Merge tag 'pull-riscv-to-apply-20240322' of https://github.com/alistair23/qemu into staging
RISC-V PR for 9.0
* Do not enable all named features by default
* A range of Vector fixes
* Update APLIC IDC after claiming iforce register
* Remove the dependency of Zvfbfmin to Zfbfmin
* Fix mode in riscv_tlb_fill
* Fix timebase-frequency when using KVM acceleration
# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEaukCtqfKh31tZZKWr3yVEwxTgBMFAmX9RscACgkQr3yVEwxT
# gBNaRg/+KUSF6AuY25pS7GawbufBbwWWaWN9G/inPVoCnLbeYrkB3uZw3nBd3iV8
# KiD9Azabl6TLBFC/f7eP9alNDIoSrq5EliayrlFEZIncYvig2Y3CkWUeK6oJqDp2
# Dz1Vah4IB96bU2/M9icyHkh3tnSnbhq0JrbgoAYwWutZy4ERYugTHulOGPxBj64I
# JIfb8wYqaak3Uak+g0mz/YBNHegLEDxIzIRhO4oWPE0MWKSO3t79G9qVAYi7pkFB
# ZQQasZy0h9ZpwKvVajiO8yjwh7COI0IPU+4vZNkNXue0SXQvAvcKA4DdaTwmMTio
# 9UM9HRB371F5LtJLdvAT2TR8FfW26Y7xBe458jheFOnPHKwxEFtUFCQ39UJB3bDN
# k7CYvU3GIqUJHD7PtYZfzTdYkdnIDpr9yKTPP2/nCN53FzXuJs/XTyySphJ6mZ2m
# dsr1bnJn/ncZP7W2vdWGfgQEKt2CHfE5qWM++RwhmQc+IKn2ImMA0hBsg6Gl2imB
# 9WANt3UX784VDmcwcFVgDgr6nftDs7gjVCtHAaRV7Oq2f9hcr17pRxg66mSXs0BX
# fMhcqHBe01LpZQRbaGQ0ImTQksEFyH2KTvt0kjF4SfpVzMfVOi/Zmy9goYNq4iYd
# tfucBbXVhpzbJ/9HeOzKAJQ2Wt0NyLiyDIOkWXj61WquS/0Mr9g=
# =8vP1
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 22 Mar 2024 08:52:23 GMT
# gpg: using RSA key 6AE902B6A7CA877D6D659296AF7C95130C538013
# gpg: Good signature from "Alistair Francis <alistair@alistair23.me>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 6AE9 02B6 A7CA 877D 6D65 9296 AF7C 9513 0C53 8013
* tag 'pull-riscv-to-apply-20240322' of https://github.com/alistair23/qemu:
target/riscv/kvm: fix timebase-frequency when using KVM acceleration
target/riscv: Fix mode in riscv_tlb_fill
target/riscv: rvv: Remove the dependency of Zvfbfmin to Zfbfmin
hw/intc: Update APLIC IDC after claiming iforce register
target/riscv/vector_helper.c: optimize loops in ldst helpers
target/riscv: enable 'vstart_eq_zero' in the end of insns
trans_rvv.c.inc: remove redundant mark_vs_dirty() calls
target/riscv: remove 'over' brconds from vector trans
target/riscv/vector_helpers: do early exit when vstart >= vl
target/riscv: always clear vstart for ldst_whole insns
target/riscv: always clear vstart in whole vec move insns
target/riscv/vector_helper.c: fix 'vmvr_v' memcpy endianess
trans_rvv.c.inc: set vstart = 0 in int scalar move insns
target/riscv/vector_helper.c: set vstart = 0 in GEN_VEXT_VSLIDEUP_VX()
target/riscv: do not enable all named features by default
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
index 6a7fbfa..fc5df0d 100644
--- a/hw/intc/riscv_aplic.c
+++ b/hw/intc/riscv_aplic.c
@@ -488,6 +488,7 @@
if (!topi) {
aplic->iforce[idc] = 0;
+ riscv_aplic_idc_update(aplic, idc);
return 0;
}
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index 72a55b8..d171e74 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -711,6 +711,8 @@
qemu_fdt_add_subnode(ms->fdt, "/cpus");
qemu_fdt_setprop_cell(ms->fdt, "/cpus", "timebase-frequency",
+ kvm_enabled() ?
