人: Feifei Wang <Feifei.Wang2@arm.com>; jerinj@marvell.com; Ruifeng
> Wang <Ruifeng.Wang@arm.com>; Guo, Jia <jia.guo@intel.com>
> 抄送: dev@dpdk.org; nd <nd@arm.com>
> 主题: RE: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON
> vector
>
> > -----Original Message-----
> > From: Feifei Wang <feifei.wang2@arm.com>
> > Sent: Wednesday, November 18, 2020 14:29
> > To: Jerin Jacob <jerinj@marvell.com>; Ruifeng Wang
> > <ruifeng.wang@arm.com>; Guo, Jia <jia.guo@intel.com>; Wang, Haiyue
> > <haiyue.wang@intel.com>
> > Cc: dev@dpdk.org; nd@arm.com; feiwan02 <feifei.wang2@arm.com>
> > Subject: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for
> > NEON vector
> >
> > From: feiwan02 <feifei.wang2@arm.com>
> >
> > Add CKSUM_GOOD flag to distinguish a good checksum from an unknown
> one
> > in neon vertor RX function.
> >
> > Test Results:
> > NICs: 82599(igb)
> > Dirver: ixgbe(vector)
> > Packet: IPv4_checksum = correct value && UDP_checksum = correct value
> >
> > $:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i
> > --port-topology=chained
> > test-pmd> set fwd rxonly
> > test-pmd> set verbose 1
> > test-pmd> start
> >
> > With this patch:
> > testpmd> port 0/queue 0: received 1 packets
> > src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 -
> > length=70 - nb_segs=1
> > ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD
> >
> > Without this patch:
> > testpmd> port 0/queue 0: received 1 packets
> > src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 -
> > length=70 - nb_segs=1
> > ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
> >
>
> How about to merge "1 & 2" and "3 & 4"? Then you will have the above test
> result. ;-)
Do you mean that combine patch 1 and patch 2 into one patch to support vlan stripping and bad checksum flag,
Then also do the same work for patch 3 and patch 4 to support good checksum flag and enable IXGBE neon vector when DEV_RX_OFFLOAD_CHECKSUM is set?
Actually, the test results are achieved without patch 4, due to that testpmd does not check rxmode->offloads, it will call IXGBE NEON vector function directly. And this change
is for the default config of l3fwd example.
Best Regards
Feifei
>
> > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > ---
> > 2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
2020-11-18 7:55 ` [dpdk-dev] 回复: " Feifei Wang
@ 2020-11-18 8:15 ` Wang, Haiyue
2020-11-18 8:29 ` [dpdk-dev] 回复: " Feifei Wang
0 siblings, 1 reply; 11+ messages in thread
From: Wang, Haiyue @ 2020-11-18 8:15 UTC (permalink / raw)
To: Feifei Wang, jerinj, Ruifeng Wang, Guo, Jia; +Cc: dev, nd, nd
> -----Original Message-----
> From: Feifei Wang <Feifei.Wang2@arm.com>
> Sent: Wednesday, November 18, 2020 15:56
> To: Wang, Haiyue <haiyue.wang@intel.com>; jerinj@marvell.com; Ruifeng Wang <Ruifeng.Wang@arm.com>; Guo,
> Jia <jia.guo@intel.com>
> Cc: dev@dpdk.org; nd <nd@arm.com>; nd <nd@arm.com>
> Subject: 回复: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
>
> Hi, Haiyue
>
> > -----邮件原件-----
> > 发件人: Wang, Haiyue <haiyue.wang@intel.com>
> > 发送时间: 2020年11月18日 15:22
> > 收件人: Feifei Wang <Feifei.Wang2@arm.com>; jerinj@marvell.com; Ruifeng
> > Wang <Ruifeng.Wang@arm.com>; Guo, Jia <jia.guo@intel.com>
> > 抄送: dev@dpdk.org; nd <nd@arm.com>
> > 主题: RE: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON
> > vector
> >
> > > -----Original Message-----
> > > From: Feifei Wang <feifei.wang2@arm.com>
> > > Sent: Wednesday, November 18, 2020 14:29
> > > To: Jerin Jacob <jerinj@marvell.com>; Ruifeng Wang
> > > <ruifeng.wang@arm.com>; Guo, Jia <jia.guo@intel.com>; Wang, Haiyue
> > > <haiyue.wang@intel.com>
> > > Cc: dev@dpdk.org; nd@arm.com; feiwan02 <feifei.wang2@arm.com>
> > > Subject: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for
> > > NEON vector
> > >
> > > From: feiwan02 <feifei.wang2@arm.com>
> > >
> > > Add CKSUM_GOOD flag to distinguish a good checksum from an unknown
> > one
> > > in neon vertor RX function.
