On Wed, Mar 24, 2021 at 3:46 PM Ciara Loftus <ciara.loftus@xxxxxxxxx> wrote:
>
> If the call to socket_create fails, the user may want to retry the
> socket creation using the same umem. Ensure that the umem is in the
> same state on exit if the call failed by restoring the _save pointers
> and not unmapping the set of umem rings if those pointers are non NULL.
>
> Fixes: 2f6324a3937f ("libbpf: Support shared umems between queues and devices")
>
> Signed-off-by: Ciara Loftus <ciara.loftus@xxxxxxxxx>
> ---
> tools/lib/bpf/xsk.c | 29 ++++++++++++++++++-----------
> 1 file changed, 18 insertions(+), 11 deletions(-)
>
> diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
> index 443b0cfb45e8..ec3c23299329 100644
> --- a/tools/lib/bpf/xsk.c
> +++ b/tools/lib/bpf/xsk.c
> @@ -743,21 +743,23 @@ static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
> return NULL;
> }
>
> -static void xsk_put_ctx(struct xsk_ctx *ctx)
> +static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap)
> {
> struct xsk_umem *umem = ctx->umem;
> struct xdp_mmap_offsets off;
> int err;
>
> if (--ctx->refcount == 0) {
> - err = xsk_get_mmap_offsets(umem->fd, &off);
> - if (!err) {
> - munmap(ctx->fill->ring - off.fr.desc,
> - off.fr.desc + umem->config.fill_size *
> - sizeof(__u64));
> - munmap(ctx->comp->ring - off.cr.desc,
> - off.cr.desc + umem->config.comp_size *
> - sizeof(__u64));
> + if (unmap) {
> + err = xsk_get_mmap_offsets(umem->fd, &off);
> + if (!err) {
> + munmap(ctx->fill->ring - off.fr.desc,
> + off.fr.desc + umem->config.fill_size *
> + sizeof(__u64));
> + munmap(ctx->comp->ring - off.cr.desc,
> + off.cr.desc + umem->config.comp_size *
> + sizeof(__u64));
> + }
> }
By not unmapping these rings we actually leave more state after a
failed socket creation. So how about skipping this logic (and
everything below) and always unmap the rings at failure as before, but
we move the fill_save = NULL and comp_save = NULL from xsk_create_ctx
to the end of xsk_socket__create_shared just before the "return 0"
where we know that the whole operation has succeeded. This way the
mappings would be redone during the next xsk_socket__create and if
someone decides not to retry (for some reason) we do not leave two
mappings behind. Would simplify things. What do you think?
>
> list_del(&ctx->list);
> @@ -854,6 +856,9 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
> struct xsk_socket *xsk;
> struct xsk_ctx *ctx;
> int err, ifindex;
> + struct xsk_ring_prod *fsave = umem->fill_save;
> + struct xsk_ring_cons *csave = umem->comp_save;
> + bool unmap = !fsave;
>
> if (!umem || !xsk_ptr || !(rx || tx))
> return -EFAULT;
> @@ -1005,7 +1010,9 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
> munmap(rx_map, off.rx.desc +
> xsk->config.rx_size * sizeof(struct xdp_desc));
> out_put_ctx:
> - xsk_put_ctx(ctx);
> + umem->fill_save = fsave;
> + umem->comp_save = csave;
> + xsk_put_ctx(ctx, unmap);
> out_socket:
> if (--umem->refcount)
> close(xsk->fd);
> @@ -1071,7 +1078,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
> }
> }
>
> - xsk_put_ctx(ctx);
> + xsk_put_ctx(ctx, true);
>
> umem->refcount--;
> /* Do not close an fd that also has an associated umem connected
> --
> 2.17.1
>
