[PATCH] powerpc: Fix handling of fpscr on 64-bit

The recent merge of fpu.S broken the handling of fpscr for
ARCH=powerpc and CONFIG_PPC64=y.  FP registers could be corrupted,
leading to strange random application crashes.

The confusion arises, because the thread_struct has (and requires) a
64-bit area to save the fpscr, because we use load/store double
instructions to get it in to/out of the FPU.  However, only the low
32-bits are actually used, so we want to treat it as a 32-bit quantity
when manipulating its bits to avoid extra load/stores on 32-bit.  This
patch replaces the current definition with a structure of two 32-bit
quantities (pad and val), to clarify things as much as is possible.
The 'val' field is used when manipulating bits, the structure itself
is used when obtaining the address for loading/unloading the value
from the FPU.

While we're at it, consolidate the 4 (!) almost identical versions of
cvt_fd() and cvt_df() (arch/ppc/kernel/misc.S,
arch/ppc64/kernel/misc.S, arch/powerpc/kernel/misc_32.S,
arch/powerpc/kernel/misc_64.S) into a single version in fpu.S.  The
new version takes a pointer to thread_struct and applies the correct
offset itself, rather than a pointer to the fpscr field itself, again
to avoid confusion as to which is the correct field to use.

Finally, this patch makes ARCH=ppc64 also use the consolidated fpu.S
code, which it previously did not.

Built for G5 (ARCH=ppc64 and ARCH=powerpc), 32-bit powermac (ARCH=ppc
and ARCH=powerpc) and Walnut (ARCH=ppc, CONFIG_MATH_EMULATION=y).
Booted on G5 (ARCH=powerpc) and things which previously fell over no
longer do.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>

2 files changed, 8 insertions, 7 deletions

diff --git a/include/asm-powerpc/processor.h b/include/asm-powerpc/processor.h
index 9592f533e058..eee954a001fd 100644
--- a/include/asm-powerpc/processor.h
+++ b/include/asm-powerpc/processor.h
@@ -162,10 +162,11 @@ struct thread_struct {
 	unsigned long	dbcr1;
 #endif
 	double		fpr[32];	/* Complete floating point set */
-#ifdef CONFIG_PPC32
-	unsigned long	fpscr_pad;	/* fpr ... fpscr must be contiguous */
-#endif
-	unsigned long	fpscr;		/* Floating point status */
+	struct {			/* fpr ... fpscr must be contiguous */
+
+		unsigned int pad;
+		unsigned int val;	/* Floating point status */
+	} fpscr;
 	int		fpexc_mode;	/* floating-point exception mode */
 #ifdef CONFIG_PPC64
 	unsigned long	start_tb;	/* Start purr when proc switched in */
@@ -207,7 +208,7 @@ struct thread_struct {
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
 	.fpr = {0}, \
-	.fpscr = 0, \
+	.fpscr = { .val = 0, }, \
 	.fpexc_mode = MSR_FE0|MSR_FE1, \
 }
 #endif
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index d60c8c928922..e926e43c4ae6 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -132,8 +132,8 @@ extern int emulate_altivec(struct pt_regs *);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
 extern int fix_alignment(struct pt_regs *);
-extern void cvt_fd(float *from, double *to, unsigned long *fpscr);
-extern void cvt_df(double *from, float *to, unsigned long *fpscr);
+extern void cvt_fd(float *from, double *to, struct thread_struct *thread);
+extern void cvt_df(double *from, float *to, struct thread_struct *thread);
 
 #ifdef CONFIG_ALTIVEC
 extern void flush_altivec_to_thread(struct task_struct *);