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, 119 insertions, 0 deletions

diff --git a/drivers/pps/kc.c b/drivers/pps/kc.c
new file mode 100644
index 000000000..4f8fffa7e
--- /dev/null
+++ b/drivers/pps/kc.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PPS kernel consumer API
+ *
+ * Copyright (C) 2009-2010   Alexander Gordeev <lasaine@lvk.cs.msu.su>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/pps_kernel.h>
+
+#include "kc.h"
+
+/*
+ * Global variables
+ */
+
+/* state variables to bind kernel consumer */
+static DEFINE_SPINLOCK(pps_kc_hardpps_lock);
+/* PPS API (RFC 2783): current source and mode for kernel consumer */
+static struct pps_device *pps_kc_hardpps_dev;	/* unique pointer to device */
+static int pps_kc_hardpps_mode;		/* mode bits for kernel consumer */
+
+/* pps_kc_bind - control PPS kernel consumer binding
+ * @pps: the PPS source
+ * @bind_args: kernel consumer bind parameters
+ *
+ * This function is used to bind or unbind PPS kernel consumer according to
+ * supplied parameters. Should not be called in interrupt context.
+ */
+int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args)
+{
+	/* Check if another consumer is already bound */
+	spin_lock_irq(&pps_kc_hardpps_lock);
+
+	/*
+	 * Don't allow PPS_KC_BIND on a removed device.
+	 */
+	if (pps->kc_removed) {
+		spin_unlock_irq(&pps_kc_hardpps_lock);
+		return -ENODEV;
+	}
+
+	if (bind_args->edge == 0)
+		if (pps_kc_hardpps_dev == pps) {
+			pps_kc_hardpps_mode = 0;
+			pps_kc_hardpps_dev = NULL;
+			spin_unlock_irq(&pps_kc_hardpps_lock);
+			dev_info(&pps->dev, "unbound kernel"
+					" consumer\n");
+		} else {
+			spin_unlock_irq(&pps_kc_hardpps_lock);
+			dev_err(&pps->dev, "selected kernel consumer"
+					" is not bound\n");
+			return -EINVAL;
+		}
+	else
+		if (pps_kc_hardpps_dev == NULL ||
+				pps_kc_hardpps_dev == pps) {
+			pps_kc_hardpps_mode = bind_args->edge;
+			pps_kc_hardpps_dev = pps;
+			spin_unlock_irq(&pps_kc_hardpps_lock);
+			dev_info(&pps->dev, "bound kernel consumer: "
+				"edge=0x%x\n", bind_args->edge);
+		} else {
+			spin_unlock_irq(&pps_kc_hardpps_lock);
+			dev_err(&pps->dev, "another kernel consumer"
+					" is already bound\n");
+			return -EINVAL;
+		}
+
+	return 0;
+}
+
+/* pps_kc_remove - unbind kernel consumer on PPS source removal
+ * @pps: the PPS source
+ *
+ * This function is used to disable kernel consumer on PPS source removal
+ * if this source was bound to PPS kernel consumer. Can be called on any
+ * source safely. Should not be called in interrupt context.
+ */
+void pps_kc_remove(struct pps_device *pps)
+{
+	spin_lock_irq(&pps_kc_hardpps_lock);
+
+	pps->kc_removed = true;
+	if (pps == pps_kc_hardpps_dev) {
+		pps_kc_hardpps_mode = 0;
+		pps_kc_hardpps_dev = NULL;
+		spin_unlock_irq(&pps_kc_hardpps_lock);
+		dev_info(&pps->dev, "unbound kernel consumer"
+				" on device removal\n");
+	} else
+		spin_unlock_irq(&pps_kc_hardpps_lock);
+}
+
+/* pps_kc_event - call hardpps() on PPS event
+ * @pps: the PPS source
+ * @ts: PPS event timestamp
+ * @event: PPS event edge
+ *
+ * This function calls hardpps() when an event from bound PPS source occurs.
+ */
+void pps_kc_event(struct pps_device *pps, struct pps_event_time *ts,
+		int event)
+{
+	unsigned long flags;
+
+	/* Pass some events to kernel consumer if activated */
+	spin_lock_irqsave(&pps_kc_hardpps_lock, flags);
+	if (pps == pps_kc_hardpps_dev && event & pps_kc_hardpps_mode)
+		hardpps(&ts->ts_real, &ts->ts_raw);
+	spin_unlock_irqrestore(&pps_kc_hardpps_lock, flags);
+}