Series comparison

The following changes since commit a97978bcc2d1f650c7d411428806e5b03082b8c7:

Merge remote-tracking branch 'remotes/dg-gitlab/tags/ppc-for-6.1-20210603' into staging (2021-06-03 10:00:35 +0100)

are available in the Git repository at:

https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210603

for you to fetch changes up to 1c861885894d840235954060050d240259f5340b:

tests/unit/test-vmstate: Assert that dup() and mkstemp() succeed (2021-06-03 16:43:27 +0100)

----------------------------------------------------------------
target-arm queue:
 * Some not-yet-enabled preliminaries for M-profile MVE support
 * Consistently use "Cortex-Axx", not "Cortex Axx" in docs, comments
 * docs: Fix installation of man pages with Sphinx 4.x
 * Mark LDS{MIN,MAX} as signed operations
 * Fix missing syndrome value for DAIF and PAC check exceptions
 * Implement BFloat16 extensions
 * Refactoring of hvf accelerator code in preparation for aarch64 support
 * Fix some coverity nits in test code

----------------------------------------------------------------
Alexander Graf (12):
      hvf: Move assert_hvf_ok() into common directory
      hvf: Move vcpu thread functions into common directory
      hvf: Move cpu functions into common directory
      hvf: Move hvf internal definitions into common header
      hvf: Make hvf_set_phys_mem() static
      hvf: Remove use of hv_uvaddr_t and hv_gpaddr_t
      hvf: Split out common code on vcpu init and destroy
      hvf: Use cpu_synchronize_state()
      hvf: Make synchronize functions static
      hvf: Remove hvf-accel-ops.h
      hvf: Introduce hvf vcpu struct
      hvf: Simplify post reset/init/loadvm hooks

Damien Goutte-Gattat (1):
      docs: Fix installation of man pages with Sphinx 4.x

Jamie Iles (4):
      target/arm: fix missing exception class
      target/arm: fold do_raise_exception into raise_exception
      target/arm: use raise_exception_ra for MTE check failure
      target/arm: use raise_exception_ra for stack limit exception

Peter Maydell (15):
      target/arm: Add isar feature check functions for MVE
      target/arm: Update feature checks for insns which are "MVE or FP"
      target/arm: Move fpsp/fpdp isar check into callers of do_vfp_2op_sp/dp
      target/arm: Add MVE check to VMOV_reg_sp and VMOV_reg_dp
      target/arm: Fix return values in fp_sysreg_checks()
      target/arm: Implement M-profile VPR register
      target/arm: Make FPSCR.LTPSIZE writable for MVE
      target/arm: Allow board models to specify initial NS VTOR
      arm: Consistently use "Cortex-Axx", not "Cortex Axx"
      tests/qtest/bios-tables-test: Check for dup2() failure
      tests/qtest/e1000e-test: Check qemu_recv() succeeded
      tests/qtest/hd-geo-test: Fix checks on mkstemp() return value
      tests/qtest/pflash-cfi02-test: Avoid potential integer overflow
      tests/qtest/tpm-tests: Remove unnecessary NULL checks
      tests/unit/test-vmstate: Assert that dup() and mkstemp() succeed

Richard Henderson (13):
      target/arm: Mark LDS{MIN,MAX} as signed operations
      target/arm: Add isar_feature_{aa32, aa64, aa64_sve}_bf16
      target/arm: Unify unallocated path in disas_fp_1src
      target/arm: Implement scalar float32 to bfloat16 conversion
      target/arm: Implement vector float32 to bfloat16 conversion
      softfpu: Add float_round_to_odd_inf
      target/arm: Implement bfloat16 dot product (vector)
      target/arm: Implement bfloat16 dot product (indexed)
      target/arm: Implement bfloat16 matrix multiply accumulate
      target/arm: Implement bfloat widening fma (vector)
      target/arm: Implement bfloat widening fma (indexed)
      linux-user/aarch64: Enable hwcap bits for bfloat16
      target/arm: Enable BFloat16 extensions

Add the isar feature check functions we will need for v8.1M MVE:
 * a check for MVE present: this corresponds to the pseudocode's
   CheckDecodeFaults(ExtType_Mve)
 * a check for the optional floating-point part of MVE: this
   corresponds to CheckDecodeFaults(ExtType_MveFp)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-2-peter.maydell@linaro.org
---
 target/arm/cpu.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

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 @@ static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id)
     }
 }
 
+static inline bool isar_feature_aa32_mve(const ARMISARegisters *id)
+{
+    /*
+     * Return true if MVE is supported (either integer or floating point).
+     * We must check for M-profile as the MVFR1 field means something
+     * else for A-profile.
+     */
+    return isar_feature_aa32_mprofile(id) &&
+        FIELD_EX32(id->mvfr1, MVFR1, MVE) > 0;
+}
+
+static inline bool isar_feature_aa32_mve_fp(const ARMISARegisters *id)
+{
+    /*
+     * Return true if MVE is supported (either integer or floating point).
+     * We must check for M-profile as the MVFR1 field means something
+     * else for A-profile.
+     */
+    return isar_feature_aa32_mprofile(id) &&
+        FIELD_EX32(id->mvfr1, MVFR1, MVE) >= 2;
+}
+
 static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id)
 {
     /*
-- 
2.20.1

Some v8M instructions are present if either the floating point
extension or MVE is implemented.  Update our implementation of them
to check for MVE as well as for FP.

This is all the insns which use CheckDecodeFaults(ExtType_MveOrFp) or
CheckDecodeFaults(ExtType_MveOrDpFp) in their pseudocode, which are
essentially the loads and stores, moves and sysreg accesses, except
for VMOV_reg_sp and VMOV_reg_dp, which we handle in subsequent
patches because they need a refactor to provide a place to put the
new MVE check.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-3-peter.maydell@linaro.org
---
 target/arm/translate-vfp.c | 48 +++++++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 19 deletions(-)

diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-vfp.c
+++ b/target/arm/translate-vfp.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a)
     /* VMOV scalar to general purpose register */
     TCGv_i32 tmp;
 
-    /* SIZE == MO_32 is a VFP instruction; otherwise NEON.  */
-    if (a->size == MO_32
-        ? !dc_isar_feature(aa32_fpsp_v2, s)
-        : !arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
+    /*
+     * SIZE == MO_32 is a VFP instruction; otherwise NEON. MVE has
+     * all sizes, whether the CPU has fp or not.
+     */
+    if (!dc_isar_feature(aa32_mve, s)) {
+        if (a->size == MO_32
+            ? !dc_isar_feature(aa32_fpsp_v2, s)
+            : !arm_dc_feature(s, ARM_FEATURE_NEON)) {
+            return false;
+        }
     }
 
     /* UNDEF accesses to D16-D31 if they don't exist */
@@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a)
     /* VMOV general purpose register to scalar */
     TCGv_i32 tmp;
 
-    /* SIZE == MO_32 is a VFP instruction; otherwise NEON.  */
-    if (a->size == MO_32
-        ? !dc_isar_feature(aa32_fpsp_v2, s)
-        : !arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
+    /*
+     * SIZE == MO_32 is a VFP instruction; otherwise NEON. MVE has
+     * all sizes, whether the CPU has fp or not.
+     */
+    if (!dc_isar_feature(aa32_mve, s)) {
+        if (a->size == MO_32
+            ? !dc_isar_feature(aa32_fpsp_v2, s)
+            : !arm_dc_feature(s, ARM_FEATURE_NEON)) {
+            return false;
+        }
     }
 
     /* UNDEF accesses to D16-D31 if they don't exist */
@@ -XXX,XX +XXX,XX @@ typedef enum FPSysRegCheckResult {
 
 static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno)
 {
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return FPSysRegCheckFailed;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a)
 {
     TCGv_i32 tmp;
 
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a)
 {
     TCGv_i32 tmp;
 
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a)
      * floating point register.  Note that this does not require support
      * for double precision arithmetic.
      */
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a)
     uint32_t offset;
     TCGv_i32 addr, tmp;
 
-    if (!dc_isar_feature(aa32_fp16_arith, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a)
     uint32_t offset;
     TCGv_i32 addr, tmp;
 
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a)
     TCGv_i64 tmp;
 
     /* Note that this does not require support for double arithmetic.  */
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a)
     TCGv_i32 addr, tmp;
     int i, n;
 
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a)
     int i, n;
 
     /* Note that this does not require support for double arithmetic.  */
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
+    if (!dc_isar_feature(aa32_fpsp_v2, s) && !dc_isar_feature(aa32_mve, s)) {
         return false;
     }
 
-- 
2.20.1

The do_vfp_2op_sp() and do_vfp_2op_dp() functions currently check
whether floating point is supported via the aa32_fpdp_v2 and
aa32_fpsp_v2 isar checks.  For v8.1M MVE support, the VMOV_reg trans
functions (but not any of the others) need to update this to also
allow the insn if MVE is implemented.  Move the check out of the do_
function and into its callsites (which are all implemented via the
DO_VFP_2OP macro), so we have a place to change the check for the
VMOV insns.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-4-peter.maydell@linaro.org
---
 target/arm/translate-vfp.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-vfp.c
+++ b/target/arm/translate-vfp.c
@@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
     int veclen = s->vec_len;
     TCGv_i32 f0, fd;
 
-    if (!dc_isar_feature(aa32_fpsp_v2, s)) {
-        return false;
-    }
+    /* Note that the caller must check the aa32_fpsp_v2 feature. */
 
     if (!dc_isar_feature(aa32_fpshvec, s) &&
         (veclen != 0 || s->vec_stride != 0)) {
@@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
      */
     TCGv_i32 f0;
 
+    /* Note that the caller must check the aa32_fp16_arith feature */
+
     if (!dc_isar_feature(aa32_fp16_arith, s)) {
         return false;
     }
@@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm)
     int veclen = s->vec_len;
     TCGv_i64 f0, fd;
 
-    if (!dc_isar_feature(aa32_fpdp_v2, s)) {
-        return false;
-    }
+    /* Note that the caller must check the aa32_fpdp_v2 feature. */
 
     /* UNDEF accesses to D16-D31 if they don't exist */
     if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vm) & 0x10)) {
@@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a)
     return true;
 }
 
-#define DO_VFP_2OP(INSN, PREC, FN)                              \
+#define DO_VFP_2OP(INSN, PREC, FN, CHECK)                       \
     static bool trans_##INSN##_##PREC(DisasContext *s,          \
                                       arg_##INSN##_##PREC *a)   \
     {                                                           \
+        if (!dc_isar_feature(CHECK, s)) {                       \
+            return false;                                       \
+        }                                                       \
         return do_vfp_2op_##PREC(s, FN, a->vd, a->vm);          \
     }
 
-DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32)
-DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64)
+DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32, aa32_fpsp_v2)
+DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64, aa32_fpdp_v2)
 
-DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh)
-DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss)
-DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd)
+DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh, aa32_fp16_arith)
+DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss, aa32_fpsp_v2)
+DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd, aa32_fpdp_v2)
 
-DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh)
-DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs)
-DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd)
+DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh, aa32_fp16_arith)
+DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs, aa32_fpsp_v2)
+DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd, aa32_fpdp_v2)
 
 static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm)
 {
@@ -XXX,XX +XXX,XX @@ static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm)
     gen_helper_vfp_sqrtd(vd, vm, cpu_env);
 }
 
-DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp)
-DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp)
-DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp)
+DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp, aa32_fp16_arith)
+DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp, aa32_fpsp_v2)
+DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp, aa32_fpdp_v2)
 
 static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a)
 {
-- 
2.20.1

Split out the handling of VMOV_reg_sp and VMOV_reg_dp so that we can
permit the insns if either FP or MVE are present.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-5-peter.maydell@linaro.org
---
 target/arm/translate-vfp.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

The fp_sysreg_checks() function is supposed to be returning an
FPSysRegCheckResult, which is an enum with three possible values.
However, three places in the function "return false" (a hangover from
a previous iteration of the design where the function just returned a
bool).  Make these return FPSysRegCheckFailed instead (for no
functional change, since both false and FPSysRegCheckFailed are
zero).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-6-peter.maydell@linaro.org
---
 target/arm/translate-vfp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-vfp.c
+++ b/target/arm/translate-vfp.c
@@ -XXX,XX +XXX,XX @@ static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno)
         break;
     case ARM_VFP_FPSCR_NZCVQC:
         if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
-            return false;
+            return FPSysRegCheckFailed;
         }
         break;
     case ARM_VFP_FPCXT_S:
     case ARM_VFP_FPCXT_NS:
         if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
-            return false;
+            return FPSysRegCheckFailed;
         }
         if (!s->v8m_secure) {
-            return false;
+            return FPSysRegCheckFailed;
         }
         break;
     default:
-- 
2.20.1

If MVE is implemented for an M-profile CPU then it has a VPR
register, which tracks predication information.

Implement the read and write handling of this register, and
the migration of its state.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-7-peter.maydell@linaro.org
---
 target/arm/cpu.h           |  6 ++++++
 target/arm/machine.c       | 19 +++++++++++++++++++
 target/arm/translate-vfp.c | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 63 insertions(+)

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 @@ typedef struct CPUARMState {
         uint32_t cpacr[M_REG_NUM_BANKS];
         uint32_t nsacr;
         int ltpsize;
+        uint32_t vpr;
     } v7m;
 
     /* Information associated with an exception about to be taken:
@@ -XXX,XX +XXX,XX @@ FIELD(V7M_FPCCR, ASPEN, 31, 1)
      R_V7M_FPCCR_UFRDY_MASK |                   \
      R_V7M_FPCCR_ASPEN_MASK)
 
+/* v7M VPR bits */
+FIELD(V7M_VPR, P0, 0, 16)
+FIELD(V7M_VPR, MASK01, 16, 4)
+FIELD(V7M_VPR, MASK23, 20, 4)
+
 /*
  * System register ID fields.
  */
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 const VMStateDescription vmstate_m_fp = {
     }
 };
 
+static bool mve_needed(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    return cpu_isar_feature(aa32_mve, cpu);
+}
+
+static const VMStateDescription vmstate_m_mve = {
+    .name = "cpu/m/mve",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = mve_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(env.v7m.vpr, ARMCPU),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 static const VMStateDescription vmstate_m = {
     .name = "cpu/m",
     .version_id = 4,
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_m = {
         &vmstate_m_other_sp,
         &vmstate_m_v8m,
         &vmstate_m_fp,
+        &vmstate_m_mve,
         NULL
     }
 };
diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-vfp.c
+++ b/target/arm/translate-vfp.c
@@ -XXX,XX +XXX,XX @@ static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno)
             return FPSysRegCheckFailed;
         }
         break;
+    case ARM_VFP_VPR:
+    case ARM_VFP_P0:
+        if (!dc_isar_feature(aa32_mve, s)) {
+            return FPSysRegCheckFailed;
+        }
+        break;
     default:
         return FPSysRegCheckFailed;
     }
@@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno,
         tcg_temp_free_i32(sfpa);
         break;
     }
+    case ARM_VFP_VPR:
+        /* Behaves as NOP if not privileged */
+        if (IS_USER(s)) {
+            break;
+        }
+        tmp = loadfn(s, opaque);
+        store_cpu_field(tmp, v7m.vpr);
+        break;
+    case ARM_VFP_P0:
+    {
+        TCGv_i32 vpr;
+        tmp = loadfn(s, opaque);
+        vpr = load_cpu_field(v7m.vpr);
+        tcg_gen_deposit_i32(vpr, vpr, tmp,
+                            R_V7M_VPR_P0_SHIFT, R_V7M_VPR_P0_LENGTH);
+        store_cpu_field(vpr, v7m.vpr);
+        tcg_temp_free_i32(tmp);
+        break;
+    }
     default:
         g_assert_not_reached();
     }
@@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno,
         tcg_temp_free_i32(fpscr);
         break;
     }
+    case ARM_VFP_VPR:
+        /* Behaves as NOP if not privileged */
+        if (IS_USER(s)) {
+            break;
+        }
+        tmp = load_cpu_field(v7m.vpr);
+        storefn(s, opaque, tmp);
+        break;
+    case ARM_VFP_P0:
+        tmp = load_cpu_field(v7m.vpr);
+        tcg_gen_extract_i32(tmp, tmp, R_V7M_VPR_P0_SHIFT, R_V7M_VPR_P0_LENGTH);
+        storefn(s, opaque, tmp);
+        break;
     default:
         g_assert_not_reached();
     }
-- 
2.20.1

The M-profile FPSCR has an LTPSIZE field, but if MVE is not
implemented it is read-only and always reads as 4; this is how QEMU
currently handles it.

Make the field writable when MVE is implemented.

We can safely add the field to the MVE migration struct because
currently no CPUs enable MVE and so the migration struct is never
used.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-8-peter.maydell@linaro.org
---
 target/arm/cpu.h        | 3 ++-
 target/arm/machine.c    | 1 +
 target/arm/vfp_helper.c | 9 ++++++---
 3 files changed, 9 insertions(+), 4 deletions(-)

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 @@ typedef struct CPUARMState {
         uint32_t fpdscr[M_REG_NUM_BANKS];
         uint32_t cpacr[M_REG_NUM_BANKS];
         uint32_t nsacr;
-        int ltpsize;
+        uint32_t ltpsize;
         uint32_t vpr;
     } v7m;
 
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val);
 
 #define FPCR_LTPSIZE_SHIFT 16   /* LTPSIZE, M-profile only */
 #define FPCR_LTPSIZE_MASK (7 << FPCR_LTPSIZE_SHIFT)
+#define FPCR_LTPSIZE_LENGTH 3
 
 #define FPCR_NZCV_MASK (FPCR_N | FPCR_Z | FPCR_C | FPCR_V)
 #define FPCR_NZCVQC_MASK (FPCR_NZCV_MASK | FPCR_QC)
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 const VMStateDescription vmstate_m_mve = {
     .needed = mve_needed,
     .fields = (VMStateField[]) {
         VMSTATE_UINT32(env.v7m.vpr, ARMCPU),
+        VMSTATE_UINT32(env.v7m.ltpsize, ARMCPU),
         VMSTATE_END_OF_LIST()
     },
 };
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t vfp_get_fpscr(CPUARMState *env)
 
 void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val)
 {
+    ARMCPU *cpu = env_archcpu(env);
+
     /* When ARMv8.2-FP16 is not supported, FZ16 is RES0.  */
-    if (!cpu_isar_feature(any_fp16, env_archcpu(env))) {
+    if (!cpu_isar_feature(any_fp16, cpu)) {
         val &= ~FPCR_FZ16;
     }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val)
          * because in v7A no-short-vector-support cores still had to
          * allow Stride/Len to be written with the only effect that
          * some insns are required to UNDEF if the guest sets them.
-         *
-         * TODO: if M-profile MVE implemented, set LTPSIZE.
          */
         env->vfp.vec_len = extract32(val, 16, 3);
         env->vfp.vec_stride = extract32(val, 20, 2);
+    } else if (cpu_isar_feature(aa32_mve, cpu)) {
+        env->v7m.ltpsize = extract32(val, FPCR_LTPSIZE_SHIFT,
+                                     FPCR_LTPSIZE_LENGTH);
     }
 
     if (arm_feature(env, ARM_FEATURE_NEON)) {
-- 
2.20.1

Currently we allow board models to specify the initial value of the
Secure VTOR register, using an init-svtor property on the TYPE_ARMV7M
object which is plumbed through to the CPU.  Allow board models to
also specify the initial value of the Non-secure VTOR via a similar
init-nsvtor property.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210520152840.24453-10-peter.maydell@linaro.org
---
 include/hw/arm/armv7m.h |  2 ++
 target/arm/cpu.h        |  2 ++
 hw/arm/armv7m.c         |  7 +++++++
 target/arm/cpu.c        | 10 ++++++++++
 4 files changed, 21 insertions(+)

diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/armv7m.h
+++ b/include/hw/arm/armv7m.h
@@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MState, ARMV7M)
  *   devices will be automatically layered on top of this view.)
  * + Property "idau": IDAU interface (forwarded to CPU object)
  * + Property "init-svtor": secure VTOR reset value (forwarded to CPU object)
+ * + Property "init-nsvtor": non-secure VTOR reset value (forwarded to CPU object)
  * + Property "vfp": enable VFP (forwarded to CPU object)
  * + Property "dsp": enable DSP (forwarded to CPU object)
  * + Property "enable-bitband": expose bitbanded IO
@@ -XXX,XX +XXX,XX @@ struct ARMv7MState {
     MemoryRegion *board_memory;
     Object *idau;
     uint32_t init_svtor;
+    uint32_t init_nsvtor;
     bool enable_bitband;
     bool start_powered_off;
     bool vfp;
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 ARMCPU {
 
