#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
+#include <linux/log2.h>
#include <asm/uaccess.h>
#include "internal.h"
return retval;
}
-/* Kill _all_ buffers, dirty or not.. */
+/* Kill _all_ buffers and pagecache , dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
- invalidate_bdev(bdev, 1);
+ if (bdev->bd_inode->i_mapping->nrpages == 0)
+ return;
+ invalidate_bh_lrus();
truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
}
int set_blocksize(struct block_device *bdev, int size)
{
/* Size must be a power of two, and between 512 and PAGE_SIZE */
- if (size > PAGE_SIZE || size < 512 || (size & (size-1)))
+ if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
/* Size cannot be smaller than the size supported by the device */
iov, offset, nr_segs, blkdev_get_blocks, NULL);
}
+#if 0
+static void blk_end_aio(struct bio *bio, int error)
+{
+ struct kiocb *iocb = bio->bi_private;
+ atomic_t *bio_count = &iocb->ki_bio_count;
+
+ if (bio_data_dir(bio) == READ)
+ bio_check_pages_dirty(bio);
+ else {
+ bio_release_pages(bio);
+ bio_put(bio);
+ }
+
+ /* iocb->ki_nbytes stores error code from LLDD */
+ if (error)
+ iocb->ki_nbytes = -EIO;
+
+ if (atomic_dec_and_test(bio_count)) {
+ if ((long)iocb->ki_nbytes < 0)
+ aio_complete(iocb, iocb->ki_nbytes, 0);
+ else
+ aio_complete(iocb, iocb->ki_left, 0);
+ }
+
+ return 0;
+}
+
+#define VEC_SIZE 16
+struct pvec {
+ unsigned short nr;
+ unsigned short idx;
+ struct page *page[VEC_SIZE];
+};
+
+#define PAGES_SPANNED(addr, len) \
+ (DIV_ROUND_UP((addr) + (len), PAGE_SIZE) - (addr) / PAGE_SIZE);
+
+/*
+ * get page pointer for user addr, we internally cache struct page array for
+ * (addr, count) range in pvec to avoid frequent call to get_user_pages. If
+ * internal page list is exhausted, a batch count of up to VEC_SIZE is used
+ * to get next set of page struct.
+ */
+static struct page *blk_get_page(unsigned long addr, size_t count, int rw,
+ struct pvec *pvec)
+{
+ int ret, nr_pages;
+ if (pvec->idx == pvec->nr) {
+ nr_pages = PAGES_SPANNED(addr, count);
+ nr_pages = min(nr_pages, VEC_SIZE);
+ down_read(¤t->mm->mmap_sem);
+ ret = get_user_pages(current, current->mm, addr, nr_pages,
+ rw == READ, 0, pvec->page, NULL);
+ up_read(¤t->mm->mmap_sem);
+ if (ret < 0)
+ return ERR_PTR(ret);
+ pvec->nr = ret;
+ pvec->idx = 0;
+ }
+ return pvec->page[pvec->idx++];
+}
+
+/* return a page back to pvec array */
+static void blk_unget_page(struct page *page, struct pvec *pvec)
+{
+ pvec->page[--pvec->idx] = page;
+}
+
+static ssize_t
+blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
+ loff_t pos, unsigned long nr_segs)
+{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ unsigned blkbits = blksize_bits(bdev_hardsect_size(I_BDEV(inode)));
+ unsigned blocksize_mask = (1 << blkbits) - 1;
+ unsigned long seg = 0; /* iov segment iterator */
+ unsigned long nvec; /* number of bio vec needed */
+ unsigned long cur_off; /* offset into current page */
+ unsigned long cur_len; /* I/O len of current page, up to PAGE_SIZE */
+
+ unsigned long addr; /* user iovec address */
+ size_t count; /* user iovec len */
+ size_t nbytes = iocb->ki_nbytes = iocb->ki_left; /* total xfer size */
+ loff_t size; /* size of block device */
+ struct bio *bio;
+ atomic_t *bio_count = &iocb->ki_bio_count;
+ struct page *page;
+ struct pvec pvec;
+
+ pvec.nr = 0;
+ pvec.idx = 0;
+
+ if (pos & blocksize_mask)
+ return -EINVAL;
+
+ size = i_size_read(inode);
+ if (pos + nbytes > size) {
+ nbytes = size - pos;
+ iocb->ki_left = nbytes;
+ }
+
+ /*
+ * check first non-zero iov alignment, the remaining
+ * iov alignment is checked inside bio loop below.
