DPDK patches and discussions
 help / color / mirror / Atom feed
From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Shiva Shankar Kommula <kshankar@marvell.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"chenbox@nvidia.com" <chenbox@nvidia.com>
Cc: "david.marchand@redhat.com" <david.marchand@redhat.com>,
	Jerin Jacob <jerinj@marvell.com>,
	Nithin Kumar Dabilpuram <ndabilpuram@marvell.com>,
	Srujana Challa <schalla@marvell.com>
Subject: Re: [EXTERNAL] Re: [PATCH v2] net/virtio: add virtio hash report feature
Date: Tue, 4 Mar 2025 13:36:07 +0100	[thread overview]
Message-ID: <71cd5e59-9576-4bad-a748-493953c7ae07@redhat.com> (raw)
In-Reply-To: <b9844729-a2a0-45f9-b0c5-387d0d1e03f2@redhat.com>



On 3/3/25 11:25 AM, Maxime Coquelin wrote:
> 
> 
> On 2/27/25 10:44 AM, Shiva Shankar Kommula wrote:
>>> -----Original Message-----
>>> From: Maxime Coquelin <maxime.coquelin@redhat.com>
>>> Sent: Tuesday, February 25, 2025 9:39 PM
>>> To: Shiva Shankar Kommula <kshankar@marvell.com>; dev@dpdk.org;
>>> chenbox@nvidia.com
>>> Cc: david.marchand@redhat.com; Jerin Jacob <jerinj@marvell.com>; Nithin
>>> Kumar Dabilpuram <ndabilpuram@marvell.com>; Srujana Challa
>>> <schalla@marvell.com>
>>> Subject: [EXTERNAL] Re: [PATCH v2] net/virtio: add virtio hash report 
>>> feature
>>>
>>> Hi, On 1/27/25 8: 41 AM, Kommula Shiva Shankar wrote: > This patch adds
>>> virtio hash report feature, which is > supported in packet queue mode 
>>> with
>>> scalar version Why only restrict to packed ring? isn't it also 
>>> compatible with
>>> split ring?
>>>
>>> Hi,
>>>
>>> On 1/27/25 8:41 AM, Kommula Shiva Shankar wrote:
>>>> This patch adds virtio hash report feature, which is supported in
>>>> packet queue mode with scalar version
>>>
>>> Why only restrict to packed ring? isn't it also compatible with split 
>>> ring?
>> Hi Maxim,
>> Yes, it is. I can add split ring support later if it's alright.
> 
> Ok, I checked the split path and it should not break. But please add its 
> support in next release.
> 
> I see one thing missing in virtio_ethdev.c:
> 
> int
> eth_virtio_dev_init(struct rte_eth_dev *eth_dev)
> {
>      struct virtio_hw *hw = eth_dev->data->dev_private;
>      uint32_t speed = RTE_ETH_SPEED_NUM_UNKNOWN;
>      int vectorized = 0;
>      int ret;
> 
>      if (sizeof(struct virtio_net_hdr_mrg_rxbuf) > RTE_PKTMBUF_HEADROOM) {
>          PMD_INIT_LOG(ERR,
>              "Not sufficient headroom required = %d, avail = %d",
>              (int)sizeof(struct virtio_net_hdr_mrg_rxbuf),
>              RTE_PKTMBUF_HEADROOM);
> 
>          return -1;
>      }
> 
> 
> It should now be checked against virtio_net_hdr_hash_report struct size.


Reviewed-by: Maxime Coquelin <maxime.coquelin@¶edhat.com>

I'll fix above issue while applying.
Please don't forget to add split ring support in next release.

