Improve performance of strstr

This patch significantly improves performance of strstr using a novel
modified Horspool algorithm.  Needles up to size 256 use a bad-character
table indexed by hashed pairs of characters to quickly skip past mismatches.
Long needles use a self-adapting filtering step to avoid comparing the whole
needle repeatedly.

By limiting the needle length to 256, the shift table only requires 8 bits
per entry, lowering preprocessing overhead and minimizing cache effects.
This limit also implies worst-case performance is linear.

Small needles up to size 3 use a dedicated linear search.  Very long needles
use the Two-Way algorithm.

The performance gain using the improved bench-strstr on Cortex-A72 is 5.8
times basic_strstr and 3.7 times twoway_strstr.

Tested against GLIBC testsuite, randomized tests and the GNULIB strstr test
(https://git.savannah.gnu.org/cgit/gnulib.git/tree/tests/test-strstr.c).

Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>

	* string/str-two-way.h (two_way_short_needle): Add inline to avoid
	warning.
	(two_way_long_needle): Block inlining.
	* string/strstr.c (strstr2): Add new function.
	(strstr3): Likewise.
	(STRSTR): Completely rewrite strstr to improve performance.

3 files changed, 132 insertions, 51 deletions

diff --git a/ChangeLog b/ChangeLog
index 2c9836d4e6..7ddec5412b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2019-06-12  Wilco Dijkstra  <wdijkstr@arm.com>
+
+	* string/str-two-way.h (two_way_short_needle): Add inline to avoid
+	warning.
+	(two_way_long_needle): Block inlining.
+	* string/strstr.c (strstr2): Add new function.
+	(strstr3): Likewise.
+	(STRSTR): Completely rewrite strstr to improve performance.
+
 2019-06-11  Wilco Dijkstra  <wdijkstr@arm.com>
 
 	* benchtests/bench-strstr.c (test_hard_needle): New function.
diff --git a/string/str-two-way.h b/string/str-two-way.h
index b5011baafa..f43c613f5a 100644
--- a/string/str-two-way.h
+++ b/string/str-two-way.h
@@ -221,7 +221,7 @@ critical_factorization (const unsigned char *needle, size_t needle_len,
    most 2 * HAYSTACK_LEN - NEEDLE_LEN comparisons occur in searching.
    If AVAILABLE modifies HAYSTACK_LEN (as in strstr), then at most 3 *
    HAYSTACK_LEN - NEEDLE_LEN comparisons occur in searching.  */
-static RETURN_TYPE
+static inline RETURN_TYPE
 two_way_short_needle (const unsigned char *haystack, size_t haystack_len,
 		      const unsigned char *needle, size_t needle_len)
 {
@@ -382,8 +382,11 @@ two_way_short_needle (const unsigned char *haystack, size_t haystack_len,
    and sublinear performance O(HAYSTACK_LEN / NEEDLE_LEN) is possible.
    If AVAILABLE modifies HAYSTACK_LEN (as in strstr), then at most 3 *
    HAYSTACK_LEN - NEEDLE_LEN comparisons occur in searching, and
-   sublinear performance is not possible.  */
-static RETURN_TYPE
+   sublinear performance is not possible.
+
+   Since this function is large and complex, block inlining to avoid
+   slowing down the common case of small needles.  */
+__attribute__((noinline)) static RETURN_TYPE
 two_way_long_needle (const unsigned char *haystack, size_t haystack_len,
 		     const unsigned char *needle, size_t needle_len)
 {
diff --git a/string/strstr.c b/string/strstr.c
index 64e478b9e7..408cce8ed5 100644
--- a/string/strstr.c
+++ b/string/strstr.c
@@ -16,29 +16,17 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-/* This particular implementation was written by Eric Blake, 2008.  */
-
 #ifndef _LIBC
 # include <config.h>
 #endif
 
