bpf: fix redirect to map under tail calls

Commits 109980b894e9 ("bpf: don't select potentially stale ri->map
from buggy xdp progs") and 7c3001313396 ("bpf: fix ri->map_owner
pointer on bpf_prog_realloc") tried to mitigate that buggy programs
using bpf_redirect_map() helper call do not leave stale maps behind.
Idea was to add a map_owner cookie into the per CPU struct redirect_info
which was set to prog->aux by the prog making the helper call as a
proof that the map is not stale since the prog is implicitly holding
a reference to it. This owner cookie could later on get compared with
the program calling into BPF whether they match and therefore the
redirect could proceed with processing the map safely.

In (obvious) hindsight, this approach breaks down when tail calls are
involved since the original caller's prog->aux pointer does not have
to match the one from one of the progs out of the tail call chain,
and therefore the xdp buffer will be dropped instead of redirected.
A way around that would be to fix the issue differently (which also
allows to remove related work in fast path at the same time): once
the life-time of a redirect map has come to its end we use it's map
free callback where we need to wait on synchronize_rcu() for current
outstanding xdp buffers and remove such a map pointer from the
redirect info if found to be present. At that time no program is
using this map anymore so we simply invalidate the map pointers to
NULL iff they previously pointed to that instance while making sure
that the redirect path only reads out the map once.

Fixes: 97f91a7cf04f ("bpf: add bpf_redirect_map helper routine")
Fixes: 109980b894e9 ("bpf: don't select potentially stale ri->map from buggy xdp progs")
Reported-by: Sebastiano Miano <[e-mail]>
Signed-off-by: Daniel Borkmann <[e-mail]>
Acked-by: John Fastabend <[e-mail]>
Signed-off-by: Alexei Starovoitov <[e-mail]>

include/linux/filter.h

···
 	u32 flags;
 	struct bpf_map *map;
 	struct bpf_map *map_to_flush;
-	unsigned long   map_owner;
 	u32 kern_flags;
 };
 
···
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
+
+void bpf_clear_redirect_map(struct bpf_map *map);
 
 static inline bool xdp_return_frame_no_direct(void)
 {

include/trace/events/xdp.h

···
 
 #define devmap_ifindex(fwd, map)				\
 	(!fwd ? 0 :						\
-	 (!map ? 0 :						\
-	  ((map->map_type == BPF_MAP_TYPE_DEVMAP) ?		\
-	   ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)))
+	 ((map->map_type == BPF_MAP_TYPE_DEVMAP) ?		\
+	  ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0))
 
 #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx)		\
 	 trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map),	\

kernel/bpf/cpumap.c

···
 	 * It does __not__ ensure pending flush operations (if any) are
 	 * complete.
 	 */
+
+	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* To ensure all pending flush operations have completed wait for flush

kernel/bpf/devmap.c

···
 	list_del_rcu(&dtab->list);
 	spin_unlock(&dev_map_lock);
 
+	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* To ensure all pending flush operations have completed wait for flush

kernel/bpf/verifier.c

···
 			goto patch_call_imm;
 		}
 
-		if (insn->imm == BPF_FUNC_redirect_map) {
-			/* Note, we cannot use prog directly as imm as subsequent
-			 * rewrites would still change the prog pointer. The only
-			 * stable address we can use is aux, which also works with
-			 * prog clones during blinding.
-			 */
-			u64 addr = (unsigned long)prog->aux;
-			struct bpf_insn r4_ld[] = {
-				BPF_LD_IMM64(BPF_REG_4, addr),
-				*insn,
-			};
-			cnt = ARRAY_SIZE(r4_ld);
-
-			new_prog = bpf_patch_insn_data(env, i + delta, r4_ld, cnt);
-			if (!new_prog)
-				return -ENOMEM;
-
-			delta    += cnt - 1;
-			env->prog = prog = new_prog;
-			insn      = new_prog->insnsi + i + delta;
-		}
 patch_call_imm:
 		fn = env->ops->get_func_proto(insn->imm, env->prog);
 		/* all functions that have prototype and verifier allowed

kernel/bpf/xskmap.c

···
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
 	int i;
 