> > >
> > > Test Results:
> > > NICs: 82599(igb)
> > > Dirver: ixgbe(vector)
> > > Packet: IPv4_checksum = correct value && UDP_checksum = correct value
> > >
> > > $:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i
> > > --port-topology=chained
> > > test-pmd> set fwd rxonly
> > > test-pmd> set verbose 1
> > > test-pmd> start
> > >
> > > With this patch:
> > > testpmd> port 0/queue 0: received 1 packets
> > > src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 -
> > > length=70 - nb_segs=1
> > > ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD
> > >
> > > Without this patch:
> > > testpmd> port 0/queue 0: received 1 packets
> > > src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 -
> > > length=70 - nb_segs=1
> > > ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
> > >
> >
> > How about to merge "1 & 2" and "3 & 4"? Then you will have the above test
> > result. ;-)
> Do you mean that combine patch 1 and patch 2 into one patch to support vlan stripping and bad checksum
> flag,
> Then also do the same work for patch 3 and patch 4 to support good checksum flag and enable IXGBE neon
> vector when DEV_RX_OFFLOAD_CHECKSUM is set?
>
> Actually, the test results are achieved without patch 4, due to that testpmd does not check rxmode-
> >offloads, it will call IXGBE NEON vector function directly. And this change
> is for the default config of l3fwd example.
>
I was messed by the vector code, sorry. Patch b is for bad checksum,
update the commit message to align your design. Then the patch set
is OF for me, thanks!
Feifei Wang (4):
a). net/ixgbe: add VLAN stripping support for Arm
b). net/ixgbe: support checksum flags for NEON vector
c). net/ixgbe: implement good checksum flag for NEON vector
d). net/ixgbe: enable IXGBE NEON vector PMD when CHECKSUM is set
> Best Regards
> Feifei
> >
> > > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > ---
> > > 2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* [dpdk-dev] 回复: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
2020-11-18 8:15 ` [dpdk-dev] " Wang, Haiyue
@ 2020-11-18 8:29 ` Feifei Wang
0 siblings, 0 replies; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 8:29 UTC (permalink / raw)
To: Wang, Haiyue, jerinj, Ruifeng Wang, Guo, Jia; +Cc: dev, nd, nd, nd
> -----邮件原件-----
> 发件人: Wang, Haiyue <haiyue.wang@intel.com>
> 发送时间: 2020年11月18日 16:15
> 收件人: Feifei Wang <Feifei.Wang2@arm.com>; jerinj@marvell.com; Ruifeng
> Wang <Ruifeng.Wang@arm.com>; Guo, Jia <jia.guo@intel.com>
> 抄送: dev@dpdk.org; nd <nd@arm.com>; nd <nd@arm.com>
> 主题: RE: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON
> vector
>
> > -----Original Message-----
> > From: Feifei Wang <Feifei.Wang2@arm.com>
> > Sent: Wednesday, November 18, 2020 15:56
> > To: Wang, Haiyue <haiyue.wang@intel.com>; jerinj@marvell.com; Ruifeng
> > Wang <Ruifeng.Wang@arm.com>; Guo, Jia <jia.guo@intel.com>
> > Cc: dev@dpdk.org; nd <nd@arm.com>; nd <nd@arm.com>
> > Subject: 回复: [PATCH v1 3/4] net/ixgbe: implement good checksum flag
> > for NEON vector
> >
> > Hi, Haiyue
> >
