Series comparison

The following changes since commit 14556211bc6d7125a44d5b5df90caba019b0ec0e:

Merge tag 'qemu-macppc-20240918' of https://github.com/mcayland/qemu into staging (2024-09-18 20:59:10 +0100)

are available in the Git repository at:

https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240919

for you to fetch changes up to 89b30b4921e51bb47313d2d8fdc3d7bce987e4c5:

docs/devel: Remove nested-papr.txt (2024-09-19 13:33:15 +0100)

----------------------------------------------------------------
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

----------------------------------------------------------------
Jacob Abrams (1):
      hw/char/stm32l4x5_usart.c: Enable USART ACK bit response

Marcin Juszkiewicz (4):
      tests: use default cpu for aarch64/sbsa-ref
      tests: add FreeBSD tests for aarch64/sbsa-ref
      tests: expand timeout information for aarch64/sbsa-ref
      tests: drop OpenBSD tests for aarch64/sbsa-ref

Peter Maydell (4):
      kvm: Make 'mmap_size' be 'int' in kvm_init_vcpu(), do_kvm_destroy_vcpu()
      kvm: Remove unreachable code in kvm_dirty_ring_reaper_thread()
      target/arm: Correct ID_AA64ISAR1_EL1 value for neoverse-v1
      docs/devel: Remove nested-papr.txt

Richard Henderson (29):
      target/arm: Replace tcg_gen_dupi_vec with constants in gengvec.c
      target/arm: Replace tcg_gen_dupi_vec with constants in translate-sve.c
      target/arm: Use cmpsel in gen_ushl_vec
      target/arm: Use cmpsel in gen_sshl_vec
      target/arm: Use tcg_gen_extract2_i64 for EXT
      target/arm: Convert EXT to decodetree
      target/arm: Convert TBL, TBX to decodetree
      target/arm: Convert UZP, TRN, ZIP to decodetree
      target/arm: Simplify do_reduction_op
      target/arm: Convert ADDV, *ADDLV, *MAXV, *MINV to decodetree
      target/arm: Convert FMAXNMV, FMINNMV, FMAXV, FMINV to decodetree
      target/arm: Convert FMOVI (scalar, immediate) to decodetree
      target/arm: Convert MOVI, FMOV, ORR, BIC (vector immediate) to decodetree
      target/arm: Introduce gen_gvec_sshr, gen_gvec_ushr
      target/arm: Fix whitespace near gen_srshr64_i64
      target/arm: Convert handle_vec_simd_shri to decodetree
      target/arm: Convert handle_vec_simd_shli to decodetree
      target/arm: Use {, s}extract in handle_vec_simd_wshli
      target/arm: Convert SSHLL, USHLL to decodetree
      target/arm: Push tcg_rnd into handle_shri_with_rndacc
      target/arm: Split out subroutines of handle_shri_with_rndacc
      target/arm: Convert SHRN, RSHRN to decodetree
      target/arm: Convert handle_scalar_simd_shri to decodetree
      target/arm: Convert handle_scalar_simd_shli to decodetree
      target/arm: Convert VQSHL, VQSHLU to gvec
      target/arm: Widen NeonGenNarrowEnvFn return to 64 bits
      target/arm: Convert SQSHL, UQSHL, SQSHLU (immediate) to decodetree
      target/arm: Convert vector [US]QSHRN, [US]QRSHRN, SQSHRUN to decodetree
      target/arm: Convert scalar [US]QSHRN, [US]QRSHRN, SQSHRUN to decodetree

From: Richard Henderson <richard.henderson@linaro.org>

Instead of copying a constant into a temporary with dupi,
use a vector constant directly.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/gengvec.c | 43 ++++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 24 deletions(-)

diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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);
@@ -XXX,XX +XXX,XX @@ 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);
 }
@@ -XXX,XX +XXX,XX @@ 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;
 
     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);
     }
@@ -XXX,XX +XXX,XX @@ 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 instructions of the x86_64 host.  For MO_8, the whole byte
@@ -XXX,XX +XXX,XX @@ static void gen_ushl_vec(unsigned vece, TCGv_vec dst,
      * 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.
      */
+    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);
@@ -XXX,XX +XXX,XX @@ static void gen_sshl_vec(unsigned vece, TCGv_vec 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
@@ -XXX,XX +XXX,XX @@ 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_cmp_vec(TCG_COND_GT, vece, tmp, lsh, max);
 
     tcg_gen_shlv_vec(vece, lval, src, lsh);
     tcg_gen_sarv_vec(vece, rval, src, rsh);
@@ -XXX,XX +XXX,XX @@ static void gen_sshl_vec(unsigned vece, TCGv_vec dst,
     tcg_gen_andc_vec(vece, lval, lval, tmp);
 
     /* Select between left and right shift.  */
+    zero = tcg_constant_vec_matching(dst, vece, 0);
     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);
     }
 }
 
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Instead of copying a constant into a temporary with dupi,
use a vector constant directly.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 128 +++++++++++++--------------------
 1 file changed, 49 insertions(+), 79 deletions(-)

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static void gen_sshll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm)
 
     if (top) {
         if (shl == halfbits) {
-            TCGv_vec t = tcg_temp_new_vec_matching(d);
-            tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(halfbits, halfbits));
-            tcg_gen_and_vec(vece, d, n, t);
+            tcg_gen_and_vec(vece, d, n,
+                            tcg_constant_vec_matching(d, vece,
+                                MAKE_64BIT_MASK(halfbits, halfbits)));
         } else {
             tcg_gen_sari_vec(vece, d, n, halfbits);
             tcg_gen_shli_vec(vece, d, d, shl);
@@ -XXX,XX +XXX,XX @@ static void gen_ushll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm)
 
     if (top) {
         if (shl == halfbits) {
-            TCGv_vec t = tcg_temp_new_vec_matching(d);
-            tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(halfbits, halfbits));
-            tcg_gen_and_vec(vece, d, n, t);
+            tcg_gen_and_vec(vece, d, n,
+                            tcg_constant_vec_matching(d, vece,
+                                MAKE_64BIT_MASK(halfbits, halfbits)));
         } else {
             tcg_gen_shri_vec(vece, d, n, halfbits);
             tcg_gen_shli_vec(vece, d, d, shl);
         }
     } else {
         if (shl == 0) {
-            TCGv_vec t = tcg_temp_new_vec_matching(d);
-            tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-            tcg_gen_and_vec(vece, d, n, t);
+            tcg_gen_and_vec(vece, d, n,
+                            tcg_constant_vec_matching(d, vece,
+                                MAKE_64BIT_MASK(0, halfbits)));
         } else {
             tcg_gen_shli_vec(vece, d, n, halfbits);
             tcg_gen_shri_vec(vece, d, d, halfbits - shl);
@@ -XXX,XX +XXX,XX @@ static const TCGOpcode sqxtn_list[] = {
 
 static void gen_sqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t mask = (1ull << halfbits) - 1;
     int64_t min = -1ull << (halfbits - 1);
     int64_t max = -min - 1;
 
-    tcg_gen_dupi_vec(vece, t, min);
-    tcg_gen_smax_vec(vece, d, n, t);
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_smin_vec(vece, d, d, t);
-    tcg_gen_dupi_vec(vece, t, mask);
-    tcg_gen_and_vec(vece, d, d, t);
+    tcg_gen_smax_vec(vece, d, n, tcg_constant_vec_matching(d, vece, min));
+    tcg_gen_smin_vec(vece, d, d, tcg_constant_vec_matching(d, vece, max));
+    tcg_gen_and_vec(vece, d, d, tcg_constant_vec_matching(d, vece, mask));
 }
 
 static const GVecGen2 sqxtnb_ops[3] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQXTNB, aa64_sve2, do_narrow_extract, a, sqxtnb_ops)
 
 static void gen_sqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t mask = (1ull << halfbits) - 1;
     int64_t min = -1ull << (halfbits - 1);
     int64_t max = -min - 1;
 
-    tcg_gen_dupi_vec(vece, t, min);
-    tcg_gen_smax_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_smin_vec(vece, n, n, t);
+    tcg_gen_smax_vec(vece, n, n, tcg_constant_vec_matching(d, vece, min));
+    tcg_gen_smin_vec(vece, n, n, tcg_constant_vec_matching(d, vece, max));
     tcg_gen_shli_vec(vece, n, n, halfbits);
-    tcg_gen_dupi_vec(vece, t, mask);
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, tcg_constant_vec_matching(d, vece, mask), d, n);
 }
 
 static const GVecGen2 sqxtnt_ops[3] = {
@@ -XXX,XX +XXX,XX @@ static const TCGOpcode uqxtn_list[] = {
 
 static void gen_uqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t max = (1ull << halfbits) - 1;
 
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_umin_vec(vece, d, n, t);
+    tcg_gen_umin_vec(vece, d, n, tcg_constant_vec_matching(d, vece, max));
 }
 
 static const GVecGen2 uqxtnb_ops[3] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UQXTNB, aa64_sve2, do_narrow_extract, a, uqxtnb_ops)
 
 static void gen_uqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t max = (1ull << halfbits) - 1;
+    TCGv_vec maxv = tcg_constant_vec_matching(d, vece, max);
 
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_umin_vec(vece, n, n, t);
+    tcg_gen_umin_vec(vece, n, n, maxv);
     tcg_gen_shli_vec(vece, n, n, halfbits);
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, maxv, d, n);
 }
 
 static const GVecGen2 uqxtnt_ops[3] = {
@@ -XXX,XX +XXX,XX @@ static const TCGOpcode sqxtun_list[] = {
 
 static void gen_sqxtunb_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t max = (1ull << halfbits) - 1;
 
-    tcg_gen_dupi_vec(vece, t, 0);
-    tcg_gen_smax_vec(vece, d, n, t);
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_umin_vec(vece, d, d, t);
+    tcg_gen_smax_vec(vece, d, n, tcg_constant_vec_matching(d, vece, 0));
+    tcg_gen_umin_vec(vece, d, d, tcg_constant_vec_matching(d, vece, max));
 }
 
 static const GVecGen2 sqxtunb_ops[3] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQXTUNB, aa64_sve2, do_narrow_extract, a, sqxtunb_ops)
 
 static void gen_sqxtunt_vec(unsigned vece, TCGv_vec d, TCGv_vec n)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t max = (1ull << halfbits) - 1;
+    TCGv_vec maxv = tcg_constant_vec_matching(d, vece, max);
 
-    tcg_gen_dupi_vec(vece, t, 0);
-    tcg_gen_smax_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_umin_vec(vece, n, n, t);
+    tcg_gen_smax_vec(vece, n, n, tcg_constant_vec_matching(d, vece, 0));
+    tcg_gen_umin_vec(vece, n, n, maxv);
     tcg_gen_shli_vec(vece, n, n, halfbits);
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, maxv, d, n);
 }
 
 static const GVecGen2 sqxtunt_ops[3] = {
@@ -XXX,XX +XXX,XX @@ static void gen_shrnb64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
 
 static void gen_shrnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     uint64_t mask = MAKE_64BIT_MASK(0, halfbits);
 
     tcg_gen_shri_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, mask);
-    tcg_gen_and_vec(vece, d, n, t);
+    tcg_gen_and_vec(vece, d, n, tcg_constant_vec_matching(d, vece, mask));
 }
 
 static const TCGOpcode shrnb_vec_list[] = { INDEX_op_shri_vec, 0 };
@@ -XXX,XX +XXX,XX @@ static void gen_shrnt64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
 
 static void gen_shrnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     uint64_t mask = MAKE_64BIT_MASK(0, halfbits);
 
     tcg_gen_shli_vec(vece, n, n, halfbits - shr);
-    tcg_gen_dupi_vec(vece, t, mask);
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, tcg_constant_vec_matching(d, vece, mask), d, n);
 }
 
 static const TCGOpcode shrnt_vec_list[] = { INDEX_op_shli_vec, 0 };
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(RSHRNT, aa64_sve2, do_shr_narrow, a, rshrnt_ops)
 static void gen_sqshrunb_vec(unsigned vece, TCGv_vec d,
                              TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
+    uint64_t max = MAKE_64BIT_MASK(0, halfbits);
 
     tcg_gen_sari_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, 0);
-    tcg_gen_smax_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-    tcg_gen_umin_vec(vece, d, n, t);
+    tcg_gen_smax_vec(vece, n, n, tcg_constant_vec_matching(d, vece, 0));
+    tcg_gen_umin_vec(vece, d, n, tcg_constant_vec_matching(d, vece, max));
 }
 
 static const TCGOpcode sqshrunb_vec_list[] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQSHRUNB, aa64_sve2, do_shr_narrow, a, sqshrunb_ops)
 static void gen_sqshrunt_vec(unsigned vece, TCGv_vec d,
                              TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
+    uint64_t max = MAKE_64BIT_MASK(0, halfbits);
+    TCGv_vec maxv = tcg_constant_vec_matching(d, vece, max);
 
     tcg_gen_sari_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, 0);
-    tcg_gen_smax_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-    tcg_gen_umin_vec(vece, n, n, t);
+    tcg_gen_smax_vec(vece, n, n, tcg_constant_vec_matching(d, vece, 0));
+    tcg_gen_umin_vec(vece, n, n, maxv);
     tcg_gen_shli_vec(vece, n, n, halfbits);
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, maxv, d, n);
 }
 
 static const TCGOpcode sqshrunt_vec_list[] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRSHRUNT, aa64_sve2, do_shr_narrow, a, sqrshrunt_ops)
 static void gen_sqshrnb_vec(unsigned vece, TCGv_vec d,
                             TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t max = MAKE_64BIT_MASK(0, halfbits - 1);
     int64_t min = -max - 1;
+    int64_t mask = MAKE_64BIT_MASK(0, halfbits);
 
     tcg_gen_sari_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, min);
-    tcg_gen_smax_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_smin_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-    tcg_gen_and_vec(vece, d, n, t);
+    tcg_gen_smax_vec(vece, n, n, tcg_constant_vec_matching(d, vece, min));
+    tcg_gen_smin_vec(vece, n, n, tcg_constant_vec_matching(d, vece, max));
+    tcg_gen_and_vec(vece, d, n, tcg_constant_vec_matching(d, vece, mask));
 }
 
 static const TCGOpcode sqshrnb_vec_list[] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQSHRNB, aa64_sve2, do_shr_narrow, a, sqshrnb_ops)
 static void gen_sqshrnt_vec(unsigned vece, TCGv_vec d,
                              TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
     int64_t max = MAKE_64BIT_MASK(0, halfbits - 1);
     int64_t min = -max - 1;
+    int64_t mask = MAKE_64BIT_MASK(0, halfbits);
 
     tcg_gen_sari_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, min);
-    tcg_gen_smax_vec(vece, n, n, t);
-    tcg_gen_dupi_vec(vece, t, max);
-    tcg_gen_smin_vec(vece, n, n, t);
+    tcg_gen_smax_vec(vece, n, n, tcg_constant_vec_matching(d, vece, min));
+    tcg_gen_smin_vec(vece, n, n, tcg_constant_vec_matching(d, vece, max));
     tcg_gen_shli_vec(vece, n, n, halfbits);
-    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, tcg_constant_vec_matching(d, vece, mask), d, n);
 }
 
 static const TCGOpcode sqshrnt_vec_list[] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRSHRNT, aa64_sve2, do_shr_narrow, a, sqrshrnt_ops)
 static void gen_uqshrnb_vec(unsigned vece, TCGv_vec d,
                             TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
+    int64_t max = MAKE_64BIT_MASK(0, halfbits);
 
     tcg_gen_shri_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-    tcg_gen_umin_vec(vece, d, n, t);
+    tcg_gen_umin_vec(vece, d, n, tcg_constant_vec_matching(d, vece, max));
 }
 
 static const TCGOpcode uqshrnb_vec_list[] = {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UQSHRNB, aa64_sve2, do_shr_narrow, a, uqshrnb_ops)
 static void gen_uqshrnt_vec(unsigned vece, TCGv_vec d,
                             TCGv_vec n, int64_t shr)
 {
-    TCGv_vec t = tcg_temp_new_vec_matching(d);
     int halfbits = 4 << vece;
+    int64_t max = MAKE_64BIT_MASK(0, halfbits);
+    TCGv_vec maxv = tcg_constant_vec_matching(d, vece, max);
 
     tcg_gen_shri_vec(vece, n, n, shr);
-    tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits));
-    tcg_gen_umin_vec(vece, n, n, t);
+    tcg_gen_umin_vec(vece, n, n, maxv);
     tcg_gen_shli_vec(vece, n, n, halfbits);
-    tcg_gen_bitsel_vec(vece, d, t, d, n);
+    tcg_gen_bitsel_vec(vece, d, maxv, d, n);
 }
 
 static const TCGOpcode uqshrnt_vec_list[] = {
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Instead of cmp+and or cmp+andc, use cmpsel.  This will
be better for hosts that use predicate registers for cmp.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/gengvec.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -XXX,XX +XXX,XX @@ 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 max;
+    TCGv_vec max, zero;
 
     tcg_gen_neg_vec(vece, rsh, shift);
     if (vece == MO_8) {
@@ -XXX,XX +XXX,XX @@ static void gen_ushl_vec(unsigned vece, TCGv_vec dst,
     tcg_gen_shrv_vec(vece, rval, src, rsh);
 
     /*
-     * 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);
 }
@@ -XXX,XX +XXX,XX @@ 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,
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Instead of cmp+and or cmp+andc, use cmpsel.  This will
be better for hosts that use predicate registers for cmp.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/gengvec.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -XXX,XX +XXX,XX @@ 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;
 
     /*
@@ -XXX,XX +XXX,XX @@ static void gen_sshl_vec(unsigned vece, TCGv_vec dst,
     /* Bound rsh so out of bound right shift gets -1.  */
     max = tcg_constant_vec_matching(dst, vece, (8 << vece) - 1);
     tcg_gen_umin_vec(vece, rsh, rsh, max);
-    tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, 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.  */
-    zero = tcg_constant_vec_matching(dst, vece, 0);
     if (vece == MO_8) {
         tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, zero, rval, lval);
     } else {
@@ -XXX,XX +XXX,XX @@ 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,
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

The extract2 tcg op performs the same operation
as the do_ext64 function.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-6-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 23 +++--------------------
 1 file changed, 3 insertions(+), 20 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
-static void do_ext64(DisasContext *s, TCGv_i64 tcg_left, TCGv_i64 tcg_right,
-                     int pos)
-{
-    /* Extract 64 bits from the middle of two concatenated 64 bit
-     * vector register slices left:right. The extracted bits start
-     * at 'pos' bits into the right (least significant) side.
-     * We return the result in tcg_right, and guarantee not to
-     * trash tcg_left.
-     */
-    TCGv_i64 tcg_tmp = tcg_temp_new_i64();
-    assert(pos > 0 && pos < 64);
-
-    tcg_gen_shri_i64(tcg_right, tcg_right, pos);
-    tcg_gen_shli_i64(tcg_tmp, tcg_left, 64 - pos);
-    tcg_gen_or_i64(tcg_right, tcg_right, tcg_tmp);
-}
-
 /* EXT
  *   31  30 29         24 23 22  21 20  16 15  14  11 10  9    5 4    0
  * +---+---+-------------+-----+---+------+---+------+---+------+------+
@@ -XXX,XX +XXX,XX @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
         read_vec_element(s, tcg_resl, rn, 0, MO_64);
         if (pos != 0) {
             read_vec_element(s, tcg_resh, rm, 0, MO_64);
-            do_ext64(s, tcg_resh, tcg_resl, pos);
+            tcg_gen_extract2_i64(tcg_resl, tcg_resl, tcg_resh, pos);
         }
     } else {
         TCGv_i64 tcg_hh;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
         read_vec_element(s, tcg_resh, elt->reg, elt->elt, MO_64);
         elt++;
         if (pos != 0) {
-            do_ext64(s, tcg_resh, tcg_resl, pos);
+            tcg_gen_extract2_i64(tcg_resl, tcg_resl, tcg_resh, pos);
             tcg_hh = tcg_temp_new_i64();
             read_vec_element(s, tcg_hh, elt->reg, elt->elt, MO_64);
-            do_ext64(s, tcg_hh, tcg_resh, pos);
+            tcg_gen_extract2_i64(tcg_resh, tcg_resh, tcg_hh, pos);
         }
     }
 
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |   5 ++
 target/arm/tcg/translate-a64.c | 121 +++++++++++++--------------------
 2 files changed, 53 insertions(+), 73 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  4 +++
 target/arm/tcg/translate-a64.c | 47 ++++++++++------------------------
 2 files changed, 18 insertions(+), 33 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@ FNMSUB          0001 1111 .. 1 ..... 1 ..... ..... .....    @rrrr_hsd
 
 EXT_d           0010 1110 00 0 rm:5 00 imm:3 0 rn:5 rd:5
 EXT_q           0110 1110 00 0 rm:5 0  imm:4 0 rn:5 rd:5
+
+# Advanced SIMD Table Lookup
+
+TBL_TBX         0 q:1 00 1110 000 rm:5 0 len:2 tbx:1 00 rn:5 rd:5
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool trans_EXTR(DisasContext *s, arg_extract *a)
     return true;
 }
 
+static bool trans_TBL_TBX(DisasContext *s, arg_TBL_TBX *a)
+{
+    if (fp_access_check(s)) {
+        int len = (a->len + 1) * 16;
+
+        tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rm), tcg_env,
+                           a->q ? 16 : 8, vec_full_reg_size(s),
+                           (len << 6) | (a->tbx << 5) | a->rn,
+                           gen_helper_simd_tblx);
+    }
+    return true;
+}
+
 /*
  * Cryptographic AES, SHA, SHA512
  */
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
-/* TBL/TBX
- *   31  30 29         24 23 22  21 20  16 15  14 13  12  11 10 9    5 4    0
- * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+
- * | 0 | Q | 0 0 1 1 1 0 | op2 | 0 |  Rm  | 0 | len | op | 0 0 |  Rn  |  Rd  |
- * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+
- */
-static void disas_simd_tb(DisasContext *s, uint32_t insn)
-{
-    int op2 = extract32(insn, 22, 2);
-    int is_q = extract32(insn, 30, 1);
-    int rm = extract32(insn, 16, 5);
-    int rn = extract32(insn, 5, 5);
-    int rd = extract32(insn, 0, 5);
-    int is_tbx = extract32(insn, 12, 1);
-    int len = (extract32(insn, 13, 2) + 1) * 16;
-
-    if (op2 != 0) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd),
-                       vec_full_reg_offset(s, rm), tcg_env,
-                       is_q ? 16 : 8, vec_full_reg_size(s),
-                       (len << 6) | (is_tbx << 5) | rn,
-                       gen_helper_simd_tblx);
-}
-
 /* ZIP/UZP/TRN
  *   31  30 29         24 23  22  21 20   16 15 14 12 11 10 9    5 4    0
  * +---+---+-------------+------+---+------+---+------------------+------+
@@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = {
     /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */
     { 0x0f000400, 0x9ff80400, disas_simd_mod_imm },
     { 0x0f000400, 0x9f800400, disas_simd_shift_imm },
-    { 0x0e000000, 0xbf208c00, disas_simd_tb },
     { 0x0e000800, 0xbf208c00, disas_simd_zip_trn },
     { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc },
     { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm },
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |   9 ++
 target/arm/tcg/translate-a64.c | 158 ++++++++++++++-------------------
 2 files changed, 77 insertions(+), 90 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@ EXT_q           0110 1110 00 0 rm:5 0  imm:4 0 rn:5 rd:5
 # Advanced SIMD Table Lookup
 
 TBL_TBX         0 q:1 00 1110 000 rm:5 0 len:2 tbx:1 00 rn:5 rd:5
+
+# Advanced SIMD Permute
+
+UZP1            0.00 1110 .. 0 ..... 0 001 10 ..... .....   @qrrr_e
+UZP2            0.00 1110 .. 0 ..... 0 101 10 ..... .....   @qrrr_e
+TRN1            0.00 1110 .. 0 ..... 0 010 10 ..... .....   @qrrr_e
+TRN2            0.00 1110 .. 0 ..... 0 110 10 ..... .....   @qrrr_e
+ZIP1            0.00 1110 .. 0 ..... 0 011 10 ..... .....   @qrrr_e
+ZIP2            0.00 1110 .. 0 ..... 0 111 10 ..... .....   @qrrr_e
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool trans_TBL_TBX(DisasContext *s, arg_TBL_TBX *a)
     return true;
 }
 
+typedef int simd_permute_idx_fn(int i, int part, int elements);
+
+static bool do_simd_permute(DisasContext *s, arg_qrrr_e *a,
+                            simd_permute_idx_fn *fn, int part)
+{
+    MemOp esz = a->esz;
+    int datasize = a->q ? 16 : 8;
+    int elements = datasize >> esz;
+    TCGv_i64 tcg_res[2], tcg_ele;
+
+    if (esz == MO_64 && !a->q) {
+        return false;
+    }
+    if (!fp_access_check(s)) {
+        return true;
+    }
+
+    tcg_res[0] = tcg_temp_new_i64();
+    tcg_res[1] = a->q ? tcg_temp_new_i64() : NULL;
+    tcg_ele = tcg_temp_new_i64();
+
+    for (int i = 0; i < elements; i++) {
+        int o, w, idx;
+
+        idx = fn(i, part, elements);
+        read_vec_element(s, tcg_ele, (idx & elements ? a->rm : a->rn),
+                         idx & (elements - 1), esz);
+
+        w = (i << (esz + 3)) / 64;
+        o = (i << (esz + 3)) % 64;
+        if (o == 0) {
+            tcg_gen_mov_i64(tcg_res[w], tcg_ele);
+        } else {
+            tcg_gen_deposit_i64(tcg_res[w], tcg_res[w], tcg_ele, o, 8 << esz);
+        }
+    }
+
+    for (int i = a->q; i >= 0; --i) {
+        write_vec_element(s, tcg_res[i], a->rd, i, MO_64);
+    }
+    clear_vec_high(s, a->q, a->rd);
+    return true;
+}
+
+static int permute_load_uzp(int i, int part, int elements)
+{
+    return 2 * i + part;
+}
+
+TRANS(UZP1, do_simd_permute, a, permute_load_uzp, 0)
+TRANS(UZP2, do_simd_permute, a, permute_load_uzp, 1)
+
+static int permute_load_trn(int i, int part, int elements)
+{
+    return (i & 1) * elements + (i & ~1) + part;
+}
+
+TRANS(TRN1, do_simd_permute, a, permute_load_trn, 0)
+TRANS(TRN2, do_simd_permute, a, permute_load_trn, 1)
+
+static int permute_load_zip(int i, int part, int elements)
+{
+    return (i & 1) * elements + ((part * elements + i) >> 1);
+}
+
+TRANS(ZIP1, do_simd_permute, a, permute_load_zip, 0)
+TRANS(ZIP2, do_simd_permute, a, permute_load_zip, 1)
+
 /*
  * Cryptographic AES, SHA, SHA512
  */
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
-/* ZIP/UZP/TRN
- *   31  30 29         24 23  22  21 20   16 15 14 12 11 10 9    5 4    0
- * +---+---+-------------+------+---+------+---+------------------+------+
- * | 0 | Q | 0 0 1 1 1 0 | size | 0 |  Rm  | 0 | opc | 1 0 |  Rn  |  Rd  |
- * +---+---+-------------+------+---+------+---+------------------+------+
- */
-static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
-{
-    int rd = extract32(insn, 0, 5);
-    int rn = extract32(insn, 5, 5);
-    int rm = extract32(insn, 16, 5);
-    int size = extract32(insn, 22, 2);
-    /* opc field bits [1:0] indicate ZIP/UZP/TRN;
-     * bit 2 indicates 1 vs 2 variant of the insn.
-     */
-    int opcode = extract32(insn, 12, 2);
-    bool part = extract32(insn, 14, 1);
-    bool is_q = extract32(insn, 30, 1);
-    int esize = 8 << size;
-    int i;
-    int datasize = is_q ? 128 : 64;
-    int elements = datasize / esize;
-    TCGv_i64 tcg_res[2], tcg_ele;
-
-    if (opcode == 0 || (size == 3 && !is_q)) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    tcg_res[0] = tcg_temp_new_i64();
-    tcg_res[1] = is_q ? tcg_temp_new_i64() : NULL;
-    tcg_ele = tcg_temp_new_i64();
-
-    for (i = 0; i < elements; i++) {
-        int o, w;
-
-        switch (opcode) {
-        case 1: /* UZP1/2 */
-        {
-            int midpoint = elements / 2;
-            if (i < midpoint) {
-                read_vec_element(s, tcg_ele, rn, 2 * i + part, size);
-            } else {
-                read_vec_element(s, tcg_ele, rm,
-                                 2 * (i - midpoint) + part, size);
-            }
-            break;
-        }
-        case 2: /* TRN1/2 */
-            if (i & 1) {
-                read_vec_element(s, tcg_ele, rm, (i & ~1) + part, size);
-            } else {
-                read_vec_element(s, tcg_ele, rn, (i & ~1) + part, size);
-            }
-            break;
-        case 3: /* ZIP1/2 */
-        {
-            int base = part * elements / 2;
-            if (i & 1) {
-                read_vec_element(s, tcg_ele, rm, base + (i >> 1), size);
-            } else {
-                read_vec_element(s, tcg_ele, rn, base + (i >> 1), size);
-            }
-            break;
-        }
-        default:
-            g_assert_not_reached();
-        }
-
-        w = (i * esize) / 64;
-        o = (i * esize) % 64;
-        if (o == 0) {
-            tcg_gen_mov_i64(tcg_res[w], tcg_ele);
-        } else {
-            tcg_gen_shli_i64(tcg_ele, tcg_ele, o);
-            tcg_gen_or_i64(tcg_res[w], tcg_res[w], tcg_ele);
-        }
-    }
-
-    for (i = 0; i <= is_q; ++i) {
-        write_vec_element(s, tcg_res[i], rd, i, MO_64);
-    }
-    clear_vec_high(s, is_q, rd);
-}
-
 /*
  * do_reduction_op helper
  *
@@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = {
     /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */
     { 0x0f000400, 0x9ff80400, disas_simd_mod_imm },
     { 0x0f000400, 0x9f800400, disas_simd_shift_imm },
-    { 0x0e000800, 0xbf208c00, disas_simd_zip_trn },
     { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc },
     { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm },
     { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 },
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Use simple shift and add instead of ctpop, ctz, shift and mask.
Unlike SVE, there is no predicate to disable elements.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 40 +++++++++++-----------------------
 1 file changed, 13 insertions(+), 27 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
  * important for correct NaN propagation that we do these
  * operations in exactly the order specified by the pseudocode.
  *
- * This is a recursive function, TCG temps should be freed by the
- * calling function once it is done with the values.
+ * This is a recursive function.
  */
 static TCGv_i32 do_reduction_op(DisasContext *s, int fpopcode, int rn,
-                                int esize, int size, int vmap, TCGv_ptr fpst)
+                                MemOp esz, int ebase, int ecount, TCGv_ptr fpst)
 {
-    if (esize == size) {
-        int element;
-        MemOp msize = esize == 16 ? MO_16 : MO_32;
-        TCGv_i32 tcg_elem;
-
-        /* We should have one register left here */
-        assert(ctpop8(vmap) == 1);
-        element = ctz32(vmap);
-        assert(element < 8);
-
-        tcg_elem = tcg_temp_new_i32();
-        read_vec_element_i32(s, tcg_elem, rn, element, msize);
+    if (ecount == 1) {
+        TCGv_i32 tcg_elem = tcg_temp_new_i32();
+        read_vec_element_i32(s, tcg_elem, rn, ebase, esz);
         return tcg_elem;
     } else {
-        int bits = size / 2;
-        int shift = ctpop8(vmap) / 2;
-        int vmap_lo = (vmap >> shift) & vmap;
-        int vmap_hi = (vmap & ~vmap_lo);
+        int half = ecount >> 1;
         TCGv_i32 tcg_hi, tcg_lo, tcg_res;
 
-        tcg_hi = do_reduction_op(s, fpopcode, rn, esize, bits, vmap_hi, fpst);
-        tcg_lo = do_reduction_op(s, fpopcode, rn, esize, bits, vmap_lo, fpst);
+        tcg_hi = do_reduction_op(s, fpopcode, rn, esz,
+                                 ebase + half, half, fpst);
+        tcg_lo = do_reduction_op(s, fpopcode, rn, esz,
+                                 ebase, half, fpst);
         tcg_res = tcg_temp_new_i32();
 
         switch (fpopcode) {
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
     bool is_u = extract32(insn, 29, 1);
     bool is_fp = false;
     bool is_min = false;
-    int esize;
     int elements;
     int i;
     TCGv_i64 tcg_res, tcg_elt;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
         return;
     }
 
-    esize = 8 << size;
-    elements = (is_q ? 128 : 64) / esize;
+    elements = (is_q ? 16 : 8) >> size;
 
     tcg_res = tcg_temp_new_i64();
     tcg_elt = tcg_temp_new_i64();
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
          */
         TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
         int fpopcode = opcode | is_min << 4 | is_u << 5;
-        int vmap = (1 << elements) - 1;
-        TCGv_i32 tcg_res32 = do_reduction_op(s, fpopcode, rn, esize,
-                                             (is_q ? 128 : 64), vmap, fpst);
+        TCGv_i32 tcg_res32 = do_reduction_op(s, fpopcode, rn, size,
+                                             0, elements, fpst);
         tcg_gen_extu_i32_i64(tcg_res, tcg_res32);
     }
 
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  12 +++
 target/arm/tcg/translate-a64.c | 140 ++++++++++++---------------------
 2 files changed, 61 insertions(+), 91 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@
 @rrr_q1e3       ........ ... rm:5 ...... rn:5 rd:5      &qrrr_e q=1 esz=3
 @rrrr_q1e3      ........ ... rm:5 . ra:5 rn:5 rd:5      &qrrrr_e q=1 esz=3
 
+@qrr_e          . q:1 ...... esz:2 ...... ...... rn:5 rd:5  &qrr_e
+
 @qrrr_b         . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=0
 @qrrr_h         . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=1
 @qrrr_s         . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=2
@@ -XXX,XX +XXX,XX @@ TRN1            0.00 1110 .. 0 ..... 0 010 10 ..... .....   @qrrr_e
 TRN2            0.00 1110 .. 0 ..... 0 110 10 ..... .....   @qrrr_e
 ZIP1            0.00 1110 .. 0 ..... 0 011 10 ..... .....   @qrrr_e
 ZIP2            0.00 1110 .. 0 ..... 0 111 10 ..... .....   @qrrr_e
+
+# Advanced SIMD Across Lanes
+
+ADDV            0.00 1110 .. 11000 11011 10 ..... .....     @qrr_e
+SADDLV          0.00 1110 .. 11000 00011 10 ..... .....     @qrr_e
+UADDLV          0.10 1110 .. 11000 00011 10 ..... .....     @qrr_e
+SMAXV           0.00 1110 .. 11000 01010 10 ..... .....     @qrr_e
+UMAXV           0.10 1110 .. 11000 01010 10 ..... .....     @qrr_e
+SMINV           0.00 1110 .. 11000 11010 10 ..... .....     @qrr_e
+UMINV           0.10 1110 .. 11000 11010 10 ..... .....     @qrr_e
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ TRANS(FNMADD, do_fmadd, a, true, true)
 TRANS(FMSUB, do_fmadd, a, false, true)
 TRANS(FNMSUB, do_fmadd, a, true, false)
 
+/*
+ * Advanced SIMD Across Lanes
+ */
+
+static bool do_int_reduction(DisasContext *s, arg_qrr_e *a, bool widen,
+                             MemOp src_sign, NeonGenTwo64OpFn *fn)
+{
+    TCGv_i64 tcg_res, tcg_elt;
+    MemOp src_mop = a->esz | src_sign;
+    int elements = (a->q ? 16 : 8) >> a->esz;
+
+    /* Reject MO_64, and MO_32 without Q: a minimum of 4 elements. */
+    if (elements < 4) {
+        return false;
+    }
+    if (!fp_access_check(s)) {
+        return true;
+    }
+
+    tcg_res = tcg_temp_new_i64();
+    tcg_elt = tcg_temp_new_i64();
+
+    read_vec_element(s, tcg_res, a->rn, 0, src_mop);
+    for (int i = 1; i < elements; i++) {
+        read_vec_element(s, tcg_elt, a->rn, i, src_mop);
+        fn(tcg_res, tcg_res, tcg_elt);
+    }
+
+    tcg_gen_ext_i64(tcg_res, tcg_res, a->esz + widen);
+    write_fp_dreg(s, a->rd, tcg_res);
+    return true;
+}
+
+TRANS(ADDV, do_int_reduction, a, false, 0, tcg_gen_add_i64)
+TRANS(SADDLV, do_int_reduction, a, true, MO_SIGN, tcg_gen_add_i64)
+TRANS(UADDLV, do_int_reduction, a, true, 0, tcg_gen_add_i64)
+TRANS(SMAXV, do_int_reduction, a, false, MO_SIGN, tcg_gen_smax_i64)
+TRANS(UMAXV, do_int_reduction, a, false, 0, tcg_gen_umax_i64)
+TRANS(SMINV, do_int_reduction, a, false, MO_SIGN, tcg_gen_smin_i64)
+TRANS(UMINV, do_int_reduction, a, false, 0, tcg_gen_umin_i64)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
     int opcode = extract32(insn, 12, 5);
     bool is_q = extract32(insn, 30, 1);
     bool is_u = extract32(insn, 29, 1);
-    bool is_fp = false;
     bool is_min = false;
     int elements;
-    int i;
-    TCGv_i64 tcg_res, tcg_elt;
 
     switch (opcode) {
-    case 0x1b: /* ADDV */
-        if (is_u) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* fall through */
-    case 0x3: /* SADDLV, UADDLV */
-    case 0xa: /* SMAXV, UMAXV */
-    case 0x1a: /* SMINV, UMINV */
-        if (size == 3 || (size == 2 && !is_q)) {
-            unallocated_encoding(s);
-            return;
-        }
-        break;
     case 0xc: /* FMAXNMV, FMINNMV */
     case 0xf: /* FMAXV, FMINV */
         /* Bit 1 of size field encodes min vs max and the actual size
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
          * precision.
          */
         is_min = extract32(size, 1, 1);
-        is_fp = true;
         if (!is_u && dc_isar_feature(aa64_fp16, s)) {
             size = 1;
         } else if (!is_u || !is_q || extract32(size, 0, 1)) {
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
         }
         break;
     default:
+    case 0x3: /* SADDLV, UADDLV */
+    case 0xa: /* SMAXV, UMAXV */
+    case 0x1a: /* SMINV, UMINV */
+    case 0x1b: /* ADDV */
         unallocated_encoding(s);
         return;
     }
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
 
     elements = (is_q ? 16 : 8) >> size;
 
-    tcg_res = tcg_temp_new_i64();
-    tcg_elt = tcg_temp_new_i64();
-
-    /* These instructions operate across all lanes of a vector
-     * to produce a single result. We can guarantee that a 64
-     * bit intermediate is sufficient:
-     *  + for [US]ADDLV the maximum element size is 32 bits, and
-     *    the result type is 64 bits
-     *  + for FMAX*V, FMIN*V, ADDV the intermediate type is the
-     *    same as the element size, which is 32 bits at most
-     * For the integer operations we can choose to work at 64
-     * or 32 bits and truncate at the end; for simplicity
-     * we use 64 bits always. The floating point
-     * ops do require 32 bit intermediates, though.
-     */
-    if (!is_fp) {
-        read_vec_element(s, tcg_res, rn, 0, size | (is_u ? 0 : MO_SIGN));
-
-        for (i = 1; i < elements; i++) {
-            read_vec_element(s, tcg_elt, rn, i, size | (is_u ? 0 : MO_SIGN));
-
-            switch (opcode) {
-            case 0x03: /* SADDLV / UADDLV */
-            case 0x1b: /* ADDV */
-                tcg_gen_add_i64(tcg_res, tcg_res, tcg_elt);
-                break;
-            case 0x0a: /* SMAXV / UMAXV */
-                if (is_u) {
-                    tcg_gen_umax_i64(tcg_res, tcg_res, tcg_elt);
-                } else {
-                    tcg_gen_smax_i64(tcg_res, tcg_res, tcg_elt);
-                }
-                break;
-            case 0x1a: /* SMINV / UMINV */
-                if (is_u) {
-                    tcg_gen_umin_i64(tcg_res, tcg_res, tcg_elt);
-                } else {
-                    tcg_gen_smin_i64(tcg_res, tcg_res, tcg_elt);
-                }
-                break;
-            default:
-                g_assert_not_reached();
-            }
-
-        }
-    } else {
+    {
         /* Floating point vector reduction ops which work across 32
          * bit (single) or 16 bit (half-precision) intermediates.
          * Note that correct NaN propagation requires that we do these
@@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
          */
         TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
         int fpopcode = opcode | is_min << 4 | is_u << 5;
-        TCGv_i32 tcg_res32 = do_reduction_op(s, fpopcode, rn, size,
-                                             0, elements, fpst);
-        tcg_gen_extu_i32_i64(tcg_res, tcg_res32);
+        TCGv_i32 tcg_res = do_reduction_op(s, fpopcode, rn, size,
+                                           0, elements, fpst);
+        write_fp_sreg(s, rd, tcg_res);
     }
-
-    /* Now truncate the result to the width required for the final output */
-    if (opcode == 0x03) {
-        /* SADDLV, UADDLV: result is 2*esize */
-        size++;
-    }
-
-    switch (size) {
-    case 0:
-        tcg_gen_ext8u_i64(tcg_res, tcg_res);
-        break;
-    case 1:
-        tcg_gen_ext16u_i64(tcg_res, tcg_res);
-        break;
-    case 2:
-        tcg_gen_ext32u_i64(tcg_res, tcg_res);
-        break;
-    case 3:
-        break;
-    default:
-        g_assert_not_reached();
-    }
-
-    write_fp_dreg(s, rd, tcg_res);
 }
 
 /* AdvSIMD modified immediate
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  14 +++
 target/arm/tcg/translate-a64.c | 176 ++++++++++-----------------------
 2 files changed, 67 insertions(+), 123 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@
 @rrx_d          ........ .. . rm:5  .... idx:1 . rn:5 rd:5  &rrx_e esz=3
 
 @rr_q1e0        ........ ........ ...... rn:5 rd:5      &qrr_e q=1 esz=0
+@rr_q1e2        ........ ........ ...... rn:5 rd:5      &qrr_e q=1 esz=2
 @r2r_q1e0       ........ ........ ...... rm:5 rd:5      &qrrr_e rn=%rd q=1 esz=0
 @rrr_q1e0       ........ ... rm:5 ...... rn:5 rd:5      &qrrr_e q=1 esz=0
 @rrr_q1e3       ........ ... rm:5 ...... rn:5 rd:5      &qrrr_e q=1 esz=3
 @rrrr_q1e3      ........ ... rm:5 . ra:5 rn:5 rd:5      &qrrrr_e q=1 esz=3
 
+@qrr_h          . q:1 ...... .. ...... ...... rn:5 rd:5  &qrr_e esz=1
 @qrr_e          . q:1 ...... esz:2 ...... ...... rn:5 rd:5  &qrr_e
 
 @qrrr_b         . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=0
@@ -XXX,XX +XXX,XX @@ SMAXV           0.00 1110 .. 11000 01010 10 ..... .....     @qrr_e
 UMAXV           0.10 1110 .. 11000 01010 10 ..... .....     @qrr_e
 SMINV           0.00 1110 .. 11000 11010 10 ..... .....     @qrr_e
 UMINV           0.10 1110 .. 11000 11010 10 ..... .....     @qrr_e
+
+FMAXNMV_h       0.00 1110 00 11000 01100 10 ..... .....     @qrr_h
+FMAXNMV_s       0110 1110 00 11000 01100 10 ..... .....     @rr_q1e2
+
+FMINNMV_h       0.00 1110 10 11000 01100 10 ..... .....     @qrr_h
+FMINNMV_s       0110 1110 10 11000 01100 10 ..... .....     @rr_q1e2
+
+FMAXV_h         0.00 1110 00 11000 01111 10 ..... .....     @qrr_h
+FMAXV_s         0110 1110 00 11000 01111 10 ..... .....     @rr_q1e2
+
+FMINV_h         0.00 1110 10 11000 01111 10 ..... .....     @qrr_h
+FMINV_s         0110 1110 10 11000 01111 10 ..... .....     @rr_q1e2
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ TRANS(UMAXV, do_int_reduction, a, false, 0, tcg_gen_umax_i64)
 TRANS(SMINV, do_int_reduction, a, false, MO_SIGN, tcg_gen_smin_i64)
 TRANS(UMINV, do_int_reduction, a, false, 0, tcg_gen_umin_i64)
 
