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, 95 insertions, 0 deletions

diff --git a/net/devres.c b/net/devres.c
new file mode 100644
index 000000000..5ccf6ca31
--- /dev/null
+++ b/net/devres.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This file contains all networking devres helpers.
+ */
+
+#include <linux/device.h>
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+struct net_device_devres {
+	struct net_device *ndev;
+};
+
+static void devm_free_netdev(struct device *dev, void *this)
+{
+	struct net_device_devres *res = this;
+
+	free_netdev(res->ndev);
+}
+
+struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv,
+					   unsigned int txqs, unsigned int rxqs)
+{
+	struct net_device_devres *dr;
+
+	dr = devres_alloc(devm_free_netdev, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return NULL;
+
+	dr->ndev = alloc_etherdev_mqs(sizeof_priv, txqs, rxqs);
+	if (!dr->ndev) {
+		devres_free(dr);
+		return NULL;
+	}
+
+	devres_add(dev, dr);
+
+	return dr->ndev;
+}
+EXPORT_SYMBOL(devm_alloc_etherdev_mqs);
+
+static void devm_unregister_netdev(struct device *dev, void *this)
+{
+	struct net_device_devres *res = this;
+
+	unregister_netdev(res->ndev);
+}
+
+static int netdev_devres_match(struct device *dev, void *this, void *match_data)
+{
+	struct net_device_devres *res = this;
+	struct net_device *ndev = match_data;
+
+	return ndev == res->ndev;
+}
+
+/**
+ *	devm_register_netdev - resource managed variant of register_netdev()
+ *	@dev: managing device for this netdev - usually the parent device
+ *	@ndev: device to register
+ *
+ *	This is a devres variant of register_netdev() for which the unregister
+ *	function will be called automatically when the managing device is
+ *	detached. Note: the net_device used must also be resource managed by
+ *	the same struct device.
+ */
+int devm_register_netdev(struct device *dev, struct net_device *ndev)
+{
+	struct net_device_devres *dr;
+	int ret;
+
+	/* struct net_device must itself be managed. For now a managed netdev
+	 * can only be allocated by devm_alloc_etherdev_mqs() so the check is
+	 * straightforward.
+	 */
+	if (WARN_ON(!devres_find(dev, devm_free_netdev,
+				 netdev_devres_match, ndev)))
+		return -EINVAL;
+
+	dr = devres_alloc(devm_unregister_netdev, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	ret = register_netdev(ndev);
+	if (ret) {
+		devres_free(dr);
+		return ret;
+	}
+
+	dr->ndev = ndev;
+	devres_add(ndev->dev.parent, dr);
+
+	return 0;
+}
+EXPORT_SYMBOL(devm_register_netdev);