return page;
}
-/*
- * dax_clear_sectors() is called from within transaction context from XFS,
- * and hence this means the stack from this point must follow GFP_NOFS
- * semantics for all operations.
- */
-int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
-{
- struct blk_dax_ctl dax = {
- .sector = _sector,
- .size = _size,
- };
-
- might_sleep();
- do {
- long count, sz;
-
- count = dax_map_atomic(bdev, &dax);
- if (count < 0)
- return count;
- sz = min_t(long, count, SZ_128K);
- clear_pmem(dax.addr, sz);
- dax.size -= sz;
- dax.sector += sz / 512;
- dax_unmap_atomic(bdev, &dax);
- cond_resched();
- } while (dax.size);
-
- wmb_pmem();
- return 0;
-}
-EXPORT_SYMBOL_GPL(dax_clear_sectors);
-
static bool buffer_written(struct buffer_head *bh)
{
return buffer_mapped(bh) && !buffer_unwritten(bh);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
- if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
- struct address_space *mapping = inode->i_mapping;
+ if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
inode_lock(inode);
- retval = filemap_write_and_wait_range(mapping, pos, end - 1);
- if (retval) {
- inode_unlock(inode);
- goto out;
- }
- }
/* Protects against truncate */
if (!(flags & DIO_SKIP_DIO_COUNT))
if (!(flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(inode);
- out:
return retval;
}
EXPORT_SYMBOL_GPL(dax_do_io);
static int dax_load_hole(struct address_space *mapping, struct page *page,
struct vm_fault *vmf)
{
- unsigned long size;
- struct inode *inode = mapping->host;
if (!page)
page = find_or_create_page(mapping, vmf->pgoff,
GFP_KERNEL | __GFP_ZERO);
if (!page)
return VM_FAULT_OOM;
- /* Recheck i_size under page lock to avoid truncate race */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (vmf->pgoff >= size) {
- unlock_page(page);
- put_page(page);
- return VM_FAULT_SIGBUS;
- }
vmf->page = page;
return VM_FAULT_LOCKED;
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
- pgoff_t size;
int error;
i_mmap_lock_read(mapping);
- /*
- * Check truncate didn't happen while we were allocating a block.
- * If it did, this block may or may not be still allocated to the
- * file. We can't tell the filesystem to free it because we can't
- * take i_mutex here. In the worst case, the file still has blocks
- * allocated past the end of the file.
- */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (unlikely(vmf->pgoff >= size)) {
- error = -EIO;
- goto out;
- }
-
if (dax_map_atomic(bdev, &dax) < 0) {
error = PTR_ERR(dax.addr);
goto out;
put_page(page);
goto repeat;
}
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (unlikely(vmf->pgoff >= size)) {
- /*
- * We have a struct page covering a hole in the file
- * from a read fault and we've raced with a truncate
- */
- error = -EIO;
- goto unlock_page;
- }
}
error = get_block(inode, block, &bh, 0);
if (error)
goto unlock_page;
vmf->page = page;
- if (!page) {
+ if (!page)
i_mmap_lock_read(mapping);
- /* Check we didn't race with truncate */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >>
- PAGE_SHIFT;
- if (vmf->pgoff >= size) {
- i_mmap_unlock_read(mapping);
- error = -EIO;
- goto out;
- }
- }
return VM_FAULT_LOCKED;
}
i_mmap_lock_read(mapping);
- /*
- * If a truncate happened while we were allocating blocks, we may
- * leave blocks allocated to the file that are beyond EOF. We can't
- * take i_mutex here, so just leave them hanging; they'll be freed
- * when the file is deleted.
- */
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (pgoff >= size) {
- result = VM_FAULT_SIGBUS;
- goto out;
- }
- if ((pgoff | PG_PMD_COLOUR) >= size) {
- dax_pmd_dbg(&bh, address,
- "offset + huge page size > file size");
- goto fallback;
- }
-
if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
spinlock_t *ptl;
pmd_t entry;
long length = dax_map_atomic(bdev, &dax);
if (length < 0) {
- result = VM_FAULT_SIGBUS;
- goto out;
+ dax_pmd_dbg(&bh, address, "dax-error fallback");
+ goto fallback;
}
if (length < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "dax-length too small");
}
EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
+static bool dax_range_is_aligned(struct block_device *bdev,
+ unsigned int offset, unsigned int length)
+{
+ unsigned short sector_size = bdev_logical_block_size(bdev);
+
+ if (!IS_ALIGNED(offset, sector_size))
+ return false;
+ if (!IS_ALIGNED(length, sector_size))
+ return false;
+
+ return true;
+}
+
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+ unsigned int offset, unsigned int length)
+{
+ struct blk_dax_ctl dax = {
+ .sector = sector,
+ .size = PAGE_SIZE,
+ };
+
+ if (dax_range_is_aligned(bdev, offset, length)) {
+ sector_t start_sector = dax.sector + (offset >> 9);
+
+ return blkdev_issue_zeroout(bdev, start_sector,
+ length >> 9, GFP_NOFS, true);
+ } else {
+ if (dax_map_atomic(bdev, &dax) < 0)
+ return PTR_ERR(dax.addr);
+ clear_pmem(dax.addr + offset, length);
+ wmb_pmem();
+ dax_unmap_atomic(bdev, &dax);
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__dax_zero_page_range);
+
/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
err = get_block(inode, index, &bh, 0);
- if (err < 0)
+ if (err < 0 || !buffer_written(&bh))
return err;
- if (buffer_written(&bh)) {
- struct block_device *bdev = bh.b_bdev;
- struct blk_dax_ctl dax = {
- .sector = to_sector(&bh, inode),
- .size = PAGE_SIZE,
- };
- if (dax_map_atomic(bdev, &dax) < 0)
- return PTR_ERR(dax.addr);
- clear_pmem(dax.addr + offset, length);
- wmb_pmem();
- dax_unmap_atomic(bdev, &dax);
- }
-
- return 0;
+ return __dax_zero_page_range(bh.b_bdev, to_sector(&bh, inode),
+ offset, length);
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);