[qemu.git] / target / ppc / mem_helper.c

/*
 *  PowerPC memory access emulation helpers for QEMU.
 *
 *  Copyright (c) 2003-2007 Jocelyn Mayer
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */
#include "qemu/osdep.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "qemu/host-utils.h"
#include "exec/helper-proto.h"

#include "helper_regs.h"
#include "exec/cpu_ldst.h"
#include "internal.h"

//#define DEBUG_OP

static inline bool needs_byteswap(const CPUPPCState *env)
{
#if defined(TARGET_WORDS_BIGENDIAN)
  return msr_le;
#else
  return !msr_le;
#endif
}

/*****************************************************************************/
/* Memory load and stores */

static inline target_ulong addr_add(CPUPPCState *env, target_ulong addr,
                                    target_long arg)
{
#if defined(TARGET_PPC64)
    if (!msr_is_64bit(env, env->msr)) {
        return (uint32_t)(addr + arg);
    } else
#endif
    {
        return addr + arg;
    }
}

void helper_lmw(CPUPPCState *env, target_ulong addr, uint32_t reg)
{
    for (; reg < 32; reg++) {
        if (needs_byteswap(env)) {
            env->gpr[reg] = bswap32(cpu_ldl_data_ra(env, addr, GETPC()));
        } else {
            env->gpr[reg] = cpu_ldl_data_ra(env, addr, GETPC());
        }
        addr = addr_add(env, addr, 4);
    }
}

void helper_stmw(CPUPPCState *env, target_ulong addr, uint32_t reg)
{
    for (; reg < 32; reg++) {
        if (needs_byteswap(env)) {
            cpu_stl_data_ra(env, addr, bswap32((uint32_t)env->gpr[reg]),
                                                   GETPC());
        } else {
            cpu_stl_data_ra(env, addr, (uint32_t)env->gpr[reg], GETPC());
        }
        addr = addr_add(env, addr, 4);
    }
}

static void do_lsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
                   uint32_t reg, uintptr_t raddr)
{
    int sh;

    for (; nb > 3; nb -= 4) {
        env->gpr[reg] = cpu_ldl_data_ra(env, addr, raddr);
        reg = (reg + 1) % 32;
        addr = addr_add(env, addr, 4);
    }
    if (unlikely(nb > 0)) {
        env->gpr[reg] = 0;
        for (sh = 24; nb > 0; nb--, sh -= 8) {
            env->gpr[reg] |= cpu_ldub_data_ra(env, addr, raddr) << sh;
            addr = addr_add(env, addr, 1);
        }
    }
}

void helper_lsw(CPUPPCState *env, target_ulong addr, uint32_t nb, uint32_t reg)
{
    do_lsw(env, addr, nb, reg, GETPC());
}

/* PPC32 specification says we must generate an exception if
 * rA is in the range of registers to be loaded.
 * In an other hand, IBM says this is valid, but rA won't be loaded.
 * For now, I'll follow the spec...
 */
void helper_lswx(CPUPPCState *env, target_ulong addr, uint32_t reg,
                 uint32_t ra, uint32_t rb)
{
    if (likely(xer_bc != 0)) {
        int num_used_regs = DIV_ROUND_UP(xer_bc, 4);
        if (unlikely((ra != 0 && lsw_reg_in_range(reg, num_used_regs, ra)) ||
                     lsw_reg_in_range(reg, num_used_regs, rb))) {
            raise_exception_err_ra(env, POWERPC_EXCP_PROGRAM,
                                   POWERPC_EXCP_INVAL |
                                   POWERPC_EXCP_INVAL_LSWX, GETPC());
        } else {
            do_lsw(env, addr, xer_bc, reg, GETPC());
        }
    }
}

void helper_stsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
                 uint32_t reg)
{
    int sh;

    for (; nb > 3; nb -= 4) {
        cpu_stl_data_ra(env, addr, env->gpr[reg], GETPC());
        reg = (reg + 1) % 32;
        addr = addr_add(env, addr, 4);
    }
    if (unlikely(nb > 0)) {
        for (sh = 24; nb > 0; nb--, sh -= 8) {
            cpu_stb_data_ra(env, addr, (env->gpr[reg] >> sh) & 0xFF, GETPC());
            addr = addr_add(env, addr, 1);
        }
    }
}

void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t opcode)
{
    target_ulong mask, dcbz_size = env->dcache_line_size;
    uint32_t i;
    void *haddr;