+/*
+ * do_fp_reduction helper
+ *
+ * This mirrors the Reduce() pseudocode in the ARM ARM. It is
+ * important for correct NaN propagation that we do these
+ * operations in exactly the order specified by the pseudocode.
+ *
+ * This is a recursive function.
+ */
+static TCGv_i32 do_reduction_op(DisasContext *s, int rn, MemOp esz,
+                                int ebase, int ecount, TCGv_ptr fpst,
+                                NeonGenTwoSingleOpFn *fn)
+{
+    if (ecount == 1) {
+        TCGv_i32 tcg_elem = tcg_temp_new_i32();
+        read_vec_element_i32(s, tcg_elem, rn, ebase, esz);
+        return tcg_elem;
+    } else {
+        int half = ecount >> 1;
+        TCGv_i32 tcg_hi, tcg_lo, tcg_res;
+
+        tcg_hi = do_reduction_op(s, rn, esz, ebase + half, half, fpst, fn);
+        tcg_lo = do_reduction_op(s, rn, esz, ebase, half, fpst, fn);
+        tcg_res = tcg_temp_new_i32();
+
+        fn(tcg_res, tcg_lo, tcg_hi, fpst);
+        return tcg_res;
+    }
+}
+
+static bool do_fp_reduction(DisasContext *s, arg_qrr_e *a,
+                              NeonGenTwoSingleOpFn *fn)
+{
+    if (fp_access_check(s)) {
+        MemOp esz = a->esz;
+        int elts = (a->q ? 16 : 8) >> esz;
+        TCGv_ptr fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
+        TCGv_i32 res = do_reduction_op(s, a->rn, esz, 0, elts, fpst, fn);
+        write_fp_sreg(s, a->rd, res);
+    }
+    return true;
+}
+
+TRANS_FEAT(FMAXNMV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_maxnumh)
+TRANS_FEAT(FMINNMV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_minnumh)
+TRANS_FEAT(FMAXV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_maxh)
+TRANS_FEAT(FMINV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_minh)
+
+TRANS(FMAXNMV_s, do_fp_reduction, a, gen_helper_vfp_maxnums)
+TRANS(FMINNMV_s, do_fp_reduction, a, gen_helper_vfp_minnums)
+TRANS(FMAXV_s, do_fp_reduction, a, gen_helper_vfp_maxs)
+TRANS(FMINV_s, do_fp_reduction, a, gen_helper_vfp_mins)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
-/*
- * do_reduction_op helper
- *
- * This mirrors the Reduce() pseudocode in the ARM ARM. It is
- * important for correct NaN propagation that we do these
- * operations in exactly the order specified by the pseudocode.
- *
- * This is a recursive function.
- */
-static TCGv_i32 do_reduction_op(DisasContext *s, int fpopcode, int rn,
-                                MemOp esz, int ebase, int ecount, TCGv_ptr fpst)
-{
-    if (ecount == 1) {
-        TCGv_i32 tcg_elem = tcg_temp_new_i32();
-        read_vec_element_i32(s, tcg_elem, rn, ebase, esz);
-        return tcg_elem;
-    } else {
-        int half = ecount >> 1;
-        TCGv_i32 tcg_hi, tcg_lo, tcg_res;
-
-        tcg_hi = do_reduction_op(s, fpopcode, rn, esz,
-                                 ebase + half, half, fpst);
-        tcg_lo = do_reduction_op(s, fpopcode, rn, esz,
-                                 ebase, half, fpst);
-        tcg_res = tcg_temp_new_i32();
-
-        switch (fpopcode) {
-        case 0x0c: /* fmaxnmv half-precision */
-            gen_helper_advsimd_maxnumh(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x0f: /* fmaxv half-precision */
-            gen_helper_advsimd_maxh(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x1c: /* fminnmv half-precision */
-            gen_helper_advsimd_minnumh(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x1f: /* fminv half-precision */
-            gen_helper_advsimd_minh(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x2c: /* fmaxnmv */
-            gen_helper_vfp_maxnums(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x2f: /* fmaxv */
-            gen_helper_vfp_maxs(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x3c: /* fminnmv */
-            gen_helper_vfp_minnums(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        case 0x3f: /* fminv */
-            gen_helper_vfp_mins(tcg_res, tcg_lo, tcg_hi, fpst);
-            break;
-        default:
-            g_assert_not_reached();
-        }
-        return tcg_res;
-    }
-}
-
-/* AdvSIMD across lanes
- *   31  30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
- * +---+---+---+-----------+------+-----------+--------+-----+------+------+
- * | 0 | Q | U | 0 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 |  Rn  |  Rd  |
- * +---+---+---+-----------+------+-----------+--------+-----+------+------+
- */
-static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
-{
-    int rd = extract32(insn, 0, 5);
-    int rn = extract32(insn, 5, 5);
-    int size = extract32(insn, 22, 2);
-    int opcode = extract32(insn, 12, 5);
-    bool is_q = extract32(insn, 30, 1);
-    bool is_u = extract32(insn, 29, 1);
-    bool is_min = false;
-    int elements;
-
-    switch (opcode) {
-    case 0xc: /* FMAXNMV, FMINNMV */
-    case 0xf: /* FMAXV, FMINV */
-        /* Bit 1 of size field encodes min vs max and the actual size
-         * depends on the encoding of the U bit. If not set (and FP16
-         * enabled) then we do half-precision float instead of single
-         * precision.
-         */
-        is_min = extract32(size, 1, 1);
-        if (!is_u && dc_isar_feature(aa64_fp16, s)) {
-            size = 1;
-        } else if (!is_u || !is_q || extract32(size, 0, 1)) {
-            unallocated_encoding(s);
-            return;
-        } else {
-            size = 2;
-        }
-        break;
-    default:
-    case 0x3: /* SADDLV, UADDLV */
-    case 0xa: /* SMAXV, UMAXV */
-    case 0x1a: /* SMINV, UMINV */
-    case 0x1b: /* ADDV */
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    elements = (is_q ? 16 : 8) >> size;
-
-    {
-        /* Floating point vector reduction ops which work across 32
-         * bit (single) or 16 bit (half-precision) intermediates.
-         * Note that correct NaN propagation requires that we do these
-         * operations in exactly the order specified by the pseudocode.
-         */
-        TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
-        int fpopcode = opcode | is_min << 4 | is_u << 5;
-        TCGv_i32 tcg_res = do_reduction_op(s, fpopcode, rn, size,
-                                           0, elements, fpst);
-        write_fp_sreg(s, rd, tcg_res);
-    }
-}
-
 /* AdvSIMD modified immediate
  *  31  30   29  28                 19 18 16 15   12  11  10  9     5 4    0
  * +---+---+----+---------------------+-----+-------+----+---+-------+------+
@@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
 static const AArch64DecodeTable data_proc_simd[] = {
     /* pattern  ,  mask     ,  fn                        */
     { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc },
-    { 0x0e300800, 0x9f3e0c00, disas_simd_across_lanes },
     /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */
     { 0x0f000400, 0x9ff80400, disas_simd_mod_imm },
     { 0x0f000400, 0x9f800400, disas_simd_shift_imm },
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  4 ++
 target/arm/tcg/translate-a64.c | 74 ++++++++++++----------------------
 2 files changed, 30 insertions(+), 48 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |   9 +++
 target/arm/tcg/translate-a64.c | 117 ++++++++++++++-------------------
 2 files changed, 59 insertions(+), 67 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@ FMINV_s         0110 1110 10 11000 01111 10 ..... .....     @rr_q1e2
 # Floating-point Immediate
 
 FMOVI_s         0001 1110 .. 1 imm:8 100 00000 rd:5         esz=%esz_hsd
+
+# Advanced SIMD Modified Immediate
+
+%abcdefgh       16:3 5:5
+
+FMOVI_v_h       0 q:1 00 1111 00000 ... 1111 11 ..... rd:5  %abcdefgh
+
+# MOVI, MVNI, ORR, BIC, FMOV are all intermixed via cmode.
+Vimm            0 q:1 op:1 0 1111 00000 ... cmode:4 01 ..... rd:5 %abcdefgh
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool trans_FMOVI_s(DisasContext *s, arg_FMOVI_s *a)
     return true;
 }
 
+/*
+ * Advanced SIMD Modified Immediate
+ */
+
+static bool trans_FMOVI_v_h(DisasContext *s, arg_FMOVI_v_h *a)
+{
+    if (!dc_isar_feature(aa64_fp16, s)) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        tcg_gen_gvec_dup_imm(MO_16, vec_full_reg_offset(s, a->rd),
+                             a->q ? 16 : 8, vec_full_reg_size(s),
+                             vfp_expand_imm(MO_16, a->abcdefgh));
+    }
+    return true;
+}
+
+static void gen_movi(unsigned vece, uint32_t dofs, uint32_t aofs,
+                     int64_t c, uint32_t oprsz, uint32_t maxsz)
+{
+    tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, c);
+}
+
+static bool trans_Vimm(DisasContext *s, arg_Vimm *a)
+{
+    GVecGen2iFn *fn;
+
+    /* Handle decode of cmode/op here between ORR/BIC/MOVI */
+    if ((a->cmode & 1) && a->cmode < 12) {
+        /* For op=1, the imm will be inverted, so BIC becomes AND. */
+        fn = a->op ? tcg_gen_gvec_andi : tcg_gen_gvec_ori;
+    } else {
+        /* There is one unallocated cmode/op combination in this space */
+        if (a->cmode == 15 && a->op == 1 && a->q == 0) {
+            return false;
+        }
+        fn = gen_movi;
+    }
+
+    if (fp_access_check(s)) {
+        uint64_t imm = asimd_imm_const(a->abcdefgh, a->cmode, a->op);
+        gen_gvec_fn2i(s, a->q, a->rd, a->rd, imm, fn, MO_64);
+    }
+    return true;
+}
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
-/* AdvSIMD modified immediate
- *  31  30   29  28                 19 18 16 15   12  11  10  9     5 4    0
- * +---+---+----+---------------------+-----+-------+----+---+-------+------+
- * | 0 | Q | op | 0 1 1 1 1 0 0 0 0 0 | abc | cmode | o2 | 1 | defgh |  Rd  |
- * +---+---+----+---------------------+-----+-------+----+---+-------+------+
- *
- * There are a number of operations that can be carried out here:
- *   MOVI - move (shifted) imm into register
- *   MVNI - move inverted (shifted) imm into register
- *   ORR  - bitwise OR of (shifted) imm with register
- *   BIC  - bitwise clear of (shifted) imm with register
- * With ARMv8.2 we also have:
- *   FMOV half-precision
- */
-static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
-{
-    int rd = extract32(insn, 0, 5);
-    int cmode = extract32(insn, 12, 4);
-    int o2 = extract32(insn, 11, 1);
-    uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5);
-    bool is_neg = extract32(insn, 29, 1);
-    bool is_q = extract32(insn, 30, 1);
-    uint64_t imm = 0;
-
-    if (o2) {
-        if (cmode != 0xf || is_neg) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* FMOV (vector, immediate) - half-precision */
-        if (!dc_isar_feature(aa64_fp16, s)) {
-            unallocated_encoding(s);
-            return;
-        }
-        imm = vfp_expand_imm(MO_16, abcdefgh);
-        /* now duplicate across the lanes */
-        imm = dup_const(MO_16, imm);
-    } else {
-        if (cmode == 0xf && is_neg && !is_q) {
-            unallocated_encoding(s);
-            return;
-        }
-        imm = asimd_imm_const(abcdefgh, cmode, is_neg);
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) {
-        /* MOVI or MVNI, with MVNI negation handled above.  */
-        tcg_gen_gvec_dup_imm(MO_64, vec_full_reg_offset(s, rd), is_q ? 16 : 8,
-                             vec_full_reg_size(s), imm);
-    } else {
-        /* ORR or BIC, with BIC negation to AND handled above.  */
-        if (is_neg) {
-            gen_gvec_fn2i(s, is_q, rd, rd, imm, tcg_gen_gvec_andi, MO_64);
-        } else {
-            gen_gvec_fn2i(s, is_q, rd, rd, imm, tcg_gen_gvec_ori, MO_64);
-        }
-    }
-}
-
 /*
  * Common SSHR[RA]/USHR[RA] - Shift right (optional rounding/accumulate)
  *
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     bool is_u = extract32(insn, 29, 1);
     bool is_q = extract32(insn, 30, 1);
 
-    /* data_proc_simd[] has sent immh == 0 to disas_simd_mod_imm. */
-    assert(immh != 0);
+    if (immh == 0) {
+        unallocated_encoding(s);
+        return;
+    }
 
     switch (opcode) {
     case 0x08: /* SRI */
@@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
 static const AArch64DecodeTable data_proc_simd[] = {
     /* pattern  ,  mask     ,  fn                        */
     { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc },
-    /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */
-    { 0x0f000400, 0x9ff80400, disas_simd_mod_imm },
     { 0x0f000400, 0x9f800400, disas_simd_shift_imm },
     { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc },
     { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm },
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Handle the two special cases within these new
functions instead of higher in the call stack.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-15-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate.h      |  5 +++++
 target/arm/tcg/gengvec.c        | 19 +++++++++++++++++++
 target/arm/tcg/translate-a64.c  | 16 +---------------
 target/arm/tcg/translate-neon.c | 25 ++-----------------------
 4 files changed, 27 insertions(+), 38 deletions(-)

diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -XXX,XX +XXX,XX @@ void gen_sqsub_d(TCGv_i64 d, TCGv_i64 q, TCGv_i64 a, TCGv_i64 b);
 void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                        uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 
+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);
+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);
+
 void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
                    int64_t shift, uint32_t opr_sz, uint32_t max_sz);
 void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -XXX,XX +XXX,XX @@ 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);
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u,
         break;
 
     case 0x00: /* SSHR / USHR */
-        if (is_u) {
-            if (shift == 8 << size) {
-                /* Shift count the same size as element size produces zero.  */
-                tcg_gen_gvec_dup_imm(size, vec_full_reg_offset(s, rd),
-                                     is_q ? 16 : 8, vec_full_reg_size(s), 0);
-                return;
-            }
-            gvec_fn = tcg_gen_gvec_shri;
-        } else {
-            /* Shift count the same size as element size produces all sign.  */
-            if (shift == 8 << size) {
-                shift -= 1;
-            }
-            gvec_fn = tcg_gen_gvec_sari;
-        }
+        gvec_fn = is_u ? gen_gvec_ushr : gen_gvec_sshr;
         break;
 
     case 0x04: /* SRSHR / URSHR (rounding) */
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -XXX,XX +XXX,XX @@ DO_2SH(VRSHR_S, gen_gvec_srshr)
 DO_2SH(VRSHR_U, gen_gvec_urshr)
 DO_2SH(VRSRA_S, gen_gvec_srsra)
 DO_2SH(VRSRA_U, gen_gvec_ursra)
-
-static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a)
-{
-    /* Signed shift out of range results in all-sign-bits */
-    a->shift = MIN(a->shift, (8 << a->size) - 1);
-    return do_vector_2sh(s, a, tcg_gen_gvec_sari);
-}
-
-static void gen_zero_rd_2sh(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs,
-                            int64_t shift, uint32_t oprsz, uint32_t maxsz)
-{
-    tcg_gen_gvec_dup_imm(vece, rd_ofs, oprsz, maxsz, 0);
-}
-
-static bool trans_VSHR_U_2sh(DisasContext *s, arg_2reg_shift *a)
-{
-    /* Shift out of range is architecturally valid and results in zero. */
-    if (a->shift >= (8 << a->size)) {
-        return do_vector_2sh(s, a, gen_zero_rd_2sh);
-    } else {
-        return do_vector_2sh(s, a, tcg_gen_gvec_shri);
-    }
-}
+DO_2SH(VSHR_S, gen_gvec_sshr)
+DO_2SH(VSHR_U, gen_gvec_ushr)
 
 static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a,
                              NeonGenTwo64OpEnvFn *fn)
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

This includes SSHR, USHR, SSRA, USRA, SRSHR, URSHR, SRSRA, URSRA, SRI.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-17-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      | 63 ++++++++++++++++++++++++-
 target/arm/tcg/translate-a64.c | 86 +++++++++++-----------------------
 2 files changed, 89 insertions(+), 60 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@
 &rrx_e          rd rn rm idx esz
 &rrrr_e         rd rn rm ra esz
 &qrr_e          q rd rn esz
+&qrri_e         q rd rn imm esz
 &qrrr_e         q rd rn rm esz
 &qrrx_e         q rd rn rm idx esz
 &qrrrr_e        q rd rn rm ra esz
@@ -XXX,XX +XXX,XX @@ FMINV_s         0110 1110 10 11000 01111 10 ..... .....     @rr_q1e2
 
 FMOVI_s         0001 1110 .. 1 imm:8 100 00000 rd:5         esz=%esz_hsd
 
-# Advanced SIMD Modified Immediate
+# Advanced SIMD Modified Immediate / Shift by Immediate
 
 %abcdefgh       16:3 5:5
 
+# Right shifts are encoded as N - shift, where N is the element size in bits.
+%neon_rshift_i6 16:6 !function=rsub_64
+%neon_rshift_i5 16:5 !function=rsub_32
+%neon_rshift_i4 16:4 !function=rsub_16
+%neon_rshift_i3 16:3 !function=rsub_8
+
+@q_shri_b       . q:1 .. ..... 0001 ... ..... . rn:5 rd:5   \
+                &qrri_e esz=0 imm=%neon_rshift_i3
+@q_shri_h       . q:1 .. ..... 001 .... ..... . rn:5 rd:5   \
+                &qrri_e esz=1 imm=%neon_rshift_i4
+@q_shri_s       . q:1 .. ..... 01 ..... ..... . rn:5 rd:5   \
+                &qrri_e esz=2 imm=%neon_rshift_i5
+@q_shri_d       . 1 .. ..... 1 ...... ..... . rn:5 rd:5     \
+                &qrri_e esz=3 imm=%neon_rshift_i6 q=1
+
 FMOVI_v_h       0 q:1 00 1111 00000 ... 1111 11 ..... rd:5  %abcdefgh
 
 # MOVI, MVNI, ORR, BIC, FMOV are all intermixed via cmode.
 Vimm            0 q:1 op:1 0 1111 00000 ... cmode:4 01 ..... rd:5 %abcdefgh
+
+SSHR_v          0.00 11110 .... ... 00000 1 ..... .....     @q_shri_b
+SSHR_v          0.00 11110 .... ... 00000 1 ..... .....     @q_shri_h
+SSHR_v          0.00 11110 .... ... 00000 1 ..... .....     @q_shri_s
+SSHR_v          0.00 11110 .... ... 00000 1 ..... .....     @q_shri_d
+
+USHR_v          0.10 11110 .... ... 00000 1 ..... .....     @q_shri_b
+USHR_v          0.10 11110 .... ... 00000 1 ..... .....     @q_shri_h
+USHR_v          0.10 11110 .... ... 00000 1 ..... .....     @q_shri_s
+USHR_v          0.10 11110 .... ... 00000 1 ..... .....     @q_shri_d
+
+SSRA_v          0.00 11110 .... ... 00010 1 ..... .....     @q_shri_b
+SSRA_v          0.00 11110 .... ... 00010 1 ..... .....     @q_shri_h
+SSRA_v          0.00 11110 .... ... 00010 1 ..... .....     @q_shri_s
+SSRA_v          0.00 11110 .... ... 00010 1 ..... .....     @q_shri_d
+
+USRA_v          0.10 11110 .... ... 00010 1 ..... .....     @q_shri_b
+USRA_v          0.10 11110 .... ... 00010 1 ..... .....     @q_shri_h
+USRA_v          0.10 11110 .... ... 00010 1 ..... .....     @q_shri_s
+USRA_v          0.10 11110 .... ... 00010 1 ..... .....     @q_shri_d
+
+SRSHR_v         0.00 11110 .... ... 00100 1 ..... .....     @q_shri_b
+SRSHR_v         0.00 11110 .... ... 00100 1 ..... .....     @q_shri_h
+SRSHR_v         0.00 11110 .... ... 00100 1 ..... .....     @q_shri_s
+SRSHR_v         0.00 11110 .... ... 00100 1 ..... .....     @q_shri_d
+
+URSHR_v         0.10 11110 .... ... 00100 1 ..... .....     @q_shri_b
+URSHR_v         0.10 11110 .... ... 00100 1 ..... .....     @q_shri_h
+URSHR_v         0.10 11110 .... ... 00100 1 ..... .....     @q_shri_s
+URSHR_v         0.10 11110 .... ... 00100 1 ..... .....     @q_shri_d
+
+SRSRA_v         0.00 11110 .... ... 00110 1 ..... .....     @q_shri_b
+SRSRA_v         0.00 11110 .... ... 00110 1 ..... .....     @q_shri_h
+SRSRA_v         0.00 11110 .... ... 00110 1 ..... .....     @q_shri_s
+SRSRA_v         0.00 11110 .... ... 00110 1 ..... .....     @q_shri_d
+
+URSRA_v         0.10 11110 .... ... 00110 1 ..... .....     @q_shri_b
+URSRA_v         0.10 11110 .... ... 00110 1 ..... .....     @q_shri_h
+URSRA_v         0.10 11110 .... ... 00110 1 ..... .....     @q_shri_s
+URSRA_v         0.10 11110 .... ... 00110 1 ..... .....     @q_shri_d
+
+SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_b
+SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_h
+SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_s
+SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_d
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool trans_Vimm(DisasContext *s, arg_Vimm *a)
     return true;
 }
 
+/*
+ * Advanced SIMD Shift by Immediate
+ */
+
+static bool do_vec_shift_imm(DisasContext *s, arg_qrri_e *a, GVecGen2iFn *fn)
+{
+    if (fp_access_check(s)) {
+        gen_gvec_fn2i(s, a->q, a->rd, a->rn, a->imm, fn, a->esz);
+    }
+    return true;
+}
+
+TRANS(SSHR_v, do_vec_shift_imm, a, gen_gvec_sshr)
+TRANS(USHR_v, do_vec_shift_imm, a, gen_gvec_ushr)
+TRANS(SSRA_v, do_vec_shift_imm, a, gen_gvec_ssra)
+TRANS(USRA_v, do_vec_shift_imm, a, gen_gvec_usra)
+TRANS(SRSHR_v, do_vec_shift_imm, a, gen_gvec_srshr)
+TRANS(URSHR_v, do_vec_shift_imm, a, gen_gvec_urshr)
+TRANS(SRSRA_v, do_vec_shift_imm, a, gen_gvec_srsra)
+TRANS(URSRA_v, do_vec_shift_imm, a, gen_gvec_ursra)
+TRANS(SRI_v, do_vec_shift_imm, a, gen_gvec_sri)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
     }
 }
 
-/* SSHR[RA]/USHR[RA] - Vector shift right (optional rounding/accumulate) */
-static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u,
-                                 int immh, int immb, int opcode, int rn, int rd)
-{
-    int size = 32 - clz32(immh) - 1;
-    int immhb = immh << 3 | immb;
-    int shift = 2 * (8 << size) - immhb;
-    GVecGen2iFn *gvec_fn;
-
-    if (extract32(immh, 3, 1) && !is_q) {
-        unallocated_encoding(s);
-        return;
-    }
-    tcg_debug_assert(size <= 3);
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    switch (opcode) {
-    case 0x02: /* SSRA / USRA (accumulate) */
-        gvec_fn = is_u ? gen_gvec_usra : gen_gvec_ssra;
-        break;
-
-    case 0x08: /* SRI */
-        gvec_fn = gen_gvec_sri;
-        break;
-
-    case 0x00: /* SSHR / USHR */
-        gvec_fn = is_u ? gen_gvec_ushr : gen_gvec_sshr;
-        break;
-
-    case 0x04: /* SRSHR / URSHR (rounding) */
-        gvec_fn = is_u ? gen_gvec_urshr : gen_gvec_srshr;
-        break;
-
-    case 0x06: /* SRSRA / URSRA (accum + rounding) */
-        gvec_fn = is_u ? gen_gvec_ursra : gen_gvec_srsra;
-        break;
-
-    default:
-        g_assert_not_reached();
-    }
-
-    gen_gvec_fn2i(s, is_q, rd, rn, shift, gvec_fn, size);
-}
-
 /* SHL/SLI - Vector shift left */
 static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert,
                                  int immh, int immb, int opcode, int rn, int rd)
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x08: /* SRI */
-        if (!is_u) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* fall through */
-    case 0x00: /* SSHR / USHR */
-    case 0x02: /* SSRA / USRA (accumulate) */
-    case 0x04: /* SRSHR / URSHR (rounding) */
-    case 0x06: /* SRSRA / URSRA (accum + rounding) */
-        handle_vec_simd_shri(s, is_q, is_u, immh, immb, opcode, rn, rd);
-        break;
     case 0x0a: /* SHL / SLI */
         handle_vec_simd_shli(s, is_q, is_u, immh, immb, opcode, rn, rd);
         break;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
         handle_simd_shift_fpint_conv(s, false, is_q, is_u, immh, immb, rn, rd);
         return;
     default:
+    case 0x00: /* SSHR / USHR */
+    case 0x02: /* SSRA / USRA (accumulate) */
+    case 0x04: /* SRSHR / URSHR (rounding) */
+    case 0x06: /* SRSRA / URSRA (accum + rounding) */
+    case 0x08: /* SRI */
         unallocated_encoding(s);
         return;
     }
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

This includes SHL and SLI.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      | 15 +++++++++++++++
 target/arm/tcg/translate-a64.c | 33 +++------------------------------
 2 files changed, 18 insertions(+), 30 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@ FMOVI_s         0001 1110 .. 1 imm:8 100 00000 rd:5         esz=%esz_hsd
 @q_shri_d       . 1 .. ..... 1 ...... ..... . rn:5 rd:5     \
                 &qrri_e esz=3 imm=%neon_rshift_i6 q=1
 
+@q_shli_b       . q:1 .. ..... 0001 imm:3 ..... . rn:5 rd:5 &qrri_e esz=0
+@q_shli_h       . q:1 .. ..... 001  imm:4 ..... . rn:5 rd:5 &qrri_e esz=1
+@q_shli_s       . q:1 .. ..... 01   imm:5 ..... . rn:5 rd:5 &qrri_e esz=2
+@q_shli_d       . 1   .. ..... 1    imm:6 ..... . rn:5 rd:5 &qrri_e esz=3 q=1
+
 FMOVI_v_h       0 q:1 00 1111 00000 ... 1111 11 ..... rd:5  %abcdefgh
 
 # MOVI, MVNI, ORR, BIC, FMOV are all intermixed via cmode.
@@ -XXX,XX +XXX,XX @@ SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_b
 SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_h
 SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_s
 SRI_v           0.10 11110 .... ... 01000 1 ..... .....     @q_shri_d
+
+SHL_v           0.00 11110 .... ... 01010 1 ..... .....     @q_shli_b
+SHL_v           0.00 11110 .... ... 01010 1 ..... .....     @q_shli_h
+SHL_v           0.00 11110 .... ... 01010 1 ..... .....     @q_shli_s
+SHL_v           0.00 11110 .... ... 01010 1 ..... .....     @q_shli_d
+
+SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_b
+SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_h
+SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_s
+SLI_v           0.10 11110 .... ... 01010 1 ..... .....     @q_shli_d
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ TRANS(URSHR_v, do_vec_shift_imm, a, gen_gvec_urshr)
 TRANS(SRSRA_v, do_vec_shift_imm, a, gen_gvec_srsra)
 TRANS(URSRA_v, do_vec_shift_imm, a, gen_gvec_ursra)
 TRANS(SRI_v, do_vec_shift_imm, a, gen_gvec_sri)
+TRANS(SHL_v, do_vec_shift_imm, a, tcg_gen_gvec_shli)
+TRANS(SLI_v, do_vec_shift_imm, a, gen_gvec_sli);
 
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
     }
 }
 
-/* SHL/SLI - Vector shift left */
-static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert,
-                                 int immh, int immb, int opcode, int rn, int rd)
-{
-    int size = 32 - clz32(immh) - 1;
-    int immhb = immh << 3 | immb;
-    int shift = immhb - (8 << size);
-
-    /* Range of size is limited by decode: immh is a non-zero 4 bit field */
-    assert(size >= 0 && size <= 3);
-
-    if (extract32(immh, 3, 1) && !is_q) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    if (insert) {
-        gen_gvec_fn2i(s, is_q, rd, rn, shift, gen_gvec_sli, size);
-    } else {
-        gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shli, size);
-    }
-}
-
 /* USHLL/SHLL - Vector shift left with widening */
 static void handle_vec_simd_wshli(DisasContext *s, bool is_q, bool is_u,
                                  int immh, int immb, int opcode, int rn, int rd)
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x0a: /* SHL / SLI */
-        handle_vec_simd_shli(s, is_q, is_u, immh, immb, opcode, rn, rd);
-        break;
     case 0x10: /* SHRN */
     case 0x11: /* RSHRN / SQRSHRUN */
         if (is_u) {
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     case 0x04: /* SRSHR / URSHR (rounding) */
     case 0x06: /* SRSRA / URSRA (accum + rounding) */
     case 0x08: /* SRI */
+    case 0x0a: /* SHL / SLI */
         unallocated_encoding(s);
         return;
     }
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Combine the right shift with the extension via
the tcg extract operations.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-20-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  8 ++++
 target/arm/tcg/translate-a64.c | 81 ++++++++++++++++------------------
 2 files changed, 45 insertions(+), 44 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

We always pass the same value for round; compute it
within common code.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-21-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 32 ++++++--------------------------
 1 file changed, 6 insertions(+), 26 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
  * the vector and scalar code.
  */
 static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
-                                    TCGv_i64 tcg_rnd, bool accumulate,
+                                    bool round, bool accumulate,
                                     bool is_u, int size, int shift)
 {
     bool extended_result = false;
-    bool round = tcg_rnd != NULL;
     int ext_lshift = 0;
     TCGv_i64 tcg_src_hi;
 
@@ -XXX,XX +XXX,XX @@ static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
 
     /* Deal with the rounding step */
     if (round) {
+        TCGv_i64 tcg_rnd = tcg_constant_i64(1ull << (shift - 1));
         if (extended_result) {
             TCGv_i64 tcg_zero = tcg_constant_i64(0);
             if (!is_u) {
@@ -XXX,XX +XXX,XX @@ static void handle_scalar_simd_shri(DisasContext *s,
     bool insert = false;
     TCGv_i64 tcg_rn;
     TCGv_i64 tcg_rd;
-    TCGv_i64 tcg_round;
 
     if (!extract32(immh, 3, 1)) {
         unallocated_encoding(s);
@@ -XXX,XX +XXX,XX @@ static void handle_scalar_simd_shri(DisasContext *s,
         break;
     }
 
-    if (round) {
-        tcg_round = tcg_constant_i64(1ULL << (shift - 1));
-    } else {
-        tcg_round = NULL;
-    }
-
     tcg_rn = read_fp_dreg(s, rn);
     tcg_rd = (accumulate || insert) ? read_fp_dreg(s, rd) : tcg_temp_new_i64();
 
@@ -XXX,XX +XXX,XX @@ static void handle_scalar_simd_shri(DisasContext *s,
             tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_rn, 0, esize - shift);
         }
     } else {
-        handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+        handle_shri_with_rndacc(tcg_rd, tcg_rn, round,
                                 accumulate, is_u, size, shift);
     }
 
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
     int elements = is_scalar ? 1 : (64 / esize);
     bool round = extract32(opcode, 0, 1);
     MemOp ldop = (size + 1) | (is_u_shift ? 0 : MO_SIGN);
-    TCGv_i64 tcg_rn, tcg_rd, tcg_round;
+    TCGv_i64 tcg_rn, tcg_rd;
     TCGv_i32 tcg_rd_narrowed;
     TCGv_i64 tcg_final;
 
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
     tcg_rd_narrowed = tcg_temp_new_i32();
     tcg_final = tcg_temp_new_i64();
 
-    if (round) {
-        tcg_round = tcg_constant_i64(1ULL << (shift - 1));
-    } else {
-        tcg_round = NULL;
-    }
-
     for (i = 0; i < elements; i++) {
         read_vec_element(s, tcg_rn, rn, i, ldop);
-        handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+        handle_shri_with_rndacc(tcg_rd, tcg_rn, round,
                                 false, is_u_shift, size+1, shift);
         narrowfn(tcg_rd_narrowed, tcg_env, tcg_rd);
         tcg_gen_extu_i32_i64(tcg_rd, tcg_rd_narrowed);
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shrn(DisasContext *s, bool is_q,
     int shift = (2 * esize) - immhb;
     bool round = extract32(opcode, 0, 1);
     TCGv_i64 tcg_rn, tcg_rd, tcg_final;
-    TCGv_i64 tcg_round;
     int i;
 
     if (extract32(immh, 3, 1)) {
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shrn(DisasContext *s, bool is_q,
     tcg_final = tcg_temp_new_i64();
     read_vec_element(s, tcg_final, rd, is_q ? 1 : 0, MO_64);
 
-    if (round) {
-        tcg_round = tcg_constant_i64(1ULL << (shift - 1));
-    } else {
-        tcg_round = NULL;
-    }
-
     for (i = 0; i < elements; i++) {
         read_vec_element(s, tcg_rn, rn, i, size+1);
-        handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+        handle_shri_with_rndacc(tcg_rd, tcg_rn, round,
                                 false, true, size+1, shift);
 
         tcg_gen_deposit_i64(tcg_final, tcg_final, tcg_rd, esize * i, esize);
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

There isn't a lot of commonality along the different paths of
handle_shri_with_rndacc.  Split them out to separate functions,
which will be usable during the decodetree conversion.

Simplify 64-bit rounding operations to not require double-word arithmetic.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-22-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 138 ++++++++++++++++++++-------------
 1 file changed, 82 insertions(+), 56 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool do_vec_shift_imm_wide(DisasContext *s, arg_qrri_e *a, bool is_u)
 TRANS(SSHLL_v, do_vec_shift_imm_wide, a, false)
 TRANS(USHLL_v, do_vec_shift_imm_wide, a, true)
 
+static void gen_sshr_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    assert(shift >= 0 && shift <= 64);
+    tcg_gen_sari_i64(dst, src, MIN(shift, 63));
+}
+
+static void gen_ushr_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    assert(shift >= 0 && shift <= 64);
+    if (shift == 64) {
+        tcg_gen_movi_i64(dst, 0);
+    } else {
+        tcg_gen_shri_i64(dst, src, shift);
+    }
+}
+
+static void gen_srshr_bhs(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    assert(shift >= 0 && shift <= 32);
+    if (shift) {
+        TCGv_i64 rnd = tcg_constant_i64(1ull << (shift - 1));
+        tcg_gen_add_i64(dst, src, rnd);
+        tcg_gen_sari_i64(dst, dst, shift);
+    } else {
+        tcg_gen_mov_i64(dst, src);
+    }
+}
+
+static void gen_urshr_bhs(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    assert(shift >= 0 && shift <= 32);
+    if (shift) {
+        TCGv_i64 rnd = tcg_constant_i64(1ull << (shift - 1));
+        tcg_gen_add_i64(dst, src, rnd);
+        tcg_gen_shri_i64(dst, dst, shift);
+    } else {
+        tcg_gen_mov_i64(dst, src);
+    }
+}
+
+static void gen_srshr_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    assert(shift >= 0 && shift <= 64);
+    if (shift == 0) {
+        tcg_gen_mov_i64(dst, src);
+    } else if (shift == 64) {
+        /* Extension of sign bit (0,-1) plus sign bit (0,1) is zero. */
+        tcg_gen_movi_i64(dst, 0);
+    } else {
+        TCGv_i64 rnd = tcg_temp_new_i64();
+        tcg_gen_extract_i64(rnd, src, shift - 1, 1);
+        tcg_gen_sari_i64(dst, src, shift);
+        tcg_gen_add_i64(dst, dst, rnd);
+    }
+}
+
+static void gen_urshr_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    assert(shift >= 0 && shift <= 64);
+    if (shift == 0) {
+        tcg_gen_mov_i64(dst, src);
+    } else if (shift == 64) {
+        /* Rounding will propagate bit 63 into bit 64. */
+        tcg_gen_shri_i64(dst, src, 63);
+    } else {
+        TCGv_i64 rnd = tcg_temp_new_i64();
+        tcg_gen_extract_i64(rnd, src, shift - 1, 1);
+        tcg_gen_shri_i64(dst, src, shift);
+        tcg_gen_add_i64(dst, dst, rnd);
+    }
+}
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
                                     bool round, bool accumulate,
                                     bool is_u, int size, int shift)
 {
-    bool extended_result = false;
-    int ext_lshift = 0;
-    TCGv_i64 tcg_src_hi;
-
-    if (round && size == 3) {
-        extended_result = true;
-        ext_lshift = 64 - shift;
-        tcg_src_hi = tcg_temp_new_i64();
-    } else if (shift == 64) {
-        if (!accumulate && is_u) {
-            /* result is zero */
-            tcg_gen_movi_i64(tcg_res, 0);
-            return;
-        }
-    }
-
-    /* Deal with the rounding step */
-    if (round) {
-        TCGv_i64 tcg_rnd = tcg_constant_i64(1ull << (shift - 1));
-        if (extended_result) {
-            TCGv_i64 tcg_zero = tcg_constant_i64(0);
-            if (!is_u) {
-                /* take care of sign extending tcg_res */
-                tcg_gen_sari_i64(tcg_src_hi, tcg_src, 63);
-                tcg_gen_add2_i64(tcg_src, tcg_src_hi,
-                                 tcg_src, tcg_src_hi,
-                                 tcg_rnd, tcg_zero);
-            } else {
-                tcg_gen_add2_i64(tcg_src, tcg_src_hi,
-                                 tcg_src, tcg_zero,
-                                 tcg_rnd, tcg_zero);
-            }
+    if (!round) {
+        if (is_u) {
+            gen_ushr_d(tcg_src, tcg_src, shift);
         } else {
-            tcg_gen_add_i64(tcg_src, tcg_src, tcg_rnd);
+            gen_sshr_d(tcg_src, tcg_src, shift);
         }
-    }
-
-    /* Now do the shift right */
-    if (round && extended_result) {
-        /* extended case, >64 bit precision required */
-        if (ext_lshift == 0) {
-            /* special case, only high bits matter */
-            tcg_gen_mov_i64(tcg_src, tcg_src_hi);
+    } else if (size == MO_64) {
+        if (is_u) {
+            gen_urshr_d(tcg_src, tcg_src, shift);
         } else {
-            tcg_gen_shri_i64(tcg_src, tcg_src, shift);
-            tcg_gen_shli_i64(tcg_src_hi, tcg_src_hi, ext_lshift);
-            tcg_gen_or_i64(tcg_src, tcg_src, tcg_src_hi);
+            gen_srshr_d(tcg_src, tcg_src, shift);
         }
     } else {
         if (is_u) {
-            if (shift == 64) {
-                /* essentially shifting in 64 zeros */
-                tcg_gen_movi_i64(tcg_src, 0);
-            } else {
-                tcg_gen_shri_i64(tcg_src, tcg_src, shift);
-            }
+            gen_urshr_bhs(tcg_src, tcg_src, shift);
         } else {
-            if (shift == 64) {
-                /* effectively extending the sign-bit */
-                tcg_gen_sari_i64(tcg_src, tcg_src, 63);
-            } else {
-                tcg_gen_sari_i64(tcg_src, tcg_src, shift);
-            }
+            gen_srshr_bhs(tcg_src, tcg_src, shift);
         }
     }
 
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-23-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  8 +++
 target/arm/tcg/translate-a64.c | 95 +++++++++++++++++-----------------
 2 files changed, 55 insertions(+), 48 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

This includes SSHR, USHR, SSRA, USRA, SRSHR, URSHR,
SRSRA, URSRA, SRI.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-24-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  16 ++++
 target/arm/tcg/translate-a64.c | 140 ++++++++++++++++-----------------
 2 files changed, 86 insertions(+), 70 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@
 &rri_sf         rd rn imm sf
 &i              imm
 &rr_e           rd rn esz
+&rri_e          rd rn imm esz
 &rrr_e          rd rn rm esz
 &rrx_e          rd rn rm idx esz
 &rrrr_e         rd rn rm ra esz
@@ -XXX,XX +XXX,XX @@ SHRN_v          0.00 11110 .... ... 10000 1 ..... .....     @q_shri_s
 RSHRN_v         0.00 11110 .... ... 10001 1 ..... .....     @q_shri_b
 RSHRN_v         0.00 11110 .... ... 10001 1 ..... .....     @q_shri_h
 RSHRN_v         0.00 11110 .... ... 10001 1 ..... .....     @q_shri_s
+
+# Advanced SIMD scalar shift by immediate
+
+@shri_d         .... ..... 1 ...... ..... . rn:5 rd:5   \
+                &rri_e esz=3 imm=%neon_rshift_i6
+
+SSHR_s          0101 11110 .... ... 00000 1 ..... .....     @shri_d
+USHR_s          0111 11110 .... ... 00000 1 ..... .....     @shri_d
+SSRA_s          0101 11110 .... ... 00010 1 ..... .....     @shri_d
+USRA_s          0111 11110 .... ... 00010 1 ..... .....     @shri_d
+SRSHR_s         0101 11110 .... ... 00100 1 ..... .....     @shri_d
+URSHR_s         0111 11110 .... ... 00100 1 ..... .....     @shri_d
+SRSRA_s         0101 11110 .... ... 00110 1 ..... .....     @shri_d
+URSRA_s         0111 11110 .... ... 00110 1 ..... .....     @shri_d
+SRI_s           0111 11110 .... ... 01000 1 ..... .....     @shri_d
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void gen_ushr_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
     }
 }
 
+static void gen_ssra_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    gen_sshr_d(src, src, shift);
+    tcg_gen_add_i64(dst, dst, src);
+}
+
+static void gen_usra_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    gen_ushr_d(src, src, shift);
+    tcg_gen_add_i64(dst, dst, src);
+}
+
 static void gen_srshr_bhs(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
 {
     assert(shift >= 0 && shift <= 32);
@@ -XXX,XX +XXX,XX @@ static void gen_urshr_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
     }
 }
 
+static void gen_srsra_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    gen_srshr_d(src, src, shift);
+    tcg_gen_add_i64(dst, dst, src);
+}
+
+static void gen_ursra_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    gen_urshr_d(src, src, shift);
+    tcg_gen_add_i64(dst, dst, src);
+}
+
+static void gen_sri_d(TCGv_i64 dst, TCGv_i64 src, int64_t shift)
+{
+    /* If shift is 64, dst is unchanged. */
+    if (shift != 64) {
+        tcg_gen_shri_i64(src, src, shift);
+        tcg_gen_deposit_i64(dst, dst, src, 0, 64 - shift);
+    }
+}
+
 static bool do_vec_shift_imm_narrow(DisasContext *s, arg_qrri_e *a,
                                     WideShiftImmFn * const fns[3], MemOp sign)
 {
@@ -XXX,XX +XXX,XX @@ static WideShiftImmFn * const rshrn_fns[] = {
 };
 TRANS(RSHRN_v, do_vec_shift_imm_narrow, a, rshrn_fns, 0)
 
+/*
+ * Advanced SIMD Scalar Shift by Immediate
+ */
+
+static bool do_scalar_shift_imm(DisasContext *s, arg_rri_e *a,
+                                WideShiftImmFn *fn, bool accumulate,
+                                MemOp sign)
+{
+    if (fp_access_check(s)) {
+        TCGv_i64 rd = tcg_temp_new_i64();
+        TCGv_i64 rn = tcg_temp_new_i64();
+
+        read_vec_element(s, rn, a->rn, 0, a->esz | sign);
+        if (accumulate) {
+            read_vec_element(s, rd, a->rd, 0, a->esz | sign);
+        }
+        fn(rd, rn, a->imm);
+        write_fp_dreg(s, a->rd, rd);
+    }
+    return true;
+}
+
+TRANS(SSHR_s, do_scalar_shift_imm, a, gen_sshr_d, false, 0)
+TRANS(USHR_s, do_scalar_shift_imm, a, gen_ushr_d, false, 0)
+TRANS(SSRA_s, do_scalar_shift_imm, a, gen_ssra_d, true, 0)
+TRANS(USRA_s, do_scalar_shift_imm, a, gen_usra_d, true, 0)
+TRANS(SRSHR_s, do_scalar_shift_imm, a, gen_srshr_d, false, 0)
+TRANS(URSHR_s, do_scalar_shift_imm, a, gen_urshr_d, false, 0)
+TRANS(SRSRA_s, do_scalar_shift_imm, a, gen_srsra_d, true, 0)
+TRANS(URSRA_s, do_scalar_shift_imm, a, gen_ursra_d, true, 0)
+TRANS(SRI_s, do_scalar_shift_imm, a, gen_sri_d, true, 0)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
     }
 }
 
-/* SSHR[RA]/USHR[RA] - Scalar shift right (optional rounding/accumulate) */
-static void handle_scalar_simd_shri(DisasContext *s,
-                                    bool is_u, int immh, int immb,
-                                    int opcode, int rn, int rd)
-{
-    const int size = 3;
-    int immhb = immh << 3 | immb;
-    int shift = 2 * (8 << size) - immhb;
-    bool accumulate = false;
-    bool round = false;
-    bool insert = false;
-    TCGv_i64 tcg_rn;
-    TCGv_i64 tcg_rd;
-
-    if (!extract32(immh, 3, 1)) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    switch (opcode) {
-    case 0x02: /* SSRA / USRA (accumulate) */
-        accumulate = true;
-        break;
-    case 0x04: /* SRSHR / URSHR (rounding) */
-        round = true;
-        break;
-    case 0x06: /* SRSRA / URSRA (accum + rounding) */
-        accumulate = round = true;
-        break;
-    case 0x08: /* SRI */
-        insert = true;
-        break;
-    }
-
-    tcg_rn = read_fp_dreg(s, rn);
-    tcg_rd = (accumulate || insert) ? read_fp_dreg(s, rd) : tcg_temp_new_i64();
-
-    if (insert) {
-        /* shift count same as element size is valid but does nothing;
-         * special case to avoid potential shift by 64.
-         */
-        int esize = 8 << size;
-        if (shift != esize) {
-            tcg_gen_shri_i64(tcg_rn, tcg_rn, shift);
-            tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_rn, 0, esize - shift);
-        }
-    } else {
-        handle_shri_with_rndacc(tcg_rd, tcg_rn, round,
-                                accumulate, is_u, size, shift);
-    }
-
-    write_fp_dreg(s, rd, tcg_rd);
-}
-
 /* SHL/SLI - Scalar shift left */
 static void handle_scalar_simd_shli(DisasContext *s, bool insert,
                                     int immh, int immb, int opcode,
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x08: /* SRI */
-        if (!is_u) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* fall through */
-    case 0x00: /* SSHR / USHR */
-    case 0x02: /* SSRA / USRA */
-    case 0x04: /* SRSHR / URSHR */
-    case 0x06: /* SRSRA / URSRA */
-        handle_scalar_simd_shri(s, is_u, immh, immb, opcode, rn, rd);
-        break;
     case 0x0a: /* SHL / SLI */
         handle_scalar_simd_shli(s, is_u, immh, immb, opcode, rn, rd);
         break;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
         handle_simd_shift_fpint_conv(s, true, false, is_u, immh, immb, rn, rd);
         break;
     default:
+    case 0x00: /* SSHR / USHR */
+    case 0x02: /* SSRA / USRA */
+    case 0x04: /* SRSHR / URSHR */
+    case 0x06: /* SRSRA / URSRA */
+    case 0x08: /* SRI */
         unallocated_encoding(s);
         break;
     }
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

