[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v4 06/18] target/arm: Use cpu_*_data_ra for sve_ldst_tlb_fn
|
From: |
Richard Henderson |
|
Subject: |
[PATCH v4 06/18] target/arm: Use cpu_*_data_ra for sve_ldst_tlb_fn |
|
Date: |
Thu, 30 Apr 2020 09:28:01 -0700 |
Use the "normal" memory access functions, rather than the
softmmu internal helper functions directly.
Since fb901c905dc3, cpu_mem_index is now a simple extract
from env->hflags and not a large computation. Which means
that it's now more work to pass around this value than it
is to recompute it.
This only adjusts the primitives, and does not clean up
all of the uses within sve_helper.c.
Reviewed-by: Peter Maydell <address@hidden>
Signed-off-by: Richard Henderson <address@hidden>
---
target/arm/sve_helper.c | 221 ++++++++++++++++------------------------
1 file changed, 86 insertions(+), 135 deletions(-)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index fdfa652094..655bc9476f 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -3991,9 +3991,8 @@ typedef intptr_t sve_ld1_host_fn(void *vd, void *vg, void
*host,
* Load one element into @vd + @reg_off from (@env, @vaddr, @ra).
* 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, TCGMemOpIdx oi, uintptr_t ra);
-typedef sve_ld1_tlb_fn sve_st1_tlb_fn;
+typedef void sve_ldst1_tlb_fn(CPUARMState *env, void *vd, intptr_t reg_off,
+ target_ulong vaddr, uintptr_t retaddr);
/*
* Generate the above primitives.
@@ -4016,27 +4015,23 @@ static intptr_t sve_##NAME##_host(void *vd, void *vg,
void *host, \
return mem_off; \
}
-#ifdef CONFIG_SOFTMMU
-#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \
+#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, TLB) \
static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \
- target_ulong addr, TCGMemOpIdx oi, uintptr_t ra)
\
+ target_ulong addr, uintptr_t ra) \
{ \
- TYPEM val = TLB(env, addr, oi, ra); \
- *(TYPEE *)(vd + H(reg_off)) = val; \
+ *(TYPEE *)(vd + H(reg_off)) = (TYPEM)TLB(env, addr, ra); \
}
-#else
-#define DO_LD_TLB(NAME, H, TYPEE, TYPEM, HOST, MOEND, TLB) \
+
+#define DO_ST_TLB(NAME, H, TYPEE, TYPEM, TLB) \
static void sve_##NAME##_tlb(CPUARMState *env, void *vd, intptr_t reg_off, \
- target_ulong addr, TCGMemOpIdx oi, uintptr_t ra)
\
+ target_ulong addr, uintptr_t ra) \
{ \
- TYPEM val = HOST(g2h(addr)); \
- *(TYPEE *)(vd + H(reg_off)) = val; \
+ TLB(env, addr, (TYPEM)*(TYPEE *)(vd + H(reg_off)), ra); \
}
-#endif
#define DO_LD_PRIM_1(NAME, H, TE, TM) \
DO_LD_HOST(NAME, H, TE, TM, ldub_p) \
- DO_LD_TLB(NAME, H, TE, TM, ldub_p, 0, helper_ret_ldub_mmu)
+ DO_LD_TLB(NAME, H, TE, TM, cpu_ldub_data_ra)
DO_LD_PRIM_1(ld1bb, H1, uint8_t, uint8_t)
DO_LD_PRIM_1(ld1bhu, H1_2, uint16_t, uint8_t)
@@ -4046,39 +4041,51 @@ DO_LD_PRIM_1(ld1bss, H1_4, uint32_t, int8_t)
DO_LD_PRIM_1(ld1bdu, , uint64_t, uint8_t)
DO_LD_PRIM_1(ld1bds, , uint64_t, int8_t)
-#define DO_LD_PRIM_2(NAME, end, MOEND, H, TE, TM, PH, PT) \
- DO_LD_HOST(NAME##_##end, H, TE, TM, PH##_##end##_p) \
