| 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
| ||
|
Message-ID: <ZWnk8BVkkbdiEthm@lzaremba-mobl.ger.corp.intel.com>
Date: Fri, 1 Dec 2023 14:51:44 +0100
From: Larysa Zaremba <larysa.zaremba@...el.com>
To: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
CC: <bpf@...r.kernel.org>, <ast@...nel.org>, <daniel@...earbox.net>,
<andrii@...nel.org>, <martin.lau@...ux.dev>, <song@...nel.org>, <yhs@...com>,
<john.fastabend@...il.com>, <kpsingh@...nel.org>, <sdf@...gle.com>,
<haoluo@...gle.com>, <jolsa@...nel.org>, David Ahern <dsahern@...il.com>,
Jakub Kicinski <kuba@...nel.org>, Willem de Bruijn <willemb@...gle.com>,
Jesper Dangaard Brouer <hawk@...nel.org>, Anatoly Burakov
<anatoly.burakov@...el.com>, Alexander Lobakin <alexandr.lobakin@...el.com>,
Magnus Karlsson <magnus.karlsson@...il.com>, Maryam Tahhan
<mtahhan@...hat.com>, <xdp-hints@...-project.net>, <netdev@...r.kernel.org>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>, Alexei Starovoitov
<alexei.starovoitov@...il.com>, Tariq Toukan <tariqt@...lanox.com>, "Saeed
Mahameed" <saeedm@...lanox.com>
Subject: Re: [PATCH bpf-next v7 04/18] ice: Introduce ice_xdp_buff
On Thu, Nov 16, 2023 at 03:55:19AM +0100, Larysa Zaremba wrote:
> On Thu, Nov 16, 2023 at 01:52:24PM +0100, Maciej Fijalkowski wrote:
> > On Wed, Nov 15, 2023 at 06:52:46PM +0100, Larysa Zaremba wrote:
> > > In order to use XDP hints via kfuncs we need to put
> > > RX descriptor and miscellaneous data next to xdp_buff.
> > > Same as in hints implementations in other drivers, we achieve
> > > this through putting xdp_buff into a child structure.
> > >
> > > Currently, xdp_buff is stored in the ring structure,
> > > so replace it with union that includes child structure.
> > > This way enough memory is available while existing XDP code
> > > remains isolated from hints.
> > >
> > > Minimum size of the new child structure (ice_xdp_buff) is exactly
> > > 64 bytes (single cache line). To place it at the start of a cache line,
> > > move 'next' field from CL1 to CL4, as it isn't used often. This still
> > > leaves 192 bits available in CL3 for packet context extensions.
> > >
> > > Signed-off-by: Larysa Zaremba <larysa.zaremba@...el.com>
> > > ---
> > > drivers/net/ethernet/intel/ice/ice_txrx.c | 7 +++++--
> > > drivers/net/ethernet/intel/ice/ice_txrx.h | 18 +++++++++++++++---
> > > drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 10 ++++++++++
> > > 3 files changed, 30 insertions(+), 5 deletions(-)
> > >
> > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
> > > index 40f2f6dabb81..4e6546d9cf85 100644
> > > --- a/drivers/net/ethernet/intel/ice/ice_txrx.c
> > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
> > > @@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
> > > * @xdp_prog: XDP program to run
> > > * @xdp_ring: ring to be used for XDP_TX action
> > > * @rx_buf: Rx buffer to store the XDP action
> > > + * @eop_desc: Last descriptor in packet to read metadata from
> > > *
> > > * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
> > > */
> > > static void
> > > ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
> > > struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
> > > - struct ice_rx_buf *rx_buf)
> > > + struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
> > > {
> > > unsigned int ret = ICE_XDP_PASS;
> > > u32 act;
> > > @@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
> > > if (!xdp_prog)
> > > goto exit;
> > >
> > > + ice_xdp_meta_set_desc(xdp, eop_desc);
> > > +
> > > act = bpf_prog_run_xdp(xdp_prog, xdp);
> > > switch (act) {
> > > case XDP_PASS:
> > > @@ -1240,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
> > > if (ice_is_non_eop(rx_ring, rx_desc))
> > > continue;
> > >
> > > - ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
> > > + ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
> > > if (rx_buf->act == ICE_XDP_PASS)
> > > goto construct_skb;
> > > total_rx_bytes += xdp_get_buff_len(xdp);
> > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > > index 166413fc33f4..9efb42f99415 100644
> > > --- a/drivers/net/ethernet/intel/ice/ice_txrx.h
> > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > > @@ -257,6 +257,14 @@ enum ice_rx_dtype {
> > > ICE_RX_DTYPE_SPLIT_ALWAYS = 2,
> > > };
> > >
> > > +struct ice_xdp_buff {
> > > + struct xdp_buff xdp_buff;
> > > + const union ice_32b_rx_flex_desc *eop_desc;
> > > +};
> > > +
> > > +/* Required for compatibility with xdp_buffs from xsk_pool */
> > > +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
> >
> > That should go to xsk core as a macro and should be used by ZC drivers
> > that support hints. Useful stuff similar to XSK_CEHCK_PRIV_TYPE() but
> > check is from the other end.
