#include <linux/eventfd.h>
#include <linux/blkdev.h>
#include <linux/compat.h>
-#include <linux/anon_inodes.h>
#include <linux/migrate.h>
#include <linux/ramfs.h>
#include <linux/percpu-refcount.h>
+#include <linux/mount.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
static struct kmem_cache *kiocb_cachep;
static struct kmem_cache *kioctx_cachep;
+static struct vfsmount *aio_mnt;
+
+static const struct file_operations aio_ring_fops;
+static const struct address_space_operations aio_ctx_aops;
+
+static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
+{
+ struct qstr this = QSTR_INIT("[aio]", 5);
+ struct file *file;
+ struct path path;
+ struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+
+ inode->i_mapping->a_ops = &aio_ctx_aops;
+ inode->i_mapping->private_data = ctx;
+ inode->i_size = PAGE_SIZE * nr_pages;
+
+ path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
+ if (!path.dentry) {
+ iput(inode);
+ return ERR_PTR(-ENOMEM);
+ }
+ path.mnt = mntget(aio_mnt);
+
+ d_instantiate(path.dentry, inode);
+ file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
+ if (IS_ERR(file)) {
+ path_put(&path);
+ return file;
+ }
+
+ file->f_flags = O_RDWR;
+ file->private_data = ctx;
+ return file;
+}
+
+static struct dentry *aio_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ static const struct dentry_operations ops = {
+ .d_dname = simple_dname,
+ };
+ return mount_pseudo(fs_type, "aio:", NULL, &ops, 0xa10a10a1);
+}
+
/* aio_setup
* Creates the slab caches used by the aio routines, panic on
* failure as this is done early during the boot sequence.
*/
static int __init aio_setup(void)
{
+ static struct file_system_type aio_fs = {
+ .name = "aio",
+ .mount = aio_mount,
+ .kill_sb = kill_anon_super,
+ };
+ aio_mnt = kern_mount(&aio_fs);
+ if (IS_ERR(aio_mnt))
+ panic("Failed to create aio fs mount.");
+
kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
int i;
for (i = 0; i < ctx->nr_pages; i++) {
+ struct page *page;
pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
page_count(ctx->ring_pages[i]));
- put_page(ctx->ring_pages[i]);
+ page = ctx->ring_pages[i];
+ if (!page)
+ continue;
+ ctx->ring_pages[i] = NULL;
+ put_page(page);
}
put_aio_ring_file(ctx);
unsigned long flags;
int rc;
+ rc = 0;
+
+ /* Make sure the old page hasn't already been changed */
+ spin_lock(&mapping->private_lock);
+ ctx = mapping->private_data;
+ if (ctx) {
+ pgoff_t idx;
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ idx = old->index;
+ if (idx < (pgoff_t)ctx->nr_pages) {
+ if (ctx->ring_pages[idx] != old)
+ rc = -EAGAIN;
+ } else
+ rc = -EINVAL;
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else
+ rc = -EINVAL;
+ spin_unlock(&mapping->private_lock);
+
+ if (rc != 0)
+ return rc;
+
/* Writeback must be complete */
BUG_ON(PageWriteback(old));
- put_page(old);
+ get_page(new);
- rc = migrate_page_move_mapping(mapping, new, old, NULL, mode);
+ rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
if (rc != MIGRATEPAGE_SUCCESS) {
- get_page(old);
+ put_page(new);
return rc;
}
- get_page(new);
-
/* We can potentially race against kioctx teardown here. Use the
* address_space's private data lock to protect the mapping's
* private_data.
spin_lock_irqsave(&ctx->completion_lock, flags);
migrate_page_copy(new, old);
idx = old->index;
- if (idx < (pgoff_t)ctx->nr_pages)
- ctx->ring_pages[idx] = new;
+ if (idx < (pgoff_t)ctx->nr_pages) {
+ /* And only do the move if things haven't changed */
+ if (ctx->ring_pages[idx] == old)
+ ctx->ring_pages[idx] = new;
+ else
+ rc = -EAGAIN;
+ } else
+ rc = -EINVAL;
spin_unlock_irqrestore(&ctx->completion_lock, flags);
} else
rc = -EBUSY;
spin_unlock(&mapping->private_lock);
+ if (rc == MIGRATEPAGE_SUCCESS)
+ put_page(old);
+ else
+ put_page(new);
+
return rc;
}
#endif
struct aio_ring *ring;
unsigned nr_events = ctx->max_reqs;
struct mm_struct *mm = current->mm;
- unsigned long size, populate;
+ unsigned long size, unused;
int nr_pages;
int i;
struct file *file;
if (nr_pages < 0)
return -EINVAL;
- file = anon_inode_getfile_private("[aio]", &aio_ring_fops, ctx, O_RDWR);
+ file = aio_private_file(ctx, nr_pages);
if (IS_ERR(file)) {
ctx->aio_ring_file = NULL;
return -EAGAIN;
}
- file->f_inode->i_mapping->a_ops = &aio_ctx_aops;
- file->f_inode->i_mapping->private_data = ctx;
- file->f_inode->i_size = PAGE_SIZE * (loff_t)nr_pages;
+ ctx->aio_ring_file = file;
+ nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
+ / sizeof(struct io_event);
+
+ ctx->ring_pages = ctx->internal_pages;
+ if (nr_pages > AIO_RING_PAGES) {
+ ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+ GFP_KERNEL);
+ if (!ctx->ring_pages) {
+ put_aio_ring_file(ctx);
+ return -ENOMEM;
+ }
+ }
for (i = 0; i < nr_pages; i++) {
struct page *page;
SetPageUptodate(page);
SetPageDirty(page);
unlock_page(page);
+
+ ctx->ring_pages[i] = page;
}
- ctx->aio_ring_file = file;
- nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
- / sizeof(struct io_event);
+ ctx->nr_pages = i;
- ctx->ring_pages = ctx->internal_pages;
- if (nr_pages > AIO_RING_PAGES) {
- ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
- GFP_KERNEL);
- if (!ctx->ring_pages) {
- put_aio_ring_file(ctx);
- return -ENOMEM;
- }
+ if (unlikely(i != nr_pages)) {
+ aio_free_ring(ctx);
+ return -EAGAIN;
}
ctx->mmap_size = nr_pages * PAGE_SIZE;
down_write(&mm->mmap_sem);
ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_POPULATE, 0, &populate);
+ MAP_SHARED, 0, &unused);
+ up_write(&mm->mmap_sem);
if (IS_ERR((void *)ctx->mmap_base)) {
- up_write(&mm->mmap_sem);
ctx->mmap_size = 0;
aio_free_ring(ctx);
return -EAGAIN;
pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
- /* We must do this while still holding mmap_sem for write, as we
- * need to be protected against userspace attempting to mremap()
- * or munmap() the ring buffer.
- */
- ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
- 1, 0, ctx->ring_pages, NULL);
-
- /* Dropping the reference here is safe as the page cache will hold
- * onto the pages for us. It is also required so that page migration
- * can unmap the pages and get the right reference count.
- */
- for (i = 0; i < ctx->nr_pages; i++)
- put_page(ctx->ring_pages[i]);
-
- up_write(&mm->mmap_sem);
-
- if (unlikely(ctx->nr_pages != nr_pages)) {
- aio_free_ring(ctx);
- return -EAGAIN;
- }
-
ctx->user_id = ctx->mmap_base;
ctx->nr_events = nr_events; /* trusted copy */
aio_nr += ctx->max_reqs;
spin_unlock(&aio_nr_lock);
- percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+ percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+ percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */
err = ioctx_add_table(ctx, mm);
if (err)