Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-26 Thread Gabriel Paubert 
On Wed, Jun 25, 2008 at 11:17:45AM -0500, Scott Wood wrote:
 Gabriel Paubert wrote:
 On Wed, Jun 25, 2008 at 10:34:32AM -0500, Scott Wood wrote:
 Kumar Gala wrote:
 +/* Macros to workout the correct index for the FPR in the thread 
 struct */
 +#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
 +#define FPRHALF(i) (((i) - PT_FPR0) % 2)
 Have you looked at what the compiler spits out here to make sure we 
 aren't getting a divide?  Seems like we could use ' 0x1'.
 GCC's not *that* dumb.  However, you may get some unnecessary 
 sign-twiddling if i is signed.
 
 Not for modulo 2, it's only an even/odd choice and GCC 
 implements that efficiently IIRC. For other powers of 2,
 making the left hand side unsigned helps the compiler.
 
 From this:
 
 int foo(int x)
 {
   return x % 2;
 }
 
 I get this with -O3:
 
 foo:
 mr 0,3
 srawi 3,3,1
 addze 3,3
 slwi 3,3,1
 subf 3,3,0
 blr
 .size   foo, .-foo
 .ident  GCC: (GNU) 4.1.2
 

Indeed. Signed modulo results can be negative...

There are probably better ways to implement this case
on PPC, for example:

rlwinm tmp,input,4,27,28 ; make shift amount from LSB and MSB 
lis result,0xff01
srw result,result,tmp
; result is now 0x00 for even, 0x01 for odd positive,
; and 0xff for odd negative
extsb result,result

No carry, shorter dependency length (although srw may be slow
on Cell it seems, but addze may be worse).


 Changing it to x  1, or to unsigned, gives this:
 
 foo:
 rlwinm 3,3,0,31,31
 blr
 .size   foo, .-foo
 .ident  GCC: (GNU) 4.1.2
 
 Maybe newer GCCs are better?

Nope, but unsigned is often better for the right shift.

Gabriel
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Kumar Gala 


Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace32.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
@@ -64,6 +64,11 @@ static long compat_ptrace_old(struct tas
return -EPERM;
}

+/* Macros to workout the correct index for the FPR in the thread  
struct */

+#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
+#define FPRHALF(i) (((i) - PT_FPR0) % 2)


Have you looked at what the compiler spits out here to make sure we  
aren't getting a divide?  Seems like we could use ' 0x1'.



+#define FPRINDEX(i) TS_FPRWIDTH * FPRNUMBER(i) + FPRHALF(i)






+
long compat_arch_ptrace(struct task_struct *child, compat_long_t  
request,

compat_ulong_t caddr, compat_ulong_t cdata)
{
@@ -122,7 +127,8 @@ long compat_arch_ptrace(struct task_stru
 * to be an array of unsigned int (32 bits) - the
 * index passed in is based on this assumption.
 */
-   tmp = ((unsigned int *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned int *)child-thread.fpr)
+   [FPRINDEX(index)];
}
ret = put_user((unsigned int)tmp, (u32 __user *)data);
break;
@@ -162,7 +168,8 @@ long compat_arch_ptrace(struct task_stru
CHECK_FULL_REGS(child-thread.regs);
if (numReg = PT_FPR0) {
flush_fp_to_thread(child);
-   tmp = ((unsigned long int *)child-thread.fpr)[numReg - 
PT_FPR0];
+   tmp = ((unsigned long int *)child-thread.fpr)
+   [FPRINDEX(numReg)];
} else { /* register within PT_REGS struct */
tmp = ptrace_get_reg(child, numReg);
}
@@ -217,7 +224,8 @@ long compat_arch_ptrace(struct task_stru
 * to be an array of unsigned int (32 bits) - the
 * index passed in is based on this assumption.
 */
-   ((unsigned int *)child-thread.fpr)[index - PT_FPR0] = 
data;
+   ((unsigned int *)child-thread.fpr)
+   [FPRINDEX(index)] = data;
ret = 0;
}
break;


- k
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Scott Wood 

Kumar Gala wrote:
+/* Macros to workout the correct index for the FPR in the thread 
struct */

+#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
+#define FPRHALF(i) (((i) - PT_FPR0) % 2)


Have you looked at what the compiler spits out here to make sure we 
aren't getting a divide?  Seems like we could use ' 0x1'.


GCC's not *that* dumb.  However, you may get some unnecessary 
sign-twiddling if i is signed.


-Scott
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Scott Wood 

Gabriel Paubert wrote:

On Wed, Jun 25, 2008 at 10:34:32AM -0500, Scott Wood wrote:

Kumar Gala wrote:
+/* Macros to workout the correct index for the FPR in the thread 
struct */

+#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
+#define FPRHALF(i) (((i) - PT_FPR0) % 2)
Have you looked at what the compiler spits out here to make sure we 
aren't getting a divide?  Seems like we could use ' 0x1'.
GCC's not *that* dumb.  However, you may get some unnecessary 
sign-twiddling if i is signed.


Not for modulo 2, it's only an even/odd choice and GCC 
implements that efficiently IIRC. For other powers of 2,

making the left hand side unsigned helps the compiler.


From this:

int foo(int x)
{
return x % 2;
}

I get this with -O3:

foo:
mr 0,3
srawi 3,3,1
addze 3,3
slwi 3,3,1
subf 3,3,0
blr
.size   foo, .-foo
.ident  GCC: (GNU) 4.1.2

Changing it to x  1, or to unsigned, gives this:

foo:
rlwinm 3,3,0,31,31
blr
.size   foo, .-foo
.ident  GCC: (GNU) 4.1.2

Maybe newer GCCs are better?

-Scott
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Gabriel Paubert 
On Wed, Jun 25, 2008 at 10:34:32AM -0500, Scott Wood wrote:
 Kumar Gala wrote:
 +/* Macros to workout the correct index for the FPR in the thread 
 struct */
 +#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
 +#define FPRHALF(i) (((i) - PT_FPR0) % 2)
 
 Have you looked at what the compiler spits out here to make sure we 
 aren't getting a divide?  Seems like we could use ' 0x1'.
 
 GCC's not *that* dumb.  However, you may get some unnecessary 
 sign-twiddling if i is signed.

Not for modulo 2, it's only an even/odd choice and GCC 
implements that efficiently IIRC. For other powers of 2,
making the left hand side unsigned helps the compiler.

The right shift OTOH might be faster if i is unsigned 
since right signed right shifts affect the carry on PPC (I really
don't know if srawi is slower than srwi on some processors,
srwi is a form of rlwinm which is always fast).

Gabriel
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Kumar Gala 


On Jun 25, 2008, at 11:17 AM, Scott Wood wrote:


Gabriel Paubert wrote:

On Wed, Jun 25, 2008 at 10:34:32AM -0500, Scott Wood wrote:

Kumar Gala wrote:
+/* Macros to workout the correct index for the FPR in the  
thread struct */

+#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
+#define FPRHALF(i) (((i) - PT_FPR0) % 2)
Have you looked at what the compiler spits out here to make sure  
we aren't getting a divide?  Seems like we could use ' 0x1'.
GCC's not *that* dumb.  However, you may get some unnecessary sign- 
twiddling if i is signed.
Not for modulo 2, it's only an even/odd choice and GCC implements  
that efficiently IIRC. For other powers of 2,

making the left hand side unsigned helps the compiler.


From this:

int foo(int x)
{
return x % 2;
}

I get this with -O3:

foo:
   mr 0,3
   srawi 3,3,1
   addze 3,3
   slwi 3,3,1
   subf 3,3,0
   blr
   .size   foo, .-foo
   .ident  GCC: (GNU) 4.1.2

Changing it to x  1, or to unsigned, gives this:

foo:
   rlwinm 3,3,0,31,31
   blr
   .size   foo, .-foo
   .ident  GCC: (GNU) 4.1.2

Maybe newer GCCs are better?


Nope. gcc-4.3.0 from fedora 9:

foo:
mr 0,3
srawi 3,3,1
addze 3,3
slwi 3,3,1
subf 3,3,0
blr

bar:
rlwinm 3,3,0,31,31
blr

if you make 'x' unsigned things are better.

- k
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Andreas Schwab 
Gabriel Paubert [EMAIL PROTECTED] writes:

 On Wed, Jun 25, 2008 at 10:34:32AM -0500, Scott Wood wrote:
 Kumar Gala wrote:
 +/* Macros to workout the correct index for the FPR in the thread 
 struct */
 +#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
 +#define FPRHALF(i) (((i) - PT_FPR0) % 2)
 
 Have you looked at what the compiler spits out here to make sure we 
 aren't getting a divide?  Seems like we could use ' 0x1'.
 
 GCC's not *that* dumb.  However, you may get some unnecessary 
 sign-twiddling if i is signed.

 Not for modulo 2, it's only an even/odd choice

That's wrong.  -1 % 2 == -1, 1 % 2 == 1.

Andreas.

-- 
Andreas Schwab, SuSE Labs, [EMAIL PROTECTED]
SuSE Linux Products GmbH, Maxfeldstraße 5, 90409 Nürnberg, Germany
PGP key fingerprint = 58CA 54C7 6D53 942B 1756  01D3 44D5 214B 8276 4ED5
And now for something completely different.
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-25 Thread Michael Neuling 
In message [EMAIL PROTECTED] you wrote:
 
 On Jun 25, 2008, at 11:17 AM, Scott Wood wrote:
 
  Gabriel Paubert wrote:
  On Wed, Jun 25, 2008 at 10:34:32AM -0500, Scott Wood wrote:
  Kumar Gala wrote:
  +/* Macros to workout the correct index for the FPR in the  
  thread struct */
  +#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
  +#define FPRHALF(i) (((i) - PT_FPR0) % 2)
  Have you looked at what the compiler spits out here to make sure  
  we aren't getting a divide?  Seems like we could use ' 0x1'.
  GCC's not *that* dumb.  However, you may get some unnecessary sign- 
  twiddling if i is signed.
  Not for modulo 2, it's only an even/odd choice and GCC implements  
  that efficiently IIRC. For other powers of 2,
  making the left hand side unsigned helps the compiler.
 
  From this:
 
  int foo(int x)
  {
  return x % 2;
  }
 
  I get this with -O3:
 
  foo:
 mr 0,3
 srawi 3,3,1
 addze 3,3
 slwi 3,3,1
 subf 3,3,0
 blr
 .size   foo, .-foo
 .ident  GCC: (GNU) 4.1.2
 
  Changing it to x  1, or to unsigned, gives this:
 
  foo:
 rlwinm 3,3,0,31,31
 blr
 .size   foo, .-foo
 .ident  GCC: (GNU) 4.1.2
 
  Maybe newer GCCs are better?
 
