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, 205 insertions, 0 deletions

diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c
new file mode 100644
index 000000000..fa904b24a
--- /dev/null
+++ b/drivers/macintosh/ans-lcd.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * /dev/lcd driver for Apple Network Servers.
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/fcntl.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/of.h>
+
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+#include <asm/io.h>
+
+#include "ans-lcd.h"
+
+#define ANSLCD_ADDR		0xf301c000
+#define ANSLCD_CTRL_IX 0x00
+#define ANSLCD_DATA_IX 0x10
+
+static unsigned long anslcd_short_delay = 80;
+static unsigned long anslcd_long_delay = 3280;
+static volatile unsigned char __iomem *anslcd_ptr;
+static DEFINE_MUTEX(anslcd_mutex);
+
+#undef DEBUG
+
+static void
+anslcd_write_byte_ctrl ( unsigned char c )
+{
+#ifdef DEBUG
+	printk(KERN_DEBUG "LCD: CTRL byte: %02x\n",c);
+#endif
+	out_8(anslcd_ptr + ANSLCD_CTRL_IX, c);
+	switch(c) {
+		case 1:
+		case 2:
+		case 3:
+			udelay(anslcd_long_delay); break;
+		default: udelay(anslcd_short_delay);
+	}
+}
+
+static void
+anslcd_write_byte_data ( unsigned char c )
+{
+	out_8(anslcd_ptr + ANSLCD_DATA_IX, c);
+	udelay(anslcd_short_delay);
+}
+
+static ssize_t
+anslcd_write( struct file * file, const char __user * buf, 
+				size_t count, loff_t *ppos )
+{
+	const char __user *p = buf;
+	int i;
+
+#ifdef DEBUG
+	printk(KERN_DEBUG "LCD: write\n");
+#endif
+
+	if (!access_ok(buf, count))
+		return -EFAULT;
+
+	mutex_lock(&anslcd_mutex);
+	for ( i = *ppos; count > 0; ++i, ++p, --count ) 
+	{
+		char c;
+		__get_user(c, p);
+		anslcd_write_byte_data( c );
+	}
+	mutex_unlock(&anslcd_mutex);
+	*ppos = i;
+	return p - buf;
+}
+
+static long
+anslcd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	char ch, __user *temp;
+	long ret = 0;
+
+#ifdef DEBUG
+	printk(KERN_DEBUG "LCD: ioctl(%d,%d)\n",cmd,arg);
+#endif
+
+	mutex_lock(&anslcd_mutex);
+
+	switch ( cmd )
+	{
+	case ANSLCD_CLEAR:
+		anslcd_write_byte_ctrl ( 0x38 );
+		anslcd_write_byte_ctrl ( 0x0f );
+		anslcd_write_byte_ctrl ( 0x06 );
+		anslcd_write_byte_ctrl ( 0x01 );
+		anslcd_write_byte_ctrl ( 0x02 );
+		break;
+	case ANSLCD_SENDCTRL:
+		temp = (char __user *) arg;
+		__get_user(ch, temp);
+		for (; ch; temp++) { /* FIXME: This is ugly, but should work, as a \0 byte is not a valid command code */
+			anslcd_write_byte_ctrl ( ch );
+			__get_user(ch, temp);
+		}
+		break;
+	case ANSLCD_SETSHORTDELAY:
+		if (!capable(CAP_SYS_ADMIN))
+			ret =-EACCES;
+		else
+			anslcd_short_delay=arg;
+		break;
+	case ANSLCD_SETLONGDELAY:
+		if (!capable(CAP_SYS_ADMIN))
+			ret = -EACCES;
+		else
+			anslcd_long_delay=arg;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&anslcd_mutex);
+	return ret;
+}
+
+static int
+anslcd_open( struct inode * inode, struct file * file )
+{
+	return 0;
+}
+
+const struct file_operations anslcd_fops = {
+	.write		= anslcd_write,
+	.unlocked_ioctl	= anslcd_ioctl,
+	.open		= anslcd_open,
+	.llseek		= default_llseek,
+};
+
+static struct miscdevice anslcd_dev = {
+	LCD_MINOR,
+	"anslcd",
+	&anslcd_fops
+};
+
+static const char anslcd_logo[] __initconst =
+				"********************"  /* Line #1 */
+				"*      LINUX!      *"  /* Line #3 */
+				"*    Welcome to    *"  /* Line #2 */
+				"********************"; /* Line #4 */
+
+static int __init
+anslcd_init(void)
+{
+	int a;
+	int retval;
+	struct device_node* node;
+
+	node = of_find_node_by_name(NULL, "lcd");
+	if (!node || !of_node_name_eq(node->parent, "gc")) {
+		of_node_put(node);
+		return -ENODEV;
+	}
+	of_node_put(node);
+
+	anslcd_ptr = ioremap(ANSLCD_ADDR, 0x20);
+	
+	retval = misc_register(&anslcd_dev);
+	if(retval < 0){
+		printk(KERN_INFO "LCD: misc_register failed\n");
+		iounmap(anslcd_ptr);
+		return retval;
+	}
+
+#ifdef DEBUG
+	printk(KERN_DEBUG "LCD: init\n");
+#endif
+
+	mutex_lock(&anslcd_mutex);
+	anslcd_write_byte_ctrl ( 0x38 );
+	anslcd_write_byte_ctrl ( 0x0c );
+	anslcd_write_byte_ctrl ( 0x06 );
+	anslcd_write_byte_ctrl ( 0x01 );
+	anslcd_write_byte_ctrl ( 0x02 );
+	for(a=0;a<80;a++) {
+		anslcd_write_byte_data(anslcd_logo[a]);
+	}
+	mutex_unlock(&anslcd_mutex);
+	return 0;
+}
+
+static void __exit
+anslcd_exit(void)
+{
+	misc_deregister(&anslcd_dev);
+	iounmap(anslcd_ptr);
+}
+
+module_init(anslcd_init);
+module_exit(anslcd_exit);
+MODULE_LICENSE("GPL v2");