This patch implements the machine class kvm_type() callback.
It returns the number of bits requested to implement the whole GPA
range including the RAM and IO regions located beyond.
The returned value in passed though the KVM_CREATE_VM ioctl and
this allows KVM to set the stage2 tables dynamically.

To compute the highest GPA used in the memory map, kvm_type()
must freeze the memory map by calling virt_set_memmap().

Signed-off-by: Eric Auger <eric.auger@redhat.com>

---
v7 -> v8:
- remove vmc->no_extended_memmap and vms->extended_memmap

v6 -> v7:
- Introduce RAMBASE and rename add LEGACY_ prefix in that patch
- use local variables with explicit names in virt_set_memmap:
  device_memory_base, device_memory_size
- add an extended_memmap field in the class

v5 -> v6:
- add some comments
- high IO region cannot start before 256GiB
---
 hw/arm/virt.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index d7aa7d3f9d..7a158571b7 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -1439,7 +1439,13 @@ static void machvirt_init(MachineState *machine)
     bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
     bool aarch64 = true;
 
-    virt_set_memmap(vms);
+    /*
+     * In accelerated mode, the memory map is computed in kvm_type()
+     * to create a VM with the right number of IPA bits.
+     */
+    if (!kvm_enabled()) {
+        virt_set_memmap(vms);
+    }
 
     /* We can probe only here because during property set
      * KVM is not available yet
@@ -1828,6 +1834,36 @@ static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine,
     return NULL;
 }
 
+/*
+ * for arm64 kvm_type [7-0] encodes the requested number of bits
+ * in the IPA address space
+ */
+static int virt_kvm_type(MachineState *ms, const char *type_str)
+{
+    VirtMachineState *vms = VIRT_MACHINE(ms);
+    int max_vm_pa_size = kvm_arm_get_max_vm_ipa_size(ms);
+    int requested_pa_size;
+
+    /* we freeze the memory map to compute the highest gpa */
+    virt_set_memmap(vms);
+
+    requested_pa_size = 64 - clz64(vms->highest_gpa);
+
+    if (requested_pa_size > max_vm_pa_size) {
+        error_report("-m and ,maxmem option values "
+                     "require an IPA range (%d bits) larger than "
+                     "the one supported by the host (%d bits)",
+                     requested_pa_size, max_vm_pa_size);
+       exit(1);
+    }
+    /*
+     * By default we return 0 which corresponds to an implicit legacy
+     * 40b IPA setting. Otherwise we return the actual requested PA
+     * logsize
+     */
+    return requested_pa_size > 40 ? requested_pa_size : 0;
+}
+
 static void virt_machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
@@ -1852,6 +1888,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
     mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a15");
     mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
+    mc->kvm_type = virt_kvm_type;
     assert(!mc->get_hotplug_handler);
     mc->get_hotplug_handler = virt_machine_get_hotplug_handler;
     hc->plug = virt_machine_device_plug_cb;
-- 
2.20.1

On Thu, 28 Feb 2019 16:03:22 +0100
Eric Auger <eric.auger@redhat.com> wrote:

> This patch implements the machine class kvm_type() callback.
> It returns the number of bits requested to implement the whole GPA
> range including the RAM and IO regions located beyond.
> The returned value in passed though the KVM_CREATE_VM ioctl and
> this allows KVM to set the stage2 tables dynamically.
> 
> To compute the highest GPA used in the memory map, kvm_type()
> must freeze the memory map by calling virt_set_memmap().
> 
> Signed-off-by: Eric Auger <eric.auger@redhat.com>
> 
> ---
> v7 -> v8:
> - remove vmc->no_extended_memmap and vms->extended_memmap
> 
> v6 -> v7:
> - Introduce RAMBASE and rename add LEGACY_ prefix in that patch
> - use local variables with explicit names in virt_set_memmap:
>   device_memory_base, device_memory_size
> - add an extended_memmap field in the class
> 
> v5 -> v6:
> - add some comments
> - high IO region cannot start before 256GiB
> ---
>  hw/arm/virt.c | 39 ++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 38 insertions(+), 1 deletion(-)
> 
> diff --git a/hw/arm/virt.c b/hw/arm/virt.c
> index d7aa7d3f9d..7a158571b7 100644
> --- a/hw/arm/virt.c
> +++ b/hw/arm/virt.c
> @@ -1439,7 +1439,13 @@ static void machvirt_init(MachineState *machine)
>      bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
>      bool aarch64 = true;
>  
> -    virt_set_memmap(vms);
> +    /*
> +     * In accelerated mode, the memory map is computed in kvm_type()
s/in/earlier in/

> +     * to create a VM with the right number of IPA bits.
> +     */
> +    if (!kvm_enabled()) {
maybe check not for KVM but for vms->memmap == NULL
so it would match with comment and be clear that we initializing memmap
because nobody else did it yet.

> +        virt_set_memmap(vms);
> +    }
>  
>      /* We can probe only here because during property set
>       * KVM is not available yet
> @@ -1828,6 +1834,36 @@ static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine,
>      return NULL;
>  }
>  
> +/*
> + * for arm64 kvm_type [7-0] encodes the requested number of bits
> + * in the IPA address space
> + */
> +static int virt_kvm_type(MachineState *ms, const char *type_str)
> +{
> +    VirtMachineState *vms = VIRT_MACHINE(ms);
> +    int max_vm_pa_size = kvm_arm_get_max_vm_ipa_size(ms);
> +    int requested_pa_size;
> +
> +    /* we freeze the memory map to compute the highest gpa */
> +    virt_set_memmap(vms);
> +

> +    requested_pa_size = 64 - clz64(vms->highest_gpa);
> +
> +    if (requested_pa_size > max_vm_pa_size) {
> +        error_report("-m and ,maxmem option values "
> +                     "require an IPA range (%d bits) larger than "
> +                     "the one supported by the host (%d bits)",
> +                     requested_pa_size, max_vm_pa_size);
> +       exit(1);
> +    }
this part is recurring pattern, is it worth using a helper function?

