yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2024-12-23 16:55:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

target/arm: Pass TCGMemOpIdx to sve memory helpers

Browse source 
There is quite a lot of code required to compute cpu_mem_index,
or even put together the full TCGMemOpIdx. This can easily be
done at translation time.

Backports commit 500d04843ba953dc4560e44f04001efec38c14a6 from qemu
This commit is contained in:
Richard Henderson 2018-10-08 13:36:57 -04:00 committed by Lioncash
parent 606e8cdb8c
commit 66ffb372e7
No known key found for this signature in database
GPG key ID: 4E3C3CC1031BA9C7
3 changed files with 121 additions and 89 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
qemu/target/arm/internals.h
View file

@ -798,4 +798,9 @@ static inline uint32_t arm_debug_exception_fsr(CPUARMState *env)
}
}
/* Note make_memop_idx reserves 4 bits for mmu_idx, and MO_BSWAP is bit 3.
* Thus a TCGMemOpIdx, without any MO_ALIGN bits, fits in 8 bits.
*/
#define MEMOPIDX_SHIFT 8
#endif

138
qemu/target/arm/sve_helper.c
View file

@ -19,6 +19,7 @@
#include "qemu/osdep.h"
#include "cpu.h"
#include "internals.h"
#include "exec/exec-all.h"
#include "exec/cpu_ldst.h"
#include "exec/helper-proto.h"
@ -3511,7 +3512,7 @@ typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void *host,
* The controlling predicate is known to be true.
*/
typedef void sve_ld1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off,
target_ulong vaddr, int mmu_idx, uintptr_t ra);
target_ulong vaddr, TCGMemOpIdx oi, uintptr_t ra);
typedef sve_ld1_tlb_fn sve_st1_tlb_fn;
/*
@ -3538,16 +3539,15 @@ static intptr_t sve_##NAME##_host(void *vd, void *vg, void *host, \
#ifdef CONFIG_SOFTMMU
#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \
static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \
target_ulong addr, int mmu_idx, uintptr_t ra) \
target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \
{ \
TCGMemOpIdx oi = make_memop_idx(ctz32(sizeof(TYPEM)) | MOEND, mmu_idx); \
TYPEM val = TLB(env, addr, oi, ra); \
*(TYPEE *)(vd + H(reg_off)) = val; \
}
#else
#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \
static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \
target_ulong addr, int mmu_idx, uintptr_t ra) \
target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \
{ \
TYPEM val = HOST(g2h(addr)); \
*(TYPEE *)(vd + H(reg_off)) = val; \
@ -3675,11 +3675,13 @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
sve_ld1_host_fn *host_fn,
sve_ld1_tlb_fn *tlb_fn)
{
void *vd = &env->vfp.zregs[simd_data(desc)];
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int mmu_idx = get_mmuidx(oi);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
void *vd = &env->vfp.zregs[rd];
const int diffsz = esz - msz;
const intptr_t reg_max = simd_oprsz(desc);
const intptr_t mem_max = reg_max >> diffsz;
const int mmu_idx = cpu_mmu_index(env, false);
ARMVectorReg scratch;
void *host;
intptr_t split, reg_off, mem_off;
@ -3753,7 +3755,7 @@ static void sve_ld1_r(CPUARMState *env, void *vg, const target_ulong addr,
* on I/O memory, it may succeed but not bring in the TLB entry.
* But even then we have still made forward progress.
