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, 148 insertions, 0 deletions

diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
new file mode 100644
index 000000000..a5b60778b
--- /dev/null
+++ b/fs/gfs2/acl.c
@@ -0,0 +1,148 @@
+// 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.
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/completion.h>
+#include <linux/buffer_head.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/gfs2_ondisk.h>
+
+#include "gfs2.h"
+#include "incore.h"
+#include "acl.h"
+#include "xattr.h"
+#include "glock.h"
+#include "inode.h"
+#include "meta_io.h"
+#include "quota.h"
+#include "rgrp.h"
+#include "trans.h"
+#include "util.h"
+
+static const char *gfs2_acl_name(int type)
+{
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		return XATTR_POSIX_ACL_ACCESS;
+	case ACL_TYPE_DEFAULT:
+		return XATTR_POSIX_ACL_DEFAULT;
+	}
+	return NULL;
+}
+
+static struct posix_acl *__gfs2_get_acl(struct inode *inode, int type)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct posix_acl *acl;
+	const char *name;
+	char *data;
+	int len;
+
+	if (!ip->i_eattr)
+		return NULL;
+
+	name = gfs2_acl_name(type);
+	len = gfs2_xattr_acl_get(ip, name, &data);
+	if (len <= 0)
+		return ERR_PTR(len);
+	acl = posix_acl_from_xattr(&init_user_ns, data, len);
+	kfree(data);
+	return acl;
+}
+
+struct posix_acl *gfs2_get_acl(struct inode *inode, int type, bool rcu)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	bool need_unlock = false;
+	struct posix_acl *acl;
+
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		int ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
+					     LM_FLAG_ANY, &gh);
+		if (ret)
+			return ERR_PTR(ret);
+		need_unlock = true;
+	}
+	acl = __gfs2_get_acl(inode, type);
+	if (need_unlock)
+		gfs2_glock_dq_uninit(&gh);
+	return acl;
+}
+
+int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int error;
+	size_t len = 0;
+	char *data = NULL;
+	const char *name = gfs2_acl_name(type);
+
+	if (acl) {
+		data = posix_acl_to_xattr(&init_user_ns, acl, &len, GFP_NOFS);
+		if (data == NULL)
+			return -ENOMEM;
+	}
+
+	error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS);
+	if (error)
+		goto out;
+	set_cached_acl(inode, type, acl);
+out:
+	kfree(data);
+	return error;
+}
+
+int gfs2_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		 struct posix_acl *acl, int type)
+{
+	struct inode *inode = d_inode(dentry);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	bool need_unlock = false;
+	int ret;
+	umode_t mode;
+
+	if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
+		return -E2BIG;
+
+	ret = gfs2_qa_get(ip);
+	if (ret)
+		return ret;
+
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+		if (ret)
+			goto out;
+		need_unlock = true;
+	}
+
+	mode = inode->i_mode;
+	if (type == ACL_TYPE_ACCESS && acl) {
+		ret = posix_acl_update_mode(&nop_mnt_idmap, inode, &mode, &acl);
+		if (ret)
+			goto unlock;
+	}
+
+	ret = __gfs2_set_acl(inode, acl, type);
+	if (!ret && mode != inode->i_mode) {
+		inode_set_ctime_current(inode);
+		inode->i_mode = mode;
+		mark_inode_dirty(inode);
+	}
+unlock:
+	if (need_unlock)
+		gfs2_glock_dq_uninit(&gh);
+out:
+	gfs2_qa_put(ip);
+	return ret;
+}