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, 87 insertions, 0 deletions

diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h
new file mode 100644
index 000000000..03b0ec7af
--- /dev/null
+++ b/include/asm-generic/delay.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_DELAY_H
+#define __ASM_GENERIC_DELAY_H
+
+#include <linux/math.h>
+#include <vdso/time64.h>
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long xloops);
+extern void __delay(unsigned long loops);
+
+/*
+ * The microseconds/nanosecond delay multiplicators are used to convert a
+ * constant microseconds/nanoseconds value to a value which can be used by the
+ * architectures specific implementation to transform it into loops.
+ */
+#define UDELAY_CONST_MULT	((unsigned long)DIV_ROUND_UP(1ULL << 32, USEC_PER_SEC))
+#define NDELAY_CONST_MULT	((unsigned long)DIV_ROUND_UP(1ULL << 32, NSEC_PER_SEC))
+
+/*
+ * The maximum constant udelay/ndelay value picked out of thin air to prevent
+ * too long constant udelays/ndelays.
+ */
+#define DELAY_CONST_MAX   20000
+
+/**
+ * udelay - Inserting a delay based on microseconds with busy waiting
+ * @usec:	requested delay in microseconds
+ *
+ * When delaying in an atomic context ndelay(), udelay() and mdelay() are the
+ * only valid variants of delaying/sleeping to go with.
+ *
+ * When inserting delays in non atomic context which are shorter than the time
+ * which is required to queue e.g. an hrtimer and to enter then the scheduler,
+ * it is also valuable to use udelay(). But it is not simple to specify a
+ * generic threshold for this which will fit for all systems. An approximation
+ * is a threshold for all delays up to 10 microseconds.
+ *
+ * When having a delay which is larger than the architecture specific
+ * %MAX_UDELAY_MS value, please make sure mdelay() is used. Otherwise a overflow
+ * risk is given.
+ *
+ * Please note that ndelay(), udelay() and mdelay() may return early for several
+ * reasons (https://lists.openwall.net/linux-kernel/2011/01/09/56):
+ *
+ * #. computed loops_per_jiffy too low (due to the time taken to execute the
+ *    timer interrupt.)
+ * #. cache behaviour affecting the time it takes to execute the loop function.
+ * #. CPU clock rate changes.
+ */
+static __always_inline void udelay(unsigned long usec)
+{
+	if (__builtin_constant_p(usec)) {
+		if (usec >= DELAY_CONST_MAX)
+			__bad_udelay();
+		else
+			__const_udelay(usec * UDELAY_CONST_MULT);
+	} else {
+		__udelay(usec);
+	}
+}
+
+/**
+ * ndelay - Inserting a delay based on nanoseconds with busy waiting
+ * @nsec:	requested delay in nanoseconds
+ *
+ * See udelay() for basic information about ndelay() and it's variants.
+ */
+static __always_inline void ndelay(unsigned long nsec)
+{
+	if (__builtin_constant_p(nsec)) {
+		if (nsec >= DELAY_CONST_MAX)
+			__bad_ndelay();
+		else
+			__const_udelay(nsec * NDELAY_CONST_MULT);
+	} else {
+		__ndelay(nsec);
+	}
+}
+#define ndelay(x) ndelay(x)
+
+#endif /* __ASM_GENERIC_DELAY_H */