Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-07-09

We've added 94 non-merge commits during the last 19 day(s) which contain
a total of 125 files changed, 5141 insertions(+), 6701 deletions(-).

The main changes are:

1) Add new way for performing BTF type queries to BPF, from Daniel Müller.

2) Add inlining of calls to bpf_loop() helper when its function callback is
   statically known, from Eduard Zingerman.

3) Implement BPF TCP CC framework usability improvements, from Jörn-Thorben Hinz.

4) Add LSM flavor for attaching per-cgroup BPF programs to existing LSM
   hooks, from Stanislav Fomichev.

5) Remove all deprecated libbpf APIs in prep for 1.0 release, from Andrii Nakryiko.

6) Add benchmarks around local_storage to BPF selftests, from Dave Marchevsky.

7) AF_XDP sample removal (given move to libxdp) and various improvements around AF_XDP
   selftests, from Magnus Karlsson & Maciej Fijalkowski.

8) Add bpftool improvements for memcg probing and bash completion, from Quentin Monnet.

9) Add arm64 JIT support for BPF-2-BPF coupled with tail calls, from Jakub Sitnicki.

10) Sockmap optimizations around throughput of UDP transmissions which have been
    improved by 61%, from Cong Wang.

11) Rework perf's BPF prologue code to remove deprecated functions, from Jiri Olsa.

12) Fix sockmap teardown path to avoid sleepable sk_psock_stop, from John Fastabend.

13) Fix libbpf's cleanup around legacy kprobe/uprobe on error case, from Chuang Wang.

14) Fix libbpf's bpf_helpers.h to work with gcc for the case of its sec/pragma
    macro, from James Hilliard.

15) Fix libbpf's pt_regs macros for riscv to use a0 for RC register, from Yixun Lan.

16) Fix bpftool to show the name of type BPF_OBJ_LINK, from Yafang Shao.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (94 commits)
  selftests/bpf: Fix xdp_synproxy build failure if CONFIG_NF_CONNTRACK=m/n
  bpf: Correctly propagate errors up from bpf_core_composites_match
  libbpf: Disable SEC pragma macro on GCC
  bpf: Check attach_func_proto more carefully in check_return_code
  selftests/bpf: Add test involving restrict type qualifier
  bpftool: Add support for KIND_RESTRICT to gen min_core_btf command
  MAINTAINERS: Add entry for AF_XDP selftests files
  selftests, xsk: Rename AF_XDP testing app
  bpf, docs: Remove deprecated xsk libbpf APIs description
  selftests/bpf: Add benchmark for local_storage RCU Tasks Trace usage
  libbpf, riscv: Use a0 for RC register
  libbpf: Remove unnecessary usdt_rel_ip assignments
  selftests/bpf: Fix few more compiler warnings
  selftests/bpf: Fix bogus uninitialized variable warning
  bpftool: Remove zlib feature test from Makefile
  libbpf: Cleanup the legacy uprobe_event on failed add/attach_event()
  libbpf: Fix wrong variable used in perf_event_uprobe_open_legacy()
  libbpf: Cleanup the legacy kprobe_event on failed add/attach_event()
  selftests/bpf: Add type match test against kernel's task_struct
  selftests/bpf: Add nested type to type based tests
  ...
====================

Link: https://lore.kernel.org/r/20220708233145.32365-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

samples/bpf/Makefile

@@ -45,9 +45,6 @@ tprogs-y += xdp_rxq_info
 tprogs-y += syscall_tp
 tprogs-y += cpustat
 tprogs-y += xdp_adjust_tail
-tprogs-y += xdpsock
-tprogs-y += xdpsock_ctrl_proc
-tprogs-y += xsk_fwd
 tprogs-y += xdp_fwd
 tprogs-y += task_fd_query
 tprogs-y += xdp_sample_pkts
@@ -109,9 +106,6 @@ xdp_rxq_info-objs := xdp_rxq_info_user.o
 syscall_tp-objs := syscall_tp_user.o
 cpustat-objs := cpustat_user.o
 xdp_adjust_tail-objs := xdp_adjust_tail_user.o
-xdpsock-objs := xdpsock_user.o
-xdpsock_ctrl_proc-objs := xdpsock_ctrl_proc.o
-xsk_fwd-objs := xsk_fwd.o
 xdp_fwd-objs := xdp_fwd_user.o
 task_fd_query-objs := task_fd_query_user.o $(TRACE_HELPERS)
 xdp_sample_pkts-objs := xdp_sample_pkts_user.o
@@ -179,7 +173,6 @@ always-y += xdp_sample_pkts_kern.o
 always-y += ibumad_kern.o
 always-y += hbm_out_kern.o
 always-y += hbm_edt_kern.o
-always-y += xdpsock_kern.o
 
 ifeq ($(ARCH), arm)
 # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
@@ -224,8 +217,6 @@ TPROGLDLIBS_tracex4		+= -lrt
 TPROGLDLIBS_trace_output	+= -lrt
 TPROGLDLIBS_map_perf_test	+= -lrt
 TPROGLDLIBS_test_overhead	+= -lrt
-TPROGLDLIBS_xdpsock		+= -pthread -lcap
-TPROGLDLIBS_xsk_fwd		+= -pthread
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 # make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang

samples/bpf/xdp1_kern.c

@@ -39,11 +39,13 @@ static int parse_ipv6(void *data, u64 nh_off, void *data_end)
 	return ip6h->nexthdr;
 }
 