 Nope. gcc-4.3.0 from fedora 9:
 
 foo:
  mr 0,3
  srawi 3,3,1
  addze 3,3
  slwi 3,3,1
  subf 3,3,0
  blr
 
 bar:
  rlwinm 3,3,0,31,31
  blr
 
 if you make 'x' unsigned things are better.

I've changed it to ' 0x1', which compiles to something better here.

Mikey
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

[PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-24 Thread Michael Neuling 
We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

 arch/powerpc/kernel/align.c  |6 ++--
 arch/powerpc/kernel/process.c|5 ++-
 arch/powerpc/kernel/ptrace.c |   14 +
 arch/powerpc/kernel/ptrace32.c   |   14 +++--
 arch/powerpc/kernel/softemu8xx.c |4 +-
 arch/powerpc/math-emu/math.c |   56 +++
 include/asm-powerpc/ppc_asm.h|5 ++-
 include/asm-powerpc/processor.h  |3 ++
 8 files changed, 61 insertions(+), 46 deletions(-)

Index: linux-2.6-ozlabs/arch/powerpc/kernel/align.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/align.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/align.c
@@ -366,7 +366,7 @@ static int emulate_multiple(struct pt_re
 static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
   unsigned int reg, unsigned int flags)
 {
-   char *ptr = (char *) current-thread.fpr[reg];
+   char *ptr = (char *) current-thread.TS_FPR(reg);
int i, ret;
 
if (!(flags  F))
@@ -784,7 +784,7 @@ int fix_alignment(struct pt_regs *regs)
return -EFAULT;
}
} else if (flags  F) {
-   data.dd = current-thread.fpr[reg];
+   data.dd = current-thread.TS_FPR(reg);
if (flags  S) {
/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -862,7 +862,7 @@ int fix_alignment(struct pt_regs *regs)
if (unlikely(ret))
return -EFAULT;
} else if (flags  F)
-   current-thread.fpr[reg] = data.dd;
+   current-thread.TS_FPR(reg) = data.dd;
else
regs-gpr[reg] = data.ll;
 
Index: linux-2.6-ozlabs/arch/powerpc/kernel/process.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/process.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/process.c
@@ -110,7 +110,7 @@ int dump_task_fpu(struct task_struct *ts
return 0;
flush_fp_to_thread(current);
 
-   memcpy(fpregs, tsk-thread.fpr[0], sizeof(*fpregs));
+   memcpy(fpregs, tsk-thread.TS_FPR(0), sizeof(*fpregs));
 
return 1;
 }
@@ -689,7 +689,8 @@ void start_thread(struct pt_regs *regs, 
 #endif
 
discard_lazy_cpu_state();
-   memset(current-thread.fpr, 0, sizeof(current-thread.fpr));
+   memset(current-thread.fpr, 0,
+  sizeof(current-thread.fpr));
current-thread.fpscr.val = 0;
 #ifdef CONFIG_ALTIVEC
memset(current-thread.vr, 0, sizeof(current-thread.vr));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.fpr, 0, -1);
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset 
*regset,
@@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyin(pos, count, kbuf, ubuf,
- target-thread.fpr, 0, -1);
+ target-thread.fpr, 0, -1);
 }
 
 
@@ -728,7 +728,8 @@ long arch_ptrace(struct task_struct *chi
tmp = ptrace_get_reg(child, (int) index);
} else {
flush_fp_to_thread(child);
-   tmp = ((unsigned long *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned long *)child-thread.fpr)
+   [TS_FPRSPACING * (index - PT_FPR0)];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
@@ -755,7 +756,8 @@ long arch_ptrace(struct task_struct *chi
ret = ptrace_put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
-   ((unsigned long *)child-thread.fpr)[index - PT_FPR0] =

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-24 Thread Kumar Gala 


On Jun 24, 2008, at 5:57 AM, Michael Neuling wrote:


We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

arch/powerpc/kernel/align.c  |6 ++--
arch/powerpc/kernel/process.c|5 ++-
arch/powerpc/kernel/ptrace.c |   14 +
arch/powerpc/kernel/ptrace32.c   |   14 +++--
arch/powerpc/kernel/softemu8xx.c |4 +-
arch/powerpc/math-emu/math.c |   56 ++ 
+

include/asm-powerpc/ppc_asm.h|5 ++-
include/asm-powerpc/processor.h  |3 ++
8 files changed, 61 insertions(+), 46 deletions(-)




Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);

BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));

return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.fpr, 0, -1);


is there a reason we can drop the ''? (I'm only look at this as a  
textual diff, not at what the code is trying to do).


}

static int fpr_set(struct task_struct *target, const struct  
user_regset *regset,

@@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);

BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));

return user_regset_copyin(pos, count, kbuf, ubuf,
- target-thread.fpr, 0, -1);
+ target-thread.fpr, 0, -1);


ditto.


