diff options
Diffstat (limited to 'virt/kvm')
| -rw-r--r-- | virt/kvm/Kconfig | 3 | ||||
| -rw-r--r-- | virt/kvm/eventfd.c | 2 | ||||
| -rw-r--r-- | virt/kvm/guest_memfd.c | 410 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 40 | ||||
| -rw-r--r-- | virt/kvm/kvm_mm.h | 9 |
5 files changed, 341 insertions, 123 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 5f0015c5dd95..267c7369c765 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -78,9 +78,6 @@ config HAVE_KVM_IRQ_BYPASS tristate select IRQ_BYPASS_MANAGER -config HAVE_KVM_VCPU_ASYNC_IOCTL - bool - config HAVE_KVM_VCPU_RUN_PID_CHANGE bool diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a7794ffdb976..0e8b5277be3b 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -707,7 +707,7 @@ bool kvm_notify_irqfd_resampler(struct kvm *kvm, */ int kvm_irqfd_init(void) { - irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0); + irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", WQ_PERCPU, 0); if (!irqfd_cleanup_wq) return -ENOMEM; diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index fbca8c0972da..fdaea3422c30 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -1,18 +1,47 @@ // 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/mempolicy.h> +#include <linux/pseudo_fs.h> #include <linux/pagemap.h> -#include <linux/anon_inodes.h> #include "kvm_mm.h" -struct kvm_gmem { +static struct vfsmount *kvm_gmem_mnt; + +/* + * A guest_memfd instance can be associated multiple VMs, each with its own + * "view" of the underlying physical memory. + * + * The gmem's inode is effectively the raw underlying physical storage, and is + * used to track properties of the physical memory, while each gmem file is + * effectively a single VM's view of that storage, and is used to track assets + * specific to its associated VM, e.g. memslots=>gmem bindings. + */ +struct gmem_file { struct kvm *kvm; struct xarray bindings; struct list_head entry; }; +struct gmem_inode { + struct shared_policy policy; + struct inode vfs_inode; + + u64 flags; +}; + +static __always_inline struct gmem_inode *GMEM_I(struct inode *inode) +{ + return container_of(inode, struct gmem_inode, vfs_inode); +} + +#define kvm_gmem_for_each_file(f, mapping) \ + list_for_each_entry(f, &(mapping)->i_private_list, entry) + /** * folio_file_pfn - like folio_file_page, but return a pfn. * @folio: The folio which contains this index. @@ -25,6 +54,11 @@ static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index) return folio_pfn(folio) + (index & (folio_nr_pages(folio) - 1)); } +static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return gfn - slot->base_gfn + slot->gmem.pgoff; +} + static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, pgoff_t index, struct folio *folio) { @@ -77,9 +111,9 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, * The order will be passed when creating the guest_memfd, and * checked when creating memslots. */ - WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, 1 << folio_order(folio))); - index = gfn - slot->base_gfn + slot->gmem.pgoff; - index = ALIGN_DOWN(index, 1 << folio_order(folio)); + WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, folio_nr_pages(folio))); + index = kvm_gmem_get_index(slot, gfn); + index = ALIGN_DOWN(index, folio_nr_pages(folio)); r = __kvm_gmem_prepare_folio(kvm, slot, index, folio); if (!r) kvm_gmem_mark_prepared(folio); @@ -99,27 +133,45 @@ 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 = mpol_shared_policy_lookup(&GMEM_I(inode)->policy, 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 enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter(struct inode *inode) { - if ((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED) + if (GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED) return KVM_FILTER_SHARED; return KVM_FILTER_PRIVATE; } -static void __kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, +static void __kvm_gmem_invalidate_begin(struct gmem_file *f, pgoff_t start, pgoff_t end, enum kvm_gfn_range_filter attr_filter) { bool flush = false, found_memslot = false; struct kvm_memory_slot *slot; - struct kvm *kvm = gmem->kvm; + struct kvm *kvm = f->kvm; unsigned long index; - xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) { + xa_for_each_range(&f->bindings, index, slot, start, end - 1) { pgoff_t pgoff = slot->gmem.pgoff; struct kvm_gfn_range gfn_range = { @@ -150,22 +202,21 @@ static void __kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, static void kvm_gmem_invalidate_begin(struct inode *inode, pgoff_t start, pgoff_t end) { - struct list_head *gmem_list = &inode->i_mapping->i_private_list; enum kvm_gfn_range_filter attr_filter; - struct kvm_gmem *gmem; + struct gmem_file *f; attr_filter = kvm_gmem_get_invalidate_filter(inode); - list_for_each_entry(gmem, gmem_list, entry) - __kvm_gmem_invalidate_begin(gmem, start, end, attr_filter); + kvm_gmem_for_each_file(f, inode->i_mapping) + __kvm_gmem_invalidate_begin(f, start, end, attr_filter); } -static void __kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start, +static void __kvm_gmem_invalidate_end(struct gmem_file *f, pgoff_t start, pgoff_t end) { - struct kvm *kvm = gmem->kvm; + struct kvm *kvm = f->kvm; - if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { + if (xa_find(&f->bindings, &start, end - 1, XA_PRESENT)) { KVM_MMU_LOCK(kvm); kvm_mmu_invalidate_end(kvm); KVM_MMU_UNLOCK(kvm); @@ -175,11 +226,10 @@ static void __kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start, static void kvm_gmem_invalidate_end(struct inode *inode, pgoff_t start, pgoff_t end) { - struct list_head *gmem_list = &inode->i_mapping->i_private_list; - struct kvm_gmem *gmem; + struct gmem_file *f; - list_for_each_entry(gmem, gmem_list, entry) - __kvm_gmem_invalidate_end(gmem, start, end); + kvm_gmem_for_each_file(f, inode->i_mapping) + __kvm_gmem_invalidate_end(f, start, end); } static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len) @@ -277,9 +327,9 @@ static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset, static int kvm_gmem_release(struct inode *inode, struct file *file) { - struct kvm_gmem *gmem = file->private_data; + struct gmem_file *f = file->private_data; struct kvm_memory_slot *slot; - struct kvm *kvm = gmem->kvm; + struct kvm *kvm = f->kvm; unsigned long index; /* @@ -299,7 +349,7 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) filemap_invalidate_lock(inode->i_mapping); - xa_for_each(&gmem->bindings, index, slot) + xa_for_each(&f->bindings, index, slot) WRITE_ONCE(slot->gmem.file, NULL); /* @@ -307,18 +357,18 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) * Zap all SPTEs pointed at by this file. Do not free the backing * memory, as its lifetime is associated with the inode, not the file. */ - __kvm_gmem_invalidate_begin(gmem, 0, -1ul, + __kvm_gmem_invalidate_begin(f, 0, -1ul, kvm_gmem_get_invalidate_filter(inode)); - __kvm_gmem_invalidate_end(gmem, 0, -1ul); + __kvm_gmem_invalidate_end(f, 0, -1ul); - list_del(&gmem->entry); + list_del(&f->entry); filemap_invalidate_unlock(inode->i_mapping); mutex_unlock(&kvm->slots_lock); - xa_destroy(&gmem->bindings); - kfree(gmem); + xa_destroy(&f->bindings); + kfree(f); kvm_put_kvm(kvm); @@ -335,16 +385,12 @@ static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) return get_file_active(&slot->gmem.file); } -static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn) -{ - return gfn - slot->base_gfn + slot->gmem.pgoff; -} +DEFINE_CLASS(gmem_get_file, struct file *, if (_T) fput(_T), + kvm_gmem_get_file(slot), struct kvm_memory_slot *slot); static bool kvm_gmem_supports_mmap(struct inode *inode) { - const u64 flags = (u64)inode->i_private; - - return flags & GUEST_MEMFD_FLAG_MMAP; + return GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_MMAP; } static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) @@ -356,17 +402,15 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) return VM_FAULT_SIGBUS; - if (!((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED)) + if (!(GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED)) return VM_FAULT_SIGBUS; folio = kvm_gmem_get_folio(inode, vmf->pgoff); if (IS_ERR(folio)) { - int err = PTR_ERR(folio); - - if (err == -EAGAIN) + if (PTR_ERR(folio) == -EAGAIN) return VM_FAULT_RETRY; - return vmf_error(err); + return vmf_error(PTR_ERR(folio)); } if (WARN_ON_ONCE(folio_test_large(folio))) { @@ -390,8 +434,40 @@ out_folio: 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(&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 the memory policy for this index, or NULL if none is set. + * + * Returning NULL, e.g. instead of the current task's memory policy, is + * important for the .get_policy kernel ABI: it indicates that no + * explicit policy has been set via mbind() for this memory. The caller + * can then replace NULL with the default memory policy instead of the + * current task's memory policy. + */ + return mpol_shared_policy_lookup(&GMEM_I(inode)->policy, *pgoff); +} +#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) @@ -416,11 +492,6 @@ static struct file_operations kvm_gmem_fops = { .fallocate = kvm_gmem_fallocate, }; -void kvm_gmem_init(struct module *module) -{ - kvm_gmem_fops.owner = module; -} - static int kvm_gmem_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) @@ -492,8 +563,8 @@ bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm) static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) { - const char *anon_name = "[kvm-gmem]"; - struct kvm_gmem *gmem; + static const char *name = "[kvm-gmem]"; + struct gmem_file *f; struct inode *inode; struct file *file; int fd, err; @@ -502,25 +573,24 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) if (fd < 0) return fd; - gmem = kzalloc(sizeof(*gmem), GFP_KERNEL); - if (!gmem) { + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) { err = -ENOMEM; goto err_fd; } - file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem, - O_RDWR, NULL); - if (IS_ERR(file)) { - err = PTR_ERR(file); + /* __fput() will take care of fops_put(). */ + if (!fops_get(&kvm_gmem_fops)) { + err = -ENOENT; goto err_gmem; } - file->f_flags |= O_LARGEFILE; - - inode = file->f_inode; - WARN_ON(file->f_mapping != inode->i_mapping); + inode = anon_inode_make_secure_inode(kvm_gmem_mnt->mnt_sb, name, NULL); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto err_fops; + } - 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; @@ -530,16 +600,31 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) /* Unmovable mappings are supposed to be marked unevictable as well. */ WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); + GMEM_I(inode)->flags = flags; + + file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto err_inode; + } + + file->f_flags |= O_LARGEFILE; + file->private_data = f; + kvm_get_kvm(kvm); - gmem->kvm = kvm; - xa_init(&gmem->bindings); - list_add(&gmem->entry, &inode->i_mapping->i_private_list); + f->kvm = kvm; + xa_init(&f->bindings); + list_add(&f->entry, &inode->i_mapping->i_private_list); fd_install(fd, file); return fd; +err_inode: + iput(inode); +err_fops: + fops_put(&kvm_gmem_fops); err_gmem: - kfree(gmem); + kfree(f); err_fd: put_unused_fd(fd); return err; @@ -564,7 +649,7 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, { loff_t size = slot->npages << PAGE_SHIFT; unsigned long start, end; - struct kvm_gmem *gmem; + struct gmem_file *f; struct inode *inode; struct file *file; int r = -EINVAL; @@ -578,8 +663,8 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, if (file->f_op != &kvm_gmem_fops) goto err; - gmem = file->private_data; - if (gmem->kvm != kvm) + f = file->private_data; + if (f->kvm != kvm) goto err; inode = file_inode(file); @@ -593,8 +678,8 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, start = offset >> PAGE_SHIFT; end = start + slot->npages; - if (!xa_empty(&gmem->bindings) && - xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { + if (!xa_empty(&f->bindings) && + xa_find(&f->bindings, &start, end - 1, XA_PRESENT)) { filemap_invalidate_unlock(inode->i_mapping); goto err; } @@ -609,7 +694,7 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, if (kvm_gmem_supports_mmap(inode)) slot->flags |= KVM_MEMSLOT_GMEM_ONLY; - xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); + xa_store_range(&f->bindings, start, end - 1, slot, GFP_KERNEL); filemap_invalidate_unlock(inode->i_mapping); /* @@ -623,34 +708,49 @@ err: return r; } -void kvm_gmem_unbind(struct kvm_memory_slot *slot) +static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct gmem_file *f) { unsigned long start = slot->gmem.pgoff; unsigned long end = start + slot->npages; - struct kvm_gmem *gmem; - struct file *file; + + xa_store_range(&f->bindings, start, end - 1, NULL, GFP_KERNEL); /* - * Nothing to do if the underlying file was already closed (or is being - * closed right