Make ppc32/64-aix5 work again following recent VG_(tt_fast) rearrangement.

git-svn-id: svn://svn.valgrind.org/valgrind/trunk@6606

diff --git a/coregrind/m_dispatch/dispatch-ppc32-aix5.S b/coregrind/m_dispatch/dispatch-ppc32-aix5.S
index cfa2c968b87c077a35cd863f94f15610a1808290..41e366baddf99353b2bf0efc4d3e19cb1aa9b50c 100644 (file)
--- a/coregrind/m_dispatch/dispatch-ppc32-aix5.S
+++ b/coregrind/m_dispatch/dispatch-ppc32-aix5.S
@@ -267,9 +267,12 @@ VG_(run_innerloop__dispatch_unprofiled):
                128(r1) (=orig guest_state)
        */
 
-       /* Has the guest state pointer been messed with?  If yes, exit. */
+       /* Has the guest state pointer been messed with?  If yes, exit.
+          Also set up & VG_(tt_fast) early in an attempt at better
+           scheduling. */
         lwz     5,128(1)         /* original guest_state ptr */
         cmpw    5,31
+       lwz     5,tocent__vgPlain_tt_fast(2)    /* r5 = &tt_fast */
         bne    gsp_changed
 
         /* save the jump address in the guest state */
@@ -281,24 +284,17 @@ VG_(run_innerloop__dispatch_unprofiled):
         beq    counter_is_zero
 
         /* try a fast lookup in the translation cache */
-        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(ULong*)
-              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 2 */
-        rlwinm  4,3, 0, 32-2-VG_TT_FAST_BITS, 31-2
-
-       lwz     5,tocent__vgPlain_tt_fast(2)    /* r5 = &tt_fast */
-
-        lwzx    5,5,4  /* r5 = tt_fast[r5] */
-
-        lwz     6,4(5)   /* big-endian, so comparing 2nd 32bit word */
+        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(FastCacheEntry)
+              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 3 */
+        rlwinm  4,3,1, 29-VG_TT_FAST_BITS, 28   /* entry# * 8 */
+       add     5,5,4    /* & VG_(tt_fast)[entry#] */
+       lwz     6,0(5)   /* .guest */
+       lwz     7,4(5)   /* .host */
         cmpw    3,6
         bne     fast_lookup_failed
 
-        /* Found a match.  Call tce[1], which is 8 bytes along, since
-           each tce element is a 64-bit int. */
-        addi    8,5,8
-        mtctr   8
-
-       /* run the translation */
+        /* Found a match.  Call .host. */
+        mtctr   7
         bctrl
 
         /* On return from guest code:
@@ -306,7 +302,6 @@ VG_(run_innerloop__dispatch_unprofiled):
            r31 may be unchanged (guest_state), or may indicate further
            details of the control transfer requested to *r3.
         */
-
        /* start over */
        b       VG_(run_innerloop__dispatch_unprofiled)
        /*NOTREACHED*/
@@ -325,10 +320,12 @@ VG_(run_innerloop__dispatch_profiled):
           Stack state:
                128(r1) (=orig guest_state)
        */
-
-       /* Has the guest state pointer been messed with?  If yes, exit. */
+       /* Has the guest state pointer been messed with?  If yes, exit.
+          Also set up & VG_(tt_fast) early in an attempt at better
+           scheduling. */
         lwz     5,128(1)         /* original guest_state ptr */
         cmpw    5,31
+       lwz     5,tocent__vgPlain_tt_fast(2)    /* r5 = &tt_fast */
         bne    gsp_changed
 
         /* save the jump address in the guest state */
@@ -340,31 +337,25 @@ VG_(run_innerloop__dispatch_profiled):
         beq    counter_is_zero
 
         /* try a fast lookup in the translation cache */
-        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(ULong*)
-              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 2 */
-        rlwinm  4,3, 0, 32-2-VG_TT_FAST_BITS, 31-2
-
-       lwz     5,tocent__vgPlain_tt_fast(2)    /* r5 = &tt_fast */
-
-        lwzx    5,5,4  /* r5 = tt_fast[r4] */
-
-        lwz     6,4(5)   /* big-endian, so comparing 2nd 32bit word */
+        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(FastCacheEntry)
+              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 3 */
+        rlwinm  4,3,1, 29-VG_TT_FAST_BITS, 28   /* entry# * 8 */
+       add     5,5,4    /* & VG_(tt_fast)[entry#] */
+       lwz     6,0(5)   /* .guest */
+       lwz     7,4(5)   /* .host */
         cmpw    3,6
         bne     fast_lookup_failed
 
