s390x: Add accelerated inflate&deflate

Makefile.in

@@ -168,6 +168,9 @@ crc32.o: $(SRCDIR)crc32.c
 crc32_vx.o: $(SRCDIR)contrib/crc32vx/crc32_vx.c
 	$(CC) $(CFLAGS) $(VGFMAFLAG) $(ZINC) -c -o $@ $(SRCDIR)contrib/crc32vx/crc32_vx.c
 
+dfltcc.o: $(SRCDIR)contrib/dfltcc/dfltcc.c
+	$(CC) $(CFLAGS) $(ZINC) -c -o $@ $(SRCDIR)contrib/dfltcc/dfltcc.c
+
 deflate.o: $(SRCDIR)deflate.c
 	$(CC) $(CFLAGS) $(ZINC) -c -o $@ $(SRCDIR)deflate.c
 
@@ -223,6 +226,11 @@ crc32_vx.lo: $(SRCDIR)contrib/crc32vx/crc32_vx.c
 	$(CC) $(SFLAGS) $(VGFMAFLAG) $(ZINC) -DPIC -c -o objs/crc32_vx.o $(SRCDIR)contrib/crc32vx/crc32_vx.c
 	-@mv objs/crc32_vx.o $@
 
+dfltcc.lo: $(SRCDIR)contrib/dfltcc/dfltcc.c
+	-@mkdir objs 2>/dev/null || test -d objs
+	$(CC) $(SFLAGS) $(ZINC) -DPIC -c -o objs/dfltcc.o $(SRCDIR)contrib/dfltcc/dfltcc.c
+	-@mv objs/dfltcc.o $@
+
 deflate.lo: $(SRCDIR)deflate.c
 	-@mkdir objs 2>/dev/null || test -d objs
 	$(CC) $(SFLAGS) $(ZINC) -DPIC -c -o objs/deflate.o $(SRCDIR)deflate.c
@@ -296,6 +304,9 @@ placebo $(SHAREDLIBV): $(PIC_OBJS) libz.a
 	ln -s $@ $(SHAREDLIBM)
 	-@rmdir objs
 
+crc32_test$(EXE): crc32_test.o $(STATICLIB)
+	$(CC) $(CFLAGS) -o $@ crc32_test.o $(TEST_LIBS)
+
 example$(EXE): example.o $(STATICLIB)
 	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ example.o $(TEST_LIBS)
 
@@ -308,6 +319,9 @@ examplesh$(EXE): example.o $(SHAREDLIBV)
 minigzipsh$(EXE): minigzip.o $(SHAREDLIBV)
 	$(CC) $(CFLAGS) -o $@ minigzip.o $(LDFLAGS) -L. $(SHAREDLIBV)
 
+crc32_test64$(EXE): crc32_test64.o $(STATICLIB)
+	$(CC) $(CFLAGS) -o $@ crc32_test64.o $(TEST_LIBS)
+
 example64$(EXE): example64.o $(STATICLIB)
 	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ example64.o $(TEST_LIBS)
 
@@ -416,6 +430,7 @@ inffast.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftrees.h $(SRCDIR
 inftrees.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftrees.h
 trees.o: $(SRCDIR)deflate.h $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)trees.h
 crc32_vx.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)contrib/crc32vx/crc32_vx_hooks.h
+dfltcc.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)contrib/dfltcc/dfltcc_hooks.h $(SRCDIR)contrib/dfltcc/dfltcc.h
 
 adler32.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h
 zutil.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)gzguts.h
@@ -427,4 +442,5 @@ infback.lo inflate.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftree
 inffast.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftrees.h $(SRCDIR)inflate.h $(SRCDIR)inffast.h
 inftrees.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)inftrees.h
 trees.lo: $(SRCDIR)deflate.h $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)trees.h
-crc32_vx.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)contrib/crc32vx/crc32_vx_hooks.h
+crc32_vx.lo: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)contrib/crc32vx/crc32_vx_hooks.h
+dfltcc.o: $(SRCDIR)zutil.h $(SRCDIR)zlib.h zconf.h $(SRCDIR)contrib/dfltcc/dfltcc_hooks.h $(SRCDIR)contrib/dfltcc/dfltcc.h

compress.c

@@ -7,6 +7,9 @@
 
 #define ZLIB_INTERNAL
 #include "zlib.h"
+#include "contrib/dfltcc/dfltcc_hooks.h"
+
+#define ZLIB_WRAPLEN 6 /* zlib format overhead */
 