Thanks,
Maxime

> Regards,
> Maxime
> 
>>>
>>>>
>>>> Signed-off-by: Kommula Shiva Shankar <kshankar@marvell.com>
>>>> ---
>>>>    drivers/net/virtio/virtio.h                   |  2 ++
>>>>    drivers/net/virtio/virtio_ethdev.c            | 20 ++++++++++++-
>>>>    drivers/net/virtio/virtio_ethdev.h            |  1 +
>>>>    drivers/net/virtio/virtio_rxtx.c              | 30 ++++++++++++++ 
>>>> +++++
>>>>    .../net/virtio/virtio_user/virtio_user_dev.c  |  1 +
>>>>    drivers/net/virtio/virtqueue.h                | 21 +++++++++++++
>>>>    6 files changed, 74 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/net/virtio/virtio.h b/drivers/net/virtio/virtio.h
>>>> index ef5827c5f5..c2a0fd477c 100644
>>>> --- a/drivers/net/virtio/virtio.h
>>>> +++ b/drivers/net/virtio/virtio.h
>>>> @@ -30,6 +30,7 @@
>>>>    #define VIRTIO_NET_F_GUEST_ANNOUNCE 21    /* Guest can
>>> announce device on the network */
>>>>    #define VIRTIO_NET_F_MQ        22    /* Device supports Receive
>>> Flow Steering */
>>>>    #define VIRTIO_NET_F_CTRL_MAC_ADDR 23    /* Set MAC address */
>>>> +#define VIRTIO_NET_F_HASH_REPORT  57    /* Supports hash report */
>>>>    #define VIRTIO_NET_F_RSS    60    /* RSS supported */
>>>>
>>>>    /*
>>>> @@ -187,6 +188,7 @@ struct virtio_hw {
>>>>        uint8_t started;
>>>>        uint8_t weak_barriers;
>>>>        uint8_t vlan_strip;
>>>> +    uint8_t has_hash_report;
>>>>        bool rx_ol_scatter;
>>>>        uint8_t has_tx_offload;
>>>>        uint8_t has_rx_offload;
>>>> diff --git a/drivers/net/virtio/virtio_ethdev.c
>>>> b/drivers/net/virtio/virtio_ethdev.c
>>>> index 70d4839def..caacbce57a 100644
>>>> --- a/drivers/net/virtio/virtio_ethdev.c
>>>> +++ b/drivers/net/virtio/virtio_ethdev.c
>>>> @@ -1796,7 +1796,9 @@ virtio_init_device(struct rte_eth_dev *eth_dev,
>>> uint64_t req_features)
>>>>            eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC;
>>>>
>>>>        /* Setting up rx_header size for the device */
>>>> -    if (virtio_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) ||
>>>> +    if (virtio_with_feature(hw, VIRTIO_NET_F_HASH_REPORT))
>>>> +        hw->vtnet_hdr_size = sizeof(struct
>>> virtio_net_hdr_hash_report);
>>>> +    else if (virtio_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) ||
>>>>            virtio_with_feature(hw, VIRTIO_F_VERSION_1) ||
>>>>            virtio_with_packed_queue(hw))
>>>>            hw->vtnet_hdr_size = sizeof(struct
>>> virtio_net_hdr_mrg_rxbuf); @@
>>>> -2181,6 +2183,10 @@ virtio_dev_configure(struct rte_eth_dev *dev)
>>>>                (1ULL << VIRTIO_NET_F_GUEST_TSO4) |
>>>>                (1ULL << VIRTIO_NET_F_GUEST_TSO6);
>>>>
>>>> +    if (rx_offloads & RTE_ETH_RX_OFFLOAD_RSS_HASH)
>>>> +        req_features |=
>>>> +            (1ULL << VIRTIO_NET_F_HASH_REPORT);
>>>> +
>>>>        if (tx_offloads & (RTE_ETH_TX_OFFLOAD_UDP_CKSUM |
>>>>                   RTE_ETH_TX_OFFLOAD_TCP_CKSUM))
>>>>            req_features |= (1ULL << VIRTIO_NET_F_CSUM); @@ -2233,6
>>> +2239,9 @@
>>>> virtio_dev_configure(struct rte_eth_dev *dev)
>>>>        if (rx_offloads & RTE_ETH_RX_OFFLOAD_VLAN_STRIP)
>>>>            hw->vlan_strip = 1;
>>>>
>>>> +    if (rx_offloads & RTE_ETH_RX_OFFLOAD_RSS_HASH)
>>>> +        hw->has_hash_report = 1;
>>>> +
>>>>        hw->rx_ol_scatter = (rx_offloads & RTE_ETH_RX_OFFLOAD_SCATTER);
>>>>
>>>>        if ((rx_offloads & RTE_ETH_RX_OFFLOAD_VLAN_FILTER) && @@ -
>>> 2285,6
>>>> +2294,12 @@ virtio_dev_configure(struct rte_eth_dev *dev)
