x86/hyperv: Skip LP/VP creation on kexec

After a kexec the logical processors and virtual processors already
exist in the hypervisor because they were created by the previous
kernel. Attempting to add them again causes either a BUG_ON or
corrupted VP state leading to MCEs in the new kernel.

Add hv_lp_exists() to probe whether an LP is already present by
calling HVCALL_GET_LOGICAL_PROCESSOR_RUN_TIME. When it succeeds the
LP exists and we skip the add-LP and create-VP loops entirely.

Also add hv_call_notify_all_processors_started() which informs the
hypervisor that all processors are online. This is required after
adding LPs (fresh boot) and is a no-op on kexec since we skip that
path.

Co-developed-by: Anirudh Rayabharam <anrayabh@linux.microsoft.com>
Signed-off-by: Anirudh Rayabharam <anrayabh@linux.microsoft.com>
Co-developed-by: Stanislav Kinsburskii <stanislav.kinsburskii@gmail.com>
Signed-off-by: Stanislav Kinsburskii <stanislav.kinsburskii@gmail.com>
Co-developed-by: Mukesh Rathor <mrathor@linux.microsoft.com>
Signed-off-by: Mukesh Rathor <mrathor@linux.microsoft.com>
Signed-off-by: Jork Loeser <jloeser@linux.microsoft.com>
Reviewed-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>

Author: Jork Loeser

arch/x86/kernel/cpu/mshyperv.c

@@ -429,13 +429,20 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 #ifdef CONFIG_X86_64
+	/* If AP LPs exist, we are in a kexec'd kernel and VPs already exist */
+	if (num_present_cpus() == 1 || hv_lp_exists(1))
+		return;
+
 	for_each_present_cpu(i) {
 		if (i == 0)
 			continue;
 		ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
 		BUG_ON(ret);
 	}
 
+	ret = hv_call_notify_all_processors_started();
+	WARN_ON(ret);
+
 	for_each_present_cpu(i) {
 		if (i == 0)
 			continue;

drivers/hv/hv_proc.c

@@ -239,3 +239,50 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hv_call_create_vp);
+
+int hv_call_notify_all_processors_started(void)
+{
+	struct hv_input_notify_partition_event *input;
+	u64 status;
+	unsigned long irq_flags;
+	int ret = 0;
+
+	local_irq_save(irq_flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	memset(input, 0, sizeof(*input));
+	input->event = HV_PARTITION_ALL_LOGICAL_PROCESSORS_STARTED;
+	status = hv_do_hypercall(HVCALL_NOTIFY_PARTITION_EVENT,
+				 input, NULL);
+	local_irq_restore(irq_flags);
+
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		ret = hv_result_to_errno(status);
+	}
+	return ret;
+}
+
+bool hv_lp_exists(u32 lp_index)
+{
+	struct hv_input_get_logical_processor_run_time *input;
+	struct hv_output_get_logical_processor_run_time *output;
+	unsigned long flags;
+	u64 status;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	input->lp_index = lp_index;
+	status = hv_do_hypercall(HVCALL_GET_LOGICAL_PROCESSOR_RUN_TIME,
+				 input, output);
+	local_irq_restore(flags);
+
+	if (!hv_result_success(status) &&
+	    hv_result(status) != HV_STATUS_INVALID_LP_INDEX) {
+		hv_status_err(status, "\n");
+		BUG();
+	}
+
+	return hv_result_success(status);
+}

include/asm-generic/mshyperv.h

@@ -347,6 +347,8 @@ bool hv_result_needs_memory(u64 status);
 int hv_deposit_memory_node(int node, u64 partition_id, u64 status);
 int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
 int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
+int hv_call_notify_all_processors_started(void);
+bool hv_lp_exists(u32 lp_index);
 int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
 
 #else /* CONFIG_MSHV_ROOT */
@@ -366,6 +368,14 @@ static inline int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id)
 {
 	return -EOPNOTSUPP;
 }
+static inline int hv_call_notify_all_processors_started(void)
+{
+	return -EOPNOTSUPP;
+}
+static inline bool hv_lp_exists(u32 lp_index)
+{
+	return false;
+}
 static inline int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 {
 	return -EOPNOTSUPP;

include/hyperv/hvgdk_mini.h

@@ -435,6 +435,7 @@ union hv_vp_assist_msr_contents {	 /* HV_REGISTER_VP_ASSIST_PAGE */
 /* HV_CALL_CODE */
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE		0x0002
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST		0x0003
+#define HVCALL_GET_LOGICAL_PROCESSOR_RUN_TIME		0x0004
 #define HVCALL_NOTIFY_LONG_SPIN_WAIT			0x0008
 #define HVCALL_SEND_IPI					0x000b
 #define HVCALL_ENABLE_VP_VTL				0x000f

include/hyperv/hvhdk_mini.h

@@ -362,13 +362,25 @@ union hv_partition_event_input {
 
 enum hv_partition_event {
 	HV_PARTITION_EVENT_ROOT_CRASHDUMP = 2,
+	HV_PARTITION_ALL_LOGICAL_PROCESSORS_STARTED = 4,
 };
 
 struct hv_input_notify_partition_event {
 	u32 event;      /* enum hv_partition_event */
 	union hv_partition_event_input input;
 } __packed;
 
+struct hv_input_get_logical_processor_run_time {
+	u32 lp_index;
+} __packed;
+
+struct hv_output_get_logical_processor_run_time {
+	u64 global_time;
+	u64 local_run_time;
+	u64 rsvdz0;
+	u64 hypervisor_time;
+} __packed;
+
 struct hv_lp_startup_status {
 	u64 hv_status;
 	u64 substatus1;