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

2 files changed, 99 insertions, 0 deletions

diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile
new file mode 100644
index 000000000..8849e85e9
--- /dev/null
+++ b/samples/workqueue/stall_detector/Makefile
@@ -0,0 +1 @@
+obj-m += wq_stall.o
diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c
new file mode 100644
index 000000000..6f4a497b1
--- /dev/null
+++ b/samples/workqueue/stall_detector/wq_stall.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * wq_stall - Test module for the workqueue stall detector.
+ *
+ * Deliberately creates a workqueue stall so the watchdog fires and
+ * prints diagnostic output.  Useful for verifying that the stall
+ * detector correctly identifies stuck workers and produces useful
+ * backtraces.
+ *
+ * The stall is triggered by clearing PF_WQ_WORKER before sleeping,
+ * which hides the worker from the concurrency manager.  A second
+ * work item queued on the same pool then sits in the worklist with
+ * no worker available to process it.
+ *
+ * After ~30s the workqueue watchdog fires:
+ *   BUG: workqueue lockup - pool cpus=N ...
+ *
+ * Build:
+ *	make -C <kernel tree> M=samples/workqueue/stall_detector modules
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Breno Leitao <leitao@debian.org>
+ */
+
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/atomic.h>
+#include <linux/sched.h>
+
+static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head);
+static atomic_t wake_condition = ATOMIC_INIT(0);
+static struct work_struct stall_work1;
+static struct work_struct stall_work2;
+
+static void stall_work2_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: second work item finally ran\n");
+}
+
+static void stall_work1_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: first work item running on cpu %d\n",
+		raw_smp_processor_id());
+
+	/*
+	 * Queue second item while we're still counted as running
+	 * (pool->nr_running > 0).  Since schedule_work() on a per-CPU
+	 * workqueue targets raw_smp_processor_id(), item 2 lands on the
+	 * same pool.  __queue_work -> kick_pool -> need_more_worker()
+	 * sees nr_running > 0 and does NOT wake a new worker.
+	 */
+	schedule_work(&stall_work2);
+
+	/*
+	 * Hide from the workqueue concurrency manager.  Without
+	 * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(),
+	 * so nr_running is never decremented and no replacement
+	 * worker is created.  Item 2 stays stuck in pool->worklist.
+	 */
+	current->flags &= ~PF_WQ_WORKER;
+
+	pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n");
+	pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n");
+	wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0);
+
+	/* Restore so process_one_work() cleanup works correctly */
+	current->flags |= PF_WQ_WORKER;
+	pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n");
+}
+
+static int __init wq_stall_init(void)
+{
+	pr_info("wq_stall: loading\n");
+
+	INIT_WORK(&stall_work1, stall_work1_fn);
+	INIT_WORK(&stall_work2, stall_work2_fn);
+	schedule_work(&stall_work1);
+
+	return 0;
+}
+
+static void __exit wq_stall_exit(void)
+{
+	pr_info("wq_stall: unloading\n");
+	atomic_set(&wake_condition, 1);
+	wake_up(&stall_wq_head);
+	flush_work(&stall_work1);
+	flush_work(&stall_work2);
+	pr_info("wq_stall: all work flushed, module unloaded\n");
+}
+
+module_init(wq_stall_init);
+module_exit(wq_stall_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse");
+MODULE_AUTHOR("Breno Leitao <leitao@debian.org>");