Merge tag 'pull-target-arm-20240919' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * target/arm: Correct ID_AA64ISAR1_EL1 value for neoverse-v1
 * target/arm: More conversions to decodetree of A64 SIMD insns
 * hw/char/stm32l4x5_usart.c: Enable USART ACK bit response
 * tests: update aarch64/sbsa-ref tests
 * kvm: minor Coverity nit fixes
 * docs/devel: Remove nested-papr.txt

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmbsIloZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3k96EACgUaTSEX1BNee0Xsk8wIHb
# KebGryNymj7LPpWdRxiyQYmZbjfelZPJW7F2tr3iGfiphz+N5TIdRDQlPrRePNg4
# 5Ure0ShRgn+RlkjFe8r9yjrr3HEAXLnVb5fgzPqGEQ+UXWRVzr72+q+wrGFVuXtn
# zfqxpc6F0TCxeyH88X6mpKkTeEjfuE++TIf885VVX6nB8qkkDUifRLjdrDcJoxp3
# BRrE0Ntob2W0NAHm/QTbATLDErsYXIzm6pX2hWy3DNEQrVHw2rJ1FAzsjt2J/8ZU
# PC7hwmkPBsrnq5wcpBtOwloHzrIYuwUBI7ABPGctCPziCSw7N55vkgUmGWZ+nYHc
# DwYGu3H84su0hBi/E9gxl8z/ATBvuAIVa1RLHvbYiwdd088DqxdBe1YLLRaZeKzP
# oldQBzVegaN1n5n8tHO43b/38V7uknu3fDXGw/OrsO5DouDAj9NoRil1caRx4ZYd
# dr4IiWKzmlW8wpWgoBnrRbycuNsi6b9HblOX1umjwubCGO+GFesBRAInUeg9gbuv
# xolfYOScUE/nkTaqulAiPGqGZV8P0fqVMbXmXuowm7iIdw3JihEUm+mU18CTPFBd
# P/6SH47lXTaQA0JJQmD4LKraZQFYzm5rlSvW/15/mnzutZXMUlWzvxK/E5fX3vhL
# VUguR6XO8Cjb0cQJWohB1w==
# =JklH
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 19 Sep 2024 14:08:42 BST
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# gpg:                 aka "Peter Maydell <peter@archaic.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* tag 'pull-target-arm-20240919' of https://git.linaro.org/people/pmaydell/qemu-arm: (38 commits)
  docs/devel: Remove nested-papr.txt
  target/arm: Correct ID_AA64ISAR1_EL1 value for neoverse-v1
  kvm: Remove unreachable code in kvm_dirty_ring_reaper_thread()
  kvm: Make 'mmap_size' be 'int' in kvm_init_vcpu(), do_kvm_destroy_vcpu()
  tests: drop OpenBSD tests for aarch64/sbsa-ref
  tests: expand timeout information for aarch64/sbsa-ref
  tests: add FreeBSD tests for aarch64/sbsa-ref
  tests: use default cpu for aarch64/sbsa-ref
  hw/char/stm32l4x5_usart.c: Enable USART ACK bit response
  target/arm: Convert scalar [US]QSHRN, [US]QRSHRN, SQSHRUN to decodetree
  target/arm: Convert vector [US]QSHRN, [US]QRSHRN, SQSHRUN to decodetree
  target/arm: Convert SQSHL, UQSHL, SQSHLU (immediate) to decodetree
  target/arm: Widen NeonGenNarrowEnvFn return to 64 bits
  target/arm: Convert VQSHL, VQSHLU to gvec
  target/arm: Convert handle_scalar_simd_shli to decodetree
  target/arm: Convert handle_scalar_simd_shri to decodetree
  target/arm: Convert SHRN, RSHRN to decodetree
  target/arm: Split out subroutines of handle_shri_with_rndacc
  target/arm: Push tcg_rnd into handle_shri_with_rndacc
  target/arm: Convert SSHLL, USHLL to decodetree
  ...

