Merge remote-tracking branch 'remotes/rth-gitlab/tags/pull-tcg-20210629' into staging

TranslatorOps conversion for target/avr
TranslatorOps conversion for target/cris
TranslatorOps conversion for target/nios2
Simple vector operations on TCGv_i32
Host signal fixes for *BSD
Improvements to tcg bswap operations

# gpg: Signature made Tue 29 Jun 2021 19:51:03 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth-gitlab/tags/pull-tcg-20210629: (63 commits)
  tcg/riscv: Remove MO_BSWAP handling
  tcg/aarch64: Unset TCG_TARGET_HAS_MEMORY_BSWAP
  tcg/arm: Unset TCG_TARGET_HAS_MEMORY_BSWAP
  target/mips: Fix gen_mxu_s32ldd_s32lddr
  target/sh4: Improve swap.b translation
  target/i386: Improve bswap translation
  target/arm: Improve REVSH
  target/arm: Improve vector REV
  target/arm: Improve REV32
  tcg: Make use of bswap flags in tcg_gen_qemu_st_*
  tcg: Make use of bswap flags in tcg_gen_qemu_ld_*
  tcg: Add flags argument to tcg_gen_bswap16_*, tcg_gen_bswap32_i64
  tcg: Handle new bswap flags during optimize
  tcg/tci: Support bswap flags
  tcg/mips: Support bswap flags in tcg_out_bswap32
  tcg/mips: Support bswap flags in tcg_out_bswap16
  tcg/s390: Support bswap flags
  tcg/ppc: Use power10 byte-reverse instructions
  tcg/ppc: Support bswap flags
  tcg/ppc: Split out tcg_out_bswap64
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 64 insertions, 9 deletions

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index c69a7de984..da55fed870 100644
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -401,4 +401,47 @@ void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t);
 void tcg_gen_vec_rotl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c);
 void tcg_gen_vec_rotl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c);
 
