torvalds
diff --git a/‎lib/Kconfig‎
Lines changed: 7 additions & 0 deletions b/‎lib/Kconfig‎
Lines changed: 7 additions & 0 deletions
diff --git a/‎lib/Makefile‎
Lines changed: 1 addition & 0 deletions b/‎lib/Makefile‎
Lines changed: 1 addition & 0 deletions
diff --git a/‎lib/zlib_deflate/deflate.c‎
Lines changed: 41 additions & 38 deletions b/‎lib/zlib_deflate/deflate.c‎
Lines changed: 41 additions & 38 deletions
diff --git a/‎lib/zlib_deflate/deftree.c‎
Lines changed: 0 additions & 54 deletions b/‎lib/zlib_deflate/deftree.c‎
Lines changed: 0 additions & 54 deletions
diff --git a/‎lib/zlib_deflate/defutil.h‎
Lines changed: 124 additions & 10 deletions b/‎lib/zlib_deflate/defutil.h‎
Lines changed: 124 additions & 10 deletions
@@ -278,6 +278,13 @@ config ZLIB_DEFLATE
 	tristate
 	select BITREVERSE
 
+config ZLIB_DFLTCC
+	def_bool y
+	depends on S390
+	prompt "Enable s390x DEFLATE CONVERSION CALL support for kernel zlib"
+	help
+	 Enable s390x hardware support for zlib in the kernel.
+
 config LZO_COMPRESS
 	tristate
 
 
@@ -140,6 +140,7 @@ obj-$(CONFIG_842_COMPRESS) += 842/
 obj-$(CONFIG_842_DECOMPRESS) += 842/
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
+obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_BCH) += bch.o
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
 
@@ -52,16 +52,18 @@
 #include <linux/zutil.h>
 #include "defutil.h"
 
+/* architecture-specific bits */
+#ifdef CONFIG_ZLIB_DFLTCC
+#  include "../zlib_dfltcc/dfltcc.h"
+#else
+#define DEFLATE_RESET_HOOK(strm) do {} while (0)
+#define DEFLATE_HOOK(strm, flush, bstate) 0
+#define DEFLATE_NEED_CHECKSUM(strm) 1
+#endif
 
 /* ===========================================================================
  *  Function prototypes.
  */
-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;
 
 typedef block_state (*compress_func) (deflate_state *s, int flush);
 /* Compression function. Returns the block state after the call. */
@@ -72,7 +74,6 @@ static block_state deflate_fast   (deflate_state *s, int flush);
 static block_state deflate_slow   (deflate_state *s, int flush);
 static void lm_init        (deflate_state *s);
 static void putShortMSB    (deflate_state *s, uInt b);
-static void flush_pending  (z_streamp strm);
 static int read_buf        (z_streamp strm, Byte *buf, unsigned size);
 static uInt longest_match  (deflate_state *s, IPos cur_match);
 
@@ -98,6 +99,25 @@ static  void check_match (deflate_state *s, IPos start, IPos match,
  * See deflate.c for comments about the MIN_MATCH+1.
  */
 
+/* Workspace to be allocated for deflate processing */
+typedef struct deflate_workspace {
+    /* State memory for the deflator */
+    deflate_state deflate_memory;
+#ifdef CONFIG_ZLIB_DFLTCC
+    /* State memory for s390 hardware deflate */
+    struct dfltcc_state dfltcc_memory;
+#endif
+    Byte *window_memory;
+    Pos *prev_memory;
+    Pos *head_memory;
+    char *overlay_memory;
+} deflate_workspace;
+
+#ifdef CONFIG_ZLIB_DFLTCC
+/* dfltcc_state must be doubleword aligned for DFLTCC call */
+static_assert(offsetof(struct deflate_workspace, dfltcc_memory) % 8 == 0);
+#endif
+
 /* Values for max_lazy_match, good_match and max_chain_length, depending on
  * the desired pack level (0..9). The values given below have been tuned to
  * exclude worst case performance for pathological files. Better values may be
@@ -207,7 +227,15 @@ int zlib_deflateInit2(
      */
     next = (char *) mem;
     next += sizeof(*mem);
+#ifdef CONFIG_ZLIB_DFLTCC
+    /*
+     *  DFLTCC requires the window to be page aligned.
+     *  Thus, we overallocate and take the aligned portion of the buffer.
+     */
+    mem->window_memory = (Byte *) PTR_ALIGN(next, PAGE_SIZE);
+#else
     mem->window_memory = (Byte *) next;
+#endif
     next += zlib_deflate_window_memsize(windowBits);
     mem->prev_memory = (Pos *) next;
     next += zlib_deflate_prev_memsize(windowBits);
@@ -277,6 +305,8 @@ int zlib_deflateReset(
     zlib_tr_init(s);
     lm_init(s);
 
+    DEFLATE_RESET_HOOK(strm);
+
     return Z_OK;
 }
 
@@ -294,35 +324,6 @@ static void putShortMSB(
     put_byte(s, (Byte)(b & 0xff));
 }   
 
-/* =========================================================================
- * 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 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;
-    }
-}
-
 /* ========================================================================= */
 int zlib_deflate(
 	z_streamp strm,
@@ -404,7 +405,8 @@ int zlib_deflate(
         (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) {
         block_state bstate;
 
-	bstate = (*(configuration_table[s->level].func))(s, flush);
+	bstate = DEFLATE_HOOK(strm, flush, &bstate) ? bstate :
+		 (*(configuration_table[s->level].func))(s, flush);
 
         if (bstate == finish_started || bstate == finish_done) {
             s->status = FINISH_STATE;
@@ -503,7 +505,8 @@ static int read_buf(
 
     strm->avail_in  -= len;
 
-    if (!((deflate_state *)(strm->state))->noheader) {
+    if (!DEFLATE_NEED_CHECKSUM(strm)) {}
+    else if (!((deflate_state *)(strm->state))->noheader) {
         strm->adler = zlib_adler32(strm->adler, strm->next_in, len);
     }
     memcpy(buf, strm->next_in, len);
 
@@ -76,11 +76,6 @@ static const uch bl_order[BL_CODES]
  * probability, to avoid transmitting the lengths for unused bit length codes.
  */
 
-#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.)
- */
-
 /* ===========================================================================
  * Local data. These are initialized only once.
  */
@@ -147,7 +142,6 @@ static void send_all_trees (deflate_state *s, int lcodes, int dcodes,
 static void compress_block (deflate_state *s, ct_data *ltree,
                            ct_data *dtree);
 static void set_data_type  (deflate_state *s);
-static void bi_windup      (deflate_state *s);
 static void bi_flush       (deflate_state *s);
 static void copy_block     (deflate_state *s, char *buf, unsigned len,
                            int header);
@@ -169,54 +163,6 @@ static void copy_block     (deflate_state *s, char *buf, unsigned len,
  * used.
  */
 
-/* ===========================================================================
- * 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 */
-
 /* ===========================================================================
  * Initialize the various 'constant' tables. In a multi-threaded environment,
  * this function may be called by two threads concurrently, but this is
 
@@ -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) \
@@ -292,6 +290,24 @@ void zlib_tr_stored_type_only (deflate_state *);
     put_byte(s, (uch)((ush)(w) >> 8)); \
 }
 
+/* ===========================================================================
+ * 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.
  */
@@ -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 */