powerpc: Introduce VSX thread_struct and CONFIG_VSX
The layout of the new VSR registers and how they overlap on top of the
legacy FPR and VR registers is:
VSR doubleword 0 VSR doubleword 1
----------------------------------------------------------------
VSR[0] | FPR[0] | |
----------------------------------------------------------------
VSR[1] | FPR[1] | |
----------------------------------------------------------------
| ... | |
| ... | |
----------------------------------------------------------------
VSR[30] | FPR[30] | |
----------------------------------------------------------------
VSR[31] | FPR[31] | |
----------------------------------------------------------------
VSR[32] | VR[0] |
----------------------------------------------------------------
VSR[33] | VR[1] |
----------------------------------------------------------------
| ... |
| ... |
----------------------------------------------------------------
VSR[62] | VR[30] |
----------------------------------------------------------------
VSR[63] | VR[31] |
----------------------------------------------------------------
VSX has 64 128bit registers. The first 32 regs overlap with the FP
registers and hence extend them with and additional 64 bits. The
second 32 regs overlap with the VMX registers.
This commit introduces the thread_struct changes required to reflect
this register layout. Ptrace and signals code is updated so that the
floating point registers are correctly accessed from the thread_struct
when CONFIG_VSX is enabled.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/include/asm-powerpc/processor.h b/include/asm-powerpc/processor.h
index a23da63..e93e72d 100644
--- a/include/asm-powerpc/processor.h
+++ b/include/asm-powerpc/processor.h
@@ -12,7 +12,11 @@
#include <asm/reg.h>
+#ifdef CONFIG_VSX
+#define TS_FPRWIDTH 2
+#else
#define TS_FPRWIDTH 1
+#endif
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
@@ -80,6 +84,7 @@
/* Lazy FPU handling on uni-processor */
extern struct task_struct *last_task_used_math;
extern struct task_struct *last_task_used_altivec;
+extern struct task_struct *last_task_used_vsx;
extern struct task_struct *last_task_used_spe;
#ifdef CONFIG_PPC32
@@ -142,7 +147,9 @@
unsigned long seg;
} mm_segment_t;
-#define TS_FPR(i) fpr[i]
+#define TS_FPROFFSET 0
+#define TS_VSRLOWOFFSET 1
+#define TS_FPR(i) fpr[i][TS_FPROFFSET]
struct thread_struct {
unsigned long ksp; /* Kernel stack pointer */
@@ -160,8 +167,9 @@
unsigned long dbcr0; /* debug control register values */
unsigned long dbcr1;
#endif
- double fpr[32]; /* Complete floating point set */
- struct { /* fpr ... fpscr must be contiguous */
+ /* FP and VSX 0-31 register set */
+ double fpr[32][TS_FPRWIDTH];
+ struct {
unsigned int pad;
unsigned int val; /* Floating point status */
@@ -181,6 +189,10 @@
unsigned long vrsave;
int used_vr; /* set if process has used altivec */
#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+ /* VSR status */
+ int used_vsr; /* set if process has used altivec */
+#endif /* CONFIG_VSX */
#ifdef CONFIG_SPE
unsigned long evr[32]; /* upper 32-bits of SPE regs */
u64 acc; /* Accumulator */