This includes SHL and SLI.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-25-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  4 ++++
 target/arm/tcg/translate-a64.c | 44 +++++++---------------------------
 2 files changed, 13 insertions(+), 35 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-26-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h             |  12 ++++
 target/arm/tcg/translate.h      |   7 ++
 target/arm/tcg/neon-dp.decode   |   6 +-
 target/arm/tcg/gengvec.c        |  36 +++++++++++
 target/arm/tcg/neon_helper.c    |  33 ++++++++++
 target/arm/tcg/translate-neon.c | 110 +-------------------------------
 6 files changed, 94 insertions(+), 110 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_uqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32
 DEF_HELPER_FLAGS_5(neon_uqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_uqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_uqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_uqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(neon_sqshlui_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -XXX,XX +XXX,XX @@ void gen_neon_sqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
 void gen_neon_uqrshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                      uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 
+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);
+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);
+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);
+
 void gen_gvec_shadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
                     uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
 void gen_gvec_uhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
diff --git a/target/arm/tcg/neon-dp.decode b/target/arm/tcg/neon-dp.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/neon-dp.decode
+++ b/target/arm/tcg/neon-dp.decode
@@ -XXX,XX +XXX,XX @@ VSLI_2sh         1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s
 VSLI_2sh         1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h
 VSLI_2sh         1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b
 
-VQSHLU_64_2sh    1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d
+VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d
 VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_s
 VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_h
 VQSHLU_2sh       1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_b
 
-VQSHL_S_64_2sh   1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
+VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
 VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s
 VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h
 VQSHL_S_2sh      1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b
 
-VQSHL_U_64_2sh   1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
+VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d
 VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s
 VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h
 VQSHL_U_2sh      1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b
diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/gengvec.c
+++ b/target/arm/tcg/gengvec.c
@@ -XXX,XX +XXX,XX @@ 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);
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \
     clear_tail(d, opr_sz, simd_maxsz(desc));                    \
 }
 
+#define NEON_GVEC_VOP2i_ENV(name, vtype) \
+void HELPER(name)(void *vd, void *vn, void *venv, uint32_t desc) \
+{                                                               \
+    intptr_t i, opr_sz = simd_oprsz(desc);                      \
+    int imm = simd_data(desc);                                  \
+    vtype *d = vd, *n = vn;                                     \
+    CPUARMState *env = venv;                                    \
+    for (i = 0; i < opr_sz / sizeof(vtype); i++) {              \
+        NEON_FN(d[i], n[i], imm);                               \
+    }                                                           \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                    \
+}
+
 /* Pairwise operations.  */
 /* For 32-bit elements each segment only contains a single element, so
    the elementwise and pairwise operations are the same.  */
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift)
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_u8, neon_u8, 4)
 NEON_GVEC_VOP2_ENV(neon_uqshl_b, uint8_t)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_b, uint8_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_u16, neon_u16, 2)
 NEON_GVEC_VOP2_ENV(neon_uqshl_h, uint16_t)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_h, uint16_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc))
 NEON_GVEC_VOP2_ENV(neon_uqshl_s, uint32_t)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_s, uint32_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_d(src1, (int8_t)src2, false, env->vfp.qc))
 NEON_GVEC_VOP2_ENV(neon_uqshl_d, uint64_t)
+NEON_GVEC_VOP2i_ENV(neon_uqshli_d, uint64_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift)
     (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_s8, neon_s8, 4)
 NEON_GVEC_VOP2_ENV(neon_sqshl_b, int8_t)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_b, int8_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshl_s16, neon_s16, 2)
 NEON_GVEC_VOP2_ENV(neon_sqshl_h, int16_t)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_h, int16_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc))
 NEON_GVEC_VOP2_ENV(neon_sqshl_s, int32_t)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_s, int32_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_sqrshl_d(src1, (int8_t)src2, false, env->vfp.qc))
 NEON_GVEC_VOP2_ENV(neon_sqshl_d, int64_t)
+NEON_GVEC_VOP2i_ENV(neon_sqshli_d, int64_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
 #define NEON_FN(dest, src1, src2) \
     (dest = do_suqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc))
 NEON_VOP_ENV(qshlu_s8, neon_s8, 4)
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_b, int8_t)
 #undef NEON_FN
 
 #define NEON_FN(dest, src1, src2) \
     (dest = do_suqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc))
 NEON_VOP_ENV(qshlu_s16, neon_s16, 2)
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_h, int16_t)
 #undef NEON_FN
 
 uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t val, uint32_t shift)
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift)
     return do_suqrshl_d(val, (int8_t)shift, false, env->vfp.qc);
 }
 
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_suqrshl_bhs(src1, (int8_t)src2, 32, false, env->vfp.qc))
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_s, int32_t)
+#undef NEON_FN
+
+#define NEON_FN(dest, src1, src2) \
+    (dest = do_suqrshl_d(src1, (int8_t)src2, false, env->vfp.qc))
+NEON_GVEC_VOP2i_ENV(neon_sqshlui_d, int64_t)
+#undef NEON_FN
+
 #define NEON_FN(dest, src1, src2) \
     (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc))
 NEON_VOP_ENV(qrshl_u8, neon_u8, 4)
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -XXX,XX +XXX,XX @@ DO_2SH(VRSRA_S, gen_gvec_srsra)
 DO_2SH(VRSRA_U, gen_gvec_ursra)
 DO_2SH(VSHR_S, gen_gvec_sshr)
 DO_2SH(VSHR_U, gen_gvec_ushr)
-
-static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a,
-                             NeonGenTwo64OpEnvFn *fn)
-{
-    /*
-     * 2-reg-and-shift operations, size == 3 case, where the
-     * function needs to be passed tcg_env.
-     */
-    TCGv_i64 constimm;
-    int pass;
-
-    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
-    }
-
-    /* UNDEF accesses to D16-D31 if they don't exist. */
-    if (!dc_isar_feature(aa32_simd_r32, s) &&
-        ((a->vd | a->vm) & 0x10)) {
-        return false;
-    }
-
-    if ((a->vm | a->vd) & a->q) {
-        return false;
-    }
-
-    if (!vfp_access_check(s)) {
-        return true;
-    }
-
-    /*
-     * To avoid excessive duplication of ops we implement shift
-     * by immediate using the variable shift operations.
-     */
-    constimm = tcg_constant_i64(dup_const(a->size, a->shift));
-
-    for (pass = 0; pass < a->q + 1; pass++) {
-        TCGv_i64 tmp = tcg_temp_new_i64();
-
-        read_neon_element64(tmp, a->vm, pass, MO_64);
-        fn(tmp, tcg_env, tmp, constimm);
-        write_neon_element64(tmp, a->vd, pass, MO_64);
-    }
-    return true;
-}
-
-static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a,
-                             NeonGenTwoOpEnvFn *fn)
-{
-    /*
-     * 2-reg-and-shift operations, size < 3 case, where the
-     * helper needs to be passed tcg_env.
-     */
-    TCGv_i32 constimm, tmp;
-    int pass;
-
-    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
-    }
-
-    /* UNDEF accesses to D16-D31 if they don't exist. */
-    if (!dc_isar_feature(aa32_simd_r32, s) &&
-        ((a->vd | a->vm) & 0x10)) {
-        return false;
-    }
-
-    if ((a->vm | a->vd) & a->q) {
-        return false;
-    }
-
-    if (!vfp_access_check(s)) {
-        return true;
-    }
-
-    /*
-     * To avoid excessive duplication of ops we implement shift
-     * by immediate using the variable shift operations.
-     */
-    constimm = tcg_constant_i32(dup_const(a->size, a->shift));
-    tmp = tcg_temp_new_i32();
-
-    for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
-        read_neon_element32(tmp, a->vm, pass, MO_32);
-        fn(tmp, tcg_env, tmp, constimm);
-        write_neon_element32(tmp, a->vd, pass, MO_32);
-    }
-    return true;
-}
-
-#define DO_2SHIFT_ENV(INSN, FUNC)                                       \
-    static bool trans_##INSN##_64_2sh(DisasContext *s, arg_2reg_shift *a) \
-    {                                                                   \
-        return do_2shift_env_64(s, a, gen_helper_neon_##FUNC##64);      \
-    }                                                                   \
-    static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a)  \
-    {                                                                   \
-        static NeonGenTwoOpEnvFn * const fns[] = {                      \
-            gen_helper_neon_##FUNC##8,                                  \
-            gen_helper_neon_##FUNC##16,                                 \
-            gen_helper_neon_##FUNC##32,                                 \
-        };                                                              \
-        assert(a->size < ARRAY_SIZE(fns));                              \
-        return do_2shift_env_32(s, a, fns[a->size]);                    \
-    }
-
-DO_2SHIFT_ENV(VQSHLU, qshlu_s)
-DO_2SHIFT_ENV(VQSHL_U, qshl_u)
-DO_2SHIFT_ENV(VQSHL_S, qshl_s)
+DO_2SH(VQSHLU, gen_neon_sqshlui)
+DO_2SH(VQSHL_U, gen_neon_uqshli)
+DO_2SH(VQSHL_S, gen_neon_sqshli)
 
 static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
                                 NeonGenTwo64OpFn *shiftfn,
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

While these functions really do return a 32-bit value,
widening the return type means that we need do less
marshalling between TCG types.

Remove NeonGenNarrowEnvFn typedef; add NeonGenOne64OpEnvFn.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20240912024114.1097832-27-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h             | 22 ++++++------
 target/arm/tcg/translate.h      |  2 +-
 target/arm/tcg/neon_helper.c    | 43 ++++++++++++++---------
 target/arm/tcg/translate-a64.c  | 60 ++++++++++++++++++---------------
 target/arm/tcg/translate-neon.c | 44 ++++++++++++------------
 5 files changed, 93 insertions(+), 78 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(neon_qrdmulh_s32, i32, env, i32, i32)
 DEF_HELPER_4(neon_qrdmlah_s32, i32, env, s32, s32, s32)
 DEF_HELPER_4(neon_qrdmlsh_s32, i32, env, s32, s32, s32)
 
-DEF_HELPER_1(neon_narrow_u8, i32, i64)
-DEF_HELPER_1(neon_narrow_u16, i32, i64)
-DEF_HELPER_2(neon_unarrow_sat8, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_u8, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_s8, i32, env, i64)
-DEF_HELPER_2(neon_unarrow_sat16, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_u16, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_s16, i32, env, i64)
-DEF_HELPER_2(neon_unarrow_sat32, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_u32, i32, env, i64)
-DEF_HELPER_2(neon_narrow_sat_s32, i32, env, i64)
+DEF_HELPER_1(neon_narrow_u8, i64, i64)
+DEF_HELPER_1(neon_narrow_u16, i64, i64)
+DEF_HELPER_2(neon_unarrow_sat8, i64, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u8, i64, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s8, i64, env, i64)
+DEF_HELPER_2(neon_unarrow_sat16, i64, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u16, i64, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s16, i64, env, i64)
+DEF_HELPER_2(neon_unarrow_sat32, i64, env, i64)
+DEF_HELPER_2(neon_narrow_sat_u32, i64, env, i64)
+DEF_HELPER_2(neon_narrow_sat_s32, i64, env, i64)
 DEF_HELPER_1(neon_narrow_high_u8, i32, i64)
 DEF_HELPER_1(neon_narrow_high_u16, i32, i64)
 DEF_HELPER_1(neon_narrow_round_high_u8, i32, i64)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -XXX,XX +XXX,XX @@ typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32,
 typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64);
 typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64);
 typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
-typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
 typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
 typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32);
 typedef void NeonGenOneSingleOpFn(TCGv_i32, TCGv_i32, TCGv_ptr);
 typedef void NeonGenTwoSingleOpFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
 typedef void NeonGenTwoDoubleOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
 typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64);
+typedef void NeonGenOne64OpEnvFn(TCGv_i64, TCGv_env, TCGv_i64);
 typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
 typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
 typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -XXX,XX +XXX,XX @@ NEON_VOP_ENV(qrdmulh_s32, neon_s32, 1)
 #undef NEON_FN
 #undef NEON_QDMULH32
 
-uint32_t HELPER(neon_narrow_u8)(uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_u8)(uint64_t x)
 {
     return (x & 0xffu) | ((x >> 8) & 0xff00u) | ((x >> 16) & 0xff0000u)
            | ((x >> 24) & 0xff000000u);
 }
 
-uint32_t HELPER(neon_narrow_u16)(uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_u16)(uint64_t x)
 {
     return (x & 0xffffu) | ((x >> 16) & 0xffff0000u);
 }
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_narrow_round_high_u16)(uint64_t x)
     return ((x >> 16) & 0xffff) | ((x >> 32) & 0xffff0000);
 }
 
-uint32_t HELPER(neon_unarrow_sat8)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_unarrow_sat8)(CPUARMState *env, uint64_t x)
 {
     uint16_t s;
     uint8_t d;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_unarrow_sat8)(CPUARMState *env, uint64_t x)
     return res;
 }
 
-uint32_t HELPER(neon_narrow_sat_u8)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_sat_u8)(CPUARMState *env, uint64_t x)
 {
     uint16_t s;
     uint8_t d;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_narrow_sat_u8)(CPUARMState *env, uint64_t x)
     return res;
 }
 
-uint32_t HELPER(neon_narrow_sat_s8)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_sat_s8)(CPUARMState *env, uint64_t x)
 {
     int16_t s;
     uint8_t d;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_narrow_sat_s8)(CPUARMState *env, uint64_t x)
     return res;
 }
 
-uint32_t HELPER(neon_unarrow_sat16)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_unarrow_sat16)(CPUARMState *env, uint64_t x)
 {
     uint32_t high;
     uint32_t low;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_unarrow_sat16)(CPUARMState *env, uint64_t x)
         high = 0xffff;
         SET_QC();
     }
-    return low | (high << 16);
+    return deposit32(low, 16, 16, high);
 }
 
-uint32_t HELPER(neon_narrow_sat_u16)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_sat_u16)(CPUARMState *env, uint64_t x)
 {
     uint32_t high;
     uint32_t low;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_narrow_sat_u16)(CPUARMState *env, uint64_t x)
         high = 0xffff;
         SET_QC();
     }
-    return low | (high << 16);
+    return deposit32(low, 16, 16, high);
 }
 
-uint32_t HELPER(neon_narrow_sat_s16)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_sat_s16)(CPUARMState *env, uint64_t x)
 {
     int32_t low;
     int32_t high;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_narrow_sat_s16)(CPUARMState *env, uint64_t x)
         high = (high >> 31) ^ 0x7fff;
         SET_QC();
     }
-    return (uint16_t)low | (high << 16);
+    return deposit32(low, 16, 16, high);
 }
 
-uint32_t HELPER(neon_unarrow_sat32)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_unarrow_sat32)(CPUARMState *env, uint64_t x)
 {
     if (x & 0x8000000000000000ull) {
         SET_QC();
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_unarrow_sat32)(CPUARMState *env, uint64_t x)
     return x;
 }
 
-uint32_t HELPER(neon_narrow_sat_u32)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_sat_u32)(CPUARMState *env, uint64_t x)
 {
     if (x > 0xffffffffu) {
         SET_QC();
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_narrow_sat_u32)(CPUARMState *env, uint64_t x)
     return x;
 }
 
-uint32_t HELPER(neon_narrow_sat_s32)(CPUARMState *env, uint64_t x)
+/* Only the low 32-bits of output are significant. */
+uint64_t HELPER(neon_narrow_sat_s32)(CPUARMState *env, uint64_t x)
 {
     if ((int64_t)x != (int32_t)x) {
         SET_QC();
-        return ((int64_t)x >> 63) ^ 0x7fffffff;
+        return (uint32_t)((int64_t)x >> 63) ^ 0x7fffffff;
     }
-    return x;
+    return (uint32_t)x;
 }
 
 uint64_t HELPER(neon_widen_u8)(uint32_t x)
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
     int elements = is_scalar ? 1 : (64 / esize);
     bool round = extract32(opcode, 0, 1);
     MemOp ldop = (size + 1) | (is_u_shift ? 0 : MO_SIGN);
-    TCGv_i64 tcg_rn, tcg_rd;
-    TCGv_i32 tcg_rd_narrowed;
-    TCGv_i64 tcg_final;
+    TCGv_i64 tcg_rn, tcg_rd, tcg_final;
 
-    static NeonGenNarrowEnvFn * const signed_narrow_fns[4][2] = {
+    static NeonGenOne64OpEnvFn * const signed_narrow_fns[4][2] = {
         { gen_helper_neon_narrow_sat_s8,
           gen_helper_neon_unarrow_sat8 },
         { gen_helper_neon_narrow_sat_s16,
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
           gen_helper_neon_unarrow_sat32 },
         { NULL, NULL },
     };
-    static NeonGenNarrowEnvFn * const unsigned_narrow_fns[4] = {
+    static NeonGenOne64OpEnvFn * const unsigned_narrow_fns[4] = {
         gen_helper_neon_narrow_sat_u8,
         gen_helper_neon_narrow_sat_u16,
         gen_helper_neon_narrow_sat_u32,
         NULL
     };
-    NeonGenNarrowEnvFn *narrowfn;
+    NeonGenOne64OpEnvFn *narrowfn;
 
     int i;
 
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
 
     tcg_rn = tcg_temp_new_i64();
     tcg_rd = tcg_temp_new_i64();
-    tcg_rd_narrowed = tcg_temp_new_i32();
     tcg_final = tcg_temp_new_i64();
 
     for (i = 0; i < elements; i++) {
         read_vec_element(s, tcg_rn, rn, i, ldop);
         handle_shri_with_rndacc(tcg_rd, tcg_rn, round,
                                 false, is_u_shift, size+1, shift);
-        narrowfn(tcg_rd_narrowed, tcg_env, tcg_rd);
-        tcg_gen_extu_i32_i64(tcg_rd, tcg_rd_narrowed);
+        narrowfn(tcg_rd, tcg_env, tcg_rd);
         if (i == 0) {
             tcg_gen_extract_i64(tcg_final, tcg_rd, 0, esize);
         } else {
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
      * in the source becomes a size element in the destination).
      */
     int pass;
-    TCGv_i32 tcg_res[2];
+    TCGv_i64 tcg_res[2];
     int destelt = is_q ? 2 : 0;
     int passes = scalar ? 1 : 2;
 
     if (scalar) {
-        tcg_res[1] = tcg_constant_i32(0);
+        tcg_res[1] = tcg_constant_i64(0);
     }
 
     for (pass = 0; pass < passes; pass++) {
         TCGv_i64 tcg_op = tcg_temp_new_i64();
-        NeonGenNarrowFn *genfn = NULL;
-        NeonGenNarrowEnvFn *genenvfn = NULL;
+        NeonGenOne64OpFn *genfn = NULL;
+        NeonGenOne64OpEnvFn *genenvfn = NULL;
 
         if (scalar) {
             read_vec_element(s, tcg_op, rn, pass, size + 1);
         } else {
             read_vec_element(s, tcg_op, rn, pass, MO_64);
         }
-        tcg_res[pass] = tcg_temp_new_i32();
+        tcg_res[pass] = tcg_temp_new_i64();
 
         switch (opcode) {
         case 0x12: /* XTN, SQXTUN */
         {
-            static NeonGenNarrowFn * const xtnfns[3] = {
+            static NeonGenOne64OpFn * const xtnfns[3] = {
                 gen_helper_neon_narrow_u8,
                 gen_helper_neon_narrow_u16,
-                tcg_gen_extrl_i64_i32,
+                tcg_gen_ext32u_i64,
             };
-            static NeonGenNarrowEnvFn * const sqxtunfns[3] = {
+            static NeonGenOne64OpEnvFn * const sqxtunfns[3] = {
                 gen_helper_neon_unarrow_sat8,
                 gen_helper_neon_unarrow_sat16,
                 gen_helper_neon_unarrow_sat32,
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
         }
         case 0x14: /* SQXTN, UQXTN */
         {
-            static NeonGenNarrowEnvFn * const fns[3][2] = {
+            static NeonGenOne64OpEnvFn * const fns[3][2] = {
                 { gen_helper_neon_narrow_sat_s8,
                   gen_helper_neon_narrow_sat_u8 },
                 { gen_helper_neon_narrow_sat_s16,
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
         case 0x16: /* FCVTN, FCVTN2 */
             /* 32 bit to 16 bit or 64 bit to 32 bit float conversion */
             if (size == 2) {
-                gen_helper_vfp_fcvtsd(tcg_res[pass], tcg_op, tcg_env);
+                TCGv_i32 tmp = tcg_temp_new_i32();
+                gen_helper_vfp_fcvtsd(tmp, tcg_op, tcg_env);
+                tcg_gen_extu_i32_i64(tcg_res[pass], tmp);
             } else {
                 TCGv_i32 tcg_lo = tcg_temp_new_i32();
                 TCGv_i32 tcg_hi = tcg_temp_new_i32();
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
                 tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, tcg_op);
                 gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp);
                 gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp);
-                tcg_gen_deposit_i32(tcg_res[pass], tcg_lo, tcg_hi, 16, 16);
+                tcg_gen_deposit_i32(tcg_lo, tcg_lo, tcg_hi, 16, 16);
+                tcg_gen_extu_i32_i64(tcg_res[pass], tcg_lo);
             }
             break;
         case 0x36: /* BFCVTN, BFCVTN2 */
             {
                 TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
-                gen_helper_bfcvt_pair(tcg_res[pass], tcg_op, fpst);
+                TCGv_i32 tmp = tcg_temp_new_i32();
+                gen_helper_bfcvt_pair(tmp, tcg_op, fpst);
+                tcg_gen_extu_i32_i64(tcg_res[pass], tmp);
             }
             break;
         case 0x56:  /* FCVTXN, FCVTXN2 */
-            /* 64 bit to 32 bit float conversion
-             * with von Neumann rounding (round to odd)
-             */
-            assert(size == 2);
-            gen_helper_fcvtx_f64_to_f32(tcg_res[pass], tcg_op, tcg_env);
+            {
+                /*
+                 * 64 bit to 32 bit float conversion
+                 * with von Neumann rounding (round to odd)
+                 */
+                TCGv_i32 tmp = tcg_temp_new_i32();
+                assert(size == 2);
+                gen_helper_fcvtx_f64_to_f32(tmp, tcg_op, tcg_env);
+                tcg_gen_extu_i32_i64(tcg_res[pass], tmp);
+            }
             break;
         default:
             g_assert_not_reached();
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
     }
 
     for (pass = 0; pass < 2; pass++) {
-        write_vec_element_i32(s, tcg_res[pass], rd, destelt + pass, MO_32);
+        write_vec_element(s, tcg_res[pass], rd, destelt + pass, MO_32);
     }
     clear_vec_high(s, is_q, rd);
 }
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -XXX,XX +XXX,XX @@ DO_2SH(VQSHL_S, gen_neon_sqshli)
 
 static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
                                 NeonGenTwo64OpFn *shiftfn,
-                                NeonGenNarrowEnvFn *narrowfn)
+                                NeonGenOne64OpEnvFn *narrowfn)
 {
     /* 2-reg-and-shift narrowing-shift operations, size == 3 case */
-    TCGv_i64 constimm, rm1, rm2;
-    TCGv_i32 rd;
+    TCGv_i64 constimm, rm1, rm2, rd;
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
@@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
     constimm = tcg_constant_i64(-a->shift);
     rm1 = tcg_temp_new_i64();
     rm2 = tcg_temp_new_i64();
-    rd = tcg_temp_new_i32();
+    rd = tcg_temp_new_i64();
 
     /* Load both inputs first to avoid potential overwrite if rm == rd */
     read_neon_element64(rm1, a->vm, 0, MO_64);
@@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a,
 
     shiftfn(rm1, rm1, constimm);
     narrowfn(rd, tcg_env, rm1);
-    write_neon_element32(rd, a->vd, 0, MO_32);
+    write_neon_element64(rd, a->vd, 0, MO_32);
 
     shiftfn(rm2, rm2, constimm);
     narrowfn(rd, tcg_env, rm2);
-    write_neon_element32(rd, a->vd, 1, MO_32);
+    write_neon_element64(rd, a->vd, 1, MO_32);
 
     return true;
 }
 
 static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a,
                                 NeonGenTwoOpFn *shiftfn,
-                                NeonGenNarrowEnvFn *narrowfn)
+                                NeonGenOne64OpEnvFn *narrowfn)
 {
     /* 2-reg-and-shift narrowing-shift operations, size < 3 case */
     TCGv_i32 constimm, rm1, rm2, rm3, rm4;
@@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a,
 
     tcg_gen_concat_i32_i64(rtmp, rm1, rm2);
 
-    narrowfn(rm1, tcg_env, rtmp);
-    write_neon_element32(rm1, a->vd, 0, MO_32);
+    narrowfn(rtmp, tcg_env, rtmp);
+    write_neon_element64(rtmp, a->vd, 0, MO_32);
 
     shiftfn(rm3, rm3, constimm);
     shiftfn(rm4, rm4, constimm);
 
     tcg_gen_concat_i32_i64(rtmp, rm3, rm4);
 
-    narrowfn(rm3, tcg_env, rtmp);
-    write_neon_element32(rm3, a->vd, 1, MO_32);
+    narrowfn(rtmp, tcg_env, rtmp);
+    write_neon_element64(rtmp, a->vd, 1, MO_32);
     return true;
 }
 
@@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a,
         return do_2shift_narrow_32(s, a, FUNC, NARROWFUNC);             \
     }
 
-static void gen_neon_narrow_u32(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src)
+static void gen_neon_narrow_u32(TCGv_i64 dest, TCGv_ptr env, TCGv_i64 src)
 {
-    tcg_gen_extrl_i64_i32(dest, src);
+    tcg_gen_ext32u_i64(dest, src);
 }
 
-static void gen_neon_narrow_u16(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src)
+static void gen_neon_narrow_u16(TCGv_i64 dest, TCGv_ptr env, TCGv_i64 src)
 {
     gen_helper_neon_narrow_u16(dest, src);
 }
 
-static void gen_neon_narrow_u8(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src)
+static void gen_neon_narrow_u8(TCGv_i64 dest, TCGv_ptr env, TCGv_i64 src)
 {
     gen_helper_neon_narrow_u8(dest, src);
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_VZIP(DisasContext *s, arg_2misc *a)
 }
 
 static bool do_vmovn(DisasContext *s, arg_2misc *a,
-                     NeonGenNarrowEnvFn *narrowfn)
+                     NeonGenOne64OpEnvFn *narrowfn)
 {
-    TCGv_i64 rm;
-    TCGv_i32 rd0, rd1;
+    TCGv_i64 rm, rd0, rd1;
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
@@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a,
     }
 
     rm = tcg_temp_new_i64();
-    rd0 = tcg_temp_new_i32();
-    rd1 = tcg_temp_new_i32();
+    rd0 = tcg_temp_new_i64();
+    rd1 = tcg_temp_new_i64();
 
     read_neon_element64(rm, a->vm, 0, MO_64);
     narrowfn(rd0, tcg_env, rm);
     read_neon_element64(rm, a->vm, 1, MO_64);
     narrowfn(rd1, tcg_env, rm);
-    write_neon_element32(rd0, a->vd, 0, MO_32);
-    write_neon_element32(rd1, a->vd, 1, MO_32);
+    write_neon_element64(rd0, a->vd, 0, MO_32);
+    write_neon_element64(rd1, a->vd, 1, MO_32);
     return true;
 }
 
 #define DO_VMOVN(INSN, FUNC)                                    \
     static bool trans_##INSN(DisasContext *s, arg_2misc *a)     \
     {                                                           \
-        static NeonGenNarrowEnvFn * const narrowfn[] = {        \
+        static NeonGenOne64OpEnvFn * const narrowfn[] = {       \
             FUNC##8,                                            \
             FUNC##16,                                           \
             FUNC##32,                                           \
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-28-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  36 +++++-
 target/arm/tcg/translate-a64.c | 223 ++++++++++++++-------------------
 2 files changed, 128 insertions(+), 131 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@ RSHRN_v         0.00 11110 .... ... 10001 1 ..... .....     @q_shri_b
 RSHRN_v         0.00 11110 .... ... 10001 1 ..... .....     @q_shri_h
 RSHRN_v         0.00 11110 .... ... 10001 1 ..... .....     @q_shri_s
 
+SQSHL_vi        0.00 11110 .... ... 01110 1 ..... .....     @q_shli_b
+SQSHL_vi        0.00 11110 .... ... 01110 1 ..... .....     @q_shli_h
+SQSHL_vi        0.00 11110 .... ... 01110 1 ..... .....     @q_shli_s
+SQSHL_vi        0.00 11110 .... ... 01110 1 ..... .....     @q_shli_d
+
+UQSHL_vi        0.10 11110 .... ... 01110 1 ..... .....     @q_shli_b
+UQSHL_vi        0.10 11110 .... ... 01110 1 ..... .....     @q_shli_h
+UQSHL_vi        0.10 11110 .... ... 01110 1 ..... .....     @q_shli_s
+UQSHL_vi        0.10 11110 .... ... 01110 1 ..... .....     @q_shli_d
+
+SQSHLU_vi       0.10 11110 .... ... 01100 1 ..... .....     @q_shli_b
+SQSHLU_vi       0.10 11110 .... ... 01100 1 ..... .....     @q_shli_h
+SQSHLU_vi       0.10 11110 .... ... 01100 1 ..... .....     @q_shli_s
+SQSHLU_vi       0.10 11110 .... ... 01100 1 ..... .....     @q_shli_d
+
 # Advanced SIMD scalar shift by immediate
 
 @shri_d         .... ..... 1 ...... ..... . rn:5 rd:5   \
                 &rri_e esz=3 imm=%neon_rshift_i6
-@shli_d         .... ..... 1 imm:6  ..... . rn:5 rd:5   &rri_e esz=3 
+
+@shli_b         .... ..... 0001 imm:3  ..... . rn:5 rd:5    &rri_e esz=0
+@shli_h         .... ..... 001  imm:4  ..... . rn:5 rd:5    &rri_e esz=1
+@shli_s         .... ..... 01   imm:5  ..... . rn:5 rd:5    &rri_e esz=2
+@shli_d         .... ..... 1    imm:6  ..... . rn:5 rd:5    &rri_e esz=3
 
 SSHR_s          0101 11110 .... ... 00000 1 ..... .....     @shri_d
 USHR_s          0111 11110 .... ... 00000 1 ..... .....     @shri_d
@@ -XXX,XX +XXX,XX @@ SRI_s           0111 11110 .... ... 01000 1 ..... .....     @shri_d
 
 SHL_s           0101 11110 .... ... 01010 1 ..... .....     @shli_d
 SLI_s           0111 11110 .... ... 01010 1 ..... .....     @shli_d
+
+SQSHL_si        0101 11110 .... ... 01110 1 ..... .....     @shli_b
+SQSHL_si        0101 11110 .... ... 01110 1 ..... .....     @shli_h
+SQSHL_si        0101 11110 .... ... 01110 1 ..... .....     @shli_s
+SQSHL_si        0101 11110 .... ... 01110 1 ..... .....     @shli_d
+
+UQSHL_si        0111 11110 .... ... 01110 1 ..... .....     @shli_b
+UQSHL_si        0111 11110 .... ... 01110 1 ..... .....     @shli_h
+UQSHL_si        0111 11110 .... ... 01110 1 ..... .....     @shli_s
+UQSHL_si        0111 11110 .... ... 01110 1 ..... .....     @shli_d
+
+SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_b
+SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_h
+SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_s
+SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_d
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ TRANS(URSRA_v, do_vec_shift_imm, a, gen_gvec_ursra)
 TRANS(SRI_v, do_vec_shift_imm, a, gen_gvec_sri)
 TRANS(SHL_v, do_vec_shift_imm, a, tcg_gen_gvec_shli)
 TRANS(SLI_v, do_vec_shift_imm, a, gen_gvec_sli);
+TRANS(SQSHL_vi, do_vec_shift_imm, a, gen_neon_sqshli)
+TRANS(UQSHL_vi, do_vec_shift_imm, a, gen_neon_uqshli)
+TRANS(SQSHLU_vi, do_vec_shift_imm, a, gen_neon_sqshlui)
 
 static bool do_vec_shift_imm_wide(DisasContext *s, arg_qrri_e *a, bool is_u)
 {
@@ -XXX,XX +XXX,XX @@ TRANS(SRI_s, do_scalar_shift_imm, a, gen_sri_d, true, 0)
 TRANS(SHL_s, do_scalar_shift_imm, a, tcg_gen_shli_i64, false, 0)
 TRANS(SLI_s, do_scalar_shift_imm, a, gen_sli_d, true, 0)
 
+static void trunc_i64_env_imm(TCGv_i64 d, TCGv_i64 s, int64_t i,
+                              NeonGenTwoOpEnvFn *fn)
+{
+    TCGv_i32 t = tcg_temp_new_i32();
+    tcg_gen_extrl_i64_i32(t, s);
+    fn(t, tcg_env, t, tcg_constant_i32(i));
+    tcg_gen_extu_i32_i64(d, t);
+}
+
+static void gen_sqshli_b(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshl_s8);
+}
+
+static void gen_sqshli_h(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshl_s16);
+}
+
+static void gen_sqshli_s(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshl_s32);
+}
+
+static void gen_sqshli_d(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    gen_helper_neon_qshl_s64(d, tcg_env, s, tcg_constant_i64(i));
+}
+
+static void gen_uqshli_b(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshl_u8);
+}
+
+static void gen_uqshli_h(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshl_u16);
+}
+
+static void gen_uqshli_s(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshl_u32);
+}
+
+static void gen_uqshli_d(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    gen_helper_neon_qshl_u64(d, tcg_env, s, tcg_constant_i64(i));
+}
+
+static void gen_sqshlui_b(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshlu_s8);
+}
+
+static void gen_sqshlui_h(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshlu_s16);
+}
+
+static void gen_sqshlui_s(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    trunc_i64_env_imm(d, s, i, gen_helper_neon_qshlu_s32);
+}
+
+static void gen_sqshlui_d(TCGv_i64 d, TCGv_i64 s, int64_t i)
+{
+    gen_helper_neon_qshlu_s64(d, tcg_env, s, tcg_constant_i64(i));
+}
+
+static WideShiftImmFn * const f_scalar_sqshli[] = {
+    gen_sqshli_b, gen_sqshli_h, gen_sqshli_s, gen_sqshli_d
+};
+
+static WideShiftImmFn * const f_scalar_uqshli[] = {
+    gen_uqshli_b, gen_uqshli_h, gen_uqshli_s, gen_uqshli_d
+};
+
+static WideShiftImmFn * const f_scalar_sqshlui[] = {
+    gen_sqshlui_b, gen_sqshlui_h, gen_sqshlui_s, gen_sqshlui_d
+};
+
+/* Note that the helpers sign-extend their inputs, so don't do it here. */
+TRANS(SQSHL_si, do_scalar_shift_imm, a, f_scalar_sqshli[a->esz], false, 0)
+TRANS(UQSHL_si, do_scalar_shift_imm, a, f_scalar_uqshli[a->esz], false, 0)
+TRANS(SQSHLU_si, do_scalar_shift_imm, a, f_scalar_sqshlui[a->esz], false, 0)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
     clear_vec_high(s, is_q, rd);
 }
 
-/* SQSHLU, UQSHL, SQSHL: saturating left shifts */
-static void handle_simd_qshl(DisasContext *s, bool scalar, bool is_q,
-                             bool src_unsigned, bool dst_unsigned,
-                             int immh, int immb, int rn, int rd)
-{
-    int immhb = immh << 3 | immb;
-    int size = 32 - clz32(immh) - 1;
-    int shift = immhb - (8 << size);
-    int pass;
-
-    assert(immh != 0);
-    assert(!(scalar && is_q));
-
-    if (!scalar) {
-        if (!is_q && extract32(immh, 3, 1)) {
-            unallocated_encoding(s);
-            return;
-        }
-
-        /* Since we use the variable-shift helpers we must
-         * replicate the shift count into each element of
-         * the tcg_shift value.
-         */
-        switch (size) {
-        case 0:
-            shift |= shift << 8;
-            /* fall through */
-        case 1:
-            shift |= shift << 16;
-            break;
-        case 2:
-        case 3:
-            break;
-        default:
-            g_assert_not_reached();
-        }
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    if (size == 3) {
-        TCGv_i64 tcg_shift = tcg_constant_i64(shift);
-        static NeonGenTwo64OpEnvFn * const fns[2][2] = {
-            { gen_helper_neon_qshl_s64, gen_helper_neon_qshlu_s64 },
-            { NULL, gen_helper_neon_qshl_u64 },
-        };
-        NeonGenTwo64OpEnvFn *genfn = fns[src_unsigned][dst_unsigned];
-        int maxpass = is_q ? 2 : 1;
-
-        for (pass = 0; pass < maxpass; pass++) {
-            TCGv_i64 tcg_op = tcg_temp_new_i64();
-
-            read_vec_element(s, tcg_op, rn, pass, MO_64);
-            genfn(tcg_op, tcg_env, tcg_op, tcg_shift);
-            write_vec_element(s, tcg_op, rd, pass, MO_64);
-        }
-        clear_vec_high(s, is_q, rd);
-    } else {
-        TCGv_i32 tcg_shift = tcg_constant_i32(shift);
-        static NeonGenTwoOpEnvFn * const fns[2][2][3] = {
-            {
-                { gen_helper_neon_qshl_s8,
-                  gen_helper_neon_qshl_s16,
-                  gen_helper_neon_qshl_s32 },
-                { gen_helper_neon_qshlu_s8,
-                  gen_helper_neon_qshlu_s16,
-                  gen_helper_neon_qshlu_s32 }
-            }, {
-                { NULL, NULL, NULL },
-                { gen_helper_neon_qshl_u8,
-                  gen_helper_neon_qshl_u16,
-                  gen_helper_neon_qshl_u32 }
-            }
-        };
-        NeonGenTwoOpEnvFn *genfn = fns[src_unsigned][dst_unsigned][size];
-        MemOp memop = scalar ? size : MO_32;
-        int maxpass = scalar ? 1 : is_q ? 4 : 2;
-
-        for (pass = 0; pass < maxpass; pass++) {
-            TCGv_i32 tcg_op = tcg_temp_new_i32();
-
-            read_vec_element_i32(s, tcg_op, rn, pass, memop);
-            genfn(tcg_op, tcg_env, tcg_op, tcg_shift);
-            if (scalar) {
-                switch (size) {
-                case 0:
-                    tcg_gen_ext8u_i32(tcg_op, tcg_op);
-                    break;
-                case 1:
-                    tcg_gen_ext16u_i32(tcg_op, tcg_op);
-                    break;
-                case 2:
-                    break;
-                default:
-                    g_assert_not_reached();
-                }
-                write_fp_sreg(s, rd, tcg_op);
-            } else {
-                write_vec_element_i32(s, tcg_op, rd, pass, MO_32);
-            }
-        }
-
-        if (!scalar) {
-            clear_vec_high(s, is_q, rd);
-        }
-    }
-}
-
 /* Common vector code for handling integer to FP conversion */
 static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn,
                                    int elements, int is_signed,
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
         handle_vec_simd_sqshrn(s, true, false, is_u, is_u,
                                immh, immb, opcode, rn, rd);
         break;
-    case 0xc: /* SQSHLU */
-        if (!is_u) {
-            unallocated_encoding(s);
-            return;
-        }
-        handle_simd_qshl(s, true, false, false, true, immh, immb, rn, rd);
-        break;
-    case 0xe: /* SQSHL, UQSHL */
-        handle_simd_qshl(s, true, false, is_u, is_u, immh, immb, rn, rd);
-        break;
     case 0x1f: /* FCVTZS, FCVTZU */
         handle_simd_shift_fpint_conv(s, true, false, is_u, immh, immb, rn, rd);
         break;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
     case 0x06: /* SRSRA / URSRA */
     case 0x08: /* SRI */
     case 0x0a: /* SHL / SLI */
+    case 0x0c: /* SQSHLU */
+    case 0x0e: /* SQSHL, UQSHL */
         unallocated_encoding(s);
         break;
     }
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
         handle_simd_shift_intfp_conv(s, false, is_q, is_u, immh, immb,
                                      opcode, rn, rd);
         break;
-    case 0xc: /* SQSHLU */
-        if (!is_u) {
-            unallocated_encoding(s);
-            return;
-        }
-        handle_simd_qshl(s, false, is_q, false, true, immh, immb, rn, rd);
-        break;
-    case 0xe: /* SQSHL, UQSHL */
-        handle_simd_qshl(s, false, is_q, is_u, is_u, immh, immb, rn, rd);
-        break;
     case 0x1f: /* FCVTZS/ FCVTZU */
         handle_simd_shift_fpint_conv(s, false, is_q, is_u, immh, immb, rn, rd);
         return;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     case 0x06: /* SRSRA / URSRA (accum + rounding) */
     case 0x08: /* SRI */
     case 0x0a: /* SHL / SLI */
+    case 0x0c: /* SQSHLU */
+    case 0x0e: /* SQSHL, UQSHL */
     case 0x14: /* SSHLL / USHLL */
         unallocated_encoding(s);
         return;
-- 
2.34.1

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-29-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  24 +++++
 target/arm/tcg/translate-a64.c | 176 ++++++++++++++++++++++++++++++---
 2 files changed, 186 insertions(+), 14 deletions(-)

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240912024114.1097832-30-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  30 +++++++
 target/arm/tcg/translate-a64.c | 160 +++++++--------------------------
 2 files changed, 63 insertions(+), 127 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -XXX,XX +XXX,XX @@ SQRSHRUN_v      0.10 11110 .... ... 10001 1 ..... .....     @q_shri_s
 
 # Advanced SIMD scalar shift by immediate
 
+@shri_b         .... ..... 0001 ... ..... . rn:5 rd:5   \
+                &rri_e esz=0 imm=%neon_rshift_i3
+@shri_h         .... ..... 001 .... ..... . rn:5 rd:5   \
+                &rri_e esz=1 imm=%neon_rshift_i4
+@shri_s         .... ..... 01 ..... ..... . rn:5 rd:5   \
+                &rri_e esz=2 imm=%neon_rshift_i5
 @shri_d         .... ..... 1 ...... ..... . rn:5 rd:5   \
                 &rri_e esz=3 imm=%neon_rshift_i6
 
@@ -XXX,XX +XXX,XX @@ SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_b
 SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_h
 SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_s
 SQSHLU_si       0111 11110 .... ... 01100 1 ..... .....     @shli_d
+
+SQSHRN_si       0101 11110 .... ... 10010 1 ..... .....     @shri_b
+SQSHRN_si       0101 11110 .... ... 10010 1 ..... .....     @shri_h
+SQSHRN_si       0101 11110 .... ... 10010 1 ..... .....     @shri_s
+
+UQSHRN_si       0111 11110 .... ... 10010 1 ..... .....     @shri_b
+UQSHRN_si       0111 11110 .... ... 10010 1 ..... .....     @shri_h
+UQSHRN_si       0111 11110 .... ... 10010 1 ..... .....     @shri_s
+
+SQSHRUN_si      0111 11110 .... ... 10000 1 ..... .....     @shri_b
+SQSHRUN_si      0111 11110 .... ... 10000 1 ..... .....     @shri_h
+SQSHRUN_si      0111 11110 .... ... 10000 1 ..... .....     @shri_s
+
+SQRSHRN_si      0101 11110 .... ... 10011 1 ..... .....     @shri_b
+SQRSHRN_si      0101 11110 .... ... 10011 1 ..... .....     @shri_h
+SQRSHRN_si      0101 11110 .... ... 10011 1 ..... .....     @shri_s
+
+UQRSHRN_si      0111 11110 .... ... 10011 1 ..... .....     @shri_b
+UQRSHRN_si      0111 11110 .... ... 10011 1 ..... .....     @shri_h
+UQRSHRN_si      0111 11110 .... ... 10011 1 ..... .....     @shri_s
+
+SQRSHRUN_si     0111 11110 .... ... 10001 1 ..... .....     @shri_b
+SQRSHRUN_si     0111 11110 .... ... 10001 1 ..... .....     @shri_h
+SQRSHRUN_si     0111 11110 .... ... 10001 1 ..... .....     @shri_s
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ TRANS(SQSHL_si, do_scalar_shift_imm, a, f_scalar_sqshli[a->esz], false, 0)
 TRANS(UQSHL_si, do_scalar_shift_imm, a, f_scalar_uqshli[a->esz], false, 0)
 TRANS(SQSHLU_si, do_scalar_shift_imm, a, f_scalar_sqshlui[a->esz], false, 0)
 
+static bool do_scalar_shift_imm_narrow(DisasContext *s, arg_rri_e *a,
+                                       WideShiftImmFn * const fns[3],
+                                       MemOp sign, bool zext)
+{
+    MemOp esz = a->esz;
+
+    tcg_debug_assert(esz >= MO_8 && esz <= MO_32);
+
+    if (fp_access_check(s)) {
+        TCGv_i64 rd = tcg_temp_new_i64();
+        TCGv_i64 rn = tcg_temp_new_i64();
+
+        read_vec_element(s, rn, a->rn, 0, (esz + 1) | sign);
+        fns[esz](rd, rn, a->imm);
+        if (zext) {
+            tcg_gen_ext_i64(rd, rd, esz);
+        }
+        write_fp_dreg(s, a->rd, rd);
+    }
+    return true;
+}
+
+TRANS(SQSHRN_si, do_scalar_shift_imm_narrow, a, sqshrn_fns, MO_SIGN, true)
+TRANS(SQRSHRN_si, do_scalar_shift_imm_narrow, a, sqrshrn_fns, MO_SIGN, true)
+TRANS(UQSHRN_si, do_scalar_shift_imm_narrow, a, uqshrn_fns, 0, false)
+TRANS(UQRSHRN_si, do_scalar_shift_imm_narrow, a, uqrshrn_fns, 0, false)
+TRANS(SQSHRUN_si, do_scalar_shift_imm_narrow, a, sqshrun_fns, MO_SIGN, false)
+TRANS(SQRSHRUN_si, do_scalar_shift_imm_narrow, a, sqrshrun_fns, MO_SIGN, false)
+
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
  * shift amount is in range (ie 0..31 or 0..63) and provide the ARM
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
-/*
- * Common SSHR[RA]/USHR[RA] - Shift right (optional rounding/accumulate)
- *
- * This code is handles the common shifting code and is used by both
- * the vector and scalar code.
- */
-static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
-                                    bool round, bool accumulate,
-                                    bool is_u, int size, int shift)
-{
-    if (!round) {
-        if (is_u) {
-            gen_ushr_d(tcg_src, tcg_src, shift);
-        } else {
-            gen_sshr_d(tcg_src, tcg_src, shift);
-        }
-    } else if (size == MO_64) {
-        if (is_u) {
-            gen_urshr_d(tcg_src, tcg_src, shift);
-        } else {
-            gen_srshr_d(tcg_src, tcg_src, shift);
-        }
-    } else {
-        if (is_u) {
-            gen_urshr_bhs(tcg_src, tcg_src, shift);
-        } else {
-            gen_srshr_bhs(tcg_src, tcg_src, shift);
-        }
-    }
-
-    if (accumulate) {
-        tcg_gen_add_i64(tcg_res, tcg_res, tcg_src);
-    } else {
-        tcg_gen_mov_i64(tcg_res, tcg_src);
-    }
-}
-
-/* SQSHRN/SQSHRUN - Saturating (signed/unsigned) shift right with
- * (signed/unsigned) narrowing */
-static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
-                                   bool is_u_shift, bool is_u_narrow,
-                                   int immh, int immb, int opcode,
-                                   int rn, int rd)
-{
-    int immhb = immh << 3 | immb;
-    int size = 32 - clz32(immh) - 1;
-    int esize = 8 << size;
-    int shift = (2 * esize) - immhb;
-    int elements = is_scalar ? 1 : (64 / esize);
-    bool round = extract32(opcode, 0, 1);
-    MemOp ldop = (size + 1) | (is_u_shift ? 0 : MO_SIGN);
-    TCGv_i64 tcg_rn, tcg_rd, tcg_final;
-
-    static NeonGenOne64OpEnvFn * const signed_narrow_fns[4][2] = {
-        { gen_helper_neon_narrow_sat_s8,
-          gen_helper_neon_unarrow_sat8 },
-        { gen_helper_neon_narrow_sat_s16,
-          gen_helper_neon_unarrow_sat16 },
-        { gen_helper_neon_narrow_sat_s32,
-          gen_helper_neon_unarrow_sat32 },
-        { NULL, NULL },
-    };
-    static NeonGenOne64OpEnvFn * const unsigned_narrow_fns[4] = {
-        gen_helper_neon_narrow_sat_u8,
-        gen_helper_neon_narrow_sat_u16,
-        gen_helper_neon_narrow_sat_u32,
-        NULL
-    };
-    NeonGenOne64OpEnvFn *narrowfn;
-
-    int i;
-
-    assert(size < 4);
-
-    if (extract32(immh, 3, 1)) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    if (is_u_shift) {
-        narrowfn = unsigned_narrow_fns[size];
-    } else {
-        narrowfn = signed_narrow_fns[size][is_u_narrow ? 1 : 0];
-    }
-
-    tcg_rn = tcg_temp_new_i64();
-    tcg_rd = tcg_temp_new_i64();
-    tcg_final = tcg_temp_new_i64();
-
-    for (i = 0; i < elements; i++) {
-        read_vec_element(s, tcg_rn, rn, i, ldop);
-        handle_shri_with_rndacc(tcg_rd, tcg_rn, round,
-                                false, is_u_shift, size+1, shift);
-        narrowfn(tcg_rd, tcg_env, tcg_rd);
-        if (i == 0) {
-            tcg_gen_extract_i64(tcg_final, tcg_rd, 0, esize);
-        } else {
-            tcg_gen_deposit_i64(tcg_final, tcg_final, tcg_rd, esize * i, esize);
-        }
-    }
-
-    if (!is_q) {
-        write_vec_element(s, tcg_final, rd, 0, MO_64);
-    } else {
-        write_vec_element(s, tcg_final, rd, 1, MO_64);
-    }
-    clear_vec_high(s, is_q, rd);
-}
-
 /* Common vector code for handling integer to FP conversion */
 static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn,
                                    int elements, int is_signed,
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
         handle_simd_shift_intfp_conv(s, true, false, is_u, immh, immb,
                                      opcode, rn, rd);
         break;
-    case 0x10: /* SQSHRUN, SQSHRUN2 */
-    case 0x11: /* SQRSHRUN, SQRSHRUN2 */
-        if (!is_u) {
-            unallocated_encoding(s);
-            return;
-        }
-        handle_vec_simd_sqshrn(s, true, false, false, true,
-                               immh, immb, opcode, rn, rd);
-        break;
-    case 0x12: /* SQSHRN, SQSHRN2, UQSHRN */
-    case 0x13: /* SQRSHRN, SQRSHRN2, UQRSHRN, UQRSHRN2 */
-        handle_vec_simd_sqshrn(s, true, false, is_u, is_u,
-                               immh, immb, opcode, rn, rd);
-        break;
     case 0x1f: /* FCVTZS, FCVTZU */
         handle_simd_shift_fpint_conv(s, true, false, is_u, immh, immb, rn, rd);
         break;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
     case 0x0a: /* SHL / SLI */
     case 0x0c: /* SQSHLU */
     case 0x0e: /* SQSHL, UQSHL */
+    case 0x10: /* SQSHRUN */
+    case 0x11: /* SQRSHRUN */
+    case 0x12: /* SQSHRN, UQSHRN */
+    case 0x13: /* SQRSHRN, UQRSHRN */
         unallocated_encoding(s);
         break;
     }
-- 
2.34.1

From: Jacob Abrams <satur9nine@gmail.com>

SW modifying USART_CR1 TE bit should cuase HW to respond by altering
USART_ISR TEACK bit, and likewise for RE and REACK bit.