> > > -----邮件原件-----
> > > 发件人: Wang, Haiyue <haiyue.wang@intel.com>
> > > 发送时间: 2020年11月18日 15:22
> > > 收件人: Feifei Wang <Feifei.Wang2@arm.com>; jerinj@marvell.com;
> Ruifeng
> > > Wang <Ruifeng.Wang@arm.com>; Guo, Jia <jia.guo@intel.com>
> > > 抄送: dev@dpdk.org; nd <nd@arm.com>
> > > 主题: RE: [PATCH v1 3/4] net/ixgbe: implement good checksum flag for
> > > NEON vector
> > >
> > > > -----Original Message-----
> > > > From: Feifei Wang <feifei.wang2@arm.com>
> > > > Sent: Wednesday, November 18, 2020 14:29
> > > > To: Jerin Jacob <jerinj@marvell.com>; Ruifeng Wang
> > > > <ruifeng.wang@arm.com>; Guo, Jia <jia.guo@intel.com>; Wang, Haiyue
> > > > <haiyue.wang@intel.com>
> > > > Cc: dev@dpdk.org; nd@arm.com; feiwan02 <feifei.wang2@arm.com>
> > > > Subject: [PATCH v1 3/4] net/ixgbe: implement good checksum flag
> > > > for NEON vector
> > > >
> > > > From: feiwan02 <feifei.wang2@arm.com>
> > > >
> > > > Add CKSUM_GOOD flag to distinguish a good checksum from an unknown
> > > one
> > > > in neon vertor RX function.
> > > >
> > > > Test Results:
> > > > NICs: 82599(igb)
> > > > Dirver: ixgbe(vector)
> > > > Packet: IPv4_checksum = correct value && UDP_checksum = correct
> > > > value
> > > >
> > > > $:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i
> > > > --port-topology=chained
> > > > test-pmd> set fwd rxonly
> > > > test-pmd> set verbose 1
> > > > test-pmd> start
> > > >
> > > > With this patch:
> > > > testpmd> port 0/queue 0: received 1 packets
> > > > src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 -
> > > > length=70 - nb_segs=1
> > > > ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD
> > > >
> > > > Without this patch:
> > > > testpmd> port 0/queue 0: received 1 packets
> > > > src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 -
> > > > length=70 - nb_segs=1
> > > > ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
> > > >
> > >
> > > How about to merge "1 & 2" and "3 & 4"? Then you will have the above
> > > test result. ;-)
> > Do you mean that combine patch 1 and patch 2 into one patch to support
> > vlan stripping and bad checksum flag, Then also do the same work for
> > patch 3 and patch 4 to support good checksum flag and enable IXGBE
> > neon vector when DEV_RX_OFFLOAD_CHECKSUM is set?
> >
> > Actually, the test results are achieved without patch 4, due to that
> > testpmd does not check rxmode-
> > >offloads, it will call IXGBE NEON vector function directly. And this
> > >change
> > is for the default config of l3fwd example.
> >
>
> I was messed by the vector code, sorry. Patch b is for bad checksum, update the
> commit message to align your design. Then the patch set is OF for me, thanks!
>
> Feifei Wang (4):
> a). net/ixgbe: add VLAN stripping support for Arm
> b). net/ixgbe: support checksum flags for NEON vector
> c). net/ixgbe: implement good checksum flag for NEON vector
> d). net/ixgbe: enable IXGBE NEON vector PMD when CHECKSUM is set
>
That's all right. I will update the commit message and then upload the new version.
Thanks for your attention.