>>>>                        "disabled packed ring vectorized rx for
>>> TCP_LRO enabled");
>>>>                    hw->use_vec_rx = 0;
>>>>                }
>>>> +
>>>> +            if (rx_offloads & RTE_ETH_RX_OFFLOAD_RSS_HASH) {
>>>> +                PMD_DRV_LOG(INFO,
>>>> +                    "disabled packed ring vectorized rx for
>>> RSS_HASH enabled");
>>>> +                hw->use_vec_rx = 0;
>>>> +            }
>>>>            }
>>>>        } else {
>>>>            if (virtio_with_feature(hw, VIRTIO_F_IN_ORDER)) { @@ -
>>> 2669,6
>>>> +2684,9 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct
>>> rte_eth_dev_info *dev_info)
>>>>            dev_info->flow_type_rss_offloads = 0;
>>>>        }
>>>>
>>>> +    if (host_features & (1ULL << VIRTIO_NET_F_HASH_REPORT))
>>>> +        dev_info->rx_offload_capa |=
>>> RTE_ETH_RX_OFFLOAD_RSS_HASH;
>>>> +
>>>>        if (host_features & (1ULL << VIRTIO_F_RING_PACKED)) {
>>>>            /*
>>>>             * According to 2.7 Packed Virtqueues, diff --git
>>>> a/drivers/net/virtio/virtio_ethdev.h
>>>> b/drivers/net/virtio/virtio_ethdev.h
>>>> index 7be1c9acd0..7aa771fd2b 100644
>>>> --- a/drivers/net/virtio/virtio_ethdev.h
>>>> +++ b/drivers/net/virtio/virtio_ethdev.h
>>>> @@ -46,6 +46,7 @@
>>>>         1u << VIRTIO_NET_F_CSUM           |    \
>>>>         1u << VIRTIO_NET_F_HOST_TSO4      |    \
>>>>         1u << VIRTIO_NET_F_HOST_TSO6      |    \
>>>> +     1ULL << VIRTIO_NET_F_HASH_REPORT  |    \
>>>>         1ULL << VIRTIO_NET_F_RSS)
>>>>
>>>>    extern const struct eth_dev_ops virtio_user_secondary_eth_dev_ops;
>>>> diff --git a/drivers/net/virtio/virtio_rxtx.c
>>>> b/drivers/net/virtio/virtio_rxtx.c
>>>> index b67f063b31..35bd61350c 100644
>>>> --- a/drivers/net/virtio/virtio_rxtx.c
>>>> +++ b/drivers/net/virtio/virtio_rxtx.c
>>>> @@ -40,6 +40,19 @@
>>>>    #define  VIRTIO_DUMP_PACKET(m, len) do { } while (0)
>>>>    #endif
>>>>
>>>> +static const uint32_t vhdr_hash_report_to_mbuf_pkt_type[] = {
>>>> +    RTE_PTYPE_UNKNOWN,
>>>> +    RTE_PTYPE_L3_IPV4,
>>>> +    RTE_PTYPE_L3_IPV4 | RTE_PTYPE_L4_TCP,
>>>> +    RTE_PTYPE_L3_IPV4 | RTE_PTYPE_L4_UDP,
>>>> +    RTE_PTYPE_L3_IPV6,
>>>> +    RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_TCP,
>>>> +    RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_UDP,
>>>> +    RTE_PTYPE_L3_IPV6_EXT,
>>>> +    RTE_PTYPE_L3_IPV6_EXT | RTE_PTYPE_L4_TCP,
>>>> +    RTE_PTYPE_L3_IPV6_EXT | RTE_PTYPE_L4_UDP, };
>>>> +
>>>>    void
>>>>    vq_ring_free_inorder(struct virtqueue *vq, uint16_t desc_idx, 
>>>> uint16_t
>>> num)
>>>>    {
>>>> @@ -901,6 +914,16 @@ virtio_discard_rxbuf_inorder(struct virtqueue *vq,
>>> struct rte_mbuf *m)
>>>>        }
>>>>    }
>>>>
>>>> +static inline void
>>>> +virtio_rx_update_hash_report(struct rte_mbuf *m, struct
>>>> +virtio_net_hdr_hash_report *hdr) {
>>>> +    if (likely(hdr->hash_report)) {
>>>> +        m->packet_type = vhdr_hash_report_to_mbuf_pkt_type[hdr-
>>>> hash_report];
>>>> +        m->hash.rss = hdr->hash_value;
>>>> +        m->ol_flags |= RTE_MBUF_F_RX_RSS_HASH;
>>>> +    }
>>>> +}
>>>> +
>>>>    /* Optionally fill offload information in structure */
>>>>    static inline int
>>>>    virtio_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr) @@
>>>> -1134,6 +1157,9 @@ virtio_recv_pkts_packed(void *rx_queue, struct
>>> rte_mbuf **rx_pkts,
>>>>            hdr = (struct virtio_net_hdr *)((char *)rxm->buf_addr +
>>>>                RTE_PKTMBUF_HEADROOM - hdr_size);
>>>>
