DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH] examples/ip_fragmentation: fix fail to send un-fragmented packets
@ 2019-07-10 14:16 Konstantin Ananyev
  2019-07-16 11:26 ` Thomas Monjalon
  2019-07-18 10:11 ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Konstantin Ananyev
  0 siblings, 2 replies; 6+ messages in thread
From: Konstantin Ananyev @ 2019-07-10 14:16 UTC (permalink / raw)
  To: dev; +Cc: Konstantin Ananyev

With latest changes l3fwd_simple_forward() blindly set
(PKT_TX_IPV4 | PKT_TX_IP_CKSUM) ol_flags for all IPv4 packets.
Though for un-fragmented packets we also do have to set l3_len
to make HW IP cksum offload to work properly.
That causes HWi/PMD to drop or generate invalid packets.
Though for un-fragmented packets we don't need to regenerate
IPv4 cksum, as L3 header is not modified.
Fix by setting ol_flags only when required.
Another small fix - don't set IPv4/IPV6 ether type for unknown
packet types.

Fixes: 16863bbb4a41 ("examples/ip_fragmentation: enable IP checksum offload")

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
---
 examples/ip_fragmentation/main.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/examples/ip_fragmentation/main.c b/examples/ip_fragmentation/main.c
index ccaf23ff0..b6a1cf9e5 100644
--- a/examples/ip_fragmentation/main.c
+++ b/examples/ip_fragmentation/main.c
@@ -242,16 +242,21 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 {
 	struct rx_queue *rxq;
 	uint32_t i, len, next_hop;
-	uint8_t ipv6;
-	uint16_t port_out;
+	uint16_t port_out, ether_type;
 	int32_t len2;
+	uint64_t ol_flags;
+	const struct rte_ether_hdr *eth;
 
-	ipv6 = 0;
+	ol_flags = 0;
 	rxq = &qconf->rx_queue_list[queueid];
 
 	/* by default, send everything back to the source port */
 	port_out = port_in;
 
+	/* save ether type of the incoming packet */
+	eth = rte_pktmbuf_mtod(m, const struct rte_ether_hdr *);
+	ether_type = eth->ether_type;
+
 	/* Remove the Ethernet header and trailer from the input packet */
 	rte_pktmbuf_adj(m, (uint16_t)sizeof(struct rte_ether_hdr));
 
@@ -289,6 +294,9 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 			/* Free input packet */
 			rte_pktmbuf_free(m);
 
+			/* request HW to regenerate IPv4 cksum */
+			ol_flags |= (PKT_TX_IPV4 | PKT_TX_IP_CKSUM);
+
 			/* If we fail to fragment the packet */
 			if (unlikely (len2 < 0))
 				return;
@@ -297,8 +305,6 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 		/* if this is an IPv6 packet */
 		struct rte_ipv6_hdr *ip_hdr;
 
-		ipv6 = 1;
-
 		/* Read the lookup key (i.e. ip_dst) from the input packet */
 		ip_hdr = rte_pktmbuf_mtod(m, struct rte_ipv6_hdr *);
 
@@ -348,23 +354,18 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 			rte_panic("No headroom in mbuf.\n");
 		}
 
+		m->ol_flags |= ol_flags;
 		m->l2_len = sizeof(struct rte_ether_hdr);
 
 		/* 02:00:00:00:00:xx */
 		d_addr_bytes = &eth_hdr->d_addr.addr_bytes[0];
-		*((uint64_t *)d_addr_bytes) = 0x000000000002 + ((uint64_t)port_out << 40);
+		*((uint64_t *)d_addr_bytes) = 0x000000000002 +
+			((uint64_t)port_out << 40);
 
 		/* src addr */
 		rte_ether_addr_copy(&ports_eth_addr[port_out],
 				&eth_hdr->s_addr);
-		if (ipv6) {
-			eth_hdr->ether_type =
-				rte_be_to_cpu_16(RTE_ETHER_TYPE_IPV6);
-		} else {
-			eth_hdr->ether_type =
-				rte_be_to_cpu_16(RTE_ETHER_TYPE_IPV4);
-			m->ol_flags |= (PKT_TX_IPV4 | PKT_TX_IP_CKSUM);
-		}
+		eth_hdr->ether_type = ether_type;
 	}
 
 	len += len2;
-- 
2.17.1


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [dpdk-dev] [PATCH] examples/ip_fragmentation: fix fail to send un-fragmented packets
  2019-07-10 14:16 [dpdk-dev] [PATCH] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
@ 2019-07-16 11:26 ` Thomas Monjalon
  2019-07-18 10:11 ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Konstantin Ananyev
  1 sibling, 0 replies; 6+ messages in thread
From: Thomas Monjalon @ 2019-07-16 11:26 UTC (permalink / raw)
  To: Konstantin Ananyev; +Cc: dev, olivier.matz