*/
tlb_fn(env, &scratch, reg_off, addr + mem_off, mmu_idx, retaddr);
tlb_fn(env, &scratch, reg_off, addr + mem_off, oi, retaddr);
reg_off += 1 << esz;
}
#endif
@ -3814,9 +3816,9 @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, int size, uintptr_t ra,
sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
ARMVectorReg scratch[2] = { };
set_helper_retaddr(ra);
@ -3824,8 +3826,8 @@ static void sve_ld2_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra);
tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra);
tlb_fn(env, &scratch[0], i, addr, oi, ra);
tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
}
i += size, pg >>= size;
addr += 2 * size;
@ -3842,9 +3844,9 @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, int size, uintptr_t ra,
sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
ARMVectorReg scratch[3] = { };
set_helper_retaddr(ra);
@ -3852,9 +3854,9 @@ static void sve_ld3_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra);
tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra);
tlb_fn(env, &scratch[2], i, addr + 2 * size, mmu_idx, ra);
tlb_fn(env, &scratch[0], i, addr, oi, ra);
tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra);
}
i += size, pg >>= size;
addr += 3 * size;
@ -3872,9 +3874,9 @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, int size, uintptr_t ra,
sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
ARMVectorReg scratch[4] = { };
set_helper_retaddr(ra);
@ -3882,10 +3884,10 @@ static void sve_ld4_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, &scratch[0], i, addr, mmu_idx, ra);
tlb_fn(env, &scratch[1], i, addr + size, mmu_idx, ra);
tlb_fn(env, &scratch[2], i, addr + 2 * size, mmu_idx, ra);
tlb_fn(env, &scratch[3], i, addr + 3 * size, mmu_idx, ra);
tlb_fn(env, &scratch[0], i, addr, oi, ra);
tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
tlb_fn(env, &scratch[2], i, addr + 2 * size, oi, ra);
tlb_fn(env, &scratch[3], i, addr + 3 * size, oi, ra);
}
i += size, pg >>= size;
addr += 4 * size;
@ -3980,11 +3982,13 @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
sve_ld1_host_fn *host_fn,
sve_ld1_tlb_fn *tlb_fn)
{
void *vd = &env->vfp.zregs[simd_data(desc)];
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int mmu_idx = get_mmuidx(oi);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
void *vd = &env->vfp.zregs[rd];
const int diffsz = esz - msz;
const intptr_t reg_max = simd_oprsz(desc);
const intptr_t mem_max = reg_max >> diffsz;
const int mmu_idx = cpu_mmu_index(env, false);
intptr_t split, reg_off, mem_off;
void *host;
@ -4036,7 +4040,7 @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const target_ulong addr,
* Perform one normal read, which will fault or not.
* But it is likely to bring the page into the tlb.
*/
tlb_fn(env, vd, reg_off, addr + mem_off, mmu_idx, retaddr);
tlb_fn(env, vd, reg_off, addr + mem_off, oi, retaddr);
/* After any fault, zero any leading predicated false elts. */
swap_memzero(vd, reg_off);
@ -4065,7 +4069,8 @@ static void sve_ldnf1_r(CPUARMState *env, void *vg, const target_ulong addr,
uint32_t desc, const int esz, const int msz,
sve_ld1_host_fn *host_fn)
{
void *vd = &env->vfp.zregs[simd_data(desc)];
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
void *vd = &env->vfp.zregs[rd];
const int diffsz = esz - msz;
const intptr_t reg_max = simd_oprsz(desc);
const intptr_t mem_max = reg_max >> diffsz;
@ -4200,15 +4205,14 @@ DO_LDFF1_LDNF1_2(dd, 3, 3)
#ifdef CONFIG_SOFTMMU
#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \
static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \
target_ulong addr, int mmu_idx, uintptr_t ra) \
target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \
{ \
TCGMemOpIdx oi = make_memop_idx(ctz32(sizeof(TYPEM)) | MOEND, mmu_idx); \
TLB(env, addr, *(TYPEM *)(vd + H(reg_off)), oi, ra); \
}
#else
#define DO_ST_TLB(NAME, H, TYPEM, HOST, MOEND, TLB) \
