xdp: Add proper __rcu annotations to redirect map entries

XDP_REDIRECT works by a three-step process: the bpf_redirect() and
bpf_redirect_map() helpers will lookup the target of the redirect and store
it (along with some other metadata) in a per-CPU struct bpf_redirect_info.
Next, when the program returns the XDP_REDIRECT return code, the driver
will call xdp_do_redirect() which will use the information thus stored to
actually enqueue the frame into a bulk queue structure (that differs
slightly by map type, but shares the same principle). Finally, before
exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will
flush all the different bulk queues, thus completing the redirect.

Pointers to the map entries will be kept around for this whole sequence of
steps, protected by RCU. However, there is no top-level rcu_read_lock() in
the core code; instead drivers add their own rcu_read_lock() around the XDP
portions of the code, but somewhat inconsistently as Martin discovered[0].
However, things still work because everything happens inside a single NAPI
poll sequence, which means it's between a pair of calls to
local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could
document this intention by using rcu_dereference_check() with
rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and
lockdep to verify that everything is done correctly.

This patch does just that: we add an __rcu annotation to the map entry
pointers and remove the various comments explaining the NAPI poll assurance
strewn through devmap.c in favour of a longer explanation in filter.c. The
goal is to have one coherent documentation of the entire flow, and rely on
the RCU annotations as a "standard" way of communicating the flow in the
map code (which can additionally be understood by sparse and lockdep).

The RCU annotation replacements result in a fairly straight-forward
replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE()
becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the
proper constructs to cast the pointer back and forth between __rcu and
__kernel address space (for the benefit of sparse). The one complication is
that xskmap has a few constructions where double-pointers are passed back
and forth; these simply all gain __rcu annotations, and only the final
reference/dereference to the inner-most pointer gets changed.

With this, everything can be run through sparse without eliciting
complaints, and lockdep can verify correctness even without the use of
rcu_read_lock() in the drivers. Subsequent patches will clean these up from
the drivers.

[0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/
[1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com

1 files changed, 17 insertions, 12 deletions

diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 9df75ea4a567..2e48d0e094d9 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -12,7 +12,7 @@
 #include "xsk.h"
 
 static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
-					       struct xdp_sock **map_entry)
+					       struct xdp_sock __rcu **map_entry)
 {
 	struct xsk_map_node *node;
 
@@ -42,7 +42,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
 }
 
 static void xsk_map_sock_delete(struct xdp_sock *xs,
-				struct xdp_sock **map_entry)
+				struct xdp_sock __rcu **map_entry)
 {
 	struct xsk_map_node *n, *tmp;
 
@@ -124,6 +124,10 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	return insn - insn_buf;
 }
 
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
 static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
@@ -131,12 +135,11 @@ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
 	if (key >= map->max_entries)
 		return NULL;
 
-	return READ_ONCE(m->xsk_map[key]);
+	return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held());
 }
 
 static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
 	return __xsk_map_lookup_elem(map, *(u32 *)key);
 }
 
@@ -149,7 +152,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *xs, *old_xs, **map_entry;
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *xs, *old_xs;
 	u32 i = *(u32 *)key, fd = *(u32 *)value;
 	struct xsk_map_node *node;
 	struct socket *sock;
@@ -179,7 +183,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 
 	spin_lock_bh(&m->lock);
-	old_xs = READ_ONCE(*map_entry);
+	old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock));
 	if (old_xs == xs) {
 		err = 0;
 		goto out;
@@ -191,7 +195,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		goto out;
 	}
 	xsk_map_sock_add(xs, node);
-	WRITE_ONCE(*map_entry, xs);
+	rcu_assign_pointer(*map_entry, xs);
 	if (old_xs)
 		xsk_map_sock_delete(old_xs, map_entry);
 	spin_unlock_bh(&m->lock);
@@ -208,7 +212,8 @@ out:
 static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *old_xs, **map_entry;
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *old_xs;
 	int k = *(u32 *)key;
 
 	if (k >= map->max_entries)
@@ -216,7 +221,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 
 	spin_lock_bh(&m->lock);
 	map_entry = &m->xsk_map[k];
-	old_xs = xchg(map_entry, NULL);
+	old_xs = unrcu_pointer(xchg(map_entry, NULL));
 	if (old_xs)
 		xsk_map_sock_delete(old_xs, map_entry);
 	spin_unlock_bh(&m->lock);
@@ -231,11 +236,11 @@ static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 }
 
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
-			     struct xdp_sock **map_entry)
+			     struct xdp_sock __rcu **map_entry)
 {
 	spin_lock_bh(&map->lock);
-	if (READ_ONCE(*map_entry) == xs) {
-		WRITE_ONCE(*map_entry, NULL);
+	if (rcu_access_pointer(*map_entry) == xs) {
+		rcu_assign_pointer(*map_entry, NULL);
 		xsk_map_sock_delete(xs, map_entry);
 	}
 	spin_unlock_bh(&map->lock);