lib/zlib: add s390 hardware support for kernel zlib_deflate

Patch series "S390 hardware support for kernel zlib", v3.

With IBM z15 mainframe the new DFLTCC instruction is available.  It
implements deflate algorithm in hardware (Nest Acceleration Unit - NXU)
with estimated compression and decompression performance orders of
magnitude faster than the current zlib.

This patchset adds s390 hardware compression support to kernel zlib.
The code is based on the userspace zlib implementation:

	https://github.com/madler/zlib/pull/410

The coding style is also preserved for future maintainability.  There is
only limited set of userspace zlib functions represented in kernel.
Apart from that, all the memory allocation should be performed in
advance.  Thus, the workarea structures are extended with the parameter
lists required for the DEFLATE CONVENTION CALL instruction.

Since kernel zlib itself does not support gzip headers, only Adler-32
checksum is processed (also can be produced by DFLTCC facility).  Like
it was implemented for userspace, kernel zlib will compress in hardware
on level 1, and in software on all other levels.  Decompression will
always happen in hardware (when enabled).

Two DFLTCC compression calls produce the same results only when they
both are made on machines of the same generation, and when the
respective buffers have the same offset relative to the start of the
page.  Therefore care should be taken when using hardware compression
when reproducible results are desired.  However it does always produce
the standard conform output which can be inflated anyway.

The new kernel command line parameter 'dfltcc' is introduced to
configure s390 zlib hardware support:

    Format: { on | off | def_only | inf_only | always }
     on:       s390 zlib hardware support for compression on
               level 1 and decompression (default)
     off:      No s390 zlib hardware support
     def_only: s390 zlib hardware support for deflate
               only (compression on level 1)
     inf_only: s390 zlib hardware support for inflate
               only (decompression)
     always:   Same as 'on' but ignores the selected compression
               level always using hardware support (used for debugging)

The main purpose of the integration of the NXU support into the kernel
zlib is the use of hardware deflate in btrfs filesystem with on-the-fly
compression enabled.  Apart from that, hardware support can also be used
during boot for decompressing the kernel or the ramdisk image

With the patch for btrfs expanding zlib buffer from 1 to 4 pages (patch
6) the following performance results have been achieved using the
ramdisk with btrfs.  These are relative numbers based on throughput rate
and compression ratio for zlib level 1:

  Input data              Deflate rate   Inflate rate   Compression ratio
                          NXU/Software   NXU/Software   NXU/Software
  stream of zeroes        1.46           1.02           1.00
  random ASCII data       10.44          3.00           0.96
  ASCII text (dickens)    6,21           3.33           0.94
  binary data (vmlinux)   8,37           3.90           1.02

This means that s390 hardware deflate can provide up to 10 times faster
compression (on level 1) and up to 4 times faster decompression (refers
to all compression levels) for btrfs zlib.

Disclaimer: Performance results are based on IBM internal tests using DD
command-line utility on btrfs on a Fedora 30 based internal driver in
native LPAR on a z15 system.  Results may vary based on individual
workload, configuration and software levels.

This patch (of 9):

Create zlib_dfltcc library with the s390 DEFLATE CONVERSION CALL
implementation and related compression functions.  Update zlib_deflate
functions with the hooks for s390 hardware support and adjust workspace
structures with extra parameter lists required for hardware deflate.

Link: http://lkml.kernel.org/r/20200103223334.20669-2-zaslonko@linux.ibm.com
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Co-developed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Chris Mason <clm@fb.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Eduard Shishkin <edward6@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Richard Purdie <rpurdie@rpsys.net>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 124 insertions, 10 deletions

diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h
index a8c370897c9f..385333b22ec6 100644
--- a/lib/zlib_deflate/defutil.h
+++ b/lib/zlib_deflate/defutil.h
@@ -1,5 +1,7 @@
+#ifndef DEFUTIL_H
+#define DEFUTIL_H
 
-
+#include <linux/zutil.h>
 
 #define Assert(err, str) 
 #define Trace(dummy) 
@@ -238,17 +240,13 @@ typedef struct deflate_state {
 
 } deflate_state;
 
