linux-kernel - Re: [Intel-wired-lan] [PATCH v4] ixgbe: let the xdpdrv work with more than 64 cpus

Open Source and information security mailing list archives

Message-ID: <20210826173733.GA35972@ranger.igk.intel.com>
Date:   Thu, 26 Aug 2021 19:37:33 +0200
From:   Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To:     Jason Xing <kerneljasonxing@...il.com>
Cc:     Jesse Brandeburg <jesse.brandeburg@...el.com>,
        songliubraving@...com, kafai@...com,
        Eric Dumazet <eric.dumazet@...il.com>, daniel@...earbox.net,
        Jason Xing <xingwanli@...ishou.com>,
        netdev <netdev@...r.kernel.org>, ast@...nel.org,
        andrii@...nel.org, Shujin Li <lishujin@...ishou.com>, yhs@...com,
        kpsingh@...nel.org, kuba@...nel.org, bpf@...r.kernel.org,
        intel-wired-lan@...ts.osuosl.org,
        David Miller <davem@...emloft.net>,
        LKML <linux-kernel@...r.kernel.org>, hawk@...nel.org
Subject: Re: [Intel-wired-lan] [PATCH v4] ixgbe: let the xdpdrv work with
 more than 64 cpus

On Fri, Aug 27, 2021 at 01:03:16AM +0800, Jason Xing wrote:
> On Fri, Aug 27, 2021 at 12:41 AM Jesse Brandeburg
> <jesse.brandeburg@...el.com> wrote:
> >
> > On 8/26/2021 9:18 AM, Eric Dumazet wrote:
> >
> > >> +static inline int ixgbe_determine_xdp_q_idx(int cpu)
> > >> +{
> > >> +    if (static_key_enabled(&ixgbe_xdp_locking_key))
> > >> +            return cpu % IXGBE_MAX_XDP_QS;
> > >> +    else
> > >> +            return cpu;
> > >
> > > Even if num_online_cpus() is 8, the returned cpu here could be
> > >
> > > 0, 32, 64, 96, 128, 161, 197, 224
> > >
> > > Are we sure this will still be ok ?
> >
> > I'm not sure about that one myself. Jason?

I meant num_possible_cpus(), Jason should have yelled at me in the first
place, sorry. Lack of coffee probably. We use num_possible_cpus() on ice
side.

> >
> > >
> > >> +}
> > >> +
> > >>  static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
> > >>  {
> > >>      switch (adapter->hw.mac.type) {
> > >> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
> > >> index 0218f6c..884bf99 100644
> > >> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
> > >> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
> > >> @@ -299,7 +299,10 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter)
> > >>
> > >>  static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter)
> > >>  {
> > >> -    return adapter->xdp_prog ? nr_cpu_ids : 0;
> > >> +    int queues;
> > >> +
> > >> +    queues = min_t(int, IXGBE_MAX_XDP_QS, num_online_cpus());
> > >
> > > num_online_cpus() might change later...
> >
> > I saw that too, but I wonder if it doesn't matter to the driver. If a
> > CPU goes offline or comes online after the driver loads, we will use
> > this logic to try to pick an available TX queue. But this is a
> > complicated thing that is easy to get wrong, is there a common example
> > of how to get it right?
> >
> 
> Honestly, I'm a little confused right now. @nr_cpu_ids is the fixed
> number which means the total number of cpus the machine has.
> I think, using @nr_cpu_ids is safe one way or the other regardless of
> whether the cpu goes offline or not. What do you think?
> 
> > A possible problem I guess is that if the "static_key_enabled" check
> > returned false in the past, we would need to update that if the number
> > of CPUs changes, do we need a notifier?
> >
> 
> Things get complicated. If the number decreases down to
> @IXGBE_MAX_XDP_QS (which is 64), the notifier could be useful because
> we wouldn't need to use the @tx_lock. I'm wondering if we really need
> to implement one notifier for this kind of change?
> 
> > Also, now that I'm asking it, I dislike the global as it would apply to
> > all ixgbe ports and each PF would increment and decrement it
> > independently. Showing my ignorance here, but I haven't seen this
> > utility in the kernel before in detail. Not sure if this is "OK" from
> > multiple device (with the same driver / global namespace) perspective.

I'm not sure if there's a flawless solution to that. static key approach
won't have an impact for < 64 cpus systems but if you trigger this on one
PF then rest of the PFs that this driver is serving will be affected.

OTOH see the discussion I had with Toke on a different approach:
https://lore.kernel.org/bpf/20210601113236.42651-3-maciej.fijalkowski@intel.com/

> >
> _______________________________________________
> Intel-wired-lan mailing list
> Intel-wired-lan@...osl.org
> https://lists.osuosl.org/mailman/listinfo/intel-wired-lan

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