From: Tariq Toukan <ttoukan.linux@gmail.com>
To: Eric Dumazet <eric.dumazet@gmail.com>,
"David S . Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>
Cc: netdev <netdev@vger.kernel.org>,
Eric Dumazet <edumazet@google.com>,
Coco Li <lixiaoyan@google.com>,
Saeed Mahameed <saeedm@nvidia.com>,
Leon Romanovsky <leon@kernel.org>,
Tariq Toukan <tariqt@nvidia.com>
Subject: Re: [PATCH net-next 15/15] mlx5: support BIG TCP packets
Date: Thu, 3 Feb 2022 09:27:46 +0200 [thread overview]
Message-ID: <3ec9a7cb-433c-41b3-f918-8b5746092482@gmail.com> (raw)
In-Reply-To: <20220203015140.3022854-16-eric.dumazet@gmail.com>
Hi,
Thanks for your patch!
On 2/3/2022 3:51 AM, Eric Dumazet wrote:
> From: Coco Li <lixiaoyan@google.com>
>
> mlx5 supports LSOv2.
>
> IPv6 gro/tcp stacks insert a temporary Hop-by-Hop header
> with JUMBO TLV for big packets.
>
> We need to ignore/skip this HBH header when populating TX descriptor.
>
> Signed-off-by: Coco Li <lixiaoyan@google.com>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Cc: Saeed Mahameed <saeedm@nvidia.com>
> Cc: Leon Romanovsky <leon@kernel.org>
> ---
> .../net/ethernet/mellanox/mlx5/core/en_main.c | 1 +
> .../net/ethernet/mellanox/mlx5/core/en_tx.c | 81 +++++++++++++++----
> 2 files changed, 65 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
> index bf80fb6124499fc4e6a0310ab92c91159b4ccbbb..1c4ce90e5d0f5186c402137b744258ff4ce6a348 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
> @@ -4888,6 +4888,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
>
> netdev->priv_flags |= IFF_UNICAST_FLT;
>
> + netif_set_tso_ipv6_max_size(netdev, 512 * 1024);
> mlx5e_set_netdev_dev_addr(netdev);
> mlx5e_ipsec_build_netdev(priv);
> mlx5e_tls_build_netdev(priv);
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
> index 7fd33b356cc8d191413e8259acd0b26b3ebd6ba9..fc945bd8219dcb69950b1840bb492649c8749976 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
> @@ -40,6 +40,7 @@
> #include "en_accel/en_accel.h"
> #include "en_accel/ipsec_rxtx.h"
> #include "en/ptp.h"
> +#include <net/ipv6.h>
>
> static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
> {
> @@ -241,8 +242,11 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
> sq->stats->csum_none++;
> }
>
> +/* Returns the number of header bytes that we plan
> + * to inline later in the transmit descriptor
> + */
> static inline u16
> -mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
> +mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop)
> {
> struct mlx5e_sq_stats *stats = sq->stats;
> u16 ihs;
> @@ -252,15 +256,18 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
> stats->tso_inner_packets++;
> stats->tso_inner_bytes += skb->len - ihs;
> } else {
> - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
> + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
> ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
> - else
> + } else {
> + if (ipv6_has_hopopt_jumbo(skb))
> + *hopbyhop = sizeof(struct hop_jumbo_hdr);
> ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
> + }
> stats->tso_packets++;
> - stats->tso_bytes += skb->len - ihs;
> + stats->tso_bytes += skb->len - ihs - *hopbyhop;
AFAIU, *hopbyhop is already accounted inside ihs, why decrement it once
more?
Probably it'd be cleaner to assign/fix both ihs and hopbyhop under
ipv6_has_hopopt_jumbo branch():
ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
if (ipv6_has_hopopt_jumbo(skb)) {
*hopbyhop = sizeof(struct hop_jumbo_hdr);
ihs -= sizeof(struct hop_jumbo_hdr);
}
...
stats->tso_bytes += skb->len - ihs - *hopbyhop;
...
return ihs;
> }
>
> - return ihs;
> + return ihs - *hopbyhop;
> }
>
> static inline int
> @@ -319,6 +326,7 @@ struct mlx5e_tx_attr {
> __be16 mss;
> u16 insz;
> u8 opcode;
> + u8 hopbyhop;
> };
>
> struct mlx5e_tx_wqe_attr {
> @@ -355,14 +363,16 @@ static void mlx5e_sq_xmit_prepare(struct mlx5e_txqsq *sq, struct sk_buff *skb,
> struct mlx5e_sq_stats *stats = sq->stats;
>
> if (skb_is_gso(skb)) {
> - u16 ihs = mlx5e_tx_get_gso_ihs(sq, skb);
> + int hopbyhop;
missing init to zero. mlx5e_tx_get_gso_ihs() doesn't always write to it.
