LB_CONFIG_MPITESTS
LB_CONFIG_SERVERS
LC_CONFIG_CRYPTO
+LC_CONFIG_LZ4
+LC_CONFIG_LZ4HC
LC_GLIBC_SUPPORT_COPY_FILE_RANGE
LC_OPENSSL_SSK
BUILT_MODULE_NAME[2]="lmv"
BUILT_MODULE_NAME[3]="lov"
BUILT_MODULE_NAME[4]="lustre"
-BUILT_MODULE_NAME[5]="mdc"
-BUILT_MODULE_NAME[6]="mgc"
-BUILT_MODULE_NAME[7]="obdclass"
-BUILT_MODULE_NAME[8]="obdecho"
-BUILT_MODULE_NAME[9]="osc"
-BUILT_MODULE_NAME[10]="ptlrpc"
-BUILT_MODULE_NAME[11]="ko2iblnd"
-BUILT_MODULE_NAME[12]="ksocklnd"
-BUILT_MODULE_NAME[13]="libcfs"
-BUILT_MODULE_NAME[14]="lnet"
-BUILT_MODULE_NAME[15]="lnet_selftest"
-BUILT_MODULE_NAME[16]="ptlrpc_gss"
-
+BUILT_MODULE_NAME[5]="lz4"
+BUILT_MODULE_NAME[6]="lz4hc"
+BUILT_MODULE_NAME[7]="mdc"
+BUILT_MODULE_NAME[8]="mgc"
+BUILT_MODULE_NAME[9]="obdclass"
+BUILT_MODULE_NAME[10]="obdecho"
+BUILT_MODULE_NAME[11]="osc"
+BUILT_MODULE_NAME[12]="ptlrpc"
+BUILT_MODULE_NAME[13]="ko2iblnd"
+BUILT_MODULE_NAME[14]="ksocklnd"
+BUILT_MODULE_NAME[15]="libcfs"
+BUILT_MODULE_NAME[16]="lnet"
+BUILT_MODULE_NAME[17]="lnet_selftest"
+BUILT_MODULE_NAME[18]="ptlrpc_gss"
# Location of the modules in the source tree after build
BUILT_MODULE_LOCATION[0]="lustre/fid"
BUILT_MODULE_LOCATION[2]="lustre/lmv"
BUILT_MODULE_LOCATION[3]="lustre/lov"
BUILT_MODULE_LOCATION[4]="lustre/llite"
-BUILT_MODULE_LOCATION[5]="lustre/mdc"
-BUILT_MODULE_LOCATION[6]="lustre/mgc"
-BUILT_MODULE_LOCATION[7]="lustre/obdclass"
-BUILT_MODULE_LOCATION[8]="lustre/obdecho"
-BUILT_MODULE_LOCATION[9]="lustre/osc"
-BUILT_MODULE_LOCATION[10]="lustre/ptlrpc"
-BUILT_MODULE_LOCATION[11]="lnet/klnds/o2iblnd"
-BUILT_MODULE_LOCATION[12]="lnet/klnds/socklnd"
-BUILT_MODULE_LOCATION[13]="libcfs/libcfs"
-BUILT_MODULE_LOCATION[14]="lnet/lnet"
-BUILT_MODULE_LOCATION[15]="lnet/selftest"
-BUILT_MODULE_LOCATION[16]="lustre/ptlrpc/gss"
-
+BUILT_MODULE_LOCATION[5]="lustre/lz4"
+BUILT_MODULE_LOCATION[6]="lustre/lz4"
+BUILT_MODULE_LOCATION[7]="lustre/mdc"
+BUILT_MODULE_LOCATION[8]="lustre/mgc"
+BUILT_MODULE_LOCATION[9]="lustre/obdclass"
+BUILT_MODULE_LOCATION[10]="lustre/obdecho"
+BUILT_MODULE_LOCATION[11]="lustre/osc"
+BUILT_MODULE_LOCATION[12]="lustre/ptlrpc"
+BUILT_MODULE_LOCATION[13]="lnet/klnds/o2iblnd"
+BUILT_MODULE_LOCATION[14]="lnet/klnds/socklnd"
+BUILT_MODULE_LOCATION[15]="libcfs/libcfs"
+BUILT_MODULE_LOCATION[16]="lnet/lnet"
+BUILT_MODULE_LOCATION[17]="lnet/selftest"
+BUILT_MODULE_LOCATION[18]="lustre/ptlrpc/gss"
# Final destination of the modules under /lib/modules/<kernel>/
DEST_MODULE_LOCATION[0]="/updates/kernel/fs/lustre"
DEST_MODULE_LOCATION[8]="/updates/kernel/fs/lustre"
DEST_MODULE_LOCATION[9]="/updates/kernel/fs/lustre"
DEST_MODULE_LOCATION[10]="/updates/kernel/fs/lustre"
-DEST_MODULE_LOCATION[11]="/updates/kernel/net/lustre"
-DEST_MODULE_LOCATION[12]="/updates/kernel/net/lustre"
+DEST_MODULE_LOCATION[11]="/updates/kernel/fs/lustre"
+DEST_MODULE_LOCATION[12]="/updates/kernel/fs/lustre"
DEST_MODULE_LOCATION[13]="/updates/kernel/net/lustre"
DEST_MODULE_LOCATION[14]="/updates/kernel/net/lustre"
DEST_MODULE_LOCATION[15]="/updates/kernel/net/lustre"
-DEST_MODULE_LOCATION[16]="/updates/kernel/fs/lustre"
+DEST_MODULE_LOCATION[16]="/updates/kernel/net/lustre"
+DEST_MODULE_LOCATION[17]="/updates/kernel/net/lustre"
+DEST_MODULE_LOCATION[18]="/updates/kernel/fs/lustre"
dh_installchangelogs -p $(TESTS_PKG) lustre/ChangeLog
dh_compress -p $(TESTS_PKG)
dh_strip -p $(TESTS_PKG)
+ if [ -e $(PWD)/lustre/tests/kernel/kcompr.ko ]; then \
+ mkdir debian/$(TESTS_PKG)/usr/lib/lustre/tests/kernel; \
+ cp $(PWD)/lustre/tests/kernel/kcompr.ko \
+ debian/$(TESTS_PKG)/usr/lib/lustre/tests/kernel/; \
+ fi
dh_installdeb -p $(TESTS_PKG)
dh_fixperms -p $(TESTS_PKG)
dh_gencontrol -p $(TESTS_PKG)
mv $basemodpath/fs/llog_test.ko $basemodpath-tests/fs/llog_test.ko
mkdir -p $RPM_BUILD_ROOT%{_libdir}/lustre/tests/kernel/
mv $basemodpath/fs/kinode.ko $RPM_BUILD_ROOT%{_libdir}/lustre/tests/kernel/
+mv $basemodpath/fs/kcompr.ko $RPM_BUILD_ROOT%{_libdir}/lustre/tests/kernel/
%endif
%endif
obj-m += tests/kernel/
@SERVER_TRUE@obj-m += ost/ mgs/ mdt/ mdd/ ofd/ quota/ osp/ lod/ lfsck/
-@CLIENT_TRUE@obj-m += lov/ osc/ mdc/ lmv/ llite/ fld/
+@CLIENT_TRUE@obj-m += lov/ osc/ mdc/ lmv/ llite/ fld/ lz4/
@LDISKFS_ENABLED_TRUE@obj-m += osd-ldiskfs/
@ZFS_ENABLED_TRUE@obj-m += osd-zfs/
@OSDADDON@
SERVER_SUBDIRS = ost mgs mdt mdd ofd osd-zfs osd-ldiskfs \
quota osp lod target lfsck
-CLIENT_SUBDIRS = mdc lmv llite lov osc
+CLIENT_SUBDIRS = mdc lmv llite lov osc lz4
SUBDIRS := $(ALWAYS_SUBDIRS)
]) # LC_HAVE_CRYPTO_ALLOC_SKCIPHER
#
+# LC_HAVE_CRYPTO_INIT_WAIT
+#
+# Kernel version 4.15 commit ada69a1639ec
+# introduced crypto_init_wait().
+#
+AC_DEFUN([LC_HAVE_CRYPTO_INIT_WAIT], [
+LB_CHECK_COMPILE([if crypto_init_wait is defined],
+crypto_init_wait, [
+ #include <linux/crypto.h>
+],[
+ crypto_init_wait(NULL);
+],[
+ AC_DEFINE(HAVE_CRYPTO_INIT_WAIT, 1,
+ [crypto_init_wait is defined])
+])
+]) # LC_HAVE_CRYPTO_INIT_WAIT
+
+#
# LC_HAVE_INTERVAL_EXP_BLK_INTEGRITY
#
# 4.3 replace interval with interval_exp in 'struct blk_integrity'
LC_PAGEVEC_LOOKUP_THREE_PARAM
LC_BI_BDEV
+ # 4.15
+ LC_HAVE_CRYPTO_INIT_WAIT
+
# 4.17
LC_VM_FAULT_T
LC_VM_FAULT_RETRY
]) # LC_CONFIG_CRYPTO
#
+# LC_CONFIG_LZ4
+#
+# Check whether to build our own LZ4 kernel module.
+# Always embed on SLES, as kernel config might not be reliable.
+#
+AC_DEFUN([LC_CONFIG_LZ4], [
+AS_IF([test x$SUSE_KERNEL = xyes], [enable_lz4=yes], [
+LB_CHECK_CONFIG_IM([CRYPTO_LZ4],[
+ enable_lz4=no],[
+ enable_lz4=yes
+])
+])
+AC_MSG_RESULT([Embed lz4 $enable_lz4])
+]) # LC_CONFIG_LZ4
+
+#
+# LC_CONFIG_LZ4HC
+#
+# Check whether to build our own LZ4HC kernel module.
+# Always embed on SLES, as kernel config might not be reliable.
+#
+AC_DEFUN([LC_CONFIG_LZ4HC], [
+AS_IF([test x$SUSE_KERNEL = xyes], [enable_lz4hc=yes], [
+LB_CHECK_CONFIG_IM([CRYPTO_LZ4HC],[
+ enable_lz4hc=no],[
+ enable_lz4hc=yes
+])
+])
+AC_MSG_RESULT([Embed lz4hc $enable_lz4hc])
+]) # LC_CONFIG_LZ4HC
+
+#
# LC_CONFIGURE
#
# other configure checks
AM_CONDITIONAL(GETSEPOL, test x$enable_getsepol = xyes)
AM_CONDITIONAL(LLCRYPT, test x$enable_llcrypt = xyes)
AM_CONDITIONAL(LIBAIO, test x$enable_libaio = xyes)
+AM_CONDITIONAL(LZ4, test x$enable_lz4 = xyes)
+AM_CONDITIONAL(LZ4HC, test x$enable_lz4hc = xyes)
]) # LC_CONDITIONALS
#
lustre/llite/autoMakefile
lustre/lov/Makefile
lustre/lov/autoMakefile
+lustre/lz4/Makefile
+lustre/lz4/autoMakefile
lustre/mdc/Makefile
lustre/mdc/autoMakefile
lustre/lmv/Makefile
/* sizeof(struct fscrypt_context_v2) = 40 */
#define LLCRYPT_ENC_CTX_SIZE 40
+/* Only the lower bits of the crt_flags field (u32) of struct crypto_tfm are
+ * currently used. So use the top 4 bits to store the compression level.
+ */
+#define LZ4COMPR_LEVEL_SHIFT 28
+#define LZ4COMPR_LEVEL_MASK (~((1 << LZ4COMPR_LEVEL_SHIFT) - 1))
+
+#include <linux/crypto.h>
+/* This is how 'level' is passed to the compression algorithm through
+ * the Cyrpto API when using the generic variant. This is taken into
+ * account only by the Lustre-modified lz4 and lz4hc modules.
+ */
+static inline void ll_crypto_comp_set_level(struct crypto_comp *cc, int level)
+{
+ crypto_tfm_set_flags(crypto_comp_tfm(cc),
+ level << LZ4COMPR_LEVEL_SHIFT);
+}
+
+#ifdef HAVE_CRYPTO_INIT_WAIT
+#include <crypto/acompress.h>
+/* This is how 'level' is passed to the compression algorithm through
+ * the Cyrpto API when using the scomp variant. This is taken into
+ * account only by the Lustre-modified lz4 and lz4hc modules.
+ */
+static inline void ll_crypto_acomp_set_level(struct crypto_acomp *ca, int level)
+{
+ struct crypto_scomp **tfm_ctx = crypto_tfm_ctx(crypto_acomp_tfm(ca));
+ struct crypto_tfm *tfm = (struct crypto_tfm *)*tfm_ctx;
+
+ crypto_tfm_set_flags(tfm, level << LZ4COMPR_LEVEL_SHIFT);
+}
+#endif
/* Encoding/decoding routines inspired from yEnc principles.
* We just take care of a few critical characters:
--- /dev/null
+MODULES :=
+EXTRA_DIST :=
+
+@LZ4_TRUE@MODULES += lz4
+@LZ4_TRUE@lz4-objs := lz4_decompress.o lz4_compress.o llz4.o
+@LZ4_TRUE@EXTRA_DIST += $(lz4-objs:.o=.c) lz4defs.h lz4.h scompress.h
+
+@LZ4HC_TRUE@MODULES += lz4hc
+@LZ4HC_TRUE@lz4hc-objs := lz4_decompress.o lz4hc_compress.o llz4hc.o
+@LZ4HC_TRUE@EXTRA_DIST += $(lz4hc-objs:.o=.c) lz4defs.h lz4.h scompress.h
+
+@INCLUDE_RULES@
--- /dev/null
+#
+# GPL HEADER START
+#
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 only,
+# as published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# General Public License version 2 for more details (a copy is included
+# in the LICENSE file that accompanied this code).
+#
+# You should have received a copy of the GNU General Public License
+# version 2 along with this program; If not, see
+# http://www.gnu.org/licenses/gpl-2.0.html
+#
+# GPL HEADER END
+#
+
+#
+# This file is part of Lustre, http://www.lustre.org/
+#
+
+if MODULES
+modulefs_DATA :=
+if LZ4
+modulefs_DATA += lz4$(KMODEXT)
+endif
+if LZ4HC
+modulefs_DATA += lz4hc$(KMODEXT)
+endif
+endif
+
+MOSTLYCLEANFILES := @MOSTLYCLEANFILES@
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2013 Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/mm.h>
+#include <lustre_crypto.h>
+#include "lz4.h"
+#include "scompress.h"
+
+struct lz4_ctx {
+ void *lz4_comp_mem;
+};
+
+static void *lz4_alloc_ctx(struct crypto_scomp *tfm)
+{
+ void *ctx;
+
+ ctx = kvmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
+ if (!ctx)
+ return ERR_PTR(-ENOMEM);
+
+ return ctx;
+}
+
+static int lz4_init(struct crypto_tfm *tfm)
+{
+ struct lz4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->lz4_comp_mem = lz4_alloc_ctx(NULL);
+ if (IS_ERR(ctx->lz4_comp_mem))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void lz4_free_ctx(struct crypto_scomp *tfm, void *ctx)
+{
+ kvfree(ctx);
+}
+
+static void lz4_exit(struct crypto_tfm *tfm)
+{
+ struct lz4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ lz4_free_ctx(NULL, ctx->lz4_comp_mem);
+}
+
+static int __lz4_compress_crypto(struct crypto_tfm *tfm,
+ const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ u32 flags = crypto_tfm_get_flags(tfm);
+ u8 level = flags >> LZ4COMPR_LEVEL_SHIFT;
+ int out_len;
+
+ /* Remove compression level from flags */
+ crypto_tfm_set_flags(tfm, flags & ~LZ4COMPR_LEVEL_MASK);
+
+ if (level)
+ out_len = LZ4_compress_fast(src, dst, slen, *dlen,
+ to_lz4_level(level), ctx);
+ else
+ out_len = LZ4_compress_default(src, dst, slen, *dlen, ctx);
+ if (!out_len)
+ return -EINVAL;
+
+ *dlen = out_len;
+ return 0;
+}
+
+static int lz4_scompress(struct crypto_scomp *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen,
+ void *ctx)
+{
+ return __lz4_compress_crypto(crypto_scomp_tfm(tfm), src, slen,
+ dst, dlen, ctx);
+}
+
+static int lz4_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ struct lz4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ return __lz4_compress_crypto(tfm, src, slen, dst, dlen,
+ ctx->lz4_comp_mem);
+}
+
+static int __lz4_decompress_crypto(const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ int out_len = LZ4_decompress_safe(src, dst, slen, *dlen);
+
+ if (out_len < 0)
+ return -EINVAL;
+
+ *dlen = out_len;
+ return 0;
+}
+
+static int lz4_sdecompress(struct crypto_scomp *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen,
+ void *ctx)
+{
+ return __lz4_decompress_crypto(src, slen, dst, dlen, NULL);
+}
+
+static int lz4_decompress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst,
+ unsigned int *dlen)
+{
+ return __lz4_decompress_crypto(src, slen, dst, dlen, NULL);
+}
+
+static struct crypto_alg alg_lz4 = {
+ .cra_name = "lz4",
+ .cra_driver_name = "lz4-lustre-generic",
+ .cra_priority = 1,
+ .cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
+ .cra_ctxsize = sizeof(struct lz4_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_init = lz4_init,
+ .cra_exit = lz4_exit,
+ .cra_u = { .compress = {
+ .coa_compress = lz4_compress_crypto,
+ .coa_decompress = lz4_decompress_crypto } }
+};
+
+static struct scomp_alg scomp = {
+ .alloc_ctx = lz4_alloc_ctx,
+ .free_ctx = lz4_free_ctx,
+ .compress = lz4_scompress,
+ .decompress = lz4_sdecompress,
+ .base = {
+ .cra_name = "lz4",
+ .cra_driver_name = "lz4-lustre-scomp",
+ .cra_priority = 1,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init lz4_mod_init(void)
+{
+ int ret;
+
+ ret = crypto_register_alg(&alg_lz4);
+ if (ret)
+ return ret;
+
+ ret = crypto_register_scomp(&scomp);
+ if (ret) {
+ crypto_unregister_alg(&alg_lz4);
+ return ret;
+ }
+
+ return ret;
+}
+
+static void __exit lz4_mod_fini(void)
+{
+ crypto_unregister_alg(&alg_lz4);
+ crypto_unregister_scomp(&scomp);
+}
+
+subsys_initcall(lz4_mod_init);
+module_exit(lz4_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2013 Chanho Min <chanho.min@lge.com>
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/mm.h>
+#include <lustre_crypto.h>
+#include "lz4.h"
+#include "scompress.h"
+
+struct lz4hc_ctx {
+ void *lz4hc_comp_mem;
+};
+
+static void *lz4hc_alloc_ctx(struct crypto_scomp *tfm)
+{
+ void *ctx;
+
+ ctx = kvmalloc(LZ4HC_MEM_COMPRESS, GFP_KERNEL);
+ if (!ctx)
+ return ERR_PTR(-ENOMEM);
+
+ return ctx;
+}
+
+static int lz4hc_init(struct crypto_tfm *tfm)
+{
+ struct lz4hc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->lz4hc_comp_mem = lz4hc_alloc_ctx(NULL);
+ if (IS_ERR(ctx->lz4hc_comp_mem))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void lz4hc_free_ctx(struct crypto_scomp *tfm, void *ctx)
+{
+ kvfree(ctx);
+}
+
+static void lz4hc_exit(struct crypto_tfm *tfm)
+{
+ struct lz4hc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ lz4hc_free_ctx(NULL, ctx->lz4hc_comp_mem);
+}
+
+static int __lz4hc_compress_crypto(struct crypto_tfm *tfm,
+ const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ u32 flags = crypto_tfm_get_flags(tfm);
+ u8 level = flags >> LZ4COMPR_LEVEL_SHIFT;
+ int out_len;
+
+ /* Remove compression level from flags */
+ crypto_tfm_set_flags(tfm, flags & ~LZ4COMPR_LEVEL_MASK);
+
+ out_len = LZ4_compress_HC(src, dst, slen, *dlen,
+ to_lz4hc_level(level), ctx);
+ if (!out_len)
+ return -EINVAL;
+
+ *dlen = out_len;
+ return 0;
+}
+
+static int lz4hc_scompress(struct crypto_scomp *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen,
+ void *ctx)
+{
+ return __lz4hc_compress_crypto(crypto_scomp_tfm(tfm), src, slen,
+ dst, dlen, ctx);
+}
+
+static int lz4hc_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst,
+ unsigned int *dlen)
+{
+ struct lz4hc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ return __lz4hc_compress_crypto(tfm, src, slen, dst, dlen,
+ ctx->lz4hc_comp_mem);
+}
+
+static int __lz4hc_decompress_crypto(const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ int out_len = LZ4_decompress_safe(src, dst, slen, *dlen);
+
+ if (out_len < 0)
+ return -EINVAL;
+
+ *dlen = out_len;
+ return 0;
+}
+
+static int lz4hc_sdecompress(struct crypto_scomp *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen,
+ void *ctx)
+{
+ return __lz4hc_decompress_crypto(src, slen, dst, dlen, NULL);
+}
+
+static int lz4hc_decompress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst,
+ unsigned int *dlen)
+{
+ return __lz4hc_decompress_crypto(src, slen, dst, dlen, NULL);
+}
+
+static struct crypto_alg alg_lz4hc = {
+ .cra_name = "lz4hc",
+ .cra_driver_name = "lz4hc-lustre-generic",
+ .cra_priority = 1,
+ .cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
+ .cra_ctxsize = sizeof(struct lz4hc_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_init = lz4hc_init,
+ .cra_exit = lz4hc_exit,
+ .cra_u = { .compress = {
+ .coa_compress = lz4hc_compress_crypto,
+ .coa_decompress = lz4hc_decompress_crypto } }
+};
+
+static struct scomp_alg scomp = {
+ .alloc_ctx = lz4hc_alloc_ctx,
+ .free_ctx = lz4hc_free_ctx,
+ .compress = lz4hc_scompress,
+ .decompress = lz4hc_sdecompress,
+ .base = {
+ .cra_name = "lz4hc",
+ .cra_driver_name = "lz4hc-lustre-scomp",
+ .cra_priority = 1,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init lz4hc_mod_init(void)
+{
+ int ret;
+
+ ret = crypto_register_alg(&alg_lz4hc);
+ if (ret)
+ return ret;
+
+ ret = crypto_register_scomp(&scomp);
+ if (ret) {
+ crypto_unregister_alg(&alg_lz4hc);
+ return ret;
+ }
+
+ return ret;
+}
+
+static void __exit lz4hc_mod_fini(void)
+{
+ crypto_unregister_alg(&alg_lz4hc);
+ crypto_unregister_scomp(&scomp);
+}
+
+subsys_initcall(lz4hc_mod_init);
+module_exit(lz4hc_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4HC Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lz4hc");
--- /dev/null
+/* LZ4 Kernel Interface
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ * Copyright (C) 2016, Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
+ *
+ * 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.