     /* For v8M, initial value of the Secure VTOR */
     uint32_t init_svtor;
+    /* For v8M, initial value of the Non-secure VTOR */
+    uint32_t init_nsvtor;
 
     /* [QEMU_]KVM_ARM_TARGET_* constant for this CPU, or
      * QEMU_KVM_ARM_TARGET_NONE if the kernel doesn't support this CPU type.
diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/armv7m.c
+++ b/hw/arm/armv7m.c
@@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp)
             return;
         }
     }
+    if (object_property_find(OBJECT(s->cpu), "init-nsvtor")) {
+        if (!object_property_set_uint(OBJECT(s->cpu), "init-nsvtor",
+                                      s->init_nsvtor, errp)) {
+            return;
+        }
+    }
     if (object_property_find(OBJECT(s->cpu), "start-powered-off")) {
         if (!object_property_set_bool(OBJECT(s->cpu), "start-powered-off",
                                       s->start_powered_off, errp)) {
@@ -XXX,XX +XXX,XX @@ static Property armv7m_properties[] = {
                      MemoryRegion *),
     DEFINE_PROP_LINK("idau", ARMv7MState, idau, TYPE_IDAU_INTERFACE, Object *),
     DEFINE_PROP_UINT32("init-svtor", ARMv7MState, init_svtor, 0),
+    DEFINE_PROP_UINT32("init-nsvtor", ARMv7MState, init_nsvtor, 0),
     DEFINE_PROP_BOOL("enable-bitband", ARMv7MState, enable_bitband, false),
     DEFINE_PROP_BOOL("start-powered-off", ARMv7MState, start_powered_off,
                      false),
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 arm_cpu_reset(DeviceState *dev)
         env->regs[14] = 0xffffffff;
 
         env->v7m.vecbase[M_REG_S] = cpu->init_svtor & 0xffffff80;
+        env->v7m.vecbase[M_REG_NS] = cpu->init_nsvtor & 0xffffff80;
 
         /* Load the initial SP and PC from offset 0 and 4 in the vector table */
         vecbase = env->v7m.vecbase[env->v7m.secure];
@@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj)
                                        &cpu->init_svtor,
                                        OBJ_PROP_FLAG_READWRITE);
     }
+    if (arm_feature(&cpu->env, ARM_FEATURE_M)) {
+        /*
+         * Initial value of the NS VTOR (for cores without the Security
+         * extension, this is the only VTOR)
+         */
+        object_property_add_uint32_ptr(obj, "init-nsvtor",
+                                       &cpu->init_nsvtor,
+                                       OBJ_PROP_FLAG_READWRITE);
+    }
 
     qdev_property_add_static(DEVICE(obj), &arm_cpu_cfgend_property);
 
-- 
2.20.1

The official punctuation for Arm CPU names uses a hyphen, like
"Cortex-A9". We mostly follow this, but in a few places usage
without the hyphen has crept in. Fix those so we consistently
use the same way of writing the CPU name.

This commit was created with:
  git grep -z -l 'Cortex ' | xargs -0 sed -i 's/Cortex /Cortex-/'

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20210527095152.10968-1-peter.maydell@linaro.org
---
 docs/system/arm/aspeed.rst    | 4 ++--
 docs/system/arm/nuvoton.rst   | 6 +++---
 docs/system/arm/sabrelite.rst | 2 +-
 include/hw/arm/allwinner-h3.h | 2 +-
 hw/arm/aspeed.c               | 6 +++---
 hw/arm/mcimx6ul-evk.c         | 2 +-
 hw/arm/mcimx7d-sabre.c        | 2 +-
 hw/arm/npcm7xx_boards.c       | 4 ++--
 hw/arm/sabrelite.c            | 2 +-
 hw/misc/npcm7xx_clk.c         | 2 +-
 10 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/aspeed.rst
+++ b/docs/system/arm/aspeed.rst
@@ -XXX,XX +XXX,XX @@ The QEMU Aspeed machines model BMCs of various OpenPOWER systems and
 Aspeed evaluation boards. They are based on different releases of the
 Aspeed SoC : the AST2400 integrating an ARM926EJ-S CPU (400MHz), the
 AST2500 with an ARM1176JZS CPU (800MHz) and more recently the AST2600
-with dual cores ARM Cortex A7 CPUs (1.2GHz).
+with dual cores ARM Cortex-A7 CPUs (1.2GHz).
 
 The SoC comes with RAM, Gigabit ethernet, USB, SD/MMC, USB, SPI, I2C,
 etc.
@@ -XXX,XX +XXX,XX @@ AST2500 SoC based machines :
 
 AST2600 SoC based machines :
 
-- ``ast2600-evb``          Aspeed AST2600 Evaluation board (Cortex A7)
+- ``ast2600-evb``          Aspeed AST2600 Evaluation board (Cortex-A7)
 - ``tacoma-bmc``           OpenPOWER Witherspoon POWER9 AST2600 BMC
 
 Supported devices
diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/nuvoton.rst
+++ b/docs/system/arm/nuvoton.rst
@@ -XXX,XX +XXX,XX @@ Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``)
 
 The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are
 designed to be used as Baseboard Management Controllers (BMCs) in various
-servers. They all feature one or two ARM Cortex A9 CPU cores, as well as an
+servers. They all feature one or two ARM Cortex-A9 CPU cores, as well as an
 assortment of peripherals targeted for either Enterprise or Data Center /
 Hyperscale applications. The former is a superset of the latter, so NPCM750 has
 all the peripherals of NPCM730 and more.
 
 .. _Nuvoton iBMC: https://www.nuvoton.com/products/cloud-computing/ibmc/
 
-The NPCM750 SoC has two Cortex A9 cores and is targeted for the Enterprise
+The NPCM750 SoC has two Cortex-A9 cores and is targeted for the Enterprise
 segment. The following machines are based on this chip :
 
 - ``npcm750-evb``       Nuvoton NPCM750 Evaluation board
 
-The NPCM730 SoC has two Cortex A9 cores and is targeted for Data Center and
+The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and
 Hyperscale applications. The following machines are based on this chip :
 
 - ``quanta-gsj``        Quanta GSJ server BMC
diff --git a/docs/system/arm/sabrelite.rst b/docs/system/arm/sabrelite.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/system/arm/sabrelite.rst
+++ b/docs/system/arm/sabrelite.rst
@@ -XXX,XX +XXX,XX @@ Supported devices
 
 The SABRE Lite machine supports the following devices:
 
- * Up to 4 Cortex A9 cores
+ * Up to 4 Cortex-A9 cores
  * Generic Interrupt Controller
  * 1 Clock Controller Module
  * 1 System Reset Controller
diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/arm/allwinner-h3.h
+++ b/include/hw/arm/allwinner-h3.h
@@ -XXX,XX +XXX,XX @@
  */
 
 /*
- * The Allwinner H3 is a System on Chip containing four ARM Cortex A7
+ * The Allwinner H3 is a System on Chip containing four ARM Cortex-A7
  * processor cores. Features and specifications include DDR2/DDR3 memory,
  * SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and
  * various I/O modules.
diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/aspeed.c
+++ b/hw/arm/aspeed.c
@@ -XXX,XX +XXX,XX @@ static void aspeed_machine_ast2600_evb_class_init(ObjectClass *oc, void *data)
     MachineClass *mc = MACHINE_CLASS(oc);
     AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc);
 
-    mc->desc       = "Aspeed AST2600 EVB (Cortex A7)";
+    mc->desc       = "Aspeed AST2600 EVB (Cortex-A7)";
     amc->soc_name  = "ast2600-a1";
     amc->hw_strap1 = AST2600_EVB_HW_STRAP1;
     amc->hw_strap2 = AST2600_EVB_HW_STRAP2;
@@ -XXX,XX +XXX,XX @@ static void aspeed_machine_tacoma_class_init(ObjectClass *oc, void *data)
     MachineClass *mc = MACHINE_CLASS(oc);
     AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc);
 
-    mc->desc       = "OpenPOWER Tacoma BMC (Cortex A7)";
+    mc->desc       = "OpenPOWER Tacoma BMC (Cortex-A7)";
     amc->soc_name  = "ast2600-a1";
     amc->hw_strap1 = TACOMA_BMC_HW_STRAP1;
     amc->hw_strap2 = TACOMA_BMC_HW_STRAP2;
@@ -XXX,XX +XXX,XX @@ static void aspeed_machine_rainier_class_init(ObjectClass *oc, void *data)
     MachineClass *mc = MACHINE_CLASS(oc);
     AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc);
 
-    mc->desc       = "IBM Rainier BMC (Cortex A7)";
+    mc->desc       = "IBM Rainier BMC (Cortex-A7)";
     amc->soc_name  = "ast2600-a1";
     amc->hw_strap1 = RAINIER_BMC_HW_STRAP1;
     amc->hw_strap2 = RAINIER_BMC_HW_STRAP2;
diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/mcimx6ul-evk.c
+++ b/hw/arm/mcimx6ul-evk.c
@@ -XXX,XX +XXX,XX @@ static void mcimx6ul_evk_init(MachineState *machine)
 
 static void mcimx6ul_evk_machine_init(MachineClass *mc)
 {
-    mc->desc = "Freescale i.MX6UL Evaluation Kit (Cortex A7)";
+    mc->desc = "Freescale i.MX6UL Evaluation Kit (Cortex-A7)";
     mc->init = mcimx6ul_evk_init;
     mc->max_cpus = FSL_IMX6UL_NUM_CPUS;
     mc->default_ram_id = "mcimx6ul-evk.ram";
diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/mcimx7d-sabre.c
+++ b/hw/arm/mcimx7d-sabre.c
@@ -XXX,XX +XXX,XX @@ static void mcimx7d_sabre_init(MachineState *machine)
 
 static void mcimx7d_sabre_machine_init(MachineClass *mc)
 {
-    mc->desc = "Freescale i.MX7 DUAL SABRE (Cortex A7)";
+    mc->desc = "Freescale i.MX7 DUAL SABRE (Cortex-A7)";
     mc->init = mcimx7d_sabre_init;
     mc->max_cpus = FSL_IMX7_NUM_CPUS;
     mc->default_ram_id = "mcimx7d-sabre.ram";
diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/npcm7xx_boards.c
+++ b/hw/arm/npcm7xx_boards.c
@@ -XXX,XX +XXX,XX @@ static void npcm750_evb_machine_class_init(ObjectClass *oc, void *data)
 
     npcm7xx_set_soc_type(nmc, TYPE_NPCM750);
 
-    mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex A9)";
+    mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex-A9)";
     mc->init = npcm750_evb_init;
     mc->default_ram_size = 512 * MiB;
 };
@@ -XXX,XX +XXX,XX @@ static void gsj_machine_class_init(ObjectClass *oc, void *data)
 
     npcm7xx_set_soc_type(nmc, TYPE_NPCM730);
 
-    mc->desc = "Quanta GSJ (Cortex A9)";
+    mc->desc = "Quanta GSJ (Cortex-A9)";
     mc->init = quanta_gsj_init;
     mc->default_ram_size = 512 * MiB;
 };
diff --git a/hw/arm/sabrelite.c b/hw/arm/sabrelite.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/sabrelite.c
+++ b/hw/arm/sabrelite.c
@@ -XXX,XX +XXX,XX @@ static void sabrelite_init(MachineState *machine)
 
 static void sabrelite_machine_init(MachineClass *mc)
 {
-    mc->desc = "Freescale i.MX6 Quad SABRE Lite Board (Cortex A9)";
+    mc->desc = "Freescale i.MX6 Quad SABRE Lite Board (Cortex-A9)";
     mc->init = sabrelite_init;
     mc->max_cpus = FSL_IMX6_NUM_CPUS;
     mc->ignore_memory_transaction_failures = true;
diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/misc/npcm7xx_clk.c
+++ b/hw/misc/npcm7xx_clk.c
@@ -XXX,XX +XXX,XX @@
 #define NPCM7XX_CLOCK_REF_HZ            (25000000)
 
 /* Register Field Definitions */
-#define NPCM7XX_CLK_WDRCR_CA9C  BIT(0) /* Cortex A9 Cores */
+#define NPCM7XX_CLK_WDRCR_CA9C  BIT(0) /* Cortex-A9 Cores */
 
 #define PLLCON_LOKI     BIT(31)
 #define PLLCON_LOKS     BIT(30)
-- 
2.20.1

From: Damien Goutte-Gattat <dgouttegattat@incenp.org>

The 4.x branch of Sphinx introduces a breaking change, as generated man
pages are now written to subdirectories corresponding to the manual
section they belong to. This results in `make install` erroring out when
attempting to install the man pages, because they are not where it
expects to find them.

This patch restores the behavior of Sphinx 3.x regarding man pages.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/256
Signed-off-by: Damien Goutte-Gattat <dgouttegattat@incenp.org>
Message-id: 20210503161422.15028-1-dgouttegattat@incenp.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/conf.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/conf.py b/docs/conf.py
index XXXXXXX..XXXXXXX 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -XXX,XX +XXX,XX @@
      ['Stefan Hajnoczi <stefanha@redhat.com>',
       'Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>'], 1),
 ]
+man_make_section_directory = False
 
 # -- Options for Texinfo output -------------------------------------------
 
-- 
2.20.1

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

The operands to tcg_gen_atomic_fetch_s{min,max}_i64 must
be signed, so that the inputs are properly extended.
Zero extend the result afterward, as needed.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/364
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20210602020720.47679-1-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/translate-a64.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn,
     int o3_opc = extract32(insn, 12, 4);
     bool r = extract32(insn, 22, 1);
     bool a = extract32(insn, 23, 1);
-    TCGv_i64 tcg_rs, clean_addr;
+    TCGv_i64 tcg_rs, tcg_rt, clean_addr;
     AtomicThreeOpFn *fn = NULL;
+    MemOp mop = s->be_data | size | MO_ALIGN;
 
     if (is_vector || !dc_isar_feature(aa64_atomics, s)) {
         unallocated_encoding(s);
@@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn,
         break;
     case 004: /* LDSMAX */
         fn = tcg_gen_atomic_fetch_smax_i64;
+        mop |= MO_SIGN;
         break;
     case 005: /* LDSMIN */
         fn = tcg_gen_atomic_fetch_smin_i64;
+        mop |= MO_SIGN;
         break;
     case 006: /* LDUMAX */
         fn = tcg_gen_atomic_fetch_umax_i64;
@@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn,
     }
 
     tcg_rs = read_cpu_reg(s, rs, true);
+    tcg_rt = cpu_reg(s, rt);
 
     if (o3_opc == 1) { /* LDCLR */
         tcg_gen_not_i64(tcg_rs, tcg_rs);
@@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn,
     /* The tcg atomic primitives are all full barriers.  Therefore we
      * can ignore the Acquire and Release bits of this instruction.
      */
-    fn(cpu_reg(s, rt), clean_addr, tcg_rs, get_mem_index(s),
-       s->be_data | size | MO_ALIGN);
+    fn(tcg_rt, clean_addr, tcg_rs, get_mem_index(s), mop);
+
+    if ((mop & MO_SIGN) && size != MO_64) {
+        tcg_gen_ext32u_i64(tcg_rt, tcg_rt);
+    }
 }
 
 /*
-- 
2.20.1

From: Jamie Iles <jamie@nuviainc.com>

The DAIF and PAC checks used raise_exception_ra to raise an exception
and unwind CPU state but raise_exception_ra is currently designed for
handling data aborts as the syndrome is partially precomputed and
encoded in the TB and then merged in merge_syn_data_abort when handling
the data abort.  Using raise_exception_ra for DAIF and PAC checks
results in an empty syndrome being retrieved from data[2] in
restore_state_to_opc and setting ESR to 0.  This manifested as:

kvm [571]: Unknown exception class: esr: 0x000000 –
  Unknown/Uncategorized

when launching a KVM guest when the host qemu used a CPU supporting
EL2+pointer authentication and enabling pointer authentication in the
guest.

Rework raise_exception_ra such that the state is restored before raising
the exception so that the exception is not clobbered by
restore_state_to_opc.

Fixes: 0d43e1a2d29a ("target/arm: Add PAuth helpers")
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jamie Iles <jamie@nuviainc.com>
[PMM: added comment]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/op_helper.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -XXX,XX +XXX,XX @@ void raise_exception(CPUARMState *env, uint32_t excp,
 void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome,
                         uint32_t target_el, uintptr_t ra)
 {
-    CPUState *cs = do_raise_exception(env, excp, syndrome, target_el);
-    cpu_loop_exit_restore(cs, ra);
+    CPUState *cs = env_cpu(env);
+
+    /*
+     * restore_state_to_opc() will set env->exception.syndrome, so
+     * we must restore CPU state here before setting the syndrome
+     * the caller passed us, and cannot use cpu_loop_exit_restore().
+     */
+    cpu_restore_state(cs, ra, true);
+    raise_exception(env, excp, syndrome, target_el);
 }
 
 uint64_t HELPER(neon_tbl)(CPUARMState *env, uint32_t desc,
-- 
2.20.1

From: Jamie Iles <jamie@nuviainc.com>

Now that there are no other users of do_raise_exception, fold it into
raise_exception.

Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jamie Iles <jamie@nuviainc.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/op_helper.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -XXX,XX +XXX,XX @@
 #define SIGNBIT (uint32_t)0x80000000
 #define SIGNBIT64 ((uint64_t)1 << 63)
 
-static CPUState *do_raise_exception(CPUARMState *env, uint32_t excp,
-                                    uint32_t syndrome, uint32_t target_el)
+void raise_exception(CPUARMState *env, uint32_t excp,
+                     uint32_t syndrome, uint32_t target_el)
 {
     CPUState *cs = env_cpu(env);
 
@@ -XXX,XX +XXX,XX @@ static CPUState *do_raise_exception(CPUARMState *env, uint32_t excp,
     cs->exception_index = excp;
     env->exception.syndrome = syndrome;
     env->exception.target_el = target_el;
-
-    return cs;
-}
-
-void raise_exception(CPUARMState *env, uint32_t excp,
-                     uint32_t syndrome, uint32_t target_el)
-{
-    CPUState *cs = do_raise_exception(env, excp, syndrome, target_el);
     cpu_loop_exit(cs);
 }
 
-- 
2.20.1

From: Jamie Iles <jamie@nuviainc.com>

Now that raise_exception_ra restores the state before raising the
exception we can use restore_exception_ra to perform the state restore +
exception raising without clobbering the syndrome.

Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jamie Iles <jamie@nuviainc.com>
[PMM: Keep the one line of the comment that is still relevant]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/mte_helper.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/mte_helper.c
+++ b/target/arm/mte_helper.c
@@ -XXX,XX +XXX,XX @@ static void mte_check_fail(CPUARMState *env, uint32_t desc,
 
     switch (tcf) {
     case 1:
-        /*
-         * Tag check fail causes a synchronous exception.
-         *
-         * In restore_state_to_opc, we set the exception syndrome
-         * for the load or store operation.  Unwind first so we
-         * may overwrite that with the syndrome for the tag check.
-         */
-        cpu_restore_state(env_cpu(env), ra, true);
+        /* Tag check fail causes a synchronous exception. */
         env->exception.vaddress = dirty_ptr;
 
         is_write = FIELD_EX32(desc, MTEDESC, WRITE);
         syn = syn_data_abort_no_iss(arm_current_el(env) != 0, 0, 0, 0, 0,
                                     is_write, 0x11);
-        raise_exception(env, EXCP_DATA_ABORT, syn, exception_target_el(env));
+        raise_exception_ra(env, EXCP_DATA_ABORT, syn,
+                           exception_target_el(env), ra);
         /* noreturn, but fall through to the assert anyway */
 
     case 0:
-- 
2.20.1

From: Jamie Iles <jamie@nuviainc.com>

The sequence cpu_restore_state() + raise_exception() is equivalent to
raise_exception_ra(), so use that instead.  (In this case we never
cared about the syndrome value, because M-profile doesn't use the
syndrome; the old code was just written unnecessarily awkwardly.)

Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Jamie Iles <jamie@nuviainc.com>
[PMM: Retain edited version of comment; rewrite commit message]
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/m_helper.c  | 5 +----
 target/arm/op_helper.c | 9 +++------
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/m_helper.c
+++ b/target/arm/m_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val)
             limit = is_psp ? env->v7m.psplim[false] : env->v7m.msplim[false];
 
             if (val < limit) {
-                CPUState *cs = env_cpu(env);
-
-                cpu_restore_state(cs, GETPC(), true);
-                raise_exception(env, EXCP_STKOF, 0, 1);
+                raise_exception_ra(env, EXCP_STKOF, 0, 1, GETPC());
             }
 
             if (is_psp) {
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/op_helper.c
+++ b/target/arm/op_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue)
      * raising an exception if the limit is breached.
      */
     if (newvalue < v7m_sp_limit(env)) {
-        CPUState *cs = env_cpu(env);
-
         /*
          * Stack limit exceptions are a rare case, so rather than syncing
-         * PC/condbits before the call, we use cpu_restore_state() to
-         * get them right before raising the exception.
+         * PC/condbits before the call, we use raise_exception_ra() so
+         * that cpu_restore_state() will sort them out.
          */
-        cpu_restore_state(cs, GETPC(), true);
-        raise_exception(env, EXCP_STKOF, 0, 1);
+        raise_exception_ra(env, EXCP_STKOF, 0, 1, GETPC());
     }
 }
 
-- 
2.20.1

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

Note that the SVE BFLOAT16 support does not require SVE2,
it is an independent extension.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

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 @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id)
     return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0;
 }
 
+static inline bool isar_feature_aa32_bf16(const ARMISARegisters *id)
+{
+    return FIELD_EX32(id->id_isar6, ID_ISAR6, BF16) != 0;
+}
+
 static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id)
 {
     return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0;
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2;
 }
 
+static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0;
+}
+
 static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id)
 {
     /* We always set the AdvSIMD and FP fields identically.  */
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0;
 }
 
+static inline bool isar_feature_aa64_sve_bf16(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BFLOAT16) != 0;
+}
+
 static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0;
-- 
2.20.1

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: 20210525225817.400336-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/translate-a64.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
     int rd = extract32(insn, 0, 5);
 
     if (mos) {
-        unallocated_encoding(s);
-        return;
+        goto do_unallocated;
     }
 
     switch (opcode) {
@@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
         /* FCVT between half, single and double precision */
         int dtype = extract32(opcode, 0, 2);
         if (type == 2 || dtype == type) {
-            unallocated_encoding(s);
-            return;
+            goto do_unallocated;
         }
         if (!fp_access_check(s)) {
             return;
@@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
 
     case 0x10 ... 0x13: /* FRINT{32,64}{X,Z} */
         if (type > 1 || !dc_isar_feature(aa64_frint, s)) {
-            unallocated_encoding(s);
-            return;
+            goto do_unallocated;
         }
         /* fall through */
     case 0x0 ... 0x3:
@@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
             break;
         case 3:
             if (!dc_isar_feature(aa64_fp16, s)) {
-                unallocated_encoding(s);
-                return;
+                goto do_unallocated;
             }
 
             if (!fp_access_check(s)) {
@@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
             handle_fp_1src_half(s, opcode, rd, rn);
             break;
         default:
-            unallocated_encoding(s);
+            goto do_unallocated;
         }
         break;
 
     default:
+    do_unallocated:
         unallocated_encoding(s);
         break;
     }
-- 
2.20.1

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

This is the 64-bit BFCVT and the 32-bit VCVT{B,T}.BF16.F32.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h        |  1 +
 target/arm/vfp.decode      |  2 ++
 target/arm/translate-a64.c | 19 +++++++++++++++++++
 target/arm/translate-vfp.c | 24 ++++++++++++++++++++++++
 target/arm/vfp_helper.c    |  5 +++++
 5 files changed, 51 insertions(+)

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(vfp_cmped, void, f64, f64, env)
 
 DEF_HELPER_2(vfp_fcvtds, f64, f32, env)
 DEF_HELPER_2(vfp_fcvtsd, f32, f64, env)
+DEF_HELPER_FLAGS_2(bfcvt, TCG_CALL_NO_RWG, i32, f32, ptr)
 
 DEF_HELPER_2(vfp_uitoh, f16, i32, ptr)
 DEF_HELPER_2(vfp_uitos, f32, i32, ptr)
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -XXX,XX +XXX,XX @@ VCVT_f64_f16 ---- 1110 1.11 0010 .... 1011 t:1 1.0 .... \
 
 # VCVTB and VCVTT to f16: Vd format is always vd_sp;
 # Vm format depends on size bit
+VCVT_b16_f32 ---- 1110 1.11 0011 .... 1001 t:1 1.0 .... \
+             vd=%vd_sp vm=%vm_sp
 VCVT_f16_f32 ---- 1110 1.11 0011 .... 1010 t:1 1.0 .... \
              vd=%vd_sp vm=%vm_sp
 VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn)
     case 0x3: /* FSQRT */
         gen_helper_vfp_sqrts(tcg_res, tcg_op, cpu_env);
         goto done;
+    case 0x6: /* BFCVT */
+        gen_fpst = gen_helper_bfcvt;
+        break;
     case 0x8: /* FRINTN */
     case 0x9: /* FRINTP */
     case 0xa: /* FRINTM */
@@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
         }
         break;
 
+    case 0x6:
+        switch (type) {
+        case 1: /* BFCVT */
+            if (!dc_isar_feature(aa64_bf16, s)) {
+                goto do_unallocated;
+            }
+            if (!fp_access_check(s)) {
+                return;
+            }
+            handle_fp_1src_single(s, opcode, rd, rn);
+            break;
+        default:
+            goto do_unallocated;
+        }
+        break;
+
     default:
     do_unallocated:
         unallocated_encoding(s);
diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-vfp.c
+++ b/target/arm/translate-vfp.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a)
     return true;
 }
 
+static bool trans_VCVT_b16_f32(DisasContext *s, arg_VCVT_b16_f32 *a)
+{
+    TCGv_ptr fpst;
+    TCGv_i32 tmp;
+
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    fpst = fpstatus_ptr(FPST_FPCR);
+    tmp = tcg_temp_new_i32();
+
+    vfp_load_reg32(tmp, a->vm);
+    gen_helper_bfcvt(tmp, tmp, fpst);
+    tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t));
+    tcg_temp_free_ptr(fpst);
+    tcg_temp_free_i32(tmp);
+    return true;
+}
+
 static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a)
 {
     TCGv_ptr fpst;
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -XXX,XX +XXX,XX @@ float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env)
     return float64_to_float32(x, &env->vfp.fp_status);
 }
 
+uint32_t HELPER(bfcvt)(float32 x, void *status)
+{
+    return float32_to_bfloat16(x, status);
+}
+
 /*
  * VFP3 fixed point conversion. The AArch32 versions of fix-to-float
  * must always round-to-nearest; the AArch64 ones honour the FPSCR
-- 
2.20.1

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

This is BFCVT{N,T} for both AArch64 AdvSIMD and SVE,
and VCVT.BF16.F32 for AArch32 NEON.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h     |  4 ++++
 target/arm/helper.h         |  1 +
 target/arm/neon-dp.decode   |  1 +
 target/arm/sve.decode       |  2 ++
 target/arm/sve_helper.c     |  2 ++
 target/arm/translate-a64.c  | 17 ++++++++++++++
 target/arm/translate-neon.c | 45 +++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c  | 16 +++++++++++++
 target/arm/vfp_helper.c     |  7 ++++++
 9 files changed, 95 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_fcvt_hd, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_fcvt_sd, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_bfcvt, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(sve_fcvtzs_hh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_fcvtnt_sh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_fcvtnt_ds, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_bfcvtnt, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(sve2_fcvtlt_hs, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
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(vfp_cmped, void, f64, f64, env)
 DEF_HELPER_2(vfp_fcvtds, f64, f32, env)
 DEF_HELPER_2(vfp_fcvtsd, f32, f64, env)
 DEF_HELPER_FLAGS_2(bfcvt, TCG_CALL_NO_RWG, i32, f32, ptr)
+DEF_HELPER_FLAGS_2(bfcvt_pair, TCG_CALL_NO_RWG, i32, i64, ptr)
 
 DEF_HELPER_2(vfp_uitoh, f16, i32, ptr)
 DEF_HELPER_2(vfp_uitos, f32, i32, ptr)
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -XXX,XX +XXX,XX @@ Vimm_1r          1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
     VRINTZ       1111 001 11 . 11 .. 10 .... 0 1011 . . 0 .... @2misc
 
     VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
+    VCVT_B16_F32 1111 001 11 . 11 .. 10 .... 0 1100 1 . 0 .... @2misc_q0
 
     VRINTM       1111 001 11 . 11 .. 10 .... 0 1101 . . 0 .... @2misc
 
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ FNMLS_zpzzz     01100101 .. 1 ..... 111 ... ..... .....         @rdn_pg_rm_ra
 # SVE floating-point convert precision
 FCVT_sh         01100101 10 0010 00 101 ... ..... .....         @rd_pg_rn_e0
 FCVT_hs         01100101 10 0010 01 101 ... ..... .....         @rd_pg_rn_e0
+BFCVT           01100101 10 0010 10 101 ... ..... .....         @rd_pg_rn_e0
 FCVT_dh         01100101 11 0010 00 101 ... ..... .....         @rd_pg_rn_e0
 FCVT_hd         01100101 11 0010 01 101 ... ..... .....         @rd_pg_rn_e0
 FCVT_ds         01100101 11 0010 10 101 ... ..... .....         @rd_pg_rn_e0
@@ -XXX,XX +XXX,XX @@ RAX1            01000101 00 1 ..... 11110 1 ..... .....  @rd_rn_rm_e0
 FCVTXNT_ds      01100100 00 0010 10 101 ... ..... .....  @rd_pg_rn_e0
 FCVTX_ds        01100101 00 0010 10 101 ... ..... .....  @rd_pg_rn_e0
 FCVTNT_sh       01100100 10 0010 00 101 ... ..... .....  @rd_pg_rn_e0
+BFCVTNT         01100100 10 0010 10 101 ... ..... .....  @rd_pg_rn_e0
 FCVTLT_hs       01100100 10 0010 01 101 ... ..... .....  @rd_pg_rn_e0
 FCVTNT_ds       01100100 11 0010 10 101 ... ..... .....  @rd_pg_rn_e0
 FCVTLT_sd       01100100 11 0010 11 101 ... ..... .....  @rd_pg_rn_e0
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -XXX,XX +XXX,XX @@ static inline uint64_t vfp_float64_to_uint64_rtz(float64 f, float_status *s)
 
 DO_ZPZ_FP(sve_fcvt_sh, uint32_t, H1_4, sve_f32_to_f16)
 DO_ZPZ_FP(sve_fcvt_hs, uint32_t, H1_4, sve_f16_to_f32)
+DO_ZPZ_FP(sve_bfcvt,   uint32_t, H1_4, float32_to_bfloat16)
 DO_ZPZ_FP(sve_fcvt_dh, uint64_t,     , sve_f64_to_f16)
 DO_ZPZ_FP(sve_fcvt_hd, uint64_t,     , sve_f16_to_f64)
 DO_ZPZ_FP(sve_fcvt_ds, uint64_t,     , float64_to_float32)
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc)  \
     } while (i != 0);                                                         \
 }
 
+DO_FCVTNT(sve_bfcvtnt,    uint32_t, uint16_t, H1_4, H1_2, float32_to_bfloat16)
 DO_FCVTNT(sve2_fcvtnt_sh, uint32_t, uint16_t, H1_4, H1_2, sve_f32_to_f16)
 DO_FCVTNT(sve2_fcvtnt_ds, uint64_t, uint32_t,     , H1_4, float64_to_float32)
 
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
                 tcg_temp_free_i32(ahp);
             }
             break;
+        case 0x36: /* BFCVTN, BFCVTN2 */
+            {
+                TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
+                gen_helper_bfcvt_pair(tcg_res[pass], tcg_op, fpst);
+                tcg_temp_free_ptr(fpst);
+            }
+            break;
         case 0x56:  /* FCVTXN, FCVTXN2 */
             /* 64 bit to 32 bit float conversion
              * with von Neumann rounding (round to odd)
@@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             }
             handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd);
             return;
+        case 0x36: /* BFCVTN, BFCVTN2 */
+            if (!dc_isar_feature(aa64_bf16, s) || size != 2) {
+                unallocated_encoding(s);
+                return;
+            }
+            if (!fp_access_check(s)) {
+                return;
+            }
+            handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd);
+            return;
         case 0x17: /* FCVTL, FCVTL2 */
             if (!fp_access_check(s)) {
                 return;
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a)
     return true;
 }
 
+static bool trans_VCVT_B16_F32(DisasContext *s, arg_2misc *a)
+{
+    TCGv_ptr fpst;
+    TCGv_i64 tmp;
+    TCGv_i32 dst0, dst1;
+
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        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 & 1) || (a->size != 1)) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    fpst = fpstatus_ptr(FPST_STD);
+    tmp = tcg_temp_new_i64();
+    dst0 = tcg_temp_new_i32();
+    dst1 = tcg_temp_new_i32();
+
+    read_neon_element64(tmp, a->vm, 0, MO_64);
+    gen_helper_bfcvt_pair(dst0, tmp, fpst);
+
+    read_neon_element64(tmp, a->vm, 1, MO_64);
+    gen_helper_bfcvt_pair(dst1, tmp, fpst);
+
+    write_neon_element32(dst0, a->vd, 0, MO_32);
+    write_neon_element32(dst1, a->vd, 1, MO_32);
+
+    tcg_temp_free_i64(tmp);
+    tcg_temp_free_i32(dst0);
+    tcg_temp_free_i32(dst1);
+    tcg_temp_free_ptr(fpst);
+    return true;
+}
+
 static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a)
 {
     TCGv_ptr fpst;
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_hs(DisasContext *s, arg_rpr_esz *a)
     return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_hs);
 }
 
+static bool trans_BFCVT(DisasContext *s, arg_rpr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_bfcvt);
+}
+
 static bool trans_FCVT_dh(DisasContext *s, arg_rpr_esz *a)
 {
     return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_dh);
@@ -XXX,XX +XXX,XX @@ static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a)
     return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_sh);
 }
 
+static bool trans_BFCVTNT(DisasContext *s, arg_rpr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_bfcvtnt);
+}
+
 static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz *a)
 {
     if (!dc_isar_feature(aa64_sve2, s)) {
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(bfcvt)(float32 x, void *status)
     return float32_to_bfloat16(x, status);
 }
 
+uint32_t HELPER(bfcvt_pair)(uint64_t pair, void *status)
+{
+    bfloat16 lo = float32_to_bfloat16(extract64(pair, 0, 32), status);
+    bfloat16 hi = float32_to_bfloat16(extract64(pair, 32, 32), status);
+    return deposit32(lo, 16, 16, hi);
+}
+
 /*
  * VFP3 fixed point conversion. The AArch32 versions of fix-to-float
  * must always round-to-nearest; the AArch64 ones honour the FPSCR
-- 
2.20.1

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

For Arm BFDOT and BFMMLA, we need a version of round-to-odd
that overflows to infinity, instead of the max normal number.

Cc: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-6-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/fpu/softfloat-types.h | 4 +++-
 fpu/softfloat-parts.c.inc     | 6 ++++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h
index XXXXXXX..XXXXXXX 100644
--- a/include/fpu/softfloat-types.h
+++ b/include/fpu/softfloat-types.h
@@ -XXX,XX +XXX,XX @@ typedef enum __attribute__((__packed__)) {
     float_round_up           = 2,
     float_round_to_zero      = 3,
     float_round_ties_away    = 4,
-    /* Not an IEEE rounding mode: round to the closest odd mantissa value */
+    /* Not an IEEE rounding mode: round to closest odd, overflow to max */
     float_round_to_odd       = 5,
+    /* Not an IEEE rounding mode: round to closest odd, overflow to inf */
+    float_round_to_odd_inf   = 6,
 } FloatRoundMode;
 
 /*
diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc
index XXXXXXX..XXXXXXX 100644
--- a/fpu/softfloat-parts.c.inc
+++ b/fpu/softfloat-parts.c.inc
@@ -XXX,XX +XXX,XX @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s,
         g_assert_not_reached();
     }
 
+    overflow_norm = false;
     switch (s->float_rounding_mode) {
     case float_round_nearest_even:
-        overflow_norm = false;
         inc = ((p->frac_lo & roundeven_mask) != frac_lsbm1 ? frac_lsbm1 : 0);
         break;
     case float_round_ties_away:
-        overflow_norm = false;
         inc = frac_lsbm1;
         break;
     case float_round_to_zero:
@@ -XXX,XX +XXX,XX @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s,
         break;
     case float_round_to_odd:
         overflow_norm = true;
+        /* fall through */
+    case float_round_to_odd_inf:
         inc = p->frac_lo & frac_lsb ? 0 : round_mask;
         break;
     default:
@@ -XXX,XX +XXX,XX @@ static void partsN(uncanon)(FloatPartsN *p, float_status *s,
                        ? frac_lsbm1 : 0);
                 break;
             case float_round_to_odd:
+            case float_round_to_odd_inf:
                 inc = p->frac_lo & frac_lsb ? 0 : round_mask;
                 break;
             default:
-- 
2.20.1

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

This is BFDOT for both AArch64 AdvSIMD and SVE,
and VDOT.BF16 for AArch32 NEON.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-7-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h           |  3 +++
 target/arm/neon-shared.decode |  2 ++
 target/arm/sve.decode         |  3 +++
 target/arm/translate-a64.c    | 20 ++++++++++++++++++
 target/arm/translate-neon.c   |  9 ++++++++
 target/arm/translate-sve.c    | 12 +++++++++++
 target/arm/vec_helper.c       | 40 +++++++++++++++++++++++++++++++++++
 7 files changed, 89 insertions(+)

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(gvec_ummla_b, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_usmmla_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_bfdot, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
 #include "helper-sve.h"
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -XXX,XX +XXX,XX @@ VUDOT          1111 110 00 . 10 .... .... 1101 . q:1 . 1 .... \
                vm=%vm_dp vn=%vn_dp vd=%vd_dp
 VUSDOT         1111 110 01 . 10 .... .... 1101 . q:1 . 0 .... \
                vm=%vm_dp vn=%vn_dp vd=%vd_dp
+VDOT_b16       1111 110 00 . 00 .... .... 1101 . q:1 . 0 .... \
+               vm=%vm_dp vn=%vn_dp vd=%vd_dp
 
 # VFM[AS]L
 VFML           1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ FMLALT_zzzw     01100100 10 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
 FMLSLB_zzzw     01100100 10 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_e0
 FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_e0
 
+### SVE2 floating-point bfloat16 dot-product
+BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
+
 ### SVE2 floating-point multiply-add long (indexed)
 FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 FMLALT_zzxw     01100100 10 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         feature = dc_isar_feature(aa64_fcma, s);
         break;
+    case 0x1f: /* BFDOT */
+        switch (size) {
+        case 1:
+            feature = dc_isar_feature(aa64_bf16, s);
+            break;
+        default:
+            unallocated_encoding(s);
+            return;
+        }
+        break;
     default:
         unallocated_encoding(s);
         return;
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         return;
 
+    case 0xf: /* BFDOT */
+        switch (size) {
+        case 1:
+            gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfdot);
+            break;
+        default:
+            g_assert_not_reached();
+        }
+        return;
+
     default:
         g_assert_not_reached();
     }
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
                         gen_helper_gvec_usdot_b);
 }
 
