xemu-project/xemu
1
0
Fork 0
mirror of https://github.com/xemu-project/xemu.git synced 2024-11-23 19:49:43 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'rth/tcg-ppc-pull' into staging

Browse Source 
# By Richard Henderson (19) and Paolo Bonzini (2)
# Via Richard Henderson
* rth/tcg-ppc-pull: (21 commits)
  tcg-ppc64: Implement CONFIG_QEMU_LDST_OPTIMIZATION
  tcg-ppc64: Add _noaddr functions for emitting forward branches
  tcg-ppc64: Streamline tcg_out_tlb_read
  tcg-ppc64: Implement tcg_register_jit
  tcg-ppc64: Handle long offsets better
  tcg-ppc64: Tidy register allocation order
  tcg-ppc64: Look through a constant function descriptor
  tcg-ppc64: Fold constant call address into descriptor load
  tcg-ppc64: Don't load the static chain from TCG
  tcg-ppc64: Avoid code for nop move
  tcg-ppc64: Use tcg_out64
  tcg-ppc64: Use TCG_REG_Rn constants
  tcg-ppc64: More use of TAI and SAI helper macros
  tcg-ppc64: Reformat tcg-target.c
  tcg-ppc: Fix and cleanup tcg_out_tlb_check
  tcg-ppc: Use conditional branch and link to slow path
  tcg-ppc: Cleanup tcg_out_qemu_ld/st_slow_path
  tcg-ppc: Avoid code for nop move
  tcg-ppc: use new return-argument ld/st helpers
  tcg-ppc: fix qemu_ld/qemu_st for AIX ABI
  ...

Message-id: 1380126458-3247-1-git-send-email-rth@twiddle.net
This commit is contained in:
Anthony Liguori 2013-09-30 17:14:01 -05:00
commit 28b9d47db6
4 changed files with 844 additions and 789 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
configure vendored
View File

@ -978,6 +978,14 @@ for opt do
done
case "$cpu" in
ppc)
CPU_CFLAGS="-m32"
LDFLAGS="-m32 $LDFLAGS"
;;
ppc64)
CPU_CFLAGS="-m64"
LDFLAGS="-m64 $LDFLAGS"
;;
sparc)
LDFLAGS="-m32 $LDFLAGS"
CPU_CFLAGS="-m32 -mcpu=ultrasparc"
@ -3787,7 +3795,7 @@ echo "libs_softmmu=$libs_softmmu" >> $config_host_mak
echo "ARCH=$ARCH" >> $config_host_mak
case "$cpu" in
arm|i386|x86_64|x32|ppc|aarch64)
aarch64 | arm | i386 | x86_64 | x32 | ppc*)
# The TCG interpreter currently does not support ld/st optimization.
if test "$tcg_interpreter" = "no" ; then
echo "CONFIG_QEMU_LDST_OPTIMIZATION=y" >> $config_host_mak

4
include/exec/exec-all.h
View File

@ -324,9 +324,7 @@ extern uintptr_t tci_tb_ptr;
In some implementations, we pass the "logical" return address manually;
in others, we must infer the logical return from the true return. */
#if defined(CONFIG_QEMU_LDST_OPTIMIZATION) && defined(CONFIG_SOFTMMU)
# if defined (_ARCH_PPC) && !defined (_ARCH_PPC64)
# define GETRA_LDST(RA) (*(int32_t *)((RA) - 4))
# elif defined(__arm__)
# if defined(__arm__)
/* We define two insns between the return address and the branch back to
straight-line. Find and decode that branch insn. */
# define GETRA_LDST(RA) tcg_getra_ldst(RA)

494
tcg/ppc/tcg-target.c
View File

@ -450,7 +450,9 @@ static const uint32_t tcg_to_bc[] = {
static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
{
tcg_out32 (s, OR | SAB (arg, ret, arg));
if (ret != arg) {
tcg_out32(s, OR | SAB(arg, ret, arg));
}
}
static void tcg_out_movi(TCGContext *s, TCGType type,
@ -490,7 +492,8 @@ static void tcg_out_b (TCGContext *s, int mask, tcg_target_long target)
}
}
static void tcg_out_call (TCGContext *s, tcg_target_long arg, int const_arg)
static void tcg_out_call (TCGContext *s, tcg_target_long arg, int const_arg,
int lk)
{
