kvm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Fuad Tabba <tabba@google.com>
To: kvm@vger.kernel.org, linux-arm-msm@vger.kernel.org, linux-mm@kvack.org
Cc: pbonzini@redhat.com, chenhuacai@kernel.org, mpe@ellerman.id.au,
	 anup@brainfault.org, paul.walmsley@sifive.com,
	palmer@dabbelt.com,  aou@eecs.berkeley.edu, seanjc@google.com,
	viro@zeniv.linux.org.uk,  brauner@kernel.org,
	willy@infradead.org, akpm@linux-foundation.org,
	 xiaoyao.li@intel.com, yilun.xu@intel.com,
	chao.p.peng@linux.intel.com,  jarkko@kernel.org,
	amoorthy@google.com, dmatlack@google.com,
	 isaku.yamahata@intel.com, mic@digikod.net, vbabka@suse.cz,
	 vannapurve@google.com, ackerleytng@google.com,
	mail@maciej.szmigiero.name,  david@redhat.com,
	michael.roth@amd.com, wei.w.wang@intel.com,
	 liam.merwick@oracle.com, isaku.yamahata@gmail.com,
	 kirill.shutemov@linux.intel.com, suzuki.poulose@arm.com,
	steven.price@arm.com,  quic_eberman@quicinc.com,
	quic_mnalajal@quicinc.com, quic_tsoni@quicinc.com,
	 quic_svaddagi@quicinc.com, quic_cvanscha@quicinc.com,
	 quic_pderrin@quicinc.com, quic_pheragu@quicinc.com,
	catalin.marinas@arm.com,  james.morse@arm.com,
	yuzenghui@huawei.com, oliver.upton@linux.dev,  maz@kernel.org,
	will@kernel.org, qperret@google.com, keirf@google.com,
	 roypat@amazon.co.uk, shuah@kernel.org, hch@infradead.org,
	jgg@nvidia.com,  rientjes@google.com, jhubbard@nvidia.com,
	fvdl@google.com, hughd@google.com,  jthoughton@google.com,
	peterx@redhat.com, pankaj.gupta@amd.com,  ira.weiny@intel.com
Subject: Re: [PATCH v10 08/16] KVM: guest_memfd: Allow host to map guest_memfd pages
Date: Mon, 2 Jun 2025 11:05:25 +0100	[thread overview]
Message-ID: <CA+EHjTx1bxEXxtKHReT7QEhbPUZNiemgiSK2Q2X1UawPXXZFiA@mail.gmail.com> (raw)
In-Reply-To: <20250527180245.1413463-9-tabba@google.com>