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

1 files changed, 83 insertions, 38 deletions

diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index 56a1dc1f75..f652520b65 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -88,6 +88,25 @@ GEN_CMP0(gen_gvec_cgt0, TCG_COND_GT)
 
 #undef GEN_CMP0
 
+void gen_gvec_sshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+                   int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+    /* Signed shift out of range results in all-sign-bits */
+    shift = MIN(shift, (8 << vece) - 1);
+    tcg_gen_gvec_sari(vece, rd_ofs, rm_ofs, shift, opr_sz, max_sz);
+}
+
+void gen_gvec_ushr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
+                   int64_t shift, uint32_t opr_sz, uint32_t max_sz)
+{
+    /* Unsigned shift out of range results in all-zero-bits */
+    if (shift >= (8 << vece)) {
+        tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0);
+    } else {
+        tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift, opr_sz, max_sz);
+    }
+}
+
 static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
 {
     tcg_gen_vec_sar8i_i64(a, a, shift);
@@ -285,7 +304,7 @@ void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
     tcg_gen_add_i32(d, d, t);
 }
 
- void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
+void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
 {
     TCGv_i64 t = tcg_temp_new_i64();
 
@@ -297,10 +316,9 @@ void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
 static void gen_srshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
 {
     TCGv_vec t = tcg_temp_new_vec_matching(d);
-    TCGv_vec ones = tcg_temp_new_vec_matching(d);
+    TCGv_vec ones = tcg_constant_vec_matching(d, vece, 1);
 
     tcg_gen_shri_vec(vece, t, a, sh - 1);
-    tcg_gen_dupi_vec(vece, ones, 1);
     tcg_gen_and_vec(vece, t, t, ones);
     tcg_gen_sari_vec(vece, d, a, sh);
     tcg_gen_add_vec(vece, d, d, t);
@@ -492,10 +510,9 @@ void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
 static void gen_urshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t shift)
 {
     TCGv_vec t = tcg_temp_new_vec_matching(d);
-    TCGv_vec ones = tcg_temp_new_vec_matching(d);
+    TCGv_vec ones = tcg_constant_vec_matching(d, vece, 1);
 
     tcg_gen_shri_vec(vece, t, a, shift - 1);
-    tcg_gen_dupi_vec(vece, ones, 1);
     tcg_gen_and_vec(vece, t, t, ones);
     tcg_gen_shri_vec(vece, d, a, shift);
     tcg_gen_add_vec(vece, d, d, t);
@@ -685,9 +702,9 @@ static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
 static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
 {
     TCGv_vec t = tcg_temp_new_vec_matching(d);
-    TCGv_vec m = tcg_temp_new_vec_matching(d);
+    int64_t mi = MAKE_64BIT_MASK((8 << vece) - sh, sh);
+    TCGv_vec m = tcg_constant_vec_matching(d, vece, mi);
 
-    tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh));
     tcg_gen_shri_vec(vece, t, a, sh);
     tcg_gen_and_vec(vece, d, d, m);
     tcg_gen_or_vec(vece, d, d, t);
@@ -773,10 +790,9 @@ static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift)
 static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh)
 {
     TCGv_vec t = tcg_temp_new_vec_matching(d);
-    TCGv_vec m = tcg_temp_new_vec_matching(d);
+    TCGv_vec m = tcg_constant_vec_matching(d, vece, MAKE_64BIT_MASK(0, sh));
 
     tcg_gen_shli_vec(vece, t, a, sh);
-    tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh));
     tcg_gen_and_vec(vece, d, d, m);
     tcg_gen_or_vec(vece, d, d, t);
 }
@@ -1044,14 +1060,13 @@ static void gen_ushl_vec(unsigned vece, TCGv_vec dst,
     TCGv_vec rval = tcg_temp_new_vec_matching(dst);
     TCGv_vec lsh = tcg_temp_new_vec_matching(dst);
     TCGv_vec rsh = tcg_temp_new_vec_matching(dst);
-    TCGv_vec msk, max;
+    TCGv_vec max, zero;
 
