Skip to contentSkip to conversation

dev Digest, Vol 231, Issue 6

DISCUSSION Anudeep Kumar 2 participants 4 messages Jan 21, 2019 1 message not in the archive

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): [email protected]

#1 lore raw

Hi,

I am unable to run l3fwd in dpdk. Please provide steps to run.

Regards,
Anudeep

Quoted 674 lines · On Mon, Jan 21, 2019, 18:49 <[email protected] wrote:

Send dev mailing list submissions to
[email protected]

To subscribe or unsubscribe via the World Wide Web, visit
https://mails.dpdk.org/listinfo/dev
or, via email, send a message with subject or body 'help' to
[email protected]

You can reach the person managing the list at
[email protected]

When replying, please edit your Subject line so it is more specific than "Re: Contents of dev digest..."

Today's Topics:

1. [PATCH v6 2/4] examples/ip_pipeline: support QinQ PPPoE encap
(Nemanja Marjanovic)
2. [PATCH v6 1/4] pipeline: support QinQ PPPoE encap (Nemanja Marjanovic)
3. [PATCH v6 3/4] net/softnic: support QinQ PPPoE encap (Nemanja Marjanovic)
4. [PATCH v6 4/4] net: add PPPoE ethertypes (Nemanja Marjanovic)
5. Re: [PATCH] doc: add deprecation notice to remove rte meter color (Mohammad Abdul Awal)
6. Re: [PATCH] service: fix parameter type (Van Haaren, Harry)
7. Re: [PATCH] vhost: fix possible out of bound access for indirect descs (Maxime Coquelin)
8. Re: IXGBE, IOMMU DMAR DRHD handling fault issue (Hu, Xuekun)

----------------------------------------------------------------------

Message: 1
Date: Mon, 21 Jan 2019 11:11:22 +0000
From: Nemanja Marjanovic <[email protected]>
To: [email protected]
Cc: [email protected], [email protected], "Nemanja
Marjanovic" <[email protected]>
Subject: [dpdk-dev] [PATCH v6 2/4] examples/ip_pipeline: support QinQ
PPPoE encap
Message-ID: <[email protected]>

From: "Nemanja Marjanovic" <[email protected]>

Add implementation of QinQ PPPoE packet encapsulation action.

---
v5:Removing footer from patch.
v6:Added missing acks.

---
 examples/ip_pipeline/cli.c | 46 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 2 deletions(-)
examples/ip_pipeline/cli.c +5 -2
index 910386282..dd05393ef 100644
@@ -1022,7 +1022,7 @@ static const char cmd_table_action_profile_help[] =
 "       tc <n_tc>\n"
 "       stats none | pkts | bytes | both]\n"
 "   [tm spp <n_subports_per_port> pps <n_pipes_per_subport>]\n"
-"   [encap ether | vlan | qinq | mpls | pppoe |\n"
+"   [encap ether | vlan | qinq | mpls | pppoe | qinq_pppoe \n"
 "       vxlan offset <ether_offset> ipv4 | ipv6 vlan on | off]\n"
 "   [nat src | dst\n"
 "       proto udp | tcp]\n"
@@ -1290,7 +1290,10 @@ cmd_table_action_profile(char **tokens,
 
                        p.encap.encap_mask = 1LLU <<
 RTE_TABLE_ACTION_ENCAP_VXLAN;
                        n_extra_tokens = 5;
-               } else {
+               } else if (strcmp(tokens[t0 + 1], "qinq_pppoe") == 0)
+                       p.encap.encap_mask =
+                               1LLU << RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE;
+               else {
                        snprintf(out, out_size, MSG_ARG_MISMATCH, "encap");
                        return;
                }
examples/ip_pipeline/cli.c +1 -0
@@ -3090,6 +3093,7 @@ parse_match(char **tokens,
  *       ether <da> <sa>
  *       | vlan <da> <sa> <pcp> <dei> <vid>
  *       | qinq <da> <sa> <pcp> <dei> <vid> <pcp> <dei> <vid>
+ *       | qinq_pppoe <da> <sa> <pcp> <dei> <vid> <pcp> <dei> <vid>

