Merge tag 'pull-target-arm-20240801' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * hw/arm/mps2-tz.c: fix RX/TX interrupts order
 * accel/kvm/kvm-all: Fixes the missing break in vCPU unpark logic
 * target/arm: Handle denormals correctly for FMOPA (widening)
 * target/xtensa: Correct assert condition in handle_interrupt()

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmarmisZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3uw4D/sGvG3uo4mncEm1DmXugj8E
# yUcnHsc6fTSP9gm0v65DmUY59+kDM9R+17STOFOhP1c851tEbv7HXQBAqI+fNoME
# 22yNxhKasWqPNOjy0XGakBDDTmMQpGUE1JcdUYc+pA9XMy+IxxkkfheedOmZ+OZ1
# r8vqzm9a2+vJLo1q00XlVrUajclXOduaRl9wKijRVcgAVtLbsdWuF3LCp6swt17O
# Zw1xARKz9nWnOQzZBWTo0VfDf53z5isaUZFNTA6XJUliBd7yxOEHHf5XM1t92Uw0
# Lilk7NWlvdpEh3EcCPdUd4UuZA+NhyK6IlZALSbWkf3BXImxslMWGVrxiWR/Zjoh
# YJzBbvtM+hP/gP+X6EzfQh/ycPoygrc9l2IwqhaIQ7ZwkukkCNs/HlcSc1JOWfLd
# ZmM7oybKRyDQ4pnc3YyqT597+sRJSUBFzss6Qy3SKqPMlhB4V+cPTV/QHV5O4xjo
# fdip3NVSSffcyiGZmwtTn0biWWUKqUubew8400gj3opbG8DGc2SyYB2vTQlEhJlp
# jm6AoA5tRdBxlLtNoG4VmZ5XlKCchoXiewImndDHHdSPPiKK9m99+JeqGegdDfLU
# 4jxv5LmMyb1MdM961yq3A4cKN0RKUwFpnrqc3DLGRu9eHBOlmfyG5vWNQafKf24r
# 4ZVUpCes0Y0rbsgbWq64+w==
# =fh2k
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 02 Aug 2024 12:22:35 AM AEST
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [full]
# gpg:                 aka "Peter Maydell <peter@archaic.org.uk>" [unknown]

* tag 'pull-target-arm-20240801' of https://git.linaro.org/people/pmaydell/qemu-arm:
  target/xtensa: Correct assert condition in handle_interrupt()
  target/arm: Handle denormals correctly for FMOPA (widening)
  accel/kvm/kvm-all: Fixes the missing break in vCPU unpark logic
  hw/arm/mps2-tz.c: fix RX/TX interrupts order

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

6 files changed, 56 insertions, 19 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index e1d1386..75d11a0 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -362,6 +362,7 @@ int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id)
             QLIST_REMOVE(cpu, node);
             kvm_fd = cpu->kvm_fd;
             g_free(cpu);
+            break;
         }
     }
 
diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
index a2d18af..aec57c0 100644
--- a/hw/arm/mps2-tz.c
+++ b/hw/arm/mps2-tz.c
@@ -435,7 +435,7 @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque,
                                const char *name, hwaddr size,
                                const int *irqs, const PPCExtraData *extradata)
 {
-    /* The irq[] array is tx, rx, combined, in that order */
+    /* The irq[] array is rx, tx, combined, in that order */
     MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms);
     CMSDKAPBUART *uart = opaque;
     int i = uart - &mms->uart[0];
@@ -447,8 +447,8 @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque,
     qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", mmc->apb_periph_frq);
     sysbus_realize(SYS_BUS_DEVICE(uart), &error_fatal);
     s = SYS_BUS_DEVICE(uart);
-    sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0]));
-    sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[1]));
+    sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[1]));
+    sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[0]));
     sysbus_connect_irq(s, 2, qdev_get_gpio_in(orgate_dev, i * 2));
     sysbus_connect_irq(s, 3, qdev_get_gpio_in(orgate_dev, i * 2 + 1));
     sysbus_connect_irq(s, 4, get_sse_irq_in(mms, irqs[2]));
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 27eef49..d22bf9d 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -121,7 +121,7 @@ DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG,
-                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+                   void, ptr, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 3ba826a..0210680 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -992,12 +992,23 @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg)
 }
 