#ifdef _CALL_AIX
int reg;
@ -504,14 +507,14 @@ static void tcg_out_call (TCGContext *s, tcg_target_long arg, int const_arg)
tcg_out32 (s, LWZ | RT (0) | RA (reg));
tcg_out32 (s, MTSPR | RA (0) | CTR);
tcg_out32 (s, LWZ | RT (2) | RA (reg) | 4);
tcg_out32 (s, BCCTR | BO_ALWAYS | LK);
tcg_out32 (s, BCCTR | BO_ALWAYS | lk);
#else
if (const_arg) {
tcg_out_b (s, LK, arg);
tcg_out_b (s, lk, arg);
}
else {
tcg_out32 (s, MTSPR | RS (arg) | LR);
tcg_out32 (s, BCLR | BO_ALWAYS | LK);
tcg_out32 (s, BCLR | BO_ALWAYS | lk);
}
#endif
}
@ -549,118 +552,128 @@ static void add_qemu_ldst_label (TCGContext *s,
label->label_ptr[0] = label_ptr;
}
/* helper signature: helper_ld_mmu(CPUState *env, target_ulong addr,
int mmu_idx) */
/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
* int mmu_idx, uintptr_t ra)
*/
static const void * const qemu_ld_helpers[4] = {
helper_ldb_mmu,
helper_ldw_mmu,
helper_ldl_mmu,
helper_ldq_mmu,
helper_ret_ldub_mmu,
helper_ret_lduw_mmu,
helper_ret_ldul_mmu,
helper_ret_ldq_mmu,
};
/* helper signature: helper_st_mmu(CPUState *env, target_ulong addr,
uintxx_t val, int mmu_idx) */
/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
* uintxx_t val, int mmu_idx, uintptr_t ra)
*/
static const void * const qemu_st_helpers[4] = {
helper_stb_mmu,
helper_stw_mmu,
helper_stl_mmu,
helper_stq_mmu,
helper_ret_stb_mmu,
helper_ret_stw_mmu,
helper_ret_stl_mmu,
helper_ret_stq_mmu,
};
static void *ld_trampolines[4];
static void *st_trampolines[4];
static void tcg_out_tlb_check (TCGContext *s, int r0, int r1, int r2,
int addr_reg, int addr_reg2, int s_bits,
int offset1, int offset2, uint8_t **label_ptr)
/* Perform the TLB load and compare. Branches to the slow path, placing the
address of the branch in *LABEL_PTR. Loads the addend of the TLB into R0.
Clobbers R1 and R2. */
static void tcg_out_tlb_check(TCGContext *s, TCGReg r0, TCGReg r1, TCGReg r2,
TCGReg addrlo, TCGReg addrhi, int s_bits,
int mem_index, int is_load, uint8_t **label_ptr)
{
int cmp_off =
(is_load
? offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
: offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
int add_off = offsetof(CPUArchState, tlb_table[mem_index][0].addend);
uint16_t retranst;
TCGReg base = TCG_AREG0;
tcg_out32 (s, (RLWINM
| RA (r0)
| RS (addr_reg)
| SH (32 - (TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS))
| MB (32 - (CPU_TLB_BITS + CPU_TLB_ENTRY_BITS))
| ME (31 - CPU_TLB_ENTRY_BITS)
)
);
tcg_out32 (s, ADD | RT (r0) | RA (r0) | RB (TCG_AREG0));
tcg_out32 (s, (LWZU
| RT (r1)
| RA (r0)
| offset1
)
);
tcg_out32 (s, (RLWINM
| RA (r2)
| RS (addr_reg)
| SH (0)
| MB ((32 - s_bits) & 31)
| ME (31 - TARGET_PAGE_BITS)
)
);
/* Extract the page index, shifted into place for tlb index. */
tcg_out32(s, (RLWINM
| RA(r0)
| RS(addrlo)
| SH(32 - (TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS))
| MB(32 - (CPU_TLB_BITS + CPU_TLB_ENTRY_BITS))
| ME(31 - CPU_TLB_ENTRY_BITS)));
tcg_out32 (s, CMP | BF (7) | RA (r2) | RB (r1));
#if TARGET_LONG_BITS == 64
tcg_out32 (s, LWZ | RT (r1) | RA (r0) | 4);
tcg_out32 (s, CMP | BF (6) | RA (addr_reg2) | RB (r1));
tcg_out32 (s, CRAND | BT (7, CR_EQ) | BA (6, CR_EQ) | BB (7, CR_EQ));
#endif
/* Compensate for very large offsets. */
if (add_off >= 0x8000) {
/* Most target env are smaller than 32k; none are larger than 64k.