> > Best Regards
> > Feifei
> > >
> > > > Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
> > > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > > ---
> > > > 2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* [dpdk-dev] [PATCH v1 4/4] net/ixgbe: enable IXGBE NEON vector PMD when CHECKSUM is set
2020-11-18 6:29 [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Feifei Wang
` (2 preceding siblings ...)
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag " Feifei Wang
@ 2020-11-18 6:29 ` Feifei Wang
2020-12-11 1:52 ` [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Zhang, Qi Z
4 siblings, 0 replies; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 6:29 UTC (permalink / raw)
To: Jerin Jacob, Ruifeng Wang, Jeff Guo, Haiyue Wang; +Cc: dev, nd, feiwan02
From: feiwan02 <feifei.wang2@arm.com>
IXGBE NEON vector PMD now supports checksum offloading, hence can be used
when DEV_RX_OFFLOAD_CHECKSUM is set.
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index b2bee2228..a5a5b2167 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -638,11 +638,5 @@ ixgbe_txq_vec_setup(struct ixgbe_tx_queue *txq)
int __rte_cold
ixgbe_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev)
{
- struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
-
- /* no csum error report support */
- if (rxmode->offloads & DEV_RX_OFFLOAD_CHECKSUM)
- return -1;
-
return ixgbe_rx_vec_dev_conf_condition_check_default(dev);
}
--
2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector
2020-11-18 6:29 [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON vector Feifei Wang
` (3 preceding siblings ...)
2020-11-18 6:29 ` [dpdk-dev] [PATCH v1 4/4] net/ixgbe: enable IXGBE NEON vector PMD when CHECKSUM is set Feifei Wang
@ 2020-12-11 1:52 ` Zhang, Qi Z
4 siblings, 0 replies; 11+ messages in thread
From: Zhang, Qi Z @ 2020-12-11 1:52 UTC (permalink / raw)
To: Feifei Wang; +Cc: dev, nd
> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Feifei Wang
> Sent: Wednesday, November 18, 2020 2:29 PM
> Cc: dev@dpdk.org; nd@arm.com; Feifei Wang <feifei.wang2@arm.com>
> Subject: [dpdk-dev] [PATCH v1 0/4] Enable Checksum Offloading for NEON
> vector
>
> This patch series are mainly to enable checksum offloading for IXGBE NEON
> vector PMD, including good and bad checksum flags. In the meanwhile, the first
> patch enable VLAN stripping flag for Arm.
>
> Feifei Wang (4):
> net/ixgbe: add VLAN stripping support for Arm
> net/ixgbe: support checksum flags for NEON vector
> net/ixgbe: implement good checksum flag for NEON vector
> net/ixgbe: enable IXGBE NEON vector PMD when CHECKSUM is set
>
> drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 94 ++++++++++++++++++-------
> 1 file changed, 68 insertions(+), 26 deletions(-)
>
> --
> 2.17.1
Applied to dpdk-next-net-intel.
Thanks
Qi
^ permalink raw reply [flat|nested] 11+ messages in thread
* [dpdk-dev] [PATCH v1 3/4] net/ixgbe: implement good checksum flag for NEON vector
2020-11-18 7:35 Feifei Wang
@ 2020-11-18 7:35 ` Feifei Wang
0 siblings, 0 replies; 11+ messages in thread
From: Feifei Wang @ 2020-11-18 7:35 UTC (permalink / raw)
To: Jerin Jacob, Ruifeng Wang, Jeff Guo, Haiyue Wang; +Cc: dev, nd, Feifei Wang
Add CKSUM_GOOD flag to distinguish a good checksum from an unknown one
in neon vertor RX function.
