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, 134 insertions, 0 deletions

diff --git a/drivers/ptp/ptp_vmw.c b/drivers/ptp/ptp_vmw.c
new file mode 100644
index 000000000..14fc587d0
--- /dev/null
+++ b/drivers/ptp/ptp_vmw.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
+/*
+ * Copyright (C) 2020 VMware, Inc., Palo Alto, CA., USA
+ *
+ * PTP clock driver for VMware precision clock virtual device.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/acpi.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/ptp_clock_kernel.h>
+#include <asm/hypervisor.h>
+#include <asm/vmware.h>
+
+#define VMWARE_CMD_PCLK(nr) ((nr << 16) | 97)
+#define VMWARE_CMD_PCLK_GETTIME VMWARE_CMD_PCLK(0)
+
+static struct ptp_clock *ptp_vmw_clock;
+
+
+static int ptp_vmw_pclk_read(u64 *ns)
+{
+	u32 ret, nsec_hi, nsec_lo;
+
+	ret = vmware_hypercall3(VMWARE_CMD_PCLK_GETTIME, 0,
+				&nsec_hi, &nsec_lo);
+	if (ret == 0)
+		*ns = ((u64)nsec_hi << 32) | nsec_lo;
+	return ret;
+}
+
+/*
+ * PTP clock ops.
+ */
+
+static int ptp_vmw_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ptp_vmw_adjfine(struct ptp_clock_info *info, long delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ptp_vmw_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
+{
+	u64 ns;
+
+	if (ptp_vmw_pclk_read(&ns) != 0)
+		return -EIO;
+	*ts = ns_to_timespec64(ns);
+	return 0;
+}
+
+static int ptp_vmw_settime(struct ptp_clock_info *info,
+			  const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+static int ptp_vmw_enable(struct ptp_clock_info *info,
+			 struct ptp_clock_request *request, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info ptp_vmw_clock_info = {
+	.owner		= THIS_MODULE,
+	.name		= "ptp_vmw",
+	.max_adj	= 0,
+	.adjtime	= ptp_vmw_adjtime,
+	.adjfine	= ptp_vmw_adjfine,
+	.gettime64	= ptp_vmw_gettime,
+	.settime64	= ptp_vmw_settime,
+	.enable		= ptp_vmw_enable,
+};
+
+/*
+ * ACPI driver ops for VMware "precision clock" virtual device.
+ */
+
+static int ptp_vmw_acpi_probe(struct platform_device *pdev)
+{
+	ptp_vmw_clock = ptp_clock_register(&ptp_vmw_clock_info, NULL);
+	if (IS_ERR(ptp_vmw_clock)) {
+		pr_err("failed to register ptp clock\n");
+		return PTR_ERR(ptp_vmw_clock);
+	}
+	return 0;
+}
+
+static void ptp_vmw_acpi_remove(struct platform_device *pdev)
+{
+	ptp_clock_unregister(ptp_vmw_clock);
+}
+
+static const struct acpi_device_id ptp_vmw_acpi_device_ids[] = {
+	{ "VMW0005", 0 },
+	{ "", 0 },
+};
+
+MODULE_DEVICE_TABLE(acpi, ptp_vmw_acpi_device_ids);
+
+static struct platform_driver ptp_vmw_acpi_driver = {
+	.probe = ptp_vmw_acpi_probe,
+	.remove = ptp_vmw_acpi_remove,
+	.driver = {
+		.name = "ptp_vmw_acpi",
+		.acpi_match_table = ptp_vmw_acpi_device_ids,
+	},
+};
+
+static int __init ptp_vmw_init(void)
+{
+	if (x86_hyper_type != X86_HYPER_VMWARE)
+		return -1;
+	return platform_driver_register(&ptp_vmw_acpi_driver);
+}
+
+static void __exit ptp_vmw_exit(void)
+{
+	platform_driver_unregister(&ptp_vmw_acpi_driver);
+}
+
+module_init(ptp_vmw_init);
+module_exit(ptp_vmw_exit);
+
+MODULE_DESCRIPTION("VMware virtual PTP clock driver");
+MODULE_AUTHOR("VMware, Inc.");
+MODULE_LICENSE("Dual BSD/GPL");