Simplify the logic here merely to offset by 0x7ff0, giving us a
range just shy of 64k. Check this assumption. */
QEMU_BUILD_BUG_ON(offsetof(CPUArchState,
tlb_table[NB_MMU_MODES - 1][1])
> 0x7ff0 + 0x7fff);
tcg_out32(s, ADDI | RT(r1) | RA(base) | 0x7ff0);
base = r1;
cmp_off -= 0x7ff0;
add_off -= 0x7ff0;
}
/* Clear the non-page, non-alignment bits from the address. */
tcg_out32(s, (RLWINM
| RA(r2)
| RS(addrlo)
| SH(0)
| MB((32 - s_bits) & 31)
| ME(31 - TARGET_PAGE_BITS)));
tcg_out32(s, ADD | RT(r0) | RA(r0) | RB(base));
base = r0;
/* Load the tlb comparator. */
tcg_out32(s, LWZ | RT(r1) | RA(base) | (cmp_off & 0xffff));
tcg_out32(s, CMP | BF(7) | RA(r2) | RB(r1));
if (TARGET_LONG_BITS == 64) {
tcg_out32(s, LWZ | RT(r1) | RA(base) | ((cmp_off + 4) & 0xffff));
}
/* Load the tlb addend for use on the fast path.
Do this asap to minimize load delay. */
tcg_out32(s, LWZ | RT(r0) | RA(base) | (add_off & 0xffff));
if (TARGET_LONG_BITS == 64) {
tcg_out32(s, CMP | BF(6) | RA(addrhi) | RB(r1));
tcg_out32(s, CRAND | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ));
}
/* Use a conditional branch-and-link so that we load a pointer to
somewhere within the current opcode, for passing on to the helper.
This address cannot be used for a tail call, but it's shorter
than forming an address from scratch. */
*label_ptr = s->code_ptr;
retranst = ((uint16_t *) s->code_ptr)[1] & ~3;
tcg_out32 (s, BC | BI (7, CR_EQ) | retranst | BO_COND_FALSE);
/* r0 now contains &env->tlb_table[mem_index][index].addr_x */
tcg_out32 (s, (LWZ
| RT (r0)
| RA (r0)
| offset2
)
);
/* r0 = env->tlb_table[mem_index][index].addend */
tcg_out32 (s, ADD | RT (r0) | RA (r0) | RB (addr_reg));
/* r0 = env->tlb_table[mem_index][index].addend + addr */
tcg_out32(s, BC | BI(7, CR_EQ) | retranst | BO_COND_FALSE | LK);
}
#endif
static void tcg_out_qemu_ld (TCGContext *s, const TCGArg *args, int opc)
{
int addr_reg, data_reg, data_reg2, r0, r1, rbase, bswap;
TCGReg addrlo, datalo, datahi, rbase;
int bswap;
#ifdef CONFIG_SOFTMMU
int mem_index, s_bits, r2, addr_reg2;
int mem_index;
TCGReg addrhi;
uint8_t *label_ptr;
#endif
data_reg = *args++;
if (opc == 3)
data_reg2 = *args++;
else
data_reg2 = 0;
addr_reg = *args++;
datalo = *args++;
datahi = (opc == 3 ? *args++ : 0);
addrlo = *args++;
#ifdef CONFIG_SOFTMMU
#if TARGET_LONG_BITS == 64
addr_reg2 = *args++;
#else
addr_reg2 = 0;
#endif
addrhi = (TARGET_LONG_BITS == 64 ? *args++ : 0);
mem_index = *args;
s_bits = opc & 3;
r0 = 3;
r1 = 4;
r2 = 0;
rbase = 0;
tcg_out_tlb_check (