#if defined(TARGET_PPC64)
    /* Check for dcbz vs dcbzl on 970 */
    if (env->excp_model == POWERPC_EXCP_970 &&
        !(opcode & 0x00200000) && ((env->spr[SPR_970_HID5] >> 7) & 0x3) == 1) {
        dcbz_size = 32;
    }
#endif

    /* Align address */
    mask = ~(dcbz_size - 1);
    addr &= mask;

    /* Check reservation */
    if ((env->reserve_addr & mask) == (addr & mask))  {
        env->reserve_addr = (target_ulong)-1ULL;
    }

    /* Try fast path translate */
    haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, env->dmmu_idx);
    if (haddr) {
        memset(haddr, 0, dcbz_size);
    } else {
        /* Slow path */
        for (i = 0; i < dcbz_size; i += 8) {
            cpu_stq_data_ra(env, addr + i, 0, GETPC());
        }
    }
}

void helper_icbi(CPUPPCState *env, target_ulong addr)
{
    addr &= ~(env->dcache_line_size - 1);
    /* Invalidate one cache line :
     * PowerPC specification says this is to be treated like a load
     * (not a fetch) by the MMU. To be sure it will be so,
     * do the load "by hand".
     */
    cpu_ldl_data_ra(env, addr, GETPC());
}

/* XXX: to be tested */
target_ulong helper_lscbx(CPUPPCState *env, target_ulong addr, uint32_t reg,
                          uint32_t ra, uint32_t rb)
{
    int i, c, d;

    d = 24;
    for (i = 0; i < xer_bc; i++) {
        c = cpu_ldub_data_ra(env, addr, GETPC());
        addr = addr_add(env, addr, 1);
        /* ra (if not 0) and rb are never modified */
        if (likely(reg != rb && (ra == 0 || reg != ra))) {
            env->gpr[reg] = (env->gpr[reg] & ~(0xFF << d)) | (c << d);
        }
        if (unlikely(c == xer_cmp)) {
            break;
        }
        if (likely(d != 0)) {
            d -= 8;
        } else {
            d = 24;
            reg++;
            reg = reg & 0x1F;
        }
    }
    return i;
}

/*****************************************************************************/
/* Altivec extension helpers */
#if defined(HOST_WORDS_BIGENDIAN)
#define HI_IDX 0
#define LO_IDX 1
#else
#define HI_IDX 1
#define LO_IDX 0
#endif

/* We use msr_le to determine index ordering in a vector.  However,
   byteswapping is not simply controlled by msr_le.  We also need to take
   into account endianness of the target.  This is done for the little-endian
   PPC64 user-mode target. */

#define LVE(name, access, swap, element)                        \
    void helper_##name(CPUPPCState *env, ppc_avr_t *r,          \
                       target_ulong addr)                       \
    {                                                           \
        size_t n_elems = ARRAY_SIZE(r->element);                \
        int adjust = HI_IDX*(n_elems - 1);                      \
        int sh = sizeof(r->element[0]) >> 1;                    \
        int index = (addr & 0xf) >> sh;                         \
        if (msr_le) {                                           \
            index = n_elems - index - 1;                        \
        }                                                       \
                                                                \
        if (needs_byteswap(env)) {                              \
            r->element[LO_IDX ? index : (adjust - index)] =     \
                swap(access(env, addr, GETPC()));               \
        } else {                                                \
            r->element[LO_IDX ? index : (adjust - index)] =     \
                access(env, addr, GETPC());                     \
        }                                                       \
    }
#define I(x) (x)
LVE(lvebx, cpu_ldub_data_ra, I, u8)
LVE(lvehx, cpu_lduw_data_ra, bswap16, u16)
LVE(lvewx, cpu_ldl_data_ra, bswap32, u32)
#undef I
#undef LVE

