19 files changed, 1966 insertions, 548 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 830181cc7a8..8991c57c196 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -51,14 +51,60 @@ config CRC_ITU_T
           functions require M here.
 
 config CRC32
-        tristate "CRC32 functions"
+        tristate "CRC32/CRC32c functions"
         default y
         select BITREVERSE
         help
           This option is provided for the case where no in-kernel-tree
-          modules require CRC32 functions, but a module built outside the
-          kernel tree does. Such modules that use library CRC32 functions
-          require M here.
+          modules require CRC32/CRC32c functions, but a module built outside
+          the kernel tree does. Such modules that use library CRC32/CRC32c
+          functions require M here.
+
+config CRC32_SELFTEST
+        bool "CRC32 perform self test on init"
+        default n
+        depends on CRC32
+        help
+          This option enables the CRC32 library functions to perform a
+          self test on initialization. The self test computes crc32_le
+          and crc32_be over byte strings with random alignment and length
+          and computes the total elapsed time and number of bytes processed.
+
+choice
+        prompt "CRC32 implementation"
+        depends on CRC32
+        default CRC32_SLICEBY8
+
+config CRC32_SLICEBY8
+        bool "Slice by 8 bytes"
+        help
+          Calculate checksum 8 bytes at a time with a clever slicing algorithm.
+          This is the fastest algorithm, but comes with a 8KiB lookup table.
+          Most modern processors have enough cache that this shouldn't be
+          a problem.
+
+          If you don't know which to choose, choose this one.
+
+config CRC32_SLICEBY4
+        bool "Slice by 4 bytes"
+        help
+          Calculate checksum 4 bytes at a time with a clever slicing algorithm.
+          This is a bit slower than slice by 8, but has a smaller 4KiB lookup
+          table.
+
+config CRC32_SARWATE
+        bool "Sarwate's Algorithm (one byte at a time)"
+        help
+          Calculate checksum a byte at a time using Sarwate's algorithm.  This
+          is not particularly fast, but has a small 256 byte lookup table.
+
+config CRC32_BIT
+        bool "Classic Algorithm (one bit at a time)"
+        help
+          Calculate checksum one bit at a time.  This is VERY slow, but has
+          no lookup table.  This is provided as a debugging option.
+
+endchoice
 
 config CRC7
         tristate "CRC7 functions"
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index dd373c8ee94..37a94aea5b7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -411,6 +411,26 @@ config SLUB_STATS
           out which slabs are relevant to a particular load.
           Try running: slabinfo -DA
 
+config SLQB_DEBUG
+        default y
+        bool "Enable SLQB debugging support"
+        depends on SLQB
+
+config SLQB_DEBUG_ON
+        default n
+        bool "SLQB debugging on by default"
+        depends on SLQB_DEBUG
+
+config SLQB_SYSFS
+        bool "Create SYSFS entries for slab caches"
+        default n
+        depends on SLQB
+
+config SLQB_STATS
+        bool "Enable SLQB performance statistics"
+        default n
+        depends on SLQB_SYSFS
+
 config DEBUG_KMEMLEAK
         bool "Kernel memory leak detector"
         depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \
@@ -667,8 +687,9 @@ config DEBUG_LOCKING_API_SELFTESTS
           mutexes and rwsems.
 
 config STACKTRACE
-        bool
+        bool "Stacktrace"
         depends on STACKTRACE_SUPPORT
+        default y
 
 config DEBUG_STACK_USAGE
         bool "Stack utilization instrumentation"
@@ -1040,7 +1061,7 @@ config FAULT_INJECTION
 config FAILSLAB
         bool "Fault-injection capability for kmalloc"
         depends on FAULT_INJECTION
-        depends on SLAB || SLUB
+        depends on SLAB || SLUB || SLQB
         help
           Provide fault-injection capability for kmalloc.
 
diff --git a/lib/Makefile b/lib/Makefile
index 6b597fdb189..7bd1afa496c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -10,9 +10,10 @@ endif
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
          rbtree.o radix-tree.o dump_stack.o timerqueue.o\
          idr.o int_sqrt.o extable.o prio_tree.o \
-         sha1.o irq_regs.o reciprocal_div.o argv_split.o \
+         sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
          proportions.o prio_heap.o ratelimit.o show_mem.o \
-         is_single_threaded.o plist.o decompress.o find_next_bit.o
+         is_single_threaded.o plist.o decompress.o find_next_bit.o \
+         memcopy.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 3f3b68199d7..cf12bb86d7c 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -315,30 +315,32 @@ void bitmap_clear(unsigned long *map, int start, int nr)
 }
 EXPORT_SYMBOL(bitmap_clear);
 
-/*
+/**
  * bitmap_find_next_zero_area - find a contiguous aligned zero area
  * @map: The address to base the search on
  * @size: The bitmap size in bits
  * @start: The bitnumber to start searching at
  * @nr: The number of zeroed bits we're looking for
  * @align_mask: Alignment mask for zero area
+ * @align_offset: Alignment offset for zero area.
  *
  * The @align_mask should be one less than a power of 2; the effect is that
- * the bit offset of all zero areas this function finds is multiples of that
- * power of 2. A @align_mask of 0 means no alignment is required.
+ * the bit offset of all zero areas this function finds plus @align_offset
+ * is multiple of that power of 2.
  */
-unsigned long bitmap_find_next_zero_area(unsigned long *map,
-                                         unsigned long size,
-                                         unsigned long start,
-                                         unsigned int nr,
-                                         unsigned long align_mask)
+unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
+                                             unsigned long size,
+                                             unsigned long start,
+                                             unsigned int nr,
+                                             unsigned long align_mask,
+                                             unsigned long align_offset)
 {
         unsigned long index, end, i;
 again:
         index = find_next_zero_bit(map, size, start);
 
         /* Align allocation */
-        index = __ALIGN_MASK(index, align_mask);
+        index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset;
 
         end = index + nr;
         if (end > size)
@@ -350,7 +352,7 @@ again:
         }
         return index;
 }
-EXPORT_SYMBOL(bitmap_find_next_zero_area);
+EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
 
 /*
  * Bitmap printing & parsing functions: first version by Bill Irwin,
diff --git a/lib/btree.c b/lib/btree.c
index 2a34392bcec..297124d4d8d 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -319,8 +319,8 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo,
 
         if (head->height == 0)
                 return NULL;
-retry:
         longcpy(key, __key, geo->keylen);
+retry:
         dec_key(geo, key);
 
         node = head->node;
@@ -351,7 +351,7 @@ retry:
         }
 miss:
         if (retry_key) {
-                __key = retry_key;
+                longcpy(key, retry_key, geo->keylen);
                 retry_key = NULL;
                 goto retry;
         }
diff --git a/lib/crc32.c b/lib/crc32.c
index 4855995fcde..382fa767a65 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -1,4 +1,8 @@
 /*
+ * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin
+ * cleaned up code to current version of sparse and added the slicing-by-8
+ * algorithm to the closely similar existing slicing-by-4 algorithm.
+ *
  * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com>
  * Nicer crc32 functions/docs submitted by linux@horizon.com.  Thanks!
  * Code was from the public domain, copyright abandoned.  Code was
@@ -20,51 +24,58 @@
  * Version 2.  See the file COPYING for more details.
  */
 
+/* see: Documentation/crc32.txt for a description of algorithms */
+
 #include <linux/crc32.h>
-#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/init.h>
-#include <asm/atomic.h>
 #include "crc32defs.h"
-#if CRC_LE_BITS == 8
-# define tole(x) __constant_cpu_to_le32(x)
+
+#if CRC_LE_BITS > 8
+# define tole(x) (__force u32) __constant_cpu_to_le32(x)
 #else
 # define tole(x) (x)
 #endif
 
-#if CRC_BE_BITS == 8
-# define tobe(x) __constant_cpu_to_be32(x)
+#if CRC_BE_BITS > 8
+# define tobe(x) (__force u32) __constant_cpu_to_be32(x)
 #else
 # define tobe(x) (x)
 #endif
+
 #include "crc32table.h"
 
 MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
-MODULE_DESCRIPTION("Ethernet CRC32 calculations");
+MODULE_DESCRIPTION("Various CRC32 calculations");
 MODULE_LICENSE("GPL");
 
-#if CRC_LE_BITS == 8 || CRC_BE_BITS == 8
+#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8
 
+/* implements slicing-by-4 or slicing-by-8 algorithm */
 static inline u32
 crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 {
 # ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[0][(crc ^ (x)) & 255] ^ (crc >> 8)
-#  define DO_CRC4 crc = tab[3][(crc) & 255] ^ \
-                tab[2][(crc >> 8) & 255] ^ \
-                tab[1][(crc >> 16) & 255] ^ \
-                tab[0][(crc >> 24) & 255]
+#  define DO_CRC(x) (crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8))
+#  define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \
+                   t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255])
+#  define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \
+                   t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255])
 # else
-#  define DO_CRC(x) crc = tab[0][((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
-#  define DO_CRC4 crc = tab[0][(crc) & 255] ^ \
-                tab[1][(crc >> 8) & 255] ^ \
-                tab[2][(crc >> 16) & 255] ^ \
-                tab[3][(crc >> 24) & 255]
+#  define DO_CRC(x) (crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8))
+#  define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \
+                   t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255])
+#  define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \
+                   t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255])
 # endif
         const u32 *b;
-        size_t    rem_len;
+        size_t rem_len;
+# ifdef CONFIG_X86
+        size_t i;
+# endif
+        const u32 *t0 = tab[0], *t1 = tab[1], *t2 = tab[2], *t3 = tab[3];
+        const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7];
+        u32 q;
 
         /* Align it */
         if (unlikely((long)buf & 3 && len)) {
@@ -72,27 +83,51 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
                         DO_CRC(*buf++);
                 } while ((--len) && ((long)buf)&3);
         }
+
+# if CRC_LE_BITS == 32
         rem_len = len & 3;
-        /* load data 32 bits wide, xor data 32 bits wide. */
         len = len >> 2;
+# else
+        rem_len = len & 7;
+        len = len >> 3;
+# endif
+
         b = (const u32 *)buf;
+# ifdef CONFIG_X86
+        --b;
+        for (i = 0; i < len; i++) {
+# else
         for (--b; len; --len) {
-                crc ^= *++b; /* use pre increment for speed */
-                DO_CRC4;
+# endif
+                q = crc ^ *++b; /* use pre increment for speed */
+# if CRC_LE_BITS == 32
+                crc = DO_CRC4;
+# else
+                crc = DO_CRC8;
+                q = *++b;
+                crc ^= DO_CRC4;
+# endif
         }
         len = rem_len;
         /* And the last few bytes */
         if (len) {
                 u8 *p = (u8 *)(b + 1) - 1;
+# ifdef CONFIG_X86
+                for (i = 0; i < len; i++)
+                        DO_CRC(*++p); /* use pre increment for speed */
+# else
                 do {
                         DO_CRC(*++p); /* use pre increment for speed */
                 } while (--len);
+# endif
         }
         return crc;
 #undef DO_CRC
 #undef DO_CRC4
+#undef DO_CRC8
 }
 #endif
+
 /**
  * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32
  * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
@@ -100,53 +135,56 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
  * @p: pointer to buffer over which CRC is run
  * @len: length of buffer @p
  */
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len);
-
-#if CRC_LE_BITS == 1
-/*
- * In fact, the table-based code will work in this case, but it can be
- * simplified by inlining the table in ?: form.
- */
-
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
+                                          size_t len, const u32 (*tab)[256],
+                                          u32 polynomial)
 {
+#if CRC_LE_BITS == 1
         int i;
         while (len--) {
                 crc ^= *p++;
                 for (i = 0; i < 8; i++)
-                        crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+                        crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
+        }
+# elif CRC_LE_BITS == 2
+        while (len--) {
+                crc ^= *p++;
+                crc = (crc >> 2) ^ tab[0][crc & 3];
+                crc = (crc >> 2) ^ tab[0][crc & 3];
+                crc = (crc >> 2) ^ tab[0][crc & 3];
+                crc = (crc >> 2) ^ tab[0][crc & 3];
         }
-        return crc;
-}
-#else                           /* Table-based approach */
-
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
-{
-# if CRC_LE_BITS == 8
-        const u32      (*tab)[] = crc32table_le;
-
-        crc = __cpu_to_le32(crc);
-        crc = crc32_body(crc, p, len, tab);
-        return __le32_to_cpu(crc);
 # elif CRC_LE_BITS == 4
         while (len--) {
                 crc ^= *p++;
-                crc = (crc >> 4) ^ crc32table_le[crc & 15];
-                crc = (crc >> 4) ^ crc32table_le[crc & 15];
+                crc = (crc >> 4) ^ tab[0][crc & 15];
+                crc = (crc >> 4) ^ tab[0][crc & 15];
         }
-        return crc;
-# elif CRC_LE_BITS == 2
+# elif CRC_LE_BITS == 8
+        /* aka Sarwate algorithm */
         while (len--) {
                 crc ^= *p++;
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
+                crc = (crc >> 8) ^ tab[0][crc & 255];
         }
+# else
+        crc = (__force u32) __cpu_to_le32(crc);
+        crc = crc32_body(crc, p, len, tab);
+        crc = __le32_to_cpu((__force __le32)crc);
+#endif
         return crc;
-# endif
 }
-#endif
+
+u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le_generic(crc, p, len, crc32table_le, CRCPOLY_LE);
+}
+EXPORT_SYMBOL(crc32_le);
+
+u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE);
+}
+EXPORT_SYMBOL(__crc32c_le);
 
 /**
  * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
@@ -155,317 +193,906 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
  * @p: pointer to buffer over which CRC is run
  * @len: length of buffer @p
  */
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len);
-
-#if CRC_BE_BITS == 1
-/*
- * In fact, the table-based code will work in this case, but it can be
- * simplified by inlining the table in ?: form.
- */
-
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
+                                          size_t len, const u32 (*tab)[256],
+                                          u32 polynomial)
 {
+#if CRC_BE_BITS == 1
         int i;
         while (len--) {
                 crc ^= *p++ << 24;
                 for (i = 0; i < 8; i++)
                         crc =
-                            (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE :
+                            (crc << 1) ^ ((crc & 0x80000000) ? polynomial :
                                           0);
         }
-        return crc;
-}
-
-#else                           /* Table-based approach */
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
-{
-# if CRC_BE_BITS == 8
-        const u32      (*tab)[] = crc32table_be;
-
-        crc = __cpu_to_be32(crc);
-        crc = crc32_body(crc, p, len, tab);
-        return __be32_to_cpu(crc);
+# elif CRC_BE_BITS == 2
+        while (len--) {
+                crc ^= *p++ << 24;
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+        }
 # elif CRC_BE_BITS == 4
         while (len--) {
                 crc ^= *p++ << 24;
-                crc = (crc << 4) ^ crc32table_be[crc >> 28];
-                crc = (crc << 4) ^ crc32table_be[crc >> 28];
+                crc = (crc << 4) ^ tab[0][crc >> 28];
+                crc = (crc << 4) ^ tab[0][crc >> 28];
         }
-        return crc;
-# elif CRC_BE_BITS == 2
+# elif CRC_BE_BITS == 8
         while (len--) {
                 crc ^= *p++ << 24;
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
+                crc = (crc << 8) ^ tab[0][crc >> 24];
         }
-        return crc;
+# else
+        crc = (__force u32) __cpu_to_be32(crc);
+        crc = crc32_body(crc, p, len, tab);
+        crc = __be32_to_cpu((__force __be32)crc);
 # endif
+        return crc;
 }
-#endif
 
-EXPORT_SYMBOL(crc32_le);
+u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_be_generic(crc, p, len, crc32table_be, CRCPOLY_BE);
+}
 EXPORT_SYMBOL(crc32_be);
 
-/*
- * A brief CRC tutorial.
- *
- * A CRC is a long-division remainder.  You add the CRC to the message,
- * and the whole thing (message+CRC) is a multiple of the given
- * CRC polynomial.  To check the CRC, you can either check that the
- * CRC matches the recomputed value, *or* you can check that the
- * remainder computed on the message+CRC is 0.  This latter approach
- * is used by a lot of hardware implementations, and is why so many
- * protocols put the end-of-frame flag after the CRC.
- *
- * It's actually the same long division you learned in school, except that
- * - We're working in binary, so the digits are only 0 and 1, and
- * - When dividing polynomials, there are no carries.  Rather than add and
- *   subtract, we just xor.  Thus, we tend to get a bit sloppy about
- *   the difference between adding and subtracting.
- *
- * A 32-bit CRC polynomial is actually 33 bits long.  But since it's
- * 33 bits long, bit 32 is always going to be set, so usually the CRC
- * is written in hex with the most significant bit omitted.  (If you're
- * familiar with the IEEE 754 floating-point format, it's the same idea.)
- *
- * Note that a CRC is computed over a string of *bits*, so you have
- * to decide on the endianness of the bits within each byte.  To get
- * the best error-detecting properties, this should correspond to the
- * order they're actually sent.  For example, standard RS-232 serial is
- * little-endian; the most significant bit (sometimes used for parity)
- * is sent last.  And when appending a CRC word to a message, you should
- * do it in the right order, matching the endianness.
- *
- * Just like with ordinary division, the remainder is always smaller than
- * the divisor (the CRC polynomial) you're dividing by.  Each step of the
- * division, you take one more digit (bit) of the dividend and append it
- * to the current remainder.  Then you figure out the appropriate multiple
- * of the divisor to subtract to being the remainder back into range.
- * In binary, it's easy - it has to be either 0 or 1, and to make the
- * XOR cancel, it's just a copy of bit 32 of the remainder.
- *
- * When computing a CRC, we don't care about the quotient, so we can
- * throw the quotient bit away, but subtract the appropriate multiple of
- * the polynomial from the remainder and we're back to where we started,
- * ready to process the next bit.
- *
- * A big-endian CRC written this way would be coded like:
- * for (i = 0; i < input_bits; i++) {
- *      multiple = remainder & 0x80000000 ? CRCPOLY : 0;
- *      remainder = (remainder << 1 | next_input_bit()) ^ multiple;
- * }
- * Notice how, to get at bit 32 of the shifted remainder, we look
- * at bit 31 of the remainder *before* shifting it.
- *
- * But also notice how the next_input_bit() bits we're shifting into
- * the remainder don't actually affect any decision-making until
- * 32 bits later.  Thus, the first 32 cycles of this are pretty boring.
- * Also, to add the CRC to a message, we need a 32-bit-long hole for it at
- * the end, so we have to add 32 extra cycles shifting in zeros at the
- * end of every message,
- *
- * So the standard trick is to rearrage merging in the next_input_bit()
- * until the moment it's needed.  Then the first 32 cycles can be precomputed,
- * and merging in the final 32 zero bits to make room for the CRC can be
- * skipped entirely.
- * This changes the code to:
- * for (i = 0; i < input_bits; i++) {
- *      remainder ^= next_input_bit() << 31;
- *      multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
- *      remainder = (remainder << 1) ^ multiple;
- * }
- * With this optimization, the little-endian code is simpler:
- * for (i = 0; i < input_bits; i++) {
- *      remainder ^= next_input_bit();
- *      multiple = (remainder & 1) ? CRCPOLY : 0;
- *      remainder = (remainder >> 1) ^ multiple;
- * }
- *
- * Note that the other details of endianness have been hidden in CRCPOLY
- * (which must be bit-reversed) and next_input_bit().
- *
- * However, as long as next_input_bit is returning the bits in a sensible
- * order, we can actually do the merging 8 or more bits at a time rather
- * than one bit at a time:
- * for (i = 0; i < input_bytes; i++) {
- *      remainder ^= next_input_byte() << 24;
- *      for (j = 0; j < 8; j++) {
- *              multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
- *              remainder = (remainder << 1) ^ multiple;
- *      }
- * }
- * Or in little-endian:
- * for (i = 0; i < input_bytes; i++) {
- *      remainder ^= next_input_byte();
- *      for (j = 0; j < 8; j++) {
- *              multiple = (remainder & 1) ? CRCPOLY : 0;
- *              remainder = (remainder << 1) ^ multiple;
- *      }
- * }
- * If the input is a multiple of 32 bits, you can even XOR in a 32-bit
- * word at a time and increase the inner loop count to 32.
- *
- * You can also mix and match the two loop styles, for example doing the
- * bulk of a message byte-at-a-time and adding bit-at-a-time processing
- * for any fractional bytes at the end.
- *
- * The only remaining optimization is to the byte-at-a-time table method.
- * Here, rather than just shifting one bit of the remainder to decide
- * in the correct multiple to subtract, we can shift a byte at a time.
- * This produces a 40-bit (rather than a 33-bit) intermediate remainder,
- * but again the multiple of the polynomial to subtract depends only on
- * the high bits, the high 8 bits in this case.  
- *
- * The multiple we need in that case is the low 32 bits of a 40-bit
- * value whose high 8 bits are given, and which is a multiple of the
- * generator polynomial.  This is simply the CRC-32 of the given
- * one-byte message.
- *
- * Two more details: normally, appending zero bits to a message which
- * is already a multiple of a polynomial produces a larger multiple of that
- * polynomial.  To enable a CRC to detect this condition, it's common to
- * invert the CRC before appending it.  This makes the remainder of the
- * message+crc come out not as zero, but some fixed non-zero value.
- *
- * The same problem applies to zero bits prepended to the message, and
- * a similar solution is used.  Instead of starting with a remainder of
- * 0, an initial remainder of all ones is used.  As long as you start
- * the same way on decoding, it doesn't make a difference.
- */
+#ifdef CONFIG_CRC32_SELFTEST
 