s, r0, r1, r2, addr_reg, addr_reg2, s_bits,
offsetof (CPUArchState, tlb_table[mem_index][0].addr_read),
offsetof (CPUTLBEntry, addend) - offsetof (CPUTLBEntry, addr_read),
&label_ptr
);
tcg_out_tlb_check(s, TCG_REG_R3, TCG_REG_R4, TCG_REG_R0, addrlo,
addrhi, opc & 3, mem_index, 0, &label_ptr);
rbase = TCG_REG_R3;
#else /* !CONFIG_SOFTMMU */
r0 = addr_reg;
r1 = 3;
rbase = GUEST_BASE ? TCG_GUEST_BASE_REG : 0;
#endif
@ -673,106 +686,72 @@ static void tcg_out_qemu_ld (TCGContext *s, const TCGArg *args, int opc)
switch (opc) {
default:
case 0:
tcg_out32 (s, LBZX | TAB (data_reg, rbase, r0));
tcg_out32(s, LBZX | TAB(datalo, rbase, addrlo));
break;
case 0|4:
tcg_out32 (s, LBZX | TAB (data_reg, rbase, r0));
tcg_out32 (s, EXTSB | RA (data_reg) | RS (data_reg));
tcg_out32(s, LBZX | TAB(datalo, rbase, addrlo));
tcg_out32(s, EXTSB | RA(datalo) | RS(datalo));
break;
case 1:
if (bswap)
tcg_out32 (s, LHBRX | TAB (data_reg, rbase, r0));
else
tcg_out32 (s, LHZX | TAB (data_reg, rbase, r0));
tcg_out32(s, (bswap ? LHBRX : LHZX) | TAB(datalo, rbase, addrlo));
break;
case 1|4:
if (bswap) {
tcg_out32 (s, LHBRX | TAB (data_reg, rbase, r0));
tcg_out32 (s, EXTSH | RA (data_reg) | RS (data_reg));
tcg_out32(s, LHBRX | TAB(datalo, rbase, addrlo));
tcg_out32(s, EXTSH | RA(datalo) | RS(datalo));
} else {
tcg_out32(s, LHAX | TAB(datalo, rbase, addrlo));
}
else tcg_out32 (s, LHAX | TAB (data_reg, rbase, r0));
break;
case 2:
if (bswap)
tcg_out32 (s, LWBRX | TAB (data_reg, rbase, r0));
else
tcg_out32 (s, LWZX | TAB (data_reg, rbase, r0));
tcg_out32(s, (bswap ? LWBRX : LWZX) | TAB(datalo, rbase, addrlo));
break;
case 3:
if (bswap) {
tcg_out32 (s, ADDI | RT (r1) | RA (r0) | 4);
tcg_out32 (s, LWBRX | TAB (data_reg, rbase, r0));
tcg_out32 (s, LWBRX | TAB (data_reg2, rbase, r1));
}
else {
#ifdef CONFIG_USE_GUEST_BASE
tcg_out32 (s, ADDI | RT (r1) | RA (r0) | 4);
tcg_out32 (s, LWZX | TAB (data_reg2, rbase, r0));
tcg_out32 (s, LWZX | TAB (data_reg, rbase, r1));
#else
if (r0 == data_reg2) {
tcg_out32 (s, LWZ | RT (0) | RA (r0));
tcg_out32 (s, LWZ | RT (data_reg) | RA (r0) | 4);
tcg_out_mov (s, TCG_TYPE_I32, data_reg2, 0);
}
else {
tcg_out32 (s, LWZ | RT (data_reg2) | RA (r0));
tcg_out32 (s, LWZ | RT (data_reg) | RA (r0) | 4);
}
#endif
tcg_out32(s, ADDI | RT(TCG_REG_R0) | RA(addrlo) | 4);
tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo));
tcg_out32(s, LWBRX | TAB(datahi, rbase, TCG_REG_R0));
} else if (rbase != 0) {
tcg_out32(s, ADDI | RT(TCG_REG_R0) | RA(addrlo) | 4);
tcg_out32(s, LWZX | TAB(datahi, rbase, addrlo));
