From: Chao Peng <chao.p.peng@linux.intel.com>
To: Sean Christopherson <seanjc@google.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
qemu-devel@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
"J . Bruce Fields" <bfields@fieldses.org>,
Andrew Morton <akpm@linux-foundation.org>,
Mike Rapoport <rppt@kernel.org>,
Steven Price <steven.price@arm.com>,
"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
Vlastimil Babka <vbabka@suse.cz>,
Vishal Annapurve <vannapurve@google.com>,
Yu Zhang <yu.c.zhang@linux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, david@redhat.com, aarcange@redhat.com,
ddutile@redhat.com, dhildenb@redhat.com,
Quentin Perret <qperret@google.com>,
Michael Roth <michael.roth@amd.com>,
mhocko@suse.com
Subject: Re: [PATCH v6 4/8] KVM: Extend the memslot to support fd-based private memory
Date: Mon, 20 Jun 2022 22:08:41 +0800 [thread overview]
Message-ID: <20220620140841.GA2016793@chaop.bj.intel.com> (raw)
In-Reply-To: <Yqzpf3AEYabFWjnW@google.com>
On Fri, Jun 17, 2022 at 08:52:15PM +0000, Sean Christopherson wrote:
> On Thu, May 19, 2022, Chao Peng wrote:
> > @@ -653,12 +662,12 @@ struct kvm_irq_routing_table {
> > };
> > #endif
> >
> > -#ifndef KVM_PRIVATE_MEM_SLOTS
> > -#define KVM_PRIVATE_MEM_SLOTS 0
> > +#ifndef KVM_INTERNAL_MEM_SLOTS
> > +#define KVM_INTERNAL_MEM_SLOTS 0
> > #endif
>
> This rename belongs in a separate patch.
Will separate it out, thanks.
>
> > #define KVM_MEM_SLOTS_NUM SHRT_MAX
> > -#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
> > +#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
> >
> > #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
> > static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
> > @@ -1087,9 +1096,9 @@ enum kvm_mr_change {
> > };
> >
> > int kvm_set_memory_region(struct kvm *kvm,
> > - const struct kvm_userspace_memory_region *mem);
> > + const struct kvm_user_mem_region *mem);
> > int __kvm_set_memory_region(struct kvm *kvm,
> > - const struct kvm_userspace_memory_region *mem);
> > + const struct kvm_user_mem_region *mem);
> > void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
> > void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
> > int kvm_arch_prepare_memory_region(struct kvm *kvm,
> > diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> > index e10d131edd80..28cacd3656d4 100644
> > --- a/include/uapi/linux/kvm.h
> > +++ b/include/uapi/linux/kvm.h
> > @@ -103,6 +103,29 @@ struct kvm_userspace_memory_region {
> > __u64 userspace_addr; /* start of the userspace allocated memory */
> > };
> >
> > +struct kvm_userspace_memory_region_ext {
> > + struct kvm_userspace_memory_region region;
> > + __u64 private_offset;
> > + __u32 private_fd;
> > + __u32 pad1;
> > + __u64 pad2[14];
> > +};
> > +
> > +#ifdef __KERNEL__
> > +/* Internal helper, the layout must match above user visible structures */
>
> It's worth explicity calling out which structureso this aliases. And rather than
> add a comment about the layout needing to match that, enforce it in code. I
> personally wouldn't bother with an expolicit comment about the layout, IMO that's
> a fairly obvious implication of aliasing.
>
> /*
> * kvm_user_mem_region is a kernel-only alias of kvm_userspace_memory_region_ext
> * that "unpacks" kvm_userspace_memory_region so that KVM can directly access
> * all fields from the top-level "extended" region.
> */
>
Thanks.
>
> And I think it's in this patch that you missed a conversion to the alias, in the
> prototype for check_memory_region_flags() (looks like it gets fixed up later in
> the series).
>
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 0f81bf0407be..8765b334477d 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -1466,7 +1466,7 @@ static void kvm_replace_memslot(struct kvm *kvm,
> }
> }
>
> -static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
> +static int check_memory_region_flags(const struct kvm_user_mem_region *mem)
> {
> u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
>
> @@ -4514,6 +4514,33 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
> return fd;
> }
>
> +#define SANITY_CHECK_MEM_REGION_FIELD(field) \
> +do { \
> + BUILD_BUG_ON(offsetof(struct kvm_user_mem_region, field) != \
> + offsetof(struct kvm_userspace_memory_region, field)); \
> + BUILD_BUG_ON(sizeof_field(struct kvm_user_mem_region, field) != \
> + sizeof_field(struct kvm_userspace_memory_region, field)); \
> +} while (0)
> +
> +#define SANITY_CHECK_MEM_REGION_EXT_FIELD(field) \
> +do { \
> + BUILD_BUG_ON(offsetof(struct kvm_user_mem_region, field) != \
> + offsetof(struct kvm_userspace_memory_region_ext, field)); \
> + BUILD_BUG_ON(sizeof_field(struct kvm_user_mem_region, field) != \
> + sizeof_field(struct kvm_userspace_memory_region_ext, field)); \
> +} while (0)
> +
> +static void kvm_sanity_check_user_mem_region_alias(void)
> +{
> + SANITY_CHECK_MEM_REGION_FIELD(slot);
> + SANITY_CHECK_MEM_REGION_FIELD(flags);
> + SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
> + SANITY_CHECK_MEM_REGION_FIELD(memory_size);
> + SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
> + SANITY_CHECK_MEM_REGION_EXT_FIELD(private_offset);
> + SANITY_CHECK_MEM_REGION_EXT_FIELD(private_fd);
> +}
> +
> static long kvm_vm_ioctl(struct file *filp,
> unsigned int ioctl, unsigned long arg)
> {
> @@ -4541,6 +4568,8 @@ static long kvm_vm_ioctl(struct file *filp,
> unsigned long size;
> u32 flags;
>
> + kvm_sanity_check_user_mem_region_alias();
> +
> memset(&mem, 0, sizeof(mem));
>
> r = -EFAULT;
>
> > +struct kvm_user_mem_region {
> > + __u32 slot;
> > + __u32 flags;
> > + __u64 guest_phys_addr;
> > + __u64 memory_size;
> > + __u64 userspace_addr;
> > + __u64 private_offset;
> > + __u32 private_fd;
> > + __u32 pad1;
> > + __u64 pad2[14];
> > +};
> > +#endif
> > +
> > /*
> > * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
> > * other bits are reserved for kvm internal use which are defined in
> > @@ -110,6 +133,7 @@ struct kvm_userspace_memory_region {
> > */
> > #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
> > #define KVM_MEM_READONLY (1UL << 1)
> > +#define KVM_MEM_PRIVATE (1UL << 2)
>
> Hmm, KVM_MEM_PRIVATE is technically wrong now that a "private" memslot maps private
> and/or shared memory. Strictly speaking, we don't actually need a new flag. Valid
> file descriptors must be >=0, so the logic for specifying a memslot that can be
> converted between private and shared could be that "(int)private_fd < 0" means
> "not convertible", i.e. derive the flag from private_fd.
I think a flag is still needed, the problem is private_fd can be safely
accessed only when this flag is set, e.g. without this flag, we can't
copy_from_user these new fields since they don't exist for previous
kvm_userspace_memory_region callers.
>
> And looking at the two KVM consumers of the flag, via kvm_slot_is_private(), they're
> both wrong. Both kvm_faultin_pfn() and kvm_mmu_max_mapping_level() should operate
> on the _fault_, not the slot. So it would actually be a positive to not have an easy
> way to query if a slot supports conversion.
>
> > /* for KVM_IRQ_LINE */
> > struct kvm_irq_level {
>
> ...
>
> > + if (flags & KVM_MEM_PRIVATE) {
>
> An added bonus of dropping KVM_MEM_PRIVATE is that these checks go away.
>
> > + r = -EINVAL;
> > + goto out;
> > + }
> > +
> > + size = sizeof(struct kvm_userspace_memory_region);
> > +
> > + if (copy_from_user(&mem, argp, size))
> > + goto out;
> > +
> > + r = -EINVAL;
> > + if ((flags ^ mem.flags) & KVM_MEM_PRIVATE)
> > goto out;
> >
> > - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
> > + r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
> > break;
> > }
> > case KVM_GET_DIRTY_LOG: {
> > --
> > 2.25.1
> >
next prev parent reply other threads:[~2022-06-20 14:53 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-19 15:37 [PATCH v6 0/8] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2022-05-19 15:37 ` [PATCH v6 1/8] mm: Introduce memfile_notifier Chao Peng
2022-05-19 15:37 ` [PATCH v6 2/8] mm/shmem: Support memfile_notifier Chao Peng
2022-05-19 15:37 ` [PATCH v6 3/8] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2022-05-31 19:15 ` Vishal Annapurve
2022-06-01 10:17 ` Chao Peng
2022-06-01 12:11 ` Gupta, Pankaj
2022-06-02 10:07 ` Chao Peng
2022-06-14 20:23 ` Sean Christopherson
2022-06-15 8:53 ` Chao Peng
2022-05-19 15:37 ` [PATCH v6 4/8] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-05-20 17:57 ` Andy Lutomirski
2022-05-20 18:31 ` Sean Christopherson
2022-05-22 4:03 ` Andy Lutomirski
2022-05-23 13:21 ` Chao Peng
2022-05-23 15:22 ` Sean Christopherson
2022-05-30 13:26 ` Chao Peng
2022-06-10 16:14 ` Sean Christopherson
2022-06-14 6:45 ` Chao Peng
2022-06-23 22:59 ` Michael Roth
2022-06-24 8:54 ` Chao Peng
2022-06-24 13:01 ` Michael Roth
2022-06-17 20:52 ` Sean Christopherson
2022-06-17 21:27 ` Sean Christopherson
2022-06-20 14:09 ` Chao Peng
2022-06-20 14:08 ` Chao Peng [this message]
2022-05-19 15:37 ` [PATCH v6 5/8] KVM: Add KVM_EXIT_MEMORY_FAULT exit Chao Peng
2022-05-19 15:37 ` [PATCH v6 6/8] KVM: Handle page fault for private memory Chao Peng
2022-06-17 21:30 ` Sean Christopherson
2022-06-20 14:16 ` Chao Peng
2022-08-19 0:40 ` Kirill A. Shutemov
2022-08-25 23:43 ` Sean Christopherson
2022-06-24 3:58 ` Nikunj A. Dadhania
2022-06-24 9:02 ` Chao Peng
2022-06-30 19:14 ` Vishal Annapurve
2022-06-30 22:21 ` Michael Roth
2022-07-01 1:21 ` Xiaoyao Li
2022-07-07 20:08 ` Sean Christopherson
2022-07-08 3:29 ` Xiaoyao Li
2022-07-20 23:08 ` Vishal Annapurve
2022-07-21 9:45 ` Chao Peng
2022-05-19 15:37 ` [PATCH v6 7/8] KVM: Enable and expose KVM_MEM_PRIVATE Chao Peng
2022-06-23 22:07 ` Michael Roth
2022-06-24 8:43 ` Chao Peng
2022-05-19 15:37 ` [PATCH v6 8/8] memfd_create.2: Describe MFD_INACCESSIBLE flag Chao Peng
2022-06-06 20:09 ` [PATCH v6 0/8] KVM: mm: fd-based approach for supporting KVM guest private memory Vishal Annapurve
2022-06-07 6:57 ` Chao Peng
2022-06-08 0:55 ` Marc Orr
2022-06-08 2:18 ` Chao Peng
2022-06-08 19:37 ` Vishal Annapurve
2022-06-09 20:29 ` Sean Christopherson
2022-06-14 7:28 ` Chao Peng
2022-06-14 17:37 ` Andy Lutomirski
2022-06-14 19:08 ` Sean Christopherson
2022-06-14 20:59 ` Andy Lutomirski
2022-06-15 9:17 ` Chao Peng
2022-06-15 14:29 ` Sean Christopherson
2022-06-10 0:11 ` Marc Orr
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=20220620140841.GA2016793@chaop.bj.intel.com \
--to=chao.p.peng@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=bfields@fieldses.org \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=ddutile@redhat.com \
--cc=dhildenb@redhat.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jlayton@kernel.org \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=jun.nakajima@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mail@maciej.szmigiero.name \
--cc=mhocko@suse.com \
--cc=michael.roth@amd.com \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qperret@google.com \
--cc=rppt@kernel.org \
--cc=seanjc@google.com \
--cc=steven.price@arm.com \
--cc=tglx@linutronix.de \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
--cc=yu.c.zhang@linux.intel.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).