-SEC("xdp1")
+#define XDPBUFSIZE	64
+SEC("xdp.frags")
 int xdp_prog1(struct xdp_md *ctx)
 {
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
+	__u8 pkt[XDPBUFSIZE] = {};
+	void *data_end = &pkt[XDPBUFSIZE-1];
+	void *data = pkt;
 	struct ethhdr *eth = data;
 	int rc = XDP_DROP;
 	long *value;
@@ -51,6 +53,9 @@ int xdp_prog1(struct xdp_md *ctx)
 	u64 nh_off;
 	u32 ipproto;
 
+	if (bpf_xdp_load_bytes(ctx, 0, pkt, sizeof(pkt)))
+		return rc;
+
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
 		return rc;

samples/bpf/xdp2_kern.c

@@ -55,11 +55,13 @@ static int parse_ipv6(void *data, u64 nh_off, void *data_end)
 	return ip6h->nexthdr;
 }
 
-SEC("xdp1")
+#define XDPBUFSIZE	64
+SEC("xdp.frags")
 int xdp_prog1(struct xdp_md *ctx)
 {
-	void *data_end = (void *)(long)ctx->data_end;
-	void *data = (void *)(long)ctx->data;
+	__u8 pkt[XDPBUFSIZE] = {};
+	void *data_end = &pkt[XDPBUFSIZE-1];
+	void *data = pkt;
 	struct ethhdr *eth = data;
 	int rc = XDP_DROP;
 	long *value;
@@ -67,6 +69,9 @@ int xdp_prog1(struct xdp_md *ctx)
 	u64 nh_off;
 	u32 ipproto;
 
+	if (bpf_xdp_load_bytes(ctx, 0, pkt, sizeof(pkt)))
+		return rc;
+
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
 		return rc;

samples/bpf/xdp_tx_iptunnel_kern.c

@@ -212,7 +212,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp)
 	return XDP_TX;
 }
 
-SEC("xdp_tx_iptunnel")
+SEC("xdp.frags")
 int _xdp_tx_iptunnel(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;

samples/bpf/xdpsock.h

@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright(c) 2019 Intel Corporation.
- */
-
-#ifndef XDPSOCK_H_
-#define XDPSOCK_H_
-
-#define MAX_SOCKS 4
-
-#define SOCKET_NAME "sock_cal_bpf_fd"
-#define MAX_NUM_OF_CLIENTS 10
-
-#define CLOSE_CONN  1
-
-typedef __u64 u64;
-typedef __u32 u32;
-
-#endif /* XDPSOCK_H */

