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

Daniel Borkmann says:

====================
pull-request: bpf 2018-06-16

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

The main changes are:

1) Fix a panic in devmap handling in generic XDP where return type
of __devmap_lookup_elem() got changed recently but generic XDP
code missed the related update, from Toshiaki.

2) Fix a freeze when BPF progs are loaded that include BPF to BPF
calls when JIT is enabled where we would later bail out via error
path w/o dropping kallsyms, and another one to silence syzkaller
splats from locking prog read-only, from Daniel.

3) Fix a bug in test_offloads.py BPF selftest which must not assume
that the underlying system have no BPF progs loaded prior to test,
and one in bpftool to fix accuracy of program load time, from Jakub.

4) Fix a bug in bpftool's probe for availability of the bpf(2)
BPF_TASK_FD_QUERY subcommand, from Yonghong.

5) Fix a regression in AF_XDP's XDP_SKB receive path where queue
id check got erroneously removed, from Björn.

6) Fix missing state cleanup in BPF's xfrm tunnel test, from William.

7) Check tunnel type more accurately in BPF's tunnel collect metadata
kselftest, from Jian.

8) Fix missing Kconfig fragments for BPF kselftests, from Anders.
====================

Signed-off-by: David S. Miller <[e-mail]>

include/linux/bpf.h

···
 
 /* Map specifics */
 struct xdp_buff;
+struct sk_buff;
 
 struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+			     struct bpf_prog *xdp_prog);
 
 struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
···
 static inline
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx)
+{
+	return 0;
+}
+
+struct sk_buff;
+
+static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
+					   struct sk_buff *skb,
+					   struct bpf_prog *xdp_prog)
 {
 	return 0;
 }

include/linux/filter.h

···
 #include <linux/cryptohash.h>
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
+#include <linux/if_vlan.h>
 
 #include <net/sch_generic.h>
 
···
 };
 
 struct bpf_binary_header {
-	unsigned int pages;
+	u16 pages;
+	u16 locked:1;
 	u8 image[];
 };
 
···
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
 	fp->locked = 1;
-	WARN_ON_ONCE(set_memory_ro((unsigned long)fp, fp->pages));
+	if (set_memory_ro((unsigned long)fp, fp->pages))
+		fp->locked = 0;
+#endif
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
 	if (fp->locked) {
 		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
 		/* In case set_memory_rw() fails, we want to be the first
···
 		 */
 		fp->locked = 0;
 	}
+#endif
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-	WARN_ON_ONCE(set_memory_ro((unsigned long)hdr, hdr->pages));
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+	hdr->locked = 1;
+	if (set_memory_ro((unsigned long)hdr, hdr->pages))
+		hdr->locked = 0;
+#endif
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
-	WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+	if (hdr->locked) {
+		WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
+		/* In case set_memory_rw() fails, we want to be the first
+		 * to crash here instead of some random place later on.
+		 */
+		hdr->locked = 0;
+	}
+#endif
 }
-#else
-static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
-{
-}
-
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
-}
-
-static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
-{
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SET_MEMORY */
 
 static inline struct bpf_binary_header *
 bpf_jit_binary_hdr(const struct bpf_prog *fp)
···
 
 	return (void *)addr;
 }
+
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp)
+{
+	if (!fp->locked)
+		return -ENOLCK;
+	if (fp->jited) {
+		const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
+
+		if (!hdr->locked)
+			return -ENOLCK;
+	}
+
+	return 0;
+}
+#endif
 
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
···
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
+
+static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
+					   struct net_device *fwd)
+{
+	unsigned int len;
+
+	if (unlikely(!(fwd->flags & IFF_UP)))
+		return -ENETDOWN;
+
+	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+	if (skb->len > len)
+		return -EMSGSIZE;
+
+	return 0;
+}
 
 /* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
  * same cpu context. Further for best results no more than a single map
···
 {
 }
 #endif /* CONFIG_BPF_JIT */
+
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
 