+static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a)
+{
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        return false;
+    }
+    return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
+                        gen_helper_gvec_bfdot);
+}
+
 static bool trans_VFML(DisasContext *s, arg_VFML *a)
 {
     int opr_sz;
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_UMMLA(DisasContext *s, arg_rrrr_esz *a)
 {
     return do_i8mm_zzzz_ool(s, a, gen_helper_gvec_ummla_b, 0);
 }
+
+static bool trans_BFDOT_zzzz(DisasContext *s, arg_rrrr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot,
+                          a->rd, a->rn, a->rm, a->ra, 0);
+    }
+    return true;
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ static void do_mmla_b(void *vd, void *vn, void *vm, void *va, uint32_t desc,
 DO_MMLA_B(gvec_smmla_b, do_smmla_b)
 DO_MMLA_B(gvec_ummla_b, do_ummla_b)
 DO_MMLA_B(gvec_usmmla_b, do_usmmla_b)
+
+/*
+ * BFloat16 Dot Product
+ */
+
+static float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2)
+{
+    /* FPCR is ignored for BFDOT and BFMMLA. */
+    float_status bf_status = {
+        .tininess_before_rounding = float_tininess_before_rounding,
+        .float_rounding_mode = float_round_to_odd_inf,
+        .flush_to_zero = true,
+        .flush_inputs_to_zero = true,
+        .default_nan_mode = true,
+    };
+    float32 t1, t2;
+
+    /*
+     * Extract each BFloat16 from the element pair, and shift
+     * them such that they become float32.
+     */
+    t1 = float32_mul(e1 << 16, e2 << 16, &bf_status);
+    t2 = float32_mul(e1 & 0xffff0000u, e2 & 0xffff0000u, &bf_status);
+    t1 = float32_add(t1, t2, &bf_status);
+    t1 = float32_add(sum, t1, &bf_status);
+
+    return t1;
+}
+
+void HELPER(gvec_bfdot)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    float32 *d = vd, *a = va;
+    uint32_t *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        d[i] = bfdotadd(a[i], n[i], m[i]);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
-- 
2.20.1

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

This is BFDOT for both AArch64 AdvSIMD and SVE,
and VDOT.BF16 for AArch32 NEON.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-8-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h           |  2 ++
 target/arm/neon-shared.decode |  2 ++
 target/arm/sve.decode         |  3 +++
 target/arm/translate-a64.c    | 41 +++++++++++++++++++++++++++--------
 target/arm/translate-neon.c   |  9 ++++++++
 target/arm/translate-sve.c    | 12 ++++++++++
 target/arm/vec_helper.c       | 20 +++++++++++++++++
 7 files changed, 80 insertions(+), 9 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(gvec_usmmla_b, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_5(gvec_bfdot, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_bfdot_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
 
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -XXX,XX +XXX,XX @@ VUSDOT_scalar  1111 1110 1 . 00 .... .... 1101 . q:1 index:1 0 vm:4 \
                vn=%vn_dp vd=%vd_dp
 VSUDOT_scalar  1111 1110 1 . 00 .... .... 1101 . q:1 index:1 1 vm:4 \
                vn=%vn_dp vd=%vd_dp
+VDOT_b16_scal  1111 1110 0 . 00 .... .... 1101 . q:1 index:1 0 vm:4 \
+               vn=%vn_dp vd=%vd_dp
 
 %vfml_scalar_q0_rm 0:3 5:1
 %vfml_scalar_q1_index 5:1 3:1
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 FMLALT_zzxw     01100100 10 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
 FMLSLB_zzxw     01100100 10 1 ..... 0110.0 ..... .....     @rrxr_3a esz=2
 FMLSLT_zzxw     01100100 10 1 ..... 0110.1 ..... .....     @rrxr_3a esz=2
+
+### SVE2 floating-point bfloat16 dot-product (indexed)
+BFDOT_zzxz      01100100 01 1 ..... 010000 ..... .....     @rrxr_2 esz=2
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             return;
         }
         break;
-    case 0x0f: /* SUDOT, USDOT */
-        if (is_scalar || (size & 1) || !dc_isar_feature(aa64_i8mm, s)) {
+    case 0x0f:
+        switch (size) {
+        case 0: /* SUDOT */
+        case 2: /* USDOT */
+            if (is_scalar || !dc_isar_feature(aa64_i8mm, s)) {
+                unallocated_encoding(s);
+                return;
+            }
+            break;
+        case 1: /* BFDOT */
+            if (is_scalar || !dc_isar_feature(aa64_bf16, s)) {
+                unallocated_encoding(s);
+                return;
+            }
+            break;
+        default:
             unallocated_encoding(s);
             return;
         }
@@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
                          u ? gen_helper_gvec_udot_idx_b
                          : gen_helper_gvec_sdot_idx_b);
         return;
-    case 0x0f: /* SUDOT, USDOT */
-        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
-                         extract32(insn, 23, 1)
-                         ? gen_helper_gvec_usdot_idx_b
-                         : gen_helper_gvec_sudot_idx_b);
-        return;
-
+    case 0x0f:
+        switch (extract32(insn, 22, 2)) {
+        case 0: /* SUDOT */
+            gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
+                             gen_helper_gvec_sudot_idx_b);
+            return;
+        case 1: /* BFDOT */
+            gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
+                             gen_helper_gvec_bfdot_idx);
+            return;
+        case 2: /* USDOT */
+            gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
+                             gen_helper_gvec_usdot_idx_b);
+            return;
+        }
+        g_assert_not_reached();
     case 0x11: /* FCMLA #0 */
     case 0x13: /* FCMLA #90 */
     case 0x15: /* FCMLA #180 */
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
                         gen_helper_gvec_sudot_idx_b);
 }
 
+static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a)
+{
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        return false;
+    }
+    return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
+                        gen_helper_gvec_bfdot_idx);
+}
+
 static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a)
 {
     int opr_sz;
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_BFDOT_zzzz(DisasContext *s, arg_rrrr_esz *a)
     }
     return true;
 }
+
+static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzz(s, gen_helper_gvec_bfdot_idx,
+                          a->rd, a->rn, a->rm, a->ra, a->index);
+    }
+    return true;
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfdot)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm,
+                            void *va, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    intptr_t index = simd_data(desc);
+    intptr_t elements = opr_sz / 4;
+    intptr_t eltspersegment = MIN(16 / 4, elements);
+    float32 *d = vd, *a = va;
+    uint32_t *n = vn, *m = vm;
+
+    for (i = 0; i < elements; i += eltspersegment) {
+        uint32_t m_idx = m[i + H4(index)];
+
+        for (j = i; j < i + eltspersegment; j++) {
+            d[j] = bfdotadd(a[j], n[j], m_idx);
+        }
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
-- 
2.20.1

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

This is BFMMLA for both AArch64 AdvSIMD and SVE,
and VMMLA.BF16 for AArch32 NEON.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h           |  3 +++
 target/arm/neon-shared.decode |  2 ++
 target/arm/sve.decode         |  6 +++--
 target/arm/translate-a64.c    | 10 +++++++++
 target/arm/translate-neon.c   |  9 ++++++++
 target/arm/translate-sve.c    | 12 ++++++++++
 target/arm/vec_helper.c       | 42 ++++++++++++++++++++++++++++++++++-
 7 files changed, 81 insertions(+), 3 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(gvec_bfdot, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_bfdot_idx, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_bfmmla, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
 #include "helper-sve.h"
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -XXX,XX +XXX,XX @@ VUMMLA         1111 1100 0.10 .... .... 1100 .1.1 .... \
                vm=%vm_dp vn=%vn_dp vd=%vd_dp
 VUSMMLA        1111 1100 1.10 .... .... 1100 .1.0 .... \
                vm=%vm_dp vn=%vn_dp vd=%vd_dp
+VMMLA_b16      1111 1100 0.00 .... .... 1100 .1.0 .... \
+               vm=%vm_dp vn=%vn_dp vd=%vd_dp
 
 VCMLA_scalar   1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \
                vn=%vn_dp vd=%vd_dp size=1
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 USDOT_zzzz      01000100 .. 0 ..... 011 110 ..... .....  @rda_rn_rm
 
 ### SVE2 floating point matrix multiply accumulate
-
-FMMLA           01100100 .. 1 ..... 111001 ..... .....  @rda_rn_rm
+{
+  BFMMLA        01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
+  FMMLA         01100100 .. 1 ..... 111 001 ..... .....  @rda_rn_rm
+}
 
 ### SVE2 Memory Gather Load Group
 
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         feature = dc_isar_feature(aa64_fcma, s);
         break;
+    case 0x1d: /* BFMMLA */
+        if (size != MO_16 || !is_q) {
+            unallocated_encoding(s);
+            return;
+        }
+        feature = dc_isar_feature(aa64_bf16, s);
+        break;
     case 0x1f: /* BFDOT */
         switch (size) {
         case 1:
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         return;
 
+    case 0xd: /* BFMMLA */
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfmmla);
+        return;
     case 0xf: /* BFDOT */
         switch (size) {
         case 1:
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VUSMMLA(DisasContext *s, arg_VUSMMLA *a)
     return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0,
                         gen_helper_gvec_usmmla_b);
 }
+
+static bool trans_VMMLA_b16(DisasContext *s, arg_VMMLA_b16 *a)
+{
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        return false;
+    }
+    return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0,
+                        gen_helper_gvec_bfmmla);
+}
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_BFDOT_zzxz(DisasContext *s, arg_rrxr_esz *a)
     }
     return true;
 }
+
+static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzz(s, gen_helper_gvec_bfmmla,
+                          a->rd, a->rn, a->rm, a->ra, 0);
+    }
+    return true;
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ static void do_mmla_b(void *vd, void *vn, void *vm, void *va, uint32_t desc,
          * Process the entire segment at once, writing back the
          * results only after we've consumed all of the inputs.
          *
-         * Key to indicies by column:
+         * Key to indices by column:
          *          i   j                  i             j
          */
         sum0 = a[H4(0 + 0)];
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm,
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
+{
+    intptr_t s, opr_sz = simd_oprsz(desc);
+    float32 *d = vd, *a = va;
+    uint32_t *n = vn, *m = vm;
+
+    for (s = 0; s < opr_sz / 4; s += 4) {
+        float32 sum00, sum01, sum10, sum11;
+
+        /*
+         * Process the entire segment at once, writing back the
+         * results only after we've consumed all of the inputs.
+         *
+         * Key to indicies by column:
+         *               i   j           i   k             j   k
+         */
+        sum00 = a[s + H4(0 + 0)];
+        sum00 = bfdotadd(sum00, n[s + H4(0 + 0)], m[s + H4(0 + 0)]);
+        sum00 = bfdotadd(sum00, n[s + H4(0 + 1)], m[s + H4(0 + 1)]);
+
+        sum01 = a[s + H4(0 + 1)];
+        sum01 = bfdotadd(sum01, n[s + H4(0 + 0)], m[s + H4(2 + 0)]);
+        sum01 = bfdotadd(sum01, n[s + H4(0 + 1)], m[s + H4(2 + 1)]);
+
+        sum10 = a[s + H4(2 + 0)];
+        sum10 = bfdotadd(sum10, n[s + H4(2 + 0)], m[s + H4(0 + 0)]);
+        sum10 = bfdotadd(sum10, n[s + H4(2 + 1)], m[s + H4(0 + 1)]);
+
+        sum11 = a[s + H4(2 + 1)];
+        sum11 = bfdotadd(sum11, n[s + H4(2 + 0)], m[s + H4(2 + 0)]);
+        sum11 = bfdotadd(sum11, n[s + H4(2 + 1)], m[s + H4(2 + 1)]);
+
+        d[s + H4(0 + 0)] = sum00;
+        d[s + H4(0 + 1)] = sum01;
+        d[s + H4(2 + 0)] = sum10;
+        d[s + H4(2 + 1)] = sum11;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
-- 
2.20.1

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

This is BFMLAL{B,T} for both AArch64 AdvSIMD and SVE,
and VFMA{B,T}.BF16 for AArch32 NEON.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h           |  3 +++
 target/arm/neon-shared.decode |  3 +++
 target/arm/sve.decode         |  3 +++
 target/arm/translate-a64.c    | 13 +++++++++----
 target/arm/translate-neon.c   |  9 +++++++++
 target/arm/translate-sve.c    | 30 ++++++++++++++++++++++++++++++
 target/arm/vec_helper.c       | 16 ++++++++++++++++
 7 files changed, 73 insertions(+), 4 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(gvec_bfdot_idx, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_bfmmla, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
 #include "helper-sve.h"
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -XXX,XX +XXX,XX @@ VUSMMLA        1111 1100 1.10 .... .... 1100 .1.0 .... \
 VMMLA_b16      1111 1100 0.00 .... .... 1100 .1.0 .... \
                vm=%vm_dp vn=%vn_dp vd=%vd_dp
 
+VFMA_b16       1111 110 0 0.11 .... .... 1000 . q:1 . 1 .... \
+               vm=%vm_dp vn=%vn_dp vd=%vd_dp
+
 VCMLA_scalar   1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \
                vn=%vn_dp vd=%vd_dp size=1
 VCMLA_scalar   1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ FMLALT_zzzw     01100100 10 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
 FMLSLB_zzzw     01100100 10 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_e0
 FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_e0
 
+BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
+BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
+
 ### SVE2 floating-point bfloat16 dot-product
 BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
 
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         feature = dc_isar_feature(aa64_bf16, s);
         break;
-    case 0x1f: /* BFDOT */
+    case 0x1f:
         switch (size) {
-        case 1:
+        case 1: /* BFDOT */
+        case 3: /* BFMLAL{B,T} */
             feature = dc_isar_feature(aa64_bf16, s);
             break;
         default:
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
     case 0xd: /* BFMMLA */
         gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfmmla);
         return;
-    case 0xf: /* BFDOT */
+    case 0xf:
         switch (size) {
-        case 1:
+        case 1: /* BFDOT */
             gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfdot);
             break;
+        case 3: /* BFMLAL{B,T} */
+            gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, false, is_q,
+                              gen_helper_gvec_bfmlal);
+            break;
         default:
             g_assert_not_reached();
         }
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VMMLA_b16(DisasContext *s, arg_VMMLA_b16 *a)
     return do_neon_ddda(s, 7, a->vd, a->vn, a->vm, 0,
                         gen_helper_gvec_bfmmla);
 }
+
+static bool trans_VFMA_b16(DisasContext *s, arg_VFMA_b16 *a)
+{
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        return false;
+    }
+    return do_neon_ddda_fpst(s, 7, a->vd, a->vn, a->vm, a->q, FPST_STD,
+                             gen_helper_gvec_bfmlal);
+}
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_BFMMLA(DisasContext *s, arg_rrrr_esz *a)
     }
     return true;
 }
+
+static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        TCGv_ptr status = fpstatus_ptr(FPST_FPCR);
+        unsigned vsz = vec_full_reg_size(s);
+
+        tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           status, vsz, vsz, sel,
+                           gen_helper_gvec_bfmlal);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
+
+static bool trans_BFMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_BFMLAL_zzzw(s, a, false);
+}
+
+static bool trans_BFMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_BFMLAL_zzzw(s, a, true);
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
+                         void *stat, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    intptr_t sel = simd_data(desc);
+    float32 *d = vd, *a = va;
+    bfloat16 *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 4; ++i) {
+        float32 nn = n[H2(i * 2 + sel)] << 16;
+        float32 mm = m[H2(i * 2 + sel)] << 16;
+        d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat);
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
-- 
2.20.1

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

This is BFMLAL{B,T} for both AArch64 AdvSIMD and SVE,
and VFMA{B,T}.BF16 for AArch32 NEON.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-11-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h           |  2 ++
 target/arm/neon-shared.decode |  2 ++
 target/arm/sve.decode         |  2 ++
 target/arm/translate-a64.c    | 15 ++++++++++++++-
 target/arm/translate-neon.c   | 10 ++++++++++
 target/arm/translate-sve.c    | 30 ++++++++++++++++++++++++++++++
 target/arm/vec_helper.c       | 22 ++++++++++++++++++++++
 7 files changed, 82 insertions(+), 1 deletion(-)

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(gvec_bfmmla, TCG_CALL_NO_RWG,
 
 DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
 
 #ifdef TARGET_AARCH64
 #include "helper-a64.h"
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/neon-shared.decode
+++ b/target/arm/neon-shared.decode
@@ -XXX,XX +XXX,XX @@ VFML_scalar    1111 1110 0 . 0 s:1 .... .... 1000 . 0 . 1 index:1 ... \
                rm=%vfml_scalar_q0_rm vn=%vn_sp vd=%vd_dp q=0
 VFML_scalar    1111 1110 0 . 0 s:1 .... .... 1000 . 1 . 1 . rm:3 \
                index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp q=1
+VFMA_b16_scal  1111 1110 0.11 .... .... 1000 . q:1 . 1 . vm:3 \
+               index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -XXX,XX +XXX,XX @@ FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 FMLALT_zzxw     01100100 10 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
 FMLSLB_zzxw     01100100 10 1 ..... 0110.0 ..... .....     @rrxr_3a esz=2
 FMLSLT_zzxw     01100100 10 1 ..... 0110.1 ..... .....     @rrxr_3a esz=2
+BFMLALB_zzxw    01100100 11 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
+BFMLALT_zzxw    01100100 11 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
 
 ### SVE2 floating-point bfloat16 dot-product (indexed)
 BFDOT_zzxz      01100100 01 1 ..... 010000 ..... .....     @rrxr_2 esz=2
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
                 unallocated_encoding(s);
                 return;
             }
+            size = MO_32;
             break;
         case 1: /* BFDOT */
             if (is_scalar || !dc_isar_feature(aa64_bf16, s)) {
                 unallocated_encoding(s);
                 return;
             }
+            size = MO_32;
+            break;
+        case 3: /* BFMLAL{B,T} */
+            if (is_scalar || !dc_isar_feature(aa64_bf16, s)) {
+                unallocated_encoding(s);
+                return;
+            }
+            /* can't set is_fp without other incorrect size checks */
+            size = MO_16;
             break;
         default:
             unallocated_encoding(s);
             return;
         }
-        size = MO_32;
         break;
     case 0x11: /* FCMLA #0 */
     case 0x13: /* FCMLA #90 */
@@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
                              gen_helper_gvec_usdot_idx_b);
             return;
+        case 3: /* BFMLAL{B,T} */
+            gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, 0, (index << 1) | is_q,
+                              gen_helper_gvec_bfmlal_idx);
+            return;
         }
         g_assert_not_reached();
     case 0x11: /* FCMLA #0 */
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-neon.c
+++ b/target/arm/translate-neon.c
@@ -XXX,XX +XXX,XX @@ static bool trans_VFMA_b16(DisasContext *s, arg_VFMA_b16 *a)
     return do_neon_ddda_fpst(s, 7, a->vd, a->vn, a->vm, a->q, FPST_STD,
                              gen_helper_gvec_bfmlal);
 }
+
+static bool trans_VFMA_b16_scal(DisasContext *s, arg_VFMA_b16_scal *a)
+{
+    if (!dc_isar_feature(aa32_bf16, s)) {
+        return false;
+    }
+    return do_neon_ddda_fpst(s, 6, a->vd, a->vn, a->vm,
+                             (a->index << 1) | a->q, FPST_STD,
+                             gen_helper_gvec_bfmlal_idx);
+}
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -XXX,XX +XXX,XX @@ static bool trans_BFMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a)
 {
     return do_BFMLAL_zzzw(s, a, true);
 }
+
+static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
+{
+    if (!dc_isar_feature(aa64_sve_bf16, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        TCGv_ptr status = fpstatus_ptr(FPST_FPCR);
+        unsigned vsz = vec_full_reg_size(s);
+
+        tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           status, vsz, vsz, (a->index << 1) | sel,
+                           gen_helper_gvec_bfmlal_idx);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
+
+static bool trans_BFMLALB_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+    return do_BFMLAL_zzxw(s, a, false);
+}
+
+static bool trans_BFMLALT_zzxw(DisasContext *s, arg_rrxr_esz *a)
+{
+    return do_BFMLAL_zzxw(s, a, true);
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm,
+                             void *va, void *stat, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1);
+    intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 1, 3);
+    intptr_t elements = opr_sz / 4;
+    intptr_t eltspersegment = MIN(16 / 4, elements);
+    float32 *d = vd, *a = va;
+    bfloat16 *n = vn, *m = vm;
+
+    for (i = 0; i < elements; i += eltspersegment) {
+        float32 m_idx = m[H2(2 * i + index)] << 16;
+
+        for (j = i; j < i + eltspersegment; j++) {
+            float32 n_j = n[H2(2 * j + sel)] << 16;
+            d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], 0, stat);
+        }
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}
-- 
2.20.1

