[PATCH V2 3/5] selftests/powerpc: Add NX-GZIP engine compress testcase
Daniel Axtens writes:
> Raphael Moreira Zinsly writes:
...
>> +#define hwsync()({ asm volatile("hwsync" ::: "memory"); })
>
> This doesn't compile on the clang version I tried as it doesn't
> recognise 'hwsync'. Does
> asm volatile("sync" ::: "memory");
> do the same thing?
Both hwsync and sync are extended mnemonics to 'sync 0'.
I just replaced hwsync for sync on this patch, but I'm
surprised that this is not recognized by clang.
--- >8 ---
Add a compression testcase for the powerpc NX-GZIP engine.
Signed-off-by: Bulent Abali
Signed-off-by: Raphael Moreira Zinsly
---
.../selftests/powerpc/nx-gzip/Makefile| 21 +
.../selftests/powerpc/nx-gzip/gzfht_test.c| 489 ++
.../selftests/powerpc/nx-gzip/gzip_vas.c | 259 ++
3 files changed, 769 insertions(+)
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/Makefile
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
diff --git a/tools/testing/selftests/powerpc/nx-gzip/Makefile
b/tools/testing/selftests/powerpc/nx-gzip/Makefile
new file mode 100644
index ..ab903f63bbbd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/Makefile
@@ -0,0 +1,21 @@
+CC = gcc
+CFLAGS = -O3
+INC = ./inc
+SRC = gzfht_test.c
+OBJ = $(SRC:.c=.o)
+TESTS = gzfht_test
+EXTRA_SOURCES = gzip_vas.c
+
+all: $(TESTS)
+
+$(OBJ): %.o: %.c
+ $(CC) $(CFLAGS) -I$(INC) -c $<
+
+$(TESTS): $(OBJ)
+ $(CC) $(CFLAGS) -I$(INC) -o $@ $@.o $(EXTRA_SOURCES)
+
+run_tests: $(TESTS)
+ ./gzfht_test gzip_vas.c
+
+clean:
+ rm -f $(TESTS) *.o *~ *.gz
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
new file mode 100644
index ..7a21c25f5611
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/* P9 gzip sample code for demonstrating the P9 NX hardware interface.
+ * Not intended for productive uses or for performance or compression
+ * ratio measurements. For simplicity of demonstration, this sample
+ * code compresses in to fixed Huffman blocks only (Deflate btype=1)
+ * and has very simple memory management. Dynamic Huffman blocks
+ * (Deflate btype=2) are more involved as detailed in the user guide.
+ * Note also that /dev/crypto/gzip, VAS and skiboot support are
+ * required.
+ *
+ * Copyright 2020 IBM Corp.
+ *
+ * https://github.com/libnxz/power-gzip for zlib api and other utils
+ *
+ * Author: Bulent Abali
+ *
+ * Definitions of acronyms used here. See
+ * P9 NX Gzip Accelerator User's Manual for details:
+ * https://github.com/libnxz/power-gzip/blob/develop/doc/power_nx_gzip_um.pdf
+ *
+ * adler/crc: 32 bit checksums appended to stream tail
+ * ce: completion extension
+ * cpb: coprocessor parameter block (metadata)
+ * crb: coprocessor request block (command)
+ * csb: coprocessor status block (status)
+ * dht: dynamic huffman table
+ * dde: data descriptor element (address, length)
+ * ddl: list of ddes
+ * dh/fh:dynamic and fixed huffman types
+ * fc: coprocessor function code
+ * histlen: history/dictionary length
+ * history: sliding window of up to 32KB of data
+ * lzcount: Deflate LZ symbol counts
+ * rembytecnt: remaining byte count
+ * sfbt: source final block type; last block's type during decomp
+ * spbc: source processed byte count
+ * subc: source unprocessed bit count
+ * tebc: target ending bit count; valid bits in the last byte
+ * tpbc: target processed byte count
+ * vas: virtual accelerator switch; the user mode interface
+ */
+
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include "nxu.h"
+#include "nx.h"
+
+int nx_dbg;
+FILE *nx_gzip_log;
+void *nx_fault_storage_address;
+
+#define NX_MIN(X, Y) (((X) < (Y)) ? (X) : (Y))
+#define FNAME_MAX 1024
+#define FEXT ".nx.gz"
+
+/*
+ * LZ counts returned in the user supplied nx_gzip_crb_cpb_t structure.