}


@@ -728,7 +728,8 @@ long arch_ptrace(struct task_struct *chi
tmp = ptrace_get_reg(child, (int) index);
} else {
flush_fp_to_thread(child);
-   tmp = ((unsigned long *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned long *)child-thread.fpr)
+   [TS_FPRSPACING * (index - PT_FPR0)];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
@@ -755,7 +756,8 @@ long arch_ptrace(struct task_struct *chi
ret = ptrace_put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
-   ((unsigned long *)child-thread.fpr)[index - PT_FPR0] = 
data;
+   ((unsigned long *)child-thread.fpr)
+   [TS_FPRSPACING * (index - PT_FPR0)] = data;
ret = 0;
}
break;
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace32.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
@@ -64,6 +64,11 @@ static long compat_ptrace_old(struct tas
return -EPERM;
}

+/* Macros to workout the correct index for the FPR in the thread  
struct */

+#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
+#define FPRHALF(i) (((i) - PT_FPR0) % 2)
+#define FPRINDEX(i) TS_FPRSPACING * FPRNUMBER(i) + FPRHALF(i)


we should either use this macros in both ptrace.c and ptrace32.c or  
drop them




+
long compat_arch_ptrace(struct task_struct *child, compat_long_t  
request,

compat_ulong_t caddr, compat_ulong_t cdata)
{
@@ -122,7 +127,8 @@ long compat_arch_ptrace(struct task_stru
 * to be an array of unsigned int (32 bits) - the
 * index passed in is based on this assumption.
 */
-   tmp = ((unsigned int *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned int *)child-thread.fpr)
+   [FPRINDEX(index)];
}
ret = put_user((unsigned int)tmp, (u32 __user *)data);
break;
@@ -162,7 +168,8 @@ long compat_arch_ptrace(struct task_stru
CHECK_FULL_REGS(child-thread.regs);
if (numReg = PT_FPR0) {
flush_fp_to_thread(child);
-   tmp = ((unsigned long int *)child-thread.fpr)[numReg - 
PT_FPR0];
+   tmp = ((unsigned long int *)child-thread.fpr)
+   [FPRINDEX(numReg)];
} else { /* register within

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-24 Thread Segher Boessenkool 

return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.fpr, 0, -1);


is there a reason we can drop the ''?


Yes, .fpr is an array.  C is _such_ a fun language, heh.


Segher

___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-24 Thread Michael Neuling 


In message [EMAIL PROTECTED] you wrote
:
 
 On Jun 24, 2008, at 5:57 AM, Michael Neuling wrote:
 
  We are going to change where the floating point registers are stored
  in the thread_struct, so in preparation add some macros to access the
  floating point registers.  Update all code to use these new macros.
 
  Signed-off-by: Michael Neuling [EMAIL PROTECTED]
  ---
 
  arch/powerpc/kernel/align.c  |6 ++--
  arch/powerpc/kernel/process.c|5 ++-
  arch/powerpc/kernel/ptrace.c |   14 +
  arch/powerpc/kernel/ptrace32.c   |   14 +++--
  arch/powerpc/kernel/softemu8xx.c |4 +-
  arch/powerpc/math-emu/math.c |   56 ++ 
  +
  include/asm-powerpc/ppc_asm.h|5 ++-
  include/asm-powerpc/processor.h  |3 ++
  8 files changed, 61 insertions(+), 46 deletions(-)
 
 
  Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
  ===
  --- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
  +++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
  @@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
  flush_fp_to_thread(target);
 
  BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
  -offsetof(struct thread_struct, fpr[32]));
  +offsetof(struct thread_struct, TS_FPR(32)));
 
  return user_regset_copyout(pos, count, kbuf, ubuf,
  -  target-thread.fpr, 0, -1);
  +  target-thread.fpr, 0, -1);
 
 is there a reason we can drop the ''? (I'm only look at this as a  
 textual diff, not at what the code is trying to do).

Oops.. I'll fix.

 
  }
 
  static int fpr_set(struct task_struct *target, const struct  
  user_regset *regset,
  @@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
  flush_fp_to_thread(target);
 
  BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
  -offsetof(struct thread_struct, fpr[32]));
  +offsetof(struct thread_struct, TS_FPR(32)));
 
  return user_regset_copyin(pos, count, kbuf, ubuf,
  - target-thread.fpr, 0, -1);
  + target-thread.fpr, 0, -1);
 
 ditto.
 
  }
 
 
  @@ -728,7 +728,8 @@ long arch_ptrace(struct task_struct *chi
  tmp = ptrace_get_reg(child, (int) index);
  } else {
  flush_fp_to_thread(child);
  -   tmp = ((unsigned long *)child-thread.fpr)[index - PT_F
PR0];
  +   tmp = ((unsigned long *)child-thread.fpr)
  +   [TS_FPRSPACING * (index - PT_FPR0)];
  }
  ret = put_user(tmp,(unsigned long __user *) data);
  break;
  @@ -755,7 +756,8 @@ long arch_ptrace(struct task_struct *chi
  ret = ptrace_put_reg(child, index, data);
  } else {
  flush_fp_to_thread(child);
  -   ((unsigned long *)child-thread.fpr)[index - PT_FPR0] =
 data;
  +   ((unsigned long *)child-thread.fpr)
  +   [TS_FPRSPACING * (index - PT_FPR0)] = data;
  ret = 0;
  }
  break;
  Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
  ===
  --- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace32.c
  +++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
  @@ -64,6 +64,11 @@ static long compat_ptrace_old(struct tas
  return -EPERM;
  }
 
  +/* Macros to workout the correct index for the FPR in the thread  
  struct */
  +#define FPRNUMBER(i) (((i) - PT_FPR0)  1)
  +#define FPRHALF(i) (((i) - PT_FPR0) % 2)
  +#define FPRINDEX(i) TS_FPRSPACING * FPRNUMBER(i) + FPRHALF(i)
 
 we should either use this macros in both ptrace.c and ptrace32.c or  
 drop them

This set of macros is really only 32 bit specific since in ptrace 32 we
access the registers as 32 bits (hence needing two accesses to get the
full 64 bits), but in ptrace 64, we access them as 64 bit (hence only 1
access).

