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, 263 insertions, 0 deletions

diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
new file mode 100644
index 000000000..09e8eccee
--- /dev/null
+++ b/include/asm-generic/bug.h
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BUG_H
+#define _ASM_GENERIC_BUG_H
+
+#include <linux/compiler.h>
+#include <linux/instrumentation.h>
+#include <linux/once_lite.h>
+
+#define CUT_HERE		"------------[ cut here ]------------\n"
+
+#ifdef CONFIG_GENERIC_BUG
+#define BUGFLAG_WARNING		(1 << 0)
+#define BUGFLAG_ONCE		(1 << 1)
+#define BUGFLAG_DONE		(1 << 2)
+#define BUGFLAG_NO_CUT_HERE	(1 << 3)	/* CUT_HERE already sent */
+#define BUGFLAG_ARGS		(1 << 4)
+#define BUGFLAG_TAINT(taint)	((taint) << 8)
+#define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
+#endif
+
+#ifndef WARN_CONDITION_STR
+#ifdef CONFIG_DEBUG_BUGVERBOSE_DETAILED
+# define WARN_CONDITION_STR(cond_str) "[" cond_str "] "
+#else
+# define WARN_CONDITION_STR(cond_str)
+#endif
+#endif /* WARN_CONDITION_STR */
+
+#ifndef __ASSEMBLY__
+#include <linux/panic.h>
+#include <linux/printk.h>
+
+struct warn_args;
+struct pt_regs;
+
+void __warn(const char *file, int line, void *caller, unsigned taint,
+	    struct pt_regs *regs, struct warn_args *args);
+
+#ifdef CONFIG_BUG
+
+#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+#define BUG_REL(type, name) type name
+#else
+#define BUG_REL(type, name) signed int name##_disp
+#endif
+
+#ifdef CONFIG_GENERIC_BUG
+struct bug_entry {
+	BUG_REL(unsigned long, bug_addr);
+#ifdef HAVE_ARCH_BUG_FORMAT
+	BUG_REL(const char *, format);
+#endif
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+	BUG_REL(const char *, file);
+	unsigned short	line;
+#endif
+	unsigned short	flags;
+};
+#endif	/* CONFIG_GENERIC_BUG */
+
+/*
+ * Don't use BUG() or BUG_ON() unless there's really no way out; one
+ * example might be detecting data structure corruption in the middle
+ * of an operation that can't be backed out of.  If the (sub)system
+ * can somehow continue operating, perhaps with reduced functionality,
+ * it's probably not BUG-worthy.
+ *
+ * If you're tempted to BUG(), think again:  is completely giving up
+ * really the *only* solution?  There are usually better options, where
+ * users don't need to reboot ASAP and can mostly shut down cleanly.
+ */
+#ifndef HAVE_ARCH_BUG
+#define BUG() do { \
+	printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
+	barrier_before_unreachable(); \
+	panic("BUG!"); \
+} while (0)
+#endif
+
+#ifndef HAVE_ARCH_BUG_ON
+#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
+#endif
+
+/*
+ * WARN(), WARN_ON(), WARN_ON_ONCE(), and so on can be used to report
+ * significant kernel issues that need prompt attention if they should ever
+ * appear at runtime.
+ *
+ * Do not use these macros when checking for invalid external inputs
+ * (e.g. invalid system call arguments, or invalid data coming from
+ * network/devices), and on transient conditions like ENOMEM or EAGAIN.
+ * These macros should be used for recoverable kernel issues only.
+ * For invalid external inputs, transient conditions, etc use
+ * pr_err[_once/_ratelimited]() followed by dump_stack(), if necessary.
+ * Do not include "BUG"/"WARNING" in format strings manually to make these
+ * conditions distinguishable from kernel issues.
+ *
+ * Use the versions with printk format strings to provide better diagnostics.