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-12-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 linux-user/elfload.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void)
     GET_FEATURE_ID(aa64_sve_i8mm, ARM_HWCAP2_A64_SVEI8MM);
     GET_FEATURE_ID(aa64_sve_f32mm, ARM_HWCAP2_A64_SVEF32MM);
     GET_FEATURE_ID(aa64_sve_f64mm, ARM_HWCAP2_A64_SVEF64MM);
+    GET_FEATURE_ID(aa64_sve_bf16, ARM_HWCAP2_A64_SVEBF16);
     GET_FEATURE_ID(aa64_i8mm, ARM_HWCAP2_A64_I8MM);
+    GET_FEATURE_ID(aa64_bf16, ARM_HWCAP2_A64_BF16);
     GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG);
     GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI);
     GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE);
-- 
2.20.1

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

Disable BF16 again for !have_neon and !have_vfp during realize.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-13-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.c     | 3 +++
 target/arm/cpu64.c   | 3 +++
 target/arm/cpu_tcg.c | 1 +
 3 files changed, 7 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 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
 
         u = cpu->isar.id_isar6;
         u = FIELD_DP32(u, ID_ISAR6, JSCVT, 0);
+        u = FIELD_DP32(u, ID_ISAR6, BF16, 0);
         cpu->isar.id_isar6 = u;
 
         u = cpu->isar.mvfr0;
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
 
         t = cpu->isar.id_aa64isar1;
         t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 0);
+        t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 0);
         t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 0);
         cpu->isar.id_aa64isar1 = t;
 
@@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
         u = cpu->isar.id_isar6;
         u = FIELD_DP32(u, ID_ISAR6, DP, 0);
         u = FIELD_DP32(u, ID_ISAR6, FHM, 0);
+        u = FIELD_DP32(u, ID_ISAR6, BF16, 0);
         u = FIELD_DP32(u, ID_ISAR6, I8MM, 0);
         cpu->isar.id_isar6 = u;
 
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_max_initfn(Object *obj)
         t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1);
         t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1);
         t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1);
+        t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 1);
         t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1);
         t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* ARMv8.4-RCPC */
         t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1);
@@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj)
         t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1);
         t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2);  /* PMULL */
         t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1);
+        t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 1);
         t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1);
         t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1);
         t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1);
@@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj)
         u = FIELD_DP32(u, ID_ISAR6, FHM, 1);
         u = FIELD_DP32(u, ID_ISAR6, SB, 1);
         u = FIELD_DP32(u, ID_ISAR6, SPECRES, 1);
+        u = FIELD_DP32(u, ID_ISAR6, BF16, 1);
         u = FIELD_DP32(u, ID_ISAR6, I8MM, 1);
         cpu->isar.id_isar6 = u;
 
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/cpu_tcg.c
+++ b/target/arm/cpu_tcg.c
@@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj)
         t = FIELD_DP32(t, ID_ISAR6, FHM, 1);
         t = FIELD_DP32(t, ID_ISAR6, SB, 1);
         t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1);
+        t = FIELD_DP32(t, ID_ISAR6, BF16, 1);
         t = FIELD_DP32(t, ID_ISAR6, I8MM, 1);
         cpu->isar.id_isar6 = t;
 
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

Until now, Hypervisor.framework has only been available on x86_64 systems.
With Apple Silicon shipping now, it extends its reach to aarch64. To
prepare for support for multiple architectures, let's start moving common
code out into its own accel directory.

This patch moves assert_hvf_ok() and introduces generic build infrastructure.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-2-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/sysemu/hvf_int.h | 18 +++++++++++++++
 accel/hvf/hvf-all.c      | 47 ++++++++++++++++++++++++++++++++++++++++
 target/i386/hvf/hvf.c    | 33 +---------------------------
 MAINTAINERS              |  8 +++++++
 accel/hvf/meson.build    |  6 +++++
 accel/meson.build        |  1 +
 6 files changed, 81 insertions(+), 32 deletions(-)
 create mode 100644 include/sysemu/hvf_int.h
 create mode 100644 accel/hvf/hvf-all.c
 create mode 100644 accel/hvf/meson.build

diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@
+/*
+ * QEMU Hypervisor.framework (HVF) support
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+/* header to be included in HVF-specific code */
+
+#ifndef HVF_INT_H
+#define HVF_INT_H
+
+#include <Hypervisor/hv.h>
+
+void assert_hvf_ok(hv_return_t ret);
+
+#endif
diff --git a/accel/hvf/hvf-all.c b/accel/hvf/hvf-all.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/accel/hvf/hvf-all.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * QEMU Hypervisor.framework support
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "qemu/error-report.h"
+#include "sysemu/hvf.h"
+#include "sysemu/hvf_int.h"
+
+void assert_hvf_ok(hv_return_t ret)
+{
+    if (ret == HV_SUCCESS) {
+        return;
+    }
+
+    switch (ret) {
+    case HV_ERROR:
+        error_report("Error: HV_ERROR");
+        break;
+    case HV_BUSY:
+        error_report("Error: HV_BUSY");
+        break;
+    case HV_BAD_ARGUMENT:
+        error_report("Error: HV_BAD_ARGUMENT");
+        break;
+    case HV_NO_RESOURCES:
+        error_report("Error: HV_NO_RESOURCES");
+        break;
+    case HV_NO_DEVICE:
+        error_report("Error: HV_NO_DEVICE");
+        break;
+    case HV_UNSUPPORTED:
+        error_report("Error: HV_UNSUPPORTED");
+        break;
+    default:
+        error_report("Unknown Error");
+    }
+
+    abort();
+}
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/error-report.h"
 
 #include "sysemu/hvf.h"
+#include "sysemu/hvf_int.h"
 #include "sysemu/runstate.h"
 #include "hvf-i386.h"
 #include "vmcs.h"
@@ -XXX,XX +XXX,XX @@
 
 HVFState *hvf_state;
 
-static void assert_hvf_ok(hv_return_t ret)
-{
-    if (ret == HV_SUCCESS) {
-        return;
-    }
-
-    switch (ret) {
-    case HV_ERROR:
-        error_report("Error: HV_ERROR");
-        break;
-    case HV_BUSY:
-        error_report("Error: HV_BUSY");
-        break;
-    case HV_BAD_ARGUMENT:
-        error_report("Error: HV_BAD_ARGUMENT");
-        break;
-    case HV_NO_RESOURCES:
-        error_report("Error: HV_NO_RESOURCES");
-        break;
-    case HV_NO_DEVICE:
-        error_report("Error: HV_NO_DEVICE");
-        break;
-    case HV_UNSUPPORTED:
-        error_report("Error: HV_UNSUPPORTED");
-        break;
-    default:
-        error_report("Unknown Error");
-    }
-
-    abort();
-}
-
 /* Memory slots */
 hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size)
 {
diff --git a/MAINTAINERS b/MAINTAINERS
index XXXXXXX..XXXXXXX 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -XXX,XX +XXX,XX @@ M: Roman Bolshakov <r.bolshakov@yadro.com>
 W: https://wiki.qemu.org/Features/HVF
 S: Maintained
 F: target/i386/hvf/
+
+HVF
+M: Cameron Esfahani <dirty@apple.com>
+M: Roman Bolshakov <r.bolshakov@yadro.com>
+W: https://wiki.qemu.org/Features/HVF
+S: Maintained
+F: accel/hvf/
 F: include/sysemu/hvf.h
+F: include/sysemu/hvf_int.h
 
 WHPX CPUs
 M: Sunil Muthuswamy <sunilmut@microsoft.com>
diff --git a/accel/hvf/meson.build b/accel/hvf/meson.build
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/accel/hvf/meson.build
@@ -XXX,XX +XXX,XX @@
+hvf_ss = ss.source_set()
+hvf_ss.add(files(
+  'hvf-all.c',
+))
+
+specific_ss.add_all(when: 'CONFIG_HVF', if_true: hvf_ss)
diff --git a/accel/meson.build b/accel/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/accel/meson.build
+++ b/accel/meson.build
@@ -XXX,XX +XXX,XX @@ specific_ss.add(files('accel-common.c'))
 softmmu_ss.add(files('accel-softmmu.c'))
 user_ss.add(files('accel-user.c'))
 
+subdir('hvf')
 subdir('qtest')
 subdir('kvm')
 subdir('tcg')
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

This patch moves the vCPU thread loop over.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-3-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 {target/i386 => accel}/hvf/hvf-accel-ops.h | 0
 {target/i386 => accel}/hvf/hvf-accel-ops.c | 0
 target/i386/hvf/x86hvf.c                   | 2 +-
 accel/hvf/meson.build                      | 1 +
 target/i386/hvf/meson.build                | 1 -
 5 files changed, 2 insertions(+), 2 deletions(-)
 rename {target/i386 => accel}/hvf/hvf-accel-ops.h (100%)
 rename {target/i386 => accel}/hvf/hvf-accel-ops.c (100%)

diff --git a/target/i386/hvf/hvf-accel-ops.h b/accel/hvf/hvf-accel-ops.h
similarity index 100%
rename from target/i386/hvf/hvf-accel-ops.h
rename to accel/hvf/hvf-accel-ops.h
diff --git a/target/i386/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
similarity index 100%
rename from target/i386/hvf/hvf-accel-ops.c
rename to accel/hvf/hvf-accel-ops.c
diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86hvf.c
+++ b/target/i386/hvf/x86hvf.c
@@ -XXX,XX +XXX,XX @@
 #include <Hypervisor/hv.h>
 #include <Hypervisor/hv_vmx.h>
 
-#include "hvf-accel-ops.h"
+#include "accel/hvf/hvf-accel-ops.h"
 
 void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg,
                      SegmentCache *qseg, bool is_tr)
diff --git a/accel/hvf/meson.build b/accel/hvf/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/meson.build
+++ b/accel/hvf/meson.build
@@ -XXX,XX +XXX,XX @@
 hvf_ss = ss.source_set()
 hvf_ss.add(files(
   'hvf-all.c',
+  'hvf-accel-ops.c',
 ))
 
 specific_ss.add_all(when: 'CONFIG_HVF', if_true: hvf_ss)
diff --git a/target/i386/hvf/meson.build b/target/i386/hvf/meson.build
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/meson.build
+++ b/target/i386/hvf/meson.build
@@ -XXX,XX +XXX,XX @@
 i386_softmmu_ss.add(when: [hvf, 'CONFIG_HVF'], if_true: files(
   'hvf.c',
-  'hvf-accel-ops.c',
   'x86.c',
   'x86_cpuid.c',
   'x86_decode.c',
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

This patch moves CPU and memory operations over. While at it, make sure
the code is consumable on non-i386 systems.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-4-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/sysemu/hvf_int.h   |   4 +
 target/i386/hvf/hvf-i386.h |   2 -
 target/i386/hvf/x86hvf.h   |   2 -
 accel/hvf/hvf-accel-ops.c  | 308 ++++++++++++++++++++++++++++++++++++-
 target/i386/hvf/hvf.c      | 302 ------------------------------------
 5 files changed, 311 insertions(+), 307 deletions(-)

diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/hvf_int.h
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@
 
 #include <Hypervisor/hv.h>
 
+void hvf_set_phys_mem(MemoryRegionSection *, bool);
 void assert_hvf_ok(hv_return_t ret);
+hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t);
+int hvf_put_registers(CPUState *);
+int hvf_get_registers(CPUState *);
 
 #endif
diff --git a/target/i386/hvf/hvf-i386.h b/target/i386/hvf/hvf-i386.h
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf-i386.h
+++ b/target/i386/hvf/hvf-i386.h
@@ -XXX,XX +XXX,XX @@ struct HVFState {
 };
 extern HVFState *hvf_state;
 
-void hvf_set_phys_mem(MemoryRegionSection *, bool);
 void hvf_handle_io(CPUArchState *, uint16_t, void *, int, int, int);
-hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t);
 
 #ifdef NEED_CPU_H
 /* Functions exported to host specific mode */
diff --git a/target/i386/hvf/x86hvf.h b/target/i386/hvf/x86hvf.h
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86hvf.h
+++ b/target/i386/hvf/x86hvf.h
@@ -XXX,XX +XXX,XX @@
 #include "x86_descr.h"
 
 int hvf_process_events(CPUState *);
-int hvf_put_registers(CPUState *);
-int hvf_get_registers(CPUState *);
 bool hvf_inject_interrupts(CPUState *);
 void hvf_set_segment(struct CPUState *cpu, struct vmx_segment *vmx_seg,
                      SegmentCache *qseg, bool is_tr);
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/osdep.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
+#include "exec/address-spaces.h"
+#include "exec/exec-all.h"
+#include "sysemu/cpus.h"
 #include "sysemu/hvf.h"
+#include "sysemu/hvf_int.h"
 #include "sysemu/runstate.h"
-#include "target/i386/cpu.h"
 #include "qemu/guest-random.h"
 
 #include "hvf-accel-ops.h"
 
+HVFState *hvf_state;
+
+/* Memory slots */
+
+hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size)
+{
+    hvf_slot *slot;
+    int x;
+    for (x = 0; x < hvf_state->num_slots; ++x) {
+        slot = &hvf_state->slots[x];
+        if (slot->size && start < (slot->start + slot->size) &&
+            (start + size) > slot->start) {
+            return slot;
+        }
+    }
+    return NULL;
+}
+
+struct mac_slot {
+    int present;
+    uint64_t size;
+    uint64_t gpa_start;
+    uint64_t gva;
+};
+
+struct mac_slot mac_slots[32];
+
+static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags)
+{
+    struct mac_slot *macslot;
+    hv_return_t ret;
+
+    macslot = &mac_slots[slot->slot_id];
+
+    if (macslot->present) {
+        if (macslot->size != slot->size) {
+            macslot->present = 0;
+            ret = hv_vm_unmap(macslot->gpa_start, macslot->size);
+            assert_hvf_ok(ret);
+        }
+    }
+
+    if (!slot->size) {
+        return 0;
+    }
+
+    macslot->present = 1;
+    macslot->gpa_start = slot->start;
+    macslot->size = slot->size;
+    ret = hv_vm_map((hv_uvaddr_t)slot->mem, slot->start, slot->size, flags);
+    assert_hvf_ok(ret);
+    return 0;
+}
+
+void hvf_set_phys_mem(MemoryRegionSection *section, bool add)
+{
+    hvf_slot *mem;
+    MemoryRegion *area = section->mr;
+    bool writeable = !area->readonly && !area->rom_device;
+    hv_memory_flags_t flags;
+
+    if (!memory_region_is_ram(area)) {
+        if (writeable) {
+            return;
+        } else if (!memory_region_is_romd(area)) {
+            /*
+             * If the memory device is not in romd_mode, then we actually want
+             * to remove the hvf memory slot so all accesses will trap.
+             */
+             add = false;
+        }
+    }
+
+    mem = hvf_find_overlap_slot(
+            section->offset_within_address_space,
+            int128_get64(section->size));
+
+    if (mem && add) {
+        if (mem->size == int128_get64(section->size) &&
+            mem->start == section->offset_within_address_space &&
+            mem->mem == (memory_region_get_ram_ptr(area) +
+            section->offset_within_region)) {
+            return; /* Same region was attempted to register, go away. */
+        }
+    }
+
+    /* Region needs to be reset. set the size to 0 and remap it. */
+    if (mem) {
+        mem->size = 0;
+        if (do_hvf_set_memory(mem, 0)) {
+            error_report("Failed to reset overlapping slot");
+            abort();
+        }
+    }
+
+    if (!add) {
+        return;
+    }
+
+    if (area->readonly ||
+        (!memory_region_is_ram(area) && memory_region_is_romd(area))) {
+        flags = HV_MEMORY_READ | HV_MEMORY_EXEC;
+    } else {
+        flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC;
+    }
+
+    /* Now make a new slot. */
+    int x;
+
+    for (x = 0; x < hvf_state->num_slots; ++x) {
+        mem = &hvf_state->slots[x];
+        if (!mem->size) {
+            break;
+        }
+    }
+
+    if (x == hvf_state->num_slots) {
+        error_report("No free slots");
+        abort();
+    }
+
+    mem->size = int128_get64(section->size);
+    mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region;
+    mem->start = section->offset_within_address_space;
+    mem->region = area;
+
+    if (do_hvf_set_memory(mem, flags)) {
+        error_report("Error registering new memory slot");
+        abort();
+    }
+}
+
+static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
+{
+    if (!cpu->vcpu_dirty) {
+        hvf_get_registers(cpu);
+        cpu->vcpu_dirty = true;
+    }
+}
+
+void hvf_cpu_synchronize_state(CPUState *cpu)
+{
+    if (!cpu->vcpu_dirty) {
+        run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL);
+    }
+}
+
+static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu,
+                                              run_on_cpu_data arg)
+{
+    hvf_put_registers(cpu);
+    cpu->vcpu_dirty = false;
+}
+
+void hvf_cpu_synchronize_post_reset(CPUState *cpu)
+{
+    run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
+}
+
+static void do_hvf_cpu_synchronize_post_init(CPUState *cpu,
+                                             run_on_cpu_data arg)
+{
+    hvf_put_registers(cpu);
+    cpu->vcpu_dirty = false;
+}
+
+void hvf_cpu_synchronize_post_init(CPUState *cpu)
+{
+    run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
+}
+
+static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu,
+                                              run_on_cpu_data arg)
+{
+    cpu->vcpu_dirty = true;
+}
+
+void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu)
+{
+    run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL);
+}
+
+static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on)
+{
+    hvf_slot *slot;
+
+    slot = hvf_find_overlap_slot(
+            section->offset_within_address_space,
+            int128_get64(section->size));
+
+    /* protect region against writes; begin tracking it */
+    if (on) {
+        slot->flags |= HVF_SLOT_LOG;
+        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
+                      HV_MEMORY_READ);
+    /* stop tracking region*/
+    } else {
+        slot->flags &= ~HVF_SLOT_LOG;
+        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
+                      HV_MEMORY_READ | HV_MEMORY_WRITE);
+    }
+}
+
+static void hvf_log_start(MemoryListener *listener,
+                          MemoryRegionSection *section, int old, int new)
+{
+    if (old != 0) {
+        return;
+    }
+
+    hvf_set_dirty_tracking(section, 1);
+}
+
+static void hvf_log_stop(MemoryListener *listener,
+                         MemoryRegionSection *section, int old, int new)
+{
+    if (new != 0) {
+        return;
+    }
+
+    hvf_set_dirty_tracking(section, 0);
+}
+
+static void hvf_log_sync(MemoryListener *listener,
+                         MemoryRegionSection *section)
+{
+    /*
+     * sync of dirty pages is handled elsewhere; just make sure we keep
+     * tracking the region.
+     */
+    hvf_set_dirty_tracking(section, 1);
+}
+
+static void hvf_region_add(MemoryListener *listener,
+                           MemoryRegionSection *section)
+{
+    hvf_set_phys_mem(section, true);
+}
+
+static void hvf_region_del(MemoryListener *listener,
+                           MemoryRegionSection *section)
+{
+    hvf_set_phys_mem(section, false);
+}
+
+static MemoryListener hvf_memory_listener = {
+    .priority = 10,
+    .region_add = hvf_region_add,
+    .region_del = hvf_region_del,
+    .log_start = hvf_log_start,
+    .log_stop = hvf_log_stop,
+    .log_sync = hvf_log_sync,
+};
+
+static void dummy_signal(int sig)
+{
+}
+
+bool hvf_allowed;
+
+static int hvf_accel_init(MachineState *ms)
+{
+    int x;
+    hv_return_t ret;
+    HVFState *s;
+
+    ret = hv_vm_create(HV_VM_DEFAULT);
+    assert_hvf_ok(ret);
+
+    s = g_new0(HVFState, 1);
+
+    s->num_slots = 32;
+    for (x = 0; x < s->num_slots; ++x) {
+        s->slots[x].size = 0;
+        s->slots[x].slot_id = x;
+    }
+
+    hvf_state = s;
+    memory_listener_register(&hvf_memory_listener, &address_space_memory);
+    return 0;
+}
+
+static void hvf_accel_class_init(ObjectClass *oc, void *data)
+{
+    AccelClass *ac = ACCEL_CLASS(oc);
+    ac->name = "HVF";
+    ac->init_machine = hvf_accel_init;
+    ac->allowed = &hvf_allowed;
+}
+
+static const TypeInfo hvf_accel_type = {
+    .name = TYPE_HVF_ACCEL,
+    .parent = TYPE_ACCEL,
+    .class_init = hvf_accel_class_init,
+};
+
+static void hvf_type_init(void)
+{
+    type_register_static(&hvf_accel_type);
+}
+
+type_init(hvf_type_init);
+
 /*
  * The HVF-specific vCPU thread function. This one should only run when the host
  * CPU supports the VMX "unrestricted guest" feature.
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@
 