Theses macros are really only here to deal with the unique indexing into
the thread struct that we now need to do for ptrace 32 only (thanks to
paulus who pointed out I got this wrong first time).

The only macro here that could potentially be reused is FPRNUMER(i).  

 
 
  +
  long compat_arch_ptrace(struct task_struct *child, compat_long_t  
  request,
  compat_ulong_t caddr, compat_ulong_t cdata)
  {
  @@ -122,7 +127,8 @@ long compat_arch_ptrace(struct task_stru
   * to be an array of unsigned int (32 bits) - the
   * index passed in is based on this assumption.
   */
  -   tmp = ((unsigned int *)child-thread.fpr)[index - PT_FP
R0];
  +   tmp = ((unsigned int *)child-thread.fpr)
  +   [FPRINDEX(index)];

[PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-24 Thread Michael Neuling 
We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

 arch/powerpc/kernel/align.c  |6 ++--
 arch/powerpc/kernel/process.c|2 -
 arch/powerpc/kernel/ptrace.c |   10 --
 arch/powerpc/kernel/ptrace32.c   |   14 +++--
 arch/powerpc/kernel/softemu8xx.c |4 +-
 arch/powerpc/math-emu/math.c |   56 +++
 include/asm-powerpc/ppc_asm.h|5 ++-
 include/asm-powerpc/processor.h  |4 ++
 8 files changed, 58 insertions(+), 43 deletions(-)

Index: linux-2.6-ozlabs/arch/powerpc/kernel/align.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/align.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/align.c
@@ -366,7 +366,7 @@ static int emulate_multiple(struct pt_re
 static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
   unsigned int reg, unsigned int flags)
 {
-   char *ptr = (char *) current-thread.fpr[reg];
+   char *ptr = (char *) current-thread.TS_FPR(reg);
int i, ret;
 
if (!(flags  F))
@@ -784,7 +784,7 @@ int fix_alignment(struct pt_regs *regs)
return -EFAULT;
}
} else if (flags  F) {
-   data.dd = current-thread.fpr[reg];
+   data.dd = current-thread.TS_FPR(reg);
if (flags  S) {
/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -862,7 +862,7 @@ int fix_alignment(struct pt_regs *regs)
if (unlikely(ret))
return -EFAULT;
} else if (flags  F)
-   current-thread.fpr[reg] = data.dd;
+   current-thread.TS_FPR(reg) = data.dd;
else
regs-gpr[reg] = data.ll;
 
Index: linux-2.6-ozlabs/arch/powerpc/kernel/process.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/process.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/process.c
@@ -110,7 +110,7 @@ int dump_task_fpu(struct task_struct *ts
return 0;
flush_fp_to_thread(current);
 
-   memcpy(fpregs, tsk-thread.fpr[0], sizeof(*fpregs));
+   memcpy(fpregs, tsk-thread.TS_FPR(0), sizeof(*fpregs));
 
return 1;
 }
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,7 +218,7 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyout(pos, count, kbuf, ubuf,
   target-thread.fpr, 0, -1);
@@ -231,7 +231,7 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyin(pos, count, kbuf, ubuf,
  target-thread.fpr, 0, -1);
@@ -728,7 +728,8 @@ long arch_ptrace(struct task_struct *chi
tmp = ptrace_get_reg(child, (int) index);
} else {
flush_fp_to_thread(child);
-   tmp = ((unsigned long *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned long *)child-thread.fpr)
+   [TS_FPRWIDTH * (index - PT_FPR0)];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
@@ -755,7 +756,8 @@ long arch_ptrace(struct task_struct *chi
ret = ptrace_put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
-   ((unsigned long *)child-thread.fpr)[index - PT_FPR0] = 
data;
+   ((unsigned long *)child-thread.fpr)
+   [TS_FPRWIDTH * (index - PT_FPR0)] = data;
ret = 0;
}
break;
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace32.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace32.c
@@ -64,6 +64,11 @@ static long compat_ptrace_old(struct tas
return -EPERM;
 }
 
+/* Macros to workout the correct index for the FPR in the thread struct */

[PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-23 Thread Michael Neuling 
We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

 arch/powerpc/kernel/align.c  |6 ++--
 arch/powerpc/kernel/process.c|5 ++-
 arch/powerpc/kernel/ptrace.c |   14 +
 arch/powerpc/kernel/ptrace32.c   |   14 +++--
 arch/powerpc/kernel/softemu8xx.c |4 +-
 arch/powerpc/math-emu/math.c |   56 +++
 include/asm-powerpc/ppc_asm.h|5 ++-
 include/asm-powerpc/processor.h  |3 ++
 8 files changed, 61 insertions(+), 46 deletions(-)

Index: linux-2.6-ozlabs/arch/powerpc/kernel/align.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/align.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/align.c
@@ -366,7 +366,7 @@ static int emulate_multiple(struct pt_re
 static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
   unsigned int reg, unsigned int flags)
 {
-   char *ptr = (char *) current-thread.fpr[reg];
+   char *ptr = (char *) current-thread.TS_FPR(reg);
int i, ret;
 
if (!(flags  F))
@@ -784,7 +784,7 @@ int fix_alignment(struct pt_regs *regs)
return -EFAULT;
}
} else if (flags  F) {
-   data.dd = current-thread.fpr[reg];
+   data.dd = current-thread.TS_FPR(reg);
if (flags  S) {
/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -862,7 +862,7 @@ int fix_alignment(struct pt_regs *regs)
if (unlikely(ret))
return -EFAULT;
} else if (flags  F)
-   current-thread.fpr[reg] = data.dd;
+   current-thread.TS_FPR(reg) = data.dd;
else
regs-gpr[reg] = data.ll;
 
