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>

1 files changed, 48 insertions, 22 deletions

diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index a58777c1b2cb..6840911e7a01 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -178,10 +178,10 @@ _GLOBAL(do_stfd)
 	EX_TABLE(2b,3b)
 
 #ifdef CONFIG_ALTIVEC
-/* Get the contents of vrN into v0; N is in r3. */
+/* Get the contents of vrN into v0; N is in r3. Doesn't touch r3 or r4. */
 _GLOBAL(get_vr)
 	mflr	r0
-	rlwinm	r3,r3,3,0xf8
+	rlwinm	r6,r3,3,0xf8
 	bcl	20,31,1f
 	blr			/* v0 is already in v0 */
 	nop
@@ -192,15 +192,15 @@ reg = 1
 reg = reg + 1
 	.endr
 1:	mflr	r5
-	add	r5,r3,r5
+	add	r5,r6,r5
 	mtctr	r5
 	mtlr	r0
 	bctr
 
-/* Put the contents of v0 into vrN; N is in r3. */
+/* Put the contents of v0 into vrN; N is in r3. Doesn't touch r3 or r4. */
 _GLOBAL(put_vr)
 	mflr	r0
-	rlwinm	r3,r3,3,0xf8
+	rlwinm	r6,r3,3,0xf8
 	bcl	20,31,1f
 	blr			/* v0 is already in v0 */
 	nop
@@ -211,7 +211,7 @@ reg = 1
 reg = reg + 1
 	.endr
 1:	mflr	r5
-	add	r5,r3,r5
+	add	r5,r6,r5
 	mtctr	r5
 	mtlr	r0
 	bctr
@@ -313,7 +313,7 @@ reg = reg + 1
 	bctr
 
 /* Load VSX reg N from vector doubleword *p.  N is in r3, p in r4. */
-_GLOBAL(do_lxvd2x)
+_GLOBAL(load_vsrn)
 	PPC_STLU r1,-STKFRM(r1)
 	mflr	r0
 	PPC_STL	r0,STKFRM+PPC_LR_STKOFF(r1)
@@ -325,41 +325,38 @@ _GLOBAL(do_lxvd2x)
 	isync
 	beq	cr7,1f
 	STXVD2X(0,R1,R8)
-1:	li	r9,-EFAULT
-2:	LXVD2X(0,R0,R4)
-	li	r9,0
-3:	beq	cr7,4f
+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
-	mr	r3,r9
 	addi	r1,r1,STKFRM
 	blr
-	EX_TABLE(2b,3b)
 
 /* Store VSX reg N to vector doubleword *p.  N is in r3, p in r4. */
-_GLOBAL(do_stxvd2x)
+_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
-	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
 	MTMSRD(r7)
 	isync
-	beq	cr7,1f
 	STXVD2X(0,R1,R8)
 	bl	get_vsr
-1:	li	r9,-EFAULT
-2:	STXVD2X(0,R0,R4)
-	li	r9,0
-3:	beq	cr7,4f
+#ifdef __LITTLE_ENDIAN__
+	XXSWAPD(0,0)
+#endif
+	STXVD2X(0,R0,R4)
 	LXVD2X(0,R1,R8)
-4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
+	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
 	MTMSRD(r6)
 	isync
@@ -367,7 +364,36 @@ _GLOBAL(do_stxvd2x)
 	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 */