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, 197 insertions, 0 deletions

diff --git a/samples/livepatch/livepatch-callbacks-demo.c b/samples/livepatch/livepatch-callbacks-demo.c
new file mode 100644
index 000000000..9e69d9cae
--- /dev/null
+++ b/samples/livepatch/livepatch-callbacks-demo.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2017 Joe Lawrence <joe.lawrence@redhat.com>
+ */
+
+/*
+ * livepatch-callbacks-demo.c - (un)patching callbacks livepatch demo
+ *
+ *
+ * Purpose
+ * -------
+ *
+ * Demonstration of registering livepatch (un)patching callbacks.
+ *
+ *
+ * Usage
+ * -----
+ *
+ * Step 1 - load the simple module
+ *
+ *   insmod samples/livepatch/livepatch-callbacks-mod.ko
+ *
+ *
+ * Step 2 - load the demonstration livepatch (with callbacks)
+ *
+ *   insmod samples/livepatch/livepatch-callbacks-demo.ko
+ *
+ *
+ * Step 3 - cleanup
+ *
+ *   echo 0 > /sys/kernel/livepatch/livepatch_callbacks_demo/enabled
+ *   rmmod livepatch_callbacks_demo
+ *   rmmod livepatch_callbacks_mod
+ *
+ * Watch dmesg output to see livepatch enablement, callback execution
+ * and patching operations for both vmlinux and module targets.
+ *
+ * NOTE: swap the insmod order of livepatch-callbacks-mod.ko and
+ *       livepatch-callbacks-demo.ko to observe what happens when a
+ *       target module is loaded after a livepatch with callbacks.
+ *
+ * NOTE: 'pre_patch_ret' is a module parameter that sets the pre-patch
+ *       callback return status.  Try setting up a non-zero status
+ *       such as -19 (-ENODEV):
+ *
+ *       # Load demo livepatch, vmlinux is patched
+ *       insmod samples/livepatch/livepatch-callbacks-demo.ko
+ *
+ *       # Setup next pre-patch callback to return -ENODEV
+ *       echo -19 > /sys/module/livepatch_callbacks_demo/parameters/pre_patch_ret
+ *
+ *       # Module loader refuses to load the target module
+ *       insmod samples/livepatch/livepatch-callbacks-mod.ko
+ *       insmod: ERROR: could not insert module samples/livepatch/livepatch-callbacks-mod.ko: No such device
+ *
+ * NOTE: There is a second target module,
+ *       livepatch-callbacks-busymod.ko, available for experimenting
+ *       with livepatch (un)patch callbacks.  This module contains
+ *       a 'sleep_secs' parameter that parks the module on one of the
+ *       functions that the livepatch demo module wants to patch.
+ *       Modifying this value and tweaking the order of module loads can
+ *       effectively demonstrate stalled patch transitions:
+ *
+ *       # Load a target module, let it park on 'busymod_work_func' for
+ *       # thirty seconds
+ *       insmod samples/livepatch/livepatch-callbacks-busymod.ko sleep_secs=30
+ *
+ *       # Meanwhile load the livepatch
+ *       insmod samples/livepatch/livepatch-callbacks-demo.ko
+ *
+ *       # ... then load and unload another target module while the
+ *       # transition is in progress
+ *       insmod samples/livepatch/livepatch-callbacks-mod.ko
+ *       rmmod samples/livepatch/livepatch-callbacks-mod.ko
+ *
+ *       # Finally cleanup
+ *       echo 0 > /sys/kernel/livepatch/livepatch_callbacks_demo/enabled
+ *       rmmod samples/livepatch/livepatch-callbacks-demo.ko
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/livepatch.h>
+
+static int pre_patch_ret;
+module_param(pre_patch_ret, int, 0644);
+MODULE_PARM_DESC(pre_patch_ret, "pre_patch_ret (default=0)");
+
+static const char *const module_state[] = {
+	[MODULE_STATE_LIVE]	= "[MODULE_STATE_LIVE] Normal state",
+	[MODULE_STATE_COMING]	= "[MODULE_STATE_COMING] Full formed, running module_init",
+	[MODULE_STATE_GOING]	= "[MODULE_STATE_GOING] Going away",
+	[MODULE_STATE_UNFORMED]	= "[MODULE_STATE_UNFORMED] Still setting it up",
+};
+
+static void callback_info(const char *callback, struct klp_object *obj)
+{
+	if (obj->mod)
+		pr_info("%s: %s -> %s\n", callback, obj->mod->name,
+			module_state[obj->mod->state]);
+	else
+		pr_info("%s: vmlinux\n", callback);
+}
+
+/* Executed on object patching (ie, patch enablement) */
+static int pre_patch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+	return pre_patch_ret;
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void post_patch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void pre_unpatch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+}
+
+/* Executed on object unpatching (ie, patch disablement) */
+static void post_unpatch_callback(struct klp_object *obj)
+{
+	callback_info(__func__, obj);
+}
+
+static void patched_work_func(struct work_struct *work)
+{
+	pr_info("%s\n", __func__);
+}
+
+static struct klp_func no_funcs[] = {
+	{ }
+};
+
+static struct klp_func busymod_funcs[] = {
+	{
+		.old_name = "busymod_work_func",
+		.new_func = patched_work_func,
+	}, { }
+};
+
+static struct klp_object objs[] = {
+	{
+		.name = NULL,	/* vmlinux */
+		.funcs = no_funcs,
+		.callbacks = {
+			.pre_patch = pre_patch_callback,
+			.post_patch = post_patch_callback,
+			.pre_unpatch = pre_unpatch_callback,
+			.post_unpatch = post_unpatch_callback,
+		},
+	},	{
+		.name = "livepatch_callbacks_mod",
+		.funcs = no_funcs,
+		.callbacks = {
+			.pre_patch = pre_patch_callback,
+			.post_patch = post_patch_callback,
+			.pre_unpatch = pre_unpatch_callback,
+			.post_unpatch = post_unpatch_callback,
+		},
+	},	{
+		.name = "livepatch_callbacks_busymod",
+		.funcs = busymod_funcs,
+		.callbacks = {
+			.pre_patch = pre_patch_callback,
+			.post_patch = post_patch_callback,
+			.pre_unpatch = pre_unpatch_callback,
+			.post_unpatch = post_unpatch_callback,
+		},
+	}, { }
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+};
+
+static int livepatch_callbacks_demo_init(void)
+{
+	return klp_enable_patch(&patch);
+}
+
+static void livepatch_callbacks_demo_exit(void)
+{
+}
+
+module_init(livepatch_callbacks_demo_init);
+module_exit(livepatch_callbacks_demo_exit);
+MODULE_DESCRIPTION("Live patching demo for (un)patching callbacks");
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");