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, 224 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c
new file mode 100644
index 000000000..b4f44999e
--- /dev/null
+++ b/drivers/rtc/rtc-efi.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * rtc-efi: RTC Class Driver for EFI-based systems
+ *
+ * Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *
+ * Author: dann frazier <dannf@dannf.org>
+ * Based on efirtc.c by Stephane Eranian
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stringify.h>
+#include <linux/time.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+#include <linux/efi.h>
+
+#define EFI_ISDST (EFI_TIME_ADJUST_DAYLIGHT|EFI_TIME_IN_DAYLIGHT)
+
+/*
+ * returns day of the year [0-365]
+ */
+static inline int
+compute_yday(efi_time_t *eft)
+{
+	/* efi_time_t.month is in the [1-12] so, we need -1 */
+	return rtc_year_days(eft->day, eft->month - 1, eft->year);
+}
+
+/*
+ * returns day of the week [0-6] 0=Sunday
+ */
+static int
+compute_wday(efi_time_t *eft, int yday)
+{
+	int ndays = eft->year * (365 % 7)
+		    + (eft->year - 1) / 4
+		    - (eft->year - 1) / 100
+		    + (eft->year - 1) / 400
+		    + yday;
+
+	/*
+	 * 1/1/0000 may or may not have been a Sunday (if it ever existed at
+	 * all) but assuming it was makes this calculation work correctly.
+	 */
+	return ndays % 7;
+}
+
+static void
+convert_to_efi_time(struct rtc_time *wtime, efi_time_t *eft)
+{
+	eft->year	= wtime->tm_year + 1900;
+	eft->month	= wtime->tm_mon + 1;
+	eft->day	= wtime->tm_mday;
+	eft->hour	= wtime->tm_hour;
+	eft->minute	= wtime->tm_min;
+	eft->second	= wtime->tm_sec;
+	eft->nanosecond = 0;
+	eft->daylight	= wtime->tm_isdst ? EFI_ISDST : 0;
+	eft->timezone	= EFI_UNSPECIFIED_TIMEZONE;
+}
+
+static bool
+convert_from_efi_time(efi_time_t *eft, struct rtc_time *wtime)
+{
+	memset(wtime, 0, sizeof(*wtime));
+
+	if (eft->second >= 60)
+		return false;
+	wtime->tm_sec  = eft->second;
+
+	if (eft->minute >= 60)
+		return false;
+	wtime->tm_min  = eft->minute;
+
+	if (eft->hour >= 24)
+		return false;
+	wtime->tm_hour = eft->hour;
+
+	if (!eft->day || eft->day > 31)
+		return false;
+	wtime->tm_mday = eft->day;
+
+	if (!eft->month || eft->month > 12)
+		return false;
+	wtime->tm_mon  = eft->month - 1;
+
+	if (eft->year < 1900 || eft->year > 9999)
+		return false;
+	wtime->tm_year = eft->year - 1900;
+
+	/* day in the year [1-365]*/
+	wtime->tm_yday = compute_yday(eft);
+
+	/* day of the week [0-6], Sunday=0 */
+	wtime->tm_wday = compute_wday(eft, wtime->tm_yday);
+
+	switch (eft->daylight & EFI_ISDST) {
+	case EFI_ISDST:
+		wtime->tm_isdst = 1;
+		break;
+	case EFI_TIME_ADJUST_DAYLIGHT:
+		wtime->tm_isdst = 0;
+		break;
+	default:
+		wtime->tm_isdst = -1;
+	}
+
+	return true;
+}
+
+static int efi_read_time(struct device *dev, struct rtc_time *tm)
+{
+	efi_status_t status;
+	efi_time_t eft;
+	efi_time_cap_t cap;
+
+	status = efi.get_time(&eft, &cap);
+
+	if (status != EFI_SUCCESS) {
+		/* should never happen */
+		dev_err_once(dev, "can't read time\n");
+		return -EINVAL;
+	}
+
+	if (!convert_from_efi_time(&eft, tm))
+		return -EIO;
+
+	return 0;
+}
+
+static int efi_set_time(struct device *dev, struct rtc_time *tm)
+{
+	efi_status_t status;
+	efi_time_t eft;
+
+	convert_to_efi_time(tm, &eft);
+
+	status = efi.set_time(&eft);
+
+	return status == EFI_SUCCESS ? 0 : -EINVAL;
+}
+
+static int efi_procfs(struct device *dev, struct seq_file *seq)
+{
+	efi_time_t        eft;
+	efi_time_cap_t    cap;
+
+	memset(&eft, 0, sizeof(eft));
+	memset(&cap, 0, sizeof(cap));
+
+	efi.get_time(&eft, &cap);
+
+	seq_printf(seq,
+		   "Time\t\t: %u:%u:%u.%09u\n"
+		   "Date\t\t: %u-%u-%u\n"
+		   "Daylight\t: %u\n",
+		   eft.hour, eft.minute, eft.second, eft.nanosecond,
+		   eft.year, eft.month, eft.day,
+		   eft.daylight);
+
+	if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE)
+		seq_puts(seq, "Timezone\t: unspecified\n");
+	else
+		/* XXX fixme: convert to string? */
+		seq_printf(seq, "Timezone\t: %u\n", eft.timezone);
+
+	/*
+	 * now prints the capabilities
+	 */
+	seq_printf(seq,
+		   "Resolution\t: %u\n"
+		   "Accuracy\t: %u\n"
+		   "SetstoZero\t: %u\n",
+		   cap.resolution, cap.accuracy, cap.sets_to_zero);
+
+	return 0;
+}
+
+static const struct rtc_class_ops efi_rtc_ops = {
+	.read_time	= efi_read_time,
+	.set_time	= efi_set_time,
+	.proc		= efi_procfs,
+};
+
+static int __init efi_rtc_probe(struct platform_device *dev)
+{
+	struct rtc_device *rtc;
+	efi_time_t eft;
+	efi_time_cap_t cap;
+
+	/* First check if the RTC is usable */
+	if (efi.get_time(&eft, &cap) != EFI_SUCCESS)
+		return -ENODEV;
+
+	rtc = devm_rtc_allocate_device(&dev->dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	platform_set_drvdata(dev, rtc);
+
+	rtc->ops = &efi_rtc_ops;
+	clear_bit(RTC_FEATURE_ALARM, rtc->features);
+
+	device_init_wakeup(&dev->dev, true);
+
+	return devm_rtc_register_device(rtc);
+}
+
+static struct platform_driver efi_rtc_driver = {
+	.driver = {
+		.name = "rtc-efi",
+	},
+};
+
+module_platform_driver_probe(efi_rtc_driver, efi_rtc_probe);
+
+MODULE_AUTHOR("dann frazier <dannf@dannf.org>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("EFI RTC driver");
+MODULE_ALIAS("platform:rtc-efi");