This resolves some but not all issues necessary for the official STM USART
HAL driver to function as is.

Fixes: 87b77e6e01ca ("hw/char/stm32l4x5_usart: Enable serial read and write")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2540
Signed-off-by: Jacob Abrams <satur9nine@gmail.com>
Message-id: 20240911043255.51966-1-satur9nine@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/char/stm32l4x5_usart.c          | 16 +++++++++++++
 tests/qtest/stm32l4x5_usart-test.c | 36 +++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/hw/char/stm32l4x5_usart.c b/hw/char/stm32l4x5_usart.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/char/stm32l4x5_usart.c
+++ b/hw/char/stm32l4x5_usart.c
@@ -XXX,XX +XXX,XX @@ REG32(RDR, 0x24)
 REG32(TDR, 0x28)
     FIELD(TDR, TDR, 0, 9)
 
+static void stm32l4x5_update_isr(Stm32l4x5UsartBaseState *s)
+{
+    if (s->cr1 & R_CR1_TE_MASK) {
+        s->isr |= R_ISR_TEACK_MASK;
+    } else {
+        s->isr &= ~R_ISR_TEACK_MASK;
+    }
+
+    if (s->cr1 & R_CR1_RE_MASK) {
+        s->isr |= R_ISR_REACK_MASK;
+    } else {
+        s->isr &= ~R_ISR_REACK_MASK;
+    }
+}
+
 static void stm32l4x5_update_irq(Stm32l4x5UsartBaseState *s)
 {
     if (((s->isr & R_ISR_WUF_MASK) && (s->cr3 & R_CR3_WUFIE_MASK))        ||
@@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr,
     case A_CR1:
         s->cr1 = value;
         stm32l4x5_update_params(s);
+        stm32l4x5_update_isr(s);
         stm32l4x5_update_irq(s);
         return;
     case A_CR2:
diff --git a/tests/qtest/stm32l4x5_usart-test.c b/tests/qtest/stm32l4x5_usart-test.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/stm32l4x5_usart-test.c
+++ b/tests/qtest/stm32l4x5_usart-test.c
@@ -XXX,XX +XXX,XX @@ REG32(GTPR, 0x10)
 REG32(RTOR, 0x14)
 REG32(RQR, 0x18)
 REG32(ISR, 0x1C)
+    FIELD(ISR, REACK, 22, 1)
+    FIELD(ISR, TEACK, 21, 1)
     FIELD(ISR, TXE, 7, 1)
     FIELD(ISR, RXNE, 5, 1)
     FIELD(ISR, ORE, 3, 1)
@@ -XXX,XX +XXX,XX @@ static void init_uart(QTestState *qts)
 
     /* Enable the transmitter, the receiver and the USART. */
     qtest_writel(qts, (USART1_BASE_ADDR + A_CR1),
-        R_CR1_UE_MASK | R_CR1_RE_MASK | R_CR1_TE_MASK);
+        cr1 | R_CR1_UE_MASK | R_CR1_RE_MASK | R_CR1_TE_MASK);
 }
 
 static void test_write_read(void)
@@ -XXX,XX +XXX,XX @@ static void test_send_str(void)
     qtest_quit(qts);
 }
 
+static void test_ack(void)
+{
+    uint32_t cr1;
+    uint32_t isr;
+    QTestState *qts = qtest_init("-M b-l475e-iot01a");
+
+    init_uart(qts);
+
+    cr1 = qtest_readl(qts, (USART1_BASE_ADDR + A_CR1));
+
+    /* Disable the transmitter and receiver. */
+    qtest_writel(qts, (USART1_BASE_ADDR + A_CR1),
+        cr1 & ~(R_CR1_RE_MASK | R_CR1_TE_MASK));
+
+    /* Test ISR ACK for transmitter and receiver disabled */
+    isr = qtest_readl(qts, (USART1_BASE_ADDR + A_ISR));
+    g_assert_false(isr & R_ISR_TEACK_MASK);
+    g_assert_false(isr & R_ISR_REACK_MASK);
+
+    /* Enable the transmitter and receiver. */
+    qtest_writel(qts, (USART1_BASE_ADDR + A_CR1),
+        cr1 | (R_CR1_RE_MASK | R_CR1_TE_MASK));
+
+    /* Test ISR ACK for transmitter and receiver disabled */
+    isr = qtest_readl(qts, (USART1_BASE_ADDR + A_ISR));
+    g_assert_true(isr & R_ISR_TEACK_MASK);
+    g_assert_true(isr & R_ISR_REACK_MASK);
+
+    qtest_quit(qts);
+}
+
 int main(int argc, char **argv)
 {
     int ret;
@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv)
     qtest_add_func("stm32l4x5/usart/send_char", test_send_char);
     qtest_add_func("stm32l4x5/usart/receive_str", test_receive_str);
     qtest_add_func("stm32l4x5/usart/send_str", test_send_str);
+    qtest_add_func("stm32l4x5/usart/ack", test_ack);
     ret = g_test_run();
 
     return ret;
-- 
2.34.1

From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>

We want to run tests using default cpu without having to remember which
Arm core is it.

Change Neoverse-N1 (old default) test to use default cpu (Neoverse-N2 at
the moment).

Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
Message-id: 20240910-b4-move-to-freebsd-v5-1-0fb66d803c93@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 tests/functional/test_aarch64_sbsaref.py | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/tests/functional/test_aarch64_sbsaref.py b/tests/functional/test_aarch64_sbsaref.py
index XXXXXXX..XXXXXXX 100755
--- a/tests/functional/test_aarch64_sbsaref.py
+++ b/tests/functional/test_aarch64_sbsaref.py
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_edk2_firmware(self):
     # This tests the whole boot chain from EFI to Userspace
     # We only boot a whole OS for the current top level CPU and GIC
     # Other test profiles should use more minimal boots
-    def boot_alpine_linux(self, cpu):
+    def boot_alpine_linux(self, cpu=None):
         self.fetch_firmware()
 
         iso_path = self.ASSET_ALPINE_ISO.fetch()
 
         self.vm.set_console()
         self.vm.add_args(
-            "-cpu", cpu,
             "-drive", f"file={iso_path},media=cdrom,format=raw",
         )
+        if cpu:
+            self.vm.add_args("-cpu", cpu)
 
         self.vm.launch()
         wait_for_console_pattern(self, "Welcome to Alpine Linux 3.17")
@@ -XXX,XX +XXX,XX @@ def boot_alpine_linux(self, cpu):
     def test_sbsaref_alpine_linux_cortex_a57(self):
         self.boot_alpine_linux("cortex-a57")
 
-    def test_sbsaref_alpine_linux_neoverse_n1(self):
-        self.boot_alpine_linux("neoverse-n1")
+    def test_sbsaref_alpine_linux_default_cpu(self):
+        self.boot_alpine_linux()
 
     def test_sbsaref_alpine_linux_max_pauth_off(self):
         self.boot_alpine_linux("max,pauth=off")
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_alpine_linux_max(self):
     # This tests the whole boot chain from EFI to Userspace
     # We only boot a whole OS for the current top level CPU and GIC
     # Other test profiles should use more minimal boots
-    def boot_openbsd73(self, cpu):
+    def boot_openbsd73(self, cpu=None):
         self.fetch_firmware()
 
         img_path = self.ASSET_OPENBSD_ISO.fetch()
 
         self.vm.set_console()
         self.vm.add_args(
-            "-cpu", cpu,
             "-drive", f"file={img_path},format=raw,snapshot=on",
         )
+        if cpu:
+            self.vm.add_args("-cpu", cpu)
 
         self.vm.launch()
         wait_for_console_pattern(self,
@@ -XXX,XX +XXX,XX @@ def boot_openbsd73(self, cpu):
     def test_sbsaref_openbsd73_cortex_a57(self):
         self.boot_openbsd73("cortex-a57")
 
-    def test_sbsaref_openbsd73_neoverse_n1(self):
-        self.boot_openbsd73("neoverse-n1")
+    def test_sbsaref_openbsd73_default_cpu(self):
+        self.boot_openbsd73()
 
     def test_sbsaref_openbsd73_max_pauth_off(self):
         self.boot_openbsd73("max,pauth=off")
-- 
2.34.1

From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>

FreeBSD has longer support cycle for stable release (14.x EoL in 2028)
than OpenBSD (7.3 we use is already EoL). Also bugfixes are backported
so we can stay on 14.x for longer.

Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
Message-id: 20240910-b4-move-to-freebsd-v5-2-0fb66d803c93@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 tests/functional/test_aarch64_sbsaref.py | 43 +++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/tests/functional/test_aarch64_sbsaref.py b/tests/functional/test_aarch64_sbsaref.py
index XXXXXXX..XXXXXXX 100755
--- a/tests/functional/test_aarch64_sbsaref.py
+++ b/tests/functional/test_aarch64_sbsaref.py
@@ -XXX,XX +XXX,XX @@
 #!/usr/bin/env python3
 #
-# Functional test that boots a Linux kernel and checks the console
+# Functional test that boots a kernel and checks the console
 #
 # SPDX-FileCopyrightText: 2023-2024 Linaro Ltd.
 # SPDX-FileContributor: Philippe Mathieu-Daudé <philmd@linaro.org>
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_openbsd73_max(self):
         self.boot_openbsd73("max")
 
 
+    ASSET_FREEBSD_ISO = Asset(
+        ('https://download.freebsd.org/releases/arm64/aarch64/ISO-IMAGES/'
+         '14.1/FreeBSD-14.1-RELEASE-arm64-aarch64-bootonly.iso'),
+        '44cdbae275ef1bb6dab1d5fbb59473d4f741e1c8ea8a80fd9e906b531d6ad461')
+
+    # This tests the whole boot chain from EFI to Userspace
+    # We only boot a whole OS for the current top level CPU and GIC
+    # Other test profiles should use more minimal boots
+    def boot_freebsd14(self, cpu=None):
+        self.fetch_firmware()
+
+        img_path = self.ASSET_FREEBSD_ISO.fetch()
+
+        self.vm.set_console()
+        self.vm.add_args(
+            "-drive", f"file={img_path},format=raw,snapshot=on",
+        )
+        if cpu:
+            self.vm.add_args("-cpu", cpu)
+
+        self.vm.launch()
+        wait_for_console_pattern(self, 'Welcome to FreeBSD!')
+
+    def test_sbsaref_freebsd14_cortex_a57(self):
+        self.boot_freebsd14("cortex-a57")
+
+    def test_sbsaref_freebsd14_default_cpu(self):
+        self.boot_freebsd14()
+
+    def test_sbsaref_freebsd14_max_pauth_off(self):
+        self.boot_freebsd14("max,pauth=off")
+
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    def test_sbsaref_freebsd14_max_pauth_impdef(self):
+        self.boot_freebsd14("max,pauth-impdef=on")
+
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    def test_sbsaref_freebsd14_max(self):
+        self.boot_freebsd14("max")
+
+
 if __name__ == '__main__':
     QemuSystemTest.main()
-- 
2.34.1

From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>

'Test might timeout' means nothing. Replace it with useful information
that it is emulation of pointer authentication what makes this test run
too long.

Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
Message-id: 20240910-b4-move-to-freebsd-v5-3-0fb66d803c93@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 tests/functional/test_aarch64_sbsaref.py | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/tests/functional/test_aarch64_sbsaref.py b/tests/functional/test_aarch64_sbsaref.py
index XXXXXXX..XXXXXXX 100755
--- a/tests/functional/test_aarch64_sbsaref.py
+++ b/tests/functional/test_aarch64_sbsaref.py
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_alpine_linux_max_pauth_off(self):
     def test_sbsaref_alpine_linux_max_pauth_impdef(self):
         self.boot_alpine_linux("max,pauth-impdef=on")
 
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
+                'Test might timeout due to PAuth emulation')
     def test_sbsaref_alpine_linux_max(self):
         self.boot_alpine_linux("max")
 
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_openbsd73_default_cpu(self):
     def test_sbsaref_openbsd73_max_pauth_off(self):
         self.boot_openbsd73("max,pauth=off")
 
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
+                'Test might timeout due to PAuth emulation')
     def test_sbsaref_openbsd73_max_pauth_impdef(self):
         self.boot_openbsd73("max,pauth-impdef=on")
 
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
+                'Test might timeout due to PAuth emulation')
     def test_sbsaref_openbsd73_max(self):
         self.boot_openbsd73("max")
 
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_freebsd14_default_cpu(self):
     def test_sbsaref_freebsd14_max_pauth_off(self):
         self.boot_freebsd14("max,pauth=off")
 
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
+                'Test might timeout due to PAuth emulation')
     def test_sbsaref_freebsd14_max_pauth_impdef(self):
         self.boot_freebsd14("max,pauth-impdef=on")
 
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'), 'Test might timeout')
+    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
+                'Test might timeout due to PAuth emulation')
     def test_sbsaref_freebsd14_max(self):
         self.boot_freebsd14("max")
 
-- 
2.34.1

From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>

OpenBSD 7.3 we use is EoL. Both 7.4 and 7.5 releases do not work on
anything above Neoverse-N1 due to PAC emulation:

https://marc.info/?l=openbsd-arm&m=171050428327850&w=2

OpenBSD 7.6 is not yet released.

Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
Message-id: 20240910-b4-move-to-freebsd-v5-4-0fb66d803c93@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 tests/functional/test_aarch64_sbsaref.py | 44 ------------------------
 1 file changed, 44 deletions(-)

diff --git a/tests/functional/test_aarch64_sbsaref.py b/tests/functional/test_aarch64_sbsaref.py
index XXXXXXX..XXXXXXX 100755
--- a/tests/functional/test_aarch64_sbsaref.py
+++ b/tests/functional/test_aarch64_sbsaref.py
@@ -XXX,XX +XXX,XX @@ def test_sbsaref_alpine_linux_max(self):
         self.boot_alpine_linux("max")
 
 
-    ASSET_OPENBSD_ISO = Asset(
-        ('https://cdn.openbsd.org/pub/OpenBSD/7.3/arm64/miniroot73.img'),
-        '7fc2c75401d6f01fbfa25f4953f72ad7d7c18650056d30755c44b9c129b707e5')
-
-    # This tests the whole boot chain from EFI to Userspace
-    # We only boot a whole OS for the current top level CPU and GIC
-    # Other test profiles should use more minimal boots
-    def boot_openbsd73(self, cpu=None):
-        self.fetch_firmware()
-
-        img_path = self.ASSET_OPENBSD_ISO.fetch()
-
-        self.vm.set_console()
-        self.vm.add_args(
-            "-drive", f"file={img_path},format=raw,snapshot=on",
-        )
-        if cpu:
-            self.vm.add_args("-cpu", cpu)
-
-        self.vm.launch()
-        wait_for_console_pattern(self,
-                                 "Welcome to the OpenBSD/arm64"
-                                 " 7.3 installation program.")
-
-    def test_sbsaref_openbsd73_cortex_a57(self):
-        self.boot_openbsd73("cortex-a57")
-
-    def test_sbsaref_openbsd73_default_cpu(self):
-        self.boot_openbsd73()
-
-    def test_sbsaref_openbsd73_max_pauth_off(self):
-        self.boot_openbsd73("max,pauth=off")
-
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
-                'Test might timeout due to PAuth emulation')
-    def test_sbsaref_openbsd73_max_pauth_impdef(self):
-        self.boot_openbsd73("max,pauth-impdef=on")
-
-    @skipUnless(os.getenv('QEMU_TEST_TIMEOUT_EXPECTED'),
-                'Test might timeout due to PAuth emulation')
-    def test_sbsaref_openbsd73_max(self):
-        self.boot_openbsd73("max")
-
-
     ASSET_FREEBSD_ISO = Asset(
         ('https://download.freebsd.org/releases/arm64/aarch64/ISO-IMAGES/'
          '14.1/FreeBSD-14.1-RELEASE-arm64-aarch64-bootonly.iso'),
-- 
2.34.1

In kvm_init_vcpu()and do_kvm_destroy_vcpu(), the return value from
  kvm_ioctl(..., KVM_GET_VCPU_MMAP_SIZE, ...)
is an 'int', but we put it into a 'long' logal variable mmap_size.
Coverity then complains that there might be a truncation when we copy
that value into the 'int ret' which we use for returning a value in
an error-exit codepath. This can't ever actually overflow because
the value was in an 'int' to start with, but it makes more sense
to use 'int' for mmap_size so we don't do the widen-then-narrow
sequence in the first place.

Resolves: Coverity CID 1547515
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20240815131206.3231819-2-peter.maydell@linaro.org
---
 accel/kvm/kvm-all.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -XXX,XX +XXX,XX @@ int kvm_create_and_park_vcpu(CPUState *cpu)
 static int do_kvm_destroy_vcpu(CPUState *cpu)
 {
     KVMState *s = kvm_state;
-    long mmap_size;
+    int mmap_size;
     int ret = 0;
 
     trace_kvm_destroy_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
@@ -XXX,XX +XXX,XX @@ void kvm_destroy_vcpu(CPUState *cpu)
 int kvm_init_vcpu(CPUState *cpu, Error **errp)
 {
     KVMState *s = kvm_state;
-    long mmap_size;
+    int mmap_size;
     int ret;
 
     trace_kvm_init_vcpu(cpu->cpu_index, kvm_arch_vcpu_id(cpu));
-- 
2.34.1

The Neoverse-V1 TRM is a bit confused about the layout of the
ID_AA64ISAR1_EL1 register, and so its table 3-6 has the wrong value
for this ID register.  Trust instead section 3.2.74's list of which
fields are set.

This means that we stop incorrectly reporting FEAT_XS as present, and
now report the presence of FEAT_BF16.

Cc: qemu-stable@nongnu.org
Reported-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240917161337.3012188-1-peter.maydell@linaro.org
---
 target/arm/tcg/cpu64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_v1_initfn(Object *obj)
     cpu->isar.id_aa64dfr0  = 0x000001f210305519ull;
     cpu->isar.id_aa64dfr1 = 0x00000000;
     cpu->isar.id_aa64isar0 = 0x1011111110212120ull; /* with FEAT_RNG */
-    cpu->isar.id_aa64isar1 = 0x0111000001211032ull;
+    cpu->isar.id_aa64isar1 = 0x0011100001211032ull;
     cpu->isar.id_aa64mmfr0 = 0x0000000000101125ull;
     cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull;
     cpu->isar.id_aa64mmfr2 = 0x0220011102101011ull;
-- 
2.34.1

docs/devel/nested-papr.txt is entirely (apart from the initial
paragraph) a partial copy of the kernel documentation
https://docs.kernel.org/arch/powerpc/kvm-nested.html

There's no benefit to the QEMU docs to converting this to rST,
so instead delete it. Anybody needing to know the API and
protocol for the guest to communicate with the hypervisor
to created nested VMs should refer to the authoratitative
documentation in the kernel docs.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Message-id: 20240816133318.3603114-1-peter.maydell@linaro.org
---
 docs/devel/nested-papr.txt | 119 -------------------------------------
 1 file changed, 119 deletions(-)
 delete mode 100644 docs/devel/nested-papr.txt

diff --git a/docs/devel/nested-papr.txt b/docs/devel/nested-papr.txt
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/docs/devel/nested-papr.txt
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-Nested PAPR API (aka KVM on PowerVM)
-====================================
-
-This API aims at providing support to enable nested virtualization with
-KVM on PowerVM. While the existing support for nested KVM on PowerNV was
-introduced with cap-nested-hv option, however, with a slight design change,
-to enable this on papr/pseries, a new cap-nested-papr option is added. eg:
-
-  qemu-system-ppc64 -cpu POWER10 -machine pseries,cap-nested-papr=true ...
-
-Work by:
-    Michael Neuling <mikey@neuling.org>
-    Vaibhav Jain <vaibhav@linux.ibm.com>
-    Jordan Niethe <jniethe5@gmail.com>
-    Harsh Prateek Bora <harshpb@linux.ibm.com>
-    Shivaprasad G Bhat <sbhat@linux.ibm.com>
-    Kautuk Consul <kconsul@linux.vnet.ibm.com>
-
-Below taken from the kernel documentation:
-
-Introduction
-============
-
-This document explains how a guest operating system can act as a
-hypervisor and run nested guests through the use of hypercalls, if the
-hypervisor has implemented them. The terms L0, L1, and L2 are used to
-refer to different software entities. L0 is the hypervisor mode entity
-that would normally be called the "host" or "hypervisor". L1 is a
-guest virtual machine that is directly run under L0 and is initiated
-and controlled by L0. L2 is a guest virtual machine that is initiated
-and controlled by L1 acting as a hypervisor. A significant design change
-wrt existing API is that now the entire L2 state is maintained within L0.
-
-Existing Nested-HV API
-======================
-
-Linux/KVM has had support for Nesting as an L0 or L1 since 2018
-
-The L0 code was added::
-
-   commit 8e3f5fc1045dc49fd175b978c5457f5f51e7a2ce
-   Author: Paul Mackerras <paulus@ozlabs.org>
-   Date:   Mon Oct 8 16:31:03 2018 +1100
-   KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization
-
-The L1 code was added::
-
-   commit 360cae313702cdd0b90f82c261a8302fecef030a
-   Author: Paul Mackerras <paulus@ozlabs.org>
-   Date:   Mon Oct 8 16:31:04 2018 +1100
-   KVM: PPC: Book3S HV: Nested guest entry via hypercall
-
-This API works primarily using a signal hcall h_enter_nested(). This
-call made by the L1 to tell the L0 to start an L2 vCPU with the given
-state. The L0 then starts this L2 and runs until an L2 exit condition
-is reached. Once the L2 exits, the state of the L2 is given back to
-the L1 by the L0. The full L2 vCPU state is always transferred from
-and to L1 when the L2 is run. The L0 doesn't keep any state on the L2
-vCPU (except in the short sequence in the L0 on L1 -> L2 entry and L2
--> L1 exit).
-
-The only state kept by the L0 is the partition table. The L1 registers
-it's partition table using the h_set_partition_table() hcall. All
-other state held by the L0 about the L2s is cached state (such as
-shadow page tables).
-
-The L1 may run any L2 or vCPU without first informing the L0. It
-simply starts the vCPU using h_enter_nested(). The creation of L2s and
-vCPUs is done implicitly whenever h_enter_nested() is called.
-
-In this document, we call this existing API the v1 API.
-
-New PAPR API
-===============
-
-The new PAPR API changes from the v1 API such that the creating L2 and
-associated vCPUs is explicit. In this document, we call this the v2
-API.
-
-h_enter_nested() is replaced with H_GUEST_VCPU_RUN().  Before this can
-be called the L1 must explicitly create the L2 using h_guest_create()
-and any associated vCPUs() created with h_guest_create_vCPU(). Getting
-and setting vCPU state can also be performed using h_guest_{g|s}et
-hcall.
-
-The basic execution flow is for an L1 to create an L2, run it, and
-delete it is:
-
-- L1 and L0 negotiate capabilities with H_GUEST_{G,S}ET_CAPABILITIES()
-  (normally at L1 boot time).
-
-- L1 requests the L0 to create an L2 with H_GUEST_CREATE() and receives a token
-
-- L1 requests the L0 to create an L2 vCPU with H_GUEST_CREATE_VCPU()
-
-- L1 and L0 communicate the vCPU state using the H_GUEST_{G,S}ET() hcall
-
-- L1 requests the L0 to run the vCPU using H_GUEST_RUN_VCPU() hcall
-
-- L1 deletes L2 with H_GUEST_DELETE()
-
-For more details, please refer:
-
-[1] Linux Kernel documentation (upstream documentation commit):
-
-commit 476652297f94a2e5e5ef29e734b0da37ade94110
-Author: Michael Neuling <mikey@neuling.org>
-Date:   Thu Sep 14 13:06:00 2023 +1000
-
-    docs: powerpc: Document nested KVM on POWER
-
-    Document support for nested KVM on POWER using the existing API as well
-    as the new PAPR API. This includes the new HCALL interface and how it
-    used by KVM.
-
-    Signed-off-by: Michael Neuling <mikey@neuling.org>
-    Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
-    Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
-    Link: https://msgid.link/20230914030600.16993-12-jniethe5@gmail.com
-- 
2.34.1

Hi; here's another arm pullreq; main parts here are the
new i.MX 8MM EVK board, and a lot of refactoring.

thanks
-- PMM

The following changes since commit aa15257174da180c6a8a9d58f87319cfe61c5520:

Merge tag 'pbouvier/pr/plugins-20260424' of https://gitlab.com/p-b-o/qemu into staging (2026-04-25 10:22:04 -0400)

are available in the Git repository at:

https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20260427

for you to fetch changes up to 4575da5ecb7a27544aa6da1f78e700e8100ceaea:

target/arm: report register in WFIT syndromes (2026-04-27 11:46:34 +0100)

----------------------------------------------------------------
target-arm queue:
docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list
hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board
target/arm: Build M-profile helper code once only
hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register
hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header
target/arm: Allow 'aarch64=off' to be set for TCG CPUs
target/arm: Allow some sysregs to not have to be an exact match for migration
hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices
hw/arm/fsl-imx6ul: Implement LCDIF display device
target/arm: Refactor syndrome value code to use registerfields
target/arm: Report the register in WFxT syndromes

----------------------------------------------------------------
Alex Bennée (24):
      docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list
      target/arm: migrate basic syndrome helpers to registerfields
      target/arm: migrate system/cp trap syndromes to registerfields
      target/arm: migrate FP/SIMD trap syndromes to registerfields
      target/arm: migrate eret trap syndromes to registerfields
      target/arm: migrate SME trap syndromes to registerfields
      target/arm: migrate PAC trap syndromes to registerfields
      target/arm: migrate BTI trap syndromes to registerfields
      target/arm: migrate BXJ trap syndromes to registerfields
      target/arm: migrate Granule Protection traps to registerfields
      target/arm: migrate fault syndromes to registerfields
      target/arm: migrate debug syndromes to registerfields
      target/arm: migrate wfx syndromes to registerfields
      target/arm: migrate gcs syndromes to registerfields
      target/arm: migrate memory op syndromes to registerfields
      target/arm: migrate check_hcr_el2_trap to use syndrome helper
      target/arm: use syndrome helpers in arm_cpu_do_interrupt_aarch32_hyp
      target/arm: use syndrome helpers to set SAME_EL EC bit
      target/arm: make whpx use syndrome helpers for decode
      target/arm: make hvf use syndrome helpers for decode
      target/arm: use syndrome helpers in merge_syn_data_abort
      target/arm: use syndrome helpers to query VNCR bit
      target/arm: remove old syndrome defines
      target/arm: report register in WFIT syndromes

Eric Auger (7):
      target/arm/cpu: Introduce the infrastructure for cpreg migration tolerances
      target/arm/machine: Handle ToleranceNotOnBothEnds migration tolerances
      target/arm/machine: Handle ToleranceOnlySrcTestValue migration tolerance
      target/arm/cpu64: Mitigate migration failures due to spurious TCR_EL1, PIRE0_EL1 and PIR_EL1
      target/arm/cpu64: Define cpreg migration tolerance for KVM_REG_ARM_VENDOR_HYP_BMAP_2
      target/arm/helper: Define cpreg migration tolerance for DGBDTR_EL0
      Revert "target/arm: Reinstate bogus AArch32 DBGDTRTX register for migration compat"

Gaurav Sharma (15):
      hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board
      hw/misc/imx8mp_analog: Add property to analog device
      hw/arm/fsl-imx8mm: Add Analog device IP to iMX8MM SOC
      hw/arm/fsl-imx8mm: Add Clock Control Module IP to iMX8MM
      hw/arm/fsl-imx8mm: Implemented support for SNVS
      hw/arm/fsl-imx8mm: Adding support for USDHC storage controllers
      hw/arm/fsl-imx8mm: Add PCIe support
      hw/arm/fsl-imx8mm: Add GPIO controllers
      hw/arm/fsl-imx8mm: Adding support for I2C emulation
      hw/arm/fsl-imx8mm: Adding support for SPI controller
      hw/arm/fsl-imx8mm: Adding support for Watchdog Timers
      hw/arm/fsl-imx8mm: Adding support for General Purpose Timers
      hw/arm/fsl-imx8mm: Adding support for ENET ethernet controller
      hw/arm/fsl-imx8mm: Adding support for USB controller
      hw/arm/fsl-imx8mm: Adding functional testing of iMX8MM emulation

Osama Abdelkader (1):
      hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices

Peter Maydell (4):
      hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header
      target/arm: Clear AArch64 ID regs from ARMISARegisters if AArch64 disabled
      target/arm: Allow 'aarch64=off' to be set for TCG CPUs
      tests/functional/aarch64: Add basic test of TCG aarch64=off

Philippe Mathieu-Daudé (9):
      target/arm: Ignore endianness when setting MTE tags
      target/arm: Explode MO_TExx -> MO_TE | MO_xx
      target/arm: Hoist MO_TE into mve_advance_vpt()
      target/arm: Hoist MO_TE into MVE DO_VSTR() macro
      target/arm: Introduce mo_endian() helper
      target/arm: Replace MO_TE -> mo_endian() for MVE helpers
      target/arm: Compile mve_helper.c once
      target/arm: Replace MO_TE -> mo_endian() for Cortex-M helpers
      target/arm: Compile m_helper.c once

Thomas Huth (1):
      hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register

Yucai Liu (2):
      hw/display: Add i.MX6UL LCDIF device model
      hw/arm/fsl-imx6ul: Wire in the LCDIF device model

MAINTAINERS                                       |  16 +-
 docs/system/arm/cpu-features.rst                  |  10 +-
 docs/system/arm/emulation.rst                     |   2 +
 docs/system/arm/{imx8mp-evk.rst => imx8m.rst}     |  49 +-
 docs/system/target-arm.rst                        |   2 +-
 hw/arm/Kconfig                                    |  25 +
 hw/arm/fsl-imx6ul.c                               |  12 +-
 hw/arm/fsl-imx8mm.c                               | 704 ++++++++++++++++++++++
 hw/arm/imx8mm-evk.c                               | 130 ++++
 hw/arm/integratorcp.c                             |   3 -
 hw/arm/meson.build                                |   2 +
 hw/arm/raspi4b.c                                  |  10 +-
 hw/arm/realview.c                                 |   2 +-
 hw/arm/vexpress.c                                 |   2 +-
 hw/arm/virt.c                                     |   1 -
 hw/display/Kconfig                                |   4 +
 hw/display/imx6ul_lcdif.c                         | 453 ++++++++++++++
 hw/display/meson.build                            |   1 +
 hw/misc/arm_sysctl.c                              |   2 +-
 hw/misc/imx8mp_analog.c                           |  12 +-
 hw/timer/imx_gpt.c                                |  26 +
 hw/vmapple/vmapple.c                              |   1 -
 include/hw/arm/fsl-imx6ul.h                       |   4 +-
 include/hw/arm/fsl-imx8mm.h                       | 242 ++++++++
 include/hw/arm/primecell.h                        |  12 -
 include/hw/display/imx6ul_lcdif.h                 |  37 ++
 include/hw/misc/arm_sysctl.h                      |  16 +
 include/hw/misc/imx8mp_analog.h                   |   3 +
 include/hw/timer/imx_gpt.h                        |   2 +
 target/arm/cpu-features.h                         |   5 +
 target/arm/cpu.c                                  | 153 ++++-
 target/arm/cpu.h                                  |   4 +-
 target/arm/cpu64.c                                |  39 ++
 target/arm/debug_helper.c                         |  29 -
 target/arm/helper.c                               |  27 +-
 target/arm/hvf/hvf.c                              |  14 +-
 target/arm/internals.h                            |  60 ++
 target/arm/machine.c                              |  33 +-
 target/arm/syndrome.h                             | 595 ++++++++++++++----
 target/arm/tcg/debug.c                            |   2 +-
 target/arm/tcg/helper-a64.c                       |   2 +-
 target/arm/tcg/helper-defs.h                      |   2 +-
 target/arm/tcg/m_helper.c                         |   8 +-
 target/arm/tcg/meson.build                        |   6 +-
 target/arm/tcg/mve_helper.c                       | 102 ++--
 target/arm/tcg/op_helper.c                        |   7 +-
 target/arm/tcg/tlb_helper.c                       |   6 +-
 target/arm/tcg/translate-a64.c                    |   2 +-
 target/arm/tcg/vfp_helper.c                       |   5 +-
 target/arm/trace-events                           |   2 +
 target/arm/whpx/whpx-all.c                        |  13 +-
 tests/functional/aarch64/meson.build              |   3 +
 tests/functional/aarch64/test_imx8mm_evk.py       |  69 +++
 tests/functional/aarch64/test_virt_aarch64_off.py |  37 ++
 tests/qtest/arm-cpu-features.c                    |   8 +-
 55 files changed, 2743 insertions(+), 275 deletions(-)
 rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%)
 create mode 100644 hw/arm/fsl-imx8mm.c
 create mode 100644 hw/arm/imx8mm-evk.c
 create mode 100644 hw/display/imx6ul_lcdif.c
 create mode 100644 include/hw/arm/fsl-imx8mm.h
 delete mode 100644 include/hw/arm/primecell.h
 create mode 100644 include/hw/display/imx6ul_lcdif.h
 create mode 100644 include/hw/misc/arm_sysctl.h
 create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py
 create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py

From: Alex Bennée <alex.bennee@linaro.org>

This is just a documentation tweak as we already support both.
FEAT_AA32 implies FEAT_AA32EL0. FEAT_AA64 implies FEAT_AA64EL[0123].

This is however useful if you are using emulation.rst as a source of
truth of what QEMU emulates and when cross checking with
Features.json from Arm.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260421093506.616307-1-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/system/arm/emulation.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -XXX,XX +XXX,XX @@ QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7,
 Armv8 and Armv9 versions of the A-profile architecture. It also has support for
 the following architecture extensions:
 
+- FEAT_AA32 (PE Support for AArch32)
 - FEAT_AA32BF16 (AArch32 BFloat16 instructions)
 - FEAT_AA32EL0 (Support for AArch32 at EL0)
 - FEAT_AA32EL1 (Support for AArch32 at EL1)
@@ -XXX,XX +XXX,XX @@ the following architecture extensions:
 - FEAT_AA32EL3 (Support for AArch32 at EL3)
 - FEAT_AA32HPD (AArch32 hierarchical permission disables)
 - FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions)
+- FEAT_AA64 (PE uses AArch64 after last reboot)
 - FEAT_AA64EL0 (Support for AArch64 at EL0)
 - FEAT_AA64EL1 (Support for AArch64 at EL1)
 - FEAT_AA64EL2 (Support for AArch64 at EL2)
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Implemented CPUs, RAM, UARTs and Interrupt Controller
Other peripherals are represented as TYPE_UNIMPLEMENTED_DEVICE
Complete memory map of the SoC is provided.

Set default RAM size to 2GB and default CPU count to 4 to match
the real i.MX8MM EVK hardware configuration.

Documentation is shared with imx8mp-evk to avoid duplication.

Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
[PMM: fixed over-long lines in doc]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS                                   |  11 +-
 docs/system/arm/{imx8mp-evk.rst => imx8m.rst} |  49 ++-
 docs/system/target-arm.rst                    |   2 +-
 hw/arm/Kconfig                                |  12 +
 hw/arm/fsl-imx8mm.c                           | 377 ++++++++++++++++++
 hw/arm/imx8mm-evk.c                           | 112 ++++++
 hw/arm/meson.build                            |   2 +
 include/hw/arm/fsl-imx8mm.h                   | 158 ++++++++
 8 files changed, 709 insertions(+), 14 deletions(-)
 rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%)
 create mode 100644 hw/arm/fsl-imx8mm.c
 create mode 100644 hw/arm/imx8mm-evk.c
 create mode 100644 include/hw/arm/fsl-imx8mm.h

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/pci-host/designware.c
 F: include/hw/pci-host/designware.h
 F: docs/system/arm/mcimx7d-sabre.rst
 
+MCIMX8MM-EVK / iMX8MM
+M: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+L: qemu-arm@nongnu.org
+S: Maintained
+F: hw/arm/fsl-imx8mm.c
+F: hw/arm/imx8mm-evk.c
+F: include/hw/arm/fsl-imx8mm.h
+F: docs/system/arm/imx8m.rst
+
 MCIMX8MP-EVK / i.MX8MP
 M: Bernhard Beschow <shentey@gmail.com>
 L: qemu-arm@nongnu.org
@@ -XXX,XX +XXX,XX @@ F: hw/rtc/rs5c372.c
 F: include/hw/arm/fsl-imx8mp.h
 F: include/hw/misc/imx8mp_*.h
 F: include/hw/pci-host/fsl_imx8m_phy.h
-F: docs/system/arm/imx8mp-evk.rst
+F: docs/system/arm/imx8m.rst
 F: tests/functional/aarch64/test_imx8mp_evk.py
 F: tests/qtest/rs5c372-test.c
 
diff --git a/docs/system/arm/imx8mp-evk.rst b/docs/system/arm/imx8m.rst
similarity index 58%
rename from docs/system/arm/imx8mp-evk.rst
rename to docs/system/arm/imx8m.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/imx8mp-evk.rst
+++ b/docs/system/arm/imx8m.rst
@@ -XXX,XX +XXX,XX @@
-NXP i.MX 8M Plus Evaluation Kit (``imx8mp-evk``)
-================================================
+NXP i.MX 8M Plus and i.MX 8M Mini Evaluation Kits (``imx8mp-evk``, ``imx8mm-evk``)
+==================================================================================
 
-The ``imx8mp-evk`` machine models the i.MX 8M Plus Evaluation Kit, based on an
-i.MX 8M Plus SoC.
+The ``imx8mp-evk`` and ``imx8mm-evk`` machine models the i.MX 8M Plus
+and i.MX 8M Mini Evaluation Kits, based on i.MX 8M Plus and i.MX8M
+Mini SoCs.
 
 Supported devices
 -----------------
 
-The ``imx8mp-evk`` machine implements the following devices:
+The ``imx8mp-evk`` and ``imx8mm-evk`` machines implement the
+following devices:
 
  * Up to 4 Cortex-A53 cores
  * Generic Interrupt Controller (GICv3)
@@ -XXX,XX +XXX,XX @@ The ``imx8mp-evk`` machine implements the following devices:
 Boot options
 ------------
 
-The ``imx8mp-evk`` machine can start a Linux kernel directly using the standard
-``-kernel`` functionality.
+The ``imx8mp-evk`` and ``imx8mm-evk`` machines can start a Linux
+kernel directly using the standard ``-kernel`` functionality.
 
