@@ -3146,6 +3146,11 @@ FIELD(TBFLAG_A32, HSTR_ACTIVE, 9, 1)
* the same thing as the current security state of the processor!
*/
FIELD(TBFLAG_A32, NS, 10, 1)
+/*
+ * Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not.
+ * This requires an SME trap from AArch32 mode when using NEON.
+ */
+FIELD(TBFLAG_A32, SME_TRAP_NONSTREAMING, 11, 1)
/*
* Bit usage when in AArch32 state, for M-profile only.
@@ -3183,6 +3188,8 @@ FIELD(TBFLAG_A64, SMEEXC_EL, 20, 2)
FIELD(TBFLAG_A64, PSTATE_SM, 22, 1)
FIELD(TBFLAG_A64, PSTATE_ZA, 23, 1)
FIELD(TBFLAG_A64, SVL, 24, 4)
+/* Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. */
+FIELD(TBFLAG_A64, SME_TRAP_NONSTREAMING, 28, 1)
/*
* Helpers for using the above.
@@ -102,6 +102,10 @@ typedef struct DisasContext {
bool pstate_sm;
/* True if PSTATE.ZA is set. */
bool pstate_za;
+ /* True if non-streaming insns should raise an SME Streaming exception. */
+ bool sme_trap_nonstreaming;
+ /* True if the current instruction is non-streaming. */
+ bool is_nonstreaming;
/* True if MVE insns are definitely not predicated by VPR or LTPSIZE */
bool mve_no_pred;
/*
new file mode 100644
@@ -0,0 +1,90 @@
+# AArch64 SME allowed instruction decoding
+#
+# Copyright (c) 2022 Linaro, Ltd
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, see <http://www.gnu.org/licenses/>.
+
+#
+# This file is processed by scripts/decodetree.py
+#
+
+# These patterns are taken from Appendix E1.1 of DDI0616 A.a,
+# Arm Architecture Reference Manual Supplement,
+# The Scalable Matrix Extension (SME), for Armv9-A
+
+{
+ [
+ OK 0-00 1110 0000 0001 0010 11-- ---- ---- # SMOV W|Xd,Vn.B[0]
+ OK 0-00 1110 0000 0010 0010 11-- ---- ---- # SMOV W|Xd,Vn.H[0]
+ OK 0100 1110 0000 0100 0010 11-- ---- ---- # SMOV Xd,Vn.S[0]
+ OK 0000 1110 0000 0001 0011 11-- ---- ---- # UMOV Wd,Vn.B[0]
+ OK 0000 1110 0000 0010 0011 11-- ---- ---- # UMOV Wd,Vn.H[0]
+ OK 0000 1110 0000 0100 0011 11-- ---- ---- # UMOV Wd,Vn.S[0]
+ OK 0100 1110 0000 1000 0011 11-- ---- ---- # UMOV Xd,Vn.D[0]
+ ]
+ FAIL 0--0 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD vector operations
+}
+
+{
+ [
+ OK 0101 1110 --1- ---- 11-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar)
+ OK 0101 1110 -10- ---- 00-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar, FP16)
+ OK 01-1 1110 1-10 0001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar)
+ OK 01-1 1110 1111 1001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar, FP16)
+ ]
+ FAIL 01-1 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD single-element operations
+}
+
+FAIL 0-00 110- ---- ---- ---- ---- ---- ---- # Advanced SIMD structure load/store
+FAIL 1100 1110 ---- ---- ---- ---- ---- ---- # Advanced SIMD cryptography extensions
+FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS
+
+# These are the "avoidance of doubt" final table of Illegal Advanced SIMD instructions
+# We don't actually need to include these, as the default is OK.