         /* increment bb profile counter */
+       srwi    4,4,1   /* entry# * sizeof(UInt*) */
        lwz     9,tocent__vgPlain_tt_fastN(2)   /* r9 = &tt_fastN */
-        lwzx    7,9,4   /* r7 = tt_fastN[r4] */
-        lwz     10,0(7)
+        lwzx    8,9,4   /* r7 = tt_fastN[r4] */
+        lwz     10,0(8)
         addi    10,10,1
-        stw     10,0(7)
+        stw     10,0(8)
        
-        /* Found a match.  Call tce[1], which is 8 bytes along, since
-           each tce element is a 64-bit int. */
-        addi    8,5,8
-        mtctr   8
-
-       /* run the translation */
+        /* Found a match.  Call .host. */
+        mtctr   7
         bctrl
 
         /* On return from guest code:
@@ -372,11 +363,11 @@ VG_(run_innerloop__dispatch_profiled):
            r31 may be unchanged (guest_state), or may indicate further
            details of the control transfer requested to *r3.
         */
-
        /* start over */
-       b       VG_(run_innerloop__dispatch_profiled)
+       b       VG_(run_innerloop__dispatch_unprofiled)
        /*NOTREACHED*/
 
+
 /*----------------------------------------------------*/
 /*--- exit points                                  ---*/
 /*----------------------------------------------------*/

diff --git a/coregrind/m_dispatch/dispatch-ppc64-aix5.S b/coregrind/m_dispatch/dispatch-ppc64-aix5.S
index 8a39a75d3318f5ba916f081e78f66e9cd0c61fad..6e2a6bf85aeaaa20577c0c0ddbdabf07f3608478 100644 (file)
--- a/coregrind/m_dispatch/dispatch-ppc64-aix5.S
+++ b/coregrind/m_dispatch/dispatch-ppc64-aix5.S
@@ -203,7 +203,7 @@ LafterVMX1:
 
         /* hold dispatch_ctr (NOTE: 32-bit value) in r29 */
         ld      5,tocent__vgPlain_dispatch_ctr(2)
-        lwz     29,0(5)
+        lwz     29,0(5)        /* 32-bit zero-extending load */
 
         /* set host FPU control word to the default mode expected 
            by VEX-generated code.  See comments in libvex.h for
@@ -258,6 +258,7 @@ VG_(run_innerloop__dispatch_unprofiled):
        /* Has the guest state pointer been messed with?  If yes, exit. */
         ld      5,256(1)         /* original guest_state ptr */
         cmpd    5,31
+       ld      5,tocent__vgPlain_tt_fast(2)    /* &VG_(tt_fast) */
         bne    gsp_changed
 
         /* save the jump address in the guest state */
@@ -269,24 +270,18 @@ VG_(run_innerloop__dispatch_unprofiled):
         beq    counter_is_zero
 
         /* try a fast lookup in the translation cache */
-        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(ULong*)
-              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 3 */
-        rldicl  4,3, 62, 64-VG_TT_FAST_BITS
-        sldi    4,4,3
-
-       ld      5,tocent__vgPlain_tt_fast(2)    /* r5 = &tt_fast */
-
-        ldx     5,5,4  /* r5 = VG_(tt_fast)[VG_TT_FAST_HASH(addr)] */
-        ld      6,0(5)  /* r6 = (r5)->orig_addr */
+        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(FastCacheEntry)
+              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 4 */
+        rldicl  4,3, 62, 64-VG_TT_FAST_BITS   /* entry# */
+        sldi    4,4,4    /* entry# * sizeof(FastCacheEntry) */
+       add     5,5,4   /* &VG_(tt_fast)[entry#] */
+       ld      6,0(5)  /* .guest */
+       ld      7,8(5)  /* .host */
         cmpd    3,6
         bne     fast_lookup_failed
 
