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, 196 insertions, 0 deletions

diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c
new file mode 100644
index 000000000..4ae29a12c
--- /dev/null
+++ b/samples/kfifo/bytestream-example.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Sample kfifo byte stream implementation
+ *
+ * Copyright (C) 2010 Stefani Seibold <stefani@seibold.net>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/mutex.h>
+#include <linux/kfifo.h>
+
+/*
+ * This module shows how to create a byte stream fifo.
+ */
+
+/* fifo size in elements (bytes) */
+#define FIFO_SIZE	32
+
+/* name of the proc entry */
+#define	PROC_FIFO	"bytestream-fifo"
+
+/* lock for procfs read access */
+static DEFINE_MUTEX(read_access);
+
+/* lock for procfs write access */
+static DEFINE_MUTEX(write_access);
+
+/*
+ * define DYNAMIC in this example for a dynamically allocated fifo.
+ *
+ * Otherwise the fifo storage will be a part of the fifo structure.
+ */
+#if 0
+#define DYNAMIC
+#endif
+
+#ifdef DYNAMIC
+static struct kfifo test;
+#else
+static DECLARE_KFIFO(test, unsigned char, FIFO_SIZE);
+#endif
+
+static const unsigned char expected_result[FIFO_SIZE] = {
+	 3,  4,  5,  6,  7,  8,  9,  0,
+	 1, 20, 21, 22, 23, 24, 25, 26,
+	27, 28, 29, 30, 31, 32, 33, 34,
+	35, 36, 37, 38, 39, 40, 41, 42,
+};
+
+static int __init testfunc(void)
+{
+	unsigned char	buf[6];
+	unsigned char	i, j;
+	unsigned int	ret;
+
+	printk(KERN_INFO "byte stream fifo test start\n");
+
+	/* put string into the fifo */
+	kfifo_in(&test, "hello", 5);
+
+	/* put values into the fifo */
+	for (i = 0; i != 10; i++)
+		kfifo_put(&test, i);
+
+	/* show the number of used elements */
+	printk(KERN_INFO "fifo len: %u\n", kfifo_len(&test));
+
+	/* get max of 5 bytes from the fifo */
+	i = kfifo_out(&test, buf, 5);
+	printk(KERN_INFO "buf: %.*s\n", i, buf);
+
+	/* get max of 2 elements from the fifo */
+	ret = kfifo_out(&test, buf, 2);
+	printk(KERN_INFO "ret: %d\n", ret);
+	/* and put it back to the end of the fifo */
+	ret = kfifo_in(&test, buf, ret);
+	printk(KERN_INFO "ret: %d\n", ret);
+
+	/* skip first element of the fifo */
+	printk(KERN_INFO "skip 1st element\n");
+	kfifo_skip(&test);
+
+	/* put values into the fifo until is full */
+	for (i = 20; kfifo_put(&test, i); i++)
+		;
+
+	printk(KERN_INFO "queue len: %u\n", kfifo_len(&test));
+
+	/* show the first value without removing from the fifo */
+	if (kfifo_peek(&test, &i))
+		printk(KERN_INFO "%d\n", i);
+
+	/* check the correctness of all values in the fifo */
+	j = 0;
+	while (kfifo_get(&test, &i)) {
+		printk(KERN_INFO "item = %d\n", i);
+		if (i != expected_result[j++]) {
+			printk(KERN_WARNING "value mismatch: test failed\n");
+			return -EIO;
+		}
+	}
+	if (j != ARRAY_SIZE(expected_result)) {
+		printk(KERN_WARNING "size mismatch: test failed\n");
+		return -EIO;
+	}
+	printk(KERN_INFO "test passed\n");
+
+	return 0;
+}
+
+static ssize_t fifo_write(struct file *file, const char __user *buf,
+						size_t count, loff_t *ppos)
+{
+	int ret;
+	unsigned int copied;
+
+	if (mutex_lock_interruptible(&write_access))
+		return -ERESTARTSYS;
+
+	ret = kfifo_from_user(&test, buf, count, &copied);
+
+	mutex_unlock(&write_access);
+	if (ret)
+		return ret;
+
+	return copied;
+}
+
+static ssize_t fifo_read(struct file *file, char __user *buf,
+						size_t count, loff_t *ppos)
+{
+	int ret;
+	unsigned int copied;
+
+	if (mutex_lock_interruptible(&read_access))
+		return -ERESTARTSYS;
+
+	ret = kfifo_to_user(&test, buf, count, &copied);
+
+	mutex_unlock(&read_access);
+	if (ret)
+		return ret;
+
+	return copied;
+}
+
+static const struct proc_ops fifo_proc_ops = {
+	.proc_read	= fifo_read,
+	.proc_write	= fifo_write,
+	.proc_lseek	= noop_llseek,
+};
+
+static int __init example_init(void)
+{
+#ifdef DYNAMIC
+	int ret;
+
+	ret = kfifo_alloc(&test, FIFO_SIZE, GFP_KERNEL);
+	if (ret) {
+		printk(KERN_ERR "error kfifo_alloc\n");
+		return ret;
+	}
+#else
+	INIT_KFIFO(test);
+#endif
+	if (testfunc() < 0) {
+#ifdef DYNAMIC
+		kfifo_free(&test);
+#endif
+		return -EIO;
+	}
+
+	if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) {
+#ifdef DYNAMIC
+		kfifo_free(&test);
+#endif
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void __exit example_exit(void)
+{
+	remove_proc_entry(PROC_FIFO, NULL);
+#ifdef DYNAMIC
+	kfifo_free(&test);
+#endif
+}
+
+module_init(example_init);
+module_exit(example_exit);
+MODULE_DESCRIPTION("Sample kfifo byte stream implementation");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Stefani Seibold <stefani@seibold.net>");