[xdp-hints] Re: [PATCH bpf-next v2 06/20] ice: Support HW timestamp hint

[Larysa Zaremba <larysa.zaremba@intel.com>]

On Wed, Jul 05, 2023 at 10:30:56AM -0700, Stanislav Fomichev wrote:
> On 07/03, Larysa Zaremba wrote:
> > Use previously refactored code and create a function
> > that allows XDP code to read HW timestamp.
> > 
> > Also, move cached_phctime into packet context, this way this data still
> > stays in the ring structure, just at the different address.
> > 
> > HW timestamp is the first supported hint in the driver,
> > so also add xdp_metadata_ops.
> > 
> > Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
> > ---
> >  drivers/net/ethernet/intel/ice/ice.h          |  2 ++
> >  drivers/net/ethernet/intel/ice/ice_ethtool.c  |  2 +-
> >  drivers/net/ethernet/intel/ice/ice_lib.c      |  2 +-
> >  drivers/net/ethernet/intel/ice/ice_main.c     |  1 +
> >  drivers/net/ethernet/intel/ice/ice_ptp.c      |  2 +-
> >  drivers/net/ethernet/intel/ice/ice_txrx.h     |  2 +-
> >  drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 24 +++++++++++++++++++
> >  7 files changed, 31 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
> > index 4ba3d99439a0..7a973a2229f1 100644
> > --- a/drivers/net/ethernet/intel/ice/ice.h
> > +++ b/drivers/net/ethernet/intel/ice/ice.h
> > @@ -943,4 +943,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
> >  	set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags);
> >  	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
> >  }
> > +
> > +extern const struct xdp_metadata_ops ice_xdp_md_ops;
> >  #endif /* _ICE_H_ */
> > diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
> > index 8d5cbbd0b3d5..3c3b9cbfbcd3 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
> > @@ -2837,7 +2837,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
> >  		/* clone ring and setup updated count */
> >  		rx_rings[i] = *vsi->rx_rings[i];
> >  		rx_rings[i].count = new_rx_cnt;
> > -		rx_rings[i].cached_phctime = pf->ptp.cached_phc_time;
> > +		rx_rings[i].pkt_ctx.cached_phctime = pf->ptp.cached_phc_time;
> >  		rx_rings[i].desc = NULL;
> >  		rx_rings[i].rx_buf = NULL;
> >  		/* this is to allow wr32 to have something to write to
> > diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
> > index 00e3afd507a4..eb69b0ac7956 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_lib.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_lib.c
> > @@ -1445,7 +1445,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
> >  		ring->netdev = vsi->netdev;
> >  		ring->dev = dev;
> >  		ring->count = vsi->num_rx_desc;
> > -		ring->cached_phctime = pf->ptp.cached_phc_time;
> > +		ring->pkt_ctx.cached_phctime = pf->ptp.cached_phc_time;
> >  		WRITE_ONCE(vsi->rx_rings[i], ring);
> >  	}
> >  
> > diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
> > index 93979ab18bc1..f21996b812ea 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_main.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_main.c
> > @@ -3384,6 +3384,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
> >  
> >  	netdev->netdev_ops = &ice_netdev_ops;
> >  	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
> > +	netdev->xdp_metadata_ops = &ice_xdp_md_ops;
> >  	ice_set_ethtool_ops(netdev);
> >  
> >  	if (vsi->type != ICE_VSI_PF)
> > diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
> > index a31333972c68..70697e4829dd 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_ptp.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
> > @@ -1038,7 +1038,7 @@ static int ice_ptp_update_cached_phctime(struct ice_pf *pf)
> >  		ice_for_each_rxq(vsi, j) {
> >  			if (!vsi->rx_rings[j])
> >  				continue;
> > -			WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime);
> > +			WRITE_ONCE(vsi->rx_rings[j]->pkt_ctx.cached_phctime, systime);
> >  		}
> >  	}
> >  	clear_bit(ICE_CFG_BUSY, pf->state);
> > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > index d0ab2c4c0c91..4237702a58a9 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_txrx.h
> > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > @@ -259,6 +259,7 @@ enum ice_rx_dtype {
> >  
> >  struct ice_pkt_ctx {
> >  	const union ice_32b_rx_flex_desc *eop_desc;
> > +	u64 cached_phctime;
> >  };
> >  
> >  struct ice_xdp_buff {
> > @@ -354,7 +355,6 @@ struct ice_rx_ring {
> >  	struct ice_tx_ring *xdp_ring;
> >  	struct xsk_buff_pool *xsk_pool;
> >  	dma_addr_t dma;			/* physical address of ring */
> > -	u64 cached_phctime;
> >  	u16 rx_buf_len;
> >  	u8 dcb_tc;			/* Traffic class of ring */
> >  	u8 ptp_rx;
> > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
> > index beb1c5bb392a..463d9e5cbe05 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
> > @@ -546,3 +546,27 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
> >  			spin_unlock(&xdp_ring->tx_lock);
> >  	}
> >  }
> > +
> > +/**
> > + * ice_xdp_rx_hw_ts - HW timestamp XDP hint handler
> > + * @ctx: XDP buff pointer
> > + * @ts_ns: destination address
> > + *
> > + * Copy HW timestamp (if available) to the destination address.
> > + */
> > +static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
> > +{
> > +	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
> > +	u64 cached_time;
> > +
> > +	cached_time = READ_ONCE(xdp_ext->pkt_ctx.cached_phctime);
> 
> I believe we have to have something like the following here:
> 
> if (!ts_ns)
> 	return -EINVAL;
> 
> IOW, I don't think verifier guarantees that those pointer args are
> non-NULL.

Oh, that's a shame.

> Same for the other ice kfunc you're adding and veth changes.
> 
> Can you also fix it for the existing veth kfuncs? (or lmk if you prefer me
> to fix it).

I think I can send fixes for RX hash and timestamp in veth separately, before 
v3 of this patchset, code probably doesn't intersect.

But argument checks in kfuncs are a little bit a gray area for me, whether they 
should be sent to stable tree or not?