+# -001 111- ---- ---- ---- ---- ---- ---- # Scalar floating-point operations
+# --10 110- ---- ---- ---- ---- ---- ---- # Load/store pair of FP registers
+# --01 1100 ---- ---- ---- ---- ---- ---- # Load FP register (PC-relative literal)
+# --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm)
+# --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset)
+# --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm)
+
+FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR
+FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA
+FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT
+FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS
+FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR
+FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP
+FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result)
+FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA
+FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL
+FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD
+FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA
+FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA
+FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions
+FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar)
+FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm)
+FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector)
+FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm)
+FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector)
+FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector)
+FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector)
+FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar)
+FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm)
+FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar)
+FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm)
+FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch
+FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar)
+FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar)
+FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector)
+FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc)
@@ -6269,6 +6269,32 @@ int sme_exception_el(CPUARMState *env, int el)
return 0;
}
+/* This corresponds to the ARM pseudocode function IsFullA64Enabled(). */
+static bool sme_fa64(CPUARMState *env, int el)
+{
+ if (!cpu_isar_feature(aa64_sme_fa64, env_archcpu(env))) {
+ return false;
+ }
+
+ if (el <= 1 && !el_is_in_host(env, el)) {
+ if (!FIELD_EX64(env->vfp.smcr_el[1], SMCR, FA64)) {
+ return false;
+ }
+ }
+ if (el <= 2 && arm_is_el2_enabled(env)) {
+ if (!FIELD_EX64(env->vfp.smcr_el[2], SMCR, FA64)) {
+ return false;
+ }
+ }
+ if (arm_feature(env, ARM_FEATURE_EL3)) {
+ if (!FIELD_EX64(env->vfp.smcr_el[3], SMCR, FA64)) {
+ return false;
+ }
+ }
+
+ return true;
+}
+
/*
* Given that SVE is enabled, return the vector length for EL.
*/
@@ -11312,6 +11338,20 @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el,
DP_TBFLAG_ANY(flags, PSTATE__IL, 1);
}
+ /*
+ * The SME exception we are testing for is raised via
+ * AArch64.CheckFPAdvSIMDEnabled(), as called from
+ * AArch32.CheckAdvSIMDOrFPEnabled().
+ */
+ if (el == 0
+ && FIELD_EX64(env->svcr, SVCR, SM)
+ && (!arm_is_el2_enabled(env)
+ || (arm_el_is_aa64(env, 2) && !(env->cp15.hcr_el2 & HCR_TGE)))
+ && arm_el_is_aa64(env, 1)
+ && !sme_fa64(env, el)) {
+ DP_TBFLAG_A32(flags, SME_TRAP_NONSTREAMING, 1);
+ }
+
return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
}
@@ -11361,6 +11401,7 @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
}
if (FIELD_EX64(env->svcr, SVCR, SM)) {
DP_TBFLAG_A64(flags, PSTATE_SM, 1);
+ DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el));
}
DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA));
}
@@ -1155,7 +1155,7 @@ static void do_vec_ld(DisasContext *s, int destidx, int element,
* unallocated-encoding checks (otherwise the syndrome information
* for the resulting exception will be incorrect).
*/
-static bool fp_access_check(DisasContext *s)
+static bool fp_access_check_only(DisasContext *s)
{
if (s->fp_excp_el) {
assert(!s->fp_access_checked);
@@ -1170,6 +1170,19 @@ static bool fp_access_check(DisasContext *s)
return true;
}
+static bool fp_access_check(DisasContext *s)
+{
+ if (!fp_access_check_only(s)) {
+ return false;
+ }
+ if (s->sme_trap_nonstreaming && s->is_nonstreaming) {
+ gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
+ syn_smetrap(SME_ET_Streaming, false));
+ return false;
+ }
+ return true;
+}
+
/* Check that SVE access is enabled. If it is, return true.
* If not, emit code to generate an appropriate exception and return false.
*/
@@ -1994,7 +2007,7 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread,
default:
g_assert_not_reached();
}
- if ((ri->type & ARM_CP_FPU) && !fp_access_check(s)) {
+ if ((ri->type & ARM_CP_FPU) && !fp_access_check_only(s)) {
return;
} else if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) {
return;
@@ -14530,6 +14543,23 @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn)
}
}
+/*
+ * Include the generated SME FA64 decoder.