 /* ===========================================================================
      Compresses the source buffer into the destination buffer. The level
@@ -90,6 +93,12 @@ z_size_t ZEXPORT compressBound_z(z_size_t sourceLen) {
     return bound < sourceLen ? (z_size_t)-1 : bound;
 }
 uLong ZEXPORT compressBound(uLong sourceLen) {
-    z_size_t bound = compressBound_z(sourceLen);
-    return (uLong)bound != bound ? (uLong)-1 : (uLong)bound;
+    uLong complen = DEFLATE_BOUND_COMPLEN(sourceLen);
+
+    if (complen > 0)
+        /* Architecture-specific code provided an upper bound. */
+        return complen + ZLIB_WRAPLEN;
+
+    return sourceLen + (sourceLen >> 12) + (sourceLen >> 14) +
+           (sourceLen >> 25) + 13;
 }

configure

@@ -96,6 +96,7 @@ undefined=0
 insecure=0
 unknown=0
 enable_crcvx=1
+enable_dfltcc=0
 old_cc="$CC"
 old_cflags="$CFLAGS"
 OBJC='$(OBJZ) $(OBJG)'
@@ -123,7 +124,7 @@ case "$1" in
       echo '  configure [--const] [--zprefix] [--prefix=PREFIX]  [--eprefix=EXPREFIX]' | tee -a configure.log
       echo '    [--insecure] [--static] [--64] [--libdir=LIBDIR] [--sharedlibdir=LIBDIR]' | tee -a configure.log
       echo '    [--includedir=INCLUDEDIR] [--archs="-arch i386 -arch x86_64"]' | tee -a configure.log
-      echo '    [--disable-crcvx]' | tee -a configure.log
+      echo '    [--disable-crcvx] [--dfltcc] [--dfltcc-level-mask=MASK]' | tee -a configure.log
         exit 0 ;;
     -p*=* | --prefix=*) prefix=`echo $1 | sed 's/.*=//'`; shift ;;
     -e*=* | --eprefix=*) exec_prefix=`echo $1 | sed 's/.*=//'`; shift ;;
@@ -153,6 +154,10 @@ case "$1" in
     --undefined) undefined=1; shift ;;
     --insecure) insecure=1; shift ;;
     --disable-crcvx) enable_crcvx=0; shift ;;
+    --dfltcc)enable_dfltcc=1; shift ;;
+    --dfltcc-level-mask=*)
+      CFLAGS="$CFLAGS -DDFLTCC_LEVEL_MASK=`echo $1 | sed 's/.*=//'`"
+      shift ;;
     *) unknown=1; echo "unknown option ignored: $1" | tee -a configure.log; shift;;
     esac
 done
@@ -955,6 +960,17 @@ EOF
     fi
 fi
 
+# enable ibm s390x dfltcc extension
+HAVE_S390X_DFLTCC=0
+if test $HAVE_S390X -eq 1 && test $enable_dfltcc -eq 1; then
+    HAVE_S390X_DFLTCC=1
+    echo "Enabeling s390x dfltcc extension ... Yes." | tee -a configure.log
+    CFLAGS="$CFLAGS -DHAVE_S390X_DFLTCC"
+    SFLAGS="$SFLAGS -DHAVE_S390X_DFLTCC"
+    OBJC="$OBJC dfltcc.o"
+    PIC_OBJC="$PIC_OBJC dfltcc.lo"
+fi
+
 # show the results in the log
 echo >> configure.log
 echo ALL = $ALL >> configure.log
@@ -988,6 +1004,7 @@ echo sharedlibdir = $sharedlibdir >> configure.log
 echo uname = $uname >> configure.log
 echo HAVE_S390X = $HAVE_S390X >> configure.log
 echo HAVE_S390X_VX = $HAVE_S390X_VX >> configure.log
+echo HAVE_S390X_DFLTCC = $HAVE_S390X_DFLTCC >> configure.log
 echo VGFMAFLAG = $VGFMAFLAG >> configure.log
 
 # update Makefile with the configure results
@@ -1000,6 +1017,7 @@ sed < ${SRCDIR}Makefile.in "
 /^LDFLAGS *=/s#=.*#=$LDFLAGS#
 /^LDSHARED *=/s#=.*#=$LDSHARED#
 /^CPP *=/s#=.*#=$CPP#
+/^VGFMAFLAG *=/s#=.*#=$VGFMAFLAG#
 /^STATICLIB *=/s#=.*#=$STATICLIB#
 /^SHAREDLIB *=/s#=.*#=$SHAREDLIB#
 /^SHAREDLIBV *=/s#=.*#=$SHAREDLIBV#

contrib/CMakeLists.txt

@@ -45,6 +45,7 @@ zlib_add_contrib_feature("GVMAT64"
 
 zlib_add_contrib_feature(INFBACK9 "with support for method 9 deflate" infback9)
 zlib_add_contrib_feature(CRC32VX "with S390X-CRC32VX implementation" crc32vx On)
+zlib_add_contrib_feature(DFLTCC "with S390X-DFLTCC deflate acceleration" dfltcc)
 zlib_add_contrib_lib(ADA "Ada bindings" ada)
 zlib_add_contrib_lib(BLAST "blast binary" blast)
 zlib_add_contrib_lib(IOSTREAM3 "IOStream C++ bindings V3" iostream3)

contrib/README.contrib

@@ -49,6 +49,10 @@ puff/       by Mark Adler <[email protected]>
 crc32vx/      by Ilya Leoshkevich <[email protected]>
         Hardware-accelerated CRC32 on IBM Z with Z13 VX extension.
 
