diff mbox series

[04/15] target/arm: Implement VSCCLRM insn

Message ID 20201116160831.31000-5-peter.maydell@linaro.org (mailing list archive)
State New, archived
Headers show
Series target/arm: More v8.1M features | expand

Commit Message

Peter Maydell Nov. 16, 2020, 4:08 p.m. UTC
Implement the v8.1M VSCCLRM insn, which zeros floating point
registers if there is an active floating point context.

Because we want to use arm_gen_condlabel(), we need to move
the definition of that function up in translate.c so it is
before the #include of translate-vfp.c.inc.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h               |  9 ++++
 target/arm/m-nocp.decode       |  8 +++-
 target/arm/translate.c         | 18 +++----
 target/arm/translate-vfp.c.inc | 86 ++++++++++++++++++++++++++++++++++
 4 files changed, 110 insertions(+), 11 deletions(-)

Comments

Richard Henderson Nov. 17, 2020, 7:31 p.m. UTC | #1
On 11/16/20 8:08 AM, Peter Maydell wrote:
> +    aspen = load_cpu_field(v7m.fpccr[M_REG_S]);
> +    sfpa = load_cpu_field(v7m.control[M_REG_S]);
> +    tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK);
> +    tcg_gen_subi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK);

xori would be clearer, i think.

> +    /* Zero the Sregs from btmreg to topreg inclusive. */
> +    zero64 = tcg_const_i64(0);
> +    zero32 = tcg_const_i32(0);
> +    if (btmreg & 1) {
> +        write_neon_element32(zero32, btmreg >> 1, 1, MO_32);
> +        btmreg++;
> +    }
> +    for (; btmreg + 1 <= topreg; btmreg += 2) {
> +        write_neon_element64(zero64, btmreg >> 1, 0, MO_64);
> +    }
> +    if (btmreg == topreg) {
> +        write_neon_element32(zero32, btmreg >> 1, 0, MO_32);
> +        btmreg++;
> +    }

I hadn't implemented MO_32 for write_neon_element64 because there were no
users.  Better to just add the case there using tcg_gen_st32_i64, then you
don't need a 32-bit zero.

Otherwise,
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>


r~
diff mbox series

Patch

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index c18a9167665..806c18a499f 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -3555,6 +3555,15 @@  static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id)
     return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0;
 }
 
+static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id)
+{
+    /*
+     * Return true if M-profile state handling insns
+     * (VSCCLRM, CLRM, FPCTX access insns) are implemented
+     */
+    return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3;
+}
+
 static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id)
 {
     /* Sadly this is encoded differently for A-profile and M-profile */
diff --git a/target/arm/m-nocp.decode b/target/arm/m-nocp.decode
index 28c8ac6b94c..ccd62e8739a 100644
--- a/target/arm/m-nocp.decode
+++ b/target/arm/m-nocp.decode
@@ -29,13 +29,17 @@ 
 # If the coprocessor is not present or disabled then we will generate
 # the NOCP exception; otherwise we let the insn through to the main decode.
 
+%vd_dp  22:1 12:4
+%vd_sp  12:4 22:1
+
 &nocp cp
 
 {
   # Special cases which do not take an early NOCP: VLLDM and VLSTM
   VLLDM_VLSTM  1110 1100 001 l:1 rn:4 0000 1010 0000 0000
-  # TODO: VSCCLRM (new in v8.1M) is similar:
-  #VSCCLRM      1110 1100 1-01 1111 ---- 1011 ---- ---0
+  # VSCCLRM (new in v8.1M) is similar:
+  VSCCLRM      1110 1100 1.01 1111 .... 1011 imm:7 0   vd=%vd_dp size=3
+  VSCCLRM      1110 1100 1.01 1111 .... 1010 imm:8     vd=%vd_sp size=2
 
   NOCP         111- 1110 ---- ---- ---- cp:4 ---- ---- &nocp
   NOCP         111- 110- ---- ---- ---- cp:4 ---- ---- &nocp
diff --git a/target/arm/translate.c b/target/arm/translate.c
index f7d4ee393b7..4b17b2e0d46 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -100,6 +100,15 @@  void arm_translate_init(void)
     a64_translate_init();
 }
 