> +    /*
> +     * By default we return 0 which corresponds to an implicit legacy
> +     * 40b IPA setting. Otherwise we return the actual requested PA
> +     * logsize
> +     */
> +    return requested_pa_size > 40 ? requested_pa_size : 0;
> +}
> +
>  static void virt_machine_class_init(ObjectClass *oc, void *data)
>  {
>      MachineClass *mc = MACHINE_CLASS(oc);
> @@ -1852,6 +1888,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
>      mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
>      mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a15");
>      mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
> +    mc->kvm_type = virt_kvm_type;
>      assert(!mc->get_hotplug_handler);
>      mc->get_hotplug_handler = virt_machine_get_hotplug_handler;
>      hc->plug = virt_machine_device_plug_cb;

Hi Igor,

On 2/28/19 5:19 PM, Igor Mammedov wrote:
> On Thu, 28 Feb 2019 16:03:22 +0100
> Eric Auger <eric.auger@redhat.com> wrote:
> 
>> This patch implements the machine class kvm_type() callback.
>> It returns the number of bits requested to implement the whole GPA
>> range including the RAM and IO regions located beyond.
>> The returned value in passed though the KVM_CREATE_VM ioctl and
>> this allows KVM to set the stage2 tables dynamically.
>>
>> To compute the highest GPA used in the memory map, kvm_type()
>> must freeze the memory map by calling virt_set_memmap().
>>
>> Signed-off-by: Eric Auger <eric.auger@redhat.com>
>>
>> ---
>> v7 -> v8:
>> - remove vmc->no_extended_memmap and vms->extended_memmap
>>
>> v6 -> v7:
>> - Introduce RAMBASE and rename add LEGACY_ prefix in that patch
>> - use local variables with explicit names in virt_set_memmap:
>>   device_memory_base, device_memory_size
>> - add an extended_memmap field in the class
>>
>> v5 -> v6:
>> - add some comments
>> - high IO region cannot start before 256GiB
>> ---
>>  hw/arm/virt.c | 39 ++++++++++++++++++++++++++++++++++++++-
>>  1 file changed, 38 insertions(+), 1 deletion(-)
>>
>> diff --git a/hw/arm/virt.c b/hw/arm/virt.c
>> index d7aa7d3f9d..7a158571b7 100644
>> --- a/hw/arm/virt.c
>> +++ b/hw/arm/virt.c
>> @@ -1439,7 +1439,13 @@ static void machvirt_init(MachineState *machine)
>>      bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
>>      bool aarch64 = true;
>>  
>> -    virt_set_memmap(vms);
>> +    /*
>> +     * In accelerated mode, the memory map is computed in kvm_type()
> s/in/earlier in/
> 
>> +     * to create a VM with the right number of IPA bits.
>> +     */
>> +    if (!kvm_enabled()) {
> maybe check not for KVM but for vms->memmap == NULL
> so it would match with comment and be clear that we initializing memmap
> because nobody else did it yet.
> 
>> +        virt_set_memmap(vms);
>> +    }
>>  
>>      /* We can probe only here because during property set
>>       * KVM is not available yet
>> @@ -1828,6 +1834,36 @@ static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine,
>>      return NULL;
>>  }
>>  
>> +/*
>> + * for arm64 kvm_type [7-0] encodes the requested number of bits
>> + * in the IPA address space
>> + */
>> +static int virt_kvm_type(MachineState *ms, const char *type_str)
>> +{
>> +    VirtMachineState *vms = VIRT_MACHINE(ms);
>> +    int max_vm_pa_size = kvm_arm_get_max_vm_ipa_size(ms);
>> +    int requested_pa_size;
>> +
>> +    /* we freeze the memory map to compute the highest gpa */
>> +    virt_set_memmap(vms);
>> +
> 
>> +    requested_pa_size = 64 - clz64(vms->highest_gpa);
>> +
>> +    if (requested_pa_size > max_vm_pa_size) {
>> +        error_report("-m and ,maxmem option values "
>> +                     "require an IPA range (%d bits) larger than "
>> +                     "the one supported by the host (%d bits)",
>> +                     requested_pa_size, max_vm_pa_size);
>> +       exit(1);
>> +    }
> this part is recurring pattern, is it worth using a helper function?
in TCG mode the message is different because this issue stems from the
fact the VCPU does not support a large enough PA range whereas here the
host kernel does not support large enough IPA. So I tend to keep the
code as is.

Thanks

Eric
> 
>> +    /*
>> +     * By default we return 0 which corresponds to an implicit legacy
>> +     * 40b IPA setting. Otherwise we return the actual requested PA
>> +     * logsize
>> +     */
>> +    return requested_pa_size > 40 ? requested_pa_size : 0;
>> +}
>> +
>>  static void virt_machine_class_init(ObjectClass *oc, void *data)
>>  {
>>      MachineClass *mc = MACHINE_CLASS(oc);
>> @@ -1852,6 +1888,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
>>      mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
>>      mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a15");
>>      mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
>> +    mc->kvm_type = virt_kvm_type;
>>      assert(!mc->get_hotplug_handler);
>>      mc->get_hotplug_handler = virt_machine_get_hotplug_handler;
>>      hc->plug = virt_machine_device_plug_cb;
>