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, 139 insertions, 0 deletions

diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
new file mode 100644
index 000000000..f39c9eca8
--- /dev/null
+++ b/lib/nmi_backtrace.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  NMI backtrace support
+ *
+ * Gratuitously copied from arch/x86/kernel/apic/hw_nmi.c by Russell King,
+ * with the following header:
+ *
+ *  HW NMI watchdog support
+ *
+ *  started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ *  Arch specific calls to support NMI watchdog
+ *
+ *  Bits copied from original nmi.c file
+ */
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/kprobes.h>
+#include <linux/stringify.h>
+#include <linux/nmi.h>
+#include <linux/cpu.h>
+#include <linux/export.h>
+#include <linux/sched/debug.h>
+
+#ifdef arch_trigger_cpumask_backtrace
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
+/* "in progress" flag of arch_trigger_cpumask_backtrace */
+static unsigned long backtrace_flag;
+
+#define NMI_BT_TIMEOUT_SEC	10
+
+/*
+ * When raise() is called it will be passed a pointer to the
+ * backtrace_mask. Architectures that call nmi_cpu_backtrace()
+ * directly from their raise() functions may rely on the mask
+ * they are passed being updated as a side effect of this call.
+ */
+void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
+				   int exclude_cpu,
+				   void (*raise)(cpumask_t *mask))
+{
+	int i, this_cpu = get_cpu();
+
+	if (test_and_set_bit(0, &backtrace_flag)) {
+		/*
+		 * If there is already a trigger_all_cpu_backtrace() in progress
+		 * (backtrace_flag == 1), don't output double cpu dump infos.
+		 */
+		put_cpu();
+		return;
+	}
+
+	cpumask_copy(to_cpumask(backtrace_mask), mask);
+	if (exclude_cpu != -1)
+		cpumask_clear_cpu(exclude_cpu, to_cpumask(backtrace_mask));
+
+	/*
+	 * Don't try to send an NMI to this cpu; it may work on some
+	 * architectures, but on others it may not, and we'll get
+	 * information at least as useful just by doing a dump_stack() here.
+	 * Note that nmi_cpu_backtrace(NULL) will clear the cpu bit.
+	 */
+	if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask)))
+		nmi_cpu_backtrace(NULL);
+
+	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+		pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n",
+			this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask));
+		nmi_backtrace_stall_snap(to_cpumask(backtrace_mask));
+		raise(to_cpumask(backtrace_mask));
+	}
+
+	/* Wait for up to NMI_BT_TIMEOUT_SEC seconds for all CPUs to do the backtrace */
+	for (i = 0; i < NMI_BT_TIMEOUT_SEC * 1000; i++) {
+		if (cpumask_empty(to_cpumask(backtrace_mask)))
+			break;
+		mdelay(1);
+		touch_softlockup_watchdog();
+	}
+
+	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+		pr_warn("After " __stringify(NMI_BT_TIMEOUT_SEC) " seconds, these CPUS still haven't responded to the NMI: %*pbl\n",
+			cpumask_pr_args(to_cpumask(backtrace_mask)));
+
+		nmi_backtrace_stall_check(to_cpumask(backtrace_mask));
+	}
+
+	/*
+	 * Force flush any remote buffers that might be stuck in IRQ context
+	 * and therefore could not run their irq_work.
+	 */
+	printk_trigger_flush();
+
+	clear_bit_unlock(0, &backtrace_flag);
+	put_cpu();
+}
+
+// Dump stacks even for idle CPUs.
+static bool backtrace_idle;
+module_param(backtrace_idle, bool, 0644);
+
+bool nmi_cpu_backtrace(struct pt_regs *regs)
+{
+	int cpu = smp_processor_id();
+	unsigned long flags;
+
+	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		/*
+		 * Allow nested NMI backtraces while serializing
+		 * against other CPUs.
+		 */
+		printk_cpu_sync_get_irqsave(flags);
+		if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) {
+			pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
+				cpu, (void *)instruction_pointer(regs));
+		} else {
+			pr_warn("NMI backtrace for cpu %d\n", cpu);
+			if (regs)
+				show_regs(regs);
+			else
+				dump_stack();
+		}
+		printk_cpu_sync_put_irqrestore(flags);
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+		return true;
+	}
+
+	return false;
+}
+NOKPROBE_SYMBOL(nmi_cpu_backtrace);
+
+void cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
+{
+	arch_trigger_cpumask_backtrace(mask, exclude_cpu);
+}
+EXPORT_SYMBOL_GPL(cpumask_backtrace);
+#endif