now), kvm_gmem_release() invalidates all bindings. + * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() + * cannot see this memslot. */ - file = kvm_gmem_get_file(slot); - if (!file) - return; + WRITE_ONCE(slot->gmem.file, NULL); +} - gmem = file->private_data; +void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ + /* + * Nothing to do if the underlying file was _already_ closed, as + * kvm_gmem_release() invalidates and nullifies all bindings. + */ + if (!slot->gmem.file) + return; - filemap_invalidate_lock(file->f_mapping); - xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + CLASS(gmem_get_file, file)(slot); /* - * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() - * cannot see this memslot. + * However, if the file is _being_ closed, then the bindings need to be + * removed as kvm_gmem_release() might not run until after the memslot + * is freed. Note, modifying the bindings is safe even though the file + * is dying as kvm_gmem_release() nullifies slot->gmem.file under + * slots_lock, and only puts its reference to KVM after destroying all + * bindings. I.e. reaching this point means kvm_gmem_release() hasn't + * yet destroyed the bindings or freed the gmem_file, and can't do so + * until the caller drops slots_lock. */ - WRITE_ONCE(slot->gmem.file, NULL); - filemap_invalidate_unlock(file->f_mapping); + if (!file) { + __kvm_gmem_unbind(slot, slot->gmem.file->private_data); + return; + } - fput(file); + filemap_invalidate_lock(file->f_mapping); + __kvm_gmem_unbind(slot, file->private_data); + filemap_invalidate_unlock(file->f_mapping); } /* Returns a locked folio on success. */ @@ -659,18 +759,17 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file, pgoff_t index, kvm_pfn_t *pfn, bool *is_prepared, int *max_order) { - struct file *gmem_file = READ_ONCE(slot->gmem.file); - struct kvm_gmem *gmem = file->private_data; + struct file *slot_file = READ_ONCE(slot->gmem.file); + struct gmem_file *f = file->private_data; struct folio *folio; - if (file != gmem_file) { - WARN_ON_ONCE(gmem_file); + if (file != slot_file) { + WARN_ON_ONCE(slot_file); return ERR_PTR(-EFAULT); } - gmem = file->private_data; - if (xa_load(&gmem->bindings, index) != slot) { - WARN_ON_ONCE(xa_load(&gmem->bindings, index)); + if (xa_load(&f->bindings, index) != slot) { + WARN_ON_ONCE(xa_load(&f->bindings, index)); return ERR_PTR(-EIO); } @@ -697,19 +796,17 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, int *max_order) { pgoff_t index = kvm_gmem_get_index(slot, gfn); - struct file *file = kvm_gmem_get_file(slot); struct folio *folio; bool is_prepared = false; int r = 0; + CLASS(gmem_get_file, file)(slot); if (!file) return -EFAULT; folio = __kvm_gmem_get_pfn(file, slot, index, pfn, &is_prepared, max_order); - if (IS_ERR(folio)) { - r = PTR_ERR(folio); - goto out; - } + if (IS_ERR(folio)) + return PTR_ERR(folio); if (!is_prepared) r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio); @@ -721,8 +818,6 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, else folio_put(folio); -out: - fput(file); return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); @@ -731,7 +826,6 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque) { - struct file *file; struct kvm_memory_slot *slot; void __user *p; @@ -747,7 +841,7 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long if (!kvm_slot_has_gmem(slot)) return -EINVAL; - file = kvm_gmem_get_file(slot); + CLASS(gmem_get_file, file)(slot); if (!file) return -EFAULT; @@ -805,8 +899,118 @@ put_folio_and_exit: filemap_invalidate_unlock(file->f_mapping); - fput(file); return ret && !i ? ret : i; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_populate); #endif + +static struct kmem_cache *kvm_gmem_inode_cachep; + +static void kvm_gmem_init_inode_once(void *__gi) +{ + struct gmem_inode *gi = __gi; + + /* + * Note! Don't initialize the inode with anything specific to the + * guest_memfd instance, or that might be specific to how the inode is + * used (from the VFS-layer's perspective). This hook is called only + * during the initial slab allocation, i.e. only fields/state that are + * idempotent across _all_ use of the inode _object_ can be initialized + * at this time! + */ + inode_init_once(&gi->vfs_inode); +} + +static struct inode *kvm_gmem_alloc_inode(struct