linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Shivank Garg <shivankg@amd.com>
To: <seanjc@google.com>, <david@redhat.com>, <vbabka@suse.cz>,
	<willy@infradead.org>, <akpm@linux-foundation.org>,
	<shuah@kernel.org>, <pbonzini@redhat.com>
Cc: <ackerleytng@google.com>, <paul@paul-moore.com>,
	<jmorris@namei.org>, <serge@hallyn.com>, <pvorel@suse.cz>,
	<bfoster@redhat.com>, <tabba@google.com>, <vannapurve@google.com>,
	<chao.gao@intel.com>, <bharata@amd.com>, <nikunj@amd.com>,
	<michael.day@amd.com>, <yan.y.zhao@intel.com>,
	<Neeraj.Upadhyay@amd.com>, <thomas.lendacky@amd.com>,
	<michael.roth@amd.com>, <aik@amd.com>, <jgg@nvidia.com>,
	<kalyazin@amazon.com>, <peterx@redhat.com>, <shivankg@amd.com>,
	<linux-fsdevel@vger.kernel.org>, <linux-mm@kvack.org>,
	<linux-kernel@vger.kernel.org>,
	<linux-security-module@vger.kernel.org>, <kvm@vger.kernel.org>,
	<linux-kselftest@vger.kernel.org>, <linux-coco@lists.linux.dev>
Subject: [PATCH RFC v7 5/8] KVM: guest_memfd: Make guest mem use guest mem inodes instead of anonymous inodes
Date: Tue, 8 Apr 2025 11:23:59 +0000	[thread overview]
Message-ID: <20250408112402.181574-6-shivankg@amd.com> (raw)
In-Reply-To: <20250408112402.181574-1-shivankg@amd.com>

From: Ackerley Tng <ackerleytng@google.com>

Using guest mem inodes allows us to store metadata for the backing
memory on the inode. Metadata will be added in a later patch to support
HugeTLB pages.

Metadata about backing memory should not be stored on the file, since
the file represents a guest_memfd's binding with a struct kvm, and
metadata about backing memory is not unique to a specific binding and
struct kvm.

Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Shivank Garg <shivankg@amd.com>
---
 include/uapi/linux/magic.h |   1 +
 virt/kvm/guest_memfd.c     | 133 +++++++++++++++++++++++++++++++------
 2 files changed, 113 insertions(+), 21 deletions(-)

diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index bb575f3ab45e..169dba2a6920 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -103,5 +103,6 @@
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 #define PID_FS_MAGIC		0x50494446	/* "PIDF" */
+#define GUEST_MEMORY_MAGIC	0x474d454d	/* "GMEM" */
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 88453b040926..002328569c9e 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -1,12 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/mount.h>
 #include <linux/backing-dev.h>
 #include <linux/falloc.h>
 #include <linux/kvm_host.h>
+#include <linux/pseudo_fs.h>
 #include <linux/pagemap.h>
 #include <linux/anon_inodes.h>
 
 #include "kvm_mm.h"
 
+static struct vfsmount *kvm_gmem_mnt;
+
 struct kvm_gmem {
 	struct kvm *kvm;
 	struct xarray bindings;
@@ -312,6 +317,38 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
 	return gfn - slot->base_gfn + slot->gmem.pgoff;
 }
 
+static const struct super_operations kvm_gmem_super_operations = {
+	.statfs		= simple_statfs,
+};
+
+static int kvm_gmem_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx;
+
+	if (!init_pseudo(fc, GUEST_MEMORY_MAGIC))
+		return -ENOMEM;
+
+	ctx = fc->fs_private;
+	ctx->ops = &kvm_gmem_super_operations;
+
+	return 0;
+}
+
+static struct file_system_type kvm_gmem_fs = {
+	.name		 = "kvm_guest_memory",
+	.init_fs_context = kvm_gmem_init_fs_context,
+	.kill_sb	 = kill_anon_super,
+};
+
+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 struct file_operations kvm_gmem_fops = {
 	.open		= generic_file_open,
 	.release	= kvm_gmem_release,
@@ -321,11 +358,13 @@ static struct file_operations kvm_gmem_fops = {
 void kvm_gmem_init(struct module *module)
 {
 	kvm_gmem_fops.owner = module;
+
+	kvm_gmem_init_mount();
 }
 
 void kvm_gmem_exit(void)
 {
-
+	kern_unmount(kvm_gmem_mnt);
 }
 
 static int kvm_gmem_migrate_folio(struct address_space *mapping,
@@ -407,11 +446,79 @@ static const struct inode_operations kvm_gmem_iops = {
 	.setattr	= kvm_gmem_setattr,
 };
 