<session_id>
* | mpls unicast | multicast
* <da> <sa>
* label0 <label> <tc> <ttl>

examples/ip_pipeline/cli.c +38 -0
@@ -3391,6 +3395,44 @@ parse_table_action_encap(char **tokens,
                return 1 + 9;
        }
 
+       /* qinq_pppoe */
+       if (n_tokens && (strcmp(tokens[0], "qinq_pppoe") == 0)) {
+               uint32_t svlan_pcp, svlan_dei, svlan_vid;
+               uint32_t cvlan_pcp, cvlan_dei, cvlan_vid;
+
+               if ((n_tokens < 10) ||
+                       parse_mac_addr(tokens[1],
+                               &a->encap.qinq_pppoe.ether.da) ||
+                       parse_mac_addr(tokens[2],
+                               &a->encap.qinq_pppoe.ether.sa) ||
+                       parser_read_uint32(&svlan_pcp, tokens[3]) ||
+                       (svlan_pcp > 0x7) ||
+                       parser_read_uint32(&svlan_dei, tokens[4]) ||
+                       (svlan_dei > 0x1) ||
+                       parser_read_uint32(&svlan_vid, tokens[5]) ||
+                       (svlan_vid > 0xFFF) ||
+                       parser_read_uint32(&cvlan_pcp, tokens[6]) ||
+                       (cvlan_pcp > 0x7) ||
+                       parser_read_uint32(&cvlan_dei, tokens[7]) ||
+                       (cvlan_dei > 0x1) ||
+                       parser_read_uint32(&cvlan_vid, tokens[8]) ||
+                       (cvlan_vid > 0xFFF) ||
+
 parser_read_uint16(&a->encap.qinq_pppoe.pppoe.session_id,
+                               tokens[9]))
+                       return 0;
+
+               a->encap.qinq_pppoe.svlan.pcp = svlan_pcp & 0x7;
+               a->encap.qinq_pppoe.svlan.dei = svlan_dei & 0x1;
+               a->encap.qinq_pppoe.svlan.vid = svlan_vid & 0xFFF;
+               a->encap.qinq_pppoe.cvlan.pcp = cvlan_pcp & 0x7;
+               a->encap.qinq_pppoe.cvlan.dei = cvlan_dei & 0x1;
+               a->encap.qinq_pppoe.cvlan.vid = cvlan_vid & 0xFFF;
+               a->encap.type = RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE;
+               a->action_mask |= 1 << RTE_TABLE_ACTION_ENCAP;
+               return 1 + 10;
+
+       }
+
        /* mpls */
        if (n_tokens && (strcmp(tokens[0], "mpls") == 0)) {
                uint32_t label, tc, ttl;

--
2.17.1

------------------------------

Message: 2
Date: Mon, 21 Jan 2019 11:11:21 +0000
From: Nemanja Marjanovic <[email protected]>
To: [email protected]
Cc: [email protected], [email protected], "Nemanja
Marjanovic" <[email protected]>
Subject: [dpdk-dev] [PATCH v6 1/4] pipeline: support QinQ PPPoE encap
Message-ID: <[email protected]>

From: "Nemanja Marjanovic" <[email protected]>

Add support of QinQ PPPoE packet encapsulation action.

---
v5:Removing footer from patch.
v6:Added missing acks.

