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/dlm/memory.c | 179 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 179 insertions(+) create mode 100644 fs/dlm/memory.c (limited to 'fs/dlm/memory.c') diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c new file mode 100644 index 000000000..ee55994ce --- /dev/null +++ b/fs/dlm/memory.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0-only +/****************************************************************************** +******************************************************************************* +** +** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. +** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. +** +** +******************************************************************************* +******************************************************************************/ + +#include "dlm_internal.h" +#include "midcomms.h" +#include "lowcomms.h" +#include "config.h" +#include "memory.h" +#include "ast.h" + +static struct kmem_cache *writequeue_cache; +static struct kmem_cache *mhandle_cache; +static struct kmem_cache *msg_cache; +static struct kmem_cache *lkb_cache; +static struct kmem_cache *rsb_cache; +static struct kmem_cache *cb_cache; + + +int __init dlm_memory_init(void) +{ + writequeue_cache = dlm_lowcomms_writequeue_cache_create(); + if (!writequeue_cache) + goto out; + + mhandle_cache = dlm_midcomms_cache_create(); + if (!mhandle_cache) + goto mhandle; + + lkb_cache = kmem_cache_create("dlm_lkb", sizeof(struct dlm_lkb), + __alignof__(struct dlm_lkb), 0, NULL); + if (!lkb_cache) + goto lkb; + + msg_cache = dlm_lowcomms_msg_cache_create(); + if (!msg_cache) + goto msg; + + rsb_cache = kmem_cache_create("dlm_rsb", sizeof(struct dlm_rsb), + __alignof__(struct dlm_rsb), 0, NULL); + if (!rsb_cache) + goto rsb; + + cb_cache = kmem_cache_create_usercopy("dlm_cb", sizeof(struct dlm_callback), + __alignof__(struct dlm_callback), 0, + offsetof(struct dlm_callback, lvbptr), + sizeof_field(struct dlm_callback, lvbptr), + NULL); + if (!cb_cache) + goto cb; + + return 0; + +cb: + kmem_cache_destroy(rsb_cache); +rsb: + kmem_cache_destroy(msg_cache); +msg: + kmem_cache_destroy(lkb_cache); +lkb: + kmem_cache_destroy(mhandle_cache); +mhandle: + kmem_cache_destroy(writequeue_cache); +out: + return -ENOMEM; +} + +void dlm_memory_exit(void) +{ + rcu_barrier(); + + kmem_cache_destroy(writequeue_cache); + kmem_cache_destroy(mhandle_cache); + kmem_cache_destroy(msg_cache); + kmem_cache_destroy(lkb_cache); + kmem_cache_destroy(rsb_cache); + kmem_cache_destroy(cb_cache); +} + +char *dlm_allocate_lvb(struct dlm_ls *ls) +{ + return kzalloc(ls->ls_lvblen, GFP_ATOMIC); +} + +void dlm_free_lvb(char *p) +{ + kfree(p); +} + +struct dlm_rsb *dlm_allocate_rsb(void) +{ + return kmem_cache_zalloc(rsb_cache, GFP_ATOMIC); +} + +static void __free_rsb_rcu(struct rcu_head *rcu) +{ + struct dlm_rsb *r = container_of(rcu, struct dlm_rsb, rcu); + if (r->res_lvbptr) + dlm_free_lvb(r->res_lvbptr); + kmem_cache_free(rsb_cache, r); +} + +void dlm_free_rsb(struct dlm_rsb *r) +{ + call_rcu(&r->rcu, __free_rsb_rcu); +} + +struct dlm_lkb *dlm_allocate_lkb(void) +{ + return kmem_cache_zalloc(lkb_cache, GFP_ATOMIC); +} + +static void __free_lkb_rcu(struct rcu_head *rcu) +{ + struct dlm_lkb *lkb = container_of(rcu, struct dlm_lkb, rcu); + + if (test_bit(DLM_DFL_USER_BIT, &lkb->lkb_dflags)) { + struct dlm_user_args *ua; + ua = lkb->lkb_ua; + if (ua) { + kfree(ua->lksb.sb_lvbptr); + kfree(ua); + } + } + + kmem_cache_free(lkb_cache, lkb); +} + +void dlm_free_lkb(struct dlm_lkb *lkb) +{ + call_rcu(&lkb->rcu, __free_lkb_rcu); +} + +struct dlm_mhandle *dlm_allocate_mhandle(void) +{ + return kmem_cache_alloc(mhandle_cache, GFP_ATOMIC); +} + +void dlm_free_mhandle(struct dlm_mhandle *mhandle) +{ + kmem_cache_free(mhandle_cache, mhandle); +} + +struct writequeue_entry *dlm_allocate_writequeue(void) +{ + return kmem_cache_alloc(writequeue_cache, GFP_ATOMIC); +} + +void dlm_free_writequeue(struct writequeue_entry *writequeue) +{ + kmem_cache_free(writequeue_cache, writequeue); +} + +struct dlm_msg *dlm_allocate_msg(void) +{ + return kmem_cache_alloc(msg_cache, GFP_ATOMIC); +} + +void dlm_free_msg(struct dlm_msg *msg) +{ + kmem_cache_free(msg_cache, msg); +} + +struct dlm_callback *dlm_allocate_cb(void) +{ + return kmem_cache_alloc(cb_cache, GFP_ATOMIC); +} + +void dlm_free_cb(struct dlm_callback *cb) +{ + kmem_cache_free(cb_cache, cb); +} -- cgit v1.3.1