bpf_map_alloc_pages() picks the allocator via can_alloc_pages(), a conservative guess for BPF program context that is always false under PREEMPT_RT. So even a caller that really is sleepable gets the non-blocking allocator, which never reclaims and never engages the OOM machinery.
Add bpf_map_alloc_page_sleepable() for callers that know they are sleepable. The next patch uses it from the arena page fault handler. Signed-off-by: Jiayuan Chen <[email protected]> --- include/linux/bpf.h | 1 + kernel/bpf/syscall.c | 21 +++++++++++++++++---- 2 files changed, 18 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d9542127dfdf..9ba03622709b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2779,6 +2779,7 @@ struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, int nid, unsigned long nr_pages, struct page **page_array); +struct page *bpf_map_alloc_page_sleepable(const struct bpf_map *map, int nid); #ifdef CONFIG_MEMCG void bpf_map_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg, struct mem_cgroup **new_memcg); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0ff9e3aa293d..cec88450e4ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -602,15 +602,14 @@ static bool can_alloc_pages(void) !IS_ENABLED(CONFIG_PREEMPT_RT); } +#define BPF_PAGE_GFP (GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT | __GFP_NOWARN) + static struct page *__bpf_alloc_page(int nid) { if (!can_alloc_pages()) return alloc_pages_nolock(__GFP_ACCOUNT, nid, 0); - return alloc_pages_node(nid, - GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT - | __GFP_NOWARN, - 0); + return alloc_pages_node(nid, BPF_PAGE_GFP, 0); } int bpf_map_alloc_pages(const struct bpf_map *map, int nid, @@ -636,6 +635,20 @@ int bpf_map_alloc_pages(const struct bpf_map *map, int nid, return ret; } +/* + * For callers that know they run in a sleepable context, e.g. a user page + * fault handler. can_alloc_pages() is a conservative guess made for BPF + * program context - notably it is always false on PREEMPT_RT - so going + * through bpf_map_alloc_pages() there would needlessly pick the + * non-blocking allocator, which never reclaims and never engages the OOM + * machinery. + */ +struct page *bpf_map_alloc_page_sleepable(const struct bpf_map *map, int nid) +{ + might_sleep(); + return alloc_pages_node(nid, BPF_PAGE_GFP, 0); +} + static int btf_field_cmp(const void *a, const void *b) { -- 2.43.0