 Direct Linux Kernel Boot
 ''''''''''''''''''''''''
@@ -XXX,XX +XXX,XX @@ is to generate an image with Buildroot. Version 2024.11.1 is tested at the time
 of writing and involves two steps. First run the following commands in the
 toplevel directory of the Buildroot source tree:
 
+For i.MX 8M Plus EVK:
+
 .. code-block:: bash
 
   $ make freescale_imx8mpevk_defconfig
   $ make
 
+For i.MX 8M Mini EVK:
+
+.. code-block:: bash
+
+  $ make freescale_imx8mmevk_defconfig
+  $ make
+
 Once finished successfully there is an ``output/image`` subfolder. Navigate into
 it and resize the SD card image to a power of two:
 
@@ -XXX,XX +XXX,XX @@ it and resize the SD card image to a power of two:
 
 Now that everything is prepared the machine can be started as follows:
 
+For i.MX 8M Plus EVK:
+
 .. code-block:: bash
 
   $ qemu-system-aarch64 -M imx8mp-evk \
@@ -XXX,XX +XXX,XX @@ Now that everything is prepared the machine can be started as follows:
       -append "root=/dev/mmcblk2p2" \
       -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2
 
+For i.MX 8M Mini EVK:
+
+.. code-block:: bash
+
+  $ qemu-system-aarch64 -M imx8mm-evk -smp 4 -m 2G \
+      -display none -serial null -serial stdio \
+      -kernel Image \
+      -dtb imx8mm-evk.dtb \
+      -append "root=/dev/mmcblk2p2" \
+      -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2
 
 KVM Acceleration
 ----------------
@@ -XXX,XX +XXX,XX @@ To enable hardware-assisted acceleration via KVM, append
 ``-accel kvm`` to the command line. While this speeds up performance
 significantly, be aware of the following limitations:
 
-* The ``imx8mp-evk`` machine is not included under the "virtualization use case"
-  of :doc:`QEMU's security policy </system/security>`. This means that you
-  should not trust that it can contain malicious guests, whether it is run
-  using TCG or KVM. If you don't trust your guests and you're relying on QEMU to
-  be the security boundary, you want to choose another machine such as ``virt``.
+* The ``imx8mp-evk`` and ``imx8mm-evk`` machines are not included
+  under the "virtualization use case" of :doc:`QEMU's security
+  policy </system/security>`.  This means that you should not trust that
+  it can contain malicious guests, whether it is run using TCG or KVM.
+  If you don't trust your guests and you're relying on QEMU to be the
+  security boundary, you want to choose another machine such as
+  ``virt``.
 * Rather than Cortex-A53 CPUs, the same CPU type as the host's will be used.
   This is a limitation of KVM and may not work with guests with a tight
   dependency on Cortex-A53.
diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/target-arm.rst
+++ b/docs/system/target-arm.rst
@@ -XXX,XX +XXX,XX @@ Board-specific documentation
    arm/imx25-pdk
    arm/mcimx6ul-evk
    arm/mcimx7d-sabre
-   arm/imx8mp-evk
+   arm/imx8m
    arm/orangepi
    arm/raspi
    arm/collie
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
     depends on TCG
     select FSL_IMX8MP
 
+config FSL_IMX8MM
+    bool
+    select ARM_GIC
+    select IMX
+
+config FSL_IMX8MM_EVK
+    bool
+    default y
+    depends on AARCH64
+    depends on TCG
+    select FSL_IMX8MM
+
 config ARM_SMMUV3_ACCEL
     bool
     depends on ARM_SMMUV3
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * i.MX 8MM SoC Implementation
+ *
+ * Based on hw/arm/fsl-imx6.c
+ *
+ * Copyright (c) 2025, NXP Semiconductors
+ * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * iMX8MM Reference Manual - https://www.nxp.com/products/i.MX8MMINI -> Documentation
+ */
+
+#include "qemu/osdep.h"
+#include "system/address-spaces.h"
+#include "hw/arm/bsa.h"
+#include "hw/arm/fsl-imx8mm.h"
+#include "hw/misc/unimp.h"
+#include "hw/core/boards.h"
+#include "system/kvm.h"
+#include "system/system.h"
+#include "target/arm/cpu.h"
+#include "target/arm/cpu-qom.h"
+#include "target/arm/kvm_arm.h"
+#include "qapi/error.h"
+#include "qobject/qlist.h"
+
+static const struct {
+    hwaddr addr;
+    size_t size;
+    const char *name;
+} fsl_imx8mm_memmap[] = {
+    [FSL_IMX8MM_RAM] = { FSL_IMX8MM_RAM_START, FSL_IMX8MM_RAM_SIZE_MAX, "ram" },
+    [FSL_IMX8MM_DDR_PHY_BROADCAST] = { 0x3dc00000, 4 * MiB, "ddr_phy_broadcast" },
+    [FSL_IMX8MM_DDR_PERF_MON] = { 0x3d800000, 4 * MiB, "ddr_perf_mon" },
+    [FSL_IMX8MM_DDR_CTL] = { 0x3d400000, 4 * MiB, "ddr_ctl" },
+    [FSL_IMX8MM_DDR_PHY] = { 0x3c000000, 16 * MiB, "ddr_phy" },
+    [FSL_IMX8MM_GIC_DIST] = { 0x38800000, 512 * KiB, "gic_dist" },
+    [FSL_IMX8MM_GIC_REDIST] = { 0x38880000, 512 * KiB, "gic_redist" },
+    [FSL_IMX8MM_VPU] = { 0x38340000, 2 * MiB, "vpu" },
+    [FSL_IMX8MM_VPU_BLK_CTRL] = { 0x38330000, 2 * MiB, "vpu_blk_ctrl" },
+    [FSL_IMX8MM_VPU_G2_DECODER] = { 0x38310000, 1 * MiB, "vpu_g2_decoder" },
+    [FSL_IMX8MM_VPU_G1_DECODER] = { 0x38300000, 1 * MiB, "vpu_g1_decoder" },
+    [FSL_IMX8MM_USB2_OTG] = { 0x32e50200, 0x200, "usb2_otg" },
+    [FSL_IMX8MM_USB2] = { 0x32e50000, 0x200, "usb2" },
+    [FSL_IMX8MM_USB1_OTG] = { 0x32e40200, 0x200, "usb1_otg" },
+    [FSL_IMX8MM_USB1] = { 0x32e40000, 0x200, "usb1" },
+    [FSL_IMX8MM_GPU2D] = { 0x38000000, 64 * KiB, "gpu2d" },
+    [FSL_IMX8MM_QSPI1_RX_BUFFER] = { 0x34000000, 32 * MiB, "qspi1_rx_buffer" },
+    [FSL_IMX8MM_PCIE1] = { 0x33800000, 4 * MiB, "pcie1" },
+    [FSL_IMX8MM_QSPI1_TX_BUFFER] = { 0x33008000, 32 * KiB, "qspi1_tx_buffer" },
+    [FSL_IMX8MM_APBH_DMA] = { 0x33000000, 32 * KiB, "apbh_dma" },
+
+    /* AIPS-4 Begin */
+    [FSL_IMX8MM_TZASC] = { 0x32f80000, 64 * KiB, "tzasc" },
+    [FSL_IMX8MM_PCIE_PHY1] = { 0x32f00000, 64 * KiB, "pcie_phy1" },
+    [FSL_IMX8MM_MEDIA_BLK_CTL] = { 0x32e28000, 256, "media_blk_ctl" },
+    [FSL_IMX8MM_LCDIF] = { 0x32e00000, 64 * KiB, "lcdif" },
+    [FSL_IMX8MM_MIPI_DSI] = { 0x32e10000, 64 * KiB, "mipi_dsi" },
+    [FSL_IMX8MM_MIPI_CSI] = { 0x32e30000, 64 * KiB, "mipi_csi" },
+    [FSL_IMX8MM_AIPS4_CONFIGURATION] = { 0x32df0000, 64 * KiB, "aips4_configuration" },
+    /* AIPS-4 End */
+
+    [FSL_IMX8MM_INTERCONNECT] = { 0x32700000, 1 * MiB, "interconnect" },
+
+    /* AIPS-3 Begin */
+    [FSL_IMX8MM_ENET1] = { 0x30be0000, 64 * KiB, "enet1" },
+    [FSL_IMX8MM_SDMA1] = { 0x30bd0000, 64 * KiB, "sdma1" },
+    [FSL_IMX8MM_QSPI] = { 0x30bb0000, 64 * KiB, "qspi" },
+    [FSL_IMX8MM_USDHC3] = { 0x30b60000, 64 * KiB, "usdhc3" },
+    [FSL_IMX8MM_USDHC2] = { 0x30b50000, 64 * KiB, "usdhc2" },
+    [FSL_IMX8MM_USDHC1] = { 0x30b40000, 64 * KiB, "usdhc1" },
+    [FSL_IMX8MM_SEMAPHORE_HS] = { 0x30ac0000, 64 * KiB, "semaphore_hs" },
+    [FSL_IMX8MM_MU_B] = { 0x30ab0000, 64 * KiB, "mu_b" },
+    [FSL_IMX8MM_MU_A] = { 0x30aa0000, 64 * KiB, "mu_a" },
+    [FSL_IMX8MM_UART4] = { 0x30a60000, 64 * KiB, "uart4" },
+    [FSL_IMX8MM_I2C4] = { 0x30a50000, 64 * KiB, "i2c4" },
+    [FSL_IMX8MM_I2C3] = { 0x30a40000, 64 * KiB, "i2c3" },
+    [FSL_IMX8MM_I2C2] = { 0x30a30000, 64 * KiB, "i2c2" },
+    [FSL_IMX8MM_I2C1] = { 0x30a20000, 64 * KiB, "i2c1" },
+    [FSL_IMX8MM_AIPS3_CONFIGURATION] = { 0x309f0000, 64 * KiB, "aips3_configuration" },
+    [FSL_IMX8MM_CAAM] = { 0x30900000, 256 * KiB, "caam" },
+    [FSL_IMX8MM_SPBA1] = { 0x308f0000, 64 * KiB, "spba1" },
+    [FSL_IMX8MM_UART2] = { 0x30890000, 64 * KiB, "uart2" },
+    [FSL_IMX8MM_UART3] = { 0x30880000, 64 * KiB, "uart3" },
+    [FSL_IMX8MM_UART1] = { 0x30860000, 64 * KiB, "uart1" },
+    [FSL_IMX8MM_ECSPI3] = { 0x30840000, 64 * KiB, "ecspi3" },
+    [FSL_IMX8MM_ECSPI2] = { 0x30830000, 64 * KiB, "ecspi2" },
+    [FSL_IMX8MM_ECSPI1] = { 0x30820000, 64 * KiB, "ecspi1" },
+    /* AIPS-3 End */
+
+    /* AIPS-2 Begin */
+    [FSL_IMX8MM_QOSC] = { 0x307f0000, 64 * KiB, "qosc" },
+    [FSL_IMX8MM_PERFMON2] = { 0x307d0000, 64 * KiB, "perfmon2" },
+    [FSL_IMX8MM_PERFMON1] = { 0x307c0000, 64 * KiB, "perfmon1" },
+    [FSL_IMX8MM_GPT4] = { 0x30700000, 64 * KiB, "gpt4" },
+    [FSL_IMX8MM_GPT5] = { 0x306f0000, 64 * KiB, "gpt5" },
+    [FSL_IMX8MM_GPT6] = { 0x306e0000, 64 * KiB, "gpt6" },
+    [FSL_IMX8MM_SYSCNT_CTRL] = { 0x306c0000, 64 * KiB, "syscnt_ctrl" },
+    [FSL_IMX8MM_SYSCNT_CMP] = { 0x306b0000, 64 * KiB, "syscnt_cmp" },
+    [FSL_IMX8MM_SYSCNT_RD] = { 0x306a0000, 64 * KiB, "syscnt_rd" },
+    [FSL_IMX8MM_PWM4] = { 0x30690000, 64 * KiB, "pwm4" },
+    [FSL_IMX8MM_PWM3] = { 0x30680000, 64 * KiB, "pwm3" },
+    [FSL_IMX8MM_PWM2] = { 0x30670000, 64 * KiB, "pwm2" },
+    [FSL_IMX8MM_PWM1] = { 0x30660000, 64 * KiB, "pwm1" },
+    [FSL_IMX8MM_AIPS2_CONFIGURATION] = { 0x305f0000, 64 * KiB, "aips2_configuration" },
+    /* AIPS-2 End */
+
+    /* AIPS-1 Begin */
+    [FSL_IMX8MM_CSU] = { 0x303e0000, 64 * KiB, "csu" },
+    [FSL_IMX8MM_RDC] = { 0x303d0000, 64 * KiB, "rdc" },
+    [FSL_IMX8MM_SEMAPHORE2] = { 0x303c0000, 64 * KiB, "semaphore2" },
+    [FSL_IMX8MM_SEMAPHORE1] = { 0x303b0000, 64 * KiB, "semaphore1" },
+    [FSL_IMX8MM_GPC] = { 0x303a0000, 64 * KiB, "gpc" },
+    [FSL_IMX8MM_SRC] = { 0x30390000, 64 * KiB, "src" },
+    [FSL_IMX8MM_CCM] = { 0x30380000, 64 * KiB, "ccm" },
+    [FSL_IMX8MM_SNVS_HP] = { 0x30370000, 64 * KiB, "snvs_hp" },
+    [FSL_IMX8MM_ANA_PLL] = { 0x30360000, 64 * KiB, "ana_pll" },
+    [FSL_IMX8MM_OCOTP_CTRL] = { 0x30350000, 64 * KiB, "ocotp_ctrl" },
+    [FSL_IMX8MM_IOMUXC_GPR] = { 0x30340000, 64 * KiB, "iomuxc_gpr" },
+    [FSL_IMX8MM_IOMUXC] = { 0x30330000, 64 * KiB, "iomuxc" },
+    [FSL_IMX8MM_GPT3] = { 0x302f0000, 64 * KiB, "gpt3" },
+    [FSL_IMX8MM_GPT2] = { 0x302e0000, 64 * KiB, "gpt2" },
+    [FSL_IMX8MM_GPT1] = { 0x302d0000, 64 * KiB, "gpt1" },
+    [FSL_IMX8MM_SDMA2] = { 0x302c0000, 64 * KiB, "sdma2" },
+    [FSL_IMX8MM_SDMA3] = { 0x302b0000, 64 * KiB, "sdma3" },
+    [FSL_IMX8MM_WDOG3] = { 0x302a0000, 64 * KiB, "wdog3" },
+    [FSL_IMX8MM_WDOG2] = { 0x30290000, 64 * KiB, "wdog2" },
+    [FSL_IMX8MM_WDOG1] = { 0x30280000, 64 * KiB, "wdog1" },
+    [FSL_IMX8MM_ANA_OSC] = { 0x30270000, 64 * KiB, "ana_osc" },
+    [FSL_IMX8MM_ANA_TSENSOR] = { 0x30260000, 64 * KiB, "ana_tsensor" },
+    [FSL_IMX8MM_GPIO5] = { 0x30240000, 64 * KiB, "gpio5" },
+    [FSL_IMX8MM_GPIO4] = { 0x30230000, 64 * KiB, "gpio4" },
+    [FSL_IMX8MM_GPIO3] = { 0x30220000, 64 * KiB, "gpio3" },
+    [FSL_IMX8MM_GPIO2] = { 0x30210000, 64 * KiB, "gpio2" },
+    [FSL_IMX8MM_GPIO1] = { 0x30200000, 64 * KiB, "gpio1" },
+    [FSL_IMX8MM_AIPS1_CONFIGURATION] = { 0x301f0000, 64 * KiB, "aips1_configuration" },
+    [FSL_IMX8MM_SAI6] = { 0x30060000, 64 * KiB, "sai6" },
+    [FSL_IMX8MM_SAI5] = { 0x30050000, 64 * KiB, "sai5" },
+    [FSL_IMX8MM_SAI3] = { 0x30030000, 64 * KiB, "sai3" },
+    [FSL_IMX8MM_SAI2] = { 0x30020000, 64 * KiB, "sai2" },
+    [FSL_IMX8MM_SAI1] = { 0x30010000, 64 * KiB, "sai1" },
+
+    /* AIPS-1 End */
+
+    [FSL_IMX8MM_A53_DAP] = { 0x28000000, 16 * MiB, "a53_dap" },
+    [FSL_IMX8MM_PCIE1_MEM] = { 0x18000000, 128 * MiB, "pcie1_mem" },
+    [FSL_IMX8MM_QSPI_MEM] = { 0x08000000, 256 * MiB, "qspi_mem" },
+    [FSL_IMX8MM_OCRAM] = { 0x00900000, 256 * KiB, "ocram" },
+    [FSL_IMX8MM_TCM_DTCM] = { 0x00800000, 128 * KiB, "tcm_dtcm" },
+    [FSL_IMX8MM_TCM_ITCM] = { 0x007e0000, 128 * KiB, "tcm_itcm" },
+    [FSL_IMX8MM_OCRAM_S] = { 0x00180000, 32 * KiB, "ocram_s" },
+    [FSL_IMX8MM_CAAM_MEM] = { 0x00100000, 32 * KiB, "caam_mem" },
+    [FSL_IMX8MM_BOOT_ROM_PROTECTED] = { 0x0003f000, 4 * KiB, "boot_rom_protected" },
+    [FSL_IMX8MM_BOOT_ROM] = { 0x00000000, 252 * KiB, "boot_rom" },
+};
+
+static void fsl_imx8mm_init(Object *obj)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    FslImx8mmState *s = FSL_IMX8MM(obj);
+    const char *cpu_type = ms->cpu_type ?: ARM_CPU_TYPE_NAME("cortex-a53");
+    int i;
+
+    for (i = 0; i < MIN(ms->smp.cpus, FSL_IMX8MM_NUM_CPUS); i++) {
+        g_autofree char *name = g_strdup_printf("cpu%d", i);
+        object_initialize_child(obj, name, &s->cpu[i], cpu_type);
+    }
+
+    object_initialize_child(obj, "gic", &s->gic, gicv3_class_name());
+
+    for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
+        g_autofree char *name = g_strdup_printf("uart%d", i + 1);
+        object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
+    }
+
+}
+
+static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    FslImx8mmState *s = FSL_IMX8MM(dev);
+    DeviceState *gicdev = DEVICE(&s->gic);
+    int i;
+
+    if (ms->smp.cpus > FSL_IMX8MM_NUM_CPUS) {
+        error_setg(errp, "%s: Only %d CPUs are supported (%d requested)",
+                   TYPE_FSL_IMX8MM, FSL_IMX8MM_NUM_CPUS, ms->smp.cpus);
+        return;
+    }
+
+    /* CPUs */
+    for (i = 0; i < ms->smp.cpus; i++) {
+        /* On uniprocessor, the CBAR is set to 0 */
+        if (ms->smp.cpus > 1 &&
+                object_property_find(OBJECT(&s->cpu[i]), "reset-cbar")) {
+            object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar",
+                                    fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr,
+                                    &error_abort);
+        }
+
+        /*
+         * CNTFID0 base frequency in Hz of system counter
+         */
+        object_property_set_int(OBJECT(&s->cpu[i]), "cntfrq", 8000000,
+                                &error_abort);
+
+        if (object_property_find(OBJECT(&s->cpu[i]), "has_el2")) {
+            object_property_set_bool(OBJECT(&s->cpu[i]), "has_el2",
+                                     !kvm_enabled(), &error_abort);
+        }
+
+        if (object_property_find(OBJECT(&s->cpu[i]), "has_el3")) {
+            object_property_set_bool(OBJECT(&s->cpu[i]), "has_el3",
+                                     !kvm_enabled(), &error_abort);
+        }
+
+        if (i) {
+            /*
+             * Secondary CPUs start in powered-down state (and can be
+             * powered up via the SRC system reset controller)
+             */
+            object_property_set_bool(OBJECT(&s->cpu[i]), "start-powered-off",
+                                     true, &error_abort);
+        }
+
+        if (!qdev_realize(DEVICE(&s->cpu[i]), NULL, errp)) {
+            return;
+        }
+    }
+
+    /* GIC */
+    {
+        SysBusDevice *gicsbd = SYS_BUS_DEVICE(&s->gic);
+        QList *redist_region_count;
+        bool pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL);
+
+        qdev_prop_set_uint32(gicdev, "num-cpu", ms->smp.cpus);
+        qdev_prop_set_uint32(gicdev, "num-irq",
+                             FSL_IMX8MM_NUM_IRQS + GIC_INTERNAL);
+        redist_region_count = qlist_new();
+        qlist_append_int(redist_region_count, ms->smp.cpus);
+        qdev_prop_set_array(gicdev, "redist-region-count", redist_region_count);
+        object_property_set_link(OBJECT(&s->gic), "sysmem",
+                                 OBJECT(get_system_memory()), &error_fatal);
+        if (!sysbus_realize(gicsbd, errp)) {
+            return;
+        }
+        sysbus_mmio_map(gicsbd, 0, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr);
+        sysbus_mmio_map(gicsbd, 1, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_REDIST].addr);
+
+        /*
+         * Wire the outputs from each CPU's generic timer and the GICv3
+         * maintenance interrupt signal to the appropriate GIC PPI inputs, and
+         * the GIC's IRQ/FIQ interrupt outputs to the CPU's inputs.
+         */
+        for (i = 0; i < ms->smp.cpus; i++) {
+            DeviceState *cpudev = DEVICE(&s->cpu[i]);
+            int intidbase = FSL_IMX8MM_NUM_IRQS + i * GIC_INTERNAL;
+            qemu_irq irq;
+
+            /*
+             * Mapping from the output timer irq lines from the CPU to the
+             * GIC PPI inputs.
+             */
+            static const int timer_irqs[] = {
+                [GTIMER_PHYS] = ARCH_TIMER_NS_EL1_IRQ,
+                [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ,
+                [GTIMER_HYP]  = ARCH_TIMER_NS_EL2_IRQ,
+                [GTIMER_SEC]  = ARCH_TIMER_S_EL1_IRQ,
+            };
+
+            for (int j = 0; j < ARRAY_SIZE(timer_irqs); j++) {
+                irq = qdev_get_gpio_in(gicdev, intidbase + timer_irqs[j]);
+                qdev_connect_gpio_out(cpudev, j, irq);
+            }
+
+            irq = qdev_get_gpio_in(gicdev, intidbase + ARCH_GIC_MAINT_IRQ);
+            qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt",
+                                        0, irq);
+
+            irq = qdev_get_gpio_in(gicdev, intidbase + VIRTUAL_PMU_IRQ);
+            qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, irq);
+
+            sysbus_connect_irq(gicsbd, i,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_IRQ));
+            sysbus_connect_irq(gicsbd, i + ms->smp.cpus,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_FIQ));
+            sysbus_connect_irq(gicsbd, i + 2 * ms->smp.cpus,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ));
+            sysbus_connect_irq(gicsbd, i + 3 * ms->smp.cpus,
+                               qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ));
+
+            if (kvm_enabled()) {
+                if (pmu) {
+                    assert(arm_feature(&s->cpu[i].env, ARM_FEATURE_PMU));
+                    if (kvm_irqchip_in_kernel()) {
+                        kvm_arm_pmu_set_irq(&s->cpu[i], VIRTUAL_PMU_IRQ);
+                    }
+                    kvm_arm_pmu_init(&s->cpu[i]);
+                }
+            }
+        }
+    }
+
+    /* UARTs */
+    for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } serial_table[FSL_IMX8MM_NUM_UARTS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART1].addr, FSL_IMX8MM_UART1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART2].addr, FSL_IMX8MM_UART2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART3].addr, FSL_IMX8MM_UART3_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_UART4].addr, FSL_IMX8MM_UART4_IRQ },
+        };
+
+        qdev_prop_set_chr(DEVICE(&s->uart[i]), "chardev", serial_hd(i));
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->uart[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart[i]), 0, serial_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0,
+                           qdev_get_gpio_in(gicdev, serial_table[i].irq));
+    }
+
+    /* On-Chip RAM */
+    if (!memory_region_init_ram(&s->ocram, OBJECT(dev), "imx8mm.ocram",
+                                fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].size,
+                                errp)) {
+        return;
+    }
+    memory_region_add_subregion(get_system_memory(),
+                                fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
+                                &s->ocram);
+
+    /* Unimplemented devices */
+    for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
+        switch (i) {
+        case FSL_IMX8MM_GIC_DIST:
+        case FSL_IMX8MM_GIC_REDIST:
+        case FSL_IMX8MM_RAM:
+        case FSL_IMX8MM_OCRAM:
+        case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
+            /* device implemented and treated above */
+            break;
+
+        default:
+            create_unimplemented_device(fsl_imx8mm_memmap[i].name,
+                                        fsl_imx8mm_memmap[i].addr,
+                                        fsl_imx8mm_memmap[i].size);
+            break;
+        }
+    }
+}
+
+static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    dc->realize = fsl_imx8mm_realize;
+
+    dc->desc = "i.MX 8MM SoC";
+}
+
+static const TypeInfo fsl_imx8mm_types[] = {
+    {
+        .name = TYPE_FSL_IMX8MM,
+        .parent = TYPE_SYS_BUS_DEVICE,
+        .instance_size = sizeof(FslImx8mmState),
+        .instance_init = fsl_imx8mm_init,
+        .class_init = fsl_imx8mm_class_init,
+    },
+};
+
+DEFINE_TYPES(fsl_imx8mm_types)
diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/arm/imx8mm-evk.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * NXP i.MX 8MM Evaluation Kit System Emulation
+ *
+ * Copyright (c) 2025, NXP Semiconductors
+ * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "system/address-spaces.h"
+#include "hw/arm/boot.h"
+#include "hw/arm/fsl-imx8mm.h"
+#include "hw/arm/machines-qom.h"
+#include "hw/core/boards.h"
+#include "hw/core/qdev-properties.h"
+#include "system/kvm.h"
+#include "system/qtest.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+#include <libfdt.h>
+
+static void imx8mm_evk_modify_dtb(const struct arm_boot_info *info, void *fdt)
+{
+    int i, offset;
+
+    /* Temporarily disable following nodes until they are implemented */
+    const char *nodes_to_remove[] = {
+        "nxp,imx8mm-fspi",
+        "fsl,imx8mm-mipi-csi",
+        "fsl,imx8mm-mipi-dsim"
+    };
+
+    for (i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) {
+        const char *dev_str = nodes_to_remove[i];
+
+        offset = fdt_node_offset_by_compatible(fdt, -1, dev_str);
+        while (offset >= 0) {
+            fdt_nop_node(fdt, offset);
+            offset = fdt_node_offset_by_compatible(fdt, offset, dev_str);
+        }
+    }
+
+    /* Remove cpu-idle-states property from CPU nodes */
+    offset = fdt_node_offset_by_compatible(fdt, -1, "arm,cortex-a53");
+    while (offset >= 0) {
+        fdt_nop_property(fdt, offset, "cpu-idle-states");
+        offset = fdt_node_offset_by_compatible(fdt, offset, "arm,cortex-a53");
+    }
+
+    if (kvm_enabled()) {
+        /* Use system counter frequency from host CPU to fix time in guest */
+        offset = fdt_node_offset_by_compatible(fdt, -1, "arm,armv8-timer");
+        while (offset >= 0) {
+            fdt_nop_property(fdt, offset, "clock-frequency");
+            offset = fdt_node_offset_by_compatible(fdt, offset, "arm,armv8-timer");
+        }
+    }
+}
+
+static void imx8mm_evk_init(MachineState *machine)
+{
+    static struct arm_boot_info boot_info;
+    FslImx8mmState *s;
+
+    if (machine->ram_size > FSL_IMX8MM_RAM_SIZE_MAX) {
+        error_report("RAM size " RAM_ADDR_FMT " above max supported (%08" PRIx64 ")",
+                     machine->ram_size, FSL_IMX8MM_RAM_SIZE_MAX);
+        exit(1);
+    }
+
+    boot_info = (struct arm_boot_info) {
+        .loader_start = FSL_IMX8MM_RAM_START,
+        .board_id = -1,
+        .ram_size = machine->ram_size,
+        .psci_conduit = QEMU_PSCI_CONDUIT_SMC,
+        .modify_dtb = imx8mm_evk_modify_dtb,
+    };
+
+    s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine),
+                                         "soc", &error_fatal, NULL));
+    sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal);
+
+    memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START,
+                                machine->ram);
+
+    if (!qtest_enabled()) {
+        arm_load_kernel(&s->cpu[0], machine, &boot_info);
+    }
+}
+
+static const char *imx8mm_evk_get_default_cpu_type(const MachineState *ms)
+{
+    if (kvm_enabled()) {
+        return ARM_CPU_TYPE_NAME("host");
+    }
+
+    return ARM_CPU_TYPE_NAME("cortex-a53");
+}
+
+static void imx8mm_evk_machine_init(MachineClass *mc)
+{
+    mc->desc = "NXP i.MX 8MM EVK Board";
+    mc->init = imx8mm_evk_init;
+    mc->max_cpus = FSL_IMX8MM_NUM_CPUS;
+    mc->default_cpus = FSL_IMX8MM_NUM_CPUS;
+    mc->default_ram_size = 2 * GiB;
+    mc->default_ram_id = "imx8mm-evk.ram";
+    mc->get_default_cpu_type = imx8mm_evk_get_default_cpu_type;
+}
+
+DEFINE_MACHINE_AARCH64("imx8mm-evk", imx8mm_evk_machine_init)
diff --git a/hw/arm/meson.build b/hw/arm/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/meson.build
+++ b/hw/arm/meson.build
@@ -XXX,XX +XXX,XX @@ arm_common_ss.add(when: 'CONFIG_ARMSSE', if_true: files('armsse.c'))
 arm_common_ss.add(when: 'CONFIG_FSL_IMX7', if_true: files('fsl-imx7.c', 'mcimx7d-sabre.c'))
 arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP', if_true: files('fsl-imx8mp.c'))
 arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP_EVK', if_true: files('imx8mp-evk.c'))
+arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM', if_true: files('fsl-imx8mm.c'))
+arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM_EVK', if_true: files('imx8mm-evk.c'))
 arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c'))
 arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3_ACCEL', if_true: files('smmuv3-accel.c'))
 stub_ss.add(files('smmuv3-accel-stubs.c'))
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * i.MX 8MM SoC Definitions
+ *
+ * Copyright (c) 2025, NXP Semiconductors
+ * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef FSL_IMX8MM_H
+#define FSL_IMX8MM_H
+
+#include "cpu.h"
+#include "hw/char/imx_serial.h"
+#include "hw/intc/arm_gicv3_common.h"
+#include "qom/object.h"
+#include "qemu/units.h"
+
+#define TYPE_FSL_IMX8MM "fsl-imx8mm"
+OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
+
+#define FSL_IMX8MM_RAM_START        0x40000000
+#define FSL_IMX8MM_RAM_SIZE_MAX     (4 * GiB)
+
+enum FslImx8mmConfiguration {
+    FSL_IMX8MM_NUM_CPUS         = 4,
+    FSL_IMX8MM_NUM_IRQS         = 128,
+    FSL_IMX8MM_NUM_UARTS        = 4,
+};
+
+struct FslImx8mmState {
+    SysBusDevice   parent_obj;
+
+    ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
+    GICv3State         gic;
+    IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
+    MemoryRegion ocram;
+};
+
+enum FslImx8mmMemoryRegions {
+    FSL_IMX8MM_A53_DAP,
+    FSL_IMX8MM_AIPS1_CONFIGURATION,
+    FSL_IMX8MM_AIPS2_CONFIGURATION,
+    FSL_IMX8MM_AIPS3_CONFIGURATION,
+    FSL_IMX8MM_AIPS4_CONFIGURATION,
+    FSL_IMX8MM_ANA_OSC,
+    FSL_IMX8MM_ANA_PLL,
+    FSL_IMX8MM_ANA_TSENSOR,
+    FSL_IMX8MM_APBH_DMA,
+    FSL_IMX8MM_BOOT_ROM,
+    FSL_IMX8MM_BOOT_ROM_PROTECTED,
+    FSL_IMX8MM_CAAM,
+    FSL_IMX8MM_CAAM_MEM,
+    FSL_IMX8MM_CCM,
+    FSL_IMX8MM_CSU,
+    FSL_IMX8MM_DDR_CTL,
+    FSL_IMX8MM_DDR_PERF_MON,
+    FSL_IMX8MM_DDR_PHY,
+    FSL_IMX8MM_DDR_PHY_BROADCAST,
+    FSL_IMX8MM_ECSPI1,
+    FSL_IMX8MM_ECSPI2,
+    FSL_IMX8MM_ECSPI3,
+    FSL_IMX8MM_ENET1,
+    FSL_IMX8MM_GIC_DIST,
+    FSL_IMX8MM_GIC_REDIST,
+    FSL_IMX8MM_GPC,
+    FSL_IMX8MM_GPIO1,
+    FSL_IMX8MM_GPIO2,
+    FSL_IMX8MM_GPIO3,
+    FSL_IMX8MM_GPIO4,
+    FSL_IMX8MM_GPIO5,
+    FSL_IMX8MM_GPT1,
+    FSL_IMX8MM_GPT2,
+    FSL_IMX8MM_GPT3,
+    FSL_IMX8MM_GPT4,
+    FSL_IMX8MM_GPT5,
+    FSL_IMX8MM_GPT6,
+    FSL_IMX8MM_GPU2D,
+    FSL_IMX8MM_I2C1,
+    FSL_IMX8MM_I2C2,
+    FSL_IMX8MM_I2C3,
+    FSL_IMX8MM_I2C4,
+    FSL_IMX8MM_INTERCONNECT,
+    FSL_IMX8MM_IOMUXC,
+    FSL_IMX8MM_IOMUXC_GPR,
+    FSL_IMX8MM_MEDIA_BLK_CTL,
+    FSL_IMX8MM_LCDIF,
+    FSL_IMX8MM_MIPI_CSI,
+    FSL_IMX8MM_MIPI_DSI,
+    FSL_IMX8MM_MU_A,
+    FSL_IMX8MM_MU_B,
+    FSL_IMX8MM_OCOTP_CTRL,
+    FSL_IMX8MM_OCRAM,
+    FSL_IMX8MM_OCRAM_S,
+    FSL_IMX8MM_PCIE1,
+    FSL_IMX8MM_PCIE1_MEM,
+    FSL_IMX8MM_PCIE_PHY1,
+    FSL_IMX8MM_PERFMON1,
+    FSL_IMX8MM_PERFMON2,
+    FSL_IMX8MM_PWM1,
+    FSL_IMX8MM_PWM2,
+    FSL_IMX8MM_PWM3,
+    FSL_IMX8MM_PWM4,
+    FSL_IMX8MM_QOSC,
+    FSL_IMX8MM_QSPI,
+    FSL_IMX8MM_QSPI1_RX_BUFFER,
+    FSL_IMX8MM_QSPI1_TX_BUFFER,
+    FSL_IMX8MM_QSPI_MEM,
+    FSL_IMX8MM_RAM,
+    FSL_IMX8MM_RDC,
+    FSL_IMX8MM_SAI1,
+    FSL_IMX8MM_SAI2,
+    FSL_IMX8MM_SAI3,
+    FSL_IMX8MM_SAI5,
+    FSL_IMX8MM_SAI6,
+    FSL_IMX8MM_SDMA1,
+    FSL_IMX8MM_SDMA2,
+    FSL_IMX8MM_SDMA3,
+    FSL_IMX8MM_SEMAPHORE1,
+    FSL_IMX8MM_SEMAPHORE2,
+    FSL_IMX8MM_SEMAPHORE_HS,
+    FSL_IMX8MM_SNVS_HP,
+    FSL_IMX8MM_SPBA1,
+    FSL_IMX8MM_SRC,
+    FSL_IMX8MM_SYSCNT_CMP,
+    FSL_IMX8MM_SYSCNT_CTRL,
+    FSL_IMX8MM_SYSCNT_RD,
+    FSL_IMX8MM_TCM_DTCM,
+    FSL_IMX8MM_TCM_ITCM,
+    FSL_IMX8MM_TZASC,
+    FSL_IMX8MM_UART1,
+    FSL_IMX8MM_UART2,
+    FSL_IMX8MM_UART3,
+    FSL_IMX8MM_UART4,
+    FSL_IMX8MM_USB1,
+    FSL_IMX8MM_USB2,
+    FSL_IMX8MM_USB1_OTG,
+    FSL_IMX8MM_USB2_OTG,
+    FSL_IMX8MM_USDHC1,
+    FSL_IMX8MM_USDHC2,
+    FSL_IMX8MM_USDHC3,
+    FSL_IMX8MM_VPU,
+    FSL_IMX8MM_VPU_BLK_CTRL,
+    FSL_IMX8MM_VPU_G1_DECODER,
+    FSL_IMX8MM_VPU_G2_DECODER,
+    FSL_IMX8MM_WDOG1,
+    FSL_IMX8MM_WDOG2,
+    FSL_IMX8MM_WDOG3,
+};
+
+enum FslImx8mmIrqs {
+    FSL_IMX8MM_UART1_IRQ    = 26,
+    FSL_IMX8MM_UART2_IRQ    = 27,
+    FSL_IMX8MM_UART3_IRQ    = 28,
+    FSL_IMX8MM_UART4_IRQ    = 29,
+};
+
+#endif /* FSL_IMX8MM_H */
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Add configurable properties for register reset values that differ
between i.MX 8M variants (Plus, Mini, etc.). This allows the same
device implementation to be shared across multiple SoCs.

Properties added:
- arm-pll-fdiv-ctl0-reset: ARM PLL divider control reset value

Default value is set to match i.MX 8MP reset value (0x000FA031).
This can be overridden in the variant like iMX8MM with its own
reset value.

Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/misc/imx8mp_analog.c         | 12 +++++++++++-
 include/hw/misc/imx8mp_analog.h |  3 +++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/hw/misc/imx8mp_analog.c b/hw/misc/imx8mp_analog.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/imx8mp_analog.c
+++ b/hw/misc/imx8mp_analog.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/log.h"
 
 #include "hw/misc/imx8mp_analog.h"
+#include "hw/core/qdev-properties.h"
 #include "migration/vmstate.h"
 
 #define ANALOG_PLL_LOCK BIT(31)
@@ -XXX,XX +XXX,XX @@ static void imx8mp_analog_reset(DeviceState *dev)
     s->analog[ANALOG_VPU_PLL_LOCKD_CTRL] = 0x0010003f;
     s->analog[ANALOG_VPU_PLL_MNIT_CTRL] = 0x00280081;
     s->analog[ANALOG_ARM_PLL_GEN_CTRL] = 0x00000810;
-    s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = 0x000fa031;
+
+    /* Use property value instead of hardcoded */
+    s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = s->arm_pll_fdiv_ctl0_reset;
+
     s->analog[ANALOG_ARM_PLL_LOCKD_CTRL] = 0x0010003f;
     s->analog[ANALOG_ARM_PLL_MNIT_CTRL] = 0x00280081;
     s->analog[ANALOG_SYS_PLL1_GEN_CTRL] = 0x0aaaa810;
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription imx8mp_analog_vmstate = {
     },
 };
 
+static const Property imx8mp_analog_properties[] = {
+    DEFINE_PROP_UINT32("arm-pll-fdiv-ctl0-reset", IMX8MPAnalogState,
+                       arm_pll_fdiv_ctl0_reset, 0x000fa031), /* imx8mp default */
+};
+
 static void imx8mp_analog_class_init(ObjectClass *klass, const void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     device_class_set_legacy_reset(dc, imx8mp_analog_reset);
+    device_class_set_props(dc, imx8mp_analog_properties);
     dc->vmsd  = &imx8mp_analog_vmstate;
     dc->desc  = "i.MX 8M Plus Analog Module";
 }
diff --git a/include/hw/misc/imx8mp_analog.h b/include/hw/misc/imx8mp_analog.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/misc/imx8mp_analog.h
+++ b/include/hw/misc/imx8mp_analog.h
@@ -XXX,XX +XXX,XX @@ struct IMX8MPAnalogState {
     } mmio;
 
     uint32_t analog[ANALOG_MAX];
+
+    /* Property for variant-specific reset values */
+    uint32_t arm_pll_fdiv_ctl0_reset;
 };
 
 #endif /* IMX8MP_ANALOG_H */
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Add the Analog IP to i.MX8MM SoC. iMX8MM and i.MX8MP uses
the same Analog IP so the analog ip source will be shared.

The ARM PLL divider control register (arm-pll-fdiv-ctl0) has
a different reset value on i.MX8MM (0x000fa030) compared to
i.MX8MP (0x000fa031). So iMX8MM will be overriding this property
with its own reset-value.

Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 12 ++++++++++++
 include/hw/arm/fsl-imx8mm.h |  2 ++
 3 files changed, 15 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
 config FSL_IMX8MM
     bool
     select ARM_GIC
+    select FSL_IMX8MP_ANALOG
     select IMX
 
 config FSL_IMX8MM_EVK
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
 
     object_initialize_child(obj, "gic", &s->gic, gicv3_class_name());
 
+    object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG);
+
     for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
         g_autofree char *name = g_strdup_printf("uart%d", i + 1);
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         }
     }
 
+    /* Analog */
+    object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset",
+                            0x000fa030, &error_abort);
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->analog), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->analog), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_ANA_PLL].addr);
+
     /* UARTs */
     for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     /* Unimplemented devices */
     for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
         switch (i) {
+        case FSL_IMX8MM_ANA_PLL:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "cpu.h"
 #include "hw/char/imx_serial.h"
 #include "hw/intc/arm_gicv3_common.h"
+#include "hw/misc/imx8mp_analog.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMX8MPAnalogState  analog;
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
 };
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Add the Clock Control Module (CCM) device to i.MX8MM SoC.
The CCM implementation is shared with i.MX8MP as the register
layout is identical between the two variants.Hence iMX8MM will
be using the source of iMX8MP CCM.

Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 10 ++++++++++
 include/hw/arm/fsl-imx8mm.h |  2 ++
 3 files changed, 13 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     bool
     select ARM_GIC
     select FSL_IMX8MP_ANALOG
+    select FSL_IMX8MP_CCM
     select IMX
 
 config FSL_IMX8MM_EVK
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
 
     object_initialize_child(obj, "gic", &s->gic, gicv3_class_name());
 
+    object_initialize_child(obj, "ccm", &s->ccm, TYPE_IMX8MP_CCM);
+
     object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG);
 
     for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         }
     }
 
+    /* CCM */
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->ccm), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_CCM].addr);
+
     /* Analog */
     object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset",
                             0x000fa030, &error_abort);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
         switch (i) {
         case FSL_IMX8MM_ANA_PLL:
+        case FSL_IMX8MM_CCM:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/char/imx_serial.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/misc/imx8mp_analog.h"
+#include "hw/misc/imx8mp_ccm.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

SNVS contains an RTC which allows Linux to deal correctly with time

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of SD/MMC cards through a virtual SDHCI interface
The emulated SDHCI controller allows guest OS to use emulated storage as
a standard block device.
This will allow running the images such as those generated
by Buildroot.

