btrfs: offline dedupe

This patch adds an ioctl, BTRFS_IOC_FILE_EXTENT_SAME which will try to
de-duplicate a list of extents across a range of files.

Internally, the ioctl re-uses code from the clone ioctl. This avoids
rewriting a large chunk of extent handling code.

Userspace passes in an array of file, offset pairs along with a length
argument. The ioctl will then (for each dedupe) do a byte-by-byte comparison
of the user data before deduping the extent. Status and number of bytes
deduped are returned for each operation.
Signed-off-by: Mark Fasheh <mfasheh@suse.de>
Reviewed-by: Zach Brown <zab@redhat.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

fs/btrfs/ioctl.c

@@ -43,6 +43,7 @@
 #include <linux/blkdev.h>
 #include <linux/uuid.h>
 #include <linux/btrfs.h>
+#include <linux/uaccess.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -57,6 +58,9 @@
 #include "send.h"
 #include "dev-replace.h"
 
+static int btrfs_clone(struct inode *src, struct inode *inode,
+		       u64 off, u64 olen, u64 olen_aligned, u64 destoff);
+
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
 {
@@ -2470,6 +2474,34 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
 	return ret;
 }
 
+static struct page *extent_same_get_page(struct inode *inode, u64 off)
+{
+	struct page *page;
+	pgoff_t index;
+	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+
+	index = off >> PAGE_CACHE_SHIFT;
+
+	page = grab_cache_page(inode->i_mapping, index);
+	if (!page)
+		return NULL;
+
+	if (!PageUptodate(page)) {
+		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
+						 0))
+			return NULL;
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			unlock_page(page);
+			page_cache_release(page);
+			return NULL;
+		}
+	}
+	unlock_page(page);
+
+	return page;
+}
+
 static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 {
 	/* do any pending delalloc/csum calc on src, one way or
@@ -2490,6 +2522,251 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 	}
 }
 
