[BZ #5807]

2009-03-15  Ulrich Drepper  <drepper@redhat.com>
	[BZ #5807]
	* string/strlen.c (strlen): Fix omission in the expression to test
	for NUL bytes.

4 files changed, 36 insertions, 151 deletions

diff --git a/ChangeLog b/ChangeLog
index 83c355e8ab..6e7c4febf4 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2009-03-15  Ulrich Drepper  <drepper@redhat.com>
+
+	[BZ #5807]
+	* string/strlen.c (strlen): Fix omission in the expression to test
+	for NUL bytes.
+
 2009-03-14  Ulrich Drepper  <drepper@redhat.com>
 
 	* crypt/sha256test.c (main): Perform 100,000 'a' test in a second way.
diff --git a/nptl/ChangeLog b/nptl/ChangeLog
index 15e79efdd4..049d3ce395 100644
--- a/nptl/ChangeLog
+++ b/nptl/ChangeLog
@@ -1,3 +1,9 @@
+2009-03-15  Ulrich Drepper  <drepper@redhat.com>
+
+	* sysdeps/unix/sysv/linux/x86_64/pthread_cond_timedwait.S
+	(__pthread_cond_timedwait): Change to use cfi directives instead of
+	hand-coded unwind sections.
+
 2009-03-10  Ulrich Drepper  <drepper@redhat.com>
 
 	* init.c (nptl_freeres): Compile only for SHARED.
diff --git a/nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_timedwait.S b/nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_timedwait.S
index 20bc59db9c..ddcf106a6d 100644
--- a/nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_timedwait.S
+++ b/nptl/sysdeps/unix/sysv/linux/x86_64/pthread_cond_timedwait.S
@@ -1,4 +1,4 @@
-/* Copyright (C) 2002, 2003, 2004, 2005, 2007 Free Software Foundation, Inc.
+/* Copyright (C) 2002-2005, 2007, 2009 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Ulrich Drepper <drepper@redhat.com>, 2002.
 
@@ -37,16 +37,19 @@
 	.type	__pthread_cond_timedwait, @function
 	.align	16
 __pthread_cond_timedwait:
-.LSTARTCODE:
+	cfi_startproc
 	pushq	%r12
-.Lpush_r12:
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%r12, 0)
 	pushq	%r13
-.Lpush_r13:
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%r13, 0)
 	pushq	%r14
-.Lpush_r14:
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%r14, 0)
 #define FRAME_SIZE 80
 	subq	$FRAME_SIZE, %rsp
-.Lsubq:
+	cfi_adjust_cfa_offset(FRAME_SIZE)
 
 	cmpq	$1000000000, 8(%rdx)
 	movl	$EINVAL, %eax
@@ -305,19 +308,25 @@ __pthread_cond_timedwait:
 	cmoveq	%r14, %rax
 
 18:	addq	$FRAME_SIZE, %rsp
-.Laddq:
+	cfi_adjust_cfa_offset(-FRAME_SIZE)
 	popq	%r14
-.Lpop_r14:
+	cfi_adjust_cfa_offset(-8)
+	cfi_restore(%r14)
 	popq	%r13
-.Lpop_r13:
+	cfi_adjust_cfa_offset(-8)
+	cfi_restore(%r13)
 	popq	%r12
-.Lpop_r12:
+	cfi_adjust_cfa_offset(-8)
+	cfi_restore(%r12)
 
