Merge remote-tracking branch 'remotes/rth/tags/pull-arm-20211102-2' into staging

Add nuvoton sd module for NPCM7XX
Add gdb-xml for MVE
More uses of tcg_constant_* in target/arm
Fix parameter naming for default-bus-bypass-iommu
Ignore cache operations to mmio in HVF

# gpg: Signature made Tue 02 Nov 2021 02:23:53 PM EDT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate]

* remotes/rth/tags/pull-arm-20211102-2:
  hvf: arm: Ignore cache operations on MMIO
  hw/arm/virt: Rename default_bus_bypass_iommu
  target/arm: Use tcg_constant_i32() in gen_rev16()
  target/arm: Use tcg_constant_i64() in do_sat_addsub_64()
  target/arm: Use the constant variant of store_cpu_field() when possible
  target/arm: Introduce store_cpu_field_constant() helper
  target/arm: Use tcg_constant_i32() in op_smlad()
  target/arm: Advertise MVE to gdb when present
  tests/qtest/libqos: add SDHCI commands
  hw/arm: Attach MMC to quanta-gbs-bmc
  hw/arm: Add Nuvoton SD module to board
  hw/sd: add nuvoton MMC

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

5 files changed, 51 insertions, 28 deletions

diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c
index e0dcb33e32..134da0d0ae 100644
--- a/target/arm/gdbstub.c
+++ b/target/arm/gdbstub.c
@@ -199,6 +199,27 @@ static int vfp_gdb_set_sysreg(CPUARMState *env, uint8_t *buf, int reg)
     return 0;
 }
 
+static int mve_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg)
+{
+    switch (reg) {
+    case 0:
+        return gdb_get_reg32(buf, env->v7m.vpr);
+    default:
+        return 0;
+    }
+}
+
+static int mve_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg)
+{
+    switch (reg) {
+    case 0:
+        env->v7m.vpr = ldl_p(buf);
+        return 4;
+    default:
+        return 0;
+    }
+}
+
 /**
  * arm_get/set_gdb_*: get/set a gdb register
  * @env: the CPU state
@@ -468,6 +489,10 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu)
                                      2, "arm-vfp-sysregs.xml", 0);
         }
     }
+    if (cpu_isar_feature(aa32_mve, cpu)) {
+        gdb_register_coprocessor(cs, mve_gdb_get_reg, mve_gdb_set_reg,
+                                 1, "arm-m-profile-mve.xml", 0);
+    }
     gdb_register_coprocessor(cs, arm_gdb_get_sysreg, arm_gdb_set_sysreg,
                              arm_gen_dynamic_sysreg_xml(cs, cs->gdb_num_regs),
                              "system-registers.xml", 0);
diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c
index bff3e0cde7..0dc96560d3 100644
--- a/target/arm/hvf/hvf.c
+++ b/target/arm/hvf/hvf.c
@@ -1150,12 +1150,19 @@ int hvf_vcpu_exec(CPUState *cpu)
         uint32_t sas = (syndrome >> 22) & 3;
         uint32_t len = 1 << sas;
         uint32_t srt = (syndrome >> 16) & 0x1f;
+        uint32_t cm = (syndrome >> 8) & 0x1;
         uint64_t val = 0;
 
         trace_hvf_data_abort(env->pc, hvf_exit->exception.virtual_address,
                              hvf_exit->exception.physical_address, isv,
                              iswrite, s1ptw, len, srt);
 
+        if (cm) {
+            /* We don't cache MMIO regions */
+            advance_pc = true;
+            break;
+        }
+
         assert(isv);
 
         if (iswrite) {
diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h
index 88f15df60e..17af8dc95a 100644
--- a/target/arm/translate-a32.h
+++ b/target/arm/translate-a32.h
@@ -70,6 +70,9 @@ static inline void store_cpu_offset(TCGv_i32 var, int offset)
 #define store_cpu_field(var, name) \
     store_cpu_offset(var, offsetof(CPUARMState, name))
 
+#define store_cpu_field_constant(val, name) \
+    tcg_gen_st_i32(tcg_constant_i32(val), cpu_env, offsetof(CPUARMState, name))
+
 /* Create a new temporary and set it to the value of a CPU register.  */
 static inline TCGv_i32 load_reg(DisasContext *s, int reg)
 {
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index bc91a64171..76b5fe9f31 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -1943,20 +1943,20 @@ static void do_sat_addsub_32(TCGv_i64 reg, TCGv_i64 val, bool u, bool d)
 static void do_sat_addsub_64(TCGv_i64 reg, TCGv_i64 val, bool u, bool d)
 {
     TCGv_i64 t0 = tcg_temp_new_i64();
-    TCGv_i64 t1 = tcg_temp_new_i64();
     TCGv_i64 t2;
 
     if (u) {
         if (d) {
             tcg_gen_sub_i64(t0, reg, val);
-            tcg_gen_movi_i64(t1, 0);
-            tcg_gen_movcond_i64(TCG_COND_LTU, reg, reg, val, t1, t0);
+            t2 = tcg_constant_i64(0);
+            tcg_gen_movcond_i64(TCG_COND_LTU, reg, reg, val, t2, t0);
         } else {
             tcg_gen_add_i64(t0, reg, val);
-            tcg_gen_movi_i64(t1, -1);
-            tcg_gen_movcond_i64(TCG_COND_LTU, reg, t0, reg, t1, t0);
+            t2 = tcg_constant_i64(-1);
+            tcg_gen_movcond_i64(TCG_COND_LTU, reg, t0, reg, t2, t0);
         }
     } else {
+        TCGv_i64 t1 = tcg_temp_new_i64();
         if (d) {
             /* Detect signed overflow for subtraction.  */
             tcg_gen_xor_i64(t0, reg, val);
@@ -1966,7 +1966,7 @@ static void do_sat_addsub_64(TCGv_i64 reg, TCGv_i64 val, bool u, bool d)
 
             /* Bound the result.  */
             tcg_gen_movi_i64(reg, INT64_MIN);
-            t2 = tcg_const_i64(0);
+            t2 = tcg_constant_i64(0);
             tcg_gen_movcond_i64(TCG_COND_LT, reg, t0, t2, reg, t1);
         } else {
             /* Detect signed overflow for addition.  */
@@ -1977,13 +1977,12 @@ static void do_sat_addsub_64(TCGv_i64 reg, TCGv_i64 val, bool u, bool d)
 
             /* Bound the result.  */
             tcg_gen_movi_i64(t1, INT64_MAX);
-            t2 = tcg_const_i64(0);
+            t2 = tcg_constant_i64(0);
             tcg_gen_movcond_i64(TCG_COND_LT, reg, t0, t2, t1, reg);
         }
-        tcg_temp_free_i64(t2);
+        tcg_temp_free_i64(t1);
     }
     tcg_temp_free_i64(t0);
-    tcg_temp_free_i64(t1);
 }
 
 /* Similarly with a vector and a scalar operand.  */
diff --git a/target/arm/translate.c b/target/arm/translate.c
index d6af5b1b03..98f5925928 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -364,8 +364,7 @@ void clear_eci_state(DisasContext *s)
      * multiple insn executes.
      */
     if (s->eci) {
-        TCGv_i32 tmp = tcg_const_i32(0);
-        store_cpu_field(tmp, condexec_bits);
+        store_cpu_field_constant(0, condexec_bits);
         s->eci = 0;
     }
 }
@@ -389,13 +388,12 @@ static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b)
 void gen_rev16(TCGv_i32 dest, TCGv_i32 var)
 {
     TCGv_i32 tmp = tcg_temp_new_i32();
-    TCGv_i32 mask = tcg_const_i32(0x00ff00ff);
+    TCGv_i32 mask = tcg_constant_i32(0x00ff00ff);
     tcg_gen_shri_i32(tmp, var, 8);
     tcg_gen_and_i32(tmp, tmp, mask);
     tcg_gen_and_i32(var, var, mask);
     tcg_gen_shli_i32(var, var, 8);
     tcg_gen_or_i32(dest, var, tmp);
-    tcg_temp_free_i32(mask);
     tcg_temp_free_i32(tmp);
 }
 
@@ -740,9 +738,8 @@ void gen_set_condexec(DisasContext *s)
 {
     if (s->condexec_mask) {
         uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1);
-        TCGv_i32 tmp = tcg_temp_new_i32();
-        tcg_gen_movi_i32(tmp, val);
-        store_cpu_field(tmp, condexec_bits);
+
+        store_cpu_field_constant(val, condexec_bits);
     }
 }
 
@@ -7849,10 +7846,9 @@ static bool op_smlad(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub)
         t3 = tcg_temp_new_i32();
         tcg_gen_sari_i32(t3, t1, 31);
         qf = load_cpu_field(QF);
-        one = tcg_const_i32(1);
+        one = tcg_constant_i32(1);
         tcg_gen_movcond_i32(TCG_COND_NE, qf, t2, t3, one, qf);
         store_cpu_field(qf, QF);
-        tcg_temp_free_i32(one);
         tcg_temp_free_i32(t3);
         tcg_temp_free_i32(t2);
     }
@@ -8363,8 +8359,6 @@ static bool trans_BL(DisasContext *s, arg_i *a)
 
 static bool trans_BLX_i(DisasContext *s, arg_BLX_i *a)
 {
-    TCGv_i32 tmp;
-
     /*
      * BLX <imm> would be useless on M-profile; the encoding space
      * is used for other insns from v8.1M onward, and UNDEFs before that.
@@ -8378,8 +8372,7 @@ static bool trans_BLX_i(DisasContext *s, arg_BLX_i *a)
         return false;
     }
     tcg_gen_movi_i32(cpu_R[14], s->base.pc_next | s->thumb);
-    tmp = tcg_const_i32(!s->thumb);
-    store_cpu_field(tmp, thumb);
+    store_cpu_field_constant(!s->thumb, thumb);
     gen_jmp(s, (read_pc(s) & ~3) + a->imm);
     return true;
 }
@@ -8678,7 +8671,6 @@ static bool trans_LCTP(DisasContext *s, arg_LCTP *a)
      * doesn't cache branch information, all we need to do is reset
      * FPSCR.LTPSIZE to 4.
      */
-    TCGv_i32 ltpsize;
 
     if (!dc_isar_feature(aa32_lob, s) ||
         !dc_isar_feature(aa32_mve, s)) {
@@ -8689,8 +8681,7 @@ static bool trans_LCTP(DisasContext *s, arg_LCTP *a)
         return true;
     }
 
-    ltpsize = tcg_const_i32(4);
-    store_cpu_field(ltpsize, v7m.ltpsize);
+    store_cpu_field_constant(4, v7m.ltpsize);
     return true;
 }
 
@@ -9488,9 +9479,7 @@ static void arm_tr_tb_start(DisasContextBase *dcbase, CPUState *cpu)
     /* Reset the conditional execution bits immediately. This avoids
        complications trying to do it at the end of the block.  */
     if (dc->condexec_mask || dc->condexec_cond) {
-        TCGv_i32 tmp = tcg_temp_new_i32();
-        tcg_gen_movi_i32(tmp, 0);
-        store_cpu_field(tmp, condexec_bits);
+        store_cpu_field_constant(0, condexec_bits);
     }
 }