tcg_out32(s, LWZX | TAB(datalo, rbase, TCG_REG_R0));
} else if (addrlo == datahi) {
tcg_out32(s, LWZ | RT(datalo) | RA(addrlo) | 4);
tcg_out32(s, LWZ | RT(datahi) | RA(addrlo));
} else {
tcg_out32(s, LWZ | RT(datahi) | RA(addrlo));
tcg_out32(s, LWZ | RT(datalo) | RA(addrlo) | 4);
}
break;
}
#ifdef CONFIG_SOFTMMU
add_qemu_ldst_label (s,
1,
opc,
data_reg,
data_reg2,
addr_reg,
addr_reg2,
mem_index,
s->code_ptr,
label_ptr);
add_qemu_ldst_label(s, 1, opc, datalo, datahi, addrlo,
addrhi, mem_index, s->code_ptr, label_ptr);
#endif
}
static void tcg_out_qemu_st (TCGContext *s, const TCGArg *args, int opc)
{
int addr_reg, r0, r1, data_reg, data_reg2, bswap, rbase;
TCGReg addrlo, datalo, datahi, rbase;
int bswap;
#ifdef CONFIG_SOFTMMU
int mem_index, r2, addr_reg2;
int mem_index;
TCGReg addrhi;
uint8_t *label_ptr;
#endif
data_reg = *args++;
if (opc == 3)
data_reg2 = *args++;
else
data_reg2 = 0;
addr_reg = *args++;
datalo = *args++;
datahi = (opc == 3 ? *args++ : 0);
addrlo = *args++;
#ifdef CONFIG_SOFTMMU
#if TARGET_LONG_BITS == 64
addr_reg2 = *args++;
#else
addr_reg2 = 0;
#endif
addrhi = (TARGET_LONG_BITS == 64 ? *args++ : 0);
mem_index = *args;
r0 = 3;
r1 = 4;
r2 = 0;
rbase = 0;
tcg_out_tlb_check (
s, r0, r1, r2, addr_reg, addr_reg2, opc & 3,
offsetof (CPUArchState, tlb_table[mem_index][0].addr_write),
offsetof (CPUTLBEntry, addend) - offsetof (CPUTLBEntry, addr_write),
&label_ptr
);
tcg_out_tlb_check(s, TCG_REG_R3, TCG_REG_R4, TCG_REG_R0, addrlo,
addrhi, opc & 3, mem_index, 0, &label_ptr);
rbase = TCG_REG_R3;
#else /* !CONFIG_SOFTMMU */
r0 = addr_reg;
r1 = 3;
rbase = GUEST_BASE ? TCG_GUEST_BASE_REG : 0;
#endif
@ -783,180 +762,132 @@ static void tcg_out_qemu_st (TCGContext *s, const TCGArg *args, int opc)
#endif
switch (opc) {
case 0:
tcg_out32 (s, STBX | SAB (data_reg, rbase, r0));
tcg_out32(s, STBX | SAB(datalo, rbase, addrlo));
break;
case 1:
if (bswap)
tcg_out32 (s, STHBRX | SAB (data_reg, rbase, r0));
else
tcg_out32 (s, STHX | SAB (data_reg, rbase, r0));
tcg_out32(s, (bswap ? STHBRX : STHX) | SAB(datalo, rbase, addrlo));
break;
case 2:
if (bswap)
tcg_out32 (s, STWBRX | SAB (data_reg, rbase, r0));
else
tcg_out32 (s, STWX | SAB (data_reg, rbase, r0));
tcg_out32(s, (bswap ? STWBRX : STWX) | SAB(datalo, rbase, addrlo));
break;
case 3:
if (bswap) {
tcg_out32 (s, ADDI | RT (r1) | RA (r0) | 4);
tcg_out32 (s, STWBRX | SAB (data_reg, rbase, r0));
tcg_out32 (s, STWBRX | SAB (data_reg2, rbase, r1));
}
else {
#ifdef CONFIG_USE_GUEST_BASE
