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, 259 insertions, 0 deletions

diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
new file mode 100644
index 000000000..66c949d94
--- /dev/null
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/etherdevice.h>
+#include "ipvlan.h"
+#include <linux/if_vlan.h>
+#include <linux/if_tap.h>
+#include <linux/interrupt.h>
+#include <linux/nsproxy.h>
+#include <linux/compat.h>
+#include <linux/if_tun.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/cdev.h>
+#include <linux/idr.h>
+#include <linux/fs.h>
+#include <linux/uio.h>
+
+#include <net/net_namespace.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
+#include <linux/virtio_net.h>
+
+#define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
+		      NETIF_F_TSO6)
+
+static dev_t ipvtap_major;
+static struct cdev ipvtap_cdev;
+
+static const struct ns_common *ipvtap_net_namespace(const struct device *d)
+{
+	const struct net_device *dev = to_net_dev(d->parent);
+
+	return to_ns_common(dev_net(dev));
+}
+
+static struct class ipvtap_class = {
+	 .name = "ipvtap",
+	 .ns_type = &net_ns_type_operations,
+	 .namespace = ipvtap_net_namespace,
+};
+
+struct ipvtap_dev {
+	struct ipvl_dev vlan;
+	struct tap_dev	  tap;
+};
+
+static void ipvtap_count_tx_dropped(struct tap_dev *tap)
+{
+	struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+	struct ipvl_dev *vlan = &vlantap->vlan;
+
+	this_cpu_inc(vlan->pcpu_stats->tx_drps);
+}
+
+static void ipvtap_count_rx_dropped(struct tap_dev *tap)
+{
+	struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+	struct ipvl_dev *vlan = &vlantap->vlan;
+
+	ipvlan_count_rx(vlan, 0, 0, 0);
+}
+
+static void ipvtap_update_features(struct tap_dev *tap,
+				   netdev_features_t features)
+{
+	struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+	struct ipvl_dev *vlan = &vlantap->vlan;
+
+	vlan->sfeatures = features;
+	netdev_update_features(vlan->dev);
+}
+
+static int ipvtap_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
+			  struct netlink_ext_ack *extack)
+{
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+	int err;
+
+	INIT_LIST_HEAD(&vlantap->tap.queue_list);
+
+	/* Since macvlan supports all offloads by default, make
+	 * tap support all offloads also.
+	 */
+	vlantap->tap.tap_features = TUN_OFFLOADS;
+	vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped;
+	vlantap->tap.update_features =	ipvtap_update_features;
+	vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped;
+
+	err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap);
+	if (err)
+		return err;
+
+	/* Don't put anything that may fail after macvlan_common_newlink
+	 * because we can't undo what it does.
+	 */
+	err = ipvlan_link_new(dev, params, extack);
+	if (err) {
+		netdev_rx_handler_unregister(dev);
+		return err;
+	}
+
+	vlantap->tap.dev = vlantap->vlan.dev;
+
+	return err;
+}
+
+static void __ipvtap_dellink(struct net *net, struct net_device *dev,
+			     struct list_head *head)
+{
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+
+	netdev_rx_handler_unregister(dev);
+	tap_del_queues(&vlantap->tap);
+	__ipvlan_link_delete(net, dev, head);
+}
+
+static void ipvtap_dellink(struct net_device *dev,
+			   struct list_head *head)
+{
+	struct ipvtap_dev *vlantap = netdev_priv(dev);
+	struct ipvl_port *port = vlantap->vlan.port;
+
+	mutex_lock(&port->pnodes_lock);
+	if (!vlantap->vlan.dying)
+		__ipvtap_dellink(dev_net(dev), dev, head);
+	mutex_unlock(&port->pnodes_lock);
+}
+
+static void ipvtap_setup(struct net_device *dev)
+{
+	ipvlan_link_setup(dev);
+	dev->tx_queue_len = TUN_READQ_SIZE;
+	dev->priv_flags &= ~IFF_NO_QUEUE;
+}
+
+static struct rtnl_link_ops ipvtap_link_ops __read_mostly = {
+	.kind		= "ipvtap",
+	.setup		= ipvtap_setup,
+	.newlink	= ipvtap_newlink,
+	.dellink	= ipvtap_dellink,
+	.priv_size	= sizeof(struct ipvtap_dev),
+};
+
+static int ipvtap_device_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ipvtap_dev *vlantap;
+	struct device *classdev;
+	dev_t devt;
+	int err;
+	char tap_name[IFNAMSIZ];
+
+	if (dev->rtnl_link_ops != &ipvtap_link_ops)
+		return NOTIFY_DONE;
+
+	snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex);
+	vlantap = netdev_priv(dev);
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		/* Create the device node here after the network device has
+		 * been registered but before register_netdevice has
+		 * finished running.
+		 */
+		err = tap_get_minor(ipvtap_major, &vlantap->tap);
+		if (err)
+			return notifier_from_errno(err);
+
+		devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor);
+		classdev = device_create(&ipvtap_class, &dev->dev, devt,
+					 dev, "%s", tap_name);
+		if (IS_ERR(classdev)) {
+			tap_free_minor(ipvtap_major, &vlantap->tap);
+			return notifier_from_errno(PTR_ERR(classdev));
+		}
+		err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj,
+					tap_name);
+		if (err)
+			return notifier_from_errno(err);
+		break;
+	case NETDEV_UNREGISTER:
+		/* vlan->minor == 0 if NETDEV_REGISTER above failed */
+		if (vlantap->tap.minor == 0)
+			break;
+		sysfs_remove_link(&dev->dev.kobj, tap_name);
+		devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor);
+		device_destroy(&ipvtap_class, devt);
+		tap_free_minor(ipvtap_major, &vlantap->tap);
+		break;
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+		if (tap_queue_resize(&vlantap->tap))
+			return NOTIFY_BAD;
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ipvtap_notifier_block __read_mostly = {
+	.notifier_call	= ipvtap_device_event,
+};
+
+static int __init ipvtap_init(void)
+{
+	int err;
+
+	__ipvtap_dellink_ptr = __ipvtap_dellink;
+
+	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap",
+			      THIS_MODULE);
+	if (err)
+		goto out1;
+
+	err = class_register(&ipvtap_class);
+	if (err)
+		goto out2;
+
+	err = register_netdevice_notifier(&ipvtap_notifier_block);
+	if (err)
+		goto out3;
+
+	err = ipvlan_link_register(&ipvtap_link_ops);
+	if (err)
+		goto out4;
+
+	return 0;
+
+out4:
+	unregister_netdevice_notifier(&ipvtap_notifier_block);
+out3:
+	class_unregister(&ipvtap_class);
+out2:
+	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+out1:
+	__ipvtap_dellink_ptr = NULL;
+
+	return err;
+}
+module_init(ipvtap_init);
+
+static void __exit ipvtap_exit(void)
+{
+	rtnl_link_unregister(&ipvtap_link_ops);
+	unregister_netdevice_notifier(&ipvtap_notifier_block);
+	class_unregister(&ipvtap_class);
+	tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+	__ipvtap_dellink_ptr = NULL;
+}
+module_exit(ipvtap_exit);
+MODULE_ALIAS_RTNL_LINK("ipvtap");
+MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
+MODULE_DESCRIPTION("IP-VLAN based tap driver");
+MODULE_LICENSE("GPL");