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, 159 insertions, 0 deletions

diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
new file mode 100644
index 000000000..ae4cb4e2e
--- /dev/null
+++ b/fs/ecryptfs/kthread.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * eCryptfs: Linux filesystem encryption layer
+ *
+ * Copyright (C) 2008 International Business Machines Corp.
+ *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
+ */
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/mount.h>
+#include "ecryptfs_kernel.h"
+
+struct ecryptfs_open_req {
+	struct file **lower_file;
+	struct path path;
+	struct completion done;
+	struct list_head kthread_ctl_list;
+};
+
+static struct ecryptfs_kthread_ctl {
+#define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001
+	u32 flags;
+	struct mutex mux;
+	struct list_head req_list;
+	wait_queue_head_t wait;
+} ecryptfs_kthread_ctl;
+
+static struct task_struct *ecryptfs_kthread;
+
+/**
+ * ecryptfs_threadfn
+ * @ignored: ignored
+ *
+ * The eCryptfs kernel thread that has the responsibility of getting
+ * the lower file with RW permissions.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_threadfn(void *ignored)
+{
+	set_freezable();
+	while (1)  {
+		struct ecryptfs_open_req *req;
+
+		wait_event_freezable(
+			ecryptfs_kthread_ctl.wait,
+			(!list_empty(&ecryptfs_kthread_ctl.req_list)
+			 || kthread_should_stop()));
+		mutex_lock(&ecryptfs_kthread_ctl.mux);
+		if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+			mutex_unlock(&ecryptfs_kthread_ctl.mux);
+			goto out;
+		}
+		while (!list_empty(&ecryptfs_kthread_ctl.req_list)) {
+			req = list_first_entry(&ecryptfs_kthread_ctl.req_list,
+					       struct ecryptfs_open_req,
+					       kthread_ctl_list);
+			list_del(&req->kthread_ctl_list);
+			*req->lower_file = dentry_open(&req->path,
+				(O_RDWR | O_LARGEFILE), current_cred());
+			complete(&req->done);
+		}
+		mutex_unlock(&ecryptfs_kthread_ctl.mux);
+	}
+out:
+	return 0;
+}
+
+int __init ecryptfs_init_kthread(void)
+{
+	int rc = 0;
+
+	mutex_init(&ecryptfs_kthread_ctl.mux);
+	init_waitqueue_head(&ecryptfs_kthread_ctl.wait);
+	INIT_LIST_HEAD(&ecryptfs_kthread_ctl.req_list);
+	ecryptfs_kthread = kthread_run(&ecryptfs_threadfn, NULL,
+				       "ecryptfs-kthread");
+	if (IS_ERR(ecryptfs_kthread)) {
+		rc = PTR_ERR(ecryptfs_kthread);
+		printk(KERN_ERR "%s: Failed to create kernel thread; rc = [%d]"
+		       "\n", __func__, rc);
+	}
+	return rc;
+}
+
+void ecryptfs_destroy_kthread(void)
+{
+	struct ecryptfs_open_req *req, *tmp;
+
+	mutex_lock(&ecryptfs_kthread_ctl.mux);
+	ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE;
+	list_for_each_entry_safe(req, tmp, &ecryptfs_kthread_ctl.req_list,
+				 kthread_ctl_list) {
+		list_del(&req->kthread_ctl_list);
+		*req->lower_file = ERR_PTR(-EIO);
+		complete(&req->done);
+	}
+	mutex_unlock(&ecryptfs_kthread_ctl.mux);
+	kthread_stop(ecryptfs_kthread);
+	wake_up(&ecryptfs_kthread_ctl.wait);
+}
+
+/**
+ * ecryptfs_privileged_open
+ * @lower_file: Result of dentry_open by root on lower dentry
+ * @lower_dentry: Lower dentry for file to open
+ * @lower_mnt: Lower vfsmount for file to open
+ * @cred: credential to use for this call
+ *
+ * This function gets a r/w file opened against the lower dentry.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_privileged_open(struct file **lower_file,
+			     struct dentry *lower_dentry,
+			     struct vfsmount *lower_mnt,
+			     const struct cred *cred)
+{
+	struct ecryptfs_open_req req;
+	int flags = O_LARGEFILE;
+	int rc = 0;
+
+	init_completion(&req.done);
+	req.lower_file = lower_file;
+	req.path.dentry = lower_dentry;
+	req.path.mnt = lower_mnt;
+
+	/* Corresponding dput() and mntput() are done when the
+	 * lower file is fput() when all eCryptfs files for the inode are
+	 * released. */
+	flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
+	(*lower_file) = dentry_open(&req.path, flags, cred);
+	if (!IS_ERR(*lower_file))
+		goto out;
+	if ((flags & O_ACCMODE) == O_RDONLY) {
+		rc = PTR_ERR((*lower_file));
+		goto out;
+	}
+	mutex_lock(&ecryptfs_kthread_ctl.mux);
+	if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+		rc = -EIO;
+		mutex_unlock(&ecryptfs_kthread_ctl.mux);
+		printk(KERN_ERR "%s: We are in the middle of shutting down; "
+		       "aborting privileged request to open lower file\n",
+			__func__);
+		goto out;
+	}
+	list_add_tail(&req.kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
+	mutex_unlock(&ecryptfs_kthread_ctl.mux);
+	wake_up(&ecryptfs_kthread_ctl.wait);
+	wait_for_completion(&req.done);
+	if (IS_ERR(*lower_file))
+		rc = PTR_ERR(*lower_file);
+out:
+	return rc;
+}