 	retq
 
 	/* Initial locking failed.  */
 1:
-.LSbl1:
+	cfi_adjust_cfa_offset(3 * 8 + FRAME_SIZE)
+	cfi_rel_offset(%r12, FRAME_SIZE + 16)
+	cfi_rel_offset(%r13, FRAME_SIZE + 8)
+	cfi_rel_offset(%r14, FRAME_SIZE)
 #if cond_lock != 0
 	addq	$cond_lock, %rdi
 #endif
@@ -414,97 +423,7 @@ __pthread_cond_timedwait:
 	js	6b
 	jmp	21b
 #endif
-.LENDCODE:
+	cfi_endproc
 	.size	__pthread_cond_timedwait, .-__pthread_cond_timedwait
 versioned_symbol (libpthread, __pthread_cond_timedwait, pthread_cond_timedwait,
 		  GLIBC_2_3_2)
-
-
-	.section .eh_frame,"a",@progbits
-.LSTARTFRAME:
-	.long	L(ENDCIE)-L(STARTCIE)		# Length of the CIE.
-.LSTARTCIE:
-	.long	0				# CIE ID.
-	.byte	1				# Version number.
-#ifdef SHARED
-	.string	"zR"				# NUL-terminated augmentation
-						# string.
-#else
-	.ascii	"\0"				# NUL-terminated augmentation
-						# string.
-#endif
-	.uleb128 1				# Code alignment factor.
-	.sleb128 -8				# Data alignment factor.
-	.byte	16				# Return address register
-						# column.
-#ifdef SHARED
-	.uleb128 1				# Augmentation value length.
-	.byte	0x1b				# Encoding: DW_EH_PE_pcrel
-						# + DW_EH_PE_sdata4.
-#endif
-	.byte 0x0c				# DW_CFA_def_cfa
-	.uleb128 7
-	.uleb128 8
-	.byte	0x90				# DW_CFA_offset, column 0x8
-	.uleb128 1
-	.align 8
-.LENDCIE:
-
-	.long	.LENDFDE-.LSTARTFDE		# Length of the FDE.
-.LSTARTFDE:
-	.long	.LSTARTFDE-.LSTARTFRAME		# CIE pointer.
-#ifdef SHARED
-	.long	.LSTARTCODE-.			# PC-relative start address
-						# of the code
-#else
-	.long	.LSTARTCODE			# Start address of the code.
-#endif
-	.long	.LENDCODE-.LSTARTCODE		# Length of the code.
-#ifdef SHARED
-	.uleb128 0				# No augmentation data.
-#endif
-	.byte	0x40+.Lpush_r12-.LSTARTCODE	# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 16
-	.byte	0x8c				# DW_CFA_offset %r12
-	.uleb128 2
-	.byte	0x40+.Lpush_r13-.Lpush_r12	# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 24
-	.byte	0x8d				# DW_CFA_offset %r13
-	.uleb128 3
-	.byte	0x40+.Lpush_r14-.Lpush_r13	# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 32
-	.byte	0x84				# DW_CFA_offset %r14
-	.uleb128 4
-	.byte	0x40+.Lsubq-.Lpush_r14		# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 32+FRAME_SIZE
-	.byte	3				# DW_CFA_advance_loc2
-	.2byte	.Laddq-.Lsubq
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 32
-	.byte	0x40+.Lpop_r14-.Laddq		# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 24
-	.byte	0xce				# DW_CFA_restore %r14
-	.byte	0x40+.Lpop_r13-.Lpop_r14	# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 16
-	.byte	0xcd				# DW_CFA_restore %r13
-	.byte	0x40+.Lpop_r12-.Lpop_r13	# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 8
-	.byte	0xcc				# DW_CFA_restore %r12
-	.byte	0x40+.LSbl1-.Lpop_r12		# DW_CFA_advance_loc+N
-	.byte	14				# DW_CFA_def_cfa_offset
-	.uleb128 32+FRAME_SIZE
-	.byte	0x8c				# DW_CFA_offset %r12
-	.uleb128 2
-	.byte	0x8d				# DW_CFA_offset %r13
-	.uleb128 3
-	.byte	0x84				# DW_CFA_offset %r14
-	.uleb128 4
-	.align	8
-.LENDFDE:
diff --git a/string/strlen.c b/string/strlen.c
index 9bc9db68f7..5f22ce9509 100644
--- a/string/strlen.c
+++ b/string/strlen.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 1991, 1993, 1997, 2000, 2003 Free Software Foundation, Inc.
+/* Copyright (C) 1991,1993,1997,2000,2003,2009 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Written by Torbjorn Granlund (tege@sics.se),
    with help from Dan Sahlin (dan@sics.se);
@@ -32,7 +32,7 @@ strlen (str)
 {
   const char *char_ptr;
   const unsigned long int *longword_ptr;
-  unsigned long int longword, magic_bits, himagic, lomagic;
+  unsigned long int longword, himagic, lomagic;
 
   /* Handle the first few characters by reading one character at a time.
      Do this until CHAR_PTR is aligned on a longword boundary.  */
@@ -56,14 +56,12 @@ strlen (str)
 
      The 1-bits make sure that carries propagate to the next 0-bit.
      The 0-bits provide holes for carries to fall into.  */
-  magic_bits = 0x7efefeffL;
   himagic = 0x80808080L;
   lomagic = 0x01010101L;
   if (sizeof (longword) > 4)
     {
       /* 64-bit version of the magic.  */
       /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
-      magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL;
       himagic = ((himagic << 16) << 16) | himagic;
       lomagic = ((lomagic << 16) << 16) | lomagic;
     }
@@ -75,53 +73,9 @@ strlen (str)
      if *any of the four* bytes in the longword in question are zero.  */
   for (;;)
     {
-      /* We tentatively exit the loop if adding MAGIC_BITS to
-	 LONGWORD fails to change any of the hole bits of LONGWORD.
-
-	 1) Is this safe?  Will it catch all the zero bytes?
-	 Suppose there is a byte with all zeros.  Any carry bits
-	 propagating from its left will fall into the hole at its
-	 least significant bit and stop.  Since there will be no
-	 carry from its most significant bit, the LSB of the
-	 byte to the left will be unchanged, and the zero will be
-	 detected.
-
-	 2) Is this worthwhile?  Will it ignore everything except
-	 zero bytes?  Suppose every byte of LONGWORD has a bit set
-	 somewhere.  There will be a carry into bit 8.  If bit 8
-	 is set, this will carry into bit 16.  If bit 8 is clear,
-	 one of bits 9-15 must be set, so there will be a carry
-	 into bit 16.  Similarly, there will be a carry into bit
-	 24.  If one of bits 24-30 is set, there will be a carry
-	 into bit 31, so all of the hole bits will be changed.
-
-	 The one misfire occurs when bits 24-30 are clear and bit
-	 31 is set; in this case, the hole at bit 31 is not
-	 changed.  If we had access to the processor carry flag,
-	 we could close this loophole by putting the fourth hole
-	 at bit 32!
-
-	 So it ignores everything except 128's, when they're aligned
-	 properly.  */
-
       longword = *longword_ptr++;
 
-      if (
-#if 0
-	  /* Add MAGIC_BITS to LONGWORD.  */
-	  (((longword + magic_bits)
-
-	    /* Set those bits that were unchanged by the addition.  */
-	    ^ ~longword)
-
-	   /* Look at only the hole bits.  If any of the hole bits
-	      are unchanged, most likely one of the bytes was a
-	      zero.  */
-	   & ~magic_bits)
-#else
-	  ((longword - lomagic) & himagic)
-#endif
-	  != 0)
+      if (((longword - lomagic) & ~longword & himagic) != 0)
 	{
 	  /* Which of the bytes was the zero?  If none of them were, it was
 	     a misfire; continue the search.  */