- DO_LD_TLB(NAME##_##end, H, TE, TM, PH##_##end##_p, \
- MOEND, helper_##end##_##PT##_mmu)
+#define DO_ST_PRIM_1(NAME, H, TE, TM) \
+ DO_ST_TLB(st1##NAME, H, TE, TM, cpu_stb_data_ra)
-DO_LD_PRIM_2(ld1hh, le, MO_LE, H1_2, uint16_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hsu, le, MO_LE, H1_4, uint32_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hss, le, MO_LE, H1_4, uint32_t, int16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hdu, le, MO_LE, , uint64_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hds, le, MO_LE, , uint64_t, int16_t, lduw, lduw)
+DO_ST_PRIM_1(bb, H1, uint8_t, uint8_t)
+DO_ST_PRIM_1(bh, H1_2, uint16_t, uint8_t)
+DO_ST_PRIM_1(bs, H1_4, uint32_t, uint8_t)
+DO_ST_PRIM_1(bd, , uint64_t, uint8_t)
-DO_LD_PRIM_2(ld1ss, le, MO_LE, H1_4, uint32_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sdu, le, MO_LE, , uint64_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sds, le, MO_LE, , uint64_t, int32_t, ldl, ldul)
+#define DO_LD_PRIM_2(NAME, H, TE, TM, LD) \
+ DO_LD_HOST(ld1##NAME##_be, H, TE, TM, LD##_be_p) \
+ DO_LD_HOST(ld1##NAME##_le, H, TE, TM, LD##_le_p) \
+ DO_LD_TLB(ld1##NAME##_be, H, TE, TM, cpu_##LD##_be_data_ra) \
+ DO_LD_TLB(ld1##NAME##_le, H, TE, TM, cpu_##LD##_le_data_ra)
-DO_LD_PRIM_2(ld1dd, le, MO_LE, , uint64_t, uint64_t, ldq, ldq)
+#define DO_ST_PRIM_2(NAME, H, TE, TM, ST) \
+ DO_ST_TLB(st1##NAME##_be, H, TE, TM, cpu_##ST##_be_data_ra) \
+ DO_ST_TLB(st1##NAME##_le, H, TE, TM, cpu_##ST##_le_data_ra)
-DO_LD_PRIM_2(ld1hh, be, MO_BE, H1_2, uint16_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hsu, be, MO_BE, H1_4, uint32_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hss, be, MO_BE, H1_4, uint32_t, int16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hdu, be, MO_BE, , uint64_t, uint16_t, lduw, lduw)
-DO_LD_PRIM_2(ld1hds, be, MO_BE, , uint64_t, int16_t, lduw, lduw)
+DO_LD_PRIM_2(hh, H1_2, uint16_t, uint16_t, lduw)
+DO_LD_PRIM_2(hsu, H1_4, uint32_t, uint16_t, lduw)
+DO_LD_PRIM_2(hss, H1_4, uint32_t, int16_t, lduw)
+DO_LD_PRIM_2(hdu, , uint64_t, uint16_t, lduw)
+DO_LD_PRIM_2(hds, , uint64_t, int16_t, lduw)
-DO_LD_PRIM_2(ld1ss, be, MO_BE, H1_4, uint32_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sdu, be, MO_BE, , uint64_t, uint32_t, ldl, ldul)
-DO_LD_PRIM_2(ld1sds, be, MO_BE, , uint64_t, int32_t, ldl, ldul)
+DO_ST_PRIM_2(hh, H1_2, uint16_t, uint16_t, stw)
+DO_ST_PRIM_2(hs, H1_4, uint32_t, uint16_t, stw)
+DO_ST_PRIM_2(hd, , uint64_t, uint16_t, stw)
-DO_LD_PRIM_2(ld1dd, be, MO_BE, , uint64_t, uint64_t, ldq, ldq)
+DO_LD_PRIM_2(ss, H1_4, uint32_t, uint32_t, ldl)
+DO_LD_PRIM_2(sdu, , uint64_t, uint32_t, ldl)
+DO_LD_PRIM_2(sds, , uint64_t, int32_t, ldl)
+
+DO_ST_PRIM_2(ss, H1_4, uint32_t, uint32_t, stl)
+DO_ST_PRIM_2(sd, , uint64_t, uint32_t, stl)
+
+DO_LD_PRIM_2(dd, , uint64_t, uint64_t, ldq)
+DO_ST_PRIM_2(dd, , uint64_t, uint64_t, stq)
#undef DO_LD_TLB
+#undef DO_ST_TLB
#undef DO_LD_HOST
#undef DO_LD_PRIM_1
+#undef DO_ST_PRIM_1
