powerpc: Put FP/VSX and VR state into structures
This creates new 'thread_fp_state' and 'thread_vr_state' structures
to store FP/VSX state (including FPSCR) and Altivec/VSX state
(including VSCR), and uses them in the thread_struct. In the
thread_fp_state, the FPRs and VSRs are represented as u64 rather
than double, since we rarely perform floating-point computations
on the values, and this will enable the structures to be used
in KVM code as well. Similarly FPSCR is now a u64 rather than
a structure of two 32-bit values.
This takes the offsets out of the macros such as SAVE_32FPRS,
REST_32FPRS, etc. This enables the same macros to be used for normal
and transactional state, enabling us to delete the transactional
versions of the macros. This also removes the unused do_load_up_fpu
and do_load_up_altivec, which were in fact buggy since they didn't
create large enough stack frames to account for the fact that
load_up_fpu and load_up_altivec are not designed to be called from C
and assume that their caller's stack frame is an interrupt frame.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 5995457..140f670 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -98,123 +98,40 @@
#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base)
#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base)
-#define SAVE_FPR(n, base) stfd n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define SAVE_FPR(n, base) stfd n,8*TS_FPRWIDTH*(n)(base)
#define SAVE_2FPRS(n, base) SAVE_FPR(n, base); SAVE_FPR(n+1, base)
#define SAVE_4FPRS(n, base) SAVE_2FPRS(n, base); SAVE_2FPRS(n+2, base)
#define SAVE_8FPRS(n, base) SAVE_4FPRS(n, base); SAVE_4FPRS(n+4, base)
#define SAVE_16FPRS(n, base) SAVE_8FPRS(n, base); SAVE_8FPRS(n+8, base)
#define SAVE_32FPRS(n, base) SAVE_16FPRS(n, base); SAVE_16FPRS(n+16, base)
-#define REST_FPR(n, base) lfd n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define REST_FPR(n, base) lfd n,8*TS_FPRWIDTH*(n)(base)
#define REST_2FPRS(n, base) REST_FPR(n, base); REST_FPR(n+1, base)
#define REST_4FPRS(n, base) REST_2FPRS(n, base); REST_2FPRS(n+2, base)
#define REST_8FPRS(n, base) REST_4FPRS(n, base); REST_4FPRS(n+4, base)
#define REST_16FPRS(n, base) REST_8FPRS(n, base); REST_8FPRS(n+8, base)
#define REST_32FPRS(n, base) REST_16FPRS(n, base); REST_16FPRS(n+16, base)
-#define SAVE_VR(n,b,base) li b,THREAD_VR0+(16*(n)); stvx n,base,b
+#define SAVE_VR(n,b,base) li b,16*(n); stvx n,base,b
#define SAVE_2VRS(n,b,base) SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
#define SAVE_4VRS(n,b,base) SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base)
#define SAVE_8VRS(n,b,base) SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base)
#define SAVE_16VRS(n,b,base) SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base)
#define SAVE_32VRS(n,b,base) SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base)
-#define REST_VR(n,b,base) li b,THREAD_VR0+(16*(n)); lvx n,base,b
+#define REST_VR(n,b,base) li b,16*(n); lvx n,base,b
#define REST_2VRS(n,b,base) REST_VR(n,b,base); REST_VR(n+1,b,base)
#define REST_4VRS(n,b,base) REST_2VRS(n,b,base); REST_2VRS(n+2,b,base)
#define REST_8VRS(n,b,base) REST_4VRS(n,b,base); REST_4VRS(n+4,b,base)
#define REST_16VRS(n,b,base) REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
#define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
-/* Save/restore FPRs, VRs and VSRs from their checkpointed backups in
- * thread_struct:
- */
-#define SAVE_FPR_TRANSACT(n, base) stfd n,THREAD_TRANSACT_FPR0+ \
- 8*TS_FPRWIDTH*(n)(base)
-#define SAVE_2FPRS_TRANSACT(n, base) SAVE_FPR_TRANSACT(n, base); \
- SAVE_FPR_TRANSACT(n+1, base)
