From: John Fastabend <john.fastabend@gmail.com>
To: "Jesper Dangaard Brouer" <jbrouer@redhat.com>,
"John Fastabend" <john.fastabend@gmail.com>,
bpf@vger.kernel.org, "Stanislav Fomichev" <sdf@google.com>,
"Toke Høiland-Jørgensen" <toke@redhat.com>,
"Tony Nguyen" <anthony.l.nguyen@intel.com>
Cc: brouer@redhat.com, netdev@vger.kernel.org, martin.lau@kernel.org,
ast@kernel.org, daniel@iogearbox.net, alexandr.lobakin@intel.com,
larysa.zaremba@intel.com, xdp-hints@xdp-project.net,
yoong.siang.song@intel.com, intel-wired-lan@lists.osuosl.org,
pabeni@redhat.com, jesse.brandeburg@intel.com, kuba@kernel.org,
edumazet@google.com, hawk@kernel.org, davem@davemloft.net
Subject: [xdp-hints] Re: [PATCH bpf-next V2 1/5] igc: enable and fix RX hash usage by netstack
Date: Mon, 24 Apr 2023 12:17:03 -0700 [thread overview]
Message-ID: <6446d5af80e06_338f220820@john.notmuch> (raw)
In-Reply-To: <622a8fa6-ec07-c150-250b-5467b0cddb0c@redhat.com>
Jesper Dangaard Brouer wrote:
>
>
> On 23/04/2023 16.46, John Fastabend wrote:
> > 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@redhat.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);
>
> Detail: This code mis-categorize (e.g. ARP) PKT_HASH_TYPE_L2 as
> PKT_HASH_TYPE_L3, but as core reduces this further to one SKB bit, it
> doesn't really matter.
>
> > avoiding the table logic. Do the driver folks care?
>
> The define IXGBE_RSS_L4_TYPES_MASK becomes the "table" logic as a 1-bit
> true/false table. It is a more compact table, let me know if this is
> preferred.
>
> Yes, it is really upto driver maintainer people to decide, what code is
> preferred ?
Yeah doesn't matter much to me either way. I was just looking at code
compared to ice driver while reviewing.
>
> --Jesper
>
next prev parent reply other threads:[~2023-04-24 19:17 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-18 13:30 [xdp-hints] [PATCH bpf-next V2 0/5] XDP-hints: XDP kfunc metadata for driver igc Jesper Dangaard Brouer
2023-04-18 13:30 ` [xdp-hints] [PATCH bpf-next V2 1/5] igc: enable and fix RX hash usage by netstack Jesper Dangaard Brouer
2023-04-23 14:46 ` [xdp-hints] " John Fastabend
2023-04-24 14:20 ` Jesper Dangaard Brouer
2023-04-24 19:17 ` John Fastabend [this message]
2023-04-25 8:43 ` Jesper Dangaard Brouer
2023-04-25 9:40 ` [xdp-hints] Re: [Intel-wired-lan] " Neftin, Sasha
2023-04-27 17:00 ` [xdp-hints] " Daniel Borkmann
2023-04-28 10:13 ` Jesper Dangaard Brouer
2023-04-18 13:30 ` [xdp-hints] [PATCH bpf-next V2 2/5] igc: add igc_xdp_buff wrapper for xdp_buff in driver Jesper Dangaard Brouer
2023-04-18 13:30 ` [xdp-hints] [PATCH bpf-next V2 3/5] igc: add XDP hints kfuncs for RX hash Jesper Dangaard Brouer
2023-04-18 13:30 ` [xdp-hints] [PATCH bpf-next V2 4/5] igc: add XDP hints kfuncs for RX timestamp Jesper Dangaard Brouer
2023-04-18 13:31 ` [xdp-hints] [PATCH bpf-next V2 5/5] selftests/bpf: xdp_hw_metadata track more timestamps Jesper Dangaard Brouer
2023-04-18 16:36 ` [xdp-hints] " Stanislav Fomichev
2023-04-19 16:41 ` Jesper Dangaard Brouer
2023-04-18 14:53 ` [xdp-hints] Re: [PATCH bpf-next V2 0/5] XDP-hints: XDP kfunc metadata for driver igc Song, Yoong Siang
2023-04-21 14:52 ` Daniel Borkmann
2023-04-24 2:14 ` Song, Yoong Siang
2023-04-27 17:00 ` patchwork-bot+netdevbpf
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
List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6446d5af80e06_338f220820@john.notmuch \
--to=john.fastabend@gmail.com \
--cc=alexandr.lobakin@intel.com \
--cc=anthony.l.nguyen@intel.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brouer@redhat.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=jbrouer@redhat.com \
--cc=jesse.brandeburg@intel.com \
--cc=kuba@kernel.org \
--cc=larysa.zaremba@intel.com \
--cc=martin.lau@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sdf@google.com \
--cc=toke@redhat.com \
--cc=xdp-hints@xdp-project.net \
--cc=yoong.siang.song@intel.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