Received-SPF: pass (google.com: domain of linux-kernel+bounces-119393-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Message-ID: <d2ea2f8e-80b1-4dda-bf47-2145859e7463@linux.intel.com>
Date: Tue, 26 Mar 2024 23:53:02 +0800
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v19 048/130] KVM: Allow page-sized MMU caches to be
 initialized with custom 64-bit values
To: isaku.yamahata@intel.com
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
 isaku.yamahata@gmail.com, Paolo Bonzini <pbonzini@redhat.com>,
 erdemaktas@google.com, Sean Christopherson <seanjc@google.com>,
 Sagi Shahar <sagis@google.com>, Kai Huang <kai.huang@intel.com>,
 chen.bo@intel.com, hang.yuan@intel.com, tina.zhang@intel.com
References: <cover.1708933498.git.isaku.yamahata@intel.com>
 <9c392612eac4f3c489ad12dd4a4d505cf10d36dc.1708933498.git.isaku.yamahata@intel.com>
From: Binbin Wu <binbin.wu@linux.intel.com>
In-Reply-To: <9c392612eac4f3c489ad12dd4a4d505cf10d36dc.1708933498.git.isaku.yamahata@intel.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit


On 2/26/2024 4:25 PM, isaku.yamahata@intel.com 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>
> ---
>   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 9d1f7835d8c1..60c8d5c9eab9 100644
> --- a/include/linux/kvm_types.h
> +++ b/include/linux/kvm_types.h
> @@ -94,6 +94,7 @@ 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 de38f308738e..d399009ef1d7 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));

Do we need a static_assert() to make sure mc->init_value is 64bit?

> +	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(sizeof(void *), capacity, gfp);
>   		if (!mc->objects)
>   			return -ENOMEM;