linux/arch/powerpc/lib/ldstfp.S
Paul Mackerras 350779a29f powerpc: Handle most loads and stores in instruction emulation code
This extends the instruction emulation infrastructure in sstep.c to
handle all the load and store instructions defined in the Power ISA
v3.0, except for the atomic memory operations, ldmx (which was never
implemented), lfdp/stfdp, and the vector element load/stores.

The instructions added are:

Integer loads and stores: lbarx, lharx, lqarx, stbcx., sthcx., stqcx.,
lq, stq.

VSX loads and stores: lxsiwzx, lxsiwax, stxsiwx, lxvx, lxvl, lxvll,
lxvdsx, lxvwsx, stxvx, stxvl, stxvll, lxsspx, lxsdx, stxsspx, stxsdx,
lxvw4x, lxsibzx, lxvh8x, lxsihzx, lxvb16x, stxvw4x, stxsibx, stxvh8x,
stxsihx, stxvb16x, lxsd, lxssp, lxv, stxsd, stxssp, stxv.

These instructions are handled both in the analyse_instr phase and in
the emulate_step phase.

The code for lxvd2ux and stxvd2ux has been taken out, as those
instructions were never implemented in any processor and have been
taken out of the architecture, and their opcodes have been reused for
other instructions in POWER9 (lxvb16x and stxvb16x).

The emulation for the VSX loads and stores uses helper functions
which don't access registers or memory directly, which can hopefully
be reused by KVM later.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-09-01 16:39:48 +10:00