#define STVE(name, access, swap, element)                               \
    void helper_##name(CPUPPCState *env, ppc_avr_t *r,                  \
                       target_ulong addr)                               \
    {                                                                   \
        size_t n_elems = ARRAY_SIZE(r->element);                        \
        int adjust = HI_IDX * (n_elems - 1);                            \
        int sh = sizeof(r->element[0]) >> 1;                            \
        int index = (addr & 0xf) >> sh;                                 \
        if (msr_le) {                                                   \
            index = n_elems - index - 1;                                \
        }                                                               \
                                                                        \
        if (needs_byteswap(env)) {                                      \
            access(env, addr, swap(r->element[LO_IDX ? index :          \
                                              (adjust - index)]),       \
                        GETPC());                                       \
        } else {                                                        \
            access(env, addr, r->element[LO_IDX ? index :               \
                                         (adjust - index)], GETPC());   \
        }                                                               \
    }
#define I(x) (x)
STVE(stvebx, cpu_stb_data_ra, I, u8)
STVE(stvehx, cpu_stw_data_ra, bswap16, u16)
STVE(stvewx, cpu_stl_data_ra, bswap32, u32)
#undef I
#undef LVE

#ifdef TARGET_PPC64
#define GET_NB(rb) ((rb >> 56) & 0xFF)

#define VSX_LXVL(name, lj)                                              \
void helper_##name(CPUPPCState *env, target_ulong addr,                 \
                   target_ulong xt_num, target_ulong rb)                \
{                                                                       \
    int i;                                                              \
    ppc_vsr_t xt;                                                       \
    uint64_t nb = GET_NB(rb);                                           \
                                                                        \
    xt.s128 = int128_zero();                                            \
    if (nb) {                                                           \
        nb = (nb >= 16) ? 16 : nb;                                      \
        if (msr_le && !lj) {                                            \
            for (i = 16; i > 16 - nb; i--) {                            \
                xt.VsrB(i - 1) = cpu_ldub_data_ra(env, addr, GETPC());  \
                addr = addr_add(env, addr, 1);                          \
            }                                                           \
        } else {                                                        \
            for (i = 0; i < nb; i++) {                                  \
                xt.VsrB(i) = cpu_ldub_data_ra(env, addr, GETPC());      \
                addr = addr_add(env, addr, 1);                          \
            }                                                           \
        }                                                               \
    }                                                                   \
    putVSR(xt_num, &xt, env);                                           \
}

VSX_LXVL(lxvl, 0)
VSX_LXVL(lxvll, 1)
#undef VSX_LXVL

#define VSX_STXVL(name, lj)                                       \
void helper_##name(CPUPPCState *env, target_ulong addr,           \
                   target_ulong xt_num, target_ulong rb)          \
{                                                                 \
    int i;                                                        \
    ppc_vsr_t xt;                                                 \
    target_ulong nb = GET_NB(rb);                                 \
                                                                  \
    if (!nb) {                                                    \
        return;                                                   \
    }                                                             \
    getVSR(xt_num, &xt, env);                                     \
    nb = (nb >= 16) ? 16 : nb;                                    \
    if (msr_le && !lj) {                                          \
        for (i = 16; i > 16 - nb; i--) {                          \
            cpu_stb_data_ra(env, addr, xt.VsrB(i - 1), GETPC());  \
            addr = addr_add(env, addr, 1);                        \
        }                                                         \
    } else {                                                      \
        for (i = 0; i < nb; i++) {                                \
            cpu_stb_data_ra(env, addr, xt.VsrB(i), GETPC());      \
            addr = addr_add(env, addr, 1);                        \
        }                                                         \
    }                                                             \
}

VSX_STXVL(stxvl, 0)
VSX_STXVL(stxvll, 1)
#undef VSX_STXVL
#undef GET_NB
#endif /* TARGET_PPC64 */