+ */
+
+#include "decode-sme-fa64.c.inc"
+
+static bool trans_OK(DisasContext *s, arg_OK *a)
+{
+ return true;
+}
+
+static bool trans_FAIL(DisasContext *s, arg_OK *a)
+{
+ s->is_nonstreaming = true;
+ return true;
+}
+
/**
* is_guarded_page:
* @env: The cpu environment
@@ -14657,6 +14687,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
dc->mte_active[1] = EX_TBFLAG_A64(tb_flags, MTE0_ACTIVE);
dc->pstate_sm = EX_TBFLAG_A64(tb_flags, PSTATE_SM);
dc->pstate_za = EX_TBFLAG_A64(tb_flags, PSTATE_ZA);
+ dc->sme_trap_nonstreaming = EX_TBFLAG_A64(tb_flags, SME_TRAP_NONSTREAMING);
dc->vec_len = 0;
dc->vec_stride = 0;
dc->cp_regs = arm_cpu->cp_regs;
@@ -14805,6 +14836,11 @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
}
}
+ s->is_nonstreaming = false;
+ if (s->sme_trap_nonstreaming) {
+ disas_sme_fa64(s, insn);
+ }
+
switch (extract32(insn, 25, 4)) {
case 0x0:
if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) {
@@ -234,6 +234,18 @@ static bool vfp_access_check_a(DisasContext *s, bool ignore_vfp_enabled)
return false;
}
+ /*
+ * Note that rebuild_hflags_a32 has already accounted for being in EL0
+ * and the higher EL in A64 mode, etc. Unlike A64 mode, there do not
+ * appear to be any insns which touch VFP which are allowed.
+ */
+ if (s->sme_trap_nonstreaming) {
+ gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
+ syn_smetrap(SME_ET_Streaming,
+ s->base.pc_next - s->pc_curr == 2));
+ return false;
+ }
+
if (!s->vfp_enabled && !ignore_vfp_enabled) {
assert(!arm_dc_feature(s, ARM_FEATURE_M));
unallocated_encoding(s);
@@ -9378,6 +9378,8 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN);
dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE);
}
+ dc->sme_trap_nonstreaming =
+ EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING);
}
dc->cp_regs = cpu->cp_regs;
dc->features = env->features;
@@ -1,6 +1,7 @@
gen = [
decodetree.process('sve.decode', extra_args: '--decode=disas_sve'),
decodetree.process('sme.decode', extra_args: '--decode=disas_sme'),
+ decodetree.process('sme-fa64.decode', extra_args: '--static-decode=disas_sme_fa64'),
decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'),
decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'),
decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'),
This new behaviour is in the ARM pseudocode function AArch64.CheckFPAdvSIMDEnabled, which applies to AArch32 via AArch32.CheckAdvSIMDOrFPEnabled when the EL to which the trap would be delivered is in AArch64 mode. Given that ARMv9 drops support for AArch32 outside EL0, the trap EL detection ought to be trivially true, but the pseudocode still contains a number of conditions, and QEMU has not yet committed to dropping A32 support for EL[12] when v9 features are present. Since the computation of SME_TRAP_NONSTREAMING is necessarily different for the two modes, we might as well preserve bits within TBFLAG_ANY and allocate separate bits within TBFLAG_A32 and TBFLAG_A64 instead. Note that DDI0616A.a has typos for bits [22:21] of LD1RO in the table of instructions illegal in streaming mode. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.h | 7 +++ target/arm/translate.h | 4 ++ target/arm/sme-fa64.decode | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 41 +++++++++++++++++ target/arm/translate-a64.c | 40 ++++++++++++++++- target/arm/translate-vfp.c | 12 +++++ target/arm/translate.c | 2 + target/arm/meson.build | 1 + 8 files changed, 195 insertions(+), 2 deletions(-) create mode 100644 target/arm/sme-fa64.decode