Index: linux-2.6-ozlabs/arch/powerpc/kernel/process.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/process.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/process.c
@@ -110,7 +110,7 @@ int dump_task_fpu(struct task_struct *ts
return 0;
flush_fp_to_thread(current);
 
-   memcpy(fpregs, tsk-thread.fpr[0], sizeof(*fpregs));
+   memcpy(fpregs, tsk-thread.TS_FPR(0), sizeof(*fpregs));
 
return 1;
 }
@@ -689,7 +689,8 @@ void start_thread(struct pt_regs *regs, 
 #endif
 
discard_lazy_cpu_state();
-   memset(current-thread.fpr, 0, sizeof(current-thread.fpr));
+   memset(current-thread.fpr, 0,
+  sizeof(current-thread.fpr));
current-thread.fpscr.val = 0;
 #ifdef CONFIG_ALTIVEC
memset(current-thread.vr, 0, sizeof(current-thread.vr));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.fpr, 0, -1);
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset 
*regset,
@@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyin(pos, count, kbuf, ubuf,
- target-thread.fpr, 0, -1);
+ target-thread.fpr, 0, -1);
 }
 
 
@@ -728,7 +728,8 @@ long arch_ptrace(struct task_struct *chi
tmp = ptrace_get_reg(child, (int) index);
} else {
flush_fp_to_thread(child);
-   tmp = ((unsigned long *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned long *)child-thread.fpr)
+   [TS_FPRSPACING * (index - PT_FPR0)];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
@@ -755,7 +756,8 @@ long arch_ptrace(struct task_struct *chi
ret = ptrace_put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
-   ((unsigned long *)child-thread.fpr)[index - PT_FPR0] =

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-22 Thread Michael Neuling 


In message [EMAIL PROTECTED] you wrote
:
 
 On Jun 19, 2008, at 11:13 PM, Michael Neuling wrote:
 
  Index: linux-2.6-ozlabs/include/asm-powerpc/processor.h
  ===
  --- linux-2.6-ozlabs.orig/include/asm-powerpc/processor.h
  +++ linux-2.6-ozlabs/include/asm-powerpc/processor.h
  @@ -136,6 +136,9 @@ typedef struct {
  unsigned long seg;
  } mm_segment_t;
 
  +#define TS_FPR(i) fpr[i]
  +#define TS_FPRSTART fpr
  +
  struct thread_struct {
  unsigned long   ksp;/* Kernel stack pointer */
  unsigned long   ksp_limit;  /* if ksp = ksp_limit stack overflow *
/
  @@ -197,12 +200,13 @@ struct thread_struct {
  .fpexc_mode = MSR_FE0 | MSR_FE1, \
  }
  #else
  +#defineFPVSR_INIT_THREAD .fpr = {0}
 
 Being a bit nit picky, but doesn't seem like this patch should  
 introduce FPVSR.

Yep.. a bit early, thanks.

 
 
  #define INIT_THREAD  { \
  .ksp = INIT_SP, \
  .ksp_limit = INIT_SP_LIMIT, \
  .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
  .fs = KERNEL_DS, \
  -   .fpr = {0}, \
  +   FPVSR_INIT_THREAD, \
  .fpscr = { .val = 0, }, \
  .fpexc_mode = 0, \
  }
  @@ -289,4 +293,5 @@ static inline void prefetchw(const void
 
  #endif /* __KERNEL__ */
  #endif /* __ASSEMBLY__ */
  +#define TS_FPRSPACING 1
  #endif /* _ASM_POWERPC_PROCESSOR_H */
 
___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

[PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-22 Thread Michael Neuling 
We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

 arch/powerpc/kernel/align.c  |6 ++--
 arch/powerpc/kernel/process.c|5 ++-
 arch/powerpc/kernel/ptrace.c |   14 +
 arch/powerpc/kernel/ptrace32.c   |9 --
 arch/powerpc/kernel/softemu8xx.c |4 +-
 arch/powerpc/math-emu/math.c |   56 +++
 include/asm-powerpc/ppc_asm.h|5 ++-
 include/asm-powerpc/processor.h  |3 ++
 8 files changed, 56 insertions(+), 46 deletions(-)

Index: linux-2.6-ozlabs/arch/powerpc/kernel/align.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/align.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/align.c
@@ -366,7 +366,7 @@ static int emulate_multiple(struct pt_re
 static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
   unsigned int reg, unsigned int flags)
 {
-   char *ptr = (char *) current-thread.fpr[reg];
+   char *ptr = (char *) current-thread.TS_FPR(reg);
int i, ret;
 
if (!(flags  F))
@@ -784,7 +784,7 @@ int fix_alignment(struct pt_regs *regs)
return -EFAULT;
}
} else if (flags  F) {
-   data.dd = current-thread.fpr[reg];
+   data.dd = current-thread.TS_FPR(reg);
if (flags  S) {
/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -862,7 +862,7 @@ int fix_alignment(struct pt_regs *regs)
if (unlikely(ret))
return -EFAULT;
} else if (flags  F)
-   current-thread.fpr[reg] = data.dd;
+   current-thread.TS_FPR(reg) = data.dd;
else
regs-gpr[reg] = data.ll;
 