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 25 +++++++++++++++++++++++++
 hw/arm/imx8mm-evk.c         | 17 +++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  7 +++++++
 4 files changed, 50 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
+    select SDHCI
 
 config FSL_IMX8MM_EVK
     bool
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
+        g_autofree char *name = g_strdup_printf("usdhc%d", i + 1);
+        object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
+    }
 }
 
 static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* USDHCs */
+    for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } usdhc_table[FSL_IMX8MM_NUM_USDHCS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC1].addr, FSL_IMX8MM_USDHC1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC2].addr, FSL_IMX8MM_USDHC2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC3].addr, FSL_IMX8MM_USDHC3_IRQ },
+        };
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->usdhc[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->usdhc[i]), 0, usdhc_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->usdhc[i]), 0,
+                           qdev_get_gpio_in(gicdev, usdhc_table[i].irq));
+    }
+
     /* SNVS */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_OCRAM:
         case FSL_IMX8MM_SNVS_HP:
         case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
+        case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3:
             /* device implemented and treated above */
             break;
 
diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/imx8mm-evk.c
+++ b/hw/arm/imx8mm-evk.c
@@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine)
     memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START,
                                 machine->ram);
 
+    for (int i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
+        BusState *bus;
+        DeviceState *carddev;
+        BlockBackend *blk;
+        DriveInfo *di = drive_get(IF_SD, i, 0);
+
+        if (!di) {
+            continue;
+        }
+
+        blk = blk_by_legacy_dinfo(di);
+        bus = qdev_get_child_bus(DEVICE(&s->usdhc[i]), "sd-bus");
+        carddev = qdev_new(TYPE_SD_CARD);
+        qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal);
+        qdev_realize_and_unref(carddev, bus, &error_fatal);
+    }
+
     if (!qtest_enabled()) {
         arm_load_kernel(&s->cpu[0], machine, &boot_info);
     }
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
+#include "hw/sd/sdhci.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
+    FSL_IMX8MM_NUM_USDHCS       = 3,
 };
 
 struct FslImx8mmState {
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX7SNVSState      snvs;
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
+    SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmMemoryRegions {
 };
 
 enum FslImx8mmIrqs {
+    FSL_IMX8MM_USDHC1_IRQ   = 22,
+    FSL_IMX8MM_USDHC2_IRQ   = 23,
+    FSL_IMX8MM_USDHC3_IRQ   = 24,
+
     FSL_IMX8MM_UART1_IRQ    = 26,
     FSL_IMX8MM_UART2_IRQ    = 27,
     FSL_IMX8MM_UART3_IRQ    = 28,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

This enables support for Designware PCI Express Controller emulation
It provides a controlled environment to debug the linux pci subsystem

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  3 +++
 hw/arm/fsl-imx8mm.c         | 30 ++++++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h | 10 ++++++++++
 3 files changed, 43 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
 
 config FSL_IMX8MM
     bool
+    imply PCI_DEVICES
     select ARM_GIC
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
     select SDHCI
+    select PCI_EXPRESS_DESIGNWARE
+    select PCI_EXPRESS_FSL_IMX8M_PHY
 
 config FSL_IMX8MM_EVK
     bool
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         g_autofree char *name = g_strdup_printf("usdhc%d", i + 1);
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
     }
+
+    object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
+    object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
+                            TYPE_FSL_IMX8M_PCIE_PHY);
 }
 
 static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0,
                     fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr);
 
+    /* PCIe */
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_PCIE1].addr);
+
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTA_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTB_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTC_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTD_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 4,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_MSI_IRQ));
+
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie_phy), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie_phy), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_PCIE_PHY1].addr);
+
     /* Unimplemented devices */
     for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) {
         switch (i) {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_CCM:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
+        case FSL_IMX8MM_PCIE1:
+        case FSL_IMX8MM_PCIE_PHY1:
         case FSL_IMX8MM_RAM:
         case FSL_IMX8MM_OCRAM:
         case FSL_IMX8MM_SNVS_HP:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
+#include "hw/pci-host/designware.h"
+#include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
 #include "qom/object.h"
 #include "qemu/units.h"
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
+    DesignwarePCIEHost pcie;
+    FslImx8mPciePhyState   pcie_phy;
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART2_IRQ    = 27,
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
+
+    FSL_IMX8MM_PCI_INTA_IRQ = 122,
+    FSL_IMX8MM_PCI_INTB_IRQ = 123,
+    FSL_IMX8MM_PCI_INTC_IRQ = 124,
+    FSL_IMX8MM_PCI_INTD_IRQ = 125,
+    FSL_IMX8MM_PCI_MSI_IRQ  = 127,
 };
 
 #endif /* FSL_IMX8MM_H */
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Enabled GPIO controller emulation
Also updated the GPIO IRQ lines of iMX8MM

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/fsl-imx8mm.c         | 54 +++++++++++++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h | 14 ++++++++++
 2 files changed, 68 insertions(+)

diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
+        g_autofree char *name = g_strdup_printf("gpio%d", i + 1);
+        object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO);
+    }
+
     for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
         g_autofree char *name = g_strdup_printf("usdhc%d", i + 1);
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* GPIOs */
+    for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq_low;
+            unsigned int irq_high;
+        } gpio_table[FSL_IMX8MM_NUM_GPIOS] = {
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO1].addr,
+                FSL_IMX8MM_GPIO1_LOW_IRQ,
+                FSL_IMX8MM_GPIO1_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO2].addr,
+                FSL_IMX8MM_GPIO2_LOW_IRQ,
+                FSL_IMX8MM_GPIO2_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO3].addr,
+                FSL_IMX8MM_GPIO3_LOW_IRQ,
+                FSL_IMX8MM_GPIO3_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO4].addr,
+                FSL_IMX8MM_GPIO4_LOW_IRQ,
+                FSL_IMX8MM_GPIO4_HIGH_IRQ
+            },
+            {
+                fsl_imx8mm_memmap[FSL_IMX8MM_GPIO5].addr,
+                FSL_IMX8MM_GPIO5_LOW_IRQ,
+                FSL_IMX8MM_GPIO5_HIGH_IRQ
+            },
+        };
+        object_property_set_bool(OBJECT(&s->gpio[i]), "has-edge-sel", true,
+                                 &error_abort);
+        object_property_set_bool(OBJECT(&s->gpio[i]), "has-upper-pin-irq",
+                                 true, &error_abort);
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpio[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpio[i]), 0, gpio_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0,
+                           qdev_get_gpio_in(gicdev, gpio_table[i].irq_low));
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1,
+                           qdev_get_gpio_in(gicdev, gpio_table[i].irq_high));
+    }
+
     /* USDHCs */
     for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_CCM:
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
+        case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 
 #include "cpu.h"
 #include "hw/char/imx_serial.h"
+#include "hw/gpio/imx_gpio.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
 
 enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
+    FSL_IMX8MM_NUM_GPIOS        = 5,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
     FSL_IMX8MM_NUM_USDHCS       = 3,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMXGPIOState       gpio[FSL_IMX8MM_NUM_GPIOS];
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMX7SNVSState      snvs;
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
 
+    FSL_IMX8MM_GPIO1_LOW_IRQ  = 64,
+    FSL_IMX8MM_GPIO1_HIGH_IRQ = 65,
+    FSL_IMX8MM_GPIO2_LOW_IRQ  = 66,
+    FSL_IMX8MM_GPIO2_HIGH_IRQ = 67,
+    FSL_IMX8MM_GPIO3_LOW_IRQ  = 68,
+    FSL_IMX8MM_GPIO3_HIGH_IRQ = 69,
+    FSL_IMX8MM_GPIO4_LOW_IRQ  = 70,
+    FSL_IMX8MM_GPIO4_HIGH_IRQ = 71,
+    FSL_IMX8MM_GPIO5_LOW_IRQ  = 72,
+    FSL_IMX8MM_GPIO5_HIGH_IRQ = 73,
+
     FSL_IMX8MM_PCI_INTA_IRQ = 122,
     FSL_IMX8MM_PCI_INTB_IRQ = 123,
     FSL_IMX8MM_PCI_INTC_IRQ = 124,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

This can be used to test and debug I2C device drivers.
Added I2C interrupts

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  2 ++
 hw/arm/fsl-imx8mm.c         | 27 +++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  8 ++++++++
 3 files changed, 37 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MP_EVK
 config FSL_IMX8MM
     bool
     imply PCI_DEVICES
+    imply I2C_DEVICES
     select ARM_GIC
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
+    select IMX_I2C
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
+        g_autofree char *name = g_strdup_printf("i2c%d", i + 1);
+        object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C);
+    }
+
     for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
         g_autofree char *name = g_strdup_printf("gpio%d", i + 1);
         object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* I2Cs */
+    for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } i2c_table[FSL_IMX8MM_NUM_I2CS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C1].addr, FSL_IMX8MM_I2C1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C2].addr, FSL_IMX8MM_I2C2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C3].addr, FSL_IMX8MM_I2C3_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_I2C4].addr, FSL_IMX8MM_I2C4_IRQ },
+        };
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->i2c[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, i2c_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0,
+                           qdev_get_gpio_in(gicdev, i2c_table[i].irq));
+    }
+
     /* GPIOs */
     for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
+        case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
         case FSL_IMX8MM_RAM:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "cpu.h"
 #include "hw/char/imx_serial.h"
 #include "hw/gpio/imx_gpio.h"
+#include "hw/i2c/imx_i2c.h"
 #include "hw/intc/arm_gicv3_common.h"
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
 enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
     FSL_IMX8MM_NUM_GPIOS        = 5,
+    FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
     FSL_IMX8MM_NUM_USDHCS       = 3,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMX7SNVSState      snvs;
+    IMXI2CState        i2c[FSL_IMX8MM_NUM_I2CS];
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
 
+    FSL_IMX8MM_I2C1_IRQ     = 35,
+    FSL_IMX8MM_I2C2_IRQ     = 36,
+    FSL_IMX8MM_I2C3_IRQ     = 37,
+    FSL_IMX8MM_I2C4_IRQ     = 38,
+
     FSL_IMX8MM_GPIO1_LOW_IRQ  = 64,
     FSL_IMX8MM_GPIO1_HIGH_IRQ = 65,
     FSL_IMX8MM_GPIO2_LOW_IRQ  = 66,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of ECSPI in iMX8MM
Added SPI IRQ lines

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/fsl-imx8mm.c         | 26 ++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  7 +++++++
 2 files changed, 33 insertions(+)

diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
+        g_autofree char *name = g_strdup_printf("spi%d", i + 1);
+        object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI);
+    }
+
     object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
     object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
                             TYPE_FSL_IMX8M_PCIE_PHY);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                            qdev_get_gpio_in(gicdev, usdhc_table[i].irq));
     }
 
+    /* ECSPIs */
+    for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } spi_table[FSL_IMX8MM_NUM_ECSPIS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI1].addr, FSL_IMX8MM_ECSPI1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI2].addr, FSL_IMX8MM_ECSPI2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI3].addr, FSL_IMX8MM_ECSPI3_IRQ },
+        };
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->spi[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, spi_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0,
+                           qdev_get_gpio_in(gicdev, spi_table[i].irq));
+    }
+
     /* SNVS */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
+        case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3:
         case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci-host/designware.h"
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
+#include "hw/ssi/imx_spi.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM)
 
 enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
+    FSL_IMX8MM_NUM_ECSPIS       = 3,
     FSL_IMX8MM_NUM_GPIOS        = 5,
     FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
     IMX7SNVSState      snvs;
+    IMXSPIState        spi[FSL_IMX8MM_NUM_ECSPIS];
     IMXI2CState        i2c[FSL_IMX8MM_NUM_I2CS];
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_UART3_IRQ    = 28,
     FSL_IMX8MM_UART4_IRQ    = 29,
 
+    FSL_IMX8MM_ECSPI1_IRQ   = 31,
+    FSL_IMX8MM_ECSPI2_IRQ   = 32,
+    FSL_IMX8MM_ECSPI3_IRQ   = 33,
+
     FSL_IMX8MM_I2C1_IRQ     = 35,
     FSL_IMX8MM_I2C2_IRQ     = 36,
     FSL_IMX8MM_I2C3_IRQ     = 37,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of WDT in iMX8MM
Added WDT IRQ lines

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 28 ++++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  7 +++++++
 3 files changed, 36 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
+    select WDT_IMX2
 
 config FSL_IMX8MM_EVK
     bool
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) {
+        g_autofree char *name = g_strdup_printf("wdt%d", i);
+        object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT);
+    }
+
     object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
     object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
                             TYPE_FSL_IMX8M_PCIE_PHY);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0,
                     fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr);
 
+    /* Watchdogs */
+    for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } wdog_table[FSL_IMX8MM_NUM_WDTS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG1].addr, FSL_IMX8MM_WDOG1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG2].addr, FSL_IMX8MM_WDOG2_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG3].addr, FSL_IMX8MM_WDOG3_IRQ },
+        };
+
+        object_property_set_bool(OBJECT(&s->wdt[i]), "pretimeout-support",
+                                 true, &error_abort);
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->wdt[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, wdog_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0,
+                           qdev_get_gpio_in(gicdev, wdog_table[i].irq));
+    }
+
     /* PCIe */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_SNVS_HP:
         case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
         case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3:
+        case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3:
             /* device implemented and treated above */
             break;
 
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
 #include "hw/ssi/imx_spi.h"
+#include "hw/watchdog/wdt_imx2.h"
 #include "qom/object.h"
 #include "qemu/units.h"
 
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
     FSL_IMX8MM_NUM_USDHCS       = 3,
+    FSL_IMX8MM_NUM_WDTS         = 3,
 };
 
 struct FslImx8mmState {
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
+    IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
 };
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_GPIO5_LOW_IRQ  = 72,
     FSL_IMX8MM_GPIO5_HIGH_IRQ = 73,
 
+    FSL_IMX8MM_WDOG1_IRQ    = 78,
+    FSL_IMX8MM_WDOG2_IRQ    = 79,
+    FSL_IMX8MM_WDOG3_IRQ    = 10,
+
     FSL_IMX8MM_PCI_INTA_IRQ = 122,
     FSL_IMX8MM_PCI_INTB_IRQ = 123,
     FSL_IMX8MM_PCI_INTC_IRQ = 124,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of GPT in iMX8MM
Added GPT IRQ lines

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 54 +++++++++++++++++++++++++++++++++++++
 hw/timer/imx_gpt.c          | 26 ++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h | 11 ++++++++
 include/hw/timer/imx_gpt.h  |  2 ++
 5 files changed, 94 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select FSL_IMX8MP_CCM
     select IMX
     select IMX_I2C
+    select OR_IRQ
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) {
+        g_autofree char *name = g_strdup_printf("gpt%d", i + 1);
+        object_initialize_child(obj, name, &s->gpt[i], TYPE_IMX8MM_GPT);
+    }
+    object_initialize_child(obj, "gpt5-gpt6-irq", &s->gpt5_gpt6_irq,
+                            TYPE_OR_IRQ);
+
     for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
         g_autofree char *name = g_strdup_printf("i2c%d", i + 1);
         object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                                 fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr,
                                 &s->ocram);
 
+    /* GPTs */
+    object_property_set_int(OBJECT(&s->gpt5_gpt6_irq), "num-lines", 2,
+                            &error_abort);
+    if (!qdev_realize(DEVICE(&s->gpt5_gpt6_irq), NULL, errp)) {
+        return;
+    }
+
+    qdev_connect_gpio_out(DEVICE(&s->gpt5_gpt6_irq), 0,
+                          qdev_get_gpio_in(gicdev, FSL_IMX8MM_GPT5_GPT6_IRQ));
+
+    for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) {
+        hwaddr gpt_addrs[FSL_IMX8MM_NUM_GPTS] = {
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT1].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT2].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT3].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT4].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT5].addr,
+            fsl_imx8mm_memmap[FSL_IMX8MM_GPT6].addr,
+        };
+
+        s->gpt[i].ccm = IMX_CCM(&s->ccm);
+
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpt[i]), errp)) {
+            return;
+        }
+
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpt[i]), 0, gpt_addrs[i]);
+
+        if (i < FSL_IMX8MM_NUM_GPTS - 2) {
+            static const unsigned int gpt_irqs[FSL_IMX8MM_NUM_GPTS - 2] = {
+                FSL_IMX8MM_GPT1_IRQ,
+                FSL_IMX8MM_GPT2_IRQ,
+                FSL_IMX8MM_GPT3_IRQ,
+                FSL_IMX8MM_GPT4_IRQ,
+            };
+
+            sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0,
+                               qdev_get_gpio_in(gicdev, gpt_irqs[i]));
+        } else {
+            int irq = i - FSL_IMX8MM_NUM_GPTS + 2;
+
+            sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0,
+                               qdev_get_gpio_in(DEVICE(&s->gpt5_gpt6_irq), irq));
+        }
+    }
+
     /* I2Cs */
     for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GIC_DIST:
         case FSL_IMX8MM_GIC_REDIST:
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
+        case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6:
         case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3:
         case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/timer/imx_gpt.c
+++ b/hw/timer/imx_gpt.c
@@ -XXX,XX +XXX,XX @@
  * Originally written by Hans Jiang
  * Updated by Peter Chubb
  * Updated by Jean-Christophe Dubois <jcd@tribudubois.net>
+ * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com>
  *
  * This code is licensed under GPL version 2 or later.  See
  * the COPYING file in the top-level directory.
@@ -XXX,XX +XXX,XX @@ static const IMXClk imx8mp_gpt_clocks[] = {
     CLK_NONE,      /* 111 not defined */
 };
 
+static const IMXClk imx8mm_gpt_clocks[] = {
+    CLK_NONE,      /* 000 No clock source */
+    CLK_IPG,       /* 001 ipg_clk, 532MHz */
+    CLK_IPG_HIGH,  /* 010 ipg_clk_highfreq */
+    CLK_EXT,       /* 011 External clock */
+    CLK_32k,       /* 100 ipg_clk_32k */
+    CLK_HIGH,      /* 101 ipg_clk_16M */
+    CLK_NONE,      /* 110 not defined */
+    CLK_NONE,      /* 111 not defined */
+};
+
 /* Must be called from within ptimer_transaction_begin/commit block */
 static void imx_gpt_set_freq(IMXGPTState *s)
 {
@@ -XXX,XX +XXX,XX @@ static void imx8mp_gpt_init(Object *obj)
     s->clocks = imx8mp_gpt_clocks;
 }
 
+static void imx8mm_gpt_init(Object *obj)
+{
+    IMXGPTState *s = IMX_GPT(obj);
+
+    s->clocks = imx8mm_gpt_clocks;
+}
+
 static const TypeInfo imx25_gpt_info = {
     .name = TYPE_IMX25_GPT,
     .parent = TYPE_SYS_BUS_DEVICE,
@@ -XXX,XX +XXX,XX @@ static const TypeInfo imx8mp_gpt_info = {
     .instance_init = imx8mp_gpt_init,
 };
 
+static const TypeInfo imx8mm_gpt_info = {
+    .name = TYPE_IMX8MM_GPT,
+    .parent = TYPE_IMX25_GPT,
+    .instance_init = imx8mm_gpt_init,
+};
+
 static void imx_gpt_register_types(void)
 {
     type_register_static(&imx25_gpt_info);
@@ -XXX,XX +XXX,XX @@ static void imx_gpt_register_types(void)
     type_register_static(&imx6ul_gpt_info);
     type_register_static(&imx7_gpt_info);
     type_register_static(&imx8mp_gpt_info);
+    type_register_static(&imx8mm_gpt_info);
 }
 
 type_init(imx_gpt_register_types)
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
+#include "hw/or-irq.h"
 #include "hw/pci-host/designware.h"
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
 #include "hw/ssi/imx_spi.h"
+#include "hw/timer/imx_gpt.h"
 #include "hw/watchdog/wdt_imx2.h"
 #include "qom/object.h"
 #include "qemu/units.h"
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_CPUS         = 4,
     FSL_IMX8MM_NUM_ECSPIS       = 3,
     FSL_IMX8MM_NUM_GPIOS        = 5,
+    FSL_IMX8MM_NUM_GPTS         = 6,
     FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
 
     ARMCPU             cpu[FSL_IMX8MM_NUM_CPUS];
     GICv3State         gic;
+    IMXGPTState        gpt[FSL_IMX8MM_NUM_GPTS];
     IMXGPIOState       gpio[FSL_IMX8MM_NUM_GPIOS];
     IMX8MPCCMState     ccm;
     IMX8MPAnalogState  analog;
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
+    OrIRQState         gpt5_gpt6_irq;
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_I2C3_IRQ     = 37,
     FSL_IMX8MM_I2C4_IRQ     = 38,
 
+    FSL_IMX8MM_GPT1_IRQ      = 55,
+    FSL_IMX8MM_GPT2_IRQ      = 54,
+    FSL_IMX8MM_GPT3_IRQ      = 53,
+    FSL_IMX8MM_GPT4_IRQ      = 52,
+    FSL_IMX8MM_GPT5_GPT6_IRQ = 51,
+
     FSL_IMX8MM_GPIO1_LOW_IRQ  = 64,
     FSL_IMX8MM_GPIO1_HIGH_IRQ = 65,
     FSL_IMX8MM_GPIO2_LOW_IRQ  = 66,
diff --git a/include/hw/timer/imx_gpt.h b/include/hw/timer/imx_gpt.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/timer/imx_gpt.h
+++ b/include/hw/timer/imx_gpt.h
@@ -XXX,XX +XXX,XX @@
  * Originally written by Hans Jiang
  * Updated by Peter Chubb
  * Updated by Jean-Christophe Dubois <jcd@tribudubois.net>
+ * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -XXX,XX +XXX,XX @@
 #define TYPE_IMX6UL_GPT "imx6ul.gpt"
 #define TYPE_IMX7_GPT "imx7.gpt"
 #define TYPE_IMX8MP_GPT "imx8mp.gpt"
+#define TYPE_IMX8MM_GPT "imx8mm.gpt"
 
 #define TYPE_IMX_GPT TYPE_IMX25_GPT
 
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of ENET ethernet controller in iMX8MM
Enables testing and debugging of network dependent drivers
Added ENET MAC IRQ lines

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 24 ++++++++++++++++++++++++
 hw/arm/imx8mm-evk.c         |  1 +
 include/hw/arm/fsl-imx8mm.h | 10 +++++++++-
 4 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select FSL_IMX8MP_ANALOG
     select FSL_IMX8MP_CCM
     select IMX
+    select IMX_FEC
     select IMX_I2C
     select OR_IRQ
     select SDHCI
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT);
     }
 
+    object_initialize_child(obj, "eth0", &s->enet, TYPE_IMX_ENET);
+
     object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST);
     object_initialize_child(obj, "pcie_phy", &s->pcie_phy,
                             TYPE_FSL_IMX8M_PCIE_PHY);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                            qdev_get_gpio_in(gicdev, spi_table[i].irq));
     }
 
+    /* ENET1 */
+    object_property_set_uint(OBJECT(&s->enet), "phy-num", s->phy_num,
+                             &error_abort);
+    object_property_set_uint(OBJECT(&s->enet), "tx-ring-num", 3, &error_abort);
+    qemu_configure_nic_device(DEVICE(&s->enet), true, NULL);
+    if (!sysbus_realize(SYS_BUS_DEVICE(&s->enet), errp)) {
+        return;
+    }
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->enet), 0,
+                    fsl_imx8mm_memmap[FSL_IMX8MM_ENET1].addr);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 0,
+                       qdev_get_gpio_in(gicdev, FSL_IMX8MM_ENET1_MAC_IRQ));
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 1,
+                       qdev_get_gpio_in(gicdev, FSL_IMX6_ENET1_MAC_1588_IRQ));
+
     /* SNVS */
     if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) {
         return;
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5:
         case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6:
         case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3:
+        case FSL_IMX8MM_ENET1:
         case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4:
         case FSL_IMX8MM_PCIE1:
         case FSL_IMX8MM_PCIE_PHY1:
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
     }
 }
 
+static const Property fsl_imx8mm_properties[] = {
+    DEFINE_PROP_UINT32("fec1-phy-num", FslImx8mmState, phy_num, 0),
+    DEFINE_PROP_BOOL("fec1-phy-connected", FslImx8mmState, phy_connected, true),
+};
+
 static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(oc);
 
+    device_class_set_props(dc, fsl_imx8mm_properties);
     dc->realize = fsl_imx8mm_realize;
 
     dc->desc = "i.MX 8MM SoC";
diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/imx8mm-evk.c
+++ b/hw/arm/imx8mm-evk.c
@@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine)
 
     s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine),
                                          "soc", &error_fatal, NULL));
+    object_property_set_uint(OBJECT(s), "fec1-phy-num", 1, &error_fatal);
     sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal);
 
     memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START,
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/misc/imx7_snvs.h"
 #include "hw/misc/imx8mp_analog.h"
 #include "hw/misc/imx8mp_ccm.h"
-#include "hw/or-irq.h"
+#include "hw/net/imx_fec.h"
+#include "hw/core/or-irq.h"
 #include "hw/pci-host/designware.h"
 #include "hw/pci-host/fsl_imx8m_phy.h"
 #include "hw/sd/sdhci.h"
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXI2CState        i2c[FSL_IMX8MM_NUM_I2CS];
     IMXSerialState     uart[FSL_IMX8MM_NUM_UARTS];
     MemoryRegion ocram;
+    IMXFECState        enet;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
     IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
     OrIRQState         gpt5_gpt6_irq;
+
+    uint32_t           phy_num;
+    bool               phy_connected;
 };
 
 enum FslImx8mmMemoryRegions {
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_WDOG2_IRQ    = 79,
     FSL_IMX8MM_WDOG3_IRQ    = 10,
 
+    FSL_IMX8MM_ENET1_MAC_IRQ    = 118,
+    FSL_IMX6_ENET1_MAC_1588_IRQ = 121,
+
     FSL_IMX8MM_PCI_INTA_IRQ = 122,
     FSL_IMX8MM_PCI_INTB_IRQ = 123,
     FSL_IMX8MM_PCI_INTC_IRQ = 124,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

It enables emulation of USB on iMX8MM
Enables testing and debugging of USB drivers

Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx8mm.c         | 27 +++++++++++++++++++++++++++
 include/hw/arm/fsl-imx8mm.h |  6 ++++++
 3 files changed, 34 insertions(+)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX8MM
     select SDHCI
     select PCI_EXPRESS_DESIGNWARE
     select PCI_EXPRESS_FSL_IMX8M_PHY
+    select USB_DWC3
     select WDT_IMX2
 
 config FSL_IMX8MM_EVK
diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx8mm.c
+++ b/hw/arm/fsl-imx8mm.c
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj)
         object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC);
     }
 
+    for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) {
+        g_autofree char *name = g_strdup_printf("usb%d", i);
+        object_initialize_child(obj, name, &s->usb[i], TYPE_USB_DWC3);
+    }
+
     for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
         g_autofree char *name = g_strdup_printf("spi%d", i + 1);
         object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI);
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
                            qdev_get_gpio_in(gicdev, usdhc_table[i].irq));
     }
 
+    /* USBs */
+    for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) {
+        static const struct {
+            hwaddr addr;
+            unsigned int irq;
+        } usb_table[FSL_IMX8MM_NUM_USBS] = {
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USB1].addr, FSL_IMX8MM_USB1_IRQ },
+            { fsl_imx8mm_memmap[FSL_IMX8MM_USB2].addr, FSL_IMX8MM_USB2_IRQ },
+        };
+
+        qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p2", 1);
+        qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p3", 1);
+        qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "slots", 2);
+        if (!sysbus_realize(SYS_BUS_DEVICE(&s->usb[i]), errp)) {
+            return;
+        }
+        sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, usb_table[i].addr);
+        sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i].sysbus_xhci), 0,
+                           qdev_get_gpio_in(gicdev, usb_table[i].irq));
+    }
+
     /* ECSPIs */
     for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) {
         static const struct {
@@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp)
         case FSL_IMX8MM_OCRAM:
         case FSL_IMX8MM_SNVS_HP:
         case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4:
+        case FSL_IMX8MM_USB1 ... FSL_IMX8MM_USB2:
         case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3:
         case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3:
             /* device implemented and treated above */
diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx8mm.h
+++ b/include/hw/arm/fsl-imx8mm.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/sd/sdhci.h"
 #include "hw/ssi/imx_spi.h"
 #include "hw/timer/imx_gpt.h"
+#include "hw/usb/hcd-dwc3.h"
 #include "hw/watchdog/wdt_imx2.h"
 #include "qom/object.h"
 #include "qemu/units.h"
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration {
     FSL_IMX8MM_NUM_I2CS         = 4,
     FSL_IMX8MM_NUM_IRQS         = 128,
     FSL_IMX8MM_NUM_UARTS        = 4,
+    FSL_IMX8MM_NUM_USBS         = 2,
     FSL_IMX8MM_NUM_USDHCS       = 3,
     FSL_IMX8MM_NUM_WDTS         = 3,
 };
@@ -XXX,XX +XXX,XX @@ struct FslImx8mmState {
     IMXFECState        enet;
     SDHCIState         usdhc[FSL_IMX8MM_NUM_USDHCS];
     IMX2WdtState       wdt[FSL_IMX8MM_NUM_WDTS];
+    USBDWC3            usb[FSL_IMX8MM_NUM_USBS];
     DesignwarePCIEHost pcie;
     FslImx8mPciePhyState   pcie_phy;
     OrIRQState         gpt5_gpt6_irq;
@@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs {
     FSL_IMX8MM_I2C3_IRQ     = 37,
     FSL_IMX8MM_I2C4_IRQ     = 38,
 
+    FSL_IMX8MM_USB1_IRQ     = 40,
+    FSL_IMX8MM_USB2_IRQ     = 41,
+
     FSL_IMX8MM_GPT1_IRQ      = 55,
     FSL_IMX8MM_GPT2_IRQ      = 54,
     FSL_IMX8MM_GPT3_IRQ      = 53,
-- 
2.43.0

From: Gaurav Sharma <gaurav.sharma_7@nxp.com>

Added script that would validate the iMX8MM emulation by checking the
linux console log. If it succeeds, it will return:-

ok 1 test_imx8mm_evk.Imx8mmEvkMachine.test_aarch64_imx8mm_evk_usdhc

Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
[PMM: Add missing blank lines that flake8 wants]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS                                 |  1 +
 tests/functional/aarch64/meson.build        |  2 +
 tests/functional/aarch64/test_imx8mm_evk.py | 69 +++++++++++++++++++++
 3 files changed, 72 insertions(+)
 create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/arm/fsl-imx8mm.c
 F: hw/arm/imx8mm-evk.c
 F: include/hw/arm/fsl-imx8mm.h
 F: docs/system/arm/imx8m.rst
+F: tests/functional/aarch64/test_imx8mm_evk.py
 
 MCIMX8MP-EVK / i.MX8MP
 M: Bernhard Beschow <shentey@gmail.com>
diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/tests/functional/aarch64/meson.build
+++ b/tests/functional/aarch64/meson.build
@@ -XXX,XX +XXX,XX @@ test_aarch64_timeouts = {
   'aspeed_ast2700a2' : 600,
   'aspeed_ast2700fc' : 600,
   'device_passthrough' : 720,
+  'imx8mm_evk' : 240,
   'imx8mp_evk' : 240,
   'raspi4' : 480,
   'reverse_debug' : 180,
@@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [
   'aspeed_ast2700fc',
   'device_passthrough',
   'hotplug_pci',
+  'imx8mm_evk',
   'imx8mp_evk',
   'kvm',
   'multiprocess',
diff --git a/tests/functional/aarch64/test_imx8mm_evk.py b/tests/functional/aarch64/test_imx8mm_evk.py
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/functional/aarch64/test_imx8mm_evk.py
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Functional test that boots a Linux kernel and checks the console
+#
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+from qemu_test import LinuxKernelTest, Asset
+
+
+class Imx8mmEvkMachine(LinuxKernelTest):
+
+    ASSET_IMAGE = Asset(
+        ('https://cloud.debian.org/images/cloud/bookworm/20231210-1590/'
+         'debian-12-generic-arm64-20231210-1590.tar.xz'),
+        '7ebf1577b32d5af6204df74b54ca2e4675de9b5a9fa14f3ff70b88eeb7b3b359')
+
+    KERNEL_OFFSET = 0x51000000
+    KERNEL_SIZE = 32622528
+    INITRD_OFFSET = 0x76000000
+    INITRD_SIZE = 30987766
+    DTB_OFFSET = 0x64DB5000
+    DTB_SIZE = 36812
+
+    def extract(self, in_path, out_path, offset, size):
+        try:
+            with open(in_path, "rb") as source:
+                source.seek(offset)
+                data = source.read(size)
+            with open(out_path, "wb") as target:
+                target.write(data)
+        except (IOError, ValueError) as e:
+            self.log.error(f"Failed to extract {out_path}: {e}")
+            raise
+
+    def setUp(self):
+        super().setUp()
+
+        self.image_path = self.scratch_file("disk.raw")
+        self.kernel_path = self.scratch_file("linux")
+        self.initrd_path = self.scratch_file("initrd.zstd")
+        self.dtb_path = self.scratch_file("imx8mm-evk.dtb")
+
+        self.archive_extract(self.ASSET_IMAGE)
+        self.extract(self.image_path, self.kernel_path,
+                     self.KERNEL_OFFSET, self.KERNEL_SIZE)
+        self.extract(self.image_path, self.initrd_path,
+                     self.INITRD_OFFSET, self.INITRD_SIZE)
+        self.extract(self.image_path, self.dtb_path,
+                     self.DTB_OFFSET, self.DTB_SIZE)
+
+    def test_aarch64_imx8mm_evk_usdhc(self):
+        self.require_accelerator("tcg")
+        self.set_machine('imx8mm-evk')
+        self.vm.set_console(console_index=1)
+        self.vm.add_args('-m', '2G',
+                         '-smp', '4',
+                         '-kernel', self.kernel_path,
+                         '-initrd', self.initrd_path,
+                         '-dtb', self.dtb_path,
+                         '-append', 'root=/dev/mmcblk2p1',
+                         '-drive', f'file={self.image_path},if=sd,bus=2,'
+                                    'format=raw,id=mmcblk2,snapshot=on')
+
+        self.vm.launch()
+        self.wait_for_console_pattern('Welcome to ')
+
+
+if __name__ == '__main__':
+    LinuxKernelTest.main()
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

As mentioned by Richard in [*]:

We don't actually need any specific endianness here, because
  every byte has the same value.  So we could simply drop MO_TE.
  That would produce a store in host-endianness, which will be
  fractionally more efficient on some hosts.

[*] https://lore.kernel.org/qemu-devel/d64d3576-9188-4e74-afdc-3492c9feb8e0@linaro.org/

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260414005348.4767-2-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-a64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -XXX,XX +XXX,XX @@ static uint64_t set_step_tags(CPUARMState *env, uint64_t toaddr,
          * the page dirty and will use the fast path.
          */
         uint64_t repldata = data * 0x0101010101010101ULL;
-        MemOpIdx oi16 = make_memop_idx(MO_TE | MO_128, memidx);
+        MemOpIdx oi16 = make_memop_idx(MO_128, memidx);
         cpu_st16_mmu(env, toaddr, int128_make128(repldata, repldata), oi16, ra);
         mte_mops_set_tags(env, toaddr, 16, *mtedesc);
         return 16;
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Extract the implicit MO_TE definition in order to replace
it in the next commit.

Mechanical change using:

$ for n in UW UL UQ UO SW SL SQ; do \
      sed -i -e "s/MO_TE$n/MO_TE | MO_$n/" \
           $(git grep -l MO_TE$n target/arm); \
    done

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-3-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c   |  6 +--
 target/arm/tcg/mve_helper.c | 79 ++++++++++++++++++++-----------------
 2 files changed, 45 insertions(+), 40 deletions(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
 
     /* Note that these stores can throw exceptions on MPU faults */
     ARMMMUIdx mmu_idx = arm_mmu_idx(env);
-    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+    MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN,
                                  arm_to_core_mmu_idx(mmu_idx));
     cpu_stl_mmu(env, sp, nextinst, oi, GETPC());
     cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC());
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
     bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK;
     uintptr_t ra = GETPC();
     ARMMMUIdx mmu_idx = arm_mmu_idx(env);
-    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+    MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN,
                                  arm_to_core_mmu_idx(mmu_idx));
 
     assert(env->v7m.secure);
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
     ARMCPU *cpu = env_archcpu(env);
     uintptr_t ra = GETPC();
     ARMMMUIdx mmu_idx = arm_mmu_idx(env);
-    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+    MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN,
                                  arm_to_core_mmu_idx(mmu_idx));
 
     /* fptr is the value of Rn, the frame pointer we load the FP regs from */
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
     }
 
 DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t)
-DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t)
-DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t)
+DO_VLDR(vldrh, MO_TE | MO_UW, 2, uint16_t, ldw, 2, uint16_t)
+DO_VLDR(vldrw, MO_TE | MO_UL, 4, uint32_t, ldl, 4, uint32_t)
 
 DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t)
-DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t)
-DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t)
+DO_VSTR(vstrh, MO_TE | MO_UW, 2, stw, 2, uint16_t)
+DO_VSTR(vstrw, MO_TE | MO_UL, 4, stl, 4, uint32_t)
 
 DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t)
 DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t)
 DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t)
 DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t)
-DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t)
-DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t)
+DO_VLDR(vldrh_sw, MO_TE | MO_SW, 2, int16_t, ldw, 4, int32_t)
+DO_VLDR(vldrh_uw, MO_TE | MO_UW, 2, uint16_t, ldw, 4, uint32_t)
 
 DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t)
 DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t)
-DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
+DO_VSTR(vstrh_w, MO_TE | MO_UW, 2, stw, 4, int32_t)
 
 #undef DO_VLDR
 #undef DO_VSTR
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
 
 DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4,
+           int32_t, uint32_t, ADDR_ADD, false)
 
 DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
+           uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
+           uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
+           uint32_t, uint32_t, ADDR_ADD, false)
 DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4,
            int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2,
+DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
            uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
            uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4,
+DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
            uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false)
 DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false)
 
-DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
+DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
+           uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
-DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true)
+DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
 
 /*
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
+        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-4-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-5-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 43 +++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 23 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
+        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx);        \
+        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
 
 DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4,
-           int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false)
 
 DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false)
 DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
-           uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
-           uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
-           uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
 DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_sw, MO_SW, int16_t, ldw, 4,
            int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2,
+DO_VLDR_SG(vldrh_sg_os_uh, MO_UW, uint16_t, ldw, 2,
            uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4,
+DO_VLDR_SG(vldrh_sg_os_uw, MO_UW, uint16_t, ldw, 4,
            uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
+DO_VLDR_SG(vldrw_sg_os_uw, MO_UL, uint32_t, ldl, 4,
            uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false)
 DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrh_sg_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD, false)
+DO_VSTR_SG(vstrw_sg_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, false)
 DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false)
 
-DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
+DO_VSTR_SG(vstrh_sg_os_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrh_sg_os_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false)
+DO_VSTR_SG(vstrw_sg_os_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4,
-           uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
-DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true)
+DO_VSTR_SG(vstrw_sg_wb_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
 
 /*
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-6-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/internals.h      | 6 ++++++
 target/arm/tcg/mve_helper.c | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/target/arm/internals.h b/target/arm/internals.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -XXX,XX +XXX,XX @@
 #include "exec/hwaddr.h"
 #include "exec/vaddr.h"
 #include "exec/breakpoint.h"
+#include "exec/memop.h"
 #include "accel/tcg/tb-cpu-state.h"
 #include "hw/core/registerfields.h"
 #include "tcg/tcg-gvec-desc.h"
@@ -XXX,XX +XXX,XX @@
 #define BANK_HYP    6
 #define BANK_MON    7
 
+static inline MemOp mo_endian(CPUARMState *env)
+{
+    return EX_TBFLAG_ANY(env->hflags, BE_DATA) ? MO_BE : MO_LE;
+}
+
 static inline int arm_env_mmu_index(CPUARMState *env)
 {
     return EX_TBFLAG_ANY(env->hflags, MMUIDX);
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-7-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 47 +++++++++++++++++++++++--------------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned b, e;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         /*                                                              \
          * R_SXTM allows the dest reg to become UNKNOWN for abandoned   \
@@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env)
         uint16_t mask = mve_element_mask(env);                          \
         unsigned b, e;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         for (b = 0, e = 0; b < 16; b += ESIZE, e++) {                   \
             if (mask & (1 << b)) {                                      \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN,          \
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \
                                      mmu_idx);                          \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t)
         unsigned e;                                                     \
         uint32_t addr;                                                  \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         uint32_t addr, data;                                            \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         int y; /* y counts 0 2 0 2 */                                   \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t *qd;                                                   \
         int y;                                                          \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint8_t *qd;                                                    \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         int e;                                                          \
         uint16_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         uint32_t *qd;                                                   \
         int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
-        MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\
+        MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \
+                                     mmu_idx);                          \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-8-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/meson.build  | 3 ++-
 target/arm/tcg/mve_helper.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c'))
 arm_ss.add(files(
   'cpu32.c',
   'm_helper.c',
-  'mve_helper.c',
 ))
 
 arm_ss.add(when: 'TARGET_AARCH64', if_true: files(
@@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add(
   'debug.c',
   'hflags.c',
   'gengvec.c',
+  'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
   'psci.c',
@@ -XXX,XX +XXX,XX @@ arm_user_ss.add(
   'debug.c',
   'gengvec.c',
   'hflags.c',
+  'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
   'tlb_helper.c',
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "helper-mve.h"
 #include "internals.h"
 #include "vec_internal.h"
-#include "accel/tcg/cpu-ldst.h"
+#include "accel/tcg/cpu-ldst-common.h"
 #include "tcg/tcg.h"
 #include "fpu/softfloat.h"
 #include "crypto/clmul.h"
-- 
2.43.0

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-9-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

From: Philippe Mathieu-Daudé <philmd@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260414005348.4767-10-philmd@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c  | 2 +-
 target/arm/tcg/meson.build | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/log.h"
 #include "exec/page-protection.h"
 #ifdef CONFIG_TCG
-#include "accel/tcg/cpu-ldst.h"
+#include "accel/tcg/cpu-ldst-common.h"
 #include "semihosting/common-semi.h"
 #endif
 #if !defined(CONFIG_USER_ONLY)
diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c'))
 
 arm_ss.add(files(
   'cpu32.c',
-  'm_helper.c',
 ))
 
 arm_ss.add(when: 'TARGET_AARCH64', if_true: files(
@@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add(
   'debug.c',
   'hflags.c',
   'gengvec.c',
+  'm_helper.c',
   'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
@@ -XXX,XX +XXX,XX @@ arm_user_ss.add(
   'debug.c',
   'gengvec.c',
   'hflags.c',
+  'm_helper.c',
   'mve_helper.c',
   'neon_helper.c',
   'op_helper.c',
-- 
2.43.0

From: Thomas Huth <thuth@redhat.com>

When writing to this register, QEMU currently aborts:

$ echo "readl 0x10000018" | ./qemu-system-arm -audiodev none,id=snd0 \
    -M integratorcp,accel=qtest,audiodev=snd0 -display none -qtest stdio
 [I 0.000000] OPENED
 [R +0.001907] readl 0x10000018
 qemu: hardware error: integratorcm_read: CM_LMBUSCNT
 [...]
 Aborted                    (core dumped)

This is bad, a guest should ideally never be able to kill QEMU like this.

Now, according to the "Intergrator/CP User Guide" from:

https://developer.arm.com/documentation/dui0159/b/porting-integrator-ap-and-im-pd1/registers

"The Integrator/AP CM_LMBUSCNT has been removed."

That means this register does not seem to be implemented on real CP boards
at all, only for older AP boards. Thus it should be fine if we simply
ignore this register in QEMU and handle it like all other unimplemented
registers in the "default" handler of the case statement.

Resolves: https://gitlab.com/qemu-project/qemu/-/work_items/3407
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260420064933.64765-1-thuth@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/integratorcp.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/integratorcp.c
+++ b/hw/arm/integratorcp.c
@@ -XXX,XX +XXX,XX @@ static uint64_t integratorcm_read(void *opaque, hwaddr offset,
         } else {
             return s->cm_lock;
         }
-    case 6: /* CM_LMBUSCNT */
-        /* ??? High frequency timer.  */
-        hw_error("integratorcm_read: CM_LMBUSCNT");
     case 7: /* CM_AUXOSC */
         return s->cm_auxosc;
     case 8: /* CM_SDRAM */
-- 
2.43.0

include/hw/arm/primecell.h used to be more expansive, but now the
only thing it defines is the ARM_SYSCTL_GPIO_* constants for the GPIO
lines for the arm-sysctl system-control device used on the Realview,
Versatile and Versatile Express boards.

Replace it with a header file specific to that device.

virt.c and vmapple.c included primecell.h despite not using the
constants it defined; there we can simply drop the include entirely.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260416172627.690396-1-peter.maydell@linaro.org
---
 MAINTAINERS                  |  2 +-
 hw/arm/realview.c            |  2 +-
 hw/arm/vexpress.c            |  2 +-
 hw/arm/virt.c                |  1 -
 hw/misc/arm_sysctl.c         |  2 +-
 hw/vmapple/vmapple.c         |  1 -
 include/hw/arm/primecell.h   | 12 ------------
 include/hw/misc/arm_sysctl.h | 16 ++++++++++++++++
 8 files changed, 20 insertions(+), 18 deletions(-)
 delete mode 100644 include/hw/arm/primecell.h
 create mode 100644 include/hw/misc/arm_sysctl.h

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ F: hw/ssi/pl022.c
 F: include/hw/ssi/pl022.h
 F: hw/rtc/pl031.c
 F: include/hw/rtc/pl031.h
-F: include/hw/arm/primecell.h
 F: hw/timer/cmsdk-apb-timer.c
 F: include/hw/timer/cmsdk-apb-timer.h
 F: tests/qtest/cmsdk-apb-timer-test.c
@@ -XXX,XX +XXX,XX @@ F: hw/*/versatile*
 F: hw/i2c/arm_sbcon_i2c.c
 F: include/hw/i2c/arm_sbcon_i2c.h
 F: hw/misc/arm_sysctl.c
+F: include/hw/misc/arm_sysctl.h
 F: docs/system/arm/versatile.rst
 
 Virt
diff --git a/hw/arm/realview.c b/hw/arm/realview.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/realview.c
+++ b/hw/arm/realview.c
@@ -XXX,XX +XXX,XX @@
 #include "target/arm/cpu.h"
 #include "hw/core/sysbus.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/arm/machines-qom.h"
 #include "hw/core/split-irq.h"
+#include "hw/misc/arm_sysctl.h"
 #include "hw/net/lan9118.h"
 #include "hw/net/smc91c111.h"
 #include "hw/pci/pci.h"
diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/vexpress.c
+++ b/hw/arm/vexpress.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/datadir.h"
 #include "hw/core/sysbus.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/arm/machines-qom.h"
+#include "hw/misc/arm_sysctl.h"
 #include "hw/net/lan9118.h"
 #include "hw/i2c/i2c.h"
 #include "net/net.h"
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -XXX,XX +XXX,XX @@
 #include "monitor/qdev.h"
 #include "hw/core/sysbus.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/arm/virt.h"
 #include "hw/arm/machines-qom.h"
 #include "hw/block/flash.h"
diff --git a/hw/misc/arm_sysctl.c b/hw/misc/arm_sysctl.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/arm_sysctl.c
+++ b/hw/misc/arm_sysctl.c
@@ -XXX,XX +XXX,XX @@
 #include "system/runstate.h"
 #include "qemu/bitops.h"
 #include "hw/core/sysbus.h"
+#include "hw/misc/arm_sysctl.h"
 #include "migration/vmstate.h"
-#include "hw/arm/primecell.h"
 #include "qemu/log.h"
 #include "qemu/module.h"
 #include "qom/object.h"
diff --git a/hw/vmapple/vmapple.c b/hw/vmapple/vmapple.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/vmapple/vmapple.c
+++ b/hw/vmapple/vmapple.c
@@ -XXX,XX +XXX,XX @@
 #include "hw/core/sysbus.h"
 #include "hw/usb/usb.h"
 #include "hw/arm/boot.h"
-#include "hw/arm/primecell.h"
 #include "hw/char/pl011.h"
 #include "hw/intc/arm_gic.h"
 #include "hw/intc/arm_gicv3_common.h"
diff --git a/include/hw/arm/primecell.h b/include/hw/arm/primecell.h
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/include/hw/arm/primecell.h
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-#ifndef PRIMECELL_H
-#define PRIMECELL_H
-
-/* Declarations for ARM PrimeCell based periperals.  */
-/* Also includes some devices that are currently only used by the
-   ARM boards.  */
-
-/* arm_sysctl GPIO lines */
-#define ARM_SYSCTL_GPIO_MMC_WPROT 0
-#define ARM_SYSCTL_GPIO_MMC_CARDIN 1
-
-#endif
diff --git a/include/hw/misc/arm_sysctl.h b/include/hw/misc/arm_sysctl.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/misc/arm_sysctl.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * Status and system control registers for ARM RealView/Versatile boards.
+ *
+ * Copyright (c) Linaro Ltd
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef HW_MISC_ARM_SYSCTL_H
+#define HW_MISC_ARM_SYSCTL_H
+
+/* arm_sysctl inbound GPIO lines */
+#define ARM_SYSCTL_GPIO_MMC_WPROT 0
+#define ARM_SYSCTL_GPIO_MMC_CARDIN 1
+
+#endif
-- 
2.43.0

If we create a normally-AArch64 CPU and configure it with
aarch64=off, this will by default leave all the AArch64 ID register
values in its ARMISARegisters struct untouched.  That in turn means
that tests of cpu_isar_feature(aa64_something, cpu) will return true.

Until now we have had a design policy that you shouldn't check an
aa64_ feature unless you know that the CPU has AArch64; but this is
quite fragile as it's easy to forget and only causes a problem in the
corner case where AArch64 was turned off.  In particular, when we
extend the ability to disable AArch64 from only KVM to also TCG there
are many more aa64 feature check points which we would otherwise have
to audit for whether they needed to be guarded with a check on
ARM_FEATURE_AARCH64.

Instead, make the CPU realize function zero out all the 64-bit ID
registers if a TCG CPU doesn't have AArch64; this will make aa64_
feature tests generally return false.