-#ifdef UNITTEST
-
-#include <stdlib.h>
-#include <stdio.h>
+/* 4096 random bytes */
+static u8 __attribute__((__aligned__(8))) test_buf[] =
+{
+        0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30,
+        0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4,
+        0xc9, 0x6e, 0x8b, 0xdb, 0x98, 0x6b, 0xaa, 0x60,
+        0xa8, 0xb5, 0xbc, 0x6c, 0xa9, 0xb1, 0x5b, 0x2c,
+        0xea, 0xb4, 0x92, 0x6a, 0x3f, 0x79, 0x91, 0xe4,
+        0xe9, 0x70, 0x51, 0x8c, 0x7f, 0x95, 0x6f, 0x1a,
+        0x56, 0xa1, 0x5c, 0x27, 0x03, 0x67, 0x9f, 0x3a,
+        0xe2, 0x31, 0x11, 0x29, 0x6b, 0x98, 0xfc, 0xc4,
+        0x53, 0x24, 0xc5, 0x8b, 0xce, 0x47, 0xb2, 0xb9,
+        0x32, 0xcb, 0xc1, 0xd0, 0x03, 0x57, 0x4e, 0xd4,
+        0xe9, 0x3c, 0xa1, 0x63, 0xcf, 0x12, 0x0e, 0xca,
+        0xe1, 0x13, 0xd1, 0x93, 0xa6, 0x88, 0x5c, 0x61,
+        0x5b, 0xbb, 0xf0, 0x19, 0x46, 0xb4, 0xcf, 0x9e,
+        0xb6, 0x6b, 0x4c, 0x3a, 0xcf, 0x60, 0xf9, 0x7a,
+        0x8d, 0x07, 0x63, 0xdb, 0x40, 0xe9, 0x0b, 0x6f,
+        0xad, 0x97, 0xf1, 0xed, 0xd0, 0x1e, 0x26, 0xfd,
+        0xbf, 0xb7, 0xc8, 0x04, 0x94, 0xf8, 0x8b, 0x8c,
+        0xf1, 0xab, 0x7a, 0xd4, 0xdd, 0xf3, 0xe8, 0x88,
+        0xc3, 0xed, 0x17, 0x8a, 0x9b, 0x40, 0x0d, 0x53,
+        0x62, 0x12, 0x03, 0x5f, 0x1b, 0x35, 0x32, 0x1f,
+        0xb4, 0x7b, 0x93, 0x78, 0x0d, 0xdb, 0xce, 0xa4,
+        0xc0, 0x47, 0xd5, 0xbf, 0x68, 0xe8, 0x5d, 0x74,
+        0x8f, 0x8e, 0x75, 0x1c, 0xb2, 0x4f, 0x9a, 0x60,
+        0xd1, 0xbe, 0x10, 0xf4, 0x5c, 0xa1, 0x53, 0x09,
+        0xa5, 0xe0, 0x09, 0x54, 0x85, 0x5c, 0xdc, 0x07,
+        0xe7, 0x21, 0x69, 0x7b, 0x8a, 0xfd, 0x90, 0xf1,
+        0x22, 0xd0, 0xb4, 0x36, 0x28, 0xe6, 0xb8, 0x0f,
+        0x39, 0xde, 0xc8, 0xf3, 0x86, 0x60, 0x34, 0xd2,
+        0x5e, 0xdf, 0xfd, 0xcf, 0x0f, 0xa9, 0x65, 0xf0,
+        0xd5, 0x4d, 0x96, 0x40, 0xe3, 0xdf, 0x3f, 0x95,
+        0x5a, 0x39, 0x19, 0x93, 0xf4, 0x75, 0xce, 0x22,
+        0x00, 0x1c, 0x93, 0xe2, 0x03, 0x66, 0xf4, 0x93,
+        0x73, 0x86, 0x81, 0x8e, 0x29, 0x44, 0x48, 0x86,
+        0x61, 0x7c, 0x48, 0xa3, 0x43, 0xd2, 0x9c, 0x8d,
+        0xd4, 0x95, 0xdd, 0xe1, 0x22, 0x89, 0x3a, 0x40,
+        0x4c, 0x1b, 0x8a, 0x04, 0xa8, 0x09, 0x69, 0x8b,
+        0xea, 0xc6, 0x55, 0x8e, 0x57, 0xe6, 0x64, 0x35,
+        0xf0, 0xc7, 0x16, 0x9f, 0x5d, 0x5e, 0x86, 0x40,
+        0x46, 0xbb, 0xe5, 0x45, 0x88, 0xfe, 0xc9, 0x63,
+        0x15, 0xfb, 0xf5, 0xbd, 0x71, 0x61, 0xeb, 0x7b,
+        0x78, 0x70, 0x07, 0x31, 0x03, 0x9f, 0xb2, 0xc8,
+        0xa7, 0xab, 0x47, 0xfd, 0xdf, 0xa0, 0x78, 0x72,
+        0xa4, 0x2a, 0xe4, 0xb6, 0xba, 0xc0, 0x1e, 0x86,
+        0x71, 0xe6, 0x3d, 0x18, 0x37, 0x70, 0xe6, 0xff,
+        0xe0, 0xbc, 0x0b, 0x22, 0xa0, 0x1f, 0xd3, 0xed,
+        0xa2, 0x55, 0x39, 0xab, 0xa8, 0x13, 0x73, 0x7c,
+        0x3f, 0xb2, 0xd6, 0x19, 0xac, 0xff, 0x99, 0xed,
+        0xe8, 0xe6, 0xa6, 0x22, 0xe3, 0x9c, 0xf1, 0x30,
+        0xdc, 0x01, 0x0a, 0x56, 0xfa, 0xe4, 0xc9, 0x99,
+        0xdd, 0xa8, 0xd8, 0xda, 0x35, 0x51, 0x73, 0xb4,
+        0x40, 0x86, 0x85, 0xdb, 0x5c, 0xd5, 0x85, 0x80,
+        0x14, 0x9c, 0xfd, 0x98, 0xa9, 0x82, 0xc5, 0x37,
+        0xff, 0x32, 0x5d, 0xd0, 0x0b, 0xfa, 0xdc, 0x04,
+        0x5e, 0x09, 0xd2, 0xca, 0x17, 0x4b, 0x1a, 0x8e,
+        0x15, 0xe1, 0xcc, 0x4e, 0x52, 0x88, 0x35, 0xbd,
+        0x48, 0xfe, 0x15, 0xa0, 0x91, 0xfd, 0x7e, 0x6c,
+        0x0e, 0x5d, 0x79, 0x1b, 0x81, 0x79, 0xd2, 0x09,
+        0x34, 0x70, 0x3d, 0x81, 0xec, 0xf6, 0x24, 0xbb,
+        0xfb, 0xf1, 0x7b, 0xdf, 0x54, 0xea, 0x80, 0x9b,
+        0xc7, 0x99, 0x9e, 0xbd, 0x16, 0x78, 0x12, 0x53,
+        0x5e, 0x01, 0xa7, 0x4e, 0xbd, 0x67, 0xe1, 0x9b,
+        0x4c, 0x0e, 0x61, 0x45, 0x97, 0xd2, 0xf0, 0x0f,
+        0xfe, 0x15, 0x08, 0xb7, 0x11, 0x4c, 0xe7, 0xff,
+        0x81, 0x53, 0xff, 0x91, 0x25, 0x38, 0x7e, 0x40,
+        0x94, 0xe5, 0xe0, 0xad, 0xe6, 0xd9, 0x79, 0xb6,
+        0x92, 0xc9, 0xfc, 0xde, 0xc3, 0x1a, 0x23, 0xbb,
+        0xdd, 0xc8, 0x51, 0x0c, 0x3a, 0x72, 0xfa, 0x73,
+        0x6f, 0xb7, 0xee, 0x61, 0x39, 0x03, 0x01, 0x3f,
+        0x7f, 0x94, 0x2e, 0x2e, 0xba, 0x3a, 0xbb, 0xb4,
+        0xfa, 0x6a, 0x17, 0xfe, 0xea, 0xef, 0x5e, 0x66,
+        0x97, 0x3f, 0x32, 0x3d, 0xd7, 0x3e, 0xb1, 0xf1,
+        0x6c, 0x14, 0x4c, 0xfd, 0x37, 0xd3, 0x38, 0x80,
+        0xfb, 0xde, 0xa6, 0x24, 0x1e, 0xc8, 0xca, 0x7f,
+        0x3a, 0x93, 0xd8, 0x8b, 0x18, 0x13, 0xb2, 0xe5,
+        0xe4, 0x93, 0x05, 0x53, 0x4f, 0x84, 0x66, 0xa7,
+        0x58, 0x5c, 0x7b, 0x86, 0x52, 0x6d, 0x0d, 0xce,
+        0xa4, 0x30, 0x7d, 0xb6, 0x18, 0x9f, 0xeb, 0xff,
+        0x22, 0xbb, 0x72, 0x29, 0xb9, 0x44, 0x0b, 0x48,
+        0x1e, 0x84, 0x71, 0x81, 0xe3, 0x6d, 0x73, 0x26,
+        0x92, 0xb4, 0x4d, 0x2a, 0x29, 0xb8, 0x1f, 0x72,
+        0xed, 0xd0, 0xe1, 0x64, 0x77, 0xea, 0x8e, 0x88,
+        0x0f, 0xef, 0x3f, 0xb1, 0x3b, 0xad, 0xf9, 0xc9,
+        0x8b, 0xd0, 0xac, 0xc6, 0xcc, 0xa9, 0x40, 0xcc,
+        0x76, 0xf6, 0x3b, 0x53, 0xb5, 0x88, 0xcb, 0xc8,
+        0x37, 0xf1, 0xa2, 0xba, 0x23, 0x15, 0x99, 0x09,
+        0xcc, 0xe7, 0x7a, 0x3b, 0x37, 0xf7, 0x58, 0xc8,
+        0x46, 0x8c, 0x2b, 0x2f, 0x4e, 0x0e, 0xa6, 0x5c,
+        0xea, 0x85, 0x55, 0xba, 0x02, 0x0e, 0x0e, 0x48,
+        0xbc, 0xe1, 0xb1, 0x01, 0x35, 0x79, 0x13, 0x3d,
+        0x1b, 0xc0, 0x53, 0x68, 0x11, 0xe7, 0x95, 0x0f,
+        0x9d, 0x3f, 0x4c, 0x47, 0x7b, 0x4d, 0x1c, 0xae,
+        0x50, 0x9b, 0xcb, 0xdd, 0x05, 0x8d, 0x9a, 0x97,
+        0xfd, 0x8c, 0xef, 0x0c, 0x1d, 0x67, 0x73, 0xa8,
+        0x28, 0x36, 0xd5, 0xb6, 0x92, 0x33, 0x40, 0x75,
+        0x0b, 0x51, 0xc3, 0x64, 0xba, 0x1d, 0xc2, 0xcc,
+        0xee, 0x7d, 0x54, 0x0f, 0x27, 0x69, 0xa7, 0x27,
+        0x63, 0x30, 0x29, 0xd9, 0xc8, 0x84, 0xd8, 0xdf,
+        0x9f, 0x68, 0x8d, 0x04, 0xca, 0xa6, 0xc5, 0xc7,
+        0x7a, 0x5c, 0xc8, 0xd1, 0xcb, 0x4a, 0xec, 0xd0,
+        0xd8, 0x20, 0x69, 0xc5, 0x17, 0xcd, 0x78, 0xc8,
+        0x75, 0x23, 0x30, 0x69, 0xc9, 0xd4, 0xea, 0x5c,
+        0x4f, 0x6b, 0x86, 0x3f, 0x8b, 0xfe, 0xee, 0x44,
+        0xc9, 0x7c, 0xb7, 0xdd, 0x3e, 0xe5, 0xec, 0x54,
+        0x03, 0x3e, 0xaa, 0x82, 0xc6, 0xdf, 0xb2, 0x38,
+        0x0e, 0x5d, 0xb3, 0x88, 0xd9, 0xd3, 0x69, 0x5f,
+        0x8f, 0x70, 0x8a, 0x7e, 0x11, 0xd9, 0x1e, 0x7b,
+        0x38, 0xf1, 0x42, 0x1a, 0xc0, 0x35, 0xf5, 0xc7,
+        0x36, 0x85, 0xf5, 0xf7, 0xb8, 0x7e, 0xc7, 0xef,
+        0x18, 0xf1, 0x63, 0xd6, 0x7a, 0xc6, 0xc9, 0x0e,
+        0x4d, 0x69, 0x4f, 0x84, 0xef, 0x26, 0x41, 0x0c,
+        0xec, 0xc7, 0xe0, 0x7e, 0x3c, 0x67, 0x01, 0x4c,
+        0x62, 0x1a, 0x20, 0x6f, 0xee, 0x47, 0x4d, 0xc0,
+        0x99, 0x13, 0x8d, 0x91, 0x4a, 0x26, 0xd4, 0x37,
+        0x28, 0x90, 0x58, 0x75, 0x66, 0x2b, 0x0a, 0xdf,
+        0xda, 0xee, 0x92, 0x25, 0x90, 0x62, 0x39, 0x9e,
+        0x44, 0x98, 0xad, 0xc1, 0x88, 0xed, 0xe4, 0xb4,
+        0xaf, 0xf5, 0x8c, 0x9b, 0x48, 0x4d, 0x56, 0x60,
+        0x97, 0x0f, 0x61, 0x59, 0x9e, 0xa6, 0x27, 0xfe,
+        0xc1, 0x91, 0x15, 0x38, 0xb8, 0x0f, 0xae, 0x61,
+        0x7d, 0x26, 0x13, 0x5a, 0x73, 0xff, 0x1c, 0xa3,
+        0x61, 0x04, 0x58, 0x48, 0x55, 0x44, 0x11, 0xfe,
+        0x15, 0xca, 0xc3, 0xbd, 0xca, 0xc5, 0xb4, 0x40,
+        0x5d, 0x1b, 0x7f, 0x39, 0xb5, 0x9c, 0x35, 0xec,
+        0x61, 0x15, 0x32, 0x32, 0xb8, 0x4e, 0x40, 0x9f,
+        0x17, 0x1f, 0x0a, 0x4d, 0xa9, 0x91, 0xef, 0xb7,
+        0xb0, 0xeb, 0xc2, 0x83, 0x9a, 0x6c, 0xd2, 0x79,
+        0x43, 0x78, 0x5e, 0x2f, 0xe5, 0xdd, 0x1a, 0x3c,
+        0x45, 0xab, 0x29, 0x40, 0x3a, 0x37, 0x5b, 0x6f,
+        0xd7, 0xfc, 0x48, 0x64, 0x3c, 0x49, 0xfb, 0x21,
+        0xbe, 0xc3, 0xff, 0x07, 0xfb, 0x17, 0xe9, 0xc9,
+        0x0c, 0x4c, 0x5c, 0x15, 0x9e, 0x8e, 0x22, 0x30,
+        0x0a, 0xde, 0x48, 0x7f, 0xdb, 0x0d, 0xd1, 0x2b,
+        0x87, 0x38, 0x9e, 0xcc, 0x5a, 0x01, 0x16, 0xee,
+        0x75, 0x49, 0x0d, 0x30, 0x01, 0x34, 0x6a, 0xb6,
+        0x9a, 0x5a, 0x2a, 0xec, 0xbb, 0x48, 0xac, 0xd3,
+        0x77, 0x83, 0xd8, 0x08, 0x86, 0x4f, 0x48, 0x09,
+        0x29, 0x41, 0x79, 0xa1, 0x03, 0x12, 0xc4, 0xcd,
+        0x90, 0x55, 0x47, 0x66, 0x74, 0x9a, 0xcc, 0x4f,
+        0x35, 0x8c, 0xd6, 0x98, 0xef, 0xeb, 0x45, 0xb9,
+        0x9a, 0x26, 0x2f, 0x39, 0xa5, 0x70, 0x6d, 0xfc,
+        0xb4, 0x51, 0xee, 0xf4, 0x9c, 0xe7, 0x38, 0x59,
+        0xad, 0xf4, 0xbc, 0x46, 0xff, 0x46, 0x8e, 0x60,
+        0x9c, 0xa3, 0x60, 0x1d, 0xf8, 0x26, 0x72, 0xf5,
+        0x72, 0x9d, 0x68, 0x80, 0x04, 0xf6, 0x0b, 0xa1,
+        0x0a, 0xd5, 0xa7, 0x82, 0x3a, 0x3e, 0x47, 0xa8,
+        0x5a, 0xde, 0x59, 0x4f, 0x7b, 0x07, 0xb3, 0xe9,
+        0x24, 0x19, 0x3d, 0x34, 0x05, 0xec, 0xf1, 0xab,
+        0x6e, 0x64, 0x8f, 0xd3, 0xe6, 0x41, 0x86, 0x80,
+        0x70, 0xe3, 0x8d, 0x60, 0x9c, 0x34, 0x25, 0x01,
+        0x07, 0x4d, 0x19, 0x41, 0x4e, 0x3d, 0x5c, 0x7e,
+        0xa8, 0xf5, 0xcc, 0xd5, 0x7b, 0xe2, 0x7d, 0x3d,
+        0x49, 0x86, 0x7d, 0x07, 0xb7, 0x10, 0xe3, 0x35,
+        0xb8, 0x84, 0x6d, 0x76, 0xab, 0x17, 0xc6, 0x38,
+        0xb4, 0xd3, 0x28, 0x57, 0xad, 0xd3, 0x88, 0x5a,
+        0xda, 0xea, 0xc8, 0x94, 0xcc, 0x37, 0x19, 0xac,
+        0x9c, 0x9f, 0x4b, 0x00, 0x15, 0xc0, 0xc8, 0xca,
+        0x1f, 0x15, 0xaa, 0xe0, 0xdb, 0xf9, 0x2f, 0x57,
+        0x1b, 0x24, 0xc7, 0x6f, 0x76, 0x29, 0xfb, 0xed,
+        0x25, 0x0d, 0xc0, 0xfe, 0xbd, 0x5a, 0xbf, 0x20,
+        0x08, 0x51, 0x05, 0xec, 0x71, 0xa3, 0xbf, 0xef,
+        0x5e, 0x99, 0x75, 0xdb, 0x3c, 0x5f, 0x9a, 0x8c,
+        0xbb, 0x19, 0x5c, 0x0e, 0x93, 0x19, 0xf8, 0x6a,
+        0xbc, 0xf2, 0x12, 0x54, 0x2f, 0xcb, 0x28, 0x64,
+        0x88, 0xb3, 0x92, 0x0d, 0x96, 0xd1, 0xa6, 0xe4,
+        0x1f, 0xf1, 0x4d, 0xa4, 0xab, 0x1c, 0xee, 0x54,
+        0xf2, 0xad, 0x29, 0x6d, 0x32, 0x37, 0xb2, 0x16,
+        0x77, 0x5c, 0xdc, 0x2e, 0x54, 0xec, 0x75, 0x26,
+        0xc6, 0x36, 0xd9, 0x17, 0x2c, 0xf1, 0x7a, 0xdc,
+        0x4b, 0xf1, 0xe2, 0xd9, 0x95, 0xba, 0xac, 0x87,
+        0xc1, 0xf3, 0x8e, 0x58, 0x08, 0xd8, 0x87, 0x60,
+        0xc9, 0xee, 0x6a, 0xde, 0xa4, 0xd2, 0xfc, 0x0d,
+        0xe5, 0x36, 0xc4, 0x5c, 0x52, 0xb3, 0x07, 0x54,
+        0x65, 0x24, 0xc1, 0xb1, 0xd1, 0xb1, 0x53, 0x13,
+        0x31, 0x79, 0x7f, 0x05, 0x76, 0xeb, 0x37, 0x59,
+        0x15, 0x2b, 0xd1, 0x3f, 0xac, 0x08, 0x97, 0xeb,
+        0x91, 0x98, 0xdf, 0x6c, 0x09, 0x0d, 0x04, 0x9f,
+        0xdc, 0x3b, 0x0e, 0x60, 0x68, 0x47, 0x23, 0x15,
+        0x16, 0xc6, 0x0b, 0x35, 0xf8, 0x77, 0xa2, 0x78,
+        0x50, 0xd4, 0x64, 0x22, 0x33, 0xff, 0xfb, 0x93,
+        0x71, 0x46, 0x50, 0x39, 0x1b, 0x9c, 0xea, 0x4e,
+        0x8d, 0x0c, 0x37, 0xe5, 0x5c, 0x51, 0x3a, 0x31,
+        0xb2, 0x85, 0x84, 0x3f, 0x41, 0xee, 0xa2, 0xc1,
+        0xc6, 0x13, 0x3b, 0x54, 0x28, 0xd2, 0x18, 0x37,
+        0xcc, 0x46, 0x9f, 0x6a, 0x91, 0x3d, 0x5a, 0x15,
+        0x3c, 0x89, 0xa3, 0x61, 0x06, 0x7d, 0x2e, 0x78,
+        0xbe, 0x7d, 0x40, 0xba, 0x2f, 0x95, 0xb1, 0x2f,
+        0x87, 0x3b, 0x8a, 0xbe, 0x6a, 0xf4, 0xc2, 0x31,
+        0x74, 0xee, 0x91, 0xe0, 0x23, 0xaa, 0x5d, 0x7f,
+        0xdd, 0xf0, 0x44, 0x8c, 0x0b, 0x59, 0x2b, 0xfc,
+        0x48, 0x3a, 0xdf, 0x07, 0x05, 0x38, 0x6c, 0xc9,
+        0xeb, 0x18, 0x24, 0x68, 0x8d, 0x58, 0x98, 0xd3,
+        0x31, 0xa3, 0xe4, 0x70, 0x59, 0xb1, 0x21, 0xbe,
+        0x7e, 0x65, 0x7d, 0xb8, 0x04, 0xab, 0xf6, 0xe4,
+        0xd7, 0xda, 0xec, 0x09, 0x8f, 0xda, 0x6d, 0x24,
+        0x07, 0xcc, 0x29, 0x17, 0x05, 0x78, 0x1a, 0xc1,
+        0xb1, 0xce, 0xfc, 0xaa, 0x2d, 0xe7, 0xcc, 0x85,
+        0x84, 0x84, 0x03, 0x2a, 0x0c, 0x3f, 0xa9, 0xf8,
+        0xfd, 0x84, 0x53, 0x59, 0x5c, 0xf0, 0xd4, 0x09,
+        0xf0, 0xd2, 0x6c, 0x32, 0x03, 0xb0, 0xa0, 0x8c,
+        0x52, 0xeb, 0x23, 0x91, 0x88, 0x43, 0x13, 0x46,
+        0xf6, 0x1e, 0xb4, 0x1b, 0xf5, 0x8e, 0x3a, 0xb5,
+        0x3d, 0x00, 0xf6, 0xe5, 0x08, 0x3d, 0x5f, 0x39,
+        0xd3, 0x21, 0x69, 0xbc, 0x03, 0x22, 0x3a, 0xd2,
+        0x5c, 0x84, 0xf8, 0x15, 0xc4, 0x80, 0x0b, 0xbc,
+        0x29, 0x3c, 0xf3, 0x95, 0x98, 0xcd, 0x8f, 0x35,
+        0xbc, 0xa5, 0x3e, 0xfc, 0xd4, 0x13, 0x9e, 0xde,
+        0x4f, 0xce, 0x71, 0x9d, 0x09, 0xad, 0xf2, 0x80,
+        0x6b, 0x65, 0x7f, 0x03, 0x00, 0x14, 0x7c, 0x15,
+        0x85, 0x40, 0x6d, 0x70, 0xea, 0xdc, 0xb3, 0x63,
+        0x35, 0x4f, 0x4d, 0xe0, 0xd9, 0xd5, 0x3c, 0x58,
+        0x56, 0x23, 0x80, 0xe2, 0x36, 0xdd, 0x75, 0x1d,
+        0x94, 0x11, 0x41, 0x8e, 0xe0, 0x81, 0x8e, 0xcf,
+        0xe0, 0xe5, 0xf6, 0xde, 0xd1, 0xe7, 0x04, 0x12,
+        0x79, 0x92, 0x2b, 0x71, 0x2a, 0x79, 0x8b, 0x7c,
+        0x44, 0x79, 0x16, 0x30, 0x4e, 0xf4, 0xf6, 0x9b,
+        0xb7, 0x40, 0xa3, 0x5a, 0xa7, 0x69, 0x3e, 0xc1,
+        0x3a, 0x04, 0xd0, 0x88, 0xa0, 0x3b, 0xdd, 0xc6,
+        0x9e, 0x7e, 0x1e, 0x1e, 0x8f, 0x44, 0xf7, 0x73,
+        0x67, 0x1e, 0x1a, 0x78, 0xfa, 0x62, 0xf4, 0xa9,
+        0xa8, 0xc6, 0x5b, 0xb8, 0xfa, 0x06, 0x7d, 0x5e,
+        0x38, 0x1c, 0x9a, 0x39, 0xe9, 0x39, 0x98, 0x22,
+        0x0b, 0xa7, 0xac, 0x0b, 0xf3, 0xbc, 0xf1, 0xeb,
+        0x8c, 0x81, 0xe3, 0x48, 0x8a, 0xed, 0x42, 0xc2,
+        0x38, 0xcf, 0x3e, 0xda, 0xd2, 0x89, 0x8d, 0x9c,
+        0x53, 0xb5, 0x2f, 0x41, 0x01, 0x26, 0x84, 0x9c,
+        0xa3, 0x56, 0xf6, 0x49, 0xc7, 0xd4, 0x9f, 0x93,
+        0x1b, 0x96, 0x49, 0x5e, 0xad, 0xb3, 0x84, 0x1f,
+        0x3c, 0xa4, 0xe0, 0x9b, 0xd1, 0x90, 0xbc, 0x38,
+        0x6c, 0xdd, 0x95, 0x4d, 0x9d, 0xb1, 0x71, 0x57,
+        0x2d, 0x34, 0xe8, 0xb8, 0x42, 0xc7, 0x99, 0x03,
+        0xc7, 0x07, 0x30, 0x65, 0x91, 0x55, 0xd5, 0x90,
+        0x70, 0x97, 0x37, 0x68, 0xd4, 0x11, 0xf9, 0xe8,
+        0xce, 0xec, 0xdc, 0x34, 0xd5, 0xd3, 0xb7, 0xc4,
+        0xb8, 0x97, 0x05, 0x92, 0xad, 0xf8, 0xe2, 0x36,
+        0x64, 0x41, 0xc9, 0xc5, 0x41, 0x77, 0x52, 0xd7,
+        0x2c, 0xa5, 0x24, 0x2f, 0xd9, 0x34, 0x0b, 0x47,
+        0x35, 0xa7, 0x28, 0x8b, 0xc5, 0xcd, 0xe9, 0x46,
+        0xac, 0x39, 0x94, 0x3c, 0x10, 0xc6, 0x29, 0x73,
+        0x0e, 0x0e, 0x5d, 0xe0, 0x71, 0x03, 0x8a, 0x72,
+        0x0e, 0x26, 0xb0, 0x7d, 0x84, 0xed, 0x95, 0x23,
+        0x49, 0x5a, 0x45, 0x83, 0x45, 0x60, 0x11, 0x4a,
+        0x46, 0x31, 0xd4, 0xd8, 0x16, 0x54, 0x98, 0x58,
+        0xed, 0x6d, 0xcc, 0x5d, 0xd6, 0x50, 0x61, 0x9f,
+        0x9d, 0xc5, 0x3e, 0x9d, 0x32, 0x47, 0xde, 0x96,
+        0xe1, 0x5d, 0xd8, 0xf8, 0xb4, 0x69, 0x6f, 0xb9,
+        0x15, 0x90, 0x57, 0x7a, 0xf6, 0xad, 0xb0, 0x5b,
+        0xf5, 0xa6, 0x36, 0x94, 0xfd, 0x84, 0xce, 0x1c,
+        0x0f, 0x4b, 0xd0, 0xc2, 0x5b, 0x6b, 0x56, 0xef,
+        0x73, 0x93, 0x0b, 0xc3, 0xee, 0xd9, 0xcf, 0xd3,
+        0xa4, 0x22, 0x58, 0xcd, 0x50, 0x6e, 0x65, 0xf4,
+        0xe9, 0xb7, 0x71, 0xaf, 0x4b, 0xb3, 0xb6, 0x2f,
+        0x0f, 0x0e, 0x3b, 0xc9, 0x85, 0x14, 0xf5, 0x17,
+        0xe8, 0x7a, 0x3a, 0xbf, 0x5f, 0x5e, 0xf8, 0x18,
+        0x48, 0xa6, 0x72, 0xab, 0x06, 0x95, 0xe9, 0xc8,
+        0xa7, 0xf4, 0x32, 0x44, 0x04, 0x0c, 0x84, 0x98,