#undef HI_IDX
#undef LO_IDX

void helper_tbegin(CPUPPCState *env)
{
    /* As a degenerate implementation, always fail tbegin.  The reason
     * given is "Nesting overflow".  The "persistent" bit is set,
     * providing a hint to the error handler to not retry.  The TFIAR
     * captures the address of the failure, which is this tbegin
     * instruction.  Instruction execution will continue with the
     * next instruction in memory, which is precisely what we want.
     */

    env->spr[SPR_TEXASR] =
        (1ULL << TEXASR_FAILURE_PERSISTENT) |
        (1ULL << TEXASR_NESTING_OVERFLOW) |
        (msr_hv << TEXASR_PRIVILEGE_HV) |
        (msr_pr << TEXASR_PRIVILEGE_PR) |
        (1ULL << TEXASR_FAILURE_SUMMARY) |
        (1ULL << TEXASR_TFIAR_EXACT);
    env->spr[SPR_TFIAR] = env->nip | (msr_hv << 1) | msr_pr;
    env->spr[SPR_TFHAR] = env->nip + 4;
    env->crf[0] = 0xB; /* 0b1010 = transaction failure */
}
Commit	Line	Data
9a64fbe4	1	/*
2f5a189c	2	* PowerPC memory access emulation helpers for QEMU.
5fafdf24	3	*
76a66253	4	* Copyright (c) 2003-2007 Jocelyn Mayer
9a64fbe4 FB	5	*
	6	* This library is free software; you can redistribute it and/or
	7	* modify it under the terms of the GNU Lesser General Public
	8	* License as published by the Free Software Foundation; either
	9	* version 2 of the License, or (at your option) any later version.
	10	*
	11	* This library is distributed in the hope that it will be useful,
	12	* but WITHOUT ANY WARRANTY; without even the implied warranty of
	13	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
	14	* Lesser General Public License for more details.
	15	*
	16	* You should have received a copy of the GNU Lesser General Public
8167ee88	17	* License along with this library; if not, see <http://www.gnu.org/licenses/>.
9a64fbe4	18	*/
0d75590d	19	#include "qemu/osdep.h"
3e457172	20	#include "cpu.h"
63c91552	21	#include "exec/exec-all.h"
1de7afc9	22	#include "qemu/host-utils.h"
2ef6175a	23	#include "exec/helper-proto.h"
9a64fbe4	24
0411a972	25	#include "helper_regs.h"
f08b6170	26	#include "exec/cpu_ldst.h"
6914bc4f	27	#include "internal.h"
3e457172	28
fdabc366	29	//#define DEBUG_OP
d12d51d5	30
e22c357b DK	31	static inline bool needs_byteswap(const CPUPPCState *env)
	32	{
	33	#if defined(TARGET_WORDS_BIGENDIAN)
	34	return msr_le;
	35	#else
	36	return !msr_le;
	37	#endif
	38	}
	39
ff4a62cd AJ	40	/*****************************************************************************/
	41	/* Memory load and stores */
	42
2f5a189c BS	43	static inline target_ulong addr_add(CPUPPCState *env, target_ulong addr,
2f5a189c BS	44	target_long arg)
ff4a62cd AJ	45	{
ff4a62cd AJ	46	#if defined(TARGET_PPC64)
e42a61f1	47	if (!msr_is_64bit(env, env->msr)) {
b327c654 BS	48	return (uint32_t)(addr + arg);
