diff mbox series

[02/21] KVM: Allow page-sized MMU caches to be initialized with custom 64-bit values

Message ID 20240227232100.478238-3-pbonzini@redhat.com
State New
Headers
Series TDX/SNP part 1 of n, for 6.9 |

Commit Message

Paolo Bonzini Feb. 27, 2024, 11:20 p.m. UTC 
  From: Sean Christopherson <seanjc@google.com>

Add support to MMU caches for initializing a page with a custom 64-bit
value, e.g. to pre-fill an entire page table with non-zero PTE values.
The functionality will be used by x86 to support Intel's TDX, which needs
to set bit 63 in all non-present PTEs in order to prevent !PRESENT page
faults from getting reflected into the guest (Intel's EPT Violation #VE
architecture made the less than brilliant decision of having the per-PTE
behavior be opt-out instead of opt-in).

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Message-Id: <5919f685f109a1b0ebc6bd8fc4536ee94bcc172d.1705965635.git.isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_types.h |  1 +
 virt/kvm/kvm_main.c       | 16 ++++++++++++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

Comments

Xiaoyao Li Feb. 29, 2024, 1:46 p.m. UTC | #1 
On 2/28/2024 7:20 AM, Paolo Bonzini wrote:
> From: Sean Christopherson <seanjc@google.com>
> 
> Add support to MMU caches for initializing a page with a custom 64-bit
> value, e.g. to pre-fill an entire page table with non-zero PTE values.
> The functionality will be used by x86 to support Intel's TDX, which needs
> to set bit 63 in all non-present PTEs in order to prevent !PRESENT page
> faults from getting reflected into the guest (Intel's EPT Violation #VE
> architecture made the less than brilliant decision of having the per-PTE
> behavior be opt-out instead of opt-in).
> 
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> Message-Id: <5919f685f109a1b0ebc6bd8fc4536ee94bcc172d.1705965635.git.isaku.yamahata@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>

> ---
>   include/linux/kvm_types.h |  1 +
>   virt/kvm/kvm_main.c       | 16 ++++++++++++++--
>   2 files changed, 15 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
> index d93f6522b2c3..827ecc0b7e10 100644
> --- a/include/linux/kvm_types.h
> +++ b/include/linux/kvm_types.h
> @@ -86,6 +86,7 @@ struct gfn_to_pfn_cache {
>   struct kvm_mmu_memory_cache {
>   	gfp_t gfp_zero;
>   	gfp_t gfp_custom;
> +	u64 init_value;
>   	struct kmem_cache *kmem_cache;
>   	int capacity;
>   	int nobjs;
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 9c99c9373a3e..c9828feb7a1c 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -401,12 +401,17 @@ static void kvm_flush_shadow_all(struct kvm *kvm)
>   static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
>   					       gfp_t gfp_flags)
>   {
> +	void *page;
> +
>   	gfp_flags |= mc->gfp_zero;
>   
>   	if (mc->kmem_cache)
>   		return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
> -	else
> -		return (void *)__get_free_page(gfp_flags);
> +
> +	page = (void *)__get_free_page(gfp_flags);
> +	if (page && mc->init_value)
> +		memset64(page, mc->init_value, PAGE_SIZE / sizeof(mc->init_value));
> +	return page;
>   }
>   
>   int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
> @@ -421,6 +426,13 @@ int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity,
>   		if (WARN_ON_ONCE(!capacity))
>   			return -EIO;
>   
> +		/*
> +		 * Custom init values can be used only for page allocations,
> +		 * and obviously conflict with __GFP_ZERO.
> +		 */
> +		if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero)))
> +			return -EIO;
> +
>   		mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp);
>   		if (!mc->objects)
>   			return -ENOMEM;
diff mbox series

Patch

diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index d93f6522b2c3..827ecc0b7e10 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -86,6 +86,7 @@  struct gfn_to_pfn_cache {
 struct kvm_mmu_memory_cache {
 	gfp_t gfp_zero;
 	gfp_t gfp_custom;
+	u64 init_value;
 	struct kmem_cache *kmem_cache;
 	int capacity;
 	int nobjs;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9c99c9373a3e..c9828feb7a1c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -401,12 +401,17 @@  static void kvm_flush_shadow_all(struct kvm *kvm)
 static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
 					       gfp_t gfp_flags)
 {
+	void *page;
+
 	gfp_flags |= mc->gfp_zero;
 
 	if (mc->kmem_cache)
 		return kmem_cache_alloc(mc->kmem_cache, gfp_flags);
-	else
-		return (void *)__get_free_page(gfp_flags);
+
+	page = (void *)__get_free_page(gfp_flags);
+	if (page && mc->init_value)
+		memset64(page, mc->init_value, PAGE_SIZE / sizeof(mc->init_value));
+	return page;
 }
 
 int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
@@ -421,6 +426,13 @@  int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity,
 		if (WARN_ON_ONCE(!capacity))
 			return -EIO;
 
+		/*
+		 * Custom init values can be used only for page allocations,
+		 * and obviously conflict with __GFP_ZERO.
+		 */
+		if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero)))
+			return -EIO;
+
 		mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp);
 		if (!mc->objects)
 			return -ENOMEM;