#undef DO_LD_PRIM_2
+#undef DO_ST_PRIM_2
/*
* Skip through a sequence of inactive elements in the guarding predicate @vg,
@@ -4152,7 +4159,7 @@ static void sve_ld1_r(CPUARMState *env, void *vg, const
target_ulong addr,
uint32_t desc, const uintptr_t retaddr,
const int esz, const int msz,
sve_ld1_host_fn *host_fn,
- sve_ld1_tlb_fn *tlb_fn)
+ sve_ldst1_tlb_fn *tlb_fn)
{
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int mmu_idx = get_mmuidx(oi);
@@ -4234,7 +4241,7 @@ 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, oi, retaddr);
+ tlb_fn(env, &scratch, reg_off, addr + mem_off, retaddr);
reg_off += 1 << esz;
}
#endif
@@ -4293,9 +4300,8 @@ DO_LD1_2(ld1dd, 3, 3)
*/
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)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
ARMVectorReg scratch[2] = { };
@@ -4305,8 +4311,8 @@ 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, oi, ra);
- tlb_fn(env, &scratch[1], i, addr + size, oi, ra);
+ tlb_fn(env, &scratch[0], i, addr, ra);
+ tlb_fn(env, &scratch[1], i, addr + size, ra);
}
i += size, pg >>= size;
addr += 2 * size;
@@ -4321,9 +4327,8 @@ static void sve_ld2_r(CPUARMState *env, void *vg,
target_ulong addr,
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)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
ARMVectorReg scratch[3] = { };
@@ -4333,9 +4338,9 @@ 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, 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[0], i, addr, ra);
+ tlb_fn(env, &scratch[1], i, addr + size, ra);
+ tlb_fn(env, &scratch[2], i, addr + 2 * size, ra);
}
i += size, pg >>= size;
addr += 3 * size;
@@ -4351,9 +4356,8 @@ static void sve_ld3_r(CPUARMState *env, void *vg,
target_ulong addr,
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)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
ARMVectorReg scratch[4] = { };
@@ -4363,10 +4367,10 @@ 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, 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);
+ tlb_fn(env, &scratch[0], i, addr, ra);
+ tlb_fn(env, &scratch[1], i, addr + size, ra);
+ tlb_fn(env, &scratch[2], i, addr + 2 * size, ra);
+ tlb_fn(env, &scratch[3], i, addr + 3 * size, ra);
}
i += size, pg >>= size;
addr += 4 * size;
@@ -4459,7 +4463,7 @@ static void sve_ldff1_r(CPUARMState *env, void *vg, const
target_ulong addr,
uint32_t desc, const uintptr_t retaddr,
const int esz, const int msz,
sve_ld1_host_fn *host_fn,
- sve_ld1_tlb_fn *tlb_fn)
+ sve_ldst1_tlb_fn *tlb_fn)
{
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
const int mmu_idx = get_mmuidx(oi);
@@ -4519,7 +4523,7 @@ 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, oi, retaddr);
+ tlb_fn(env, vd, reg_off, addr + mem_off, retaddr);
/* After any fault, zero any leading predicated false elts. */
swap_memzero(vd, reg_off);
@@ -4671,60 +4675,14 @@ DO_LDFF1_LDNF1_2(dd, 3, 3)
#undef DO_LDFF1_LDNF1_1
#undef DO_LDFF1_LDNF1_2
-/*
- * Store contiguous data, protected by a governing predicate.
