From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- fs/f2fs/shrinker.c | 247 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 247 insertions(+) create mode 100644 fs/f2fs/shrinker.c (limited to 'fs/f2fs/shrinker.c') diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c new file mode 100644 index 000000000..4f6bf5926 --- /dev/null +++ b/fs/f2fs/shrinker.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * f2fs shrinker support + * the basic infra was copied from fs/ubifs/shrinker.c + * + * Copyright (c) 2015 Motorola Mobility + * Copyright (c) 2015 Jaegeuk Kim + */ +#include +#include + +#include "f2fs.h" +#include "node.h" + +static LIST_HEAD(f2fs_list); +static DEFINE_SPINLOCK(f2fs_list_lock); +static unsigned int shrinker_run_no; + +static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi) +{ + return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT]; +} + +static unsigned long __count_free_nids(struct f2fs_sb_info *sbi) +{ + long count = NM_I(sbi)->nid_cnt[FREE_NID] - MAX_FREE_NIDS; + + return count > 0 ? count : 0; +} + +static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi, + enum extent_type type) +{ + struct extent_tree_info *eti = &sbi->extent_tree[type]; + + return atomic_read(&eti->total_zombie_tree) + + atomic_read(&eti->total_ext_node); +} + +unsigned long f2fs_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct f2fs_sb_info *sbi; + struct list_head *p; + unsigned long count = 0; + + spin_lock(&f2fs_list_lock); + p = f2fs_list.next; + while (p != &f2fs_list) { + sbi = list_entry(p, struct f2fs_sb_info, s_list); + + /* stop f2fs_put_super */ + if (!mutex_trylock(&sbi->umount_mutex)) { + p = p->next; + continue; + } + spin_unlock(&f2fs_list_lock); + + /* count read extent cache entries */ + count += __count_extent_cache(sbi, EX_READ); + + /* count block age extent cache entries */ + count += __count_extent_cache(sbi, EX_BLOCK_AGE); + + /* count clean nat cache entries */ + count += __count_nat_entries(sbi); + + /* count free nids cache entries */ + count += __count_free_nids(sbi); + + spin_lock(&f2fs_list_lock); + p = p->next; + mutex_unlock(&sbi->umount_mutex); + } + spin_unlock(&f2fs_list_lock); + return count ?: SHRINK_EMPTY; +} + +unsigned long f2fs_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long nr = sc->nr_to_scan; + struct f2fs_sb_info *sbi; + struct list_head *p; + unsigned int run_no; + unsigned long freed = 0; + + spin_lock(&f2fs_list_lock); + do { + run_no = ++shrinker_run_no; + } while (run_no == 0); + p = f2fs_list.next; + while (p != &f2fs_list) { + sbi = list_entry(p, struct f2fs_sb_info, s_list); + + if (sbi->shrinker_run_no == run_no) + break; + + /* stop f2fs_put_super */ + if (!mutex_trylock(&sbi->umount_mutex)) { + p = p->next; + continue; + } + spin_unlock(&f2fs_list_lock); + + sbi->shrinker_run_no = run_no; + + /* shrink extent cache entries */ + freed += f2fs_shrink_age_extent_tree(sbi, nr >> 2); + + /* shrink read extent cache entries */ + if (freed < nr) + freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2); + + /* shrink clean nat cache entries */ + if (freed < nr) + freed += f2fs_try_to_free_nats(sbi, nr - freed); + + /* shrink free nids cache entries */ + if (freed < nr) + freed += f2fs_try_to_free_nids(sbi, nr - freed); + + spin_lock(&f2fs_list_lock); + p = p->next; + list_move_tail(&sbi->s_list, &f2fs_list); + mutex_unlock(&sbi->umount_mutex); + if (freed >= nr) + break; + } + spin_unlock(&f2fs_list_lock); + return freed; +} + +unsigned int f2fs_donate_files(void) +{ + struct f2fs_sb_info *sbi; + struct list_head *p; + unsigned int donate_files = 0; + + spin_lock(&f2fs_list_lock); + p = f2fs_list.next; + while (p != &f2fs_list) { + sbi = list_entry(p, struct f2fs_sb_info, s_list); + + /* stop f2fs_put_super */ + if (!mutex_trylock(&sbi->umount_mutex)) { + p = p->next; + continue; + } + spin_unlock(&f2fs_list_lock); + + donate_files += sbi->donate_files; + + spin_lock(&f2fs_list_lock); + p = p->next; + mutex_unlock(&sbi->umount_mutex); + } + spin_unlock(&f2fs_list_lock); + + return donate_files; +} + +static unsigned int do_reclaim_caches(struct f2fs_sb_info *sbi, + unsigned int reclaim_caches_kb) +{ + struct inode *inode; + struct f2fs_inode_info *fi; + unsigned int nfiles = sbi->donate_files; + pgoff_t npages = reclaim_caches_kb >> (PAGE_SHIFT - 10); + + while (npages && nfiles--) { + pgoff_t len; + + spin_lock(&sbi->inode_lock[DONATE_INODE]); + if (list_empty(&sbi->inode_list[DONATE_INODE])) { + spin_unlock(&sbi->inode_lock[DONATE_INODE]); + break; + } + fi = list_first_entry(&sbi->inode_list[DONATE_INODE], + struct f2fs_inode_info, gdonate_list); + list_move_tail(&fi->gdonate_list, &sbi->inode_list[DONATE_INODE]); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[DONATE_INODE]); + + if (!inode) + continue; + + inode_lock(inode); + if (!is_inode_flag_set(inode, FI_DONATE_FINISHED)) { + len = fi->donate_end - fi->donate_start + 1; + npages = npages < len ? 0 : npages - len; + + invalidate_inode_pages2_range(inode->i_mapping, + fi->donate_start, fi->donate_end); + set_inode_flag(inode, FI_DONATE_FINISHED); + } + inode_unlock(inode); + + iput(inode); + cond_resched(); + } + return npages << (PAGE_SHIFT - 10); +} + +void f2fs_reclaim_caches(unsigned int reclaim_caches_kb) +{ + struct f2fs_sb_info *sbi; + struct list_head *p; + + spin_lock(&f2fs_list_lock); + p = f2fs_list.next; + while (p != &f2fs_list && reclaim_caches_kb) { + sbi = list_entry(p, struct f2fs_sb_info, s_list); + + /* stop f2fs_put_super */ + if (!mutex_trylock(&sbi->umount_mutex)) { + p = p->next; + continue; + } + spin_unlock(&f2fs_list_lock); + + reclaim_caches_kb = do_reclaim_caches(sbi, reclaim_caches_kb); + + spin_lock(&f2fs_list_lock); + p = p->next; + mutex_unlock(&sbi->umount_mutex); + } + spin_unlock(&f2fs_list_lock); +} + +void f2fs_join_shrinker(struct f2fs_sb_info *sbi) +{ + spin_lock(&f2fs_list_lock); + list_add_tail(&sbi->s_list, &f2fs_list); + spin_unlock(&f2fs_list_lock); +} + +void f2fs_leave_shrinker(struct f2fs_sb_info *sbi) +{ + f2fs_shrink_read_extent_tree(sbi, __count_extent_cache(sbi, EX_READ)); + f2fs_shrink_age_extent_tree(sbi, + __count_extent_cache(sbi, EX_BLOCK_AGE)); + + spin_lock(&f2fs_list_lock); + list_del_init(&sbi->s_list); + spin_unlock(&f2fs_list_lock); +} -- cgit v1.3.1