[to-be-updated] btrfs-use-larger-zlib-buffer-for-s390-hardware-compression.patch removed from -mm tree

[to-be-updated] btrfs-use-larger-zlib-buffer-for-s390-hardware-compression.patch removed from -mm tree

[akpm]

The patch titled
     Subject: btrfs: use larger zlib buffer for s390 hardware compression
has been removed from the -mm tree.  Its filename was
     btrfs-use-larger-zlib-buffer-for-s390-hardware-compression.patch

This patch was dropped because an updated version will be merged

------------------------------------------------------
From: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Subject: btrfs: use larger zlib buffer for s390 hardware compression

Due to the small size of zlib buffer (1 page) set in btrfs code, s390
hardware compression is rather limited in terms of performance. 
Increasing the buffer size to 4 pages when s390 zlib hardware support is
enabled would bring significant benefit to btrfs zlib (up to 60% better
performance compared to the PAGE_SIZE buffer).  In case of memory pressure
we fall back to a single page buffer during workspace allocation.

Link: http://lkml.kernel.org/r/20191209152948.37080-7-zaslonko@linux.ibm.com
Signed-off-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Eduard Shishkin <edward6@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Richard Purdie <rpurdie@rpsys.net>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/btrfs/compression.c |    2 
 fs/btrfs/zlib.c        |  118 ++++++++++++++++++++++++++-------------
 2 files changed, 80 insertions(+), 40 deletions(-)

--- a/fs/btrfs/compression.c~btrfs-use-larger-zlib-buffer-for-s390-hardware-compression
+++ a/fs/btrfs/compression.c
@@ -1290,7 +1290,7 @@ int btrfs_decompress_buf2page(const char
 	/* copy bytes from the working buffer into the pages */
 	while (working_bytes > 0) {
 		bytes = min_t(unsigned long, bvec.bv_len,
-				PAGE_SIZE - buf_offset);
+				PAGE_SIZE - (buf_offset % PAGE_SIZE));
 		bytes = min(bytes, working_bytes);
 
 		kaddr = kmap_atomic(bvec.bv_page);
--- a/fs/btrfs/zlib.c~btrfs-use-larger-zlib-buffer-for-s390-hardware-compression
+++ a/fs/btrfs/zlib.c
@@ -20,9 +20,12 @@
 #include <linux/refcount.h>
 #include "compression.h"
 
+#define ZLIB_DFLTCC_BUF_SIZE    (4 * PAGE_SIZE)
+
 struct workspace {
 	z_stream strm;
 	char *buf;
+	unsigned long buf_size;
 	struct list_head list;
 	int level;
 };
@@ -61,7 +64,17 @@ struct list_head *zlib_alloc_workspace(u
 			zlib_inflate_workspacesize());
 	workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL);
 	workspace->level = level;
-	workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	workspace->buf = NULL;
+	if (zlib_deflate_dfltcc_enabled()) {
+		workspace->buf = kmalloc(ZLIB_DFLTCC_BUF_SIZE,
+					 __GFP_NOMEMALLOC | __GFP_NORETRY |
+					 __GFP_NOWARN | GFP_NOIO);
+		workspace->buf_size = ZLIB_DFLTCC_BUF_SIZE;
+	}
+	if (!workspace->buf) {
+		workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		workspace->buf_size = PAGE_SIZE;
+	}
 	if (!workspace->strm.workspace || !workspace->buf)
 		goto fail;
 
@@ -78,6 +91,7 @@ int zlib_compress_pages(struct list_head
 		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	int i;
 	int ret;
 	char *data_in;
 	char *cpage_out;
@@ -85,6 +99,7 @@ int zlib_compress_pages(struct list_head
 	struct page *in_page = NULL;
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
+	unsigned long in_buf_pages;
 	unsigned long len = *total_out;
 	unsigned long nr_dest_pages = *out_pages;
 	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
@@ -102,9 +117,6 @@ int zlib_compress_pages(struct list_head
 	workspace->strm.total_in = 0;
 	workspace->strm.total_out = 0;
 
-	in_page = find_get_page(mapping, start >> PAGE_SHIFT);
-	data_in = kmap(in_page);
-
 	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
 	if (out_page == NULL) {
 		ret = -ENOMEM;
@@ -114,12 +126,34 @@ int zlib_compress_pages(struct list_head
 	pages[0] = out_page;
 	nr_pages = 1;
 
-	workspace->strm.next_in = data_in;
+	workspace->strm.next_in = workspace->buf;
+	workspace->strm.avail_in = 0;
 	workspace->strm.next_out = cpage_out;
 	workspace->strm.avail_out = PAGE_SIZE;
-	workspace->strm.avail_in = min(len, PAGE_SIZE);
 