---
 lib/librte_pipeline/rte_table_action.c | 61 ++++++++++++++++++++++++++
 lib/librte_pipeline/rte_table_action.h | 16 +++++++
 2 files changed, 77 insertions(+)
lib/librte_pipeline/rte_table_action.c +11 -0
index 7c7c8dd82..466019934 100644
@@ -432,6 +432,7 @@ encap_valid(enum rte_table_action_encap_type encap)
        case RTE_TABLE_ACTION_ENCAP_MPLS:
        case RTE_TABLE_ACTION_ENCAP_PPPOE:
        case RTE_TABLE_ACTION_ENCAP_VXLAN:
+       case RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE:
                return 1;
        default:
                return 0;
@@ -532,6 +533,13 @@ struct encap_vxlan_ipv6_vlan_data {
        struct vxlan_hdr vxlan;
 } __attribute__((__packed__));
 
+struct encap_qinq_pppoe_data {
+       struct ether_hdr ether;
+       struct vlan_hdr svlan;
+       struct vlan_hdr cvlan;
+       struct pppoe_ppp_hdr pppoe_ppp;
+} __attribute__((__packed__));
+
 static size_t
 encap_data_size(struct rte_table_action_encap_config *encap)
 {
@@ -563,6 +571,9 @@ encap_data_size(struct rte_table_action_encap_config
 *encap)
                        else
                                return sizeof(struct
 encap_vxlan_ipv6_data);
 
+       case 1LLU << RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE:
+                       return sizeof(struct encap_qinq_pppoe_data);
+
        default:
                return 0;
        }
lib/librte_pipeline/rte_table_action.c +3 -0
@@ -599,6 +610,9 @@ encap_apply_check(struct rte_table_action_encap_params
 *p,
        case RTE_TABLE_ACTION_ENCAP_VXLAN:
                return 0;
 
+       case RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE:
+               return 0;
+
        default:
                return -EINVAL;
        }
lib/librte_pipeline/rte_table_action.c +32 -0
@@ -676,6 +690,38 @@ encap_qinq_apply(void *data,
        return 0;
 }
 
+static int
+encap_qinq_pppoe_apply(void *data,
+       struct rte_table_action_encap_params *p)
+{
+       struct encap_qinq_pppoe_data *d = data;
+
+       /* Ethernet */
+       ether_addr_copy(&p->qinq.ether.da, &d->ether.d_addr);
+       ether_addr_copy(&p->qinq.ether.sa, &d->ether.s_addr);
+       d->ether.ether_type = rte_htons(ETHER_TYPE_VLAN);
+
+       /* SVLAN */
+       d->svlan.vlan_tci = rte_htons(VLAN(p->qinq.svlan.pcp,
+               p->qinq.svlan.dei,
+               p->qinq.svlan.vid));
+       d->svlan.eth_proto = rte_htons(ETHER_TYPE_VLAN);
+
+       /* CVLAN */
+       d->cvlan.vlan_tci = rte_htons(VLAN(p->qinq.cvlan.pcp,
+               p->qinq.cvlan.dei,
+               p->qinq.cvlan.vid));
+       d->cvlan.eth_proto = rte_htons(ETHER_TYPE_PPPOE_SESSION);
+
+       /* PPPoE and PPP*/
+       d->pppoe_ppp.ver_type_code = rte_htons(0x1100);
+       d->pppoe_ppp.session_id =
 rte_htons(p->qinq_pppoe.pppoe.session_id);
+       d->pppoe_ppp.length = 0; /* not pre-computed */
+       d->pppoe_ppp.protocol = rte_htons(PPP_PROTOCOL_IP);
+
+       return 0;
+}
+
 static int
 encap_mpls_apply(void *data,

struct rte_table_action_encap_params *p)

lib/librte_pipeline/rte_table_action.c +15 -0
@@ -921,6 +967,9 @@ encap_apply(void *data,
        case RTE_TABLE_ACTION_ENCAP_VXLAN:
                return encap_vxlan_apply(data, p, cfg);
 
+       case RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE:
+               return encap_qinq_pppoe_apply(data, p);
+
        default:
                return -EINVAL;
        }
@@ -1119,6 +1168,18 @@ pkt_work_encap(struct rte_mbuf *mbuf,
                break;
        }
 