400 lines
6.6 KiB
ArmAsm

/*
* Floating-point, VMX/Altivec and VSX loads and stores
* for use in instruction emulation.
*
* Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* 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/processor.h>
#include <asm/ppc_asm.h>
#include <asm/ppc-opcode.h>
#include <asm/reg.h>
#include <asm/asm-offsets.h>
#include <linux/errno.h>
#ifdef CONFIG_PPC_FPU
#define STKFRM (PPC_MIN_STKFRM + 16)
.macro inst32 op
reg = 0
.rept 32
20: \op reg,0,r4
b 3f
EX_TABLE(20b,99f)
reg = reg + 1
.endr
.endm
/* Get the contents of frN into fr0; N is in r3. */
_GLOBAL(get_fpr)
mflr r0
rlwinm r3,r3,3,0xf8
bcl 20,31,1f
blr /* fr0 is already in fr0 */
nop
reg = 1
.rept 31
fmr fr0,reg
blr
reg = reg + 1
.endr
1: mflr r5
add r5,r3,r5
mtctr r5
mtlr r0
bctr
/* Put the contents of fr0 into frN; N is in r3. */
_GLOBAL(put_fpr)
mflr r0
rlwinm r3,r3,3,0xf8
bcl 20,31,1f
blr /* fr0 is already in fr0 */
nop
reg = 1
.rept 31
fmr reg,fr0
blr
reg = reg + 1
.endr
1: mflr r5
add r5,r3,r5
mtctr r5
mtlr r0
bctr
/* Load FP reg N from float at *p. N is in r3, p in r4. */
_GLOBAL(do_lfs)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
ori r7,r6,MSR_FP
cmpwi cr7,r3,0
MTMSRD(r7)
isync
beq cr7,1f
stfd fr0,STKFRM-16(r1)
1: li r9,-EFAULT
2: lfs fr0,0(r4)
li r9,0
3: bl put_fpr
beq cr7,4f
lfd fr0,STKFRM-16(r1)
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
/* Load FP reg N from double at *p. N is in r3, p in r4. */
_GLOBAL(do_lfd)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
ori r7,r6,MSR_FP
cmpwi cr7,r3,0
MTMSRD(r7)
isync
beq cr7,1f
stfd fr0,STKFRM-16(r1)
1: li r9,-EFAULT
2: lfd fr0,0(r4)
li r9,0
3: beq cr7,4f
bl put_fpr
lfd fr0,STKFRM-16(r1)
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
/* Store FP reg N to float at *p. N is in r3, p in r4. */
_GLOBAL(do_stfs)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
ori r7,r6,MSR_FP
cmpwi cr7,r3,0
MTMSRD(r7)
isync
beq cr7,1f
stfd fr0,STKFRM-16(r1)
bl get_fpr
1: li r9,-EFAULT
2: stfs fr0,0(r4)
li r9,0
3: beq cr7,4f
lfd fr0,STKFRM-16(r1)
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
/* Store FP reg N to double at *p. N is in r3, p in r4. */
_GLOBAL(do_stfd)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
ori r7,r6,MSR_FP
cmpwi cr7,r3,0
MTMSRD(r7)
isync
beq cr7,1f
stfd fr0,STKFRM-16(r1)
bl get_fpr
1: li r9,-EFAULT
2: stfd fr0,0(r4)
li r9,0
3: beq cr7,4f
lfd fr0,STKFRM-16(r1)
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
#ifdef CONFIG_ALTIVEC
/* Get the contents of vrN into v0; N is in r3. Doesn't touch r3 or r4. */
_GLOBAL(get_vr)
mflr r0
rlwinm r6,r3,3,0xf8
bcl 20,31,1f
blr /* v0 is already in v0 */
nop
reg = 1
.rept 31
vor v0,reg,reg /* assembler doesn't know vmr? */
blr
reg = reg + 1
.endr
1: mflr r5
add r5,r6,r5
mtctr r5
mtlr r0
bctr
/* Put the contents of v0 into vrN; N is in r3. Doesn't touch r3 or r4. */
_GLOBAL(put_vr)
mflr r0
rlwinm r6,r3,3,0xf8
bcl 20,31,1f
blr /* v0 is already in v0 */
nop
reg = 1
.rept 31
vor reg,v0,v0
blr
reg = reg + 1
.endr
1: mflr r5
add r5,r6,r5
mtctr r5
mtlr r0
bctr
/* Load vector reg N from *p. N is in r3, p in r4. */
_GLOBAL(do_lvx)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
oris r7,r6,MSR_VEC@h
cmpwi cr7,r3,0
li r8,STKFRM-16
MTMSRD(r7)
isync
beq cr7,1f
stvx v0,r1,r8
1: li r9,-EFAULT
2: lvx v0,0,r4
li r9,0
3: beq cr7,4f
bl put_vr
lvx v0,r1,r8
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
/* Store vector reg N to *p. N is in r3, p in r4. */
_GLOBAL(do_stvx)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
oris r7,r6,MSR_VEC@h
cmpwi cr7,r3,0
li r8,STKFRM-16
MTMSRD(r7)
isync
beq cr7,1f
stvx v0,r1,r8
bl get_vr
1: li r9,-EFAULT
2: stvx v0,0,r4
li r9,0
3: beq cr7,4f
lvx v0,r1,r8
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
/* Get the contents of vsN into vs0; N is in r3. */
_GLOBAL(get_vsr)
mflr r0
rlwinm r3,r3,3,0x1f8
bcl 20,31,1f
blr /* vs0 is already in vs0 */
nop
reg = 1
.rept 63
XXLOR(0,reg,reg)
blr
reg = reg + 1
.endr
1: mflr r5
add r5,r3,r5
mtctr r5
mtlr r0
bctr
/* Put the contents of vs0 into vsN; N is in r3. */
_GLOBAL(put_vsr)
mflr r0
rlwinm r3,r3,3,0x1f8
bcl 20,31,1f
blr /* v0 is already in v0 */
nop
reg = 1
.rept 63
XXLOR(reg,0,0)
blr
reg = reg + 1
.endr
1: mflr r5
add r5,r3,r5
mtctr r5
mtlr r0
bctr
/* Load VSX reg N from vector doubleword *p. N is in r3, p in r4. */
_GLOBAL(load_vsrn)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
oris r7,r6,MSR_VSX@h
cmpwi cr7,r3,0
li r8,STKFRM-16
MTMSRD(r7)
isync
beq cr7,1f
STXVD2X(0,R1,R8)
1: LXVD2X(0,R0,R4)
#ifdef __LITTLE_ENDIAN__
XXSWAPD(0,0)
#endif
beq cr7,4f
bl put_vsr
LXVD2X(0,R1,R8)
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
addi r1,r1,STKFRM
blr
/* Store VSX reg N to vector doubleword *p. N is in r3, p in r4. */
_GLOBAL(store_vsrn)
PPC_STLU r1,-STKFRM(r1)
mflr r0
PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1)
mfmsr r6
oris r7,r6,MSR_VSX@h
li r8,STKFRM-16
MTMSRD(r7)
isync
STXVD2X(0,R1,R8)
bl get_vsr
#ifdef __LITTLE_ENDIAN__
XXSWAPD(0,0)
#endif
STXVD2X(0,R0,R4)
LXVD2X(0,R1,R8)
PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
isync
mr r3,r9
addi r1,r1,STKFRM
blr
EX_TABLE(2b,3b)
#endif /* CONFIG_VSX */
/* Convert single-precision to double, without disturbing FPRs. */
/* conv_sp_to_dp(float *sp, double *dp) */
_GLOBAL(conv_sp_to_dp)
mfmsr r6
ori r7, r6, MSR_FP
MTMSRD(r7)
isync
stfd fr0, -16(r1)
lfs fr0, 0(r3)
stfd fr0, 0(r4)
lfd fr0, -16(r1)
MTMSRD(r6)
isync
blr
/* Convert single-precision to double, without disturbing FPRs. */
/* conv_sp_to_dp(double *dp, float *sp) */
_GLOBAL(conv_dp_to_sp)
mfmsr r6
ori r7, r6, MSR_FP
MTMSRD(r7)
isync
stfd fr0, -16(r1)
lfd fr0, 0(r3)
stfs fr0, 0(r4)
lfd fr0, -16(r1)
MTMSRD(r6)
isync
blr
#endif /* CONFIG_PPC_FPU */