+ *
+ * This file is based on the original header file
+ * for LZ4 - Fast LZ compression algorithm.
+ *
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2016, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
+ */
+
+#ifndef __LZ4_H__
+#define __LZ4_H__
+
+#include <linux/types.h>
+#include <linux/string.h> /* memset, memcpy */
+
+/*-************************************************************************
+ * CONSTANTS
+ **************************************************************************/
+/*
+ * LZ4_MEMORY_USAGE :
+ * Memory usage formula : N->2^N Bytes
+ * (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+ * Increasing memory usage improves compression ratio
+ * Reduced memory usage can improve speed, due to cache effect
+ * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
+ */
+#define LZ4_MEMORY_USAGE 14
+
+#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */
+#define LZ4_COMPRESSBOUND(isize) (\
+ (unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE \
+ ? 0 \
+ : (isize) + ((isize)/255) + 16)
+
+#define LZ4_ACCELERATION_DEFAULT 1
+#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2)
+#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)
+
+/* Level as stored in the Lustre file layout is limited to 4 bits, i.e.
+ * between 0 and 15. But for lz4, acceleration factor can be fine tuned
+ * with each successive value providing roughly +~3% to speed.
+ * So we map the provided level to the lz4 acceleration factor by keeping 1-9
+ * as-is, and then going by steps of 3 so 12 15 18 21 24 27.
+ */
+static inline u8 to_lz4_level(u8 level)
+{
+ if (!level)
+ return LZ4_ACCELERATION_DEFAULT;
+ else if (level < 10)
+ return level;
+ else
+ return (level - 9) * 3 + 9;
+}
+
+#define LZ4HC_MIN_CLEVEL 3
+#define LZ4HC_DEFAULT_CLEVEL 9
+#define LZ4HC_MAX_CLEVEL 16
+
+/* Level as stored in the Lustre file layout is limited to 4 bits, i.e.
+ * between 0 and 15.
+ * So we map the provided level to the lz4hc compression level
+ * simply by adding 1.
+ */
+static inline u8 to_lz4hc_level(u8 level)
+{
+ if (!level)
+ return LZ4HC_DEFAULT_CLEVEL;
+ else
+ return level + 1;
+}
+
+#define LZ4HC_DICTIONARY_LOGSIZE 16
+#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE)
+#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1)
+#define LZ4HC_HASH_LOG (LZ4HC_DICTIONARY_LOGSIZE - 1)
+#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG)
+#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1)
+
+/*-************************************************************************
+ * STREAMING CONSTANTS AND STRUCTURES
+ **************************************************************************/
+#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE - 3)) + 4)
+#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+
+#define LZ4_STREAMHCSIZE 262192
+#define LZ4_STREAMHCSIZE_SIZET (262192 / sizeof(size_t))
+
+#define LZ4_STREAMDECODESIZE_U64 4
+#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * \
+ sizeof(unsigned long long))
+
+/*
+ * LZ4_stream_t - information structure to track an LZ4 stream.
+ */
+typedef struct {
+ uint32_t hashTable[LZ4_HASH_SIZE_U32];
+ uint32_t currentOffset;
+ uint32_t initCheck;
+ const uint8_t *dictionary;
+ uint8_t *bufferStart;
+ uint32_t dictSize;
+} LZ4_stream_t_internal;
+typedef union {
+ unsigned long long table[LZ4_STREAMSIZE_U64];
+ LZ4_stream_t_internal internal_donotuse;
+} LZ4_stream_t;
+
+/*
+ * LZ4_streamHC_t - information structure to track an LZ4HC stream.
+ */
+typedef struct {
+ unsigned int hashTable[LZ4HC_HASHTABLESIZE];
+ unsigned short chainTable[LZ4HC_MAXD];
+ /* next block to continue on current prefix */
+ const unsigned char *end;
+ /* All index relative to this position */
+ const unsigned char *base;
+ /* alternate base for extDict */
+ const unsigned char *dictBase;
+ /* below that point, need extDict */
+ unsigned int dictLimit;
+ /* below that point, no more dict */
+ unsigned int lowLimit;
+ /* index from which to continue dict update */
+ unsigned int nextToUpdate;
+ unsigned int compressionLevel;
+} LZ4HC_CCtx_internal;
+typedef union {
+ size_t table[LZ4_STREAMHCSIZE_SIZET];
+ LZ4HC_CCtx_internal internal_donotuse;
+} LZ4_streamHC_t;
+
+/*
+ * LZ4_streamDecode_t - information structure to track an
+ * LZ4 stream during decompression.
+ *
+ * init this structure using LZ4_setStreamDecode (or memset()) before first use
+ */
+typedef struct {
+ const uint8_t *externalDict;
+ size_t extDictSize;
+ const uint8_t *prefixEnd;
+ size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+typedef union {
+ unsigned long long table[LZ4_STREAMDECODESIZE_U64];
+ LZ4_streamDecode_t_internal internal_donotuse;
+} LZ4_streamDecode_t;
+
+/*-************************************************************************
+ * SIZE OF STATE
+ **************************************************************************/
+#define LZ4_MEM_COMPRESS LZ4_STREAMSIZE
+#define LZ4HC_MEM_COMPRESS LZ4_STREAMHCSIZE
+
+/*-************************************************************************
+ * Compression Functions
+ **************************************************************************/
+
+/**
+ * LZ4_compressBound() - Max. output size in worst case szenarios
+ * @isize: Size of the input data
+ *
+ * Return: Max. size LZ4 may output in a "worst case" szenario
+ * (data not compressible)
+ */
+static inline int LZ4_compressBound(size_t isize)
+{
+ return LZ4_COMPRESSBOUND(isize);
+}
+
+/**
+ * LZ4_compress_default() - Compress data from source to dest
+ * @source: source address of the original data
+ * @dest: output buffer address of the compressed data
+ * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @maxOutputSize: full or partial size of buffer 'dest'
+ * which must be already allocated
+ * @wrkmem: address of the working memory.
+ * This requires 'workmem' of LZ4_MEM_COMPRESS.
+ *
+ * Compresses 'sourceSize' bytes from buffer 'source'
+ * into already allocated 'dest' buffer of size 'maxOutputSize'.
+ * Compression is guaranteed to succeed if
+ * 'maxOutputSize' >= LZ4_compressBound(inputSize).
+ * It also runs faster, so it's a recommended setting.
+ * If the function cannot compress 'source' into a more limited 'dest' budget,
+ * compression stops *immediately*, and the function result is zero.
+ * As a consequence, 'dest' content is not valid.
+ *
+ * Return: Number of bytes written into buffer 'dest'
+ * (necessarily <= maxOutputSize) or 0 if compression fails
+ */
+int LZ4_compress_default(const char *source, char *dest, int inputSize,
+ int maxOutputSize, void *wrkmem);
+
+/**
+ * LZ4_compress_fast() - As LZ4_compress_default providing an acceleration param
+ * @source: source address of the original data
+ * @dest: output buffer address of the compressed data
+ * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @maxOutputSize: full or partial size of buffer 'dest'
+ * which must be already allocated
+ * @acceleration: acceleration factor
+ * @wrkmem: address of the working memory.
+ * This requires 'workmem' of LZ4_MEM_COMPRESS.
+ *
+ * Same as LZ4_compress_default(), but allows to select an "acceleration"
+ * factor. The larger the acceleration value, the faster the algorithm,
+ * but also the lesser the compression. It's a trade-off. It can be fine tuned,
+ * with each successive value providing roughly +~3% to speed.
+ * An acceleration value of "1" is the same as regular LZ4_compress_default()
+ * Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT, which is 1.
+ *
+ * Return: Number of bytes written into buffer 'dest'
+ * (necessarily <= maxOutputSize) or 0 if compression fails
+ */
+int LZ4_compress_fast(const char *source, char *dest, int inputSize,
+ int maxOutputSize, int acceleration, void *wrkmem);
+
+/**
+ * LZ4_compress_destSize() - Compress as much data as possible
+ * from source to dest
+ * @source: source address of the original data
+ * @dest: output buffer address of the compressed data
+ * @sourceSizePtr: will be modified to indicate how many bytes where read
+ * from 'source' to fill 'dest'. New value is necessarily <= old value.
+ * @targetDestSize: Size of buffer 'dest' which must be already allocated
+ * @wrkmem: address of the working memory.
+ * This requires 'workmem' of LZ4_MEM_COMPRESS.
+ *
+ * Reverse the logic, by compressing as much data as possible
+ * from 'source' buffer into already allocated buffer 'dest'
+ * of size 'targetDestSize'.
+ * This function either compresses the entire 'source' content into 'dest'
+ * if it's large enough, or fill 'dest' buffer completely with as much data as
+ * possible from 'source'.
+ *
+ * Return: Number of bytes written into 'dest' (necessarily <= targetDestSize)
+ * or 0 if compression fails
+ */
+int LZ4_compress_destSize(const char *source, char *dest, int *sourceSizePtr,
+ int targetDestSize, void *wrkmem);
+
+/*-************************************************************************
+ * Decompression Functions
+ **************************************************************************/
+
+/**
+ * LZ4_decompress_fast() - Decompresses data from 'source' into 'dest'
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the uncompressed data
+ * which must be already allocated with 'originalSize' bytes
+ * @originalSize: is the original and therefore uncompressed size
+ *
+ * Decompresses data from 'source' into 'dest'.
+ * This function fully respect memory boundaries for properly formed
+ * compressed data.
+ * It is a bit faster than LZ4_decompress_safe().
+ * However, it does not provide any protection against intentionally
+ * modified data stream (malicious input).
+ * Use this function in trusted environment only
+ * (data to decode comes from a trusted source).
+ *
+ * Return: number of bytes read from the source buffer
+ * or a negative result if decompression fails.
+ */
+int LZ4_decompress_fast(const char *source, char *dest, int originalSize);
+
+/**
+ * LZ4_decompress_safe() - Decompression protected against buffer overflow
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the uncompressed data
+ * which must be already allocated
+ * @compressedSize: is the precise full size of the compressed block
+ * @maxDecompressedSize: is the size of 'dest' buffer
+ *
+ * Decompresses data from 'source' into 'dest'.
+ * If the source stream is detected malformed, the function will
+ * stop decoding and return a negative result.
+ * This function is protected against buffer overflow exploits,
+ * including malicious data packets. It never writes outside output buffer,
+ * nor reads outside input buffer.
+ *
+ * Return: number of bytes decompressed into destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * or a negative result in case of error
+ */
+int LZ4_decompress_safe(const char *source, char *dest, int compressedSize,
+ int maxDecompressedSize);
+
+/**
+ * LZ4_decompress_safe_partial() - Decompress a block of size 'compressedSize'
+ * at position 'source' into buffer 'dest'
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the decompressed data which must be
+ * already allocated
+ * @compressedSize: is the precise full size of the compressed block.
+ * @targetOutputSize: the decompression operation will try
+ * to stop as soon as 'targetOutputSize' has been reached
+ * @maxDecompressedSize: is the size of destination buffer
+ *
+ * This function decompresses a compressed block of size 'compressedSize'
+ * at position 'source' into destination buffer 'dest'
+ * of size 'maxDecompressedSize'.
+ * The function tries to stop decompressing operation as soon as
+ * 'targetOutputSize' has been reached, reducing decompression time.
+ * This function never writes outside of output buffer,
+ * and never reads outside of input buffer.
+ * It is therefore protected against malicious data packets.
+ *
+ * Return: the number of bytes decoded in the destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * or a negative result in case of error
+ *
+ */
+int LZ4_decompress_safe_partial(const char *source, char *dest,
+ int compressedSize, int targetOutputSize, int maxDecompressedSize);
+
+/*-************************************************************************
+ * LZ4 HC Compression
+ **************************************************************************/
+
+/**
+ * LZ4_compress_HC() - Compress data from `src` into `dst`, using HC algorithm
+ * @src: source address of the original data
+ * @dst: output buffer address of the compressed data
+ * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @dstCapacity: full or partial size of buffer 'dst',
+ * which must be already allocated
+ * @compressionLevel: Recommended values are between 4 and 9, although any
+ * value between 1 and LZ4HC_MAX_CLEVEL will work.
+ * Values >LZ4HC_MAX_CLEVEL behave the same as 16.
+ * @wrkmem: address of the working memory.
+ * This requires 'wrkmem' of size LZ4HC_MEM_COMPRESS.
+ *
+ * Compress data from 'src' into 'dst', using the more powerful
+ * but slower "HC" algorithm. Compression is guaranteed to succeed if
+ * `dstCapacity >= LZ4_compressBound(srcSize)
+ *
+ * Return : the number of bytes written into 'dst' or 0 if compression fails.
+ */
+int LZ4_compress_HC(const char *src, char *dst, int srcSize, int dstCapacity,
+ int compressionLevel, void *wrkmem);
+
+/**
+ * LZ4_resetStreamHC() - Init an allocated 'LZ4_streamHC_t' structure
+ * @streamHCPtr: pointer to the 'LZ4_streamHC_t' structure
+ * @compressionLevel: Recommended values are between 4 and 9, although any
+ * value between 1 and LZ4HC_MAX_CLEVEL will work.
+ * Values >LZ4HC_MAX_CLEVEL behave the same as 16.
+ *
+ * An LZ4_streamHC_t structure can be allocated once
+ * and re-used multiple times.
+ * Use this function to init an allocated `LZ4_streamHC_t` structure
+ * and start a new compression.
+ */
+void LZ4_resetStreamHC(LZ4_streamHC_t *streamHCPtr, int compressionLevel);
+
+/**
+ * LZ4_loadDictHC() - Load a static dictionary into LZ4_streamHC
+ * @streamHCPtr: pointer to the LZ4HC_stream_t
+ * @dictionary: dictionary to load
+ * @dictSize: size of dictionary
+ *
+ * Use this function to load a static dictionary into LZ4HC_stream.
+ * Any previous data will be forgotten, only 'dictionary'
+ * will remain in memory.
+ * Loading a size of 0 is allowed.
+ *
+ * Return : dictionary size, in bytes (necessarily <= 64 KB)
+ */
+int LZ4_loadDictHC(LZ4_streamHC_t *streamHCPtr, const char *dictionary,
+ int dictSize);
+
+/**
+ * LZ4_compress_HC_continue() - Compress 'src' using data from previously
+ * compressed blocks as a dictionary using the HC algorithm
+ * @streamHCPtr: Pointer to the previous 'LZ4_streamHC_t' structure
+ * @src: source address of the original data
+ * @dst: output buffer address of the compressed data,
+ * which must be already allocated
+ * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @maxDstSize: full or partial size of buffer 'dest'
+ * which must be already allocated
+ *
+ * These functions compress data in successive blocks of any size, using
+ * previous blocks as dictionary. One key assumption is that previous
+ * blocks (up to 64 KB) remain read-accessible while
+ * compressing next blocks. There is an exception for ring buffers,
+ * which can be smaller than 64 KB.
+ * Ring buffers scenario is automatically detected and handled by
+ * LZ4_compress_HC_continue().
+ * Before starting compression, state must be properly initialized,
+ * using LZ4_resetStreamHC().
+ * A first "fictional block" can then be designated as
+ * initial dictionary, using LZ4_loadDictHC() (Optional).
+ * Then, use LZ4_compress_HC_continue()
+ * to compress each successive block. Previous memory blocks
+ * (including initial dictionary when present) must remain accessible
+ * and unmodified during compression.
+ * 'dst' buffer should be sized to handle worst case scenarios, using
+ * LZ4_compressBound(), to ensure operation success.
+ * If, for any reason, previous data blocks can't be preserved unmodified
+ * in memory during next compression block,
+ * you must save it to a safer memory space, using LZ4_saveDictHC().
+ * Return value of LZ4_saveDictHC() is the size of dictionary
+ * effectively saved into 'safeBuffer'.
+ *
+ * Return: Number of bytes written into buffer 'dst' or 0 if compression fails
+ */
+int LZ4_compress_HC_continue(LZ4_streamHC_t *streamHCPtr, const char *src,
+ char *dst, int srcSize, int maxDstSize);
+
+/**
+ * LZ4_saveDictHC() - Save static dictionary from LZ4HC_stream
+ * @streamHCPtr: pointer to the 'LZ4HC_stream_t' structure
+ * @safeBuffer: buffer to save dictionary to, must be already allocated
+ * @maxDictSize: size of 'safeBuffer'
+ *
+ * If previously compressed data block is not guaranteed
+ * to remain available at its memory location,
+ * save it into a safer place (char *safeBuffer).
