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, 133 insertions, 0 deletions

diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c
new file mode 100644
index 000000000..b99122cb2
--- /dev/null
+++ b/samples/livepatch/livepatch-shadow-fix2.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2017 Joe Lawrence <joe.lawrence@redhat.com>
+ */
+
+/*
+ * livepatch-shadow-fix2.c - Shadow variables, livepatch demo
+ *
+ * Purpose
+ * -------
+ *
+ * Adds functionality to livepatch-shadow-mod's in-flight data
+ * structures through a shadow variable.  The livepatch patches a
+ * routine that periodically inspects data structures, incrementing a
+ * per-data-structure counter, creating the counter if needed.
+ *
+ *
+ * Usage
+ * -----
+ *
+ * This module is not intended to be standalone.  See the "Usage"
+ * section of livepatch-shadow-mod.c.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/livepatch.h>
+#include <linux/slab.h>
+
+/* Shadow variable enums */
+#define SV_LEAK		1
+#define SV_COUNTER	2
+
+struct dummy {
+	struct list_head list;
+	unsigned long jiffies_expire;
+};
+
+static bool livepatch_fix2_dummy_check(struct dummy *d, unsigned long jiffies)
+{
+	int *shadow_count;
+
+	/*
+	 * Patch: handle in-flight dummy structures, if they do not
+	 * already have a SV_COUNTER shadow variable, then attach a
+	 * new one.
+	 */
+	shadow_count = klp_shadow_get_or_alloc(d, SV_COUNTER,
+				sizeof(*shadow_count), GFP_NOWAIT,
+				NULL, NULL);
+	if (shadow_count)
+		*shadow_count += 1;
+
+	return time_after(jiffies, d->jiffies_expire);
+}
+
+static void livepatch_fix2_dummy_leak_dtor(void *obj, void *shadow_data)
+{
+	void *d = obj;
+	int **shadow_leak = shadow_data;
+
+	pr_info("%s: dummy @ %p, prevented leak @ %p\n",
+			 __func__, d, *shadow_leak);
+	kfree(*shadow_leak);
+}
+
+static void livepatch_fix2_dummy_free(struct dummy *d)
+{
+	int **shadow_leak;
+	int *shadow_count;
+
+	/* Patch: copy the memory leak patch from the fix1 module. */
+	shadow_leak = klp_shadow_get(d, SV_LEAK);
+	if (shadow_leak)
+		klp_shadow_free(d, SV_LEAK, livepatch_fix2_dummy_leak_dtor);
+	else
+		pr_info("%s: dummy @ %p leaked!\n", __func__, d);
+
+	/*
+	 * Patch: fetch the SV_COUNTER shadow variable and display
+	 * the final count.  Detach the shadow variable.
+	 */
+	shadow_count = klp_shadow_get(d, SV_COUNTER);
+	if (shadow_count) {
+		pr_info("%s: dummy @ %p, check counter = %d\n",
+			__func__, d, *shadow_count);
+		klp_shadow_free(d, SV_COUNTER, NULL);
+	}
+
+	kfree(d);
+}
+
+static struct klp_func funcs[] = {
+	{
+		.old_name = "dummy_check",
+		.new_func = livepatch_fix2_dummy_check,
+	},
+	{
+		.old_name = "dummy_free",
+		.new_func = livepatch_fix2_dummy_free,
+	}, { }
+};
+
+static struct klp_object objs[] = {
+	{
+		.name = "livepatch_shadow_mod",
+		.funcs = funcs,
+	}, { }
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+};
+
+static int livepatch_shadow_fix2_init(void)
+{
+	return klp_enable_patch(&patch);
+}
+
+static void livepatch_shadow_fix2_exit(void)
+{
+	/* Cleanup any existing SV_COUNTER shadow variables */
+	klp_shadow_free_all(SV_COUNTER, NULL);
+}
+
+module_init(livepatch_shadow_fix2_init);
+module_exit(livepatch_shadow_fix2_exit);
+MODULE_DESCRIPTION("Live patching demo for shadow variables");
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");