 #define BPF_ANC		BIT(15)
 

kernel/bpf/core.c

···
 	return prog_adj;
 }
 
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+	int i;
+
+	for (i = 0; i < fp->aux->func_cnt; i++)
+		bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+	bpf_prog_kallsyms_del_subprogs(fp);
+	bpf_prog_kallsyms_del(fp);
+}
+
 #ifdef CONFIG_BPF_JIT
 /* All BPF JIT sysctl knobs here. */
 int bpf_jit_enable   __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
···
 	bpf_fill_ill_insns(hdr, size);
 
 	hdr->pages = size / PAGE_SIZE;
+	hdr->locked = 0;
+
 	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
 		     PAGE_SIZE - sizeof(*hdr));
 	start = (get_random_int() % hole) & ~(alignment - 1);
···
 	return 0;
 }
 
+static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
+{
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+	int i, err;
+
+	for (i = 0; i < fp->aux->func_cnt; i++) {
+		err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
+		if (err)
+			return err;
+	}
+
+	return bpf_prog_check_pages_ro_single(fp);
+#endif
+	return 0;
+}
+
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+	fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
 /**
  *	bpf_prog_select_runtime - select exec runtime for BPF program
  *	@fp: bpf_prog populated with internal BPF program
···
  */
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 {
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+	/* In case of BPF to BPF calls, verifier did all the prep
+	 * work with regards to JITing, etc.
+	 */
+	if (fp->bpf_func)
+		goto finalize;
 
-	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
-#else
-	fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
+	bpf_prog_select_func(fp);
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during
···
 		if (*err)
 			return fp;
 	}
+
+finalize:
 	bpf_prog_lock_ro(fp);
 
 	/* The tail call compatibility check can only be done at
···
 	 * all eBPF JITs might immediately support all features.
 	 */
 	*err = bpf_check_tail_call(fp);
+	if (*err)
+		return fp;
 
+	/* Checkpoint: at this point onwards any cBPF -> eBPF or
+	 * native eBPF program is read-only. If we failed to change
+	 * the page attributes (e.g. allocation failure from
+	 * splitting large pages), then reject the whole program
+	 * in order to guarantee not ending up with any W+X pages
+	 * from BPF side in kernel.
+	 */
+	*err = bpf_prog_check_pages_ro_locked(fp);
 	return fp;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);

kernel/bpf/devmap.c

···
 	return bq_enqueue(dst, xdpf, dev_rx);
 }
 
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+			     struct bpf_prog *xdp_prog)
+{
+	int err;
+
+	err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+	if (unlikely(err))
+		return err;
+	skb->dev = dst->dev;
+	generic_xdp_tx(skb, xdp_prog);
+
+	return 0;
+}
+
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);

kernel/bpf/syscall.c

···
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
-		int i;
-
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
-
-		for (i = 0; i < prog->aux->func_cnt; i++)
-			bpf_prog_kallsyms_del(prog->aux->func[i]);
-		bpf_prog_kallsyms_del(prog);
+		bpf_prog_kallsyms_del_all(prog);
 
 		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
 	}
···
 	if (err < 0)
 		goto free_used_maps;
 
-	/* eBPF program is ready to be JITed */
-	if (!prog->bpf_func)
-		prog = bpf_prog_select_runtime(prog, &err);
+	prog = bpf_prog_select_runtime(prog, &err);
 	if (err < 0)
 		goto free_used_maps;
 
···
 	return err;
 
 free_used_maps:
+	bpf_prog_kallsyms_del_subprogs(prog);
 	free_used_maps(prog->aux);
 free_prog:
 	bpf_prog_uncharge_memlock(prog);

net/core/filter.c

···
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
 
-static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
-{
-	unsigned int len;
-
-	if (unlikely(!(fwd->flags & IFF_UP)))
-		return -ENETDOWN;
-
-	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
-	if (skb->len > len)
-		return -EMSGSIZE;
-
-	return 0;
-}
-
 static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct xdp_buff *xdp,
···
 	}
 