+ * Note : you don't need to call LZ4_loadDictHC() afterwards,
+ * dictionary is immediately usable, you can therefore call
+ * LZ4_compress_HC_continue().
+ *
+ * Return : saved dictionary size in bytes (necessarily <= maxDictSize),
+ * or 0 if error.
+ */
+int LZ4_saveDictHC(LZ4_streamHC_t *streamHCPtr, char *safeBuffer,
+ int maxDictSize);
+
+/*-*********************************************
+ * Streaming Compression Functions
+ ***********************************************/
+
+/**
+ * LZ4_resetStream() - Init an allocated 'LZ4_stream_t' structure
+ * @LZ4_stream: pointer to the 'LZ4_stream_t' structure
+ *
+ * An LZ4_stream_t structure can be allocated once
+ * and re-used multiple times.
+ * Use this function to init an allocated `LZ4_stream_t` structure
+ * and start a new compression.
+ */
+void LZ4_resetStream(LZ4_stream_t *LZ4_stream);
+
+/**
+ * LZ4_loadDict() - Load a static dictionary into LZ4_stream
+ * @streamPtr: pointer to the LZ4_stream_t
+ * @dictionary: dictionary to load
+ * @dictSize: size of dictionary
+ *
+ * Use this function to load a static dictionary into LZ4_stream.
+ * Any previous data will be forgotten, only 'dictionary'
+ * will remain in memory.
+ * Loading a size of 0 is allowed.
+ *
+ * Return : dictionary size, in bytes (necessarily <= 64 KB)
+ */
+int LZ4_loadDict(LZ4_stream_t *streamPtr, const char *dictionary,
+ int dictSize);
+
+/**
+ * LZ4_saveDict() - Save static dictionary from LZ4_stream
+ * @streamPtr: pointer to the 'LZ4_stream_t' structure
+ * @safeBuffer: buffer to save dictionary to, must be already allocated
+ * @dictSize: size of 'safeBuffer'
+ *
+ * If previously compressed data block is not guaranteed
+ * to remain available at its memory location,
+ * save it into a safer place (char *safeBuffer).
+ * Note : you don't need to call LZ4_loadDict() afterwards,
+ * dictionary is immediately usable, you can therefore call
+ * LZ4_compress_fast_continue().
+ *
+ * Return : saved dictionary size in bytes (necessarily <= dictSize),
+ * or 0 if error.
+ */
+int LZ4_saveDict(LZ4_stream_t *streamPtr, char *safeBuffer, int dictSize);
+
+/**
+ * LZ4_compress_fast_continue() - Compress 'src' using data from previously
+ * compressed blocks as a dictionary
+ * @streamPtr: Pointer to the previous 'LZ4_stream_t' structure
+ * @src: source address of the original data
+ * @dst: output buffer address of the compressed data,
+ * which must be already allocated
+ * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @maxDstSize: full or partial size of buffer 'dest'
+ * which must be already allocated
+ * @acceleration: acceleration factor
+ *
+ * Compress buffer content 'src', using data from previously compressed blocks
+ * as dictionary to improve compression ratio.
+ * Important : Previous data blocks are assumed to still
+ * be present and unmodified !
+ * If maxDstSize >= LZ4_compressBound(srcSize),
+ * compression is guaranteed to succeed, and runs faster.
+ *
+ * Return: Number of bytes written into buffer 'dst' or 0 if compression fails
+ */
+int LZ4_compress_fast_continue(LZ4_stream_t *streamPtr, const char *src,
+ char *dst, int srcSize, int maxDstSize, int acceleration);
+
+/**
+ * LZ4_setStreamDecode() - Instruct where to find dictionary
+ * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure
+ * @dictionary: dictionary to use
+ * @dictSize: size of dictionary
+ *
+ * Use this function to instruct where to find the dictionary.
+ * Setting a size of 0 is allowed (same effect as reset).
+ *
+ * Return: 1 if OK, 0 if error
+ */
+int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *dictionary, int dictSize);
+
+/**
+ * LZ4_decompress_safe_continue() - Decompress blocks in streaming mode
+ * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the uncompressed data
+ * which must be already allocated
+ * @compressedSize: is the precise full size of the compressed block
+ * @maxDecompressedSize: is the size of 'dest' buffer
+ *
+ * This decoding function allows decompression of multiple blocks
+ * in "streaming" mode.
+ * Previously decoded blocks *must* remain available at the memory position
+ * where they were decoded (up to 64 KB)
+ * In the case of a ring buffers, decoding buffer must be either :
+ * - Exactly same size as encoding buffer, with same update rule
+ * (block boundaries at same positions) In which case,
+ * the decoding & encoding ring buffer can have any size,
+ * including very small ones ( < 64 KB).
+ * - Larger than encoding buffer, by a minimum of maxBlockSize more bytes.
+ * maxBlockSize is implementation dependent.
+ * It's the maximum size you intend to compress into a single block.
+ * In which case, encoding and decoding buffers do not need
+ * to be synchronized, and encoding ring buffer can have any size,
+ * including small ones ( < 64 KB).
+ * - _At least_ 64 KB + 8 bytes + maxBlockSize.
+ * In which case, encoding and decoding buffers do not need to be
+ * synchronized, and encoding ring buffer can have any size,
+ * including larger than decoding buffer. W
+ * Whenever these conditions are not possible, save the last 64KB of decoded
+ * data into a safe buffer, and indicate where it is saved
+ * using LZ4_setStreamDecode()
+ *
+ * Return: number of bytes decompressed into destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * or a negative result in case of error
+ */
+int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int compressedSize,
+ int maxDecompressedSize);
+
+/**
+ * LZ4_decompress_fast_continue() - Decompress blocks in streaming mode
+ * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the uncompressed data
+ * which must be already allocated with 'originalSize' bytes
+ * @originalSize: is the original and therefore uncompressed size
+ *
+ * This decoding function allows decompression of multiple blocks
+ * in "streaming" mode.
+ * Previously decoded blocks *must* remain available at the memory position
+ * where they were decoded (up to 64 KB)
+ * In the case of a ring buffers, decoding buffer must be either :
+ * - Exactly same size as encoding buffer, with same update rule
+ * (block boundaries at same positions) In which case,
+ * the decoding & encoding ring buffer can have any size,
+ * including very small ones ( < 64 KB).
+ * - Larger than encoding buffer, by a minimum of maxBlockSize more bytes.
+ * maxBlockSize is implementation dependent.
+ * It's the maximum size you intend to compress into a single block.
+ * In which case, encoding and decoding buffers do not need
+ * to be synchronized, and encoding ring buffer can have any size,
+ * including small ones ( < 64 KB).
+ * - _At least_ 64 KB + 8 bytes + maxBlockSize.
+ * In which case, encoding and decoding buffers do not need to be
+ * synchronized, and encoding ring buffer can have any size,
+ * including larger than decoding buffer. W
+ * Whenever these conditions are not possible, save the last 64KB of decoded
+ * data into a safe buffer, and indicate where it is saved
+ * using LZ4_setStreamDecode()
+ *
+ * Return: number of bytes decompressed into destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * or a negative result in case of error
+ */
+int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int originalSize);
+
+/**
+ * LZ4_decompress_safe_usingDict() - Same as LZ4_setStreamDecode()
+ * followed by LZ4_decompress_safe_continue()
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the uncompressed data
+ * which must be already allocated
+ * @compressedSize: is the precise full size of the compressed block
+ * @maxDecompressedSize: is the size of 'dest' buffer
+ * @dictStart: pointer to the start of the dictionary in memory
+ * @dictSize: size of dictionary
+ *
+ * This decoding function works the same as
+ * a combination of LZ4_setStreamDecode() followed by
+ * LZ4_decompress_safe_continue()
+ * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure.
+ *
+ * Return: number of bytes decompressed into destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * or a negative result in case of error
+ */
+int LZ4_decompress_safe_usingDict(const char *source, char *dest,
+ int compressedSize, int maxDecompressedSize, const char *dictStart,
+ int dictSize);
+
+/**
+ * LZ4_decompress_fast_usingDict() - Same as LZ4_setStreamDecode()
+ * followed by LZ4_decompress_fast_continue()
+ * @source: source address of the compressed data
+ * @dest: output buffer address of the uncompressed data
+ * which must be already allocated with 'originalSize' bytes
+ * @originalSize: is the original and therefore uncompressed size
+ * @dictStart: pointer to the start of the dictionary in memory
+ * @dictSize: size of dictionary
+ *
+ * This decoding function works the same as
+ * a combination of LZ4_setStreamDecode() followed by
+ * LZ4_decompress_fast_continue()
+ * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure.
+ *
+ * Return: number of bytes decompressed into destination buffer
+ * (necessarily <= maxDecompressedSize)
+ * or a negative result in case of error
+ */
+int LZ4_decompress_fast_usingDict(const char *source, char *dest,
+ int originalSize, const char *dictStart, int dictSize);
+
+#endif
--- /dev/null
+/*
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011 - 2016, Yann Collet.
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
+ *
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
+ */
+
+/*-************************************
+ * Dependencies
+ **************************************/
+#include "lz4.h"
+#include "lz4defs.h"
+#include <linux/kernel.h>
+#include <asm/unaligned.h>
+
+static const int LZ4_minLength = (MFLIMIT + 1);
+static const int LZ4_64Klimit = ((64 * KB) + (MFLIMIT - 1));
+
+/*-******************************
+ * Compression functions
+ ********************************/
+static FORCE_INLINE U32 LZ4_hash4(
+ U32 sequence,
+ tableType_t const tableType)
+{
+ if (tableType == byU16)
+ return ((sequence * 2654435761U)
+ >> ((MINMATCH * 8) - (LZ4_HASHLOG + 1)));
+ else
+ return ((sequence * 2654435761U)
+ >> ((MINMATCH * 8) - LZ4_HASHLOG));
+}
+
+static FORCE_INLINE U32 LZ4_hash5(
+ U64 sequence,
+ tableType_t const tableType)
+{
+ const U32 hashLog = (tableType == byU16)
+ ? LZ4_HASHLOG + 1
+ : LZ4_HASHLOG;
+
+#if LZ4_LITTLE_ENDIAN
+ static const U64 prime5bytes = 889523592379ULL;
+
+ return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
+#else
+ static const U64 prime8bytes = 11400714785074694791ULL;
+
+ return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
+#endif
+}
+
+static FORCE_INLINE U32 LZ4_hashPosition(
+ const void *p,
+ tableType_t const tableType)
+{
+#if LZ4_ARCH64
+ if (tableType == byU32)
+ return LZ4_hash5(LZ4_read_ARCH(p), tableType);
+#endif
+
+ return LZ4_hash4(LZ4_read32(p), tableType);
+}
+
+static void LZ4_putPositionOnHash(
+ const BYTE *p,
+ U32 h,
+ void *tableBase,
+ tableType_t const tableType,
+ const BYTE *srcBase)
+{
+ switch (tableType) {
+ case byPtr:
+ {
+ const BYTE **hashTable = (const BYTE **)tableBase;
+
+ hashTable[h] = p;
+ return;
+ }
+ case byU32:
+ {
+ U32 *hashTable = (U32 *) tableBase;
+
+ hashTable[h] = (U32)(p - srcBase);
+ return;
+ }
+ case byU16:
+ {
+ U16 *hashTable = (U16 *) tableBase;
+
+ hashTable[h] = (U16)(p - srcBase);
+ return;
+ }
+ }
+}
+
+static FORCE_INLINE void LZ4_putPosition(
+ const BYTE *p,
+ void *tableBase,
+ tableType_t tableType,
+ const BYTE *srcBase)
+{
+ U32 const h = LZ4_hashPosition(p, tableType);
+
+ LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
+}
+
+static const BYTE *LZ4_getPositionOnHash(
+ U32 h,
+ void *tableBase,
+ tableType_t tableType,
+ const BYTE *srcBase)
+{
+ if (tableType == byPtr) {
+ const BYTE **hashTable = (const BYTE **) tableBase;
+
+ return hashTable[h];
+ }
+
+ if (tableType == byU32) {
+ const U32 * const hashTable = (U32 *) tableBase;
+
+ return hashTable[h] + srcBase;
+ }
+
+ {
+ /* default, to ensure a return */
+ const U16 * const hashTable = (U16 *) tableBase;
+
+ return hashTable[h] + srcBase;
+ }
+}
+
+static FORCE_INLINE const BYTE *LZ4_getPosition(
+ const BYTE *p,
+ void *tableBase,
+ tableType_t tableType,
+ const BYTE *srcBase)
+{
+ U32 const h = LZ4_hashPosition(p, tableType);
+
+ return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
+}
+
+
+/*
+ * LZ4_compress_generic() :
+ * inlined, to ensure branches are decided at compilation time
+ */
+static FORCE_INLINE int LZ4_compress_generic(
+ LZ4_stream_t_internal * const dictPtr,
+ const char * const source,
+ char * const dest,
+ const int inputSize,
+ const int maxOutputSize,
+ const limitedOutput_directive outputLimited,
+ const tableType_t tableType,
+ const dict_directive dict,
+ const dictIssue_directive dictIssue,
+ const U32 acceleration)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *base;
+ const BYTE *lowLimit;
+ const BYTE * const lowRefLimit = ip - dictPtr->dictSize;
+ const BYTE * const dictionary = dictPtr->dictionary;
+ const BYTE * const dictEnd = dictionary + dictPtr->dictSize;
+ const size_t dictDelta = dictEnd - (const BYTE *)source;
+ const BYTE *anchor = (const BYTE *) source;
+ const BYTE * const iend = ip + inputSize;
+ const BYTE * const mflimit = iend - MFLIMIT;
+ const BYTE * const matchlimit = iend - LASTLITERALS;
+
+ BYTE *op = (BYTE *) dest;
+ BYTE * const olimit = op + maxOutputSize;
+
+ U32 forwardH;
+ size_t refDelta = 0;
+
+ /* Init conditions */
+ if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) {
+ /* Unsupported inputSize, too large (or negative) */
+ return 0;
+ }
+
+ switch (dict) {
+ case noDict:
+ default:
+ base = (const BYTE *)source;
+ lowLimit = (const BYTE *)source;
+ break;
+ case withPrefix64k:
+ base = (const BYTE *)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE *)source - dictPtr->dictSize;
+ break;
+ case usingExtDict:
+ base = (const BYTE *)source - dictPtr->currentOffset;
+ lowLimit = (const BYTE *)source;
+ break;
+ }
+
+ if ((tableType == byU16)
+ && (inputSize >= LZ4_64Klimit)) {
+ /* Size too large (not within 64K limit) */
+ return 0;
+ }
+
+ if (inputSize < LZ4_minLength) {
+ /* Input too small, no compression (all literals) */
+ goto _last_literals;
+ }
+
+ /* First Byte */
+ LZ4_putPosition(ip, dictPtr->hashTable, tableType, base);
+ ip++;
+ forwardH = LZ4_hashPosition(ip, tableType);
+
+ /* Main Loop */
+ for ( ; ; ) {
+ const BYTE *match;
+ BYTE *token;
+
+ /* Find a match */
+ {
+ const BYTE *forwardIp = ip;
+ unsigned int step = 1;
+ unsigned int searchMatchNb = acceleration << LZ4_SKIPTRIGGER;
+
+ do {
+ U32 const h = forwardH;
+
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_SKIPTRIGGER);
+
+ if (unlikely(forwardIp > mflimit))
+ goto _last_literals;
+
+ match = LZ4_getPositionOnHash(h,
+ dictPtr->hashTable,
+ tableType, base);
+
+ if (dict == usingExtDict) {
+ if (match < (const BYTE *)source) {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ } else {
+ refDelta = 0;
+ lowLimit = (const BYTE *)source;
+ } }
+
+ forwardH = LZ4_hashPosition(forwardIp,
+ tableType);
+
+ LZ4_putPositionOnHash(ip, h, dictPtr->hashTable,
+ tableType, base);
+ } while (((dictIssue == dictSmall)
+ ? (match < lowRefLimit)
+ : 0)
+ || ((tableType == byU16)
+ ? 0
+ : (match + MAX_DISTANCE < ip))
+ || (LZ4_read32(match + refDelta)
+ != LZ4_read32(ip)));
+ }
+
+ /* Catch up */
+ while (((ip > anchor) & (match + refDelta > lowLimit))
+ && (unlikely(ip[-1] == match[refDelta - 1]))) {
+ ip--;
+ match--;
+ }
+
+ /* Encode Literals */
+ {
+ unsigned const int litLength = (unsigned int)(ip - anchor);
+
+ token = op++;
+
+ if ((outputLimited) &&
+ /* Check output buffer overflow */
+ (unlikely(op + litLength +
+ (2 + 1 + LASTLITERALS) +
+ (litLength / 255) > olimit)))
+ return 0;
+
+ if (litLength >= RUN_MASK) {
+ int len = (int)litLength - RUN_MASK;
+
+ *token = (RUN_MASK << ML_BITS);
+
+ for (; len >= 255; len -= 255)
+ *op++ = 255;
+ *op++ = (BYTE)len;
+ } else
+ *token = (BYTE)(litLength << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(op, anchor, op + litLength);
+ op += litLength;
+ }
+
+_next_match:
+ /* Encode Offset */
+ LZ4_writeLE16(op, (U16)(ip - match));
+ op += 2;
+
+ /* Encode MatchLength */
+ {
+ unsigned int matchCode;
+
+ if ((dict == usingExtDict)
+ && (lowLimit == dictionary)) {
+ const BYTE *limit;
+
+ match += refDelta;
+ limit = ip + (dictEnd - match);
+
+ if (limit > matchlimit)
+ limit = matchlimit;
+
+ matchCode = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, limit);
+
+ ip += MINMATCH + matchCode;
+
+ if (ip == limit) {
+ unsigned const int more = LZ4_count(ip,
+ (const BYTE *)source,
+ matchlimit);
+
+ matchCode += more;
+ ip += more;
+ }
+ } else {
+ matchCode = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, matchlimit);
+ ip += MINMATCH + matchCode;
+ }
+
+ if (outputLimited &&
+ /* Check output buffer overflow */
+ (unlikely(op +
+ (1 + LASTLITERALS) +
+ (matchCode >> 8) > olimit)))
+ return 0;
+
+ if (matchCode >= ML_MASK) {
+ *token += ML_MASK;
+ matchCode -= ML_MASK;
+ LZ4_write32(op, 0xFFFFFFFF);
+
+ while (matchCode >= 4 * 255) {
+ op += 4;
+ LZ4_write32(op, 0xFFFFFFFF);
