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, 161 insertions, 0 deletions

diff --git a/net/devlink/sh_dev.c b/net/devlink/sh_dev.c
new file mode 100644
index 000000000..85acce97e
--- /dev/null
+++ b/net/devlink/sh_dev.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <net/devlink.h>
+
+#include "devl_internal.h"
+
+static LIST_HEAD(shd_list);
+static DEFINE_MUTEX(shd_mutex); /* Protects shd_list and shd->list */
+
+/* This structure represents a shared devlink instance,
+ * there is one created per identifier (e.g., serial number).
+ */
+struct devlink_shd {
+	struct list_head list; /* Node in shd list */
+	const char *id; /* Identifier string (e.g., serial number) */
+	refcount_t refcount; /* Reference count */
+	size_t priv_size; /* Size of driver private data */
+	char priv[] __aligned(NETDEV_ALIGN) __counted_by(priv_size);
+};
+
+static struct devlink_shd *devlink_shd_lookup(const char *id)
+{
+	struct devlink_shd *shd;
+
+	list_for_each_entry(shd, &shd_list, list) {
+		if (!strcmp(shd->id, id))
+			return shd;
+	}
+
+	return NULL;
+}
+
+static struct devlink_shd *devlink_shd_create(const char *id,
+					      const struct devlink_ops *ops,
+					      size_t priv_size,
+					      const struct device_driver *driver)
+{
+	struct devlink_shd *shd;
+	struct devlink *devlink;
+
+	devlink = __devlink_alloc(ops, sizeof(struct devlink_shd) + priv_size,
+				  &init_net, NULL, driver);
+	if (!devlink)
+		return NULL;
+	shd = devlink_priv(devlink);
+
+	shd->id = kstrdup(id, GFP_KERNEL);
+	if (!shd->id)
+		goto err_devlink_free;
+	shd->priv_size = priv_size;
+	refcount_set(&shd->refcount, 1);
+
+	devl_lock(devlink);
+	devl_register(devlink);
+	devl_unlock(devlink);
+
+	list_add_tail(&shd->list, &shd_list);
+
+	return shd;
+
+err_devlink_free:
+	devlink_free(devlink);
+	return NULL;
+}
+
+static void devlink_shd_destroy(struct devlink_shd *shd)
+{
+	struct devlink *devlink = priv_to_devlink(shd);
+
+	list_del(&shd->list);
+	devl_lock(devlink);
+	devl_unregister(devlink);
+	devl_unlock(devlink);
+	kfree(shd->id);
+	devlink_free(devlink);
+}
+
+/**
+ * devlink_shd_get - Get or create a shared devlink instance
+ * @id: Identifier string (e.g., serial number) for the shared instance
+ * @ops: Devlink operations structure
+ * @priv_size: Size of private data structure
+ * @driver: Driver associated with the shared devlink instance
+ *
+ * Get an existing shared devlink instance identified by @id, or create
+ * a new one if it doesn't exist. Return the devlink instance with a
+ * reference held. The caller must call devlink_shd_put() when done.
+ *
+ * All callers sharing the same @id must pass identical @ops, @priv_size
+ * and @driver. A mismatch triggers a warning and returns NULL.
+ *
+ * Return: Pointer to the shared devlink instance on success,
+ *         NULL on failure
+ */
+struct devlink *devlink_shd_get(const char *id,
+				const struct devlink_ops *ops,
+				size_t priv_size,
+				const struct device_driver *driver)
+{
+	struct devlink *devlink;
+	struct devlink_shd *shd;
+
+	mutex_lock(&shd_mutex);
+
+	shd = devlink_shd_lookup(id);
+	if (!shd) {
+		shd = devlink_shd_create(id, ops, priv_size, driver);
+		goto unlock;
+	}
+
+	devlink = priv_to_devlink(shd);
+	if (WARN_ON_ONCE(devlink->ops != ops ||
+			 shd->priv_size != priv_size ||
+			 devlink->dev_driver != driver)) {
+		shd = NULL;
+		goto unlock;
+	}
+	refcount_inc(&shd->refcount);
+
+unlock:
+	mutex_unlock(&shd_mutex);
+	return shd ? priv_to_devlink(shd) : NULL;
+}
+EXPORT_SYMBOL_GPL(devlink_shd_get);
+
+/**
+ * devlink_shd_put - Release a reference on a shared devlink instance
+ * @devlink: Shared devlink instance
+ *
+ * Release a reference on a shared devlink instance obtained via
+ * devlink_shd_get().
+ */
+void devlink_shd_put(struct devlink *devlink)
+{
+	struct devlink_shd *shd;
+
+	mutex_lock(&shd_mutex);
+	shd = devlink_priv(devlink);
+	if (refcount_dec_and_test(&shd->refcount))
+		devlink_shd_destroy(shd);
+	mutex_unlock(&shd_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_shd_put);
+
+/**
+ * devlink_shd_get_priv - Get private data from shared devlink instance
+ * @devlink: Devlink instance
+ *
+ * Returns a pointer to the driver's private data structure within
+ * the shared devlink instance.
+ *
+ * Return: Pointer to private data
+ */
+void *devlink_shd_get_priv(struct devlink *devlink)
+{
+	struct devlink_shd *shd = devlink_priv(devlink);
+
+	return shd->priv;
+}
+EXPORT_SYMBOL_GPL(devlink_shd_get_priv);