util/cbfstool: Add cbfs-compression-tool

cbfs-compression-tool provides a way to benchmark the compression
algorithms as used by cbfstool (and coreboot) and allows to
pre-compress data for later consumption by cbfstool (once it supports
the format).

For an impression, the benchmark's results on my machine:

measuring 'none'
compressing 10485760 bytes to 10485760 took 0 seconds
measuring 'LZMA'
compressing 10485760 bytes to 1736 took 2 seconds
measuring 'LZ4'
compressing 10485760 bytes to 41880 took 0 seconds

And a possible use for external compression, parallel and non-parallel
(60MB in 53 files compressed to 650KB on a machine with 40 threads):

$ time (ls -1 *.* |xargs -n 1 -P $(nproc) -I '{}' cbfs-compression-tool compress '{}' out/'{}' LZMA)

real	0m0.786s
user	0m11.440s
sys	0m0.044s

$ time (ls -1 *.* |xargs -n 1 -P 1 -I '{}' cbfs-compression-tool compress '{}' out/'{}' LZMA)

real	0m10.444s
user	0m10.280s
sys	0m0.064s

Change-Id: I40be087e85d09a895b1ed277270350ab65a4d6d4
Signed-off-by: Patrick Georgi <pgeorgi@chromium.org>
Reviewed-on: https://review.coreboot.org/18099
Tested-by: build bot (Jenkins)
Reviewed-by: Martin Roth <martinroth@google.com>

6 files changed, 230 insertions, 28 deletions

diff --git a/util/cbfstool/Makefile b/util/cbfstool/Makefile
index d6249bc24e..caa8c7daa4 100644
--- a/util/cbfstool/Makefile
+++ b/util/cbfstool/Makefile
@@ -9,7 +9,7 @@ OBJCOPY ?= objcopy
 VBOOT_SOURCE ?= $(top)/3rdparty/vboot
 
 .PHONY: all
-all: cbfstool fmaptool rmodtool ifwitool
+all: cbfstool fmaptool rmodtool ifwitool cbfs-compression-tool
 
 cbfstool: $(objutil)/cbfstool/cbfstool
 
@@ -19,13 +19,16 @@ rmodtool: $(objutil)/cbfstool/rmodtool
 
 ifwitool: $(objutil)/cbfstool/ifwitool
 
-.PHONY: clean cbfstool fmaptool rmodtool ifwitool
+cbfs-compression-tool: $(objutil)/cbfstool/cbfs-compression-tool
+
+.PHONY: clean cbfstool fmaptool rmodtool ifwitool cbfs-compression-tool
 clean:
 	$(RM) fmd_parser.c fmd_parser.h fmd_scanner.c fmd_scanner.h
 	$(RM) $(objutil)/cbfstool/cbfstool $(cbfsobj)
 	$(RM) $(objutil)/cbfstool/fmaptool $(fmapobj)
 	$(RM) $(objutil)/cbfstool/rmodtool $(rmodobj)
 	$(RM) $(objutil)/cbfstool/ifwitool $(ifwiobj)
+	$(RM) $(objutil)/cbfstool/cbfs-compression-tool $(cbfscompobj)
 