+ matchCode -= 4 * 255;
+ }
+
+ op += matchCode / 255;
+ *op++ = (BYTE)(matchCode % 255);
+ } else
+ *token += (BYTE)(matchCode);
+ }
+
+ anchor = ip;
+
+ /* Test end of chunk */
+ if (ip > mflimit)
+ break;
+
+ /* Fill table */
+ LZ4_putPosition(ip - 2, dictPtr->hashTable, tableType, base);
+
+ /* Test next position */
+ match = LZ4_getPosition(ip, dictPtr->hashTable,
+ tableType, base);
+
+ if (dict == usingExtDict) {
+ if (match < (const BYTE *)source) {
+ refDelta = dictDelta;
+ lowLimit = dictionary;
+ } else {
+ refDelta = 0;
+ lowLimit = (const BYTE *)source;
+ }
+ }
+
+ LZ4_putPosition(ip, dictPtr->hashTable, tableType, base);
+
+ if (((dictIssue == dictSmall) ? (match >= lowRefLimit) : 1)
+ && (match + MAX_DISTANCE >= ip)
+ && (LZ4_read32(match + refDelta) == LZ4_read32(ip))) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ forwardH = LZ4_hashPosition(++ip, tableType);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ {
+ size_t const lastRun = (size_t)(iend - anchor);
+
+ if ((outputLimited) &&
+ /* Check output buffer overflow */
+ ((op - (BYTE *)dest) + lastRun + 1 +
+ ((lastRun + 255 - RUN_MASK) / 255) > (U32)maxOutputSize))
+ return 0;
+
+ if (lastRun >= RUN_MASK) {
+ size_t accumulator = lastRun - RUN_MASK;
+ *op++ = RUN_MASK << ML_BITS;
+ for (; accumulator >= 255; accumulator -= 255)
+ *op++ = 255;
+ *op++ = (BYTE) accumulator;
+ } else {
+ *op++ = (BYTE)(lastRun << ML_BITS);
+ }
+
+ LZ4_memcpy(op, anchor, lastRun);
+
+ op += lastRun;
+ }
+
+ /* End */
+ return (int) (((char *)op) - dest);
+}
+
+static int LZ4_compress_fast_extState(
+ void *state,
+ const char *source,
+ char *dest,
+ int inputSize,
+ int maxOutputSize,
+ int acceleration)
+{
+ LZ4_stream_t_internal *ctx = &((LZ4_stream_t *)state)->internal_donotuse;
+#if LZ4_ARCH64
+ const tableType_t tableType = byU32;
+#else
+ const tableType_t tableType = byPtr;
+#endif
+
+ LZ4_resetStream((LZ4_stream_t *)state);
+
+ if (acceleration < 1)
+ acceleration = LZ4_ACCELERATION_DEFAULT;
+
+ if (maxOutputSize >= LZ4_COMPRESSBOUND(inputSize)) {
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize, 0,
+ noLimit, byU16, noDict,
+ noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize, 0,
+ noLimit, tableType, noDict,
+ noDictIssue, acceleration);
+ } else {
+ if (inputSize < LZ4_64Klimit)
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize,
+ maxOutputSize, limitedOutput, byU16, noDict,
+ noDictIssue, acceleration);
+ else
+ return LZ4_compress_generic(ctx, source,
+ dest, inputSize,
+ maxOutputSize, limitedOutput, tableType, noDict,
+ noDictIssue, acceleration);
+ }
+}
+
+int LZ4_compress_fast(const char *source, char *dest, int inputSize,
+ int maxOutputSize, int acceleration, void *wrkmem)
+{
+ return LZ4_compress_fast_extState(wrkmem, source, dest, inputSize,
+ maxOutputSize, acceleration);
+}
+
+int LZ4_compress_default(const char *source, char *dest, int inputSize,
+ int maxOutputSize, void *wrkmem)
+{
+ return LZ4_compress_fast(source, dest, inputSize,
+ maxOutputSize, LZ4_ACCELERATION_DEFAULT, wrkmem);
+}
+
+/*-******************************
+ * *_destSize() variant
+ ********************************/
+static int LZ4_compress_destSize_generic(
+ LZ4_stream_t_internal * const ctx,
+ const char * const src,
+ char * const dst,
+ int * const srcSizePtr,
+ const int targetDstSize,
+ const tableType_t tableType)
+{
+ const BYTE *ip = (const BYTE *) src;
+ const BYTE *base = (const BYTE *) src;
+ const BYTE *lowLimit = (const BYTE *) src;
+ const BYTE *anchor = ip;
+ const BYTE * const iend = ip + *srcSizePtr;
+ const BYTE * const mflimit = iend - MFLIMIT;
+ const BYTE * const matchlimit = iend - LASTLITERALS;
+
+ BYTE *op = (BYTE *) dst;
+ BYTE * const oend = op + targetDstSize;
+ BYTE * const oMaxLit = op + targetDstSize - 2 /* offset */
+ - 8 /* because 8 + MINMATCH == MFLIMIT */ - 1 /* token */;
+ BYTE * const oMaxMatch = op + targetDstSize
+ - (LASTLITERALS + 1 /* token */);
+ BYTE * const oMaxSeq = oMaxLit - 1 /* token */;
+
+ U32 forwardH;
+
+ /* Init conditions */
+ /* Impossible to store anything */
+ if (targetDstSize < 1)
+ return 0;
+ /* Unsupported input size, too large (or negative) */
+ if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE)
+ return 0;
+ /* Size too large (not within 64K limit) */
+ if ((tableType == byU16) && (*srcSizePtr >= LZ4_64Klimit))
+ return 0;
+ /* Input too small, no compression (all literals) */
+ if (*srcSizePtr < LZ4_minLength)
+ goto _last_literals;
+
+ /* First Byte */
+ *srcSizePtr = 0;
+ LZ4_putPosition(ip, ctx->hashTable, tableType, base);
+ ip++; forwardH = LZ4_hashPosition(ip, tableType);
+
+ /* Main Loop */
+ for ( ; ; ) {
+ const BYTE *match;
+ BYTE *token;
+
+ /* Find a match */
+ {
+ const BYTE *forwardIp = ip;
+ unsigned int step = 1;
+ unsigned int searchMatchNb = 1 << LZ4_SKIPTRIGGER;
+
+ do {
+ U32 h = forwardH;
+
+ ip = forwardIp;
+ forwardIp += step;
+ step = (searchMatchNb++ >> LZ4_SKIPTRIGGER);
+
+ if (unlikely(forwardIp > mflimit))
+ goto _last_literals;
+
+ match = LZ4_getPositionOnHash(h, ctx->hashTable,
+ tableType, base);
+ forwardH = LZ4_hashPosition(forwardIp,
+ tableType);
+ LZ4_putPositionOnHash(ip, h,
+ ctx->hashTable, tableType,
+ base);
+
+ } while (((tableType == byU16)
+ ? 0
+ : (match + MAX_DISTANCE < ip))
+ || (LZ4_read32(match) != LZ4_read32(ip)));
+ }
+
+ /* Catch up */
+ while ((ip > anchor)
+ && (match > lowLimit)
+ && (unlikely(ip[-1] == match[-1]))) {
+ ip--;
+ match--;
+ }
+
+ /* Encode Literal length */
+ {
+ unsigned int litLength = (unsigned int)(ip - anchor);
+
+ token = op++;
+ if (op + ((litLength + 240) / 255)
+ + litLength > oMaxLit) {
+ /* Not enough space for a last match */
+ op--;
+ goto _last_literals;
+ }
+ if (litLength >= RUN_MASK) {
+ unsigned int len = litLength - RUN_MASK;
+ *token = (RUN_MASK<<ML_BITS);
+ for (; len >= 255; len -= 255)
+ *op++ = 255;
+ *op++ = (BYTE)len;
+ } else
+ *token = (BYTE)(litLength << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(op, anchor, op + litLength);
+ op += litLength;
+ }
+
+_next_match:
+ /* Encode Offset */
+ LZ4_writeLE16(op, (U16)(ip - match)); op += 2;
+
+ /* Encode MatchLength */
+ {
+ size_t matchLength = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, matchlimit);
+
+ if (op + ((matchLength + 240)/255) > oMaxMatch) {
+ /* Match description too long : reduce it */
+ matchLength = (15 - 1) + (oMaxMatch - op) * 255;
+ }
+ ip += MINMATCH + matchLength;
+
+ if (matchLength >= ML_MASK) {
+ *token += ML_MASK;
+ matchLength -= ML_MASK;
+ while (matchLength >= 255) {
+ matchLength -= 255;
+ *op++ = 255;
+ }
+ *op++ = (BYTE)matchLength;
+ } else
+ *token += (BYTE)(matchLength);
+ }
+
+ anchor = ip;
+
+ /* Test end of block */
+ if (ip > mflimit)
+ break;
+ if (op > oMaxSeq)
+ break;
+
+ /* Fill table */
+ LZ4_putPosition(ip - 2, ctx->hashTable, tableType, base);
+
+ /* Test next position */
+ match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
+ LZ4_putPosition(ip, ctx->hashTable, tableType, base);
+
+ if ((match + MAX_DISTANCE >= ip)
+ && (LZ4_read32(match) == LZ4_read32(ip))) {
+ token = op++; *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ forwardH = LZ4_hashPosition(++ip, tableType);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ {
+ size_t lastRunSize = (size_t)(iend - anchor);
+
+ if (op + 1 /* token */
+ + ((lastRunSize + 240) / 255) /* litLength */
+ + lastRunSize /* literals */ > oend) {
+ /* adapt lastRunSize to fill 'dst' */
+ lastRunSize = (oend - op) - 1;
+ lastRunSize -= (lastRunSize + 240) / 255;
+ }
+ ip = anchor + lastRunSize;
+
+ if (lastRunSize >= RUN_MASK) {
+ size_t accumulator = lastRunSize - RUN_MASK;
+
+ *op++ = RUN_MASK << ML_BITS;
+ for (; accumulator >= 255; accumulator -= 255)
+ *op++ = 255;
+ *op++ = (BYTE) accumulator;
+ } else {
+ *op++ = (BYTE)(lastRunSize<<ML_BITS);
+ }
+ LZ4_memcpy(op, anchor, lastRunSize);
+ op += lastRunSize;
+ }
+
+ /* End */
+ *srcSizePtr = (int) (((const char *)ip) - src);
+ return (int) (((char *)op) - dst);
+}
+
+static int LZ4_compress_destSize_extState(
+ LZ4_stream_t *state,
+ const char *src,
+ char *dst,
+ int *srcSizePtr,
+ int targetDstSize)
+{
+#if LZ4_ARCH64
+ const tableType_t tableType = byU32;
+#else
+ const tableType_t tableType = byPtr;
+#endif
+
+ LZ4_resetStream(state);
+
+ if (targetDstSize >= LZ4_COMPRESSBOUND(*srcSizePtr)) {
+ /* compression success is guaranteed */
+ return LZ4_compress_fast_extState(
+ state, src, dst, *srcSizePtr,
+ targetDstSize, 1);
+ } else {
+ if (*srcSizePtr < LZ4_64Klimit)
+ return LZ4_compress_destSize_generic(
+ &state->internal_donotuse,
+ src, dst, srcSizePtr,
+ targetDstSize, byU16);
+ else
+ return LZ4_compress_destSize_generic(
+ &state->internal_donotuse,
+ src, dst, srcSizePtr,
+ targetDstSize, tableType);
+ }
+}
+
+
+int LZ4_compress_destSize(
+ const char *src,
+ char *dst,
+ int *srcSizePtr,
+ int targetDstSize,
+ void *wrkmem)
+{
+ return LZ4_compress_destSize_extState(wrkmem, src, dst, srcSizePtr,
+ targetDstSize);
+}
+
+/*-******************************
+ * Streaming functions
+ ********************************/
+void LZ4_resetStream(LZ4_stream_t *LZ4_stream)
+{
+ memset(LZ4_stream, 0, sizeof(LZ4_stream_t));
+}
+
+int LZ4_loadDict(LZ4_stream_t *LZ4_dict,
+ const char *dictionary, int dictSize)
+{
+ LZ4_stream_t_internal *dict = &LZ4_dict->internal_donotuse;
+ const BYTE *p = (const BYTE *)dictionary;
+ const BYTE * const dictEnd = p + dictSize;
+ const BYTE *base;
+
+ if ((dict->initCheck)
+ || (dict->currentOffset > 1 * GB)) {
+ /* Uninitialized structure, or reuse overflow */
+ LZ4_resetStream(LZ4_dict);
+ }
+
+ if (dictSize < (int)HASH_UNIT) {
+ dict->dictionary = NULL;
+ dict->dictSize = 0;
+ return 0;
+ }
+
+ if ((dictEnd - p) > 64 * KB)
+ p = dictEnd - 64 * KB;
+ dict->currentOffset += 64 * KB;
+ base = p - dict->currentOffset;
+ dict->dictionary = p;
+ dict->dictSize = (U32)(dictEnd - p);
+ dict->currentOffset += dict->dictSize;
+
+ while (p <= dictEnd - HASH_UNIT) {
+ LZ4_putPosition(p, dict->hashTable, byU32, base);
+ p += 3;
+ }
+
+ return dict->dictSize;
+}
+
+static void LZ4_renormDictT(LZ4_stream_t_internal *LZ4_dict,
+ const BYTE *src)
+{
+ if ((LZ4_dict->currentOffset > 0x80000000) ||
+ ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {
+ /* address space overflow */
+ /* rescale hash table */
+ U32 const delta = LZ4_dict->currentOffset - 64 * KB;
+ const BYTE *dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
+ int i;
+
+ for (i = 0; i < LZ4_HASH_SIZE_U32; i++) {
+ if (LZ4_dict->hashTable[i] < delta)
+ LZ4_dict->hashTable[i] = 0;
+ else
+ LZ4_dict->hashTable[i] -= delta;
+ }
+ LZ4_dict->currentOffset = 64 * KB;
+ if (LZ4_dict->dictSize > 64 * KB)
+ LZ4_dict->dictSize = 64 * KB;
+ LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
+ }
+}
+
+int LZ4_saveDict(LZ4_stream_t *LZ4_dict, char *safeBuffer, int dictSize)
+{
+ LZ4_stream_t_internal * const dict = &LZ4_dict->internal_donotuse;
+ const BYTE * const previousDictEnd = dict->dictionary + dict->dictSize;
+
+ if ((U32)dictSize > 64 * KB) {
+ /* useless to define a dictionary > 64 * KB */
+ dictSize = 64 * KB;
+ }
+ if ((U32)dictSize > dict->dictSize)
+ dictSize = dict->dictSize;
+
+ memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
+
+ dict->dictionary = (const BYTE *)safeBuffer;
+ dict->dictSize = (U32)dictSize;
+
+ return dictSize;
+}
+
+int LZ4_compress_fast_continue(LZ4_stream_t *LZ4_stream, const char *source,
+ char *dest, int inputSize, int maxOutputSize, int acceleration)
+{
+ LZ4_stream_t_internal *streamPtr = &LZ4_stream->internal_donotuse;
+ const BYTE * const dictEnd = streamPtr->dictionary
+ + streamPtr->dictSize;
+
+ const BYTE *smallest = (const BYTE *) source;
+
+ if (streamPtr->initCheck) {
+ /* Uninitialized structure detected */
+ return 0;
+ }
+
+ if ((streamPtr->dictSize > 0) && (smallest > dictEnd))
+ smallest = dictEnd;
+
+ LZ4_renormDictT(streamPtr, smallest);
+
+ if (acceleration < 1)
+ acceleration = LZ4_ACCELERATION_DEFAULT;
+
+ /* Check overlapping input/dictionary space */
+ {
+ const BYTE *sourceEnd = (const BYTE *) source + inputSize;
+
+ if ((sourceEnd > streamPtr->dictionary)
+ && (sourceEnd < dictEnd)) {
+ streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
+ if (streamPtr->dictSize > 64 * KB)
+ streamPtr->dictSize = 64 * KB;
+ if (streamPtr->dictSize < 4)
+ streamPtr->dictSize = 0;
+ streamPtr->dictionary = dictEnd - streamPtr->dictSize;
+ }
+ }
+
+ /* prefix mode : source data follows dictionary */
+ if (dictEnd == (const BYTE *)source) {
+ int result;
+
+ if ((streamPtr->dictSize < 64 * KB) &&
+ (streamPtr->dictSize < streamPtr->currentOffset)) {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ withPrefix64k, dictSmall, acceleration);
+ } else {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ withPrefix64k, noDictIssue, acceleration);
+ }
+ streamPtr->dictSize += (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+
+ /* external dictionary mode */
+ {
+ int result;
+
+ if ((streamPtr->dictSize < 64 * KB) &&
+ (streamPtr->dictSize < streamPtr->currentOffset)) {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ usingExtDict, dictSmall, acceleration);
+ } else {
+ result = LZ4_compress_generic(
+ streamPtr, source, dest, inputSize,
+ maxOutputSize, limitedOutput, byU32,
+ usingExtDict, noDictIssue, acceleration);
+ }
+ streamPtr->dictionary = (const BYTE *)source;
+ streamPtr->dictSize = (U32)inputSize;
+ streamPtr->currentOffset += (U32)inputSize;
+ return result;
+ }
+}
--- /dev/null
+/*
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011 - 2016, Yann Collet.
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
+ *
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
+ */
+
+/*-************************************
+ * Dependencies
+ **************************************/
+#include "lz4.h"
+#include "lz4defs.h"
+#include <linux/kernel.h>
+#include <asm/unaligned.h>
+
+/*-*****************************
+ * Decompression functions
+ *******************************/
+
+#define DEBUGLOG(l, ...) {} /* disabled */
+
+#ifndef assert
+#define assert(condition) ((void)0)
+#endif
+
+/*
+ * LZ4_decompress_generic() :
+ * This generic decompression function covers all use cases.
+ * It shall be instantiated several times, using different sets of directives.
+ * Note that it is important for performance that this function really get inlined,
+ * in order to remove useless branches during compilation optimization.
+ */
+static FORCE_INLINE int LZ4_decompress_generic(
+ const char * const src,
+ char * const dst,
+ int srcSize,
+ /*
+ * If endOnInput == endOnInputSize,
+ * this value is `dstCapacity`
+ */
+ int outputSize,
+ /* endOnOutputSize, endOnInputSize */
+ endCondition_directive endOnInput,
+ /* full, partial */
+ earlyEnd_directive partialDecoding,
+ /* noDict, withPrefix64k, usingExtDict */
+ dict_directive dict,
+ /* always <= dst, == dst when no prefix */
+ const BYTE * const lowPrefix,
+ /* only if dict == usingExtDict */
+ const BYTE * const dictStart,
+ /* note : = 0 if noDict */
+ const size_t dictSize
+ )
+{
+ const BYTE *ip = (const BYTE *) src;
+ const BYTE * const iend = ip + srcSize;
+
+ BYTE *op = (BYTE *) dst;
+ BYTE * const oend = op + outputSize;
+ BYTE *cpy;
+
+ const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize;
+ static const unsigned int inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4};
+ static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3};
+
+ const int safeDecode = (endOnInput == endOnInputSize);
+ const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB)));
+
+ /* Set up the "end" pointers for the shortcut. */
+ const BYTE *const shortiend = iend -
+ (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/;
+ const BYTE *const shortoend = oend -
+ (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/;
+
+ DEBUGLOG(5, "%s (srcSize:%i, dstSize:%i)", __func__,
+ srcSize, outputSize);
+
+ /* Special cases */
+ assert(lowPrefix <= op);
+ assert(src != NULL);
+
+ /* Empty output buffer */
+ if ((endOnInput) && (unlikely(outputSize == 0)))
+ return ((srcSize == 1) && (*ip == 0)) ? 0 : -1;
+
+ if ((!endOnInput) && (unlikely(outputSize == 0)))
+ return (*ip == 0 ? 1 : -1);
+
+ if ((endOnInput) && unlikely(srcSize == 0))
+ return -1;
+
+ /* Main Loop : decode sequences */
+ while (1) {
+ size_t length;
+ const BYTE *match;
+ size_t offset;
+
+ /* get literal length */
+ unsigned int const token = *ip++;
+ length = token>>ML_BITS;
+
+ /* ip < iend before the increment */
+ assert(!endOnInput || ip <= iend);
+
+ /*
+ * A two-stage shortcut for the most common case:
+ * 1) If the literal length is 0..14, and there is enough
+ * space, enter the shortcut and copy 16 bytes on behalf
+ * of the literals (in the fast mode, only 8 bytes can be
+ * safely copied this way).
+ * 2) Further if the match length is 4..18, copy 18 bytes
+ * in a similar manner; but we ensure that there's enough
+ * space in the output for those 18 bytes earlier, upon
+ * entering the shortcut (in other words, there is a
+ * combined check for both stages).