b327c654 BS	49	} else
ff4a62cd	50	#endif
b327c654 BS	51	{
	52	return addr + arg;
	53	}
ff4a62cd AJ	54	}
ff4a62cd AJ	55
2f5a189c	56	void helper_lmw(CPUPPCState *env, target_ulong addr, uint32_t reg)
ff4a62cd	57	{
76db3ba4	58	for (; reg < 32; reg++) {
e22c357b	59	if (needs_byteswap(env)) {
af6d376e	60	env->gpr[reg] = bswap32(cpu_ldl_data_ra(env, addr, GETPC()));
b327c654	61	} else {
af6d376e	62	env->gpr[reg] = cpu_ldl_data_ra(env, addr, GETPC());
b327c654	63	}
2f5a189c	64	addr = addr_add(env, addr, 4);
ff4a62cd AJ	65	}
	66	}
	67
2f5a189c	68	void helper_stmw(CPUPPCState *env, target_ulong addr, uint32_t reg)
ff4a62cd	69	{
76db3ba4	70	for (; reg < 32; reg++) {
e22c357b	71	if (needs_byteswap(env)) {
af6d376e BH	72	cpu_stl_data_ra(env, addr, bswap32((uint32_t)env->gpr[reg]),
af6d376e BH	73	GETPC());
b327c654	74	} else {
af6d376e	75	cpu_stl_data_ra(env, addr, (uint32_t)env->gpr[reg], GETPC());
b327c654	76	}
2f5a189c	77	addr = addr_add(env, addr, 4);
ff4a62cd AJ	78	}
	79	}
	80
e41029b3 BH	81	static void do_lsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
e41029b3 BH	82	uint32_t reg, uintptr_t raddr)
dfbc799d AJ	83	{
dfbc799d AJ	84	int sh;
b327c654	85
76db3ba4	86	for (; nb > 3; nb -= 4) {
e41029b3	87	env->gpr[reg] = cpu_ldl_data_ra(env, addr, raddr);
dfbc799d	88	reg = (reg + 1) % 32;
2f5a189c	89	addr = addr_add(env, addr, 4);
dfbc799d AJ	90	}
	91	if (unlikely(nb > 0)) {
	92	env->gpr[reg] = 0;
76db3ba4	93	for (sh = 24; nb > 0; nb--, sh -= 8) {
e41029b3	94	env->gpr[reg] \|= cpu_ldub_data_ra(env, addr, raddr) << sh;
2f5a189c	95	addr = addr_add(env, addr, 1);
dfbc799d AJ	96	}
	97	}
	98	}
e41029b3 BH	99
	100	void helper_lsw(CPUPPCState *env, target_ulong addr, uint32_t nb, uint32_t reg)
	101	{
	102	do_lsw(env, addr, nb, reg, GETPC());
	103	}
	104
dfbc799d AJ	105	/* PPC32 specification says we must generate an exception if
	106	* rA is in the range of registers to be loaded.
	107	* In an other hand, IBM says this is valid, but rA won't be loaded.
	108	* For now, I'll follow the spec...
	109	*/
2f5a189c BS	110	void helper_lswx(CPUPPCState *env, target_ulong addr, uint32_t reg,
2f5a189c BS	111	uint32_t ra, uint32_t rb)
dfbc799d AJ	112	{
dfbc799d AJ	113	if (likely(xer_bc != 0)) {
f0704d78	114	int num_used_regs = DIV_ROUND_UP(xer_bc, 4);
537d3e8e TH	115	if (unlikely((ra != 0 && lsw_reg_in_range(reg, num_used_regs, ra)) \|\|
537d3e8e TH	116	lsw_reg_in_range(reg, num_used_regs, rb))) {
e41029b3 BH	117	raise_exception_err_ra(env, POWERPC_EXCP_PROGRAM,
	118	POWERPC_EXCP_INVAL \|
	119	POWERPC_EXCP_INVAL_LSWX, GETPC());
dfbc799d	120	} else {
e41029b3	121	do_lsw(env, addr, xer_bc, reg, GETPC());
dfbc799d AJ	122	}
	123	}
	124	}
	125
2f5a189c BS	126	void helper_stsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
