On 02.06.25 21:17, Ackerley Tng wrote:
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@xxxxxxxxxx>
Signed-off-by: Fuad Tabba <tabba@xxxxxxxxxx>
The trailing SOB from Fuag is likely wrong. Probably you wnat
Co-developed-by: Fuad Tabba <tabba@xxxxxxxxxx>
Signed-off-by: Fuad Tabba <tabba@xxxxxxxxxx>
Signed-off-by: Ackerley Tng <ackerleytng@xxxxxxxxxx>
---
include/uapi/linux/magic.h | 1 +
virt/kvm/guest_memfd.c | 134 +++++++++++++++++++++++++++++++------
virt/kvm/kvm_main.c | 7 +-
virt/kvm/kvm_mm.h | 9 ++-
4 files changed, 125 insertions(+), 26 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 b2aa6bf24d3a..1283b85aeb44 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;
@@ -318,9 +322,51 @@ 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);
Hmm, is this WARN_ON_ONCE really warrented?
Nothing else jumped at me. I hope some fs experts can take a look as well.
--
Cheers,
David / dhildenb
