summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2021-08-24 10:30:07 -0700
committerAlexei Starovoitov <ast@kernel.org>2021-08-25 17:40:35 -0700
commiteb18b49ea758ec052ac2a12c6bb204e1e877ec31 (patch)
tree25b1abda9fa79a60a006ec13ec752307cba2c91f /kernel
parent7d789bd0089ad2a6cc2315f281018bfafae820bc (diff)
bpf: tcp: Allow bpf-tcp-cc to call bpf_(get|set)sockopt
This patch allows the bpf-tcp-cc to call bpf_setsockopt. One use case is to allow a bpf-tcp-cc switching to another cc during init(). For example, when the tcp flow is not ecn ready, the bpf_dctcp can switch to another cc by calling setsockopt(TCP_CONGESTION). During setsockopt(TCP_CONGESTION), the new tcp-cc's init() will be called and this could cause a recursion but it is stopped by the current trampoline's logic (in the prog->active counter). While retiring a bpf-tcp-cc (e.g. in tcp_v[46]_destroy_sock()), the tcp stack calls bpf-tcp-cc's release(). To avoid the retiring bpf-tcp-cc making further changes to the sk, bpf_setsockopt is not available to the bpf-tcp-cc's release(). This will avoid release() making setsockopt() call that will potentially allocate new resources. Although the bpf-tcp-cc already has a more powerful way to read tcp_sock from the PTR_TO_BTF_ID, it is usually expected that bpf_getsockopt and bpf_setsockopt are available together. Thus, bpf_getsockopt() is also added to all tcp_congestion_ops except release(). When the old bpf-tcp-cc is calling setsockopt(TCP_CONGESTION) to switch to a new cc, the old bpf-tcp-cc will be released by bpf_struct_ops_put(). Thus, this patch also puts the bpf_struct_ops_map after a rcu grace period because the trampoline's image cannot be freed while the old bpf-tcp-cc is still running. bpf-tcp-cc can only access icsk_ca_priv as SCALAR. All kernel's tcp-cc is also accessing the icsk_ca_priv as SCALAR. The size of icsk_ca_priv has already been raised a few times to avoid extra kmalloc and memory referencing. The only exception is the kernel's tcp_cdg.c that stores a kmalloc()-ed pointer in icsk_ca_priv. To avoid the old bpf-tcp-cc accidentally overriding this tcp_cdg's pointer value stored in icsk_ca_priv after switching and without over-complicating the bpf's verifier for this one exception in tcp_cdg, this patch does not allow switching to tcp_cdg. If there is a need, bpf_tcp_cdg can be implemented and then use the bpf_sk_storage as the extended storage. bpf_sk_setsockopt proto has only been recently added and used in bpf-sockopt and bpf-iter-tcp, so impose the tcp_cdg limitation in the same proto instead of adding a new proto specifically for bpf-tcp-cc. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210824173007.3976921-1-kafai@fb.com
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/bpf_struct_ops.c22
1 files changed, 21 insertions, 1 deletions
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 70f6fd4fa305..d6731c32864e 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -28,6 +28,7 @@ struct bpf_struct_ops_value {
struct bpf_struct_ops_map {
struct bpf_map map;
+ struct rcu_head rcu;
const struct bpf_struct_ops *st_ops;
/* protect map_update */
struct mutex lock;
@@ -622,6 +623,14 @@ bool bpf_struct_ops_get(const void *kdata)
return refcount_inc_not_zero(&kvalue->refcnt);
}
+static void bpf_struct_ops_put_rcu(struct rcu_head *head)
+{
+ struct bpf_struct_ops_map *st_map;
+
+ st_map = container_of(head, struct bpf_struct_ops_map, rcu);
+ bpf_map_put(&st_map->map);
+}
+
void bpf_struct_ops_put(const void *kdata)
{
struct bpf_struct_ops_value *kvalue;
@@ -632,6 +641,17 @@ void bpf_struct_ops_put(const void *kdata)
st_map = container_of(kvalue, struct bpf_struct_ops_map,
kvalue);
- bpf_map_put(&st_map->map);
+ /* The struct_ops's function may switch to another struct_ops.
+ *
+ * For example, bpf_tcp_cc_x->init() may switch to
+ * another tcp_cc_y by calling
+ * setsockopt(TCP_CONGESTION, "tcp_cc_y").
+ * During the switch, bpf_struct_ops_put(tcp_cc_x) is called
+ * and its map->refcnt may reach 0 which then free its
+ * trampoline image while tcp_cc_x is still running.
+ *
+ * Thus, a rcu grace period is needed here.
+ */
+ call_rcu(&st_map->rcu, bpf_struct_ops_put_rcu);
}
}