static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \
target_ulong addr, int mmu_idx, uintptr_t ra) \
target_ulong addr, TCGMemOpIdx oi, uintptr_t ra) \
{ \
HOST(g2h(addr), *(TYPEM *)(vd + H(reg_off))); \
}
@ -4247,9 +4251,9 @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
const int esize, const int msize,
sve_st1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
void *vd = &env->vfp.zregs[rd];
set_helper_retaddr(ra);
@ -4257,7 +4261,7 @@ static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, vd, i, addr, mmu_idx, ra);
tlb_fn(env, vd, i, addr, oi, ra);
}
i += esize, pg >>= esize;
addr += msize;
@ -4271,9 +4275,9 @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
const int esize, const int msize,
sve_st1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
void *d1 = &env->vfp.zregs[rd];
void *d2 = &env->vfp.zregs[(rd + 1) & 31];
@ -4282,8 +4286,8 @@ static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, d1, i, addr, mmu_idx, ra);
tlb_fn(env, d2, i, addr + msize, mmu_idx, ra);
tlb_fn(env, d1, i, addr, oi, ra);
tlb_fn(env, d2, i, addr + msize, oi, ra);
}
i += esize, pg >>= esize;
addr += 2 * msize;
@ -4297,9 +4301,9 @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
const int esize, const int msize,
sve_st1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
void *d1 = &env->vfp.zregs[rd];
void *d2 = &env->vfp.zregs[(rd + 1) & 31];
void *d3 = &env->vfp.zregs[(rd + 2) & 31];
@ -4309,9 +4313,9 @@ static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, d1, i, addr, mmu_idx, ra);
tlb_fn(env, d2, i, addr + msize, mmu_idx, ra);
tlb_fn(env, d3, i, addr + 2 * msize, mmu_idx, ra);
tlb_fn(env, d1, i, addr, oi, ra);
tlb_fn(env, d2, i, addr + msize, oi, ra);
tlb_fn(env, d3, i, addr + 2 * msize, oi, ra);
}
i += esize, pg >>= esize;
addr += 3 * msize;
@ -4325,9 +4329,9 @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
const int esize, const int msize,
sve_st1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const unsigned rd = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 5);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned rd = simd_data(desc);
void *d1 = &env->vfp.zregs[rd];
void *d2 = &env->vfp.zregs[(rd + 1) & 31];
void *d3 = &env->vfp.zregs[(rd + 2) & 31];
@ -4338,10 +4342,10 @@ static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3));
do {
if (pg & 1) {
tlb_fn(env, d1, i, addr, mmu_idx, ra);
tlb_fn(env, d2, i, addr + msize, mmu_idx, ra);
tlb_fn(env, d3, i, addr + 2 * msize, mmu_idx, ra);
tlb_fn(env, d4, i, addr + 3 * msize, mmu_idx, ra);
tlb_fn(env, d1, i, addr, oi, ra);
tlb_fn(env, d2, i, addr + msize, oi, ra);
tlb_fn(env, d3, i, addr + 2 * msize, oi, ra);
tlb_fn(env, d4, i, addr + 3 * msize, oi, ra);
}
i += esize, pg >>= esize;
addr += 4 * msize;
@ -4911,9 +4915,9 @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
target_ulong base, uint32_t desc, uintptr_t ra,
zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned scale = simd_data(desc);
ARMVectorReg scratch = { };
set_helper_retaddr(ra);
@ -4922,7 +4926,7 @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
do {
if (likely(pg & 1)) {
target_ulong off = off_fn(vm, i);
tlb_fn(env, &scratch, i, base + (off << scale), mmu_idx, ra);
tlb_fn(env, &scratch, i, base + (off << scale), oi, ra);
}
i += 4, pg >>= 4;
} while (i & 15);
@ -4937,9 +4941,9 @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
target_ulong base, uint32_t desc, uintptr_t ra,
zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
intptr_t i, oprsz = simd_oprsz(desc) / 8;
unsigned scale = simd_data(desc);
ARMVectorReg scratch = { };
set_helper_retaddr(ra);
@ -4947,7 +4951,7 @@ static void sve_ld1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
uint8_t pg = *(uint8_t *)(vg + H1(i));
if (likely(pg & 1)) {
target_ulong off = off_fn(vm, i * 8);
tlb_fn(env, &scratch, i * 8, base + (off << scale), mmu_idx, ra);
tlb_fn(env, &scratch, i * 8, base + (off << scale), oi, ra);