Test Results:
NICs: 82599(igb)
Driver: ixgbe(vector)
Packet: IPv4_checksum = correct value && UDP_checksum = correct value
$:./app/dpdk-testpmd -c 0x3 -w 0002:f9:00.0 -- -i --port-topology=chained
test-pmd> set fwd rxonly
test-pmd> set verbose 1
test-pmd> start
With this patch:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD
Without this patch:
testpmd> port 0/queue 0: received 1 packets
src=00:00:00:00:00:02 - dst=00:00:00:00:00:01 - type=0x0800 - length=70 - nb_segs=1
ol_flags: PKT_RX_L4_CKSUM_UNKNOWN PKT_RX_IP_CKSUM_UNKNOWN
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 37 +++++++++++++++++--------
1 file changed, 25 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index 4d6f057e7..b2bee2228 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -86,13 +86,13 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
uint8x16_t staterr, uint8_t vlan_flags, struct rte_mbuf **rx_pkts)
{
uint8x16_t ptype;
- uint8x16_t vtag;
+ uint8x16_t vtag_lo, vtag_hi, vtag;
uint8x16_t temp_csum;
uint32x4_t csum = {0, 0, 0, 0};
union {
- uint8_t e[4];
- uint32_t word;
+ uint16_t e[4];
+ uint64_t word;
} vol;
const uint8x16_t rsstype_msk = {
@@ -119,18 +119,26 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
(IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 24};
/* map vlan present (0x8), IPE (0x2), L4E (0x1) to ol_flags */
- const uint8x16_t vlan_csum_map = {
- 0,
- PKT_RX_L4_CKSUM_BAD,
+ const uint8x16_t vlan_csum_map_lo = {
+ PKT_RX_IP_CKSUM_GOOD,
+ PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD,
PKT_RX_IP_CKSUM_BAD,
PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
0, 0, 0, 0,
- vlan_flags,
- vlan_flags | PKT_RX_L4_CKSUM_BAD,
+ vlan_flags | PKT_RX_IP_CKSUM_GOOD,
+ vlan_flags | PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD,
vlan_flags | PKT_RX_IP_CKSUM_BAD,
vlan_flags | PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
0, 0, 0, 0};
+ const uint8x16_t vlan_csum_map_hi = {
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ 0, 0, 0, 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ PKT_RX_L4_CKSUM_GOOD >> sizeof(uint8_t), 0,
+ 0, 0, 0, 0};
+
ptype = vzipq_u8(sterr_tmp1.val[0], sterr_tmp2.val[0]).val[0];
ptype = vandq_u8(ptype, rsstype_msk);
ptype = vqtbl1q_u8(rss_flags, ptype);
@@ -150,11 +158,16 @@ desc_to_olflags_v(uint8x16x2_t sterr_tmp1, uint8x16x2_t sterr_tmp2,
csum = vsetq_lane_u32(vgetq_lane_u32(vreinterpretq_u32_u8(temp_csum), 3), csum, 0);
vtag = vorrq_u8(vreinterpretq_u8_u32(csum), vtag);
- /* convert VP, IPE, L4E to ol_flags */
- vtag = vqtbl1q_u8(vlan_csum_map, vtag);
- vtag = vorrq_u8(ptype, vtag);
+ /* convert L4 checksum correct type to vtag_hi */
+ vtag_hi = vqtbl1q_u8(vlan_csum_map_hi, vtag);
+ vtag_hi = vshrq_n_u8(vtag_hi, 7);
+
+ /* convert VP, IPE, L4E to vtag_lo */
+ vtag_lo = vqtbl1q_u8(vlan_csum_map_lo, vtag);
+ vtag_lo = vorrq_u8(ptype, vtag_lo);
- vol.word = vgetq_lane_u32(vreinterpretq_u32_u8(vtag), 0);
+ vtag = vzipq_u8(vtag_lo, vtag_hi).val[0];
+ vol.word = vgetq_lane_u64(vreinterpretq_u64_u8(vtag), 0);
rx_pkts[0]->ol_flags = vol.e[0];
rx_pkts[1]->ol_flags = vol.e[1];
--
2.17.1
^ permalink raw reply [flat|nested] 11+ messages in thread