+ */
+static int compress_fht_sample(char *src, uint32_t srclen, char *dst,
+ uint32_t dstlen, int with_count,
+ struct nx_gzip_crb_cpb_t *cmdp, void *handle)
+{
+ int cc;
+ uint32_t fc;
+
+ assert(!!cmdp);
+
+ put32(cmdp->crb, gzip_fc, 0); /* clear */
+ fc = (with_count) ? GZIP_FC_COMPRESS_RESUME_FHT_COUNT :
+ GZIP_FC_COMPRESS_RESUME_FHT;
+ putnn(cmdp->crb, gzip_fc, fc);
+ putnn(cmdp->cpb, in_histlen, 0); /* resuming with no history */
+ memset((void *) >crb.csb, 0, sizeof(cmdp->crb.csb));
+
+ /* Section 6.6 programming notes; spbc may be in two different
+* places depending on FC.
+*/
+ if (!with_count)
+
Re: [PATCH V2 3/5] selftests/powerpc: Add NX-GZIP engine compress testcase
Daniel Axtens writes:
> Raphael Moreira Zinsly writes:
>
>> Add a compression testcase for the powerpc NX-GZIP engine.
>>
>> Signed-off-by: Bulent Abali
>> Signed-off-by: Raphael Moreira Zinsly
...
>> diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
>> b/tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
>> new file mode 100644
>> index ..d28e1efb527b
>> --- /dev/null
>> +++ b/tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
>> @@ -0,0 +1,259 @@
>> +// SPDX-License-Identifier: GPL-2.0-or-later
>> +
>> +/* Copyright 2020 IBM Corp.
>> + *
>> + * Author: Bulent Abali
>> + *
>> + */
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include
>> +#include "nx-gzip.h"
>> +#include "nx.h"
>> +#include "copy-paste.h"
>> +#include "nxu.h"
>> +#include "nx_dbg.h"
>> +#include
>> +
>> +#define barrier()
>> +#define hwsync()({ asm volatile("hwsync" ::: "memory"); })
>
> This doesn't compile on the clang version I tried as it doesn't
> recognise 'hwsync'.
What assembler are you using? I guess the LLVM one?
Can you try with -fno-integrated-as ?
> Does asm volatile("sync" ::: "memory");
> do the same thing? That is recognised by clang, but I don't know if
> dropping the hw prefix matters!
It shouldn't matter.
But you can just try it and look at the generated code to be sure, you
should get 0x7c0004ac.
cheers
Re: [PATCH V2 3/5] selftests/powerpc: Add NX-GZIP engine compress testcase
Raphael Moreira Zinsly writes:
> Add a compression testcase for the powerpc NX-GZIP engine.
>
> Signed-off-by: Bulent Abali
> Signed-off-by: Raphael Moreira Zinsly
> ---
> .../selftests/powerpc/nx-gzip/Makefile| 21 +
> .../selftests/powerpc/nx-gzip/gzfht_test.c| 489 ++
> .../selftests/powerpc/nx-gzip/gzip_vas.c | 259 ++
> 3 files changed, 769 insertions(+)
> create mode 100644 tools/testing/selftests/powerpc/nx-gzip/Makefile
> create mode 100644 tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
> create mode 100644 tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
>
> diff --git a/tools/testing/selftests/powerpc/nx-gzip/Makefile
> b/tools/testing/selftests/powerpc/nx-gzip/Makefile
> new file mode 100644
> index ..ab903f63bbbd
> --- /dev/null
> +++ b/tools/testing/selftests/powerpc/nx-gzip/Makefile
> @@ -0,0 +1,21 @@
> +CC = gcc
> +CFLAGS = -O3
> +INC = ./inc
> +SRC = gzfht_test.c
> +OBJ = $(SRC:.c=.o)
> +TESTS = gzfht_test
> +EXTRA_SOURCES = gzip_vas.c
> +
> +all: $(TESTS)
> +
> +$(OBJ): %.o: %.c
> + $(CC) $(CFLAGS) -I$(INC) -c $<
> +
> +$(TESTS): $(OBJ)
> + $(CC) $(CFLAGS) -I$(INC) -o $@ $@.o $(EXTRA_SOURCES)
> +
> +run_tests: $(TESTS)
> + ./gzfht_test gzip_vas.c
> +
> +clean:
> + rm -f $(TESTS) *.o *~ *.gz
> diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
> b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
> new file mode 100644
> index ..7a21c25f5611
> --- /dev/null
> +++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
> @@ -0,0 +1,489 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +
> +/* P9 gzip sample code for demonstrating the P9 NX hardware interface.
