All of lore.kernel.org
 help / color / mirror / Atom feed
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
To: daniel@iogearbox.net, ast@kernel.org, bpf@vger.kernel.org,
	netdev@vger.kernel.org
Cc: andrii@kernel.org, toke@redhat.com, bjorn.topel@intel.com,
	magnus.karlsson@intel.com, ciara.loftus@intel.com,
	Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Subject: [PATCH bpf-next 1/3] libbpf: xsk: use bpf_link
Date: Mon, 15 Feb 2021 16:46:36 +0100	[thread overview]
Message-ID: <20210215154638.4627-2-maciej.fijalkowski@intel.com> (raw)
In-Reply-To: <20210215154638.4627-1-maciej.fijalkowski@intel.com>

Currently, if there are multiple xdpsock instances running on a single
interface and in case one of the instances is terminated, the rest of
them are left in an inoperable state due to the fact of unloaded XDP
prog from interface.

To address that, step away from setting bpf prog in favour of bpf_link.
This means that refcounting of BPF resources will be done automatically
by bpf_link itself.

When setting up BPF resources during xsk socket creation, check whether
bpf_link for a given ifindex already exists via set of calls to
bpf_link_get_next_id -> bpf_link_get_fd_by_id -> bpf_obj_get_info_by_fd
and comparing the ifindexes from bpf_link and xsk socket.

If there's no bpf_link yet, create one for a given XDP prog and unload
explicitly existing prog if XDP_FLAGS_UPDATE_IF_NOEXIST is not set.

If bpf_link is already at a given ifindex and underlying program is not
AF-XDP one, bail out or update the bpf_link's prog given the presence of
XDP_FLAGS_UPDATE_IF_NOEXIST.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
---
 tools/lib/bpf/xsk.c | 143 +++++++++++++++++++++++++++++++++++++-------
 1 file changed, 122 insertions(+), 21 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 20500fb1f17e..5911868efa43 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -28,6 +28,7 @@
 #include <sys/mman.h>
 #include <sys/socket.h>
 #include <sys/types.h>
+#include <linux/if_link.h>
 
 #include "bpf.h"
 #include "libbpf.h"
@@ -70,6 +71,7 @@ struct xsk_ctx {
 	int ifindex;
 	struct list_head list;
 	int prog_fd;
+	int link_fd;
 	int xsks_map_fd;
 	char ifname[IFNAMSIZ];
 };
@@ -409,7 +411,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	static const int log_buf_size = 16 * 1024;
 	struct xsk_ctx *ctx = xsk->ctx;
 	char log_buf[log_buf_size];
-	int err, prog_fd;
+	int prog_fd;
 
 	/* This is the fallback C-program:
 	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
@@ -499,14 +501,47 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 		return prog_fd;
 	}
 
-	err = bpf_set_link_xdp_fd(xsk->ctx->ifindex, prog_fd,
-				  xsk->config.xdp_flags);
-	if (err) {
-		close(prog_fd);
-		return err;
+	ctx->prog_fd = prog_fd;
+	return 0;
+}
+
+static int xsk_create_bpf_link(struct xsk_socket *xsk)
+{
+	/* bpf_link only accepts XDP_FLAGS_MODES, but xsk->config.xdp_flags
+	 * might have set XDP_FLAGS_UPDATE_IF_NOEXIST
+	 */
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
+			    .flags = (xsk->config.xdp_flags & XDP_FLAGS_MODES));
+	struct xsk_ctx *ctx = xsk->ctx;
+	__u32 prog_id;
+	int link_fd;
+	int err;
+
+	/* for !XDP_FLAGS_UPDATE_IF_NOEXIST, unload the program first, if any,
+	 * so that bpf_link can be attached
+	 */
+	if (!(xsk->config.xdp_flags & XDP_FLAGS_UPDATE_IF_NOEXIST)) {
+		err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id, xsk->config.xdp_flags);
+		if (err) {
+			pr_warn("getting XDP prog id failed\n");
+			return err;
+		}
+		if (prog_id) {
+			err = bpf_set_link_xdp_fd(ctx->ifindex, -1, 0);
+			if (err < 0) {
+				pr_warn("detaching XDP prog failed\n");
+				return err;
+			}
+		}
 	}
 
