kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Binbin Wu <binbin.wu@linux.intel.com>
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>,
	David Matlack <dmatlack@google.com>,
	Kai Huang <kai.huang@intel.com>,
	Zhi Wang <zhi.wang.linux@gmail.com>,
	chen.bo@intel.com, hang.yuan@intel.com, tina.zhang@intel.com
Subject: Re: [PATCH v6 15/16] KVM: x86/mmu: Make kvm fault handler aware of large page of private memslot
Date: Wed, 22 Nov 2023 17:05:43 +0800	[thread overview]
Message-ID: <376511f8-1d84-41fc-84ad-73d2f0ed3af1@linux.intel.com> (raw)
In-Reply-To: <075de567893a2b09bdfb203ae7ecd1867e5c3d8e.1699368363.git.isaku.yamahata@intel.com>



On 11/7/2023 11:00 PM, isaku.yamahata@intel.com wrote:
> From: Isaku Yamahata <isaku.yamahata@intel.com>
>
> struct kvm_page_fault.req_level is the page level which takes care of the
> faulted-in page size.  For now its calculation is only for the conventional
> kvm memslot by host_pfn_mapping_level() that traverses page table.
>
> However, host_pfn_mapping_level() cannot be used for private kvm memslot
> because pages of private kvm memlost aren't mapped into user virtual
> address space.

The description here is not accurate.  A memslot can be private doesn't mean
all pages of the memslot can't be mapped into user virtual address space.

> Instead page order is given when getting pfn.  Remember it
> in struct kvm_page_fault and use it.
>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> ---
>   arch/x86/kvm/mmu/mmu.c          | 34 +++++++++++++++++----------------
>   arch/x86/kvm/mmu/mmu_internal.h | 12 +++++++++++-
>   arch/x86/kvm/mmu/tdp_mmu.c      |  2 +-
>   3 files changed, 30 insertions(+), 18 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 0bf043812644..0aec7c11f4e2 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3158,10 +3158,10 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
>   
>   static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
>   				       const struct kvm_memory_slot *slot,
> -				       gfn_t gfn, int max_level, bool is_private)
> +				       gfn_t gfn, int max_level, int host_level,
> +				       bool is_private)
>   {
>   	struct kvm_lpage_info *linfo;
> -	int host_level;
>   
>   	max_level = min(max_level, max_huge_page_level);
>   	for ( ; max_level > PG_LEVEL_4K; max_level--) {
> @@ -3170,24 +3170,23 @@ static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
>   			break;
>   	}
>   
> -	if (is_private)
> -		return max_level;
> -
>   	if (max_level == PG_LEVEL_4K)
>   		return PG_LEVEL_4K;
>   
> -	host_level = host_pfn_mapping_level(kvm, gfn, slot);
> +	if (!is_private) {
> +		WARN_ON_ONCE(host_level != PG_LEVEL_NONE);
> +		host_level = host_pfn_mapping_level(kvm, gfn, slot);
> +	}
> +	WARN_ON_ONCE(host_level == PG_LEVEL_NONE);
>   	return min(host_level, max_level);
>   }
>   
>   int kvm_mmu_max_mapping_level(struct kvm *kvm,
>   			      const struct kvm_memory_slot *slot, gfn_t gfn,
> -			      int max_level)
> +			      int max_level, bool faultin_private)

When the parameter "faultin_private" is added, the only valid value is
"false".  If the caller passes in "faultin_private = true", then it 
would be a
problem based on this patch.
It seems meaningless and confusing to introduce the parameter 
"faultin_private"
here.

>   {
> -	bool is_private = kvm_slot_can_be_private(slot) &&
> -			  kvm_mem_is_private(kvm, gfn);
> -
> -	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
> +	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level,
> +					   PG_LEVEL_NONE, faultin_private);
>   }
>   
>   void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> @@ -3212,7 +3211,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>   	 */
>   	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
>   						       fault->gfn, fault->max_level,
> -						       fault->is_private);
> +						       fault->host_level,
> +						       kvm_is_faultin_private(fault));
>   	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
>   		return;
>   
> @@ -4336,6 +4336,7 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
>   				   struct kvm_page_fault *fault)
>   {
>   	int max_order, r;
> +	u8 max_level;
>   
>   	if (!kvm_slot_can_be_private(fault->slot)) {
>   		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
> @@ -4349,8 +4350,9 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
>   		return r;
>   	}
>   
> -	fault->max_level = min(kvm_max_level_for_order(max_order),
> -			       fault->max_level);
> +	max_level = kvm_max_level_for_order(max_order);
> +	fault->host_level = max_level;
> +	fault->max_level = min(max_level, fault->max_level);
>   	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
>   
>   	return RET_PF_CONTINUE;
> @@ -4400,7 +4402,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>   		return -EFAULT;
>   	}
>   
> -	if (fault->is_private)
> +	if (kvm_is_faultin_private(fault))
>   		return kvm_faultin_pfn_private(vcpu, fault);
>   
>   	async = false;
> @@ -6809,7 +6811,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
>   		 */
>   		if (sp->role.direct &&
>   		    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> -							       PG_LEVEL_NUM)) {
> +							       PG_LEVEL_NUM, false)) {
>   			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
>   
>   			if (kvm_available_flush_remote_tlbs_range())
> diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> index 653e96769956..6b540a10fd67 100644
> --- a/arch/x86/kvm/mmu/mmu_internal.h
> +++ b/arch/x86/kvm/mmu/mmu_internal.h
> @@ -357,6 +357,9 @@ struct kvm_page_fault {
>   	 * is changing its own translation in the guest page tables.
>   	 */
>   	bool write_fault_to_shadow_pgtable;
> +
> +	/* valid only for private memslot && private gfn */
> +	enum pg_level host_level;
>   };
>   
>   int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> @@ -451,7 +454,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>   
>   int kvm_mmu_max_mapping_level(struct kvm *kvm,
>   			      const struct kvm_memory_slot *slot, gfn_t gfn,
> -			      int max_level);
> +			      int max_level, bool faultin_private);
>   void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
>   void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
>   
> @@ -469,4 +472,11 @@ static inline bool kvm_hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t g
>   }
>   #endif
>   
> +static inline bool kvm_is_faultin_private(const struct kvm_page_fault *fault)
> +{
> +	if (IS_ENABLED(CONFIG_KVM_GENERIC_PRIVATE_MEM))
> +		return fault->is_private && kvm_slot_can_be_private(fault->slot);
> +	return false;
> +}
> +
>   #endif /* __KVM_X86_MMU_INTERNAL_H */
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index c8a4bd052c71..173e4e9053fc 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -2179,7 +2179,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
>   			continue;
>   
>   		max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
> -							      iter.gfn, PG_LEVEL_NUM);
> +							      iter.gfn, PG_LEVEL_NUM, false);
>   		if (max_mapping_level < iter.level)
>   			continue;
>   