2f5a189c BS	127	uint32_t reg)
dfbc799d AJ	128	{
dfbc799d AJ	129	int sh;
b327c654	130
76db3ba4	131	for (; nb > 3; nb -= 4) {
e41029b3	132	cpu_stl_data_ra(env, addr, env->gpr[reg], GETPC());
dfbc799d	133	reg = (reg + 1) % 32;
2f5a189c	134	addr = addr_add(env, addr, 4);
dfbc799d AJ	135	}
dfbc799d AJ	136	if (unlikely(nb > 0)) {
a16b45e7	137	for (sh = 24; nb > 0; nb--, sh -= 8) {
e41029b3	138	cpu_stb_data_ra(env, addr, (env->gpr[reg] >> sh) & 0xFF, GETPC());
2f5a189c	139	addr = addr_add(env, addr, 1);
a16b45e7	140	}
dfbc799d AJ	141	}
	142	}
	143
c9f82d01	144	void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t opcode)
799a8c8d	145	{
c9f82d01 BH	146	target_ulong mask, dcbz_size = env->dcache_line_size;
	147	uint32_t i;
	148	void *haddr;
799a8c8d	149
414f5d14	150	#if defined(TARGET_PPC64)
c9f82d01 BH	151	/* Check for dcbz vs dcbzl on 970 */
	152	if (env->excp_model == POWERPC_EXCP_970 &&
	153	!(opcode & 0x00200000) && ((env->spr[SPR_970_HID5] >> 7) & 0x3) == 1) {
8e33944f	154	dcbz_size = 32;
b327c654	155	}
8e33944f AG	156	#endif
8e33944f AG	157
c9f82d01 BH	158	/* Align address */
	159	mask = ~(dcbz_size - 1);
	160	addr &= mask;
	161
	162	/* Check reservation */
	163	if ((env->reserve_addr & mask) == (addr & mask)) {
	164	env->reserve_addr = (target_ulong)-1ULL;
	165	}
8e33944f	166
c9f82d01 BH	167	/* Try fast path translate */
	168	haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, env->dmmu_idx);
	169	if (haddr) {
	170	memset(haddr, 0, dcbz_size);
	171	} else {
	172	/* Slow path */
	173	for (i = 0; i < dcbz_size; i += 8) {
	174	cpu_stq_data_ra(env, addr + i, 0, GETPC());
	175	}
	176	}
799a8c8d AJ	177	}
799a8c8d AJ	178
2f5a189c	179	void helper_icbi(CPUPPCState *env, target_ulong addr)
37d269df	180	{
76db3ba4	181	addr &= ~(env->dcache_line_size - 1);
37d269df AJ	182	/* Invalidate one cache line :
	183	* PowerPC specification says this is to be treated like a load
	184	* (not a fetch) by the MMU. To be sure it will be so,
	185	* do the load "by hand".
	186	*/
af6d376e	187	cpu_ldl_data_ra(env, addr, GETPC());
37d269df AJ	188	}
37d269df AJ	189
b327c654	190	/* XXX: to be tested */
2f5a189c BS	191	target_ulong helper_lscbx(CPUPPCState *env, target_ulong addr, uint32_t reg,
2f5a189c BS	192	uint32_t ra, uint32_t rb)
bdb4b689 AJ	193	{
bdb4b689 AJ	194	int i, c, d;
b327c654	195
bdb4b689 AJ	196	d = 24;
bdb4b689 AJ	197	for (i = 0; i < xer_bc; i++) {
b00a3b36	198	c = cpu_ldub_data_ra(env, addr, GETPC());
2f5a189c	199	addr = addr_add(env, addr, 1);
bdb4b689 AJ	200	/* ra (if not 0) and rb are never modified */
	201	if (likely(reg != rb && (ra == 0 \|\| reg != ra))) {
	202	env->gpr[reg] = (env->gpr[reg] & ~(0xFF << d)) \| (c << d);
	203	}
b327c654	204	if (unlikely(c == xer_cmp)) {
bdb4b689	205	break;