+ kvm_riscv_get_timebase_frequency(first_cpu) :
RISCV_ACLINT_DEFAULT_TIMEBASE_FREQ);
qemu_fdt_setprop_cell(ms->fdt, "/cpus", "#size-cells", 0x0);
qemu_fdt_setprop_cell(ms->fdt, "/cpus", "#address-cells", 0x1);
diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c
index c160b92..36e3e5f 100644
--- a/target/riscv/cpu.c
+++ b/target/riscv/cpu.c
@@ -102,10 +102,10 @@
ISA_EXT_DATA_ENTRY(zicbom, PRIV_VERSION_1_12_0, ext_zicbom),
ISA_EXT_DATA_ENTRY(zicbop, PRIV_VERSION_1_12_0, ext_zicbop),
ISA_EXT_DATA_ENTRY(zicboz, PRIV_VERSION_1_12_0, ext_zicboz),
- ISA_EXT_DATA_ENTRY(ziccamoa, PRIV_VERSION_1_11_0, ext_always_enabled),
- ISA_EXT_DATA_ENTRY(ziccif, PRIV_VERSION_1_11_0, ext_always_enabled),
- ISA_EXT_DATA_ENTRY(zicclsm, PRIV_VERSION_1_11_0, ext_always_enabled),
- ISA_EXT_DATA_ENTRY(ziccrse, PRIV_VERSION_1_11_0, ext_always_enabled),
+ ISA_EXT_DATA_ENTRY(ziccamoa, PRIV_VERSION_1_11_0, has_priv_1_11),
+ ISA_EXT_DATA_ENTRY(ziccif, PRIV_VERSION_1_11_0, has_priv_1_11),
+ ISA_EXT_DATA_ENTRY(zicclsm, PRIV_VERSION_1_11_0, has_priv_1_11),
+ ISA_EXT_DATA_ENTRY(ziccrse, PRIV_VERSION_1_11_0, has_priv_1_11),
ISA_EXT_DATA_ENTRY(zicond, PRIV_VERSION_1_12_0, ext_zicond),
ISA_EXT_DATA_ENTRY(zicntr, PRIV_VERSION_1_12_0, ext_zicntr),
ISA_EXT_DATA_ENTRY(zicsr, PRIV_VERSION_1_10_0, ext_zicsr),
@@ -114,7 +114,7 @@
ISA_EXT_DATA_ENTRY(zihintpause, PRIV_VERSION_1_10_0, ext_zihintpause),
ISA_EXT_DATA_ENTRY(zihpm, PRIV_VERSION_1_12_0, ext_zihpm),
ISA_EXT_DATA_ENTRY(zmmul, PRIV_VERSION_1_12_0, ext_zmmul),
- ISA_EXT_DATA_ENTRY(za64rs, PRIV_VERSION_1_12_0, ext_always_enabled),
+ ISA_EXT_DATA_ENTRY(za64rs, PRIV_VERSION_1_12_0, has_priv_1_11),
ISA_EXT_DATA_ENTRY(zaamo, PRIV_VERSION_1_12_0, ext_zaamo),
ISA_EXT_DATA_ENTRY(zacas, PRIV_VERSION_1_12_0, ext_zacas),
ISA_EXT_DATA_ENTRY(zalrsc, PRIV_VERSION_1_12_0, ext_zalrsc),
@@ -179,12 +179,12 @@
ISA_EXT_DATA_ENTRY(smepmp, PRIV_VERSION_1_12_0, ext_smepmp),
ISA_EXT_DATA_ENTRY(smstateen, PRIV_VERSION_1_12_0, ext_smstateen),
ISA_EXT_DATA_ENTRY(ssaia, PRIV_VERSION_1_12_0, ext_ssaia),
- ISA_EXT_DATA_ENTRY(ssccptr, PRIV_VERSION_1_11_0, ext_always_enabled),
+ ISA_EXT_DATA_ENTRY(ssccptr, PRIV_VERSION_1_11_0, has_priv_1_11),
ISA_EXT_DATA_ENTRY(sscofpmf, PRIV_VERSION_1_12_0, ext_sscofpmf),
- ISA_EXT_DATA_ENTRY(sscounterenw, PRIV_VERSION_1_12_0, ext_always_enabled),
+ ISA_EXT_DATA_ENTRY(sscounterenw, PRIV_VERSION_1_12_0, has_priv_1_12),
ISA_EXT_DATA_ENTRY(sstc, PRIV_VERSION_1_12_0, ext_sstc),
- ISA_EXT_DATA_ENTRY(sstvala, PRIV_VERSION_1_12_0, ext_always_enabled),
- ISA_EXT_DATA_ENTRY(sstvecd, PRIV_VERSION_1_12_0, ext_always_enabled),
+ ISA_EXT_DATA_ENTRY(sstvala, PRIV_VERSION_1_12_0, has_priv_1_12),
+ ISA_EXT_DATA_ENTRY(sstvecd, PRIV_VERSION_1_12_0, has_priv_1_12),
ISA_EXT_DATA_ENTRY(svade, PRIV_VERSION_1_11_0, ext_svade),
ISA_EXT_DATA_ENTRY(svadu, PRIV_VERSION_1_12_0, ext_svadu),
ISA_EXT_DATA_ENTRY(svinval, PRIV_VERSION_1_12_0, ext_svinval),
@@ -1575,11 +1575,6 @@
DEFINE_PROP_END_OF_LIST(),
};
-#define ALWAYS_ENABLED_FEATURE(_name) \
- {.name = _name, \
- .offset = CPU_CFG_OFFSET(ext_always_enabled), \
- .enabled = true}
-
/*
* 'Named features' is the name we give to extensions that we
* don't want to expose to users. They are either immutable
@@ -1590,23 +1585,6 @@
const RISCVCPUMultiExtConfig riscv_cpu_named_features[] = {
MULTI_EXT_CFG_BOOL("zic64b", ext_zic64b, true),
- /*
- * cache-related extensions that are always enabled
- * in TCG since QEMU RISC-V does not have a cache
- * model.
- */
- ALWAYS_ENABLED_FEATURE("za64rs"),
- ALWAYS_ENABLED_FEATURE("ziccif"),
- ALWAYS_ENABLED_FEATURE("ziccrse"),
- ALWAYS_ENABLED_FEATURE("ziccamoa"),
- ALWAYS_ENABLED_FEATURE("zicclsm"),
- ALWAYS_ENABLED_FEATURE("ssccptr"),
-
- /* Other named features that TCG always implements */
- ALWAYS_ENABLED_FEATURE("sstvecd"),
- ALWAYS_ENABLED_FEATURE("sstvala"),
- ALWAYS_ENABLED_FEATURE("sscounterenw"),
-
DEFINE_PROP_END_OF_LIST(),
};
diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h
index 2040b90..cb75015 100644
--- a/target/riscv/cpu_cfg.h
+++ b/target/riscv/cpu_cfg.h
@@ -130,10 +130,12 @@
bool ext_zic64b;
/*
- * Always 'true' boolean for named features
- * TCG always implement/can't be disabled.
+ * Always 'true' booleans for named features
+ * TCG always implement/can't be user disabled,
+ * based on spec version.