Index: linux-2.6-ozlabs/arch/powerpc/kernel/process.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/process.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/process.c
@@ -110,7 +110,7 @@ int dump_task_fpu(struct task_struct *ts
return 0;
flush_fp_to_thread(current);
 
-   memcpy(fpregs, tsk-thread.fpr[0], sizeof(*fpregs));
+   memcpy(fpregs, tsk-thread.TS_FPR(0), sizeof(*fpregs));
 
return 1;
 }
@@ -689,7 +689,8 @@ void start_thread(struct pt_regs *regs, 
 #endif
 
discard_lazy_cpu_state();
-   memset(current-thread.fpr, 0, sizeof(current-thread.fpr));
+   memset(current-thread.fpr, 0,
+  sizeof(current-thread.fpr));
current-thread.fpscr.val = 0;
 #ifdef CONFIG_ALTIVEC
memset(current-thread.vr, 0, sizeof(current-thread.vr));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.fpr, 0, -1);
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset 
*regset,
@@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyin(pos, count, kbuf, ubuf,
- target-thread.fpr, 0, -1);
+ target-thread.fpr, 0, -1);
 }
 
 
@@ -728,7 +728,8 @@ long arch_ptrace(struct task_struct *chi
tmp = ptrace_get_reg(child, (int) index);
} else {
flush_fp_to_thread(child);
-   tmp = ((unsigned long *)child-thread.fpr)[index - 
PT_FPR0];
+   tmp = ((unsigned long *)child-thread.fpr)
+   [TS_FPRSPACING * (index - PT_FPR0)];
}
ret = put_user(tmp,(unsigned long __user *) data);
break;
@@ -755,7 +756,8 @@ long arch_ptrace(struct task_struct *chi
ret = ptrace_put_reg(child, index, data);
} else {
flush_fp_to_thread(child);
-   ((unsigned long *)child-thread.fpr)[index - PT_FPR0] =

Re: [PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-20 Thread Kumar Gala 


On Jun 19, 2008, at 11:13 PM, Michael Neuling wrote:


Index: linux-2.6-ozlabs/include/asm-powerpc/processor.h
===
--- linux-2.6-ozlabs.orig/include/asm-powerpc/processor.h
+++ linux-2.6-ozlabs/include/asm-powerpc/processor.h
@@ -136,6 +136,9 @@ typedef struct {
unsigned long seg;
} mm_segment_t;

+#define TS_FPR(i) fpr[i]
+#define TS_FPRSTART fpr
+
struct thread_struct {
unsigned long   ksp;/* Kernel stack pointer */
unsigned long   ksp_limit;  /* if ksp = ksp_limit stack overflow */
@@ -197,12 +200,13 @@ struct thread_struct {
.fpexc_mode = MSR_FE0 | MSR_FE1, \
}
#else
+#defineFPVSR_INIT_THREAD .fpr = {0}


Being a bit nit picky, but doesn't seem like this patch should  
introduce FPVSR.




#define INIT_THREAD  { \
.ksp = INIT_SP, \
.ksp_limit = INIT_SP_LIMIT, \
.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
.fs = KERNEL_DS, \
-   .fpr = {0}, \
+   FPVSR_INIT_THREAD, \
.fpscr = { .val = 0, }, \
.fpexc_mode = 0, \
}
@@ -289,4 +293,5 @@ static inline void prefetchw(const void

#endif /* __KERNEL__ */
#endif /* __ASSEMBLY__ */
+#define TS_FPRSPACING 1
#endif /* _ASM_POWERPC_PROCESSOR_H */


___
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev

[PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-19 Thread Michael Neuling 
We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

 arch/powerpc/kernel/align.c   |6 ++--
 arch/powerpc/kernel/asm-offsets.c |2 -
 arch/powerpc/kernel/process.c |5 ++-
 arch/powerpc/kernel/ptrace.c  |   14 +
 arch/powerpc/kernel/ptrace32.c|9 --
 arch/powerpc/kernel/signal_32.c   |6 ++--
 arch/powerpc/kernel/signal_64.c   |   13 +---
 arch/powerpc/kernel/softemu8xx.c  |4 +-
 arch/powerpc/math-emu/math.c  |   56 +++---
 include/asm-powerpc/ppc_asm.h |5 ++-
 include/asm-powerpc/processor.h   |7 
 11 files changed, 71 insertions(+), 56 deletions(-)

Index: linux-2.6-ozlabs/arch/powerpc/kernel/align.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/align.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/align.c
@@ -366,7 +366,7 @@ static int emulate_multiple(struct pt_re
 static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
   unsigned int reg, unsigned int flags)
 {
-   char *ptr = (char *) current-thread.fpr[reg];
+   char *ptr = (char *) current-thread.TS_FPR(reg);
int i, ret;
 
if (!(flags  F))
@@ -784,7 +784,7 @@ int fix_alignment(struct pt_regs *regs)
return -EFAULT;
}
} else if (flags  F) {
-   data.dd = current-thread.fpr[reg];
+   data.dd = current-thread.TS_FPR(reg);
if (flags  S) {
/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -862,7 +862,7 @@ int fix_alignment(struct pt_regs *regs)
if (unlikely(ret))
return -EFAULT;
} else if (flags  F)
-   current-thread.fpr[reg] = data.dd;
+   current-thread.TS_FPR(reg) = data.dd;
else
regs-gpr[reg] = data.ll;
 
