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, 136 insertions, 0 deletions

diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
new file mode 100644
index 000000000..4fdc26ade
--- /dev/null
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Core routines for interacting with Microsoft's Hyper-V hypervisor,
+ * including hypervisor initialization.
+ *
+ * Copyright (C) 2021, Microsoft, Inc.
+ *
+ * Author : Michael Kelley <mikelley@microsoft.com>
+ */
+
+#include <linux/types.h>
+#include <linux/acpi.h>
+#include <linux/export.h>
+#include <linux/errno.h>
+#include <linux/version.h>
+#include <linux/cpuhotplug.h>
+#include <asm/mshyperv.h>
+
+static bool hyperv_initialized;
+
+int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
+{
+	hv_get_vpreg_128(HV_REGISTER_HYPERVISOR_VERSION,
+			 (struct hv_get_vp_registers_output *)info);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
+
+#ifdef CONFIG_ACPI
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	if (acpi_disabled)
+		return false;
+	/*
+	 * Hypervisor ID is only available in ACPI v6+, and the
+	 * structure layout was extended in v6 to accommodate that
+	 * new field.
+	 *
+	 * At the very minimum, this check makes sure not to read
+	 * past the FADT structure.
+	 *
+	 * It is also needed to catch running in some unknown
+	 * non-Hyper-V environment that has ACPI 5.x or less.
+	 * In such a case, it can't be Hyper-V.
+	 */
+	if (acpi_gbl_FADT.header.revision < 6)
+		return false;
+	return strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8) == 0;
+}
+
+#else
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+	return false;
+}
+
+#endif
+
+static bool __init hyperv_detect_via_smccc(void)
+{
+	uuid_t hyperv_uuid = UUID_INIT(
+		0x58ba324d, 0x6447, 0x24cd,
+		0x75, 0x6c, 0xef, 0x8e,
+		0x24, 0x70, 0x59, 0x16);
+
+	return arm_smccc_hypervisor_has_uuid(&hyperv_uuid);
+}
+
+static int __init hyperv_init(void)
+{
+	struct hv_get_vp_registers_output	result;
+	u64	guest_id;
+	int	ret;
+
+	/*
+	 * Allow for a kernel built with CONFIG_HYPERV to be running in
+	 * a non-Hyper-V environment.
+	 *
+	 * In such cases, do nothing and return success.
+	 */
+	if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
+		return 0;
+
+	/* Setup the guest ID */
+	guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
+	hv_set_vpreg(HV_REGISTER_GUEST_OS_ID, guest_id);
+
+	/* Get the features and hints from Hyper-V */
+	hv_get_vpreg_128(HV_REGISTER_PRIVILEGES_AND_FEATURES_INFO, &result);
+	ms_hyperv.features = result.as32.a;
+	ms_hyperv.priv_high = result.as32.b;
+	ms_hyperv.misc_features = result.as32.c;
+
+	hv_get_vpreg_128(HV_REGISTER_FEATURES_INFO, &result);
+	ms_hyperv.hints = result.as32.a;
+
+	pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints,
+		ms_hyperv.misc_features);
+
+	hv_identify_partition_type();
+
+	ret = hv_common_init();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "arm64/hyperv_init:online",
+				hv_common_cpu_init, hv_common_cpu_die);
+	if (ret < 0) {
+		hv_common_free();
+		return ret;
+	}
+
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
+		hv_get_partition_id();
+	ms_hyperv.vtl = get_vtl();
+	if (ms_hyperv.vtl > 0) /* non default VTL */
+		pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
+
+	ms_hyperv_late_init();
+
+	hyperv_initialized = true;
+	return 0;
+}
+
+early_initcall(hyperv_init);
+
+bool hv_is_hyperv_initialized(void)
+{
+	return hyperv_initialized;
+}
+EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);