DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Morten Brørup" <mb@smartsharesystems.com>
To: "Olivier Matz" <olivier.matz@6wind.com>, <dev@dpdk.org>
Cc: "Keith Wiles" <keith.wiles@intel.com>,
	"Hongzhi Guo" <guohongzhi1@huawei.com>,
	"Thomas Monjalon" <thomas@monjalon.net>
Subject: Re: [dpdk-dev] [PATCH 3/4] net: introduce functions to verify L4 checksums
Date: Tue, 27 Apr 2021 17:07:04 +0200	[thread overview]
Message-ID: <98CBD80474FA8B44BF855DF32C47DC35C61718@smartserver.smartshare.dk> (raw)
In-Reply-To: <20210427135755.927-4-olivier.matz@6wind.com>

> From: Olivier Matz [mailto:olivier.matz@6wind.com]
> Sent: Tuesday, April 27, 2021 3:58 PM
> 
> Since commit d5df2ae0428a ("net: fix unneeded replacement of TCP
> checksum 0"), the functions rte_ipv4_udptcp_cksum() and
> rte_ipv6_udptcp_cksum() can return either 0x0000 or 0xffff when used to
> verify a packet containing a valid checksum.
> 
> Since these functions should be used to calculate the checksum to set
> in
> a packet, introduce 2 new helpers for checksum verification. They
> return
> 0 if the checksum is valid in the packet.
> 
> Use this new helper in net/tap driver.
> 
> Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
> ---
>  drivers/net/tap/rte_eth_tap.c |   7 +-
>  lib/net/rte_ip.h              | 124 +++++++++++++++++++++++++++-------
>  2 files changed, 104 insertions(+), 27 deletions(-)
> 
> diff --git a/drivers/net/tap/rte_eth_tap.c
> b/drivers/net/tap/rte_eth_tap.c
> index 71282e8065..b14d5a1d55 100644
> --- a/drivers/net/tap/rte_eth_tap.c
> +++ b/drivers/net/tap/rte_eth_tap.c
> @@ -365,11 +365,12 @@ tap_verify_csum(struct rte_mbuf *mbuf)
>  					return;
>  				}
>  			}
> -			cksum = rte_ipv4_udptcp_cksum(l3_hdr, l4_hdr);
> +			cksum_ok = !rte_ipv4_udptcp_cksum_verify(l3_hdr,
> +								 l4_hdr);
>  		} else { /* l3 == RTE_PTYPE_L3_IPV6, checked above */
> -			cksum = rte_ipv6_udptcp_cksum(l3_hdr, l4_hdr);
> +			cksum_ok = !rte_ipv6_udptcp_cksum_verify(l3_hdr,
> +								 l4_hdr);
>  		}
> -		cksum_ok = (cksum == 0) || (cksum == 0xffff);
>  		mbuf->ol_flags |= cksum_ok ?
>  			PKT_RX_L4_CKSUM_GOOD : PKT_RX_L4_CKSUM_BAD;
>  	}
> diff --git a/lib/net/rte_ip.h b/lib/net/rte_ip.h
> index 8c189009b0..ef84bcc5bf 100644
> --- a/lib/net/rte_ip.h
> +++ b/lib/net/rte_ip.h
> @@ -344,20 +344,10 @@ rte_ipv4_phdr_cksum(const struct rte_ipv4_hdr
> *ipv4_hdr, uint64_t ol_flags)
>  }
> 
>  /**
> - * Process the IPv4 UDP or TCP checksum.
> - *
> - * The IP and layer 4 checksum must be set to 0 in the packet by
> - * the caller.
> - *
> - * @param ipv4_hdr
> - *   The pointer to the contiguous IPv4 header.
> - * @param l4_hdr
> - *   The pointer to the beginning of the L4 header.
> - * @return
> - *   The complemented checksum to set in the IP packet.
> + * @internal Calculate the non-complemented IPv4 L4 checksum
>   */
>  static inline uint16_t
> -rte_ipv4_udptcp_cksum(const struct rte_ipv4_hdr *ipv4_hdr, const void
> *l4_hdr)
> +__rte_ipv4_udptcp_cksum(const struct rte_ipv4_hdr *ipv4_hdr, const
> void *l4_hdr)
>  {
>  	uint32_t cksum;
>  	uint32_t l3_len, l4_len;
> @@ -374,16 +364,62 @@ rte_ipv4_udptcp_cksum(const struct rte_ipv4_hdr
> *ipv4_hdr, const void *l4_hdr)
>  	cksum += rte_ipv4_phdr_cksum(ipv4_hdr, 0);
> 
>  	cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
> -	cksum = (~cksum) & 0xffff;
> +
> +	return (uint16_t)cksum;
> +}
> +
> +/**
> + * Process the IPv4 UDP or TCP checksum.
> + *
> + * The IP and layer 4 checksum must be set to 0 in the packet by
> + * the caller.
> + *
> + * @param ipv4_hdr
> + *   The pointer to the contiguous IPv4 header.
> + * @param l4_hdr
> + *   The pointer to the beginning of the L4 header.
> + * @return
> + *   The complemented checksum to set in the IP packet.
> + */
> +static inline uint16_t
> +rte_ipv4_udptcp_cksum(const struct rte_ipv4_hdr *ipv4_hdr, const void
> *l4_hdr)
> +{
> +	uint16_t cksum = __rte_ipv4_udptcp_cksum(ipv4_hdr, l4_hdr);
> +
> +	cksum = ~cksum;
> +
>  	/*
> -	 * Per RFC 768:If the computed checksum is zero for UDP,
> +	 * Per RFC 768: If the computed checksum is zero for UDP,
>  	 * it is transmitted as all ones
>  	 * (the equivalent in one's complement arithmetic).
>  	 */
>  	if (cksum == 0 && ipv4_hdr->next_proto_id == IPPROTO_UDP)
>  		cksum = 0xffff;
> 
> -	return (uint16_t)cksum;
> +	return cksum;
> +}