+ */
+extern __printf(4, 5)
+void warn_slowpath_fmt(const char *file, const int line, unsigned taint,
+		       const char *fmt, ...);
+extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
+
+#ifdef __WARN_FLAGS
+#define __WARN()		__WARN_FLAGS("", BUGFLAG_TAINT(TAINT_WARN))
+
+#ifndef WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_FLAGS(#condition,				\
+			     BUGFLAG_TAINT(TAINT_WARN));		\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN_ON_ONCE
+#define WARN_ON_ONCE(condition) ({					\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_FLAGS(#condition,				\
+			     BUGFLAG_ONCE |				\
+			     BUGFLAG_TAINT(TAINT_WARN));		\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+#endif /* __WARN_FLAGS */
+
+#if defined(__WARN_FLAGS) && !defined(__WARN_printf)
+#define __WARN_printf(taint, arg...) do {				\
+		instrumentation_begin();				\
+		__warn_printk(arg);					\
+		__WARN_FLAGS("", BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\
+		instrumentation_end();					\
+	} while (0)
+#endif
+
+#ifndef __WARN_printf
+#define __WARN_printf(taint, arg...) do {				\
+		instrumentation_begin();				\
+		warn_slowpath_fmt(__FILE__, __LINE__, taint, arg);	\
+		instrumentation_end();					\
+	} while (0)
+#endif
+
+#ifndef __WARN
+#define __WARN()		__WARN_printf(TAINT_WARN, NULL)
+#endif
+
+/* used internally by panic.c */
+
+#ifndef WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN();						\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN
+#define WARN(condition, format...) ({					\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_printf(TAINT_WARN, format);			\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#define WARN_TAINT(condition, taint, format...) ({			\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_printf(taint, format);				\
+	unlikely(__ret_warn_on);					\
+})
+
+#ifndef WARN_ON_ONCE
+#define WARN_ON_ONCE(condition)					\
+	DO_ONCE_LITE_IF(condition, WARN_ON, 1)
+#endif
+
+#ifndef WARN_ONCE
+#define WARN_ONCE(condition, format...)				\
+	DO_ONCE_LITE_IF(condition, WARN, 1, format)
+#endif
+
+#define WARN_TAINT_ONCE(condition, taint, format...)		\
+	DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format)
+
+#else /* !CONFIG_BUG */
+#ifndef HAVE_ARCH_BUG
+#define BUG() do {		\
+	do {} while (1);	\
+	unreachable();		\
+} while (0)
+#endif
+
+#ifndef HAVE_ARCH_BUG_ON
+#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
+#endif
+
+#ifndef HAVE_ARCH_WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN
+#define WARN(condition, format...) ({					\
+	int __ret_warn_on = !!(condition);				\
+	no_printk(format);						\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#define WARN_ON_ONCE(condition) WARN_ON(condition)
+#define WARN_ONCE(condition, format...) WARN(condition, format)
+#define WARN_TAINT(condition, taint, format...) WARN(condition, format)
+#define WARN_TAINT_ONCE(condition, taint, format...) WARN(condition, format)
+
+#endif
+
+/*
+ * WARN_ON_SMP() is for cases that the warning is either
+ * meaningless for !SMP or may even cause failures.
+ * It can also be used with values that are only defined
+ * on SMP:
+ *
+ * struct foo {
+ *  [...]
+ * #ifdef CONFIG_SMP
+ *	int bar;
+ * #endif
+ * };
+ *
+ * void func(struct foo *zoot)
+ * {
+ *	WARN_ON_SMP(!zoot->bar);
+ *
+ * For CONFIG_SMP, WARN_ON_SMP() should act the same as WARN_ON(),
+ * and should be a nop and return false for uniprocessor.
+ *
+ * if (WARN_ON_SMP(x)) returns true only when CONFIG_SMP is set
+ * and x is true.
+ */
+#ifdef CONFIG_SMP
+# define WARN_ON_SMP(x)			WARN_ON(x)
+#else
+/*
+ * Use of ({0;}) because WARN_ON_SMP(x) may be used either as
+ * a stand alone line statement or as a condition in an if ()
+ * statement.
+ * A simple "0" would cause gcc to give a "statement has no effect"
+ * warning.
+ */
+# define WARN_ON_SMP(x)			({0;})
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif