qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Chao Peng <chao.p.peng@linux.intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	qemu-devel@nongnu.org
Cc: Wanpeng Li <wanpengli@tencent.com>,
	luto@kernel.org, david@redhat.com,
	"J . Bruce Fields" <bfields@fieldses.org>,
	dave.hansen@intel.com, "H . Peter Anvin" <hpa@zytor.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	ak@linux.intel.com, Jonathan Corbet <corbet@lwn.net>,
	Joerg Roedel <joro@8bytes.org>,
	x86@kernel.org, Hugh Dickins <hughd@google.com>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	jun.nakajima@intel.com, Thomas Gleixner <tglx@linutronix.de>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Jim Mattson <jmattson@google.com>,
	Sean Christopherson <seanjc@google.com>,
	Jeff Layton <jlayton@kernel.org>,
	Yu Zhang <yu.c.zhang@linux.intel.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH v4 12/12] KVM: Expose KVM_MEM_PRIVATE
Date: Tue, 18 Jan 2022 21:21:21 +0800	[thread overview]
Message-ID: <20220118132121.31388-13-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20220118132121.31388-1-chao.p.peng@linux.intel.com>

KVM_MEM_PRIVATE is not exposed by default but architecture code can turn
on it by implementing kvm_arch_private_memory_supported().

Also private memslot cannot be movable and the same file+offset can not
be mapped into different GFNs.

Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 49 ++++++++++++++++++++++++++++++++++------
 2 files changed, 43 insertions(+), 7 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 117cf0da9c5e..444b390261c0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1328,6 +1328,7 @@ bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_post_init_vm(struct kvm *kvm);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
 int kvm_arch_create_vm_debugfs(struct kvm *kvm);
+bool kvm_arch_private_memory_supported(struct kvm *kvm);
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 /*
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 10e553215618..51d0f08a8601 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1491,10 +1491,19 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+bool __weak kvm_arch_private_memory_supported(struct kvm *kvm)
+{
+	return false;
+}
+
+static int check_memory_region_flags(struct kvm *kvm,
+				const struct kvm_userspace_memory_region *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
+	if (kvm_arch_private_memory_supported(kvm))
+		valid_flags |= KVM_MEM_PRIVATE;
+
 #ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
@@ -1873,15 +1882,32 @@ static int kvm_set_memslot(struct kvm *kvm,
 }
 
 static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
-				      gfn_t start, gfn_t end)
+				      struct file *file,
+				      gfn_t start, gfn_t end,
+				      loff_t start_off, loff_t end_off)
 {
 	struct kvm_memslot_iter iter;
+	struct kvm_memory_slot *slot;
+	struct inode *inode;
+	int bkt;
 
 	kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) {
 		if (iter.slot->id != id)
 			return true;
 	}
 
+	/* Disallow mapping the same file+offset into multiple gfns. */
+	if (file) {
+		inode = file_inode(file);
+		kvm_for_each_memslot(slot, bkt, slots) {
+			if (slot->private_file &&
+			     file_inode(slot->private_file) == inode &&
+			     !(end_off <= slot->private_offset ||
+			       start_off >= slot->private_offset
+					     + (slot->npages >> PAGE_SHIFT)))
+				return true;
+		}
+	}
 	return false;
 }
 
@@ -1906,7 +1932,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(mem);
+	r = check_memory_region_flags(kvm, mem);
 	if (r)
 		return r;
 