We only do this for TCG because only TCG really needs it, and for
KVM it might be confusing to have QEMU's idea of the ID registers
be different from KVM's.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20260416165353.589569-2-peter.maydell@linaro.org
---
 target/arm/cpu.c | 35 +++++++++++++++++++++++++++++++++++
 target/arm/cpu.h |  3 ++-
 2 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp)
     }
 }
 
+static void arm_clear_aarch64_idregs(ARMCPU *cpu)
+{
+    /* Zero out all the AArch64 ID registers in ARMISARegisters */
+    SET_IDREG(&cpu->isar, ID_AA64ISAR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64ISAR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64ISAR2, 0);
+    SET_IDREG(&cpu->isar, ID_AA64PFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64PFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64PFR2, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR2, 0);
+    SET_IDREG(&cpu->isar, ID_AA64MMFR3, 0);
+    SET_IDREG(&cpu->isar, ID_AA64DFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64DFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64AFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64AFR1, 0);
+    SET_IDREG(&cpu->isar, ID_AA64ZFR0, 0);
+    SET_IDREG(&cpu->isar, ID_AA64SMFR0, 0);
+}
+
 static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
 {
     CPUState *cs = CPU(dev);
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
     }
 #endif
 
+    /*
+     * A TCG aarch64=off CPU has no AArch64 at all, so we clear out the
+     * ID registers to avoid cpu_isar_feature(aa64_something, cpu) tests
+     * incorrectly returning true. We don't do this for other accelerators
+     * (which in practice means "for KVM", since no others have AArch32
+     * guest support) because from KVM's point of view the AArch64 ID
+     * registers still exist and must have their correct values. So we
+     * avoid clearing them out so that we don't have QEMU and KVM with
+     * different ideas of the ID registers.
+     */
+    if (tcg_enabled() && !arm_feature(env, ARM_FEATURE_AARCH64)) {
+        arm_clear_aarch64_idregs(cpu);
+    }
+
 #ifdef CONFIG_USER_ONLY
     /*
      * User mode relies on IC IVAU instructions to catch modification of
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
      * Note that if you add an ID register to the ARMISARegisters struct
      * you need to also update the 32-bit and 64-bit versions of the
      * kvm_arm_get_host_cpu_features() function to correctly populate the
-     * field by reading the value from the KVM vCPU.
+     * field by reading the value from the KVM vCPU. If it is an AArch64
+     * ID register then you also must update arm_clear_aarch64_idregs().
      */
     struct ARMISARegisters {
         uint32_t mvfr0;
-- 
2.43.0

Allow the 'aarch64=off' property, which is currently KVM-only, to
be set for TCG CPUs also.

Note that we don't permit it on the qemu-aarch64 user-mode binary:
this makes no sense as that executable can only handle AArch64
syscalls (and it would also assert at startup since it doesn't
compile in the A32-specific GDB xml files like arm-neon.xml).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Clément Chigot <chigot@adacore.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260416165353.589569-3-peter.maydell@linaro.org
---
 docs/system/arm/cpu-features.rst | 10 +++++----
 target/arm/cpu-features.h        |  5 +++++
 target/arm/cpu.c                 | 36 ++++++++++++++++++++++++++++----
 tests/qtest/arm-cpu-features.c   |  8 ++-----
 4 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/cpu-features.rst
+++ b/docs/system/arm/cpu-features.rst
@@ -XXX,XX +XXX,XX @@ not implement ARMv8-A, will not have the ``aarch64`` CPU property.
 QEMU's support may be limited for some CPU features, only partially
 supporting the feature or only supporting the feature under certain
 configurations.  For example, the ``aarch64`` CPU feature, which, when
-disabled, enables the optional AArch32 CPU feature, is only supported
-when using the KVM accelerator and when running on a host CPU type that
-supports the feature.  While ``aarch64`` currently only works with KVM,
-it could work with TCG.  CPU features that are specific to KVM are
+disabled, enables the optional AArch32 CPU feature, can only be set to
+``off`` on the TCG and KVM accelerators, and it cannot be set to
+``off`` under KVM unless running on a host CPU type that supports
+running guests in AArch32.
+
+CPU features that are inherently specific to KVM are
 prefixed with "kvm-" and are described in "KVM VCPU Features".
 
 CPU Feature Probing
diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL2) >= 2;
 }
 
+static inline bool isar_feature_aa64_aa32_el3(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL3) >= 2;
+}
+
 static inline bool isar_feature_aa64_ras(const ARMISARegisters *id)
 {
     return FIELD_EX64_IDREG(id, ID_AA64PFR0, RAS) != 0;
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp)
      * uniform execution state like do_interrupt.
      */
     if (value == false) {
-        if (!kvm_enabled() || !kvm_arm_aarch32_supported()) {
-            error_setg(errp, "'aarch64' feature cannot be disabled "
-                             "unless KVM is enabled and 32-bit EL1 "
-                             "is supported");
+        if (kvm_enabled()) {
+            if (!kvm_arm_aarch32_supported()) {
+                error_setg(errp, "'aarch64' feature cannot be disabled for KVM "
+                           "because this host does not support 32-bit EL1");
+                return;
+            }
+        } else if (tcg_enabled()) {
+#ifdef CONFIG_USER_ONLY
+            error_setg(errp, "'aarch64' feature cannot be disabled for "
+                       "usermode emulator qemu-aarch64; use qemu-arm instead");
+            return;
+#else
+            bool aa32_at_highest_el;
+            if (arm_feature(&cpu->env, ARM_FEATURE_EL3)) {
+                aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el3, cpu);
+            } else if (arm_feature(&cpu->env, ARM_FEATURE_EL2)) {
+                aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el2, cpu);
+            } else {
+                aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el1, cpu);
+            }
+
+            if (!aa32_at_highest_el) {
+                error_setg(errp, "'aarch64' feature cannot be disabled for "
+                           "this TCG CPU because it does not support 32-bit "
+                           "execution at its highest implemented exception "
+                           "level");
+                return;
+            }
+#endif
+        } else {
+            error_setg(errp, "'aarch64' feature cannot be disabled for "
+                       "this accelerator");
             return;
         }
         unset_feature(&cpu->env, ARM_FEATURE_AARCH64);
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/arm-cpu-features.c
+++ b/tests/qtest/arm-cpu-features.c
@@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data)
         sve_tests_default(qts, "max");
         pauth_tests_default(qts, "max");
 
-        /* Test that features that depend on KVM generate errors without. */
-        assert_error(qts, "max",
-                     "'aarch64' feature cannot be disabled "
-                     "unless KVM is enabled and 32-bit EL1 "
-                     "is supported",
-                     "{ 'aarch64': false }");
+        /* TCG allows us to turn off AArch64 on the 'max' CPU type */
+        assert_set_feature(qts, "max", "aarch64", false);
     }
 
     qtest_quit(qts);
-- 
2.43.0

Add a basic test of the TCG 'aarch64=off' functionality; this is the
same as our existing arm/test_virt test, but it runs the AArch32
guest kernel on qemu-system-aarch64 with -cpu max,aarch64=off.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260416165353.589569-4-peter.maydell@linaro.org
---
 tests/functional/aarch64/meson.build          |  1 +
 .../aarch64/test_virt_aarch64_off.py          | 37 +++++++++++++++++++
 2 files changed, 38 insertions(+)
 create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py

diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/tests/functional/aarch64/meson.build
+++ b/tests/functional/aarch64/meson.build
@@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [
   'tcg_plugins',
   'tuxrun',
   'virt',
+  'virt_aarch64_off',
   'virt_gpu',
   'virt_vbsa',
   'xen',
diff --git a/tests/functional/aarch64/test_virt_aarch64_off.py b/tests/functional/aarch64/test_virt_aarch64_off.py
new file mode 100755
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/tests/functional/aarch64/test_virt_aarch64_off.py
@@ -XXX,XX +XXX,XX @@
+#!/usr/bin/env python3
+#
+# Functional test that boots an AArch32 Linux kernel and checks the console
+# on a TCG aarch64 CPU with aarch64=off. This is the same image etc
+# as we use in tests/functional/arm/test_virt.py.
+#
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+from qemu_test import LinuxKernelTest, Asset
+
+class ArmVirtMachine(LinuxKernelTest):
+
+    ASSET_KERNEL = Asset(
+        ('https://archives.fedoraproject.org/pub/archive/fedora/linux/'
+         'releases/29/Everything/armhfp/os/images/pxeboot/vmlinuz'),
+        '18dd5f1a9a28bd539f9d047f7c0677211bae528e8712b40ca5a229a4ad8e2591')
+
+    def test_arm_virt(self):
+        self.set_machine('virt')
+        # KVM aarch64=off requires a host CPU that supports it, so
+        # restrict the test to TCG only
+        self.require_accelerator('tcg')
+        self.vm.add_args('-cpu', 'max,aarch64=off')
+
+        kernel_path = self.ASSET_KERNEL.fetch()
+
+        self.vm.set_console()
+        kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
+                               'console=ttyAMA0')
+        self.vm.add_args('-kernel', kernel_path,
+                         '-append', kernel_command_line)
+        self.vm.launch()
+        console_pattern = 'Kernel command line: %s' % kernel_command_line
+        self.wait_for_console_pattern(console_pattern)
+
+if __name__ == '__main__':
+    LinuxKernelTest.main()
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

We introduce a datatype for a tolerance with respect to a given
cpreg migration issue. The tolerance applies to a given cpreg kvm index,
and can be of different types:
a) mismatch in cpreg indexes
- ToleranceNotOnBothEnds (cpreg index is allowed to be only present
  on one end)
- ToleranceOnlySrcTestValue (cpreg index is allowed to be only
  present in source if its value @mask field matches @value)
b) mismatch in cpreg values
- ToleranceDiffInMask (value differences are allowed only within a mask)
- ToleranceFieldLT (incoming field value must be less than a given value)
- ToleranceFieldGT (incoming field value must be greater than a given value)

A QLIST of such tolerances can be populated using a new helper:
arm_register_cpreg_mig_tolerance() and arm_cpu_match_cpreg_mig_tolerance()
allows to check whether a tolerance exists for a given kvm index and its
criterion is matched.

callers for those helpers will be introduced in subsequent patches.

Only registration of migration tolerances related to cpreg index
mismatch is currently allowed.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20260420140552.104369-2-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.c       | 82 ++++++++++++++++++++++++++++++++++++++++++
 target/arm/cpu.h       |  1 +
 target/arm/internals.h | 54 ++++++++++++++++++++++++++++
 3 files changed, 137 insertions(+)

diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -XXX,XX +XXX,XX @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook,
     QLIST_INSERT_HEAD(&cpu->el_change_hooks, entry, node);
 }
 
+static ARMCPRegMigTolerance *find_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx)
+{
+    ARMCPRegMigTolerance *t;
+    QLIST_FOREACH(t, &cpu->cpreg_mig_tolerances, node) {
+        if (t->kvmidx == kvmidx)  {
+            return t;
+        }
+    }
+    return NULL;
+}
+
+void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                      uint64_t mask, uint64_t value,
+                                      ARMCPRegMigToleranceType type)
+{
+    ARMCPRegMigTolerance *entry;
+
+    /* make sure the kvmidx has not tolerance already registered */
+    assert(!find_mig_tolerance(cpu, kvmidx));
+
+    assert(type == ToleranceNotOnBothEnds ||
+           type == ToleranceOnlySrcTestValue);
+
+    entry = g_new0(ARMCPRegMigTolerance, 1);
+
+    entry->kvmidx = kvmidx;
+    entry->mask = mask;
+    entry->value = value;
+    entry->type = type;
+
+    QLIST_INSERT_HEAD(&cpu->cpreg_mig_tolerances, entry, node);
+}
+
+bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                       uint64_t vmstate_value, uint64_t local_value,
+                                       ARMCPRegMigToleranceType type)
+{
+    ARMCPRegMigTolerance *t = find_mig_tolerance(cpu, kvmidx);
+    uint64_t diff, diff_outside_mask, field;
+
+    if (!t || t->type != type) {
+        return false;
+    }
+
+    if (type == ToleranceNotOnBothEnds) {
+        return true;
+    }
+
+    if (type == ToleranceOnlySrcTestValue &&
+        ((vmstate_value & t->mask) == t->value)) {
+        return true;
+    }
+
+    /* Need to check the mask */
+    diff = vmstate_value ^ local_value;
+    diff_outside_mask = diff & ~t->mask;
+
+    if (diff_outside_mask) {
+        /* there are differences outside of the mask */
+        return false;
+    }
+    if (type == ToleranceDiffInMask) {
+        /* differences only in the field, tolerance matched */
+        return true;
+    }
+    /* need to compare field value against authorized ones */
+    field = vmstate_value & t->mask;
+    if (type == ToleranceFieldLT && (field < t->value)) {
+        return true;
+    }
+    if (type == ToleranceFieldGT && (field > t->value)) {
+        return true;
+    }
+    return false;
+}
+
 static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque)
 {
     /* Reset a single ARMCPRegInfo register */
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj)
 
     QLIST_INIT(&cpu->pre_el_change_hooks);
     QLIST_INIT(&cpu->el_change_hooks);
+    QLIST_INIT(&cpu->cpreg_mig_tolerances);
 
 #ifdef CONFIG_USER_ONLY
 # ifdef TARGET_AARCH64
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
     ARMELChangeHook *hook, *next;
+    ARMCPRegMigTolerance *t, *n;
 
     g_hash_table_destroy(cpu->cp_regs);
 
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj)
         QLIST_REMOVE(hook, node);
         g_free(hook);
     }
+    QLIST_FOREACH_SAFE(t, &cpu->cpreg_mig_tolerances, node, n) {
+        QLIST_REMOVE(t, node);
+        g_free(t);
+    }
 #ifndef CONFIG_USER_ONLY
     if (cpu->pmu_timer) {
         timer_free(cpu->pmu_timer);
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -XXX,XX +XXX,XX @@ struct ArchCPU {
 
     QLIST_HEAD(, ARMELChangeHook) pre_el_change_hooks;
     QLIST_HEAD(, ARMELChangeHook) el_change_hooks;
+    QLIST_HEAD(, ARMCPRegMigTolerance) cpreg_mig_tolerances;
 
     int32_t node_id; /* NUMA node this CPU belongs to */
 
diff --git a/target/arm/internals.h b/target/arm/internals.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -XXX,XX +XXX,XX @@ int compare_u64(const void *a, const void *b);
 /* Used in FEAT_MEC to set the MECIDWidthm1 field in the MECIDR_EL2 register. */
 #define MECID_WIDTH 16
 
+typedef enum {
+    ToleranceNotOnBothEnds,
+    ToleranceOnlySrcTestValue,
+    ToleranceDiffInMask,
+    ToleranceFieldLT,
+    ToleranceFieldGT,
+} ARMCPRegMigToleranceType;
+
+typedef struct ARMCPRegMigTolerance {
+    uint64_t kvmidx;
+    uint64_t mask;
+    uint64_t value;
+    ARMCPRegMigToleranceType type;
+    QLIST_ENTRY(ARMCPRegMigTolerance) node;
+} ARMCPRegMigTolerance;
+
+/**
+ * arm_register_cpreg_mig_tolerance:
+ * Register a migration tolerance wrt one given cpreg identified by its
+ * @kvmidx. Calling this function twice for the same @kvmidx is a
+ * programming error and will cause an assertion failure.
+ *
+ * @cpu: vcpu to apply the migration tolerance on
+ * @kvmidx: kvm index of the cpreg the tolerance applies to
+ * @mask: bitmask where a difference is tolerated
+ *        (relevant with ToleranceDiffInMask)
+ * @value: value the bitmask field is compared with
+ *        (relevant with ToleranceFieldLT and ToleranceFieldGT)
+ * @type: type of the migration tolerance:
+ * - ToleranceNotOnBothEnds (cpreg index is allowed to be only present
+ *   on one end)
+ * - ToleranceOnlySrcTestValue (cpreg index is allowed to be only
+ *   present in source if its value @mask field matches @value)
+ * - ToleranceDiffInMask (mismatch in cpreg values are only tolerated
+ *   if differences are within @mask)
+ * - ToleranceFieldLT (mismatch in cpreg values are only tolerated
+ *   if incoming @bitmask field value is less than @value)
+ * - ToleranceFieldGT (mismatch in cpreg values are only tolerated
+ *   if incoming @bitmask field value is greater than @value)
+ */
+void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                      uint64_t mask, uint64_t value,
+                                      ARMCPRegMigToleranceType type);
+
+/**
+ * arm_cpu_match_cpreg_mig_tolerance:
+ * Check whether a tolerance of type @type exists for a given @kvmidx
+ * and the tolerance criterion is satisfied
+ */
+bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx,
+                                       uint64_t vmstate_value, uint64_t local_value,
+                                       ARMCPRegMigToleranceType type);
+
+
 #endif
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

If there is a mismatch between the cpreg indexes found on both ends,
check whether a tolerance was registered for the given kvmidx. If any,
silence warning/errors.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-3-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/machine.c    | 21 +++++++++++++++------
 target/arm/trace-events |  2 ++
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/target/arm/machine.c b/target/arm/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx
 {
     g_autofree gchar *name = print_register_name(kvmidx);
 
+    if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
+                                          0, 0, ToleranceNotOnBothEnds)) {
+        trace_tolerate_cpreg_missing_in_incoming_stream(name);
+        return;
+    }
     warn_report("%s: %s "
                 "expected by the destination but not in the incoming stream: "
                  "skip it", __func__, name);
 }
 
 /*
- * Handle the situation where @kvmidx is in the incoming stream
- * but not on destination. This currently fails the migration but
- * we plan to accomodate some exceptions, hence the boolean returned value.
+ * Handle the situation where @kvmidx is in the incoming
+ * stream but not on destination. This fails the migration if
+ * no cpreg mig tolerance is matched for this @kvmidx
+ * Return true if the migration should eventually fail
  */
 static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx)
 {
     g_autofree gchar *name = print_register_name(kvmidx);
-    bool fail = true;
 
+    if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
+                                          0, 0, ToleranceNotOnBothEnds)) {
+        trace_tolerate_cpreg_only_in_incoming_stream(name);
+        return false;
+    }
     error_report("%s: %s in the incoming stream but unknown on the "
                  "destination: fail migration", __func__, name);
-
-    return fail;
+    return true;
 }
 
 static int cpu_post_load(void *opaque, int version_id)
diff --git a/target/arm/trace-events b/target/arm/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/trace-events
+++ b/target/arm/trace-events
@@ -XXX,XX +XXX,XX @@ arm_psci_call(uint64_t x0, uint64_t x1, uint64_t x2, uint64_t x3, uint32_t cpuid
 
 # machine.c
 cpu_post_load(uint32_t cpreg_vmstate_array_len, uint32_t cpreg_array_len) "cpreg_vmstate_array_len=%d cpreg_array_len=%d"
+tolerate_cpreg_missing_in_incoming_stream(char *name) "%s is missing in incoming stream but this is explicitly tolerated"
+tolerate_cpreg_only_in_incoming_stream(char *name) "%s is in incoming stream but not on destination but this is explicitly tolerated"
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

Pass the value of the incoming register to
handle_cpreg_only_in_incoming_stream and check whether there is
a matching ToleranceOnlySrcTestValue tolerance.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20260420140552.104369-4-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/machine.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/target/arm/machine.c b/target/arm/machine.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx
  * no cpreg mig tolerance is matched for this @kvmidx
  * Return true if the migration should eventually fail
  */
-static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx)
+static bool
+handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx, uint64_t value)
 {
     g_autofree gchar *name = print_register_name(kvmidx);
 
     if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
-                                          0, 0, ToleranceNotOnBothEnds)) {
+                                          0, 0, ToleranceNotOnBothEnds) ||
+        arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx,
+                                          value, 0, ToleranceOnlySrcTestValue)) {
         trace_tolerate_cpreg_only_in_incoming_stream(name);
         return false;
     }
@@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id)
         }
         if (cpu->cpreg_vmstate_indexes[v] < cpu->cpreg_indexes[i]) {
             fail = handle_cpreg_only_in_incoming_stream(cpu,
-                                                        cpu->cpreg_vmstate_indexes[v++]);
+                                                        cpu->cpreg_vmstate_indexes[v],
+                                                        cpu->cpreg_vmstate_values[v]);
+            v++;
             continue;
         }
         /* matching register, copy the value over */
@@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id)
      */
     for ( ; v < cpu->cpreg_vmstate_array_len; v++) {
         fail = handle_cpreg_only_in_incoming_stream(cpu,
-                                                    cpu->cpreg_vmstate_indexes[v]);
+                                                    cpu->cpreg_vmstate_indexes[v],
+                                                    cpu->cpreg_vmstate_values[v]);
     }
     if (fail) {
         return -1;
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

Before linux v6.13 those registers were erroneously unconditionally
exposed and this was fixed by commits:
- 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace when
                 disabled for guests")
- a68cddbe47ef ("KVM: arm64: Hide S1PIE registers from userspace
                 when disabled for guests")
in v6.13.

This means if we migrate from an old kernel host to a >= 6.13 kernel
host, migration currently fails.

Declare cpreg migration tolerance for those registers.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-5-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu64.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj)
     define_cortex_a72_a57_a53_cp_reginfo(cpu);
 }
 
+#if defined(CONFIG_KVM)
+static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu)
+{
+    /*
+     * Registers that may be in the incoming stream and not exposed
+     * on the destination
+     */
+
+    /*
+     * TCR_EL1 was erroneously unconditionnally exposed before linux v6.13.
+     * See commit 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace
+     * when disabled for guests")
+     */
+    arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 2, 0, 3),
+                                     0, 0, ToleranceNotOnBothEnds);
+    /*
+     * PIRE0_EL1 and PIR_EL1 were erroneously unconditionnally exposed
+     * before linux v6.13. See commit a68cddbe47ef ("KVM: arm64: Hide
+     * S1PIE registers from userspace when disabled for guests")
+     */
+    arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 2),
+                                     0, 0, ToleranceNotOnBothEnds);
+    arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3),
+                                     0, 0, ToleranceNotOnBothEnds);
+}
+#endif
+
 static void aarch64_host_initfn(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
@@ -XXX,XX +XXX,XX @@ static void aarch64_host_initfn(Object *obj)
 #endif
 
 #if defined(CONFIG_KVM)
+    kvm_arm_set_cpreg_mig_tolerances(cpu);
     kvm_arm_set_cpu_features_from_host(cpu);
     aarch64_add_sve_properties(obj);
 #elif defined(CONFIG_HVF)
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed
from v6.15 onwards. Backward migration from a >= v6.15 to an older
kernel would fail without cpreg migration tolerance definition
for this register. If the register is present on source but not
on destination, its value must be checked to make sure it matches
the reset value, ie. 0, meaning no service is exposed to the guest,
hence the choice of a ToleranceOnlySrcTestValue migration
tolerance.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-6-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu64.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -XXX,XX +XXX,XX @@ static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu)
                                      0, 0, ToleranceNotOnBothEnds);
     arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3),
                                      0, 0, ToleranceNotOnBothEnds);
+
+    /*
+     * KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed
+     * from v6.15 onwards. Backward migration from a >= v6.15 to an older
+     * kernel would fail without cpreg migration tolerance definition.
+     * If the register is present on source but not on destination, make
+     * sure it has its reset value, ie. 0, meaning no service is exposed
+     * to the guest.
+     */
+    arm_register_cpreg_mig_tolerance(cpu, KVM_REG_ARM_FW_FEAT_BMAP_REG(3),
+                                     UINT64_MAX, 0, ToleranceOnlySrcTestValue);
 }
 #endif
 
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

We want to remove AArch32 DBGDTRTX which was erroneously exposed.
This was attempted by 655659a74a36b ("target/arm: Correct encoding
of Debug Communications Channel registers") but it was discovered
that the removal of this debug register broke forward migration on
TCG. Now we have the cpreg migration tolerance infrastructure, we
can declare one for the DBGDTRTX. This allow to revert the reinstate
patch.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-7-eric.auger@redhat.com
[PMM: revised comment, included note about when we can drop
 the workaround]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu)
             .fgt = FGT_CLIDR_EL1,
             .resetvalue = GET_IDREG(isar, CLIDR)
         };
+        uint64_t dbgtr_el0_kvmidx =
+            cpreg_to_kvm_id(ENCODE_CP_REG(14, 0, 1, 0, 5, 3, 0));
+
         define_one_arm_cp_reg(cpu, &clidr);
         define_arm_cp_regs(cpu, v7_cp_reginfo);
         define_debug_regs(cpu);
+        /*
+         * We used to incorrectly expose a non-existent AArch32 "DBGDTRTX"
+         * register with this encoding. This has been fixed by commit
+         * 655659a74a36 ("target/arm: Correct encoding of Debug
+         * Communications Channel registers") by the introduction of correct
+         * separate cpreg definitions for AA64 and AA32 versions. However,
+         * the old cpreg definition couldn't be removed without breaking
+         * migration, so commit 4f2b82f604 reinstated the bogus encoding
+         * for migration data only.
+         *
+         * Now that we have migration tolerance infrastructure, we can use
+         * this to allow forward migration from the buggy QEMU versions,
+         * accepting and ignoring the bogus register if it is in the
+         * source data. QEMU 11.0 was the last version that sent the
+         * bogus encoding, so this workaround can be removed at the point
+         * where we no longer care about migration from that version
+         * (i.e. when we remove the "virt-11.0" machine type).
+         */
+        arm_register_cpreg_mig_tolerance(cpu, dbgtr_el0_kvmidx,
+                                         0, 0, ToleranceNotOnBothEnds);
     } else {
         define_arm_cp_regs(cpu, not_v7_cp_reginfo);
     }
-- 
2.43.0

From: Eric Auger <eric.auger@redhat.com>

This reverts commit 4f2b82f60431 ("target/arm: Reinstate bogus AArch32
DBGDTRTX register for migration compat). We don't need that commit
anymore as the AArch32 DBGDTRTX register is declared to
be safe to ignore in the incoming migration stream.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20260420140552.104369-8-eric.auger@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/debug_helper.c | 29 -----------------------------
 1 file changed, 29 deletions(-)

diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/debug_helper.c
+++ b/target/arm/debug_helper.c
@@ -XXX,XX +XXX,XX @@ static void dbgclaimclr_write(CPUARMState *env, const ARMCPRegInfo *ri,
     env->cp15.dbgclaim &= ~(value & 0xFF);
 }
 
-static CPAccessResult access_bogus(CPUARMState *env, const ARMCPRegInfo *ri,
-                                   bool isread)
-{
-    /* Always UNDEF, as if this cpreg didn't exist */
-    return CP_ACCESS_UNDEFINED;
-}
-
 static const ARMCPRegInfo debug_cp_reginfo[] = {
     /*
      * DBGDRAR, DBGDSAR: always RAZ since we don't implement memory mapped
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_cp_reginfo[] = {
       .opc0 = 2, .opc1 = 3, .crn = 0, .crm = 4, .opc2 = 0,
       .access = PL0_RW, .accessfn = access_tdcc,
       .type = ARM_CP_CONST, .resetvalue = 0 },
-    /*
-     * This is not a real AArch32 register. We used to incorrectly expose
-     * this due to a QEMU bug; to avoid breaking migration compatibility we
-     * need to continue to provide it so that we don't fail the inbound
-     * migration when it tells us about a sysreg that we don't have.
-     * We set an always-fails .accessfn, which means that the guest doesn't
-     * actually see this register (it will always UNDEF, identically to if
-     * there were no cpreg definition for it other than that we won't print
-     * a LOG_UNIMP message about it), and we set the ARM_CP_NO_GDB flag so the
-     * gdbstub won't see it either.
-     * (We can't just set .access = 0, because add_cpreg_to_hashtable()
-     * helpfully ignores cpregs which aren't accessible to the highest
-     * implemented EL.)
-     *
-     * TODO: implement a system for being able to describe "this register
-     * can be ignored if it appears in the inbound stream"; then we can
-     * remove this temporary hack.
-     */
-    { .name = "BOGUS_DBGDTR_EL0", .state = ARM_CP_STATE_AA32,
-      .cp = 14, .opc1 = 3, .crn = 0, .crm = 5, .opc2 = 0,
-      .access = PL0_RW, .accessfn = access_bogus,
-      .type = ARM_CP_CONST | ARM_CP_NO_GDB, .resetvalue = 0 },
     /*
      * OSECCR_EL1 provides a mechanism for an operating system
      * to access the contents of EDECCR. EDECCR is not implemented though,
-- 
2.43.0

From: Osama Abdelkader <osama.abdelkader@gmail.com>

fdt_node_offset_by_compatible(fdt, -1, compat) only finds the first match.
If the blob has more than one node with the same compatible string, extra
nodes will remain active. Remove all the matching nodes, using the same
loop as imx8mp-evk.c does for this purpose.

Signed-off-by: Osama Abdelkader <osama.abdelkader@gmail.com>
Message-id: 20260420162114.308519-1-osama.abdelkader@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/raspi4b.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/hw/arm/raspi4b.c b/hw/arm/raspi4b.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/raspi4b.c
+++ b/hw/arm/raspi4b.c
@@ -XXX,XX +XXX,XX @@ static void raspi4_modify_dtb(const struct arm_boot_info *info, void *fdt)
 
     for (int i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) {
         const char *dev_str = nodes_to_remove[i];
+        int offset;
 
-        int offset = fdt_node_offset_by_compatible(fdt, -1, dev_str);
-        if (offset >= 0) {
-            if (!fdt_nop_node(fdt, offset)) {
-                warn_report("bcm2711 dtc: %s has been disabled!", dev_str);
+        offset = fdt_node_offset_by_compatible(fdt, -1, dev_str);
+        while (offset >= 0) {
+            if (fdt_nop_node(fdt, offset) == 0) {
+                warn_report("bcm2711 dtb: %s has been disabled!", dev_str);
             }
+            offset = fdt_node_offset_by_compatible(fdt, offset, dev_str);
         }
     }
 
-- 
2.43.0

From: Yucai Liu <1486344514@qq.com>

Implement a basic i.MX6UL LCDIF controller model with MMIO registers,
frame-done interrupt behavior, and framebuffer-backed display updates
for RGB565 and XRGB8888 input formats.

Place the LCDIF device under hw/display and build it via a dedicated
CONFIG_IMX6UL_LCDIF symbol. Model register fields with
registerfields.h helpers and provide migration support via vmstate.

Signed-off-by: Yucai Liu <1486344514@qq.com>
Message-id: 20260412110240.93116-2-yangyanglan718@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 MAINTAINERS                       |   2 +
 hw/display/Kconfig                |   4 +
 hw/display/imx6ul_lcdif.c         | 453 ++++++++++++++++++++++++++++++
 hw/display/meson.build            |   1 +
 include/hw/display/imx6ul_lcdif.h |  37 +++
 5 files changed, 497 insertions(+)
 create mode 100644 hw/display/imx6ul_lcdif.c
 create mode 100644 include/hw/display/imx6ul_lcdif.h

diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org
 S: Odd Fixes
 F: hw/arm/mcimx6ul-evk.c
 F: hw/arm/fsl-imx6ul.c
+F: hw/display/imx6ul_lcdif.c
 F: hw/misc/imx6ul_ccm.c
 F: include/hw/arm/fsl-imx6ul.h
+F: include/hw/display/imx6ul_lcdif.h
 F: include/hw/misc/imx6ul_ccm.h
 F: docs/system/arm/mcimx6ul-evk.rst
 
diff --git a/hw/display/Kconfig b/hw/display/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/Kconfig
+++ b/hw/display/Kconfig
@@ -XXX,XX +XXX,XX @@ config PL110
     bool
     select FRAMEBUFFER
 
+config IMX6UL_LCDIF
+    bool
+    select FRAMEBUFFER
+
 config SII9022
     bool
     depends on I2C
diff --git a/hw/display/imx6ul_lcdif.c b/hw/display/imx6ul_lcdif.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/hw/display/imx6ul_lcdif.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * i.MX6UL LCDIF controller
+ *
+ * Copyright (c) 2026 Yucai Liu <1486344514@qq.com>
+ */
+
+#include "qemu/osdep.h"
+#include "hw/display/imx6ul_lcdif.h"
+#include "hw/core/irq.h"
+#include "hw/core/registerfields.h"
+#include "hw/display/framebuffer.h"
+#include "migration/vmstate.h"
+#include "system/address-spaces.h"
+#include "qemu/module.h"
+#include "qemu/units.h"
+#include "ui/pixel_ops.h"
+
+#define LCDIF_MMIO_SIZE             (16 * KiB)
+#define LCDIF_RESET_CTRL1           0x000f0000
+
+REG32(CTRL, 0x00)
+    FIELD(CTRL, RUN, 0, 1)
+    FIELD(CTRL, WORD_LENGTH, 8, 2)
+REG32(CTRL1, 0x10)
+    FIELD(CTRL1, CUR_FRAME_DONE_IRQ, 9, 1)
+    FIELD(CTRL1, CUR_FRAME_DONE_IRQ_EN, 13, 1)
+    FIELD(CTRL1, BYTE_PACKING_FORMAT, 16, 4)
+REG32(V4_TRANSFER_COUNT, 0x30)
+    FIELD(V4_TRANSFER_COUNT, H_COUNT, 0, 16)
+    FIELD(V4_TRANSFER_COUNT, V_COUNT, 16, 16)
+REG32(V4_CUR_BUF, 0x40)
+REG32(V4_NEXT_BUF, 0x50)
+REG32(AS_NEXT_BUF, 0x230)
+
+#define REG_SET                     0x4
+#define REG_CLR                     0x8
+#define REG_TOG                     0xc
+
+#define CTRL_WORD_LENGTH_16         0
+#define CTRL_WORD_LENGTH_24         3
+
+#define FRAME_PERIOD_NS             (16 * 1000 * 1000ULL)
+
+enum IMX6ULLCDIFReg {
+    IMX6UL_LCDIF_REG_CTRL = A_CTRL >> 4,
+    IMX6UL_LCDIF_REG_CTRL1 = A_CTRL1 >> 4,
+    IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT = A_V4_TRANSFER_COUNT >> 4,
+    IMX6UL_LCDIF_REG_V4_CUR_BUF = A_V4_CUR_BUF >> 4,
+    IMX6UL_LCDIF_REG_V4_NEXT_BUF = A_V4_NEXT_BUF >> 4,
+    IMX6UL_LCDIF_REG_AS_NEXT_BUF = A_AS_NEXT_BUF >> 4,
+};
+
+static inline bool imx6ul_lcdif_reg_exists(hwaddr reg)
+{
+    return (reg >> 4) < IMX6UL_LCDIF_REGS_NUM;
+}
+
+static inline bool imx6ul_lcdif_reg_has_setclr(hwaddr reg)
+{
+    switch (reg) {
+    case A_CTRL:
+    case A_CTRL1:
+        return true;
+    default:
+        return false;
+    }
+}
+
+static inline bool imx6ul_lcdif_is_running(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL];
+
+    return FIELD_EX32(ctrl, CTRL, RUN);
+}
+
+static inline bool imx6ul_lcdif_frame_done_pending(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1];
+
+    return FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ);
+}
+
+static void imx6ul_lcdif_schedule_frame(IMX6ULLCDIFState *s)
+{
+    int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+
+    timer_mod(s->frame_timer, now + FRAME_PERIOD_NS);
+}
+
+static void imx6ul_lcdif_maybe_schedule_frame(IMX6ULLCDIFState *s)
+{
+    if (imx6ul_lcdif_is_running(s) && !imx6ul_lcdif_frame_done_pending(s)) {
+        imx6ul_lcdif_schedule_frame(s);
+    } else {
+        timer_del(s->frame_timer);
+    }
+}
+
+static void imx6ul_lcdif_update_irq(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1];
+    bool level = FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ_EN) &&
+                 FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ);
+
+    qemu_set_irq(s->irq, level);
+}
+
+static void imx6ul_lcdif_frame_done(IMX6ULLCDIFState *s)
+{
+    uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1];
+
+    ctrl1 = FIELD_DP32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ, 1);
+    s->regs[IMX6UL_LCDIF_REG_CTRL1] = ctrl1;
+    imx6ul_lcdif_update_irq(s);
+}
+
+static void imx6ul_lcdif_draw_line_rgb565(void *opaque, uint8_t *dst,
+                                          const uint8_t *src, int width,
+                                          int dststep)
+{
+    uint32_t *dst32 = (uint32_t *)dst;
+    int i;
+
+    for (i = 0; i < width; i++) {
+        uint16_t pixel = lduw_le_p(src);
+        uint8_t r = ((pixel >> 11) & 0x1f) << 3;
+        uint8_t g = ((pixel >> 5) & 0x3f) << 2;
+        uint8_t b = (pixel & 0x1f) << 3;
+
+        *dst32++ = rgb_to_pixel32(r, g, b);
+        src += 2;
+    }
+}
+
+static void imx6ul_lcdif_draw_line_xrgb8888(void *opaque, uint8_t *dst,
+                                            const uint8_t *src, int width,
+                                            int dststep)
+{
+    uint32_t *dst32 = (uint32_t *)dst;
+    int i;
+
+    for (i = 0; i < width; i++) {
+        uint32_t pixel = ldl_le_p(src);
+        uint8_t r = (pixel >> 16) & 0xff;
+        uint8_t g = (pixel >> 8) & 0xff;
+        uint8_t b = pixel & 0xff;
+
+        *dst32++ = rgb_to_pixel32(r, g, b);
+        src += 4;
+    }
+}
+
+static void imx6ul_lcdif_update_display(void *opaque)
+{
+    IMX6ULLCDIFState *s = opaque;
+    DisplaySurface *surface = qemu_console_surface(s->con);
+    uint32_t transfer_count = s->regs[IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT];
+    uint32_t width = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, H_COUNT);
+    uint32_t height = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, V_COUNT);
+    uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL];
+    uint32_t frame_base = s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF];
+    drawfn fn;
+    int first = 0;
+    int last = 0;
+    int src_width;
+
+    if (!imx6ul_lcdif_is_running(s) || width == 0 || height == 0) {
+        return;
+    }
+
+    switch (FIELD_EX32(ctrl, CTRL, WORD_LENGTH)) {
+    case CTRL_WORD_LENGTH_16:
+        s->src_bpp = 2;
+        fn = imx6ul_lcdif_draw_line_rgb565;
+        break;
+    case CTRL_WORD_LENGTH_24:
+        s->src_bpp = 4;
+        fn = imx6ul_lcdif_draw_line_xrgb8888;
+        break;
+    default:
+        return;
+    }
+
+    if (surface_width(surface) != width || surface_height(surface) != height) {
+        qemu_console_resize(s->con, width, height);
+        surface = qemu_console_surface(s->con);
+        s->invalidate = true;
+    }
+
+    src_width = width * s->src_bpp;
+    if (s->invalidate || s->fb_base != frame_base ||
+        s->src_width != src_width || s->rows != height) {
+        framebuffer_update_memory_section(&s->fbsection, get_system_memory(),
+                                          frame_base, height, src_width);
+        s->fb_base = frame_base;
+        s->src_width = src_width;
+        s->rows = height;
+    }
+
+    framebuffer_update_display(surface, &s->fbsection, width, height,
+                               src_width, surface_stride(surface), 0,
+                               s->invalidate, fn, s, &first, &last);
+    if (first >= 0) {
+        dpy_gfx_update(s->con, 0, first, width, last - first + 1);
+    }
+
+    s->invalidate = false;
+}
+
+static void imx6ul_lcdif_invalidate_display(void *opaque)
+{
+    IMX6ULLCDIFState *s = opaque;
+
+    s->invalidate = true;
+}
+
+static const GraphicHwOps imx6ul_lcdif_graphic_ops = {
+    .invalidate = imx6ul_lcdif_invalidate_display,
+    .gfx_update = imx6ul_lcdif_update_display,
+};
+
+static void imx6ul_lcdif_frame_timer_cb(void *opaque)
+{
+    IMX6ULLCDIFState *s = opaque;
+
+    if (!imx6ul_lcdif_is_running(s) || imx6ul_lcdif_frame_done_pending(s)) {
+        return;
+    }
+
+    imx6ul_lcdif_frame_done(s);
+}
+
+static uint64_t imx6ul_lcdif_read(void *opaque, hwaddr offset, unsigned size)
+{
+    IMX6ULLCDIFState *s = opaque;
+    hwaddr reg = offset & ~0xf;
+    uint32_t idx;
+
+    assert(size == 4);
+    assert(!(offset & 0x3));
+    assert(offset < LCDIF_MMIO_SIZE);
+
+    idx = reg >> 4;
+    if (idx >= ARRAY_SIZE(s->regs)) {
+        return 0;
+    }
+
+    return s->regs[idx];
+}
+
+static void imx6ul_lcdif_write(void *opaque, hwaddr offset,
+                               uint64_t value, unsigned size)
+{
+    IMX6ULLCDIFState *s = opaque;
+    hwaddr reg = offset & ~0xf;
+    uint32_t idx;
+    uint32_t oldv;
+
+    assert(size == 4);
+    assert(!(offset & 0x3));
+    assert(offset < LCDIF_MMIO_SIZE);
+
+    if (!imx6ul_lcdif_reg_exists(reg)) {
+        return;
+    }
+
+    idx = reg >> 4;
+    oldv = s->regs[idx];
+
+    switch (offset & 0xf) {
+    case 0:
+        s->regs[idx] = (uint32_t)value;
+        break;
+    case REG_SET:
+        if (!imx6ul_lcdif_reg_has_setclr(reg)) {
+            return;
+        }
+        s->regs[idx] = oldv | (uint32_t)value;
+        break;
+    case REG_CLR:
+        if (!imx6ul_lcdif_reg_has_setclr(reg)) {
+            return;
+        }
+        s->regs[idx] = oldv & ~(uint32_t)value;
+        break;
+    case REG_TOG:
+        if (!imx6ul_lcdif_reg_has_setclr(reg)) {
+            return;
+        }
+        s->regs[idx] = oldv ^ (uint32_t)value;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    switch (reg) {
+    case A_CTRL:
+        if (!FIELD_EX32(oldv, CTRL, RUN) &&
+            FIELD_EX32(s->regs[idx], CTRL, RUN)) {
+            s->invalidate = true;
+            graphic_hw_invalidate(s->con);
+            imx6ul_lcdif_maybe_schedule_frame(s);
+            break;
+        }
+        if (FIELD_EX32(oldv, CTRL, RUN) &&
+            !FIELD_EX32(s->regs[idx], CTRL, RUN)) {
+            timer_del(s->frame_timer);
+        }
+        break;
+    case A_CTRL1:
+        if (FIELD_EX32(oldv, CTRL1, CUR_FRAME_DONE_IRQ) &&
+            !FIELD_EX32(s->regs[idx], CTRL1, CUR_FRAME_DONE_IRQ)) {
+            imx6ul_lcdif_maybe_schedule_frame(s);
+        }
+        break;
+    case A_V4_TRANSFER_COUNT:
+        s->invalidate = true;
+        graphic_hw_invalidate(s->con);
+        break;
+    case A_V4_CUR_BUF:
+        s->invalidate = true;
+        graphic_hw_invalidate(s->con);
+        break;
+    case A_V4_NEXT_BUF:
+        s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF] = s->regs[idx];
+        imx6ul_lcdif_frame_done(s);
+        s->invalidate = true;
+        graphic_hw_invalidate(s->con);
+        imx6ul_lcdif_maybe_schedule_frame(s);
+        return;
+    case A_AS_NEXT_BUF:
+        imx6ul_lcdif_frame_done(s);
+        imx6ul_lcdif_maybe_schedule_frame(s);
+        return;
+    default:
+        break;
+    }
+
+    imx6ul_lcdif_update_irq(s);
+}
+
+static const MemoryRegionOps imx6ul_lcdif_ops = {
+    .read = imx6ul_lcdif_read,
+    .write = imx6ul_lcdif_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+        .unaligned = false,
+    },
+};
+
+static void imx6ul_lcdif_reset(DeviceState *dev)
+{
+    IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev);
+
+    memset(s->regs, 0, sizeof(s->regs));
+    s->regs[IMX6UL_LCDIF_REG_CTRL1] = LCDIF_RESET_CTRL1;
+    s->fb_base = 0;
+    s->src_width = 0;
+    s->rows = 0;
+    s->src_bpp = 0;
+    s->invalidate = true;
+    timer_del(s->frame_timer);
+    imx6ul_lcdif_update_irq(s);
+}
+
+static int imx6ul_lcdif_post_load(void *opaque, int version_id)
+{
+    IMX6ULLCDIFState *s = opaque;
+
+    s->fb_base = 0;
+    s->src_width = 0;
+    s->rows = 0;
+    s->src_bpp = 0;
+    s->invalidate = true;
+
+    imx6ul_lcdif_update_irq(s);
+    if (imx6ul_lcdif_is_running(s) &&
+        !imx6ul_lcdif_frame_done_pending(s) &&
+        !timer_pending(s->frame_timer)) {
+        imx6ul_lcdif_schedule_frame(s);
+    }
+
+    return 0;
+}
+
+static const VMStateDescription vmstate_imx6ul_lcdif = {
+    .name = TYPE_IMX6UL_LCDIF,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .post_load = imx6ul_lcdif_post_load,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT32_ARRAY(regs, IMX6ULLCDIFState, IMX6UL_LCDIF_REGS_NUM),
+        VMSTATE_TIMER_PTR(frame_timer, IMX6ULLCDIFState),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static void imx6ul_lcdif_realize(DeviceState *dev, Error **errp)
+{
+    IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev);
+
+    s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                  imx6ul_lcdif_frame_timer_cb, s);
+    s->invalidate = true;
+    memory_region_init_io(&s->iomem, OBJECT(dev), &imx6ul_lcdif_ops, s,
+                          TYPE_IMX6UL_LCDIF, LCDIF_MMIO_SIZE);
+    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem);
+    sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq);
+    s->con = graphic_console_init(dev, 0, &imx6ul_lcdif_graphic_ops, s);
+}
+
+static void imx6ul_lcdif_unrealize(DeviceState *dev)
+{
+    IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev);
+
+    timer_del(s->frame_timer);
+    timer_free(s->frame_timer);
+    s->frame_timer = NULL;
+
+    if (s->con) {
+        graphic_console_close(s->con);
+        s->con = NULL;
+    }
+}
+
+static void imx6ul_lcdif_class_init(ObjectClass *klass, const void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->realize = imx6ul_lcdif_realize;
+    dc->unrealize = imx6ul_lcdif_unrealize;
+    dc->vmsd = &vmstate_imx6ul_lcdif;
+    device_class_set_legacy_reset(dc, imx6ul_lcdif_reset);
+    dc->desc = "i.MX6UL LCDIF";
+}
+
+static const TypeInfo imx6ul_lcdif_info = {
+    .name = TYPE_IMX6UL_LCDIF,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(IMX6ULLCDIFState),
+    .class_init = imx6ul_lcdif_class_init,
+};
+
+static void imx6ul_lcdif_register_types(void)
+{
+    type_register_static(&imx6ul_lcdif_info);
+}
+
+type_init(imx6ul_lcdif_register_types)
diff --git a/hw/display/meson.build b/hw/display/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/hw/display/meson.build
+++ b/hw/display/meson.build
@@ -XXX,XX +XXX,XX @@ system_ss.add(when: ['CONFIG_VGA_CIRRUS', 'CONFIG_VGA_ISA'], if_true: files('cir
 system_ss.add(when: 'CONFIG_G364FB', if_true: files('g364fb.c'))
 system_ss.add(when: 'CONFIG_JAZZ_LED', if_true: files('jazz_led.c'))
 system_ss.add(when: 'CONFIG_PL110', if_true: files('pl110.c'))
+system_ss.add(when: 'CONFIG_IMX6UL_LCDIF', if_true: files('imx6ul_lcdif.c'))
 system_ss.add(when: 'CONFIG_SII9022', if_true: files('sii9022.c'))
 system_ss.add(when: 'CONFIG_SSD0303', if_true: files('ssd0303.c'))
 system_ss.add(when: 'CONFIG_SSD0323', if_true: files('ssd0323.c'))
diff --git a/include/hw/display/imx6ul_lcdif.h b/include/hw/display/imx6ul_lcdif.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/hw/display/imx6ul_lcdif.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * i.MX6UL LCDIF controller
+ *
+ * Copyright (c) 2026 Yucai Liu <1486344514@qq.com>
+ */
+
+#ifndef IMX6UL_LCDIF_H
+#define IMX6UL_LCDIF_H
+
+#include "hw/core/sysbus.h"
+#include "qom/object.h"
+#include "qemu/timer.h"
+#include "ui/console.h"
+
+#define TYPE_IMX6UL_LCDIF "imx6ul-lcdif"
+#define IMX6UL_LCDIF_REGS_NUM ((0x230 >> 4) + 1)
+OBJECT_DECLARE_SIMPLE_TYPE(IMX6ULLCDIFState, IMX6UL_LCDIF)
+
+struct IMX6ULLCDIFState {
+    SysBusDevice parent_obj;
+
+    MemoryRegion iomem;
+    MemoryRegionSection fbsection;
+    qemu_irq irq;
+    QemuConsole *con;
+    QEMUTimer *frame_timer;
+    uint32_t fb_base;
+    uint32_t src_width;
+    uint32_t rows;
+    uint8_t src_bpp;
+    bool invalidate;
+    uint32_t regs[IMX6UL_LCDIF_REGS_NUM];
+};
+
+#endif /* IMX6UL_LCDIF_H */
-- 
2.43.0

From: Yucai Liu <1486344514@qq.com>

Instantiate LCDIF as a child object of the i.MX6UL SoC in init and
realize it in the SoC realize path before MMIO/IRQ hookup.

