DPDK patches and discussions
 help / color / mirror / Atom feed
From: Haiyue Wang <haiyue.wang@intel.com>
To: dev@dpdk.org
Cc: pvalerio@redhat.com, aconole@redhat.com,
	david.marchand@redhat.com, qi.z.zhang@intel.com,
	leyi.rong@intel.com, Lijuan.Tu@intel.com,
	Haiyue Wang <haiyue.wang@intel.com>,
	stable@dpdk.org, Jeff Guo <jia.guo@intel.com>,
	Bruce Richardson <bruce.richardson@intel.com>,
	Konstantin Ananyev <konstantin.ananyev@intel.com>
Subject: [dpdk-dev] [PATCH v1] net/ixgbe: adjust error for UDP with zero checksum
Date: Tue,  2 Feb 2021 15:06:52 +0800
Message-ID: <20210202070652.145861-1-haiyue.wang@intel.com> (raw)

There is an 82599 errata that UDP frames with a zero checksum are
incorrectly marked as checksum invalid by the hardware.  This was
leading to misleading PKT_RX_L4_CKSUM_BAD flag. This patch adds a
test around this checksum error flag set for this condition.

1. UDP Test
  sendp(Ether()/IP()/UDP(chksum=0)/Raw("a"*100), iface="ens802f0")
  port 0/queue 0: received 1 packets
    ol_flags: PKT_RX_L4_CKSUM_GOOD PKT_RX_IP_CKSUM_GOOD

2. TCP Test
  sendp(Ether()/IP()/TCP(chksum=0)/Raw("a"*100), iface="ens802f0")
  port 0/queue 0: received 1 packets
    ol_flags: PKT_RX_L4_CKSUM_BAD PKT_RX_IP_CKSUM_GOOD

Bugzilla ID: 629
Cc: stable@dpdk.org

Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
---
 doc/guides/nics/ixgbe.rst              |  6 ++++
 drivers/net/ixgbe/ixgbe_rxtx.c         | 27 +++++++++++---
 drivers/net/ixgbe/ixgbe_rxtx.h         |  2 ++
 drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c | 49 ++++++++++++++++++++------
 4 files changed, 70 insertions(+), 14 deletions(-)

diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
index 696cbd93b..de210b7b8 100644
--- a/doc/guides/nics/ixgbe.rst
+++ b/doc/guides/nics/ixgbe.rst
@@ -287,6 +287,12 @@ the VFs which are required.::
 Currently hot-plugging of representor ports is not supported so all required
 representors must be specified on the creation of the PF.
 
+Limitations or Known issues
+---------------------------
+The 82599 hardware errata: UDP frames with a zero checksum can be marked as
+checksum errors. To support zero checksum, the UDP checksum is always marked
+as good.
+
 Supported Chipsets and NICs
 ---------------------------
 
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index c1f0c446a..550e3f390 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -1466,7 +1466,8 @@ rx_desc_status_to_pkt_flags(uint32_t rx_status, uint64_t vlan_flags)
 }
 
 static inline uint64_t
-rx_desc_error_to_pkt_flags(uint32_t rx_status)
+rx_desc_error_to_pkt_flags(uint32_t rx_status, uint16_t pkt_info,
+			   uint8_t rx_udp_csum_zero_err)
 {
 	uint64_t pkt_flags;
 
@@ -1480,6 +1481,12 @@ rx_desc_error_to_pkt_flags(uint32_t rx_status)
 		PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD,
 		PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD
 	};
+
+	if ((rx_status & IXGBE_RXDADV_ERR_TCPE) &&
+	    (pkt_info & IXGBE_RXDADV_PKTTYPE_UDP) &&
+	    rx_udp_csum_zero_err)
+		rx_status &= ~IXGBE_RXDADV_ERR_TCPE;
+
 	pkt_flags = error_to_pkt_flags_map[(rx_status >>
 		IXGBE_RXDADV_ERR_CKSUM_BIT) & IXGBE_RXDADV_ERR_CKSUM_MSK];
 
@@ -1569,7 +1576,9 @@ ixgbe_rx_scan_hw_ring(struct ixgbe_rx_queue *rxq)
 			/* convert descriptor fields to rte mbuf flags */
 			pkt_flags = rx_desc_status_to_pkt_flags(s[j],
 				vlan_flags);
-			pkt_flags |= rx_desc_error_to_pkt_flags(s[j]);
+			pkt_flags |= rx_desc_error_to_pkt_flags(s[j],
+					(uint16_t)pkt_info[j],
+					rxq->rx_udp_csum_zero_err);
 			pkt_flags |= ixgbe_rxd_pkt_info_to_pkt_flags
 					((uint16_t)pkt_info[j]);
 			mb->ol_flags = pkt_flags;
@@ -1902,7 +1911,9 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 		rxm->vlan_tci = rte_le_to_cpu_16(rxd.wb.upper.vlan);
 
