bpf: introduce bpf_spin_lock

Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let
bpf program serialize access to other variables.

Example:
struct hash_elem {
    int cnt;
    struct bpf_spin_lock lock;
};
struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key);
if (val) {
    bpf_spin_lock(&val->lock);
    val->cnt++;
    bpf_spin_unlock(&val->lock);
}

Restrictions and safety checks:
- bpf_spin_lock is only allowed inside HASH and ARRAY maps.
- BTF description of the map is mandatory for safety analysis.
- bpf program can take one bpf_spin_lock at a time, since two or more can
  cause dead locks.
- only one 'struct bpf_spin_lock' is allowed per map element.
  It drastically simplifies implementation yet allows bpf program to use
  any number of bpf_spin_locks.
- when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed.
- bpf program must bpf_spin_unlock() before return.
- bpf program can access 'struct bpf_spin_lock' only via
  bpf_spin_lock()/bpf_spin_unlock() helpers.
- load/store into 'struct bpf_spin_lock lock;' field is not allowed.
- to use bpf_spin_lock() helper the BTF description of map value must be
  a struct and have 'struct bpf_spin_lock anyname;' field at the top level.
  Nested lock inside another struct is not allowed.
- syscall map_lookup doesn't copy bpf_spin_lock field to user space.
- syscall map_update and program map_update do not update bpf_spin_lock field.
- bpf_spin_lock cannot be on the stack or inside networking packet.
  bpf_spin_lock can only be inside HASH or ARRAY map value.
- bpf_spin_lock is available to root only and to all program types.
- bpf_spin_lock is not allowed in inner maps of map-in-map.
- ld_abs is not allowed inside spin_lock-ed region.
- tracing progs and socket filter progs cannot use bpf_spin_lock due to
  insufficient preemption checks

Implementation details:
- cgroup-bpf class of programs can nest with xdp/tc programs.
  Hence bpf_spin_lock is equivalent to spin_lock_irqsave.
  Other solutions to avoid nested bpf_spin_lock are possible.
  Like making sure that all networking progs run with softirq disabled.
  spin_lock_irqsave is the simplest and doesn't add overhead to the
  programs that don't use it.
- arch_spinlock_t is used when its implemented as queued_spin_lock
- archs can force their own arch_spinlock_t
- on architectures where queued_spin_lock is not available and
  sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used.
- presence of bpf_spin_lock inside map value could have been indicated via
  extra flag during map_create, but specifying it via BTF is cleaner.
  It provides introspection for map key/value and reduces user mistakes.

Next steps:
- allow bpf_spin_lock in other map types (like cgroup local storage)
- introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper
  to request kernel to grab bpf_spin_lock before rewriting the value.
  That will serialize access to map elements.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 42 insertions, 0 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 3d661f0606fe..7019c1f05cab 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -355,6 +355,11 @@ static bool btf_type_is_struct(const struct btf_type *t)
 	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
 }
 
+static bool __btf_type_is_struct(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
+}
+
 static bool btf_type_is_array(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
@@ -2045,6 +2050,43 @@ static void btf_struct_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
+/* find 'struct bpf_spin_lock' in map value.
+ * return >= 0 offset if found
+ * and < 0 in case of error
+ */
+int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
+{
+	const struct btf_member *member;
+	u32 i, off = -ENOENT;
+
+	if (!__btf_type_is_struct(t))
+		return -EINVAL;
+
+	for_each_member(i, t, member) {
+		const struct btf_type *member_type = btf_type_by_id(btf,
+								    member->type);
+		if (!__btf_type_is_struct(member_type))
+			continue;
+		if (member_type->size != sizeof(struct bpf_spin_lock))
+			continue;
+		if (strcmp(__btf_name_by_offset(btf, member_type->name_off),
+			   "bpf_spin_lock"))
+			continue;
+		if (off != -ENOENT)
+			/* only one 'struct bpf_spin_lock' is allowed */
+			return -E2BIG;
+		off = btf_member_bit_offset(t, member);
+		if (off % 8)
+			/* valid C code cannot generate such BTF */
+			return -EINVAL;
+		off /= 8;
+		if (off % __alignof__(struct bpf_spin_lock))
+			/* valid struct bpf_spin_lock will be 4 byte aligned */
+			return -EINVAL;
+	}
+	return off;
+}
+
 static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
 				u32 type_id, void *data, u8 bits_offset,
 				struct seq_file *m)