- */
-
-#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, TCGMemOpIdx oi, uintptr_t ra) \
-{ \
- 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, TCGMemOpIdx oi, uintptr_t ra) \
-{ \
- HOST(g2h(addr), *(TYPEM *)(vd + H(reg_off))); \
-}
-#endif
-
-DO_ST_TLB(st1bb, H1, uint8_t, stb_p, 0, helper_ret_stb_mmu)
-DO_ST_TLB(st1bh, H1_2, uint16_t, stb_p, 0, helper_ret_stb_mmu)
-DO_ST_TLB(st1bs, H1_4, uint32_t, stb_p, 0, helper_ret_stb_mmu)
-DO_ST_TLB(st1bd, , uint64_t, stb_p, 0, helper_ret_stb_mmu)
-
-DO_ST_TLB(st1hh_le, H1_2, uint16_t, stw_le_p, MO_LE, helper_le_stw_mmu)
-DO_ST_TLB(st1hs_le, H1_4, uint32_t, stw_le_p, MO_LE, helper_le_stw_mmu)
-DO_ST_TLB(st1hd_le, , uint64_t, stw_le_p, MO_LE, helper_le_stw_mmu)
-
-DO_ST_TLB(st1ss_le, H1_4, uint32_t, stl_le_p, MO_LE, helper_le_stl_mmu)
-DO_ST_TLB(st1sd_le, , uint64_t, stl_le_p, MO_LE, helper_le_stl_mmu)
-
-DO_ST_TLB(st1dd_le, , uint64_t, stq_le_p, MO_LE, helper_le_stq_mmu)
-
-DO_ST_TLB(st1hh_be, H1_2, uint16_t, stw_be_p, MO_BE, helper_be_stw_mmu)
-DO_ST_TLB(st1hs_be, H1_4, uint32_t, stw_be_p, MO_BE, helper_be_stw_mmu)
-DO_ST_TLB(st1hd_be, , uint64_t, stw_be_p, MO_BE, helper_be_stw_mmu)
-
-DO_ST_TLB(st1ss_be, H1_4, uint32_t, stl_be_p, MO_BE, helper_be_stl_mmu)
-DO_ST_TLB(st1sd_be, , uint64_t, stl_be_p, MO_BE, helper_be_stl_mmu)
-
-DO_ST_TLB(st1dd_be, , uint64_t, stq_be_p, MO_BE, helper_be_stq_mmu)
-
-#undef DO_ST_TLB
-
/*
* Common helpers for all contiguous 1,2,3,4-register predicated stores.
*/
static void sve_st1_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, const uintptr_t ra,
const int esize, const int msize,
- sve_st1_tlb_fn *tlb_fn)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
void *vd = &env->vfp.zregs[rd];
@@ -4734,7 +4692,7 @@ 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, oi, ra);
+ tlb_fn(env, vd, i, addr, ra);
}
i += esize, pg >>= esize;
addr += msize;
@@ -4746,9 +4704,8 @@ static void sve_st1_r(CPUARMState *env, void *vg,
target_ulong addr,
static void sve_st2_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, const uintptr_t ra,
const int esize, const int msize,
- sve_st1_tlb_fn *tlb_fn)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
void *d1 = &env->vfp.zregs[rd];
@@ -4759,8 +4716,8 @@ 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, oi, ra);
- tlb_fn(env, d2, i, addr + msize, oi, ra);
+ tlb_fn(env, d1, i, addr, ra);
+ tlb_fn(env, d2, i, addr + msize, ra);
}
i += esize, pg >>= esize;
addr += 2 * msize;
@@ -4772,9 +4729,8 @@ static void sve_st2_r(CPUARMState *env, void *vg,
target_ulong addr,
static void sve_st3_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, const uintptr_t ra,
const int esize, const int msize,
- sve_st1_tlb_fn *tlb_fn)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
void *d1 = &env->vfp.zregs[rd];
@@ -4786,9 +4742,9 @@ 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, oi, ra);
- tlb_fn(env, d2, i, addr + msize, oi, ra);
- tlb_fn(env, d3, i, addr + 2 * msize, oi, ra);
+ tlb_fn(env, d1, i, addr, ra);
+ tlb_fn(env, d2, i, addr + msize, ra);
+ tlb_fn(env, d3, i, addr + 2 * msize, ra);
}
i += esize, pg >>= esize;
addr += 3 * msize;
@@ -4800,9 +4756,8 @@ static void sve_st3_r(CPUARMState *env, void *vg,
target_ulong addr,
static void sve_st4_r(CPUARMState *env, void *vg, target_ulong addr,
uint32_t desc, const uintptr_t ra,
const int esize, const int msize,
- sve_st1_tlb_fn *tlb_fn)
+ sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
void *d1 = &env->vfp.zregs[rd];
@@ -4815,10 +4770,10 @@ 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, 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);
+ tlb_fn(env, d1, i, addr, ra);
+ tlb_fn(env, d2, i, addr + msize, ra);
+ tlb_fn(env, d3, i, addr + 2 * msize, ra);
+ tlb_fn(env, d4, i, addr + 3 * msize, ra);
}
i += esize, pg >>= esize;
addr += 4 * msize;
@@ -4914,9 +4869,8 @@ static target_ulong off_zd_d(void *reg, intptr_t reg_ofs)
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)
+ zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
ARMVectorReg scratch = { };
@@ -4927,7 +4881,7 @@ 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), oi, ra);