 #include "hvf-accel-ops.h"
 
-HVFState *hvf_state;
-
-/* Memory slots */
-hvf_slot *hvf_find_overlap_slot(uint64_t start, uint64_t size)
-{
-    hvf_slot *slot;
-    int x;
-    for (x = 0; x < hvf_state->num_slots; ++x) {
-        slot = &hvf_state->slots[x];
-        if (slot->size && start < (slot->start + slot->size) &&
-            (start + size) > slot->start) {
-            return slot;
-        }
-    }
-    return NULL;
-}
-
-struct mac_slot {
-    int present;
-    uint64_t size;
-    uint64_t gpa_start;
-    uint64_t gva;
-};
-
-struct mac_slot mac_slots[32];
-
-static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags)
-{
-    struct mac_slot *macslot;
-    hv_return_t ret;
-
-    macslot = &mac_slots[slot->slot_id];
-
-    if (macslot->present) {
-        if (macslot->size != slot->size) {
-            macslot->present = 0;
-            ret = hv_vm_unmap(macslot->gpa_start, macslot->size);
-            assert_hvf_ok(ret);
-        }
-    }
-
-    if (!slot->size) {
-        return 0;
-    }
-
-    macslot->present = 1;
-    macslot->gpa_start = slot->start;
-    macslot->size = slot->size;
-    ret = hv_vm_map((hv_uvaddr_t)slot->mem, slot->start, slot->size, flags);
-    assert_hvf_ok(ret);
-    return 0;
-}
-
-void hvf_set_phys_mem(MemoryRegionSection *section, bool add)
-{
-    hvf_slot *mem;
-    MemoryRegion *area = section->mr;
-    bool writeable = !area->readonly && !area->rom_device;
-    hv_memory_flags_t flags;
-
-    if (!memory_region_is_ram(area)) {
-        if (writeable) {
-            return;
-        } else if (!memory_region_is_romd(area)) {
-            /*
-             * If the memory device is not in romd_mode, then we actually want
-             * to remove the hvf memory slot so all accesses will trap.
-             */
-             add = false;
-        }
-    }
-
-    mem = hvf_find_overlap_slot(
-            section->offset_within_address_space,
-            int128_get64(section->size));
-
-    if (mem && add) {
-        if (mem->size == int128_get64(section->size) &&
-            mem->start == section->offset_within_address_space &&
-            mem->mem == (memory_region_get_ram_ptr(area) +
-            section->offset_within_region)) {
-            return; /* Same region was attempted to register, go away. */
-        }
-    }
-
-    /* Region needs to be reset. set the size to 0 and remap it. */
-    if (mem) {
-        mem->size = 0;
-        if (do_hvf_set_memory(mem, 0)) {
-            error_report("Failed to reset overlapping slot");
-            abort();
-        }
-    }
-
-    if (!add) {
-        return;
-    }
-
-    if (area->readonly ||
-        (!memory_region_is_ram(area) && memory_region_is_romd(area))) {
-        flags = HV_MEMORY_READ | HV_MEMORY_EXEC;
-    } else {
-        flags = HV_MEMORY_READ | HV_MEMORY_WRITE | HV_MEMORY_EXEC;
-    }
-
-    /* Now make a new slot. */
-    int x;
-
-    for (x = 0; x < hvf_state->num_slots; ++x) {
-        mem = &hvf_state->slots[x];
-        if (!mem->size) {
-            break;
-        }
-    }
-
-    if (x == hvf_state->num_slots) {
-        error_report("No free slots");
-        abort();
-    }
-
-    mem->size = int128_get64(section->size);
-    mem->mem = memory_region_get_ram_ptr(area) + section->offset_within_region;
-    mem->start = section->offset_within_address_space;
-    mem->region = area;
-
-    if (do_hvf_set_memory(mem, flags)) {
-        error_report("Error registering new memory slot");
-        abort();
-    }
-}
-
 void vmx_update_tpr(CPUState *cpu)
 {
     /* TODO: need integrate APIC handling */
@@ -XXX,XX +XXX,XX @@ void hvf_handle_io(CPUArchState *env, uint16_t port, void *buffer,
     }
 }
 
-static void do_hvf_cpu_synchronize_state(CPUState *cpu, run_on_cpu_data arg)
-{
-    if (!cpu->vcpu_dirty) {
-        hvf_get_registers(cpu);
-        cpu->vcpu_dirty = true;
-    }
-}
-
-void hvf_cpu_synchronize_state(CPUState *cpu)
-{
-    if (!cpu->vcpu_dirty) {
-        run_on_cpu(cpu, do_hvf_cpu_synchronize_state, RUN_ON_CPU_NULL);
-    }
-}
-
-static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu,
-                                              run_on_cpu_data arg)
-{
-    hvf_put_registers(cpu);
-    cpu->vcpu_dirty = false;
-}
-
-void hvf_cpu_synchronize_post_reset(CPUState *cpu)
-{
-    run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
-}
-
-static void do_hvf_cpu_synchronize_post_init(CPUState *cpu,
-                                             run_on_cpu_data arg)
-{
-    hvf_put_registers(cpu);
-    cpu->vcpu_dirty = false;
-}
-
-void hvf_cpu_synchronize_post_init(CPUState *cpu)
-{
-    run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
-}
-
-static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu,
-                                              run_on_cpu_data arg)
-{
-    cpu->vcpu_dirty = true;
-}
-
-void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu)
-{
-    run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL);
-}
-
 static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual)
 {
     int read, write;
@@ -XXX,XX +XXX,XX @@ static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual)
     return false;
 }
 
-static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on)
-{
-    hvf_slot *slot;
-
-    slot = hvf_find_overlap_slot(
-            section->offset_within_address_space,
-            int128_get64(section->size));
-
-    /* protect region against writes; begin tracking it */
-    if (on) {
-        slot->flags |= HVF_SLOT_LOG;
-        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
-                      HV_MEMORY_READ);
-    /* stop tracking region*/
-    } else {
-        slot->flags &= ~HVF_SLOT_LOG;
-        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
-                      HV_MEMORY_READ | HV_MEMORY_WRITE);
-    }
-}
-
-static void hvf_log_start(MemoryListener *listener,
-                          MemoryRegionSection *section, int old, int new)
-{
-    if (old != 0) {
-        return;
-    }
-
-    hvf_set_dirty_tracking(section, 1);
-}
-
-static void hvf_log_stop(MemoryListener *listener,
-                         MemoryRegionSection *section, int old, int new)
-{
-    if (new != 0) {
-        return;
-    }
-
-    hvf_set_dirty_tracking(section, 0);
-}
-
-static void hvf_log_sync(MemoryListener *listener,
-                         MemoryRegionSection *section)
-{
-    /*
-     * sync of dirty pages is handled elsewhere; just make sure we keep
-     * tracking the region.
-     */
-    hvf_set_dirty_tracking(section, 1);
-}
-
-static void hvf_region_add(MemoryListener *listener,
-                           MemoryRegionSection *section)
-{
-    hvf_set_phys_mem(section, true);
-}
-
-static void hvf_region_del(MemoryListener *listener,
-                           MemoryRegionSection *section)
-{
-    hvf_set_phys_mem(section, false);
-}
-
-static MemoryListener hvf_memory_listener = {
-    .priority = 10,
-    .region_add = hvf_region_add,
-    .region_del = hvf_region_del,
-    .log_start = hvf_log_start,
-    .log_stop = hvf_log_stop,
-    .log_sync = hvf_log_sync,
-};
-
 void hvf_vcpu_destroy(CPUState *cpu)
 {
     X86CPU *x86_cpu = X86_CPU(cpu);
@@ -XXX,XX +XXX,XX @@ void hvf_vcpu_destroy(CPUState *cpu)
     assert_hvf_ok(ret);
 }
 
-static void dummy_signal(int sig)
-{
-}
-
 static void init_tsc_freq(CPUX86State *env)
 {
     size_t length;
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
 
     return ret;
 }
-
-bool hvf_allowed;
-
-static int hvf_accel_init(MachineState *ms)
-{
-    int x;
-    hv_return_t ret;
-    HVFState *s;
-
-    ret = hv_vm_create(HV_VM_DEFAULT);
-    assert_hvf_ok(ret);
-
-    s = g_new0(HVFState, 1);
- 
-    s->num_slots = 32;
-    for (x = 0; x < s->num_slots; ++x) {
-        s->slots[x].size = 0;
-        s->slots[x].slot_id = x;
-    }
-  
-    hvf_state = s;
-    memory_listener_register(&hvf_memory_listener, &address_space_memory);
-    return 0;
-}
-
-static void hvf_accel_class_init(ObjectClass *oc, void *data)
-{
-    AccelClass *ac = ACCEL_CLASS(oc);
-    ac->name = "HVF";
-    ac->init_machine = hvf_accel_init;
-    ac->allowed = &hvf_allowed;
-}
-
-static const TypeInfo hvf_accel_type = {
-    .name = TYPE_HVF_ACCEL,
-    .parent = TYPE_ACCEL,
-    .class_init = hvf_accel_class_init,
-};
-
-static void hvf_type_init(void)
-{
-    type_register_static(&hvf_accel_type);
-}
-
-type_init(hvf_type_init);
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

This patch moves a few internal struct and constant defines over.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-5-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/sysemu/hvf_int.h   | 30 ++++++++++++++++++++++++++++++
 target/i386/hvf/hvf-i386.h | 31 +------------------------------
 2 files changed, 31 insertions(+), 30 deletions(-)

diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/hvf_int.h
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@
 
 #include <Hypervisor/hv.h>
 
+/* hvf_slot flags */
+#define HVF_SLOT_LOG (1 << 0)
+
+typedef struct hvf_slot {
+    uint64_t start;
+    uint64_t size;
+    uint8_t *mem;
+    int slot_id;
+    uint32_t flags;
+    MemoryRegion *region;
+} hvf_slot;
+
+typedef struct hvf_vcpu_caps {
+    uint64_t vmx_cap_pinbased;
+    uint64_t vmx_cap_procbased;
+    uint64_t vmx_cap_procbased2;
+    uint64_t vmx_cap_entry;
+    uint64_t vmx_cap_exit;
+    uint64_t vmx_cap_preemption_timer;
+} hvf_vcpu_caps;
+
+struct HVFState {
+    AccelState parent;
+    hvf_slot slots[32];
+    int num_slots;
+
+    hvf_vcpu_caps *hvf_caps;
+};
+extern HVFState *hvf_state;
+
 void hvf_set_phys_mem(MemoryRegionSection *, bool);
 void assert_hvf_ok(hv_return_t ret);
 hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t);
diff --git a/target/i386/hvf/hvf-i386.h b/target/i386/hvf/hvf-i386.h
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf-i386.h
+++ b/target/i386/hvf/hvf-i386.h
@@ -XXX,XX +XXX,XX @@
 
 #include "qemu/accel.h"
 #include "sysemu/hvf.h"
+#include "sysemu/hvf_int.h"
 #include "cpu.h"
 #include "x86.h"
 
-/* hvf_slot flags */
-#define HVF_SLOT_LOG (1 << 0)
-
-typedef struct hvf_slot {
-    uint64_t start;
-    uint64_t size;
-    uint8_t *mem;
-    int slot_id;
-    uint32_t flags;
-    MemoryRegion *region;
-} hvf_slot;
-
-typedef struct hvf_vcpu_caps {
-    uint64_t vmx_cap_pinbased;
-    uint64_t vmx_cap_procbased;
-    uint64_t vmx_cap_procbased2;
-    uint64_t vmx_cap_entry;
-    uint64_t vmx_cap_exit;
-    uint64_t vmx_cap_preemption_timer;
-} hvf_vcpu_caps;
-
-struct HVFState {
-    AccelState parent;
-    hvf_slot slots[32];
-    int num_slots;
-
-    hvf_vcpu_caps *hvf_caps;
-};
-extern HVFState *hvf_state;
-
 void hvf_handle_io(CPUArchState *, uint16_t, void *, int, int, int);
 
 #ifdef NEED_CPU_H
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

The hvf_set_phys_mem() function is only called within the same file.
Make it static.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-6-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/sysemu/hvf_int.h  | 1 -
 accel/hvf/hvf-accel-ops.c | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

From: Alexander Graf <agraf@csgraf.de>

The ARM version of Hypervisor.framework no longer defines these two
types, so let's just revert to standard ones.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-7-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/hvf/hvf-accel-ops.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@ static int do_hvf_set_memory(hvf_slot *slot, hv_memory_flags_t flags)
     macslot->present = 1;
     macslot->gpa_start = slot->start;
     macslot->size = slot->size;
-    ret = hv_vm_map((hv_uvaddr_t)slot->mem, slot->start, slot->size, flags);
+    ret = hv_vm_map(slot->mem, slot->start, slot->size, flags);
     assert_hvf_ok(ret);
     return 0;
 }
@@ -XXX,XX +XXX,XX @@ static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on)
     /* protect region against writes; begin tracking it */
     if (on) {
         slot->flags |= HVF_SLOT_LOG;
-        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
+        hv_vm_protect((uintptr_t)slot->start, (size_t)slot->size,
                       HV_MEMORY_READ);
     /* stop tracking region*/
     } else {
         slot->flags &= ~HVF_SLOT_LOG;
-        hv_vm_protect((hv_gpaddr_t)slot->start, (size_t)slot->size,
+        hv_vm_protect((uintptr_t)slot->start, (size_t)slot->size,
                       HV_MEMORY_READ | HV_MEMORY_WRITE);
     }
 }
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

This patch splits the vcpu init and destroy functions into a generic and
an architecture specific portion. This also allows us to move the generic
functions into the generic hvf code, removing exported functions.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-8-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/hvf/hvf-accel-ops.h |  2 --
 include/sysemu/hvf_int.h  |  2 ++
 accel/hvf/hvf-accel-ops.c | 30 ++++++++++++++++++++++++++++++
 target/i386/hvf/hvf.c     | 23 ++---------------------
 4 files changed, 34 insertions(+), 23 deletions(-)

diff --git a/accel/hvf/hvf-accel-ops.h b/accel/hvf/hvf-accel-ops.h
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.h
+++ b/accel/hvf/hvf-accel-ops.h
@@ -XXX,XX +XXX,XX @@
 
 #include "sysemu/cpus.h"
 
-int hvf_init_vcpu(CPUState *);
 int hvf_vcpu_exec(CPUState *);
 void hvf_cpu_synchronize_state(CPUState *);
 void hvf_cpu_synchronize_post_reset(CPUState *);
 void hvf_cpu_synchronize_post_init(CPUState *);
 void hvf_cpu_synchronize_pre_loadvm(CPUState *);
-void hvf_vcpu_destroy(CPUState *);
 
 #endif /* HVF_CPUS_H */
diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/hvf_int.h
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@ struct HVFState {
 extern HVFState *hvf_state;
 
 void assert_hvf_ok(hv_return_t ret);
+int hvf_arch_init_vcpu(CPUState *cpu);
+void hvf_arch_vcpu_destroy(CPUState *cpu);
 hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t);
 int hvf_put_registers(CPUState *);
 int hvf_get_registers(CPUState *);
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@ static void hvf_type_init(void)
 
 type_init(hvf_type_init);
 
+static void hvf_vcpu_destroy(CPUState *cpu)
+{
+    hv_return_t ret = hv_vcpu_destroy(cpu->hvf_fd);
+    assert_hvf_ok(ret);
+
+    hvf_arch_vcpu_destroy(cpu);
+}
+
+static int hvf_init_vcpu(CPUState *cpu)
+{
+    int r;
+
+    /* init cpu signals */
+    sigset_t set;
+    struct sigaction sigact;
+
+    memset(&sigact, 0, sizeof(sigact));
+    sigact.sa_handler = dummy_signal;
+    sigaction(SIG_IPI, &sigact, NULL);
+
+    pthread_sigmask(SIG_BLOCK, NULL, &set);
+    sigdelset(&set, SIG_IPI);
+
+    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT);
+    cpu->vcpu_dirty = 1;
+    assert_hvf_ok(r);
+
+    return hvf_arch_init_vcpu(cpu);
+}
+
 /*
  * The HVF-specific vCPU thread function. This one should only run when the host
  * CPU supports the VMX "unrestricted guest" feature.
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@ static bool ept_emulation_fault(hvf_slot *slot, uint64_t gpa, uint64_t ept_qual)
     return false;
 }
 
-void hvf_vcpu_destroy(CPUState *cpu)
+void hvf_arch_vcpu_destroy(CPUState *cpu)
 {
     X86CPU *x86_cpu = X86_CPU(cpu);
     CPUX86State *env = &x86_cpu->env;
 
-    hv_return_t ret = hv_vcpu_destroy((hv_vcpuid_t)cpu->hvf_fd);
     g_free(env->hvf_mmio_buf);
-    assert_hvf_ok(ret);
 }
 
 static void init_tsc_freq(CPUX86State *env)
@@ -XXX,XX +XXX,XX @@ static inline bool apic_bus_freq_is_known(CPUX86State *env)
     return env->apic_bus_freq != 0;
 }
 
-int hvf_init_vcpu(CPUState *cpu)
+int hvf_arch_init_vcpu(CPUState *cpu)
 {
-
     X86CPU *x86cpu = X86_CPU(cpu);
     CPUX86State *env = &x86cpu->env;
-    int r;
-
-    /* init cpu signals */
-    sigset_t set;
-    struct sigaction sigact;
-
-    memset(&sigact, 0, sizeof(sigact));
-    sigact.sa_handler = dummy_signal;
-    sigaction(SIG_IPI, &sigact, NULL);
-
-    pthread_sigmask(SIG_BLOCK, NULL, &set);
-    sigdelset(&set, SIG_IPI);
 
     init_emu();
     init_decoder();
@@ -XXX,XX +XXX,XX @@ int hvf_init_vcpu(CPUState *cpu)
         }
     }
 
-    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT);
-    cpu->vcpu_dirty = 1;
-    assert_hvf_ok(r);
-
     if (hv_vmx_read_capability(HV_VMX_CAP_PINBASED,
         &hvf_state->hvf_caps->vmx_cap_pinbased)) {
         abort();
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

There is no reason to call the hvf specific hvf_cpu_synchronize_state()
when we can just use the generic cpu_synchronize_state() instead. This
allows us to have less dependency on internal function definitions and
allows us to make hvf_cpu_synchronize_state() static.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-9-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/hvf/hvf-accel-ops.h | 1 -
 accel/hvf/hvf-accel-ops.c | 2 +-
 target/i386/hvf/x86hvf.c  | 9 ++++-----
 3 files changed, 5 insertions(+), 7 deletions(-)

From: Alexander Graf <agraf@csgraf.de>

The hvf accel synchronize functions are only used as input for local
callback functions, so we can make them static.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-10-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/hvf/hvf-accel-ops.h | 3 ---
 accel/hvf/hvf-accel-ops.c | 6 +++---
 2 files changed, 3 insertions(+), 6 deletions(-)