+       case 1LLU << RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE:
+       {
+               struct encap_qinq_pppoe_data *qinq_pppoe =
+                       encap(ip, data, sizeof(struct
 encap_qinq_pppoe_data));
+               qinq_pppoe->pppoe_ppp.length = rte_htons(total_length + 2);
+               mbuf->data_off = ip_offset - (sizeof(struct rte_mbuf) +
+                       sizeof(struct encap_qinq_pppoe_data));
+               mbuf->pkt_len = mbuf->data_len = total_length +
+                       sizeof(struct encap_qinq_pppoe_data);
+               break;
+       }
+
        case 1LLU << RTE_TABLE_ACTION_ENCAP_VXLAN:
        {
                if (cfg->vxlan.ip_version)
lib/librte_pipeline/rte_table_action.h +13 -0
index c96061291..53d16af8a 100644
@@ -380,6 +380,9 @@ enum rte_table_action_encap_type {
         * Ether -> { Ether | VLAN | IP | UDP | VXLAN | Ether }
         */
        RTE_TABLE_ACTION_ENCAP_VXLAN,
+
+       /** IP -> { Ether | S-VLAN | C-VLAN | PPPoE | PPP | IP } */
+       RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE,
 };
 
 /** Pre-computed Ethernet header fields for encapsulation action. */
@@ -529,6 +532,16 @@ struct rte_table_action_encap_config {
        };
 };
 
+/** QinQ_PPPoE encap paramaeters. */
+struct rte_table_encap_ether_qinq_pppoe {
+
+       /** Only valid when *type* is set to QinQ. */
+       struct rte_table_action_ether_hdr ether;
+       struct rte_table_action_vlan_hdr svlan; /**< Service VLAN header.
 */
+       struct rte_table_action_vlan_hdr cvlan; /**< Customer VLAN header.
 */
+       struct rte_table_action_pppoe_hdr pppoe; /**< PPPoE/PPP headers. */
+};
+
 /** Encap action parameters (per table rule). */
 struct rte_table_action_encap_params {
        /** Encapsulation type. */
lib/librte_pipeline/rte_table_action.h +3 -1
@@ -553,6 +566,9 @@ struct rte_table_action_encap_params {
 
                /** Only valid when *type* is set to VXLAN. */
                struct rte_table_action_encap_vxlan_params vxlan;
+
+               /** Only valid when *type* is set to QinQ_PPPoE. */
+               struct rte_table_encap_ether_qinq_pppoe qinq_pppoe;
        };
 };
 
--

2.17.1

------------------------------

Message: 3
Date: Mon, 21 Jan 2019 11:11:23 +0000
From: Nemanja Marjanovic <[email protected]>
To: [email protected]
Cc: [email protected], [email protected], "Nemanja
Marjanovic" <[email protected]>
Subject: [dpdk-dev] [PATCH v6 3/4] net/softnic: support QinQ PPPoE
encap
Message-ID: <[email protected]>

From: "Nemanja Marjanovic" <[email protected]>

Add implementation of QinQ PPPoE packet encapsulation action.

---
v5:Removing footer from patch.
v6:Added missing acks.

---
 drivers/net/softnic/rte_eth_softnic_cli.c | 44 ++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)
drivers/net/softnic/rte_eth_softnic_cli.c +1 -1
index 57b623377..c15b57b5b 100644
@@ -1335,7 +1335,7 @@ cmd_port_in_action_profile(struct pmd_internals
 *softnic,
  *      tc <n_tc>
  *      stats none | pkts | bytes | both]
  *  [tm spp <n_subports_per_port> pps <n_pipes_per_subport>]
- *  [encap ether | vlan | qinq | mpls | pppoe |
+ *  [encap ether | vlan | qinq | mpls | pppoe | qinq_pppoe |
  *      vxlan offset <ether_offset> ipv4 | ipv6 vlan on | off]
  *  [nat src | dst

