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, 10 insertions, 11 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4b7c76765d9d..6d3b22c5ad68 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -718,21 +718,12 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 	       BITS_PER_LONG == 64;
 }
 
-static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
-{
-	u32 size = htab->map.value_size;
-
-	if (percpu || fd_htab_map_needs_adjust(htab))
-		size = round_up(size, 8);
-	return size;
-}
-
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 					 void *value, u32 key_size, u32 hash,
 					 bool percpu, bool onallcpus,
 					 struct htab_elem *old_elem)
 {
-	u32 size = htab_size_value(htab, percpu);
+	u32 size = htab->map.value_size;
 	bool prealloc = htab_is_prealloc(htab);
 	struct htab_elem *l_new, **pl_new;
 	void __percpu *pptr;
@@ -770,10 +761,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			l_new = ERR_PTR(-ENOMEM);
 			goto dec_count;
 		}
+		check_and_init_map_lock(&htab->map,
+					l_new->key + round_up(key_size, 8));
 	}
 
 	memcpy(l_new->key, key, key_size);
 	if (percpu) {
+		size = round_up(size, 8);
 		if (prealloc) {
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
@@ -791,8 +785,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 		if (!prealloc)
 			htab_elem_set_ptr(l_new, key_size, pptr);
-	} else {
+	} else if (fd_htab_map_needs_adjust(htab)) {
+		size = round_up(size, 8);
 		memcpy(l_new->key + round_up(key_size, 8), value, size);
+	} else {
+		copy_map_value(&htab->map,
+			       l_new->key + round_up(key_size, 8),
+			       value);
 	}
 
 	l_new->hash = hash;