+ *
+ * The & in the likely() below is intentionally not && so that
+ * some compilers can produce better parallelized runtime code
+ */
+ if ((endOnInput ? length != RUN_MASK : length <= 8)
+ /*
+ * strictly "less than" on input, to re-enter
+ * the loop with at least one byte
+ */
+ && likely((endOnInput ? ip < shortiend : 1) &
+ (op <= shortoend))) {
+ /* Copy the literals */
+ LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
+ op += length; ip += length;
+
+ /*
+ * The second stage:
+ * prepare for match copying, decode full info.
+ * If it doesn't work out, the info won't be wasted.
+ */
+ length = token & ML_MASK; /* match length */
+ offset = LZ4_readLE16(ip);
+ ip += 2;
+ match = op - offset;
+ assert(match <= op); /* check overflow */
+
+ /* Do not deal with overlapping matches. */
+ if ((length != ML_MASK) &&
+ (offset >= 8) &&
+ (dict == withPrefix64k || match >= lowPrefix)) {
+ /* Copy the match. */
+ LZ4_memcpy(op + 0, match + 0, 8);
+ LZ4_memcpy(op + 8, match + 8, 8);
+ LZ4_memcpy(op + 16, match + 16, 2);
+ op += length + MINMATCH;
+ /* Both stages worked, load the next token. */
+ continue;
+ }
+
+ /*
+ * The second stage didn't work out, but the info
+ * is ready. Propel it right to the point of match
+ * copying.
+ */
+ goto _copy_match;
+ }
+
+ /* decode literal length */
+ if (length == RUN_MASK) {
+ unsigned int s;
+
+ if (unlikely(endOnInput ? ip >= iend - RUN_MASK : 0)) {
+ /* overflow detection */
+ goto _output_error;
+ }
+ do {
+ s = *ip++;
+ length += s;
+ } while (likely(endOnInput
+ ? ip < iend - RUN_MASK
+ : 1) & (s == 255));
+
+ if ((safeDecode)
+ && unlikely((uptrval)(op) +
+ length < (uptrval)(op))) {
+ /* overflow detection */
+ goto _output_error;
+ }
+ if ((safeDecode)
+ && unlikely((uptrval)(ip) +
+ length < (uptrval)(ip))) {
+ /* overflow detection */
+ goto _output_error;
+ }
+ }
+
+ /* copy literals */
+ cpy = op + length;
+ LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+
+ if (((endOnInput) && ((cpy > oend - MFLIMIT)
+ || (ip + length > iend - (2 + 1 + LASTLITERALS))))
+ || ((!endOnInput) && (cpy > oend - WILDCOPYLENGTH))) {
+ if (partialDecoding) {
+ if (cpy > oend) {
+ /*
+ * Partial decoding :
+ * stop in the middle of literal segment
+ */
+ cpy = oend;
+ length = oend - op;
+ }
+ if ((endOnInput)
+ && (ip + length > iend)) {
+ /*
+ * Error :
+ * read attempt beyond
+ * end of input buffer
+ */
+ goto _output_error;
+ }
+ } else {
+ if ((!endOnInput)
+ && (cpy != oend)) {
+ /*
+ * Error :
+ * block decoding must
+ * stop exactly there
+ */
+ goto _output_error;
+ }
+ if ((endOnInput)
+ && ((ip + length != iend)
+ || (cpy > oend))) {
+ /*
+ * Error :
+ * input must be consumed
+ */
+ goto _output_error;
+ }
+ }
+
+ /*
+ * supports overlapping memory regions; only matters
+ * for in-place decompression scenarios
+ */
+ LZ4_memmove(op, ip, length);
+ ip += length;
+ op += length;
+
+ /* Necessarily EOF when !partialDecoding.
+ * When partialDecoding, it is EOF if we've either
+ * filled the output buffer or
+ * can't proceed with reading an offset for following match.
+ */
+ if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2)))
+ break;
+ } else {
+ /* may overwrite up to WILDCOPYLENGTH beyond cpy */
+ LZ4_wildCopy(op, ip, cpy);
+ ip += length;
+ op = cpy;
+ }
+
+ /* get offset */
+ offset = LZ4_readLE16(ip);
+ ip += 2;
+ match = op - offset;
+
+ /* get matchlength */
+ length = token & ML_MASK;
+
+_copy_match:
+ if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) {
+ /* Error : offset outside buffers */
+ goto _output_error;
+ }
+
+ /* costs ~1%; silence an msan warning when offset == 0 */
+ /*
+ * note : when partialDecoding, there is no guarantee that
+ * at least 4 bytes remain available in output buffer
+ */
+ if (!partialDecoding) {
+ assert(oend > op);
+ assert(oend - op >= 4);
+
+ LZ4_write32(op, (U32)offset);
+ }
+
+ if (length == ML_MASK) {
+ unsigned int s;
+
+ do {
+ s = *ip++;
+
+ if ((endOnInput) && (ip > iend - LASTLITERALS))
+ goto _output_error;
+
+ length += s;
+ } while (s == 255);
+
+ if ((safeDecode)
+ && unlikely(
+ (uptrval)(op) + length < (uptrval)op)) {
+ /* overflow detection */
+ goto _output_error;
+ }
+ }
+
+ length += MINMATCH;
+
+ /* match starting within external dictionary */
+ if ((dict == usingExtDict) && (match < lowPrefix)) {
+ if (unlikely(op + length > oend - LASTLITERALS)) {
+ /* doesn't respect parsing restriction */
+ if (!partialDecoding)
+ goto _output_error;
+ length = min(length, (size_t)(oend - op));
+ }
+
+ if (length <= (size_t)(lowPrefix - match)) {
+ /*
+ * match fits entirely within external
+ * dictionary : just copy
+ */
+ memmove(op, dictEnd - (lowPrefix - match),
+ length);
+ op += length;
+ } else {
+ /*
+ * match stretches into both external
+ * dictionary and current block
+ */
+ size_t const copySize = (size_t)(lowPrefix - match);
+ size_t const restSize = length - copySize;
+
+ LZ4_memcpy(op, dictEnd - copySize, copySize);
+ op += copySize;
+ if (restSize > (size_t)(op - lowPrefix)) {
+ /* overlap copy */
+ BYTE * const endOfMatch = op + restSize;
+ const BYTE *copyFrom = lowPrefix;
+
+ while (op < endOfMatch)
+ *op++ = *copyFrom++;
+ } else {
+ LZ4_memcpy(op, lowPrefix, restSize);
+ op += restSize;
+ }
+ }
+ continue;
+ }
+
+ /* copy match within block */
+ cpy = op + length;
+
+ /*
+ * partialDecoding :
+ * may not respect endBlock parsing restrictions
+ */
+ assert(op <= oend);
+ if (partialDecoding &&
+ (cpy > oend - MATCH_SAFEGUARD_DISTANCE)) {
+ size_t const mlen = min(length, (size_t)(oend - op));
+ const BYTE * const matchEnd = match + mlen;
+ BYTE * const copyEnd = op + mlen;
+
+ if (matchEnd > op) {
+ /* overlap copy */
+ while (op < copyEnd)
+ *op++ = *match++;
+ } else {
+ LZ4_memcpy(op, match, mlen);
+ }
+ op = copyEnd;
+ if (op == oend)
+ break;
+ continue;
+ }
+
+ if (unlikely(offset < 8)) {
+ op[0] = match[0];
+ op[1] = match[1];
+ op[2] = match[2];
+ op[3] = match[3];
+ match += inc32table[offset];
+ LZ4_memcpy(op + 4, match, 4);
+ match -= dec64table[offset];
+ } else {
+ LZ4_copy8(op, match);
+ match += 8;
+ }
+
+ op += 8;
+
+ if (unlikely(cpy > oend - MATCH_SAFEGUARD_DISTANCE)) {
+ BYTE * const oCopyLimit = oend - (WILDCOPYLENGTH - 1);
+
+ if (cpy > oend - LASTLITERALS) {
+ /*
+ * Error : last LASTLITERALS bytes
+ * must be literals (uncompressed)
+ */
+ goto _output_error;
+ }
+
+ if (op < oCopyLimit) {
+ LZ4_wildCopy(op, match, oCopyLimit);
+ match += oCopyLimit - op;
+ op = oCopyLimit;
+ }
+ while (op < cpy)
+ *op++ = *match++;
+ } else {
+ LZ4_copy8(op, match);
+ if (length > 16)
+ LZ4_wildCopy(op + 8, match + 8, cpy);
+ }
+ op = cpy; /* wildcopy correction */
+ }
+
+ /* end of decoding */
+ if (endOnInput) {
+ /* Nb of output bytes decoded */
+ return (int) (((char *)op) - dst);
+ } else {
+ /* Nb of input bytes read */
+ return (int) (((const char *)ip) - src);
+ }
+
+ /* Overflow error detected */
+_output_error:
+ return (int) (-(((const char *)ip) - src)) - 1;
+}
+
+int LZ4_decompress_safe(const char *source, char *dest,
+ int compressedSize, int maxDecompressedSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxDecompressedSize,
+ endOnInputSize, decode_full_block,
+ noDict, (BYTE *)dest, NULL, 0);
+}
+
+int LZ4_decompress_safe_partial(const char *src, char *dst,
+ int compressedSize, int targetOutputSize, int dstCapacity)
+{
+ dstCapacity = min(targetOutputSize, dstCapacity);
+ return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
+ endOnInputSize, partial_decode,
+ noDict, (BYTE *)dst, NULL, 0);
+}
+
+int LZ4_decompress_fast(const char *source, char *dest, int originalSize)
+{
+ return LZ4_decompress_generic(source, dest, 0, originalSize,
+ endOnOutputSize, decode_full_block,
+ withPrefix64k,
+ (BYTE *)dest - 64 * KB, NULL, 0);
+}
+
+/* ===== Instantiate a few more decoding cases, used more than once. ===== */
+
+static int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest,
+ int compressedSize, int maxOutputSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block,
+ withPrefix64k,
+ (BYTE *)dest - 64 * KB, NULL, 0);
+}
+
+static int LZ4_decompress_safe_withSmallPrefix(const char *source, char *dest,
+ int compressedSize,
+ int maxOutputSize,
+ size_t prefixSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block,
+ noDict,
+ (BYTE *)dest - prefixSize, NULL, 0);
+}
+
+static int LZ4_decompress_safe_forceExtDict(const char *source, char *dest,
+ int compressedSize, int maxOutputSize,
+ const void *dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block,
+ usingExtDict, (BYTE *)dest,
+ (const BYTE *)dictStart, dictSize);
+}
+
+static int LZ4_decompress_fast_extDict(const char *source, char *dest,
+ int originalSize,
+ const void *dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ 0, originalSize,
+ endOnOutputSize, decode_full_block,
+ usingExtDict, (BYTE *)dest,
+ (const BYTE *)dictStart, dictSize);
+}
+
+/*
+ * The "double dictionary" mode, for use with e.g. ring buffers: the first part
+ * of the dictionary is passed as prefix, and the second via dictStart + dictSize.
+ * These routines are used only once, in LZ4_decompress_*_continue().
+ */
+static FORCE_INLINE
+int LZ4_decompress_safe_doubleDict(const char *source, char *dest,
+ int compressedSize, int maxOutputSize,
+ size_t prefixSize,
+ const void *dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ compressedSize, maxOutputSize,
+ endOnInputSize, decode_full_block,
+ usingExtDict, (BYTE *)dest - prefixSize,
+ (const BYTE *)dictStart, dictSize);
+}
+
+static FORCE_INLINE
+int LZ4_decompress_fast_doubleDict(const char *source, char *dest,
+ int originalSize, size_t prefixSize,
+ const void *dictStart, size_t dictSize)
+{
+ return LZ4_decompress_generic(source, dest,
+ 0, originalSize,
+ endOnOutputSize, decode_full_block,
+ usingExtDict, (BYTE *)dest - prefixSize,
+ (const BYTE *)dictStart, dictSize);
+}
+
+/* ===== streaming decompression functions ===== */
+
+int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *dictionary, int dictSize)
+{
+ LZ4_streamDecode_t_internal *lz4sd =
+ &LZ4_streamDecode->internal_donotuse;
+
+ lz4sd->prefixSize = (size_t) dictSize;
+ lz4sd->prefixEnd = (const BYTE *) dictionary + dictSize;
+ lz4sd->externalDict = NULL;
+ lz4sd->extDictSize = 0;
+ return 1;
+}
+
+/*
+ * *_continue() :
+ * These decoding functions allow decompression of multiple blocks
+ * in "streaming" mode.
+ * Previously decoded blocks must still be available at the memory
+ * position where they were decoded.
+ * If it's not possible, save the relevant part of
+ * decoded data into a safe buffer,
+ * and indicate where it stands using LZ4_setStreamDecode()
+ */
+int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int compressedSize, int maxOutputSize)
+{
+ LZ4_streamDecode_t_internal *lz4sd =
+ &LZ4_streamDecode->internal_donotuse;
+ int result;
+
+ if (lz4sd->prefixSize == 0) {
+ /* The first call, no dictionary yet. */
+ assert(lz4sd->extDictSize == 0);
+ result = LZ4_decompress_safe(source, dest,
+ compressedSize, maxOutputSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize = result;
+ lz4sd->prefixEnd = (BYTE *)dest + result;
+ } else if (lz4sd->prefixEnd == (BYTE *)dest) {
+ /* They're rolling the current segment. */
+ if (lz4sd->prefixSize >= 64 * KB - 1)
+ result = LZ4_decompress_safe_withPrefix64k(source, dest,
+ compressedSize, maxOutputSize);
+ else if (lz4sd->extDictSize == 0)
+ result = LZ4_decompress_safe_withSmallPrefix(source,
+ dest, compressedSize, maxOutputSize,
+ lz4sd->prefixSize);
+ else
+ result = LZ4_decompress_safe_doubleDict(source, dest,
+ compressedSize, maxOutputSize,
+ lz4sd->prefixSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize += result;
+ lz4sd->prefixEnd += result;
+ } else {
+ /*
+ * The buffer wraps around, or they're
+ * switching to another buffer.
+ */
+ lz4sd->extDictSize = lz4sd->prefixSize;
+ lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+ result = LZ4_decompress_safe_forceExtDict(source, dest,
+ compressedSize, maxOutputSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize = result;
+ lz4sd->prefixEnd = (BYTE *)dest + result;
+ }
+
+ return result;
+}
+
+int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
+ const char *source, char *dest, int originalSize)
+{
+ LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse;
+ int result;
+
+ if (lz4sd->prefixSize == 0) {
+ assert(lz4sd->extDictSize == 0);
+ result = LZ4_decompress_fast(source, dest, originalSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize = originalSize;
+ lz4sd->prefixEnd = (BYTE *)dest + originalSize;
+ } else if (lz4sd->prefixEnd == (BYTE *)dest) {
+ if (lz4sd->prefixSize >= 64 * KB - 1 ||
+ lz4sd->extDictSize == 0)
+ result = LZ4_decompress_fast(source, dest,
+ originalSize);
+ else
+ result = LZ4_decompress_fast_doubleDict(source, dest,
+ originalSize, lz4sd->prefixSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize += originalSize;
+ lz4sd->prefixEnd += originalSize;
+ } else {
+ lz4sd->extDictSize = lz4sd->prefixSize;
+ lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+ result = LZ4_decompress_fast_extDict(source, dest,
+ originalSize, lz4sd->externalDict, lz4sd->extDictSize);
+ if (result <= 0)
+ return result;
+ lz4sd->prefixSize = originalSize;
+ lz4sd->prefixEnd = (BYTE *)dest + originalSize;
+ }
+ return result;
+}
+
+int LZ4_decompress_safe_usingDict(const char *source, char *dest,
+ int compressedSize, int maxOutputSize,
+ const char *dictStart, int dictSize)
+{
+ if (dictSize == 0)
+ return LZ4_decompress_safe(source, dest,
+ compressedSize, maxOutputSize);
+ if (dictStart+dictSize == dest) {
+ if (dictSize >= 64 * KB - 1)
+ return LZ4_decompress_safe_withPrefix64k(source, dest,
+ compressedSize, maxOutputSize);
+ return LZ4_decompress_safe_withSmallPrefix(source, dest,
+ compressedSize, maxOutputSize, dictSize);
+ }
+ return LZ4_decompress_safe_forceExtDict(source, dest,
+ compressedSize, maxOutputSize, dictStart, dictSize);
+}
+
+int LZ4_decompress_fast_usingDict(const char *source, char *dest,
+ int originalSize,
+ const char *dictStart, int dictSize)
+{
+ if (dictSize == 0 || dictStart + dictSize == dest)
+ return LZ4_decompress_fast(source, dest, originalSize);
+
+ return LZ4_decompress_fast_extDict(source, dest, originalSize,
+ dictStart, dictSize);
+}
--- /dev/null
+#ifndef __LZ4DEFS_H__
+#define __LZ4DEFS_H__
+
+/*
+ * lz4defs.h -- common and architecture specific defines for the kernel usage
+
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2016, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
+ *
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
+ */
+
+#include <asm/unaligned.h>
+
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/string.h> /* memset, memcpy */
+
+#define FORCE_INLINE __always_inline
+
+/*-************************************
+ * Basic Types
+ **************************************/
+#include <linux/types.h>
+
+typedef uint8_t BYTE;
+typedef uint16_t U16;
+typedef uint32_t U32;
+typedef int32_t S32;
+typedef uint64_t U64;
+typedef uintptr_t uptrval;
+
+/*-************************************
+ * Architecture specifics
+ **************************************/
+#if defined(CONFIG_64BIT)
+#define LZ4_ARCH64 1
+#else
+#define LZ4_ARCH64 0
+#endif
+
+#if defined(__LITTLE_ENDIAN)
+#define LZ4_LITTLE_ENDIAN 1
+#else
+#define LZ4_LITTLE_ENDIAN 0
+#endif
+
+/*-************************************
+ * Constants
+ **************************************/
+#define MINMATCH 4
+
+#define WILDCOPYLENGTH 8
+#define LASTLITERALS 5
+#define MFLIMIT (WILDCOPYLENGTH + MINMATCH)
+/*
+ * ensure it's possible to write 2 x wildcopyLength
+ * without overflowing output buffer
+ */
+#define MATCH_SAFEGUARD_DISTANCE ((2 * WILDCOPYLENGTH) - MINMATCH)
+
+/* Increase this value ==> compression run slower on incompressible data */
+#define LZ4_SKIPTRIGGER 6
+
+#define HASH_UNIT sizeof(size_t)
+
+#define KB (1 << 10)
+#define MB (1 << 20)
+#define GB (1U << 30)
+
+#define MAXD_LOG 16
+#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
+#define STEPSIZE sizeof(size_t)
+
+#define ML_BITS 4
+#define ML_MASK ((1U << ML_BITS) - 1)
+#define RUN_BITS (8 - ML_BITS)
+#define RUN_MASK ((1U << RUN_BITS) - 1)
+
+/*-************************************
+ * Reading and writing into memory
+ **************************************/
+static FORCE_INLINE U16 LZ4_read16(const void *ptr)
+{
+ return get_unaligned((const U16 *)ptr);
+}
+
+static FORCE_INLINE U32 LZ4_read32(const void *ptr)
+{
+ return get_unaligned((const U32 *)ptr);
+}
+
+static FORCE_INLINE size_t LZ4_read_ARCH(const void *ptr)
+{
+ return get_unaligned((const size_t *)ptr);
+}
+
+static FORCE_INLINE void LZ4_write16(void *memPtr, U16 value)
+{
+ put_unaligned(value, (U16 *)memPtr);
+}
+
+static FORCE_INLINE void LZ4_write32(void *memPtr, U32 value)
+{
+ put_unaligned(value, (U32 *)memPtr);
+}
+
+static FORCE_INLINE U16 LZ4_readLE16(const void *memPtr)
+{
+ return get_unaligned_le16(memPtr);
+}
+
+static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value)
+{
+ return put_unaligned_le16(value, memPtr);
+}
+
+/*
+ * LZ4 relies on memcpy with a constant size being inlined. In freestanding
+ * environments, the compiler can't assume the implementation of memcpy() is
+ * standard compliant, so apply its specialized memcpy() inlining logic. When
+ * possible, use __builtin_memcpy() to tell the compiler to analyze memcpy()
+ * as-if it were standard compliant, so it can inline it in freestanding
+ * environments. This is needed when decompressing the Linux Kernel, for example.
