Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Alexei Starovoitov says:

====================
pull-request: bpf 2018-02-02

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) support XDP attach in libbpf, from Eric.

2) minor fixes, from Daniel, Jakub, Yonghong, Alexei.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

Documentation/bpf/bpf_devel_QA.txt

@@ -516,4 +516,35 @@ A: LLVM has a -mcpu selector for the BPF back end in order to allow the
    By the way, the BPF kernel selftests run with -mcpu=probe for better
    test coverage.
 
+Q: In some cases clang flag "-target bpf" is used but in other cases the
+   default clang target, which matches the underlying architecture, is used.
+   What is the difference and when I should use which?
+
+A: Although LLVM IR generation and optimization try to stay architecture
+   independent, "-target <arch>" still has some impact on generated code:
+
+     - BPF program may recursively include header file(s) with file scope
+       inline assembly codes. The default target can handle this well,
+       while bpf target may fail if bpf backend assembler does not
+       understand these assembly codes, which is true in most cases.
+
+     - When compiled without -g, additional elf sections, e.g.,
+       .eh_frame and .rela.eh_frame, may be present in the object file
+       with default target, but not with bpf target.
+
+     - The default target may turn a C switch statement into a switch table
+       lookup and jump operation. Since the switch table is placed
+       in the global readonly section, the bpf program will fail to load.
+       The bpf target does not support switch table optimization.
+       The clang option "-fno-jump-tables" can be used to disable
+       switch table generation.
+
+   You should use default target when:
+
+     - Your program includes a header file, e.g., ptrace.h, which eventually
+       pulls in some header files containing file scope host assembly codes.
+     - You can add "-fno-jump-tables" to work around the switch table issue.
+
+   Otherwise, you can use bpf target.
+
 Happy BPF hacking!

drivers/net/netdevsim/bpf.c

@@ -480,8 +480,7 @@ static int
 nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 {
 	struct nsim_bpf_bound_map *nmap;
-	unsigned int i;
-	int err;
+	int i, err;
 
 	if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY &&
 		    offmap->map.map_type != BPF_MAP_TYPE_HASH))
@@ -518,7 +517,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 	return 0;
 
 err_free:
-	while (--i) {
+	while (--i >= 0) {
 		kfree(nmap->entry[i].key);
 		kfree(nmap->entry[i].value);
 	}

include/linux/netdevice.h

@@ -3228,6 +3228,12 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev,
 }
 #endif
 
+static inline struct netdev_rx_queue *
+__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
+{
+	return dev->_rx + rxq;
+}
+
 #ifdef CONFIG_SYSFS
 static inline unsigned int get_netdev_rx_queue_index(
 		struct netdev_rx_queue *queue)

kernel/bpf/core.c

@@ -1576,25 +1576,41 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 				__u32 __user *prog_ids, u32 cnt)
 {
 	struct bpf_prog **prog;
-	u32 i = 0, id;
-
+	unsigned long err = 0;
+	u32 i = 0, *ids;
+	bool nospc;
+
+	/* users of this function are doing:
+	 * cnt = bpf_prog_array_length();
+	 * if (cnt > 0)
+	 *     bpf_prog_array_copy_to_user(..., cnt);
+	 * so below kcalloc doesn't need extra cnt > 0 check, but
+	 * bpf_prog_array_length() releases rcu lock and
+	 * prog array could have been swapped with empty or larger array,
+	 * so always copy 'cnt' prog_ids to the user.
+	 * In a rare race the user will see zero prog_ids
+	 */
+	ids = kcalloc(cnt, sizeof(u32), GFP_USER);
+	if (!ids)
+		return -ENOMEM;
 	rcu_read_lock();
 	prog = rcu_dereference(progs)->progs;
 	for (; *prog; prog++) {
 		if (*prog == &dummy_bpf_prog.prog)
 			continue;
-		id = (*prog)->aux->id;
-		if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
-			rcu_read_unlock();
-			return -EFAULT;
-		}
+		ids[i] = (*prog)->aux->id;
 		if (++i == cnt) {
 			prog++;
 			break;
 		}
 	}
+	nospc = !!(*prog);
 	rcu_read_unlock();
-	if (*prog)
+	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
+	kfree(ids);
+	if (err)
+		return -EFAULT;
+	if (nospc)
 		return -ENOSPC;
 	return 0;
 }

net/bpf/test_run.c

@@ -151,6 +151,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 {
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
+	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
 	u32 retval, duration;
 	void *data;
@@ -165,6 +166,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	xdp.data_meta = xdp.data;
 	xdp.data_end = xdp.data + size;
 