 linux_trampoline.c: linux_trampoline.S
 	rm -f linux_trampoline.c
diff --git a/util/cbfstool/Makefile.inc b/util/cbfstool/Makefile.inc
index 6882cbaf60..950092fb62 100644
--- a/util/cbfstool/Makefile.inc
+++ b/util/cbfstool/Makefile.inc
@@ -1,7 +1,20 @@
+compressionobj :=
+compressionobj += compress.o
+# LZ4
+compressionobj += lz4.o
+compressionobj += lz4hc.o
+compressionobj += lz4frame.o
+compressionobj += xxhash.o
+compressionobj += lz4_wrapper.o
+# LZMA
+compressionobj += lzma.o
+compressionobj += LzFind.o
+compressionobj += LzmaDec.o
+compressionobj += LzmaEnc.o
+
 cbfsobj :=
 cbfsobj += cbfstool.o
 cbfsobj += common.o
-cbfsobj += compress.o
 cbfsobj += cbfs_image.o
 cbfsobj += cbfs-mkstage.o
 cbfsobj += cbfs-mkpayload.o
@@ -13,24 +26,13 @@ cbfsobj += partitioned_file.o
 # COMMONLIB
 cbfsobj += cbfs.o
 cbfsobj += fsp_relocate.o
-cbfsobj += lz4_wrapper.o
 cbfsobj += mem_pool.o
 cbfsobj += region.o
-# LZMA
-cbfsobj += lzma.o
-cbfsobj += LzFind.o
-cbfsobj += LzmaDec.o
-cbfsobj += LzmaEnc.o
 # CRYPTOLIB
 cbfsobj += 2sha_utility.o
 cbfsobj += 2sha1.o
 cbfsobj += 2sha256.o
 cbfsobj += 2sha512.o
-# LZ4
-cbfsobj += lz4.o
-cbfsobj += lz4hc.o
-cbfsobj += lz4frame.o
-cbfsobj += xxhash.o
 # FMAP
 cbfsobj += fmap.o
 cbfsobj += kv_pair.o
@@ -38,6 +40,8 @@ cbfsobj += valstr.o
 # linux as payload
 cbfsobj += linux_trampoline.o
 cbfsobj += cbfs-payload-linux.o
+# compression algorithms
+cbfsobj += $(compressionobj)
 
 fmapobj :=
 fmapobj += fmaptool.o
@@ -62,6 +66,10 @@ ifwiobj :=
 ifwiobj += ifwitool.o
 ifwiobj += common.o
 
+cbfscompobj :=
+cbfscompobj += $(compressionobj)
+cbfscompobj += cbfscomptool.o
+
 TOOLCFLAGS ?= -Werror -Wall -Wextra
 TOOLCFLAGS += -Wcast-qual -Wmissing-prototypes -Wredundant-decls -Wshadow
 TOOLCFLAGS += -Wstrict-prototypes -Wwrite-strings
@@ -141,6 +149,10 @@ $(objutil)/cbfstool/ifwitool: $(addprefix $(objutil)/cbfstool/,$(ifwiobj))
 	printf "    HOSTCC     $(subst $(objutil)/,,$(@)) (link)\n"
 	$(HOSTCC) $(TOOLLDFLAGS) -o $@ $(addprefix $(objutil)/cbfstool/,$(ifwiobj))
 
+$(objutil)/cbfstool/cbfs-compression-tool: $(addprefix $(objutil)/cbfstool/,$(cbfscompobj))
+	printf "    HOSTCC     $(subst $(objutil)/,,$(@)) (link)\n"
+	$(HOSTCC) $(TOOLLDFLAGS) -o $@ $(addprefix $(objutil)/cbfstool/,$(cbfscompobj))
+
 # Yacc source is superset of header
 $(objutil)/cbfstool/fmd.o: TOOLCFLAGS += -Wno-redundant-decls
 $(objutil)/cbfstool/fmd_parser.o: TOOLCFLAGS += -Wno-redundant-decls
diff --git a/util/cbfstool/cbfs.h b/util/cbfstool/cbfs.h
index f1ae09d97a..451ef9fd8b 100644
--- a/util/cbfstool/cbfs.h
+++ b/util/cbfstool/cbfs.h
@@ -204,11 +204,6 @@ struct cbfs_payload {
  */
 #define CBFS_COMPONENT_NULL 0xFFFFFFFF
 