super_block *sb) +{ + struct gmem_inode *gi; + + gi = alloc_inode_sb(sb, kvm_gmem_inode_cachep, GFP_KERNEL); + if (!gi) + return NULL; + + mpol_shared_policy_init(&gi->policy, NULL); + + gi->flags = 0; + return &gi->vfs_inode; +} + +static void kvm_gmem_destroy_inode(struct inode *inode) +{ + mpol_free_shared_policy(&GMEM_I(inode)->policy); +} + +static void kvm_gmem_free_inode(struct inode *inode) +{ + kmem_cache_free(kvm_gmem_inode_cachep, 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; +} + +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) +{ + struct kmem_cache_args args = { + .align = 0, + .ctor = kvm_gmem_init_inode_once, + }; + int ret; + + kvm_gmem_fops.owner = module; + kvm_gmem_inode_cachep = kmem_cache_create("kvm_gmem_inode_cache", + sizeof(struct gmem_inode), + &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; + rcu_barrier(); + kmem_cache_destroy(kvm_gmem_inode_cachep); +} diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b7a0ae2a7b20..5fcd401a5897 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -49,6 +49,7 @@ #include <linux/lockdep.h> #include <linux/kthread.h> #include <linux/suspend.h> +#include <linux/rseq.h> #include <asm/processor.h> #include <asm/ioctl.h> @@ -4026,7 +4027,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - WRITE_ONCE(kvm->last_boosted_vcpu, i); + WRITE_ONCE(kvm->last_boosted_vcpu, idx); break; } else if (yielded < 0 && !--try) { break; @@ -4434,10 +4435,10 @@ static long kvm_vcpu_ioctl(struct file *filp, return r; /* - * Some architectures have vcpu ioctls that are asynchronous to vcpu - * execution; mutex_lock() would break them. + * Let arch code handle select vCPU ioctls without holding vcpu->mutex, + * e.g. to support ioctls that can run asynchronous to vCPU execution. */ - r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg); + r = kvm_arch_vcpu_unlocked_ioctl(filp, ioctl, arg); if (r != -ENOIOCTLCMD) return r; @@ -4476,6 +4477,12 @@ static long kvm_vcpu_ioctl(struct file *filp, r = kvm_arch_vcpu_ioctl_run(vcpu); vcpu->wants_to_run = false; + /* + * FIXME: Remove this hack once all KVM architectures + * support the generic TIF bits, i.e. a dedicated TIF_RSEQ. + */ + rseq_virt_userspace_exit(); + trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; } @@ -5629,7 +5636,7 @@ static int kvm_offline_cpu(unsigned int cpu) return 0; } -static void kvm_shutdown(void) +static void kvm_shutdown(void *data) { /* * Disable hardware virtualization and set kvm_rebooting to indicate @@ -5647,7 +5654,7 @@ static void kvm_shutdown(void) on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1); } -static int kvm_suspend(void) +static int kvm_suspend(void *data) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume @@ -5664,7 +5671,7 @@ static int kvm_suspend(void) return 0; } -static void kvm_resume(void) +static void kvm_resume(void *data) { lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); @@ -5672,12 +5679,16 @@ static void kvm_resume(void) WARN_ON_ONCE(kvm_enable_virtualization_cpu()); } -static struct syscore_ops kvm_syscore_ops = { +static const struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, .shutdown = kvm_shutdown, }; +static struct syscore kvm_syscore = { + .ops = &kvm_syscore_ops, +}; + int kvm_enable_virtualization(void) { int r; @@ -5694,7 +5705,7 @@ int kvm_enable_virtualization(void) if (r) goto err_cpuhp; - register_syscore_ops(&kvm_syscore_ops); + register_syscore(&kvm_syscore); /* * Undo virtualization enabling and bail if the system is going down. @@ -5716,7 +5727,7 @@ int kvm_enable_virtualization(void) return 0; err_rebooting: - unregister_syscore_ops(&kvm_syscore_ops); + unregister_syscore(&kvm_syscore); cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); err_cpuhp: kvm_arch_disable_virtualization(); @@ -5732,7 +5743,7 @@ void kvm_disable_virtualization(void) if (--kvm_usage_count) return; - unregister_syscore_ops(&kvm_syscore_ops); + unregister_syscore(&kvm_syscore); cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); kvm_arch_disable_virtualization(); } @@ -6517,7 +6528,9 @@ 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) @@ -6538,6 +6551,8 @@ 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(); @@ -6569,6 +6584,7 @@ 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) |