btrfs: make compression path to be subpage compatible

Currently btrfs compression path is not really subpage compatible, every
thing is still done in page unit.

That's fine for regular sector size and subpage routine. As even for
subpage routine compression is only enabled if the whole range is page
aligned, so reading the page cache in page unit is totally fine.

However in preparation for the future subpage perfect compression
support, we need to change the compression routine to properly handle a
subpage range.

This patch would prepare both zlib and zstd to only read the subpage
range for compression.
Lzo is already doing subpage aware read, as lzo's on-disk format is
already sectorsize dependent.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

3 files changed, 37 insertions, 9 deletions

diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index cfdc64319186..5d01f092ae13 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -82,6 +82,14 @@ static inline unsigned int btrfs_compress_level(unsigned int type_level)
 	return ((type_level & 0xF0) >> 4);
 }
 
+/* @range_end must be exclusive. */
+static inline u32 btrfs_calc_input_length(u64 range_end, u64 cur)
+{
+	u64 page_end = round_down(cur, PAGE_SIZE) + PAGE_SIZE;
+
+	return min(range_end, page_end) - cur;
+}
+
 int __init btrfs_init_compress(void);
 void __cold btrfs_exit_compress(void);
 
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 30971dd741e2..ee80d064b954 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -20,6 +20,8 @@
 #include <linux/refcount.h>
 #include "btrfs_inode.h"
 #include "compression.h"
+#include "fs.h"
+#include "subpage.h"
 
 /* workspace buffer size for s390 zlib hardware support */
 #define ZLIB_DFLTCC_BUF_SIZE    (4 * PAGE_SIZE)
@@ -108,6 +110,7 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
 	unsigned long len = *total_out;
 	unsigned long nr_dest_folios = *out_folios;
 	const unsigned long max_out = nr_dest_folios * PAGE_SIZE;
+	const u64 orig_end = start + len;
 
 	*out_folios = 0;
 	*total_out = 0;
@@ -153,6 +156,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
 			if (in_buf_folios > 1) {
 				int i;
 
+				/* S390 hardware acceleration path, not subpage. */
+				ASSERT(!btrfs_is_subpage(
+						inode_to_fs_info(mapping->host),
+						mapping));
 				for (i = 0; i < in_buf_folios; i++) {
 					if (data_in) {
 						kunmap_local(data_in);
@@ -167,9 +174,14 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
 					copy_page(workspace->buf + i * PAGE_SIZE,
 						  data_in);
 					start += PAGE_SIZE;
+					workspace->strm.avail_in =
+						(in_buf_folios << PAGE_SHIFT);
 				}
 				workspace->strm.next_in = workspace->buf;
 			} else {
+				unsigned int pg_off;
+				unsigned int cur_len;
+
 				if (data_in) {
 					kunmap_local(data_in);
 					folio_put(in_folio);
@@ -179,12 +191,13 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
 						start, &in_folio);
 				if (ret < 0)
 					goto out;
-				data_in = kmap_local_folio(in_folio, 0);
+				pg_off = offset_in_page(start);
+				cur_len = btrfs_calc_input_length(orig_end, start);
+				data_in = kmap_local_folio(in_folio, pg_off);
 				start += PAGE_SIZE;
 				workspace->strm.next_in = data_in;
+				workspace->strm.avail_in = cur_len;
 			}
-			workspace->strm.avail_in = min(bytes_left,
-						       (unsigned long) workspace->buf_size);
 		}
 
 		ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 2a079561b2b1..05cf7cebc17c 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -389,7 +389,10 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping,
 	unsigned long tot_out = 0;
 	unsigned long len = *total_out;
 	const unsigned long nr_dest_folios = *out_folios;
+	const u64 orig_end = start + len;
 	unsigned long max_out = nr_dest_folios * PAGE_SIZE;
+	unsigned int pg_off;
+	unsigned int cur_len;
 	zstd_parameters params = zstd_get_btrfs_parameters(workspace->req_level,
 							   len);
 
@@ -415,9 +418,11 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping,
 	ret = btrfs_compress_filemap_get_folio(mapping, start, &in_folio);
 	if (ret < 0)
 		goto out;
-	workspace->in_buf.src = kmap_local_folio(in_folio, 0);
+	pg_off = offset_in_page(start);
+	cur_len = btrfs_calc_input_length(orig_end, start);
+	workspace->in_buf.src = kmap_local_folio(in_folio, pg_off);
 	workspace->in_buf.pos = 0;
-	workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
+	workspace->in_buf.size = cur_len;
 
 	/* Allocate and map in the output buffer */
 	out_folio = btrfs_alloc_compr_folio();
@@ -494,14 +499,16 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping,
 			kunmap_local(workspace->in_buf.src);
 			workspace->in_buf.src = NULL;
 			folio_put(in_folio);
-			start += PAGE_SIZE;
-			len -= PAGE_SIZE;
+			start += cur_len;
+			len -= cur_len;
 			ret = btrfs_compress_filemap_get_folio(mapping, start, &in_folio);
 			if (ret < 0)
 				goto out;
-			workspace->in_buf.src = kmap_local_folio(in_folio, 0);
+			pg_off = offset_in_page(start);
+			cur_len = btrfs_calc_input_length(orig_end, start);
+			workspace->in_buf.src = kmap_local_folio(in_folio, pg_off);
 			workspace->in_buf.pos = 0;
-			workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
+			workspace->in_buf.size = cur_len;
 		}
 	}
 	while (1) {