b327c654	206	}
bdb4b689 AJ	207	if (likely(d != 0)) {
	208	d -= 8;
	209	} else {
	210	d = 24;
	211	reg++;
	212	reg = reg & 0x1F;
	213	}
	214	}
	215	return i;
	216	}
	217
d6a46fe8 AJ	218	/*****************************************************************************/
d6a46fe8 AJ	219	/* Altivec extension helpers */
e2542fe2	220	#if defined(HOST_WORDS_BIGENDIAN)
d6a46fe8 AJ	221	#define HI_IDX 0
	222	#define LO_IDX 1
	223	#else
	224	#define HI_IDX 1
	225	#define LO_IDX 0
	226	#endif
	227
e22c357b DK	228	/* We use msr_le to determine index ordering in a vector. However,
	229	byteswapping is not simply controlled by msr_le. We also need to take
	230	into account endianness of the target. This is done for the little-endian
	231	PPC64 user-mode target. */
	232
cbfb6ae9	233	#define LVE(name, access, swap, element) \
2f5a189c BS	234	void helper_##name(CPUPPCState env, ppc_avr_t r, \
2f5a189c BS	235	target_ulong addr) \
cbfb6ae9 AJ	236	{ \
cbfb6ae9 AJ	237	size_t n_elems = ARRAY_SIZE(r->element); \
b327c654	238	int adjust = HI_IDX*(n_elems - 1); \
cbfb6ae9 AJ	239	int sh = sizeof(r->element[0]) >> 1; \
cbfb6ae9 AJ	240	int index = (addr & 0xf) >> sh; \
b327c654	241	if (msr_le) { \
bbfb6f13	242	index = n_elems - index - 1; \
e22c357b DK	243	} \
	244	\
	245	if (needs_byteswap(env)) { \
b327c654	246	r->element[LO_IDX ? index : (adjust - index)] = \
bcd510b1	247	swap(access(env, addr, GETPC())); \
b327c654 BS	248	} else { \
b327c654 BS	249	r->element[LO_IDX ? index : (adjust - index)] = \
bcd510b1	250	access(env, addr, GETPC()); \
b327c654	251	} \
cbfb6ae9 AJ	252	}
cbfb6ae9 AJ	253	#define I(x) (x)
bcd510b1 BH	254	LVE(lvebx, cpu_ldub_data_ra, I, u8)
	255	LVE(lvehx, cpu_lduw_data_ra, bswap16, u16)
	256	LVE(lvewx, cpu_ldl_data_ra, bswap32, u32)
cbfb6ae9 AJ	257	#undef I
	258	#undef LVE
	259
b327c654	260	#define STVE(name, access, swap, element) \
2f5a189c BS	261	void helper_##name(CPUPPCState env, ppc_avr_t r, \
2f5a189c BS	262	target_ulong addr) \
b327c654 BS	263	{ \
	264	size_t n_elems = ARRAY_SIZE(r->element); \
	265	int adjust = HI_IDX * (n_elems - 1); \
	266	int sh = sizeof(r->element[0]) >> 1; \
	267	int index = (addr & 0xf) >> sh; \
b327c654	268	if (msr_le) { \
bbfb6f13	269	index = n_elems - index - 1; \
e22c357b DK	270	} \
	271	\
	272	if (needs_byteswap(env)) { \
2f5a189c	273	access(env, addr, swap(r->element[LO_IDX ? index : \
bcd510b1 BH	274	(adjust - index)]), \
bcd510b1 BH	275	GETPC()); \
cbfb6ae9	276	} else { \
2f5a189c	277	access(env, addr, r->element[LO_IDX ? index : \
bcd510b1	278	(adjust - index)], GETPC()); \
cbfb6ae9 AJ	279	} \
	280	}
	281	#define I(x) (x)
bcd510b1 BH	282	STVE(stvebx, cpu_stb_data_ra, I, u8)
	283	STVE(stvehx, cpu_stw_data_ra, bswap16, u16)
	284	STVE(stvewx, cpu_stl_data_ra, bswap32, u32)