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
-		if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+		struct bpf_dtab_netdev *dst = fwd;
+
+		err = dev_map_generic_redirect(dst, skb, xdp_prog);
+		if (unlikely(err))
 			goto err;
-		skb->dev = fwd;
-		generic_xdp_tx(skb, xdp_prog);
 	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 		struct xdp_sock *xs = fwd;
 

net/xdp/xsk.c

···
 	u64 addr;
 	int err;
 
+	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
+		return -EINVAL;
+
 	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
 	    len > xs->umem->chunk_size_nohr) {
 		xs->rx_dropped++;

tools/bpf/bpftool/perf.c

···
 	if (perf_query_supported)
 		goto out;
 
-	fd = open(bin_name, O_RDONLY);
+	fd = open("/", O_RDONLY);
 	if (fd < 0) {
-		p_err("perf_query_support: %s", strerror(errno));
+		p_err("perf_query_support: cannot open directory \"/\" (%s)",
+		      strerror(errno));
 		goto out;
 	}
 

tools/bpf/bpftool/prog.c

···
 	}
 
 	wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
-		nsecs / 1000000000;
+		(real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
+		1000000000;
+
 
 	if (!localtime_r(&wallclock_secs, &load_tm)) {
 		snprintf(buf, size, "%llu", nsecs / 1000000000);

tools/testing/selftests/bpf/config

···
 CONFIG_NETDEVSIM=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_IPIP=y
+CONFIG_IPV6=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPGRE=y
+CONFIG_IPV6_GRE=y
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_HMAC=m
+CONFIG_CRYPTO_SHA256=m
+CONFIG_VXLAN=y
+CONFIG_GENEVE=y

tools/testing/selftests/bpf/test_offload.py

···
 
 def bpftool_prog_list(expected=None, ns=""):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
+    # Remove the base progs
+    for p in base_progs:
+        if p in progs:
+            progs.remove(p)
     if expected is not None:
         if len(progs) != expected:
             fail(True, "%d BPF programs loaded, expected %d" %
···
 
 def bpftool_map_list(expected=None, ns=""):
     _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+    # Remove the base maps
+    for m in base_maps:
+        if m in maps:
+            maps.remove(m)
     if expected is not None:
         if len(maps) != expected:
             fail(True, "%d BPF maps loaded, expected %d" %
···
 # Check tools
 ret, progs = bpftool("prog", fail=False)
 skip(ret != 0, "bpftool not installed")
-# Check no BPF programs are loaded
-skip(len(progs) != 0, "BPF programs already loaded on the system")
+base_progs = progs
+_, base_maps = bpftool("map")
 
 # Check netdevsim
 ret, out = cmd("modprobe netdevsim", fail=False)

tools/testing/selftests/bpf/test_tunnel.sh

···
 test_xfrm_tunnel()
 {
 	config_device
-        #tcpdump -nei veth1 ip &
-	output=$(mktemp)
-	cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
-        setup_xfrm_tunnel
+	> /sys/kernel/debug/tracing/trace
+	setup_xfrm_tunnel
 	tc qdisc add dev veth1 clsact
 	tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
 		sec xfrm_get_state
 	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
 	sleep 1
-	grep "reqid 1" $output
+	grep "reqid 1" /sys/kernel/debug/tracing/trace
 	check_err $?
-	grep "spi 0x1" $output
+	grep "spi 0x1" /sys/kernel/debug/tracing/trace
 	check_err $?
-	grep "remote ip 0xac100164" $output
+	grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
 	check_err $?
 	cleanup
 
 	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: xfrm tunnel"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
+		echo -e ${RED}"FAIL: xfrm tunnel"${NC}
+		return 1
+	fi
+	echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
 }
 
 attach_bpf()
···
 	ip link del ip6geneve11 2> /dev/null
 	ip link del erspan11 2> /dev/null
 	ip link del ip6erspan11 2> /dev/null
+	ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
+	ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
+	ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
+	ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
 }
 
 cleanup_exit()
···
 
 check()
 {
-	ip link help $1 2>&1 | grep -q "^Usage:"
+	ip link help 2>&1 | grep -q "\s$1\s"
 	if [ $? -ne 0 ];then
 		echo "SKIP $1: iproute2 not support"
 	cleanup