[v10,09/24] string: Improve generic strncmp

Message ID 20230120211622.3445279-10-adhemerval.zanella@linaro.org
State Superseded
Headers
Series Improve generic string routines |

Checks

Context Check Description
dj/TryBot-apply_patch success Patch applied to master at the time it was sent

Commit Message

Adhemerval Zanella Netto Jan. 20, 2023, 9:16 p.m. UTC
  New generic implementation tries to use word operations along with
the new string-fz{b,i} functions even for inputs with different
alignments (with still uses aligned access plus merge operation
to get a correct word by word comparison).

Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
---
 string/strcmp-impl.h |  41 ++++++++++++++
 string/strcmp.c      |  23 ++------
 string/strncmp.c     | 130 +++++++++++++++++++++++++++++++------------
 3 files changed, 138 insertions(+), 56 deletions(-)
 create mode 100644 string/strcmp-impl.h
  

Patch

diff --git a/string/strcmp-impl.h b/string/strcmp-impl.h
new file mode 100644
index 0000000000..618240368a
--- /dev/null
+++ b/string/strcmp-impl.h
@@ -0,0 +1,41 @@ 
+/* Common definition for string compare implementations.
+   Copyright (C) 2023 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library 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
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <https://www.gnu.org/licenses/>.  */
+
+#ifndef _STRCMP_IMPL_H
+#define _STRCMP_IMPL_H
+
+#include <stddef.h>
+#include <string-misc.h>
+
+static inline int
+final_cmp (const op_t w1, const op_t w2, size_t n)
+{
+  /* It can not use index_first_zero_ne because it must not compare past the
+     final '\0' is present (and final_cmp is called before has_zero check).
+   */
+  for (size_t i = 0; i < n; i++)
+    {
+      unsigned char c1 = extractbyte (w1, i);
+      unsigned char c2 = extractbyte (w2, i);
+      if (c1 == '\0' || c1 != c2)
+        return c1 - c2;
+    }
+  return 0;
+}
+
+#endif
diff --git a/string/strcmp.c b/string/strcmp.c
index 42e24242b6..8e7b3310db 100644
--- a/string/strcmp.c
+++ b/string/strcmp.c
@@ -16,6 +16,7 @@ 
    <https://www.gnu.org/licenses/>.  */
 
 #include <stdint.h>
+#include <strcmp-impl.h>
 #include <string-fzb.h>
 #include <string-fzi.h>
 #include <string.h>
@@ -25,22 +26,6 @@ 
 # define strcmp STRCMP
 #endif
 
-static inline int
-final_cmp (const op_t w1, const op_t w2)
-{
-  /* It can not use index_first_zero_ne because it must not compare past the
-     final '\0' is present (and final_cmp is called before has_zero check).
-   */
-  for (size_t i = 0; i < sizeof (op_t); i++)
-    {
-      unsigned char c1 = extractbyte (w1, i);
-      unsigned char c2 = extractbyte (w2, i);
-      if (c1 == '\0' || c1 != c2)
-        return c1 - c2;
-    }
-  return 0;
-}
-
 /* Aligned loop: if a difference is found, exit to compare the bytes.  Else
    if a zero is found we have equal strings.  */
 static inline int
@@ -56,7 +41,7 @@  strcmp_aligned_loop (const op_t *x1, const op_t *x2, op_t w1)
       w2 = *x2++;
     }
 
-  return final_cmp (w1, w2);
+  return final_cmp (w1, w2, sizeof (op_t));
 }
 
 /* Unaligned loop: align the first partial of P2, with 0xff for the rest of
@@ -83,7 +68,7 @@  strcmp_unaligned_loop (const op_t *x1, const op_t *x2, op_t w1, uintptr_t ofs)
 	  w2b = *x2++;
 	  w2 = MERGE (w2a, sh_1, w2b, sh_2);
 	  if (w1 != w2)
-	    return final_cmp (w1, w2);
+	    return final_cmp (w1, w2, sizeof (op_t));
 	  if (has_zero (w2b))
 	    break;
 	  w1 = *x1++;
@@ -100,7 +85,7 @@  strcmp_unaligned_loop (const op_t *x1, const op_t *x2, op_t w1, uintptr_t ofs)
       w2 = MERGE (w2b, sh_1, 0, sh_2);
     }
 
-  return final_cmp (w1, w2);
+  return final_cmp (w1, w2, sizeof (op_t));
 }
 
 /* Compare S1 and S2, returning less than, equal to or
diff --git a/string/strncmp.c b/string/strncmp.c
index fd7cee09b6..3e6040df09 100644
--- a/string/strncmp.c
+++ b/string/strncmp.c
@@ -15,7 +15,13 @@ 
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
+#include <stdint.h>
+#include <strcmp-impl.h>
+#include <string-fza.h>
+#include <string-fzb.h>
+#include <string-fzi.h>
 #include <string.h>
+#include <sys/param.h>
 #include <memcopy.h>
 
