From: Mykyta Yatsenko <yatsenko@meta.com> mainline inclusion from mainline-v7.2-rc1 commit 89edbdfc5d0308cef57b71359331de5c4ddbf763 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/9693 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- NMI and tracepoint BPF programs can re-enter the per-CPU or global LRU lock that bpf_lru_pop_free()/push_free() already hold on the same CPU, AA-deadlocking. Lockdep reports "inconsistent {INITIAL USE} -> {IN-NMI}" on &l->lock (syzbot c69a0a2c816716f1e0d5) and "possible recursive locking detected" on &loc_l->lock (syzbot 18b26edb69b2e19f3b33). Prior trylock and rqspinlock based fixes (see links) were nacked because compromised on reliability. This patch converts every LRU lock site to rqspinlock_t and adds a recovery path for some failure windows to avoid node leaks. Failure recovery: - *_pop_free top-level: return NULL; prealloc_lru_pop() already treats that as no-free-element (-ENOMEM). - Cross-CPU steal: skip the victim's locked loc_l, try next CPU. - Post-steal local lock fail: publish stolen node to lockless per-CPU free_llist; next pop on this CPU picks it up. - push_free fail: mark node pending_free=1. __local_list_flush(), __local_list_pop_pending() reclaim the node from pending_list. __bpf_lru_list_shrink_inactive() reclaims the node from inactive list. Nodes from active list are reclaimed by __bpf_lru_list_shrink() or after __bpf_lru_list_rotate_active() demotes it to the inactive. Fixes: 3a08c2fd7634 ("bpf: LRU List") Reported-by: syzbot+c69a0a2c816716f1e0d5@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c69a0a2c816716f1e0d5 Reported-by: syzbot+18b26edb69b2e19f3b33@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=18b26edb69b2e19f3b33 Link: https://lore.kernel.org/bpf/CAPPBnEYO4R+m+SpVc2gNj_x31R6fo1uJvj2bK2YS1P09GWT... Link: https://lore.kernel.org/bpf/CAPPBnEZmFA3ab8Uc=PEm0bdojZy=7T_F5_+eyZSHyZR3MBG... Link: https://lore.kernel.org/bpf/20251030030010.95352-1-dongml2@chinatelecom.cn/ Link: https://lore.kernel.org/bpf/20260119142120.28170-1-leon.hwang@linux.dev/ Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com> Link: https://lore.kernel.org/r/20260607-lru_map_spin-v3-1-bcd9332e911b@meta.com Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Pu Lehui <pulehui@huawei.com> --- kernel/bpf/bpf_lru_list.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index fe2661a58ea9..8d0ee61622af 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -6,11 +6,11 @@ #include <linux/cache.h> #include <linux/list.h> -#include <linux/spinlock_types.h> +#include <linux/llist.h> +#include <asm/rqspinlock.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 { @@ -22,10 +22,22 @@ enum bpf_lru_list_type { }; struct bpf_lru_node { - struct list_head list; + /* + * A node is in at most one list at a time. The free path on the + * per-CPU locallist uses an llist, so share storage via a union. + */ + union { + struct list_head list; + struct llist_node llist; + }; u16 cpu; u8 type; u8 ref; + /* + * Marks nodes whose *_push_free() lock acquire failed; reclaimed + * by flush/shrink which honor the flag instead of del_from_htab(). + */ + u8 pending_free; }; struct bpf_lru_list { @@ -34,13 +46,14 @@ struct bpf_lru_list { /* The next inactive list rotation starts from here */ struct list_head *next_inactive_rotation; - raw_spinlock_t lock ____cacheline_aligned_in_smp; + rqspinlock_t lock ____cacheline_aligned_in_smp; }; struct bpf_lru_locallist { - struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T]; + struct list_head pending_list; + struct llist_head free_llist; u16 next_steal; - raw_spinlock_t lock; + rqspinlock_t lock; }; struct bpf_common_lru { -- 2.34.1