> + * Not intended for productive uses or for performance or compression
> + * ratio measurements. For simplicity of demonstration, this sample
> + * code compresses in to fixed Huffman blocks only (Deflate btype=1)
> + * and has very simple memory management. Dynamic Huffman blocks
> + * (Deflate btype=2) are more involved as detailed in the user guide.
> + * Note also that /dev/crypto/gzip, VAS and skiboot support are
> + * required.
> + *
> + * Copyright 2020 IBM Corp.
> + *
> + * https://github.com/libnxz/power-gzip for zlib api and other utils
> + *
> + * Author: Bulent Abali
> + *
> + * Definitions of acronyms used here. See
> + * P9 NX Gzip Accelerator User's Manual for details:
> + * https://github.com/libnxz/power-gzip/blob/develop/doc/power_nx_gzip_um.pdf
> + *
> + * adler/crc: 32 bit checksums appended to stream tail
> + * ce: completion extension
> + * cpb: coprocessor parameter block (metadata)
> + * crb: coprocessor request block (command)
> + * csb: coprocessor status block (status)
> + * dht: dynamic huffman table
> + * dde: data descriptor element (address, length)
> + * ddl: list of ddes
> + * dh/fh:dynamic and fixed huffman types
> + * fc: coprocessor function code
> + * histlen: history/dictionary length
> + * history: sliding window of up to 32KB of data
> + * lzcount: Deflate LZ symbol counts
> + * rembytecnt: remaining byte count
> + * sfbt: source final block type; last block's type during decomp
> + * spbc: source processed byte count
> + * subc: source unprocessed bit count
> + * tebc: target ending bit count; valid bits in the last byte
> + * tpbc: target processed byte count
> + * vas: virtual accelerator switch; the user mode interface
> + */
> +
> +
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include
> +#include "nxu.h"
> +#include "nx.h"
> +
> +int nx_dbg;
> +FILE *nx_gzip_log;
> +void *nx_fault_storage_address;
> +
> +#define NX_MIN(X, Y) (((X) < (Y)) ? (X) : (Y))
> +#define FNAME_MAX 1024
> +#define FEXT ".nx.gz"
> +
> +/*
> + * LZ counts returned in the user supplied nx_gzip_crb_cpb_t structure.
> + */
> +static int compress_fht_sample(char *src, uint32_t srclen, char *dst,
> + uint32_t dstlen, int with_count,
> + struct nx_gzip_crb_cpb_t *cmdp, void *handle)
> +{
> + int cc;
> + uint32_t fc;
> +
> + assert(!!cmdp);
> +
> + put32(cmdp->crb, gzip_fc, 0); /* clear */
> + fc = (with_count) ? GZIP_FC_COMPRESS_RESUME_FHT_COUNT :
> + GZIP_FC_COMPRESS_RESUME_FHT;
> + putnn(cmdp->crb, gzip_fc, fc);
> + putnn(cmdp->cpb, in_histlen, 0); /* resuming with no history */
> + memset((void *) >crb.csb, 0, sizeof(cmdp->crb.csb));
> +
> + /* Section 6.6 programming notes; spbc may be in two different
> + * places depending on FC.
> + */
> + if (!with_count)
> + put32(cmdp->cpb, out_spbc_comp, 0);
> + else
> + put32(cmdp->cpb, out_spbc_comp_with_count, 0);
> +
> + /* Figure 6-3 6-4; CSB location */
> +
[PATCH V2 3/5] selftests/powerpc: Add NX-GZIP engine compress testcase
Add a compression testcase for the powerpc NX-GZIP engine.
Signed-off-by: Bulent Abali
Signed-off-by: Raphael Moreira Zinsly
---
.../selftests/powerpc/nx-gzip/Makefile| 21 +
.../selftests/powerpc/nx-gzip/gzfht_test.c| 489 ++
.../selftests/powerpc/nx-gzip/gzip_vas.c | 259 ++
3 files changed, 769 insertions(+)
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/Makefile
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
create mode 100644 tools/testing/selftests/powerpc/nx-gzip/gzip_vas.c
diff --git a/tools/testing/selftests/powerpc/nx-gzip/Makefile
b/tools/testing/selftests/powerpc/nx-gzip/Makefile
new file mode 100644
index ..ab903f63bbbd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/Makefile
@@ -0,0 +1,21 @@
+CC = gcc
+CFLAGS = -O3
+INC = ./inc
+SRC = gzfht_test.c
+OBJ = $(SRC:.c=.o)
+TESTS = gzfht_test
+EXTRA_SOURCES = gzip_vas.c
+
+all: $(TESTS)
+
+$(OBJ): %.o: %.c
+ $(CC) $(CFLAGS) -I$(INC) -c $<
+
+$(TESTS): $(OBJ)
+ $(CC) $(CFLAGS) -I$(INC) -o $@ $@.o $(EXTRA_SOURCES)
+
+run_tests: $(TESTS)
+ ./gzfht_test gzip_vas.c
+
+clean:
+ rm -f $(TESTS) *.o *~ *.gz
diff --git a/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
new file mode 100644
index ..7a21c25f5611
--- /dev/null
+++ b/tools/testing/selftests/powerpc/nx-gzip/gzfht_test.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/* P9 gzip sample code for demonstrating the P9 NX hardware interface.
