linux_dsm_epyc7002/arch/powerpc/kernel/fpu.S
Michael Neuling 7e875e9dc8 powerpc: Disable VSX or current process in giveup_fpu/altivec
When we call giveup_fpu, we need to need to turn off VSX for the
current process.  If we don't, on return to userspace it may execute a
VSX instruction before the next FP instruction, and not have its
register state refreshed correctly from the thread_struct.  Ditto for
altivec.

This caused a bug where an unaligned lfs or stfs results in
fix_alignment calling giveup_fpu so it can use the FPRs (in order to
do a single <-> double conversion), and then returning to userspace
with FP off but VSX on.  Then if a VSX instruction is executed, before
another FP instruction, it will proceed without another exception and
hence have the incorrect register state for VSX registers 0-31.

   lfs unaligned   <- alignment exception turns FP off but leaves VSX on

   VSX instruction <- no exception since VSX on, hence we get the
                      wrong VSX register values for VSX registers 0-31,
                      which overlap the FPRs.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-04-07 15:18:59 +10:00

187 lines
4.7 KiB
ArmAsm

/*
* FPU support code, moved here from head.S so that it can be used
* by chips which use other head-whatever.S files.
*
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
* Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
* Copyright (C) 1996 Paul Mackerras.
* Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
*/
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/cputable.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#ifdef CONFIG_VSX
#define REST_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
REST_32FPRS(n,base); \
b 3f; \
2: REST_32VSRS(n,c,base); \
3:
#define SAVE_32FPVSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
SAVE_32FPRS(n,base); \
b 3f; \
2: SAVE_32VSRS(n,c,base); \
3:
#else
#define REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
#define SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
#endif
/*
* This task wants to use the FPU now.
* On UP, disable FP for the task which had the FPU previously,
* and save its floating-point registers in its thread_struct.
* Load up this task's FP registers from its thread_struct,
* enable the FPU for the current task and return to the task.
*/
_GLOBAL(load_up_fpu)
mfmsr r5
ori r5,r5,MSR_FP
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
oris r5,r5,MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
SYNC
MTMSRD(r5) /* enable use of fpu now */
isync
/*
* For SMP, we don't do lazy FPU switching because it just gets too
* horrendously complex, especially when a task switches from one CPU
* to another. Instead we call giveup_fpu in switch_to.
*/
#ifndef CONFIG_SMP
LOAD_REG_ADDRBASE(r3, last_task_used_math)
toreal(r3)
PPC_LL r4,ADDROFF(last_task_used_math)(r3)
PPC_LCMPI 0,r4,0
beq 1f
toreal(r4)
addi r4,r4,THREAD /* want last_task_used_math->thread */
SAVE_32FPVSRS(0, r5, r4)
mffs fr0
stfd fr0,THREAD_FPSCR(r4)
PPC_LL r5,PT_REGS(r4)
toreal(r5)
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
li r10,MSR_FP|MSR_FE0|MSR_FE1
andc r4,r4,r10 /* disable FP for previous task */
PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
1:
#endif /* CONFIG_SMP */
/* enable use of FP after return */
#ifdef CONFIG_PPC32
mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */
lwz r4,THREAD_FPEXC_MODE(r5)
ori r9,r9,MSR_FP /* enable FP for current */
or r9,r9,r4
#else
ld r4,PACACURRENT(r13)
addi r5,r4,THREAD /* Get THREAD */
lwz r4,THREAD_FPEXC_MODE(r5)
ori r12,r12,MSR_FP
or r12,r12,r4
std r12,_MSR(r1)
#endif
lfd fr0,THREAD_FPSCR(r5)
MTFSF_L(fr0)
REST_32FPVSRS(0, r4, r5)
#ifndef CONFIG_SMP
subi r4,r5,THREAD
fromreal(r4)
PPC_STL r4,ADDROFF(last_task_used_math)(r3)
#endif /* CONFIG_SMP */
/* restore registers and return */
/* we haven't used ctr or xer or lr */
blr
/*
* giveup_fpu(tsk)
* Disable FP for the task given as the argument,
* and save the floating-point registers in its thread_struct.
* Enables the FPU for use in the kernel on return.
*/
_GLOBAL(giveup_fpu)
mfmsr r5
ori r5,r5,MSR_FP
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
oris r5,r5,MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
SYNC_601
ISYNC_601
MTMSRD(r5) /* enable use of fpu now */
SYNC_601
isync
PPC_LCMPI 0,r3,0
beqlr- /* if no previous owner, done */
addi r3,r3,THREAD /* want THREAD of task */
PPC_LL r5,PT_REGS(r3)
PPC_LCMPI 0,r5,0
SAVE_32FPVSRS(0, r4 ,r3)
mffs fr0
stfd fr0,THREAD_FPSCR(r3)
beq 1f
PPC_LL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
li r3,MSR_FP|MSR_FE0|MSR_FE1
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
oris r3,r3,MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
andc r4,r4,r3 /* disable FP for previous task */
PPC_STL r4,_MSR-STACK_FRAME_OVERHEAD(r5)
1:
#ifndef CONFIG_SMP
li r5,0
LOAD_REG_ADDRBASE(r4,last_task_used_math)
PPC_STL r5,ADDROFF(last_task_used_math)(r4)
#endif /* CONFIG_SMP */
blr
/*
* These are used in the alignment trap handler when emulating
* single-precision loads and stores.
* We restore and save the fpscr so the task gets the same result
* and exceptions as if the cpu had performed the load or store.
*/
_GLOBAL(cvt_fd)
lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */
MTFSF_L(0)
lfs 0,0(r3)
stfd 0,0(r4)
mffs 0
stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */
blr
_GLOBAL(cvt_df)
lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */
MTFSF_L(0)
lfd 0,0(r3)
stfs 0,0(r4)
mffs 0
stfd 0,THREAD_FPSCR(r5) /* save new fpscr value */
blr