bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Magnus Karlsson <magnus.karlsson@gmail.com>
To: Mariusz Dudek <mariusz.dudek@gmail.com>
Cc: "Andrii Nakryiko" <andrii.nakryiko@gmail.com>,
	"Karlsson, Magnus" <magnus.karlsson@intel.com>,
	"Björn Töpel" <bjorn.topel@intel.com>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Network Development" <netdev@vger.kernel.org>,
	"Jonathan Lemon" <jonathan.lemon@gmail.com>,
	bpf <bpf@vger.kernel.org>,
	"Mariusz Dudek" <mariuszx.dudek@intel.com>
Subject: Re: [PATCH v5 bpf-next 1/2] libbpf: separate XDP program load with xsk socket creation
Date: Fri, 27 Nov 2020 10:06:45 +0100	[thread overview]
Message-ID: <CAJ8uoz1TkEQ0-YJmqHaOULKvTGKbvfuMNB9c71vE-39RM6YvJw@mail.gmail.com> (raw)
In-Reply-To: <20201127082601.4762-2-mariuszx.dudek@intel.com>

On Fri, Nov 27, 2020 at 9:52 AM <mariusz.dudek@gmail.com> wrote:
>
> From: Mariusz Dudek <mariuszx.dudek@intel.com>
>
> Add support for separation of eBPF program load and xsk socket
> creation.
>
> This is needed for use-case when you want to privide as little
> privileges as possible to the data plane application that will
> handle xsk socket creation and incoming traffic.
>
> With this patch the data entity container can be run with only
> CAP_NET_RAW capability to fulfill its purpose of creating xsk
> socket and handling packages. In case your umem is larger or
> equal process limit for MEMLOCK you need either increase the
> limit or CAP_IPC_LOCK capability.
>
> To resolve privileges issue two APIs are introduced:
>
> - xsk_setup_xdp_prog - loads the built in XDP program. It can
> also return xsks_map_fd which is needed by unprivileged process
> to update xsks_map with AF_XDP socket "fd"
>
> - xsk_socket__update_xskmap - inserts an AF_XDP socket into an xskmap
> for a particular xsk_socket
>
> Signed-off-by: Mariusz Dudek <mariuszx.dudek@intel.com>
> ---
>  tools/lib/bpf/libbpf.map |  2 +
>  tools/lib/bpf/xsk.c      | 92 ++++++++++++++++++++++++++++++++++++----
>  tools/lib/bpf/xsk.h      |  5 +++
>  3 files changed, 90 insertions(+), 9 deletions(-)

Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>

> diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
> index 29ff4807b909..d939d5ac092e 100644
> --- a/tools/lib/bpf/libbpf.map
> +++ b/tools/lib/bpf/libbpf.map
> @@ -345,4 +345,6 @@ LIBBPF_0.3.0 {
>                 btf__parse_split;
>                 btf__new_empty_split;
>                 btf__new_split;
> +               xsk_setup_xdp_prog;
> +               xsk_socket__update_xskmap;
>  } LIBBPF_0.2.0;
> diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
> index 9bc537d0b92d..4b051ec7cfbb 100644
> --- a/tools/lib/bpf/xsk.c
> +++ b/tools/lib/bpf/xsk.c
> @@ -566,8 +566,35 @@ static int xsk_set_bpf_maps(struct xsk_socket *xsk)
>                                    &xsk->fd, 0);
>  }
>
> -static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
> +static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
>  {
> +       char ifname[IFNAMSIZ];
> +       struct xsk_ctx *ctx;
> +       char *interface;
> +
> +       ctx = calloc(1, sizeof(*ctx));
> +       if (!ctx)
> +               return -ENOMEM;
> +
> +       interface = if_indextoname(ifindex, &ifname[0]);
> +       if (!interface) {
> +               free(ctx);
> +               return -errno;
> +       }
> +
> +       ctx->ifindex = ifindex;
> +       strncpy(ctx->ifname, ifname, IFNAMSIZ - 1);
> +       ctx->ifname[IFNAMSIZ - 1] = 0;
> +
> +       xsk->ctx = ctx;
> +
> +       return 0;
> +}
> +
> +static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
> +                               int *xsks_map_fd)
> +{
> +       struct xsk_socket *xsk = _xdp;
>         struct xsk_ctx *ctx = xsk->ctx;
>         __u32 prog_id = 0;
>         int err;
> @@ -584,8 +611,7 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
>
>                 err = xsk_load_xdp_prog(xsk);
>                 if (err) {
> -                       xsk_delete_bpf_maps(xsk);
> -                       return err;
> +                       goto err_load_xdp_prog;
>                 }
>         } else {
>                 ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
> @@ -598,15 +624,29 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
>                 }
>         }
>
> -       if (xsk->rx)
> +       if (xsk->rx) {
>                 err = xsk_set_bpf_maps(xsk);
> -       if (err) {
> -               xsk_delete_bpf_maps(xsk);
> -               close(ctx->prog_fd);
> -               return err;
> +               if (err) {
> +                       if (!prog_id) {
> +                               goto err_set_bpf_maps;
> +                       } else {
> +                               close(ctx->prog_fd);
> +                               return err;
> +                       }
> +               }
>         }
> +       if (xsks_map_fd)
> +               *xsks_map_fd = ctx->xsks_map_fd;
>
>         return 0;
> +
> +err_set_bpf_maps:
> +       close(ctx->prog_fd);
> +       bpf_set_link_xdp_fd(ctx->ifindex, -1, 0);
> +err_load_xdp_prog:
> +       xsk_delete_bpf_maps(xsk);
> +
> +       return err;
>  }
>
>  static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
> @@ -689,6 +729,40 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
>         return ctx;
>  }
>
> +static void xsk_destroy_xsk_struct(struct xsk_socket *xsk)
> +{
> +       free(xsk->ctx);
> +       free(xsk);
> +}
> +
> +int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd)
> +{
> +       xsk->ctx->xsks_map_fd = fd;
> +       return xsk_set_bpf_maps(xsk);
> +}
> +
> +int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd)
> +{
> +       struct xsk_socket *xsk;
> +       int res;
> +
> +       xsk = calloc(1, sizeof(*xsk));
> +       if (!xsk)
> +               return -ENOMEM;
> +
> +       res = xsk_create_xsk_struct(ifindex, xsk);
> +       if (res) {
> +               free(xsk);
> +               return -EINVAL;
> +       }
> +
> +       res = __xsk_setup_xdp_prog(xsk, xsks_map_fd);
> +
> +       xsk_destroy_xsk_struct(xsk);
> +
> +       return res;
> +}
> +
>  int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
>                               const char *ifname,
>                               __u32 queue_id, struct xsk_umem *umem,
> @@ -838,7 +912,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
>         ctx->prog_fd = -1;
>
>         if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
> -               err = xsk_setup_xdp_prog(xsk);
> +               err = __xsk_setup_xdp_prog(xsk, NULL);
>                 if (err)
>                         goto out_mmap_tx;
>         }
> diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
> index 1719a327e5f9..10b4259f8875 100644
> --- a/tools/lib/bpf/xsk.h
> +++ b/tools/lib/bpf/xsk.h
> @@ -207,6 +207,11 @@ struct xsk_umem_config {
>         __u32 flags;
>  };
>
> +LIBBPF_API int xsk_setup_xdp_prog(int ifindex,
> +                                 int *xsks_map_fd);
> +LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk,
> +                                        int xsks_map_fd);
> +
>  /* Flags for the libbpf_flags field. */
>  #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
>
> --
> 2.20.1
>

  reply	other threads:[~2020-11-27  9:07 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-27  8:25 [PATCH v5 bpf-next 0/2] libbpf: add support for privileged/unprivileged control separation mariusz.dudek
2020-11-27  8:26 ` [PATCH v5 bpf-next 1/2] libbpf: separate XDP program load with xsk socket creation mariusz.dudek
2020-11-27  9:06   ` Magnus Karlsson [this message]
2020-11-27  8:26 ` [PATCH v5 bpf-next 2/2] samples/bpf: sample application for eBPF load and socket creation split mariusz.dudek
2020-11-27  9:07   ` Magnus Karlsson
2020-12-02  1:14 ` [PATCH v5 bpf-next 0/2] libbpf: add support for privileged/unprivileged control separation Andrii Nakryiko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAJ8uoz1TkEQ0-YJmqHaOULKvTGKbvfuMNB9c71vE-39RM6YvJw@mail.gmail.com \
    --to=magnus.karlsson@gmail.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=ast@kernel.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=jonathan.lemon@gmail.com \
    --cc=magnus.karlsson@intel.com \
    --cc=mariusz.dudek@gmail.com \
    --cc=mariuszx.dudek@intel.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).