+static struct inode *kvm_gmem_inode_make_secure_inode(const char *name,
+						      loff_t size, u64 flags)
+{
+	const struct qstr qname = QSTR_INIT(name, strlen(name));
+	struct inode *inode;
+	int err;
+
+	inode = alloc_anon_inode(kvm_gmem_mnt->mnt_sb);
+	if (IS_ERR(inode))
+		return inode;
+
+	err = security_inode_init_security_anon(inode, &qname, NULL);
+	if (err) {
+		iput(inode);
+		return ERR_PTR(err);
+	}
+
+	inode->i_private = (void *)(unsigned long)flags;
+	inode->i_op = &kvm_gmem_iops;
+	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mode |= S_IFREG;
+	inode->i_size = size;
+	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_inaccessible(inode->i_mapping);
+	/* Unmovable mappings are supposed to be marked unevictable as well. */
+	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+	return inode;
+}
+
+static struct file *kvm_gmem_inode_create_getfile(void *priv, loff_t size,
+						  u64 flags)
+{
+	static const char *name = "[kvm-gmem]";
+	struct inode *inode;
+	struct file *file;
+	int err;
+
+	err = -ENOENT;
+	if (!try_module_get(kvm_gmem_fops.owner))
+		goto err;
+
+	inode = kvm_gmem_inode_make_secure_inode(name, size, flags);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		goto err_put_module;
+	}
+
+	file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR,
+				 &kvm_gmem_fops);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_put_inode;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+	file->private_data = priv;
+
+out:
+	return file;
+
+err_put_inode:
+	iput(inode);
+err_put_module:
+	module_put(kvm_gmem_fops.owner);
+err:
+	file = ERR_PTR(err);
+	goto out;
+}
+
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 {
-	const char *anon_name = "[kvm-gmem]";
 	struct kvm_gmem *gmem;
-	struct inode *inode;
 	struct file *file;
 	int fd, err;
 
@@ -425,32 +532,16 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 		goto err_fd;
 	}
 
-	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
-					 O_RDWR, NULL);
+	file = kvm_gmem_inode_create_getfile(gmem, size, flags);
 	if (IS_ERR(file)) {
 		err = PTR_ERR(file);
 		goto err_gmem;
 	}
 
-	file->f_flags |= O_LARGEFILE;
-
-	inode = file->f_inode;
-	WARN_ON(file->f_mapping != inode->i_mapping);
-
-	inode->i_private = (void *)(unsigned long)flags;
-	inode->i_op = &kvm_gmem_iops;
-	inode->i_mapping->a_ops = &kvm_gmem_aops;
-	inode->i_mode |= S_IFREG;
-	inode->i_size = size;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
-	mapping_set_inaccessible(inode->i_mapping);
-	/* Unmovable mappings are supposed to be marked unevictable as well. */
-	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
-
 	kvm_get_kvm(kvm);
 	gmem->kvm = kvm;
 	xa_init(&gmem->bindings);
-	list_add(&gmem->entry, &inode->i_mapping->i_private_list);
+	list_add(&gmem->entry, &file_inode(file)->i_mapping->i_private_list);
 
 	fd_install(fd, file);
 	return fd;
-- 
2.34.1



  parent reply	other threads:[~2025-04-08 11:25 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-08 11:23 [PATCH RFC v7 0/8] Add NUMA mempolicy support for KVM guest-memfd Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 1/8] mm/filemap: Add mempolicy support to the filemap layer Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 2/8] mm/mempolicy: Export memory policy symbols Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 3/8] security: Export security_inode_init_security_anon for KVM guest_memfd Shivank Garg
2025-04-09 20:19   ` Paul Moore
2025-04-11  6:07     ` Shivank Garg
2025-04-22 16:49       ` David Hildenbrand
2025-04-10  8:41   ` Christoph Hellwig
2025-04-11  6:51     ` Shivank Garg
2025-04-22 17:25     ` David Hildenbrand
2025-05-08  6:37       ` Shivank Garg
2025-04-08 11:23 ` [PATCH RFC v7 4/8] KVM: Add kvm_gmem_exit() cleanup function Shivank Garg
2025-04-08 11:23 ` Shivank Garg [this message]
2025-04-10  8:42   ` [PATCH RFC v7 5/8] KVM: guest_memfd: Make guest mem use guest mem inodes instead of anonymous inodes Christoph Hellwig
2025-04-10 13:53     ` Ackerley Tng
2025-04-10 14:23       ` Christoph Hellwig
2025-04-08 11:24 ` [PATCH RFC v7 6/8] KVM: guest_memfd: Add slab-allocated inode cache Shivank Garg
2025-04-08 11:24 ` [PATCH RFC v7 7/8] KVM: guest_memfd: Enforce NUMA mempolicy using shared policy Shivank Garg
2025-04-10 13:40   ` Ackerley Tng
2025-04-11  6:42     ` Shivank Garg
2025-04-08 11:24 ` [PATCH RFC v7 8/8] KVM: guest_memfd: selftests: Add tests for mmap and NUMA policy support Shivank Garg

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=20250408112402.181574-6-shivankg@amd.com \
    --to=shivankg@amd.com \
    --cc=Neeraj.Upadhyay@amd.com \
    --cc=ackerleytng@google.com \
    --cc=aik@amd.com \
    --cc=akpm@linux-foundation.org \
    --cc=bfoster@redhat.com \
    --cc=bharata@amd.com \
    --cc=chao.gao@intel.com \
    --cc=david@redhat.com \
    --cc=jgg@nvidia.com \
    --cc=jmorris@namei.org \
    --cc=kalyazin@amazon.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-coco@lists.linux.dev \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-security-module@vger.kernel.org \
    --cc=michael.day@amd.com \
    --cc=michael.roth@amd.com \
    --cc=nikunj@amd.com \
    --cc=paul@paul-moore.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pvorel@suse.cz \
    --cc=seanjc@google.com \
    --cc=serge@hallyn.com \
    --cc=shuah@kernel.org \
    --cc=tabba@google.com \
    --cc=thomas.lendacky@amd.com \
    --cc=vannapurve@google.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=yan.y.zhao@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