-/* Specification of strstr.  */
 #include <string.h>
 
-#include <stdbool.h>
-
-#ifndef _LIBC
-# define __builtin_expect(expr, val)   (expr)
-#endif
-
 #define RETURN_TYPE char *
 #define AVAILABLE(h, h_l, j, n_l)			\
   (((j) + (n_l) <= (h_l)) \
    || ((h_l) += __strnlen ((void*)((h) + (h_l)), (n_l) + 512), \
        (j) + (n_l) <= (h_l)))
-#define CHECK_EOL (1)
-#define RET0_IF_0(a) if (!a) goto ret0
-#define FASTSEARCH(S,C,N) (void*) strchr ((void*)(S), (C))
 #include "str-two-way.h"
 
 #undef strstr
@@ -47,47 +35,128 @@
 #define STRSTR strstr
 #endif
 
-/* Return the first occurrence of NEEDLE in HAYSTACK.  Return HAYSTACK
-   if NEEDLE is empty, otherwise NULL if NEEDLE is not found in
-   HAYSTACK.  */
-char *
-STRSTR (const char *haystack, const char *needle)
+static inline char *
+strstr2 (const unsigned char *hs, const unsigned char *ne)
 {
-  size_t needle_len; /* Length of NEEDLE.  */
-  size_t haystack_len; /* Known minimum length of HAYSTACK.  */
-
-  /* Handle empty NEEDLE special case.  */
-  if (needle[0] == '\0')
-    return (char *) haystack;
+  uint32_t h1 = (ne[0] << 16) | ne[1];
+  uint32_t h2 = 0;
+  for (int c = hs[0]; h1 != h2 && c != 0; c = *++hs)
+      h2 = (h2 << 16) | c;
+  return h1 == h2 ? (char *)hs - 2 : NULL;
+}
 
-  /* Skip until we find the first matching char from NEEDLE.  */
-  haystack = strchr (haystack, needle[0]);
-  if (haystack == NULL || needle[1] == '\0')
-    return (char *) haystack;
+static inline char *
+strstr3 (const unsigned char *hs, const unsigned char *ne)
+{
+  uint32_t h1 = ((uint32_t)ne[0] << 24) | (ne[1] << 16) | (ne[2] << 8);
+  uint32_t h2 = 0;
+  for (int c = hs[0]; h1 != h2 && c != 0; c = *++hs)
+      h2 = (h2 | c) << 8;
+  return h1 == h2 ? (char *)hs - 3 : NULL;
+}
 
-  /* Ensure HAYSTACK length is at least as long as NEEDLE length.
-     Since a match may occur early on in a huge HAYSTACK, use strnlen
+/* Hash character pairs so a small shift table can be used.  All bits of
+   p[0] are included, but not all bits from p[-1].  So if two equal hashes
+   match on p[-1], p[0] matches too.  Hash collisions are harmless and result
+   in smaller shifts.  */
+#define hash2(p) (((size_t)(p)[0] - ((size_t)(p)[-1] << 3)) % sizeof (shift))
+
+/* Fast strstr algorithm with guaranteed linear-time performance.
+   Small needles up to size 3 use a dedicated linear search.  Longer needles
+   up to size 256 use a novel modified Horspool algorithm.  It hashes pairs
+   of characters to quickly skip past mismatches.  The main search loop only
+   exits if the last 2 characters match, avoiding unnecessary calls to memcmp
+   and allowing for a larger skip if there is no match.  A self-adapting
+   filtering check is used to quickly detect mismatches in long needles.
+   By limiting the needle length to 256, the shift table can be reduced to 8
+   bits per entry, lowering preprocessing overhead and minimizing cache effects.
+   The limit also implies worst-case performance is linear.
+   Needles larger than 256 characters use the linear-time Two-Way algorithm.  */
+char *
+STRSTR (const char *haystack, const char *needle)
+{
+  const unsigned char *hs = (const unsigned char *) haystack;
+  const unsigned char *ne = (const unsigned char *) needle;
+
+  /* Handle short needle special cases first.  */
+  if (ne[0] == '\0')
+    return (char *)hs;
+  hs = (const unsigned char *)strchr ((const char*)hs, ne[0]);
+  if (hs == NULL || ne[1] == '\0')
+    return (char*)hs;
+  if (ne[2] == '\0')
+    return strstr2 (hs, ne);
+  if (ne[3] == '\0')
+    return strstr3 (hs, ne);
+
+  /* Ensure haystack length is at least as long as needle length.
+     Since a match may occur early on in a huge haystack, use strnlen
      and read ahead a few cachelines for improved performance.  */
-  needle_len = strlen (needle);
-  haystack_len = __strnlen (haystack, needle_len + 256);
-  if (haystack_len < needle_len)
+  size_t ne_len = strlen ((const char*)ne);
+  size_t hs_len = __strnlen ((const char*)hs, ne_len | 512);
+  if (hs_len < ne_len)
     return NULL;
 