-#define SAVE_4FPRS_TRANSACT(n, base) SAVE_2FPRS_TRANSACT(n, base); \
- SAVE_2FPRS_TRANSACT(n+2, base)
-#define SAVE_8FPRS_TRANSACT(n, base) SAVE_4FPRS_TRANSACT(n, base); \
- SAVE_4FPRS_TRANSACT(n+4, base)
-#define SAVE_16FPRS_TRANSACT(n, base) SAVE_8FPRS_TRANSACT(n, base); \
- SAVE_8FPRS_TRANSACT(n+8, base)
-#define SAVE_32FPRS_TRANSACT(n, base) SAVE_16FPRS_TRANSACT(n, base); \
- SAVE_16FPRS_TRANSACT(n+16, base)
-
-#define REST_FPR_TRANSACT(n, base) lfd n,THREAD_TRANSACT_FPR0+ \
- 8*TS_FPRWIDTH*(n)(base)
-#define REST_2FPRS_TRANSACT(n, base) REST_FPR_TRANSACT(n, base); \
- REST_FPR_TRANSACT(n+1, base)
-#define REST_4FPRS_TRANSACT(n, base) REST_2FPRS_TRANSACT(n, base); \
- REST_2FPRS_TRANSACT(n+2, base)
-#define REST_8FPRS_TRANSACT(n, base) REST_4FPRS_TRANSACT(n, base); \
- REST_4FPRS_TRANSACT(n+4, base)
-#define REST_16FPRS_TRANSACT(n, base) REST_8FPRS_TRANSACT(n, base); \
- REST_8FPRS_TRANSACT(n+8, base)
-#define REST_32FPRS_TRANSACT(n, base) REST_16FPRS_TRANSACT(n, base); \
- REST_16FPRS_TRANSACT(n+16, base)
-
-
-#define SAVE_VR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VR0+(16*(n)); \
- stvx n,b,base
-#define SAVE_2VRS_TRANSACT(n,b,base) SAVE_VR_TRANSACT(n,b,base); \
- SAVE_VR_TRANSACT(n+1,b,base)
-#define SAVE_4VRS_TRANSACT(n,b,base) SAVE_2VRS_TRANSACT(n,b,base); \
- SAVE_2VRS_TRANSACT(n+2,b,base)
-#define SAVE_8VRS_TRANSACT(n,b,base) SAVE_4VRS_TRANSACT(n,b,base); \
- SAVE_4VRS_TRANSACT(n+4,b,base)
-#define SAVE_16VRS_TRANSACT(n,b,base) SAVE_8VRS_TRANSACT(n,b,base); \
- SAVE_8VRS_TRANSACT(n+8,b,base)
-#define SAVE_32VRS_TRANSACT(n,b,base) SAVE_16VRS_TRANSACT(n,b,base); \
- SAVE_16VRS_TRANSACT(n+16,b,base)
-
-#define REST_VR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VR0+(16*(n)); \
- lvx n,b,base
-#define REST_2VRS_TRANSACT(n,b,base) REST_VR_TRANSACT(n,b,base); \
- REST_VR_TRANSACT(n+1,b,base)
-#define REST_4VRS_TRANSACT(n,b,base) REST_2VRS_TRANSACT(n,b,base); \
- REST_2VRS_TRANSACT(n+2,b,base)
-#define REST_8VRS_TRANSACT(n,b,base) REST_4VRS_TRANSACT(n,b,base); \
- REST_4VRS_TRANSACT(n+4,b,base)
-#define REST_16VRS_TRANSACT(n,b,base) REST_8VRS_TRANSACT(n,b,base); \
- REST_8VRS_TRANSACT(n+8,b,base)
-#define REST_32VRS_TRANSACT(n,b,base) REST_16VRS_TRANSACT(n,b,base); \
- REST_16VRS_TRANSACT(n+16,b,base)
-
-
-#define SAVE_VSR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VSR0+(16*(n)); \
- STXVD2X(n,R##base,R##b)
-#define SAVE_2VSRS_TRANSACT(n,b,base) SAVE_VSR_TRANSACT(n,b,base); \
- SAVE_VSR_TRANSACT(n+1,b,base)
-#define SAVE_4VSRS_TRANSACT(n,b,base) SAVE_2VSRS_TRANSACT(n,b,base); \
- SAVE_2VSRS_TRANSACT(n+2,b,base)
-#define SAVE_8VSRS_TRANSACT(n,b,base) SAVE_4VSRS_TRANSACT(n,b,base); \
- SAVE_4VSRS_TRANSACT(n+4,b,base)
-#define SAVE_16VSRS_TRANSACT(n,b,base) SAVE_8VSRS_TRANSACT(n,b,base); \
- SAVE_8VSRS_TRANSACT(n+8,b,base)
-#define SAVE_32VSRS_TRANSACT(n,b,base) SAVE_16VSRS_TRANSACT(n,b,base); \
- SAVE_16VSRS_TRANSACT(n+16,b,base)
-
-#define REST_VSR_TRANSACT(n,b,base) li b,THREAD_TRANSACT_VSR0+(16*(n)); \
- LXVD2X(n,R##base,R##b)
-#define REST_2VSRS_TRANSACT(n,b,base) REST_VSR_TRANSACT(n,b,base); \
- REST_VSR_TRANSACT(n+1,b,base)
-#define REST_4VSRS_TRANSACT(n,b,base) REST_2VSRS_TRANSACT(n,b,base); \
- REST_2VSRS_TRANSACT(n+2,b,base)
-#define REST_8VSRS_TRANSACT(n,b,base) REST_4VSRS_TRANSACT(n,b,base); \
- REST_4VSRS_TRANSACT(n+4,b,base)
-#define REST_16VSRS_TRANSACT(n,b,base) REST_8VSRS_TRANSACT(n,b,base); \
- REST_8VSRS_TRANSACT(n+8,b,base)
-#define REST_32VSRS_TRANSACT(n,b,base) REST_16VSRS_TRANSACT(n,b,base); \
- REST_16VSRS_TRANSACT(n+16,b,base)
-
/* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); STXVD2X(n,R##base,R##b)
