From: Nikita Kalyazin kalyazin@amazon.com
write syscall populates guest_memfd with user-supplied data in a generic way, ie no vendor-specific preparation is performed. This is supposed to be used in non-CoCo setups where guest memory is not hardware-encrypted.
The following behaviour is implemented: - only page-aligned count and offset are allowed - if the memory is already allocated, the call will successfully populate it - if the memory is not allocated, the call will both allocate and populate - if the memory is already populated, the call will not repopulate it
Signed-off-by: Nikita Kalyazin kalyazin@amazon.com --- virt/kvm/guest_memfd.c | 64 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 63 insertions(+), 1 deletion(-)
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 08a6bc7d25b6..a2e86ec13e4b 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -379,7 +379,9 @@ static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma) }
static struct file_operations kvm_gmem_fops = { - .mmap = kvm_gmem_mmap, + .mmap = kvm_gmem_mmap, + .llseek = default_llseek, + .write_iter = generic_perform_write, .open = generic_file_open, .release = kvm_gmem_release, .fallocate = kvm_gmem_fallocate, @@ -390,6 +392,63 @@ void kvm_gmem_init(struct module *module) kvm_gmem_fops.owner = module; }
+static int kvm_kmem_gmem_write_begin(const struct kiocb *kiocb, + struct address_space *mapping, + loff_t pos, unsigned int len, + struct folio **foliop, + void **fsdata) +{ + struct file *file = kiocb->ki_filp; + pgoff_t index = pos >> PAGE_SHIFT; + struct folio *folio; + + if (!PAGE_ALIGNED(pos) || len != PAGE_SIZE) + return -EINVAL; + + if (pos + len > i_size_read(file_inode(file))) + return -EINVAL; + + folio = kvm_gmem_get_folio(file_inode(file), index); + if (IS_ERR(folio)) + return -EFAULT; + + if (WARN_ON_ONCE(folio_test_large(folio))) { + folio_unlock(folio); + folio_put(folio); + return -EFAULT; + } + + if (folio_test_uptodate(folio)) { + folio_unlock(folio); + folio_put(folio); + return -ENOSPC; + } + + *foliop = folio; + return 0; +} + +static int kvm_kmem_gmem_write_end(const struct kiocb *kiocb, + struct address_space *mapping, + loff_t pos, unsigned int len, + unsigned int copied, + struct folio *folio, void *fsdata) +{ + if (copied) { + if (copied < len) { + unsigned int from = pos & (PAGE_SIZE - 1); + + folio_zero_range(folio, from + copied, len - copied); + } + kvm_gmem_mark_prepared(folio); + } + + folio_unlock(folio); + folio_put(folio); + + return copied; +} + static int kvm_gmem_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) @@ -442,6 +501,8 @@ static void kvm_gmem_free_folio(struct folio *folio)
static const struct address_space_operations kvm_gmem_aops = { .dirty_folio = noop_dirty_folio, + .write_begin = kvm_kmem_gmem_write_begin, + .write_end = kvm_kmem_gmem_write_end, .migrate_folio = kvm_gmem_migrate_folio, .error_remove_folio = kvm_gmem_error_folio, #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE @@ -489,6 +550,7 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) }
file->f_flags |= O_LARGEFILE; + file->f_mode |= FMODE_LSEEK | FMODE_PWRITE;
inode = file->f_inode; WARN_ON(file->f_mapping != inode->i_mapping);