+/* 32-bit vector operations. */
+void tcg_gen_vec_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
+void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
+
+void tcg_gen_vec_sub8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
+void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
+
+void tcg_gen_vec_shl8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t);
+void tcg_gen_vec_shl16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t);
+void tcg_gen_vec_shr8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t);
+void tcg_gen_vec_shr16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t);
+void tcg_gen_vec_sar8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t);
+void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t);
+
+#if TARGET_LONG_BITS == 64
+#define tcg_gen_vec_add8_tl  tcg_gen_vec_add8_i64
+#define tcg_gen_vec_sub8_tl  tcg_gen_vec_sub8_i64
+#define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i64
+#define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i64
+#define tcg_gen_vec_add32_tl tcg_gen_vec_add32_i64
+#define tcg_gen_vec_sub32_tl tcg_gen_vec_sub32_i64
+#define tcg_gen_vec_shl8i_tl tcg_gen_vec_shl8i_i64
+#define tcg_gen_vec_shr8i_tl tcg_gen_vec_shr8i_i64
+#define tcg_gen_vec_sar8i_tl tcg_gen_vec_sar8i_i64
+#define tcg_gen_vec_shl16i_tl tcg_gen_vec_shl16i_i64
+#define tcg_gen_vec_shr16i_tl tcg_gen_vec_shr16i_i64
+#define tcg_gen_vec_sar16i_tl tcg_gen_vec_sar16i_i64
+
+#else
+#define tcg_gen_vec_add8_tl  tcg_gen_vec_add8_i32
+#define tcg_gen_vec_sub8_tl  tcg_gen_vec_sub8_i32
+#define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i32
+#define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i32
+#define tcg_gen_vec_add32_tl tcg_gen_add_i32
+#define tcg_gen_vec_sub32_tl tcg_gen_sub_i32
+#define tcg_gen_vec_shl8i_tl tcg_gen_vec_shl8i_i32
+#define tcg_gen_vec_shr8i_tl tcg_gen_vec_shr8i_i32
+#define tcg_gen_vec_sar8i_tl tcg_gen_vec_sar8i_i32
+#define tcg_gen_vec_shl16i_tl tcg_gen_vec_shl16i_i32
+#define tcg_gen_vec_shr16i_tl tcg_gen_vec_shr16i_i32
+#define tcg_gen_vec_sar16i_tl tcg_gen_vec_sar16i_i32
+#endif
+
 #endif
diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h
index 1a2ae93758..2a654f350c 100644
--- a/include/tcg/tcg-op.h
+++ b/include/tcg/tcg-op.h
@@ -330,7 +330,7 @@ void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg);
-void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags);
 void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
@@ -528,8 +528,8 @@ void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg);
-void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg);
-void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
+void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
 void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
@@ -1192,7 +1192,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t);
 #define tcg_gen_ext32u_tl tcg_gen_mov_i32
 #define tcg_gen_ext32s_tl tcg_gen_mov_i32
 #define tcg_gen_bswap16_tl tcg_gen_bswap16_i32
-#define tcg_gen_bswap32_tl tcg_gen_bswap32_i32
+#define tcg_gen_bswap32_tl(D, S, F) tcg_gen_bswap32_i32(D, S)
 #define tcg_gen_bswap_tl tcg_gen_bswap32_i32
 #define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64
 #define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32
diff --git a/include/tcg/tcg-opc.h b/include/tcg/tcg-opc.h
index 5bbec858aa..993992373e 100644
--- a/include/tcg/tcg-opc.h
+++ b/include/tcg/tcg-opc.h
@@ -96,8 +96,8 @@ DEF(ext8s_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext8s_i32))
 DEF(ext16s_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext16s_i32))
 DEF(ext8u_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext8u_i32))
 DEF(ext16u_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext16u_i32))
-DEF(bswap16_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_bswap16_i32))
-DEF(bswap32_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_bswap32_i32))
+DEF(bswap16_i32, 1, 1, 1, IMPL(TCG_TARGET_HAS_bswap16_i32))
+DEF(bswap32_i32, 1, 1, 1, IMPL(TCG_TARGET_HAS_bswap32_i32))
 DEF(not_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_not_i32))
 DEF(neg_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_neg_i32))
 DEF(andc_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_andc_i32))
@@ -165,9 +165,9 @@ DEF(ext32s_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext32s_i64))
 DEF(ext8u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext8u_i64))
 DEF(ext16u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext16u_i64))
 DEF(ext32u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext32u_i64))
-DEF(bswap16_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap16_i64))
-DEF(bswap32_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap32_i64))
-DEF(bswap64_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap64_i64))
+DEF(bswap16_i64, 1, 1, 1, IMPL64 | IMPL(TCG_TARGET_HAS_bswap16_i64))
+DEF(bswap32_i64, 1, 1, 1, IMPL64 | IMPL(TCG_TARGET_HAS_bswap32_i64))
+DEF(bswap64_i64, 1, 1, 1, IMPL64 | IMPL(TCG_TARGET_HAS_bswap64_i64))
 DEF(not_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_not_i64))
 DEF(neg_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_neg_i64))
 DEF(andc_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_andc_i64))
diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h
index 2dad364240..899493701c 100644
--- a/include/tcg/tcg.h
+++ b/include/tcg/tcg.h
@@ -408,6 +408,18 @@ typedef TCGv_ptr TCGv_env;
 /* Used to align parameters.  See the comment before tcgv_i32_temp.  */
 #define TCG_CALL_DUMMY_ARG      ((TCGArg)0)
 
+/*
+ * Flags for the bswap opcodes.
+ * If IZ, the input is zero-extended, otherwise unknown.
+ * If OZ or OS, the output is zero- or sign-extended respectively,
+ * otherwise the high bits are undefined.
+ */
+enum {
+    TCG_BSWAP_IZ = 1,
+    TCG_BSWAP_OZ = 2,
+    TCG_BSWAP_OS = 4,
+};
+
 typedef enum TCGTempVal {
     TEMP_VAL_DEAD,
     TEMP_VAL_REG,