From: Isaku Yamahata <isaku.yamahata@intel.com>
Wire KVM_MAP_MEMORY ioctl to kvm_mmu_map_tdp_page() to populate guest
memory. When KVM_CREATE_VCPU creates vCPU, it initializes the x86
KVM MMU part by kvm_mmu_create() and kvm_init_mmu(). vCPU is ready to
invoke the KVM page fault handler.
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
v2:
- Catch up the change of struct kvm_memory_mapping. (Sean)
- Removed mapping level check. Push it down into vendor code. (David, Sean)
- Rename goal_level to level. (Sean)
- Drop kvm_arch_pre_vcpu_map_memory(), directly call kvm_mmu_reload().
(David, Sean)
- Fixed the update of mapping.
---
arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2d2619d3eee4..2c765de3531e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4713,6 +4713,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
case KVM_CAP_IRQFD_RESAMPLE:
case KVM_CAP_MEMORY_FAULT_INFO:
+ case KVM_CAP_MAP_MEMORY:
r = 1;
break;
case KVM_CAP_EXIT_HYPERCALL:
@@ -5867,6 +5868,35 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
}
}
+int kvm_arch_vcpu_map_memory(struct kvm_vcpu *vcpu,
+ struct kvm_memory_mapping *mapping)
+{
+ u64 end, error_code = 0;
+ u8 level = PG_LEVEL_4K;
+ int r;
+
+ /*
+ * Shadow paging uses GVA for kvm page fault. The first implementation
+ * supports GPA only to avoid confusion.
+ */
+ if (!tdp_enabled)
+ return -EOPNOTSUPP;
+
+ /* reload is optimized for repeated call. */
+ kvm_mmu_reload(vcpu);
+
+ r = kvm_tdp_map_page(vcpu, mapping->base_address, error_code, &level);
+ if (r)
+ return r;
+
+ /* mapping->base_address is not necessarily aligned to level-hugepage. */
+ end = (mapping->base_address & KVM_HPAGE_MASK(level)) +
+ KVM_HPAGE_SIZE(level);
+ mapping->size -= end - mapping->base_address;
+ mapping->base_address = end;
+ return r;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
--
2.43.2On Thu, Apr 11, 2024 at 12:08 AM <isaku.yamahata@intel.com> wrote:
>
> From: Isaku Yamahata <isaku.yamahata@intel.com>
>
> Wire KVM_MAP_MEMORY ioctl to kvm_mmu_map_tdp_page() to populate guest
> memory. When KVM_CREATE_VCPU creates vCPU, it initializes the x86
> KVM MMU part by kvm_mmu_create() and kvm_init_mmu(). vCPU is ready to
> invoke the KVM page fault handler.
>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> ---
> v2:
> - Catch up the change of struct kvm_memory_mapping. (Sean)
> - Removed mapping level check. Push it down into vendor code. (David, Sean)
> - Rename goal_level to level. (Sean)
> - Drop kvm_arch_pre_vcpu_map_memory(), directly call kvm_mmu_reload().
> (David, Sean)
> - Fixed the update of mapping.
> ---
> arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++++++++++
> 1 file changed, 30 insertions(+)
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 2d2619d3eee4..2c765de3531e 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4713,6 +4713,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
> case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
> case KVM_CAP_IRQFD_RESAMPLE:
> case KVM_CAP_MEMORY_FAULT_INFO:
> + case KVM_CAP_MAP_MEMORY:
> r = 1;
> break;
> case KVM_CAP_EXIT_HYPERCALL:
> @@ -5867,6 +5868,35 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
> }
> }
>
> +int kvm_arch_vcpu_map_memory(struct kvm_vcpu *vcpu,
> + struct kvm_memory_mapping *mapping)
> +{
> + u64 end, error_code = 0;
> + u8 level = PG_LEVEL_4K;
> + int r;
> +
> + /*
> + * Shadow paging uses GVA for kvm page fault. The first implementation
> + * supports GPA only to avoid confusion.
> + */
> + if (!tdp_enabled)
> + return -EOPNOTSUPP;
> +
> + /* reload is optimized for repeated call. */
> + kvm_mmu_reload(vcpu);
> +
> + r = kvm_tdp_map_page(vcpu, mapping->base_address, error_code, &level);
> + if (r)
> + return r;
> +
> + /* mapping->base_address is not necessarily aligned to level-hugepage. */
/*
* level can be more than the alignment of mapping->base_address if
* the mapping can use a huge page.
*/
> + end = (mapping->base_address & KVM_HPAGE_MASK(level)) +
> + KVM_HPAGE_SIZE(level);
> + mapping->size -= end - mapping->base_address;
> + mapping->base_address = end;
Slightly safer in the case where level is more than the alignment of
mapping->base_address:
mapped = min(mapping->size, end - mapping->base_address);
mapping->size -= mapped;
mapping->base_address += mapped;
Paolo
> + return r;
> +}
> +
> long kvm_arch_vcpu_ioctl(struct file *filp,
> unsigned int ioctl, unsigned long arg)
> {
> --
> 2.43.2
>
On Wed, Apr 10, 2024 at 03:07:32PM -0700, isaku.yamahata@intel.com wrote:
>From: Isaku Yamahata <isaku.yamahata@intel.com>
>
>Wire KVM_MAP_MEMORY ioctl to kvm_mmu_map_tdp_page() to populate guest
>memory. When KVM_CREATE_VCPU creates vCPU, it initializes the x86
>KVM MMU part by kvm_mmu_create() and kvm_init_mmu(). vCPU is ready to
>invoke the KVM page fault handler.