The GCC static branch predictor treats the above comparison as likely. Playing around with Godbolt, I came up with this alternative:

	if (likely(cksum != 0)) return cksum;
	if (ipv4_hdr->next_proto_id == IPPROTO_UDP) return 0xffff;
	return 0;

> +
> +/**
> + * Validate the IPv4 UDP or TCP checksum.
> + *
> + * @param ipv4_hdr
> + *   The pointer to the contiguous IPv4 header.
> + * @param l4_hdr
> + *   The pointer to the beginning of the L4 header.
> + * @return
> + *   Return 0 if the checksum is correct, else -1.
> + */
> +__rte_experimental
> +static inline int
> +rte_ipv4_udptcp_cksum_verify(const struct rte_ipv4_hdr *ipv4_hdr,
> +			     const void *l4_hdr)
> +{
> +	uint16_t cksum = __rte_ipv4_udptcp_cksum(ipv4_hdr, l4_hdr);
> +
> +	if (cksum != 0xffff)
> +		return -1;

The GCC static branch predictor treats the above comparison as likely, so I would prefer unlikely() around it.

> +
> +	return 0;
>  }
> 
>  /**
> @@ -448,6 +484,25 @@ rte_ipv6_phdr_cksum(const struct rte_ipv6_hdr
> *ipv6_hdr, uint64_t ol_flags)
>  	return __rte_raw_cksum_reduce(sum);
>  }
> 
> +/**
> + * @internal Calculate the non-complemented IPv4 L4 checksum
> + */
> +static inline uint16_t
> +__rte_ipv6_udptcp_cksum(const struct rte_ipv6_hdr *ipv6_hdr, const
> void *l4_hdr)
> +{
> +	uint32_t cksum;
> +	uint32_t l4_len;
> +
> +	l4_len = rte_be_to_cpu_16(ipv6_hdr->payload_len);
> +
> +	cksum = rte_raw_cksum(l4_hdr, l4_len);
> +	cksum += rte_ipv6_phdr_cksum(ipv6_hdr, 0);
> +
> +	cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
> +
> +	return (uint16_t)cksum;
> +}
> +
>  /**
>   * Process the IPv6 UDP or TCP checksum.
>   *
> @@ -464,16 +519,10 @@ rte_ipv6_phdr_cksum(const struct rte_ipv6_hdr
> *ipv6_hdr, uint64_t ol_flags)
>  static inline uint16_t
>  rte_ipv6_udptcp_cksum(const struct rte_ipv6_hdr *ipv6_hdr, const void
> *l4_hdr)
>  {
> -	uint32_t cksum;
> -	uint32_t l4_len;
> -
> -	l4_len = rte_be_to_cpu_16(ipv6_hdr->payload_len);
> +	uint16_t cksum = __rte_ipv6_udptcp_cksum(ipv6_hdr, l4_hdr);
> 
> -	cksum = rte_raw_cksum(l4_hdr, l4_len);
> -	cksum += rte_ipv6_phdr_cksum(ipv6_hdr, 0);
> +	cksum = ~cksum;
> 
> -	cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff);
> -	cksum = (~cksum) & 0xffff;
>  	/*
>  	 * Per RFC 768: If the computed checksum is zero for UDP,
>  	 * it is transmitted as all ones
> @@ -482,7 +531,34 @@ rte_ipv6_udptcp_cksum(const struct rte_ipv6_hdr
> *ipv6_hdr, const void *l4_hdr)
>  	if (cksum == 0 && ipv6_hdr->proto == IPPROTO_UDP)
>  		cksum = 0xffff;

Same comment about GCC static branch prediction as above.

