alpha: fix memchr to not cause memory faults.

http://www.mail-archive.com/debian-alpha@lists.debian.org/msg25088.html

Signed-off-by: Matt Turner <mattst88@gmail.com>

diff --git a/ChangeLog.alpha b/ChangeLog.alpha
index c3bbe12582b81c3ee51dfad5d4a6a92606fc8c86..39d58166bc24a75b7f5743dd32f6a782c70d766d 100644 (file)
--- a/ChangeLog.alpha
+++ b/ChangeLog.alpha
@@ -1,3 +1,8 @@
+2010-05-03  Aurelien Jarno  <aurelien@aurel32.net>
+ 
+       * sysdeps/alpha/memchr.S: Use prefetch load.
+       * sysdeps/alpha/alphaev6/memchr.S: Likewise.
+
 2010-05-03  Aurelien Jarno  <aurelien@aurel32.net>
 
        * sysdeps/alpha/dl-machine.h: Add dl-procinfo support.

diff --git a/sysdeps/alpha/alphaev6/memchr.S b/sysdeps/alpha/alphaev6/memchr.S
index 88e91fa98826689eeeb345cb909a86cad1cb60a7..fe77cd897b69991543fa6669794ba98744ae014f 100644 (file)
--- a/sysdeps/alpha/alphaev6/memchr.S
+++ b/sysdeps/alpha/alphaev6/memchr.S
@@ -127,7 +127,7 @@ $first_quad:
         cmpbge  $31, $1, $2    # E :
         bne     $2, $found_it  # U :
        # At least one byte left to process.
-       ldq     $1, 8($0)       # L :
+       ldq     $31, 8($0)      # L :
        subq    $5, 1, $18      # E : U L U L
 
        addq    $0, 8, $0       # E :
@@ -143,38 +143,38 @@ $first_quad:
        and     $4, 8, $4       # E : odd number of quads?
        bne     $4, $odd_quad_count # U :
        # At least three quads remain to be accessed
-       mov     $1, $4          # E : L U L U : move prefetched value to correct reg
+       nop                     # E : L U L U : move prefetched value to correct reg
 
        .align  4
 $unrolled_loop:
-       ldq     $1, 8($0)       # L : prefetch $1
-       xor     $17, $4, $2     # E :
-       cmpbge  $31, $2, $2     # E :
-       bne     $2, $found_it   # U : U L U L
+       ldq     $1, 0($0)       # L : load quad
+       xor     $17, $1, $2     # E :
+       ldq     $31, 8($0)      # L : prefetch next quad
+       cmpbge  $31, $2, $2     # E : U L U L
 
+       bne     $2, $found_it   # U :
        addq    $0, 8, $0       # E :
        nop                     # E :
        nop                     # E :
-       nop                     # E :
 
 $odd_quad_count:
+       ldq     $1, 0($0)       # L : load quad
        xor     $17, $1, $2     # E :
-       ldq     $4, 8($0)       # L : prefetch $4
+       ldq     $31, 8($0)      # L : prefetch $4
        cmpbge  $31, $2, $2     # E :
-       addq    $0, 8, $6       # E :
 
+       addq    $0, 8, $6       # E :
        bne     $2, $found_it   # U :
        cmpult  $6, $18, $6     # E :
        addq    $0, 8, $0       # E :
-       nop                     # E :
 
        bne     $6, $unrolled_loop # U :
-       mov     $4, $1          # E : move prefetched value into $1
        nop                     # E :
        nop                     # E :
-
-$final:        subq    $5, $0, $18     # E : $18 <- number of bytes left to do
        nop                     # E :
+
+$final:        ldq     $1, 0($0)       # L : load last quad
+       subq    $5, $0, $18     # E : $18 <- number of bytes left to do
        nop                     # E :
        bne     $18, $last_quad # U :
 

diff --git a/sysdeps/alpha/memchr.S b/sysdeps/alpha/memchr.S
index 5d713d53ba7994f7ef07026a82b0f6e141e4f3b5..87c7fb10c005e4560e1f0616aa7e55f2620c92c5 100644 (file)
--- a/sysdeps/alpha/memchr.S
+++ b/sysdeps/alpha/memchr.S
@@ -119,7 +119,7 @@ $first_quad:
 
        # At least one byte left to process.
 
-       ldq     t0, 8(v0)       # e0    :
+       ldq     zero, 8(v0)     # e0    : prefetch next quad
        subq    t4, 1, a2       # .. e1 :
        addq    v0, 8, v0       #-e0    :
 
@@ -138,19 +138,19 @@ $first_quad:
 
        # At least three quads remain to be accessed
 
-       mov     t0, t3          # e0    : move prefetched value to correct reg
-
        .align  4
 $unrolled_loop:
-       ldq     t0, 8(v0)       #-e0    : prefetch t0
-       xor     a1, t3, t1      # .. e1 :
-       cmpbge  zero, t1, t1    # e0    :
-       bne     t1, $found_it   # .. e1 :
+       ldq     t0, 0(v0)       # e0    : load quad
+       xor     a1, t0, t1      # .. e1 :
+       ldq     zero, 8(v0)     # e0    : prefetch next quad
+       cmpbge  zero, t1, t1    # .. e1:
+       bne     t1, $found_it   # e0    :
 
-       addq    v0, 8, v0       #-e0    :
+       addq    v0, 8, v0       #    e1 :
 $odd_quad_count:
+       ldq     t0, 0(v0)       # e0    : load quad
        xor     a1, t0, t1      # .. e1 :
-       ldq     t3, 8(v0)       # e0    : prefetch t3
+       ldq     zero, 8(v0)     # e0    : prefetch next quad
        cmpbge  zero, t1, t1    # .. e1 :
        addq    v0, 8, t5       #-e0    :
        bne     t1, $found_it   # .. e1 :
@@ -159,8 +159,8 @@ $odd_quad_count:
        addq    v0, 8, v0       # .. e1 :
        bne     t5, $unrolled_loop #-e1 :
 
-       mov     t3, t0          # e0    : move prefetched value into t0
-$final:        subq    t4, v0, a2      # .. e1 : a2 <- number of bytes left to do
+$final:        ldq     t0, 0(v0)       # e0    : load last quad
+       subq    t4, v0, a2      # .. e1 : a2 <- number of bytes left to do
        bne     a2, $last_quad  # e1    :
 
 $not_found: