x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

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) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 261 insertions, 0 deletions

diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
new file mode 100644
index 000000000..36c9c06e9
--- /dev/null
+++ b/fs/gfs2/main.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
+ * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfs2_ondisk.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <linux/atomic.h>
+#include <linux/mempool.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "super.h"
+#include "sys.h"
+#include "util.h"
+#include "glock.h"
+#include "quota.h"
+#include "recovery.h"
+#include "dir.h"
+#include "glops.h"
+
+struct workqueue_struct *gfs2_control_wq;
+
+static void gfs2_init_inode_once(void *foo)
+{
+	struct gfs2_inode *ip = foo;
+
+	inode_init_once(&ip->i_inode);
+	atomic_set(&ip->i_sizehint, 0);
+	init_rwsem(&ip->i_rw_mutex);
+	INIT_LIST_HEAD(&ip->i_ordered);
+	ip->i_qadata = NULL;
+	gfs2_holder_mark_uninitialized(&ip->i_rgd_gh);
+	memset(&ip->i_res, 0, sizeof(ip->i_res));
+	RB_CLEAR_NODE(&ip->i_res.rs_node);
+	ip->i_hash_cache = NULL;
+	gfs2_holder_mark_uninitialized(&ip->i_iopen_gh);
+}
+
+static void gfs2_init_glock_once(void *foo)
+{
+	struct gfs2_glock *gl = foo;
+
+	INIT_LIST_HEAD(&gl->gl_holders);
+	INIT_LIST_HEAD(&gl->gl_ail_list);
+	atomic_set(&gl->gl_ail_count, 0);
+	atomic_set(&gl->gl_revokes, 0);
+}
+
+static void gfs2_init_gl_aspace_once(void *foo)
+{
+	struct gfs2_glock_aspace *gla = foo;
+
+	gfs2_init_glock_once(&gla->glock);
+	address_space_init_once(&gla->mapping);
+}
+
+/**
+ * init_gfs2_fs - Register GFS2 as a filesystem
+ *
+ * Returns: 0 on success, error code on failure
+ */
+
+static int __init init_gfs2_fs(void)
+{
+	int error;
+
+	gfs2_str2qstr(&gfs2_qdot, ".");
+	gfs2_str2qstr(&gfs2_qdotdot, "..");
+	gfs2_quota_hash_init();
+
+	error = gfs2_sys_init();
+	if (error)
+		return error;
+
+	error = list_lru_init(&gfs2_qd_lru);
+	if (error)
+		goto fail_lru;
+
+	error = gfs2_glock_init();
+	if (error)
+		goto fail_glock;
+
+	error = -ENOMEM;
+	gfs2_glock_cachep = kmem_cache_create("gfs2_glock",
+					      sizeof(struct gfs2_glock),
+					      0, SLAB_RECLAIM_ACCOUNT,
+					      gfs2_init_glock_once);
+	if (!gfs2_glock_cachep)
+		goto fail_cachep1;
+
+	gfs2_glock_aspace_cachep = kmem_cache_create("gfs2_glock(aspace)",
+					sizeof(struct gfs2_glock_aspace),
+					0, 0, gfs2_init_gl_aspace_once);
+
+	if (!gfs2_glock_aspace_cachep)
+		goto fail_cachep2;
+
+	gfs2_inode_cachep = kmem_cache_create("gfs2_inode",
+					      sizeof(struct gfs2_inode),
+					      0,  SLAB_RECLAIM_ACCOUNT|
+						  SLAB_ACCOUNT,
+					      gfs2_init_inode_once);
+	if (!gfs2_inode_cachep)
+		goto fail_cachep3;
+
+	gfs2_bufdata_cachep = kmem_cache_create("gfs2_bufdata",
+						sizeof(struct gfs2_bufdata),
+					        0, 0, NULL);
+	if (!gfs2_bufdata_cachep)
+		goto fail_cachep4;
+
+	gfs2_rgrpd_cachep = kmem_cache_create("gfs2_rgrpd",
+					      sizeof(struct gfs2_rgrpd),
+					      0, 0, NULL);
+	if (!gfs2_rgrpd_cachep)
+		goto fail_cachep5;
+
+	gfs2_quotad_cachep = kmem_cache_create("gfs2_quotad",