 #undef strncmp
@@ -24,51 +30,101 @@ 
 #define STRNCMP strncmp
 #endif
 
-/* Compare no more than N characters of S1 and S2,
-   returning less than, equal to or greater than zero
-   if S1 is lexicographically less than, equal to or
-   greater than S2.  */
-int
-STRNCMP (const char *s1, const char *s2, size_t n)
+/* Aligned loop: if a difference is found, exit to compare the bytes.  Else
+   if a zero is found we have equal strings.  */
+static inline int
+strncmp_aligned_loop (const op_t *x1, const op_t *x2, op_t w1, size_t n)
 {
-  unsigned char c1 = '\0';
-  unsigned char c2 = '\0';
+  op_t w2 = *x2++;
 
-  if (n >= 4)
+  while (w1 == w2)
     {
-      size_t n4 = n >> 2;
-      do
-	{
-	  c1 = (unsigned char) *s1++;
-	  c2 = (unsigned char) *s2++;
-	  if (c1 == '\0' || c1 != c2)
-	    return c1 - c2;
-	  c1 = (unsigned char) *s1++;
-	  c2 = (unsigned char) *s2++;
-	  if (c1 == '\0' || c1 != c2)
-	    return c1 - c2;
-	  c1 = (unsigned char) *s1++;
-	  c2 = (unsigned char) *s2++;
-	  if (c1 == '\0' || c1 != c2)
-	    return c1 - c2;
-	  c1 = (unsigned char) *s1++;
-	  c2 = (unsigned char) *s2++;
-	  if (c1 == '\0' || c1 != c2)
-	    return c1 - c2;
-	} while (--n4 > 0);
-      n &= 3;
+      if (n <= sizeof (op_t))
+	break;
+      n -= sizeof (op_t);
+
+      if (has_zero (w1))
+	return 0;
+      w1 = *x1++;
+      w2 = *x2++;
     }
 
-  while (n > 0)
+  return final_cmp (w1, w2, n);
+}
+
+/* Unaligned loop: align the first partial of P2, with 0xff for the rest of
+   the bytes so that we can also apply the has_zero test to see if we have
+   already reached EOS.  If we have, then we can simply fall through to the
+   final comparison.  */
+static inline int
+strncmp_unaligned_loop (const op_t *x1, const op_t *x2, op_t w1, uintptr_t ofs,
+			size_t n)
+{
+  op_t w2a = *x2++;
+  uintptr_t sh_1 = ofs * CHAR_BIT;
+  uintptr_t sh_2 = sizeof(op_t) * CHAR_BIT - sh_1;
+
+  op_t w2 = MERGE (w2a, sh_1, (op_t)-1, sh_2);
+  if (!has_zero (w2) && n > (sizeof (op_t) - ofs))
     {
-      c1 = (unsigned char) *s1++;
-      c2 = (unsigned char) *s2++;
-      if (c1 == '\0' || c1 != c2)
-	return c1 - c2;
-      n--;
+      op_t w2b;
+
+      /* Unaligned loop.  The invariant is that W2B, which is "ahead" of W1,
+	 does not contain end-of-string.  Therefore it is safe (and necessary)
+	 to read another word from each while we do not have a difference.  */
+      while (1)
+	{
+	  w2b = *x2++;
+	  w2 = MERGE (w2a, sh_1, w2b, sh_2);
+	  if (n <= sizeof (op_t) || w1 != w2)
+	    return final_cmp (w1, w2, n);
+	  n -= sizeof(op_t);
+	  if (has_zero (w2b) || n <= (sizeof (op_t) - ofs))
+	    break;
+	  w1 = *x1++;
+	  w2a = w2b;
+	}
+
+      /* Zero found in the second partial of P2.  If we had EOS in the aligned
+	 word, we have equality.  */
+      if (has_zero (w1))
+	return 0;
+
+      /* Load the final word of P1 and align the final partial of P2.  */
+      w1 = *x1++;
+      w2 = MERGE (w2b, sh_1, 0, sh_2);
     }
 
-  return c1 - c2;
+  return final_cmp (w1, w2, n);
 }
 
+/* Compare no more than N characters of S1 and S2,
+   returning less than, equal to or greater than zero
+   if S1 is lexicographically less than, equal to or
+   greater than S2.  */
+int
+STRNCMP (const char *p1, const char *p2, size_t n)
+{
+  /* Handle the unaligned bytes of p1 first.  */
+  uintptr_t a = MIN (-(uintptr_t)p1 % sizeof(op_t), n);
+  int diff = 0;
+  for (int i = 0; i < a; ++i)
+    {
+      unsigned char c1 = *p1++;
+      unsigned char c2 = *p2++;
+      diff = c1 - c2;
+      if (c1 == '\0' || diff != 0)
+	return diff;
+    }
+  if (a == n)
+    return diff;
+
+  /* P1 is now aligned to op_t.  P2 may or may not be.  */
+  const op_t *x1 = (const op_t *) p1;
+  op_t w1 = *x1++;
+  uintptr_t ofs = (uintptr_t) p2 % sizeof(op_t);
+  return ofs == 0
+    ? strncmp_aligned_loop (x1, (const op_t *) p2, w1, n - a)
+    : strncmp_unaligned_loop (x1, (const op_t *) (p2 - ofs), w1, ofs, n - a);
+}
 libc_hidden_builtin_def (STRNCMP)