From: "Matthew Wilcox (Oracle)" willy@infradead.org

Extend __filemap_get_folio() to support NUMA memory policies by renaming the implementation to __filemap_get_folio_mpol() and adding a mempolicy parameter. The original function becomes a static inline wrapper that passes NULL for the mempolicy.

This infrastructure will enable future support for NUMA-aware page cache allocations in guest_memfd memory backend KVM guests.

Reviewed-by: Pankaj Gupta pankaj.gupta@amd.com Reviewed-by: Vlastimil Babka vbabka@suse.cz Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Reviewed-by: David Hildenbrand david@redhat.com Signed-off-by: Shivank Garg shivankg@amd.com --- include/linux/pagemap.h | 10 ++++++++-- mm/filemap.c | 11 ++++++----- 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ce617a35dc35..94d65ced0a1d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -747,11 +747,17 @@ static inline fgf_t fgf_set_order(size_t size) }

void *filemap_get_entry(struct address_space *mapping, pgoff_t index); -struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, - fgf_t fgp_flags, gfp_t gfp); +struct folio *__filemap_get_folio_mpol(struct address_space *mapping, + pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp);

+static inline struct folio *__filemap_get_folio(struct address_space *mapping, + pgoff_t index, fgf_t fgf_flags, gfp_t gfp) +{ + return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL); +} + /** * write_begin_get_folio - Get folio for write_begin with flags. * @iocb: The kiocb passed from write_begin (may be NULL). diff --git a/mm/filemap.c b/mm/filemap.c index 495f7f5c3d2e..03f223be575c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1897,11 +1897,12 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) }

/** - * __filemap_get_folio - Find and get a reference to a folio. + * __filemap_get_folio_mpol - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. + * @policy: NUMA memory allocation policy to follow. * * Looks up the page cache entry at @mapping & @index. * @@ -1912,8 +1913,8 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) * * Return: The found folio or an ERR_PTR() otherwise. */ -struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, - fgf_t fgp_flags, gfp_t gfp) +struct folio *__filemap_get_folio_mpol(struct address_space *mapping, + pgoff_t index, fgf_t fgp_flags, gfp_t gfp, struct mempolicy *policy) { struct folio *folio;

@@ -1983,7 +1984,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, err = -ENOMEM; if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; - folio = filemap_alloc_folio(alloc_gfp, order, NULL); + folio = filemap_alloc_folio(alloc_gfp, order, policy); if (!folio) continue;

@@ -2030,7 +2031,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, folio_clear_dropbehind(folio); return folio; } -EXPORT_SYMBOL(__filemap_get_folio); +EXPORT_SYMBOL(__filemap_get_folio_mpol);

static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark)

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.

Co-developed-by: Fuad Tabba tabba@google.com Signed-off-by: Fuad Tabba tabba@google.com Signed-off-by: Ackerley Tng ackerleytng@google.com Signed-off-by: Shivank Garg shivankg@amd.com --- include/uapi/linux/magic.h | 1 + virt/kvm/guest_memfd.c | 128 ++++++++++++++++++++++++++++++------- virt/kvm/kvm_main.c | 7 +- virt/kvm/kvm_mm.h | 9 +-- 4 files changed, 118 insertions(+), 27 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 08a6bc7d25b6..0e93323fc839 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; @@ -385,9 +389,45 @@ static struct file_operations kvm_gmem_fops = { .fallocate = kvm_gmem_fallocate, };

-void kvm_gmem_init(struct module *module) +static int kvm_gmem_init_fs_context(struct fs_context *fc) +{ + if (!init_pseudo(fc, GUEST_MEMFD_MAGIC)) + return -ENOMEM; + + fc->s_iflags |= SB_I_NOEXEC; + fc->s_iflags |= SB_I_NODEV; + + return 0; +} + +static struct file_system_type kvm_gmem_fs = { + .name = "guest_memfd", + .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 (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, @@ -463,11 +503,71 @@ bool __weak kvm_arch_supports_gmem_mmap(struct kvm *kvm) return true; }

+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;

@@ -481,32 +581,16 @@ 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 18f29ef93543..301d48d6e00d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -6489,7 +6489,9 @@ 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) @@ -6510,6 +6512,8 @@ 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(); @@ -6541,6 +6545,7 @@ 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 31defb08ccba..9fcc5d5b7f8d 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -68,17 +68,18 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, #endif /* HAVE_KVM_PFNCACHE */

#ifdef CONFIG_KVM_GUEST_MEMFD -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)

Add dedicated inode structure (kvm_gmem_inode_info) and slab-allocated inode cache for guest memory backing, similar to how shmem handles inodes.