* proto udp | tcp]

drivers/net/softnic/rte_eth_softnic_cli.c +4 -0
@@ -1612,10 +1612,14 @@ cmd_table_action_profile(struct pmd_internals
 *softnic,
                        p.encap.encap_mask = 1LLU <<
 RTE_TABLE_ACTION_ENCAP_VXLAN;
                        n_extra_tokens = 5;
 
+               } else if (strcmp(tokens[t0 + 1], "qinq_pppoe") == 0) {
+                       p.encap.encap_mask =
+                               1LLU << RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE;
                } else {
                        snprintf(out, out_size, MSG_ARG_MISMATCH, "encap");
                        return;
                }
+
                p.action_mask |= 1LLU << RTE_TABLE_ACTION_ENCAP;
                t0 += 2 + n_extra_tokens;
        } /* encap */
drivers/net/softnic/rte_eth_softnic_cli.c +1 -0
@@ -3353,6 +3357,7 @@ parse_match(char **tokens,
  *       ether <da> <sa>
  *       | vlan <da> <sa> <pcp> <dei> <vid>
  *       | qinq <da> <sa> <pcp> <dei> <vid> <pcp> <dei> <vid>
+ *       | qinq_pppoe <da> <sa> <pcp> <dei> <vid> <pcp> <dei> <vid>

<session_id>
* | mpls unicast | multicast
* <da> <sa>
* label0 <label> <tc> <ttl>

drivers/net/softnic/rte_eth_softnic_cli.c +11 -0
@@ -3658,6 +3663,43 @@ parse_table_action_encap(char **tokens,
                return 1 + 9;
        }
 
+       /* qinq_pppoe */
+       if (n_tokens && (strcmp(tokens[0], "qinq_pppoe") == 0)) {
+               uint32_t svlan_pcp, svlan_dei, svlan_vid;
+               uint32_t cvlan_pcp, cvlan_dei, cvlan_vid;
+
+               if (n_tokens < 10 ||
+                       softnic_parse_mac_addr(tokens[1],
+                               &a->encap.qinq_pppoe.ether.da) ||
+                       softnic_parse_mac_addr(tokens[2],
+                               &a->encap.qinq_pppoe.ether.sa) ||
+                       softnic_parser_read_uint32(&svlan_pcp, tokens[3])

||

drivers/net/softnic/rte_eth_softnic_cli.c +2 -0
+                       svlan_pcp > 0x7 ||
+                       softnic_parser_read_uint32(&svlan_dei, tokens[4])

||

drivers/net/softnic/rte_eth_softnic_cli.c +2 -0
+                       svlan_dei > 0x1 ||
+                       softnic_parser_read_uint32(&svlan_vid, tokens[5])

||

drivers/net/softnic/rte_eth_softnic_cli.c +2 -0
+                       svlan_vid > 0xFFF ||
+                       softnic_parser_read_uint32(&cvlan_pcp, tokens[6])

||

drivers/net/softnic/rte_eth_softnic_cli.c +2 -0
+                       cvlan_pcp > 0x7 ||
+                       softnic_parser_read_uint32(&cvlan_dei, tokens[7])

||

drivers/net/softnic/rte_eth_softnic_cli.c +2 -0
+                       cvlan_dei > 0x1 ||
+                       softnic_parser_read_uint32(&cvlan_vid, tokens[8])

||

drivers/net/softnic/rte_eth_softnic_cli.c +16 -1
+                       cvlan_vid > 0xFFF ||
+
 softnic_parser_read_uint16(&a->encap.qinq_pppoe.pppoe.session_id,
+                               tokens[9]))
+                       return 0;
+
+               a->encap.qinq_pppoe.svlan.pcp = svlan_pcp & 0x7;
+               a->encap.qinq_pppoe.svlan.dei = svlan_dei & 0x1;
+               a->encap.qinq_pppoe.svlan.vid = svlan_vid & 0xFFF;
+               a->encap.qinq_pppoe.cvlan.pcp = cvlan_pcp & 0x7;
+               a->encap.qinq_pppoe.cvlan.dei = cvlan_dei & 0x1;
+               a->encap.qinq_pppoe.cvlan.vid = cvlan_vid & 0xFFF;
+               a->encap.type = RTE_TABLE_ACTION_ENCAP_QINQ_PPPOE;
+               a->action_mask |= 1 << RTE_TABLE_ACTION_ENCAP;
+               return 1 + 10;
+       }
+
        /* mpls */
        if (n_tokens && (strcmp(tokens[0], "mpls") == 0)) {
                uint32_t label, tc, ttl;
--

