bpf: Add map side support for bpf timers.

Restrict bpf timers to array, hash (both preallocated and kmalloced), and
lru map types. The per-cpu maps with timers don't make sense, since 'struct
bpf_timer' is a part of map value. bpf timers in per-cpu maps would mean that
the number of timers depends on number of possible cpus and timers would not be
accessible from all cpus. lpm map support can be added in the future.
The timers in inner maps are supported.

The bpf_map_update/delete_elem() helpers and sys_bpf commands cancel and free
bpf_timer in a given map element.

Similar to 'struct bpf_spin_lock' BTF is required and it is used to validate
that map element indeed contains 'struct bpf_timer'.

Make check_and_init_map_value() init both bpf_spin_lock and bpf_timer when
map element data is reused in preallocated htab and lru maps.

Teach copy_map_value() to support both bpf_spin_lock and bpf_timer in a single
map element. There could be one of each, but not more than one. Due to 'one
bpf_timer in one element' restriction do not support timers in global data,
since global data is a map of single element, but from bpf program side it's
seen as many global variables and restriction of single global timer would be
odd. The sys_bpf map_freeze and sys_mmap syscalls are not allowed on maps with
timers, since user space could have corrupted mmap element and crashed the
kernel. The maps with timers cannot be readonly. Due to these restrictions
search for bpf_timer in datasec BTF in case it was placed in the global data to
report clear error.

The previous patch allowed 'struct bpf_timer' as a first field in a map
element only. Relax this restriction.

Refactor lru map to s/bpf_lru_push_free/htab_lru_push_free/ to cancel and free
the timer when lru map deletes an element as a part of it eviction algorithm.

Make sure that bpf program cannot access 'struct bpf_timer' via direct load/store.
The timer operation are done through helpers only.
This is similar to 'struct bpf_spin_lock'.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210715005417.78572-5-alexei.starovoitov@gmail.com

1 files changed, 33 insertions, 11 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 125240b7cefb..a9a4a480a6d0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -198,24 +198,46 @@ static inline bool map_value_has_spin_lock(const struct bpf_map *map)
 	return map->spin_lock_off >= 0;
 }
 
-static inline void check_and_init_map_lock(struct bpf_map *map, void *dst)
+static inline bool map_value_has_timer(const struct bpf_map *map)
 {
-	if (likely(!map_value_has_spin_lock(map)))
-		return;
-	*(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
-		(struct bpf_spin_lock){};
+	return map->timer_off >= 0;
 }
 
-/* copy everything but bpf_spin_lock */
+static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
+{
+	if (unlikely(map_value_has_spin_lock(map)))
+		*(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
+			(struct bpf_spin_lock){};
+	if (unlikely(map_value_has_timer(map)))
+		*(struct bpf_timer *)(dst + map->timer_off) =
+			(struct bpf_timer){};
+}
+
+/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */
 static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
 {
+	u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0;
+
 	if (unlikely(map_value_has_spin_lock(map))) {
-		u32 off = map->spin_lock_off;
+		s_off = map->spin_lock_off;
+		s_sz = sizeof(struct bpf_spin_lock);
+	} else if (unlikely(map_value_has_timer(map))) {
+		t_off = map->timer_off;
+		t_sz = sizeof(struct bpf_timer);
+	}
 
-		memcpy(dst, src, off);
-		memcpy(dst + off + sizeof(struct bpf_spin_lock),
-		       src + off + sizeof(struct bpf_spin_lock),
-		       map->value_size - off - sizeof(struct bpf_spin_lock));
+	if (unlikely(s_sz || t_sz)) {
+		if (s_off < t_off || !s_sz) {
+			swap(s_off, t_off);
+			swap(s_sz, t_sz);
+		}
+		memcpy(dst, src, t_off);
+		memcpy(dst + t_off + t_sz,
+		       src + t_off + t_sz,
+		       s_off - t_off - t_sz);
+		memcpy(dst + s_off + s_sz,
+		       src + s_off + s_sz,
+		       map->value_size - s_off - s_sz);
 	} else {
 		memcpy(dst, src, map->value_size);
 	}