Re: [PATCH] net/i40e: fix x86 vPMD Rx checksum flag

-----Original Message-----
From: Zhang, Qi Z
Sent: Wednesday, January 25, 2017 2:49 AM
To: Wu, Jingjing <redacted>; Zhang, Helin
[off-list ref]
Cc: dev@dpdk.org; Zhang, Qi Z <redacted>
Subject: [PATCH] net/i40e: fix x86 vPMD Rx checksum flag

When no error reported in Rx descriptor, we should set CKSUM_GOOD flag
before return.

Fixes: 9966a00a0688 ("net/i40e: enable bad checksum flags in vector Rx")ple

Signed-off-by: Qi Zhang <redacted>
---
 drivers/net/i40e/i40e_rxtx_vec_sse.c | 38
++++++++++++++++++++++++++++--------
 1 file changed, 30 insertions(+), 8 deletions(-)

diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c

b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index 7c84a41..2c4061c 100644

--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c

@@ -148,6 +148,20 @@ desc_to_olflags_v(__m128i descs[4], struct rte_mbuf

**rx_pkts)
 	const __m128i rss_vlan_msk = _mm_set_epi32(
 			0x1c03804, 0x1c03804, 0x1c03804, 0x1c03804);

+	const __m128i cksum_mask = _mm_set_epi32(
+			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
+			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
+			PKT_RX_EIP_CKSUM_BAD,
+			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
+			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
+			PKT_RX_EIP_CKSUM_BAD,
+			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
+			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
+			PKT_RX_EIP_CKSUM_BAD,
+			PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
+			PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
+			PKT_RX_EIP_CKSUM_BAD);
+
 	/* map rss and vlan type to rss hash and vlan flag */
 	const __m128i vlan_flags = _mm_set_epi8(0, 0, 0, 0,
 			0, 0, 0, 0,

@@ -160,14 +174,17 @@ desc_to_olflags_v(__m128i descs[4], struct

rte_mbuf **rx_pkts)
 			0, 0, PKT_RX_FDIR, 0);

 	const __m128i l3_l4e_flags = _mm_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
-			PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
PKT_RX_IP_CKSUM_BAD,
-			PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD,
-			PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD,
-			PKT_RX_EIP_CKSUM_BAD,
-			PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD,
-			PKT_RX_L4_CKSUM_BAD,
-			PKT_RX_IP_CKSUM_BAD,
-			0);
+			/* shift right 1 bit to make sure it not exceed 255 */
+			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
+			 PKT_RX_IP_CKSUM_BAD) >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD |
+			 PKT_RX_L4_CKSUM_BAD) >> 1,
+			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1,
+			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1,
+			PKT_RX_IP_CKSUM_BAD >> 1,
+			(PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1);

 	vlan0 = _mm_unpackhi_epi32(descs[0], descs[1]);
 	vlan1 = _mm_unpackhi_epi32(descs[2], descs[3]); @@ -181,6 +198,10

@@ desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)

 	l3_l4e = _mm_srli_epi32(vlan1, 22);
 	l3_l4e = _mm_shuffle_epi8(l3_l4e_flags, l3_l4e);
+	/* then we shift left 1 bit */
+	l3_l4e = _mm_slli_epi32(l3_l4e, 1);
+	/* we need to mask out the reduntant bits */
+	l3_l4e = _mm_and_si128(l3_l4e, cksum_mask);

 	vlan0 = _mm_or_si128(vlan0, rss);
 	vlan0 = _mm_or_si128(vlan0, l3_l4e);

@@ -189,6 +210,7 @@ desc_to_olflags_v(__m128i descs[4], struct rte_mbuf

**rx_pkts)
 	rx_pkts[1]->ol_flags = _mm_extract_epi16(vlan0, 2);
 	rx_pkts[2]->ol_flags = _mm_extract_epi16(vlan0, 4);
 	rx_pkts[3]->ol_flags = _mm_extract_epi16(vlan0, 6);
+	printf("ol_flags = %lx\n", rx_pkts[0]->ol_flags);
 }
 #else
 #define desc_to_olflags_v(desc, rx_pkts) do {} while (0)
--
2.7.4