tcg_out32 (s, STWX | SAB (data_reg2, rbase, r0));
tcg_out32 (s, ADDI | RT (r1) | RA (r0) | 4);
tcg_out32 (s, STWX | SAB (data_reg, rbase, r1));
#else
tcg_out32 (s, STW | RS (data_reg2) | RA (r0));
tcg_out32 (s, STW | RS (data_reg) | RA (r0) | 4);
#endif
tcg_out32(s, ADDI | RT(TCG_REG_R0) | RA(addrlo) | 4);
tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo));
tcg_out32(s, STWBRX | SAB(datahi, rbase, TCG_REG_R0));
} else if (rbase != 0) {
tcg_out32(s, ADDI | RT(TCG_REG_R0) | RA(addrlo) | 4);
tcg_out32(s, STWX | SAB(datahi, rbase, addrlo));
tcg_out32(s, STWX | SAB(datalo, rbase, TCG_REG_R0));
} else {
tcg_out32(s, STW | RS(datahi) | RA(addrlo));
tcg_out32(s, STW | RS(datalo) | RA(addrlo) | 4);
}
break;
}
#ifdef CONFIG_SOFTMMU
add_qemu_ldst_label (s,
0,
opc,
data_reg,
data_reg2,
addr_reg,
addr_reg2,
mem_index,
s->code_ptr,
label_ptr);
add_qemu_ldst_label(s, 0, opc, datalo, datahi, addrlo, addrhi,
mem_index, s->code_ptr, label_ptr);
#endif
}
#if defined(CONFIG_SOFTMMU)
static void tcg_out_qemu_ld_slow_path (TCGContext *s, TCGLabelQemuLdst *label)
static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
{
int s_bits;
int ir;
int opc = label->opc;
int mem_index = label->mem_index;
int data_reg = label->datalo_reg;
int data_reg2 = label->datahi_reg;
int addr_reg = label->addrlo_reg;
uint8_t *raddr = label->raddr;
uint8_t **label_ptr = &label->label_ptr[0];
TCGReg ir, datalo, datahi;
s_bits = opc & 3;
reloc_pc14 (l->label_ptr[0], (uintptr_t)s->code_ptr);
/* resolve label address */
reloc_pc14 (label_ptr[0], (tcg_target_long) s->code_ptr);
/* slow path */
ir = 4;
#if TARGET_LONG_BITS == 32
tcg_out_mov (s, TCG_TYPE_I32, ir++, addr_reg);
#else
ir = TCG_REG_R4;
if (TARGET_LONG_BITS == 32) {
tcg_out_mov(s, TCG_TYPE_I32, ir++, l->addrlo_reg);
} else {
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
ir |= 1;
ir |= 1;
#endif
tcg_out_mov (s, TCG_TYPE_I32, ir++, label->addrhi_reg);
tcg_out_mov (s, TCG_TYPE_I32, ir++, addr_reg);
#endif
tcg_out_movi (s, TCG_TYPE_I32, ir, mem_index);
tcg_out_call (s, (tcg_target_long) ld_trampolines[s_bits], 1);
tcg_out32 (s, (tcg_target_long) raddr);
switch (opc) {
tcg_out_mov(s, TCG_TYPE_I32, ir++, l->addrhi_reg);
tcg_out_mov(s, TCG_TYPE_I32, ir++, l->addrlo_reg);
}
tcg_out_movi(s, TCG_TYPE_I32, ir++, l->mem_index);
tcg_out32(s, MFSPR | RT(ir++) | LR);
tcg_out_b(s, LK, (uintptr_t)ld_trampolines[l->opc & 3]);
datalo = l->datalo_reg;
switch (l->opc) {
case 0|4:
tcg_out32 (s, EXTSB | RA (data_reg) | RS (3));
tcg_out32(s, EXTSB | RA(datalo) | RS(TCG_REG_R3));
