Merge branch 'zstd-minimal' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull zstd support from Chris Mason:
 "Nick Terrell's patch series to add zstd support to the kernel has been
  floating around for a while. After talking with Dave Sterba, Herbert
  and Phillip, we decided to send the whole thing in as one pull
  request.

  zstd is a big win in speed over zlib and in compression ratio over
  lzo, and the compression team here at FB has gotten great results
  using it in production. Nick will continue to update the kernel side
  with new improvements from the open source zstd userland code.

  Nick has a number of benchmarks for the main zstd code in his lib/zstd
  commit:

      I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB
      of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel
      Core i7 processor, 16 GB of RAM, and a SSD. I benchmarked using
      `silesia.tar` [3], which is 211,988,480 B large. Run the following
      commands for the benchmark:

        sudo modprobe zstd_compress_test
        sudo mknod zstd_compress_test c 245 0
        sudo cp silesia.tar zstd_compress_test

      The time is reported by the time of the userland `cp`.
      The MB/s is computed with

        1,536,217,008 B / time(buffer size, hash)

      which includes the time to copy from userland.
      The Adjusted MB/s is computed with

        1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)).

      The memory reported is the amount of memory the compressor
      requests.

        | Method   | Size (B) | Time (s) | Ratio | MB/s    | Adj MB/s | Mem (MB) |
        |----------|----------|----------|-------|---------|----------|----------|
        | none     | 11988480 |    0.100 |     1 | 2119.88 |        - |        - |
        | zstd -1  | 73645762 |    1.044 | 2.878 |  203.05 |   224.56 |     1.23 |
        | zstd -3  | 66988878 |    1.761 | 3.165 |  120.38 |   127.63 |     2.47 |
        | zstd -5  | 65001259 |    2.563 | 3.261 |   82.71 |    86.07 |     2.86 |
        | zstd -10 | 60165346 |   13.242 | 3.523 |   16.01 |    16.13 |    13.22 |
        | zstd -15 | 58009756 |   47.601 | 3.654 |    4.45 |     4.46 |    21.61 |
        | zstd -19 | 54014593 |  102.835 | 3.925 |    2.06 |     2.06 |    60.15 |
        | zlib -1  | 77260026 |    2.895 | 2.744 |   73.23 |    75.85 |     0.27 |
        | zlib -3  | 72972206 |    4.116 | 2.905 |   51.50 |    52.79 |     0.27 |
        | zlib -6  | 68190360 |    9.633 | 3.109 |   22.01 |    22.24 |     0.27 |
        | zlib -9  | 67613382 |   22.554 | 3.135 |    9.40 |     9.44 |     0.27 |

      I benchmarked zstd decompression using the same method on the same
      machine. The benchmark file is located in the upstream zstd repo
      under `contrib/linux-kernel/zstd_decompress_test.c` [4]. The
      memory reported is the amount of memory required to decompress
      data compressed with the given compression level. If you know the
      maximum size of your input, you can reduce the memory usage of
      decompression irrespective of the compression level.

        | Method   | Time (s) | MB/s    | Adjusted MB/s | Memory (MB) |
        |----------|----------|---------|---------------|-------------|
        | none     |    0.025 | 8479.54 |             - |           - |
        | zstd -1  |    0.358 |  592.15 |        636.60 |        0.84 |
        | zstd -3  |    0.396 |  535.32 |        571.40 |        1.46 |
        | zstd -5  |    0.396 |  535.32 |        571.40 |        1.46 |
        | zstd -10 |    0.374 |  566.81 |        607.42 |        2.51 |
        | zstd -15 |    0.379 |  559.34 |        598.84 |        4.61 |
        | zstd -19 |    0.412 |  514.54 |        547.77 |        8.80 |
        | zlib -1  |    0.940 |  225.52 |        231.68 |        0.04 |
        | zlib -3  |    0.883 |  240.08 |        247.07 |        0.04 |
        | zlib -6  |    0.844 |  251.17 |        258.84 |        0.04 |
        | zlib -9  |    0.837 |  253.27 |        287.64 |        0.04 |

  I ran a long series of tests and benchmarks on the btrfs side and the
  gains are very similar to the core benchmarks Nick ran"

* 'zstd-minimal' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  squashfs: Add zstd support
  btrfs: Add zstd support
  lib: Add zstd modules
  lib: Add xxhash module

6 files changed, 178 insertions, 0 deletions

diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index ffb093e72b6c..1adb3346b9d6 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -165,6 +165,20 @@ config SQUASHFS_XZ
 
 	  If unsure, say N.
 
+config SQUASHFS_ZSTD
+	bool "Include support for ZSTD compressed file systems"
+	depends on SQUASHFS
+	select ZSTD_DECOMPRESS
+	help
+	  Saying Y here includes support for reading Squashfs file systems
+	  compressed with ZSTD compression.  ZSTD gives better compression than
+	  the default ZLIB compression, while using less CPU.
+
+	  ZSTD is not the standard compression used in Squashfs and so most
+	  file systems will be readable without selecting this option.
+
+	  If unsure, say N.
+
 config SQUASHFS_4K_DEVBLK_SIZE
 	bool "Use 4K device block size?"
 	depends on SQUASHFS
diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index 246a6f329d89..6655631c53ae 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -15,3 +15,4 @@ squashfs-$(CONFIG_SQUASHFS_LZ4) += lz4_wrapper.o
 squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o
 squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o
 squashfs-$(CONFIG_SQUASHFS_ZLIB) += zlib_wrapper.o
+squashfs-$(CONFIG_SQUASHFS_ZSTD) += zstd_wrapper.o
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index d2bc13636f79..836639810ea0 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -65,6 +65,12 @@ static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
 };
 #endif
 