+	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
+	xdp.rxq = &rxqueue->xdp_rxq;
+
 	retval = bpf_test_run(prog, &xdp, repeat, &duration);
 	if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 		size = xdp.data_end - xdp.data;

samples/bpf/Makefile

@@ -45,7 +45,7 @@ hostprogs-y += xdp_rxq_info
 hostprogs-y += syscall_tp
 
 # Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o
+LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
 CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 
 test_lru_dist-objs := test_lru_dist.o $(LIBBPF)

samples/bpf/bpf_load.c

@@ -695,105 +695,3 @@ struct ksym *ksym_search(long key)
 	return &syms[0];
 }
 
-int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
-	struct sockaddr_nl sa;
-	int sock, seq = 0, len, ret = -1;
-	char buf[4096];
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	struct nlmsghdr *nh;
-	struct nlmsgerr *err;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.nl_family = AF_NETLINK;
-
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
-	if (sock < 0) {
-		printf("open netlink socket: %s\n", strerror(errno));
-		return -1;
-	}
-
-	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
-		printf("bind to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
-	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
-	}
-
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		printf("send to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	len = recv(sock, buf, sizeof(buf), 0);
-	if (len < 0) {
-		printf("recv from netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
-	     nh = NLMSG_NEXT(nh, len)) {
-		if (nh->nlmsg_pid != getpid()) {
-			printf("Wrong pid %d, expected %d\n",
-			       nh->nlmsg_pid, getpid());
-			goto cleanup;
-		}
-		if (nh->nlmsg_seq != seq) {
-			printf("Wrong seq %d, expected %d\n",
-			       nh->nlmsg_seq, seq);
-			goto cleanup;
-		}
-		switch (nh->nlmsg_type) {
-		case NLMSG_ERROR:
-			err = (struct nlmsgerr *)NLMSG_DATA(nh);
-			if (!err->error)
-				continue;
-			printf("nlmsg error %s\n", strerror(-err->error));
-			goto cleanup;
-		case NLMSG_DONE:
-			break;
-		}
-	}
-
-	ret = 0;
-
-cleanup:
-	close(sock);
-	return ret;
-}

samples/bpf/bpf_load.h

@@ -61,5 +61,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
-int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif

samples/bpf/xdp1_user.c

@@ -25,7 +25,7 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -116,7 +116,7 @@ int main(int argc, char **argv)
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}

samples/bpf/xdp_redirect_cpu_user.c

@@ -26,7 +26,7 @@ static const char *__doc__ =
 
 /* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
  * use bpf/libbpf.h), but cannot as (currently) needed for XDP
- * attaching to a device via set_link_xdp_fd()
+ * attaching to a device via bpf_set_link_xdp_fd()
  */
 #include "libbpf.h"
 #include "bpf_load.h"
@@ -67,7 +67,7 @@ static void int_exit(int sig)
 		"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
 		ifindex, ifname);
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(EXIT_OK);
 }
 
@@ -682,7 +682,7 @@ int main(int argc, char **argv)
 	/* Remove XDP program when program is interrupted */
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
 		fprintf(stderr, "link set xdp fd failed\n");
 		return EXIT_FAIL_XDP;
 	}

samples/bpf/xdp_redirect_map_user.c

@@ -34,9 +34,9 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
 	if (ifindex_out_xdp_dummy_attached)
-		set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
 	exit(0);
 }
 
@@ -120,13 +120,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
 		return 1;
 	}
 
 	/* Loading dummy XDP prog on out-device */
-	if (set_link_xdp_fd(ifindex_out, prog_fd[1],
+	if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
 			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
 		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
 		ifindex_out_xdp_dummy_attached = false;

samples/bpf/xdp_redirect_user.c

@@ -33,9 +33,9 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
 	if (ifindex_out_xdp_dummy_attached)
-		set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
 	exit(0);
 }
 
@@ -114,13 +114,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
 		return 1;
 	}
 
 	/* Loading dummy XDP prog on out-device */
-	if (set_link_xdp_fd(ifindex_out, prog_fd[1],
+	if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
 			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
 		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
 		ifindex_out_xdp_dummy_attached = false;