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>
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 3dd8a6e..ce0930d 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)