+        0x73, 0xe3, 0x89, 0x8d, 0x5f, 0x7e, 0x4a, 0x42,
+        0x8f, 0xc5, 0x28, 0xb1, 0x82, 0xef, 0x1c, 0x97,
+        0x31, 0x3b, 0x4d, 0xe0, 0x0e, 0x10, 0x10, 0x97,
+        0x93, 0x49, 0x78, 0x2f, 0x0d, 0x86, 0x8b, 0xa1,
+        0x53, 0xa9, 0x81, 0x20, 0x79, 0xe7, 0x07, 0x77,
+        0xb6, 0xac, 0x5e, 0xd2, 0x05, 0xcd, 0xe9, 0xdb,
+        0x8a, 0x94, 0x82, 0x8a, 0x23, 0xb9, 0x3d, 0x1c,
+        0xa9, 0x7d, 0x72, 0x4a, 0xed, 0x33, 0xa3, 0xdb,
+        0x21, 0xa7, 0x86, 0x33, 0x45, 0xa5, 0xaa, 0x56,
+        0x45, 0xb5, 0x83, 0x29, 0x40, 0x47, 0x79, 0x04,
+        0x6e, 0xb9, 0x95, 0xd0, 0x81, 0x77, 0x2d, 0x48,
+        0x1e, 0xfe, 0xc3, 0xc2, 0x1e, 0xe5, 0xf2, 0xbe,
+        0xfd, 0x3b, 0x94, 0x9f, 0xc4, 0xc4, 0x26, 0x9d,
+        0xe4, 0x66, 0x1e, 0x19, 0xee, 0x6c, 0x79, 0x97,
+        0x11, 0x31, 0x4b, 0x0d, 0x01, 0xcb, 0xde, 0xa8,
+        0xf6, 0x6d, 0x7c, 0x39, 0x46, 0x4e, 0x7e, 0x3f,
+        0x94, 0x17, 0xdf, 0xa1, 0x7d, 0xd9, 0x1c, 0x8e,
+        0xbc, 0x7d, 0x33, 0x7d, 0xe3, 0x12, 0x40, 0xca,
+        0xab, 0x37, 0x11, 0x46, 0xd4, 0xae, 0xef, 0x44,
+        0xa2, 0xb3, 0x6a, 0x66, 0x0e, 0x0c, 0x90, 0x7f,
+        0xdf, 0x5c, 0x66, 0x5f, 0xf2, 0x94, 0x9f, 0xa6,
+        0x73, 0x4f, 0xeb, 0x0d, 0xad, 0xbf, 0xc0, 0x63,
+        0x5c, 0xdc, 0x46, 0x51, 0xe8, 0x8e, 0x90, 0x19,
+        0xa8, 0xa4, 0x3c, 0x91, 0x79, 0xfa, 0x7e, 0x58,
+        0x85, 0x13, 0x55, 0xc5, 0x19, 0x82, 0x37, 0x1b,
+        0x0a, 0x02, 0x1f, 0x99, 0x6b, 0x18, 0xf1, 0x28,
+        0x08, 0xa2, 0x73, 0xb8, 0x0f, 0x2e, 0xcd, 0xbf,
+        0xf3, 0x86, 0x7f, 0xea, 0xef, 0xd0, 0xbb, 0xa6,
+        0x21, 0xdf, 0x49, 0x73, 0x51, 0xcc, 0x36, 0xd3,
+        0x3e, 0xa0, 0xf8, 0x44, 0xdf, 0xd3, 0xa6, 0xbe,
+        0x8a, 0xd4, 0x57, 0xdd, 0x72, 0x94, 0x61, 0x0f,
+        0x82, 0xd1, 0x07, 0xb8, 0x7c, 0x18, 0x83, 0xdf,
+        0x3a, 0xe5, 0x50, 0x6a, 0x82, 0x20, 0xac, 0xa9,
+        0xa8, 0xff, 0xd9, 0xf3, 0x77, 0x33, 0x5a, 0x9e,
+        0x7f, 0x6d, 0xfe, 0x5d, 0x33, 0x41, 0x42, 0xe7,
+        0x6c, 0x19, 0xe0, 0x44, 0x8a, 0x15, 0xf6, 0x70,
+        0x98, 0xb7, 0x68, 0x4d, 0xfa, 0x97, 0x39, 0xb0,
+        0x8e, 0xe8, 0x84, 0x8b, 0x75, 0x30, 0xb7, 0x7d,
+        0x92, 0x69, 0x20, 0x9c, 0x81, 0xfb, 0x4b, 0xf4,
+        0x01, 0x50, 0xeb, 0xce, 0x0c, 0x1c, 0x6c, 0xb5,
+        0x4a, 0xd7, 0x27, 0x0c, 0xce, 0xbb, 0xe5, 0x85,
+        0xf0, 0xb6, 0xee, 0xd5, 0x70, 0xdd, 0x3b, 0xfc,
+        0xd4, 0x99, 0xf1, 0x33, 0xdd, 0x8b, 0xc4, 0x2f,
+        0xae, 0xab, 0x74, 0x96, 0x32, 0xc7, 0x4c, 0x56,
+        0x3c, 0x89, 0x0f, 0x96, 0x0b, 0x42, 0xc0, 0xcb,
+        0xee, 0x0f, 0x0b, 0x8c, 0xfb, 0x7e, 0x47, 0x7b,
+        0x64, 0x48, 0xfd, 0xb2, 0x00, 0x80, 0x89, 0xa5,
+        0x13, 0x55, 0x62, 0xfc, 0x8f, 0xe2, 0x42, 0x03,
+        0xb7, 0x4e, 0x2a, 0x79, 0xb4, 0x82, 0xea, 0x23,
+        0x49, 0xda, 0xaf, 0x52, 0x63, 0x1e, 0x60, 0x03,
+        0x89, 0x06, 0x44, 0x46, 0x08, 0xc3, 0xc4, 0x87,
+        0x70, 0x2e, 0xda, 0x94, 0xad, 0x6b, 0xe0, 0xe4,
+        0xd1, 0x8a, 0x06, 0xc2, 0xa8, 0xc0, 0xa7, 0x43,
+        0x3c, 0x47, 0x52, 0x0e, 0xc3, 0x77, 0x81, 0x11,
+        0x67, 0x0e, 0xa0, 0x70, 0x04, 0x47, 0x29, 0x40,
+        0x86, 0x0d, 0x34, 0x56, 0xa7, 0xc9, 0x35, 0x59,
+        0x68, 0xdc, 0x93, 0x81, 0x70, 0xee, 0x86, 0xd9,
+        0x80, 0x06, 0x40, 0x4f, 0x1a, 0x0d, 0x40, 0x30,
+        0x0b, 0xcb, 0x96, 0x47, 0xc1, 0xb7, 0x52, 0xfd,
+        0x56, 0xe0, 0x72, 0x4b, 0xfb, 0xbd, 0x92, 0x45,
+        0x61, 0x71, 0xc2, 0x33, 0x11, 0xbf, 0x52, 0x83,
+        0x79, 0x26, 0xe0, 0x49, 0x6b, 0xb7, 0x05, 0x8b,
+        0xe8, 0x0e, 0x87, 0x31, 0xd7, 0x9d, 0x8a, 0xf5,
+        0xc0, 0x5f, 0x2e, 0x58, 0x4a, 0xdb, 0x11, 0xb3,
+        0x6c, 0x30, 0x2a, 0x46, 0x19, 0xe3, 0x27, 0x84,
+        0x1f, 0x63, 0x6e, 0xf6, 0x57, 0xc7, 0xc9, 0xd8,
+        0x5e, 0xba, 0xb3, 0x87, 0xd5, 0x83, 0x26, 0x34,
+        0x21, 0x9e, 0x65, 0xde, 0x42, 0xd3, 0xbe, 0x7b,
+        0xbc, 0x91, 0x71, 0x44, 0x4d, 0x99, 0x3b, 0x31,
+        0xe5, 0x3f, 0x11, 0x4e, 0x7f, 0x13, 0x51, 0x3b,
+        0xae, 0x79, 0xc9, 0xd3, 0x81, 0x8e, 0x25, 0x40,
+        0x10, 0xfc, 0x07, 0x1e, 0xf9, 0x7b, 0x9a, 0x4b,
+        0x6c, 0xe3, 0xb3, 0xad, 0x1a, 0x0a, 0xdd, 0x9e,
+        0x59, 0x0c, 0xa2, 0xcd, 0xae, 0x48, 0x4a, 0x38,
+        0x5b, 0x47, 0x41, 0x94, 0x65, 0x6b, 0xbb, 0xeb,
+        0x5b, 0xe3, 0xaf, 0x07, 0x5b, 0xd4, 0x4a, 0xa2,
+        0xc9, 0x5d, 0x2f, 0x64, 0x03, 0xd7, 0x3a, 0x2c,
+        0x6e, 0xce, 0x76, 0x95, 0xb4, 0xb3, 0xc0, 0xf1,
+        0xe2, 0x45, 0x73, 0x7a, 0x5c, 0xab, 0xc1, 0xfc,
+        0x02, 0x8d, 0x81, 0x29, 0xb3, 0xac, 0x07, 0xec,
+        0x40, 0x7d, 0x45, 0xd9, 0x7a, 0x59, 0xee, 0x34,
+        0xf0, 0xe9, 0xd5, 0x7b, 0x96, 0xb1, 0x3d, 0x95,
+        0xcc, 0x86, 0xb5, 0xb6, 0x04, 0x2d, 0xb5, 0x92,
+        0x7e, 0x76, 0xf4, 0x06, 0xa9, 0xa3, 0x12, 0x0f,
+        0xb1, 0xaf, 0x26, 0xba, 0x7c, 0xfc, 0x7e, 0x1c,
+        0xbc, 0x2c, 0x49, 0x97, 0x53, 0x60, 0x13, 0x0b,
+        0xa6, 0x61, 0x83, 0x89, 0x42, 0xd4, 0x17, 0x0c,
+        0x6c, 0x26, 0x52, 0xc3, 0xb3, 0xd4, 0x67, 0xf5,
+        0xe3, 0x04, 0xb7, 0xf4, 0xcb, 0x80, 0xb8, 0xcb,
+        0x77, 0x56, 0x3e, 0xaa, 0x57, 0x54, 0xee, 0xb4,
+        0x2c, 0x67, 0xcf, 0xf2, 0xdc, 0xbe, 0x55, 0xf9,
+        0x43, 0x1f, 0x6e, 0x22, 0x97, 0x67, 0x7f, 0xc4,
+        0xef, 0xb1, 0x26, 0x31, 0x1e, 0x27, 0xdf, 0x41,
+        0x80, 0x47, 0x6c, 0xe2, 0xfa, 0xa9, 0x8c, 0x2a,
+        0xf6, 0xf2, 0xab, 0xf0, 0x15, 0xda, 0x6c, 0xc8,
+        0xfe, 0xb5, 0x23, 0xde, 0xa9, 0x05, 0x3f, 0x06,
+        0x54, 0x4c, 0xcd, 0xe1, 0xab, 0xfc, 0x0e, 0x62,
+        0x33, 0x31, 0x73, 0x2c, 0x76, 0xcb, 0xb4, 0x47,
+        0x1e, 0x20, 0xad, 0xd8, 0xf2, 0x31, 0xdd, 0xc4,
+        0x8b, 0x0c, 0x77, 0xbe, 0xe1, 0x8b, 0x26, 0x00,
+        0x02, 0x58, 0xd6, 0x8d, 0xef, 0xad, 0x74, 0x67,
+        0xab, 0x3f, 0xef, 0xcb, 0x6f, 0xb0, 0xcc, 0x81,
+        0x44, 0x4c, 0xaf, 0xe9, 0x49, 0x4f, 0xdb, 0xa0,
+        0x25, 0xa4, 0xf0, 0x89, 0xf1, 0xbe, 0xd8, 0x10,
+        0xff, 0xb1, 0x3b, 0x4b, 0xfa, 0x98, 0xf5, 0x79,
+        0x6d, 0x1e, 0x69, 0x4d, 0x57, 0xb1, 0xc8, 0x19,
+        0x1b, 0xbd, 0x1e, 0x8c, 0x84, 0xb7, 0x7b, 0xe8,
+        0xd2, 0x2d, 0x09, 0x41, 0x41, 0x37, 0x3d, 0xb1,
+        0x6f, 0x26, 0x5d, 0x71, 0x16, 0x3d, 0xb7, 0x83,
+        0x27, 0x2c, 0xa7, 0xb6, 0x50, 0xbd, 0x91, 0x86,
+        0xab, 0x24, 0xa1, 0x38, 0xfd, 0xea, 0x71, 0x55,
+        0x7e, 0x9a, 0x07, 0x77, 0x4b, 0xfa, 0x61, 0x66,
+        0x20, 0x1e, 0x28, 0x95, 0x18, 0x1b, 0xa4, 0xa0,
+        0xfd, 0xc0, 0x89, 0x72, 0x43, 0xd9, 0x3b, 0x49,
+        0x5a, 0x3f, 0x9d, 0xbf, 0xdb, 0xb4, 0x46, 0xea,
+        0x42, 0x01, 0x77, 0x23, 0x68, 0x95, 0xb6, 0x24,
+        0xb3, 0xa8, 0x6c, 0x28, 0x3b, 0x11, 0x40, 0x7e,
+        0x18, 0x65, 0x6d, 0xd8, 0x24, 0x42, 0x7d, 0x88,
+        0xc0, 0x52, 0xd9, 0x05, 0xe4, 0x95, 0x90, 0x87,
+        0x8c, 0xf4, 0xd0, 0x6b, 0xb9, 0x83, 0x99, 0x34,
+        0x6d, 0xfe, 0x54, 0x40, 0x94, 0x52, 0x21, 0x4f,
+        0x14, 0x25, 0xc5, 0xd6, 0x5e, 0x95, 0xdc, 0x0a,
+        0x2b, 0x89, 0x20, 0x11, 0x84, 0x48, 0xd6, 0x3a,
+        0xcd, 0x5c, 0x24, 0xad, 0x62, 0xe3, 0xb1, 0x93,
+        0x25, 0x8d, 0xcd, 0x7e, 0xfc, 0x27, 0xa3, 0x37,
+        0xfd, 0x84, 0xfc, 0x1b, 0xb2, 0xf1, 0x27, 0x38,
+        0x5a, 0xb7, 0xfc, 0xf2, 0xfa, 0x95, 0x66, 0xd4,
+        0xfb, 0xba, 0xa7, 0xd7, 0xa3, 0x72, 0x69, 0x48,
+        0x48, 0x8c, 0xeb, 0x28, 0x89, 0xfe, 0x33, 0x65,
+        0x5a, 0x36, 0x01, 0x7e, 0x06, 0x79, 0x0a, 0x09,
+        0x3b, 0x74, 0x11, 0x9a, 0x6e, 0xbf, 0xd4, 0x9e,
+        0x58, 0x90, 0x49, 0x4f, 0x4d, 0x08, 0xd4, 0xe5,
+        0x4a, 0x09, 0x21, 0xef, 0x8b, 0xb8, 0x74, 0x3b,
+        0x91, 0xdd, 0x36, 0x85, 0x60, 0x2d, 0xfa, 0xd4,
+        0x45, 0x7b, 0x45, 0x53, 0xf5, 0x47, 0x87, 0x7e,
+        0xa6, 0x37, 0xc8, 0x78, 0x7a, 0x68, 0x9d, 0x8d,
+        0x65, 0x2c, 0x0e, 0x91, 0x5c, 0xa2, 0x60, 0xf0,
+        0x8e, 0x3f, 0xe9, 0x1a, 0xcd, 0xaa, 0xe7, 0xd5,
+        0x77, 0x18, 0xaf, 0xc9, 0xbc, 0x18, 0xea, 0x48,
+        0x1b, 0xfb, 0x22, 0x48, 0x70, 0x16, 0x29, 0x9e,
+        0x5b, 0xc1, 0x2c, 0x66, 0x23, 0xbc, 0xf0, 0x1f,
+        0xef, 0xaf, 0xe4, 0xd6, 0x04, 0x19, 0x82, 0x7a,
+        0x0b, 0xba, 0x4b, 0x46, 0xb1, 0x6a, 0x85, 0x5d,
+        0xb4, 0x73, 0xd6, 0x21, 0xa1, 0x71, 0x60, 0x14,
+        0xee, 0x0a, 0x77, 0xc4, 0x66, 0x2e, 0xf9, 0x69,
+        0x30, 0xaf, 0x41, 0x0b, 0xc8, 0x83, 0x3c, 0x53,
+        0x99, 0x19, 0x27, 0x46, 0xf7, 0x41, 0x6e, 0x56,
+        0xdc, 0x94, 0x28, 0x67, 0x4e, 0xb7, 0x25, 0x48,
+        0x8a, 0xc2, 0xe0, 0x60, 0x96, 0xcc, 0x18, 0xf4,
+        0x84, 0xdd, 0xa7, 0x5e, 0x3e, 0x05, 0x0b, 0x26,
+        0x26, 0xb2, 0x5c, 0x1f, 0x57, 0x1a, 0x04, 0x7e,
+        0x6a, 0xe3, 0x2f, 0xb4, 0x35, 0xb6, 0x38, 0x40,
+        0x40, 0xcd, 0x6f, 0x87, 0x2e, 0xef, 0xa3, 0xd7,
+        0xa9, 0xc2, 0xe8, 0x0d, 0x27, 0xdf, 0x44, 0x62,
+        0x99, 0xa0, 0xfc, 0xcf, 0x81, 0x78, 0xcb, 0xfe,
+        0xe5, 0xa0, 0x03, 0x4e, 0x6c, 0xd7, 0xf4, 0xaf,
+        0x7a, 0xbb, 0x61, 0x82, 0xfe, 0x71, 0x89, 0xb2,
+        0x22, 0x7c, 0x8e, 0x83, 0x04, 0xce, 0xf6, 0x5d,
+        0x84, 0x8f, 0x95, 0x6a, 0x7f, 0xad, 0xfd, 0x32,
+        0x9c, 0x5e, 0xe4, 0x9c, 0x89, 0x60, 0x54, 0xaa,
+        0x96, 0x72, 0xd2, 0xd7, 0x36, 0x85, 0xa9, 0x45,
+        0xd2, 0x2a, 0xa1, 0x81, 0x49, 0x6f, 0x7e, 0x04,
+        0xfa, 0xe2, 0xfe, 0x90, 0x26, 0x77, 0x5a, 0x33,
+        0xb8, 0x04, 0x9a, 0x7a, 0xe6, 0x4c, 0x4f, 0xad,
+        0x72, 0x96, 0x08, 0x28, 0x58, 0x13, 0xf8, 0xc4,
+        0x1c, 0xf0, 0xc3, 0x45, 0x95, 0x49, 0x20, 0x8c,
+        0x9f, 0x39, 0x70, 0xe1, 0x77, 0xfe, 0xd5, 0x4b,
+        0xaf, 0x86, 0xda, 0xef, 0x22, 0x06, 0x83, 0x36,
+        0x29, 0x12, 0x11, 0x40, 0xbc, 0x3b, 0x86, 0xaa,
+        0xaa, 0x65, 0x60, 0xc3, 0x80, 0xca, 0xed, 0xa9,
+        0xf3, 0xb0, 0x79, 0x96, 0xa2, 0x55, 0x27, 0x28,
+        0x55, 0x73, 0x26, 0xa5, 0x50, 0xea, 0x92, 0x4b,
+        0x3c, 0x5c, 0x82, 0x33, 0xf0, 0x01, 0x3f, 0x03,
+        0xc1, 0x08, 0x05, 0xbf, 0x98, 0xf4, 0x9b, 0x6d,
+        0xa5, 0xa8, 0xb4, 0x82, 0x0c, 0x06, 0xfa, 0xff,
+        0x2d, 0x08, 0xf3, 0x05, 0x4f, 0x57, 0x2a, 0x39,
+        0xd4, 0x83, 0x0d, 0x75, 0x51, 0xd8, 0x5b, 0x1b,
+        0xd3, 0x51, 0x5a, 0x32, 0x2a, 0x9b, 0x32, 0xb2,
+        0xf2, 0xa4, 0x96, 0x12, 0xf2, 0xae, 0x40, 0x34,
+        0x67, 0xa8, 0xf5, 0x44, 0xd5, 0x35, 0x53, 0xfe,
+        0xa3, 0x60, 0x96, 0x63, 0x0f, 0x1f, 0x6e, 0xb0,
+        0x5a, 0x42, 0xa6, 0xfc, 0x51, 0x0b, 0x60, 0x27,
+        0xbc, 0x06, 0x71, 0xed, 0x65, 0x5b, 0x23, 0x86,
+        0x4a, 0x07, 0x3b, 0x22, 0x07, 0x46, 0xe6, 0x90,
+        0x3e, 0xf3, 0x25, 0x50, 0x1b, 0x4c, 0x7f, 0x03,
+        0x08, 0xa8, 0x36, 0x6b, 0x87, 0xe5, 0xe3, 0xdb,
+        0x9a, 0x38, 0x83, 0xff, 0x9f, 0x1a, 0x9f, 0x57,
+        0xa4, 0x2a, 0xf6, 0x37, 0xbc, 0x1a, 0xff, 0xc9,
+        0x1e, 0x35, 0x0c, 0xc3, 0x7c, 0xa3, 0xb2, 0xe5,
+        0xd2, 0xc6, 0xb4, 0x57, 0x47, 0xe4, 0x32, 0x16,
+        0x6d, 0xa9, 0xae, 0x64, 0xe6, 0x2d, 0x8d, 0xc5,
+        0x8d, 0x50, 0x8e, 0xe8, 0x1a, 0x22, 0x34, 0x2a,
+        0xd9, 0xeb, 0x51, 0x90, 0x4a, 0xb1, 0x41, 0x7d,
+        0x64, 0xf9, 0xb9, 0x0d, 0xf6, 0x23, 0x33, 0xb0,
+        0x33, 0xf4, 0xf7, 0x3f, 0x27, 0x84, 0xc6, 0x0f,
+        0x54, 0xa5, 0xc0, 0x2e, 0xec, 0x0b, 0x3a, 0x48,
+        0x6e, 0x80, 0x35, 0x81, 0x43, 0x9b, 0x90, 0xb1,
+        0xd0, 0x2b, 0xea, 0x21, 0xdc, 0xda, 0x5b, 0x09,
+        0xf4, 0xcc, 0x10, 0xb4, 0xc7, 0xfe, 0x79, 0x51,
+        0xc3, 0xc5, 0xac, 0x88, 0x74, 0x84, 0x0b, 0x4b,
+        0xca, 0x79, 0x16, 0x29, 0xfb, 0x69, 0x54, 0xdf,
+        0x41, 0x7e, 0xe9, 0xc7, 0x8e, 0xea, 0xa5, 0xfe,
+        0xfc, 0x76, 0x0e, 0x90, 0xc4, 0x92, 0x38, 0xad,
+        0x7b, 0x48, 0xe6, 0x6e, 0xf7, 0x21, 0xfd, 0x4e,
+        0x93, 0x0a, 0x7b, 0x41, 0x83, 0x68, 0xfb, 0x57,
+        0x51, 0x76, 0x34, 0xa9, 0x6c, 0x00, 0xaa, 0x4f,
+        0x66, 0x65, 0x98, 0x4a, 0x4f, 0xa3, 0xa0, 0xef,
+        0x69, 0x3f, 0xe3, 0x1c, 0x92, 0x8c, 0xfd, 0xd8,
+        0xe8, 0xde, 0x7c, 0x7f, 0x3e, 0x84, 0x8e, 0x69,
+        0x3c, 0xf1, 0xf2, 0x05, 0x46, 0xdc, 0x2f, 0x9d,
+        0x5e, 0x6e, 0x4c, 0xfb, 0xb5, 0x99, 0x2a, 0x59,
+        0x63, 0xc1, 0x34, 0xbc, 0x57, 0xc0, 0x0d, 0xb9,
+        0x61, 0x25, 0xf3, 0x33, 0x23, 0x51, 0xb6, 0x0d,
+        0x07, 0xa6, 0xab, 0x94, 0x4a, 0xb7, 0x2a, 0xea,
+        0xee, 0xac, 0xa3, 0xc3, 0x04, 0x8b, 0x0e, 0x56,
+        0xfe, 0x44, 0xa7, 0x39, 0xe2, 0xed, 0xed, 0xb4,
+        0x22, 0x2b, 0xac, 0x12, 0x32, 0x28, 0x91, 0xd8,
+        0xa5, 0xab, 0xff, 0x5f, 0xe0, 0x4b, 0xda, 0x78,
+        0x17, 0xda, 0xf1, 0x01, 0x5b, 0xcd, 0xe2, 0x5f,
+        0x50, 0x45, 0x73, 0x2b, 0xe4, 0x76, 0x77, 0xf4,
+        0x64, 0x1d, 0x43, 0xfb, 0x84, 0x7a, 0xea, 0x91,
+        0xae, 0xf9, 0x9e, 0xb7, 0xb4, 0xb0, 0x91, 0x5f,
+        0x16, 0x35, 0x9a, 0x11, 0xb8, 0xc7, 0xc1, 0x8c,
+        0xc6, 0x10, 0x8d, 0x2f, 0x63, 0x4a, 0xa7, 0x57,
+        0x3a, 0x51, 0xd6, 0x32, 0x2d, 0x64, 0x72, 0xd4,
+        0x66, 0xdc, 0x10, 0xa6, 0x67, 0xd6, 0x04, 0x23,
+        0x9d, 0x0a, 0x11, 0x77, 0xdd, 0x37, 0x94, 0x17,
+        0x3c, 0xbf, 0x8b, 0x65, 0xb0, 0x2e, 0x5e, 0x66,
+        0x47, 0x64, 0xac, 0xdd, 0xf0, 0x84, 0xfd, 0x39,
+        0xfa, 0x15, 0x5d, 0xef, 0xae, 0xca, 0xc1, 0x36,
+        0xa7, 0x5c, 0xbf, 0xc7, 0x08, 0xc2, 0x66, 0x00,
+        0x74, 0x74, 0x4e, 0x27, 0x3f, 0x55, 0x8a, 0xb7,
+        0x38, 0x66, 0x83, 0x6d, 0xcf, 0x99, 0x9e, 0x60,
+        0x8f, 0xdd, 0x2e, 0x62, 0x22, 0x0e, 0xef, 0x0c,
+        0x98, 0xa7, 0x85, 0x74, 0x3b, 0x9d, 0xec, 0x9e,
+        0xa9, 0x19, 0x72, 0xa5, 0x7f, 0x2c, 0x39, 0xb7,
+        0x7d, 0xb7, 0xf1, 0x12, 0x65, 0x27, 0x4b, 0x5a,
+        0xde, 0x17, 0xfe, 0xad, 0x44, 0xf3, 0x20, 0x4d,
+        0xfd, 0xe4, 0x1f, 0xb5, 0x81, 0xb0, 0x36, 0x37,
+        0x08, 0x6f, 0xc3, 0x0c, 0xe9, 0x85, 0x98, 0x82,
+        0xa9, 0x62, 0x0c, 0xc4, 0x97, 0xc0, 0x50, 0xc8,
+        0xa7, 0x3c, 0x50, 0x9f, 0x43, 0xb9, 0xcd, 0x5e,
+        0x4d, 0xfa, 0x1c, 0x4b, 0x0b, 0xa9, 0x98, 0x85,
+        0x38, 0x92, 0xac, 0x8d, 0xe4, 0xad, 0x9b, 0x98,
+        0xab, 0xd9, 0x38, 0xac, 0x62, 0x52, 0xa3, 0x22,
+        0x63, 0x0f, 0xbf, 0x95, 0x48, 0xdf, 0x69, 0xe7,
+        0x8b, 0x33, 0xd5, 0xb2, 0xbd, 0x05, 0x49, 0x49,
+        0x9d, 0x57, 0x73, 0x19, 0x33, 0xae, 0xfa, 0x33,
+        0xf1, 0x19, 0xa8, 0x80, 0xce, 0x04, 0x9f, 0xbc,
+        0x1d, 0x65, 0x82, 0x1b, 0xe5, 0x3a, 0x51, 0xc8,
+        0x1c, 0x21, 0xe3, 0x5d, 0xf3, 0x7d, 0x9b, 0x2f,
+        0x2c, 0x1d, 0x4a, 0x7f, 0x9b, 0x68, 0x35, 0xa3,
+        0xb2, 0x50, 0xf7, 0x62, 0x79, 0xcd, 0xf4, 0x98,
+        0x4f, 0xe5, 0x63, 0x7c, 0x3e, 0x45, 0x31, 0x8c,
+        0x16, 0xa0, 0x12, 0xc8, 0x58, 0xce, 0x39, 0xa6,
+        0xbc, 0x54, 0xdb, 0xc5, 0xe0, 0xd5, 0xba, 0xbc,
+        0xb9, 0x04, 0xf4, 0x8d, 0xe8, 0x2f, 0x15, 0x9d,
+};
 
