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.
> /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