+					       sizeof(struct gfs2_quota_data),
+					       0, SLAB_RECLAIM_ACCOUNT, NULL);
+	if (!gfs2_quotad_cachep)
+		goto fail_cachep6;
+
+	gfs2_qadata_cachep = kmem_cache_create("gfs2_qadata",
+					       sizeof(struct gfs2_qadata),
+					       0, 0, NULL);
+	if (!gfs2_qadata_cachep)
+		goto fail_cachep7;
+
+	gfs2_trans_cachep = kmem_cache_create("gfs2_trans",
+					       sizeof(struct gfs2_trans),
+					       0, 0, NULL);
+	if (!gfs2_trans_cachep)
+		goto fail_cachep8;
+
+	error = gfs2_qd_shrinker_init();
+	if (error)
+		goto fail_shrinker;
+
+	error = -ENOMEM;
+	gfs2_recovery_wq = alloc_workqueue("gfs2_recovery",
+					  WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU,
+					  0);
+	if (!gfs2_recovery_wq)
+		goto fail_wq1;
+
+	gfs2_control_wq = alloc_workqueue("gfs2_control",
+					  WQ_UNBOUND | WQ_FREEZABLE, 0);
+	if (!gfs2_control_wq)
+		goto fail_wq2;
+
+	gfs2_freeze_wq = alloc_workqueue("gfs2_freeze", WQ_PERCPU, 0);
+
+	if (!gfs2_freeze_wq)
+		goto fail_wq3;
+
+	gfs2_page_pool = mempool_create_page_pool(64, 0);
+	if (!gfs2_page_pool)
+		goto fail_mempool;
+
+	gfs2_register_debugfs();
+	error = register_filesystem(&gfs2_fs_type);
+	if (error)
+		goto fail_fs1;
+
+	error = register_filesystem(&gfs2meta_fs_type);
+	if (error)
+		goto fail_fs2;
+
+
+	pr_info("GFS2 installed\n");
+
+	return 0;
+
+fail_fs2:
+	unregister_filesystem(&gfs2_fs_type);
+fail_fs1:
+	mempool_destroy(gfs2_page_pool);
+fail_mempool:
+	destroy_workqueue(gfs2_freeze_wq);
+fail_wq3:
+	destroy_workqueue(gfs2_control_wq);
+fail_wq2:
+	destroy_workqueue(gfs2_recovery_wq);
+fail_wq1:
+	gfs2_qd_shrinker_exit();
+fail_shrinker:
+	kmem_cache_destroy(gfs2_trans_cachep);
+fail_cachep8:
+	kmem_cache_destroy(gfs2_qadata_cachep);
+fail_cachep7:
+	kmem_cache_destroy(gfs2_quotad_cachep);
+fail_cachep6:
+	kmem_cache_destroy(gfs2_rgrpd_cachep);
+fail_cachep5:
+	kmem_cache_destroy(gfs2_bufdata_cachep);
+fail_cachep4:
+	kmem_cache_destroy(gfs2_inode_cachep);
+fail_cachep3:
+	kmem_cache_destroy(gfs2_glock_aspace_cachep);
+fail_cachep2:
+	kmem_cache_destroy(gfs2_glock_cachep);
+fail_cachep1:
+	gfs2_glock_exit();
+fail_glock:
+	list_lru_destroy(&gfs2_qd_lru);
+fail_lru:
+	gfs2_sys_uninit();
+	return error;
+}
+
+/**
+ * exit_gfs2_fs - Unregister the file system
+ *
+ */
+
+static void __exit exit_gfs2_fs(void)
+{
+	gfs2_qd_shrinker_exit();
+	gfs2_glock_exit();
+	gfs2_unregister_debugfs();
+	unregister_filesystem(&gfs2_fs_type);
+	unregister_filesystem(&gfs2meta_fs_type);
+	destroy_workqueue(gfs2_recovery_wq);
+	destroy_workqueue(gfs2_control_wq);
+	destroy_workqueue(gfs2_freeze_wq);
+	list_lru_destroy(&gfs2_qd_lru);
+
+	rcu_barrier();
+
+	mempool_destroy(gfs2_page_pool);
+	kmem_cache_destroy(gfs2_trans_cachep);
+	kmem_cache_destroy(gfs2_qadata_cachep);
+	kmem_cache_destroy(gfs2_quotad_cachep);
+	kmem_cache_destroy(gfs2_rgrpd_cachep);
+	kmem_cache_destroy(gfs2_bufdata_cachep);
+	kmem_cache_destroy(gfs2_inode_cachep);
+	kmem_cache_destroy(gfs2_glock_aspace_cachep);
+	kmem_cache_destroy(gfs2_glock_cachep);
+
+	gfs2_sys_uninit();
+}
+
+MODULE_DESCRIPTION("Global File System");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+module_init(init_gfs2_fs);
+module_exit(exit_gfs2_fs);
+