-#if 0                           /*Not used at present */
-static void
-buf_dump(char const *prefix, unsigned char const *buf, size_t len)
+/* 100 test cases */
+static struct crc_test {
+        u32 crc;        /* random starting crc */
+        u32 start;      /* random 6 bit offset in buf */
+        u32 length;     /* random 11 bit length of test */
+        u32 crc_le;     /* expected crc32_le result */
+        u32 crc_be;     /* expected crc32_be result */
+        u32 crc32c_le;  /* expected crc32c_le result */
+} test[] =
 {
-        fputs(prefix, stdout);
-        while (len--)
-                printf(" %02x", *buf++);
-        putchar('\n');
+        {0x674bf11d, 0x00000038, 0x00000542, 0x0af6d466, 0xd8b6e4c1,
+         0xf6e93d6c},
+        {0x35c672c6, 0x0000003a, 0x000001aa, 0xc6d3dfba, 0x28aaf3ad,
+         0x0fe92aca},
+        {0x496da28e, 0x00000039, 0x000005af, 0xd933660f, 0x5d57e81f,
+         0x52e1ebb8},
+        {0x09a9b90e, 0x00000027, 0x000001f8, 0xb45fe007, 0xf45fca9a,
+         0x0798af9a},
+        {0xdc97e5a9, 0x00000025, 0x000003b6, 0xf81a3562, 0xe0126ba2,
+         0x18eb3152},
+        {0x47c58900, 0x0000000a, 0x000000b9, 0x8e58eccf, 0xf3afc793,
+         0xd00d08c7},
+        {0x292561e8, 0x0000000c, 0x00000403, 0xa2ba8aaf, 0x0b797aed,
+         0x8ba966bc},
+        {0x415037f6, 0x00000003, 0x00000676, 0xa17d52e8, 0x7f0fdf35,
+         0x11d694a2},
+        {0x3466e707, 0x00000026, 0x00000042, 0x258319be, 0x75c484a2,
+         0x6ab3208d},
+        {0xafd1281b, 0x00000023, 0x000002ee, 0x4428eaf8, 0x06c7ad10,
+         0xba4603c5},
+        {0xd3857b18, 0x00000028, 0x000004a2, 0x5c430821, 0xb062b7cb,
+         0xe6071c6f},
+        {0x1d825a8f, 0x0000002b, 0x0000050b, 0xd2c45f0c, 0xd68634e0,
+         0x179ec30a},
+        {0x5033e3bc, 0x0000000b, 0x00000078, 0xa3ea4113, 0xac6d31fb,
+         0x0903beb8},
+        {0x94f1fb5e, 0x0000000f, 0x000003a2, 0xfbfc50b1, 0x3cfe50ed,
+         0x6a7cb4fa},
+        {0xc9a0fe14, 0x00000009, 0x00000473, 0x5fb61894, 0x87070591,
+         0xdb535801},
+        {0x88a034b1, 0x0000001c, 0x000005ad, 0xc1b16053, 0x46f95c67,
+         0x92bed597},
+        {0xf0f72239, 0x00000020, 0x0000026d, 0xa6fa58f3, 0xf8c2c1dd,
+         0x192a3f1b},
+        {0xcc20a5e3, 0x0000003b, 0x0000067a, 0x7740185a, 0x308b979a,
+         0xccbaec1a},
+        {0xce589c95, 0x0000002b, 0x00000641, 0xd055e987, 0x40aae25b,
+         0x7eabae4d},
+        {0x78edc885, 0x00000035, 0x000005be, 0xa39cb14b, 0x035b0d1f,
+         0x28c72982},
+        {0x9d40a377, 0x0000003b, 0x00000038, 0x1f47ccd2, 0x197fbc9d,
+         0xc3cd4d18},
+        {0x703d0e01, 0x0000003c, 0x000006f1, 0x88735e7c, 0xfed57c5a,
+         0xbca8f0e7},
+        {0x776bf505, 0x0000000f, 0x000005b2, 0x5cc4fc01, 0xf32efb97,
+         0x713f60b3},
+        {0x4a3e7854, 0x00000027, 0x000004b8, 0x8d923c82, 0x0cbfb4a2,
+         0xebd08fd5},
+        {0x209172dd, 0x0000003b, 0x00000356, 0xb89e9c2b, 0xd7868138,
+         0x64406c59},
+        {0x3ba4cc5b, 0x0000002f, 0x00000203, 0xe51601a9, 0x5b2a1032,
+         0x7421890e},
+        {0xfc62f297, 0x00000000, 0x00000079, 0x71a8e1a2, 0x5d88685f,
+         0xe9347603},
+        {0x64280b8b, 0x00000016, 0x000007ab, 0x0fa7a30c, 0xda3a455f,
+         0x1bef9060},
+        {0x97dd724b, 0x00000033, 0x000007ad, 0x5788b2f4, 0xd7326d32,
+         0x34720072},
+        {0x61394b52, 0x00000035, 0x00000571, 0xc66525f1, 0xcabe7fef,
+         0x48310f59},
+        {0x29b4faff, 0x00000024, 0x0000006e, 0xca13751e, 0x993648e0,
+         0x783a4213},
+        {0x29bfb1dc, 0x0000000b, 0x00000244, 0x436c43f7, 0x429f7a59,
+         0x9e8efd41},
+        {0x86ae934b, 0x00000035, 0x00000104, 0x0760ec93, 0x9cf7d0f4,
+         0xfc3d34a5},
+        {0xc4c1024e, 0x0000002e, 0x000006b1, 0x6516a3ec, 0x19321f9c,
+         0x17a52ae2},
+        {0x3287a80a, 0x00000026, 0x00000496, 0x0b257eb1, 0x754ebd51,
+         0x886d935a},
+        {0xa4db423e, 0x00000023, 0x0000045d, 0x9b3a66dc, 0x873e9f11,
+         0xeaaeaeb2},
+        {0x7a1078df, 0x00000015, 0x0000014a, 0x8c2484c5, 0x6a628659,
+         0x8e900a4b},
+        {0x6048bd5b, 0x00000006, 0x0000006a, 0x897e3559, 0xac9961af,
+         0xd74662b1},
+        {0xd8f9ea20, 0x0000003d, 0x00000277, 0x60eb905b, 0xed2aaf99,
+         0xd26752ba},
+        {0xea5ec3b4, 0x0000002a, 0x000004fe, 0x869965dc, 0x6c1f833b,
+         0x8b1fcd62},
+        {0x2dfb005d, 0x00000016, 0x00000345, 0x6a3b117e, 0xf05e8521,
+         0xf54342fe},
+        {0x5a214ade, 0x00000020, 0x000005b6, 0x467f70be, 0xcb22ccd3,
+         0x5b95b988},
+        {0xf0ab9cca, 0x00000032, 0x00000515, 0xed223df3, 0x7f3ef01d,
+         0x2e1176be},
+        {0x91b444f9, 0x0000002e, 0x000007f8, 0x84e9a983, 0x5676756f,
+         0x66120546},
+        {0x1b5d2ddb, 0x0000002e, 0x0000012c, 0xba638c4c, 0x3f42047b,
+         0xf256a5cc},
+        {0xd824d1bb, 0x0000003a, 0x000007b5, 0x6288653b, 0x3a3ebea0,
+         0x4af1dd69},
+        {0x0470180c, 0x00000034, 0x000001f0, 0x9d5b80d6, 0x3de08195,
+         0x56f0a04a},
+        {0xffaa3a3f, 0x00000036, 0x00000299, 0xf3a82ab8, 0x53e0c13d,
+         0x74f6b6b2},
+        {0x6406cfeb, 0x00000023, 0x00000600, 0xa920b8e8, 0xe4e2acf4,
+         0x085951fd},
+        {0xb24aaa38, 0x0000003e, 0x000004a1, 0x657cc328, 0x5077b2c3,
+         0xc65387eb},
+        {0x58b2ab7c, 0x00000039, 0x000002b4, 0x3a17ee7e, 0x9dcb3643,
+         0x1ca9257b},
+        {0x3db85970, 0x00000006, 0x000002b6, 0x95268b59, 0xb9812c10,
+         0xfd196d76},
+        {0x857830c5, 0x00000003, 0x00000590, 0x4ef439d5, 0xf042161d,
+         0x5ef88339},
+        {0xe1fcd978, 0x0000003e, 0x000007d8, 0xae8d8699, 0xce0a1ef5,
+         0x2c3714d9},
+        {0xb982a768, 0x00000016, 0x000006e0, 0x62fad3df, 0x5f8a067b,
+         0x58576548},
+        {0x1d581ce8, 0x0000001e, 0x0000058b, 0xf0f5da53, 0x26e39eee,
+         0xfd7c57de},
+        {0x2456719b, 0x00000025, 0x00000503, 0x4296ac64, 0xd50e4c14,
+         0xd5fedd59},
+        {0xfae6d8f2, 0x00000000, 0x0000055d, 0x057fdf2e, 0x2a31391a,
+         0x1cc3b17b},
+        {0xcba828e3, 0x00000039, 0x000002ce, 0xe3f22351, 0x8f00877b,
+         0x270eed73},
+        {0x13d25952, 0x0000000a, 0x0000072d, 0x76d4b4cc, 0x5eb67ec3,
+         0x91ecbb11},
+        {0x0342be3f, 0x00000015, 0x00000599, 0xec75d9f1, 0x9d4d2826,
+         0x05ed8d0c},
+        {0xeaa344e0, 0x00000014, 0x000004d8, 0x72a4c981, 0x2064ea06,
+         0x0b09ad5b},
+        {0xbbb52021, 0x0000003b, 0x00000272, 0x04af99fc, 0xaf042d35,
+         0xf8d511fb},
+        {0xb66384dc, 0x0000001d, 0x000007fc, 0xd7629116, 0x782bd801,
+         0x5ad832cc},
+        {0x616c01b6, 0x00000022, 0x000002c8, 0x5b1dab30, 0x783ce7d2,
+         0x1214d196},
+        {0xce2bdaad, 0x00000016, 0x0000062a, 0x932535c8, 0x3f02926d,
+         0x5747218a},
+        {0x00fe84d7, 0x00000005, 0x00000205, 0x850e50aa, 0x753d649c,
+         0xde8f14de},
+        {0xbebdcb4c, 0x00000006, 0x0000055d, 0xbeaa37a2, 0x2d8c9eba,
+         0x3563b7b9},
+        {0xd8b1a02a, 0x00000010, 0x00000387, 0x5017d2fc, 0x503541a5,
+         0x071475d0},
+        {0x3b96cad2, 0x00000036, 0x00000347, 0x1d2372ae, 0x926cd90b,
+         0x54c79d60},
+        {0xc94c1ed7, 0x00000005, 0x0000038b, 0x9e9fdb22, 0x144a9178,
+         0x4c53eee6},
+        {0x1aad454e, 0x00000025, 0x000002b2, 0xc3f6315c, 0x5c7a35b3,
+         0x10137a3c},
+        {0xa4fec9a6, 0x00000000, 0x000006d6, 0x90be5080, 0xa4107605,
+         0xaa9d6c73},
+        {0x1bbe71e2, 0x0000001f, 0x000002fd, 0x4e504c3b, 0x284ccaf1,
+         0xb63d23e7},
+        {0x4201c7e4, 0x00000002, 0x000002b7, 0x7822e3f9, 0x0cc912a9,
+         0x7f53e9cf},
+        {0x23fddc96, 0x00000003, 0x00000627, 0x8a385125, 0x07767e78,
+         0x13c1cd83},
+        {0xd82ba25c, 0x00000016, 0x0000063e, 0x98e4148a, 0x283330c9,
+         0x49ff5867},
+        {0x786f2032, 0x0000002d, 0x0000060f, 0xf201600a, 0xf561bfcd,
+         0x8467f211},
+        {0xfebe4e1f, 0x0000002a, 0x000004f2, 0x95e51961, 0xfd80dcab,
+         0x3f9683b2},
+        {0x1a6e0a39, 0x00000008, 0x00000672, 0x8af6c2a5, 0x78dd84cb,
+         0x76a3f874},
+        {0x56000ab8, 0x0000000e, 0x000000e5, 0x36bacb8f, 0x22ee1f77,
+         0x863b702f},
+        {0x4717fe0c, 0x00000000, 0x000006ec, 0x8439f342, 0x5c8e03da,
+         0xdc6c58ff},
+        {0xd5d5d68e, 0x0000003c, 0x000003a3, 0x46fff083, 0x177d1b39,
+         0x0622cc95},
+        {0xc25dd6c6, 0x00000024, 0x000006c0, 0x5ceb8eb4, 0x892b0d16,
+         0xe85605cd},
+        {0xe9b11300, 0x00000023, 0x00000683, 0x07a5d59a, 0x6c6a3208,
+         0x31da5f06},
+        {0x95cd285e, 0x00000001, 0x00000047, 0x7b3a4368, 0x0202c07e,
+         0xa1f2e784},
+        {0xd9245a25, 0x0000001e, 0x000003a6, 0xd33c1841, 0x1936c0d5,
+         0xb07cc616},
+        {0x103279db, 0x00000006, 0x0000039b, 0xca09b8a0, 0x77d62892,
+         0xbf943b6c},
+        {0x1cba3172, 0x00000027, 0x000001c8, 0xcb377194, 0xebe682db,
+         0x2c01af1c},
+        {0x8f613739, 0x0000000c, 0x000001df, 0xb4b0bc87, 0x7710bd43,
+         0x0fe5f56d},
+        {0x1c6aa90d, 0x0000001b, 0x0000053c, 0x70559245, 0xda7894ac,
+         0xf8943b2d},
+        {0xaabe5b93, 0x0000003d, 0x00000715, 0xcdbf42fa, 0x0c3b99e7,
+         0xe4d89272},
+        {0xf15dd038, 0x00000006, 0x000006db, 0x6e104aea, 0x8d5967f2,
+         0x7c2f6bbb},
+        {0x584dd49c, 0x00000020, 0x000007bc, 0x36b6cfd6, 0xad4e23b2,
+         0xabbf388b},
+        {0x5d8c9506, 0x00000020, 0x00000470, 0x4c62378e, 0x31d92640,
+         0x1dca1f4e},
+        {0xb80d17b0, 0x00000032, 0x00000346, 0x22a5bb88, 0x9a7ec89f,
+         0x5c170e23},
+        {0xdaf0592e, 0x00000023, 0x000007b0, 0x3cab3f99, 0x9b1fdd99,
+         0xc0e9d672},
+        {0x4793cc85, 0x0000000d, 0x00000706, 0xe82e04f6, 0xed3db6b7,
+         0xc18bdc86},
+        {0x82ebf64e, 0x00000009, 0x000007c3, 0x69d590a9, 0x9efa8499,
+         0xa874fcdd},
+        {0xb18a0319, 0x00000026, 0x000007db, 0x1cf98dcc, 0x8fa9ad6a,
+         0x9dc0bb48},
+};
 
