xen: add LZ4 decompression support

Add support for LZ4 decompression in Xen. LZ4 Decompression APIs for
Xen are based on LZ4 implementation by Yann Collet.

Benchmark Results(PATCH v3)
Compiler: Linaro ARM gcc 4.6.2

1. ARMv7, 1.5GHz based board
   Kernel: linux 3.4
   Uncompressed Kernel Size: 14MB
        Compressed Size  Decompression Speed
   LZO  6.7MB            20.1MB/s, 25.2MB/s(UA)
   LZ4  7.3MB            29.1MB/s, 45.6MB/s(UA)

2. ARMv7, 1.7GHz based board
   Kernel: linux 3.7
   Uncompressed Kernel Size: 14MB
        Compressed Size  Decompression Speed
   LZO  6.0MB            34.1MB/s, 52.2MB/s(UA)
   LZ4  6.5MB            86.7MB/s
- UA: Unaligned memory Access support
- Latest patch set for LZO applied

This patch set is for adding support for LZ4-compressed Kernel.  LZ4 is a
very fast lossless compression algorithm and it also features an extremely
fast decoder [1].

But we have five of decompressors already and one question which does
arise, however, is that of where do we stop adding new ones?  This issue
had been discussed and came to the conclusion [2].

Russell King said that we should have:

 - one decompressor which is the fastest
 - one decompressor for the highest compression ratio
 - one popular decompressor (eg conventional gzip)

If we have a replacement one for one of these, then it should do exactly
that: replace it.

The benchmark shows that an 8% increase in image size vs a 66% increase
in decompression speed compared to LZO(which has been known as the
fastest decompressor in the Kernel).  Therefore the "fast but may not be
small" compression title has clearly been taken by LZ4 [3].

[1] http://code.google.com/p/lz4/
[2] http://thread.gmane.org/gmane.linux.kbuild.devel/9157
[3] http://thread.gmane.org/gmane.linux.kbuild.devel/9347

LZ4 homepage: http://fastcompression.blogspot.com/p/lz4.html
LZ4 source repository: http://code.google.com/p/lz4/

Signed-off-by: Kyungsik Lee <kyungsik.lee@lge.com>
Signed-off-by: Yann Collet <yann.collet.73@gmail.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>

1 files changed, 166 insertions, 0 deletions

diff --git a/xen/common/unlz4.c b/xen/common/unlz4.c
new file mode 100644
index 0000000000..195d8299a2
--- /dev/null
+++ b/xen/common/unlz4.c
@@ -0,0 +1,166 @@
+/*
+ * Wrapper for decompressing LZ4-compressed kernel, initramfs, and initrd
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "decompress.h"
+#include <xen/lz4.h>
+#include "lz4/decompress.c"
+
+/*
+ * Note: Uncompressed chunk size is used in the compressor side
+ * (userspace side for compression).
+ * It is hardcoded because there is not proper way to extract it
+ * from the binary stream which is generated by the preliminary
+ * version of LZ4 tool so far.
+ */
+#define LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE (8 << 20)
+#define ARCHIVE_MAGICNUMBER 0x184C2102
+
+STATIC int INIT unlz4(unsigned char *input, unsigned int in_len,
+		      int (*fill)(void *, unsigned int),
+		      int (*flush)(void *, unsigned int),
+		      unsigned char *output,
+		      unsigned int *posp,
+		      void (*error)(const char *x))
+{
+	int ret = -1;
+	size_t chunksize = 0;
+	size_t uncomp_chunksize = LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE;
+	u8 *inp;
+	u8 *inp_start;
+	u8 *outp;
+	int size = in_len -= 4;
+#if defined(__XEN__) || defined(__MINIOS__)
+	size_t out_len = get_unaligned_le32(input + in_len);
+#endif
+	size_t dest_len;
+
+
+	if (output) {
+		outp = output;
+	} else if (!flush) {
+		error("NULL output pointer and no flush function provided");
+		goto exit_0;
+	} else {
+		outp = large_malloc(uncomp_chunksize);
+		if (!outp) {
+			error("Could not allocate output buffer");
+			goto exit_0;
+		}
+	}
+
+	if (input && fill) {
+		error("Both input pointer and fill function provided,");
+		goto exit_1;
+	} else if (input) {
+		inp = input;
+	} else if (!fill) {
+		error("NULL input pointer and missing fill function");
+		goto exit_1;
+	} else {
+		inp = large_malloc(lz4_compressbound(uncomp_chunksize));
+		if (!inp) {
+			error("Could not allocate input buffer");
+			goto exit_1;
+		}
+	}
+	inp_start = inp;
+
+	if (posp)
+		*posp = 0;
+
+	if (fill)
+		fill(inp, 4);
+
+	chunksize = get_unaligned_le32(inp);
+	if (chunksize == ARCHIVE_MAGICNUMBER) {
+		inp += 4;
+		size -= 4;
+	} else {
+		error("invalid header");
+		goto exit_2;
+	}
+
+	if (posp)
+		*posp += 4;
+
+	for (;;) {
+
+		if (fill)
+			fill(inp, 4);
+
+		chunksize = get_unaligned_le32(inp);
+		if (chunksize == ARCHIVE_MAGICNUMBER) {
+			inp += 4;
+			size -= 4;
+			if (posp)
+				*posp += 4;
+			continue;
+		}
+		inp += 4;
+		size -= 4;
+
+		if (posp)
+			*posp += 4;
+
+		if (fill) {
+			if (chunksize > lz4_compressbound(uncomp_chunksize)) {
+				error("chunk length is longer than allocated");
+				goto exit_2;
+			}
+			fill(inp, chunksize);
+		}
+#if defined(__XEN__) || defined(__MINIOS__)
+		if (out_len >= uncomp_chunksize) {
+			dest_len = uncomp_chunksize;
+			out_len -= dest_len;
+		} else
+			dest_len = out_len;
+		ret = lz4_decompress(inp, &chunksize, outp, dest_len);
+#else
+		dest_len = uncomp_chunksize;
+		ret = lz4_decompress_unknownoutputsize(inp, chunksize, outp,
+				&dest_len);
+#endif
+		if (ret < 0) {
+			error("Decoding failed");
+			goto exit_2;
+		}
+
+		if (flush && flush(outp, dest_len) != dest_len)
+			goto exit_2;
+		if (output)
+			outp += dest_len;
+		if (posp)
+			*posp += chunksize;
+
+		size -= chunksize;
+
+		if (size == 0)
+			break;
+		else if (size < 0) {
+			error("data corrupted");
+			goto exit_2;
+		}
+
+		inp += chunksize;
+		if (fill)
+			inp = inp_start;
+	}
+
+	ret = 0;
+exit_2:
+	if (!input)
+		large_free(inp_start);
+exit_1:
+	if (!output)
+		large_free(outp);
+exit_0:
+	return ret;
+}