+#ifndef CONFIG_SQUASHFS_ZSTD
+static const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+	NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0
+};
+#endif
+
 static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
 	NULL, NULL, NULL, NULL, 0, "unknown", 0
 };
@@ -75,6 +81,7 @@ static const struct squashfs_decompressor *decompressor[] = {
 	&squashfs_lzo_comp_ops,
 	&squashfs_xz_comp_ops,
 	&squashfs_lzma_unsupported_comp_ops,
+	&squashfs_zstd_comp_ops,
 	&squashfs_unknown_comp_ops
 };
 
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index a25713c031a5..0f5a8e4e58da 100644
--- a/fs/squashfs/decompressor.h
+++ b/fs/squashfs/decompressor.h
@@ -58,4 +58,8 @@ extern const struct squashfs_decompressor squashfs_lzo_comp_ops;
 extern const struct squashfs_decompressor squashfs_zlib_comp_ops;
 #endif
 
+#ifdef CONFIG_SQUASHFS_ZSTD
+extern const struct squashfs_decompressor squashfs_zstd_comp_ops;
+#endif
+
 #endif
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 506f4ba5b983..24d12fd14177 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -241,6 +241,7 @@ struct meta_index {
 #define LZO_COMPRESSION		3
 #define XZ_COMPRESSION		4
 #define LZ4_COMPRESSION		5
+#define ZSTD_COMPRESSION	6
 
 struct squashfs_super_block {
 	__le32			s_magic;
diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
new file mode 100644
index 000000000000..eeaabf881159
--- /dev/null
+++ b/fs/squashfs/zstd_wrapper.c
@@ -0,0 +1,151 @@
+/*
+ * Squashfs - a compressed read only filesystem for Linux
+ *
+ * Copyright (c) 2016-present, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2,
+ * or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * zstd_wrapper.c
+ */
+
+#include <linux/mutex.h>
+#include <linux/buffer_head.h>
+#include <linux/slab.h>
+#include <linux/zstd.h>
+#include <linux/vmalloc.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs.h"
+#include "decompressor.h"
+#include "page_actor.h"
+
+struct workspace {
+	void *mem;
+	size_t mem_size;
+	size_t window_size;
+};
+
+static void *zstd_init(struct squashfs_sb_info *msblk, void *buff)
+{
+	struct workspace *wksp = kmalloc(sizeof(*wksp), GFP_KERNEL);
+
+	if (wksp == NULL)
+		goto failed;
+	wksp->window_size = max_t(size_t,
+			msblk->block_size, SQUASHFS_METADATA_SIZE);
+	wksp->mem_size = ZSTD_DStreamWorkspaceBound(wksp->window_size);
+	wksp->mem = vmalloc(wksp->mem_size);
+	if (wksp->mem == NULL)
+		goto failed;
+
+	return wksp;
+
+failed:
+	ERROR("Failed to allocate zstd workspace\n");
+	kfree(wksp);
+	return ERR_PTR(-ENOMEM);
+}
+
+
+static void zstd_free(void *strm)
+{
+	struct workspace *wksp = strm;
+
+	if (wksp)
+		vfree(wksp->mem);
+	kfree(wksp);
+}
+
+
+static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct buffer_head **bh, int b, int offset, int length,
+	struct squashfs_page_actor *output)
+{
+	struct workspace *wksp = strm;
+	ZSTD_DStream *stream;
+	size_t total_out = 0;
+	size_t zstd_err;
+	int k = 0;
+	ZSTD_inBuffer in_buf = { NULL, 0, 0 };
+	ZSTD_outBuffer out_buf = { NULL, 0, 0 };
+
+	stream = ZSTD_initDStream(wksp->window_size, wksp->mem, wksp->mem_size);
+
+	if (!stream) {
+		ERROR("Failed to initialize zstd decompressor\n");
+		goto out;
+	}
+
+	out_buf.size = PAGE_SIZE;
+	out_buf.dst = squashfs_first_page(output);
+
+	do {
+		if (in_buf.pos == in_buf.size && k < b) {
+			int avail = min(length, msblk->devblksize - offset);
+
+			length -= avail;
+			in_buf.src = bh[k]->b_data + offset;
+			in_buf.size = avail;
+			in_buf.pos = 0;
+			offset = 0;
+		}
+
+		if (out_buf.pos == out_buf.size) {
+			out_buf.dst = squashfs_next_page(output);
+			if (out_buf.dst == NULL) {
+				/* Shouldn't run out of pages
+				 * before stream is done.
+				 */
+				squashfs_finish_page(output);
+				goto out;
+			}
+			out_buf.pos = 0;
+			out_buf.size = PAGE_SIZE;
+		}
+
+		total_out -= out_buf.pos;
+		zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf);
+		total_out += out_buf.pos; /* add the additional data produced */
+
+		if (in_buf.pos == in_buf.size && k < b)
+			put_bh(bh[k++]);
+	} while (zstd_err != 0 && !ZSTD_isError(zstd_err));
+
+	squashfs_finish_page(output);
+
+	if (ZSTD_isError(zstd_err)) {
+		ERROR("zstd decompression error: %d\n",
+				(int)ZSTD_getErrorCode(zstd_err));
+		goto out;
+	}
+
+	if (k < b)
+		goto out;
+
+	return (int)total_out;
+
+out:
+	for (; k < b; k++)
+		put_bh(bh[k]);
+
+	return -EIO;
+}
+
+const struct squashfs_decompressor squashfs_zstd_comp_ops = {
+	.init = zstd_init,
+	.free = zstd_free,
+	.decompress = zstd_uncompress,
+	.id = ZSTD_COMPRESSION,
+	.name = "zstd",
+	.supported = 1
+};