}
}
set_helper_retaddr(0);
@ -5053,7 +5057,7 @@ typedef bool sve_ld1_nf_fn(CPUARMState *env, void *vd, intptr_t reg_off,
#ifdef CONFIG_SOFTMMU
#define DO_LD_NF(NAME, H, TYPEE, TYPEM, HOST) \
static bool sve_ld##NAME##_nf(CPUARMState *env, void *vd, intptr_t reg_off, \
target_ulong addr, int mmu_idx) \
target_ulong addr, int mmu_idx) \
{ \
target_ulong next_page = -(addr | TARGET_PAGE_MASK); \
if (likely(next_page - addr >= sizeof(TYPEM))) { \
@ -5112,9 +5116,10 @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn,
sve_ld1_nf_fn *nonfault_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int mmu_idx = get_mmuidx(oi);
const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
intptr_t reg_off, reg_max = simd_oprsz(desc);
unsigned scale = simd_data(desc);
target_ulong addr;
/* Skip to the first true predicate. */
@ -5124,7 +5129,7 @@ static inline void sve_ldff1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
set_helper_retaddr(ra);
addr = off_fn(vm, reg_off);
addr = base + (addr << scale);
tlb_fn(env, vd, reg_off, addr, mmu_idx, ra);
tlb_fn(env, vd, reg_off, addr, oi, ra);
/* The rest of the reads will be non-faulting. */
set_helper_retaddr(0);
@ -5153,9 +5158,10 @@ static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn,
sve_ld1_nf_fn *nonfault_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int mmu_idx = get_mmuidx(oi);
const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
intptr_t reg_off, reg_max = simd_oprsz(desc);
unsigned scale = simd_data(desc);
target_ulong addr;
/* Skip to the first true predicate. */
@ -5165,7 +5171,7 @@ static inline void sve_ldff1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
set_helper_retaddr(ra);
addr = off_fn(vm, reg_off);
addr = base + (addr << scale);
tlb_fn(env, vd, reg_off, addr, mmu_idx, ra);
tlb_fn(env, vd, reg_off, addr, oi, ra);
/* The rest of the reads will be non-faulting. */
set_helper_retaddr(0);
@ -5277,9 +5283,9 @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
target_ulong base, uint32_t desc, uintptr_t ra,
zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
intptr_t i, oprsz = simd_oprsz(desc);
unsigned scale = simd_data(desc);
set_helper_retaddr(ra);
for (i = 0; i < oprsz; ) {
@ -5287,7 +5293,7 @@ static void sve_st1_zs(CPUARMState *env, void *vd, void *vg, void *vm,
do {
if (likely(pg & 1)) {
target_ulong off = off_fn(vm, i);
tlb_fn(env, vd, i, base + (off << scale), mmu_idx, ra);
tlb_fn(env, vd, i, base + (off << scale), oi, ra);
}
i += 4, pg >>= 4;
} while (i & 15);
@ -5299,16 +5305,16 @@ static void sve_st1_zd(CPUARMState *env, void *vd, void *vg, void *vm,
target_ulong base, uint32_t desc, uintptr_t ra,
zreg_off_fn *off_fn, sve_ld1_tlb_fn *tlb_fn)
{
const int mmu_idx = cpu_mmu_index(env, false);
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int scale = extract32(desc, SIMD_DATA_SHIFT + MEMOPIDX_SHIFT, 2);
intptr_t i, oprsz = simd_oprsz(desc) / 8;
unsigned scale = simd_data(desc);
set_helper_retaddr(ra);
for (i = 0; i < oprsz; i++) {
uint8_t pg = *(uint8_t *)(vg + H1(i));
if (likely(pg & 1)) {
target_ulong off = off_fn(vm, i * 8);
tlb_fn(env, vd, i * 8, base + (off << scale), mmu_idx, ra);
tlb_fn(env, vd, i * 8, base + (off << scale), oi, ra);
}
}
set_helper_retaddr(0);

67
qemu/target/arm/translate-sve.c
View file

@ -4765,26 +4765,35 @@ static const uint8_t dtype_esz[16] = {
3, 2, 1, 3
};
static TCGMemOpIdx sve_memopidx(DisasContext *s, int dtype)
{
return make_memop_idx(s->be_data | dtype_mop[dtype], get_mem_index(s));
}
static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
gen_helper_gvec_mem *fn)
int dtype, gen_helper_gvec_mem *fn)
{
TCGContext *tcg_ctx = s->uc->tcg_ctx;
unsigned vsz = vec_full_reg_size(s);
TCGv_ptr t_pg;
TCGv_i32 desc;
TCGv_i32 t_desc;
int desc;
/* For e.g. LD4, there are not enough arguments to pass all 4
* registers as pointers, so encode the regno into the data field.