2.17.1

------------------------------

Message: 4
Date: Mon, 21 Jan 2019 11:11:24 +0000
From: Nemanja Marjanovic <[email protected]>
To: [email protected]
Cc: [email protected], [email protected], "Nemanja
Marjanovic" <[email protected]>
Subject: [dpdk-dev] [PATCH v6 4/4] net: add PPPoE ethertypes
Message-ID: <[email protected]>

From: "Nemanja Marjanovic" <[email protected]>

Add PPPoE ethertypes in to rte_ether.h.

---
v5:Removing footer from patch.
v6:Added missing acks.

---
 lib/librte_net/rte_ether.h             | 2 ++
 lib/librte_pipeline/rte_table_action.c | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)
lib/librte_net/rte_ether.h +2 -0
index c2c5e249f..54822df75 100644
@@ -301,6 +301,8 @@ struct vxlan_hdr {
 #define ETHER_TYPE_RARP 0x8035 /**< Reverse Arp Protocol. */
 #define ETHER_TYPE_VLAN 0x8100 /**< IEEE 802.1Q VLAN tagging. */
 #define ETHER_TYPE_QINQ 0x88A8 /**< IEEE 802.1ad QinQ tagging. */
+#define ETHER_TYPE_PPPOE_DISCOVERY 0x8863 /**< PPPoE Discovery Stage. */
+#define ETHER_TYPE_PPPOE_SESSION 0x8864 /**< PPPoE Session Stage. */
 #define ETHER_TYPE_ETAG 0x893F /**< IEEE 802.1BR E-Tag. */
 #define ETHER_TYPE_1588 0x88F7 /**< IEEE 802.1AS 1588 Precise Time

Protocol. */
#define ETHER_TYPE_SLOW 0x8809 /**< Slow protocols (LACP and Marker). */

lib/librte_pipeline/rte_table_action.c +0 -3
index 466019934..ac8109f00 100644
@@ -485,8 +485,6 @@ struct encap_mpls_data {
        uint32_t mpls_count;
 } __attribute__((__packed__));
 
-#define ETHER_TYPE_PPPOE_SESSION                           0x8864
-
 #define PPP_PROTOCOL_IP                                    0x0021
 
 struct pppoe_ppp_hdr {
--

2.17.1

------------------------------

Message: 5
Date: Mon, 21 Jan 2019 11:39:09 +0000
From: Mohammad Abdul Awal <[email protected]>
To: Reshma Pattan <[email protected]>, [email protected]
Cc: [email protected]
Subject: Re: [dpdk-dev] [PATCH] doc: add deprecation notice to remove
rte meter color
Message-ID: <[email protected]>
Content-Type: text/plain; charset=utf-8; format=flowed

Review

Quoted 10 lines · Reshma Pattan

Added deprecation notice to replace rte_meter_color with rte_color.

---
  doc/guides/rel_notes/deprecation.rst | 5 +++++
  1 file changed, 5 insertions(+)
(quoted diff) +0 -0

b/doc/guides/rel_notes/deprecation.rst

doc/guides/rel_notes/deprecation.rst Deprecation Notices · line 109

Quoted 9 lines

index b48486d36..bf1fdf369 100644

doc/guides/rel_notes/deprecation.rst +2 -0
@@ -105,3 +105,8 @@ Deprecation Notices
    - ``rte_pdump_set_socket_dir`` will be removed;
    - The parameter, ``path``, of ``rte_pdump_init`` will be removed;
    - The enum ``rte_pdump_socktype`` will be removed.
+
+* meter: New ``rte_color`` definition will be added in 19.02 and that