+ */
+#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
+#define LZ4_memmove(dst, src, size) __builtin_memmove(dst, src, size)
+
+static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
+{
+#if LZ4_ARCH64
+ U64 a = get_unaligned((const U64 *)src);
+
+ put_unaligned(a, (U64 *)dst);
+#else
+ U32 a = get_unaligned((const U32 *)src);
+ U32 b = get_unaligned((const U32 *)src + 1);
+
+ put_unaligned(a, (U32 *)dst);
+ put_unaligned(b, (U32 *)dst + 1);
+#endif
+}
+
+/*
+ * customized variant of memcpy,
+ * which can overwrite up to 7 bytes beyond dstEnd
+ */
+static FORCE_INLINE void LZ4_wildCopy(void *dstPtr,
+ const void *srcPtr, void *dstEnd)
+{
+ BYTE *d = (BYTE *)dstPtr;
+ const BYTE *s = (const BYTE *)srcPtr;
+ BYTE *const e = (BYTE *)dstEnd;
+
+ do {
+ LZ4_copy8(d, s);
+ d += 8;
+ s += 8;
+ } while (d < e);
+}
+
+static FORCE_INLINE unsigned int LZ4_NbCommonBytes(register size_t val)
+{
+#if LZ4_LITTLE_ENDIAN
+ return __ffs(val) >> 3;
+#else
+ return (BITS_PER_LONG - 1 - __fls(val)) >> 3;
+#endif
+}
+
+static FORCE_INLINE unsigned int LZ4_count(
+ const BYTE *pIn,
+ const BYTE *pMatch,
+ const BYTE *pInLimit)
+{
+ const BYTE *const pStart = pIn;
+
+ while (likely(pIn < pInLimit - (STEPSIZE - 1))) {
+ size_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+
+ if (!diff) {
+ pIn += STEPSIZE;
+ pMatch += STEPSIZE;
+ continue;
+ }
+
+ pIn += LZ4_NbCommonBytes(diff);
+
+ return (unsigned int)(pIn - pStart);
+ }
+
+#if LZ4_ARCH64
+ if ((pIn < (pInLimit - 3))
+ && (LZ4_read32(pMatch) == LZ4_read32(pIn))) {
+ pIn += 4;
+ pMatch += 4;
+ }
+#endif
+
+ if ((pIn < (pInLimit - 1))
+ && (LZ4_read16(pMatch) == LZ4_read16(pIn))) {
+ pIn += 2;
+ pMatch += 2;
+ }
+
+ if ((pIn < pInLimit) && (*pMatch == *pIn))
+ pIn++;
+
+ return (unsigned int)(pIn - pStart);
+}
+
+typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive;
+typedef enum { byPtr, byU32, byU16 } tableType_t;
+
+typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
+
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
+
+#define LZ4_STATIC_ASSERT(c) BUILD_BUG_ON(!(c))
+
+#endif
--- /dev/null
+/*
+ * LZ4 HC - High Compression Mode of LZ4
+ * Copyright (C) 2011-2015, Yann Collet.
+ *
+ * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ * - LZ4 homepage : http://www.lz4.org
+ * - LZ4 source repository : https://github.com/lz4/lz4
+ *
+ * Changed for kernel usage by:
+ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
+ */
+
+/*-************************************
+ * Dependencies
+ **************************************/
+#include "lz4.h"
+#include "lz4defs.h"
+#include <linux/kernel.h>
+#include <linux/string.h> /* memset */
+
+/* *************************************
+ * Local Constants and types
+ ***************************************/
+
+#define OPTIMAL_ML (int)((ML_MASK - 1) + MINMATCH)
+
+#define HASH_FUNCTION(i) (((i) * 2654435761U) \
+ >> ((MINMATCH*8) - LZ4HC_HASH_LOG))
+#define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */
+
+static U32 LZ4HC_hashPtr(const void *ptr)
+{
+ return HASH_FUNCTION(LZ4_read32(ptr));
+}
+
+/**************************************
+ * HC Compression
+ **************************************/
+static void LZ4HC_init(LZ4HC_CCtx_internal *hc4, const BYTE *start)
+{
+ memset((void *)hc4->hashTable, 0, sizeof(hc4->hashTable));
+ memset(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
+ hc4->nextToUpdate = 64 * KB;
+ hc4->base = start - 64 * KB;
+ hc4->end = start;
+ hc4->dictBase = start - 64 * KB;
+ hc4->dictLimit = 64 * KB;
+ hc4->lowLimit = 64 * KB;
+}
+
+/* Update chains up to ip (excluded) */
+static FORCE_INLINE void LZ4HC_Insert(LZ4HC_CCtx_internal *hc4,
+ const BYTE *ip)
+{
+ U16 * const chainTable = hc4->chainTable;
+ U32 * const hashTable = hc4->hashTable;
+ const BYTE * const base = hc4->base;
+ U32 const target = (U32)(ip - base);
+ U32 idx = hc4->nextToUpdate;
+
+ while (idx < target) {
+ U32 const h = LZ4HC_hashPtr(base + idx);
+ size_t delta = idx - hashTable[h];
+
+ if (delta > MAX_DISTANCE)
+ delta = MAX_DISTANCE;
+
+ DELTANEXTU16(idx) = (U16)delta;
+
+ hashTable[h] = idx;
+ idx++;
+ }
+
+ hc4->nextToUpdate = target;
+}
+
+static FORCE_INLINE int LZ4HC_InsertAndFindBestMatch(
+ LZ4HC_CCtx_internal *hc4, /* Index table will be updated */
+ const BYTE *ip,
+ const BYTE * const iLimit,
+ const BYTE **matchpos,
+ const int maxNbAttempts)
+{
+ U16 * const chainTable = hc4->chainTable;
+ U32 * const HashTable = hc4->hashTable;
+ const BYTE * const base = hc4->base;
+ const BYTE * const dictBase = hc4->dictBase;
+ const U32 dictLimit = hc4->dictLimit;
+ const U32 lowLimit = (hc4->lowLimit + 64 * KB > (U32)(ip - base))
+ ? hc4->lowLimit
+ : (U32)(ip - base) - (64 * KB - 1);
+ U32 matchIndex;
+ int nbAttempts = maxNbAttempts;
+ size_t ml = 0;
+
+ /* HC4 match finder */
+ LZ4HC_Insert(hc4, ip);
+ matchIndex = HashTable[LZ4HC_hashPtr(ip)];
+
+ while ((matchIndex >= lowLimit)
+ && (nbAttempts)) {
+ nbAttempts--;
+ if (matchIndex >= dictLimit) {
+ const BYTE * const match = base + matchIndex;
+
+ if (*(match + ml) == *(ip + ml)
+ && (LZ4_read32(match) == LZ4_read32(ip))) {
+ size_t const mlt = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, iLimit) + MINMATCH;
+
+ if (mlt > ml) {
+ ml = mlt;
+ *matchpos = match;
+ }
+ }
+ } else {
+ const BYTE * const match = dictBase + matchIndex;
+
+ if (LZ4_read32(match) == LZ4_read32(ip)) {
+ size_t mlt;
+ const BYTE *vLimit = ip
+ + (dictLimit - matchIndex);
+
+ if (vLimit > iLimit)
+ vLimit = iLimit;
+ mlt = LZ4_count(ip + MINMATCH,
+ match + MINMATCH, vLimit) + MINMATCH;
+ if ((ip + mlt == vLimit)
+ && (vLimit < iLimit))
+ mlt += LZ4_count(ip + mlt,
+ base + dictLimit,
+ iLimit);
+ if (mlt > ml) {
+ /* virtual matchpos */
+ ml = mlt;
+ *matchpos = base + matchIndex;
+ }
+ }
+ }
+ matchIndex -= DELTANEXTU16(matchIndex);
+ }
+
+ return (int)ml;
+}
+
+static FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch(
+ LZ4HC_CCtx_internal *hc4,
+ const BYTE * const ip,
+ const BYTE * const iLowLimit,
+ const BYTE * const iHighLimit,
+ int longest,
+ const BYTE **matchpos,
+ const BYTE **startpos,
+ const int maxNbAttempts)
+{
+ U16 * const chainTable = hc4->chainTable;
+ U32 * const HashTable = hc4->hashTable;
+ const BYTE * const base = hc4->base;
+ const U32 dictLimit = hc4->dictLimit;
+ const BYTE * const lowPrefixPtr = base + dictLimit;
+ const U32 lowLimit = (hc4->lowLimit + 64 * KB > (U32)(ip - base))
+ ? hc4->lowLimit
+ : (U32)(ip - base) - (64 * KB - 1);
+ const BYTE * const dictBase = hc4->dictBase;
+ U32 matchIndex;
+ int nbAttempts = maxNbAttempts;
+ int delta = (int)(ip - iLowLimit);
+
+ /* First Match */
+ LZ4HC_Insert(hc4, ip);
+ matchIndex = HashTable[LZ4HC_hashPtr(ip)];
+
+ while ((matchIndex >= lowLimit)
+ && (nbAttempts)) {
+ nbAttempts--;
+ if (matchIndex >= dictLimit) {
+ const BYTE *matchPtr = base + matchIndex;
+
+ if (*(iLowLimit + longest)
+ == *(matchPtr - delta + longest)) {
+ if (LZ4_read32(matchPtr) == LZ4_read32(ip)) {
+ int mlt = MINMATCH + LZ4_count(
+ ip + MINMATCH,
+ matchPtr + MINMATCH,
+ iHighLimit);
+ int back = 0;
+
+ while ((ip + back > iLowLimit)
+ && (matchPtr + back > lowPrefixPtr)
+ && (ip[back - 1] == matchPtr[back - 1]))
+ back--;
+
+ mlt -= back;
+
+ if (mlt > longest) {
+ longest = (int)mlt;
+ *matchpos = matchPtr + back;
+ *startpos = ip + back;
+ }
+ }
+ }
+ } else {
+ const BYTE * const matchPtr = dictBase + matchIndex;
+
+ if (LZ4_read32(matchPtr) == LZ4_read32(ip)) {
+ size_t mlt;
+ int back = 0;
+ const BYTE *vLimit = ip + (dictLimit - matchIndex);
+
+ if (vLimit > iHighLimit)
+ vLimit = iHighLimit;
+
+ mlt = LZ4_count(ip + MINMATCH,
+ matchPtr + MINMATCH, vLimit) + MINMATCH;
+
+ if ((ip + mlt == vLimit) && (vLimit < iHighLimit))
+ mlt += LZ4_count(ip + mlt, base + dictLimit,
+ iHighLimit);
+ while ((ip + back > iLowLimit)
+ && (matchIndex + back > lowLimit)
+ && (ip[back - 1] == matchPtr[back - 1]))
+ back--;
+
+ mlt -= back;
+
+ if ((int)mlt > longest) {
+ longest = (int)mlt;
+ *matchpos = base + matchIndex + back;
+ *startpos = ip + back;
+ }
+ }
+ }
+
+ matchIndex -= DELTANEXTU16(matchIndex);
+ }
+
+ return longest;
+}
+
+static FORCE_INLINE int LZ4HC_encodeSequence(
+ const BYTE **ip,
+ BYTE **op,
+ const BYTE **anchor,
+ int matchLength,
+ const BYTE * const match,
+ limitedOutput_directive limitedOutputBuffer,
+ BYTE *oend)
+{
+ int length;
+ BYTE *token;
+
+ /* Encode Literal length */
+ length = (int)(*ip - *anchor);
+ token = (*op)++;
+
+ if ((limitedOutputBuffer)
+ && ((*op + (length>>8)
+ + length + (2 + 1 + LASTLITERALS)) > oend)) {
+ /* Check output limit */
+ return 1;
+ }
+ if (length >= (int)RUN_MASK) {
+ int len;
+
+ *token = (RUN_MASK<<ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *(*op)++ = 255;
+ *(*op)++ = (BYTE)len;
+ } else
+ *token = (BYTE)(length<<ML_BITS);
+
+ /* Copy Literals */
+ LZ4_wildCopy(*op, *anchor, (*op) + length);
+ *op += length;
+
+ /* Encode Offset */
+ LZ4_writeLE16(*op, (U16)(*ip - match));
+ *op += 2;
+
+ /* Encode MatchLength */
+ length = (int)(matchLength - MINMATCH);
+
+ if ((limitedOutputBuffer)
+ && (*op + (length>>8)
+ + (1 + LASTLITERALS) > oend)) {
+ /* Check output limit */
+ return 1;
+ }
+
+ if (length >= (int)ML_MASK) {
+ *token += ML_MASK;
+ length -= ML_MASK;
+
+ for (; length > 509 ; length -= 510) {
+ *(*op)++ = 255;
+ *(*op)++ = 255;
+ }
+
+ if (length > 254) {
+ length -= 255;
+ *(*op)++ = 255;
+ }
+
+ *(*op)++ = (BYTE)length;
+ } else
+ *token += (BYTE)(length);
+
+ /* Prepare next loop */
+ *ip += matchLength;
+ *anchor = *ip;
+
+ return 0;
+}
+
+static int LZ4HC_compress_generic(
+ LZ4HC_CCtx_internal *const ctx,
+ const char * const source,
+ char * const dest,
+ int const inputSize,
+ int const maxOutputSize,
+ int compressionLevel,
+ limitedOutput_directive limit
+ )
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *anchor = ip;
+ const BYTE * const iend = ip + inputSize;
+ const BYTE * const mflimit = iend - MFLIMIT;
+ const BYTE * const matchlimit = (iend - LASTLITERALS);
+
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + maxOutputSize;
+
+ unsigned int maxNbAttempts;
+ int ml, ml2, ml3, ml0;
+ const BYTE *ref = NULL;
+ const BYTE *start2 = NULL;
+ const BYTE *ref2 = NULL;
+ const BYTE *start3 = NULL;
+ const BYTE *ref3 = NULL;
+ const BYTE *start0;
+ const BYTE *ref0;
+
+ /* init */
+ if (compressionLevel > LZ4HC_MAX_CLEVEL)
+ compressionLevel = LZ4HC_MAX_CLEVEL;
+ if (compressionLevel < 1)
+ compressionLevel = LZ4HC_DEFAULT_CLEVEL;
+ maxNbAttempts = 1 << (compressionLevel - 1);
+ ctx->end += inputSize;
+
+ ip++;
+
+ /* Main Loop */
+ while (ip < mflimit) {
+ ml = LZ4HC_InsertAndFindBestMatch(ctx, ip,
+ matchlimit, (&ref), maxNbAttempts);
+ if (!ml) {
+ ip++;
+ continue;
+ }
+
+ /* saved, in case we would skip too much */
+ start0 = ip;
+ ref0 = ref;
+ ml0 = ml;
+
+_Search2:
+ if (ip + ml < mflimit)
+ ml2 = LZ4HC_InsertAndGetWiderMatch(ctx,
+ ip + ml - 2, ip + 0,
+ matchlimit, ml, &ref2,
+ &start2, maxNbAttempts);
+ else
+ ml2 = ml;
+
+ if (ml2 == ml) {
+ /* No better match */
+ if (LZ4HC_encodeSequence(&ip, &op,
+ &anchor, ml, ref, limit, oend))
+ return 0;
+ continue;
+ }
+
+ if (start0 < ip) {
+ if (start2 < ip + ml0) {
+ /* empirical */
+ ip = start0;
+ ref = ref0;
+ ml = ml0;
+ }
+ }
+
+ /* Here, start0 == ip */
+ if ((start2 - ip) < 3) {
+ /* First Match too small : removed */
+ ml = ml2;
+ ip = start2;
+ ref = ref2;
+ goto _Search2;
+ }
+
+_Search3:
+ /*
+ * Currently we have :
+ * ml2 > ml1, and
+ * ip1 + 3 <= ip2 (usually < ip1 + ml1)
+ */
+ if ((start2 - ip) < OPTIMAL_ML) {
+ int correction;
+ int new_ml = ml;
+
+ if (new_ml > OPTIMAL_ML)
+ new_ml = OPTIMAL_ML;
+ if (ip + new_ml > start2 + ml2 - MINMATCH)
+ new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
+
+ correction = new_ml - (int)(start2 - ip);
+
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ }
+ /*
+ * Now, we have start2 = ip + new_ml,
+ * with new_ml = min(ml, OPTIMAL_ML = 18)
+ */
+
+ if (start2 + ml2 < mflimit)
+ ml3 = LZ4HC_InsertAndGetWiderMatch(ctx,
+ start2 + ml2 - 3, start2,
+ matchlimit, ml2, &ref3, &start3,
+ maxNbAttempts);
+ else
+ ml3 = ml2;
+
+ if (ml3 == ml2) {
+ /* No better match : 2 sequences to encode */
+ /* ip & ref are known; Now for ml */
+ if (start2 < ip + ml)
+ ml = (int)(start2 - ip);
+ /* Now, encode 2 sequences */
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor,
+ ml, ref, limit, oend))
+ return 0;
+ ip = start2;
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor,
+ ml2, ref2, limit, oend))
+ return 0;
+ continue;
+ }
+
+ if (start3 < ip + ml + 3) {
+ /* Not enough space for match 2 : remove it */
+ if (start3 >= (ip + ml)) {
+ /* can write Seq1 immediately
+ * ==> Seq2 is removed,
+ * so Seq3 becomes Seq1
+ */
+ if (start2 < ip + ml) {
+ int correction = (int)(ip + ml - start2);
+
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ if (ml2 < MINMATCH) {
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ }
+ }
+
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor,
+ ml, ref, limit, oend))
+ return 0;
+ ip = start3;
+ ref = ref3;
+ ml = ml3;
+
+ start0 = start2;
+ ref0 = ref2;
+ ml0 = ml2;
+ goto _Search2;
+ }
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ goto _Search3;
+ }
+
+ /*
+ * OK, now we have 3 ascending matches;
+ * let's write at least the first one
+ * ip & ref are known; Now for ml
+ */
+ if (start2 < ip + ml) {
+ if ((start2 - ip) < (int)ML_MASK) {
+ int correction;
+
+ if (ml > OPTIMAL_ML)
+ ml = OPTIMAL_ML;
+ if (ip + ml > start2 + ml2 - MINMATCH)
+ ml = (int)(start2 - ip) + ml2 - MINMATCH;
+ correction = ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ } else
+ ml = (int)(start2 - ip);
+ }
+ if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml,
+ ref, limit, oend))
+ return 0;
+
+ ip = start2;
+ ref = ref2;
+ ml = ml2;
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+
+ goto _Search3;
+ }
+
+ /* Encode Last Literals */
+ {
+ int lastRun = (int)(iend - anchor);
+
+ if ((limit)
+ && (((char *)op - dest) + lastRun + 1
+ + ((lastRun + 255 - RUN_MASK)/255)
+ > (U32)maxOutputSize)) {
+ /* Check output limit */
+ return 0;
+ }
+ if (lastRun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK<<ML_BITS);
+ lastRun -= RUN_MASK;
+ for (; lastRun > 254 ; lastRun -= 255)
+ *op++ = 255;
+ *op++ = (BYTE) lastRun;
+ } else
+ *op++ = (BYTE)(lastRun<<ML_BITS);
+ LZ4_memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ }
+
+ /* End */
+ return (int) (((char *)op) - dest);
+}
+
+static int LZ4_compress_HC_extStateHC(
+ void *state,
+ const char *src,
+ char *dst,
+ int srcSize,
+ int maxDstSize,
+ int compressionLevel)
+{
+ LZ4HC_CCtx_internal *ctx = &((LZ4_streamHC_t *)state)->internal_donotuse;
+
+ if (((size_t)(state)&(sizeof(void *) - 1)) != 0) {
+ /* Error : state is not aligned
+ * for pointers (32 or 64 bits)
+ */
+ return 0;
+ }
+
+ LZ4HC_init(ctx, (const BYTE *)src);
+
+ if (maxDstSize < LZ4_compressBound(srcSize))
+ return LZ4HC_compress_generic(ctx, src, dst,
+ srcSize, maxDstSize, compressionLevel, limitedOutput);
+ else
+ return LZ4HC_compress_generic(ctx, src, dst,
+ srcSize, maxDstSize, compressionLevel, noLimit);
+}
+
+int LZ4_compress_HC(const char *src, char *dst, int srcSize,
+ int maxDstSize, int compressionLevel, void *wrkmem)
+{
+ return LZ4_compress_HC_extStateHC(wrkmem, src, dst,
+ srcSize, maxDstSize, compressionLevel);
+}
+
+/**************************************
+ * Streaming Functions
+ **************************************/
+void LZ4_resetStreamHC(LZ4_streamHC_t *LZ4_streamHCPtr, int compressionLevel)
+{
