[PATCH] PPC64 Replace cmp instructions with cmpw/cmpd

There were a few places in assembly code in the ppc64 part of the
kernel where we were using the old forms of the compare instruction
(cmp, cmpi, cmpl, cmpli) which don't specify the operand size (word or
doubleword).  These have been accepted for a long time for backward
compatibility with the old POWER architecture (and defaulted to a
32-bit comparison) but are now being rejected by the latest versions
of binutils.  Some of them were actual bugs in that they were on
things which were actually 64-bit values such as pointers (not that
any of them actually caused a problem in practice).

This patch replaces cmp{,l}{,i} with cmp{,l}[wd]{,i} as appropriate.
The original patch was from Segher Boessenkool, slightly modified by
me.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/ppc64/kernel/entry.S b/arch/ppc64/kernel/entry.S
index edf1db7db8bed266fa8b84fa4e2b852aa04be777..f0a12eaa3e2fb384082d01fa0dd3d79617b92a21 100644 (file)
--- a/arch/ppc64/kernel/entry.S
+++ b/arch/ppc64/kernel/entry.S
@@ -122,7 +122,7 @@ SystemCall_common:
        andi.   r11,r10,_TIF_SYSCALL_T_OR_A
        bne-    syscall_dotrace
 syscall_dotrace_cont:
-       cmpli   0,r0,NR_syscalls
+       cmpldi  0,r0,NR_syscalls
        bge-    syscall_enosys
 
 system_call:                   /* label this so stack traces look sane */
@@ -204,7 +204,7 @@ syscall_enosys:
 
 syscall_error:
        lbz     r11,TI_SC_NOERR(r12)
-       cmpi    0,r11,0
+       cmpwi   0,r11,0
        bne-    syscall_error_cont
        neg     r3,r3
        oris    r5,r5,0x1000    /* Set SO bit in CR */

diff --git a/arch/ppc64/kernel/idle_power4.S b/arch/ppc64/kernel/idle_power4.S
index fb983069dfa51d5de2df3b432438af9e624e7b40..97e4a26550402dbd6dc9199a9adac7b8541f6ab7 100644 (file)
--- a/arch/ppc64/kernel/idle_power4.S
+++ b/arch/ppc64/kernel/idle_power4.S
@@ -46,7 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
        /* Now check if user or arch enabled NAP mode */
        LOADBASE(r3,powersave_nap)
        lwz     r4,powersave_nap@l(r3)
-       cmpi    0,r4,0
+       cmpwi   0,r4,0
        beqlr
 
        /* Clear MSR:EE */

diff --git a/arch/ppc64/kernel/misc.S b/arch/ppc64/kernel/misc.S
index c153e266f4848e316afcd7266279223129898f63..30314c5961e77462966b0e060b6e3fdd05925e6d 100644 (file)
--- a/arch/ppc64/kernel/misc.S
+++ b/arch/ppc64/kernel/misc.S
@@ -670,7 +670,7 @@ _GLOBAL(kernel_thread)
        li      r4,0            /* new sp (unused) */
        li      r0,__NR_clone
        sc
-       cmpi    0,r3,0          /* parent or child? */
+       cmpdi   0,r3,0          /* parent or child? */
        bne     1f              /* return if parent */
        li      r0,0
        stdu    r0,-STACK_FRAME_OVERHEAD(r1)

diff --git a/arch/ppc64/lib/checksum.S b/arch/ppc64/lib/checksum.S
index 4ac6a63cab1ea32b8200fd330df95392bddee324..ef96c6c58efc6644d68ac534fb1f4d40253aa605 100644 (file)
--- a/arch/ppc64/lib/checksum.S
+++ b/arch/ppc64/lib/checksum.S
@@ -92,19 +92,19 @@ _GLOBAL(csum_partial)
         adde    r5,r5,r6
         bdnz    2b
         andi.  r4,r4,7         /* compute bytes left to sum after doublewords */
-3:     cmpi    0,r4,4          /* is at least a full word left? */
+3:     cmpwi   0,r4,4          /* is at least a full word left? */
        blt     4f
        lwz     r6,8(r3)        /* sum this word */
        addi    r3,r3,4
        subi    r4,r4,4
        adde    r5,r5,r6
-4:      cmpi    0,r4,2         /* is at least a halfword left? */
+4:     cmpwi   0,r4,2          /* is at least a halfword left? */
         blt+   5f
         lhz     r6,8(r3)        /* sum this halfword */
         addi    r3,r3,2
         subi    r4,r4,2
         adde    r5,r5,r6
-5:      cmpi    0,r4,1         /* is at least a byte left? */
+5:     cmpwi   0,r4,1          /* is at least a byte left? */
         bne+    6f
         lbz     r6,8(r3)        /* sum this byte */
         slwi    r6,r6,8         /* this byte is assumed to be the upper byte of a halfword */
@@ -150,7 +150,7 @@ _GLOBAL(csum_partial_copy_generic)
        adde    r0,r0,r6
        bdnz    82b
        andi.   r5,r5,3
-3:     cmpi    0,r5,2
+3:     cmpwi   0,r5,2
        blt+    4f
 83:    lhz     r6,4(r3)
        addi    r3,r3,2
@@ -158,7 +158,7 @@ _GLOBAL(csum_partial_copy_generic)
 93:    sth     r6,4(r4)
        addi    r4,r4,2
        adde    r0,r0,r6
-4:     cmpi    0,r5,1
+4:     cmpwi   0,r5,1
        bne+    5f
 84:    lbz     r6,4(r3)
 94:    stb     r6,4(r4)
@@ -198,7 +198,7 @@ src_error_3:
        bdnz    97b
        .globl src_error
 src_error:
-       cmpi    0,r7,0
+       cmpdi   0,r7,0
        beq     1f
        li      r6,-EFAULT
        stw     r6,0(r7)
@@ -207,7 +207,7 @@ src_error:
 
        .globl dst_error
 dst_error:
-       cmpi    0,r8,0
+       cmpdi   0,r8,0
        beq     1f
        li      r6,-EFAULT
        stw     r6,0(r8)

diff --git a/arch/ppc64/mm/hash_low.S b/arch/ppc64/mm/hash_low.S
index 93c868e687bb7779d4bb5d330fbce83dd58a4910..f179979c03838018b4e4c0aa06e7e3654de755ba 100644 (file)
--- a/arch/ppc64/mm/hash_low.S
+++ b/arch/ppc64/mm/hash_low.S
@@ -172,9 +172,9 @@ htab_insert_pte:
        li      r9,0
 _GLOBAL(htab_call_hpte_insert1)
        bl      .                       /* Will be patched by htab_finish_init() */
-       cmpi    0,r3,0
+       cmpdi   0,r3,0
        bge     htab_pte_insert_ok      /* Insertion successful */
-       cmpi    0,r3,-2                 /* Critical failure */
+       cmpdi   0,r3,-2                 /* Critical failure */
        beq-    htab_pte_insert_failure
 
        /* Now try secondary slot */
@@ -194,9 +194,9 @@ _GLOBAL(htab_call_hpte_insert1)
        li      r9,0
 _GLOBAL(htab_call_hpte_insert2)
        bl      .                       /* Will be patched by htab_finish_init() */
-       cmpi    0,r3,0
+       cmpdi   0,r3,0
        bge+    htab_pte_insert_ok      /* Insertion successful */
-       cmpi    0,r3,-2                 /* Critical failure */
+       cmpdi   0,r3,-2                 /* Critical failure */
        beq-    htab_pte_insert_failure
 
        /* Both are full, we need to evict something */