target/mips: Implement emulation of nanoMIPS ROTX instruction

Added a helper for ROTX based on the pseudocode from the
architecture spec. This instraction was not present in previous
MIPS instruction sets.

Backports commit e222f5067269392af489731221750976d0cf3c05 from qemu

qemu/header_gen.py

@@ -5039,6 +5039,7 @@ mips_symbols = (
     'helper_rdhwr_performance',
     'helper_rdhwr_synci_step',
     'helper_rdhwr_xnp',
+    'helper_rotx',
     'helper_sc',
     'helper_scd',
     'helper_sdl',

qemu/mips.h

@@ -4129,6 +4129,7 @@
 #define helper_rdhwr_performance helper_rdhwr_performance_mips
 #define helper_rdhwr_synci_step helper_rdhwr_synci_step_mips
 #define helper_rdhwr_xnp helper_rdhwr_xnp_mips
+#define helper_rotx helper_rotx_mips
 #define helper_sc helper_sc_mips
 #define helper_scd helper_scd_mips
 #define helper_sdl helper_sdl_mips

qemu/mips64.h

@@ -4129,6 +4129,7 @@
 #define helper_rdhwr_performance helper_rdhwr_performance_mips64
 #define helper_rdhwr_synci_step helper_rdhwr_synci_step_mips64
 #define helper_rdhwr_xnp helper_rdhwr_xnp_mips64
+#define helper_rotx helper_rotx_mips64
 #define helper_sc helper_sc_mips64
 #define helper_scd helper_scd_mips64
 #define helper_sdl helper_sdl_mips64

qemu/mips64el.h

@@ -4129,6 +4129,7 @@
 #define helper_rdhwr_performance helper_rdhwr_performance_mips64el
 #define helper_rdhwr_synci_step helper_rdhwr_synci_step_mips64el
 #define helper_rdhwr_xnp helper_rdhwr_xnp_mips64el
+#define helper_rotx helper_rotx_mips64el
 #define helper_sc helper_sc_mips64el
 #define helper_scd helper_scd_mips64el
 #define helper_sdl helper_sdl_mips64el

qemu/mipsel.h

@@ -4129,6 +4129,7 @@
 #define helper_rdhwr_performance helper_rdhwr_performance_mipsel
 #define helper_rdhwr_synci_step helper_rdhwr_synci_step_mipsel
 #define helper_rdhwr_xnp helper_rdhwr_xnp_mipsel
+#define helper_rotx helper_rotx_mipsel
 #define helper_sc helper_sc_mipsel
 #define helper_scd helper_scd_mipsel
 #define helper_sdl helper_sdl_mipsel

qemu/target/mips/helper.h

@@ -40,6 +40,8 @@ DEF_HELPER_FLAGS_1(bitswap, TCG_CALL_NO_RWG_SE, tl, tl)
 DEF_HELPER_FLAGS_1(dbitswap, TCG_CALL_NO_RWG_SE, tl, tl)
 #endif
 
+DEF_HELPER_FLAGS_4(rotx, TCG_CALL_NO_RWG_SE, tl, tl, i32, i32, i32)
+
 #ifndef CONFIG_USER_ONLY
 /* CP0 helpers */
 DEF_HELPER_1(mfc0_mvpcontrol, tl, env)

qemu/target/mips/op_helper.c

@@ -247,6 +247,100 @@ target_ulong helper_bitswap(target_ulong rt)
     return (int32_t)bitswap(rt);
 }
 
+target_ulong helper_rotx(target_ulong rs, uint32_t shift, uint32_t shiftx,
+                        uint32_t stripe)
+{
+    int i;
+    uint64_t tmp0 = ((uint64_t)rs) << 32 | ((uint64_t)rs & 0xffffffff);
+    uint64_t tmp1 = tmp0;
+    for (i = 0; i <= 46; i++) {
+        int s;
+        if (i & 0x8) {
+            s = shift;
+        } else {
+            s = shiftx;
+        }
+
+        if (stripe != 0 && !(i & 0x4)) {
+            s = ~s;
+        }
+        if (s & 0x10) {
+            if (tmp0 & (1LL << (i + 16))) {
+                tmp1 |= 1LL << i;
+            } else {
+                tmp1 &= ~(1LL << i);
+            }
+        }
+    }
+
+    uint64_t tmp2 = tmp1;
+    for (i = 0; i <= 38; i++) {
+        int s;
+        if (i & 0x4) {
+            s = shift;
+        } else {
+            s = shiftx;
+        }
+
+        if (s & 0x8) {
+            if (tmp1 & (1LL << (i + 8))) {
+                tmp2 |= 1LL << i;
+            } else {
+                tmp2 &= ~(1LL << i);
+            }
+        }
+    }
+
+    uint64_t tmp3 = tmp2;
+    for (i = 0; i <= 34; i++) {
+        int s;
+        if (i & 0x2) {
+            s = shift;
+        } else {
+            s = shiftx;
+        }
+        if (s & 0x4) {
+            if (tmp2 & (1LL << (i + 4))) {
+                tmp3 |= 1LL << i;
+            } else {
+                tmp3 &= ~(1LL << i);
+            }
+        }
+    }
+
+    uint64_t tmp4 = tmp3;
+    for (i = 0; i <= 32; i++) {
+        int s;
+        if (i & 0x1) {
+            s = shift;
+        } else {
+            s = shiftx;
+        }
+        if (s & 0x2) {
+            if (tmp3 & (1LL << (i + 2))) {
+                tmp4 |= 1LL << i;
+            } else {
+                tmp4 &= ~(1LL << i);
+            }
+        }
+    }
+
+    uint64_t tmp5 = tmp4;
+    for (i = 0; i <= 31; i++) {
+        int s;
+        s = shift;
+        if (s & 0x1) {
+            if (tmp4 & (1LL << (i + 1))) {
+                tmp5 |= 1LL << i;
+            } else {
+                tmp5 &= ~(1LL << i);
+            }
+        }
+    }
+
+    return (int64_t)(int32_t)(uint32_t)tmp5;
+}
+
 #ifndef CONFIG_USER_ONLY
 
 static inline hwaddr do_translate_address(CPUMIPSState *env,

qemu/target/mips/translate.c

@@ -17933,6 +17933,21 @@ static int decode_nanomips_32_48_opc(CPUMIPSState *env, DisasContext *ctx)
             }
             break;
         case NM_P_ROTX:
+            if (rt != 0) {
+                TCGv t0 = tcg_temp_new(tcg_ctx);
+                TCGv_i32 shift = tcg_const_i32(tcg_ctx, extract32(ctx->opcode, 0, 5));
+                TCGv_i32 shiftx = tcg_const_i32(tcg_ctx, extract32(ctx->opcode, 7, 4)
+                                                << 1);
+                TCGv_i32 stripe = tcg_const_i32(tcg_ctx, extract32(ctx->opcode, 6, 1));
+
+                gen_load_gpr(ctx, t0, rs);
+                gen_helper_rotx(tcg_ctx, tcg_ctx->cpu_gpr[rt], t0, shift, shiftx, stripe);
+                tcg_temp_free(tcg_ctx, t0);
+
+                tcg_temp_free_i32(tcg_ctx, shift);
+                tcg_temp_free_i32(tcg_ctx, shiftx);
+                tcg_temp_free_i32(tcg_ctx, stripe);
+            }
             break;
         case NM_P_INS:
             switch (((ctx->opcode >> 10) & 2) |