>>>> +        if (hw->has_hash_report)
>>>> +            virtio_rx_update_hash_report(rxm,
>>>> +                            (struct
>>> virtio_net_hdr_hash_report *)hdr);
>>>>            if (hw->vlan_strip)
>>>>                rte_vlan_strip(rxm);
>>>>
>>>> @@ -1617,6 +1643,10 @@ virtio_recv_mergeable_pkts_packed(void
>>> *rx_queue,
>>>>            if (hw->vlan_strip)
>>>>                rte_vlan_strip(rx_pkts[nb_rx]);
>>>>
>>>> +        if (hw->has_hash_report)
>>>> +            virtio_rx_update_hash_report(rxm,
>>>> +                            (struct
>>> virtio_net_hdr_hash_report *)header);
>>>> +
>>>>            seg_res = seg_num - 1;
>>>>
>>>>            /* Merge remaining segments */
>>>> diff --git a/drivers/net/virtio/virtio_user/virtio_user_dev.c
>>>> b/drivers/net/virtio/virtio_user/virtio_user_dev.c
>>>> index 2997d2bd26..187f81b066 100644
>>>> --- a/drivers/net/virtio/virtio_user/virtio_user_dev.c
>>>> +++ b/drivers/net/virtio/virtio_user/virtio_user_dev.c
>>>> @@ -726,6 +726,7 @@ virtio_user_free_vrings(struct virtio_user_dev 
>>>> *dev)
>>>>         1ULL << VIRTIO_F_RING_PACKED        |    \
>>>>         1ULL << VIRTIO_F_NOTIFICATION_DATA    |    \
>>>>         1ULL << VIRTIO_F_ORDER_PLATFORM        |       \
>>>> +     1ULL << VIRTIO_NET_F_HASH_REPORT       |       \
>>>>         1ULL << VIRTIO_NET_F_RSS)
>>>>
>>>>    int
>>>> diff --git a/drivers/net/virtio/virtqueue.h
>>>> b/drivers/net/virtio/virtqueue.h index 60211a40c9..3b468bd4f4 100644
>>>> --- a/drivers/net/virtio/virtqueue.h
>>>> +++ b/drivers/net/virtio/virtqueue.h
>>>> @@ -257,6 +257,27 @@ struct virtio_net_hdr_mrg_rxbuf {
>>>>        uint16_t num_buffers; /**< Number of merged rx buffers */
>>>>    };
>>>>
>>>> +/**
>>>> + * This is the version of the header to use when the HASH_REPORT
>>>> + * feature has been negotiated.
>>>> + */
>>>> +struct virtio_net_hdr_hash_report {
>>>> +    struct virtio_net_hdr_mrg_rxbuf hdr;
>>>> +    uint32_t hash_value;
>>>> +#define VIRTIO_NET_HASH_REPORT_NONE    0
>>>> +#define VIRTIO_NET_HASH_REPORT_IPV4    1
>>>> +#define VIRTIO_NET_HASH_REPORT_TCPV4    2
>>>> +#define VIRTIO_NET_HASH_REPORT_UDPV4    3
>>>> +#define VIRTIO_NET_HASH_REPORT_IPV6    4
>>>> +#define VIRTIO_NET_HASH_REPORT_TCPV6    5
>>>> +#define VIRTIO_NET_HASH_REPORT_UDPV6    6
>>>> +#define VIRTIO_NET_HASH_REPORT_IPV6_EX    7
>>>> +#define VIRTIO_NET_HASH_REPORT_TCPV6_EX    8
>>>> +#define VIRTIO_NET_HASH_REPORT_UDPV6_EX    9
>>>> +    uint16_t hash_report;
>>>> +    uint16_t pad_reserved;
>>>> +};
>>>> +
>>>>    /* Region reserved to allow for transmit header and indirect ring */
>>>>    #define VIRTIO_MAX_TX_INDIRECT 8
>>>>    struct virtio_tx_region {
>>
> 


  reply	other threads:[~2025-03-04 12:36 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-26 19:34 [PATCH] " Kommula Shiva Shankar
2025-01-27  7:41 ` [PATCH v2] " Kommula Shiva Shankar
2025-02-25 16:09   ` Maxime Coquelin
2025-02-27  9:44     ` [EXTERNAL] " Shiva Shankar Kommula
2025-03-03 10:25       ` Maxime Coquelin
2025-03-04 12:36         ` Maxime Coquelin [this message]
2025-03-04 13:41       ` Maxime Coquelin

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=71cd5e59-9576-4bad-a748-493953c7ae07@redhat.com \
    --to=maxime.coquelin@redhat.com \
    --cc=chenbox@nvidia.com \
    --cc=david.marchand@redhat.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=kshankar@marvell.com \
    --cc=ndabilpuram@marvell.com \
    --cc=schalla@marvell.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).