-	ctx->prog_fd = prog_fd;
+	link_fd = bpf_link_create(ctx->prog_fd, xsk->ctx->ifindex, BPF_XDP, &opts);
+	if (link_fd < 0) {
+		pr_warn("bpf_link_create failed: %s\n", strerror(errno));
+		return link_fd;
+	}
+
+	ctx->link_fd = link_fd;
 	return 0;
 }
 
@@ -625,8 +660,32 @@ static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
 	}
 
 	err = 0;
-	if (ctx->xsks_map_fd == -1)
+	if (ctx->xsks_map_fd != -1)
+		goto out_map_ids;
+
+	/* if prog load is forced and we found bpf_link on a given ifindex BUT
+	 * the underlying XDP prog is not an AF-XDP one, close old prog's fd,
+	 * load AF-XDP and update existing bpf_link
+	 */
+	if (!(xsk->config.xdp_flags & XDP_FLAGS_UPDATE_IF_NOEXIST)) {
+		close(ctx->prog_fd);
+		err = xsk_create_bpf_maps(xsk);
+		if (err)
+			goto out_map_ids;
+
+		err = xsk_load_xdp_prog(xsk);
+		if (err) {
+			xsk_delete_bpf_maps(xsk);
+			goto out_map_ids;
+		}
+
+		/* if update failed, caller will close fds */
+		err = bpf_link_update(ctx->link_fd, ctx->prog_fd, 0);
+		if (err)
+			pr_warn("bpf_link_update failed: %s\n", strerror(errno));
+	} else {
 		err = -ENOENT;
+	}
 
 out_map_ids:
 	free(map_ids);
@@ -666,6 +725,49 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
 	return 0;
 }
 
+static int xsk_link_lookup(struct xsk_ctx *ctx, __u32 *prog_id)
+{
+	__u32 link_len = sizeof(struct bpf_link_info);
+	struct bpf_link_info link_info;
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	while (true) {
+		err = bpf_link_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT)
+				break;
+			pr_warn("can't get next link: %s\n", strerror(errno));
+			break;
+		}
+
+		fd = bpf_link_get_fd_by_id(id);
+		if (fd < 0) {
+			if (errno == ENOENT)
+				continue;
+			pr_warn("can't get link by id (%u): %s\n", id, strerror(errno));
+			break;
+		}
+
+		memset(&link_info, 0, link_len);
+		err = bpf_obj_get_info_by_fd(fd, &link_info, &link_len);
+		if (err) {
+			pr_warn("can't get link info: %s\n", strerror(errno));
+			close(fd);
+			break;
+		}
+		if (link_info.xdp.ifindex == ctx->ifindex) {
+			ctx->link_fd = fd;
+			*prog_id = link_info.prog_id;
+			break;
+		}
+		close(fd);
+	}
+
+	return errno == ENOENT ? 0 : err;
+}
+
 static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
 				int *xsks_map_fd)
 {
@@ -674,8 +776,7 @@ static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
 	__u32 prog_id = 0;
 	int err;
 
-	err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id,
-				  xsk->config.xdp_flags);
+	err = xsk_link_lookup(ctx, &prog_id);
 	if (err)
 		return err;
 
@@ -685,9 +786,12 @@ static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
 			return err;
 
 		err = xsk_load_xdp_prog(xsk);
-		if (err) {
+		if (err)
 			goto err_load_xdp_prog;
-		}
+
+		err = xsk_create_bpf_link(xsk);
+		if (err)
+			goto err_create_bpf_link;
 	} else {
 		ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
 		if (ctx->prog_fd < 0)
@@ -695,20 +799,15 @@ static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
 		err = xsk_lookup_bpf_maps(xsk);
 		if (err) {
 			close(ctx->prog_fd);
+			close(ctx->link_fd);
 			return err;
 		}
 	}
 