+ tlb_fn(env, &scratch, i, base + (off << scale), ra);
}
i += 4, pg >>= 4;
} while (i & 15);
@@ -4940,9 +4894,8 @@ static void sve_ld1_zs(CPUARMState *env, void *vd, void
*vg, void *vm,
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)
+ zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
{
- 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;
ARMVectorReg scratch = { };
@@ -4952,7 +4905,7 @@ 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), oi, ra);
+ tlb_fn(env, &scratch, i * 8, base + (off << scale), ra);
}
}
clear_helper_retaddr();
@@ -5114,7 +5067,7 @@ DO_LD_NF(dd_be, , uint64_t, uint64_t, ldq_be_p)
*/
static inline void sve_ldff1_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,
+ zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn,
sve_ld1_nf_fn *nonfault_fn)
{
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
@@ -5130,7 +5083,7 @@ 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, oi, ra);
+ tlb_fn(env, vd, reg_off, addr, ra);
/* The rest of the reads will be non-faulting. */
clear_helper_retaddr();
@@ -5156,7 +5109,7 @@ static inline void sve_ldff1_zs(CPUARMState *env, void
*vd, void *vg, void *vm,
static inline void sve_ldff1_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,
+ zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn,
sve_ld1_nf_fn *nonfault_fn)
{
const TCGMemOpIdx oi = extract32(desc, SIMD_DATA_SHIFT, MEMOPIDX_SHIFT);
@@ -5172,7 +5125,7 @@ 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, oi, ra);
+ tlb_fn(env, vd, reg_off, addr, ra);
/* The rest of the reads will be non-faulting. */
clear_helper_retaddr();
@@ -5282,9 +5235,8 @@ DO_LDFF1_ZPZ_D(dd_be, zd)
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)
+ zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
{
- 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);
@@ -5294,7 +5246,7 @@ 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), oi, ra);
+ tlb_fn(env, vd, i, base + (off << scale), ra);
}
i += 4, pg >>= 4;
} while (i & 15);
@@ -5304,9 +5256,8 @@ static void sve_st1_zs(CPUARMState *env, void *vd, void
*vg, void *vm,
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)
+ zreg_off_fn *off_fn, sve_ldst1_tlb_fn *tlb_fn)
{
- 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;
@@ -5315,7 +5266,7 @@ static void sve_st1_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, vd, i * 8, base + (off << scale), oi, ra);
+ tlb_fn(env, vd, i * 8, base + (off << scale), ra);
}
}
clear_helper_retaddr();
--
2.20.1
- [PATCH v4 00/18] target/arm: sve load/store improvements, Richard Henderson, 2020/04/30
- [PATCH v4 02/18] exec: Fix cpu_watchpoint_address_matches address length, Richard Henderson, 2020/04/30
- [PATCH v4 01/18] exec: Add block comments for watchpoint routines, Richard Henderson, 2020/04/30
- [PATCH v4 03/18] accel/tcg: Add block comment for probe_access, Richard Henderson, 2020/04/30
- [PATCH v4 04/18] accel/tcg: Add probe_access_flags, Richard Henderson, 2020/04/30
- [PATCH v4 06/18] target/arm: Use cpu_*_data_ra for sve_ldst_tlb_fn,
Richard Henderson <=
- [PATCH v4 05/18] accel/tcg: Add endian-specific cpu_{ld, st}* operations, Richard Henderson, 2020/04/30
- [PATCH v4 08/18] target/arm: Add sve infrastructure for page lookup, Richard Henderson, 2020/04/30
- [PATCH v4 07/18] target/arm: Drop manual handling of set/clear_helper_retaddr, Richard Henderson, 2020/04/30
- [PATCH v4 09/18] target/arm: Adjust interface of sve_ld1_host_fn, Richard Henderson, 2020/04/30
- [PATCH v4 10/18] target/arm: Use SVEContLdSt in sve_ld1_r, Richard Henderson, 2020/04/30
- [PATCH v4 11/18] target/arm: Handle watchpoints in sve_ld1_r, Richard Henderson, 2020/04/30
- [PATCH v4 16/18] target/arm: Reuse sve_probe_page for scatter stores, Richard Henderson, 2020/04/30
- [PATCH v4 14/18] target/arm: Use SVEContLdSt for contiguous stores, Richard Henderson, 2020/04/30
- [PATCH v4 13/18] target/arm: Update contiguous first-fault and no-fault loads, Richard Henderson, 2020/04/30
- [PATCH v4 18/18] target/arm: Remove sve_memopidx, Richard Henderson, 2020/04/30