-  /* Check whether we have a match.  This improves performance since we avoid
-     the initialization overhead of the two-way algorithm.  */
-  if (memcmp (haystack, needle, needle_len) == 0)
-    return (char *) haystack;
-
-  /* Perform the search.  Abstract memory is considered to be an array
-     of 'unsigned char' values, not an array of 'char' values.  See
-     ISO C 99 section 6.2.6.1.  */
-  if (needle_len < LONG_NEEDLE_THRESHOLD)
-    return two_way_short_needle ((const unsigned char *) haystack,
-				 haystack_len,
-				 (const unsigned char *) needle, needle_len);
-  return two_way_long_needle ((const unsigned char *) haystack, haystack_len,
-			      (const unsigned char *) needle, needle_len);
+  /* Check whether we have a match.  This improves performance since we
+     avoid initialization overheads.  */
+  if (memcmp (hs, ne, ne_len) == 0)
+    return (char *) hs;
+
+  /* Use Two-Way algorithm for very long needles.  */
+  if (__glibc_unlikely (ne_len > 256))
+    return two_way_long_needle (hs, hs_len, ne, ne_len);
+
+  const unsigned char *end = hs + hs_len - ne_len;
+  uint8_t shift[256];
+  size_t tmp, shift1;
+  size_t m1 = ne_len - 1;
+  size_t offset = 0;
+
+  /* Initialize bad character shift hash table.  */
+  memset (shift, 0, sizeof (shift));
+  for (int i = 1; i < m1; i++)
+    shift[hash2 (ne + i)] = i;
+  /* Shift1 is the amount we can skip after matching the hash of the
+     needle end but not the full needle.  */
+  shift1 = m1 - shift[hash2 (ne + m1)];
+  shift[hash2 (ne + m1)] = m1;
+
+  while (1)
+    {
+      if (__glibc_unlikely (hs > end))
+	{
+	  end += __strnlen ((const char*)end + m1 + 1, 2048);
+	  if (hs > end)
+	    return NULL;
+	}
+
+      /* Skip past character pairs not in the needle.  */
+      do
+	{
+	  hs += m1;
+	  tmp = shift[hash2 (hs)];
+	}
+      while (tmp == 0 && hs <= end);
+
+      /* If the match is not at the end of the needle, shift to the end
+	 and continue until we match the hash of the needle end.  */
+      hs -= tmp;
+      if (tmp < m1)
+	continue;
+
+      /* Hash of the last 2 characters matches.  If the needle is long,
+	 try to quickly filter out mismatches.  */
+      if (m1 < 15 || memcmp (hs + offset, ne + offset, 8) == 0)
+	{
+	  if (memcmp (hs, ne, m1) == 0)
+	    return (void *) hs;
+
+	  /* Adjust filter offset when it doesn't find the mismatch.  */
+	  offset = (offset >= 8 ? offset : m1) - 8;
+	}
+
+      /* Skip based on matching the hash of the needle end.  */
+      hs += shift1;
+    }
 }
 libc_hidden_builtin_def (strstr)
-
-#undef LONG_NEEDLE_THRESHOLD