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: Fuad Tabba tabba@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com --- include/uapi/linux/magic.h | 1 + virt/kvm/guest_memfd.c | 132 +++++++++++++++++++++++++++++++------ virt/kvm/kvm_main.c | 7 +- virt/kvm/kvm_mm.h | 9 ++- 4 files changed, 124 insertions(+), 25 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 b2aa6bf24d3a..2ee26695dc31 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/fs.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; @@ -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_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 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, @@ -402,11 +448,71 @@ 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 = alloc_anon_secure_inode(kvm_gmem_mnt->mnt_sb, name); + 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;
@@ -420,32 +526,16 @@ 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 69782df3617f..1e3fd81868bc 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -6412,7 +6412,9 @@ 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) @@ -6433,6 +6435,8 @@ 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(); @@ -6464,6 +6468,7 @@ 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 acef3f5c582a..dcacb76b8f00 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -68,17 +68,20 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, #endif /* HAVE_KVM_PFNCACHE */
#ifdef CONFIG_KVM_PRIVATE_MEM -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 int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned int fd, loff_t offset)