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>, <brauner@kernel.org>,
	<viro@zeniv.linux.org.uk>
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>,
	<jack@suse.cz>, <rppt@kernel.org>, <hch@infradead.org>,
	<cgzones@googlemail.com>, <ira.weiny@intel.com>,
	<rientjes@google.com>, <roypat@amazon.co.uk>, <ziy@nvidia.com>,
	<matthew.brost@intel.com>, <joshua.hahnjy@gmail.com>,
	<rakie.kim@sk.com>, <byungchul@sk.com>, <gourry@gourry.net>,
	<kent.overstreet@linux.dev>, <ying.huang@linux.alibaba.com>,
	<apopple@nvidia.com>, <chao.p.peng@intel.com>,
	<amit@infradead.org>, <ddutile@redhat.com>,
	<dan.j.williams@intel.com>, <ashish.kalra@amd.com>,
	<gshan@redhat.com>, <jgowans@amazon.com>, <pankaj.gupta@amd.com>,
	<papaluri@amd.com>, <yuzhao@google.com>, <suzuki.poulose@arm.com>,
	<quic_eberman@quicinc.com>, <aneeshkumar.kizhakeveetil@arm.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: [RFC PATCH v8 2/7] KVM: guest_memfd: Use guest mem inodes instead of anonymous inodes
Date: Wed, 18 Jun 2025 11:29:30 +0000	[thread overview]
Message-ID: <20250618112935.7629-3-shivankg@amd.com> (raw)
In-Reply-To: <20250618112935.7629-1-shivankg@amd.com>

From: Ackerley Tng <ackerleytng@google.com>

guest_memfd's inode represents memory the guest_memfd is
providing. guest_memfd's file represents a struct kvm's view of that
memory.

Using a custom inode allows customization of the inode teardown
process via callbacks. For example, ->evict_inode() allows
customization of the truncation process on file close, and
->destroy_inode() and ->free_inode() allow customization of the inode
freeing process.

Customizing the truncation process allows flexibility in management of
guest_memfd memory and customization of the inode freeing process
allows proper cleanup of memory metadata stored on the inode.

Memory metadata is more appropriately stored on the inode (as opposed
to the file), since the metadata is for the memory and is not unique
to a specific binding and struct kvm.

Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Fuad Tabba <tabba@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     | 134 +++++++++++++++++++++++++++++++------
 virt/kvm/kvm_main.c        |   7 +-
 virt/kvm/kvm_mm.h          |  10 ++-
 4 files changed, 127 insertions(+), 25 deletions(-)

diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index bb575f3ab45e..638ca21b7a90 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_MEMFD_MAGIC	0x474d454d	/* "GMEM" */
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index ebdb2d8bf57a..159df462d193 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -1,12 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/anon_inodes.h>
 #include <linux/backing-dev.h>
 #include <linux/falloc.h>
+#include <linux/fs.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;
@@ -388,9 +392,51 @@ static struct file_operations kvm_gmem_fops = {
 	.fallocate	= kvm_gmem_fallocate,
 };
 
-void kvm_gmem_init(struct module *module)
+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_MEMFD_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 int kvm_gmem_init_mount(void)
+{
+	kvm_gmem_mnt = kern_mount(&kvm_gmem_fs);
+
+	if (WARN_ON_ONCE(IS_ERR(kvm_gmem_mnt)))
+		return PTR_ERR(kvm_gmem_mnt);
+
+	kvm_gmem_mnt->mnt_flags |= MNT_NOEXEC;
+	return 0;
+}
+
+int kvm_gmem_init(struct module *module)
 {
 	kvm_gmem_fops.owner = module;
+
+	return kvm_gmem_init_mount();
+}
+
+void kvm_gmem_exit(void)
+{
+	kern_unmount(kvm_gmem_mnt);
+	kvm_gmem_mnt = NULL;
 }
 
 static int kvm_gmem_migrate_folio(struct address_space *mapping,
@@ -472,11 +518,71 @@ 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)
+{
+	struct inode *inode;
+
+	inode = anon_inode_make_secure_inode(kvm_gmem_mnt->mnt_sb, name, NULL);
+	if (IS_ERR(inode))
+		return inode;
+
+	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;
 
@@ -490,32 +596,16 @@ 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;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e2f6344256ce..88c7dd6770da 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -6482,7 +6482,9 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
-	kvm_gmem_init(module);
+	r = kvm_gmem_init(module);
+	if (r)
+		goto err_gmem;
 
 	r = kvm_init_virtualization();
 	if (r)
@@ -6503,6 +6505,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 err_register:
 	kvm_uninit_virtualization();
 err_virt:
+	kvm_gmem_exit();
+err_gmem:
 	kvm_vfio_ops_exit();
 err_vfio:
 	kvm_async_pf_deinit();
@@ -6534,6 +6538,7 @@ void kvm_exit(void)
 	for_each_possible_cpu(cpu)
 		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
 	kmem_cache_destroy(kvm_vcpu_cache);
+	kvm_gmem_exit();
 	kvm_vfio_ops_exit();
 	kvm_async_pf_deinit();
 	kvm_irqfd_exit();
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index ec311c0d6718..4b825a7f114a 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -68,16 +68,22 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 #endif /* HAVE_KVM_PFNCACHE */
 