+/* Generate a label used for skipping this instruction */
+static void arm_gen_condlabel(DisasContext *s)
+{
+    if (!s->condjmp) {
+        s->condlabel = gen_new_label();
+        s->condjmp = 1;
+    }
+}
+
 /* Flags for the disas_set_da_iss info argument:
  * lower bits hold the Rt register number, higher bits are flags.
  */
@@ -5156,15 +5165,6 @@  static void gen_srs(DisasContext *s,
     s->base.is_jmp = DISAS_UPDATE_EXIT;
 }
 
-/* Generate a label used for skipping this instruction */
-static void arm_gen_condlabel(DisasContext *s)
-{
-    if (!s->condjmp) {
-        s->condlabel = gen_new_label();
-        s->condjmp = 1;
-    }
-}
-
 /* Skip this instruction if the ARM condition is false */
 static void arm_skip_unless(DisasContext *s, uint32_t cond)
 {
diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc
index f966de5b1f8..daf39306d04 100644
--- a/target/arm/translate-vfp.c.inc
+++ b/target/arm/translate-vfp.c.inc
@@ -3406,6 +3406,92 @@  static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a)
     return true;
 }
 
+static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a)
+{
+    int btmreg, topreg;
+    TCGv_i64 zero64;
+    TCGv_i32 zero32;
+    TCGv_i32 aspen, sfpa;
+
+    if (!dc_isar_feature(aa32_m_sec_state, s)) {
+        /* Before v8.1M, fall through in decode to NOCP check */
+        return false;
+    }
+
+    /* Explicitly UNDEF because this takes precedence over NOCP */
+    if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) {
+        unallocated_encoding(s);
+        return true;
+    }
+
+    if (!dc_isar_feature(aa32_vfp_simd, s)) {
+        /* NOP if we have neither FP nor MVE */
+        return true;
+    }
+
+    /*
+     * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no
+     * active floating point context so we must NOP (without doing
+     * any lazy state preservation or the NOCP check).
+     */
+    aspen = load_cpu_field(v7m.fpccr[M_REG_S]);
+    sfpa = load_cpu_field(v7m.control[M_REG_S]);
+    tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK);
+    tcg_gen_subi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK);
+    tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK);
+    tcg_gen_or_i32(sfpa, sfpa, aspen);
+    arm_gen_condlabel(s);
+    tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel);
+
+    if (s->fp_excp_el != 0) {
+        gen_exception_insn(s, s->pc_curr, EXCP_NOCP,
+                           syn_uncategorized(), s->fp_excp_el);
+        return true;
+    }
+
+    topreg = a->vd + a->imm - 1;
+    btmreg = a->vd;
+
+    /* Convert to Sreg numbers if the insn specified in Dregs */
+    if (a->size == 3) {
+        topreg = topreg * 2 + 1;
+        btmreg *= 2;
+    }
+
+    if (topreg > 63 || (topreg > 31 && !(topreg & 1))) {
+        /* UNPREDICTABLE: we choose to undef */
+        unallocated_encoding(s);
+        return true;
+    }
+
+    /* Silently ignore requests to clear D16-D31 if they don't exist */
+    if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) {
+        topreg = 31;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    /* Zero the Sregs from btmreg to topreg inclusive. */
+    zero64 = tcg_const_i64(0);
+    zero32 = tcg_const_i32(0);
+    if (btmreg & 1) {
+        write_neon_element32(zero32, btmreg >> 1, 1, MO_32);
+        btmreg++;
+    }
+    for (; btmreg + 1 <= topreg; btmreg += 2) {
+        write_neon_element64(zero64, btmreg >> 1, 0, MO_64);
+    }
+    if (btmreg == topreg) {
+        write_neon_element32(zero32, btmreg >> 1, 0, MO_32);
+        btmreg++;
+    }
+    assert(btmreg == topreg + 1);
+    /* TODO: when MVE is implemented, zero VPR here */
+    return true;
+}
+
 static bool trans_NOCP(DisasContext *s, arg_nocp *a)
 {
     /*