will

doc/guides/rel_notes/deprecation.rst Deprecation Notices · line 110

Quoted 1 line
doc/guides/rel_notes/deprecation.rst +1 -0
+  replace ``enum rte_meter_color`` in meter library in 19.05. This will

help

doc/guides/rel_notes/deprecation.rst Deprecation Notices · line 111

Quoted 1 line
doc/guides/rel_notes/deprecation.rst +1 -0
+  to consolidate color definition, which is currently replicated in

many places,

doc/guides/rel_notes/deprecation.rst Deprecation Notices · line 112

Quoted 1 line
doc/guides/rel_notes/deprecation.rst +1 -0
+  such as: rte_meter.h, rte_mtr.h, rte_tm.h.

------------------------------

Message: 6
Date: Mon, 21 Jan 2019 11:43:59 +0000
From: "Van Haaren, Harry" <[email protected]>
To: "Rao, Nikhil" <[email protected]>
Cc: "[email protected]" <[email protected]>
Subject: Re: [dpdk-dev] [PATCH] service: fix parameter type Message-ID:

        <

E923DB57A917B54B9182A2E928D00FA6757C579E@IRSMSX102.ger.corp.intel.com>

Content-Type: text/plain; charset="us-ascii"

Quoted 7 lines

-----Original Message-----
From: Rao, Nikhil
Sent: Saturday, January 19, 2019 2:01 PM
To: Van Haaren, Harry <[email protected]>
Cc: [email protected]; Rao, Nikhil <[email protected]>
Subject: [PATCH] service: fix parameter type

Quoted 8 lines

The type of value parameter to rte_service_attr_get should be uint64_t *, since the attributes are of type uint64_t.

Fixes 4d55194d76a4 ("service: add attribute get function")
Quoted 8 lines
---
 lib/librte_eal/common/include/rte_service.h | 2 +-
 lib/librte_eal/common/rte_service.c         | 2 +-
 test/test/test_service_cores.c              | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

For 19.02, I assume this will require the ABI change announcement. I will post it once this patch is acked.

Correct - this breaks API and ABI, so certainly will need an announce.

Thanks for the fixup, -Harry

------------------------------

Message: 7
Date: Mon, 21 Jan 2019 13:43:55 +0100
From: Maxime Coquelin <[email protected]>
To: Tiwei Bie <[email protected]>, [email protected],
[email protected]
Cc: [email protected], [email protected]
Subject: Re: [dpdk-dev] [PATCH] vhost: fix possible out of bound
access for indirect descs
Message-ID: <[email protected]>
Content-Type: text/plain; charset=utf-8; format=flowed

Quoted 4 lines · Tiwei Bie

Fix a possible out of bound access which may happen when handling indirect descs in split ring.

Fixes 1be4ebb1c464 ("vhost: support indirect descriptor in mergeable

Rx")

Quoted 8 lines
---
  lib/librte_vhost/virtio_net.c | 8 ++------
  1 file changed, 2 insertions(+), 6 deletions(-)

Applide to dpdk-next-virtio/master.

Thanks,
Maxime

------------------------------

Message: 8
Date: Mon, 21 Jan 2019 13:18:57 +0000
From: "Hu, Xuekun" <[email protected]>
To: "Burakov, Anatoly" <[email protected]>, Ravi Kerur
<[email protected]>
Cc: "[email protected]" <[email protected]>, "Ananyev, Konstantin"
<[email protected]>, "Lu, Wenzhuo" <
[email protected]>
Subject: Re: [dpdk-dev] IXGBE, IOMMU DMAR DRHD handling fault issue Message-ID:

        <

88A92D351643BA4CB23E30315517062663547499@SHSMSX103.ccr.corp.intel.com>

Content-Type: text/plain; charset="utf-8"

Quoted 1 line

You might also want to look here:

https://bugs.dpdk.org/show_bug.cgi?id=76

Quoted 1 line

There are apparently issues with some kernel versions that will manifest

themselves as problems with using VF devices with IOMMU in a VM.

