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>

2 files changed, 29 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 3dd8a6e43bb2..ce0930d68857 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -205,6 +205,8 @@
 #define PPC_INST_ISEL_MASK		0xfc00003e
 #define PPC_INST_LDARX			0x7c0000a8
 #define PPC_INST_STDCX			0x7c0001ad
+#define PPC_INST_LQARX			0x7c000228
+#define PPC_INST_STQCX			0x7c00016d
 #define PPC_INST_LSWI			0x7c0004aa
 #define PPC_INST_LSWX			0x7c00042a
 #define PPC_INST_LWARX			0x7c000028
@@ -403,12 +405,18 @@
 					__PPC_RA(a) | __PPC_RB(b))
 #define	PPC_DCBZL(a, b)		stringify_in_c(.long PPC_INST_DCBZL | \
 					__PPC_RA(a) | __PPC_RB(b))
+#define PPC_LQARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LQARX | \
+					___PPC_RT(t) | ___PPC_RA(a) | \
+					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_LDARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LDARX | \
 					___PPC_RT(t) | ___PPC_RA(a) | \
 					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_LWARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LWARX | \
 					___PPC_RT(t) | ___PPC_RA(a) | \
 					___PPC_RB(b) | __PPC_EH(eh))
+#define PPC_STQCX(t, a, b)	stringify_in_c(.long PPC_INST_STQCX | \
+					___PPC_RT(t) | ___PPC_RA(a) | \
+					___PPC_RB(b))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					___PPC_RB(b))
 #define PPC_MSGSYNC		stringify_in_c(.long PPC_INST_MSGSYNC)
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index 442e6363eb5a..980197024c0b 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -83,6 +83,12 @@ enum instruction_type {
 #define DCBT		0x300
 #define ICBI		0x400
 
+/* VSX flags values */
+#define VSX_FPCONV	1	/* do floating point SP/DP conversion */
+#define VSX_SPLAT	2	/* store loaded value into all elements */
+#define VSX_LDLEFT	4	/* load VSX register from left */
+#define VSX_CHECK_VEC	8	/* check MSR_VEC not MSR_VSX for reg >= 32 */
+
 /* Size field in type word */
 #define SIZE(n)		((n) << 8)
 #define GETSIZE(w)	((w) >> 8)
@@ -100,6 +106,17 @@ struct instruction_op {
 	int spr;
 	u32 ccval;
 	u32 xerval;
+	u8 element_size;	/* for VSX/VMX loads/stores */
+	u8 vsx_flags;
+};
+
+union vsx_reg {
+	u8	b[16];
+	u16	h[8];
+	u32	w[4];
+	unsigned long d[2];
+	float	fp[4];
+	double	dp[2];
 };
 
 /*
@@ -131,3 +148,7 @@ void emulate_update_regs(struct pt_regs *reg, struct instruction_op *op);
  */
 extern int emulate_step(struct pt_regs *regs, unsigned int instr);
 
+extern void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg,
+			     const void *mem);
+extern void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg,
+			      void *mem);