From: Alexander Graf <agraf@csgraf.de>

We can move the definition of hvf_vcpu_exec() into our internal
hvf header, obsoleting the need for hvf-accel-ops.h.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-11-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/hvf/hvf-accel-ops.h | 17 -----------------
 include/sysemu/hvf_int.h  |  1 +
 accel/hvf/hvf-accel-ops.c |  2 --
 target/i386/hvf/hvf.c     |  2 --
 4 files changed, 1 insertion(+), 21 deletions(-)
 delete mode 100644 accel/hvf/hvf-accel-ops.h

diff --git a/accel/hvf/hvf-accel-ops.h b/accel/hvf/hvf-accel-ops.h
deleted file mode 100644
index XXXXXXX..XXXXXXX
--- a/accel/hvf/hvf-accel-ops.h
+++ /dev/null
@@ -XXX,XX +XXX,XX @@
-/*
- * Accelerator CPUS Interface
- *
- * Copyright 2020 SUSE LLC
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#ifndef HVF_CPUS_H
-#define HVF_CPUS_H
-
-#include "sysemu/cpus.h"
-
-int hvf_vcpu_exec(CPUState *);
-
-#endif /* HVF_CPUS_H */
diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/hvf_int.h
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@ extern HVFState *hvf_state;
 void assert_hvf_ok(hv_return_t ret);
 int hvf_arch_init_vcpu(CPUState *cpu);
 void hvf_arch_vcpu_destroy(CPUState *cpu);
+int hvf_vcpu_exec(CPUState *);
 hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t);
 int hvf_put_registers(CPUState *);
 int hvf_get_registers(CPUState *);
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@
 #include "sysemu/runstate.h"
 #include "qemu/guest-random.h"
 
-#include "hvf-accel-ops.h"
-
 HVFState *hvf_state;
 
 /* Memory slots */
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@
 #include "qemu/accel.h"
 #include "target/i386/cpu.h"
 
-#include "hvf-accel-ops.h"
-
 void vmx_update_tpr(CPUState *cpu)
 {
     /* TODO: need integrate APIC handling */
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

We will need more than a single field for hvf going forward. To keep
the global vcpu struct uncluttered, let's allocate a special hvf vcpu
struct, similar to how hax does it.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Roman Bolshakov <r.bolshakov@yadro.com>
Tested-by: Roman Bolshakov <r.bolshakov@yadro.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-12-agraf@csgraf.de
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 include/hw/core/cpu.h       |   3 +-
 include/sysemu/hvf_int.h    |   4 +
 target/i386/hvf/vmx.h       |  24 +++--
 accel/hvf/hvf-accel-ops.c   |   8 +-
 target/i386/hvf/hvf.c       | 104 +++++++++---------
 target/i386/hvf/x86.c       |  28 ++---
 target/i386/hvf/x86_descr.c |  26 ++---
 target/i386/hvf/x86_emu.c   |  62 +++++------
 target/i386/hvf/x86_mmu.c   |   4 +-
 target/i386/hvf/x86_task.c  |  12 +--
 target/i386/hvf/x86hvf.c    | 210 ++++++++++++++++++------------------
 11 files changed, 248 insertions(+), 237 deletions(-)

diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index XXXXXXX..XXXXXXX 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -XXX,XX +XXX,XX @@ struct KVMState;
 struct kvm_run;
 
 struct hax_vcpu_state;
+struct hvf_vcpu_state;
 
 #define TB_JMP_CACHE_BITS 12
 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS)
@@ -XXX,XX +XXX,XX @@ struct CPUState {
 
     struct hax_vcpu_state *hax_vcpu;
 
-    int hvf_fd;
+    struct hvf_vcpu_state *hvf;
 
     /* track IOMMUs whose translations we've cached in the TCG TLB */
     GArray *iommu_notifiers;
diff --git a/include/sysemu/hvf_int.h b/include/sysemu/hvf_int.h
index XXXXXXX..XXXXXXX 100644
--- a/include/sysemu/hvf_int.h
+++ b/include/sysemu/hvf_int.h
@@ -XXX,XX +XXX,XX @@ struct HVFState {
 };
 extern HVFState *hvf_state;
 
+struct hvf_vcpu_state {
+    int fd;
+};
+
 void assert_hvf_ok(hv_return_t ret);
 int hvf_arch_init_vcpu(CPUState *cpu);
 void hvf_arch_vcpu_destroy(CPUState *cpu);
diff --git a/target/i386/hvf/vmx.h b/target/i386/hvf/vmx.h
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/vmx.h
+++ b/target/i386/hvf/vmx.h
@@ -XXX,XX +XXX,XX @@
 #include "vmcs.h"
 #include "cpu.h"
 #include "x86.h"
+#include "sysemu/hvf.h"
+#include "sysemu/hvf_int.h"
 
 #include "exec/address-spaces.h"
 
@@ -XXX,XX +XXX,XX @@ static inline void macvm_set_rip(CPUState *cpu, uint64_t rip)
     uint64_t val;
 
     /* BUG, should take considering overlap.. */
-    wreg(cpu->hvf_fd, HV_X86_RIP, rip);
+    wreg(cpu->hvf->fd, HV_X86_RIP, rip);
     env->eip = rip;
 
     /* after moving forward in rip, we need to clean INTERRUPTABILITY */
-   val = rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY);
+   val = rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY);
    if (val & (VMCS_INTERRUPTIBILITY_STI_BLOCKING |
                VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) {
         env->hflags &= ~HF_INHIBIT_IRQ_MASK;
-        wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY,
+        wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY,
                val & ~(VMCS_INTERRUPTIBILITY_STI_BLOCKING |
                VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING));
    }
@@ -XXX,XX +XXX,XX @@ static inline void vmx_clear_nmi_blocking(CPUState *cpu)
     CPUX86State *env = &x86_cpu->env;
 
     env->hflags2 &= ~HF2_NMI_MASK;
-    uint32_t gi = (uint32_t) rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY);
+    uint32_t gi = (uint32_t) rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY);
     gi &= ~VMCS_INTERRUPTIBILITY_NMI_BLOCKING;
-    wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
+    wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
 }
 
 static inline void vmx_set_nmi_blocking(CPUState *cpu)
@@ -XXX,XX +XXX,XX @@ static inline void vmx_set_nmi_blocking(CPUState *cpu)
     CPUX86State *env = &x86_cpu->env;
 
     env->hflags2 |= HF2_NMI_MASK;
-    uint32_t gi = (uint32_t)rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY);
+    uint32_t gi = (uint32_t)rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY);
     gi |= VMCS_INTERRUPTIBILITY_NMI_BLOCKING;
-    wvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
+    wvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY, gi);
 }
 
 static inline void vmx_set_nmi_window_exiting(CPUState *cpu)
 {
     uint64_t val;
-    val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
-    wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val |
+    val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS);
+    wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val |
           VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING);
 
 }
@@ -XXX,XX +XXX,XX @@ static inline void vmx_clear_nmi_window_exiting(CPUState *cpu)
 {
 
     uint64_t val;
-    val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
-    wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val &
+    val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS);
+    wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val &
           ~VMCS_PRI_PROC_BASED_CTLS_NMI_WINDOW_EXITING);
 }
 
diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@ type_init(hvf_type_init);
 
 static void hvf_vcpu_destroy(CPUState *cpu)
 {
-    hv_return_t ret = hv_vcpu_destroy(cpu->hvf_fd);
+    hv_return_t ret = hv_vcpu_destroy(cpu->hvf->fd);
     assert_hvf_ok(ret);
 
     hvf_arch_vcpu_destroy(cpu);
+    g_free(cpu->hvf);
+    cpu->hvf = NULL;
 }
 
 static int hvf_init_vcpu(CPUState *cpu)
 {
     int r;
 
+    cpu->hvf = g_malloc0(sizeof(*cpu->hvf));
+
     /* init cpu signals */
     sigset_t set;
     struct sigaction sigact;
@@ -XXX,XX +XXX,XX @@ static int hvf_init_vcpu(CPUState *cpu)
     pthread_sigmask(SIG_BLOCK, NULL, &set);
     sigdelset(&set, SIG_IPI);
 
-    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf_fd, HV_VCPU_DEFAULT);
+    r = hv_vcpu_create((hv_vcpuid_t *)&cpu->hvf->fd, HV_VCPU_DEFAULT);
     cpu->vcpu_dirty = 1;
     assert_hvf_ok(r);
 
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -XXX,XX +XXX,XX @@ void vmx_update_tpr(CPUState *cpu)
     int tpr = cpu_get_apic_tpr(x86_cpu->apic_state) << 4;
     int irr = apic_get_highest_priority_irr(x86_cpu->apic_state);
 
-    wreg(cpu->hvf_fd, HV_X86_TPR, tpr);
+    wreg(cpu->hvf->fd, HV_X86_TPR, tpr);
     if (irr == -1) {
-        wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0);
+        wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, 0);
     } else {
-        wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 :
+        wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, (irr > tpr) ? tpr >> 4 :
               irr >> 4);
     }
 }
@@ -XXX,XX +XXX,XX @@ void vmx_update_tpr(CPUState *cpu)
 static void update_apic_tpr(CPUState *cpu)
 {
     X86CPU *x86_cpu = X86_CPU(cpu);
-    int tpr = rreg(cpu->hvf_fd, HV_X86_TPR) >> 4;
+    int tpr = rreg(cpu->hvf->fd, HV_X86_TPR) >> 4;
     cpu_set_apic_tpr(x86_cpu->apic_state, tpr);
 }
 
@@ -XXX,XX +XXX,XX @@ int hvf_arch_init_vcpu(CPUState *cpu)
     }
 
     /* set VMCS control fields */
-    wvmcs(cpu->hvf_fd, VMCS_PIN_BASED_CTLS,
+    wvmcs(cpu->hvf->fd, VMCS_PIN_BASED_CTLS,
           cap2ctrl(hvf_state->hvf_caps->vmx_cap_pinbased,
           VMCS_PIN_BASED_CTLS_EXTINT |
           VMCS_PIN_BASED_CTLS_NMI |
           VMCS_PIN_BASED_CTLS_VNMI));
-    wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS,
+    wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS,
           cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased,
           VMCS_PRI_PROC_BASED_CTLS_HLT |
           VMCS_PRI_PROC_BASED_CTLS_MWAIT |
           VMCS_PRI_PROC_BASED_CTLS_TSC_OFFSET |
           VMCS_PRI_PROC_BASED_CTLS_TPR_SHADOW) |
           VMCS_PRI_PROC_BASED_CTLS_SEC_CONTROL);
-    wvmcs(cpu->hvf_fd, VMCS_SEC_PROC_BASED_CTLS,
+    wvmcs(cpu->hvf->fd, VMCS_SEC_PROC_BASED_CTLS,
           cap2ctrl(hvf_state->hvf_caps->vmx_cap_procbased2,
                    VMCS_PRI_PROC_BASED2_CTLS_APIC_ACCESSES));
 
-    wvmcs(cpu->hvf_fd, VMCS_ENTRY_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_entry,
+    wvmcs(cpu->hvf->fd, VMCS_ENTRY_CTLS, cap2ctrl(hvf_state->hvf_caps->vmx_cap_entry,
           0));
-    wvmcs(cpu->hvf_fd, VMCS_EXCEPTION_BITMAP, 0); /* Double fault */
+    wvmcs(cpu->hvf->fd, VMCS_EXCEPTION_BITMAP, 0); /* Double fault */
 
-    wvmcs(cpu->hvf_fd, VMCS_TPR_THRESHOLD, 0);
+    wvmcs(cpu->hvf->fd, VMCS_TPR_THRESHOLD, 0);
 
     x86cpu = X86_CPU(cpu);
     x86cpu->env.xsave_buf = qemu_memalign(4096, 4096);
 
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_STAR, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_LSTAR, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_CSTAR, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FMASK, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_FSBASE, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_GSBASE, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_KERNELGSBASE, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_TSC_AUX, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_TSC, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_CS, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_EIP, 1);
-    hv_vcpu_enable_native_msr(cpu->hvf_fd, MSR_IA32_SYSENTER_ESP, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_STAR, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_LSTAR, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_CSTAR, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_FMASK, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_FSBASE, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_GSBASE, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_KERNELGSBASE, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_TSC_AUX, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_TSC, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_SYSENTER_CS, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_SYSENTER_EIP, 1);
+    hv_vcpu_enable_native_msr(cpu->hvf->fd, MSR_IA32_SYSENTER_ESP, 1);
 
     return 0;
 }
@@ -XXX,XX +XXX,XX @@ static void hvf_store_events(CPUState *cpu, uint32_t ins_len, uint64_t idtvec_in
         }
         if (idtvec_info & VMCS_IDT_VEC_ERRCODE_VALID) {
             env->has_error_code = true;
-            env->error_code = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_ERROR);
+            env->error_code = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_ERROR);
         }
     }
-    if ((rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) &
+    if ((rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY) &
         VMCS_INTERRUPTIBILITY_NMI_BLOCKING)) {
         env->hflags2 |= HF2_NMI_MASK;
     } else {
         env->hflags2 &= ~HF2_NMI_MASK;
     }
-    if (rvmcs(cpu->hvf_fd, VMCS_GUEST_INTERRUPTIBILITY) &
+    if (rvmcs(cpu->hvf->fd, VMCS_GUEST_INTERRUPTIBILITY) &
          (VMCS_INTERRUPTIBILITY_STI_BLOCKING |
          VMCS_INTERRUPTIBILITY_MOVSS_BLOCKING)) {
         env->hflags |= HF_INHIBIT_IRQ_MASK;
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
             return EXCP_HLT;
         }
 
-        hv_return_t r  = hv_vcpu_run(cpu->hvf_fd);
+        hv_return_t r  = hv_vcpu_run(cpu->hvf->fd);
         assert_hvf_ok(r);
 
         /* handle VMEXIT */
-        uint64_t exit_reason = rvmcs(cpu->hvf_fd, VMCS_EXIT_REASON);
-        uint64_t exit_qual = rvmcs(cpu->hvf_fd, VMCS_EXIT_QUALIFICATION);
-        uint32_t ins_len = (uint32_t)rvmcs(cpu->hvf_fd,
+        uint64_t exit_reason = rvmcs(cpu->hvf->fd, VMCS_EXIT_REASON);
+        uint64_t exit_qual = rvmcs(cpu->hvf->fd, VMCS_EXIT_QUALIFICATION);
+        uint32_t ins_len = (uint32_t)rvmcs(cpu->hvf->fd,
                                            VMCS_EXIT_INSTRUCTION_LENGTH);
 
-        uint64_t idtvec_info = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO);
+        uint64_t idtvec_info = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_INFO);
 
         hvf_store_events(cpu, ins_len, idtvec_info);
-        rip = rreg(cpu->hvf_fd, HV_X86_RIP);
-        env->eflags = rreg(cpu->hvf_fd, HV_X86_RFLAGS);
+        rip = rreg(cpu->hvf->fd, HV_X86_RIP);
+        env->eflags = rreg(cpu->hvf->fd, HV_X86_RFLAGS);
 
         qemu_mutex_lock_iothread();
 
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
         case EXIT_REASON_EPT_FAULT:
         {
             hvf_slot *slot;
-            uint64_t gpa = rvmcs(cpu->hvf_fd, VMCS_GUEST_PHYSICAL_ADDRESS);
+            uint64_t gpa = rvmcs(cpu->hvf->fd, VMCS_GUEST_PHYSICAL_ADDRESS);
 
             if (((idtvec_info & VMCS_IDT_VEC_VALID) == 0) &&
                 ((exit_qual & EXIT_QUAL_NMIUDTI) != 0)) {
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
                 store_regs(cpu);
                 break;
             } else if (!string && !in) {
-                RAX(env) = rreg(cpu->hvf_fd, HV_X86_RAX);
+                RAX(env) = rreg(cpu->hvf->fd, HV_X86_RAX);
                 hvf_handle_io(env, port, &RAX(env), 1, size, 1);
                 macvm_set_rip(cpu, rip + ins_len);
                 break;
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
             break;
         }
         case EXIT_REASON_CPUID: {
-            uint32_t rax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX);
-            uint32_t rbx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RBX);
-            uint32_t rcx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX);
-            uint32_t rdx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX);
+            uint32_t rax = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RAX);
+            uint32_t rbx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RBX);
+            uint32_t rcx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RCX);
+            uint32_t rdx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RDX);
 
             if (rax == 1) {
                 /* CPUID1.ecx.OSXSAVE needs to know CR4 */
-                env->cr[4] = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR4);
+                env->cr[4] = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR4);
             }
             hvf_cpu_x86_cpuid(env, rax, rcx, &rax, &rbx, &rcx, &rdx);
 
-            wreg(cpu->hvf_fd, HV_X86_RAX, rax);
-            wreg(cpu->hvf_fd, HV_X86_RBX, rbx);
-            wreg(cpu->hvf_fd, HV_X86_RCX, rcx);
-            wreg(cpu->hvf_fd, HV_X86_RDX, rdx);
+            wreg(cpu->hvf->fd, HV_X86_RAX, rax);
+            wreg(cpu->hvf->fd, HV_X86_RBX, rbx);
+            wreg(cpu->hvf->fd, HV_X86_RCX, rcx);
+            wreg(cpu->hvf->fd, HV_X86_RDX, rdx);
 
             macvm_set_rip(cpu, rip + ins_len);
             break;
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
         case EXIT_REASON_XSETBV: {
             X86CPU *x86_cpu = X86_CPU(cpu);
             CPUX86State *env = &x86_cpu->env;
-            uint32_t eax = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RAX);
-            uint32_t ecx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RCX);
-            uint32_t edx = (uint32_t)rreg(cpu->hvf_fd, HV_X86_RDX);
+            uint32_t eax = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RAX);
+            uint32_t ecx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RCX);
+            uint32_t edx = (uint32_t)rreg(cpu->hvf->fd, HV_X86_RDX);
 
             if (ecx) {
                 macvm_set_rip(cpu, rip + ins_len);
                 break;
             }
             env->xcr0 = ((uint64_t)edx << 32) | eax;
-            wreg(cpu->hvf_fd, HV_X86_XCR0, env->xcr0 | 1);
+            wreg(cpu->hvf->fd, HV_X86_XCR0, env->xcr0 | 1);
             macvm_set_rip(cpu, rip + ins_len);
             break;
         }
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
 
             switch (cr) {
             case 0x0: {
-                macvm_set_cr0(cpu->hvf_fd, RRX(env, reg));
+                macvm_set_cr0(cpu->hvf->fd, RRX(env, reg));
                 break;
             }
             case 4: {
-                macvm_set_cr4(cpu->hvf_fd, RRX(env, reg));
+                macvm_set_cr4(cpu->hvf->fd, RRX(env, reg));
                 break;
             }
             case 8: {
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
             break;
         }
         case EXIT_REASON_TASK_SWITCH: {
-            uint64_t vinfo = rvmcs(cpu->hvf_fd, VMCS_IDT_VECTORING_INFO);
+            uint64_t vinfo = rvmcs(cpu->hvf->fd, VMCS_IDT_VECTORING_INFO);
             x68_segment_selector sel = {.sel = exit_qual & 0xffff};
             vmx_handle_task_switch(cpu, sel, (exit_qual >> 30) & 0x3,
              vinfo & VMCS_INTR_VALID, vinfo & VECTORING_INFO_VECTOR_MASK, vinfo
@@ -XXX,XX +XXX,XX @@ int hvf_vcpu_exec(CPUState *cpu)
             break;
         }
         case EXIT_REASON_RDPMC:
-            wreg(cpu->hvf_fd, HV_X86_RAX, 0);
-            wreg(cpu->hvf_fd, HV_X86_RDX, 0);
+            wreg(cpu->hvf->fd, HV_X86_RAX, 0);
+            wreg(cpu->hvf->fd, HV_X86_RDX, 0);
             macvm_set_rip(cpu, rip + ins_len);
             break;
         case VMX_REASON_VMCALL:
diff --git a/target/i386/hvf/x86.c b/target/i386/hvf/x86.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86.c
+++ b/target/i386/hvf/x86.c
@@ -XXX,XX +XXX,XX @@ bool x86_read_segment_descriptor(struct CPUState *cpu,
     }
 
     if (GDT_SEL == sel.ti) {
-        base  = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE);
-        limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT);
+        base  = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_BASE);
+        limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_LIMIT);
     } else {
-        base  = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE);
-        limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT);
+        base  = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_BASE);
+        limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_LIMIT);
     }
 
     if (sel.index * 8 >= limit) {
@@ -XXX,XX +XXX,XX @@ bool x86_write_segment_descriptor(struct CPUState *cpu,
     uint32_t limit;
     
     if (GDT_SEL == sel.ti) {
-        base  = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_BASE);
-        limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_GDTR_LIMIT);
+        base  = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_BASE);
+        limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_GDTR_LIMIT);
     } else {
-        base  = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_BASE);
-        limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_LDTR_LIMIT);
+        base  = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_BASE);
+        limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_LDTR_LIMIT);
     }
     
     if (sel.index * 8 >= limit) {
@@ -XXX,XX +XXX,XX @@ bool x86_write_segment_descriptor(struct CPUState *cpu,
 bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc,
                         int gate)
 {
-    target_ulong base  = rvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_BASE);
-    uint32_t limit = rvmcs(cpu->hvf_fd, VMCS_GUEST_IDTR_LIMIT);
+    target_ulong base  = rvmcs(cpu->hvf->fd, VMCS_GUEST_IDTR_BASE);
+    uint32_t limit = rvmcs(cpu->hvf->fd, VMCS_GUEST_IDTR_LIMIT);
 
     memset(idt_desc, 0, sizeof(*idt_desc));
     if (gate * 8 >= limit) {
@@ -XXX,XX +XXX,XX @@ bool x86_read_call_gate(struct CPUState *cpu, struct x86_call_gate *idt_desc,
 
 bool x86_is_protected(struct CPUState *cpu)
 {
-    uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0);
+    uint64_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0);
     return cr0 & CR0_PE;
 }
 