> 
> -	return (uint16_t)cksum;
> +	return cksum;
> +}
> +
> +/**
> + * Validate the IPv6 UDP or TCP checksum.
> + *
> + * The function accepts a 0 checksum, since it can exceptionally
> happen. See 8.1
> + * (Upper-Layer Checksums) in RFC 8200.
> + *
> + * @param ipv6_hdr
> + *   The pointer to the contiguous IPv6 header.
> + * @param l4_hdr
> + *   The pointer to the beginning of the L4 header.
> + * @return
> + *   Return 0 if the checksum is correct, else -1.
> + */
> +__rte_experimental
> +static inline int
> +rte_ipv6_udptcp_cksum_verify(const struct rte_ipv6_hdr *ipv6_hdr,
> +			     const void *l4_hdr)
> +{
> +	uint16_t cksum;
> +
> +	cksum = __rte_ipv6_udptcp_cksum(ipv6_hdr, l4_hdr);
> +	if (cksum != 0xffff)
> +		return -1;

Same comment about GCC static branch prediction as above.

> +
> +	return 0;
>  }
> 
>  /** IPv6 fragment extension header. */
> --
> 2.29.2
> 

With or without my suggested modifications:

Acked-by: Morten Brørup <mb@smartsharesystems.com>

Without my suggested modifications:

Reviewed-by: Morten Brørup <mb@smartsharesystems.com>


  parent reply	other threads:[~2021-04-27 15:07 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-27 13:57 [dpdk-dev] [PATCH 0/4] net/tap: fix Rx cksum Olivier Matz
2021-04-27 13:57 ` [dpdk-dev] [PATCH 1/4] net/tap: fix Rx cksum flags on IP options packets Olivier Matz
2021-04-30 14:48   ` [dpdk-dev] [dpdk-stable] " Ferruh Yigit
2021-06-08 10:13     ` Andrew Rybchenko
2021-06-08 12:29       ` Olivier Matz
2021-06-08 12:34         ` Andrew Rybchenko
2021-06-08 12:49           ` Olivier Matz
2021-06-08 13:57             ` Andrew Rybchenko
2021-06-08 14:30               ` Olivier Matz
2021-04-27 13:57 ` [dpdk-dev] [PATCH 2/4] net/tap: fix Rx cksum flags on TCP packets Olivier Matz
2021-06-08 10:18   ` Andrew Rybchenko
2021-04-27 13:57 ` [dpdk-dev] [PATCH 3/4] net: introduce functions to verify L4 checksums Olivier Matz
2021-04-27 15:02   ` Morten Brørup
2021-04-27 15:07   ` Morten Brørup [this message]
2021-04-28 12:21     ` Olivier Matz
2021-04-28 12:42       ` Morten Brørup
2021-04-30 15:42   ` Ferruh Yigit
2021-06-08 10:23     ` Andrew Rybchenko
2021-06-08 12:29       ` Olivier Matz
2021-06-08 12:39         ` Andrew Rybchenko
2021-06-25 15:38           ` Ferruh Yigit
2021-04-27 13:57 ` [dpdk-dev] [PATCH 4/4] test/cksum: new test for L3/L4 checksum API Olivier Matz
2021-06-30 13:51 ` [dpdk-dev] [PATCH v2 0/4] net/tap: fix Rx cksum Olivier Matz
2021-06-30 13:51   ` [dpdk-dev] [PATCH v2 1/4] net/tap: fix Rx cksum flags on IP options packets Olivier Matz
2021-06-30 13:51   ` [dpdk-dev] [PATCH v2 2/4] net/tap: fix Rx cksum flags on TCP packets Olivier Matz
2021-06-30 13:51   ` [dpdk-dev] [PATCH v2 3/4] net: introduce functions to verify L4 checksums Olivier Matz
2021-06-30 13:51   ` [dpdk-dev] [PATCH v2 4/4] test/cksum: new test for L3/L4 checksum API Olivier Matz
2021-07-01  9:28   ` [dpdk-dev] [PATCH v2 0/4] net/tap: fix Rx cksum Andrew Rybchenko

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=98CBD80474FA8B44BF855DF32C47DC35C61718@smartserver.smartshare.dk \
    --to=mb@smartsharesystems.com \
    --cc=dev@dpdk.org \
    --cc=guohongzhi1@huawei.com \
    --cc=keith.wiles@intel.com \
    --cc=olivier.matz@6wind.com \
    --cc=thomas@monjalon.net \
    /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).