netdev - Re: [PATCH bpf RFC 1/4] xdp: rss hash types representation

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZCNjHAY81gS02FVW@google.com>
Date:   Tue, 28 Mar 2023 14:58:52 -0700
From:   Stanislav Fomichev <sdf@...gle.com>
To:     Jesper Dangaard Brouer <brouer@...hat.com>
Cc:     bpf@...r.kernel.org, netdev@...r.kernel.org, martin.lau@...nel.org,
        ast@...nel.org, daniel@...earbox.net, alexandr.lobakin@...el.com,
        larysa.zaremba@...el.com, xdp-hints@...-project.net,
        anthony.l.nguyen@...el.com, yoong.siang.song@...el.com,
        boon.leong.ong@...el.com, intel-wired-lan@...ts.osuosl.org,
        pabeni@...hat.com, jesse.brandeburg@...el.com, kuba@...nel.org,
        edumazet@...gle.com, john.fastabend@...il.com, hawk@...nel.org,
        davem@...emloft.net
Subject: Re: [PATCH bpf RFC 1/4] xdp: rss hash types representation

On 03/28, Jesper Dangaard Brouer wrote:
> The RSS hash type specifies what portion of packet data NIC hardware used
> when calculating RSS hash value. The RSS types are focused on Internet
> traffic protocols at OSI layers L3 and L4. L2 (e.g. ARP) often get hash
> value zero and no RSS type. For L3 focused on IPv4 vs. IPv6, and L4
> primarily TCP vs UDP, but some hardware supports SCTP.

> Hardware RSS types are differently encoded for each hardware NIC. Most
> hardware represent RSS hash type as a number. Determining L3 vs L4 often
> requires a mapping table as there often isn't a pattern or sorting
> according to ISO layer.

> The patch introduce a XDP RSS hash type (xdp_rss_hash_type) that can both
> be seen as a number that is ordered according by ISO layer, and can be bit
> masked to separate IPv4 and IPv6 types for L4 protocols. Room is available
> for extending later while keeping these properties. This maps and unifies
> difference to hardware specific hashes.

Looks good overall. Any reason we're making this specific layout?
Why not simply the following?

enum {
	XDP_RSS_TYPE_NONE = 0,
	XDP_RSS_TYPE_IPV4 = BIT(0),
	XDP_RSS_TYPE_IPV6 = BIT(1),
	/* IPv6 with extension header. */
	/* let's note ^^^ it in the UAPI? */
	XDP_RSS_TYPE_IPV6_EX = BIT(2),
	XDP_RSS_TYPE_UDP = BIT(3),
	XDP_RSS_TYPE_TCP = BIT(4),
	XDP_RSS_TYPE_SCTP = BIT(5),
}

And then using XDP_RSS_TYPE_IPV4|XDP_RSS_TYPE_UDP vs XDP_RSS_TYPE_IPV6|XXX ?

> This proposal change the kfunc API bpf_xdp_metadata_rx_hash() to return
> this RSS hash type on success.

> Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
> ---
>   include/net/xdp.h |   51  
> +++++++++++++++++++++++++++++++++++++++++++++++++++
>   net/core/xdp.c    |    4 +++-
>   2 files changed, 54 insertions(+), 1 deletion(-)

> diff --git a/include/net/xdp.h b/include/net/xdp.h
> index 5393b3ebe56e..63f462f5ea7f 100644
> --- a/include/net/xdp.h
> +++ b/include/net/xdp.h
> @@ -8,6 +8,7 @@

>   #include <linux/skbuff.h> /* skb_shared_info */
>   #include <uapi/linux/netdev.h>
> +#include <linux/bitfield.h>

>   /**
>    * DOC: XDP RX-queue information
> @@ -396,6 +397,56 @@ XDP_METADATA_KFUNC_xxx
>   MAX_XDP_METADATA_KFUNC,
>   };