> + u16 ihs = mlx5e_tx_get_gso_ihs(sq, skb, &hopbyhop);
>
> *attr = (struct mlx5e_tx_attr) {
> .opcode = MLX5_OPCODE_LSO,
> .mss = cpu_to_be16(skb_shinfo(skb)->gso_size),
> .ihs = ihs,
> .num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs,
> - .headlen = skb_headlen(skb) - ihs,
> + .headlen = skb_headlen(skb) - ihs - hopbyhop,
> + .hopbyhop = hopbyhop,
> };
>
> stats->packets += skb_shinfo(skb)->gso_segs;
> @@ -476,7 +486,8 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
> struct mlx5_wqe_eth_seg *eseg;
> struct mlx5_wqe_data_seg *dseg;
> struct mlx5e_tx_wqe_info *wi;
> -
> + u16 ihs = attr->ihs;
> + struct ipv6hdr *h6;
> struct mlx5e_sq_stats *stats = sq->stats;
> int num_dma;
>
> @@ -490,15 +501,36 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
>
> eseg->mss = attr->mss;
>
> - if (attr->ihs) {
> - if (skb_vlan_tag_present(skb)) {
> - eseg->inline_hdr.sz |= cpu_to_be16(attr->ihs + VLAN_HLEN);
> - mlx5e_insert_vlan(eseg->inline_hdr.start, skb, attr->ihs);
> + if (ihs) {
> + u8 *start = eseg->inline_hdr.start;
> +
> + if (unlikely(attr->hopbyhop)) {
> + /* remove the HBH header.
> + * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
> + */
> + if (skb_vlan_tag_present(skb)) {
> + mlx5e_insert_vlan(start, skb, ETH_HLEN + sizeof(*h6));
> + ihs += VLAN_HLEN;
> + h6 = (struct ipv6hdr *)(start + sizeof(struct vlan_ethhdr));
> + } else {
> + memcpy(start, skb->data, ETH_HLEN + sizeof(*h6));
> + h6 = (struct ipv6hdr *)(start + ETH_HLEN);
> + }
> + h6->nexthdr = IPPROTO_TCP;
> + /* Copy the TCP header after the IPv6 one */
> + memcpy(h6 + 1,
> + skb->data + ETH_HLEN + sizeof(*h6) +
> + sizeof(struct hop_jumbo_hdr),
> + tcp_hdrlen(skb));
> + /* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
You are not using ihs when preparing the inline part of the descriptor,
so this might yield a mismatch between ihs and the sum of the sizes
you're copying above. Is there a guarantee that this won't happen?
> + } else if (skb_vlan_tag_present(skb)) {
> + mlx5e_insert_vlan(start, skb, ihs);
> + ihs += VLAN_HLEN;
> stats->added_vlan_packets++;
> } else {
> - eseg->inline_hdr.sz |= cpu_to_be16(attr->ihs);
> - memcpy(eseg->inline_hdr.start, skb->data, attr->ihs);
> + memcpy(start, skb->data, ihs);
> }
> + eseg->inline_hdr.sz |= cpu_to_be16(ihs);
> dseg += wqe_attr->ds_cnt_inl;
> } else if (skb_vlan_tag_present(skb)) {
> eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN);
> @@ -509,7 +541,7 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
> }
>
> dseg += wqe_attr->ds_cnt_ids;
> - num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr->ihs,
> + num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr->ihs + attr->hopbyhop,
> attr->headlen, dseg);
> if (unlikely(num_dma < 0))
> goto err_drop;
> @@ -1016,12 +1048,27 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
> eseg->mss = attr.mss;
>
> if (attr.ihs) {
> - memcpy(eseg->inline_hdr.start, skb->data, attr.ihs);
> + if (unlikely(attr.hopbyhop)) {
> + /* remove the HBH header.
> + * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
> + */
> + memcpy(eseg->inline_hdr.start, skb->data, ETH_HLEN + sizeof(*h6));
> + h6 = (struct ipv6hdr *)((char *)eseg->inline_hdr.start + ETH_HLEN);
> + h6->nexthdr = IPPROTO_TCP;
> + /* Copy the TCP header after the IPv6 one */
> + memcpy(h6 + 1,
> + skb->data + ETH_HLEN + sizeof(*h6) +
> + sizeof(struct hop_jumbo_hdr),
> + tcp_hdrlen(skb));
> + /* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
> + } else {
> + memcpy(eseg->inline_hdr.start, skb->data, attr.ihs);
> + }
> eseg->inline_hdr.sz = cpu_to_be16(attr.ihs);
> dseg += wqe_attr.ds_cnt_inl;
> }
>
> - num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr.ihs,
> + num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + attr.ihs + attr.hopbyhop,
> attr.headlen, dseg);
> if (unlikely(num_dma < 0))
> goto err_drop;
next prev parent reply other threads:[~2022-02-03 7:27 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-03 1:51 [PATCH net-next 00/15] tcp: BIG TCP implementation Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 01/15] net: add netdev->tso_ipv6_max_size attribute Eric Dumazet
2022-02-03 16:34 ` Jakub Kicinski
2022-02-03 16:56 ` Eric Dumazet
2022-02-03 18:58 ` Jakub Kicinski
2022-02-03 19:12 ` Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 02/15] ipv6: add dev->gso_ipv6_max_size Eric Dumazet
2022-02-03 8:57 ` Paolo Abeni
2022-02-03 15:34 ` Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 03/15] tcp_cubic: make hystart_ack_delay() aware of BIG TCP Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 04/15] ipv6: add struct hop_jumbo_hdr definition Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 05/15] ipv6/gso: remove temporary HBH/jumbo header Eric Dumazet
2022-02-03 18:53 ` Alexander H Duyck
2022-02-03 19:17 ` Eric Dumazet
2022-02-03 19:45 ` Alexander Duyck
2022-02-03 19:59 ` Eric Dumazet
2022-02-03 21:08 ` Alexander H Duyck
2022-02-03 21:41 ` Eric Dumazet
2022-02-04 0:05 ` Alexander Duyck
2022-02-04 0:27 ` Eric Dumazet
2022-02-04 1:14 ` Eric Dumazet
2022-02-04 1:48 ` Eric Dumazet
2022-02-04 2:15 ` Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 06/15] ipv6/gro: insert " Eric Dumazet
2022-02-03 9:19 ` Paolo Abeni
2022-02-03 15:48 ` Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 07/15] ipv6: add GRO_IPV6_MAX_SIZE Eric Dumazet
2022-02-03 2:18 ` Eric Dumazet
2022-02-03 10:44 ` Paolo Abeni
2022-02-03 1:51 ` [PATCH net-next 08/15] ipv6: Add hop-by-hop header to jumbograms in ip6_output Eric Dumazet
2022-02-03 9:07 ` Paolo Abeni
2022-02-03 16:31 ` Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 09/15] net: increase MAX_SKB_FRAGS Eric Dumazet
2022-02-03 5:02 ` kernel test robot
2022-02-03 5:20 ` Eric Dumazet
2022-02-03 5:31 ` Jakub Kicinski
2022-02-03 6:35 ` Eric Dumazet
2022-02-03 5:23 ` kernel test robot
2022-02-03 5:43 ` kernel test robot
2022-02-03 16:01 ` Paolo Abeni
2022-02-03 17:26 ` Alexander H Duyck
2022-02-03 17:34 ` Eric Dumazet
2022-02-03 17:56 ` Alexander Duyck
2022-02-03 19:18 ` Jakub Kicinski
2022-02-03 19:20 ` Eric Dumazet
2022-02-03 19:54 ` Eric Dumazet
2022-02-04 10:18 ` David Laight
2022-02-04 15:46 ` Alexander Duyck
2022-02-03 1:51 ` [PATCH net-next 10/15] net: loopback: enable BIG TCP packets Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 11/15] bonding: update dev->tso_ipv6_max_size Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 12/15] macvlan: enable BIG TCP Packets Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 13/15] ipvlan: " Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 14/15] mlx4: support BIG TCP packets Eric Dumazet
2022-02-03 13:04 ` Tariq Toukan
2022-02-03 15:54 ` Eric Dumazet
2022-02-03 1:51 ` [PATCH net-next 15/15] mlx5: " Eric Dumazet
2022-02-03 7:27 ` Tariq Toukan [this message]
2022-02-04 4:03 ` kernel test robot
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=3ec9a7cb-433c-41b3-f918-8b5746092482@gmail.com \
--to=ttoukan.linux@gmail.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=lixiaoyan@google.com \
--cc=netdev@vger.kernel.org \
--cc=saeedm@nvidia.com \
--cc=tariqt@nvidia.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).