-}
-#endif
+#include <linux/time.h>
 
-static void bytereverse(unsigned char *buf, size_t len)
+static int __init crc32c_test(void)
 {
-        while (len--) {
-                unsigned char x = bitrev8(*buf);
-                *buf++ = x;
+        int i;
+        int errors = 0;
+        int bytes = 0;
+        struct timespec start, stop;
+        u64 nsec;
+        unsigned long flags;
+
+        /* keep static to prevent cache warming code from
+         * getting eliminated by the compiler */
+        static u32 crc;
+
+        /* pre-warm the cache */
+        for (i = 0; i < 100; i++) {
+                bytes += 2*test[i].length;
+
+                crc ^= __crc32c_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length);
         }
-}
 
-static void random_garbage(unsigned char *buf, size_t len)
-{
-        while (len--)
-                *buf++ = (unsigned char) random();
-}
+        /* reduce OS noise */
+        local_irq_save(flags);
+        local_irq_disable();
 
-#if 0                           /* Not used at present */
-static void store_le(u32 x, unsigned char *buf)
-{
-        buf[0] = (unsigned char) x;
-        buf[1] = (unsigned char) (x >> 8);
-        buf[2] = (unsigned char) (x >> 16);
-        buf[3] = (unsigned char) (x >> 24);
-}
-#endif
+        getnstimeofday(&start);
+        for (i = 0; i < 100; i++) {
+                if (test[i].crc32c_le != __crc32c_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length))
+                        errors++;
+        }
+        getnstimeofday(&stop);
 
-static void store_be(u32 x, unsigned char *buf)
-{
-        buf[0] = (unsigned char) (x >> 24);
-        buf[1] = (unsigned char) (x >> 16);
-        buf[2] = (unsigned char) (x >> 8);
-        buf[3] = (unsigned char) x;
+        local_irq_restore(flags);
+        local_irq_enable();
+
+        nsec = stop.tv_nsec - start.tv_nsec +
+                1000000000 * (stop.tv_sec - start.tv_sec);
+
+        pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
+
+        if (errors)
+                pr_warn("crc32c: %d self tests failed\n", errors);
+        else {
+                pr_info("crc32c: self tests passed, processed %d bytes in %lld nsec\n",
+                        bytes, nsec);
+        }
+
+        return 0;
 }
 
-/*
- * This checks that CRC(buf + CRC(buf)) = 0, and that
- * CRC commutes with bit-reversal.  This has the side effect
- * of bytewise bit-reversing the input buffer, and returns
- * the CRC of the reversed buffer.
- */
-static u32 test_step(u32 init, unsigned char *buf, size_t len)
+static int __init crc32_test(void)
 {
-        u32 crc1, crc2;
-        size_t i;
+        int i;
+        int errors = 0;
+        int bytes = 0;
+        struct timespec start, stop;
+        u64 nsec;
+        unsigned long flags;
+
+        /* keep static to prevent cache warming code from
+         * getting eliminated by the compiler */
+        static u32 crc;
+
+        /* pre-warm the cache */
+        for (i = 0; i < 100; i++) {
+                bytes += 2*test[i].length;
 
-        crc1 = crc32_be(init, buf, len);
-        store_be(crc1, buf + len);
-        crc2 = crc32_be(init, buf, len + 4);
-        if (crc2)
-                printf("\nCRC cancellation fail: 0x%08x should be 0\n",
-                       crc2);
-
-        for (i = 0; i <= len + 4; i++) {
-                crc2 = crc32_be(init, buf, i);
-                crc2 = crc32_be(crc2, buf + i, len + 4 - i);
-                if (crc2)
-                        printf("\nCRC split fail: 0x%08x\n", crc2);
+                crc ^= crc32_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length);
+
+                crc ^= crc32_be(test[i].crc, test_buf +
+                    test[i].start, test[i].length);
         }
 