Hi,

On Tue, 27 May 2025 at 19:03, Fuad Tabba <tabba@google.com> wrote:
>
> This patch enables support for shared memory in guest_memfd, including
> mapping that memory at the host userspace. This support is gated by the
> configuration option KVM_GMEM_SHARED_MEM, and toggled by the guest_memfd
> flag GUEST_MEMFD_FLAG_SUPPORT_SHARED, which can be set when creating a
> guest_memfd instance.
>
> Co-developed-by: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Fuad Tabba <tabba@google.com>
> ---
>  arch/x86/include/asm/kvm_host.h | 10 ++++
>  arch/x86/kvm/x86.c              |  3 +-
>  include/linux/kvm_host.h        | 13 ++++++
>  include/uapi/linux/kvm.h        |  1 +
>  virt/kvm/Kconfig                |  5 ++
>  virt/kvm/guest_memfd.c          | 81 +++++++++++++++++++++++++++++++++
>  6 files changed, 112 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 709cc2a7ba66..ce9ad4cd93c5 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -2255,8 +2255,18 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
>
>  #ifdef CONFIG_KVM_GMEM
>  #define kvm_arch_supports_gmem(kvm) ((kvm)->arch.supports_gmem)
> +
> +/*
> + * CoCo VMs with hardware support that use guest_memfd only for backing private
> + * memory, e.g., TDX, cannot use guest_memfd with userspace mapping enabled.
> + */
> +#define kvm_arch_supports_gmem_shared_mem(kvm)                 \
> +       (IS_ENABLED(CONFIG_KVM_GMEM_SHARED_MEM) &&                      \
> +        ((kvm)->arch.vm_type == KVM_X86_SW_PROTECTED_VM ||             \
> +         (kvm)->arch.vm_type == KVM_X86_DEFAULT_VM))
>  #else
>  #define kvm_arch_supports_gmem(kvm) false
> +#define kvm_arch_supports_gmem_shared_mem(kvm) false
>  #endif
>
>  #define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state)
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 035ced06b2dd..2a02f2457c42 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -12718,7 +12718,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
>                 return -EINVAL;
>
>         kvm->arch.vm_type = type;
> -       kvm->arch.supports_gmem = (type == KVM_X86_SW_PROTECTED_VM);
> +       kvm->arch.supports_gmem =
> +               type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM;
>         /* Decided by the vendor code for other VM types.  */
>         kvm->arch.pre_fault_allowed =
>                 type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM;
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 80371475818f..ba83547e62b0 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -729,6 +729,19 @@ static inline bool kvm_arch_supports_gmem(struct kvm *kvm)
>  }
>  #endif
>
> +/*
> + * Returns true if this VM supports shared mem in guest_memfd.
> + *
> + * Arch code must define kvm_arch_supports_gmem_shared_mem if support for
> + * guest_memfd is enabled.
> + */
> +#if !defined(kvm_arch_supports_gmem_shared_mem) && !IS_ENABLED(CONFIG_KVM_GMEM)
> +static inline bool kvm_arch_supports_gmem_shared_mem(struct kvm *kvm)
> +{
> +       return false;
> +}
> +#endif
> +
>  #ifndef kvm_arch_has_readonly_mem
>  static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
>  {
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index b6ae8ad8934b..c2714c9d1a0e 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1566,6 +1566,7 @@ struct kvm_memory_attributes {
>  #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
>
>  #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
> +#define GUEST_MEMFD_FLAG_SUPPORT_SHARED        (1ULL << 0)
>
>  struct kvm_create_guest_memfd {
>         __u64 size;
> diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
> index 559c93ad90be..df225298ab10 100644
> --- a/virt/kvm/Kconfig
> +++ b/virt/kvm/Kconfig
> @@ -128,3 +128,8 @@ config HAVE_KVM_ARCH_GMEM_PREPARE
>  config HAVE_KVM_ARCH_GMEM_INVALIDATE
>         bool
>         depends on KVM_GMEM
> +
> +config KVM_GMEM_SHARED_MEM
> +       select KVM_GMEM
> +       bool
> +       prompt "Enable support for non-private (shared) memory in guest_memfd"
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index 6db515833f61..5d34712f64fc 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -312,7 +312,81 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
>         return gfn - slot->base_gfn + slot->gmem.pgoff;
>  }
>
> +static bool kvm_gmem_supports_shared(struct inode *inode)
> +{
> +       u64 flags;
> +
> +       if (!IS_ENABLED(CONFIG_KVM_GMEM_SHARED_MEM))
> +               return false;
> +
> +       flags = (u64)inode->i_private;
> +
> +       return flags & GUEST_MEMFD_FLAG_SUPPORT_SHARED;
> +}
> +
> +
> +#ifdef CONFIG_KVM_GMEM_SHARED_MEM
> +static vm_fault_t kvm_gmem_fault_shared(struct vm_fault *vmf)
> +{
> +       struct inode *inode = file_inode(vmf->vma->vm_file);
> +       struct folio *folio;
> +       vm_fault_t ret = VM_FAULT_LOCKED;
> +

This was mentioned in a different thread [*], but it should also be
mentioned here. This is missing a bound check. I have added the
following for the next spin:

+       if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+               return VM_FAULT_SIGBUS;
+

I've also added a selftest to test this.

Cheers,
/fuad

[*] https://lore.kernel.org/all/CA+EHjTyv9KsRsbf6ec9u5mLjBbcnNti9k8hPi9Do59Mw7ayYqw@mail.gmail.com/