-        /* Found a match.  Call tce[1], which is 8 bytes along, since
-           each tce element is a 64-bit int. */
-        addi    8,5,8
-        mtctr   8
-
-       /* run the translation */
+        /* Found a match.  Call .host. */
+        mtctr   7
         bctrl
 
         /* On return from guest code:
@@ -294,7 +289,6 @@ VG_(run_innerloop__dispatch_unprofiled):
            r31 may be unchanged (guest_state), or may indicate further
            details of the control transfer requested to *r3.
         */
-
        /* start over */
        b       VG_(run_innerloop__dispatch_unprofiled)
        /*NOTREACHED*/
@@ -317,6 +311,7 @@ VG_(run_innerloop__dispatch_profiled):
        /* Has the guest state pointer been messed with?  If yes, exit. */
         ld      5,256(1)         /* original guest_state ptr */
         cmpd    5,31
+       ld      5,tocent__vgPlain_tt_fast(2)    /* &VG_(tt_fast) */
         bne    gsp_changed
 
         /* save the jump address in the guest state */
@@ -328,31 +323,26 @@ VG_(run_innerloop__dispatch_profiled):
         beq    counter_is_zero
 
         /* try a fast lookup in the translation cache */
-        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(ULong*)
-              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 3 */
-        rldicl  4,3, 62, 64-VG_TT_FAST_BITS
-        sldi    4,4,3
-
-       ld      5,tocent__vgPlain_tt_fast(2)    /* r5 = &tt_fast */
-
-        ldx     5,5,4  /* r5 = VG_(tt_fast)[VG_TT_FAST_HASH(addr)] */
-        ld      6,0(5)  /* r6 = (r5)->orig_addr */
+        /* r4 = VG_TT_FAST_HASH(addr)           * sizeof(FastCacheEntry)
+              = ((r3 >>u 2) & VG_TT_FAST_MASK)  << 4 */
+        rldicl  4,3, 62, 64-VG_TT_FAST_BITS   /* entry# */
+        sldi    4,4,4    /* entry# * sizeof(FastCacheEntry) */
+       add     5,5,4   /* &VG_(tt_fast)[entry#] */
+       ld      6,0(5)  /* .guest */
+       ld      7,8(5)  /* .host */
         cmpd    3,6
         bne     fast_lookup_failed
 
         /* increment bb profile counter */
        ld      9,tocent__vgPlain_tt_fastN(2)   /* r9 = &tt_fastN */
-        ldx     7,9,4   /* r7 = tt_fastN[r4] */
-        lwz     10,0(7)
+       srdi    4,4,1   /* entry# * sizeof(UInt*) */    
+        ldx     8,9,4   /* r7 = tt_fastN[r4] */
+        lwz     10,0(8)
         addi    10,10,1
-        stw     10,0(7)
+        stw     10,0(8)
        
-        /* Found a match.  Call tce[1], which is 8 bytes along, since
-           each tce element is a 64-bit int. */
-        addi    8,5,8
-        mtctr   8
-
-       /* run the translation */
+        /* Found a match.  Call .host. */
+        mtctr   7
         bctrl
 
         /* On return from guest code:
@@ -360,7 +350,6 @@ VG_(run_innerloop__dispatch_profiled):
            r31 may be unchanged (guest_state), or may indicate further
            details of the control transfer requested to *r3.
         */
-
        /* start over */
        b       VG_(run_innerloop__dispatch_profiled)
        /*NOTREACHED*/

diff --git a/coregrind/m_dispatch/dispatch-ppc64-linux.S b/coregrind/m_dispatch/dispatch-ppc64-linux.S
index e4c328a575755495338f96f5dbf02a8305644e90..04775681d672d2e66a31b7bca02f2b26318a9e62 100644 (file)
--- a/coregrind/m_dispatch/dispatch-ppc64-linux.S
+++ b/coregrind/m_dispatch/dispatch-ppc64-linux.S
@@ -204,7 +204,7 @@ VG_(run_innerloop):
 
         /* hold dispatch_ctr (=32bit value) in r29 */
        ld      29,.tocent__vgPlain_dispatch_ctr@toc(2)
-       lwz     29,0(29)
+       lwz     29,0(29)  /* 32-bit zero-extending load */
 
         /* set host FPU control word to the default mode expected 
            by VEX-generated code.  See comments in libvex.h for