[Qemu-arm] [PATCH v2 11/26] target/arm: Implement ADDG, SUBG instructions

[Richard Henderson]

Reviewed-by: Peter Maydell <address@hidden>
Signed-off-by: Richard Henderson <address@hidden>
---
v2: Shift offset in translate; use extract32.
---
 target/arm/helper-a64.h    |  2 ++
 target/arm/internals.h     |  3 ++
 target/arm/mte_helper.c    | 32 +++++++++++++++++
 target/arm/translate-a64.c | 71 ++++++++++++++++++++++++++------------
 4 files changed, 85 insertions(+), 23 deletions(-)

diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h
index 7a6051fdab..47577207b2 100644
--- a/target/arm/helper-a64.h
+++ b/target/arm/helper-a64.h
@@ -105,3 +105,5 @@ DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64)
 
 DEF_HELPER_FLAGS_2(mte_check, TCG_CALL_NO_WG, i64, env, i64)
 DEF_HELPER_FLAGS_3(irg, TCG_CALL_NO_RWG, i64, env, i64, i64)
+DEF_HELPER_FLAGS_4(addg, TCG_CALL_NO_RWG_SE, i64, env, i64, i32, i32)
+DEF_HELPER_FLAGS_4(subg, TCG_CALL_NO_RWG_SE, i64, env, i64, i32, i32)
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 2922324f63..a5a249b001 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -1002,4 +1002,7 @@ static inline bool 
allocation_tag_access_enabled(CPUARMState *env, int el,
     return sctlr != 0;
 }
 
+/* We associate one allocation tag per 16 bytes, the minimum.  */
+#define LOG2_TAG_GRANULE 4
+
 #endif
diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c
index 493c2f7bb2..3eb5d622fc 100644
--- a/target/arm/mte_helper.c
+++ b/target/arm/mte_helper.c
@@ -202,3 +202,35 @@ uint64_t HELPER(irg)(CPUARMState *env, uint64_t rn, 
uint64_t rm)
 
     return address_with_allocation_tag(rn, rtag);
 }
+
+uint64_t HELPER(addg)(CPUARMState *env, uint64_t ptr,
+                      uint32_t offset, uint32_t tag_offset)
+{
+    int el = arm_current_el(env);
+    uint64_t sctlr = arm_sctlr(env, el);
+    int rtag = 0;
+
+    if (allocation_tag_access_enabled(env, el, sctlr)) {
+        int start_tag = allocation_tag_from_addr(ptr);
+        uint16_t exclude = extract32(env->cp15.gcr_el1, 0, 16);
+        rtag = choose_nonexcluded_tag(start_tag, tag_offset, exclude);
+    }
+
+    return address_with_allocation_tag(ptr + offset, rtag);
+}
+
+uint64_t HELPER(subg)(CPUARMState *env, uint64_t ptr,
+                      uint32_t offset, uint32_t tag_offset)
+{
+    int el = arm_current_el(env);
+    uint64_t sctlr = arm_sctlr(env, el);
+    int rtag = 0;
+
+    if (allocation_tag_access_enabled(env, el, sctlr)) {
+        int start_tag = allocation_tag_from_addr(ptr);
+        uint16_t exclude = extract32(env->cp15.gcr_el1, 0, 16);
+        rtag = choose_nonexcluded_tag(start_tag, tag_offset, exclude);
+    }
+
+    return address_with_allocation_tag(ptr - offset, rtag);
+}
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 5e7d7f2d5e..3d71a9701f 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -3672,7 +3672,9 @@ static void disas_pc_rel_adr(DisasContext *s, uint32_t 
insn)
  *    sf: 0 -> 32bit, 1 -> 64bit
  *    op: 0 -> add  , 1 -> sub
  *     S: 1 -> set flags
- * shift: 00 -> LSL imm by 0, 01 -> LSL imm by 12
+ * shift: 00 -> LSL imm by 0,
+ *        01 -> LSL imm by 12
+ *        10 -> ADDG, SUBG
  */
 static void disas_add_sub_imm(DisasContext *s, uint32_t insn)
 {
@@ -3683,10 +3685,10 @@ static void disas_add_sub_imm(DisasContext *s, uint32_t 
insn)
     bool setflags = extract32(insn, 29, 1);
     bool sub_op = extract32(insn, 30, 1);
     bool is_64bit = extract32(insn, 31, 1);
+    bool is_tag = false;
 
     TCGv_i64 tcg_rn = cpu_reg_sp(s, rn);
     TCGv_i64 tcg_rd = setflags ? cpu_reg(s, rd) : cpu_reg_sp(s, rd);
-    TCGv_i64 tcg_result;
 
     switch (shift) {
     case 0x0:
@@ -3694,35 +3696,58 @@ static void disas_add_sub_imm(DisasContext *s, uint32_t 
insn)
     case 0x1:
         imm <<= 12;
         break;
+    case 0x2:
+        /* ADDG, SUBG */
+        if (!is_64bit || setflags || (imm & 0x30) ||
+            !dc_isar_feature(aa64_mte_insn_reg, s)) {
+            goto do_unallocated;
+        }
+        is_tag = true;
+        break;
     default:
+    do_unallocated:
         unallocated_encoding(s);
         return;
     }
 
-    tcg_result = tcg_temp_new_i64();
-    if (!setflags) {
-        if (sub_op) {
-            tcg_gen_subi_i64(tcg_result, tcg_rn, imm);
-        } else {
-            tcg_gen_addi_i64(tcg_result, tcg_rn, imm);
-        }
-    } else {
-        TCGv_i64 tcg_imm = tcg_const_i64(imm);
-        if (sub_op) {
-            gen_sub_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
-        } else {
-            gen_add_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
-        }
-        tcg_temp_free_i64(tcg_imm);
-    }
+    if (is_tag) {
+        TCGv_i32 tag_offset = tcg_const_i32(imm & 15);
+        TCGv_i32 offset = tcg_const_i32((imm >> 6) << LOG2_TAG_GRANULE);
 
-    if (is_64bit) {
-        tcg_gen_mov_i64(tcg_rd, tcg_result);
+        if (sub_op) {
+            gen_helper_subg(tcg_rd, cpu_env, tcg_rn, offset, tag_offset);
+        } else {
+            gen_helper_addg(tcg_rd, cpu_env, tcg_rn, offset, tag_offset);
+        }
+        tcg_temp_free_i32(tag_offset);
+        tcg_temp_free_i32(offset);
     } else {
-        tcg_gen_ext32u_i64(tcg_rd, tcg_result);
-    }
+        TCGv_i64 tcg_result;
 
-    tcg_temp_free_i64(tcg_result);
+        if (!setflags) {
+            tcg_result = tcg_rd;
+            if (sub_op) {
+                tcg_gen_subi_i64(tcg_result, tcg_rn, imm);
+            } else {
+                tcg_gen_addi_i64(tcg_result, tcg_rn, imm);
+            }
+        } else {
+            TCGv_i64 tcg_imm = tcg_const_i64(imm);
+            tcg_result = new_tmp_a64(s);
+            if (sub_op) {
+                gen_sub_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
+            } else {
+                gen_add_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
+            }
+            tcg_temp_free_i64(tcg_imm);
+        }
+
+        if (is_64bit) {
+            tcg_gen_mov_i64(tcg_rd, tcg_result);
+        } else {
+            tcg_gen_ext32u_i64(tcg_rd, tcg_result);
+        }
+    }
 }
 
 /* The input should be a value in the bottom e bits (with higher
-- 
2.17.2