Also make FSL_IMX6UL select CONFIG_IMX6UL_LCDIF and map the LCDIF
region with a 16 KiB size to match the SoC memory map.

Signed-off-by: Yucai Liu <1486344514@qq.com>
Message-id: 20260412110240.93116-3-yangyanglan718@gmail.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/Kconfig              |  1 +
 hw/arm/fsl-imx6ul.c         | 12 ++++++++++--
 include/hw/arm/fsl-imx6ul.h |  4 +++-
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/Kconfig
+++ b/hw/arm/Kconfig
@@ -XXX,XX +XXX,XX @@ config FSL_IMX6UL
     imply I2C_DEVICES
     select A15MPCORE
     select IMX
+    select IMX6UL_LCDIF
     select IMX_FEC
     select IMX_I2C
     select IMX_USBPHY
diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/fsl-imx6ul.c
+++ b/hw/arm/fsl-imx6ul.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "hw/arm/fsl-imx6ul.h"
+#include "hw/display/imx6ul_lcdif.h"
 #include "hw/misc/unimp.h"
 #include "hw/usb/imx-usb-phy.h"
 #include "hw/core/boards.h"
@@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj)
         object_initialize_child(obj, name, &s->usb[i], TYPE_CHIPIDEA);
     }
 
+    /*
+     * LCDIF
+     */
+    object_initialize_child(obj, "lcdif", &s->lcdif, TYPE_IMX6UL_LCDIF);
+
     /*
      * SDHCIs
      */
@@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp)
     /*
      * LCD
      */
-    create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR,
-                                FSL_IMX6UL_LCDIF_SIZE);
+    sysbus_realize(SYS_BUS_DEVICE(&s->lcdif), &error_abort);
+    sysbus_mmio_map(SYS_BUS_DEVICE(&s->lcdif), 0, FSL_IMX6UL_LCDIF_ADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(&s->lcdif), 0,
+                       qdev_get_gpio_in(gic, FSL_IMX6UL_LCDIF_IRQ));
 
     /*
      * CSU
diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/fsl-imx6ul.h
+++ b/include/hw/arm/fsl-imx6ul.h
@@ -XXX,XX +XXX,XX @@
 #include "hw/net/imx_fec.h"
 #include "hw/usb/chipidea.h"
 #include "hw/usb/imx-usb-phy.h"
+#include "hw/display/imx6ul_lcdif.h"
 #include "system/memory.h"
 #include "target/arm/cpu.h"
 #include "qom/object.h"
@@ -XXX,XX +XXX,XX @@ struct FslIMX6ULState {
     IMX2WdtState       wdt[FSL_IMX6UL_NUM_WDTS];
     IMXUSBPHYState     usbphy[FSL_IMX6UL_NUM_USB_PHYS];
     ChipideaState      usb[FSL_IMX6UL_NUM_USBS];
+    IMX6ULLCDIFState   lcdif;
     MemoryRegion       rom;
     MemoryRegion       caam;
     MemoryRegion       ocram;
@@ -XXX,XX +XXX,XX @@ enum FslIMX6ULMemoryMap {
     FSL_IMX6UL_PXP_SIZE             = (16 * KiB),
 
     FSL_IMX6UL_LCDIF_ADDR           = 0x021C8000,
-    FSL_IMX6UL_LCDIF_SIZE           = 0x100,
+    FSL_IMX6UL_LCDIF_SIZE           = (16 * KiB),
 
     FSL_IMX6UL_CSI_ADDR             = 0x021C4000,
     FSL_IMX6UL_CSI_SIZE             = 0x100,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

We have a registerfields interface which we can use for defining
fields alongside helpers to access them. Define the basic syndrome
layout and convert the helpers that take the imm16 data directly.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-2-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 75 ++++++++++++++++++++++++++++++++-----------
 1 file changed, 57 insertions(+), 18 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@
 #ifndef TARGET_ARM_SYNDROME_H
 #define TARGET_ARM_SYNDROME_H
 
-#include "qemu/bitops.h"
+#include "hw/core/registerfields.h"
 
 /* Valid Syndrome Register EC field values */
 enum arm_exception_class {
@@ -XXX,XX +XXX,XX @@ enum arm_exception_class {
     EC_AA64_BKPT              = 0x3c,
 };
 
+/* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */
+FIELD(SYNDROME, EC, 26, 6)
+FIELD(SYNDROME, IL, 25, 1)
+FIELD(SYNDROME, ISS, 0, 25)
+
 typedef enum {
     SME_ET_AccessTrap,
     SME_ET_Streaming,
@@ -XXX,XX +XXX,XX @@ typedef enum {
 
 static inline uint32_t syn_get_ec(uint32_t syn)
 {
-    return syn >> ARM_EL_EC_SHIFT;
+    return FIELD_EX32(syn, SYNDROME, EC);
 }
 
 static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec)
 {
-    return deposit32(syn, ARM_EL_EC_SHIFT, ARM_EL_EC_LENGTH, ec);
+    return FIELD_DP32(syn, SYNDROME, EC, ec);
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec)
  */
 static inline uint32_t syn_uncategorized(void)
 {
-    return (EC_UNCATEGORIZED << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_UNCATEGORIZED);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
+FIELD(ISS_IMM16, IMM16, 0, 16)
+
 static inline uint32_t syn_aa64_svc(uint32_t imm16)
 {
-    return (EC_AA64_SVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_SVC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa64_hvc(uint32_t imm16)
 {
-    return (EC_AA64_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_HVC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa64_smc(uint32_t imm16)
 {
-    return (EC_AA64_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_SMC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit)
 {
-    return (EC_AA32_SVC << ARM_EL_EC_SHIFT) | (imm16 & 0xffff)
-        | (is_16bit ? 0 : ARM_EL_IL);
+    uint32_t res = syn_set_ec(0, EC_AA32_SVC);
+    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_hvc(uint32_t imm16)
 {
-    return (EC_AA32_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA32_HVC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_smc(void)
 {
-    return (EC_AA32_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_AA32_SMC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_aa64_bkpt(uint32_t imm16)
 {
-    return (EC_AA64_BKPT << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff);
+    uint32_t res = syn_set_ec(0, EC_AA64_BKPT);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit)
 {
-    return (EC_AA32_BKPT << ARM_EL_EC_SHIFT) | (imm16 & 0xffff)
-        | (is_16bit ? 0 : ARM_EL_IL);
+    uint32_t res = syn_set_ec(0, EC_AA32_BKPT);
+    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
+    return res;
 }
 
 static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2,
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit)
 
 static inline uint32_t syn_sve_access_trap(void)
 {
-    return (EC_SVEACCESSTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_SVEACCESSTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
 
 static inline uint32_t syn_illegalstate(void)
 {
-    return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_ILLEGALSTATE);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_pcalignment(void)
 {
-    return (EC_PCALIGNMENT << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_PCALIGNMENT);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn)
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gcs_gcsstr(int ra, int rn)
 
 static inline uint32_t syn_serror(uint32_t extra)
 {
-    return (EC_SERROR << ARM_EL_EC_SHIFT) | ARM_EL_IL | extra;
+    uint32_t res = syn_set_ec(0, EC_SERROR);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, SYNDROME, ISS, extra);
+    return res;
 }
 
 static inline uint32_t syn_mop(bool is_set, bool is_setg, int options,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Migrate syn_aa64_sysregtrap and co-processor register trap syndromes
to the registerfields API. The co-processor syndromes are split
between single and duel register moves.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-3-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 124 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 102 insertions(+), 22 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ enum arm_exception_class {
 
 /* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */
 FIELD(SYNDROME, EC, 26, 6)
-FIELD(SYNDROME, IL, 25, 1)
+FIELD(SYNDROME, IL, 25, 1) /* IL=1 for 32 bit instructions */
 FIELD(SYNDROME, ISS, 0, 25)
 
 typedef enum {
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_smc(uint32_t imm16)
 static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit)
 {
     uint32_t res = syn_set_ec(0, EC_AA32_SVC);
-    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
     res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
     return res;
 }
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_bkpt(uint32_t imm16)
 static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit)
 {
     uint32_t res = syn_set_ec(0, EC_AA32_BKPT);
-    res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
     res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16);
     return res;
 }
 
+/*
+ * ISS encoding for an exception from MSR, MRS, or System instruction
+ * in AArch64 state.
+ */
+FIELD(SYSREG_ISS, ISREAD, 0, 1) /* Direction, 1 is read */
+FIELD(SYSREG_ISS, CRM, 1, 4)
+FIELD(SYSREG_ISS, RT, 5, 5)
+FIELD(SYSREG_ISS, CRN, 10, 4)
+FIELD(SYSREG_ISS, OP1, 14, 3)
+FIELD(SYSREG_ISS, OP2, 17, 3)
+FIELD(SYSREG_ISS, OP0, 20, 2)
+
 static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2,
                                            int crn, int crm, int rt,
                                            int isread)
 {
-    return (EC_SYSTEMREGISTERTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL
-        | (op0 << 20) | (op2 << 17) | (op1 << 14) | (crn << 10) | (rt << 5)
-        | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_SYSTEMREGISTERTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, SYSREG_ISS, OP0, op0);
+    res = FIELD_DP32(res, SYSREG_ISS, OP2, op2);
+    res = FIELD_DP32(res, SYSREG_ISS, OP1, op1);
+    res = FIELD_DP32(res, SYSREG_ISS, CRN, crn);
+    res = FIELD_DP32(res, SYSREG_ISS, RT, rt);
+    res = FIELD_DP32(res, SYSREG_ISS, CRM, crm);
+    res = FIELD_DP32(res, SYSREG_ISS, ISREAD, isread);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from an MCR or MRC access
+ * (move to/from co-processor)
+ */
+FIELD(COPROC_ISS, ISREAD, 0, 1)
+FIELD(COPROC_ISS, CRM, 1, 4)
+FIELD(COPROC_ISS, RT, 5, 5)
+FIELD(COPROC_ISS, CRN, 10, 4)
+FIELD(COPROC_ISS, OP1, 14, 3)
+FIELD(COPROC_ISS, OP2, 17, 3)
+FIELD(COPROC_ISS, COND, 20, 4)
+FIELD(COPROC_ISS, CV, 24, 1)
+
 static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2,
                                         int crn, int crm, int rt, int isread,
                                         bool is_16bit)
 {
-    return (EC_CP14RTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14)
-        | (crn << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP14RTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_ISS, OP2, opc2);
+    res = FIELD_DP32(res, COPROC_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_ISS, CRN, crn);
+    res = FIELD_DP32(res, COPROC_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread);
+
+    return res;
 }
 
 static inline uint32_t syn_cp15_rt_trap(int cv, int cond, int opc1, int opc2,
                                         int crn, int crm, int rt, int isread,
                                         bool is_16bit)
 {
-    return (EC_CP15RTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14)
-        | (crn << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP15RTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_ISS, OP2, opc2);
+    res = FIELD_DP32(res, COPROC_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_ISS, CRN, crn);
+    res = FIELD_DP32(res, COPROC_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from an MCRR or MRRC access
+ * (move to/from co-processor with 2 regs)
+ */
+FIELD(COPROC_R2_ISS, ISREAD, 0, 1)
+FIELD(COPROC_R2_ISS, CRM, 1, 4)
+FIELD(COPROC_R2_ISS, RT, 5, 5)
+FIELD(COPROC_R2_ISS, RT2, 10, 5)
+FIELD(COPROC_R2_ISS, OP1, 16, 4)
+FIELD(COPROC_R2_ISS, COND, 20, 4)
+FIELD(COPROC_R2_ISS, CV, 24, 1)
+
 static inline uint32_t syn_cp14_rrt_trap(int cv, int cond, int opc1, int crm,
                                          int rt, int rt2, int isread,
                                          bool is_16bit)
 {
-    return (EC_CP14RRTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc1 << 16)
-        | (rt2 << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP14RRTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread);
+
+    return res;
 }
 
 static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm,
                                          int rt, int rt2, int isread,
                                          bool is_16bit)
 {
-    return (EC_CP15RRTTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (opc1 << 16)
-        | (rt2 << 10) | (rt << 5) | (crm << 1) | isread;
+    uint32_t res = syn_set_ec(0, EC_CP15RRTTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2);
+    res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm);
+    res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread);
+
+    return res;
 }
 
 static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

The syn_simd_access trap was never used so remove it. We should only
see the COPROC encoding on v7 architectures.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-4-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm,
     return res;
 }
 
+/*
+ * ISS encoding for an exception from an access to a register of
+ * instruction resulting from the FPEN or TFP traps.
+ */
+FIELD(FP_ISS, COPROC, 0, 4) /* ARMv7 only */
+FIELD(FP_ISS, COND, 20, 4)
+FIELD(FP_ISS, CV, 24, 1)
+
 static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit,
                                           int coproc)
 {
     /* AArch32 FP trap or any AArch64 FP/SIMD trap: TA == 0 */
-    return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | coproc;
-}
+    uint32_t res = syn_set_ec(0, EC_ADVSIMDFPACCESSTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
 
-static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit)
-{
-    /* AArch32 SIMD trap: TA == 1 coproc == 0 */
-    return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL)
-        | (cv << 24) | (cond << 20) | (1 << 5);
+    res = FIELD_DP32(res, FP_ISS, CV, cv);
+    res = FIELD_DP32(res, FP_ISS, COND, cond);
+    res = FIELD_DP32(res, FP_ISS, COPROC, coproc);
+
+    return res;
 }
 
 static inline uint32_t syn_sve_access_trap(void)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

For simplicity keep the OP as a two bit field rather than the two
interlinked fields in the docs (ERET/ERETA).

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-5-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_sve_access_trap(void)
 }
 
 /*
+ * ISS encoding for an exception from an ERET, ERETAA or ERETAB
+ * instructions.
+ *
  * eret_op is bits [1:0] of the ERET instruction, so:
  * 0 for ERET, 2 for ERETAA, 3 for ERETAB.
  */
+FIELD(ERET_ISS, OP, 0, 2)
+
 static inline uint32_t syn_erettrap(int eret_op)
 {
-    return (EC_ERETTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | eret_op;
+    uint32_t res = syn_set_ec(0, EC_ERETTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, ERET_ISS, OP, eret_op);
+
+    return res;
 }
 
 static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-6-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_erettrap(int eret_op)
     return res;
 }
 
+/*
+ * ISS encoding for an exception due to SME functionality
+ */
+FIELD(SME_ISS, SMTC, 0, 2)
+
 static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit)
 {
-    return (EC_SMETRAP << ARM_EL_EC_SHIFT)
-        | (is_16bit ? 0 : ARM_EL_IL) | etype;
+    uint32_t res = syn_set_ec(0, EC_SMETRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+    res = FIELD_DP32(res, SME_ISS, SMTC, etype);
+
+    return res;
 }
 
 static inline uint32_t syn_pacfail(bool data, int keynumber)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

syn_pactrap is fairly simple as the ISS is all RES0.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-7-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit)
     return res;
 }
 
+/*
+ * ISS encoding for a PAC Fail exceptions
+ */
+FIELD(PACFAIL_ISS, BnA, 0, 1) /* B key or A key */
+FIELD(PACFAIL_ISS, DnI, 1, 1) /* Data or Instruction */
+
 static inline uint32_t syn_pacfail(bool data, int keynumber)
 {
-    int error_code = (data << 1) | keynumber;
-    return (EC_PACFAIL << ARM_EL_EC_SHIFT) | ARM_EL_IL | error_code;
+    uint32_t res = syn_set_ec(0, EC_PACFAIL);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, PACFAIL_ISS, DnI, data);
+    res = FIELD_DP32(res, PACFAIL_ISS, BnA, keynumber);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a trapped Pointer
+ * Authentication instruction is RES0
+ */
 static inline uint32_t syn_pactrap(void)
 {
-    return (EC_PACTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL;
+    uint32_t res = syn_set_ec(0, EC_PACTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    return res;
 }
 
 static inline uint32_t syn_btitrap(int btype)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-8-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pactrap(void)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from a Branch Target Identification
+ * instruction.
+ */
+FIELD(BTI_ISS, BTYPE, 0, 2)
+
 static inline uint32_t syn_btitrap(int btype)
 {
-    return (EC_BTITRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | btype;
+    uint32_t res = syn_set_ec(0, EC_BTITRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, BTI_ISS, BTYPE, btype);
+    return res;
 }
 
 static inline uint32_t syn_bxjtrap(int cv, int cond, int rm)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

This is an Armv7 specific syndrome for chips with Jazelle
functionality.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-9-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_btitrap(int btype)
     return res;
 }
 
+/*
+ * ISS encoding for trapped BXJ execution
+ *
+ * This is an Armv7 encoding.
+ */
+FIELD(BXJ_ISS, RM, 0, 4)
+/* bits 4:19 are Reserved, UNK/SBZP */
+FIELD(BXJ_ISS, COND, 20, 4)
+FIELD(BXJ_ISS, CV, 24, 1)
+
 static inline uint32_t syn_bxjtrap(int cv, int cond, int rm)
 {
-    return (EC_BXJTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-        (cv << 24) | (cond << 20) | rm;
+    uint32_t res = syn_set_ec(0, EC_BXJTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, BXJ_ISS, CV, cv);
+    res = FIELD_DP32(res, BXJ_ISS, COND, cond);
+    res = FIELD_DP32(res, BXJ_ISS, RM, rm);
+
+    return res;
 }
 
 static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr,
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-10-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_bxjtrap(int cv, int cond, int rm)
     return res;
 }
 
+/*
+ * ISS encoding for a Granule Protection Check exception
+ *
+ * These are only reported to EL3
+ */
+FIELD(GPC_ISS, xFSC, 0, 6)
+FIELD(GPC_ISS, WnR, 6, 1) /* Write not Read */
+FIELD(GPC_ISS, S1PTW, 7, 1)
+FIELD(GPC_ISS, CM, 8, 1)
+FIELD(GPC_ISS, VNCR, 13, 1)
+FIELD(GPC_ISS, GPCSC, 14, 6)
+FIELD(GPC_ISS, InD, 20, 1) /* Instruction not Data access */
+FIELD(GPC_ISS, S2PTW, 21, 1)
+
 static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr,
                                int cm, int s1ptw, int wnr, int fsc)
 {
-    return (EC_GPC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (s2ptw << 21)
-        | (ind << 20) | (gpcsc << 14) | (vncr << 13) | (cm << 8)
-        | (s1ptw << 7) | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_GPC);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GPC_ISS, S2PTW, s2ptw);
+    res = FIELD_DP32(res, GPC_ISS, InD, ind);
+    res = FIELD_DP32(res, GPC_ISS, GPCSC, gpcsc);
+    res = FIELD_DP32(res, GPC_ISS, VNCR, vncr);
+    res = FIELD_DP32(res, GPC_ISS, CM, cm);
+    res = FIELD_DP32(res, GPC_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, GPC_ISS, WnR, wnr);
+    res = FIELD_DP32(res, GPC_ISS, xFSC, fsc);
+
+    return res;
 }
 
 static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Migrate syn_insn_abort and syn_data_abort_* to the registerfields API.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260422125250.1303100-11-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 87 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 74 insertions(+), 13 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr,
     return res;
 }
 
+/*
+ * ISS encoding for an exception from an Instruction Abort
+ *
+ * (aka instruction abort)
+ */
+FIELD(IABORT_ISS, IFSC, 0, 6)
+FIELD(IABORT_ISS, S1PTW, 7, 1)
+FIELD(IABORT_ISS, EA, 9, 1)
+FIELD(IABORT_ISS, FnV, 10, 1) /* FAR not Valid */
+FIELD(IABORT_ISS, SET, 11, 2)
+FIELD(IABORT_ISS, PFV, 14, 1)
+FIELD(IABORT_ISS, TopLevel, 21, 1) /* FEAT_THE */
+
 static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc)
 {
-    return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc;
+    uint32_t res = syn_set_ec(0, EC_INSNABORT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, IABORT_ISS, EA, ea);
+    res = FIELD_DP32(res, IABORT_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, IABORT_ISS, IFSC, fsc);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a Data Abort
+ */
+FIELD(DABORT_ISS, DFSC, 0, 6)
+FIELD(DABORT_ISS, WNR, 6, 1)
+FIELD(DABORT_ISS, S1PTW, 7, 1)
+FIELD(DABORT_ISS, CM, 8, 1)
+FIELD(DABORT_ISS, EA, 9, 1)
+FIELD(DABORT_ISS, FnV, 10, 1)
+FIELD(DABORT_ISS, LST, 11, 2)
+FIELD(DABORT_ISS, VNCR, 13, 1)
+FIELD(DABORT_ISS, AR, 14, 1)
+FIELD(DABORT_ISS, SF, 15, 1)
+FIELD(DABORT_ISS, SRT, 16, 5)
+FIELD(DABORT_ISS, SSE, 21, 1)
+FIELD(DABORT_ISS, SAS, 22, 2)
+FIELD(DABORT_ISS, ISV, 24, 1)
+
 static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv,
                                              int ea, int cm, int s1ptw,
                                              int wnr, int fsc)
 {
-    return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-           | ARM_EL_IL
-           | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7)
-           | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, DABORT_ISS, FnV, fnv);
+    res = FIELD_DP32(res, DABORT_ISS, EA, ea);
+    res = FIELD_DP32(res, DABORT_ISS, CM, cm);
+    res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, DABORT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc);
+
+    return res;
 }
 
 static inline uint32_t syn_data_abort_with_iss(int same_el,
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el,
                                                int wnr, int fsc,
                                                bool is_16bit)
 {
-    return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-           | (is_16bit ? 0 : ARM_EL_IL)
-           | ARM_EL_ISV | (sas << 22) | (sse << 21) | (srt << 16)
-           | (sf << 15) | (ar << 14)
-           | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, DABORT_ISS, ISV, 1);
+    res = FIELD_DP32(res, DABORT_ISS, SAS, sas);
+    res = FIELD_DP32(res, DABORT_ISS, SSE, sse);
+    res = FIELD_DP32(res, DABORT_ISS, SRT, srt);
+    res = FIELD_DP32(res, DABORT_ISS, SF, sf);
+    res = FIELD_DP32(res, DABORT_ISS, AR, ar);
+    res = FIELD_DP32(res, DABORT_ISS, EA, ea);
+    res = FIELD_DP32(res, DABORT_ISS, CM, cm);
+    res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw);
+    res = FIELD_DP32(res, DABORT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc);
+
+    return res;
 }
 
 /*
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el,
  */
 static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc)
 {
-    return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (1 << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | ARM_EL_VNCR | (wnr << 6) | fsc;
+    uint32_t res = syn_set_ec(0, EC_DATAABORT_SAME_EL);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, DABORT_ISS, VNCR, 1);
+    res = FIELD_DP32(res, DABORT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc);
+
+    return res;
 }
 
 static inline uint32_t syn_swstep(int same_el, int isv, int ex)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Migrate syn_swstep, syn_watchpoint and syn_breakpoint to the
registerfields API.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-12-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 54 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 48 insertions(+), 6 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from a Software Step exception.
+ */
+FIELD(SOFTSTEP_ISS, IFSC, 0, 6)
+FIELD(SOFTSTEP_ISS, EX, 6, 1)
+FIELD(SOFTSTEP_ISS, ISV, 24, 1)
+
 static inline uint32_t syn_swstep(int same_el, int isv, int ex)
 {
-    return (EC_SOFTWARESTEP << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | (isv << 24) | (ex << 6) | 0x22;
+    uint32_t res = syn_set_ec(0, EC_SOFTWARESTEP + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, SOFTSTEP_ISS, ISV, isv);
+    res = FIELD_DP32(res, SOFTSTEP_ISS, EX, ex);
+    res = FIELD_DP32(res, SOFTSTEP_ISS, IFSC, 0x22);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a Watchpoint exception
+ */
+FIELD(WATCHPOINT_ISS, DFSC, 0, 6)
+FIELD(WATCHPOINT_ISS, WNR, 6, 1)
+FIELD(WATCHPOINT_ISS, CM, 8, 1)
+FIELD(WATCHPOINT_ISS, FnV, 10, 1)
+FIELD(WATCHPOINT_ISS, VNCR, 13, 1) /* FEAT_NV2 */
+FIELD(WATCHPOINT_ISS, FnP, 15, 1)
+FIELD(WATCHPOINT_ISS, WPF, 16, 1)
+/* bellow mandatory from FEAT_Debugv8p9 */
+FIELD(WATCHPOINT_ISS, WPTV, 17, 1) /* FEAT_Debugv8p2 - WPT valid */
+FIELD(WATCHPOINT_ISS, WPT, 18, 6) /* FEAT_Debugv8p2 - missing WP number */
+
 static inline uint32_t syn_watchpoint(int same_el, int cm, int wnr)
 {
-    return (EC_WATCHPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | (cm << 8) | (wnr << 6) | 0x22;
+    uint32_t res = syn_set_ec(0, EC_WATCHPOINT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, WATCHPOINT_ISS, CM, cm);
+    res = FIELD_DP32(res, WATCHPOINT_ISS, WNR, wnr);
+    res = FIELD_DP32(res, WATCHPOINT_ISS, DFSC, 0x22);
+
+    return res;
 }
 
+/*
+ * ISS encoding for an exception from a Breakpoint or a Vector Catch
+ * debug exception.
+ */
+FIELD(BREAKPOINT_ISS, IFSC, 0, 6)
+
 static inline uint32_t syn_breakpoint(int same_el)
 {
-    return (EC_BREAKPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT)
-        | ARM_EL_IL | 0x22;
+    uint32_t res = syn_set_ec(0, EC_BREAKPOINT + same_el);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+    res = FIELD_DP32(res, BREAKPOINT_ISS, IFSC, 0x22);
+
+    return res;
 }
 
 static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

This will help later when we expand the fields we report.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-13-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_breakpoint(int same_el)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from a WF* instruction
+ */
+FIELD(WFX_ISS, TI, 0, 2)
+FIELD(WFX_ISS, RV, 2, 1)
+FIELD(WFX_ISS, RN, 5, 5)
+FIELD(WFX_ISS, COND, 20, 4)
+FIELD(WFX_ISS, CV, 24, 1)
+
 static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
 {
-    return (EC_WFX_TRAP << ARM_EL_EC_SHIFT) |
-           (is_16bit ? 0 : (1 << ARM_EL_IL_SHIFT)) |
-           (cv << 24) | (cond << 20) | ti;
+    uint32_t res = syn_set_ec(0, EC_WFX_TRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
+
+    res = FIELD_DP32(res, WFX_ISS, CV, cv);
+    res = FIELD_DP32(res, WFX_ISS, COND, cond);
+    res = FIELD_DP32(res, WFX_ISS, TI, ti);
+
+    return res;
 }
 
 static inline uint32_t syn_illegalstate(void)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Tweak arg names to make it clear raddr is the data address register
number.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-14-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 39 +++++++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 6 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pcalignment(void)
     return res;
 }
 
+/*
+ * ISS encoding for a GCS exception
+ *
+ * Field validity depends on EXTYPE
+ */
+FIELD(GCS_ISS, IT, 0, 5)
+FIELD(GCS_ISS, RN, 5, 5) /* only for non EXLOCK exceptions */
+FIELD(GCS_ISS, RADDR, 10, 5) /* only for GCSSTR/GCSSTTR traps */
+FIELD(GCS_ISS, EXTYPE, 20, 4)
+
 static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn)
 {
-    return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-            (GCS_ET_DataCheck << 20) | (rn << 5) | it);
+    uint32_t res = syn_set_ec(0, EC_GCS);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_DataCheck);
+    res = FIELD_DP32(res, GCS_ISS, RN, rn);
+    res = FIELD_DP32(res, GCS_ISS, IT, it);
+
+    return res;
 }
 
 static inline uint32_t syn_gcs_exlock(void)
 {
-    return (EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | (GCS_ET_EXLOCK << 20);
+    uint32_t res = syn_set_ec(0, EC_GCS);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_EXLOCK);
+
+    return res;
 }
 
-static inline uint32_t syn_gcs_gcsstr(int ra, int rn)
+static inline uint32_t syn_gcs_gcsstr(int raddr, int rn)
 {
-    return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-            (GCS_ET_GCSSTR_GCSSTTR << 20) | (ra << 10) | (rn << 5));
+    uint32_t res = syn_set_ec(0, EC_GCS);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_GCSSTR_GCSSTTR);
+    res = FIELD_DP32(res, GCS_ISS, RADDR, raddr);
+    res = FIELD_DP32(res, GCS_ISS, RN, rn);
+
+    return res;
 }
 
 static inline uint32_t syn_serror(uint32_t extra)
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-15-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_serror(uint32_t extra)
     return res;
 }
 
+/*
+ * ISS encoding for an exception from the Memory Copy and Memory Set
+ * instructions.
+ */
+FIELD(MOP_ISS, SIZEREG, 0, 5)
+FIELD(MOP_ISS, SRCREG, 5, 5)
+FIELD(MOP_ISS, DESTREG, 10, 5)
+FIELD(MOP_ISS, FORMATOPT, 16, 2)
+FIELD(MOP_ISS, OPT_A, 16, 1)
+FIELD(MOP_ISS, WRONG_OPT, 17, 1)
+FIELD(MOP_ISS, EPILOGUE, 18, 1)
+FIELD(MOP_ISS, OPTIONS, 19, 4)
+FIELD(MOP_ISS, IS_SETG, 23, 1)
+FIELD(MOP_ISS, MEMINST, 24, 1)
+
 static inline uint32_t syn_mop(bool is_set, bool is_setg, int options,
                                bool epilogue, bool wrong_option, bool option_a,
                                int destreg, int srcreg, int sizereg)
 {
-    return (EC_MOP << ARM_EL_EC_SHIFT) | ARM_EL_IL |
-        (is_set << 24) | (is_setg << 23) | (options << 19) |
-        (epilogue << 18) | (wrong_option << 17) | (option_a << 16) |
-        (destreg << 10) | (srcreg << 5) | sizereg;
+    uint32_t res = syn_set_ec(0, EC_MOP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, MOP_ISS, MEMINST, is_set);
+    res = FIELD_DP32(res, MOP_ISS, IS_SETG, is_setg);
+    res = FIELD_DP32(res, MOP_ISS, OPTIONS, options);
+    res = FIELD_DP32(res, MOP_ISS, EPILOGUE, epilogue);
+    res = FIELD_DP32(res, MOP_ISS, WRONG_OPT, wrong_option);
+    res = FIELD_DP32(res, MOP_ISS, OPT_A, option_a);
+    res = FIELD_DP32(res, MOP_ISS, DESTREG, destreg);
+    res = FIELD_DP32(res, MOP_ISS, SRCREG, srcreg);
+    res = FIELD_DP32(res, MOP_ISS, SIZEREG, sizereg);
+
+    return res;
 }
 
 
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

It shares the same COPROC_ISS encoding as the other CP traps although
not all the fields are used.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-16-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h       | 16 ++++++++++++++++
 target/arm/tcg/vfp_helper.c |  5 +----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ FIELD(COPROC_ISS, OP2, 17, 3)
 FIELD(COPROC_ISS, COND, 20, 4)
 FIELD(COPROC_ISS, CV, 24, 1)
 
+static inline uint32_t syn_cp10_rt_trap(int cv, int cond, int opc1,
+                                        int crn, int rt, int isread)
+{
+    uint32_t res = syn_set_ec(0, EC_FPIDTRAP);
+    res = FIELD_DP32(res, SYNDROME, IL, 1);
+
+    res = FIELD_DP32(res, COPROC_ISS, CV, cv);
+    res = FIELD_DP32(res, COPROC_ISS, COND, cond);
+    res = FIELD_DP32(res, COPROC_ISS, OP1, opc1);
+    res = FIELD_DP32(res, COPROC_ISS, CRN, crn);
+    res = FIELD_DP32(res, COPROC_ISS, RT, rt);
+    res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread);
+
+    return res;
+}
+
 static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2,
                                         int crn, int crm, int rt, int isread,
                                         bool is_16bit)
diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vfp_helper.c
+++ b/target/arm/tcg/vfp_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(check_hcr_el2_trap)(CPUARMState *env, uint32_t rt, uint32_t reg)
         g_assert_not_reached();
     }
 
-    syndrome = ((EC_FPIDTRAP << ARM_EL_EC_SHIFT)
-                | ARM_EL_IL
-                | (1 << 24) | (0xe << 20) | (7 << 14)
-                | (reg << 10) | (rt << 5) | 1);
+    syndrome = syn_cp10_rt_trap(1, 0xe, 7, reg, rt, 1);
 
     raise_exception(env, EXCP_HYP_TRAP, syndrome, 2);
 }
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

One more step towards dropping the old #defines.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-17-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/arm/helper.c b/target/arm/helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs)
              */
             if (cs->exception_index == EXCP_PREFETCH_ABORT ||
                 (cs->exception_index == EXCP_DATA_ABORT &&
-                 !(env->exception.syndrome & ARM_EL_ISV)) ||
+                 !FIELD_EX32(env->exception.syndrome, SYNDROME, IL)) ||
                 syn_get_ec(env->exception.syndrome) == EC_UNCATEGORIZED) {
-                env->exception.syndrome &= ~ARM_EL_IL;
+                env->exception.syndrome = FIELD_DP32(env->exception.syndrome, SYNDROME, IL, 0);
             }
         }
         env->cp15.esr_el[2] = env->exception.syndrome;
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

This removes the last use of ARM_EL_EC_SHIFT.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-18-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h  | 1 -
 target/arm/tcg/debug.c | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
 } GCSInstructionType;
 
 #define ARM_EL_EC_LENGTH 6
-#define ARM_EL_EC_SHIFT 26
 #define ARM_EL_IL_SHIFT 25
 #define ARM_EL_ISV_SHIFT 24
 #define ARM_EL_IL (1 << ARM_EL_IL_SHIFT)
diff --git a/target/arm/tcg/debug.c b/target/arm/tcg/debug.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/debug.c
+++ b/target/arm/tcg/debug.c
@@ -XXX,XX +XXX,XX @@ raise_exception_debug(CPUARMState *env, uint32_t excp, uint32_t syndrome)
      * Similarly for watchpoint and breakpoint matches.
      */
     assert(debug_el >= cur_el);
-    syndrome |= (debug_el == cur_el) << ARM_EL_EC_SHIFT;
+    syndrome |= (debug_el == cur_el) << R_SYNDROME_EC_SHIFT;
     raise_exception(env, excp, syndrome, debug_el);
 }
 
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Rather than open coding a bunch of shifts and masks we can use the
syndrome definitions. While we are at it assert it really is a
EC_DATAABORT.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-19-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/whpx/whpx-all.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/target/arm/whpx/whpx-all.c b/target/arm/whpx/whpx-all.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/whpx/whpx-all.c
+++ b/target/arm/whpx/whpx-all.c
@@ -XXX,XX +XXX,XX @@ static int whpx_handle_mmio(CPUState *cpu, WHV_MEMORY_ACCESS_CONTEXT *ctx)
 {
     uint64_t syndrome = ctx->Syndrome;
 
-    bool isv = syndrome & ARM_EL_ISV;
-    bool iswrite = (syndrome >> 6) & 1;
-    bool sse = (syndrome >> 21) & 1;
-    uint32_t sas = (syndrome >> 22) & 3;
+    bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV);
+    bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR);
+    bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE);
+    uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS);
     uint32_t len = 1 << sas;
-    uint32_t srt = (syndrome >> 16) & 0x1f;
-    uint32_t cm = (syndrome >> 8) & 0x1;
+    uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT);
+    uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM);
     uint64_t val = 0;
 
+    assert(syn_get_ec(syndrome) == EC_DATAABORT);
     assert(!cm);
     assert(isv);
 
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Rather than open coding a bunch of shifts and masks we can use the
syndrome definitions.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20260422125250.1303100-20-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/hvf/hvf.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/hvf/hvf.c
+++ b/target/arm/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@ static int hvf_handle_exception(CPUState *cpu, hv_vcpu_exit_exception_t *excp)
         break;
     }
     case EC_DATAABORT: {
-        bool isv = syndrome & ARM_EL_ISV;
-        bool iswrite = (syndrome >> 6) & 1;
-        bool s1ptw = (syndrome >> 7) & 1;
-        bool sse = (syndrome >> 21) & 1;
-        uint32_t sas = (syndrome >> 22) & 3;
+        bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV);
+        bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR);
+        bool s1ptw = FIELD_EX32(syndrome, DABORT_ISS, S1PTW);
+        bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE);
+        uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS);
         uint32_t len = 1 << sas;
-        uint32_t srt = (syndrome >> 16) & 0x1f;
-        uint32_t cm = (syndrome >> 8) & 0x1;
+        uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT);
+        uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM);
         uint64_t val = 0;
         uint64_t ipa = excp->physical_address;
         AddressSpace *as = cpu_get_address_space(cpu, ARMASIdx_NS);
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

One more step to removing the old defines.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-21-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/tlb_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

From: Alex Bennée <alex.bennee@linaro.org>

These are only valid for data abort syndromes.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-22-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/tlb_helper.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/tlb_helper.c
+++ b/target/arm/tcg/tlb_helper.c
@@ -XXX,XX +XXX,XX @@ static inline uint64_t merge_syn_data_abort(uint32_t template_syn,
      * ST64BV, or ST64BV0 insns report syndrome info even for stage-1
      * faults and regardless of the target EL.
      */
-    if (template_syn & ARM_EL_VNCR) {
+    if (FIELD_EX32(template_syn, DABORT_ISS, VNCR)) {
         /*
          * FEAT_NV2 faults on accesses via VNCR_EL2 are a special case:
          * they are always reported as "same EL", even though we are going
@@ -XXX,XX +XXX,XX @@ void arm_deliver_fault(ARMCPU *cpu, vaddr addr,
      * because we masked that out in disas_set_insn_syndrome())
      */
     bool is_vncr = (access_type != MMU_INST_FETCH) &&
-        (env->exception.syndrome & ARM_EL_VNCR);
+        FIELD_EX32(env->exception.syndrome, DABORT_ISS, VNCR);
 
     if (is_vncr) {
         /* FEAT_NV2 faults on accesses via VNCR_EL2 go to EL2 */
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Now everything is defined with registerfields we can drop the old
defines.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-23-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ typedef enum {
     GCS_IT_GCSPOPX = 9,
 } GCSInstructionType;
 
-#define ARM_EL_EC_LENGTH 6
-#define ARM_EL_IL_SHIFT 25
-#define ARM_EL_ISV_SHIFT 24
-#define ARM_EL_IL (1 << ARM_EL_IL_SHIFT)
-#define ARM_EL_ISV (1 << ARM_EL_ISV_SHIFT)
-
-/* In the Data Abort syndrome */
-#define ARM_EL_VNCR (1 << 13)
-
 static inline uint32_t syn_get_ec(uint32_t syn)
 {
     return FIELD_EX32(syn, SYNDROME, EC);
-- 
2.43.0

From: Alex Bennée <alex.bennee@linaro.org>

Pass the register number (rd) to the wfit helper and report it in the
syndrome ISS.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20260422125250.1303100-24-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h          | 11 ++++++++++-
 target/arm/tcg/helper-defs.h   |  2 +-
 target/arm/tcg/op_helper.c     |  7 ++++---
 target/arm/tcg/translate-a64.c |  2 +-
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -XXX,XX +XXX,XX @@ FIELD(WFX_ISS, RN, 5, 5)
 FIELD(WFX_ISS, COND, 20, 4)
 FIELD(WFX_ISS, CV, 24, 1)
 
-static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
+typedef enum {
+    WFI = 0b00,
+    WFE = 0b01,
+    WFIT = 0b10,
+    WFET = 0xb11
+} wfx_ti;
+
+static inline uint32_t syn_wfx(int cv, int cond, int rn, bool rv, wfx_ti ti, bool is_16bit)
 {
     uint32_t res = syn_set_ec(0, EC_WFX_TRAP);
     res = FIELD_DP32(res, SYNDROME, IL, !is_16bit);
@@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit)
     res = FIELD_DP32(res, WFX_ISS, CV, cv);
     res = FIELD_DP32(res, WFX_ISS, COND, cond);
     res = FIELD_DP32(res, WFX_ISS, TI, ti);
+    res = FIELD_DP32(res, WFX_ISS, RN, rn);
+    res = FIELD_DP32(res, WFX_ISS, RV, rv);
 
     return res;
 }
diff --git a/target/arm/tcg/helper-defs.h b/target/arm/tcg/helper-defs.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-defs.h
+++ b/target/arm/tcg/helper-defs.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(exception_pc_alignment, noreturn, env, vaddr)
 DEF_HELPER_1(setend, void, env)
 DEF_HELPER_2(wfi, void, env, i32)
 DEF_HELPER_1(wfe, void, env)
-DEF_HELPER_2(wfit, void, env, i64)
+DEF_HELPER_2(wfit, void, env, i32)
 DEF_HELPER_1(yield, void, env)
 DEF_HELPER_1(pre_hvc, void, env)
 DEF_HELPER_2(pre_smc, void, env, i32)
diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/op_helper.c
+++ b/target/arm/tcg/op_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len)
             env->regs[15] -= insn_len;
         }
 
-        raise_exception(env, excp, syn_wfx(1, 0xe, 0, insn_len == 2),
+        raise_exception(env, excp, syn_wfx(1, 0xe, 0, false, WFI, insn_len == 2),
                         target_el);
     }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len)
 #endif
 }
 
-void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
+void HELPER(wfit)(CPUARMState *env, uint32_t rd)
 {
 #ifdef CONFIG_USER_ONLY
     /*
@@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
     int target_el = check_wfx_trap(env, false, &excp);
     /* The WFIT should time out when CNTVCT_EL0 >= the specified value. */
     uint64_t cntval = gt_get_countervalue(env);
+    uint64_t timeout = env->xregs[rd];
     /*
      * We want the value that we would get if we read CNTVCT_EL0 from
      * the current exception level, so the direct_access offset, not
@@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout)
 
     if (target_el) {
         env->pc -= 4;
-        raise_exception(env, excp, syn_wfx(1, 0xe, 2, false), target_el);
+        raise_exception(env, excp, syn_wfx(1, 0xe, rd, true, WFIT, false), target_el);
     }
 
     if (uadd64_overflow(timeout, offset, &nexttick)) {
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static bool trans_WFIT(DisasContext *s, arg_WFIT *a)
     }
 
     gen_a64_update_pc(s, 4);
-    gen_helper_wfit(tcg_env, cpu_reg(s, a->rd));
+    gen_helper_wfit(tcg_env, tcg_constant_i32(a->rd));
     /* Go back to the main loop to check for interrupts */
     s->base.is_jmp = DISAS_EXIT;
     return true;
-- 
2.43.0