*/
- bool ext_always_enabled;
+ bool has_priv_1_12;
+ bool has_priv_1_11;
/* Vendor-specific custom extensions */
bool ext_xtheadba;
diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index ce73220..fc090d7 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -1315,7 +1315,7 @@
bool two_stage_lookup = mmuidx_2stage(mmu_idx);
bool two_stage_indirect_error = false;
int ret = TRANSLATE_FAIL;
- int mode = mmu_idx;
+ int mode = mmuidx_priv(mmu_idx);
/* default TLB page size */
target_ulong tlb_size = TARGET_PAGE_SIZE;
diff --git a/target/riscv/insn_trans/trans_rvbf16.c.inc b/target/riscv/insn_trans/trans_rvbf16.c.inc
index 8ee99df..0a9cd1e 100644
--- a/target/riscv/insn_trans/trans_rvbf16.c.inc
+++ b/target/riscv/insn_trans/trans_rvbf16.c.inc
@@ -71,11 +71,8 @@
if (opfv_narrow_check(ctx, a) && (ctx->sew == MO_16)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
gen_set_rm_chkfrm(ctx, RISCV_FRM_DYN);
- tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul);
@@ -86,8 +83,7 @@
ctx->cfg_ptr->vlenb,
ctx->cfg_ptr->vlenb, data,
gen_helper_vfncvtbf16_f_f_w);
- mark_vs_dirty(ctx);
- gen_set_label(over);
+ finalize_rvv_inst(ctx);
return true;
}
return false;
@@ -100,11 +96,8 @@
if (opfv_widen_check(ctx, a) && (ctx->sew == MO_16)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
gen_set_rm_chkfrm(ctx, RISCV_FRM_DYN);
- tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul);
@@ -115,8 +108,7 @@
ctx->cfg_ptr->vlenb,
ctx->cfg_ptr->vlenb, data,
gen_helper_vfwcvtbf16_f_f_v);
- mark_vs_dirty(ctx);
- gen_set_label(over);
+ finalize_rvv_inst(ctx);
return true;
}
return false;
@@ -130,11 +122,8 @@
if (require_rvv(ctx) && vext_check_isa_ill(ctx) && (ctx->sew == MO_16) &&
vext_check_dss(ctx, a->rd, a->rs1, a->rs2, a->vm)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
gen_set_rm_chkfrm(ctx, RISCV_FRM_DYN);
- tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, ctx->lmul);
@@ -146,8 +135,7 @@
ctx->cfg_ptr->vlenb,
ctx->cfg_ptr->vlenb, data,
gen_helper_vfwmaccbf16_vv);
- mark_vs_dirty(ctx);
- gen_set_label(over);
+ finalize_rvv_inst(ctx);
return true;
}
return false;
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index e427289..7d84e7d 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -167,7 +167,7 @@
gen_helper_vsetvl(dst, tcg_env, s1, s2);
gen_set_gpr(s, rd, dst);
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
gen_update_pc(s, s->cur_insn_len);
lookup_and_goto_ptr(s);
@@ -187,7 +187,7 @@
gen_helper_vsetvl(dst, tcg_env, s1, s2);
gen_set_gpr(s, rd, dst);
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
gen_update_pc(s, s->cur_insn_len);
lookup_and_goto_ptr(s);
s->base.is_jmp = DISAS_NORETURN;
@@ -616,9 +616,6 @@
TCGv base;
TCGv_i32 desc;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
base = get_gpr(s, rs1, EXT_NONE);
@@ -660,7 +657,7 @@
tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
}
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -802,9 +799,6 @@
TCGv base, stride;
TCGv_i32 desc;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
base = get_gpr(s, rs1, EXT_NONE);
@@ -819,7 +813,7 @@
fn(dest, mask, base, stride, tcg_env, desc);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -906,9 +900,6 @@
TCGv base;
TCGv_i32 desc;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
index = tcg_temp_new_ptr();
@@ -924,7 +915,7 @@
fn(dest, mask, base, index, tcg_env, desc);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -1044,9 +1035,6 @@
TCGv base;
TCGv_i32 desc;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
base = get_gpr(s, rs1, EXT_NONE);
@@ -1058,8 +1046,7 @@
fn(dest, mask, base, tcg_env, desc);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -1097,13 +1084,9 @@
typedef void gen_helper_ldst_whole(TCGv_ptr, TCGv, TCGv_env, TCGv_i32);
static bool ldst_whole_trans(uint32_t vd, uint32_t rs1, uint32_t nf,
- uint32_t width, gen_helper_ldst_whole *fn,
+ gen_helper_ldst_whole *fn,
DisasContext *s)
{
- uint32_t evl = s->cfg_ptr->vlenb * nf / width;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcondi_tl(TCG_COND_GEU, cpu_vstart, evl, over);
-
TCGv_ptr dest;
TCGv base;
TCGv_i32 desc;
@@ -1120,8 +1103,7 @@
fn(dest, base, tcg_env, desc);
- gen_set_label(over);
-
+ finalize_rvv_inst(s);
return true;
}
@@ -1129,42 +1111,42 @@
* load and store whole register instructions ignore vtype and vl setting.
