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, 454 insertions, 0 deletions

diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c
new file mode 100644
index 000000000..c20d54088
--- /dev/null
+++ b/drivers/bluetooth/virtio_bt.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/module.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/skbuff.h>
+
+#include <uapi/linux/virtio_ids.h>
+#include <uapi/linux/virtio_bt.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#define VERSION "0.1"
+#define VIRTBT_RX_BUF_SIZE 1000
+
+enum {
+	VIRTBT_VQ_TX,
+	VIRTBT_VQ_RX,
+	VIRTBT_NUM_VQS,
+};
+
+struct virtio_bluetooth {
+	struct virtio_device *vdev;
+	struct virtqueue *vqs[VIRTBT_NUM_VQS];
+	struct work_struct rx;
+	struct hci_dev *hdev;
+};
+
+static int virtbt_add_inbuf(struct virtio_bluetooth *vbt)
+{
+	struct virtqueue *vq = vbt->vqs[VIRTBT_VQ_RX];
+	struct scatterlist sg[1];
+	struct sk_buff *skb;
+	int err;
+
+	skb = alloc_skb(VIRTBT_RX_BUF_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	sg_init_one(sg, skb->data, VIRTBT_RX_BUF_SIZE);
+
+	err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL);
+	if (err < 0) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	return 0;
+}
+
+static int virtbt_open(struct hci_dev *hdev)
+{
+	return 0;
+}
+
+static int virtbt_open_vdev(struct virtio_bluetooth *vbt)
+{
+	if (virtbt_add_inbuf(vbt) < 0)
+		return -EIO;
+
+	virtqueue_kick(vbt->vqs[VIRTBT_VQ_RX]);
+	return 0;
+}
+
+static int virtbt_close(struct hci_dev *hdev)
+{
+	return 0;
+}
+
+static int virtbt_close_vdev(struct virtio_bluetooth *vbt)
+{
+	int i;
+
+	cancel_work_sync(&vbt->rx);
+
+	for (i = 0; i < ARRAY_SIZE(vbt->vqs); i++) {
+		struct virtqueue *vq = vbt->vqs[i];
+		struct sk_buff *skb;
+
+		while ((skb = virtqueue_detach_unused_buf(vq)))
+			kfree_skb(skb);
+		cond_resched();
+	}
+
+	return 0;
+}
+
+static int virtbt_flush(struct hci_dev *hdev)
+{
+	return 0;
+}
+
+static int virtbt_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct virtio_bluetooth *vbt = hci_get_drvdata(hdev);
+	struct scatterlist sg[1];
+	int err;
+
+	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+
+	sg_init_one(sg, skb->data, skb->len);
+	err = virtqueue_add_outbuf(vbt->vqs[VIRTBT_VQ_TX], sg, 1, skb,
+				   GFP_KERNEL);
+	if (err) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	virtqueue_kick(vbt->vqs[VIRTBT_VQ_TX]);
+	return 0;
+}
+
+static int virtbt_setup_zephyr(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+
+	/* Read Build Information */
+	skb = __hci_cmd_sync(hdev, 0xfc08, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* Bounded print: the backend controls skb->len. */
+	if (skb->len > 1) {
+		int len = skb->len - 1;
+
+		bt_dev_info(hdev, "%.*s", len, (char *)(skb->data + 1));
+		hci_set_fw_info(hdev, "%.*s", len, skb->data + 1);
+	}
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int virtbt_set_bdaddr_zephyr(struct hci_dev *hdev,
+				    const bdaddr_t *bdaddr)
+{
+	struct sk_buff *skb;
+
+	/* Write BD_ADDR */
+	skb = __hci_cmd_sync(hdev, 0xfc06, 6, bdaddr, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int virtbt_setup_intel(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+
+	/* Intel Read Version */
+	skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int virtbt_set_bdaddr_intel(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	struct sk_buff *skb;
