[PATCH 3/6] x86/hyperv: Skip LP/VP creation on kexec

Jork Loeser posted 6 patches 5 days, 17 hours ago
[PATCH 3/6] x86/hyperv: Skip LP/VP creation on kexec
Posted by Jork Loeser 5 days, 17 hours ago
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.kinsburski@gmail.com>
Signed-off-by: Stanislav Kinsburskii <stanislav.kinsburski@gmail.com>
Co-developed-by: Mukesh Rathor <mukeshrathor@microsoft.com>
Signed-off-by: Mukesh Rathor <mukeshrathor@microsoft.com>
Signed-off-by: Jork Loeser <jloeser@linux.microsoft.com>
---
 arch/x86/kernel/cpu/mshyperv.c |  7 +++++
 drivers/hv/hv_proc.c           | 47 ++++++++++++++++++++++++++++++++++
 include/asm-generic/mshyperv.h | 10 ++++++++
 include/hyperv/hvgdk_mini.h    |  1 +
 include/hyperv/hvhdk_mini.h    | 12 +++++++++
 5 files changed, 77 insertions(+)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 235087456bdf..f653feea880b 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -429,6 +429,10 @@ 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;
@@ -436,6 +440,9 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
 		BUG_ON(ret);
 	}
 
+	ret = hv_call_notify_all_processors_started();
+	WARN_ON(ret);
+
 	for_each_present_cpu(i) {
 		if (i == 0)
 			continue;
diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
index 5f4fd9c3231c..63a48e5a02c5 100644
--- a/drivers/hv/hv_proc.c
+++ b/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);
+}
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index d37b68238c97..bf601d67cecb 100644
--- a/include/asm-generic/mshyperv.h
+++ b/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;
diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 056ef7b6b360..f2598e186550 100644
--- a/include/hyperv/hvgdk_mini.h
+++ b/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
diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
index 091c03e26046..b4cb2fa26e9b 100644
--- a/include/hyperv/hvhdk_mini.h
+++ b/include/hyperv/hvhdk_mini.h
@@ -362,6 +362,7 @@ 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 {
@@ -369,6 +370,17 @@ struct hv_input_notify_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;
-- 
2.43.0
Re: [PATCH 3/6] x86/hyperv: Skip LP/VP creation on kexec
Posted by Stanislav Kinsburskii 2 days, 16 hours ago
On Fri, Mar 27, 2026 at 01:19:14PM -0700, Jork Loeser wrote:
> 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.kinsburski@gmail.com>
> Signed-off-by: Stanislav Kinsburskii <stanislav.kinsburski@gmail.com>
> Co-developed-by: Mukesh Rathor <mukeshrathor@microsoft.com>
> Signed-off-by: Mukesh Rathor <mukeshrathor@microsoft.com>
> Signed-off-by: Jork Loeser <jloeser@linux.microsoft.com>
> ---
>  arch/x86/kernel/cpu/mshyperv.c |  7 +++++
>  drivers/hv/hv_proc.c           | 47 ++++++++++++++++++++++++++++++++++
>  include/asm-generic/mshyperv.h | 10 ++++++++
>  include/hyperv/hvgdk_mini.h    |  1 +
>  include/hyperv/hvhdk_mini.h    | 12 +++++++++
>  5 files changed, 77 insertions(+)
> 
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index 235087456bdf..f653feea880b 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -429,6 +429,10 @@ 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;
> @@ -436,6 +440,9 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
>  		BUG_ON(ret);
>  	}
>  
> +	ret = hv_call_notify_all_processors_started();
> +	WARN_ON(ret);
> +
>  	for_each_present_cpu(i) {
>  		if (i == 0)
>  			continue;
> diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
> index 5f4fd9c3231c..63a48e5a02c5 100644
> --- a/drivers/hv/hv_proc.c
> +++ b/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);

nit: hv_do_fast_hypercall8 should do here as this would simplify the
code.

Reviewed-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>

> +	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);
> +}
> diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
> index d37b68238c97..bf601d67cecb 100644
> --- a/include/asm-generic/mshyperv.h
> +++ b/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;
> diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
> index 056ef7b6b360..f2598e186550 100644
> --- a/include/hyperv/hvgdk_mini.h
> +++ b/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
> diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
> index 091c03e26046..b4cb2fa26e9b 100644
> --- a/include/hyperv/hvhdk_mini.h
> +++ b/include/hyperv/hvhdk_mini.h
> @@ -362,6 +362,7 @@ 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 {
> @@ -369,6 +370,17 @@ struct hv_input_notify_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;
> -- 
> 2.43.0
>