10/07/2019 16:16, Konstantin Ananyev:
> With latest changes l3fwd_simple_forward() blindly set
> (PKT_TX_IPV4 | PKT_TX_IP_CKSUM) ol_flags for all IPv4 packets.
> Though for un-fragmented packets we also do have to set l3_len
> to make HW IP cksum offload to work properly.
> That causes HWi/PMD to drop or generate invalid packets.
> Though for un-fragmented packets we don't need to regenerate
> IPv4 cksum, as L3 header is not modified.
> Fix by setting ol_flags only when required.
> Another small fix - don't set IPv4/IPV6 ether type for unknown
> packet types.
> 
> Fixes: 16863bbb4a41 ("examples/ip_fragmentation: enable IP checksum offload")

Shouldn't it be 2 separate fixes?




^ permalink raw reply	[flat|nested] 6+ messages in thread

* [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation
  2019-07-10 14:16 [dpdk-dev] [PATCH] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
  2019-07-16 11:26 ` Thomas Monjalon
@ 2019-07-18 10:11 ` Konstantin Ananyev
  2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 1/2] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
                     ` (2 more replies)
  1 sibling, 3 replies; 6+ messages in thread
From: Konstantin Ananyev @ 2019-07-18 10:11 UTC (permalink / raw)
  To: dev; +Cc: Konstantin Ananyev

v1 -> v2
As requested, split one patch into two

Konstantin Ananyev (2):
  examples/ip_fragmentation: fix fail to send un-fragmented packets
  examples/ip_fragmentation: fix set IPv4 for unknown packet types

 examples/ip_fragmentation/main.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

-- 
2.17.1


^ permalink raw reply	[flat|nested] 6+ messages in thread

* [dpdk-dev] [PATCH v2 1/2] examples/ip_fragmentation: fix fail to send un-fragmented packets
  2019-07-18 10:11 ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Konstantin Ananyev
@ 2019-07-18 10:11   ` Konstantin Ananyev
  2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 2/2] examples/ip_fragmentation: fix set IPv4 for unknown packet types Konstantin Ananyev
  2019-07-18 21:10   ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Thomas Monjalon
  2 siblings, 0 replies; 6+ messages in thread
From: Konstantin Ananyev @ 2019-07-18 10:11 UTC (permalink / raw)
  To: dev; +Cc: Konstantin Ananyev

With latest changes l3fwd_simple_forward() blindly set
(PKT_TX_IPV4 | PKT_TX_IP_CKSUM) ol_flags for all IPv4 packets.
Though for un-fragmented packets we also do have to set l3_len
to make HW IP cksum offload to work properly.
That causes HWi/PMD to drop or generate invalid packets.
Though for un-fragmented packets we don't need to regenerate
IPv4 cksum, as L3 header is not modified.
Fix by setting ol_flags only when required.

Fixes: 16863bbb4a41 ("examples/ip_fragmentation: enable IP checksum offload")

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
---
 examples/ip_fragmentation/main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/examples/ip_fragmentation/main.c b/examples/ip_fragmentation/main.c
index ccaf23ff0..c30dd5b5a 100644
--- a/examples/ip_fragmentation/main.c
+++ b/examples/ip_fragmentation/main.c
@@ -245,8 +245,10 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 	uint8_t ipv6;
 	uint16_t port_out;
 	int32_t len2;
+	uint64_t ol_flags;
 
 	ipv6 = 0;
+	ol_flags = 0;
 	rxq = &qconf->rx_queue_list[queueid];
 
 	/* by default, send everything back to the source port */
@@ -289,6 +291,9 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 			/* Free input packet */
 			rte_pktmbuf_free(m);
 
+			/* request HW to regenerate IPv4 cksum */
+			ol_flags |= (PKT_TX_IPV4 | PKT_TX_IP_CKSUM);
+
 			/* If we fail to fragment the packet */
 			if (unlikely (len2 < 0))
 				return;
@@ -348,11 +353,13 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 			rte_panic("No headroom in mbuf.\n");
 		}
 
+		m->ol_flags |= ol_flags;
 		m->l2_len = sizeof(struct rte_ether_hdr);
 
 		/* 02:00:00:00:00:xx */
 		d_addr_bytes = &eth_hdr->d_addr.addr_bytes[0];
-		*((uint64_t *)d_addr_bytes) = 0x000000000002 + ((uint64_t)port_out << 40);
+		*((uint64_t *)d_addr_bytes) = 0x000000000002 +
+			((uint64_t)port_out << 40);
 