* Thus, we don't need to check vill bit. (Section 7.9)
*/
-#define GEN_LDST_WHOLE_TRANS(NAME, ARG_NF, WIDTH) \
+#define GEN_LDST_WHOLE_TRANS(NAME, ARG_NF) \
static bool trans_##NAME(DisasContext *s, arg_##NAME * a) \
{ \
if (require_rvv(s) && \
QEMU_IS_ALIGNED(a->rd, ARG_NF)) { \
- return ldst_whole_trans(a->rd, a->rs1, ARG_NF, WIDTH, \
+ return ldst_whole_trans(a->rd, a->rs1, ARG_NF, \
gen_helper_##NAME, s); \
} \
return false; \
}
-GEN_LDST_WHOLE_TRANS(vl1re8_v, 1, 1)
-GEN_LDST_WHOLE_TRANS(vl1re16_v, 1, 2)
-GEN_LDST_WHOLE_TRANS(vl1re32_v, 1, 4)
-GEN_LDST_WHOLE_TRANS(vl1re64_v, 1, 8)
-GEN_LDST_WHOLE_TRANS(vl2re8_v, 2, 1)
-GEN_LDST_WHOLE_TRANS(vl2re16_v, 2, 2)
-GEN_LDST_WHOLE_TRANS(vl2re32_v, 2, 4)
-GEN_LDST_WHOLE_TRANS(vl2re64_v, 2, 8)
-GEN_LDST_WHOLE_TRANS(vl4re8_v, 4, 1)
-GEN_LDST_WHOLE_TRANS(vl4re16_v, 4, 2)
-GEN_LDST_WHOLE_TRANS(vl4re32_v, 4, 4)
-GEN_LDST_WHOLE_TRANS(vl4re64_v, 4, 8)
-GEN_LDST_WHOLE_TRANS(vl8re8_v, 8, 1)
-GEN_LDST_WHOLE_TRANS(vl8re16_v, 8, 2)
-GEN_LDST_WHOLE_TRANS(vl8re32_v, 8, 4)
-GEN_LDST_WHOLE_TRANS(vl8re64_v, 8, 8)
+GEN_LDST_WHOLE_TRANS(vl1re8_v, 1)
+GEN_LDST_WHOLE_TRANS(vl1re16_v, 1)
+GEN_LDST_WHOLE_TRANS(vl1re32_v, 1)
+GEN_LDST_WHOLE_TRANS(vl1re64_v, 1)
+GEN_LDST_WHOLE_TRANS(vl2re8_v, 2)
+GEN_LDST_WHOLE_TRANS(vl2re16_v, 2)
+GEN_LDST_WHOLE_TRANS(vl2re32_v, 2)
+GEN_LDST_WHOLE_TRANS(vl2re64_v, 2)
+GEN_LDST_WHOLE_TRANS(vl4re8_v, 4)
+GEN_LDST_WHOLE_TRANS(vl4re16_v, 4)
+GEN_LDST_WHOLE_TRANS(vl4re32_v, 4)
+GEN_LDST_WHOLE_TRANS(vl4re64_v, 4)
+GEN_LDST_WHOLE_TRANS(vl8re8_v, 8)
+GEN_LDST_WHOLE_TRANS(vl8re16_v, 8)
+GEN_LDST_WHOLE_TRANS(vl8re32_v, 8)
+GEN_LDST_WHOLE_TRANS(vl8re64_v, 8)
/*
* The vector whole register store instructions are encoded similar to
* unmasked unit-stride store of elements with EEW=8.
*/
-GEN_LDST_WHOLE_TRANS(vs1r_v, 1, 1)
-GEN_LDST_WHOLE_TRANS(vs2r_v, 2, 1)
-GEN_LDST_WHOLE_TRANS(vs4r_v, 4, 1)
-GEN_LDST_WHOLE_TRANS(vs8r_v, 8, 1)
+GEN_LDST_WHOLE_TRANS(vs1r_v, 1)
+GEN_LDST_WHOLE_TRANS(vs2r_v, 2)
+GEN_LDST_WHOLE_TRANS(vs4r_v, 4)
+GEN_LDST_WHOLE_TRANS(vs8r_v, 8)
/*
*** Vector Integer Arithmetic Instructions
@@ -1195,10 +1177,6 @@
do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
gen_helper_gvec_4_ptr *fn)
{
- TCGLabel *over = gen_new_label();
-
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd),
vreg_ofs(s, a->rs2), vreg_ofs(s, a->rs1),
@@ -1215,8 +1193,7 @@
tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data, fn);
}
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -1248,9 +1225,6 @@
TCGv_i32 desc;
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
src2 = tcg_temp_new_ptr();
@@ -1270,8 +1244,7 @@
fn(dest, mask, src1, src2, tcg_env, desc);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -1296,7 +1269,7 @@
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
src1, MAXSZ(s), MAXSZ(s));
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
return true;
}
return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
@@ -1410,9 +1383,6 @@
TCGv_i32 desc;
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
src2 = tcg_temp_new_ptr();
@@ -1432,8 +1402,7 @@
fn(dest, mask, src1, src2, tcg_env, desc);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -1447,7 +1416,7 @@
if (a->vm && s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
extract_imm(s, a->rs1, imm_mode), MAXSZ(s), MAXSZ(s));
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
return true;
}
return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s, imm_mode);
@@ -1495,8 +1464,6 @@
{
if (checkfn(s, a)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1508,8 +1475,7 @@
tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb,
data, fn);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -1571,8 +1537,6 @@
{
if (opiwv_widen_check(s, a)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1583,8 +1547,7 @@
vreg_ofs(s, a->rs2),
tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data, fn);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -1643,8 +1606,6 @@
gen_helper_gvec_4_ptr *fn, DisasContext *s)
{
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1654,8 +1615,7 @@
tcg_gen_gvec_4_ptr(vreg_ofs(s, vd), vreg_ofs(s, 0), vreg_ofs(s, vs1),
vreg_ofs(s, vs2), tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data, fn);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -1788,7 +1748,7 @@
gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
src1, MAXSZ(s), MAXSZ(s));
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
return true;
}
return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
@@ -1834,8 +1794,6 @@
gen_helper_##NAME##_h, \
gen_helper_##NAME##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -1847,8 +1805,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2045,16 +2002,13 @@
gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h,
gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
};
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data,
fns[s->sew]);
- gen_set_label(over);
}
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -2068,8 +2022,6 @@
/* vmv.v.x has rs2 = 0 and vm = 1 */
vext_check_ss(s, a->rd, 0, 1)) {
TCGv s1;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
s1 = get_gpr(s, a->rs1, EXT_SIGN);
@@ -2101,8 +2053,7 @@
fns[s->sew](dest, s1_i64, tcg_env, desc);
}
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -2118,7 +2069,6 @@
if (s->vl_eq_vlmax && !(s->vta && s->lmul < 0)) {
tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), simm);
- mark_vs_dirty(s);
} else {
TCGv_i32 desc;
TCGv_i64 s1;
@@ -2129,8 +2079,6 @@
gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
};
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
s1 = tcg_constant_i64(simm);
dest = tcg_temp_new_ptr();
@@ -2138,10 +2086,8 @@
s->cfg_ptr->vlenb, data));
tcg_gen_addi_ptr(dest, tcg_env, vreg_ofs(s, a->rd));
