From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Dec 2017 14:22:39 -0800
Subject: bpf: add schedule points to map alloc/free
Patch-mainline: v4.15-rc4
Git-commit: 9147efcbe0b7cc96b18eb64b1a3f0d4bba81443c
References: bsc#1083647
While using large percpu maps, htab_map_alloc() can hold
cpu for hundreds of ms.
This patch adds cond_resched() calls to percpu alloc/free
call sites, all running in process context.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Gary Lin <glin@suse.com>
---
kernel/bpf/hashtab.c | 2 ++
1 file changed, 2 insertions(+)
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -110,6 +110,7 @@ static void htab_free_elems(struct bpf_h
pptr = htab_elem_get_ptr(get_htab_elem(htab, i),
htab->map.key_size);
free_percpu(pptr);
+ cond_resched();
}
free_elems:
bpf_map_area_free(htab->elems);
@@ -154,6 +155,7 @@ static int prealloc_init(struct bpf_htab
goto free_elems;
htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
pptr);
+ cond_resched();
}
skip_percpu_elems: