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, 88 insertions, 0 deletions

diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
new file mode 100644
index 000000000..36e35c155
--- /dev/null
+++ b/fs/coda/pioctl.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Pioctl operations for Coda.
+ * Original version: (C) 1996 Peter Braam
+ * Rewritten for Linux 2.1: (C) 1997 Carnegie Mellon University
+ *
+ * Carnegie Mellon encourages users of this code to contribute improvements
+ * to the Coda project. Contact Peter Braam <coda@cs.cmu.edu>.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/namei.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+
+#include <linux/coda.h>
+#include "coda_psdev.h"
+#include "coda_linux.h"
+
+/* pioctl ops */
+static int coda_ioctl_permission(struct mnt_idmap *idmap,
+				 struct inode *inode, int mask);
+static long coda_pioctl(struct file *filp, unsigned int cmd,
+			unsigned long user_data);
+
+/* exported from this file */
+const struct inode_operations coda_ioctl_inode_operations = {
+	.permission	= coda_ioctl_permission,
+	.setattr	= coda_setattr,
+};
+
+const struct file_operations coda_ioctl_operations = {
+	.unlocked_ioctl	= coda_pioctl,
+	.llseek		= noop_llseek,
+};
+
+/* the coda pioctl inode ops */
+static int coda_ioctl_permission(struct mnt_idmap *idmap,
+				 struct inode *inode, int mask)
+{
+	return (mask & MAY_EXEC) ? -EACCES : 0;
+}
+
+static long coda_pioctl(struct file *filp, unsigned int cmd,
+			unsigned long user_data)
+{
+	struct path path;
+	int error;
+	struct PioctlData data;
+	struct inode *inode = file_inode(filp);
+	struct inode *target_inode = NULL;
+	struct coda_inode_info *cnp;
+
+	/* get the Pioctl data arguments from user space */
+	if (copy_from_user(&data, (void __user *)user_data, sizeof(data)))
+		return -EINVAL;
+
+	/*
+	 * Look up the pathname. Note that the pathname is in
+	 * user memory, and namei takes care of this
+	 */
+	error = user_path_at(AT_FDCWD, data.path,
+			     data.follow ? LOOKUP_FOLLOW : 0, &path);
+	if (error)
+		return error;
+
+	target_inode = d_inode(path.dentry);
+
+	/* return if it is not a Coda inode */
+	if (target_inode->i_sb != inode->i_sb) {
+		error = -EINVAL;
+		goto out;
+	}
+
+	/* now proceed to make the upcall */
+	cnp = ITOC(target_inode);
+
+	error = venus_pioctl(inode->i_sb, &(cnp->c_fid), cmd, &data);
+out:
+	path_put(&path);
+	return error;
+}