break;
case 1|4:
tcg_out32 (s, EXTSH | RA (data_reg) | RS (3));
tcg_out32(s, EXTSH | RA(datalo) | RS(TCG_REG_R3));
break;
case 0:
case 1:
case 2:
if (data_reg != 3)
tcg_out_mov (s, TCG_TYPE_I32, data_reg, 3);
tcg_out_mov(s, TCG_TYPE_I32, datalo, TCG_REG_R3);
break;
case 3:
if (data_reg == 3) {
if (data_reg2 == 4) {
tcg_out_mov (s, TCG_TYPE_I32, 0, 4);
tcg_out_mov (s, TCG_TYPE_I32, 4, 3);
tcg_out_mov (s, TCG_TYPE_I32, 3, 0);
}
else {
tcg_out_mov (s, TCG_TYPE_I32, data_reg2, 3);
tcg_out_mov (s, TCG_TYPE_I32, 3, 4);
}
}
else {
if (data_reg != 4) tcg_out_mov (s, TCG_TYPE_I32, data_reg, 4);
if (data_reg2 != 3) tcg_out_mov (s, TCG_TYPE_I32, data_reg2, 3);
datahi = l->datahi_reg;
if (datalo != TCG_REG_R3) {
tcg_out_mov(s, TCG_TYPE_I32, datalo, TCG_REG_R4);
tcg_out_mov(s, TCG_TYPE_I32, datahi, TCG_REG_R3);
} else if (datahi != TCG_REG_R4) {
tcg_out_mov(s, TCG_TYPE_I32, datahi, TCG_REG_R3);
tcg_out_mov(s, TCG_TYPE_I32, datalo, TCG_REG_R4);
} else {
tcg_out_mov(s, TCG_TYPE_I32, TCG_REG_R0, TCG_REG_R4);
tcg_out_mov(s, TCG_TYPE_I32, datahi, TCG_REG_R3);
tcg_out_mov(s, TCG_TYPE_I32, datalo, TCG_REG_R0);
}
break;
}
/* Jump to the code corresponding to next IR of qemu_st */
tcg_out_b (s, 0, (tcg_target_long) raddr);
tcg_out_b (s, 0, (uintptr_t)l->raddr);
}
static void tcg_out_qemu_st_slow_path (TCGContext *s, TCGLabelQemuLdst *label)
static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
{
int ir;
int opc = label->opc;
int mem_index = label->mem_index;
int data_reg = label->datalo_reg;
int data_reg2 = label->datahi_reg;
int addr_reg = label->addrlo_reg;
uint8_t *raddr = label->raddr;
uint8_t **label_ptr = &label->label_ptr[0];
TCGReg ir, datalo;
/* resolve label address */
reloc_pc14 (label_ptr[0], (tcg_target_long) s->code_ptr);
reloc_pc14 (l->label_ptr[0], (tcg_target_long) s->code_ptr);
/* slow path */
ir = 4;
#if TARGET_LONG_BITS == 32
tcg_out_mov (s, TCG_TYPE_I32, ir++, addr_reg);
#else
ir = TCG_REG_R4;
if (TARGET_LONG_BITS == 32) {
tcg_out_mov (s, TCG_TYPE_I32, ir++, l->addrlo_reg);
} else {
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
ir |= 1;
#endif
tcg_out_mov (s, TCG_TYPE_I32, ir++, label->addrhi_reg);
tcg_out_mov (s, TCG_TYPE_I32, ir++, addr_reg);
ir |= 1;
#endif
tcg_out_mov (s, TCG_TYPE_I32, ir++, l->addrhi_reg);
tcg_out_mov (s, TCG_TYPE_I32, ir++, l->addrlo_reg);
}
switch (opc) {
datalo = l->datalo_reg;
switch (l->opc) {
case 0:
tcg_out32 (s, (RLWINM
| RA (ir)
| RS (data_reg)
| SH (0)
| MB (24)
| ME (31)));
tcg_out32(s, (RLWINM | RA (ir) | RS (datalo)
