Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH v6 10/14] mm: x86: Invoke hypercall when page encryption
 status is changed
To:     Ashish Kalra <Ashish.Kalra@amd.com>, pbonzini@redhat.com
Cc:     tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com,
        joro@8bytes.org, bp@suse.de, thomas.lendacky@amd.com,
        x86@kernel.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        rientjes@google.com, srutherford@google.com, luto@kernel.org,
        brijesh.singh@amd.com
References: <cover.1585548051.git.ashish.kalra@amd.com>
 <05c9015fb13b25c07a84d5638a7cd65a8c136cf0.1585548051.git.ashish.kalra@amd.com>
From:   Krish Sadhukhan <krish.sadhukhan@oracle.com>
Message-ID: <4021365b-c43a-02ae-475c-626199c8c451@oracle.com>
Date:   Fri, 3 Apr 2020 14:07:02 -0700
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.7.0
MIME-Version: 1.0
In-Reply-To: <05c9015fb13b25c07a84d5638a7cd65a8c136cf0.1585548051.git.ashish.kalra@amd.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Content-Language: en-US
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


On 3/29/20 11:22 PM, Ashish Kalra wrote:
> From: Brijesh Singh <Brijesh.Singh@amd.com>
>
> Invoke a hypercall when a memory region is changed from encrypted ->
> decrypted and vice versa. Hypervisor need to know the page encryption
> status during the guest migration.
>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: "Radim Krčmář" <rkrcmar@redhat.com>
> Cc: Joerg Roedel <joro@8bytes.org>
> Cc: Borislav Petkov <bp@suse.de>
> Cc: Tom Lendacky <thomas.lendacky@amd.com>
> Cc: x86@kernel.org
> Cc: kvm@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
> Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
> ---
>   arch/x86/include/asm/paravirt.h       | 10 +++++
>   arch/x86/include/asm/paravirt_types.h |  2 +
>   arch/x86/kernel/paravirt.c            |  1 +
>   arch/x86/mm/mem_encrypt.c             | 57 ++++++++++++++++++++++++++-
>   arch/x86/mm/pat/set_memory.c          |  7 ++++
>   5 files changed, 76 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
> index 694d8daf4983..8127b9c141bf 100644
> --- a/arch/x86/include/asm/paravirt.h
> +++ b/arch/x86/include/asm/paravirt.h
> @@ -78,6 +78,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
>   	PVOP_VCALL1(mmu.exit_mmap, mm);
>   }
>   
> +static inline void page_encryption_changed(unsigned long vaddr, int npages,
> +						bool enc)
> +{
> +	PVOP_VCALL3(mmu.page_encryption_changed, vaddr, npages, enc);
> +}
> +
>   #ifdef CONFIG_PARAVIRT_XXL
>   static inline void load_sp0(unsigned long sp0)
>   {
> @@ -946,6 +952,10 @@ static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
>   static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
>   {
>   }
> +
> +static inline void page_encryption_changed(unsigned long vaddr, int npages, bool enc)
> +{
> +}
>   #endif
>   #endif /* __ASSEMBLY__ */
>   #endif /* _ASM_X86_PARAVIRT_H */
> diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
> index 732f62e04ddb..03bfd515c59c 100644
> --- a/arch/x86/include/asm/paravirt_types.h
> +++ b/arch/x86/include/asm/paravirt_types.h
> @@ -215,6 +215,8 @@ struct pv_mmu_ops {
>   
>   	/* Hook for intercepting the destruction of an mm_struct. */
>   	void (*exit_mmap)(struct mm_struct *mm);
> +	void (*page_encryption_changed)(unsigned long vaddr, int npages,
> +					bool enc);
>   
>   #ifdef CONFIG_PARAVIRT_XXL
>   	struct paravirt_callee_save read_cr2;
> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
> index c131ba4e70ef..840c02b23aeb 100644
> --- a/arch/x86/kernel/paravirt.c
> +++ b/arch/x86/kernel/paravirt.c
> @@ -367,6 +367,7 @@ struct paravirt_patch_template pv_ops = {
>   			(void (*)(struct mmu_gather *, void *))tlb_remove_page,
>   
>   	.mmu.exit_mmap		= paravirt_nop,
> +	.mmu.page_encryption_changed	= paravirt_nop,
>   
>   #ifdef CONFIG_PARAVIRT_XXL
>   	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(native_read_cr2),
> diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
> index f4bd4b431ba1..c9800fa811f6 100644
> --- a/arch/x86/mm/mem_encrypt.c
> +++ b/arch/x86/mm/mem_encrypt.c
> @@ -19,6 +19,7 @@
>   #include <linux/kernel.h>
>   #include <linux/bitops.h>
>   #include <linux/dma-mapping.h>
> +#include <linux/kvm_para.h>
>   
>   #include <asm/tlbflush.h>
>   #include <asm/fixmap.h>
> @@ -29,6 +30,7 @@
>   #include <asm/processor-flags.h>
>   #include <asm/msr.h>
>   #include <asm/cmdline.h>
> +#include <asm/kvm_para.h>
>   
>   #include "mm_internal.h"
>   
> @@ -196,6 +198,47 @@ void __init sme_early_init(void)
>   		swiotlb_force = SWIOTLB_FORCE;
>   }
>   
> +static void set_memory_enc_dec_hypercall(unsigned long vaddr, int npages,
> +					bool enc)
> +{
> +	unsigned long sz = npages << PAGE_SHIFT;
> +	unsigned long vaddr_end, vaddr_next;
> +
> +	vaddr_end = vaddr + sz;
> +
> +	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
> +		int psize, pmask, level;
> +		unsigned long pfn;
> +		pte_t *kpte;
> +
> +		kpte = lookup_address(vaddr, &level);
> +		if (!kpte || pte_none(*kpte))
> +			return;
> +
> +		switch (level) {
> +		case PG_LEVEL_4K:
> +			pfn = pte_pfn(*kpte);
> +			break;
> +		case PG_LEVEL_2M:
> +			pfn = pmd_pfn(*(pmd_t *)kpte);
> +			break;
> +		case PG_LEVEL_1G:
> +			pfn = pud_pfn(*(pud_t *)kpte);
> +			break;
> +		default:
> +			return;
> +		}