+#define SAVE_VSR(n,b,base) li b,16*(n); STXVD2X(n,R##base,R##b)
#define SAVE_2VSRS(n,b,base) SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
#define SAVE_4VSRS(n,b,base) SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
#define SAVE_8VSRS(n,b,base) SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
#define SAVE_16VSRS(n,b,base) SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
#define SAVE_32VSRS(n,b,base) SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); LXVD2X(n,R##base,R##b)
+#define REST_VSR(n,b,base) li b,16*(n); LXVD2X(n,R##base,R##b)
#define REST_2VSRS(n,b,base) REST_VSR(n,b,base); REST_VSR(n+1,b,base)
#define REST_4VSRS(n,b,base) REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
#define REST_8VSRS(n,b,base) REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index ce4de5a..afe695e 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -144,8 +144,20 @@
#define TS_FPROFFSET 0
#define TS_VSRLOWOFFSET 1
-#define TS_FPR(i) fpr[i][TS_FPROFFSET]
-#define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET]
+#define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET]
+#define TS_TRANS_FPR(i) transact_fp.fpr[i][TS_FPROFFSET]
+
+/* FP and VSX 0-31 register set */
+struct thread_fp_state {
+ u64 fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
+ u64 fpscr; /* Floating point status */
+};
+
+/* Complete AltiVec register set including VSCR */
+struct thread_vr_state {
+ vector128 vr[32] __attribute__((aligned(16)));
+ vector128 vscr __attribute__((aligned(16)));
+};
struct thread_struct {
unsigned long ksp; /* Kernel stack pointer */
@@ -198,13 +210,7 @@
unsigned long dvc2;
#endif
#endif
- /* FP and VSX 0-31 register set */
- double fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
- struct {
-
- unsigned int pad;
- unsigned int val; /* Floating point status */
- } fpscr;
+ struct thread_fp_state fp_state;
int fpexc_mode; /* floating-point exception mode */
unsigned int align_ctl; /* alignment handling control */
#ifdef CONFIG_PPC64
@@ -222,10 +228,7 @@
struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
unsigned long trap_nr; /* last trap # on this thread */
#ifdef CONFIG_ALTIVEC
- /* Complete AltiVec register set */
- vector128 vr[32] __attribute__((aligned(16)));
- /* AltiVec status */
- vector128 vscr __attribute__((aligned(16)));
+ struct thread_vr_state vr_state;
unsigned long vrsave;
int used_vr; /* set if process has used altivec */
#endif /* CONFIG_ALTIVEC */
@@ -262,13 +265,8 @@
* transact_fpr[] is the new set of transactional values.
* VRs work the same way.
*/
- double transact_fpr[32][TS_FPRWIDTH];
- struct {
- unsigned int pad;
- unsigned int val; /* Floating point status */
- } transact_fpscr;
- vector128 transact_vr[32] __attribute__((aligned(16)));
- vector128 transact_vscr __attribute__((aligned(16)));
+ struct thread_fp_state transact_fp;
+ struct thread_vr_state transact_vr;
unsigned long transact_vrsave;
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
@@ -322,8 +320,6 @@
.ksp = INIT_SP, \
.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
.fs = KERNEL_DS, \
- .fpr = {{0}}, \
- .fpscr = { .val = 0, }, \
.fpexc_mode = 0, \
.ppr = INIT_PPR, \
}
diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
index 3a7a67a..d89beab 100644
--- a/arch/powerpc/include/asm/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -125,7 +125,7 @@
#define FP_EX_DIVZERO (1 << (31 - 5))
#define FP_EX_INEXACT (1 << (31 - 6))
-#define __FPU_FPSCR (current->thread.fpscr.val)
+#define __FPU_FPSCR (current->thread.fp_state.fpscr)
/* We only actually write to the destination register
* if exceptions signalled (if any) will not trap.