> +/* For partitioning of xdp_rss_hash_type */
> +#define RSS_L3		GENMASK(2,0) /* 3-bits = values between 1-7 */
> +#define L4_BIT		BIT(3)       /* 1-bit - L4 indication */
> +#define RSS_L4_IPV4	GENMASK(6,4) /* 3-bits */
> +#define RSS_L4_IPV6	GENMASK(9,7) /* 3-bits */
> +#define RSS_L4		GENMASK(9,3) /* = 7-bits - covering L4 IPV4+IPV6 */
> +#define L4_IPV6_EX_BIT	BIT(9)       /* 1-bit - L4 IPv6 with Extension  
> hdr */
> +				     /* 11-bits in total */
> +
> +/* The XDP RSS hash type (xdp_rss_hash_type) can both be seen as a  
> number that
> + * is ordered according by ISO layer, and can be bit masked to separate  
> IPv4 and
> + * IPv6 types for L4 protocols. Room is available for extending later  
> while
> + * keeping above properties, as this need to cover NIC hardware RSS  
> types.
> + */
> +enum xdp_rss_hash_type {
> +	XDP_RSS_TYPE_NONE            = 0,
> +	XDP_RSS_TYPE_L2              = XDP_RSS_TYPE_NONE,
> +
> +	XDP_RSS_TYPE_L3_MASK         = RSS_L3,
> +	XDP_RSS_TYPE_L3_IPV4         = FIELD_PREP_CONST(RSS_L3, 1),
> +	XDP_RSS_TYPE_L3_IPV6         = FIELD_PREP_CONST(RSS_L3, 2),
> +	XDP_RSS_TYPE_L3_IPV6_EX      = FIELD_PREP_CONST(RSS_L3, 4),
> +
> +	XDP_RSS_TYPE_L4_MASK         = RSS_L4,
> +	XDP_RSS_TYPE_L4_SHIFT        = __bf_shf(RSS_L4),
> +	XDP_RSS_TYPE_L4_MASK_EX      = RSS_L4 | L4_IPV6_EX_BIT,
> +
> +	XDP_RSS_TYPE_L4_IPV4_MASK    = RSS_L4_IPV4,
> +	XDP_RSS_TYPE_L4_BIT          = L4_BIT,
> +	XDP_RSS_TYPE_L4_IPV4_TCP     = L4_BIT|FIELD_PREP_CONST(RSS_L4_IPV4, 1),
> +	XDP_RSS_TYPE_L4_IPV4_UDP     = L4_BIT|FIELD_PREP_CONST(RSS_L4_IPV4, 2),
> +	XDP_RSS_TYPE_L4_IPV4_SCTP    = L4_BIT|FIELD_PREP_CONST(RSS_L4_IPV4, 3),
> +
> +	XDP_RSS_TYPE_L4_IPV6_MASK    = RSS_L4_IPV6,
> +	XDP_RSS_TYPE_L4_IPV6_TCP     = L4_BIT|FIELD_PREP_CONST(RSS_L4_IPV6, 1),
> +	XDP_RSS_TYPE_L4_IPV6_UDP     = L4_BIT|FIELD_PREP_CONST(RSS_L4_IPV6, 2),
> +	XDP_RSS_TYPE_L4_IPV6_SCTP    = L4_BIT|FIELD_PREP_CONST(RSS_L4_IPV6, 3),
> +
> +	XDP_RSS_TYPE_L4_IPV6_EX_MASK = L4_IPV6_EX_BIT,
> +	XDP_RSS_TYPE_L4_IPV6_TCP_EX  = XDP_RSS_TYPE_L4_IPV6_TCP |L4_IPV6_EX_BIT,
> +	XDP_RSS_TYPE_L4_IPV6_UDP_EX  = XDP_RSS_TYPE_L4_IPV6_UDP |L4_IPV6_EX_BIT,
> +	XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP|L4_IPV6_EX_BIT,
> +};
> +#undef RSS_L3
> +#undef L4_BIT
> +#undef RSS_L4_IPV4
> +#undef RSS_L4_IPV6
> +#undef RSS_L4
> +#undef L4_IPV6_EX_BIT
> +
>   #ifdef CONFIG_NET
>   u32 bpf_xdp_metadata_kfunc_id(int id);
>   bool bpf_dev_bound_kfunc_id(u32 btf_id);
> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index 7133017bcd74..81d41df30695 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -721,12 +721,14 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const  
> struct xdp_md *ctx, u64 *tim
>    * @hash: Return value pointer.
>    *
>    * Return:
> - * * Returns 0 on success or ``-errno`` on error.
> + * * Returns (positive) RSS hash **type** on success or ``-errno`` on  
> error.
> + * * ``enum xdp_rss_hash_type`` : RSS hash type
>    * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc
>    * * ``-ENODATA``    : means no RX-hash available for this frame
>    */
>   __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32  
> *hash)
>   {
> +	BTF_TYPE_EMIT(enum xdp_rss_hash_type);
>   	return -EOPNOTSUPP;
>   }