fns[s->sew](dest, s1, tcg_env, desc);
-
- mark_vs_dirty(s);
- gen_set_label(over);
}
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -2275,9 +2221,7 @@
gen_helper_##NAME##_w, \
gen_helper_##NAME##_d, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2291,8 +2235,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew - 1]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2310,9 +2253,6 @@
TCGv_i32 desc;
TCGv_i64 t1;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
-
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
src2 = tcg_temp_new_ptr();
@@ -2329,8 +2269,7 @@
fn(dest, mask, t1, src2, tcg_env, desc);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
@@ -2393,9 +2332,7 @@
static gen_helper_gvec_4_ptr * const fns[2] = { \
gen_helper_##NAME##_h, gen_helper_##NAME##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2407,8 +2344,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew - 1]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2467,9 +2403,7 @@
static gen_helper_gvec_4_ptr * const fns[2] = { \
gen_helper_##NAME##_h, gen_helper_##NAME##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2481,8 +2415,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew - 1]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2584,9 +2517,7 @@
{
if (checkfn(s, a)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
gen_set_rm_chkfrm(s, rm);
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -2596,8 +2527,7 @@
vreg_ofs(s, a->rs2), tcg_env,
s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data, fn);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -2684,7 +2614,6 @@
tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), t1);
- mark_vs_dirty(s);
} else {
TCGv_ptr dest;
TCGv_i32 desc;
@@ -2696,8 +2625,6 @@
gen_helper_vmv_v_x_w,
gen_helper_vmv_v_x_d,
};
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
t1 = tcg_temp_new_i64();
/* NaN-box f[rs1] */
@@ -2709,10 +2636,8 @@
tcg_gen_addi_ptr(dest, tcg_env, vreg_ofs(s, a->rd));
fns[s->sew - 1](dest, t1, tcg_env, desc);
-
- mark_vs_dirty(s);
- gen_set_label(over);
}
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -2773,9 +2698,7 @@
gen_helper_##HELPER##_h, \
gen_helper_##HELPER##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm_chkfrm(s, FRM); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2786,8 +2709,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew - 1]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2824,9 +2746,7 @@
gen_helper_##NAME##_h, \
gen_helper_##NAME##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm(s, RISCV_FRM_DYN); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2837,8 +2757,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2891,9 +2810,7 @@
gen_helper_##HELPER##_h, \
gen_helper_##HELPER##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm_chkfrm(s, FRM); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2904,8 +2821,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew - 1]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -2940,9 +2856,7 @@
gen_helper_##HELPER##_h, \
gen_helper_##HELPER##_w, \
}; \
- TCGLabel *over = gen_new_label(); \
gen_set_rm_chkfrm(s, FRM); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -2953,8 +2867,7 @@
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, \
fns[s->sew]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -3031,8 +2944,6 @@
vext_check_isa_ill(s)) { \
uint32_t data = 0; \
gen_helper_gvec_4_ptr *fn = gen_helper_##NAME; \
- TCGLabel *over = gen_new_label(); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
data = \
@@ -3042,8 +2953,7 @@
vreg_ofs(s, a->rs2), tcg_env, \
s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, data, fn); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -3131,8 +3041,6 @@
s->vstart_eq_zero) { \
uint32_t data = 0; \
gen_helper_gvec_3_ptr *fn = gen_helper_##NAME; \
- TCGLabel *over = gen_new_label(); \
- tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -3144,8 +3052,7 @@
tcg_env, s->cfg_ptr->vlenb, \
s->cfg_ptr->vlenb, \
data, fn); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -3171,8 +3078,6 @@
require_align(a->rd, s->lmul) &&
s->vstart_eq_zero) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -3186,8 +3091,7 @@
vreg_ofs(s, a->rs2), tcg_env,
s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data, fns[s->sew]);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3201,8 +3105,6 @@
require_align(a->rd, s->lmul) &&
require_vm(a->vm, a->rd)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
data = FIELD_DP32(data, VDATA, VM, a->vm);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -3216,8 +3118,7 @@
tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb,
data, fns[s->sew]);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3373,6 +3274,8 @@
vec_element_loadi(s, t1, a->rs2, 0, true);
tcg_gen_trunc_i64_tl(dest, t1);
gen_set_gpr(s, a->rd, dest);
+ tcg_gen_movi_tl(cpu_vstart, 0);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3399,8 +3302,9 @@
s1 = get_gpr(s, a->rs1, EXT_NONE);
tcg_gen_ext_tl_i64(t1, s1);
vec_element_storei(s, a->rd, 0, t1);
- mark_vs_dirty(s);
gen_set_label(over);
+ tcg_gen_movi_tl(cpu_vstart, 0);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3427,6 +3331,8 @@
}
mark_fs_dirty(s);
+ tcg_gen_movi_tl(cpu_vstart, 0);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3452,8 +3358,10 @@
do_nanbox(s, t1, cpu_fpr[a->rs1]);
vec_element_storei(s, a->rd, 0, t1);
- mark_vs_dirty(s);
+
gen_set_label(over);
+ tcg_gen_movi_tl(cpu_vstart, 0);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3559,7 +3467,7 @@
tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
MAXSZ(s), MAXSZ(s), dest);
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
} else {
static gen_helper_opivx * const fns[4] = {
gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
