linux/kernel/bpf/bpf_lru_list.h
Martin KaFai Lau ee9fd0ac30 bpf: Address KCSAN report on bpf_lru_list
KCSAN reported a data-race when accessing node->ref.
Although node->ref does not have to be accurate,
take this chance to use a more common READ_ONCE() and WRITE_ONCE()
pattern instead of data_race().

There is an existing bpf_lru_node_is_ref() and bpf_lru_node_set_ref().
This patch also adds bpf_lru_node_clear_ref() to do the
WRITE_ONCE(node->ref, 0) also.

==================================================================
BUG: KCSAN: data-race in __bpf_lru_list_rotate / __htab_lru_percpu_map_update_elem

write to 0xffff888137038deb of 1 bytes by task 11240 on cpu 1:
__bpf_lru_node_move kernel/bpf/bpf_lru_list.c:113 [inline]
__bpf_lru_list_rotate_active kernel/bpf/bpf_lru_list.c:149 [inline]
__bpf_lru_list_rotate+0x1bf/0x750 kernel/bpf/bpf_lru_list.c:240
bpf_lru_list_pop_free_to_local kernel/bpf/bpf_lru_list.c:329 [inline]
bpf_common_lru_pop_free kernel/bpf/bpf_lru_list.c:447 [inline]
bpf_lru_pop_free+0x638/0xe20 kernel/bpf/bpf_lru_list.c:499
prealloc_lru_pop kernel/bpf/hashtab.c:290 [inline]
__htab_lru_percpu_map_update_elem+0xe7/0x820 kernel/bpf/hashtab.c:1316
bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313
bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200
generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687
bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534
__sys_bpf+0x338/0x810
__do_sys_bpf kernel/bpf/syscall.c:5096 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5094 [inline]
__x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff888137038deb of 1 bytes by task 11241 on cpu 0:
bpf_lru_node_set_ref kernel/bpf/bpf_lru_list.h:70 [inline]
__htab_lru_percpu_map_update_elem+0x2f1/0x820 kernel/bpf/hashtab.c:1332
bpf_percpu_hash_update+0x5e/0x90 kernel/bpf/hashtab.c:2313
bpf_map_update_value+0x2a9/0x370 kernel/bpf/syscall.c:200
generic_map_update_batch+0x3ae/0x4f0 kernel/bpf/syscall.c:1687
bpf_map_do_batch+0x2d9/0x3d0 kernel/bpf/syscall.c:4534
__sys_bpf+0x338/0x810
__do_sys_bpf kernel/bpf/syscall.c:5096 [inline]
__se_sys_bpf kernel/bpf/syscall.c:5094 [inline]
__x64_sys_bpf+0x43/0x50 kernel/bpf/syscall.c:5094
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x01 -> 0x00

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 11241 Comm: syz-executor.3 Not tainted 6.3.0-rc7-syzkaller-00136-g6a66fdd29ea1 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023
==================================================================

Reported-by: syzbot+ebe648a84e8784763f82@syzkaller.appspotmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20230511043748.1384166-1-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-05-12 12:01:03 -07:00

81 lines
2.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2016 Facebook
*/
#ifndef __BPF_LRU_LIST_H_
#define __BPF_LRU_LIST_H_
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/spinlock_types.h>
#define NR_BPF_LRU_LIST_T (3)
#define NR_BPF_LRU_LIST_COUNT (2)
#define NR_BPF_LRU_LOCAL_LIST_T (2)
#define BPF_LOCAL_LIST_T_OFFSET NR_BPF_LRU_LIST_T
enum bpf_lru_list_type {
BPF_LRU_LIST_T_ACTIVE,
BPF_LRU_LIST_T_INACTIVE,
BPF_LRU_LIST_T_FREE,
BPF_LRU_LOCAL_LIST_T_FREE,
BPF_LRU_LOCAL_LIST_T_PENDING,
};
struct bpf_lru_node {
struct list_head list;
u16 cpu;
u8 type;
u8 ref;
};
struct bpf_lru_list {
struct list_head lists[NR_BPF_LRU_LIST_T];
unsigned int counts[NR_BPF_LRU_LIST_COUNT];
/* The next inactive list rotation starts from here */
struct list_head *next_inactive_rotation;
raw_spinlock_t lock ____cacheline_aligned_in_smp;
};
struct bpf_lru_locallist {
struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T];
u16 next_steal;
raw_spinlock_t lock;
};
struct bpf_common_lru {
struct bpf_lru_list lru_list;
struct bpf_lru_locallist __percpu *local_list;
};
typedef bool (*del_from_htab_func)(void *arg, struct bpf_lru_node *node);
struct bpf_lru {
union {
struct bpf_common_lru common_lru;
struct bpf_lru_list __percpu *percpu_lru;
};
del_from_htab_func del_from_htab;
void *del_arg;
unsigned int hash_offset;
unsigned int nr_scans;
bool percpu;
};
static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node)
{
if (!READ_ONCE(node->ref))
WRITE_ONCE(node->ref, 1);
}
int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,
del_from_htab_func del_from_htab, void *delete_arg);
void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
u32 elem_size, u32 nr_elems);
void bpf_lru_destroy(struct bpf_lru *lru);
struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash);
void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node);
void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node);
#endif