We only use count for kmalloc hashtab not for prealloc hashtab, because
__pcpu_freelist_pop() return NULL when no more elem in pcpu freelist.
But the problem is that __pcpu_freelist_pop() will traverse all CPUs and
spin_lock for all CPUs to find there is no more elem at last.
We encountered bad case on big system with 96 CPUs that alloc_htab_elem()
would last for 1ms. This patch use count for prealloc hashtab too,
avoid traverse and spin_lock for all CPUs in this case.
Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
---
kernel/bpf/hashtab.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 32471ba02708..0c432a23aa00 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -855,12 +855,12 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
htab_put_fd_value(htab, l);
+ atomic_dec(&htab->count);
if (htab_is_prealloc(htab)) {
check_and_free_timer(htab, l);
__pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
- atomic_dec(&htab->count);
l->htab = htab;
call_rcu(&l->rcu, htab_elem_free_rcu);
}
@@ -938,6 +938,11 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
} else {
struct pcpu_freelist_node *l;
+ if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
+ }
+
l = __pcpu_freelist_pop(&htab->freelist);
if (!l)
return ERR_PTR(-E2BIG);
--
2.11.0