-        /* Now swap it around for the other test */
-
-        bytereverse(buf, len + 4);
-        init = bitrev32(init);
-        crc2 = bitrev32(crc1);
-        if (crc1 != bitrev32(crc2))
-                printf("\nBit reversal fail: 0x%08x -> 0x%08x -> 0x%08x\n",
-                       crc1, crc2, bitrev32(crc2));
-        crc1 = crc32_le(init, buf, len);
-        if (crc1 != crc2)
-                printf("\nCRC endianness fail: 0x%08x != 0x%08x\n", crc1,
-                       crc2);
-        crc2 = crc32_le(init, buf, len + 4);
-        if (crc2)
-                printf("\nCRC cancellation fail: 0x%08x should be 0\n",
-                       crc2);
-
-        for (i = 0; i <= len + 4; i++) {
-                crc2 = crc32_le(init, buf, i);
-                crc2 = crc32_le(crc2, buf + i, len + 4 - i);
-                if (crc2)
-                        printf("\nCRC split fail: 0x%08x\n", crc2);
+        /* reduce OS noise */
+        local_irq_save(flags);
+        local_irq_disable();
+
+        getnstimeofday(&start);
+        for (i = 0; i < 100; i++) {
+                if (test[i].crc_le != crc32_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length))
+                        errors++;
+
+                if (test[i].crc_be != crc32_be(test[i].crc, test_buf +
+                    test[i].start, test[i].length))
+                        errors++;
         }
+        getnstimeofday(&stop);
 
-        return crc1;
-}
+        local_irq_restore(flags);
+        local_irq_enable();
 
-#define SIZE 64
-#define INIT1 0
-#define INIT2 0
+        nsec = stop.tv_nsec - start.tv_nsec +
+                1000000000 * (stop.tv_sec - start.tv_sec);
 
-int main(void)
-{
-        unsigned char buf1[SIZE + 4];
-        unsigned char buf2[SIZE + 4];
-        unsigned char buf3[SIZE + 4];
-        int i, j;
-        u32 crc1, crc2, crc3;
-
-        for (i = 0; i <= SIZE; i++) {
-                printf("\rTesting length %d...", i);
-                fflush(stdout);
-                random_garbage(buf1, i);
-                random_garbage(buf2, i);
-                for (j = 0; j < i; j++)
-                        buf3[j] = buf1[j] ^ buf2[j];
-
-                crc1 = test_step(INIT1, buf1, i);
-                crc2 = test_step(INIT2, buf2, i);
-                /* Now check that CRC(buf1 ^ buf2) = CRC(buf1) ^ CRC(buf2) */
-                crc3 = test_step(INIT1 ^ INIT2, buf3, i);
-                if (crc3 != (crc1 ^ crc2))
-                        printf("CRC XOR fail: 0x%08x != 0x%08x ^ 0x%08x\n",
-                               crc3, crc1, crc2);
+        pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
+                 CRC_LE_BITS, CRC_BE_BITS);
+
+        if (errors)
+                pr_warn("crc32: %d self tests failed\n", errors);
+        else {
+                pr_info("crc32: self tests passed, processed %d bytes in %lld nsec\n",
+                        bytes, nsec);
         }
-        printf("\nAll test complete.  No failures expected.\n");
+
+        return 0;
+}
+
+static int __init crc32test_init(void)
+{
+        crc32_test();
+        crc32c_test();
         return 0;
 }
 
-#endif                          /* UNITTEST */
+static void __exit crc32_exit(void)
+{
+}
+
+module_init(crc32test_init);
+module_exit(crc32_exit);
+#endif /* CONFIG_CRC32_SELFTEST */
diff --git a/lib/crc32defs.h b/lib/crc32defs.h
index 9b6773d7374..64cba2c3c70 100644
--- a/lib/crc32defs.h
+++ b/lib/crc32defs.h
@@ -6,27 +6,67 @@
 #define CRCPOLY_LE 0xedb88320
 #define CRCPOLY_BE 0x04c11db7
 
-/* How many bits at a time to use.  Requires a table of 4<<CRC_xx_BITS bytes. */
-/* For less performance-sensitive, use 4 */
-#ifndef CRC_LE_BITS 
+/*
+ * This is the CRC32c polynomial, as outlined by Castagnoli.
+ * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
+ * x^8+x^6+x^0
+ */
+#define CRC32C_POLY_LE 0x82F63B78
+
+/* Try to choose an implementation variant via Kconfig */
+#ifdef CONFIG_CRC32_SLICEBY8
+# define CRC_LE_BITS 64
+# define CRC_BE_BITS 64
+#endif
+#ifdef CONFIG_CRC32_SLICEBY4
+# define CRC_LE_BITS 32
+# define CRC_BE_BITS 32
+#endif
+#ifdef CONFIG_CRC32_SARWATE
 # define CRC_LE_BITS 8
+# define CRC_BE_BITS 8
+#endif
+#ifdef CONFIG_CRC32_BIT
+# define CRC_LE_BITS 1
+# define CRC_BE_BITS 1
+#endif
+
+/*
+ * How many bits at a time to use.  Valid values are 1, 2, 4, 8, 32 and 64.
+ * For less performance-sensitive, use 4 or 8 to save table size.
+ * For larger systems choose same as CPU architecture as default.
+ * This works well on X86_64, SPARC64 systems. This may require some
+ * elaboration after experiments with other architectures.
+ */
+#ifndef CRC_LE_BITS
+#  ifdef CONFIG_64BIT
+#  define CRC_LE_BITS 64
+#  else
+#  define CRC_LE_BITS 32
+#  endif
 #endif
 #ifndef CRC_BE_BITS
-# define CRC_BE_BITS 8
+#  ifdef CONFIG_64BIT
+#  define CRC_BE_BITS 64
+#  else
+#  define CRC_BE_BITS 32
+#  endif
 #endif
 
 /*
  * Little-endian CRC computation.  Used with serial bit streams sent
  * lsbit-first.  Be sure to use cpu_to_le32() to append the computed CRC.
  */
-#if CRC_LE_BITS > 8 || CRC_LE_BITS < 1 || CRC_LE_BITS & CRC_LE_BITS-1
-# error CRC_LE_BITS must be a power of 2 between 1 and 8
+#if CRC_LE_BITS > 64 || CRC_LE_BITS < 1 || CRC_LE_BITS == 16 || \
+        CRC_LE_BITS & CRC_LE_BITS-1
+# error "CRC_LE_BITS must be one of {1, 2, 4, 8, 32, 64}"
 #endif
 
 /*
  * Big-endian CRC computation.  Used with serial bit streams sent
  * msbit-first.  Be sure to use cpu_to_be32() to append the computed CRC.
  */
-#if CRC_BE_BITS > 8 || CRC_BE_BITS < 1 || CRC_BE_BITS & CRC_BE_BITS-1
-# error CRC_BE_BITS must be a power of 2 between 1 and 8
+#if CRC_BE_BITS > 64 || CRC_BE_BITS < 1 || CRC_BE_BITS == 16 || \
+        CRC_BE_BITS & CRC_BE_BITS-1
+# error "CRC_BE_BITS must be one of {1, 2, 4, 8, 32, 64}"
 #endif
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index 85d0e412a04..8f8d5439e2d 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -1,14 +1,29 @@
 #include <stdio.h>
+#include "../include/generated/autoconf.h"
 #include "crc32defs.h"
 #include <inttypes.h>
 
 #define ENTRIES_PER_LINE 4
 
-#define LE_TABLE_SIZE (1 << CRC_LE_BITS)
-#define BE_TABLE_SIZE (1 << CRC_BE_BITS)
+#if CRC_LE_BITS > 8
+# define LE_TABLE_ROWS (CRC_LE_BITS/8)
+# define LE_TABLE_SIZE 256
+#else
+# define LE_TABLE_ROWS 1
+# define LE_TABLE_SIZE (1 << CRC_LE_BITS)
+#endif
 
-static uint32_t crc32table_le[4][LE_TABLE_SIZE];
-static uint32_t crc32table_be[4][BE_TABLE_SIZE];
+#if CRC_BE_BITS > 8
+# define BE_TABLE_ROWS (CRC_BE_BITS/8)
+# define BE_TABLE_SIZE 256
+#else
+# define BE_TABLE_ROWS 1
+# define BE_TABLE_SIZE (1 << CRC_BE_BITS)
+#endif
+
+static uint32_t crc32table_le[LE_TABLE_ROWS][256];
+static uint32_t crc32table_be[BE_TABLE_ROWS][256];
+static uint32_t crc32ctable_le[LE_TABLE_ROWS][256];
 
 /**
  * crc32init_le() - allocate and initialize LE table data
@@ -17,27 +32,38 @@ static uint32_t crc32table_be[4][BE_TABLE_SIZE];
  * fact that crctable[i^j] = crctable[i] ^ crctable[j].
  *
  */
-static void crc32init_le(void)
+static void crc32init_le_generic(const uint32_t polynomial,
+                                 uint32_t (*tab)[256])
 {
         unsigned i, j;
         uint32_t crc = 1;
 
-        crc32table_le[0][0] = 0;
+        tab[0][0] = 0;
 
-        for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) {
-                crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+        for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) {
+                crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
                 for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
-                        crc32table_le[0][i + j] = crc ^ crc32table_le[0][j];
+                        tab[0][i + j] = crc ^ tab[0][j];
         }
         for (i = 0; i < LE_TABLE_SIZE; i++) {
-                crc = crc32table_le[0][i];
-                for (j = 1; j < 4; j++) {
-                        crc = crc32table_le[0][crc & 0xff] ^ (crc >> 8);
-                        crc32table_le[j][i] = crc;
+                crc = tab[0][i];
+                for (j = 1; j < LE_TABLE_ROWS; j++) {
+                        crc = tab[0][crc & 0xff] ^ (crc >> 8);
+                        tab[j][i] = crc;
                 }
         }
 }
 
+static void crc32init_le(void)
+{
+        crc32init_le_generic(CRCPOLY_LE, crc32table_le);
+}
+
+static void crc32cinit_le(void)
+{
+        crc32init_le_generic(CRC32C_POLY_LE, crc32ctable_le);
+}
+
 /**
  * crc32init_be() - allocate and initialize BE table data
  */
@@ -55,18 +81,18 @@ static void crc32init_be(void)
         }
         for (i = 0; i < BE_TABLE_SIZE; i++) {
                 crc = crc32table_be[0][i];
-                for (j = 1; j < 4; j++) {
+                for (j = 1; j < BE_TABLE_ROWS; j++) {
                         crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8);
                         crc32table_be[j][i] = crc;
                 }
         }
 }
 
-static void output_table(uint32_t table[4][256], int len, char *trans)
+static void output_table(uint32_t (*table)[256], int rows, int len, char *trans)
 {
         int i, j;
 
-        for (j = 0 ; j < 4; j++) {
+        for (j = 0 ; j < rows; j++) {
                 printf("{");
                 for (i = 0; i < len - 1; i++) {
                         if (i % ENTRIES_PER_LINE == 0)
@@ -83,15 +109,30 @@ int main(int argc, char** argv)
 
         if (CRC_LE_BITS > 1) {
                 crc32init_le();
-                printf("static const u32 crc32table_le[4][256] = {");
-                output_table(crc32table_le, LE_TABLE_SIZE, "tole");
+                printf("static const u32 __cacheline_aligned "
+                       "crc32table_le[%d][%d] = {",
+                       LE_TABLE_ROWS, LE_TABLE_SIZE);
+                output_table(crc32table_le, LE_TABLE_ROWS,
+                             LE_TABLE_SIZE, "tole");
                 printf("};\n");
         }
 
         if (CRC_BE_BITS > 1) {
                 crc32init_be();
-                printf("static const u32 crc32table_be[4][256] = {");
-                output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
+                printf("static const u32 __cacheline_aligned "
+                       "crc32table_be[%d][%d] = {",
+                       BE_TABLE_ROWS, BE_TABLE_SIZE);
+                output_table(crc32table_be, LE_TABLE_ROWS,
+                             BE_TABLE_SIZE, "tobe");
+                printf("};\n");
+        }
+        if (CRC_LE_BITS > 1) {
+                crc32cinit_le();
+                printf("static const u32 __cacheline_aligned "
+                       "crc32ctable_le[%d][%d] = {",
+                       LE_TABLE_ROWS, LE_TABLE_SIZE);
+                output_table(crc32ctable_le, LE_TABLE_ROWS,
+                             LE_TABLE_SIZE, "tole");
                 printf("};\n");
         }
 
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 577ddf80597..b41dd90f290 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -16,23 +16,46 @@
 #include <linux/genalloc.h>
 
 
+/* General purpose special memory pool descriptor. */
+struct gen_pool {
+        rwlock_t lock;                  /* protects chunks list */
+        struct list_head chunks;        /* list of chunks in this pool */
+        unsigned order;                 /* minimum allocation order */
+};
+
+/* General purpose special memory pool chunk descriptor. */
+struct gen_pool_chunk {
+        spinlock_t lock;                /* protects bits */
+        struct list_head next_chunk;    /* next chunk in pool */
+        phys_addr_t phys_addr;          /* physical starting address of memory chunk */
+        unsigned long start;            /* start of memory chunk */
+        unsigned long size;             /* number of bits */
+        unsigned long bits[0];          /* bitmap for allocating memory chunk */
+};
+
+
 /**
- * gen_pool_create - create a new special memory pool
- * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents
- * @nid: node id of the node the pool structure should be allocated on, or -1
+ * gen_pool_create() - create a new special memory pool
+ * @order:      Log base 2 of number of bytes each bitmap bit
+ *              represents.
+ * @nid:        Node id of the node the pool structure should be allocated
+ *              on, or -1.  This will be also used for other allocations.
  *
  * Create a new special memory pool that can be used to manage special purpose
  * memory not managed by the regular kmalloc/kfree interface.
  */
-struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
+struct gen_pool *__must_check gen_pool_create(unsigned order, int nid)
 {
         struct gen_pool *pool;
 
-        pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
-        if (pool != NULL) {
+        if (WARN_ON(order >= BITS_PER_LONG))
+                return NULL;
+
+        pool = kmalloc_node(sizeof *pool, GFP_KERNEL, nid);
+        if (pool) {
                 rwlock_init(&pool->lock);
                 INIT_LIST_HEAD(&pool->chunks);
-                pool->min_alloc_order = min_alloc_order;
+                pool->order = order;
         }
         return pool;
 }
@@ -40,33 +63,41 @@ EXPORT_SYMBOL(gen_pool_create);
 
 /**
  * gen_pool_add_virt - add a new chunk of special memory to the pool
- * @pool: pool to add new memory chunk to
- * @virt: virtual starting address of memory chunk to add to pool
- * @phys: physical starting address of memory chunk to add to pool
- * @size: size in bytes of the memory chunk to add to pool
- * @nid: node id of the node the chunk structure and bitmap should be
- *       allocated on, or -1
+ * @pool:       Pool to add new memory chunk to
+ * @virt:       Virtual starting address of memory chunk to add to pool
+ * @phys:       Physical starting address of memory chunk to add to pool
+ * @size:       Size in bytes of the memory chunk to add to pool
+ * @nid:        Node id of the node the chunk structure and bitmap should be
+ *              allocated on, or -1
  *
  * Add a new chunk of special memory to the specified pool.
  *
  * Returns 0 on success or a -ve errno on failure.
  */
-int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
-                 size_t size, int nid)
+int __must_check
+gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
+                  size_t size, int nid)
 {
         struct gen_pool_chunk *chunk;
-        int nbits = size >> pool->min_alloc_order;
-        int nbytes = sizeof(struct gen_pool_chunk) +
-                                (nbits + BITS_PER_BYTE - 1) / BITS_PER_BYTE;
+        size_t nbytes;
 
-        chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
-        if (unlikely(chunk == NULL))
+        if (WARN_ON(!virt || virt + size < virt ||
+                    (virt & ((1 << pool->order) - 1))))
+                return -EINVAL;
+
+        size = size >> pool->order;
+        if (WARN_ON(!size))
+                return -EINVAL;
+
+        nbytes = sizeof *chunk + BITS_TO_LONGS(size) * sizeof *chunk->bits;
+        chunk = kzalloc_node(nbytes, GFP_KERNEL, nid);
+        if (!chunk)
                 return -ENOMEM;
 
         spin_lock_init(&chunk->lock);
+        chunk->start = virt >> pool->order;
+        chunk->size  = size;
         chunk->phys_addr = phys;
-        chunk->start_addr = virt;
-        chunk->end_addr = virt + size;
 
         write_lock(&pool->lock);
         list_add(&chunk->next_chunk, &pool->chunks);
@@ -90,10 +121,12 @@ phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
 
         read_lock(&pool->lock);
         list_for_each(_chunk, &pool->chunks) {
+                unsigned long start_addr;
                 chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
 
-                if (addr >= chunk->start_addr && addr < chunk->end_addr)
-                        return chunk->phys_addr + addr - chunk->start_addr;
+                start_addr = chunk->start << pool->order;
+                if (addr >= start_addr && addr < start_addr + chunk->size)
+                        return chunk->phys_addr + addr - start_addr;
         }
         read_unlock(&pool->lock);
 
@@ -102,115 +135,116 @@ phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
 EXPORT_SYMBOL(gen_pool_virt_to_phys);
 
 /**
- * gen_pool_destroy - destroy a special memory pool
- * @pool: pool to destroy
+ * gen_pool_destroy() - destroy a special memory pool
+ * @pool:       Pool to destroy.
  *
  * Destroy the specified special memory pool. Verifies that there are no
  * outstanding allocations.
  */
 void gen_pool_destroy(struct gen_pool *pool)
 {
-        struct list_head *_chunk, *_next_chunk;
         struct gen_pool_chunk *chunk;
-        int order = pool->min_alloc_order;
-        int bit, end_bit;
-
+        int bit;
 
-        list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
-                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+        while (!list_empty(&pool->chunks)) {
+                chunk = list_entry(pool->chunks.next, struct gen_pool_chunk,
+                                   next_chunk);
                 list_del(&chunk->next_chunk);
 
-                end_bit = (chunk->end_addr - chunk->start_addr) >> order;
-                bit = find_next_bit(chunk->bits, end_bit, 0);
-                BUG_ON(bit < end_bit);
+                bit = find_next_bit(chunk->bits, chunk->size, 0);
+                BUG_ON(bit < chunk->size);
 
                 kfree(chunk);
         }
         kfree(pool);
-        return;
 }
 EXPORT_SYMBOL(gen_pool_destroy);
 
 /**
- * gen_pool_alloc - allocate special memory from the pool
- * @pool: pool to allocate from
- * @size: number of bytes to allocate from the pool
+ * gen_pool_alloc_aligned() - allocate special memory from the pool
+ * @pool:       Pool to allocate from.
+ * @size:       Number of bytes to allocate from the pool.
+ * @alignment_order:    Order the allocated space should be
+ *                      aligned to (eg. 20 means allocated space
+ *                      must be aligned to 1MiB).
  *
  * Allocate the requested number of bytes from the specified pool.
  * Uses a first-fit algorithm.
  */
-unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
+unsigned long __must_check
+gen_pool_alloc_aligned(struct gen_pool *pool, size_t size,
+                       unsigned alignment_order)
 {
-        struct list_head *_chunk;
+        unsigned long addr, align_mask = 0, flags, start;
         struct gen_pool_chunk *chunk;
-        unsigned long addr, flags;
-        int order = pool->min_alloc_order;
-        int nbits, start_bit, end_bit;
 
         if (size == 0)
                 return 0;
 