samples/bpf/xdpsock_ctrl_proc.c

@@ -1,190 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2017 - 2018 Intel Corporation. */
-
-#include <errno.h>
-#include <getopt.h>
-#include <libgen.h>
-#include <net/if.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/socket.h>
-#include <sys/un.h>
-#include <unistd.h>
-
-#include <bpf/bpf.h>
-#include <bpf/xsk.h>
-#include "xdpsock.h"
-
-/* libbpf APIs for AF_XDP are deprecated starting from v0.7 */
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
-static const char *opt_if = "";
-
-static struct option long_options[] = {
-	{"interface", required_argument, 0, 'i'},
-	{0, 0, 0, 0}
-};
-
-static void usage(const char *prog)
-{
-	const char *str =
-		"  Usage: %s [OPTIONS]\n"
-		"  Options:\n"
-		"  -i, --interface=n	Run on interface n\n"
-		"\n";
-	fprintf(stderr, "%s\n", str);
-
-	exit(0);
-}
-
-static void parse_command_line(int argc, char **argv)
-{
-	int option_index, c;
-
-	opterr = 0;
-
-	for (;;) {
-		c = getopt_long(argc, argv, "i:",
-				long_options, &option_index);
-		if (c == -1)
-			break;
-
-		switch (c) {
-		case 'i':
-			opt_if = optarg;
-			break;
-		default:
-			usage(basename(argv[0]));
-		}
-	}
-}
-
-static int send_xsks_map_fd(int sock, int fd)
-{
-	char cmsgbuf[CMSG_SPACE(sizeof(int))];
-	struct msghdr msg;
-	struct iovec iov;
-	int value = 0;
-
-	if (fd == -1) {
-		fprintf(stderr, "Incorrect fd = %d\n", fd);
-		return -1;
-	}
-	iov.iov_base = &value;
-	iov.iov_len = sizeof(int);
-
-	msg.msg_name = NULL;
-	msg.msg_namelen = 0;
-	msg.msg_iov = &iov;
-	msg.msg_iovlen = 1;
-	msg.msg_flags = 0;
-	msg.msg_control = cmsgbuf;
-	msg.msg_controllen = CMSG_LEN(sizeof(int));
-
-	struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
-
-	cmsg->cmsg_level = SOL_SOCKET;
-	cmsg->cmsg_type = SCM_RIGHTS;
-	cmsg->cmsg_len = CMSG_LEN(sizeof(int));
-
-	*(int *)CMSG_DATA(cmsg) = fd;
-	int ret = sendmsg(sock, &msg, 0);
-
-	if (ret == -1) {
-		fprintf(stderr, "Sendmsg failed with %s", strerror(errno));
-		return -errno;
-	}
-
-	return ret;
-}
-
-int
-main(int argc, char **argv)
-{
-	struct sockaddr_un server;
-	int listening = 1;
-	int rval, msgsock;
-	int ifindex = 0;
-	int flag = 1;
-	int cmd = 0;
-	int sock;
-	int err;
-	int xsks_map_fd;
-
-	parse_command_line(argc, argv);
-
-	ifindex = if_nametoindex(opt_if);
-	if (ifindex == 0) {
-		fprintf(stderr, "Unable to get ifindex for Interface %s. Reason:%s",
-			opt_if, strerror(errno));
-		return -errno;
-	}
-
-	sock = socket(AF_UNIX, SOCK_STREAM, 0);
-	if (sock < 0) {
-		fprintf(stderr, "Opening socket stream failed: %s", strerror(errno));
-		return -errno;
-	}
-
-	server.sun_family = AF_UNIX;
-	strcpy(server.sun_path, SOCKET_NAME);
-
-	setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &flag, sizeof(int));
-
-	if (bind(sock, (struct sockaddr *)&server, sizeof(struct sockaddr_un))) {
-		fprintf(stderr, "Binding to socket stream failed: %s", strerror(errno));
-		return -errno;
-	}
-
-	listen(sock, MAX_NUM_OF_CLIENTS);
-
-	err = xsk_setup_xdp_prog(ifindex, &xsks_map_fd);
-	if (err) {
-		fprintf(stderr, "Setup of xdp program failed\n");
-		goto close_sock;
-	}
-
-	while (listening) {
-		msgsock = accept(sock, 0, 0);
-		if (msgsock == -1) {
-			fprintf(stderr, "Error accepting connection: %s", strerror(errno));
-			err = -errno;
-			goto close_sock;
-		}
-		err = send_xsks_map_fd(msgsock, xsks_map_fd);
-		if (err <= 0) {
-			fprintf(stderr, "Error %d sending xsks_map_fd\n", err);
-			goto cleanup;
-		}
-		do {
-			rval = read(msgsock, &cmd, sizeof(int));
-			if (rval < 0) {
-				fprintf(stderr, "Error reading stream message");
-			} else {
-				if (cmd != CLOSE_CONN)
-					fprintf(stderr, "Recv unknown cmd = %d\n", cmd);
-				listening = 0;
-				break;
-			}
-		} while (rval > 0);
-	}
-	close(msgsock);
-	close(sock);
-	unlink(SOCKET_NAME);
-
-	/* Unset fd for given ifindex */
-	err = bpf_xdp_detach(ifindex, 0, NULL);
-	if (err) {
-		fprintf(stderr, "Error when unsetting bpf prog_fd for ifindex(%d)\n", ifindex);
-		return err;
-	}
-
-	return 0;
-
-cleanup:
-	close(msgsock);
-close_sock:
-	close(sock);
-	unlink(SOCKET_NAME);
-	return err;
-}

samples/bpf/xdpsock_kern.c

@@ -1,24 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-#include "xdpsock.h"
-
-/* This XDP program is only needed for the XDP_SHARED_UMEM mode.
- * If you do not use this mode, libbpf can supply an XDP program for you.
- */
-
-struct {
-	__uint(type, BPF_MAP_TYPE_XSKMAP);
-	__uint(max_entries, MAX_SOCKS);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
-} xsks_map SEC(".maps");
-
-static unsigned int rr;
-
-SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
-{
-	rr = (rr + 1) & (MAX_SOCKS - 1);
-
-	return bpf_redirect_map(&xsks_map, rr, XDP_DROP);
-}