Is it possible to re-use the code in __set_clr_pte_enc() ?

> +
> +		psize = page_level_size(level);
> +		pmask = page_level_mask(level);
> +
> +		kvm_sev_hypercall3(KVM_HC_PAGE_ENC_STATUS,
> +				   pfn << PAGE_SHIFT, psize >> PAGE_SHIFT, enc);
> +
> +		vaddr_next = (vaddr & pmask) + psize;
> +	}
> +}
> +
>   static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
>   {
>   	pgprot_t old_prot, new_prot;
> @@ -253,12 +296,13 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
>   static int __init early_set_memory_enc_dec(unsigned long vaddr,
>   					   unsigned long size, bool enc)
>   {
> -	unsigned long vaddr_end, vaddr_next;
> +	unsigned long vaddr_end, vaddr_next, start;
>   	unsigned long psize, pmask;
>   	int split_page_size_mask;
>   	int level, ret;
>   	pte_t *kpte;
>   
> +	start = vaddr;
>   	vaddr_next = vaddr;
>   	vaddr_end = vaddr + size;
>   
> @@ -313,6 +357,8 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr,
>   
>   	ret = 0;
>   
> +	set_memory_enc_dec_hypercall(start, PAGE_ALIGN(size) >> PAGE_SHIFT,
> +					enc);


If I haven't missed anything, it seems early_set_memory_encrypted() 
doesn't have a caller. So is there a possibility that we can end up 
calling it in non-SEV context and hence do we need to have the 
sev_active() guard here ?

>   out:
>   	__flush_tlb_all();
>   	return ret;
> @@ -451,6 +497,15 @@ void __init mem_encrypt_init(void)
>   	if (sev_active())
>   		static_branch_enable(&sev_enable_key);
>   
> +#ifdef CONFIG_PARAVIRT
> +	/*
> +	 * With SEV, we need to make a hypercall when page encryption state is
> +	 * changed.
> +	 */
> +	if (sev_active())
> +		pv_ops.mmu.page_encryption_changed = set_memory_enc_dec_hypercall;
> +#endif
> +
>   	pr_info("AMD %s active\n",
>   		sev_active() ? "Secure Encrypted Virtualization (SEV)"
>   			     : "Secure Memory Encryption (SME)");
> diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
> index c4aedd00c1ba..86b7804129fc 100644
> --- a/arch/x86/mm/pat/set_memory.c
> +++ b/arch/x86/mm/pat/set_memory.c
> @@ -26,6 +26,7 @@
>   #include <asm/proto.h>
>   #include <asm/memtype.h>
>   #include <asm/set_memory.h>
> +#include <asm/paravirt.h>
>   
>   #include "../mm_internal.h"
>   
> @@ -1987,6 +1988,12 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
>   	 */
>   	cpa_flush(&cpa, 0);
>   
> +	/* Notify hypervisor that a given memory range is mapped encrypted
> +	 * or decrypted. The hypervisor will use this information during the
> +	 * VM migration.
> +	 */
> +	page_encryption_changed(addr, numpages, enc);
> +
>   	return ret;
>   }
>