-struct typedesc_t {
-	uint32_t type;
-	const char *name;
-};
-
 static struct typedesc_t filetypes[] unused = {
 	{CBFS_COMPONENT_BOOTBLOCK, "bootblock"},
 	{CBFS_COMPONENT_CBFSHEADER, "cbfs header"},
diff --git a/util/cbfstool/cbfs_image.c b/util/cbfstool/cbfs_image.c
index c34ca8366c..e530224fac 100644
--- a/util/cbfstool/cbfs_image.c
+++ b/util/cbfstool/cbfs_image.c
@@ -50,15 +50,6 @@
  * (old) cbfstool. */
 #define CBFS_FILENAME_ALIGN	(16)
 
-/* Type and format */
-
-static const struct typedesc_t types_cbfs_compression[] = {
-	{CBFS_COMPRESS_NONE, "none"},
-	{CBFS_COMPRESS_LZMA, "LZMA"},
-	{CBFS_COMPRESS_LZ4, "LZ4"},
-	{0, NULL},
-};
-
 static const char *lookup_name_by_type(const struct typedesc_t *desc, uint32_t type,
 				const char *default_value)
 {
diff --git a/util/cbfstool/cbfscomptool.c b/util/cbfstool/cbfscomptool.c
new file mode 100644
index 0000000000..1aa1699588
--- /dev/null
+++ b/util/cbfstool/cbfscomptool.c
@@ -0,0 +1,189 @@
+/*
+ * cbfs-compression-tool, CLI utility for dealing with CBFS compressed data
+ *
+ * Copyright (C) 2017 Google, Inc.
+ *
+ * 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; version 2 of the License.
+ *
+ * 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.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+
+#include "common.h"
+
+void usage(void);
+int benchmark(void);
+int compress(char *infile, char *outfile, char *algoname);
+
+const char *usage_text = "cbfs-compression-tool benchmark\n"
+	"  runs benchmarks for all implemented algorithms\n"
+	"cbfs-compression-tool compress inFile outFile algo\n"
+	"  compresses inFile with algo and stores in outFile\n"
+	"\n"
+	"'compress' file format:\n"
+	" 4 bytes little endian: algorithm ID (as used in CBFS)\n"
+	" 4 bytes little endian: uncompressed size\n"
+	" ...: compressed data stream\n";
+
+void usage()
+{
+	puts(usage_text);
+}
+
+int benchmark()
+{
+	const int bufsize = 10*1024*1024;
+	char *data = malloc(bufsize);
+	if (!data) {
+		fprintf(stderr, "out of memory\n");
+		return 1;
+	}
+	char *compressed_data = malloc(bufsize);
+	if (!compressed_data) {
+		fprintf(stderr, "out of memory\n");
+		return 1;
+	}
+	int i, l = strlen(usage_text) + 1;
+	for (i = 0; i + l < bufsize; i += l) {
+		memcpy(data + i, usage_text, l);
+	}
+	memset(data + i, 0, bufsize - i);
+	const struct typedesc_t *algo;
+	for (algo = &types_cbfs_compression[0]; algo->name != NULL; algo++) {
+		int outsize = bufsize;
+		printf("measuring '%s'\n", algo->name);
+		comp_func_ptr comp = compression_function(algo->type);
+		if (comp == NULL) {
+			printf("no handler associated with algorithm\n");
+			return 1;
+		}
+
+		struct timespec t_s, t_e;
+		clock_gettime(CLOCK_MONOTONIC, &t_s);
+
+		if (comp(data, bufsize, compressed_data, &outsize)) {
+			printf("compression failed");
+			return 1;
+		}
+
+		clock_gettime(CLOCK_MONOTONIC, &t_e);
+		printf("compressing %d bytes to %d took %ld seconds\n",
+			bufsize, outsize,
+			t_e.tv_sec - t_s.tv_sec);
+	}
+	return 0;
+}
+