* For consistency, do this even for LD1.
*/
desc = tcg_const_i32(tcg_ctx, simd_desc(vsz, vsz, zt));
desc = sve_memopidx(s, dtype);
desc |= zt << MEMOPIDX_SHIFT;
desc = simd_desc(vsz, vsz, desc);
t_desc = tcg_const_i32(tcg_ctx, desc);
t_pg = tcg_temp_new_ptr(tcg_ctx);
tcg_gen_addi_ptr(tcg_ctx, t_pg, tcg_ctx->cpu_env, pred_full_reg_offset(s, pg));
fn(tcg_ctx, tcg_ctx->cpu_env, t_pg, addr, desc);
fn(tcg_ctx, tcg_ctx->cpu_env, t_pg, addr, t_desc);
tcg_temp_free_ptr(tcg_ctx, t_pg);
tcg_temp_free_i32(tcg_ctx, desc);
tcg_temp_free_i32(tcg_ctx, t_desc);
}
static void do_ld_zpa(DisasContext *s, int zt, int pg,
@ -4847,7 +4856,7 @@ static void do_ld_zpa(DisasContext *s, int zt, int pg,
* accessible via the instruction encoding.
*/
assert(fn != NULL);
do_mem_zpa(s, zt, pg, addr, fn);
do_mem_zpa(s, zt, pg, addr, dtype, fn);
}
static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn)
@ -4932,7 +4941,8 @@ static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn)
TCGv_i64 addr = new_tmp_a64(s);
tcg_gen_shli_i64(tcg_ctx, addr, cpu_reg(s, a->rm), dtype_msz(a->dtype));
tcg_gen_add_i64(tcg_ctx, addr, addr, cpu_reg_sp(s, a->rn));
do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]);
do_mem_zpa(s, a->rd, a->pg, addr, a->dtype,
fns[s->be_data == MO_BE][a->dtype]);
}
return true;
}
@ -4991,7 +5001,8 @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
TCGv_i64 addr = new_tmp_a64(s);
tcg_gen_addi_i64(tcg_ctx, addr, cpu_reg_sp(s, a->rn), off);
do_mem_zpa(s, a->rd, a->pg, addr, fns[s->be_data == MO_BE][a->dtype]);
do_mem_zpa(s, a->rd, a->pg, addr, a->dtype,
fns[s->be_data == MO_BE][a->dtype]);
}
return true;
}
@ -5007,11 +5018,14 @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz)
};
unsigned vsz = vec_full_reg_size(s);
TCGv_ptr t_pg;
TCGv_i32 desc;
int poff;
TCGv_i32 t_desc;
int desc, poff;
/* Load the first quadword using the normal predicated load helpers. */
desc = tcg_const_i32(tcg_ctx, simd_desc(16, 16, zt));
desc = sve_memopidx(s, msz_dtype(msz));
desc |= zt << MEMOPIDX_SHIFT;
desc = simd_desc(16, 16, desc);
t_desc = tcg_const_i32(tcg_ctx, desc);
poff = pred_full_reg_offset(s, pg);
if (vsz > 16) {
@ -5035,10 +5049,10 @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz)
t_pg = tcg_temp_new_ptr(tcg_ctx);
tcg_gen_addi_ptr(tcg_ctx, t_pg, tcg_ctx->cpu_env, poff);
fns[s->be_data == MO_BE][msz](tcg_ctx, tcg_ctx->cpu_env, t_pg, addr, desc);
fns[s->be_data == MO_BE][msz](tcg_ctx, tcg_ctx->cpu_env, t_pg, addr, t_desc);
tcg_temp_free_ptr(tcg_ctx, t_pg);
tcg_temp_free_i32(tcg_ctx, desc);
tcg_temp_free_i32(tcg_ctx, t_desc);
/* Replicate that first quadword. */
if (vsz > 16) {
@ -5193,7 +5207,7 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
fn = fn_multiple[be][nreg - 1][msz];
}
assert(fn != NULL);
