Merge branch 'libbpf: add support for privileged/unprivileged control separation'

Mariusz Dudek says:

====================

From: Mariusz Dudek <mariuszx.dudek@intel.com>

This patch series adds support for separation of eBPF program
load and xsk socket creation. In for example a Kubernetes
environment you can have an AF_XDP CNI or daemonset that is
responsible for launching pods that execute an application
using AF_XDP sockets. It is desirable that the pod runs with
as low privileges as possible, CAP_NET_RAW in this case,
and that all operations that require privileges are contained
in the CNI or daemonset.

In this case, you have to be able separate ePBF program load from
xsk socket creation.

Currently, this will not work with the xsk_socket__create APIs
because you need to have CAP_NET_ADMIN privileges to load eBPF
program and CAP_SYS_ADMIN privileges to create update xsk_bpf_maps.
To be exact xsk_set_bpf_maps does not need those privileges but
it takes the prog_fd and xsks_map_fd and those are known only to
process that was loading eBPF program. The api bpf_prog_get_fd_by_id
that looks up the fd of the prog using an prog_id and
bpf_map_get_fd_by_id that looks for xsks_map_fd usinb map_id both
requires CAP_SYS_ADMIN.

With this patch, the pod can be run with CAP_NET_RAW capability
only. In case your umem is larger or equal process limit for
MEMLOCK you need either increase the limit or CAP_IPC_LOCK capability.
Without this patch in case of insufficient rights ENOPERM is
returned by xsk_socket__create.

To resolve this privileges issue two new 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_sokcet__update_xskmap - inserts an AF_XDP socket into an
xskmap for a particular xsk_socket

Usage example:
int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd)

int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);

Inserts AF_XDP socket "fd" into the xskmap.

The first patch introduces the new APIs. The second patch provides
a new sample applications working as control and modification to
existing xdpsock application to work with less privileges.

This patch set is based on bpf-next commit 97306be45fbe
(Merge branch 'switch to memcg-based memory accounting')

Since v6
- rebase on 97306be45fbe to resolve RLIMIT conflicts

Since v5
- fixed sample/bpf/xdpsock_user.c to resolve merge conflicts

Since v4
- sample/bpf/Makefile issues fixed

Since v3:
- force_set_map flag removed
- leaking of xsk struct fixed
- unified function error returning policy implemented

Since v2:
- new APIs moved itto LIBBPF_0.3.0 section
- struct bpf_prog_cfg_opts removed
- loading own eBPF program via xsk_setup_xdp_prog functionality removed

Since v1:
- struct bpf_prog_cfg improved for backward/forward compatibility
- API xsk_update_xskmap renamed to xsk_socket__update_xskmap
- commit message formatting fixed
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 90 insertions, 9 deletions

diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index ed55498c4122..7c4126542e2b 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -346,4 +346,6 @@ 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 5865e082ba0b..e9f121f5d129 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -204,6 +204,11 @@ 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)