 	if (xsk->rx) {
 		err = xsk_set_bpf_maps(xsk);
-		if (err) {
-			if (!prog_id) {
-				goto err_set_bpf_maps;
-			} else {
-				close(ctx->prog_fd);
-				return err;
-			}
-		}
+		if (err)
+			goto err_set_bpf_maps;
 	}
 	if (xsks_map_fd)
 		*xsks_map_fd = ctx->xsks_map_fd;
@@ -716,8 +815,9 @@ static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp,
 	return 0;
 
 err_set_bpf_maps:
+	close(ctx->link_fd);
+err_create_bpf_link:
 	close(ctx->prog_fd);
-	bpf_set_link_xdp_fd(ctx->ifindex, -1, 0);
 err_load_xdp_prog:
 	xsk_delete_bpf_maps(xsk);
 
@@ -1053,6 +1153,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 	if (ctx->prog_fd != -1) {
 		xsk_delete_bpf_maps(xsk);
 		close(ctx->prog_fd);
+		close(ctx->link_fd);
 	}
 
 	err = xsk_get_mmap_offsets(xsk->fd, &off);
-- 
2.20.1


  reply	other threads:[~2021-02-15 16:08 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-15 15:46 [PATCH bpf-next 0/3] Introduce bpf_link in libbpf's xsk Maciej Fijalkowski
2021-02-15 15:46 ` Maciej Fijalkowski [this message]
2021-02-15 17:07   ` [PATCH bpf-next 1/3] libbpf: xsk: use bpf_link Toke Høiland-Jørgensen
2021-02-15 17:38     ` Björn Töpel
2021-02-15 19:35       ` Toke Høiland-Jørgensen
2021-02-16  2:01         ` Maciej Fijalkowski
2021-02-16  9:15           ` Björn Töpel
2021-02-16 10:27           ` Toke Høiland-Jørgensen
2021-02-16 20:15             ` Maciej Fijalkowski
2021-02-15 20:22       ` John Fastabend
2021-02-15 21:38         ` Toke Høiland-Jørgensen
2021-02-16  0:18           ` John Fastabend
2021-02-16  2:23             ` Maciej Fijalkowski
2021-02-16  9:23               ` Björn Töpel
2021-02-16 10:36             ` Toke Høiland-Jørgensen
2021-02-23  1:15               ` Andrii Nakryiko
2021-02-17  2:23           ` Dan Siemon
2021-02-17  7:16             ` Magnus Karlsson
2021-02-17  7:36               ` Magnus Karlsson
2021-02-16  2:10         ` Maciej Fijalkowski
2021-02-15 20:49   ` John Fastabend
2021-02-16  2:38     ` Maciej Fijalkowski
2021-02-16 18:19       ` John Fastabend
2021-02-16 20:10         ` Maciej Fijalkowski
2021-02-16  9:20     ` Björn Töpel
2021-02-16 10:39       ` Toke Høiland-Jørgensen
2021-02-16 19:15         ` John Fastabend
2021-02-16 20:50           ` Maciej Fijalkowski
2021-02-16 21:17             ` John Fastabend
2021-02-15 15:46 ` [PATCH bpf-next 2/3] libbpf: clear map_info before each bpf_obj_get_info_by_fd Maciej Fijalkowski
2021-02-15 20:33   ` John Fastabend
2021-02-16  2:42     ` Maciej Fijalkowski
2021-02-15 15:46 ` [PATCH bpf-next 3/3] samples: bpf: do not unload prog within xdpsock Maciej Fijalkowski
2021-02-15 20:24   ` John Fastabend
2021-02-16  9:22     ` Björn Töpel
2021-02-16 14:15       ` Maciej Fijalkowski
2021-02-15 16:07 ` [PATCH bpf-next 0/3] Introduce bpf_link in libbpf's xsk Björn Töpel

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=20210215154638.4627-2-maciej.fijalkowski@intel.com \
    --to=maciej.fijalkowski@intel.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bjorn.topel@intel.com \
    --cc=bpf@vger.kernel.org \
    --cc=ciara.loftus@intel.com \
    --cc=daniel@iogearbox.net \
    --cc=magnus.karlsson@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=toke@redhat.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.