This adds the necessary allocation/destruction functions and prepares for upcoming guest_memfd NUMA policy support changes.

Signed-off-by: Shivank Garg shivankg@amd.com --- virt/kvm/guest_memfd.c | 69 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 67 insertions(+), 2 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 0e93323fc839..d9c23401e770 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -17,6 +17,15 @@ struct kvm_gmem { struct list_head entry; };

+struct kvm_gmem_inode_info { + struct inode vfs_inode; +}; + +static inline struct kvm_gmem_inode_info *KVM_GMEM_I(struct inode *inode) +{ + return container_of(inode, struct kvm_gmem_inode_info, vfs_inode); +} + /** * folio_file_pfn - like folio_file_page, but return a pfn. * @folio: The folio which contains this index. @@ -389,13 +398,46 @@ static struct file_operations kvm_gmem_fops = { .fallocate = kvm_gmem_fallocate, };

+static struct kmem_cache *kvm_gmem_inode_cachep; + +static struct inode *kvm_gmem_alloc_inode(struct super_block *sb) +{ + struct kvm_gmem_inode_info *info; + + info = alloc_inode_sb(sb, kvm_gmem_inode_cachep, GFP_KERNEL); + if (!info) + return NULL; + + return &info->vfs_inode; +} + +static void kvm_gmem_destroy_inode(struct inode *inode) +{ +} + +static void kvm_gmem_free_inode(struct inode *inode) +{ + kmem_cache_free(kvm_gmem_inode_cachep, KVM_GMEM_I(inode)); +} + +static const struct super_operations kvm_gmem_super_operations = { + .statfs = simple_statfs, + .alloc_inode = kvm_gmem_alloc_inode, + .destroy_inode = kvm_gmem_destroy_inode, + .free_inode = kvm_gmem_free_inode, +}; + 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;

fc->s_iflags |= SB_I_NOEXEC; fc->s_iflags |= SB_I_NODEV; + ctx = fc->fs_private; + ctx->ops = &kvm_gmem_super_operations;

return 0; } @@ -417,17 +459,40 @@ static int kvm_gmem_init_mount(void) return 0; }

+static void kvm_gmem_init_inode(void *foo) +{ + struct kvm_gmem_inode_info *info = foo; + + inode_init_once(&info->vfs_inode); +} + int kvm_gmem_init(struct module *module) { - kvm_gmem_fops.owner = module; + int ret; + struct kmem_cache_args args = { + .align = 0, + .ctor = kvm_gmem_init_inode, + };

- return kvm_gmem_init_mount(); + kvm_gmem_fops.owner = module; + kvm_gmem_inode_cachep = kmem_cache_create("kvm_gmem_inode_cache", + sizeof(struct kvm_gmem_inode_info), + &args, SLAB_ACCOUNT); + if (!kvm_gmem_inode_cachep) + return -ENOMEM; + ret = kvm_gmem_init_mount(); + if (ret) { + kmem_cache_destroy(kvm_gmem_inode_cachep); + return ret; + } + return 0; }

void kvm_gmem_exit(void) { kern_unmount(kvm_gmem_mnt); kvm_gmem_mnt = NULL; + kmem_cache_destroy(kvm_gmem_inode_cachep); }

static int kvm_gmem_migrate_folio(struct address_space *mapping,

Previously, guest-memfd allocations followed local NUMA node id in absence of process mempolicy, resulting in arbitrary memory allocation. Moreover, mbind() couldn't be used by the VMM as guest memory wasn't mapped into userspace when allocation occurred.

Enable NUMA policy support by implementing vm_ops for guest-memfd mmap operation. This allows the VMM to map the memory and use mbind() to set the desired NUMA policy. The policy is stored in the inode structure via kvm_gmem_inode_info, as memory policy is a property of the memory (struct inode) itself. The policy is then retrieved via mpol_shared_policy_lookup() and passed to filemap_grab_folio_mpol() to ensure that allocations follow the specified memory policy.