+ */
+ do {
+ addr = (unsigned long) iov[seg].iov_base;
+ count = min(iov[seg].iov_len, nbytes);
+ if (addr & blocksize_mask || count & blocksize_mask)
+ return -EINVAL;
+ } while (!count && ++seg < nr_segs);
+ atomic_set(bio_count, 1);
+
+ while (nbytes) {
+ /* roughly estimate number of bio vec needed */
+ nvec = (nbytes + PAGE_SIZE - 1) / PAGE_SIZE;
+ nvec = max(nvec, nr_segs - seg);
+ nvec = min(nvec, (unsigned long) BIO_MAX_PAGES);
+
+ /* bio_alloc should not fail with GFP_KERNEL flag */
+ bio = bio_alloc(GFP_KERNEL, nvec);
+ bio->bi_bdev = I_BDEV(inode);
+ bio->bi_end_io = blk_end_aio;
+ bio->bi_private = iocb;
+ bio->bi_sector = pos >> blkbits;
+same_bio:
+ cur_off = addr & ~PAGE_MASK;
+ cur_len = PAGE_SIZE - cur_off;
+ if (count < cur_len)
+ cur_len = count;
+
+ page = blk_get_page(addr, count, rw, &pvec);
+ if (unlikely(IS_ERR(page)))
+ goto backout;
+
+ if (bio_add_page(bio, page, cur_len, cur_off)) {
+ pos += cur_len;
+ addr += cur_len;
+ count -= cur_len;
+ nbytes -= cur_len;
+
+ if (count)
+ goto same_bio;
+ while (++seg < nr_segs) {
+ addr = (unsigned long) iov[seg].iov_base;
+ count = iov[seg].iov_len;
+ if (!count)
+ continue;
+ if (unlikely(addr & blocksize_mask ||
+ count & blocksize_mask)) {
+ page = ERR_PTR(-EINVAL);
+ goto backout;
+ }
+ count = min(count, nbytes);
+ goto same_bio;
+ }
+ } else {
+ blk_unget_page(page, &pvec);
+ }
+
+ /* bio is ready, submit it */
+ if (rw == READ)
+ bio_set_pages_dirty(bio);
+ atomic_inc(bio_count);
+ submit_bio(rw, bio);
+ }
+
+completion:
+ iocb->ki_left -= nbytes;
+ nbytes = iocb->ki_left;
+ iocb->ki_pos += nbytes;
+
+ blk_run_address_space(inode->i_mapping);
+ if (atomic_dec_and_test(bio_count))
+ aio_complete(iocb, nbytes, 0);
+
+ return -EIOCBQUEUED;
+
+backout:
+ /*
+ * back out nbytes count constructed so far for this bio,
+ * we will throw away current bio.
+ */
+ nbytes += bio->bi_size;
+ bio_release_pages(bio);
+ bio_put(bio);
+
+ /*
+ * if no bio was submmitted, return the error code.
+ * otherwise, proceed with pending I/O completion.
+ */
+ if (atomic_read(bio_count) == 1)
+ return PTR_ERR(page);
+ goto completion;
+}
+#endif
+
static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, blkdev_get_block, wbc);
return block_read_full_page(page, blkdev_get_block);
}
-static int blkdev_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to)
+static int blkdev_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- return block_prepare_write(page, from, to, blkdev_get_block);
+ *pagep = NULL;
+ return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+ blkdev_get_block);
}
-static int blkdev_commit_write(struct file *file, struct page *page, unsigned from, unsigned to)
+static int blkdev_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
- return block_commit_write(page, from, to);
+ int ret;
+ ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret;
}
/*
* private llseek:
- * for a block special file file->f_dentry->d_inode->i_size is zero
+ * for a block special file file->f_path.dentry->d_inode->i_size is zero
* so we compute the size by hand (just as in block_read/write above)
*/
static loff_t block_llseek(struct file *file, loff_t offset, int origin)
kmem_cache_free(bdev_cachep, bdi);
}
-static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
+static void init_once(struct kmem_cache * cachep, void *foo)
{
struct bdev_inode *ei = (struct bdev_inode *) foo;
struct block_device *bdev = &ei->bdev;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR)
- {
- memset(bdev, 0, sizeof(*bdev));
- mutex_init(&bdev->bd_mutex);
- mutex_init(&bdev->bd_mount_mutex);
- INIT_LIST_HEAD(&bdev->bd_inodes);
- INIT_LIST_HEAD(&bdev->bd_list);
+ memset(bdev, 0, sizeof(*bdev));
+ mutex_init(&bdev->bd_mutex);
+ sema_init(&bdev->bd_mount_sem, 1);
+ INIT_LIST_HEAD(&bdev->bd_inodes);
+ INIT_LIST_HEAD(&bdev->bd_list);
#ifdef CONFIG_SYSFS
- INIT_LIST_HEAD(&bdev->bd_holder_list);
+ INIT_LIST_HEAD(&bdev->bd_holder_list);
#endif
- inode_init_once(&ei->vfs_inode);
- }