do_mem_zpa(s, zt, pg, addr, fn);
do_mem_zpa(s, zt, pg, addr, msz_dtype(msz), fn);
}
static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a, uint32_t insn)
@ -5233,25 +5247,32 @@ static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a, uint32_t insn)
*** SVE gather loads / scatter stores
*/
static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, int scale,
TCGv_i64 scalar, gen_helper_gvec_mem_scatter *fn)
static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm,
int scale, TCGv_i64 scalar, int msz,
gen_helper_gvec_mem_scatter *fn)
{
TCGContext *tcg_ctx = s->uc->tcg_ctx;
unsigned vsz = vec_full_reg_size(s);
TCGv_i32 desc = tcg_const_i32(tcg_ctx, simd_desc(vsz, vsz, scale));
TCGv_ptr t_zm = tcg_temp_new_ptr(tcg_ctx);
TCGv_ptr t_pg = tcg_temp_new_ptr(tcg_ctx);
TCGv_ptr t_zt = tcg_temp_new_ptr(tcg_ctx);
TCGv_i32 t_desc;
int desc;
desc = sve_memopidx(s, msz_dtype(msz));
desc |= scale << MEMOPIDX_SHIFT;
desc = simd_desc(vsz, vsz, desc);
t_desc = tcg_const_i32(tcg_ctx, desc);
tcg_gen_addi_ptr(tcg_ctx, t_pg, tcg_ctx->cpu_env, pred_full_reg_offset(s, pg));
tcg_gen_addi_ptr(tcg_ctx, t_zm, tcg_ctx->cpu_env, vec_full_reg_offset(s, zm));
tcg_gen_addi_ptr(tcg_ctx, t_zt, tcg_ctx->cpu_env, vec_full_reg_offset(s, zt));
fn(tcg_ctx, tcg_ctx->cpu_env, t_zt, t_pg, t_zm, scalar, desc);
fn(tcg_ctx, tcg_ctx->cpu_env, t_zt, t_pg, t_zm, scalar, t_desc);
tcg_temp_free_ptr(tcg_ctx, t_zt);
tcg_temp_free_ptr(tcg_ctx, t_zm);
tcg_temp_free_ptr(tcg_ctx, t_pg);
tcg_temp_free_i32(tcg_ctx, desc);
tcg_temp_free_i32(tcg_ctx, t_desc);
}
/* Indexed by [be][ff][xs][u][msz]. */
@ -5440,7 +5461,7 @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn)
assert(fn != NULL);
do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz,
cpu_reg_sp(s, a->rn), fn);
cpu_reg_sp(s, a->rn), a->msz, fn);
return true;
}
@ -5473,7 +5494,7 @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn)
* by loading the immediate into the scalar parameter.
*/
imm = tcg_const_i64(tcg_ctx, a->imm << a->msz);
do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn);
do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, a->msz, fn);
tcg_temp_free_i64(tcg_ctx, imm);
return true;
}
@ -5549,7 +5570,7 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn)
g_assert_not_reached();
}
do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz,
cpu_reg_sp(s, a->rn), fn);
cpu_reg_sp(s, a->rn), a->msz, fn);
return true;
}
@ -5582,7 +5603,7 @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn)
* by loading the immediate into the scalar parameter.
*/
imm = tcg_const_i64(tcg_ctx, a->imm << a->msz);
do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn);
do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, a->msz, fn);
tcg_temp_free_i64(tcg_ctx, imm);
return true;
}