@@ -1919,10 +1945,12 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		return -EINVAL;
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		return -EINVAL;
-	/* We can read the guest memory with __xxx_user() later on. */
 	if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
-	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
-	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
+	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)))
+		return -EINVAL;
+	/* We can read the guest memory with __xxx_user() later on. */
+	if (!(mem->flags & KVM_MEM_PRIVATE) &&
+	    !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
@@ -1963,6 +1991,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
 			return -EINVAL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_PRIVATE)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -1983,7 +2014,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	}
 
 	if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) &&
-	    kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) {
+	    kvm_check_memslot_overlap(slots, id, file,
+				      base_gfn, base_gfn + npages,
+				      region_ext->private_offset,
+				      region_ext->private_offset +
+						mem->memory_size)) {
 		r = -EEXIST;
 		goto out;
 	}
-- 
2.17.1



  parent reply	other threads:[~2022-01-18 15:16 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-18 13:21 [PATCH v4 00/12] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 01/12] mm/shmem: Introduce F_SEAL_INACCESSIBLE Chao Peng
2022-02-07 12:24   ` Vlastimil Babka
2022-02-17 12:56     ` Chao Peng
2022-02-11 23:33   ` Andy Lutomirski
2022-02-17 13:06     ` Chao Peng
2022-02-17 19:09       ` Andy Lutomirski
2022-02-23 11:49         ` Chao Peng
2022-02-23 12:05           ` Steven Price
2022-03-04 19:24             ` Andy Lutomirski
2022-03-07 13:26               ` Chao Peng
2022-03-08 12:17                 ` Paolo Bonzini
2022-01-18 13:21 ` [PATCH v4 02/12] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2022-01-21 15:50   ` Steven Price
2022-01-24 13:29     ` Chao Peng
2022-02-07 18:51   ` Vlastimil Babka
2022-02-08  8:49     ` David Hildenbrand
2022-02-08 18:22       ` Mike Rapoport
2022-01-18 13:21 ` [PATCH v4 03/12] mm: Introduce memfile_notifier Chao Peng
2022-03-07 15:42   ` Vlastimil Babka
2022-03-08  1:45     ` Chao Peng
2022-01-18 13:21 ` [PATCH v4 04/12] mm/shmem: Support memfile_notifier Chao Peng
2022-02-08 18:29   ` Mike Rapoport
2022-02-17 13:10     ` Chao Peng
2022-02-11 23:40   ` Andy Lutomirski
2022-02-17 13:23     ` Chao Peng
2022-01-18 13:21 ` [PATCH v4 05/12] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 06/12] KVM: Use kvm_userspace_memory_region_ext Chao Peng
2022-01-18 13:21 ` [PATCH v4 07/12] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2022-01-18 13:21 ` [PATCH v4 08/12] KVM: Use memfile_pfn_ops to obtain pfn for private pages Chao Peng
2022-01-18 13:21 ` [PATCH v4 09/12] KVM: Handle page fault for private memory Chao Peng
2022-01-18 13:21 ` [PATCH v4 10/12] KVM: Register private memslot to memory backing store Chao Peng
2022-01-18 13:21 ` [PATCH v4 11/12] KVM: Zap existing KVM mappings when pages changed in the private fd Chao Peng
2022-01-18 13:21 ` Chao Peng [this message]
2022-01-25 20:20   ` [PATCH v4 12/12] KVM: Expose KVM_MEM_PRIVATE Maciej S. Szmigiero
2022-02-17 13:45     ` Chao Peng
2022-02-22  1:16       ` Maciej S. Szmigiero
2022-02-23 12:00         ` Chao Peng
2022-02-23 18:32           ` Maciej S. Szmigiero
2022-02-24  8:07             ` Chao Peng
2022-01-28 16:47 ` [PATCH v4 00/12] KVM: mm: fd-based approach for supporting KVM guest private memory Steven Price
2022-02-02  2:28   ` Nakajima, Jun
2022-02-02  9:23     ` Steven Price
2022-02-02 20:47       ` Nakajima, Jun
2022-02-08 18:33 ` Mike Rapoport
2022-02-17 13:47   ` Chao Peng

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=20220118132121.31388-13-chao.p.peng@linux.intel.com \
    --to=chao.p.peng@linux.intel.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=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-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=seanjc@google.com \
    --cc=tglx@linutronix.de \
    --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).