+
+	/* Intel Write BD Address */
+	skb = __hci_cmd_sync(hdev, 0xfc31, 6, bdaddr, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int virtbt_setup_realtek(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+
+	/* Read ROM Version */
+	skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	bt_dev_info(hdev, "ROM version %u", *((__u8 *) (skb->data + 1)));
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int virtbt_shutdown_generic(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+
+	/* Reset */
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void virtbt_rx_handle(struct virtio_bluetooth *vbt, struct sk_buff *skb)
+{
+	size_t min_hdr;
+	__u8 pkt_type;
+
+	pkt_type = *((__u8 *) skb->data);
+	skb_pull(skb, 1);
+
+	switch (pkt_type) {
+	case HCI_EVENT_PKT:
+		min_hdr = sizeof(struct hci_event_hdr);
+		break;
+	case HCI_ACLDATA_PKT:
+		min_hdr = sizeof(struct hci_acl_hdr);
+		break;
+	case HCI_SCODATA_PKT:
+		min_hdr = sizeof(struct hci_sco_hdr);
+		break;
+	case HCI_ISODATA_PKT:
+		min_hdr = sizeof(struct hci_iso_hdr);
+		break;
+	default:
+		kfree_skb(skb);
+		return;
+	}
+
+	if (skb->len < min_hdr) {
+		bt_dev_err_ratelimited(vbt->hdev,
+				       "rx pkt_type 0x%02x payload %u < hdr %zu\n",
+				       pkt_type, skb->len, min_hdr);
+		kfree_skb(skb);
+		return;
+	}
+
+	hci_skb_pkt_type(skb) = pkt_type;
+	hci_recv_frame(vbt->hdev, skb);
+}
+
+static void virtbt_rx_work(struct work_struct *work)
+{
+	struct virtio_bluetooth *vbt = container_of(work,
+						    struct virtio_bluetooth, rx);
+	struct sk_buff *skb;
+	unsigned int len;
+
+	skb = virtqueue_get_buf(vbt->vqs[VIRTBT_VQ_RX], &len);
+	if (!skb)
+		return;
+
+	if (!len || len > VIRTBT_RX_BUF_SIZE) {
+		bt_dev_err_ratelimited(vbt->hdev,
+				       "rx reply len %u outside [1, %u]\n",
+				       len, VIRTBT_RX_BUF_SIZE);
+		kfree_skb(skb);
+	} else {
+		skb_put(skb, len);
+		virtbt_rx_handle(vbt, skb);
+	}
+
+	if (virtbt_add_inbuf(vbt) < 0)
+		return;
+
+	virtqueue_kick(vbt->vqs[VIRTBT_VQ_RX]);
+}
+
+static void virtbt_tx_done(struct virtqueue *vq)
+{
+	struct sk_buff *skb;
+	unsigned int len;
+
+	while ((skb = virtqueue_get_buf(vq, &len)))
+		kfree_skb(skb);
+}
+
+static void virtbt_rx_done(struct virtqueue *vq)
+{
+	struct virtio_bluetooth *vbt = vq->vdev->priv;
+
+	schedule_work(&vbt->rx);
+}
+
+static int virtbt_probe(struct virtio_device *vdev)
+{
+	struct virtqueue_info vqs_info[VIRTBT_NUM_VQS] = {
+		[VIRTBT_VQ_TX] = { "tx", virtbt_tx_done },
+		[VIRTBT_VQ_RX] = { "rx", virtbt_rx_done },
+	};
+	struct virtio_bluetooth *vbt;
+	struct hci_dev *hdev;
+	int err;
+	__u8 type;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
+		return -ENODEV;
+
+	type = virtio_cread8(vdev, offsetof(struct virtio_bt_config, type));
+
+	switch (type) {
+	case VIRTIO_BT_CONFIG_TYPE_PRIMARY:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vbt = kzalloc_obj(*vbt);
+	if (!vbt)
+		return -ENOMEM;
+
+	vdev->priv = vbt;
+	vbt->vdev = vdev;
+
+	INIT_WORK(&vbt->rx, virtbt_rx_work);
+
+	err = virtio_find_vqs(vdev, VIRTBT_NUM_VQS, vbt->vqs, vqs_info, NULL);
+	if (err)
+		return err;
+
+	hdev = hci_alloc_dev();
+	if (!hdev) {
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	vbt->hdev = hdev;
+
+	hdev->bus = HCI_VIRTIO;
+	hci_set_drvdata(hdev, vbt);
+