| SH (0) | MB (24) | ME (31)));
break;
case 1:
tcg_out32 (s, (RLWINM
| RA (ir)
| RS (data_reg)
| SH (0)
| MB (16)
| ME (31)));
tcg_out32(s, (RLWINM | RA (ir) | RS (datalo)
| SH (0) | MB (16) | ME (31)));
break;
case 2:
tcg_out_mov (s, TCG_TYPE_I32, ir, data_reg);
tcg_out_mov(s, TCG_TYPE_I32, ir, datalo);
break;
case 3:
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
ir |= 1;
#endif
tcg_out_mov (s, TCG_TYPE_I32, ir++, data_reg2);
tcg_out_mov (s, TCG_TYPE_I32, ir, data_reg);
tcg_out_mov(s, TCG_TYPE_I32, ir++, l->datahi_reg);
tcg_out_mov(s, TCG_TYPE_I32, ir, datalo);
break;
}
ir++;
tcg_out_movi (s, TCG_TYPE_I32, ir, mem_index);
tcg_out_call (s, (tcg_target_long) st_trampolines[opc], 1);
tcg_out32 (s, (tcg_target_long) raddr);
tcg_out_b (s, 0, (tcg_target_long) raddr);
tcg_out_movi(s, TCG_TYPE_I32, ir++, l->mem_index);
tcg_out32(s, MFSPR | RT(ir++) | LR);
tcg_out_b(s, LK, (uintptr_t)st_trampolines[l->opc]);
tcg_out_b(s, 0, (uintptr_t)l->raddr);
}
void tcg_out_tb_finalize(TCGContext *s)
@ -980,11 +911,8 @@ void tcg_out_tb_finalize(TCGContext *s)
#ifdef CONFIG_SOFTMMU
static void emit_ldst_trampoline (TCGContext *s, const void *ptr)
{
tcg_out32 (s, MFSPR | RT (3) | LR);
tcg_out32 (s, ADDI | RT (3) | RA (3) | 4);
tcg_out32 (s, MTSPR | RS (3) | LR);
tcg_out_mov (s, TCG_TYPE_I32, 3, TCG_AREG0);
tcg_out_b (s, 0, (tcg_target_long) ptr);
tcg_out_call (s, (tcg_target_long) ptr, 1, 0);
}
#endif
@ -1493,7 +1421,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
}
break;
case INDEX_op_call:
tcg_out_call (s, args[0], const_args[0]);
tcg_out_call (s, args[0], const_args[0], LK);
break;
case INDEX_op_movi_i32:
tcg_out_movi(s, TCG_TYPE_I32, args[0], args[1]);
@ -2018,7 +1946,7 @@ static const TCGTargetOpDef ppc_op_defs[] = {
{ INDEX_op_qemu_ld16u, { "r", "L" } },
{ INDEX_op_qemu_ld16s, { "r", "L" } },
{ INDEX_op_qemu_ld32, { "r", "L" } },
{ INDEX_op_qemu_ld64, { "r", "r", "L" } },
{ INDEX_op_qemu_ld64, { "L", "L", "L" } },
{ INDEX_op_qemu_st8, { "K", "K" } },
{ INDEX_op_qemu_st16, { "K", "K" } },
@ -2030,7 +1958,7 @@ static const TCGTargetOpDef ppc_op_defs[] = {
{ INDEX_op_qemu_ld16u, { "r", "L", "L" } },
{ INDEX_op_qemu_ld16s, { "r", "L", "L" } },
{ INDEX_op_qemu_ld32, { "r", "L", "L" } },
{ INDEX_op_qemu_ld64, { "r", "L", "L", "L" } },
{ INDEX_op_qemu_ld64, { "L", "L", "L", "L" } },
{ INDEX_op_qemu_st8, { "K", "K", "K" } },
{ INDEX_op_qemu_st16, { "K", "K", "K" } },

1125
tcg/ppc64/tcg-target.c
View File

File diff suppressed because it is too large Load Diff