+static void btrfs_double_unlock(struct inode *inode1, u64 loff1,
+				struct inode *inode2, u64 loff2, u64 len)
+{
+	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+
+	mutex_unlock(&inode1->i_mutex);
+	mutex_unlock(&inode2->i_mutex);
+}
+
+static void btrfs_double_lock(struct inode *inode1, u64 loff1,
+			      struct inode *inode2, u64 loff2, u64 len)
+{
+	if (inode1 < inode2) {
+		swap(inode1, inode2);
+		swap(loff1, loff2);
+	}
+
+	mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+	lock_extent_range(inode1, loff1, len);
+	if (inode1 != inode2) {
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+		lock_extent_range(inode2, loff2, len);
+	}
+}
+
+static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
+			  u64 dst_loff, u64 len)
+{
+	int ret = 0;
+	struct page *src_page, *dst_page;
+	unsigned int cmp_len = PAGE_CACHE_SIZE;
+	void *addr, *dst_addr;
+
+	while (len) {
+		if (len < PAGE_CACHE_SIZE)
+			cmp_len = len;
+
+		src_page = extent_same_get_page(src, loff);
+		if (!src_page)
+			return -EINVAL;
+		dst_page = extent_same_get_page(dst, dst_loff);
+		if (!dst_page) {
+			page_cache_release(src_page);
+			return -EINVAL;
+		}
+		addr = kmap_atomic(src_page);
+		dst_addr = kmap_atomic(dst_page);
+
+		flush_dcache_page(src_page);
+		flush_dcache_page(dst_page);
+
+		if (memcmp(addr, dst_addr, cmp_len))
+			ret = BTRFS_SAME_DATA_DIFFERS;
+
+		kunmap_atomic(addr);
+		kunmap_atomic(dst_addr);
+		page_cache_release(src_page);
+		page_cache_release(dst_page);
+
+		if (ret)
+			break;
+
+		loff += cmp_len;
+		dst_loff += cmp_len;
+		len -= cmp_len;
+	}
+
+	return ret;
+}
+
+static int extent_same_check_offsets(struct inode *inode, u64 off, u64 len)
+{
+	u64 bs = BTRFS_I(inode)->root->fs_info->sb->s_blocksize;
+
+	if (off + len > inode->i_size || off + len < off)
+		return -EINVAL;
+	/* Check that we are block aligned - btrfs_clone() requires this */
+	if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int btrfs_extent_same(struct inode *src, u64 loff, u64 len,
+			     struct inode *dst, u64 dst_loff)
+{
+	int ret;
+
+	/*
+	 * btrfs_clone() can't handle extents in the same file
+	 * yet. Once that works, we can drop this check and replace it
+	 * with a check for the same inode, but overlapping extents.
+	 */
+	if (src == dst)
+		return -EINVAL;
+
+	btrfs_double_lock(src, loff, dst, dst_loff, len);
+
+	ret = extent_same_check_offsets(src, loff, len);
+	if (ret)
+		goto out_unlock;
+
+	ret = extent_same_check_offsets(dst, dst_loff, len);
+	if (ret)
+		goto out_unlock;
+
+	/* don't make the dst file partly checksummed */
+	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+	    (BTRFS_I(dst)->flags & BTRFS_INODE_NODATASUM)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	ret = btrfs_cmp_data(src, loff, dst, dst_loff, len);
+	if (ret == 0)
+		ret = btrfs_clone(src, dst, loff, len, len, dst_loff);
+
+out_unlock:
+	btrfs_double_unlock(src, loff, dst, dst_loff, len);
+
+	return ret;
+}
+
+#define BTRFS_MAX_DEDUPE_LEN	(16 * 1024 * 1024)
+
+static long btrfs_ioctl_file_extent_same(struct file *file,
+					 void __user *argp)
+{
+	struct btrfs_ioctl_same_args *args = argp;
+	struct btrfs_ioctl_same_args same;
+	struct btrfs_ioctl_same_extent_info info;
+	struct inode *src = file->f_dentry->d_inode;
+	struct file *dst_file = NULL;
+	struct inode *dst;
+	u64 off;
+	u64 len;
+	int i;
+	int ret;
+	u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
+	bool is_admin = capable(CAP_SYS_ADMIN);
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EINVAL;
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
+	if (copy_from_user(&same,
+			   (struct btrfs_ioctl_same_args __user *)argp,
+			   sizeof(same))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	off = same.logical_offset;
+	len = same.length;
+
+	/*
+	 * Limit the total length we will dedupe for each operation.
+	 * This is intended to bound the total time spent in this
+	 * ioctl to something sane.
+	 */
+	if (len > BTRFS_MAX_DEDUPE_LEN)
+		len = BTRFS_MAX_DEDUPE_LEN;
+
+	if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
+		/*
+		 * Btrfs does not support blocksize < page_size. As a
+		 * result, btrfs_cmp_data() won't correctly handle
+		 * this situation without an update.
+		 */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = -EISDIR;
+	if (S_ISDIR(src->i_mode))
+		goto out;
+
+	ret = -EACCES;
+	if (!S_ISREG(src->i_mode))
+		goto out;
+
+	ret = 0;
+	for (i = 0; i < same.dest_count; i++) {
+		if (copy_from_user(&info, &args->info[i], sizeof(info))) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		info.bytes_deduped = 0;
+
+		dst_file = fget(info.fd);
+		if (!dst_file) {
+			info.status = -EBADF;
+			goto next;
+		}
+
+		if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
+			info.status = -EINVAL;
+			goto next;
+		}
+
+		info.status = -EXDEV;
+		if (file->f_path.mnt != dst_file->f_path.mnt)
+			goto next;
+
+		dst = dst_file->f_dentry->d_inode;
+		if (src->i_sb != dst->i_sb)
+			goto next;
+
+		if (S_ISDIR(dst->i_mode)) {
+			info.status = -EISDIR;
+			goto next;
+		}
+
+		if (!S_ISREG(dst->i_mode)) {
+			info.status = -EACCES;
+			goto next;
+		}
+
+		info.status = btrfs_extent_same(src, off, len, dst,
+						info.logical_offset);
+		if (info.status == 0)
+			info.bytes_deduped += len;
+
+next:
+		if (dst_file)
+			fput(dst_file);
+
+		if (__put_user_unaligned(info.status, &args->info[i].status) ||
+		    __put_user_unaligned(info.bytes_deduped,
+					 &args->info[i].bytes_deduped)) {
+			ret = -EFAULT;
+			goto out;
+		}                                                               
+	}
+
+out:
+	mnt_drop_write_file(file);
+	return ret;
+}
+
 /**
  * btrfs_clone() - clone a range from inode file to another
  *
@@ -4242,6 +4519,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_get_fslabel(file, argp);
 	case BTRFS_IOC_SET_FSLABEL:
 		return btrfs_ioctl_set_fslabel(file, argp);
+	case BTRFS_IOC_FILE_EXTENT_SAME:
+		return btrfs_ioctl_file_extent_same(file, argp);
 	}
 
 	return -ENOTTY;

include/uapi/linux/btrfs.h

@@ -305,6 +305,31 @@ struct btrfs_ioctl_clone_range_args {
 #define BTRFS_DEFRAG_RANGE_COMPRESS 1
 #define BTRFS_DEFRAG_RANGE_START_IO 2
 
+#define BTRFS_SAME_DATA_DIFFERS	1
+/* For extent-same ioctl */
+struct btrfs_ioctl_same_extent_info {
+	__s64 fd;		/* in - destination file */
+	__u64 logical_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file */
+	/* status of this dedupe operation:
+	 * 0 if dedup succeeds
+	 * < 0 for error
+	 * == BTRFS_SAME_DATA_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;
+};
+
+struct btrfs_ioctl_same_args {
+	__u64 logical_offset;	/* in - start of extent in source */
+	__u64 length;		/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;
+	__u32 reserved2;
+	struct btrfs_ioctl_same_extent_info info[0];
+};
+
 struct btrfs_ioctl_space_info {
 	__u64 flags;
 	__u64 total_bytes;
@@ -579,4 +604,7 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 				      struct btrfs_ioctl_get_dev_stats)
 #define BTRFS_IOC_DEV_REPLACE _IOWR(BTRFS_IOCTL_MAGIC, 53, \
 				    struct btrfs_ioctl_dev_replace_args)
+#define BTRFS_IOC_FILE_EXTENT_SAME _IOWR(BTRFS_IOCTL_MAGIC, 54, \
+					 struct btrfs_ioctl_same_args)
+
 #endif /* _UAPI_LINUX_BTRFS_H */