+int compress(char *infile, char *outfile, char *algoname)
+{
+	int err = 1;
+	FILE *fin = NULL;
+	FILE *fout = NULL;
+	void *indata = NULL;
+
+	const struct typedesc_t *algo = &types_cbfs_compression[0];
+	while (algo->name != NULL) {
+		if (strcmp(algo->name, algoname) == 0) break;
+		algo++;
+	}
+	if (algo->name == NULL) {
+		fprintf(stderr, "algo '%s' is not supported.\n", algoname);
+	}
+
+	comp_func_ptr comp = compression_function(algo->type);
+	if (comp == NULL) {
+		printf("no handler associated with algorithm\n");
+		return 1;
+	}
+
+	fin = fopen(infile, "rb");
+	if (!fin) {
+		fprintf(stderr, "could not open '%s'\n", infile);
+		return 1;
+	}
+	fout = fopen(outfile, "wb");
+	if (!fout) {
+		fprintf(stderr, "could not open '%s' for writing\n", outfile);
+		goto out;
+	}
+
+	if (fseek(fin, 0, SEEK_END) != 0) {
+		fprintf(stderr, "could not seek in input\n");
+		goto out;
+	}
+	long insize = ftell(fin);
+	if (insize < 0) {
+		fprintf(stderr, "could not determine input size\n");
+		goto out;
+	}
+	rewind(fin);
+
+	indata = malloc(insize);
+	if (!indata) {
+		fprintf(stderr, "out of memory\n");
+		goto out;
+	}
+
+	void *outdata = malloc(insize);
+	if (!outdata) {
+		fprintf(stderr, "out of memory\n");
+		goto out;
+	}
+	int outsize;
+
+	int remsize = insize;
+	while (remsize > 0) {
+		int readsz = fread(indata, 1, remsize, fin);
+		if (readsz < 0) {
+			fprintf(stderr, "failed to read input with %d bytes left\n", remsize);
+			goto out;
+		}
+		remsize -= readsz;
+	}
+
+	comp(indata, insize, outdata, &outsize);
+
+	char header[8];
+	header[0] = algo->type & 0xff;
+	header[1] = (algo->type >> 8) & 0xff;
+	header[2] = (algo->type >> 16) & 0xff;
+	header[3] = (algo->type >> 24) & 0xff;
+	header[4] = insize & 0xff;
+	header[5] = (insize >> 8) & 0xff;
+	header[6] = (insize >> 16) & 0xff;
+	header[7] = (insize >> 24) & 0xff;
+	if (fwrite(header, 8, 1, fout) != 1) {
+		fprintf(stderr, "failed writing header\n");
+		goto out;
+	}
+	if (fwrite(outdata, outsize, 1, fout) != 1) {
+		fprintf(stderr, "failed writing compressed data\n");
+		goto out;
+	}
+
+	err = 0;
+out:
+	if (fin) fclose(fin);
+	if (fout) fclose(fout);
+	if (indata) free(indata);
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	if ((argc == 2) && (strcmp(argv[1], "benchmark") == 0))
+		return benchmark();
+	if ((argc == 5) && (strcmp(argv[1], "compress") == 0))
+		return compress(argv[2], argv[3], argv[4]);
+	usage();
+	return 1;
+}
diff --git a/util/cbfstool/common.h b/util/cbfstool/common.h
index d4b7021428..85dfdeb589 100644
--- a/util/cbfstool/common.h
+++ b/util/cbfstool/common.h
@@ -166,6 +166,18 @@ enum comp_algo {
 	CBFS_COMPRESS_LZ4 = 2,
 };
 
+struct typedesc_t {
+	uint32_t type;
+	const char *name;
+};
+
+static const struct typedesc_t types_cbfs_compression[] = {
+	{CBFS_COMPRESS_NONE, "none"},
+	{CBFS_COMPRESS_LZMA, "LZMA"},
+	{CBFS_COMPRESS_LZ4, "LZ4"},
+	{0, NULL},
+};
+
 comp_func_ptr compression_function(enum comp_algo algo);
 decomp_func_ptr decompression_function(enum comp_algo algo);