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, 178 insertions, 0 deletions

diff --git a/drivers/accessibility/speakup/devsynth.c b/drivers/accessibility/speakup/devsynth.c
new file mode 100644
index 000000000..e3d909bd0
--- /dev/null
+++ b/drivers/accessibility/speakup/devsynth.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/errno.h>
+#include <linux/miscdevice.h>	/* for misc_register, and MISC_DYNAMIC_MINOR */
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+#include "speakup.h"
+#include "spk_priv.h"
+
+static int synth_registered, synthu_registered;
+static int dev_opened;
+
+/* Latin1 version */
+static ssize_t speakup_file_write(struct file *fp, const char __user *buffer,
+				  size_t nbytes, loff_t *ppos)
+{
+	size_t count = nbytes;
+	const char __user *ptr = buffer;
+	size_t bytes;
+	unsigned long flags;
+	u_char buf[256];
+
+	if (!synth)
+		return -ENODEV;
+	while (count > 0) {
+		bytes = min(count, sizeof(buf));
+		if (copy_from_user(buf, ptr, bytes))
+			return -EFAULT;
+		count -= bytes;
+		ptr += bytes;
+		spin_lock_irqsave(&speakup_info.spinlock, flags);
+		synth_write(buf, bytes);
+		spin_unlock_irqrestore(&speakup_info.spinlock, flags);
+	}
+	return (ssize_t)nbytes;
+}
+
+/* UTF-8 version */
+static ssize_t speakup_file_writeu(struct file *fp, const char __user *buffer,
+				   size_t nbytes, loff_t *ppos)
+{
+	size_t count = nbytes, consumed, want;
+	const char __user *ptr = buffer;
+	size_t bytes;
+	unsigned long flags;
+	unsigned char buf[256];
+	u16 ubuf[256];
+	size_t in, out;
+
+	if (!synth)
+		return -ENODEV;
+
+	want = 1;
+	while (count >= want) {
+		/* Copy some UTF-8 piece from userland */
+		bytes = min(count, sizeof(buf));
+		if (copy_from_user(buf, ptr, bytes))
+			return -EFAULT;
+
+		/* Convert to u16 */
+		for (in = 0, out = 0; in < bytes; in += consumed) {
+			s32 value;
+
+			value = synth_utf8_get(buf + in, bytes - in, &consumed, &want);
+			if (value == -1) {
+				/* Invalid or incomplete */
+
+				if (want > bytes - in)
+					/* We don't have it all yet, stop here
+					 * and wait for the rest
+					 */
+					bytes = in;
+
+				continue;
+			}
+
+			if (value < 0x10000)
+				ubuf[out++] = value;
+		}
+
+		count -= bytes;
+		ptr += bytes;
+
+		/* And speak this up */
+		if (out) {
+			spin_lock_irqsave(&speakup_info.spinlock, flags);
+			for (in = 0; in < out; in++)
+				synth_buffer_add(ubuf[in]);
+			synth_start();
+			spin_unlock_irqrestore(&speakup_info.spinlock, flags);
+		}
+	}
+
+	return (ssize_t)(nbytes - count);
+}
+
+static ssize_t speakup_file_read(struct file *fp, char __user *buf,
+				 size_t nbytes, loff_t *ppos)
+{
+	return 0;
+}
+
+static int speakup_file_open(struct inode *ip, struct file *fp)
+{
+	if (!synth)
+		return -ENODEV;
+	if (xchg(&dev_opened, 1))
+		return -EBUSY;
+	return 0;
+}
+
+static int speakup_file_release(struct inode *ip, struct file *fp)
+{
+	dev_opened = 0;
+	return 0;
+}
+
+static const struct file_operations synth_fops = {
+	.read = speakup_file_read,
+	.write = speakup_file_write,
+	.open = speakup_file_open,
+	.release = speakup_file_release,
+};
+
+static const struct file_operations synthu_fops = {
+	.read = speakup_file_read,
+	.write = speakup_file_writeu,
+	.open = speakup_file_open,
+	.release = speakup_file_release,
+};
+
+static struct miscdevice synth_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "synth",
+	.fops = &synth_fops,
+};
+
+static struct miscdevice synthu_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "synthu",
+	.fops = &synthu_fops,
+};
+
+void speakup_register_devsynth(void)
+{
+	if (!synth_registered) {
+		if (misc_register(&synth_device)) {
+			pr_warn("Couldn't initialize miscdevice /dev/synth.\n");
+		} else {
+			pr_info("initialized device: /dev/synth, node (MAJOR %d, MINOR %d)\n",
+				MISC_MAJOR, synth_device.minor);
+			synth_registered = 1;
+		}
+	}
+	if (!synthu_registered) {
+		if (misc_register(&synthu_device)) {
+			pr_warn("Couldn't initialize miscdevice /dev/synthu.\n");
+		} else {
+			pr_info("initialized device: /dev/synthu, node (MAJOR %d, MINOR %d)\n",
+				MISC_MAJOR, synthu_device.minor);
+			synthu_registered = 1;
+		}
+	}
+}
+
+void speakup_unregister_devsynth(void)
+{
+	if (synth_registered) {
+		pr_info("speakup: unregistering synth device /dev/synth\n");
+		misc_deregister(&synth_device);
+		synth_registered = 0;
+	}
+	if (synthu_registered) {
+		pr_info("speakup: unregistering synth device /dev/synthu\n");
+		misc_deregister(&synthu_device);
+		synthu_registered = 0;
+	}
+}