+ * Not intended for productive uses or for performance or compression
+ * ratio measurements. For simplicity of demonstration, this sample
+ * code compresses in to fixed Huffman blocks only (Deflate btype=1)
+ * and has very simple memory management. Dynamic Huffman blocks
+ * (Deflate btype=2) are more involved as detailed in the user guide.
+ * Note also that /dev/crypto/gzip, VAS and skiboot support are
+ * required.
+ *
+ * Copyright 2020 IBM Corp.
+ *
+ * https://github.com/libnxz/power-gzip for zlib api and other utils
+ *
+ * Author: Bulent Abali
+ *
+ * Definitions of acronyms used here. See
+ * P9 NX Gzip Accelerator User's Manual for details:
+ * https://github.com/libnxz/power-gzip/blob/develop/doc/power_nx_gzip_um.pdf
+ *
+ * adler/crc: 32 bit checksums appended to stream tail
+ * ce: completion extension
+ * cpb: coprocessor parameter block (metadata)
+ * crb: coprocessor request block (command)
+ * csb: coprocessor status block (status)
+ * dht: dynamic huffman table
+ * dde: data descriptor element (address, length)
+ * ddl: list of ddes
+ * dh/fh:dynamic and fixed huffman types
+ * fc: coprocessor function code
+ * histlen: history/dictionary length
+ * history: sliding window of up to 32KB of data
+ * lzcount: Deflate LZ symbol counts
+ * rembytecnt: remaining byte count
+ * sfbt: source final block type; last block's type during decomp
+ * spbc: source processed byte count
+ * subc: source unprocessed bit count
+ * tebc: target ending bit count; valid bits in the last byte
+ * tpbc: target processed byte count
+ * vas: virtual accelerator switch; the user mode interface
+ */
+
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include "nxu.h"
+#include "nx.h"
+
+int nx_dbg;
+FILE *nx_gzip_log;
+void *nx_fault_storage_address;
+
+#define NX_MIN(X, Y) (((X) < (Y)) ? (X) : (Y))
+#define FNAME_MAX 1024
+#define FEXT ".nx.gz"
+
+/*
+ * LZ counts returned in the user supplied nx_gzip_crb_cpb_t structure.
+ */
+static int compress_fht_sample(char *src, uint32_t srclen, char *dst,
+ uint32_t dstlen, int with_count,
+ struct nx_gzip_crb_cpb_t *cmdp, void *handle)
+{
+ int cc;
+ uint32_t fc;
+
+ assert(!!cmdp);
+
+ put32(cmdp->crb, gzip_fc, 0); /* clear */
+ fc = (with_count) ? GZIP_FC_COMPRESS_RESUME_FHT_COUNT :
+ GZIP_FC_COMPRESS_RESUME_FHT;
+ putnn(cmdp->crb, gzip_fc, fc);
+ putnn(cmdp->cpb, in_histlen, 0); /* resuming with no history */
+ memset((void *) >crb.csb, 0, sizeof(cmdp->crb.csb));
+
+ /* Section 6.6 programming notes; spbc may be in two different
+* places depending on FC.
+*/
+ if (!with_count)
+ put32(cmdp->cpb, out_spbc_comp, 0);
+ else
+ put32(cmdp->cpb, out_spbc_comp_with_count, 0);
+
+ /* Figure 6-3 6-4; CSB location */
+ put64(cmdp->crb, csb_address, 0);
+ put64(cmdp->crb, csb_address,
+ (uint64_t) >crb.csb & csb_address_mask);
+
+ /* Source direct dde (scatter-gather list) */
+ clear_dde(cmdp->crb.source_dde);
+ putnn(cmdp->crb.source_dde, dde_count, 0);
+
