KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Dave Hansen <dave.hansen@linux.intel.com>,
	Andy Lutomirski <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	David Rientjes <rientjes@google.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Kees Cook <keescook@chromium.org>, Will Drewry <wad@chromium.org>,
	"Edgecombe, Rick P" <rick.p.edgecombe@intel.com>,
	"Kleen, Andi" <andi.kleen@intel.com>,
	x86@kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: Re: [RFC 07/16] KVM: mm: Introduce VM_KVM_PROTECTED
Date: Tue, 26 May 2020 09:15:52 +0300
Message-ID: <20200526061552.GD13247@kernel.org> (raw)
In-Reply-To: <20200522125214.31348-8-kirill.shutemov@linux.intel.com>

On Fri, May 22, 2020 at 03:52:05PM +0300, Kirill A. Shutemov wrote:
> The new VMA flag that indicate a VMA that is not accessible to userspace
> but usable by kernel with GUP if FOLL_KVM is specified.
> 
> The FOLL_KVM is only used in the KVM code. The code has to know how to
> deal with such pages.
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
>  include/linux/mm.h  |  8 ++++++++
>  mm/gup.c            | 20 ++++++++++++++++----
>  mm/huge_memory.c    | 20 ++++++++++++++++----
>  mm/memory.c         |  3 +++
>  mm/mmap.c           |  3 +++
>  virt/kvm/async_pf.c |  4 ++--
>  virt/kvm/kvm_main.c |  9 +++++----
>  7 files changed, 53 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index e1882eec1752..4f7195365cc0 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -329,6 +329,8 @@ extern unsigned int kobjsize(const void *objp);
>  # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
>  #endif
>  
> +#define VM_KVM_PROTECTED 0

With all the ideas about removing pages from the direct mapi floating
around I wouldn't limit this to KVM.

VM_NOT_IN_DIRECT_MAP would describe such areas better, but I realise
it's very far from perfect and nothing better does not comes to mind :)


>  #ifndef VM_GROWSUP
>  # define VM_GROWSUP	VM_NONE
>  #endif
> @@ -646,6 +648,11 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma)
>  	return vma->vm_flags & VM_ACCESS_FLAGS;
>  }
>  
> +static inline bool vma_is_kvm_protected(struct vm_area_struct *vma)

Ditto

> +{
> +	return vma->vm_flags & VM_KVM_PROTECTED;
> +}
> +
>  #ifdef CONFIG_SHMEM
>  /*
>   * The vma_is_shmem is not inline because it is used only by slow
> @@ -2773,6 +2780,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
>  #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
>  #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
>  #define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
> +#define FOLL_KVM	0x80000 /* access to VM_KVM_PROTECTED VMAs */

Maybe

FOLL_DM		0x80000  /* access  memory dropped from the direct map */

>  /*
>   * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
> diff --git a/mm/gup.c b/mm/gup.c
> index 87a6a59fe667..bd7b9484b35a 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c

...

> diff --git a/mm/mmap.c b/mm/mmap.c
> index f609e9ec4a25..d56c3f6efc99 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -112,6 +112,9 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags)
>  				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
>  			pgprot_val(arch_vm_get_page_prot(vm_flags)));
>  
> +	if (vm_flags & VM_KVM_PROTECTED)
> +		ret = PAGE_NONE;

Nit: vma_is_kvm_protected()?

> +
>  	return arch_filter_pgprot(ret);
>  }
>  EXPORT_SYMBOL(vm_get_page_prot);
> diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
> index 15e5b037f92d..7663e962510a 100644
> --- a/virt/kvm/async_pf.c
> +++ b/virt/kvm/async_pf.c
> @@ -60,8 +60,8 @@ static void async_pf_execute(struct work_struct *work)
>  	 * access remotely.
>  	 */
>  	down_read(&mm->mmap_sem);
> -	get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE, NULL, NULL,
> -			&locked);
> +	get_user_pages_remote(NULL, mm, addr, 1, FOLL_WRITE | FOLL_KVM, NULL,
> +			      NULL, &locked);
>  	if (locked)
>  		up_read(&mm->mmap_sem);
>  
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 033471f71dae..530af95efdf3 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -1727,7 +1727,7 @@ unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *w
>  
>  static inline int check_user_page_hwpoison(unsigned long addr)
>  {
> -	int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
> +	int rc, flags = FOLL_HWPOISON | FOLL_WRITE | FOLL_KVM;
>  
>  	rc = get_user_pages(addr, 1, flags, NULL, NULL);
>  	return rc == -EHWPOISON;
> @@ -1771,7 +1771,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
>  static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
>  			   bool *writable, kvm_pfn_t *pfn)
>  {
> -	unsigned int flags = FOLL_HWPOISON;
> +	unsigned int flags = FOLL_HWPOISON | FOLL_KVM;
>  	struct page *page;
>  	int npages = 0;
>  
> @@ -2255,7 +2255,7 @@ int copy_from_guest(void *data, unsigned long hva, int len)
>  	int npages, seg;
>  
>  	while ((seg = next_segment(len, offset)) != 0) {
> -		npages = get_user_pages_unlocked(hva, 1, &page, 0);
> +		npages = get_user_pages_unlocked(hva, 1, &page, FOLL_KVM);
>  		if (npages != 1)
>  			return -EFAULT;
>  		memcpy(data, page_address(page) + offset, seg);
> @@ -2275,7 +2275,8 @@ int copy_to_guest(unsigned long hva, const void *data, int len)
>  	int npages, seg;
>  
>  	while ((seg = next_segment(len, offset)) != 0) {
> -		npages = get_user_pages_unlocked(hva, 1, &page, FOLL_WRITE);
> +		npages = get_user_pages_unlocked(hva, 1, &page,
> +						 FOLL_WRITE | FOLL_KVM);
>  		if (npages != 1)
>  			return -EFAULT;
>  		memcpy(page_address(page) + offset, data, seg);
> -- 
> 2.26.2
> 
> 