-        nbits = (size + (1UL << order) - 1) >> order;
+        if (alignment_order > pool->order)
+                align_mask = (1 << (alignment_order - pool->order)) - 1;
 
-        read_lock(&pool->lock);
-        list_for_each(_chunk, &pool->chunks) {
-                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+        size = (size + (1UL << pool->order) - 1) >> pool->order;
 
-                end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+        read_lock(&pool->lock);
+        list_for_each_entry(chunk, &pool->chunks, next_chunk) {
+                if (chunk->size < size)
+                        continue;
 
                 spin_lock_irqsave(&chunk->lock, flags);
-                start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, 0,
-                                                nbits, 0);
-                if (start_bit >= end_bit) {
+                start = bitmap_find_next_zero_area_off(chunk->bits, chunk->size,
+                                                       0, size, align_mask,
+                                                       chunk->start);
+                if (start >= chunk->size) {
                         spin_unlock_irqrestore(&chunk->lock, flags);
                         continue;
                 }
 
-                addr = chunk->start_addr + ((unsigned long)start_bit << order);
-
-                bitmap_set(chunk->bits, start_bit, nbits);
+                bitmap_set(chunk->bits, start, size);
                 spin_unlock_irqrestore(&chunk->lock, flags);
-                read_unlock(&pool->lock);
-                return addr;
+                addr = (chunk->start + start) << pool->order;
+                goto done;
         }
+
+        addr = 0;
+done:
         read_unlock(&pool->lock);
-        return 0;
+        return addr;
 }
-EXPORT_SYMBOL(gen_pool_alloc);
+EXPORT_SYMBOL(gen_pool_alloc_aligned);
 
 /**
- * gen_pool_free - free allocated special memory back to the pool
- * @pool: pool to free to
- * @addr: starting address of memory to free back to pool
- * @size: size in bytes of memory to free
+ * gen_pool_free() - free allocated special memory back to the pool
+ * @pool:       Pool to free to.
+ * @addr:       Starting address of memory to free back to pool.
+ * @size:       Size in bytes of memory to free.
  *
  * Free previously allocated special memory back to the specified pool.
  */
 void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
 {
-        struct list_head *_chunk;
         struct gen_pool_chunk *chunk;
         unsigned long flags;
-        int order = pool->min_alloc_order;
-        int bit, nbits;
 
-        nbits = (size + (1UL << order) - 1) >> order;
+        if (!size)
+                return;
 
-        read_lock(&pool->lock);
-        list_for_each(_chunk, &pool->chunks) {
-                chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+        addr = addr >> pool->order;
+        size = (size + (1UL << pool->order) - 1) >> pool->order;
 
-                if (addr >= chunk->start_addr && addr < chunk->end_addr) {
-                        BUG_ON(addr + size > chunk->end_addr);
+        BUG_ON(addr + size < addr);
+
+        read_lock(&pool->lock);
+        list_for_each_entry(chunk, &pool->chunks, next_chunk)
+                if (addr >= chunk->start &&
+                    addr + size <= chunk->start + chunk->size) {
                         spin_lock_irqsave(&chunk->lock, flags);
-                        bit = (addr - chunk->start_addr) >> order;
-                        while (nbits--)
-                                __clear_bit(bit++, chunk->bits);
+                        bitmap_clear(chunk->bits, addr - chunk->start, size);
                         spin_unlock_irqrestore(&chunk->lock, flags);
-                        break;
+                        goto done;
                 }
-        }
-        BUG_ON(nbits > 0);
+        BUG_ON(1);
+done:
         read_unlock(&pool->lock);
 }
 EXPORT_SYMBOL(gen_pool_free);
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 70af0a7f97c..6d40244e801 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -29,16 +29,17 @@
 
 u64 uevent_seqnum;
 char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH;
-static DEFINE_SPINLOCK(sequence_lock);
 #ifdef CONFIG_NET
 struct uevent_sock {
         struct list_head list;
         struct sock *sk;
 };
 static LIST_HEAD(uevent_sock_list);
-static DEFINE_MUTEX(uevent_sock_mutex);
 #endif
 
+/* This lock protects uevent_seqnum and uevent_sock_list */
+static DEFINE_MUTEX(uevent_sock_mutex);
+
 /* the strings here must match the enum in include/linux/kobject.h */
 static const char *kobject_actions[] = {
         [KOBJ_ADD] =            "add",
@@ -136,7 +137,6 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
         struct kobject *top_kobj;
         struct kset *kset;
         const struct kset_uevent_ops *uevent_ops;
-        u64 seq;
         int i = 0;
         int retval = 0;
 #ifdef CONFIG_NET
@@ -243,17 +243,16 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
         else if (action == KOBJ_REMOVE)
                 kobj->state_remove_uevent_sent = 1;
 
+        mutex_lock(&uevent_sock_mutex);
         /* we will send an event, so request a new sequence number */
-        spin_lock(&sequence_lock);
-        seq = ++uevent_seqnum;
-        spin_unlock(&sequence_lock);
-        retval = add_uevent_var(env, "SEQNUM=%llu", (unsigned long long)seq);
-        if (retval)
+        retval = add_uevent_var(env, "SEQNUM=%llu", (unsigned long long)++uevent_seqnum);
+        if (retval) {
+                mutex_unlock(&uevent_sock_mutex);
                 goto exit;
+        }
 
 #if defined(CONFIG_NET)
         /* send netlink message */
-        mutex_lock(&uevent_sock_mutex);
         list_for_each_entry(ue_sk, &uevent_sock_list, list) {
                 struct sock *uevent_sock = ue_sk->sk;
                 struct sk_buff *skb;
@@ -282,13 +281,13 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
                                                             kobj_bcast_filter,
                                                             kobj);
                         /* ENOBUFS should be handled in userspace */
-                        if (retval == -ENOBUFS)
+                        if (retval == -ENOBUFS || retval == -ESRCH)
                                 retval = 0;
                 } else
                         retval = -ENOMEM;
         }
-        mutex_unlock(&uevent_sock_mutex);
 #endif
+        mutex_unlock(&uevent_sock_mutex);
 
         /* call uevent_helper, usually only enabled during early boot */
         if (uevent_helper[0] && !kobj_usermode_filter(kobj)) {
diff --git a/lib/md5.c b/lib/md5.c
new file mode 100644
index 00000000000..c777180e1f2
--- /dev/null
+++ b/lib/md5.c
@@ -0,0 +1,95 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cryptohash.h>
+
+#define F1(x, y, z)     (z ^ (x & (y ^ z)))
+#define F2(x, y, z)     F1(z, x, y)
+#define F3(x, y, z)     (x ^ y ^ z)
+#define F4(x, y, z)     (y ^ (x | ~z))
+
+#define MD5STEP(f, w, x, y, z, in, s) \
+        (w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
+
+void md5_transform(__u32 *hash, __u32 const *in)
+{
+        u32 a, b, c, d;
+
+        a = hash[0];
+        b = hash[1];
+        c = hash[2];
+        d = hash[3];
+
+        MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
+        MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
+        MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
+        MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
+        MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
+        MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
+        MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
+        MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
+        MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
+        MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
+        MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
+        MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
+        MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
+        MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
+        MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
+        MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
+
+        MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
+        MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
+        MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
+        MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
+        MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
+        MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
+        MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
+        MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
+        MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
+        MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
+        MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
+        MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
+        MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
+        MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
+        MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
+        MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
+
+        MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
+        MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
+        MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
+        MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
+        MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
+        MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
+        MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
+        MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
+        MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
+        MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
+        MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
+        MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
+        MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
+        MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
+        MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
+        MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
+
+        MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
+        MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
+        MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
+        MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
+        MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
+        MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
+        MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
+        MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
+        MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
+        MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
+        MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
+        MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
+        MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
+        MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
+        MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
+        MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
+
+        hash[0] += a;
+        hash[1] += b;
+        hash[2] += c;
+        hash[3] += d;
+}
+EXPORT_SYMBOL(md5_transform);
diff --git a/lib/memcopy.c b/lib/memcopy.c
new file mode 100644
index 00000000000..d2d3376f738
--- /dev/null
+++ b/lib/memcopy.c
@@ -0,0 +1,403 @@
+/* 
+ * memcopy.c -- subroutines for memory copy functions. 
+ * 
+ * This program is free software; you can redistribute it and/or modify it 
+ * under the terms of the GNU General Public License as published by the Free 
+ * Software Foundation; either version 2.1 of the License, or (at your option) 
+ * any later version. 
+ * 
+ * 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 for more details. 
+ * 
+ * You should have received a copy of the GNU General Public License along 
+ * with this program; if not, write to the Free Software Foundation, Inc., 
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. 
+ * 
+ * The code is derived from the GNU C Library. 
+ * Copyright (C) 1991, 1992, 1993, 1997, 2004 Free Software Foundation, Inc. 
+ */ 
+ 
+/* BE VERY CAREFUL IF YOU CHANGE THIS CODE...!  */ 
+ 
+#include <linux/memcopy.h>
+ 
+/* 
+ * _wordcopy_fwd_aligned -- Copy block beginning at SRCP to block beginning 
+ * at DSTP with LEN `op_t' words (not LEN bytes!). 
+ * Both SRCP and DSTP should be aligned for memory operations on `op_t's. 
+ */ 
+void _wordcopy_fwd_aligned (long int dstp, long int srcp, size_t len) 
+{ 
+    op_t a0, a1; 
+ 
+    switch (len % 8) { 
+    case 2: 
+        a0 = ((op_t *) srcp)[0]; 
+        srcp -= 6 * OPSIZ; 
+        dstp -= 7 * OPSIZ; 
+        len += 6; 
+        goto do1; 
+    case 3: 
+        a1 = ((op_t *) srcp)[0]; 
+        srcp -= 5 * OPSIZ; 
+        dstp -= 6 * OPSIZ; 
+        len += 5; 
+        goto do2; 
+    case 4: 
+        a0 = ((op_t *) srcp)[0]; 
+        srcp -= 4 * OPSIZ; 
+        dstp -= 5 * OPSIZ; 
+        len += 4; 
+        goto do3; 
+    case 5: 
+        a1 = ((op_t *) srcp)[0]; 
+        srcp -= 3 * OPSIZ; 
+        dstp -= 4 * OPSIZ; 
+        len += 3; 
+        goto do4; 
+    case 6: 
+        a0 = ((op_t *) srcp)[0]; 
+        srcp -= 2 * OPSIZ; 
+        dstp -= 3 * OPSIZ; 
+        len += 2; 
+        goto do5; 
+    case 7: 
+        a1 = ((op_t *) srcp)[0]; 
+        srcp -= 1 * OPSIZ; 
+        dstp -= 2 * OPSIZ; 
+        len += 1; 
+        goto do6; 
+    case 0: 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            return; 
+        a0 = ((op_t *) srcp)[0]; 
+        srcp -= 0 * OPSIZ; 
+        dstp -= 1 * OPSIZ; 
+        goto do7; 
+    case 1: 
+        a1 = ((op_t *) srcp)[0]; 
+        srcp -=-1 * OPSIZ; 
+        dstp -= 0 * OPSIZ; 
+        len -= 1; 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            goto do0; 
+        goto do8;            /* No-op.  */ 
+    } 
+ 
+    do { 
+do8:
+        a0 = ((op_t *) srcp)[0]; 
+        ((op_t *) dstp)[0] = a1; 
+do7:
+        a1 = ((op_t *) srcp)[1]; 
+        ((op_t *) dstp)[1] = a0; 
+do6:
+        a0 = ((op_t *) srcp)[2]; 
+        ((op_t *) dstp)[2] = a1; 
+do5:
+        a1 = ((op_t *) srcp)[3]; 
+        ((op_t *) dstp)[3] = a0; 
+do4:
+        a0 = ((op_t *) srcp)[4]; 
+        ((op_t *) dstp)[4] = a1; 
+do3:
+        a1 = ((op_t *) srcp)[5]; 
+        ((op_t *) dstp)[5] = a0; 
+do2:
+        a0 = ((op_t *) srcp)[6]; 
+        ((op_t *) dstp)[6] = a1; 
+do1:
+        a1 = ((op_t *) srcp)[7]; 
+        ((op_t *) dstp)[7] = a0; 
+ 
+        srcp += 8 * OPSIZ; 
+        dstp += 8 * OPSIZ; 
+        len -= 8; 
+    } while (len != 0); 
+ 
+    /* 
+     * This is the right position for do0.  Please don't move it into 
+     * the loop. 
+     */ 
+do0: 
+    ((op_t *) dstp)[0] = a1; 
+} 
+ 
+/* 
+ * _wordcopy_fwd_dest_aligned -- Copy block beginning at SRCP to block 
+ * beginning at DSTP with LEN `op_t' words (not LEN bytes!). DSTP should 
+ * be aligned for memory operations on `op_t's, but SRCP must *not* be aligned. 
+ */ 
+ 
+void _wordcopy_fwd_dest_aligned (long int dstp, long int srcp, size_t len) 
+{ 
+    op_t a0, a1, a2, a3; 
+    int sh_1, sh_2; 
+ 
+    /* 
+     * Calculate how to shift a word read at the memory operation aligned 
+     * srcp to make it aligned for copy. 
+     */ 
+    sh_1 = 8 * (srcp % OPSIZ); 
+    sh_2 = 8 * OPSIZ - sh_1; 
+ 
+    /* 
+     * Make SRCP aligned by rounding it down to the beginning of the `op_t' 
+     * it points in the middle of. 
+     */ 
+    srcp &= -OPSIZ; 
+ 
+    switch (len % 4) { 
+    case 2: 
+        a1 = ((op_t *) srcp)[0]; 
+        a2 = ((op_t *) srcp)[1]; 
+        srcp -= 1 * OPSIZ; 
+        dstp -= 3 * OPSIZ; 
+        len += 2; 
+        goto do1; 
+    case 3: 
+        a0 = ((op_t *) srcp)[0]; 
+        a1 = ((op_t *) srcp)[1]; 
+        srcp -= 0 * OPSIZ; 
+        dstp -= 2 * OPSIZ; 
+        len += 1; 
+        goto do2; 
+    case 0: 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            return; 
+        a3 = ((op_t *) srcp)[0]; 
+        a0 = ((op_t *) srcp)[1]; 
+        srcp -=-1 * OPSIZ; 
+        dstp -= 1 * OPSIZ; 
+        len += 0; 
+        goto do3; 
+    case 1: 
+        a2 = ((op_t *) srcp)[0]; 
+        a3 = ((op_t *) srcp)[1]; 
+        srcp -=-2 * OPSIZ; 
+        dstp -= 0 * OPSIZ; 
+        len -= 1; 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            goto do0; 
+        goto do4;            /* No-op. */ 
+    } 
+ 
+    do { 
+do4: 
+        a0 = ((op_t *) srcp)[0]; 
+        ((op_t *) dstp)[0] = MERGE (a2, sh_1, a3, sh_2); 
+do3: 
+        a1 = ((op_t *) srcp)[1]; 
+        ((op_t *) dstp)[1] = MERGE (a3, sh_1, a0, sh_2); 
+do2: 
+        a2 = ((op_t *) srcp)[2]; 
+        ((op_t *) dstp)[2] = MERGE (a0, sh_1, a1, sh_2); 
+do1: 
+        a3 = ((op_t *) srcp)[3]; 
+        ((op_t *) dstp)[3] = MERGE (a1, sh_1, a2, sh_2); 
+ 
+        srcp += 4 * OPSIZ; 
+        dstp += 4 * OPSIZ; 
+        len -= 4; 
+    } while (len != 0); 
+ 
+    /* 
+     * This is the right position for do0.  Please don't move it into 
+     * the loop. 
+     */ 
+do0: 
+    ((op_t *) dstp)[0] = MERGE (a2, sh_1, a3, sh_2); 
+} 
+ 
+/* 
+ * _wordcopy_bwd_aligned -- Copy block finishing right before 
+ * SRCP to block finishing right before DSTP with LEN `op_t' words (not LEN 
+ * bytes!).  Both SRCP and DSTP should be aligned for memory operations 
+ * on `op_t's. 
+ */ 
+void _wordcopy_bwd_aligned (long int dstp, long int srcp, size_t len) 
+{ 
+    op_t a0, a1; 
+ 
+    switch (len % 8) { 
+    case 2: 
+        srcp -= 2 * OPSIZ; 
+        dstp -= 1 * OPSIZ; 
+        a0 = ((op_t *) srcp)[1]; 
+        len += 6; 
+        goto do1; 
+    case 3: 
+        srcp -= 3 * OPSIZ; 
+        dstp -= 2 * OPSIZ; 
+        a1 = ((op_t *) srcp)[2]; 
+        len += 5; 
+        goto do2; 
+    case 4: 
+        srcp -= 4 * OPSIZ; 
+        dstp -= 3 * OPSIZ; 
+        a0 = ((op_t *) srcp)[3]; 
+        len += 4; 
+        goto do3; 
+    case 5: 
+        srcp -= 5 * OPSIZ; 
+        dstp -= 4 * OPSIZ; 
+        a1 = ((op_t *) srcp)[4]; 
+        len += 3; 
+        goto do4; 
+    case 6: 
+        srcp -= 6 * OPSIZ; 
+        dstp -= 5 * OPSIZ; 
+        a0 = ((op_t *) srcp)[5]; 
+        len += 2; 
+        goto do5; 
+    case 7: 
+        srcp -= 7 * OPSIZ; 
+        dstp -= 6 * OPSIZ; 
+        a1 = ((op_t *) srcp)[6]; 
+        len += 1; 
+        goto do6; 
+    case 0: 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            return; 
+        srcp -= 8 * OPSIZ; 
+        dstp -= 7 * OPSIZ; 
+        a0 = ((op_t *) srcp)[7]; 
+        goto do7; 
+    case 1: 
+        srcp -= 9 * OPSIZ; 
+        dstp -= 8 * OPSIZ; 
+        a1 = ((op_t *) srcp)[8]; 
+        len -= 1; 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            goto do0; 
+        goto do8;            /* No-op.  */ 
+    } 
+ 
+    do { 
+do8: 
+        a0 = ((op_t *) srcp)[7]; 
+        ((op_t *) dstp)[7] = a1; 
+do7: 
+        a1 = ((op_t *) srcp)[6]; 
+        ((op_t *) dstp)[6] = a0; 
+do6: 
+        a0 = ((op_t *) srcp)[5]; 
+        ((op_t *) dstp)[5] = a1; 
+do5: 
+        a1 = ((op_t *) srcp)[4]; 
+        ((op_t *) dstp)[4] = a0; 
+do4: 
+        a0 = ((op_t *) srcp)[3]; 
+        ((op_t *) dstp)[3] = a1; 
+do3: 
+        a1 = ((op_t *) srcp)[2]; 
+        ((op_t *) dstp)[2] = a0; 
+do2: 
+        a0 = ((op_t *) srcp)[1]; 
+        ((op_t *) dstp)[1] = a1; 
+do1: 
+        a1 = ((op_t *) srcp)[0]; 
+        ((op_t *) dstp)[0] = a0; 
+ 
+        srcp -= 8 * OPSIZ; 
+        dstp -= 8 * OPSIZ; 
+        len -= 8; 
+    } while (len != 0); 
+ 
+    /* 
+     * This is the right position for do0.  Please don't move it into 
+     * the loop. 
+     */ 
+do0: 
+    ((op_t *) dstp)[7] = a1; 
+} 
+ 
+/* 
+ * _wordcopy_bwd_dest_aligned -- Copy block finishing right before SRCP to 
+ * block finishing right before DSTP with LEN `op_t' words (not LEN bytes!). 
+ * DSTP should be aligned for memory operations on `op_t', but SRCP must *not* 
+ * be aligned. 
+ */ 
+void _wordcopy_bwd_dest_aligned (long int dstp, long int srcp, size_t len) 
+{ 
+    op_t a0, a1, a2, a3; 
+    int sh_1, sh_2; 
+ 
+    /* 
+     * Calculate how to shift a word read at the memory operation aligned 
+     * srcp to make it aligned for copy. 
+     */ 
+ 
+    sh_1 = 8 * (srcp % OPSIZ); 
+    sh_2 = 8 * OPSIZ - sh_1; 
+ 
+    /* 
+     * Make srcp aligned by rounding it down to the beginning of the op_t 
+     * it points in the middle of. 
+     */ 
+    srcp &= -OPSIZ; 
+    srcp += OPSIZ; 
+ 
+    switch (len % 4) { 
+    case 2: 
+        srcp -= 3 * OPSIZ; 
+        dstp -= 1 * OPSIZ; 
+        a2 = ((op_t *) srcp)[2]; 
+        a1 = ((op_t *) srcp)[1]; 
+        len += 2; 
+        goto do1; 
+    case 3: 
+        srcp -= 4 * OPSIZ; 
+        dstp -= 2 * OPSIZ; 
+        a3 = ((op_t *) srcp)[3]; 
+        a2 = ((op_t *) srcp)[2]; 
+        len += 1; 
+        goto do2; 
+    case 0: 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            return; 
+        srcp -= 5 * OPSIZ; 
+        dstp -= 3 * OPSIZ; 
+        a0 = ((op_t *) srcp)[4]; 
+        a3 = ((op_t *) srcp)[3]; 
+        goto do3; 
+    case 1: 
+        srcp -= 6 * OPSIZ; 
+        dstp -= 4 * OPSIZ; 
+        a1 = ((op_t *) srcp)[5]; 
+        a0 = ((op_t *) srcp)[4]; 
+        len -= 1; 
+        if (OP_T_THRESHOLD <= 3 * OPSIZ && len == 0) 
+            goto do0; 
+        goto do4;            /* No-op.  */ 
+    } 
+ 
+    do { 
+do4: 
+        a3 = ((op_t *) srcp)[3]; 
+        ((op_t *) dstp)[3] = MERGE (a0, sh_1, a1, sh_2); 
+do3: 
+        a2 = ((op_t *) srcp)[2]; 
+        ((op_t *) dstp)[2] = MERGE (a3, sh_1, a0, sh_2); 
+do2: 
+        a1 = ((op_t *) srcp)[1]; 
+        ((op_t *) dstp)[1] = MERGE (a2, sh_1, a3, sh_2); 
+do1: 
+        a0 = ((op_t *) srcp)[0]; 
+        ((op_t *) dstp)[0] = MERGE (a1, sh_1, a2, sh_2); 
+ 
+        srcp -= 4 * OPSIZ; 
+        dstp -= 4 * OPSIZ; 
+        len -= 4; 
+    } while (len != 0); 
+ 
+    /* 
+     * This is the right position for do0.  Please don't move it into 
+     * the loop. 
+     */ 
+do0: 
+    ((op_t *) dstp)[3] = MERGE (a0, sh_1, a1, sh_2); 
+} 
+ 
diff --git a/lib/nlattr.c b/lib/nlattr.c
index ac09f2226dc..a8408b6cacd 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -20,6 +20,7 @@ static const u16 nla_attr_minlen[NLA_TYPE_MAX+1] = {
         [NLA_U16]       = sizeof(u16),
         [NLA_U32]       = sizeof(u32),
         [NLA_U64]       = sizeof(u64),
+        [NLA_MSECS]     = sizeof(u64),
         [NLA_NESTED]    = NLA_HDRLEN,
 };
 