-typedef struct deflate_workspace {
-    /* State memory for the deflator */
-    deflate_state deflate_memory;
-    Byte *window_memory;
-    Pos *prev_memory;
-    Pos *head_memory;
-    char *overlay_memory;
-} deflate_workspace;
-
+#ifdef CONFIG_ZLIB_DFLTCC
+#define zlib_deflate_window_memsize(windowBits) \
+	(2 * (1 << (windowBits)) * sizeof(Byte) + PAGE_SIZE)
+#else
 #define zlib_deflate_window_memsize(windowBits) \
 	(2 * (1 << (windowBits)) * sizeof(Byte))
+#endif
 #define zlib_deflate_prev_memsize(windowBits) \
 	((1 << (windowBits)) * sizeof(Pos))
 #define zlib_deflate_head_memsize(memLevel) \
@@ -293,6 +291,24 @@ void zlib_tr_stored_type_only (deflate_state *);
 }
 
 /* ===========================================================================
+ * Reverse the first len bits of a code, using straightforward code (a faster
+ * method would use a table)
+ * IN assertion: 1 <= len <= 15
+ */
+static inline unsigned  bi_reverse(
+    unsigned code, /* the value to invert */
+    int len        /* its bit length */
+)
+{
+    register unsigned res = 0;
+    do {
+        res |= code & 1;
+        code >>= 1, res <<= 1;
+    } while (--len > 0);
+    return res >> 1;
+}
+
+/* ===========================================================================
  * Flush the bit buffer, keeping at most 7 bits in it.
  */
 static inline void bi_flush(deflate_state *s)
@@ -325,3 +341,101 @@ static inline void bi_windup(deflate_state *s)
 #endif
 }
 
+typedef enum {
+    need_more,      /* block not completed, need more input or more output */
+    block_done,     /* block flush performed */
+    finish_started, /* finish started, need only more output at next deflate */
+    finish_done     /* finish done, accept no more input or output */
+} block_state;
+
+#define Buf_size (8 * 2*sizeof(char))
+/* Number of bits used within bi_buf. (bi_buf might be implemented on
+ * more than 16 bits on some systems.)
+ */
+
+/* ===========================================================================
+ * Send a value on a given number of bits.
+ * IN assertion: length <= 16 and value fits in length bits.
+ */
+#ifdef DEBUG_ZLIB
+static void send_bits      (deflate_state *s, int value, int length);
+
+static void send_bits(
+    deflate_state *s,
+    int value,  /* value to send */
+    int length  /* number of bits */
+)
+{
+    Tracevv((stderr," l %2d v %4x ", length, value));
+    Assert(length > 0 && length <= 15, "invalid length");
+    s->bits_sent += (ulg)length;
+
+    /* If not enough room in bi_buf, use (valid) bits from bi_buf and
+     * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid))
+     * unused bits in value.
+     */
+    if (s->bi_valid > (int)Buf_size - length) {
+        s->bi_buf |= (value << s->bi_valid);
+        put_short(s, s->bi_buf);
+        s->bi_buf = (ush)value >> (Buf_size - s->bi_valid);
+        s->bi_valid += length - Buf_size;
+    } else {
+        s->bi_buf |= value << s->bi_valid;
+        s->bi_valid += length;
+    }
+}
+#else /* !DEBUG_ZLIB */
+
+#define send_bits(s, value, length) \
+{ int len = length;\
+  if (s->bi_valid > (int)Buf_size - len) {\
+    int val = value;\
+    s->bi_buf |= (val << s->bi_valid);\
+    put_short(s, s->bi_buf);\
+    s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\
+    s->bi_valid += len - Buf_size;\
+  } else {\
+    s->bi_buf |= (value) << s->bi_valid;\
+    s->bi_valid += len;\
+  }\
+}
+#endif /* DEBUG_ZLIB */
+
+static inline void zlib_tr_send_bits(
+    deflate_state *s,
+    int value,
+    int length
+)
+{
+    send_bits(s, value, length);
+}
+
+/* =========================================================================
+ * Flush as much pending output as possible. All deflate() output goes
+ * through this function so some applications may wish to modify it
+ * to avoid allocating a large strm->next_out buffer and copying into it.
+ * (See also read_buf()).
+ */
+static inline void flush_pending(
+	z_streamp strm
+)
+{
+    deflate_state *s = (deflate_state *) strm->state;
+    unsigned len = s->pending;
+
+    if (len > strm->avail_out) len = strm->avail_out;
+    if (len == 0) return;
+
+    if (strm->next_out != NULL) {
+	memcpy(strm->next_out, s->pending_out, len);
+	strm->next_out += len;
+    }
+    s->pending_out += len;
+    strm->total_out += len;
+    strm->avail_out  -= len;
+    s->pending -= len;
+    if (s->pending == 0) {
+        s->pending_out = s->pending_buf;
+    }
+}
+#endif /* DEFUTIL_H */