-- 
Sincerely yours,
Mike.

  reply index

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-22 12:51 [RFC 00/16] KVM protected memory extension Kirill A. Shutemov
2020-05-22 12:51 ` [RFC 01/16] x86/mm: Move force_dma_unencrypted() to common code Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 02/16] x86/kvm: Introduce KVM memory protection feature Kirill A. Shutemov
2020-05-25 14:58   ` Vitaly Kuznetsov
2020-05-25 15:15     ` Kirill A. Shutemov
2020-05-27  5:03       ` Sean Christopherson
2020-05-27  8:39         ` Vitaly Kuznetsov
2020-05-27  8:52           ` Sean Christopherson
2020-06-03  2:09           ` Huang, Kai
2020-06-03 11:14             ` Vitaly Kuznetsov
2020-05-22 12:52 ` [RFC 03/16] x86/kvm: Make DMA pages shared Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 04/16] x86/kvm: Use bounce buffers for KVM memory protection Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 05/16] x86/kvm: Make VirtIO use DMA API in KVM guest Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 06/16] KVM: Use GUP instead of copy_from/to_user() to access guest memory Kirill A. Shutemov
2020-05-25 15:08   ` Vitaly Kuznetsov
2020-05-25 15:17     ` Kirill A. Shutemov
2020-06-01 16:35       ` Paolo Bonzini
2020-06-02 13:33         ` Kirill A. Shutemov
2020-05-26  6:14   ` Mike Rapoport
2020-05-26 21:56     ` Kirill A. Shutemov
2020-05-29 15:24   ` Kees Cook
2020-05-22 12:52 ` [RFC 07/16] KVM: mm: Introduce VM_KVM_PROTECTED Kirill A. Shutemov
2020-05-26  6:15   ` Mike Rapoport [this message]
2020-05-26 22:01     ` Kirill A. Shutemov
2020-05-26  6:40   ` John Hubbard
2020-05-26 22:04     ` Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 08/16] KVM: x86: Use GUP for page walk instead of __get_user() Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 09/16] KVM: Protected memory extension Kirill A. Shutemov
2020-05-25 15:26   ` Vitaly Kuznetsov
2020-05-25 15:34     ` Kirill A. Shutemov
2020-06-03  1:34       ` Huang, Kai
2020-05-22 12:52 ` [RFC 10/16] KVM: x86: Enabled protected " Kirill A. Shutemov
2020-05-25 15:26   ` Vitaly Kuznetsov
2020-05-26  6:16   ` Mike Rapoport
2020-05-26 21:58     ` Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 11/16] KVM: Rework copy_to/from_guest() to avoid direct mapping Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 12/16] x86/kvm: Share steal time page with host Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 13/16] x86/kvmclock: Share hvclock memory with the host Kirill A. Shutemov
2020-05-25 15:22   ` Vitaly Kuznetsov
2020-05-25 15:25     ` Kirill A. Shutemov
2020-05-25 15:42       ` Vitaly Kuznetsov
2020-05-22 12:52 ` [RFC 14/16] KVM: Introduce gfn_to_pfn_memslot_protected() Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 15/16] KVM: Handle protected memory in __kvm_map_gfn()/__kvm_unmap_gfn() Kirill A. Shutemov
2020-05-22 12:52 ` [RFC 16/16] KVM: Unmap protected pages from direct mapping Kirill A. Shutemov
2020-05-26  6:16   ` Mike Rapoport
2020-05-26 22:10     ` Kirill A. Shutemov
2020-05-25  5:27 ` [RFC 00/16] KVM protected memory extension Kirill A. Shutemov
2020-05-25 13:47 ` Liran Alon
2020-05-25 14:46   ` Kirill A. Shutemov
2020-05-25 15:56     ` Liran Alon
2020-05-26  6:17   ` Mike Rapoport
2020-05-26 10:16     ` Liran Alon
2020-05-26 11:38       ` Mike Rapoport
2020-05-27 15:45         ` Dave Hansen
2020-05-27 21:22           ` Mike Rapoport
2020-06-04 15:15 ` Marc Zyngier
2020-06-04 15:48   ` Sean Christopherson
2020-06-04 16:27     ` Marc Zyngier
2020-06-04 16:35     ` Will Deacon
2020-06-04 19:09       ` Nakajima, Jun
2020-06-04 21:03         ` Jim Mattson
2020-06-04 23:29           ` Nakajima, Jun

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=20200526061552.GD13247@kernel.org \
    --to=rppt@kernel.org \
    --cc=aarcange@redhat.com \
    --cc=andi.kleen@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=keescook@chromium.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kirill@shutemov.name \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rick.p.edgecombe@intel.com \
    --cc=rientjes@google.com \
    --cc=sean.j.christopherson@intel.com \
    --cc=vkuznets@redhat.com \
    --cc=wad@chromium.org \
    --cc=wanpengli@tencent.com \
    --cc=x86@kernel.org \
    /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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git