Thanks, Anatoly. By updating host kernel to 4.18, the issue is gone. ?

End of dev Digest, Vol 231, Issue 6
***********************************

#2 lore raw
Quoted 13 lines · Anudeep Kumar

Hi,

I am unable to run l3fwd in dpdk. Please provide steps to run.

Regards,
Anudeep

On Mon, Jan 21, 2019, 18:49 <[email protected] wrote:

Please provide much more information as to what the problem is here.

DPDK version used?
What do you mean by l3fwd does not work?
Do you mean you can not compile DPDK or l3fwd?
Does the l3fwd application crash or not execute?
Does is it not find ports?
Does is it not forward?
What is the command line you used to build and run l3fwd plus DPDK?

As you can tell you have left out a huge amount of data for us to help you?

Please provide as much detail as you can, versions, machine, NICS, how you built DPDK, how you are testing l3fwd or the setup / configuration, too little information is bad.

Regards,
Keith

#3 lore raw

Hi Keith,

Thanks for replying,

Now able to run l3fwd application,

But once we run l3fwd application, able to send packets using pktgen,

but if we ping packets unable to reach destination. Why this issue ? Is there any method to ping the Packets to destination?

Regards,
Anudeep

Quoted 36 lines · On Mon, Jan 21, 2019, 21:27 Wiles, Keith <[email protected] wrote:
Quoted 3 lines

On Jan 21, 2019, at 7:23 AM, Anudeep Kumar <[email protected]>

Quoted 10 lines · wrote:

Hi,

I am unable to run l3fwd in dpdk. Please provide steps to run.

Regards,
Anudeep

On Mon, Jan 21, 2019, 18:49 <[email protected] wrote:

Please provide much more information as to what the problem is here.

DPDK version used?
What do you mean by l3fwd does not work?
Do you mean you can not compile DPDK or l3fwd?
Does the l3fwd application crash or not execute?
Does is it not find ports?
Does is it not forward?
What is the command line you used to build and run l3fwd plus DPDK?

As you can tell you have left out a huge amount of data for us to help you?

Please provide as much detail as you can, versions, machine, NICS, how you built DPDK, how you are testing l3fwd or the setup / configuration, too little information is bad.

Regards,
Keith

#4 lore raw

Please do not top post, your response should be inline with the text.

Quoted 12 lines · Anudeep Kumar

Hi Keith,

Thanks for replying,

Now able to run l3fwd application,

But once we run l3fwd application, able to send packets using pktgen,

but if we ping packets unable to reach destination. Why this issue ? Is there any method to ping the Packets to destination?

Did you enable processing incoming packets with ‘enable <portlist> process’?

Enabling this options will effect performance, so turn it off if after you verify that pings are working.

Quoted 30 lines

Regards,
Anudeep

Quoted 11 lines · On Mon, Jan 21, 2019, 21:27 Wiles, Keith <[email protected] wrote:

On Jan 21, 2019, at 7:23 AM, Anudeep Kumar <[email protected]> wrote:

Hi,

I am unable to run l3fwd in dpdk. Please provide steps to run.

Regards,
Anudeep

On Mon, Jan 21, 2019, 18:49 <[email protected] wrote:

Please provide much more information as to what the problem is here.

DPDK version used?
What do you mean by l3fwd does not work?
Do you mean you can not compile DPDK or l3fwd?
Does the l3fwd application crash or not execute?
Does is it not find ports?
Does is it not forward?
What is the command line you used to build and run l3fwd plus DPDK?

Quoted 8 lines

As you can tell you have left out a huge amount of data for us to help you?

Please provide as much detail as you can, versions, machine, NICS, how you built DPDK, how you are testing l3fwd or the setup / configuration, too little information is bad.

Regards,
Keith

Regards,
Keith