+	bpf_clear_redirect_map(map);
 	synchronize_net();
 
 	for (i = 0; i < map->max_entries; i++) {

net/core/filter.c

···
 	}
 }
 
-static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
-				   unsigned long aux)
+void bpf_clear_redirect_map(struct bpf_map *map)
 {
-	return (unsigned long)xdp_prog->aux != aux;
+	struct bpf_redirect_info *ri;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
+		/* Avoid polluting remote cacheline due to writes if
+		 * not needed. Once we pass this test, we need the
+		 * cmpxchg() to make sure it hasn't been changed in
+		 * the meantime by remote CPU.
+		 */
+		if (unlikely(READ_ONCE(ri->map) == map))
+			cmpxchg(&ri->map, map, NULL);
+	}
 }
 
 static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
-			       struct bpf_prog *xdp_prog)
+			       struct bpf_prog *xdp_prog, struct bpf_map *map)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	unsigned long map_owner = ri->map_owner;
-	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
 	void *fwd = NULL;
 	int err;
 
 	ri->ifindex = 0;
-	ri->map = NULL;
-	ri->map_owner = 0;
-
-	if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
-		err = -EFAULT;
-		map = NULL;
-		goto err;
-	}
+	WRITE_ONCE(ri->map, NULL);
 
 	fwd = __xdp_map_lookup_elem(map, index);
 	if (!fwd) {
···
 		    struct bpf_prog *xdp_prog)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *map = READ_ONCE(ri->map);
 	struct net_device *fwd;
 	u32 index = ri->ifindex;
 	int err;
 
-	if (ri->map)
-		return xdp_do_redirect_map(dev, xdp, xdp_prog);
+	if (map)
+		return xdp_do_redirect_map(dev, xdp, xdp_prog, map);
 
 	fwd = dev_get_by_index_rcu(dev_net(dev), index);
 	ri->ifindex = 0;
···
 static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct xdp_buff *xdp,
-				       struct bpf_prog *xdp_prog)
+				       struct bpf_prog *xdp_prog,
+				       struct bpf_map *map)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	unsigned long map_owner = ri->map_owner;
-	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
 	void *fwd = NULL;
 	int err = 0;
 
 	ri->ifindex = 0;
-	ri->map = NULL;
-	ri->map_owner = 0;
+	WRITE_ONCE(ri->map, NULL);
 
-	if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
-		err = -EFAULT;
-		map = NULL;
-		goto err;
-	}
 	fwd = __xdp_map_lookup_elem(map, index);
 	if (unlikely(!fwd)) {
 		err = -EINVAL;
···
 			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *map = READ_ONCE(ri->map);
 	u32 index = ri->ifindex;
 	struct net_device *fwd;
 	int err = 0;
 
-	if (ri->map)
-		return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog);
-
+	if (map)
+		return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog,
+						   map);
 	ri->ifindex = 0;
 	fwd = dev_get_by_index_rcu(dev_net(dev), index);
 	if (unlikely(!fwd)) {
···
 
 	ri->ifindex = ifindex;
 	ri->flags = flags;
-	ri->map = NULL;
-	ri->map_owner = 0;
+	WRITE_ONCE(ri->map, NULL);
 
 	return XDP_REDIRECT;
 }
···
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
-	   unsigned long, map_owner)
+BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
+	   u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
···
 
 	ri->ifindex = ifindex;
 	ri->flags = flags;
-	ri->map = map;
-	ri->map_owner = map_owner;
+	WRITE_ONCE(ri->map, map);
 
 	return XDP_REDIRECT;
 }
 
-/* Note, arg4 is hidden from users and populated by the verifier
- * with the right pointer.
- */
 static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
 	.func           = bpf_xdp_redirect_map,
 	.gpl_only       = false,