 		/* src addr */
 		rte_ether_addr_copy(&ports_eth_addr[port_out],
@@ -363,7 +370,6 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 		} else {
 			eth_hdr->ether_type =
 				rte_be_to_cpu_16(RTE_ETHER_TYPE_IPV4);
-			m->ol_flags |= (PKT_TX_IPV4 | PKT_TX_IP_CKSUM);
 		}
 	}
 
-- 
2.17.1


^ permalink raw reply	[flat|nested] 6+ messages in thread

* [dpdk-dev] [PATCH v2 2/2] examples/ip_fragmentation: fix set IPv4 for unknown packet types
  2019-07-18 10:11 ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Konstantin Ananyev
  2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 1/2] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
@ 2019-07-18 10:11   ` Konstantin Ananyev
  2019-07-18 21:10   ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Thomas Monjalon
  2 siblings, 0 replies; 6+ messages in thread
From: Konstantin Ananyev @ 2019-07-18 10:11 UTC (permalink / raw)
  To: dev; +Cc: Konstantin Ananyev, stable

Right now app blindly set IPv4 ether type for all non IPv6 packets.
Instead we can save and later restore original type value.

Fixes: 74de12b7b63a ("examples/ip_fragmentation: overhaul")
Cc: stable@dpdk.org

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
---
 examples/ip_fragmentation/main.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/examples/ip_fragmentation/main.c b/examples/ip_fragmentation/main.c
index c30dd5b5a..b6a1cf9e5 100644
--- a/examples/ip_fragmentation/main.c
+++ b/examples/ip_fragmentation/main.c
@@ -242,18 +242,21 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 {
 	struct rx_queue *rxq;
 	uint32_t i, len, next_hop;
-	uint8_t ipv6;
-	uint16_t port_out;
+	uint16_t port_out, ether_type;
 	int32_t len2;
 	uint64_t ol_flags;
+	const struct rte_ether_hdr *eth;
 
-	ipv6 = 0;
 	ol_flags = 0;
 	rxq = &qconf->rx_queue_list[queueid];
 
 	/* by default, send everything back to the source port */
 	port_out = port_in;
 
+	/* save ether type of the incoming packet */
+	eth = rte_pktmbuf_mtod(m, const struct rte_ether_hdr *);
+	ether_type = eth->ether_type;
+
 	/* Remove the Ethernet header and trailer from the input packet */
 	rte_pktmbuf_adj(m, (uint16_t)sizeof(struct rte_ether_hdr));
 
@@ -302,8 +305,6 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 		/* if this is an IPv6 packet */
 		struct rte_ipv6_hdr *ip_hdr;
 
-		ipv6 = 1;
-
 		/* Read the lookup key (i.e. ip_dst) from the input packet */
 		ip_hdr = rte_pktmbuf_mtod(m, struct rte_ipv6_hdr *);
 
@@ -364,13 +365,7 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf,
 		/* src addr */
 		rte_ether_addr_copy(&ports_eth_addr[port_out],
 				&eth_hdr->s_addr);
-		if (ipv6) {
-			eth_hdr->ether_type =
-				rte_be_to_cpu_16(RTE_ETHER_TYPE_IPV6);
-		} else {
-			eth_hdr->ether_type =
-				rte_be_to_cpu_16(RTE_ETHER_TYPE_IPV4);
-		}
+		eth_hdr->ether_type = ether_type;
 	}
 
 	len += len2;
-- 
2.17.1


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation
  2019-07-18 10:11 ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Konstantin Ananyev
  2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 1/2] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
  2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 2/2] examples/ip_fragmentation: fix set IPv4 for unknown packet types Konstantin Ananyev
@ 2019-07-18 21:10   ` Thomas Monjalon
  2 siblings, 0 replies; 6+ messages in thread
From: Thomas Monjalon @ 2019-07-18 21:10 UTC (permalink / raw)
  To: Konstantin Ananyev; +Cc: dev

18/07/2019 12:11, Konstantin Ananyev:
> v1 -> v2
> As requested, split one patch into two
> 
> Konstantin Ananyev (2):
>   examples/ip_fragmentation: fix fail to send un-fragmented packets
>   examples/ip_fragmentation: fix set IPv4 for unknown packet types

Applied, thanks




^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2019-07-18 21:10 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-07-10 14:16 [dpdk-dev] [PATCH] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
2019-07-16 11:26 ` Thomas Monjalon
2019-07-18 10:11 ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Konstantin Ananyev
2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 1/2] examples/ip_fragmentation: fix fail to send un-fragmented packets Konstantin Ananyev
2019-07-18 10:11   ` [dpdk-dev] [PATCH v2 2/2] examples/ip_fragmentation: fix set IPv4 for unknown packet types Konstantin Ananyev
2019-07-18 21:10   ` [dpdk-dev] [PATCH v2 0/2] Few fixes for ip_fragmentation Thomas Monjalon

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).