+ inode_init_once(&ei->vfs_inode);
}
static inline void __bd_forget(struct inode *inode)
spin_unlock(&bdev_lock);
}
-static struct super_operations bdev_sops = {
+static const struct super_operations bdev_sops = {
.statfs = simple_statfs,
.alloc_inode = bdev_alloc_inode,
.destroy_inode = bdev_destroy_inode,
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_PANIC),
- init_once, NULL);
+ init_once);
err = register_filesystem(&bd_type);
if (err)
panic("Cannot register bdev pseudo-fs");
long nr_blockdev_pages(void)
{
- struct list_head *p;
+ struct block_device *bdev;
long ret = 0;
spin_lock(&bdev_lock);
- list_for_each(p, &all_bdevs) {
- struct block_device *bdev;
- bdev = list_entry(p, struct block_device, bd_list);
+ list_for_each_entry(bdev, &all_bdevs, bd_list) {
ret += bdev->bd_inode->i_mapping->nrpages;
}
spin_unlock(&bdev_lock);
*/
static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
{
- int ret;
+ int err;
if (!bo)
return -EINVAL;
if (!bd_holder_grab_dirs(bdev, bo))
return -EBUSY;
- ret = add_symlink(bo->sdir, bo->sdev);
- if (ret == 0) {
- ret = add_symlink(bo->hdir, bo->hdev);
- if (ret)
- del_symlink(bo->sdir, bo->sdev);
+ err = add_symlink(bo->sdir, bo->sdev);
+ if (err)
+ return err;
+
+ err = add_symlink(bo->hdir, bo->hdev);
+ if (err) {
+ del_symlink(bo->sdir, bo->sdev);
+ return err;
}
- if (ret == 0)
- list_add_tail(&bo->list, &bdev->bd_holder_list);
- return ret;
+
+ list_add_tail(&bo->list, &bdev->bd_holder_list);
+ return 0;
}
/**
static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
struct kobject *kobj)
{
- int res;
+ int err;
struct bd_holder *bo, *found;
if (!kobj)
return -ENOMEM;
mutex_lock(&bdev->bd_mutex);
- res = bd_claim(bdev, holder);
- if (res == 0) {
- found = find_bd_holder(bdev, bo);
- if (found == NULL) {
- res = add_bd_holder(bdev, bo);
- if (res)
- bd_release(bdev);
- }
- }
- if (res || found)
- free_bd_holder(bo);
- mutex_unlock(&bdev->bd_mutex);
+ err = bd_claim(bdev, holder);
+ if (err)
+ goto fail;
- return res;
+ found = find_bd_holder(bdev, bo);
+ if (found)
+ goto fail;
+
+ err = add_bd_holder(bdev, bo);
+ if (err)
+ bd_release(bdev);
+ else
+ bo = NULL;
+fail:
+ mutex_unlock(&bdev->bd_mutex);
+ free_bd_holder(bo);
+ return err;
}
/**
static void bd_release_from_kobject(struct block_device *bdev,
struct kobject *kobj)
{
- struct bd_holder *bo;
-
if (!kobj)
return;
mutex_lock(&bdev->bd_mutex);
bd_release(bdev);
- if ((bo = del_bd_holder(bdev, kobj)))
- free_bd_holder(bo);
+ free_bd_holder(del_bd_holder(bdev, kobj));
mutex_unlock(&bdev->bd_mutex);
}
static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
int for_part);
+static int __blkdev_put(struct block_device *bdev, int for_part);
+
+/*
+ * bd_mutex locking:
+ *
+ * mutex_lock(part->bd_mutex)
+ * mutex_lock_nested(whole->bd_mutex, 1)
+ */
static int do_open(struct block_device *bdev, struct file *file, int for_part)
{
bdev->bd_disk = NULL;
bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
if (bdev != bdev->bd_contains)
- blkdev_put(bdev->bd_contains);
+ __blkdev_put(bdev->bd_contains, 1);
bdev->bd_contains = NULL;
put_disk(disk);
module_put(owner);
struct dentry fake_dentry = {};
fake_file.f_mode = mode;
fake_file.f_flags = flags;
- fake_file.f_dentry = &fake_dentry;
+ fake_file.f_path.dentry = &fake_dentry;
fake_dentry.d_inode = bdev->bd_inode;
return do_open(bdev, &fake_file, for_part);
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
.sync_page = block_sync_page,
- .prepare_write = blkdev_prepare_write,
- .commit_write = blkdev_commit_write,
+ .write_begin = blkdev_write_begin,
+ .write_end = blkdev_write_end,
.writepages = generic_writepages,
.direct_IO = blkdev_direct_IO,
};
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_blkdev_ioctl,
#endif
- .sendfile = generic_file_sendfile,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
};
res = invalidate_inodes(sb);
drop_super(sb);
}
- invalidate_bdev(bdev, 0);
+ invalidate_bdev(bdev);
return res;
}
EXPORT_SYMBOL(__invalidate_device);