This enables the VMM to control guest memory NUMA placement by calling mbind() on the mapped memory regions, providing fine-grained control over guest memory allocation across NUMA nodes.

The policy change only affect future allocations and does not migrate existing memory. This matches mbind(2)'s default behavior which affects only new allocations unless overridden with MPOL_MF_MOVE/MPOL_MF_MOVE_ALL flags, which are not supported for guest_memfd as it is unmovable.

Suggested-by: David Hildenbrand david@redhat.com Acked-by: David Hildenbrand david@redhat.com Acked-by: Vlastimil Babka vbabka@suse.cz Signed-off-by: Shivank Garg shivankg@amd.com --- virt/kvm/guest_memfd.c | 67 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 65 insertions(+), 2 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index d9c23401e770..7821c1036e49 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -4,6 +4,7 @@ #include <linux/falloc.h> #include <linux/fs.h> #include <linux/kvm_host.h> +#include <linux/mempolicy.h> #include <linux/pseudo_fs.h> #include <linux/pagemap.h>

@@ -18,6 +19,7 @@ struct kvm_gmem { };

struct kvm_gmem_inode_info { + struct shared_policy policy; struct inode vfs_inode; };

@@ -26,6 +28,9 @@ static inline struct kvm_gmem_inode_info *KVM_GMEM_I(struct inode *inode) return container_of(inode, struct kvm_gmem_inode_info, vfs_inode); }

+static struct mempolicy *kvm_gmem_get_pgoff_policy(struct kvm_gmem_inode_info *info, + pgoff_t index); + /** * folio_file_pfn - like folio_file_page, but return a pfn. * @folio: The folio which contains this index. @@ -112,7 +117,25 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) { /* TODO: Support huge pages. */ - return filemap_grab_folio(inode->i_mapping, index); + struct mempolicy *policy; + struct folio *folio; + + /* + * Fast-path: See if folio is already present in mapping to avoid + * policy_lookup. + */ + folio = __filemap_get_folio(inode->i_mapping, index, + FGP_LOCK | FGP_ACCESSED, 0); + if (!IS_ERR(folio)) + return folio; + + policy = kvm_gmem_get_pgoff_policy(KVM_GMEM_I(inode), index); + folio = __filemap_get_folio_mpol(inode->i_mapping, index, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mapping_gfp_mask(inode->i_mapping), policy); + mpol_cond_put(policy); + + return folio; }

static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, @@ -372,8 +395,45 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) return ret; }

+#ifdef CONFIG_NUMA +static int kvm_gmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) +{ + struct inode *inode = file_inode(vma->vm_file); + + return mpol_set_shared_policy(&KVM_GMEM_I(inode)->policy, vma, mpol); +} + +static struct mempolicy *kvm_gmem_get_policy(struct vm_area_struct *vma, + unsigned long addr, pgoff_t *pgoff) +{ + struct inode *inode = file_inode(vma->vm_file); + + *pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT); + return mpol_shared_policy_lookup(&KVM_GMEM_I(inode)->policy, *pgoff); +} + +static struct mempolicy *kvm_gmem_get_pgoff_policy(struct kvm_gmem_inode_info *info, + pgoff_t index) +{ + struct mempolicy *mpol; + + mpol = mpol_shared_policy_lookup(&info->policy, index); + return mpol ? mpol : get_task_policy(current); +} +#else +static struct mempolicy *kvm_gmem_get_pgoff_policy(struct kvm_gmem_inode_info *info, + pgoff_t index) +{ + return NULL; +} +#endif /* CONFIG_NUMA */ + static const struct vm_operations_struct kvm_gmem_vm_ops = { - .fault = kvm_gmem_fault_user_mapping, + .fault = kvm_gmem_fault_user_mapping, +#ifdef CONFIG_NUMA + .get_policy = kvm_gmem_get_policy, + .set_policy = kvm_gmem_set_policy, +#endif };

static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma) @@ -408,11 +468,14 @@ static struct inode *kvm_gmem_alloc_inode(struct super_block *sb) if (!info) return NULL;

+ mpol_shared_policy_init(&info->policy, NULL); + return &info->vfs_inode; }

static void kvm_gmem_destroy_inode(struct inode *inode) { + mpol_free_shared_policy(&KVM_GMEM_I(inode)->policy); }

static void kvm_gmem_free_inode(struct inode *inode)