+ LZ4_streamHCPtr->internal_donotuse.base = NULL;
+ LZ4_streamHCPtr->internal_donotuse.compressionLevel = (unsigned int)compressionLevel;
+}
+
+int LZ4_loadDictHC(LZ4_streamHC_t *LZ4_streamHCPtr,
+ const char *dictionary,
+ int dictSize)
+{
+ LZ4HC_CCtx_internal *ctxPtr = &LZ4_streamHCPtr->internal_donotuse;
+
+ if (dictSize > 64 * KB) {
+ dictionary += dictSize - 64 * KB;
+ dictSize = 64 * KB;
+ }
+ LZ4HC_init(ctxPtr, (const BYTE *)dictionary);
+ if (dictSize >= 4)
+ LZ4HC_Insert(ctxPtr, (const BYTE *)dictionary + (dictSize - 3));
+ ctxPtr->end = (const BYTE *)dictionary + dictSize;
+ return dictSize;
+}
+
+/* compression */
+
+static void LZ4HC_setExternalDict(
+ LZ4HC_CCtx_internal *ctxPtr,
+ const BYTE *newBlock)
+{
+ if (ctxPtr->end >= ctxPtr->base + 4) {
+ /* Referencing remaining dictionary content */
+ LZ4HC_Insert(ctxPtr, ctxPtr->end - 3);
+ }
+
+ /*
+ * Only one memory segment for extDict,
+ * so any previous extDict is lost at this stage
+ */
+ ctxPtr->lowLimit = ctxPtr->dictLimit;
+ ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base);
+ ctxPtr->dictBase = ctxPtr->base;
+ ctxPtr->base = newBlock - ctxPtr->dictLimit;
+ ctxPtr->end = newBlock;
+ /* match referencing will resume from there */
+ ctxPtr->nextToUpdate = ctxPtr->dictLimit;
+}
+
+static int LZ4_compressHC_continue_generic(
+ LZ4_streamHC_t *LZ4_streamHCPtr,
+ const char *source,
+ char *dest,
+ int inputSize,
+ int maxOutputSize,
+ limitedOutput_directive limit)
+{
+ LZ4HC_CCtx_internal *ctxPtr = &LZ4_streamHCPtr->internal_donotuse;
+
+ /* auto - init if forgotten */
+ if (ctxPtr->base == NULL)
+ LZ4HC_init(ctxPtr, (const BYTE *) source);
+
+ /* Check overflow */
+ if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 * GB) {
+ size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base)
+ - ctxPtr->dictLimit;
+ if (dictSize > 64 * KB)
+ dictSize = 64 * KB;
+ LZ4_loadDictHC(LZ4_streamHCPtr,
+ (const char *)(ctxPtr->end) - dictSize, (int)dictSize);
+ }
+
+ /* Check if blocks follow each other */
+ if ((const BYTE *)source != ctxPtr->end)
+ LZ4HC_setExternalDict(ctxPtr, (const BYTE *)source);
+
+ /* Check overlapping input/dictionary space */
+ {
+ const BYTE *sourceEnd = (const BYTE *) source + inputSize;
+ const BYTE * const dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit;
+ const BYTE * const dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit;
+
+ if ((sourceEnd > dictBegin)
+ && ((const BYTE *)source < dictEnd)) {
+ if (sourceEnd > dictEnd)
+ sourceEnd = dictEnd;
+ ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase);
+
+ if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4)
+ ctxPtr->lowLimit = ctxPtr->dictLimit;
+ }
+ }
+
+ return LZ4HC_compress_generic(ctxPtr, source, dest,
+ inputSize, maxOutputSize, ctxPtr->compressionLevel, limit);
+}
+
+int LZ4_compress_HC_continue(
+ LZ4_streamHC_t *LZ4_streamHCPtr,
+ const char *source,
+ char *dest,
+ int inputSize,
+ int maxOutputSize)
+{
+ if (maxOutputSize < LZ4_compressBound(inputSize))
+ return LZ4_compressHC_continue_generic(LZ4_streamHCPtr,
+ source, dest, inputSize, maxOutputSize, limitedOutput);
+ else
+ return LZ4_compressHC_continue_generic(LZ4_streamHCPtr,
+ source, dest, inputSize, maxOutputSize, noLimit);
+}
+
+/* dictionary saving */
+
+int LZ4_saveDictHC(
+ LZ4_streamHC_t *LZ4_streamHCPtr,
+ char *safeBuffer,
+ int dictSize)
+{
+ LZ4HC_CCtx_internal *const streamPtr = &LZ4_streamHCPtr->internal_donotuse;
+ int const prefixSize = (int)(streamPtr->end
+ - (streamPtr->base + streamPtr->dictLimit));
+
+ if (dictSize > 64 * KB)
+ dictSize = 64 * KB;
+ if (dictSize < 4)
+ dictSize = 0;
+ if (dictSize > prefixSize)
+ dictSize = prefixSize;
+
+ memmove(safeBuffer, streamPtr->end - dictSize, dictSize);
+
+ {
+ U32 const endIndex = (U32)(streamPtr->end - streamPtr->base);
+
+ streamPtr->end = (const BYTE *)safeBuffer + dictSize;
+ streamPtr->base = streamPtr->end - endIndex;
+ streamPtr->dictLimit = endIndex - dictSize;
+ streamPtr->lowLimit = endIndex - dictSize;
+
+ if (streamPtr->nextToUpdate < streamPtr->dictLimit)
+ streamPtr->nextToUpdate = streamPtr->dictLimit;
+ }
+ return dictSize;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Synchronous Compression operations
+ *
+ * Copyright 2015 LG Electronics Inc.
+ * Copyright (c) 2016, Intel Corporation
+ * Author: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
+ */
+#ifndef _CRYPTO_SCOMP_INT_H
+#define _CRYPTO_SCOMP_INT_H
+#include <linux/crypto.h>
+
+#define SCOMP_SCRATCH_SIZE 131072
+
+struct crypto_scomp {
+ struct crypto_tfm base;
+};
+
+/**
+ * struct scomp_alg - synchronous compression algorithm
+ *
+ * @alloc_ctx: Function allocates algorithm specific context
+ * @free_ctx: Function frees context allocated with alloc_ctx
+ * @compress: Function performs a compress operation
+ * @decompress: Function performs a de-compress operation
+ * @base: Common crypto API algorithm data structure
+ */
+struct scomp_alg {
+ void *(*alloc_ctx)(struct crypto_scomp *tfm);
+ void (*free_ctx)(struct crypto_scomp *tfm, void *ctx);
+ int (*compress)(struct crypto_scomp *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen,
+ void *ctx);
+ int (*decompress)(struct crypto_scomp *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen,
+ void *ctx);
+ struct crypto_alg base;
+};
+
+static inline struct scomp_alg *__crypto_scomp_alg(struct crypto_alg *alg)
+{
+ return container_of(alg, struct scomp_alg, base);
+}
+
+static inline struct crypto_scomp *__crypto_scomp_tfm(struct crypto_tfm *tfm)
+{
+ return container_of(tfm, struct crypto_scomp, base);
+}
+
+static inline struct crypto_tfm *crypto_scomp_tfm(struct crypto_scomp *tfm)
+{
+ return &tfm->base;
+}
+
+static inline void crypto_free_scomp(struct crypto_scomp *tfm)
+{
+ crypto_destroy_tfm(tfm, crypto_scomp_tfm(tfm));
+}
+
+static inline struct scomp_alg *crypto_scomp_alg(struct crypto_scomp *tfm)
+{
+ return __crypto_scomp_alg(crypto_scomp_tfm(tfm)->__crt_alg);
+}
+
+static inline void *crypto_scomp_alloc_ctx(struct crypto_scomp *tfm)
+{
+ return crypto_scomp_alg(tfm)->alloc_ctx(tfm);
+}
+
+static inline void crypto_scomp_free_ctx(struct crypto_scomp *tfm,
+ void *ctx)
+{
+ return crypto_scomp_alg(tfm)->free_ctx(tfm, ctx);
+}
+
+static inline int crypto_scomp_compress(struct crypto_scomp *tfm,
+ const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen, void *ctx)
+{
+ return crypto_scomp_alg(tfm)->compress(tfm, src, slen, dst, dlen, ctx);
+}
+
+static inline int crypto_scomp_decompress(struct crypto_scomp *tfm,
+ const u8 *src, unsigned int slen,
+ u8 *dst, unsigned int *dlen,
+ void *ctx)
+{
+ return crypto_scomp_alg(tfm)->decompress(tfm, src, slen, dst, dlen,
+ ctx);
+}
+
+int crypto_init_scomp_ops_async(struct crypto_tfm *tfm);
+struct acomp_req *crypto_acomp_scomp_alloc_ctx(struct acomp_req *req);
+void crypto_acomp_scomp_free_ctx(struct acomp_req *req);
+
+/**
+ * crypto_register_scomp() -- Register synchronous compression algorithm
+ *
+ * Function registers an implementation of a synchronous
+ * compression algorithm
+ *
+ * @alg: algorithm definition
+ *
+ * Return: zero on success; error code in case of error
+ */
+int crypto_register_scomp(struct scomp_alg *alg);
+
+/**
+ * crypto_unregister_scomp() -- Unregister synchronous compression algorithm
+ *
+ * Function unregisters an implementation of a synchronous
+ * compression algorithm
+ *
+ * @alg: algorithm definition
+ */
+void crypto_unregister_scomp(struct scomp_alg *alg);
+
+int crypto_register_scomps(struct scomp_alg *algs, int count);
+void crypto_unregister_scomps(struct scomp_alg *algs, int count);
+
+#endif
BUILT_MODULE_NAME[\${#BUILT_MODULE_NAME[@]}]="lustre"
BUILT_MODULE_LOCATION[\${#BUILT_MODULE_LOCATION[@]}]="lustre/llite/"
DEST_MODULE_LOCATION[\${#DEST_MODULE_LOCATION[@]}]="/${kmoddir}/lustre/"
+BUILT_MODULE_NAME[\${#BUILT_MODULE_NAME[@]}]="lz4"
+BUILT_MODULE_LOCATION[\${#BUILT_MODULE_LOCATION[@]}]="lustre/lz4/"
+DEST_MODULE_LOCATION[\${#DEST_MODULE_LOCATION[@]}]="/${kmoddir}/lustre/"
+BUILT_MODULE_NAME[\${#BUILT_MODULE_NAME[@]}]="lz4hc"
+BUILT_MODULE_LOCATION[\${#BUILT_MODULE_LOCATION[@]}]="lustre/lz4/"
+DEST_MODULE_LOCATION[\${#DEST_MODULE_LOCATION[@]}]="/${kmoddir}/lustre/"
if \$( rpm -qa | grep -q krb5-devel ) ; then
BUILT_MODULE_NAME[\${#BUILT_MODULE_NAME[@]}]="ptlrpc_gss"
BUILT_MODULE_LOCATION[\${#BUILT_MODULE_LOCATION[@]}]="lustre/ptlrpc/gss/"
# is given. It's ugly, but is needed to emulate the prior functionality
if [ "${#modules[@]}" -eq 0 ] || [ "${modules[*]}" = "ldiskfs" ]; then
unload_all=true
- modules=('lnet_selftest' 'ldiskfs' 'libcfs')
+ modules=('lnet_selftest' 'ldiskfs' 'libcfs' 'lz4' 'lz4hc')
else
unload_all=false
fi
noinst_DATA += ldiskfs_ost1_2_11.tar.bz2 ldiskfs_ost2_2_11.tar.bz2
noinst_DATA += zfs_mdt1_2_11.tar.bz2 zfs_mdt2_2_11.tar.bz2
noinst_DATA += zfs_ost1_2_11.tar.bz2 zfs_ost2_2_11.tar.bz2
+noinst_DATA += AMSR_E_L3_DailyOcean_V05_20111003.hdf.bz2
noinst_SCRIPTS = leak_finder.pl llmount.sh llmountcleanup.sh functions.sh
noinst_SCRIPTS += test-framework.sh runvmstat runiozone runtests sanity.sh
noinst_SCRIPTS += rundbench acceptance-small.sh compile.sh conf-sanity.sh
-MODULES := kinode
+MODULES := kinode kcompr
-EXTRA_DIST = kinode.c
+EXTRA_DIST = kinode.c kcompr.c
@INCLUDE_RULES@
if MODULES
if TESTS
-modulefs_DATA = kinode$(KMODEXT)
+modulefs_DATA = kinode$(KMODEXT) kcompr$(KMODEXT)
endif
endif
--- /dev/null
+/*
+ * GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * 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 version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see
+ * http://www.gnu.org/licenses/gpl-2.0.html
+ *
+ * GPL HEADER END
+ */
+/*
+ * Copyright (c) 2022 DataDirect Networks
+ */
+/*
+ * This file is part of Lustre, http://www.lustre.org/
+ */
+
+/* Test various compression/decompression routines as exported via the
+ * kernel Crypto API.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/version.h>
+#include <linux/crypto.h>
+#ifdef HAVE_CRYPTO_INIT_WAIT
+#include <linux/scatterlist.h>
+#include <crypto/acompress.h>
+#endif
+#include <linux/random.h>
+#include <lustre_crypto.h>
+#include <obd_support.h>
+
+/* Random ID passed by userspace, and printed in messages, used to
+ * separate different runs of that module.
+ */
+static int run_id;
+module_param(run_id, int, 0644);
+MODULE_PARM_DESC(run_id, "run ID");
+
+/* Path to file to compress passed by userspace. */
+static char *input_file;
+module_param(input_file, charp, 0644);
+MODULE_PARM_DESC(input_file, "path to file to compress");
+
+#define PREFIX "lustre_kcompr_%u: "
+#define COMPR_CHUNK_SIZE (1 << 16) /* 64 KB */
+
+struct compr_desc {
+ char *cd_name; /* compression alg name */
+ int cd_level; /* compression level */
+};
+
+/* Compression algorithms to test */
+/* For LZ4, cd_level is interpreted as an "acceleration" factor. The larger the
+ * acceleration value, the faster the algorithm, but the lesser the compression.
+ * An acceleration value of "1" is the default.
+ * This acceleration factor is taken into account only by the Lustre-modified
+ * lz4 module.
+ */
+/* For LZ4HC, cd_level is interpreted as a compression level. The higher the
+ * level value, the better the compression, but the slower the algorithm.
+ * A level value of "9" is the default.
+ * This acceleration factor is taken into account only by the Lustre-modified
+ * lz4hc module.
+ */
+/* To conform to values that can be stored in the Lustre file layout (limited to
+ * 4 bits) we use levels between 0 and 15, 0 meaning 'use default'. Then this
+ * level is mapped to actual acceleration factor or compression level in the
+ * corresponding compression module. See lustre/lz4/lz4.h for mapping in place.
+ */
+static struct compr_desc compr_algs[] = {
+ { .cd_name = "lz4", .cd_level = 1 },
+ { .cd_name = "lz4", .cd_level = 4 },
+ { .cd_name = "lz4", .cd_level = 9 },
+ { .cd_name = "lz4", .cd_level = 15 },
+ { .cd_name = "lz4hc", .cd_level = 1 },
+ { .cd_name = "lz4hc", .cd_level = 3 },
+ { .cd_name = "lz4hc", .cd_level = 8 },
+ { .cd_name = "lz4hc", .cd_level = 15 },
+ { .cd_name = "lzo", .cd_level = -1 },
+ /* deflate is the crypto module implementing zlib compression (gzip) */
+ { .cd_name = "deflate", .cd_level = -1 },
+};
+
+int fill_input_from_file(char *filepath, struct page *page, size_t count)
+{
+ struct file *filp;
+ loff_t pos = 0;
+ void *pageaddr;
+ int err = 0;
+
+ pageaddr = kmap(page);
+ filp = filp_open(filepath, O_RDONLY, 0);
+ if (IS_ERR_OR_NULL(filp)) {
+ err = PTR_ERR(filp);
+ filp = NULL;
+ goto out;
+ }
+
+ err = cfs_kernel_read(filp, pageaddr, count, &pos);
+ if (err < 0)
+ goto out;
+
+out:
+ if (filp)
+ filp_close(filp, NULL);
+ kunmap(page);
+ return err;
+}
+
+int fill_input_with_rand(struct page *page, size_t count)
+{
+ char randbuf1[67], randbuf2[14];
+ void *pageaddr;
+ char *p;
+
+ pageaddr = kmap(page);
+ /* write binary test data into pages */
+ p = pageaddr;
+ get_random_bytes(randbuf1, sizeof(randbuf1));
+ while (p + sizeof(randbuf1) - (char *)pageaddr < count) {
+ memcpy(p, randbuf1, sizeof(randbuf1));
+ p += sizeof(randbuf1);
+ }
+ p = pageaddr;
+ while (p + sizeof(randbuf2) - (char *)pageaddr < count) {
+ get_random_bytes(randbuf2, sizeof(randbuf2));
+ memcpy(p, randbuf2, sizeof(randbuf2));
+ p += sizeof(randbuf2) + prandom_u32_max(1 << 13);
+ }
+ kunmap(page);
+ return count;
+}
+
+/* compress and decompress, generic variant */
+int test_comp_compress_decompress(struct page *in_page, unsigned int order,
+ char *compr_name, int level)
+{
+ void *inpageaddr = NULL, *comppageaddr = NULL, *decomppageaddr = NULL;
+ struct page *comp_out_page = NULL, *decomp_out_page = NULL;
+ unsigned int in_len = 1 << (PAGE_SHIFT + order);
+ unsigned int comp_len = in_len, decomp_len = in_len;
+ unsigned int curr_len, curr_comp_len;
+ void *incurrpageaddr, *outcurrpageaddr;
+ unsigned int chunk_size = COMPR_CHUNK_SIZE;
+ struct crypto_comp *cc = NULL;
+ ktime_t started, finished;
+ u64 usdelta, currusdelta;
+ int err = -1;
+
+ /* allocate 1 << order contiguous pages for compression output */
+ comp_out_page = alloc_pages(GFP_KERNEL, order);
+ if (!comp_out_page) {
+ pr_err(PREFIX "ENOMEM cannot allocate comp_out_page\n", run_id);
+ goto free;
+ }
+ /* allocate 1 << order contiguous pages for decompression output */
+ decomp_out_page = alloc_pages(GFP_KERNEL, order);
+ if (!decomp_out_page) {
+ pr_err(PREFIX "ENOMEM cannot allocate decomp_out_page\n",
+ run_id);
+ goto free;
+ }
+
+ cc = crypto_alloc_comp(compr_name, 0, 0);
+ if (IS_ERR(cc)) {
+ pr_err(PREFIX
+ "ERROR cannot initialize compressor %s, error %ld\n",
+ run_id, compr_name, PTR_ERR(cc));
+ cc = NULL;
+ goto free;
+ }
+
+ if (level != -1)
+ ll_crypto_comp_set_level(cc, level);
+
+ inpageaddr = kmap(in_page);
+ comppageaddr = kmap(comp_out_page);
+
+ /* Try compression by COMPR_CHUNK_SIZE chunks only if multiple */
+ if (!(in_len & (COMPR_CHUNK_SIZE - 1))) {
+ /* loop on chunk_size, from COMPR_CHUNK_SIZE
+ * and double each time
+ */
+ while (chunk_size < in_len) {
+ incurrpageaddr = inpageaddr;
+ outcurrpageaddr = comppageaddr;
+ curr_len = in_len;
+ currusdelta = 0;
+ curr_comp_len = 0;
+ /* compress input data, one chunk at a time */
+ while (curr_len > 0) {
+ comp_len = chunk_size;
+ started = ktime_get();
+ err = crypto_comp_compress(cc, incurrpageaddr,
+ chunk_size,
+ outcurrpageaddr,
+ &comp_len);
+ finished = ktime_get();
+ if (err || comp_len >= chunk_size) {
+ /* If compress returns error, or if
+ * output len is greater than input len,
+ * it means it is not worth compressing.
