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, 274 insertions, 0 deletions

diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
new file mode 100644
index 000000000..767372707
--- /dev/null
+++ b/drivers/bluetooth/hci_h4.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ *  Bluetooth HCI UART driver
+ *
+ *  Copyright (C) 2000-2001  Qualcomm Incorporated
+ *  Copyright (C) 2002-2003  Maxim Krasnyansky <maxk@qualcomm.com>
+ *  Copyright (C) 2004-2005  Marcel Holtmann <marcel@holtmann.org>
+ */
+
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/poll.h>
+
+#include <linux/slab.h>
+#include <linux/tty.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/signal.h>
+#include <linux/ioctl.h>
+#include <linux/skbuff.h>
+#include <linux/unaligned.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "hci_uart.h"
+
+struct h4_struct {
+	struct sk_buff *rx_skb;
+	struct sk_buff_head txq;
+};
+
+/* Initialize protocol */
+static int h4_open(struct hci_uart *hu)
+{
+	struct h4_struct *h4;
+
+	BT_DBG("hu %p", hu);
+
+	h4 = kzalloc_obj(*h4);
+	if (!h4)
+		return -ENOMEM;
+
+	skb_queue_head_init(&h4->txq);
+
+	hu->priv = h4;
+	return 0;
+}
+
+/* Flush protocol data */
+static int h4_flush(struct hci_uart *hu)
+{
+	struct h4_struct *h4 = hu->priv;
+
+	BT_DBG("hu %p", hu);
+
+	skb_queue_purge(&h4->txq);
+
+	return 0;
+}
+
+/* Close protocol */
+static int h4_close(struct hci_uart *hu)
+{
+	struct h4_struct *h4 = hu->priv;
+
+	BT_DBG("hu %p", hu);
+
+	skb_queue_purge(&h4->txq);
+
+	kfree_skb(h4->rx_skb);
+
+	hu->priv = NULL;
+	kfree(h4);
+
+	return 0;
+}
+
+/* Enqueue frame for transmission (padding, crc, etc) */
+static int h4_enqueue(struct hci_uart *hu, struct sk_buff *skb)
+{
+	struct h4_struct *h4 = hu->priv;
+
+	BT_DBG("hu %p skb %p", hu, skb);
+
+	/* Prepend skb with frame type */
+	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+	skb_queue_tail(&h4->txq, skb);
+
+	return 0;
+}
+
+static const struct h4_recv_pkt h4_recv_pkts[] = {
+	{ H4_RECV_ACL,   .recv = hci_recv_frame },
+	{ H4_RECV_SCO,   .recv = hci_recv_frame },
+	{ H4_RECV_EVENT, .recv = hci_recv_frame },
+	{ H4_RECV_ISO,   .recv = hci_recv_frame },
+};
+
+/* Recv data */
+static int h4_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct h4_struct *h4 = hu->priv;
+
+	if (!h4)
+		return -ENODEV;
+
+	h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count,
+				 h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts));
+	if (IS_ERR(h4->rx_skb)) {
+		int err = PTR_ERR(h4->rx_skb);
+		bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err);
+		h4->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
+static struct sk_buff *h4_dequeue(struct hci_uart *hu)
+{
+	struct h4_struct *h4 = hu->priv;
+	return skb_dequeue(&h4->txq);
+}
+
+static const struct hci_uart_proto h4p = {
+	.id		= HCI_UART_H4,
+	.name		= "H4",
+	.open		= h4_open,
+	.close		= h4_close,
+	.recv		= h4_recv,
+	.enqueue	= h4_enqueue,
+	.dequeue	= h4_dequeue,
+	.flush		= h4_flush,
+};
+
+int __init h4_init(void)
+{
+	return hci_uart_register_proto(&h4p);
+}
+
+int __exit h4_deinit(void)
+{
+	return hci_uart_unregister_proto(&h4p);
+}
+
+struct sk_buff *h4_recv_buf(struct hci_uart *hu, struct sk_buff *skb,
+			    const unsigned char *buffer, int count,
+			    const struct h4_recv_pkt *pkts, int pkts_count)
+{
+	u8 alignment = hu->alignment ? hu->alignment : 1;
+	struct hci_dev *hdev = hu->hdev;
+
+	/* Check for error from previous call */
+	if (IS_ERR(skb))
+		skb = NULL;
+
+	while (count) {
+		int i, len;
+
+		/* remove padding bytes from buffer */
+		for (; hu->padding && count > 0; hu->padding--) {
+			count--;
+			buffer++;
+		}
+		if (!count)
+			break;
+
+		if (!skb) {
+			for (i = 0; i < pkts_count; i++) {
+				if (buffer[0] != (&pkts[i])->type)
+					continue;
+
+				skb = bt_skb_alloc((&pkts[i])->maxlen,
+						   GFP_ATOMIC);
+				if (!skb)
+					return ERR_PTR(-ENOMEM);
+
+				hci_skb_pkt_type(skb) = (&pkts[i])->type;
+				hci_skb_expect(skb) = (&pkts[i])->hlen;
+				break;
+			}
+
+			/* Check for invalid packet type */
+			if (!skb)
+				return ERR_PTR(-EILSEQ);
+
+			count -= 1;
+			buffer += 1;
+		}
+
+		len = min_t(uint, hci_skb_expect(skb) - skb->len, count);
+		skb_put_data(skb, buffer, len);
+
+		count -= len;
+		buffer += len;
+
+		/* Check for partial packet */
+		if (skb->len < hci_skb_expect(skb))
+			continue;
+
+		for (i = 0; i < pkts_count; i++) {
+			if (hci_skb_pkt_type(skb) == (&pkts[i])->type)
+				break;
+		}
+
+		if (i >= pkts_count) {
+			kfree_skb(skb);
+			return ERR_PTR(-EILSEQ);
+		}
+
+		if (skb->len == (&pkts[i])->hlen) {
+			u16 dlen;
+
+			switch ((&pkts[i])->lsize) {
+			case 0:
+				/* No variable data length */
+				dlen = 0;
+				break;
+			case 1:
+				/* Single octet variable length */
+				dlen = skb->data[(&pkts[i])->loff];
+				hci_skb_expect(skb) += dlen;
+
+				if (skb_tailroom(skb) < dlen) {
+					kfree_skb(skb);
+					return ERR_PTR(-EMSGSIZE);
+				}
+				break;
+			case 2:
+				/* Double octet variable length */
+				dlen = get_unaligned_le16(skb->data +
+							  (&pkts[i])->loff);
+				hci_skb_expect(skb) += dlen;
+
+				if (skb_tailroom(skb) < dlen) {
+					kfree_skb(skb);
+					return ERR_PTR(-EMSGSIZE);
+				}
+				break;
+			default:
+				/* Unsupported variable length */
+				kfree_skb(skb);
+				return ERR_PTR(-EILSEQ);
+			}
+
+			if (!dlen) {
+				hu->padding = (skb->len + 1) % alignment;
+				hu->padding = (alignment - hu->padding) % alignment;
+
+				/* No more data, complete frame */
+				(&pkts[i])->recv(hdev, skb);
+				skb = NULL;
+			}
+		} else {
+			hu->padding = (skb->len + 1) % alignment;
+			hu->padding = (alignment - hu->padding) % alignment;
+
+			/* Complete frame */
+			(&pkts[i])->recv(hdev, skb);
+			skb = NULL;
+		}
+	}
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(h4_recv_buf);