| 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
| ||
|
Date: Sun, 23 Apr 2023 07:46:11 -0700
From: John Fastabend <john.fastabend@...il.com>
To: Jesper Dangaard Brouer <brouer@...hat.com>, bpf@...r.kernel.org,
Stanislav Fomichev <sdf@...gle.com>,
Toke Høiland-Jørgensen <toke@...hat.com>
Cc: Jesper Dangaard Brouer <brouer@...hat.com>, 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, yoong.siang.song@...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-next V2 1/5] igc: enable and fix RX hash usage by
netstack
Jesper Dangaard Brouer wrote:
> When function igc_rx_hash() was introduced in v4.20 via commit 0507ef8a0372
> ("igc: Add transmit and receive fastpath and interrupt handlers"), the
> hardware wasn't configured to provide RSS hash, thus it made sense to not
> enable net_device NETIF_F_RXHASH feature bit.
>
> The NIC hardware was configured to enable RSS hash info in v5.2 via commit
> 2121c2712f82 ("igc: Add multiple receive queues control supporting"), but
> forgot to set the NETIF_F_RXHASH feature bit.
>
> The original implementation of igc_rx_hash() didn't extract the associated
> pkt_hash_type, but statically set PKT_HASH_TYPE_L3. The largest portions of
> this patch are about extracting the RSS Type from the hardware and mapping
> this to enum pkt_hash_types. This was based on Foxville i225 software user
> manual rev-1.3.1 and tested on Intel Ethernet Controller I225-LM (rev 03).
>
> For UDP it's worth noting that RSS (type) hashing have been disabled both for
> IPv4 and IPv6 (see IGC_MRQC_RSS_FIELD_IPV4_UDP + IGC_MRQC_RSS_FIELD_IPV6_UDP)
> because hardware RSS doesn't handle fragmented pkts well when enabled (can
> cause out-of-order). This results in PKT_HASH_TYPE_L3 for UDP packets, and
> hash value doesn't include UDP port numbers. Not being PKT_HASH_TYPE_L4, have
> the effect that netstack will do a software based hash calc calling into
> flow_dissect, but only when code calls skb_get_hash(), which doesn't
> necessary happen for local delivery.
>
> For QA verification testing I wrote a small bpftrace prog:
> [0] https://github.com/xdp-project/xdp-project/blob/master/areas/hints/monitor_skb_hash_on_dev.bt
>
> Fixes: 2121c2712f82 ("igc: Add multiple receive queues control supporting")
> Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
> ---
> drivers/net/ethernet/intel/igc/igc.h | 28 ++++++++++++++++++++++++++
> drivers/net/ethernet/intel/igc/igc_main.c | 31 +++++++++++++++++++++++++----
> 2 files changed, 55 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
> index 34aebf00a512..f7f9e217e7b4 100644
> --- a/drivers/net/ethernet/intel/igc/igc.h
> +++ b/drivers/net/ethernet/intel/igc/igc.h
> @@ -13,6 +13,7 @@
> #include <linux/ptp_clock_kernel.h>
> #include <linux/timecounter.h>
> #include <linux/net_tstamp.h>
> +#include <linux/bitfield.h>
>
> #include "igc_hw.h"
>
> @@ -311,6 +312,33 @@ extern char igc_driver_name[];
> #define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000
> #define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000
>
> +/* RX-desc Write-Back format RSS Type's */
> +enum igc_rss_type_num {
> + IGC_RSS_TYPE_NO_HASH = 0,
> + IGC_RSS_TYPE_HASH_TCP_IPV4 = 1,
> + IGC_RSS_TYPE_HASH_IPV4 = 2,
> + IGC_RSS_TYPE_HASH_TCP_IPV6 = 3,
> + IGC_RSS_TYPE_HASH_IPV6_EX = 4,
> + IGC_RSS_TYPE_HASH_IPV6 = 5,
> + IGC_RSS_TYPE_HASH_TCP_IPV6_EX = 6,
> + IGC_RSS_TYPE_HASH_UDP_IPV4 = 7,
> + IGC_RSS_TYPE_HASH_UDP_IPV6 = 8,
> + IGC_RSS_TYPE_HASH_UDP_IPV6_EX = 9,
> + IGC_RSS_TYPE_MAX = 10,
> +};
> +#define IGC_RSS_TYPE_MAX_TABLE 16
> +#define IGC_RSS_TYPE_MASK GENMASK(3,0) /* 4-bits (3:0) = mask 0x0F */
> +
> +/* igc_rss_type - Rx descriptor RSS type field */
> +static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
> +{
> + /* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved)
> + * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info)
> + * is slightly slower than via u32 (wb.lower.lo_dword.data)
> + */
> + return le32_get_bits(rx_desc->wb.lower.lo_dword.data, IGC_RSS_TYPE_MASK);
> +}
> +
> /* Interrupt defines */
> #define IGC_START_ITR 648 /* ~6000 ints/sec */
> #define IGC_4K_ITR 980
> diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
> index 1c4676882082..bfa9768d447f 100644
> --- a/drivers/net/ethernet/intel/igc/igc_main.c
> +++ b/drivers/net/ethernet/intel/igc/igc_main.c
> @@ -1690,14 +1690,36 @@ static void igc_rx_checksum(struct igc_ring *ring,
> le32_to_cpu(rx_desc->wb.upper.status_error));
> }
>
> +/* Mapping HW RSS Type to enum pkt_hash_types */
> +static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {
> + [IGC_RSS_TYPE_NO_HASH] = PKT_HASH_TYPE_L2,
> + [IGC_RSS_TYPE_HASH_TCP_IPV4] = PKT_HASH_TYPE_L4,
> + [IGC_RSS_TYPE_HASH_IPV4] = PKT_HASH_TYPE_L3,
> + [IGC_RSS_TYPE_HASH_TCP_IPV6] = PKT_HASH_TYPE_L4,
> + [IGC_RSS_TYPE_HASH_IPV6_EX] = PKT_HASH_TYPE_L3,
> + [IGC_RSS_TYPE_HASH_IPV6] = PKT_HASH_TYPE_L3,
> + [IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4,
> + [IGC_RSS_TYPE_HASH_UDP_IPV4] = PKT_HASH_TYPE_L4,
> + [IGC_RSS_TYPE_HASH_UDP_IPV6] = PKT_HASH_TYPE_L4,
> + [IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4,
> + [10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW */
> + [11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask */
> + [12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons */
> + [13] = PKT_HASH_TYPE_NONE,
> + [14] = PKT_HASH_TYPE_NONE,
> + [15] = PKT_HASH_TYPE_NONE,
> +};
> +
> static inline void igc_rx_hash(struct igc_ring *ring,
> union igc_adv_rx_desc *rx_desc,
> struct sk_buff *skb)
> {
> - if (ring->netdev->features & NETIF_F_RXHASH)
> - skb_set_hash(skb,
> - le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
> - PKT_HASH_TYPE_L3);
> + if (ring->netdev->features & NETIF_F_RXHASH) {
> + u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
> + u32 rss_type = igc_rss_type(rx_desc);
> +
> + skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]);
Just curious why not copy the logic from the other driver fms10k, ice, ect.
skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
(IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ?
PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3);
avoiding the table logic. Do the driver folks care?
Powered by blists - more mailing lists