@@ -3587,7 +3495,7 @@
endian_ofs(s, a->rs2, a->rs1),
MAXSZ(s), MAXSZ(s));
}
- mark_vs_dirty(s);
+ finalize_rvv_inst(s);
} else {
static gen_helper_opivx * const fns[4] = {
gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
@@ -3624,8 +3532,6 @@
gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h,
gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d,
};
- TCGLabel *over = gen_new_label();
- tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
data = FIELD_DP32(data, VDATA, VTA, s->vta);
@@ -3634,8 +3540,7 @@
tcg_env, s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data,
fns[s->sew]);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -3656,15 +3561,11 @@
if (s->vstart_eq_zero) { \
tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd), \
vreg_ofs(s, a->rs2), maxsz, maxsz); \
- mark_vs_dirty(s); \
} else { \
- TCGLabel *over = gen_new_label(); \
- tcg_gen_brcondi_tl(TCG_COND_GEU, cpu_vstart, maxsz, over); \
tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2), \
tcg_env, maxsz, maxsz, 0, gen_helper_vmvr_v); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
} \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -3692,8 +3593,6 @@
{
uint32_t data = 0;
gen_helper_gvec_3_ptr *fn;
- TCGLabel *over = gen_new_label();
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
static gen_helper_gvec_3_ptr * const fns[6][4] = {
{
@@ -3737,8 +3636,7 @@
s->cfg_ptr->vlenb,
s->cfg_ptr->vlenb, data, fn);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc
index a5cdd1b..ae1f401 100644
--- a/target/riscv/insn_trans/trans_rvvk.c.inc
+++ b/target/riscv/insn_trans/trans_rvvk.c.inc
@@ -164,8 +164,6 @@
gen_helper_##NAME##_w, \
gen_helper_##NAME##_d, \
}; \
- TCGLabel *over = gen_new_label(); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
@@ -176,8 +174,7 @@
vreg_ofs(s, a->rs2), tcg_env, \
s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, \
data, fns[s->sew]); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -249,14 +246,12 @@
TCGv_ptr rd_v, rs2_v; \
TCGv_i32 desc, egs; \
uint32_t data = 0; \
- TCGLabel *over = gen_new_label(); \
\
if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \
/* save opcode for unwinding in case we throw an exception */ \
decode_save_opc(s); \
egs = tcg_constant_i32(EGS); \
gen_helper_egs_check(egs, tcg_env); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
} \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
@@ -271,8 +266,7 @@
tcg_gen_addi_ptr(rd_v, tcg_env, vreg_ofs(s, a->rd)); \
tcg_gen_addi_ptr(rs2_v, tcg_env, vreg_ofs(s, a->rs2)); \
gen_helper_##NAME(rd_v, rs2_v, tcg_env, desc); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -325,14 +319,12 @@
TCGv_ptr rd_v, rs2_v; \
TCGv_i32 uimm_v, desc, egs; \
uint32_t data = 0; \
- TCGLabel *over = gen_new_label(); \
\
if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \
/* save opcode for unwinding in case we throw an exception */ \
decode_save_opc(s); \
egs = tcg_constant_i32(EGS); \
gen_helper_egs_check(egs, tcg_env); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
} \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
@@ -349,8 +341,7 @@
tcg_gen_addi_ptr(rd_v, tcg_env, vreg_ofs(s, a->rd)); \
tcg_gen_addi_ptr(rs2_v, tcg_env, vreg_ofs(s, a->rs2)); \
gen_helper_##NAME(rd_v, rs2_v, uimm_v, tcg_env, desc); \
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -394,7 +385,6 @@
{ \
if (CHECK(s, a)) { \
uint32_t data = 0; \
- TCGLabel *over = gen_new_label(); \
TCGv_i32 egs; \
\
if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \
@@ -402,7 +392,6 @@
decode_save_opc(s); \
egs = tcg_constant_i32(EGS); \
gen_helper_egs_check(egs, tcg_env); \
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
} \
\
data = FIELD_DP32(data, VDATA, VM, a->vm); \
@@ -416,8 +405,7 @@
s->cfg_ptr->vlenb, s->cfg_ptr->vlenb, \
data, gen_helper_##NAME); \
\
- mark_vs_dirty(s); \
- gen_set_label(over); \
+ finalize_rvv_inst(s); \
return true; \
} \
return false; \
@@ -448,7 +436,6 @@
{
if (vsha_check(s, a)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
TCGv_i32 egs;
if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {
@@ -456,7 +443,6 @@
decode_save_opc(s);
egs = tcg_constant_i32(ZVKNH_EGS);
gen_helper_egs_check(egs, tcg_env);
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
}
data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -471,8 +457,7 @@
s->sew == MO_32 ?
gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
@@ -482,7 +467,6 @@
{
if (vsha_check(s, a)) {
uint32_t data = 0;
- TCGLabel *over = gen_new_label();
TCGv_i32 egs;
if (!s->vstart_eq_zero || !s->vl_eq_vlmax) {
@@ -490,7 +474,6 @@
decode_save_opc(s);
egs = tcg_constant_i32(ZVKNH_EGS);
gen_helper_egs_check(egs, tcg_env);
- tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
}
data = FIELD_DP32(data, VDATA, VM, a->vm);
@@ -505,8 +488,7 @@
s->sew == MO_32 ?
gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv);
- mark_vs_dirty(s);
- gen_set_label(over);
+ finalize_rvv_inst(s);
return true;
}
return false;
diff --git a/target/riscv/kvm/kvm-cpu.c b/target/riscv/kvm/kvm-cpu.c
index cda7d78..6a6c6ca 100644
--- a/target/riscv/kvm/kvm-cpu.c
+++ b/target/riscv/kvm/kvm-cpu.c
@@ -739,6 +739,15 @@
env->kvm_timer_dirty = false;
}
+uint64_t kvm_riscv_get_timebase_frequency(CPUState *cs)
+{
+ uint64_t reg;
+
+ KVM_RISCV_GET_TIMER(cs, frequency, reg);
+
+ return reg;
+}
+
static int kvm_riscv_get_regs_vector(CPUState *cs)
{
RISCVCPU *cpu = RISCV_CPU(cs);
diff --git a/target/riscv/kvm/kvm_riscv.h b/target/riscv/kvm/kvm_riscv.h
index 4bd98fd..5851898 100644
--- a/target/riscv/kvm/kvm_riscv.h
+++ b/target/riscv/kvm/kvm_riscv.h
@@ -28,5 +28,6 @@
void riscv_kvm_aplic_request(void *opaque, int irq, int level);
int kvm_riscv_sync_mpstate_to_kvm(RISCVCPU *cpu, int state);
void riscv_kvm_cpu_finalize_features(RISCVCPU *cpu, Error **errp);
