Btrfs: reuse cmp workspace in EXTENT_SAME ioctl

We support big dedup requests by splitting range to smaller parts, and
call dedupe logic on each of them.

Instead of repeated allocation and deallocation, allocate once at the
beginning and reuse in the iteration.
Signed-off-by: NTimofey Titovets <nefelim4ag@gmail.com>
Reviewed-by: NDavid Sterba <dsterba@suse.com>
Signed-off-by: NDavid Sterba <dsterba@suse.com>

fs/btrfs/ioctl.c

@@ -2914,8 +2914,6 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 			put_page(pg);
 		}
 	}
-	kfree(cmp->src_pages);
-	kfree(cmp->dst_pages);
 }
 
 static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
@@ -2924,40 +2922,14 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 {
 	int ret;
 	int num_pages = PAGE_ALIGN(len) >> PAGE_SHIFT;
-	struct page **src_pgarr, **dst_pgarr;
 
-	/*
-	 * We must gather up all the pages before we initiate our
-	 * extent locking. We use an array for the page pointers. Size
-	 * of the array is bounded by len, which is in turn bounded by
-	 * BTRFS_MAX_DEDUPE_LEN.
-	 */
-	src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
-	dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
-	if (!src_pgarr || !dst_pgarr) {
-		kfree(src_pgarr);
-		kfree(dst_pgarr);
-		return -ENOMEM;
-	}
 	cmp->num_pages = num_pages;
-	cmp->src_pages = src_pgarr;
-	cmp->dst_pages = dst_pgarr;
-
-	/*
-	 * If deduping ranges in the same inode, locking rules make it mandatory
-	 * to always lock pages in ascending order to avoid deadlocks with
-	 * concurrent tasks (such as starting writeback/delalloc).
-	 */
-	if (src == dst && dst_loff < loff) {
-		swap(src_pgarr, dst_pgarr);
-		swap(loff, dst_loff);
-	}
 
-	ret = gather_extent_pages(src, src_pgarr, cmp->num_pages, loff);
+	ret = gather_extent_pages(src, cmp->src_pages, num_pages, loff);
 	if (ret)
 		goto out;
 
-	ret = gather_extent_pages(dst, dst_pgarr, cmp->num_pages, dst_loff);
+	ret = gather_extent_pages(dst, cmp->dst_pages, num_pages, dst_loff);
 
 out:
 	if (ret)
@@ -3028,11 +3000,11 @@ static int extent_same_check_offsets(struct inode *inode, u64 off, u64 *plen,
 }
 
 static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
-			       struct inode *dst, u64 dst_loff)
+				   struct inode *dst, u64 dst_loff,
+				   struct cmp_pages *cmp)
 {
 	int ret;
 	u64 len = olen;
-	struct cmp_pages cmp;
 	bool same_inode = (src == dst);
 	u64 same_lock_start = 0;
 	u64 same_lock_len = 0;
@@ -3072,7 +3044,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 	}
 
 again:
-	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
+	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, cmp);
 	if (ret)
 		return ret;
 
@@ -3095,7 +3067,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 		 * Ranges in the io trees already unlocked. Now unlock all
 		 * pages before waiting for all IO to complete.
 		 */
-		btrfs_cmp_data_free(&cmp);
+		btrfs_cmp_data_free(cmp);
 		if (same_inode) {
 			btrfs_wait_ordered_range(src, same_lock_start,
 						 same_lock_len);
@@ -3108,12 +3080,12 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 	ASSERT(ret == 0);
 	if (WARN_ON(ret)) {
 		/* ranges in the io trees already unlocked */
-		btrfs_cmp_data_free(&cmp);
+		btrfs_cmp_data_free(cmp);
 		return ret;
 	}
 
 	/* pass original length for comparison so we stay within i_size */
-	ret = btrfs_cmp_data(olen, &cmp);
+	ret = btrfs_cmp_data(olen, cmp);
 	if (ret == 0)
 		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
 
@@ -3123,7 +3095,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 	else
 		btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
 
-	btrfs_cmp_data_free(&cmp);
+	btrfs_cmp_data_free(cmp);
 
 	return ret;
 }
@@ -3134,6 +3106,8 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 			     struct inode *dst, u64 dst_loff)
 {
 	int ret;
+	struct cmp_pages cmp;
+	int num_pages = PAGE_ALIGN(BTRFS_MAX_DEDUPE_LEN) >> PAGE_SHIFT;
 	bool same_inode = (src == dst);
 	u64 i, tail_len, chunk_count;
 
@@ -3154,10 +3128,33 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 
 	tail_len = olen % BTRFS_MAX_DEDUPE_LEN;
 	chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN);
+	if (chunk_count == 0)
+		num_pages = PAGE_ALIGN(tail_len) >> PAGE_SHIFT;
+
+	/*
+	 * If deduping ranges in the same inode, locking rules make it
+	 * mandatory to always lock pages in ascending order to avoid deadlocks
+	 * with concurrent tasks (such as starting writeback/delalloc).
+	 */
+	if (same_inode && dst_loff < loff)
+		swap(loff, dst_loff);
+
+	/*
+	 * We must gather up all the pages before we initiate our extent
+	 * locking. We use an array for the page pointers. Size of the array is
+	 * bounded by len, which is in turn bounded by BTRFS_MAX_DEDUPE_LEN.
+	 */
+	cmp.src_pages = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
+	cmp.dst_pages = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!cmp.src_pages || !cmp.dst_pages) {
+		kfree(cmp.src_pages);
+		kfree(cmp.dst_pages);
+		return -ENOMEM;
+	}
 
 	for (i = 0; i < chunk_count; i++) {
 		ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
-					      dst, dst_loff);
+					      dst, dst_loff, &cmp);
 		if (ret)
 			goto out_unlock;
 
@@ -3166,7 +3163,8 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 	}
 
 	if (tail_len > 0)
-		ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff);
+		ret = btrfs_extent_same_range(src, loff, tail_len, dst,
+					      dst_loff, &cmp);
 
 out_unlock:
 	if (same_inode)
@@ -3174,6 +3172,9 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 	else
 		btrfs_double_inode_unlock(src, dst);
 
+	kfree(cmp.src_pages);
+	kfree(cmp.dst_pages);
+
 	return ret;
 }