 		pkt_flags = rx_desc_status_to_pkt_flags(staterr, vlan_flags);
-		pkt_flags = pkt_flags | rx_desc_error_to_pkt_flags(staterr);
+		pkt_flags = pkt_flags |
+			rx_desc_error_to_pkt_flags(staterr, (uint16_t)pkt_info,
+						   rxq->rx_udp_csum_zero_err);
 		pkt_flags = pkt_flags |
 			ixgbe_rxd_pkt_info_to_pkt_flags((uint16_t)pkt_info);
 		rxm->ol_flags = pkt_flags;
@@ -1995,7 +2006,8 @@ ixgbe_fill_cluster_head_buf(
 	head->vlan_tci = rte_le_to_cpu_16(desc->wb.upper.vlan);
 	pkt_info = rte_le_to_cpu_32(desc->wb.lower.lo_dword.data);
 	pkt_flags = rx_desc_status_to_pkt_flags(staterr, rxq->vlan_flags);
-	pkt_flags |= rx_desc_error_to_pkt_flags(staterr);
+	pkt_flags |= rx_desc_error_to_pkt_flags(staterr, (uint16_t)pkt_info,
+						rxq->rx_udp_csum_zero_err);
 	pkt_flags |= ixgbe_rxd_pkt_info_to_pkt_flags((uint16_t)pkt_info);
 	head->ol_flags = pkt_flags;
 	head->packet_type =
@@ -3116,6 +3128,13 @@ ixgbe_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	else
 		rxq->pkt_type_mask = IXGBE_PACKET_TYPE_MASK_82599;
 
+	/*
+	 * 82599 errata, UDP frames with a 0 checksum can be marked as checksum
+	 * errors.
+	 */
+	if (hw->mac.type == ixgbe_mac_82599EB)
+		rxq->rx_udp_csum_zero_err = 1;
+
 	/*
 	 * Allocate RX ring hardware descriptors. A memzone large enough to
 	 * handle the maximum ring size is allocated in order to allow for
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.h b/drivers/net/ixgbe/ixgbe_rxtx.h
index 8a25e98df..476ef62cf 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.h
+++ b/drivers/net/ixgbe/ixgbe_rxtx.h
@@ -129,6 +129,8 @@ struct ixgbe_rx_queue {
 	uint8_t             crc_len;  /**< 0 if CRC stripped, 4 otherwise. */
 	uint8_t             drop_en;  /**< If not 0, set SRRCTL.Drop_En. */
 	uint8_t             rx_deferred_start; /**< not in global dev start. */
+	/** UDP frames with a 0 checksum can be marked as checksum errors. */
+	uint8_t             rx_udp_csum_zero_err;
 	/** flags to set in mbuf when a vlan is detected. */
 	uint64_t            vlan_flags;
 	uint64_t	    offloads; /**< Rx offloads with DEV_RX_OFFLOAD_* */
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
index 90c076825..8bffafc71 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
@@ -132,9 +132,9 @@ desc_to_olflags_v_ipsec(__m128i descs[4], struct rte_mbuf **rx_pkts)
 
 static inline void
 desc_to_olflags_v(__m128i descs[4], __m128i mbuf_init, uint8_t vlan_flags,
-	struct rte_mbuf **rx_pkts)
+		  uint16_t udp_p_flag, struct rte_mbuf **rx_pkts)
 {
-	__m128i ptype0, ptype1, vtag0, vtag1, csum;
+	__m128i ptype0, ptype1, vtag0, vtag1, csum, vlan_csum_msk;
 	__m128i rearm0, rearm1, rearm2, rearm3;
 
 	/* mask everything except rss type */
@@ -154,13 +154,29 @@ desc_to_olflags_v(__m128i descs[4], __m128i mbuf_init, uint8_t vlan_flags,
 			PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, PKT_RX_RSS_HASH, 0);
 
 	/* mask everything except vlan present and l4/ip csum error */
-	const __m128i vlan_csum_msk = _mm_set_epi16(
-		(IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
-		(IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
-		(IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
-		(IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
-		IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
-		IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP);
+	const __m128i vlan_csum_all_msk = _mm_set_epi16
+		((IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
+		 (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
+		 (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
+		 (IXGBE_RXDADV_ERR_TCPE | IXGBE_RXDADV_ERR_IPE) >> 16,
+		 IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP,
+		 IXGBE_RXD_STAT_VP, IXGBE_RXD_STAT_VP);
+
+	/* mask everything except UDP header present */
+	const __m128i udptype_msk = _mm_set_epi16
+		(0, 0, 0, 0,
+		 udp_p_flag, udp_p_flag, udp_p_flag, udp_p_flag);
+
+	/* convert UDP header present 16 bits 0x0200 to 8 bits 0x02, then get
+	 * the TCP/UDP checksum error mask 8 bits ~0x40 from 32 bits value of
+	 * 0x40000000.
+	 */
+	const __m128i udp_csum_err_skip = _mm_set_epi8
+		(0, 0, 0, 0,
+		 0, 0, 0, 0,
+		 0, 0, 0, 0,
+		 0, ~(IXGBE_RXDADV_ERR_TCPE >> 24), 0, 0xFF);
+
 	/* map vlan present (0x8), IPE (0x2), L4E (0x1) to ol_flags */
 	const __m128i vlan_csum_map_lo = _mm_set_epi8(
 		0, 0, 0, 0,
@@ -188,9 +204,17 @@ desc_to_olflags_v(__m128i descs[4], __m128i mbuf_init, uint8_t vlan_flags,
 	vtag1 = _mm_unpackhi_epi16(descs[2], descs[3]);
 