 	while (workspace->strm.total_in < len) {
+		/* get next set of pages and copy their contents to
+		 * the input buffer for the following deflate call
+		 */
+		if (workspace->strm.avail_in == 0) {
+			bytes_left = len - workspace->strm.total_in;
+			in_buf_pages = min(DIV_ROUND_UP(bytes_left, PAGE_SIZE),
+					   workspace->buf_size / PAGE_SIZE);
+			for (i = 0; i < in_buf_pages; i++) {
+				in_page = find_get_page(mapping,
+							start >> PAGE_SHIFT);
+				data_in = kmap(in_page);
+				memcpy(workspace->buf + i*PAGE_SIZE, data_in,
+				       PAGE_SIZE);
+				kunmap(in_page);
+				put_page(in_page);
+				start += PAGE_SIZE;
+			}
+			workspace->strm.avail_in = min(bytes_left,
+						       workspace->buf_size);
+			workspace->strm.next_in = workspace->buf;
+		}
+
 		ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
 		if (ret != Z_OK) {
 			pr_debug("BTRFS: deflate in loop returned %d\n",
@@ -136,6 +170,7 @@ int zlib_compress_pages(struct list_head
 			ret = -E2BIG;
 			goto out;
 		}
+
 		/* we need another page for writing out.  Test this
 		 * before the total_in so we will pull in a new page for
 		 * the stream end if required
@@ -161,33 +196,42 @@ int zlib_compress_pages(struct list_head
 		/* we're all done */
 		if (workspace->strm.total_in >= len)
 			break;
-
-		/* we've read in a full page, get a new one */
-		if (workspace->strm.avail_in == 0) {
-			if (workspace->strm.total_out > max_out)
-				break;
-
-			bytes_left = len - workspace->strm.total_in;
-			kunmap(in_page);
-			put_page(in_page);
-
-			start += PAGE_SIZE;
-			in_page = find_get_page(mapping,
-						start >> PAGE_SHIFT);
-			data_in = kmap(in_page);
-			workspace->strm.avail_in = min(bytes_left,
-							   PAGE_SIZE);
-			workspace->strm.next_in = data_in;
-		}
+		if (workspace->strm.total_out > max_out)
+			break;
 	}
 	workspace->strm.avail_in = 0;
-	ret = zlib_deflate(&workspace->strm, Z_FINISH);
-	zlib_deflateEnd(&workspace->strm);
-
-	if (ret != Z_STREAM_END) {
-		ret = -EIO;
-		goto out;
+	/* call deflate with Z_FINISH flush parameter providing more output
+	 * space but no more input data, until it returns with Z_STREAM_END
+	 */
+	while (ret != Z_STREAM_END) {
+		ret = zlib_deflate(&workspace->strm, Z_FINISH);
+		if (ret == Z_STREAM_END)
+			break;
+		if (ret != Z_OK && ret != Z_BUF_ERROR) {
+			zlib_deflateEnd(&workspace->strm);
+			ret = -EIO;
+			goto out;
+		} else if (workspace->strm.avail_out == 0) {
+			/* get another page for the stream end */
+			kunmap(out_page);
+			if (nr_pages == nr_dest_pages) {
+				out_page = NULL;
+				ret = -E2BIG;
+				goto out;
+			}
+			out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+			if (out_page == NULL) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			cpage_out = kmap(out_page);
+			pages[nr_pages] = out_page;
+			nr_pages++;
+			workspace->strm.avail_out = PAGE_SIZE;
+			workspace->strm.next_out = cpage_out;
+		}
 	}
+	zlib_deflateEnd(&workspace->strm);
 
 	if (workspace->strm.total_out >= workspace->strm.total_in) {
 		ret = -E2BIG;
@@ -202,10 +246,6 @@ out:
 	if (out_page)
 		kunmap(out_page);
 
-	if (in_page) {
-		kunmap(in_page);
-		put_page(in_page);
-	}
 	return ret;
 }
 
@@ -231,7 +271,7 @@ int zlib_decompress_bio(struct list_head
 
 	workspace->strm.total_out = 0;
 	workspace->strm.next_out = workspace->buf;
-	workspace->strm.avail_out = PAGE_SIZE;
+	workspace->strm.avail_out = workspace->buf_size;
 
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
@@ -270,7 +310,7 @@ int zlib_decompress_bio(struct list_head
 		}
 
 		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = PAGE_SIZE;
+		workspace->strm.avail_out = workspace->buf_size;
 
 		if (workspace->strm.avail_in == 0) {
 			unsigned long tmp;
@@ -320,7 +360,7 @@ int zlib_decompress(struct list_head *ws
 	workspace->strm.total_in = 0;
 
 	workspace->strm.next_out = workspace->buf;
-	workspace->strm.avail_out = PAGE_SIZE;
+	workspace->strm.avail_out = workspace->buf_size;
 	workspace->strm.total_out = 0;
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
@@ -364,7 +404,7 @@ int zlib_decompress(struct list_head *ws
 			buf_offset = 0;
 
 		bytes = min(PAGE_SIZE - pg_offset,
-			    PAGE_SIZE - buf_offset);
+			    PAGE_SIZE - (buf_offset % PAGE_SIZE));
 		bytes = min(bytes, bytes_left);
 
 		kaddr = kmap_atomic(dest_page);
@@ -375,7 +415,7 @@ int zlib_decompress(struct list_head *ws
 		bytes_left -= bytes;
 next:
 		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = PAGE_SIZE;
+		workspace->strm.avail_out = workspace->buf_size;
 	}
 
 	if (ret != Z_STREAM_END && bytes_left != 0)
_

Patches currently in -mm which might be from zaslonko@linux.ibm.com are

lib-zlib-add-s390-hardware-support-for-kernel-zlib_deflate.patch
s390-boot-rename-heap_size-due-to-name-collision.patch
lib-zlib-add-s390-hardware-support-for-kernel-zlib_inflate.patch
s390-boot-add-dfltcc=-kernel-command-line-parameter.patch
lib-zlib-add-zlib_deflate_dfltcc_enabled-function.patch