diff --git a/lib/plist.c b/lib/plist.c
index 0ae7e643172..a0a4da489c2 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -56,11 +56,6 @@ static void plist_check_list(struct list_head *top)
 
 static void plist_check_head(struct plist_head *head)
 {
-        WARN_ON(head != &test_head && !head->rawlock && !head->spinlock);
-        if (head->rawlock)
-                WARN_ON_SMP(!raw_spin_is_locked(head->rawlock));
-        if (head->spinlock)
-                WARN_ON_SMP(!spin_is_locked(head->spinlock));
         if (!plist_head_empty(head))
                 plist_check_list(&plist_first(head)->prio_list);
         plist_check_list(&head->node_list);
@@ -180,7 +175,7 @@ static int  __init plist_test(void)
         unsigned int r = local_clock();
 
         printk(KERN_INFO "start plist test\n");
-        plist_head_init(&test_head, NULL);
+        plist_head_init(&test_head);
         for (i = 0; i < ARRAY_SIZE(test_node); i++)
                 plist_node_init(test_node + i, 0);
 
diff --git a/lib/sha1.c b/lib/sha1.c
index 4c45fd50e91..f33271dd00c 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -1,31 +1,72 @@
 /*
- * SHA transform algorithm, originally taken from code written by
- * Peter Gutmann, and placed in the public domain.
+ * SHA1 routine optimized to do word accesses rather than byte accesses,
+ * and to avoid unnecessary copies into the context array.
+ *
+ * This was based on the git SHA1 implementation.
  */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/cryptohash.h>
+#include <linux/bitops.h>
+#include <asm/unaligned.h>
 
-/* The SHA f()-functions.  */
+/*
+ * If you have 32 registers or more, the compiler can (and should)
+ * try to change the array[] accesses into registers. However, on
+ * machines with less than ~25 registers, that won't really work,
+ * and at least gcc will make an unholy mess of it.
+ *
+ * So to avoid that mess which just slows things down, we force
+ * the stores to memory to actually happen (we might be better off
+ * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
+ * suggested by Artur Skawina - that will also make gcc unable to
+ * try to do the silly "optimize away loads" part because it won't
+ * see what the value will be).
+ *
+ * Ben Herrenschmidt reports that on PPC, the C version comes close
+ * to the optimized asm with this (ie on PPC you don't want that
+ * 'volatile', since there are lots of registers).
+ *
+ * On ARM we get the best code generation by forcing a full memory barrier
+ * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
+ * the stack frame size simply explode and performance goes down the drain.
+ */
 
-#define f1(x,y,z)   (z ^ (x & (y ^ z)))         /* x ? y : z */
-#define f2(x,y,z)   (x ^ y ^ z)                 /* XOR */
-#define f3(x,y,z)   ((x & y) + (z & (x ^ y)))   /* majority */
+#ifdef CONFIG_X86
+  #define setW(x, val) (*(volatile __u32 *)&W(x) = (val))
+#elif defined(CONFIG_ARM)
+  #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
+#else
+  #define setW(x, val) (W(x) = (val))
+#endif
 
-/* The SHA Mysterious Constants */
+/* This "rolls" over the 512-bit array */
+#define W(x) (array[(x)&15])
 
-#define K1  0x5A827999L                 /* Rounds  0-19: sqrt(2) * 2^30 */
-#define K2  0x6ED9EBA1L                 /* Rounds 20-39: sqrt(3) * 2^30 */
-#define K3  0x8F1BBCDCL                 /* Rounds 40-59: sqrt(5) * 2^30 */
-#define K4  0xCA62C1D6L                 /* Rounds 60-79: sqrt(10) * 2^30 */
+/*
+ * Where do we get the source from? The first 16 iterations get it from
+ * the input data, the next mix it from the 512-bit array.
+ */
+#define SHA_SRC(t) get_unaligned_be32((__u32 *)data + t)
+#define SHA_MIX(t) rol32(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)
+
+#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
+        __u32 TEMP = input(t); setW(t, TEMP); \
+        E += TEMP + rol32(A,5) + (fn) + (constant); \
+        B = ror32(B, 2); } while (0)
+
+#define T_0_15(t, A, B, C, D, E)  SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
+#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
+#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )
 
 /**
  * sha_transform - single block SHA1 transform
  *
  * @digest: 160 bit digest to update
  * @data:   512 bits of data to hash
- * @W:      80 words of workspace (see note)
+ * @array:  16 words of workspace (see note)
  *
  * This function generates a SHA1 digest for a single 512-bit block.
  * Be warned, it does not handle padding and message digest, do not
@@ -36,47 +77,111 @@
  * to clear the workspace. This is left to the caller to avoid
  * unnecessary clears between chained hashing operations.
  */
-void sha_transform(__u32 *digest, const char *in, __u32 *W)
+void sha_transform(__u32 *digest, const char *data, __u32 *array)
 {
-        __u32 a, b, c, d, e, t, i;
-
-        for (i = 0; i < 16; i++)
-                W[i] = be32_to_cpu(((const __be32 *)in)[i]);
-
-        for (i = 0; i < 64; i++)
-                W[i+16] = rol32(W[i+13] ^ W[i+8] ^ W[i+2] ^ W[i], 1);
-
-        a = digest[0];
-        b = digest[1];
-        c = digest[2];
-        d = digest[3];
-        e = digest[4];
-
-        for (i = 0; i < 20; i++) {
-                t = f1(b, c, d) + K1 + rol32(a, 5) + e + W[i];
-                e = d; d = c; c = rol32(b, 30); b = a; a = t;
-        }
-
-        for (; i < 40; i ++) {
-                t = f2(b, c, d) + K2 + rol32(a, 5) + e + W[i];
-                e = d; d = c; c = rol32(b, 30); b = a; a = t;
-        }
-
-        for (; i < 60; i ++) {
-                t = f3(b, c, d) + K3 + rol32(a, 5) + e + W[i];
-                e = d; d = c; c = rol32(b, 30); b = a; a = t;
-        }
-
-        for (; i < 80; i ++) {
-                t = f2(b, c, d) + K4 + rol32(a, 5) + e + W[i];
-                e = d; d = c; c = rol32(b, 30); b = a; a = t;
-        }
-
-        digest[0] += a;
-        digest[1] += b;
-        digest[2] += c;
-        digest[3] += d;
-        digest[4] += e;
+        __u32 A, B, C, D, E;
+
+        A = digest[0];
+        B = digest[1];
+        C = digest[2];
+        D = digest[3];
+        E = digest[4];
+
+        /* Round 1 - iterations 0-16 take their input from 'data' */
+        T_0_15( 0, A, B, C, D, E);
+        T_0_15( 1, E, A, B, C, D);
+        T_0_15( 2, D, E, A, B, C);
+        T_0_15( 3, C, D, E, A, B);
+        T_0_15( 4, B, C, D, E, A);
+        T_0_15( 5, A, B, C, D, E);
+        T_0_15( 6, E, A, B, C, D);
+        T_0_15( 7, D, E, A, B, C);
+        T_0_15( 8, C, D, E, A, B);
+        T_0_15( 9, B, C, D, E, A);
+        T_0_15(10, A, B, C, D, E);
+        T_0_15(11, E, A, B, C, D);
+        T_0_15(12, D, E, A, B, C);
+        T_0_15(13, C, D, E, A, B);
+        T_0_15(14, B, C, D, E, A);
+        T_0_15(15, A, B, C, D, E);
+
+        /* Round 1 - tail. Input from 512-bit mixing array */
+        T_16_19(16, E, A, B, C, D);
+        T_16_19(17, D, E, A, B, C);
+        T_16_19(18, C, D, E, A, B);
+        T_16_19(19, B, C, D, E, A);
+
+        /* Round 2 */
+        T_20_39(20, A, B, C, D, E);
+        T_20_39(21, E, A, B, C, D);
+        T_20_39(22, D, E, A, B, C);
+        T_20_39(23, C, D, E, A, B);
+        T_20_39(24, B, C, D, E, A);
+        T_20_39(25, A, B, C, D, E);
+        T_20_39(26, E, A, B, C, D);
+        T_20_39(27, D, E, A, B, C);
+        T_20_39(28, C, D, E, A, B);
+        T_20_39(29, B, C, D, E, A);
+        T_20_39(30, A, B, C, D, E);
+        T_20_39(31, E, A, B, C, D);
+        T_20_39(32, D, E, A, B, C);
+        T_20_39(33, C, D, E, A, B);
+        T_20_39(34, B, C, D, E, A);
+        T_20_39(35, A, B, C, D, E);
+        T_20_39(36, E, A, B, C, D);
+        T_20_39(37, D, E, A, B, C);
+        T_20_39(38, C, D, E, A, B);
+        T_20_39(39, B, C, D, E, A);
+
+        /* Round 3 */
+        T_40_59(40, A, B, C, D, E);
+        T_40_59(41, E, A, B, C, D);
+        T_40_59(42, D, E, A, B, C);
+        T_40_59(43, C, D, E, A, B);
+        T_40_59(44, B, C, D, E, A);
+        T_40_59(45, A, B, C, D, E);
+        T_40_59(46, E, A, B, C, D);
+        T_40_59(47, D, E, A, B, C);
+        T_40_59(48, C, D, E, A, B);
+        T_40_59(49, B, C, D, E, A);
+        T_40_59(50, A, B, C, D, E);
+        T_40_59(51, E, A, B, C, D);
+        T_40_59(52, D, E, A, B, C);
+        T_40_59(53, C, D, E, A, B);
+        T_40_59(54, B, C, D, E, A);
+        T_40_59(55, A, B, C, D, E);
+        T_40_59(56, E, A, B, C, D);
+        T_40_59(57, D, E, A, B, C);
+        T_40_59(58, C, D, E, A, B);
+        T_40_59(59, B, C, D, E, A);
+
+        /* Round 4 */
+        T_60_79(60, A, B, C, D, E);
+        T_60_79(61, E, A, B, C, D);
+        T_60_79(62, D, E, A, B, C);
+        T_60_79(63, C, D, E, A, B);
+        T_60_79(64, B, C, D, E, A);
+        T_60_79(65, A, B, C, D, E);
+        T_60_79(66, E, A, B, C, D);
+        T_60_79(67, D, E, A, B, C);
+        T_60_79(68, C, D, E, A, B);
+        T_60_79(69, B, C, D, E, A);
+        T_60_79(70, A, B, C, D, E);
+        T_60_79(71, E, A, B, C, D);
+        T_60_79(72, D, E, A, B, C);
+        T_60_79(73, C, D, E, A, B);
+        T_60_79(74, B, C, D, E, A);
+        T_60_79(75, A, B, C, D, E);
+        T_60_79(76, E, A, B, C, D);
+        T_60_79(77, D, E, A, B, C);
+        T_60_79(78, C, D, E, A, B);
+        T_60_79(79, B, C, D, E, A);
+
+        digest[0] += A;
+        digest[1] += B;
+        digest[2] += C;
+        digest[3] += D;
+        digest[4] += E;
 }
 EXPORT_SYMBOL(sha_transform);
 
@@ -92,4 +197,3 @@ void sha_init(__u32 *buf)
         buf[3] = 0x10325476;
         buf[4] = 0xc3d2e1f0;
 }
-
diff --git a/lib/string.c b/lib/string.c
index 01fad9b203e..ed166883858 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -23,6 +23,7 @@
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
+#include <linux/memcopy.h>
 
 #ifndef __HAVE_ARCH_STRNICMP
 /**
@@ -596,11 +597,11 @@ EXPORT_SYMBOL(memset);
  */
 void *memcpy(void *dest, const void *src, size_t count)
 {
-        char *tmp = dest;
-        const char *s = src;
+        unsigned long dstp = (unsigned long)dest; 
+        unsigned long srcp = (unsigned long)src; 
 
-        while (count--)
-                *tmp++ = *s++;
+        /* Copy from the beginning to the end */ 
+        mem_copy_fwd(dstp, srcp, count); 
         return dest;
 }
 EXPORT_SYMBOL(memcpy);
@@ -617,21 +618,15 @@ EXPORT_SYMBOL(memcpy);
  */
 void *memmove(void *dest, const void *src, size_t count)
 {
-        char *tmp;
-        const char *s;
+        unsigned long dstp = (unsigned long)dest; 
+        unsigned long srcp = (unsigned long)src; 
 
-        if (dest <= src) {
-                tmp = dest;
-                s = src;
-                while (count--)
-                        *tmp++ = *s++;
+        if (dest - src >= count) { 
+                /* Copy from the beginning to the end */ 
+                mem_copy_fwd(dstp, srcp, count); 
         } else {
-                tmp = dest;
-                tmp += count;
-                s = src;
-                s += count;
-                while (count--)
-                        *--tmp = *--s;
+                /* Copy from the end to the beginning */ 
+                mem_copy_bwd(dstp, srcp, count); 
         }
         return dest;
 }
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index e51e2558ca9..a768e6d28bb 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -441,8 +441,12 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
          * next filter in the chain. Apply the BCJ filter on the new data
          * in the output buffer. If everything cannot be filtered, copy it
          * to temp and rewind the output buffer position accordingly.
+         *
+         * This needs to be always run when temp.size == 0 to handle a special
+         * case where the output buffer is full and the next filter has no
+         * more output coming but hasn't returned XZ_STREAM_END yet.
          */
-        if (s->temp.size < b->out_size - b->out_pos) {
+        if (s->temp.size < b->out_size - b->out_pos || s->temp.size == 0) {
                 out_start = b->out_pos;
                 memcpy(b->out + b->out_pos, s->temp.buf, s->temp.size);
                 b->out_pos += s->temp.size;
@@ -465,16 +469,25 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
                 s->temp.size = b->out_pos - out_start;
                 b->out_pos -= s->temp.size;
                 memcpy(s->temp.buf, b->out + b->out_pos, s->temp.size);
+
+                /*
+                 * If there wasn't enough input to the next filter to fill
+                 * the output buffer with unfiltered data, there's no point
+                 * to try decoding more data to temp.
+                 */
+                if (b->out_pos + s->temp.size < b->out_size)
+                        return XZ_OK;
         }
 
         /*
-         * If we have unfiltered data in temp, try to fill by decoding more
-         * data from the next filter. Apply the BCJ filter on temp. Then we
-         * hopefully can fill the actual output buffer by copying filtered
-         * data from temp. A mix of filtered and unfiltered data may be left
-         * in temp; it will be taken care on the next call to this function.
+         * We have unfiltered data in temp. If the output buffer isn't full
+         * yet, try to fill the temp buffer by decoding more data from the
+         * next filter. Apply the BCJ filter on temp. Then we hopefully can
+         * fill the actual output buffer by copying filtered data from temp.
+         * A mix of filtered and unfiltered data may be left in temp; it will
+         * be taken care on the next call to this function.
          */
-        if (s->temp.size > 0) {
+        if (b->out_pos < b->out_size) {
                 /* Make b->out{,_pos,_size} temporarily point to s->temp. */
                 s->out = b->out;
                 s->out_pos = b->out_pos;
diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c
index ac809b1e64f..9a60cc21964 100644
--- a/lib/xz/xz_dec_stream.c
+++ b/lib/xz/xz_dec_stream.c
@@ -9,6 +9,7 @@
 
 #include "xz_private.h"
 #include "xz_stream.h"
+#include <linux/kernel.h>
 
 /* Hash used to validate the Index field */
 struct xz_dec_hash {
diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h
index a65633e0696..482b90f363f 100644
--- a/lib/xz/xz_private.h
+++ b/lib/xz/xz_private.h
@@ -12,7 +12,7 @@
 
 #ifdef __KERNEL__
 #       include <linux/xz.h>
-#       include <asm/byteorder.h>
+#       include <linux/kernel.h>
 #       include <asm/unaligned.h>
         /* XZ_PREBOOT may be defined only via decompress_unxz.c. */
 #       ifndef XZ_PREBOOT