>
> Seems like there will be a v8 anyway, so I might as well do this :)
>
After going back and forth about this for a few days, I think this is not a good
idea to include such change into the series.
But I do have to change the comment, this assert is mostly needed,
because my code converts ice_xdp_buff <-> xdp_buff on multiple occasions (and
this flooding code with container_of is not a solution).
Currently, XSK_CHECK_PRIV_TYPE() performs the most important task of ensuring
nothing outside cb[] is overwritten, just fine. Offset check macro could be
added in a separate patch to the xdp header (instead of xsk_buff_pool.h), ice
isn't the only driver relying on xdp_buff inheritance. This will happen only if
I (or someone else) can make such generic macro not look ugly, though.
> >
> > > +
> > > /* indices into GLINT_ITR registers */
> > > #define ICE_RX_ITR ICE_IDX_ITR0
> > > #define ICE_TX_ITR ICE_IDX_ITR1
> > > @@ -298,7 +306,6 @@ enum ice_dynamic_itr {
> > > /* descriptor ring, associated with a VSI */
> > > struct ice_rx_ring {
> > > /* CL1 - 1st cacheline starts here */
> > > - struct ice_rx_ring *next; /* pointer to next ring in q_vector */
> > > void *desc; /* Descriptor ring memory */
> > > struct device *dev; /* Used for DMA mapping */
> > > struct net_device *netdev; /* netdev ring maps to */
> > > @@ -310,12 +317,16 @@ struct ice_rx_ring {
> > > u16 count; /* Number of descriptors */
> > > u16 reg_idx; /* HW register index of the ring */
> > > u16 next_to_alloc;
> > > - /* CL2 - 2nd cacheline starts here */
> > > +
> > > union {
> > > struct ice_rx_buf *rx_buf;
> > > struct xdp_buff **xdp_buf;
> > > };
> > > - struct xdp_buff xdp;
> > > + /* CL2 - 2nd cacheline starts here */
> > > + union {
> > > + struct ice_xdp_buff xdp_ext;
> > > + struct xdp_buff xdp;
> > > + };
> > > /* CL3 - 3rd cacheline starts here */
> > > struct bpf_prog *xdp_prog;
> > > u16 rx_offset;
> > > @@ -332,6 +343,7 @@ struct ice_rx_ring {
> > > /* CL4 - 4th cacheline starts here */
> > > struct ice_channel *ch;
> > > struct ice_tx_ring *xdp_ring;
> > > + struct ice_rx_ring *next; /* pointer to next ring in q_vector */
> > > struct xsk_buff_pool *xsk_pool;
> > > dma_addr_t dma; /* physical address of ring */
> > > u64 cached_phctime;
> > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > > index e1d49e1235b3..81b8856d8e13 100644
> > > --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > > @@ -151,4 +151,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
> > > struct sk_buff *skb);
> > > void
> > > ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
> > > +
> > > +static inline void
> > > +ice_xdp_meta_set_desc(struct xdp_buff *xdp,
> > > + union ice_32b_rx_flex_desc *eop_desc)
> > > +{
> > > + struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
> > > + xdp_buff);
> > > +
> > > + xdp_ext->eop_desc = eop_desc;
> > > +}
> > > #endif /* !_ICE_TXRX_LIB_H_ */
> > > --
> > > 2.41.0
> > >
>
Powered by blists - more mailing lists