  reply	other threads:[~2023-11-22  9:05 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-07 15:00 [PATCH v6 00/16] KVM TDX: TDP MMU: large page support isaku.yamahata
2023-11-07 15:00 ` [PATCH v6 01/16] KVM: TDP_MMU: Go to next level if smaller private mapping exists isaku.yamahata
2023-11-16  1:32   ` Binbin Wu
2023-11-17  1:05     ` Isaku Yamahata
2023-11-07 15:00 ` [PATCH v6 02/16] KVM: TDX: Pass page level to cache flush before TDX SEAMCALL isaku.yamahata
2023-11-16  5:36   ` Binbin Wu
2023-11-07 15:00 ` [PATCH v6 03/16] KVM: TDX: Pass KVM page level to tdh_mem_page_add() and tdh_mem_page_aug() isaku.yamahata
2023-11-16  8:18   ` Binbin Wu
2023-11-17  0:23     ` Isaku Yamahata
2023-11-07 15:00 ` [PATCH v6 04/16] KVM: TDX: Pass size to tdx_measure_page() isaku.yamahata
2023-11-16  8:57   ` Binbin Wu
2023-11-17  0:36     ` Isaku Yamahata
2023-11-07 15:00 ` [PATCH v6 05/16] KVM: TDX: Pass size to reclaim_page() isaku.yamahata
2023-11-19  6:42   ` Binbin Wu
2023-11-19  6:58     ` Binbin Wu
2023-11-07 15:00 ` [PATCH v6 06/16] KVM: TDX: Update tdx_sept_{set,drop}_private_spte() to support large page isaku.yamahata
2023-11-07 15:00 ` [PATCH v6 07/16] KVM: MMU: Introduce level info in PFERR code isaku.yamahata
2023-11-20 10:54   ` Binbin Wu
2023-11-21 10:02     ` Isaku Yamahata
2023-11-07 15:00 ` [PATCH v6 08/16] KVM: TDX: Pin pages via get_page() right before ADD/AUG'ed to TDs isaku.yamahata
2023-11-20 11:05   ` Binbin Wu
2023-11-21 10:04     ` Isaku Yamahata
2023-11-07 15:00 ` [PATCH v6 09/16] KVM: TDX: Pass desired page level in err code for page fault handler isaku.yamahata
2023-11-20 11:24   ` Binbin Wu
2023-11-21 10:27     ` Isaku Yamahata
2023-11-07 15:00 ` [PATCH v6 10/16] KVM: x86/tdp_mmu: Allocate private page table for large page split isaku.yamahata
2023-11-07 15:00 ` [PATCH v6 11/16] KVM: x86/tdp_mmu: Split the large page when zap leaf isaku.yamahata
2023-11-21  9:57   ` Binbin Wu
2023-11-21 11:00     ` Isaku Yamahata
2023-11-22  2:18       ` Binbin Wu
2023-11-07 15:00 ` [PATCH v6 12/16] KVM: x86/tdp_mmu, TDX: Split a large page when 4KB page within it converted to shared isaku.yamahata
2023-11-22  5:45   ` Binbin Wu
2023-11-07 15:00 ` [PATCH v6 13/16] KVM: x86/tdp_mmu: Try to merge pages into a large page isaku.yamahata
2023-11-22  7:24   ` Binbin Wu
2023-11-07 15:00 ` [PATCH v6 14/16] KVM: x86/tdp_mmu: TDX: Implement " isaku.yamahata
2023-11-22  7:50   ` Binbin Wu
2023-11-07 15:00 ` [PATCH v6 15/16] KVM: x86/mmu: Make kvm fault handler aware of large page of private memslot isaku.yamahata
2023-11-22  9:05   ` Binbin Wu [this message]
2023-11-07 15:00 ` [PATCH v6 16/16] KVM: TDX: Allow 2MB large page for TD GUEST isaku.yamahata

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=376511f8-1d84-41fc-84ad-73d2f0ed3af1@linux.intel.com \
    --to=binbin.wu@linux.intel.com \
    --cc=chen.bo@intel.com \
    --cc=dmatlack@google.com \
    --cc=erdemaktas@google.com \
    --cc=hang.yuan@intel.com \
    --cc=isaku.yamahata@gmail.com \
    --cc=isaku.yamahata@intel.com \
    --cc=kai.huang@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=sagis@google.com \
    --cc=seanjc@google.com \
    --cc=tina.zhang@intel.com \
    --cc=zhi.wang.linux@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).