+dfltcc/      by Ilya Leoshkevich <[email protected]>
+        Hardware-accelerated deflate on IBM Z with Z15 DEFLATE CONVERSION CALL
+        instruction.
+
 testzlib/   by Gilles Vollant <[email protected]>
         Example of the use of zlib
 

contrib/dfltcc/CMakeLists.txt

@@ -0,0 +1,61 @@
+# check if we compile for IBM s390x
+#
+CHECK_C_SOURCE_COMPILES("
+#ifndef __s390x__
+    #error
+#endif
+int main() {return 0;}
+" HAS_S390X_SUPPORT)
+
+#
+# Check for IBM S390X - DFLTCC extensions
+#
+if(ZLIB_WITH_DFLTCC AND HAS_S390X_SUPPORT)
+    # check if we have static_assert
+    check_c_source_compiles("
+        #include <assert.h>
+        static_assert(1==1,\"true\");
+        " HAS_STATIC_ASSERT)
+
+    # check if we have secure_getenv
+    set(CMAKE_REQUIRED_FLAGS -D_GNU_SOURCE=1)
+    check_c_source_compiles("
+        #include <stdlib.h>
+        int main() { char* _foo = secure_getenv(\"PWD\");return 0; }
+        " HAS_SECURE_GETENV)
+    unset(CMAKE_REQUIRED_FLAGS)
+
+    # check for specific headers
+    check_include_file(sys/sdt.h HAS_SYS_SDT_H)
+
+    set(definitions "-DHAVE_S390X_DFLTCC=1")
+    if(HAS_STATIC_ASSERT)
+        list(APPEND definitions "-DHAVE_STATIC_ASSERT=1")
+    endif()
+    if(HAS_SECURE_GETENV)
+        list(APPEND definitions "-DHAVE_SECURE_GETENV=1")
+        list(APPEND definitions "-D_GNU_SOURCE=1")
+    endif()
+    if(HAS_SYS_SDT_H)
+        list(APPEND definitions "-DHAVE_SYS_SDT_H=1")
+    endif()
+
+    # prepare compiling for s390x
+    if(ZLIB_BUILD_SHARED)
+        target_sources(zlib
+            PRIVATE
+                dfltcc.c
+                dfltcc_hooks.h
+                dfltcc_common.h)
+        target_compile_definitions(zlib PUBLIC ${definitions})
+    endif(ZLIB_BUILD_SHARED)
+    if(ZLIB_BUILD_STATIC)
+        target_sources(zlibstatic
+            PRIVATE
+                dfltcc.c
+                dfltcc_hooks.h
+                dfltcc_common.h)
+        target_compile_definitions(zlibstatic PUBLIC ${definitions})
+    endif(ZLIB_BUILD_STATIC)
+
+endif(ZLIB_WITH_DFLTCC AND HAS_S390X_SUPPORT)

contrib/dfltcc/README

@@ -0,0 +1,28 @@
+IBM Z mainframes starting from version z13 provide vector instructions, which 
+allows vectorization of crc32. This extension is build by default when targeting
+ibm s390x. However this extension can disabled if desired:
+
+    # for configure build
+    $ ./configure --disable-crcvx
+
+    # for cmake build
+    $ cmake .. -DZLIB_CRC32VX=off
+
+
+IBM Z mainframes starting from version z15 provide DFLTCC instruction,
+which implements deflate algorithm in hardware with estimated
+compression and decompression performance orders of magnitude faster
+than the current zlib and ratio comparable with that of level 1.
+
+This directory adds DFLTCC support. In order to enable it, the following
+build commands should be used:
+
+    $ ./configure --dfltcc
+    $ make
+
+When built like this, zlib would compress in hardware on level 1, and in
+software on all other levels. Decompression will always happen in
+hardware. In order to enable DFLTCC compression for levels 1-6 (i.e. to
+make it used by default) one could either configure with
+--dfltcc-level-mask=0x7e or set the environment variable
+DFLTCC_LEVEL_MASK to 0x7e at run time.