+	hdev->open  = virtbt_open;
+	hdev->close = virtbt_close;
+	hdev->flush = virtbt_flush;
+	hdev->send  = virtbt_send_frame;
+
+	if (virtio_has_feature(vdev, VIRTIO_BT_F_VND_HCI)) {
+		__u16 vendor;
+
+		if (virtio_has_feature(vdev, VIRTIO_BT_F_CONFIG_V2))
+			virtio_cread(vdev, struct virtio_bt_config_v2,
+				     vendor, &vendor);
+		else
+			virtio_cread(vdev, struct virtio_bt_config,
+				     vendor, &vendor);
+
+		switch (vendor) {
+		case VIRTIO_BT_CONFIG_VENDOR_ZEPHYR:
+			hdev->manufacturer = 1521;
+			hdev->setup = virtbt_setup_zephyr;
+			hdev->shutdown = virtbt_shutdown_generic;
+			hdev->set_bdaddr = virtbt_set_bdaddr_zephyr;
+			break;
+
+		case VIRTIO_BT_CONFIG_VENDOR_INTEL:
+			hdev->manufacturer = 2;
+			hdev->setup = virtbt_setup_intel;
+			hdev->shutdown = virtbt_shutdown_generic;
+			hdev->set_bdaddr = virtbt_set_bdaddr_intel;
+			hci_set_quirk(hdev, HCI_QUIRK_STRICT_DUPLICATE_FILTER);
+			hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY);
+			hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED);
+			break;
+
+		case VIRTIO_BT_CONFIG_VENDOR_REALTEK:
+			hdev->manufacturer = 93;
+			hdev->setup = virtbt_setup_realtek;
+			hdev->shutdown = virtbt_shutdown_generic;
+			hci_set_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY);
+			hci_set_quirk(hdev, HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED);
+			break;
+		}
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BT_F_MSFT_EXT)) {
+		__u16 msft_opcode;
+
+		if (virtio_has_feature(vdev, VIRTIO_BT_F_CONFIG_V2))
+			virtio_cread(vdev, struct virtio_bt_config_v2,
+				     msft_opcode, &msft_opcode);
+		else
+			virtio_cread(vdev, struct virtio_bt_config,
+				     msft_opcode, &msft_opcode);
+
+		hci_set_msft_opcode(hdev, msft_opcode);
+	}
+
+	if (virtio_has_feature(vdev, VIRTIO_BT_F_AOSP_EXT))
+		hci_set_aosp_capable(hdev);
+
+	if (hci_register_dev(hdev) < 0) {
+		hci_free_dev(hdev);
+		err = -EBUSY;
+		goto failed;
+	}
+
+	virtio_device_ready(vdev);
+	err = virtbt_open_vdev(vbt);
+	if (err)
+		goto open_failed;
+
+	return 0;
+
+open_failed:
+	hci_free_dev(hdev);
+failed:
+	vdev->config->del_vqs(vdev);
+	return err;
+}
+
+static void virtbt_remove(struct virtio_device *vdev)
+{
+	struct virtio_bluetooth *vbt = vdev->priv;
+	struct hci_dev *hdev = vbt->hdev;
+
+	hci_unregister_dev(hdev);
+	virtio_reset_device(vdev);
+	virtbt_close_vdev(vbt);
+
+	hci_free_dev(hdev);
+	vbt->hdev = NULL;
+
+	vdev->config->del_vqs(vdev);
+	kfree(vbt);
+}
+
+static struct virtio_device_id virtbt_table[] = {
+	{ VIRTIO_ID_BT, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+MODULE_DEVICE_TABLE(virtio, virtbt_table);
+
+static const unsigned int virtbt_features[] = {
+	VIRTIO_BT_F_VND_HCI,
+	VIRTIO_BT_F_MSFT_EXT,
+	VIRTIO_BT_F_AOSP_EXT,
+	VIRTIO_BT_F_CONFIG_V2,
+};
+
+static struct virtio_driver virtbt_driver = {
+	.driver.name         = KBUILD_MODNAME,
+	.feature_table       = virtbt_features,
+	.feature_table_size  = ARRAY_SIZE(virtbt_features),
+	.id_table            = virtbt_table,
+	.probe               = virtbt_probe,
+	.remove              = virtbt_remove,
+};
+
+module_virtio_driver(virtbt_driver);
+
+MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>");
+MODULE_DESCRIPTION("Generic Bluetooth VIRTIO driver ver " VERSION);
+MODULE_VERSION(VERSION);
+MODULE_LICENSE("GPL");