 #ifdef CONFIG_KVM_GMEM
-void kvm_gmem_init(struct module *module);
+int kvm_gmem_init(struct module *module);
+void kvm_gmem_exit(void);
 int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
 int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
 		  unsigned int fd, loff_t offset);
 void kvm_gmem_unbind(struct kvm_memory_slot *slot);
 #else
-static inline void kvm_gmem_init(struct module *module)
+static inline int kvm_gmem_init(struct module *module)
 {
 
+	return 0;
 }
+
+static inline void kvm_gmem_exit(void) {};
+
+static inline void kvm_gmem_init(struct module *module)
 
 static inline int kvm_gmem_bind(struct kvm *kvm,
 					 struct kvm_memory_slot *slot,
-- 
2.43.0



  parent reply	other threads:[~2025-06-18 11:30 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-18 11:29 [RFC PATCH v8 0/7] Add NUMA mempolicy support for KVM guest-memfd Shivank Garg
2025-06-18 11:29 ` [RFC PATCH v8 1/7] security: Export anon_inode_make_secure_inode for KVM guest_memfd Shivank Garg
2025-06-18 11:29 ` Shivank Garg [this message]
2025-06-18 11:29 ` [RFC PATCH v8 3/7] mm/filemap: Add mempolicy support to the filemap layer Shivank Garg
2025-06-19 15:08   ` Vlastimil Babka
2025-06-19 16:03   ` Matthew Wilcox
2025-06-20  5:59     ` Shivank Garg
2025-06-20  9:37       ` Vlastimil Babka
2025-06-20 14:34       ` Matthew Wilcox
2025-06-20 14:52         ` Shivank Garg
2025-06-20 14:58           ` Matthew Wilcox
2025-06-20 14:34   ` [PATCH 1/2] filemap: Add a mempolicy argument to filemap_alloc_folio() Matthew Wilcox (Oracle)
2025-06-23  6:13     ` Gupta, Pankaj
2025-06-23  7:19     ` Vlastimil Babka
2025-06-20 14:34   ` [PATCH 2/2] filemap: Add __filemap_get_folio_mpol() Matthew Wilcox (Oracle)
2025-06-20 16:53     ` Matthew Wilcox
2025-06-22 18:43       ` Andrew Morton
2025-06-22 19:02         ` Shivank Garg
2025-06-22 22:16           ` Andrew Morton
2025-06-23  4:18             ` Shivank Garg
2025-06-23 10:01             ` Shivank Garg
2025-06-23  7:16           ` Vlastimil Babka
2025-06-23  9:56             ` Shivank Garg
2025-06-23  6:15     ` Gupta, Pankaj
2025-06-23  7:20     ` Vlastimil Babka
2025-06-18 11:29 ` [RFC PATCH v8 4/7] mm/mempolicy: Export memory policy symbols Shivank Garg
2025-06-18 15:12   ` Gregory Price
2025-06-19 11:13     ` Shivank Garg
2025-06-19 16:28       ` Vlastimil Babka
2025-06-18 11:29 ` [RFC PATCH v8 5/7] KVM: guest_memfd: Add slab-allocated inode cache Shivank Garg
2025-06-24  4:16   ` Huang, Ying
2025-06-29 18:25     ` Shivank Garg
2025-06-18 11:29 ` [RFC PATCH v8 6/7] KVM: guest_memfd: Enforce NUMA mempolicy using shared policy Shivank Garg
2025-06-18 11:29 ` [RFC PATCH v8 7/7] 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=20250618112935.7629-3-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=amit@infradead.org \
    --cc=aneeshkumar.kizhakeveetil@arm.com \
    --cc=apopple@nvidia.com \
    --cc=ashish.kalra@amd.com \
    --cc=bfoster@redhat.com \
    --cc=bharata@amd.com \
    --cc=brauner@kernel.org \
    --cc=byungchul@sk.com \
    --cc=cgzones@googlemail.com \
    --cc=chao.gao@intel.com \
    --cc=chao.p.peng@intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=david@redhat.com \
    --cc=ddutile@redhat.com \
    --cc=gourry@gourry.net \
    --cc=gshan@redhat.com \
    --cc=hch@infradead.org \
    --cc=ira.weiny@intel.com \
    --cc=jack@suse.cz \
    --cc=jgg@nvidia.com \
    --cc=jgowans@amazon.com \
    --cc=jmorris@namei.org \
    --cc=joshua.hahnjy@gmail.com \
    --cc=kalyazin@amazon.com \
    --cc=kent.overstreet@linux.dev \
    --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=matthew.brost@intel.com \
    --cc=michael.day@amd.com \
    --cc=michael.roth@amd.com \
    --cc=nikunj@amd.com \
    --cc=pankaj.gupta@amd.com \
    --cc=papaluri@amd.com \
    --cc=paul@paul-moore.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pvorel@suse.cz \
    --cc=quic_eberman@quicinc.com \
    --cc=rakie.kim@sk.com \
    --cc=rientjes@google.com \
    --cc=roypat@amazon.co.uk \
    --cc=rppt@kernel.org \
    --cc=seanjc@google.com \
    --cc=serge@hallyn.com \
    --cc=shuah@kernel.org \
    --cc=suzuki.poulose@arm.com \
    --cc=tabba@google.com \
    --cc=thomas.lendacky@amd.com \
    --cc=vannapurve@google.com \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --cc=yan.y.zhao@intel.com \
    --cc=ying.huang@linux.alibaba.com \
    --cc=yuzhao@google.com \
    --cc=ziy@nvidia.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