From: Alexei Starovoitov ast@fb.com
commit 9f691549f76d488a0c74397b3e51e943865ea01f upstream.
when htab_elem is removed from the bucket list the htab_elem.hash_node.next field should not be overridden too early otherwise we have a tiny race window between lookup and delete. The bug was discovered by manual code analysis and reproducible only with explicit udelay() in lookup_elem_raw().
Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements") Reported-by: Jonathan Perry jonperry@fb.com Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Chenbo Feng fengc@google.com --- kernel/bpf/hashtab.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a36a532c056d..f9d53ac57f64 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -41,8 +41,13 @@ enum extra_elem_state { struct htab_elem { union { struct hlist_node hash_node; - struct bpf_htab *htab; - struct pcpu_freelist_node fnode; + struct { + void *padding; + union { + struct bpf_htab *htab; + struct pcpu_freelist_node fnode; + }; + }; }; union { struct rcu_head rcu; @@ -114,8 +119,10 @@ static int prealloc_elems_and_freelist(struct bpf_htab *htab) if (err) goto free_elems;
- pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size, - htab->map.max_entries); + pcpu_freelist_populate(&htab->freelist, + htab->elems + offsetof(struct htab_elem, fnode), + htab->elem_size, htab->map.max_entries); + return 0;
free_elems: @@ -148,6 +155,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) int err, i; u64 cost;
+ BUILD_BUG_ON(offsetof(struct htab_elem, htab) != + offsetof(struct htab_elem, hash_node.pprev)); + BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) != + offsetof(struct htab_elem, hash_node.pprev)); + if (attr->map_flags & ~BPF_F_NO_PREALLOC) /* reserved bits should not be used */ return ERR_PTR(-EINVAL); @@ -429,9 +441,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, int err = 0;
if (prealloc) { - l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); - if (!l_new) + struct pcpu_freelist_node *l; + + l = pcpu_freelist_pop(&htab->freelist); + if (!l) err = -E2BIG; + else + l_new = container_of(l, struct htab_elem, fnode); } else { if (atomic_inc_return(&htab->count) > htab->map.max_entries) { atomic_dec(&htab->count);