>
>Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
>---
>v2:
>- Catch up the change of struct kvm_memory_mapping. (Sean)
>- Removed mapping level check. Push it down into vendor code. (David, Sean)
>- Rename goal_level to level. (Sean)
>- Drop kvm_arch_pre_vcpu_map_memory(), directly call kvm_mmu_reload().
> (David, Sean)
>- Fixed the update of mapping.
>---
> arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++++++++++
> 1 file changed, 30 insertions(+)
>
>diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>index 2d2619d3eee4..2c765de3531e 100644
>--- a/arch/x86/kvm/x86.c
>+++ b/arch/x86/kvm/x86.c
>@@ -4713,6 +4713,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
> case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
> case KVM_CAP_IRQFD_RESAMPLE:
> case KVM_CAP_MEMORY_FAULT_INFO:
>+ case KVM_CAP_MAP_MEMORY:
> r = 1;
> break;
> case KVM_CAP_EXIT_HYPERCALL:
>@@ -5867,6 +5868,35 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
> }
> }
>
>+int kvm_arch_vcpu_map_memory(struct kvm_vcpu *vcpu,
>+ struct kvm_memory_mapping *mapping)
>+{
>+ u64 end, error_code = 0;
>+ u8 level = PG_LEVEL_4K;
IIUC, no need to initialize @level here.
>+ int r;
>+
>+ /*
>+ * Shadow paging uses GVA for kvm page fault. The first implementation
>+ * supports GPA only to avoid confusion.
>+ */
>+ if (!tdp_enabled)
>+ return -EOPNOTSUPP;
This check duplicates the one for vcpu->arch.mmu->page_fault() in patch 5.
>+
>+ /* reload is optimized for repeated call. */
>+ kvm_mmu_reload(vcpu);
>+
>+ r = kvm_tdp_map_page(vcpu, mapping->base_address, error_code, &level);
>+ if (r)
>+ return r;
>+
>+ /* mapping->base_address is not necessarily aligned to level-hugepage. */
>+ end = (mapping->base_address & KVM_HPAGE_MASK(level)) +
>+ KVM_HPAGE_SIZE(level);
maybe
end = ALIGN(mapping->base_address, KVM_HPAGE_SIZE(level));
>+ mapping->size -= end - mapping->base_address;
>+ mapping->base_address = end;
>+ return r;
>+}
>+
> long kvm_arch_vcpu_ioctl(struct file *filp,
> unsigned int ioctl, unsigned long arg)
> {
>--
>2.43.2
>
>
On Wed, 2024-04-10 at 15:07 -0700, isaku.yamahata@intel.com wrote:
> From: Isaku Yamahata <isaku.yamahata@intel.com>
>
> Wire KVM_MAP_MEMORY ioctl to kvm_mmu_map_tdp_page() to populate guest
> memory. When KVM_CREATE_VCPU creates vCPU, it initializes the x86
> KVM MMU part by kvm_mmu_create() and kvm_init_mmu(). vCPU is ready to
> invoke the KVM page fault handler.
>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> ---
> v2:
> - Catch up the change of struct kvm_memory_mapping. (Sean)
> - Removed mapping level check. Push it down into vendor code. (David, Sean)
> - Rename goal_level to level. (Sean)
> - Drop kvm_arch_pre_vcpu_map_memory(), directly call kvm_mmu_reload().
> (David, Sean)
> - Fixed the update of mapping.
> ---
> arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++++++++++
> 1 file changed, 30 insertions(+)
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 2d2619d3eee4..2c765de3531e 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4713,6 +4713,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long
> ext)
> case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
> case KVM_CAP_IRQFD_RESAMPLE:
> case KVM_CAP_MEMORY_FAULT_INFO:
> + case KVM_CAP_MAP_MEMORY:
> r = 1;
> break;
Should we add this after all of the pieces are in place?
> case KVM_CAP_EXIT_HYPERCALL:
> @@ -5867,6 +5868,35 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu
> *vcpu,
> }
> }
>
> +int kvm_arch_vcpu_map_memory(struct kvm_vcpu *vcpu,
> + struct kvm_memory_mapping *mapping)
> +{
> + u64 end, error_code = 0;
> + u8 level = PG_LEVEL_4K;
> + int r;
> +
> + /*
> + * Shadow paging uses GVA for kvm page fault. The first
> implementation
> + * supports GPA only to avoid confusion.
> + */
> + if (!tdp_enabled)
> + return -EOPNOTSUPP;
It's not confusion, it's that you can't pre-map GPAs for legacy shadow paging.
Or you are saying why not to support pre-mapping GVAs? I think that discussion
belongs more in the commit log. The code should just say it's not possible to
pre-map GPAs in shadow paging.
> +
> + /* reload is optimized for repeated call. */
> + kvm_mmu_reload(vcpu);
> +
> + r = kvm_tdp_map_page(vcpu, mapping->base_address, error_code, &level);
> + if (r)
> + return r;
> +
> + /* mapping->base_address is not necessarily aligned to level-hugepage.
> */
> + end = (mapping->base_address & KVM_HPAGE_MASK(level)) +
> + KVM_HPAGE_SIZE(level);
> + mapping->size -= end - mapping->base_address;
> + mapping->base_address = end;
> + return r;
> +}
> +
> long kvm_arch_vcpu_ioctl(struct file *filp,
> unsigned int ioctl, unsigned long arg)
> {
© 2016 - 2026 Red Hat, Inc.