     tcg_gen_neg_vec(vece, rsh, shift);
     if (vece == MO_8) {
         tcg_gen_mov_vec(lsh, shift);
     } else {
-        msk = tcg_temp_new_vec_matching(dst);
-        tcg_gen_dupi_vec(vece, msk, 0xff);
+        TCGv_vec msk = tcg_constant_vec_matching(dst, vece, 0xff);
         tcg_gen_and_vec(vece, lsh, shift, msk);
         tcg_gen_and_vec(vece, rsh, rsh, msk);
     }
@@ -1064,26 +1079,21 @@ static void gen_ushl_vec(unsigned vece, TCGv_vec dst,
     tcg_gen_shlv_vec(vece, lval, src, lsh);
     tcg_gen_shrv_vec(vece, rval, src, rsh);
 
-    max = tcg_temp_new_vec_matching(dst);
-    tcg_gen_dupi_vec(vece, max, 8 << vece);
-
     /*
-     * The choice of LT (signed) and GEU (unsigned) are biased toward
+     * The choice of GE (signed) and GEU (unsigned) are biased toward
      * the instructions of the x86_64 host.  For MO_8, the whole byte
      * is significant so we must use an unsigned compare; otherwise we
      * have already masked to a byte and so a signed compare works.
      * Other tcg hosts have a full set of comparisons and do not care.
      */
+    zero = tcg_constant_vec_matching(dst, vece, 0);
+    max = tcg_constant_vec_matching(dst, vece, 8 << vece);
     if (vece == MO_8) {
-        tcg_gen_cmp_vec(TCG_COND_GEU, vece, lsh, lsh, max);
-        tcg_gen_cmp_vec(TCG_COND_GEU, vece, rsh, rsh, max);
-        tcg_gen_andc_vec(vece, lval, lval, lsh);
-        tcg_gen_andc_vec(vece, rval, rval, rsh);
+        tcg_gen_cmpsel_vec(TCG_COND_GEU, vece, lval, lsh, max, zero, lval);
+        tcg_gen_cmpsel_vec(TCG_COND_GEU, vece, rval, rsh, max, zero, rval);
     } else {
-        tcg_gen_cmp_vec(TCG_COND_LT, vece, lsh, lsh, max);
-        tcg_gen_cmp_vec(TCG_COND_LT, vece, rsh, rsh, max);
-        tcg_gen_and_vec(vece, lval, lval, lsh);
-        tcg_gen_and_vec(vece, rval, rval, rsh);
+        tcg_gen_cmpsel_vec(TCG_COND_GE, vece, lval, lsh, max, zero, lval);
+        tcg_gen_cmpsel_vec(TCG_COND_GE, vece, rval, rsh, max, zero, rval);
     }
     tcg_gen_or_vec(vece, dst, lval, rval);
 }
@@ -1093,7 +1103,7 @@ void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
 {
     static const TCGOpcode vecop_list[] = {
         INDEX_op_neg_vec, INDEX_op_shlv_vec,
-        INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0
+        INDEX_op_shrv_vec, INDEX_op_cmpsel_vec, 0
     };
     static const GVecGen3 ops[4] = {
         { .fniv = gen_ushl_vec,
@@ -1169,7 +1179,7 @@ static void gen_sshl_vec(unsigned vece, TCGv_vec dst,
     TCGv_vec rval = tcg_temp_new_vec_matching(dst);
     TCGv_vec lsh = tcg_temp_new_vec_matching(dst);
     TCGv_vec rsh = tcg_temp_new_vec_matching(dst);
-    TCGv_vec tmp = tcg_temp_new_vec_matching(dst);
+    TCGv_vec max, zero;
 
     /*
      * Rely on the TCG guarantee that out of range shifts produce
@@ -1180,29 +1190,28 @@ static void gen_sshl_vec(unsigned vece, TCGv_vec dst,
     if (vece == MO_8) {
         tcg_gen_mov_vec(lsh, shift);
     } else {
-        tcg_gen_dupi_vec(vece, tmp, 0xff);
-        tcg_gen_and_vec(vece, lsh, shift, tmp);
-        tcg_gen_and_vec(vece, rsh, rsh, tmp);
+        TCGv_vec msk = tcg_constant_vec_matching(dst, vece, 0xff);
+        tcg_gen_and_vec(vece, lsh, shift, msk);
+        tcg_gen_and_vec(vece, rsh, rsh, msk);
     }
 