 	ptype0 = _mm_unpacklo_epi32(ptype0, ptype1);
+	/* save the UDP header present information */
+	vlan_csum_msk = _mm_and_si128(ptype0, udptype_msk);
 	ptype0 = _mm_and_si128(ptype0, rsstype_msk);
 	ptype0 = _mm_shuffle_epi8(rss_flags, ptype0);
 
+	/* now the most significant 64 bits containing the UDP present */
+	vlan_csum_msk = _mm_slli_si128(vlan_csum_msk, 8);
+	/* use UDP present 0x02 index to get L4 checksum error mask ~0x40 */
+	vlan_csum_msk = _mm_shuffle_epi8(udp_csum_err_skip, vlan_csum_msk);
+	/* then mask out the L4 checksum error bit as needed */
+	vlan_csum_msk = _mm_and_si128(vlan_csum_all_msk, vlan_csum_msk);
 	vtag1 = _mm_unpacklo_epi32(vtag0, vtag1);
 	vtag1 = _mm_and_si128(vtag1, vlan_csum_msk);
 
@@ -341,6 +365,7 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 	__m128i dd_check, eop_check;
 	__m128i mbuf_init;
 	uint8_t vlan_flags;
+	uint16_t udp_p_flag = 0; /* Rx Descriptor UDP header present */
 
 	/* 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);
@@ -365,6 +390,9 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 				rte_cpu_to_le_32(IXGBE_RXDADV_STAT_DD)))
 		return 0;
 
+	if (rxq->rx_udp_csum_zero_err)
+		udp_p_flag = IXGBE_RXDADV_PKTTYPE_UDP;
+
 	/* 4 packets DD mask */
 	dd_check = _mm_set_epi64x(0x0000000100000001LL, 0x0000000100000001LL);
 
@@ -477,7 +505,8 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
 
 		/* set ol_flags with vlan packet type */
-		desc_to_olflags_v(descs, mbuf_init, vlan_flags, &rx_pkts[pos]);
+		desc_to_olflags_v(descs, mbuf_init, vlan_flags, udp_p_flag,
+				  &rx_pkts[pos]);
 
 #ifdef RTE_LIB_SECURITY
 		if (unlikely(use_ipsec))
-- 
2.30.0


             reply	other threads:[~2021-02-02  7:23 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-02  7:06 Haiyue Wang [this message]
2021-02-02  9:45 ` David Marchand
2021-02-02 12:42   ` Wang, Haiyue
2021-02-02 12:53     ` David Marchand
2021-02-02 12:56       ` Wang, Haiyue
2021-02-02 14:28         ` Wang, Haiyue
2021-02-02 17:42           ` Paolo Valerio
2021-02-02 12:54   ` Wang, Haiyue
2021-02-03  2:19 ` [dpdk-dev] [PATCH v2] net/ixgbe: fix UDP zero checksum error Haiyue Wang
2021-02-03  8:07   ` Zhang, Qi Z
2021-02-03  8:32     ` David Marchand
2021-02-04  7:45       ` Zhang, Qi Z
2021-02-04 14:39 ` [dpdk-dev] [PATCH v3] " Haiyue Wang
2021-02-05 17:50   ` Paolo Valerio
2021-02-07 18:40   ` Paolo Valerio
2021-02-08 13:48   ` Ananyev, Konstantin
2021-02-09  1:23     ` Zhang, Qi Z
2021-02-25 10:54   ` [dpdk-dev] [dpdk-stable] " David Marchand
2021-04-07 11:53     ` David Marchand
2021-04-08  1:12       ` Wang, Haiyue

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=20210202070652.145861-1-haiyue.wang@intel.com \
    --to=haiyue.wang@intel.com \
    --cc=Lijuan.Tu@intel.com \
    --cc=aconole@redhat.com \
    --cc=bruce.richardson@intel.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=jia.guo@intel.com \
    --cc=konstantin.ananyev@intel.com \
    --cc=leyi.rong@intel.com \
    --cc=pvalerio@redhat.com \
    --cc=qi.z.zhang@intel.com \
    --cc=stable@dpdk.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

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git