+uint64_t kvm_riscv_get_timebase_frequency(CPUState *cs);
#endif
diff --git a/target/riscv/tcg/tcg-cpu.c b/target/riscv/tcg/tcg-cpu.c
index ab6db81..b5b95e0 100644
--- a/target/riscv/tcg/tcg-cpu.c
+++ b/target/riscv/tcg/tcg-cpu.c
@@ -315,9 +315,19 @@
static void riscv_cpu_update_named_features(RISCVCPU *cpu)
{
+ if (cpu->env.priv_ver >= PRIV_VERSION_1_11_0) {
+ cpu->cfg.has_priv_1_11 = true;
+ }
+
+ if (cpu->env.priv_ver >= PRIV_VERSION_1_12_0) {
+ cpu->cfg.has_priv_1_12 = true;
+ }
+
+ /* zic64b is 1.12 or later */
cpu->cfg.ext_zic64b = cpu->cfg.cbom_blocksize == 64 &&
cpu->cfg.cbop_blocksize == 64 &&
- cpu->cfg.cboz_blocksize == 64;
+ cpu->cfg.cboz_blocksize == 64 &&
+ cpu->cfg.has_priv_1_12;
}
static void riscv_cpu_validate_g(RISCVCPU *cpu)
@@ -520,11 +530,6 @@
return;
}
- if (cpu->cfg.ext_zvfbfmin && !cpu->cfg.ext_zfbfmin) {
- error_setg(errp, "Zvfbfmin extension depends on Zfbfmin extension");
- return;
- }
-
if (cpu->cfg.ext_zvfbfmin && !cpu->cfg.ext_zve32f) {
error_setg(errp, "Zvfbfmin extension depends on Zve32f extension");
return;
@@ -1316,8 +1321,6 @@
RISCVCPU *cpu = RISCV_CPU(cs);
Object *obj = OBJECT(cpu);
- cpu->cfg.ext_always_enabled = true;
-
misa_ext_user_opts = g_hash_table_new(NULL, g_direct_equal);
multi_ext_user_opts = g_hash_table_new(NULL, g_direct_equal);
riscv_cpu_add_user_properties(obj);
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index ea5d52b..9d57089 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -676,6 +676,12 @@
static inline void mark_vs_dirty(DisasContext *ctx) { }
#endif
+static void finalize_rvv_inst(DisasContext *ctx)
+{
+ mark_vs_dirty(ctx);
+ ctx->vstart_eq_zero = true;
+}
+
static void gen_set_rm(DisasContext *ctx, int rm)
{
if (ctx->frm == rm) {
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index e2d719b..f7423df 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -222,6 +222,8 @@
uint32_t total_elems = vext_get_total_elems(env, desc, 4); \
uint32_t vta = vext_vta(desc); \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \
AESState round_key; \
round_key.d[0] = *((uint64_t *)vs2 + H8(i * 2 + 0)); \
@@ -246,6 +248,8 @@
uint32_t total_elems = vext_get_total_elems(env, desc, 4); \
uint32_t vta = vext_vta(desc); \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \
AESState round_key; \
round_key.d[0] = *((uint64_t *)vs2 + H8(0)); \
@@ -305,6 +309,8 @@
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
uimm &= 0b1111;
if (uimm > 10 || uimm == 0) {
uimm ^= 0b1000;
@@ -351,6 +357,8 @@
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
uimm &= 0b1111;
if (uimm > 14 || uimm < 2) {
uimm ^= 0b1000;
@@ -457,6 +465,8 @@
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
if (sew == MO_32) {
vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * 4,
@@ -572,6 +582,8 @@
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
((uint32_t *)vs1) + 4 * i + 2);
@@ -590,6 +602,8 @@
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
((uint64_t *)vs1) + 4 * i + 2);
@@ -608,6 +622,8 @@
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i,
(((uint32_t *)vs1) + 4 * i));
@@ -626,6 +642,8 @@
uint32_t total_elems;
uint32_t vta = vext_vta(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i,
(((uint64_t *)vs1) + 4 * i));
@@ -658,6 +676,8 @@
uint32_t *vs1 = vs1_vptr;
uint32_t *vs2 = vs2_vptr;
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (int i = env->vstart / 8; i < env->vl / 8; i++) {
uint32_t w[24];
for (int j = 0; j < 8; j++) {
@@ -757,6 +777,8 @@
uint32_t *vs2 = vs2_vptr;
uint32_t v1[8], v2[8], v3[8];
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (int i = env->vstart / 8; i < env->vl / 8; i++) {
for (int k = 0; k < 8; k++) {
v2[k] = bswap32(vd[H4(i * 8 + k)]);
@@ -780,6 +802,8 @@
uint32_t vta = vext_vta(desc);
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]};
uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])};
@@ -817,6 +841,8 @@
uint32_t vta = vext_vta(desc);
uint32_t total_elems = vext_get_total_elems(env, desc, 4);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
uint64_t Y[2] = {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])};
uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])};
@@ -853,6 +879,8 @@
uint32_t esz = sizeof(uint32_t);
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = group_start; i < group_end; ++i) {
uint32_t vstart = i * egs;
uint32_t vend = (i + 1) * egs;
@@ -909,6 +937,8 @@
uint32_t esz = sizeof(uint32_t);
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = group_start; i < group_end; ++i) {
uint32_t vstart = i * egs;
uint32_t vend = (i + 1) * egs;
@@ -943,6 +973,8 @@
uint32_t esz = sizeof(uint32_t);
uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = group_start; i < group_end; ++i) {
uint32_t vstart = i * egs;
uint32_t vend = (i + 1) * egs;
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index fe56c00..fa13904 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -207,7 +207,9 @@
uint32_t esz = 1 << log2_esz;
uint32_t vma = vext_vma(desc);
- for (i = env->vstart; i < env->vl; i++, env->vstart++) {
+ VSTART_CHECK_EARLY_EXIT(env);
+
+ for (i = env->vstart; i < env->vl; env->vstart = ++i) {
k = 0;
while (k < nf) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -272,8 +274,10 @@
uint32_t max_elems = vext_max_elems(desc, log2_esz);
uint32_t esz = 1 << log2_esz;
+ VSTART_CHECK_EARLY_EXIT(env);
+
/* load bytes from guest memory */
- for (i = env->vstart; i < evl; i++, env->vstart++) {
+ for (i = env->vstart; i < evl; env->vstart = ++i) {
k = 0;
while (k < nf) {
target_ulong addr = base + ((i * nf + k) << log2_esz);
@@ -386,8 +390,10 @@
uint32_t esz = 1 << log2_esz;
uint32_t vma = vext_vma(desc);
+ VSTART_CHECK_EARLY_EXIT(env);
+
/* load bytes from guest memory */
- for (i = env->vstart; i < env->vl; i++, env->vstart++) {
