linux-kernel - [RFC PATCH 27/39] KVM: guest_memfd: Allow mmapping guest

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5a05eb947cf7aa21f00b94171ca818cc3d5bdfee.1726009989.git.ackerleytng@google.com>
Date: Tue, 10 Sep 2024 23:43:58 +0000
From: Ackerley Tng <ackerleytng@...gle.com>
To: tabba@...gle.com, quic_eberman@...cinc.com, roypat@...zon.co.uk, 
	jgg@...dia.com, peterx@...hat.com, david@...hat.com, rientjes@...gle.com, 
	fvdl@...gle.com, jthoughton@...gle.com, seanjc@...gle.com, 
	pbonzini@...hat.com, zhiquan1.li@...el.com, fan.du@...el.com, 
	jun.miao@...el.com, isaku.yamahata@...el.com, muchun.song@...ux.dev, 
	mike.kravetz@...cle.com
Cc: erdemaktas@...gle.com, vannapurve@...gle.com, ackerleytng@...gle.com, 
	qperret@...gle.com, jhubbard@...dia.com, willy@...radead.org, 
	shuah@...nel.org, brauner@...nel.org, bfoster@...hat.com, 
	kent.overstreet@...ux.dev, pvorel@...e.cz, rppt@...nel.org, 
	richard.weiyang@...il.com, anup@...infault.org, haibo1.xu@...el.com, 
	ajones@...tanamicro.com, vkuznets@...hat.com, maciej.wieczor-retman@...el.com, 
	pgonda@...gle.com, oliver.upton@...ux.dev, linux-kernel@...r.kernel.org, 
	linux-mm@...ck.org, kvm@...r.kernel.org, linux-kselftest@...r.kernel.org, 
	linux-fsdevel@...ck.org
Subject: [RFC PATCH 27/39] KVM: guest_memfd: Allow mmapping guest_memfd files

guest_memfd files can always be mmap()ed to userspace, but
faultability is controlled by an attribute on the inode.

Co-developed-by: Fuad Tabba <tabba@...gle.com>
Signed-off-by: Fuad Tabba <tabba@...gle.com>
Co-developed-by: Ackerley Tng <ackerleytng@...gle.com>
Signed-off-by: Ackerley Tng <ackerleytng@...gle.com>

---
 virt/kvm/guest_memfd.c | 46 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 2 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index b603518f7b62..fc2483e35876 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -781,7 +781,8 @@ static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
 	pgoff_t start = offset >> PAGE_SHIFT;
-	pgoff_t end = (offset + len) >> PAGE_SHIFT;
+	pgoff_t nr = len >> PAGE_SHIFT;
+	pgoff_t end = start + nr;
 	struct kvm_gmem *gmem;
 
 	/*
@@ -790,6 +791,9 @@ static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 */
 	filemap_invalidate_lock(inode->i_mapping);
 
+	/* TODO: Check if even_cows should be 0 or 1 */
+	unmap_mapping_range(inode->i_mapping, start, len, 0);
+
 	list_for_each_entry(gmem, gmem_list, entry)
 		kvm_gmem_invalidate_begin(gmem, start, end);
 
@@ -946,6 +950,9 @@ static void kvm_gmem_hugetlb_teardown(struct inode *inode)
 {
 	struct kvm_gmem_hugetlb *hgmem;
 
+	/* TODO: Check if even_cows should be 0 or 1 */
+	unmap_mapping_range(inode->i_mapping, 0, LLONG_MAX, 0);
+
 	truncate_inode_pages_final_prepare(inode->i_mapping);
 	kvm_gmem_hugetlb_truncate_folios_range(inode, 0, LLONG_MAX);
 
@@ -1003,11 +1010,46 @@ static void kvm_gmem_init_mount(void)
 	kvm_gmem_mnt = kern_mount(&kvm_gmem_fs);
 	BUG_ON(IS_ERR(kvm_gmem_mnt));
 
-	/* For giggles. Userspace can never map this anyways. */
 	kvm_gmem_mnt->mnt_flags |= MNT_NOEXEC;
 }
 
+static vm_fault_t kvm_gmem_fault(struct vm_fault *vmf)
+{
+	struct inode *inode;
+	struct folio *folio;
+
+	inode = file_inode(vmf->vma->vm_file);
+	if (!kvm_gmem_is_faultable(inode, vmf->pgoff))
+		return VM_FAULT_SIGBUS;
+
+	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
+	if (!folio)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = folio_file_page(folio, vmf->pgoff);
+	return VM_FAULT_LOCKED;
+}
+
+static const struct vm_operations_struct kvm_gmem_vm_ops = {
+	.fault = kvm_gmem_fault,
+};
+
+static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
+	    (VM_SHARED | VM_MAYSHARE)) {
+		return -EINVAL;
+	}
+
+	file_accessed(file);
+	vm_flags_set(vma, VM_DONTDUMP);
+	vma->vm_ops = &kvm_gmem_vm_ops;
+
+	return 0;
+}
+
 static struct file_operations kvm_gmem_fops = {
+	.mmap		= kvm_gmem_mmap,
 	.open		= generic_file_open,
 	.release	= kvm_gmem_release,
 	.fallocate	= kvm_gmem_fallocate,
-- 
2.46.0.598.g6f2099f65c-goog