+ * So just copy input into output.
+ */
+ pr_err(PREFIX "cannot compress %d bytes, compressor %s (out len %d), leave uncompressed\n",
+ run_id, chunk_size, compr_name,
+ comp_len);
+ memcpy(outcurrpageaddr, incurrpageaddr,
+ chunk_size);
+ comp_len = chunk_size;
+ err = 0;
+ }
+ curr_comp_len += comp_len;
+ currusdelta +=
+ ktime_us_delta(finished, started);
+ curr_len -= chunk_size;
+ incurrpageaddr += chunk_size;
+ outcurrpageaddr += chunk_size;
+ }
+ pr_err(PREFIX "compr %s(%d) in %ukB chunks took %lld us (%llu MB/s), compress ratio: %u.%02u\n",
+ run_id, compr_name, level, chunk_size >> 10,
+ currusdelta,
+ (u64)in_len * 1000000 / currusdelta / 1048576,
+ in_len / curr_comp_len,
+ (in_len % curr_comp_len) * 100 / curr_comp_len);
+ chunk_size = chunk_size << 1;
+ cond_resched();
+ }
+ }
+
+ comp_len = in_len;
+ started = ktime_get();
+ err = crypto_comp_compress(cc, inpageaddr, in_len,
+ comppageaddr, &comp_len);
+ finished = ktime_get();
+ if (err || comp_len >= in_len) {
+ /* If compress returns error, or if output len is greater than
+ * input len, it means it is not worth compressing.
+ * So just copy input into output.
+ */
+ pr_err(PREFIX "cannot compress %d bytes, compressor %s,%d (out len %d), leave uncompressed\n",
+ run_id, in_len, compr_name, level, comp_len);
+ memcpy(comppageaddr, inpageaddr, in_len);
+ comp_len = in_len;
+ err = 0;
+ }
+ usdelta = ktime_us_delta(finished, started);
+ pr_err(PREFIX "compr %s(%d) in %ukB chunks took %lld us (%llu MB/s), compress ratio: %u.%02u\n",
+ run_id, compr_name, level, in_len >> 10,
+ usdelta, (u64)in_len * 1000000 / usdelta / 1048576,
+ in_len / comp_len, (in_len % comp_len) * 100 / comp_len);
+
+ decomppageaddr = kmap(decomp_out_page);
+ started = ktime_get();
+ err = crypto_comp_decompress(cc, comppageaddr, comp_len,
+ decomppageaddr, &decomp_len);
+ finished = ktime_get();
+ if (err) {
+ pr_err(PREFIX "ERROR cannot decompress %d bytes, compressor %s, error %d\n",
+ run_id, comp_len, compr_name, err);
+ goto free;
+ }
+ if (decomp_len != in_len) {
+ pr_err(PREFIX "ERROR decompressed len %d != initial len %d\n",
+ run_id, decomp_len, in_len);
+ err = -1;
+ goto free;
+ }
+ if (memcmp(inpageaddr, decomppageaddr, in_len)) {
+ pr_err(PREFIX "ERROR decompressed different from initial\n",
+ run_id);
+ err = -1;
+ }
+ usdelta = ktime_us_delta(finished, started);
+ pr_err(PREFIX "decompr %s(%d) took %lld us (%llu MB/s)\n",
+ run_id, compr_name, level, usdelta,
+ (u64)comp_len * 1000000 / usdelta / 1048576);
+
+free:
+ if (cc)
+ crypto_free_comp(cc);
+ if (inpageaddr)
+ kunmap(inpageaddr);
+ if (comppageaddr)
+ kunmap(comppageaddr);
+ if (decomppageaddr)
+ kunmap(decomppageaddr);
+ if (comp_out_page)
+ __free_pages(comp_out_page, order);
+ if (decomp_out_page)
+ __free_pages(decomp_out_page, order);
+ return err;
+}
+
+/* compress and decompress, scomp variant */
+int test_acomp_compress_decompress(struct page *in_page, unsigned int order,
+ char *compr_name, int level)
+{
+#ifdef HAVE_CRYPTO_INIT_WAIT
+ struct page *comp_out_page = NULL, *decomp_out_page = NULL;
+ unsigned int in_len = 1 << (PAGE_SHIFT + order);
+ void *inpageaddr = NULL, *decomppageaddr = NULL;
+ struct sg_table src_sgt, dst_sgt;
+ unsigned int comp_len, decomp_len;
+ struct crypto_acomp *ca = NULL;
+ struct acomp_req *req = NULL;
+ ktime_t started, finished;
+ struct crypto_wait wait;
+ struct scatterlist *s;
+ unsigned long size;
+ struct page *p;
+ u64 usdelta;
+ int i, err = -1;
+
+ /* allocate 1 << order contiguous pages for compression output */
+ comp_out_page = alloc_pages(GFP_KERNEL, order);
+ if (!comp_out_page) {
+ pr_err(PREFIX "ENOMEM cannot allocate comp_out_page\n", run_id);
+ goto free;
+ }
+ /* allocate 1 << order contiguous pages for decompression output */
+ decomp_out_page = alloc_pages(GFP_KERNEL, order);
+ if (!decomp_out_page) {
+ pr_err(PREFIX "ENOMEM cannot allocate decomp_out_page\n",
+ run_id);
+ goto free;
+ }
+
+ ca = crypto_alloc_acomp(compr_name, 0, 0);
+ if (IS_ERR(ca)) {
+ pr_err(PREFIX
+ "ERROR cannot initialize compressor %s, error %ld\n",
+ run_id, compr_name, PTR_ERR(ca));
+ ca = NULL;
+ goto free;
+ }
+
+ if (level != -1)
+ ll_crypto_acomp_set_level(ca, level);
+
+ req = acomp_request_alloc(ca);
+ if (!req) {
+ pr_err(PREFIX
+ "ERROR request alloc failed for %s\n",
+ run_id, compr_name);
+ goto free;
+ }
+
+ crypto_init_wait(&wait);
+ err = sg_alloc_table(&src_sgt, 1 << order, GFP_KERNEL);
+ if (err)
+ goto free;
+ p = in_page;
+ for_each_sg(src_sgt.sgl, s, src_sgt.orig_nents, i)
+ sg_set_page(s, p + i, PAGE_SIZE, 0);
+ err = sg_alloc_table(&dst_sgt, 1 << order, GFP_KERNEL);
+ if (err) {
+ sg_free_table(&src_sgt);
+ goto free;
+ }
+ p = comp_out_page;
+ for_each_sg(dst_sgt.sgl, s, dst_sgt.orig_nents, i)
+ sg_set_page(s, p + i, PAGE_SIZE, 0);
+
+ acomp_request_set_params(req, src_sgt.sgl, dst_sgt.sgl, in_len, in_len);
+ acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ crypto_req_done, &wait);
+
+ started = ktime_get();
+ err = crypto_wait_req(crypto_acomp_compress(req), &wait);
+ finished = ktime_get();
+ sg_free_table(&src_sgt);
+ sg_free_table(&dst_sgt);
+ comp_len = req->dlen;
+ if (err || comp_len >= in_len) {
+ /* If compress returns error, or if output len is greater than
+ * input len, it means it is not worth compressing.
+ * So just copy input into output.
+ */
+ pr_err(PREFIX "cannot compress %d bytes, compressor %s,%d (out len %d), leave uncompressed\n",
+ run_id, in_len, compr_name, level, comp_len);
+ inpageaddr = kmap(in_page);
+ decomppageaddr = kmap(comp_out_page);
+ memcpy(decomppageaddr, inpageaddr, in_len);
+ kunmap(inpageaddr);
+ kunmap(decomppageaddr);
+ comp_len = in_len;
+ err = 0;
+ }
+ usdelta = ktime_us_delta(finished, started);
+ pr_err(PREFIX "acompr %s(%d) of %ukB chunks took %lld us (%llu MB/s), compress ratio: %u.%02u\n",
+ run_id, compr_name, level, in_len >> 10,
+ usdelta, (u64)in_len * 1000000 / usdelta / 1048576,
+ in_len / comp_len, (in_len % comp_len) * 100 / comp_len);
+
+ crypto_init_wait(&wait);
+ err = sg_alloc_table(&src_sgt, 1 << order, GFP_KERNEL);
+ if (err)
+ goto free;
+ p = comp_out_page;
+ size = comp_len;
+ for_each_sg(src_sgt.sgl, s, src_sgt.orig_nents, i) {
+ sg_set_page(s, p + i, min_t(unsigned long, size, PAGE_SIZE), 0);
+ if (size < PAGE_SIZE)
+ break;
+ size -= PAGE_SIZE;
+ }
+ err = sg_alloc_table(&dst_sgt, 1 << order, GFP_KERNEL);
+ if (err) {
+ sg_free_table(&src_sgt);
+ goto free;
+ }
+ p = decomp_out_page;
+ for_each_sg(dst_sgt.sgl, s, dst_sgt.orig_nents, i)
+ sg_set_page(s, p + i, PAGE_SIZE, 0);
+
+ acomp_request_set_params(req, src_sgt.sgl, dst_sgt.sgl,
+ comp_len, in_len);
+
+ started = ktime_get();
+ err = crypto_wait_req(crypto_acomp_decompress(req), &wait);
+ finished = ktime_get();
+ sg_free_table(&src_sgt);
+ sg_free_table(&dst_sgt);
+ decomp_len = req->dlen;
+ if (err) {
+ pr_err(PREFIX "ERROR cannot decompress %d bytes, compressor %s, error %d\n",
+ run_id, comp_len, compr_name, err);
+ goto free;
+ }
+ if (decomp_len != in_len) {
+ pr_err(PREFIX "ERROR decompressed len %d != initial len %d\n",
+ run_id, decomp_len, in_len);
+ err = -1;
+ goto free;
+ }
+ inpageaddr = kmap(in_page);
+ decomppageaddr = kmap(decomp_out_page);
+ if (memcmp(inpageaddr, decomppageaddr, in_len)) {
+ pr_err(PREFIX "ERROR decompressed different from initial\n",
+ run_id);
+ err = -1;
+ }
+ kunmap(inpageaddr);
+ kunmap(decomppageaddr);
+ usdelta = ktime_us_delta(finished, started);
+ pr_err(PREFIX "adecompr %s(%d) took %lld us (%llu MB/s)\n",
+ run_id, compr_name, level, usdelta,
+ (u64)comp_len * 1000000 / usdelta / 1048576);
+
+free:
+ if (req)
+ acomp_request_free(req);
+ if (ca)
+ crypto_free_acomp(ca);
+ return err;
+#else /* !HAVE_CRYPTO_INIT_WAIT */
+ pr_err(PREFIX "SKIP test_acomp_compress_decompress(%s), not supported\n",
+ run_id, compr_name);
+ return 0;
+#endif /* HAVE_CRYPTO_INIT_WAIT */
+}
+
+static int order_from_len(unsigned int len)
+{
+ int order = 0;
+
+ while (len > 1) {
+ order++;
+ len >>= 1;
+ }
+
+ return order - PAGE_SHIFT;
+}
+
+static int __init kcompr_init(void)
+{
+ /* Allocate 1 << 22 = 4MB for input data */
+ unsigned int order = 22 - PAGE_SHIFT, order_eff;
+ struct page *page = NULL;
+ int idx = 0;
+ int rc = 0;
+
+ /* allocate 1 << order contiguous pages */
+ page = alloc_pages(GFP_KERNEL, order);
+ if (!page) {
+ pr_err(PREFIX "ENOMEM cannot allocate pages\n", run_id);
+ goto out;
+ }
+
+ /* initialize input buffers */
+ if (input_file != NULL && input_file[0] != '\0') {
+ /* write content of provided file into pages to compress */
+ rc = fill_input_from_file(input_file, page,
+ 1 << (PAGE_SHIFT + order));
+ pr_err(PREFIX "*****\n", run_id);
+ pr_err(PREFIX "(de)compression test on provided file %s\n",
+ run_id, input_file);
+ pr_err(PREFIX "*****\n", run_id);
+ } else {
+ /* write binary test data into pages to compress */
+ rc = fill_input_with_rand(page, 1 << (PAGE_SHIFT + order));
+ pr_err(PREFIX "*****\n", run_id);
+ pr_err(PREFIX "(de)compression test on random binary data\n",
+ run_id);
+ pr_err(PREFIX "*****\n", run_id);
+ }
+ if (rc < 0) {
+ pr_err(PREFIX "cannot fill in input buffer, ret %d\n",
+ run_id, rc);
+ goto out;
+ }
+
+ order_eff = order_from_len(rc);
+
+ /* proceed to compression/decompression, for each algorithm in the list,
+ * for both generic and scomp variants
+ */
+ for (idx = 0; idx < ARRAY_SIZE(compr_algs); idx++) {
+ rc = test_comp_compress_decompress(page, order_eff,
+ compr_algs[idx].cd_name,
+ compr_algs[idx].cd_level);
+ pr_err(PREFIX "test_comp_compress_decompress(%s,%d) ret %d\n",
+ run_id, compr_algs[idx].cd_name,
+ compr_algs[idx].cd_level, rc);
+ if (rc)
+ goto out;
+
+ /* only compress first 1 << 17 = 128 kB,
+ * max len accepted by scomp variants
+ */
+ rc = test_acomp_compress_decompress(page,
+ min((int)order_eff,
+ 17 - PAGE_SHIFT),
+ compr_algs[idx].cd_name,
+ compr_algs[idx].cd_level);
+ pr_err(PREFIX "test_acomp_compress_decompress(%s,%d) ret %d\n",
+ run_id, compr_algs[idx].cd_name,
+ compr_algs[idx].cd_level, rc);
+ if (rc)
+ goto out;
+ }
+
+ pr_err(PREFIX "SUCCESS\n", run_id);
+
+out:
+ if (page)
+ __free_pages(page, order);
+ /* Don't load. */
+ return -EINVAL;
+}
+
+static void __exit kcompr_exit(void)
+{
+}
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("compression/decompression test module");
+MODULE_VERSION(LUSTRE_VERSION_STRING);
+
+module_init(kcompr_init);
+module_exit(kcompr_exit);
}
run_test 81b "OST should return -ENOSPC when retry still fails ======="
+test_84()
+{
+ (( $CLIENT_VERSION >= $(version_code 2.14.0.66) )) ||
+ skip "Need at least version 2.14.0.66"
+ [ -f $LUSTRE/tests/kernel/kcompr.ko ] || skip "Need MODULES build"
+
+ local run_id=$RANDOM
+ local tmpfile=$TMP/$tfile
+ local tmpout=$TMP/$tfile.$run_id.out
+ local hdf=$LUSTRE/tests/AMSR_E_L3_DailyOcean_V05_20111003.hdf
+
+ # Try to insert the module. This will always fail as the
+ # module is designed to not be inserted.
+
+ # First launch without input_file: use auto generated random input
+ echo "Compress/decompress synthetic data"
+ insmod $LUSTRE/tests/kernel/kcompr.ko run_id=$run_id &> /dev/null
+
+ dmesg | grep "lustre_kcompr_$run_id:" > $tmpout
+ stack_trap "rm -f $tmpout"
+ cat $tmpout
+ if $(grep -q "lustre_kcompr_$run_id: ENOMEM" $tmpout); then
+ error_noexit "lz4 compression/decompression failed"
+ elif ! $(grep -q "lustre_kcompr_$run_id: SUCCESS" $tmpout); then
+ error "compression/decompression for large text file failed"
+ fi
+
+ run_id=$RANDOM
+ # Second launch with large text file we build
+ find "$LUSTRE" -name "*.sh" -o -name "*.[ch]" -o -name "*.py" |
+ while read F; do
+ echo "$F"
+ cat $F
+ (( $(stat -c %s $tmpfile) < (8 << 20) )) || break
+ done >> $tmpfile
+ find /etc -type f |
+ while read F; do
+ echo "$F"
+ cat $F
+ (( $(stat -c %s $tmpfile) < (8 << 20) )) || break
+ done >> $tmpfile
+ stack_trap "rm -f $tmpfile"
+ echo "Compress/decompress text file, size $(stat -c %s $tmpfile)"
+ insmod $LUSTRE/tests/kernel/kcompr.ko run_id=$run_id \
+ input_file=$tmpfile &> /dev/null
+
+ dmesg | grep "lustre_kcompr_$run_id:" > $tmpout
+ stack_trap "rm -f $tmpout"
+ cat $tmpout
+ if $(grep -q "lustre_kcompr_$run_id: ENOMEM" $tmpout); then
+ error_noexit "lz4 compression/decompression failed"
+ elif ! $(grep -q "lustre_kcompr_$run_id: SUCCESS" $tmpout); then
+ error "compression/decompression for pseudo random data failed"
+ fi
+
+ run_id=$RANDOM
+ # Third launch with downloaded HDF file
+ # HDF file AMSR_E_L3_DailyOcean_V05_20111003.hdf taken from
+ # https://nsidc.org/data/ae_dyocn/versions/2
+ if ! [ -e $hdf.bz2 ]; then
+ echo "HDF file not present"
+ exit 0
+ fi
+ if [ $(which bzcat) ]; then
+ bzcat $hdf.bz2 > $tmpfile
+ else
+ cp $hdf.bz2 $tmpfile.bz2
+ bunzip2 $tmpfile.bz2
+ fi
+ echo "Compress/decompress $hdf"
+ insmod $LUSTRE/tests/kernel/kcompr.ko run_id=$run_id \
+ input_file=$tmpfile &> /dev/null
+
+ dmesg | grep "lustre_kcompr_$run_id:" > $tmpout
+ stack_trap "rm -f $tmpout"
+ cat $tmpout
+ if $(grep -q "lustre_kcompr_$run_id: ENOMEM" $tmpout); then
+ error_noexit "lz4 compression/decompression failed"
+ elif ! $(grep -q "lustre_kcompr_$run_id: SUCCESS" $tmpout); then
+ error "compression/decompression for HDF file failed"
+ fi
+}
+run_test 84 "lz4/lz4hc compression/decompression kernel module"
+
test_99() {
[ -z "$(which cvs 2>/dev/null)" ] && skip_env "could not find cvs"
git://git.whamcloud.com / fs / lustre-release.git / commitdiff