+ for (i = env->vstart; i < env->vl; env->vstart = ++i) {
k = 0;
while (k < nf) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -477,6 +483,8 @@
target_ulong addr, offset, remain;
int mmu_index = riscv_env_mmu_index(env, false);
+ VSTART_CHECK_EARLY_EXIT(env);
+
/* probe every access */
for (i = env->vstart; i < env->vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
@@ -572,6 +580,11 @@
uint32_t vlenb = riscv_cpu_cfg(env)->vlenb;
uint32_t max_elems = vlenb >> log2_esz;
+ if (env->vstart >= ((vlenb * nf) >> log2_esz)) {
+ env->vstart = 0;
+ return;
+ }
+
k = env->vstart / max_elems;
off = env->vstart % max_elems;
@@ -877,6 +890,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -909,6 +924,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
ETYPE carry = vext_elem_mask(v0, i); \
@@ -944,6 +961,8 @@
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -982,6 +1001,8 @@
uint32_t vta_all_1s = vext_vta_all_1s(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
ETYPE carry = !vm && vext_elem_mask(v0, i); \
@@ -1078,6 +1099,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -1125,6 +1148,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -1187,6 +1212,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -1252,6 +1279,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -1799,6 +1828,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
*((ETYPE *)vd + H(i)) = s1; \
@@ -1823,6 +1854,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
*((ETYPE *)vd + H(i)) = (ETYPE)s1; \
} \
@@ -1846,6 +1879,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE *vt = (!vext_elem_mask(v0, i) ? vs2 : vs1); \
*((ETYPE *)vd + H(i)) = *(vt + H(i)); \
@@ -1870,6 +1905,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
ETYPE d = (!vext_elem_mask(v0, i) ? s2 : \
@@ -1915,6 +1952,8 @@
uint32_t vl, uint32_t vm, int vxrm,
opivv2_rm_fn *fn, uint32_t vma, uint32_t esz)
{
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -2040,6 +2079,8 @@
uint32_t vl, uint32_t vm, int vxrm,
opivx2_rm_fn *fn, uint32_t vma, uint32_t esz)
{
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (uint32_t i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -2837,6 +2878,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -2880,6 +2923,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -3466,6 +3511,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
if (vl == 0) { \
return; \
} \
@@ -3987,6 +4034,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s1 = *((ETYPE *)vs1 + H(i)); \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
@@ -4027,6 +4076,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -4220,6 +4271,8 @@
uint32_t vta = vext_vta(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
ETYPE s2 = *((ETYPE *)vs2 + H(i)); \
*((ETYPE *)vd + H(i)) = \
@@ -4544,6 +4597,8 @@
uint32_t i; \
int a, b; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
a = vext_elem_mask(vs1, i); \
b = vext_elem_mask(vs2, i); \
@@ -4737,6 +4792,8 @@
uint32_t vma = vext_vma(desc); \
int i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4772,6 +4829,8 @@
uint32_t vma = vext_vma(desc); \
target_ulong offset = s1, i_min, i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
i_min = MAX(env->vstart, offset); \
for (i = i_min; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
@@ -4781,6 +4840,7 @@
} \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset)); \
} \
+ env->vstart = 0; \
/* set tail elements to 1s */ \
vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz); \
}
@@ -4804,6 +4864,8 @@
uint32_t vma = vext_vma(desc); \
target_ulong i_max, i_min, i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
i_min = MIN(s1 < vlmax ? vlmax - s1 : 0, vl); \
i_max = MAX(i_min, env->vstart); \
for (i = env->vstart; i < i_max; ++i) { \
@@ -4846,6 +4908,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4895,6 +4959,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -4970,6 +5036,8 @@
uint64_t index; \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -5013,6 +5081,8 @@
uint64_t index = s1; \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
@@ -5074,9 +5144,22 @@
uint32_t startb = env->vstart * sewb;
uint32_t i = startb;
+ if (startb >= maxsz) {
+ env->vstart = 0;
+ return;
+ }
+
+ if (HOST_BIG_ENDIAN && i % 8 != 0) {
+ uint32_t j = ROUND_UP(i, 8);
+ memcpy((uint8_t *)vd + H1(j - 1),
+ (uint8_t *)vs2 + H1(j - 1),
+ j - i);
+ i = j;
+ }
+
memcpy((uint8_t *)vd + H1(i),
(uint8_t *)vs2 + H1(i),
- maxsz - startb);
+ maxsz - i);
env->vstart = 0;
}
@@ -5094,6 +5177,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
diff --git a/target/riscv/vector_internals.c b/target/riscv/vector_internals.c
index 12f5964..996c21e 100644
--- a/target/riscv/vector_internals.c
+++ b/target/riscv/vector_internals.c
@@ -44,6 +44,8 @@
uint32_t vma = vext_vma(desc);
uint32_t i;
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
@@ -68,6 +70,8 @@
uint32_t vma = vext_vma(desc);
uint32_t i;
+ VSTART_CHECK_EARLY_EXIT(env);
+
for (i = env->vstart; i < vl; i++) {
if (!vm && !vext_elem_mask(v0, i)) {
/* set masked-off elements to 1s */
diff --git a/target/riscv/vector_internals.h b/target/riscv/vector_internals.h
index 842765f..9e1e15b 100644
--- a/target/riscv/vector_internals.h
+++ b/target/riscv/vector_internals.h
@@ -24,6 +24,13 @@
#include "tcg/tcg-gvec-desc.h"
#include "internals.h"
+#define VSTART_CHECK_EARLY_EXIT(env) do { \
+ if (env->vstart >= env->vl) { \
+ env->vstart = 0; \
+ return; \
+ } \
+} while (0)
+
static inline uint32_t vext_nf(uint32_t desc)
{
return FIELD_EX32(simd_data(desc), VDATA, NF);
@@ -151,6 +158,8 @@
uint32_t vma = vext_vma(desc); \
uint32_t i; \
\
+ VSTART_CHECK_EARLY_EXIT(env); \
+ \
for (i = env->vstart; i < vl; i++) { \
if (!vm && !vext_elem_mask(v0, i)) { \
/* set masked-off elements to 1s */ \