 static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
-                          float_status *s_std, float_status *s_odd)
+                          float_status *s_f16, float_status *s_std,
+                          float_status *s_odd)
 {
-    float64 e1r = float16_to_float64(e1 & 0xffff, true, s_std);
-    float64 e1c = float16_to_float64(e1 >> 16, true, s_std);
-    float64 e2r = float16_to_float64(e2 & 0xffff, true, s_std);
-    float64 e2c = float16_to_float64(e2 >> 16, true, s_std);
+    /*
+     * We need three different float_status for different parts of this
+     * operation:
+     *  - the input conversion of the float16 values must use the
+     *    f16-specific float_status, so that the FPCR.FZ16 control is applied
+     *  - operations on float32 including the final accumulation must use
+     *    the normal float_status, so that FPCR.FZ is applied
+     *  - we have pre-set-up copy of s_std which is set to round-to-odd,
+     *    for the multiply (see below)
+     */
+    float64 e1r = float16_to_float64(e1 & 0xffff, true, s_f16);
+    float64 e1c = float16_to_float64(e1 >> 16, true, s_f16);
+    float64 e2r = float16_to_float64(e2 & 0xffff, true, s_f16);
+    float64 e2c = float16_to_float64(e2 >> 16, true, s_f16);
     float64 t64;
     float32 t32;
 
@@ -1019,20 +1030,23 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
 }
 
 void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
-                         void *vpm, void *vst, uint32_t desc)
+                         void *vpm, CPUARMState *env, uint32_t desc)
 {
     intptr_t row, col, oprsz = simd_maxsz(desc);
     uint32_t neg = simd_data(desc) * 0x80008000u;
     uint16_t *pn = vpn, *pm = vpm;
-    float_status fpst_odd, fpst_std;
+    float_status fpst_odd, fpst_std, fpst_f16;
 
     /*
-     * Make a copy of float_status because this operation does not
-     * update the cumulative fp exception status.  It also produces
-     * default nans.  Make a second copy with round-to-odd -- see above.
+     * Make copies of fp_status and fp_status_f16, because this operation
+     * does not update the cumulative fp exception status.  It also
+     * produces default NaNs. We also need a second copy of fp_status with
+     * round-to-odd -- see above.
      */
-    fpst_std = *(float_status *)vst;
+    fpst_f16 = env->vfp.fp_status_f16;
+    fpst_std = env->vfp.fp_status;
     set_default_nan_mode(true, &fpst_std);
+    set_default_nan_mode(true, &fpst_f16);
     fpst_odd = fpst_std;
     set_float_rounding_mode(float_round_to_odd, &fpst_odd);
 
@@ -1052,7 +1066,8 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
                         uint32_t m = *(uint32_t *)(vzm + H1_4(col));
 
                         m = f16mop_adj_pair(m, pcol, 0);
-                        *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd);
+                        *a = f16_dotadd(*a, n, m,
+                                        &fpst_f16, &fpst_std, &fpst_odd);
                     }
                     col += 4;
                     pcol >>= 4;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index a50a419..ae42dde 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -334,8 +334,29 @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz,
     return true;
 }
 
-TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a,
-           MO_32, FPST_FPCR_F16, gen_helper_sme_fmopa_h)
+static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
+                           gen_helper_gvec_5_ptr *fn)
+{
+    int svl = streaming_vec_reg_size(s);
+    uint32_t desc = simd_desc(svl, svl, a->sub);
+    TCGv_ptr za, zn, zm, pn, pm;
+
+    if (!sme_smza_enabled_check(s)) {
+        return true;
+    }
+
+    za = get_tile(s, esz, a->zad);
+    zn = vec_full_reg_ptr(s, a->zn);
+    zm = vec_full_reg_ptr(s, a->zm);
+    pn = pred_full_reg_ptr(s, a->pn);
+    pm = pred_full_reg_ptr(s, a->pm);
+
+    fn(za, zn, zm, pn, pm, tcg_env, tcg_constant_i32(desc));
+    return true;
+}
+
+TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a,
+           MO_32, gen_helper_sme_fmopa_h)
 TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
            MO_32, FPST_FPCR, gen_helper_sme_fmopa_s)
 TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
diff --git a/target/xtensa/exc_helper.c b/target/xtensa/exc_helper.c
index 0514c2c..ca629f0 100644
--- a/target/xtensa/exc_helper.c
+++ b/target/xtensa/exc_helper.c
@@ -171,7 +171,7 @@ static void handle_interrupt(CPUXtensaState *env)
 
         if (level > 1) {
             /* env->config->nlevel check should have ensured this */
-            assert(level < sizeof(env->config->interrupt_vector));
+            assert(level < ARRAY_SIZE(env->config->interrupt_vector));
 
             env->sregs[EPC1 + level - 1] = env->pc;
             env->sregs[EPS2 + level - 2] = env->sregs[PS];