| Message ID | 20250408112402.181574-6-shivankg@amd.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Add NUMA mempolicy support for KVM guest-memfd | expand |
On Tue, Apr 08, 2025 at 11:23:59AM +0000, Shivank Garg wrote: > 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); > + } So why do other alloc_anon_inode callers not need security_inode_init_security_anon?
Christoph Hellwig <hch@infradead.org> writes: > On Tue, Apr 08, 2025 at 11:23:59AM +0000, Shivank Garg wrote: >> 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(-) >> >> <snip> >> >> +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); >> + } > > So why do other alloc_anon_inode callers not need > security_inode_init_security_anon? Thanks for this tip! When I did this refactoring, I was just refactoring anon_inode_create_getfile(), to set up the guest_memfd inode and file in separate stages, and anon_inode_create_getfile() was already using security_inode_init_security_anon(). In the next revision I can remove this call. Is it too late to remove the call to security_inode_init_security_anon() though? IIUC it is used by LSMs, which means security modules may already be assuming this call?
On Thu, Apr 10, 2025 at 06:53:15AM -0700, Ackerley Tng wrote: > > So why do other alloc_anon_inode callers not need > > security_inode_init_security_anon? > > Thanks for this tip! > > When I did this refactoring, I was just refactoring > anon_inode_create_getfile(), to set up the guest_memfd inode and file in > separate stages, and anon_inode_create_getfile() was already using > security_inode_init_security_anon(). > > In the next revision I can remove this call. > > Is it too late to remove the call to security_inode_init_security_anon() > though? IIUC it is used by LSMs, which means security modules may > already be assuming this call? I'd really like to here from the security folks if we need it or not, both in this case and for other alloc_anon_inode callers.
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;