On Wed, Sep 4, 2019 at 8:56 AM Yauheni Kaliuta
<yauheni.kaliuta@xxxxxxxxxx> wrote:
>
> Hi, Magnus!
>
> >>>>> On Wed, 4 Sep 2019 08:39:24 +0200, Magnus Karlsson wrote:
>
> > On Wed, Sep 4, 2019 at 7:32 AM Yauheni Kaliuta
> > <yauheni.kaliuta@xxxxxxxxxx> wrote:
> >>
> >> Hi, Magnus!
> >>
> >> >>>>> On Tue, 9 Apr 2019 08:44:13 +0200, Magnus Karlsson wrote:
> >>
> >> > The use of smp_rmb() and smp_wmb() creates a Linux header dependency
> >> > on barrier.h that is uneccessary in most parts. This patch implements
> >> > the two small defines that are needed from barrier.h. As a bonus, the
> >> > new implementations are faster than the default ones as they default
> >> > to sfence and lfence for x86, while we only need a compiler barrier in
> >> > our case. Just as it is when the same ring access code is compiled in
> >> > the kernel.
> >>
> >> > Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets")
> >> > Signed-off-by: Magnus Karlsson <magnus.karlsson@xxxxxxxxx>
> >> > ---
> >> > tools/lib/bpf/xsk.h | 19 +++++++++++++++++--
> >> > 1 file changed, 17 insertions(+), 2 deletions(-)
> >>
> >> > diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
> >> > index 3638147..317b44f 100644
> >> > --- a/tools/lib/bpf/xsk.h
> >> > +++ b/tools/lib/bpf/xsk.h
> >> > @@ -39,6 +39,21 @@ DEFINE_XSK_RING(xsk_ring_cons);
> >> > struct xsk_umem;
> >> > struct xsk_socket;
> >>
> >> > +#if !defined bpf_smp_rmb && !defined bpf_smp_wmb
> >> > +# if defined(__i386__) || defined(__x86_64__)
> >> > +# define bpf_smp_rmb() asm volatile("" : : : "memory")
> >> > +# define bpf_smp_wmb() asm volatile("" : : : "memory")
> >> > +# elif defined(__aarch64__)
> >> > +# define bpf_smp_rmb() asm volatile("dmb ishld" : : : "memory")
> >> > +# define bpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
> >> > +# elif defined(__arm__)
> >> > +# define bpf_smp_rmb() asm volatile("dmb ish" : : : "memory")
> >> > +# define bpf_smp_wmb() asm volatile("dmb ishst" : : : "memory")
> >> > +# else
> >> > +# error Architecture not supported by the XDP socket code in libbpf.
> >> > +# endif
> >> > +#endif
> >> > +
> >>
> >> What about other architectures then?
>
> > AF_XDP has not been tested on anything else, as far as I
> > know. But contributions that extend it to more archs are very
> > welcome.
>
> Well, I'll may be try to fetch something from barrier.h's (since
> I cannot consider myself as a specialist in the area), but at the
> moment the patch breaks the build on that arches.
Do you have a specific architecture in mind and do you have some
board/server (of that architecture) you could test AF_XDP on?
> > /Magnus
>
> >>
> >> > static inline __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill,
> >> > __u32 idx)
> >> > {
> >> > @@ -119,7 +134,7 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
> >> > /* Make sure everything has been written to the ring before signalling
> >> > * this to the kernel.
> >> > */
> >> > - smp_wmb();
> >> > + bpf_smp_wmb();
> >>
> >> > *prod->producer += nb;
> >> > }
> >> > @@ -133,7 +148,7 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
> >> > /* Make sure we do not speculatively read the data before
> >> > * we have received the packet buffers from the ring.
> >> > */
> >> > - smp_rmb();
> >> > + bpf_smp_rmb();
> >>
> >> > *idx = cons->cached_cons;
> cons-> cached_cons += entries;
> >> > --
> >> > 2.7.4
> >>
> >>
> >> --
> >> WBR,
> >> Yauheni Kaliuta
>
> --
> WBR,
> Yauheni Kaliuta