> +       folio = kvm_gmem_get_folio(inode, vmf->pgoff);
> +       if (IS_ERR(folio)) {
> +               int err = PTR_ERR(folio);
> +
> +               if (err == -EAGAIN)
> +                       return VM_FAULT_RETRY;
> +
> +               return vmf_error(err);
> +       }
> +
> +       if (WARN_ON_ONCE(folio_test_large(folio))) {
> +               ret = VM_FAULT_SIGBUS;
> +               goto out_folio;
> +       }
> +
> +       if (!folio_test_uptodate(folio)) {
> +               clear_highpage(folio_page(folio, 0));
> +               kvm_gmem_mark_prepared(folio);
> +       }
> +
> +       vmf->page = folio_file_page(folio, vmf->pgoff);
> +
> +out_folio:
> +       if (ret != VM_FAULT_LOCKED) {
> +               folio_unlock(folio);
> +               folio_put(folio);
> +       }
> +
> +       return ret;
> +}
> +
> +static const struct vm_operations_struct kvm_gmem_vm_ops = {
> +       .fault = kvm_gmem_fault_shared,
> +};
> +
> +static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
> +{
> +       if (!kvm_gmem_supports_shared(file_inode(file)))
> +               return -ENODEV;
> +
> +       if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
> +           (VM_SHARED | VM_MAYSHARE)) {
> +               return -EINVAL;
> +       }
> +
> +       vma->vm_ops = &kvm_gmem_vm_ops;
> +
> +       return 0;
> +}
> +#else
> +#define kvm_gmem_mmap NULL
> +#endif /* CONFIG_KVM_GMEM_SHARED_MEM */
> +
>  static struct file_operations kvm_gmem_fops = {
> +       .mmap           = kvm_gmem_mmap,
>         .open           = generic_file_open,
>         .release        = kvm_gmem_release,
>         .fallocate      = kvm_gmem_fallocate,
> @@ -463,6 +537,9 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
>         u64 flags = args->flags;
>         u64 valid_flags = 0;
>
> +       if (kvm_arch_supports_gmem_shared_mem(kvm))
> +               valid_flags |= GUEST_MEMFD_FLAG_SUPPORT_SHARED;
> +
>         if (flags & ~valid_flags)
>                 return -EINVAL;
>
> @@ -501,6 +578,10 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
>             offset + size > i_size_read(inode))
>                 goto err;
>
> +       if (kvm_gmem_supports_shared(inode) &&
> +           !kvm_arch_supports_gmem_shared_mem(kvm))
> +               goto err;
> +
>         filemap_invalidate_lock(inode->i_mapping);
>
>         start = offset >> PAGE_SHIFT;
> --
> 2.49.0.1164.gab81da1b16-goog
>

  parent reply	other threads:[~2025-06-02 10:06 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-27 18:02 [PATCH v10 00/16] KVM: Mapping guest_memfd backed memory at the host for software protected VMs Fuad Tabba
2025-05-27 18:02 ` [PATCH v10 01/16] KVM: Rename CONFIG_KVM_PRIVATE_MEM to CONFIG_KVM_GMEM Fuad Tabba
2025-05-31 19:05   ` Shivank Garg
2025-06-05  8:19   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 02/16] KVM: Rename CONFIG_KVM_GENERIC_PRIVATE_MEM to CONFIG_KVM_GENERIC_GMEM_POPULATE Fuad Tabba
2025-05-31 19:07   ` Shivank Garg
2025-06-05  8:19   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 03/16] KVM: Rename kvm_arch_has_private_mem() to kvm_arch_supports_gmem() Fuad Tabba
2025-05-31 19:12   ` Shivank Garg
2025-06-05  8:20   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 04/16] KVM: x86: Rename kvm->arch.has_private_mem to kvm->arch.supports_gmem Fuad Tabba
2025-05-31 19:13   ` Shivank Garg
2025-06-05  8:21   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 05/16] KVM: Rename kvm_slot_can_be_private() to kvm_slot_has_gmem() Fuad Tabba
2025-05-31 19:13   ` Shivank Garg
2025-06-05  8:22   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 06/16] KVM: Fix comments that refer to slots_lock Fuad Tabba
2025-05-31 19:14   ` Shivank Garg
2025-06-05  8:22   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 07/16] KVM: Fix comment that refers to kvm uapi header path Fuad Tabba
2025-05-31 19:19   ` Shivank Garg
2025-06-02 10:10     ` Fuad Tabba
2025-06-02 10:23   ` David Hildenbrand
2025-06-04  9:00   ` Gavin Shan
2025-06-05  8:22   ` Vlastimil Babka
2025-05-27 18:02 ` [PATCH v10 08/16] KVM: guest_memfd: Allow host to map guest_memfd pages Fuad Tabba
2025-05-28 23:17   ` kernel test robot
2025-06-02 10:05   ` Fuad Tabba [this message]
2025-06-02 10:43   ` Shivank Garg
2025-06-02 11:13     ` Fuad Tabba
2025-06-04  6:02   ` Gavin Shan
2025-06-04  8:37     ` Fuad Tabba
2025-06-04 12:26   ` David Hildenbrand
2025-06-04 12:32     ` Fuad Tabba
2025-06-04 13:02       ` David Hildenbrand
2025-06-05  6:40   ` Gavin Shan
2025-06-05  8:25     ` Fuad Tabba
2025-06-05  9:53       ` Gavin Shan
2025-06-05  8:28   ` Vlastimil Babka
2025-06-05  8:44     ` Fuad Tabba
2025-05-27 18:02 ` [PATCH v10 09/16] KVM: guest_memfd: Track shared memory support in memslot Fuad Tabba
2025-06-04 12:25   ` David Hildenbrand
2025-06-04 12:31     ` Fuad Tabba
2025-05-27 18:02 ` [PATCH v10 10/16] KVM: x86/mmu: Handle guest page faults for guest_memfd with shared memory Fuad Tabba
2025-05-27 18:02 ` [PATCH v10 11/16] KVM: x86: Compute max_mapping_level with input from guest_memfd Fuad Tabba
2025-06-04 13:09   ` David Hildenbrand
2025-05-27 18:02 ` [PATCH v10 12/16] KVM: arm64: Refactor user_mem_abort() calculation of force_pte Fuad Tabba
2025-06-04  6:05   ` Gavin Shan
2025-05-27 18:02 ` [PATCH v10 13/16] KVM: arm64: Handle guest_memfd-backed guest page faults Fuad Tabba
2025-06-04 13:17   ` David Hildenbrand
2025-06-04 13:30     ` Fuad Tabba
2025-06-04 13:33       ` David Hildenbrand
2025-05-27 18:02 ` [PATCH v10 14/16] KVM: arm64: Enable mapping guest_memfd in arm64 Fuad Tabba
2025-06-04 13:17   ` David Hildenbrand
2025-06-04 13:31     ` Fuad Tabba
2025-05-27 18:02 ` [PATCH v10 15/16] KVM: Introduce the KVM capability KVM_CAP_GMEM_SHARED_MEM Fuad Tabba
2025-06-05  9:59   ` Gavin Shan
2025-05-27 18:02 ` [PATCH v10 16/16] KVM: selftests: guest_memfd mmap() test when mapping is allowed Fuad Tabba
2025-06-04  9:19   ` Gavin Shan
2025-06-04  9:48     ` Fuad Tabba
2025-06-04 10:05       ` Gavin Shan
2025-06-04 10:25         ` Fuad Tabba