cbfb6ae9 AJ	285	#undef I
	286	#undef LVE
	287
6914bc4f ND	288	#ifdef TARGET_PPC64
	289	#define GET_NB(rb) ((rb >> 56) & 0xFF)
	290
	291	#define VSX_LXVL(name, lj) \
	292	void helper_##name(CPUPPCState *env, target_ulong addr, \
	293	target_ulong xt_num, target_ulong rb) \
	294	{ \
	295	int i; \
	296	ppc_vsr_t xt; \
	297	uint64_t nb = GET_NB(rb); \
	298	\
	299	xt.s128 = int128_zero(); \
	300	if (nb) { \
	301	nb = (nb >= 16) ? 16 : nb; \
	302	if (msr_le && !lj) { \
	303	for (i = 16; i > 16 - nb; i--) { \
	304	xt.VsrB(i - 1) = cpu_ldub_data_ra(env, addr, GETPC()); \
	305	addr = addr_add(env, addr, 1); \
	306	} \
	307	} else { \
	308	for (i = 0; i < nb; i++) { \
	309	xt.VsrB(i) = cpu_ldub_data_ra(env, addr, GETPC()); \
	310	addr = addr_add(env, addr, 1); \
	311	} \
	312	} \
	313	} \
	314	putVSR(xt_num, &xt, env); \
	315	}
	316
	317	VSX_LXVL(lxvl, 0)
176e44e7	318	VSX_LXVL(lxvll, 1)
6914bc4f	319	#undef VSX_LXVL
681c2478 ND	320
	321	#define VSX_STXVL(name, lj) \
	322	void helper_##name(CPUPPCState *env, target_ulong addr, \
	323	target_ulong xt_num, target_ulong rb) \
	324	{ \
	325	int i; \
	326	ppc_vsr_t xt; \
	327	target_ulong nb = GET_NB(rb); \
	328	\
	329	if (!nb) { \
	330	return; \
	331	} \
	332	getVSR(xt_num, &xt, env); \
	333	nb = (nb >= 16) ? 16 : nb; \
	334	if (msr_le && !lj) { \
	335	for (i = 16; i > 16 - nb; i--) { \
	336	cpu_stb_data_ra(env, addr, xt.VsrB(i - 1), GETPC()); \
	337	addr = addr_add(env, addr, 1); \
	338	} \
	339	} else { \
	340	for (i = 0; i < nb; i++) { \
	341	cpu_stb_data_ra(env, addr, xt.VsrB(i), GETPC()); \
	342	addr = addr_add(env, addr, 1); \
	343	} \
	344	} \
	345	}
	346
	347	VSX_STXVL(stxvl, 0)
e122090d	348	VSX_STXVL(stxvll, 1)
681c2478	349	#undef VSX_STXVL
6914bc4f ND	350	#undef GET_NB
	351	#endif /* TARGET_PPC64 */
	352
d6a46fe8 AJ	353	#undef HI_IDX
d6a46fe8 AJ	354	#undef LO_IDX
0ff93d11 TM	355
	356	void helper_tbegin(CPUPPCState *env)
	357	{
	358	/* As a degenerate implementation, always fail tbegin. The reason
	359	* given is "Nesting overflow". The "persistent" bit is set,
	360	* providing a hint to the error handler to not retry. The TFIAR
	361	* captures the address of the failure, which is this tbegin
	362	* instruction. Instruction execution will continue with the
	363	* next instruction in memory, which is precisely what we want.
	364	*/
	365
	366	env->spr[SPR_TEXASR] =
	367	(1ULL << TEXASR_FAILURE_PERSISTENT) \|
	368	(1ULL << TEXASR_NESTING_OVERFLOW) \|
	369	(msr_hv << TEXASR_PRIVILEGE_HV) \|
	370	(msr_pr << TEXASR_PRIVILEGE_PR) \|
	371	(1ULL << TEXASR_FAILURE_SUMMARY) \|
	372	(1ULL << TEXASR_TFIAR_EXACT);
	373	env->spr[SPR_TFIAR] = env->nip \| (msr_hv << 1) \| msr_pr;
	374	env->spr[SPR_TFHAR] = env->nip + 4;
	375	env->crf[0] = 0xB; /* 0b1010 = transaction failure */
	376	}