Index: linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/asm-offsets.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
@@ -66,7 +66,7 @@ int main(void)
DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
-   DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
+   DEFINE(THREAD_FPR0, offsetof(struct thread_struct, TS_FPR(0)));
DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
 #ifdef CONFIG_ALTIVEC
DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/process.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/process.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/process.c
@@ -110,7 +110,7 @@ int dump_task_fpu(struct task_struct *ts
return 0;
flush_fp_to_thread(current);
 
-   memcpy(fpregs, tsk-thread.fpr[0], sizeof(*fpregs));
+   memcpy(fpregs, tsk-thread.TS_FPR(0), sizeof(*fpregs));
 
return 1;
 }
@@ -689,7 +689,8 @@ void start_thread(struct pt_regs *regs, 
 #endif
 
discard_lazy_cpu_state();
-   memset(current-thread.fpr, 0, sizeof(current-thread.fpr));
+   memset(current-thread.TS_FPRSTART, 0,
+  sizeof(current-thread.TS_FPRSTART));
current-thread.fpscr.val = 0;
 #ifdef CONFIG_ALTIVEC
memset(current-thread.vr, 0, sizeof(current-thread.vr));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.TS_FPRSTART, 0, -1);
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset 
*regset,
@@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyin(pos,

[PATCH 2/9] powerpc: Add macros to access floating point registers in thread_struct.

2008-06-17 Thread Michael Neuling 
We are going to change where the floating point registers are stored
in the thread_struct, so in preparation add some macros to access the
floating point registers.  Update all code to use these new macros.

Signed-off-by: Michael Neuling [EMAIL PROTECTED]
---

 arch/powerpc/kernel/align.c   |6 ++--
 arch/powerpc/kernel/asm-offsets.c |2 -
 arch/powerpc/kernel/process.c |5 ++-
 arch/powerpc/kernel/ptrace.c  |   14 +
 arch/powerpc/kernel/ptrace32.c|9 --
 arch/powerpc/kernel/signal_32.c   |6 ++--
 arch/powerpc/kernel/signal_64.c   |   13 +---
 arch/powerpc/kernel/softemu8xx.c  |4 +-
 arch/powerpc/math-emu/math.c  |   56 +++---
 include/asm-powerpc/ppc_asm.h |5 ++-
 include/asm-powerpc/processor.h   |7 
 11 files changed, 71 insertions(+), 56 deletions(-)

Index: linux-2.6-ozlabs/arch/powerpc/kernel/align.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/align.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/align.c
@@ -366,7 +366,7 @@ static int emulate_multiple(struct pt_re
 static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
   unsigned int reg, unsigned int flags)
 {
-   char *ptr = (char *) current-thread.fpr[reg];
+   char *ptr = (char *) current-thread.TS_FPR(reg);
int i, ret;
 
if (!(flags  F))
@@ -784,7 +784,7 @@ int fix_alignment(struct pt_regs *regs)
return -EFAULT;
}
} else if (flags  F) {
-   data.dd = current-thread.fpr[reg];
+   data.dd = current-thread.TS_FPR(reg);
if (flags  S) {
/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -862,7 +862,7 @@ int fix_alignment(struct pt_regs *regs)
if (unlikely(ret))
return -EFAULT;
} else if (flags  F)
-   current-thread.fpr[reg] = data.dd;
+   current-thread.TS_FPR(reg) = data.dd;
else
regs-gpr[reg] = data.ll;
 
Index: linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/asm-offsets.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
@@ -66,7 +66,7 @@ int main(void)
DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
-   DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
+   DEFINE(THREAD_FPR0, offsetof(struct thread_struct, TS_FPR(0)));
DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
 #ifdef CONFIG_ALTIVEC
DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/process.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/process.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/process.c
@@ -110,7 +110,7 @@ int dump_task_fpu(struct task_struct *ts
return 0;
flush_fp_to_thread(current);
 
-   memcpy(fpregs, tsk-thread.fpr[0], sizeof(*fpregs));
+   memcpy(fpregs, tsk-thread.TS_FPR(0), sizeof(*fpregs));
 
return 1;
 }
@@ -689,7 +689,8 @@ void start_thread(struct pt_regs *regs, 
 #endif
 
discard_lazy_cpu_state();
-   memset(current-thread.fpr, 0, sizeof(current-thread.fpr));
+   memset(current-thread.TS_FPRSTART, 0,
+  sizeof(current-thread.TS_FPRSTART));
current-thread.fpscr.val = 0;
 #ifdef CONFIG_ALTIVEC
memset(current-thread.vr, 0, sizeof(current-thread.vr));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
===
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/ptrace.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/ptrace.c
@@ -218,10 +218,10 @@ static int fpr_get(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyout(pos, count, kbuf, ubuf,
-  target-thread.fpr, 0, -1);
+  target-thread.TS_FPRSTART, 0, -1);
 }
 
 static int fpr_set(struct task_struct *target, const struct user_regset 
*regset,
@@ -231,10 +231,10 @@ static int fpr_set(struct task_struct *t
flush_fp_to_thread(target);
 
BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-offsetof(struct thread_struct, fpr[32]));
+offsetof(struct thread_struct, TS_FPR(32)));
 
return user_regset_copyin(pos,