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, 271 insertions, 0 deletions

diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c
new file mode 100644
index 000000000..8201fa7f6
--- /dev/null
+++ b/drivers/bluetooth/hci_ath.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Atheros Communication Bluetooth HCIATH3K UART protocol
+ *
+ *  HCIATH3K (HCI Atheros AR300x Protocol) is a Atheros Communication's
+ *  power management protocol extension to H4 to support AR300x Bluetooth Chip.
+ *
+ *  Copyright (c) 2009-2010 Atheros Communications Inc.
+ *
+ *  Acknowledgements:
+ *  This file is based on hci_h4.c, which was written
+ *  by Maxim Krasnyansky and Marcel Holtmann.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/tty.h>
+#include <linux/errno.h>
+#include <linux/ioctl.h>
+#include <linux/skbuff.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "hci_uart.h"
+
+struct ath_struct {
+	struct hci_uart *hu;
+	unsigned int cur_sleep;
+
+	struct sk_buff *rx_skb;
+	struct sk_buff_head txq;
+	struct work_struct ctxtsw;
+};
+
+#define OP_WRITE_TAG	0x01
+
+#define INDEX_BDADDR	0x01
+
+struct ath_vendor_cmd {
+	__u8 opcode;
+	__le16 index;
+	__u8 len;
+	__u8 data[251];
+} __packed;
+
+static int ath_wakeup_ar3k(struct tty_struct *tty)
+{
+	int status = tty->driver->ops->tiocmget(tty);
+
+	if (status & TIOCM_CTS)
+		return status;
+
+	/* Clear RTS first */
+	tty->driver->ops->tiocmget(tty);
+	tty->driver->ops->tiocmset(tty, 0x00, TIOCM_RTS);
+	msleep(20);
+
+	/* Set RTS, wake up board */
+	tty->driver->ops->tiocmget(tty);
+	tty->driver->ops->tiocmset(tty, TIOCM_RTS, 0x00);
+	msleep(20);
+
+	status = tty->driver->ops->tiocmget(tty);
+	return status;
+}
+
+static void ath_hci_uart_work(struct work_struct *work)
+{
+	int status;
+	struct ath_struct *ath;
+	struct hci_uart *hu;
+	struct tty_struct *tty;
+
+	ath = container_of(work, struct ath_struct, ctxtsw);
+
+	hu = ath->hu;
+	tty = hu->tty;
+
+	/* verify and wake up controller */
+	if (ath->cur_sleep) {
+		status = ath_wakeup_ar3k(tty);
+		if (!(status & TIOCM_CTS))
+			return;
+	}
+
+	/* Ready to send Data */
+	clear_bit(HCI_UART_SENDING, &hu->tx_state);
+	hci_uart_tx_wakeup(hu);
+}
+
+static int ath_open(struct hci_uart *hu)
+{
+	struct ath_struct *ath;
+
+	BT_DBG("hu %p", hu);
+
+	if (!hci_uart_has_flow_control(hu))
+		return -EOPNOTSUPP;
+
+	ath = kzalloc_obj(*ath);
+	if (!ath)
+		return -ENOMEM;
+
+	skb_queue_head_init(&ath->txq);
+
+	hu->priv = ath;
+	ath->hu = hu;
+
+	INIT_WORK(&ath->ctxtsw, ath_hci_uart_work);
+
+	return 0;
+}
+
+static int ath_close(struct hci_uart *hu)
+{
+	struct ath_struct *ath = hu->priv;
+
+	BT_DBG("hu %p", hu);
+
+	skb_queue_purge(&ath->txq);
+
+	kfree_skb(ath->rx_skb);
+
+	cancel_work_sync(&ath->ctxtsw);
+
+	hu->priv = NULL;
+	kfree(ath);
+
+	return 0;
+}
+
+static int ath_flush(struct hci_uart *hu)
+{
+	struct ath_struct *ath = hu->priv;
+
+	BT_DBG("hu %p", hu);
+
+	skb_queue_purge(&ath->txq);
+
+	return 0;
+}
+
+static int ath_vendor_cmd(struct hci_dev *hdev, uint8_t opcode, uint16_t index,
+			  const void *data, size_t dlen)
+{
+	struct sk_buff *skb;
+	struct ath_vendor_cmd cmd;
+
+	if (dlen > sizeof(cmd.data))
+		return -EINVAL;
+
+	cmd.opcode = opcode;
+	cmd.index = cpu_to_le16(index);
+	cmd.len = dlen;
+	memcpy(cmd.data, data, dlen);
+
+	skb = __hci_cmd_sync(hdev, 0xfc0b, dlen + 4, &cmd, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+	kfree_skb(skb);
+
+	return 0;
+}
+
+static int ath_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	return ath_vendor_cmd(hdev, OP_WRITE_TAG, INDEX_BDADDR, bdaddr,
+			      sizeof(*bdaddr));
+}
+
+static int ath_setup(struct hci_uart *hu)
+{
+	BT_DBG("hu %p", hu);
+
+	hu->hdev->set_bdaddr = ath_set_bdaddr;
+
+	return 0;
+}
+
+static const struct h4_recv_pkt ath_recv_pkts[] = {
+	{ H4_RECV_ACL,   .recv = hci_recv_frame },
+	{ H4_RECV_SCO,   .recv = hci_recv_frame },
+	{ H4_RECV_EVENT, .recv = hci_recv_frame },
+};
+
+static int ath_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct ath_struct *ath = hu->priv;
+
+	if (!ath)
+		return -ENODEV;
+
+	ath->rx_skb = h4_recv_buf(hu, ath->rx_skb, data, count,
+				  ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts));
+	if (IS_ERR(ath->rx_skb)) {
+		int err = PTR_ERR(ath->rx_skb);
+		bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err);
+		ath->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
+#define HCI_OP_ATH_SLEEP 0xFC04
+
+static int ath_enqueue(struct hci_uart *hu, struct sk_buff *skb)
+{
+	struct ath_struct *ath = hu->priv;
+
+	if (hci_skb_pkt_type(skb) == HCI_SCODATA_PKT) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	/* Update power management enable flag with parameters of
+	 * HCI sleep enable vendor specific HCI command.
+	 */
+	if (hci_skb_pkt_type(skb) == HCI_COMMAND_PKT) {
+		struct hci_command_hdr *hdr = (void *)skb->data;
+
+		if (__le16_to_cpu(hdr->opcode) == HCI_OP_ATH_SLEEP)
+			ath->cur_sleep = skb->data[HCI_COMMAND_HDR_SIZE];
+	}
+
+	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(&ath->txq, skb);
+	set_bit(HCI_UART_SENDING, &hu->tx_state);
+
+	schedule_work(&ath->ctxtsw);
+
+	return 0;
+}
+
+static struct sk_buff *ath_dequeue(struct hci_uart *hu)
+{
+	struct ath_struct *ath = hu->priv;
+
+	return skb_dequeue(&ath->txq);
+}
+
+static const struct hci_uart_proto athp = {
+	.id		= HCI_UART_ATH3K,
+	.name		= "ATH3K",
+	.manufacturer	= 69,
+	.open		= ath_open,
+	.close		= ath_close,
+	.flush		= ath_flush,
+	.setup		= ath_setup,
+	.recv		= ath_recv,
+	.enqueue	= ath_enqueue,
+	.dequeue	= ath_dequeue,
+};
+
+int __init ath_init(void)
+{
+	return hci_uart_register_proto(&athp);
+}
+
+int __exit ath_deinit(void)
+{
+	return hci_uart_unregister_proto(&athp);
+}