     /* Bound rsh so out of bound right shift gets -1.  */
-    tcg_gen_dupi_vec(vece, tmp, (8 << vece) - 1);
-    tcg_gen_umin_vec(vece, rsh, rsh, tmp);
-    tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, tmp);
+    max = tcg_constant_vec_matching(dst, vece, (8 << vece) - 1);
+    tcg_gen_umin_vec(vece, rsh, rsh, max);
 
     tcg_gen_shlv_vec(vece, lval, src, lsh);
     tcg_gen_sarv_vec(vece, rval, src, rsh);
 
     /* Select in-bound left shift.  */
-    tcg_gen_andc_vec(vece, lval, lval, tmp);
+    zero = tcg_constant_vec_matching(dst, vece, 0);
+    tcg_gen_cmpsel_vec(TCG_COND_GT, vece, lval, lsh, max, zero, lval);
 
     /* Select between left and right shift.  */
     if (vece == MO_8) {
-        tcg_gen_dupi_vec(vece, tmp, 0);
-        tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, rval, lval);
+        tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, zero, rval, lval);
     } else {
-        tcg_gen_dupi_vec(vece, tmp, 0x80);
-        tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, lval, rval);
+        TCGv_vec sgn = tcg_constant_vec_matching(dst, vece, 0x80);
+        tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, sgn, lval, rval);
     }
 }
 
@@ -1211,7 +1220,7 @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
 {
     static const TCGOpcode vecop_list[] = {
         INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec,
-        INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0
+        INDEX_op_sarv_vec, INDEX_op_cmpsel_vec, 0
     };
     static const GVecGen3 ops[4] = {
         { .fniv = gen_sshl_vec,
@@ -1304,6 +1313,42 @@ void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                        opr_sz, max_sz, 0, fns[vece]);
 }
 
+void gen_neon_sqshli(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     int64_t c, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_2_ptr * const fns[] = {
+        gen_helper_neon_sqshli_b, gen_helper_neon_sqshli_h,
+        gen_helper_neon_sqshli_s, gen_helper_neon_sqshli_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_debug_assert(c >= 0 && c <= (8 << vece));
+    tcg_gen_gvec_2_ptr(rd_ofs, rn_ofs, tcg_env, opr_sz, max_sz, c, fns[vece]);
+}
+
+void gen_neon_uqshli(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                     int64_t c, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_2_ptr * const fns[] = {
+        gen_helper_neon_uqshli_b, gen_helper_neon_uqshli_h,
+        gen_helper_neon_uqshli_s, gen_helper_neon_uqshli_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_debug_assert(c >= 0 && c <= (8 << vece));
+    tcg_gen_gvec_2_ptr(rd_ofs, rn_ofs, tcg_env, opr_sz, max_sz, c, fns[vece]);
+}
+
+void gen_neon_sqshlui(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                      int64_t c, uint32_t opr_sz, uint32_t max_sz)
+{
+    static gen_helper_gvec_2_ptr * const fns[] = {
+        gen_helper_neon_sqshlui_b, gen_helper_neon_sqshlui_h,
+        gen_helper_neon_sqshlui_s, gen_helper_neon_sqshlui_d,
+    };
+    tcg_debug_assert(vece <= MO_64);
+    tcg_debug_assert(c >= 0 && c <= (8 << vece));
+    tcg_gen_gvec_2_ptr(rd_ofs, rn_ofs, tcg_env, opr_sz, max_sz, c, fns[vece]);
+}
+
 void gen_uqadd_bhs(TCGv_i64 res, TCGv_i64 qc, TCGv_i64 a, TCGv_i64 b, MemOp esz)
 {
     uint64_t max = MAKE_64BIT_MASK(0, 8 << esz);