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=CA+EHjTx1bxEXxtKHReT7QEhbPUZNiemgiSK2Q2X1UawPXXZFiA@mail.gmail.com \
    --to=tabba@google.com \
    --cc=ackerleytng@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=amoorthy@google.com \
    --cc=anup@brainfault.org \
    --cc=aou@eecs.berkeley.edu \
    --cc=brauner@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=chao.p.peng@linux.intel.com \
    --cc=chenhuacai@kernel.org \
    --cc=david@redhat.com \
    --cc=dmatlack@google.com \
    --cc=fvdl@google.com \
    --cc=hch@infradead.org \
    --cc=hughd@google.com \
    --cc=ira.weiny@intel.com \
    --cc=isaku.yamahata@gmail.com \
    --cc=isaku.yamahata@intel.com \
    --cc=james.morse@arm.com \
    --cc=jarkko@kernel.org \
    --cc=jgg@nvidia.com \
    --cc=jhubbard@nvidia.com \
    --cc=jthoughton@google.com \
    --cc=keirf@google.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=liam.merwick@oracle.com \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mail@maciej.szmigiero.name \
    --cc=maz@kernel.org \
    --cc=mic@digikod.net \
    --cc=michael.roth@amd.com \
    --cc=mpe@ellerman.id.au \
    --cc=oliver.upton@linux.dev \
    --cc=palmer@dabbelt.com \
    --cc=pankaj.gupta@amd.com \
    --cc=paul.walmsley@sifive.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=qperret@google.com \
    --cc=quic_cvanscha@quicinc.com \
    --cc=quic_eberman@quicinc.com \
    --cc=quic_mnalajal@quicinc.com \
    --cc=quic_pderrin@quicinc.com \
    --cc=quic_pheragu@quicinc.com \
    --cc=quic_svaddagi@quicinc.com \
    --cc=quic_tsoni@quicinc.com \
    --cc=rientjes@google.com \
    --cc=roypat@amazon.co.uk \
    --cc=seanjc@google.com \
    --cc=shuah@kernel.org \
    --cc=steven.price@arm.com \
    --cc=suzuki.poulose@arm.com \
    --cc=vannapurve@google.com \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wei.w.wang@intel.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=xiaoyao.li@intel.com \
    --cc=yilun.xu@intel.com \
    --cc=yuzenghui@huawei.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).