@@ -XXX,XX +XXX,XX @@ bool x86_is_v8086(struct CPUState *cpu)
 
 bool x86_is_long_mode(struct CPUState *cpu)
 {
-    return rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA;
+    return rvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER) & MSR_EFER_LMA;
 }
 
 bool x86_is_long64_mode(struct CPUState *cpu)
@@ -XXX,XX +XXX,XX @@ bool x86_is_long64_mode(struct CPUState *cpu)
 
 bool x86_is_paging_mode(struct CPUState *cpu)
 {
-    uint64_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0);
+    uint64_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0);
     return cr0 & CR0_PG;
 }
 
 bool x86_is_pae_enabled(struct CPUState *cpu)
 {
-    uint64_t cr4 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR4);
+    uint64_t cr4 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR4);
     return cr4 & CR4_PAE;
 }
 
diff --git a/target/i386/hvf/x86_descr.c b/target/i386/hvf/x86_descr.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86_descr.c
+++ b/target/i386/hvf/x86_descr.c
@@ -XXX,XX +XXX,XX @@ static const struct vmx_segment_field {
 
 uint32_t vmx_read_segment_limit(CPUState *cpu, X86Seg seg)
 {
-    return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit);
+    return (uint32_t)rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].limit);
 }
 
 uint32_t vmx_read_segment_ar(CPUState *cpu, X86Seg seg)
 {
-    return (uint32_t)rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].ar_bytes);
+    return (uint32_t)rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].ar_bytes);
 }
 
 uint64_t vmx_read_segment_base(CPUState *cpu, X86Seg seg)
 {
-    return rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].base);
+    return rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].base);
 }
 
 x68_segment_selector vmx_read_segment_selector(CPUState *cpu, X86Seg seg)
 {
     x68_segment_selector sel;
-    sel.sel = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector);
+    sel.sel = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].selector);
     return sel;
 }
 
 void vmx_write_segment_selector(struct CPUState *cpu, x68_segment_selector selector, X86Seg seg)
 {
-    wvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector, selector.sel);
+    wvmcs(cpu->hvf->fd, vmx_segment_fields[seg].selector, selector.sel);
 }
 
 void vmx_read_segment_descriptor(struct CPUState *cpu, struct vmx_segment *desc, X86Seg seg)
 {
-    desc->sel = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].selector);
-    desc->base = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].base);
-    desc->limit = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].limit);
-    desc->ar = rvmcs(cpu->hvf_fd, vmx_segment_fields[seg].ar_bytes);
+    desc->sel = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].selector);
+    desc->base = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].base);
+    desc->limit = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].limit);
+    desc->ar = rvmcs(cpu->hvf->fd, vmx_segment_fields[seg].ar_bytes);
 }
 
 void vmx_write_segment_descriptor(CPUState *cpu, struct vmx_segment *desc, X86Seg seg)
 {
     const struct vmx_segment_field *sf = &vmx_segment_fields[seg];
 
-    wvmcs(cpu->hvf_fd, sf->base, desc->base);
-    wvmcs(cpu->hvf_fd, sf->limit, desc->limit);
-    wvmcs(cpu->hvf_fd, sf->selector, desc->sel);
-    wvmcs(cpu->hvf_fd, sf->ar_bytes, desc->ar);
+    wvmcs(cpu->hvf->fd, sf->base, desc->base);
+    wvmcs(cpu->hvf->fd, sf->limit, desc->limit);
+    wvmcs(cpu->hvf->fd, sf->selector, desc->sel);
+    wvmcs(cpu->hvf->fd, sf->ar_bytes, desc->ar);
 }
 
 void x86_segment_descriptor_to_vmx(struct CPUState *cpu, x68_segment_selector selector, struct x86_segment_descriptor *desc, struct vmx_segment *vmx_desc)
diff --git a/target/i386/hvf/x86_emu.c b/target/i386/hvf/x86_emu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86_emu.c
+++ b/target/i386/hvf/x86_emu.c
@@ -XXX,XX +XXX,XX @@ void simulate_rdmsr(struct CPUState *cpu)
 
     switch (msr) {
     case MSR_IA32_TSC:
-        val = rdtscp() + rvmcs(cpu->hvf_fd, VMCS_TSC_OFFSET);
+        val = rdtscp() + rvmcs(cpu->hvf->fd, VMCS_TSC_OFFSET);
         break;
     case MSR_IA32_APICBASE:
         val = cpu_get_apic_base(X86_CPU(cpu)->apic_state);
@@ -XXX,XX +XXX,XX @@ void simulate_rdmsr(struct CPUState *cpu)
         val = x86_cpu->ucode_rev;
         break;
     case MSR_EFER:
-        val = rvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER);
+        val = rvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER);
         break;
     case MSR_FSBASE:
-        val = rvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE);
+        val = rvmcs(cpu->hvf->fd, VMCS_GUEST_FS_BASE);
         break;
     case MSR_GSBASE:
-        val = rvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE);
+        val = rvmcs(cpu->hvf->fd, VMCS_GUEST_GS_BASE);
         break;
     case MSR_KERNELGSBASE:
-        val = rvmcs(cpu->hvf_fd, VMCS_HOST_FS_BASE);
+        val = rvmcs(cpu->hvf->fd, VMCS_HOST_FS_BASE);
         break;
     case MSR_STAR:
         abort();
@@ -XXX,XX +XXX,XX @@ void simulate_wrmsr(struct CPUState *cpu)
         cpu_set_apic_base(X86_CPU(cpu)->apic_state, data);
         break;
     case MSR_FSBASE:
-        wvmcs(cpu->hvf_fd, VMCS_GUEST_FS_BASE, data);
+        wvmcs(cpu->hvf->fd, VMCS_GUEST_FS_BASE, data);
         break;
     case MSR_GSBASE:
-        wvmcs(cpu->hvf_fd, VMCS_GUEST_GS_BASE, data);
+        wvmcs(cpu->hvf->fd, VMCS_GUEST_GS_BASE, data);
         break;
     case MSR_KERNELGSBASE:
-        wvmcs(cpu->hvf_fd, VMCS_HOST_FS_BASE, data);
+        wvmcs(cpu->hvf->fd, VMCS_HOST_FS_BASE, data);
         break;
     case MSR_STAR:
         abort();
@@ -XXX,XX +XXX,XX @@ void simulate_wrmsr(struct CPUState *cpu)
         break;
     case MSR_EFER:
         /*printf("new efer %llx\n", EFER(cpu));*/
-        wvmcs(cpu->hvf_fd, VMCS_GUEST_IA32_EFER, data);
+        wvmcs(cpu->hvf->fd, VMCS_GUEST_IA32_EFER, data);
         if (data & MSR_EFER_NXE) {
-            hv_vcpu_invalidate_tlb(cpu->hvf_fd);
+            hv_vcpu_invalidate_tlb(cpu->hvf->fd);
         }
         break;
     case MSR_MTRRphysBase(0):
@@ -XXX,XX +XXX,XX @@ void load_regs(struct CPUState *cpu)
     CPUX86State *env = &x86_cpu->env;
 
     int i = 0;
-    RRX(env, R_EAX) = rreg(cpu->hvf_fd, HV_X86_RAX);
-    RRX(env, R_EBX) = rreg(cpu->hvf_fd, HV_X86_RBX);
-    RRX(env, R_ECX) = rreg(cpu->hvf_fd, HV_X86_RCX);
-    RRX(env, R_EDX) = rreg(cpu->hvf_fd, HV_X86_RDX);
-    RRX(env, R_ESI) = rreg(cpu->hvf_fd, HV_X86_RSI);
-    RRX(env, R_EDI) = rreg(cpu->hvf_fd, HV_X86_RDI);
-    RRX(env, R_ESP) = rreg(cpu->hvf_fd, HV_X86_RSP);
-    RRX(env, R_EBP) = rreg(cpu->hvf_fd, HV_X86_RBP);
+    RRX(env, R_EAX) = rreg(cpu->hvf->fd, HV_X86_RAX);
+    RRX(env, R_EBX) = rreg(cpu->hvf->fd, HV_X86_RBX);
+    RRX(env, R_ECX) = rreg(cpu->hvf->fd, HV_X86_RCX);
+    RRX(env, R_EDX) = rreg(cpu->hvf->fd, HV_X86_RDX);
+    RRX(env, R_ESI) = rreg(cpu->hvf->fd, HV_X86_RSI);
+    RRX(env, R_EDI) = rreg(cpu->hvf->fd, HV_X86_RDI);
+    RRX(env, R_ESP) = rreg(cpu->hvf->fd, HV_X86_RSP);
+    RRX(env, R_EBP) = rreg(cpu->hvf->fd, HV_X86_RBP);
     for (i = 8; i < 16; i++) {
-        RRX(env, i) = rreg(cpu->hvf_fd, HV_X86_RAX + i);
+        RRX(env, i) = rreg(cpu->hvf->fd, HV_X86_RAX + i);
     }
 
-    env->eflags = rreg(cpu->hvf_fd, HV_X86_RFLAGS);
+    env->eflags = rreg(cpu->hvf->fd, HV_X86_RFLAGS);
     rflags_to_lflags(env);
-    env->eip = rreg(cpu->hvf_fd, HV_X86_RIP);
+    env->eip = rreg(cpu->hvf->fd, HV_X86_RIP);
 }
 
 void store_regs(struct CPUState *cpu)
@@ -XXX,XX +XXX,XX @@ void store_regs(struct CPUState *cpu)
     CPUX86State *env = &x86_cpu->env;
 
     int i = 0;
-    wreg(cpu->hvf_fd, HV_X86_RAX, RAX(env));
-    wreg(cpu->hvf_fd, HV_X86_RBX, RBX(env));
-    wreg(cpu->hvf_fd, HV_X86_RCX, RCX(env));
-    wreg(cpu->hvf_fd, HV_X86_RDX, RDX(env));
-    wreg(cpu->hvf_fd, HV_X86_RSI, RSI(env));
-    wreg(cpu->hvf_fd, HV_X86_RDI, RDI(env));
-    wreg(cpu->hvf_fd, HV_X86_RBP, RBP(env));
-    wreg(cpu->hvf_fd, HV_X86_RSP, RSP(env));
+    wreg(cpu->hvf->fd, HV_X86_RAX, RAX(env));
+    wreg(cpu->hvf->fd, HV_X86_RBX, RBX(env));
+    wreg(cpu->hvf->fd, HV_X86_RCX, RCX(env));
+    wreg(cpu->hvf->fd, HV_X86_RDX, RDX(env));
+    wreg(cpu->hvf->fd, HV_X86_RSI, RSI(env));
+    wreg(cpu->hvf->fd, HV_X86_RDI, RDI(env));
+    wreg(cpu->hvf->fd, HV_X86_RBP, RBP(env));
+    wreg(cpu->hvf->fd, HV_X86_RSP, RSP(env));
     for (i = 8; i < 16; i++) {
-        wreg(cpu->hvf_fd, HV_X86_RAX + i, RRX(env, i));
+        wreg(cpu->hvf->fd, HV_X86_RAX + i, RRX(env, i));
     }
 
     lflags_to_rflags(env);
-    wreg(cpu->hvf_fd, HV_X86_RFLAGS, env->eflags);
+    wreg(cpu->hvf->fd, HV_X86_RFLAGS, env->eflags);
     macvm_set_rip(cpu, env->eip);
 }
 
diff --git a/target/i386/hvf/x86_mmu.c b/target/i386/hvf/x86_mmu.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86_mmu.c
+++ b/target/i386/hvf/x86_mmu.c
@@ -XXX,XX +XXX,XX @@ static bool test_pt_entry(struct CPUState *cpu, struct gpt_translation *pt,
         pt->err_code |= MMU_PAGE_PT;
     }
 
-    uint32_t cr0 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0);
+    uint32_t cr0 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0);
     /* check protection */
     if (cr0 & CR0_WP) {
         if (pt->write_access && !pte_write_access(pte)) {
@@ -XXX,XX +XXX,XX @@ static bool walk_gpt(struct CPUState *cpu, target_ulong addr, int err_code,
 {
     int top_level, level;
     bool is_large = false;
-    target_ulong cr3 = rvmcs(cpu->hvf_fd, VMCS_GUEST_CR3);
+    target_ulong cr3 = rvmcs(cpu->hvf->fd, VMCS_GUEST_CR3);
     uint64_t page_mask = pae ? PAE_PTE_PAGE_MASK : LEGACY_PTE_PAGE_MASK;
     
     memset(pt, 0, sizeof(*pt));
diff --git a/target/i386/hvf/x86_task.c b/target/i386/hvf/x86_task.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86_task.c
+++ b/target/i386/hvf/x86_task.c
@@ -XXX,XX +XXX,XX @@ static void load_state_from_tss32(CPUState *cpu, struct x86_tss_segment32 *tss)
     X86CPU *x86_cpu = X86_CPU(cpu);
     CPUX86State *env = &x86_cpu->env;
 
-    wvmcs(cpu->hvf_fd, VMCS_GUEST_CR3, tss->cr3);
+    wvmcs(cpu->hvf->fd, VMCS_GUEST_CR3, tss->cr3);
 
     env->eip = tss->eip;
     env->eflags = tss->eflags | 2;
@@ -XXX,XX +XXX,XX @@ static int task_switch_32(CPUState *cpu, x68_segment_selector tss_sel, x68_segme
 
 void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel, int reason, bool gate_valid, uint8_t gate, uint64_t gate_type)
 {
-    uint64_t rip = rreg(cpu->hvf_fd, HV_X86_RIP);
+    uint64_t rip = rreg(cpu->hvf->fd, HV_X86_RIP);
     if (!gate_valid || (gate_type != VMCS_INTR_T_HWEXCEPTION &&
                         gate_type != VMCS_INTR_T_HWINTR &&
                         gate_type != VMCS_INTR_T_NMI)) {
-        int ins_len = rvmcs(cpu->hvf_fd, VMCS_EXIT_INSTRUCTION_LENGTH);
+        int ins_len = rvmcs(cpu->hvf->fd, VMCS_EXIT_INSTRUCTION_LENGTH);
         macvm_set_rip(cpu, rip + ins_len);
         return;
     }
@@ -XXX,XX +XXX,XX @@ void vmx_handle_task_switch(CPUState *cpu, x68_segment_selector tss_sel, int rea
         //ret = task_switch_16(cpu, tss_sel, old_tss_sel, old_tss_base, &next_tss_desc);
         VM_PANIC("task_switch_16");
 
-    macvm_set_cr0(cpu->hvf_fd, rvmcs(cpu->hvf_fd, VMCS_GUEST_CR0) | CR0_TS);
+    macvm_set_cr0(cpu->hvf->fd, rvmcs(cpu->hvf->fd, VMCS_GUEST_CR0) | CR0_TS);
     x86_segment_descriptor_to_vmx(cpu, tss_sel, &next_tss_desc, &vmx_seg);
     vmx_write_segment_descriptor(cpu, &vmx_seg, R_TR);
 
     store_regs(cpu);
 
-    hv_vcpu_invalidate_tlb(cpu->hvf_fd);
-    hv_vcpu_flush(cpu->hvf_fd);
+    hv_vcpu_invalidate_tlb(cpu->hvf->fd);
+    hv_vcpu_flush(cpu->hvf->fd);
 }
diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86hvf.c
+++ b/target/i386/hvf/x86hvf.c
@@ -XXX,XX +XXX,XX @@ void hvf_put_xsave(CPUState *cpu_state)
 
     x86_cpu_xsave_all_areas(X86_CPU(cpu_state), xsave);
 
-    if (hv_vcpu_write_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) {
+    if (hv_vcpu_write_fpstate(cpu_state->hvf->fd, (void*)xsave, 4096)) {
         abort();
     }
 }
@@ -XXX,XX +XXX,XX @@ void hvf_put_segments(CPUState *cpu_state)
     CPUX86State *env = &X86_CPU(cpu_state)->env;
     struct vmx_segment seg;
     
-    wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_LIMIT, env->idt.limit);
-    wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_BASE, env->idt.base);
+    wvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_LIMIT, env->idt.limit);
+    wvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_BASE, env->idt.base);
 
-    wvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_LIMIT, env->gdt.limit);
-    wvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_BASE, env->gdt.base);
+    wvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_LIMIT, env->gdt.limit);
+    wvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_BASE, env->gdt.base);
 
-    /* wvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR2, env->cr[2]); */
-    wvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR3, env->cr[3]);
+    /* wvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR2, env->cr[2]); */
+    wvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR3, env->cr[3]);
     vmx_update_tpr(cpu_state);
-    wvmcs(cpu_state->hvf_fd, VMCS_GUEST_IA32_EFER, env->efer);
+    wvmcs(cpu_state->hvf->fd, VMCS_GUEST_IA32_EFER, env->efer);
 
-    macvm_set_cr4(cpu_state->hvf_fd, env->cr[4]);
-    macvm_set_cr0(cpu_state->hvf_fd, env->cr[0]);
+    macvm_set_cr4(cpu_state->hvf->fd, env->cr[4]);
+    macvm_set_cr0(cpu_state->hvf->fd, env->cr[0]);
 
     hvf_set_segment(cpu_state, &seg, &env->segs[R_CS], false);
     vmx_write_segment_descriptor(cpu_state, &seg, R_CS);
@@ -XXX,XX +XXX,XX @@ void hvf_put_segments(CPUState *cpu_state)
     hvf_set_segment(cpu_state, &seg, &env->ldt, false);
     vmx_write_segment_descriptor(cpu_state, &seg, R_LDTR);
     
-    hv_vcpu_flush(cpu_state->hvf_fd);
+    hv_vcpu_flush(cpu_state->hvf->fd);
 }
     
 void hvf_put_msrs(CPUState *cpu_state)
 {
     CPUX86State *env = &X86_CPU(cpu_state)->env;
 
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_CS,
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_CS,
                       env->sysenter_cs);
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_ESP,
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_ESP,
                       env->sysenter_esp);
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_EIP,
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_EIP,
                       env->sysenter_eip);
 
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_STAR, env->star);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_STAR, env->star);
 
 #ifdef TARGET_X86_64
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_CSTAR, env->cstar);
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_KERNELGSBASE, env->kernelgsbase);
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_FMASK, env->fmask);
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_LSTAR, env->lstar);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_CSTAR, env->cstar);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_KERNELGSBASE, env->kernelgsbase);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_FMASK, env->fmask);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_LSTAR, env->lstar);
 #endif
 
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_GSBASE, env->segs[R_GS].base);
-    hv_vcpu_write_msr(cpu_state->hvf_fd, MSR_FSBASE, env->segs[R_FS].base);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_GSBASE, env->segs[R_GS].base);
+    hv_vcpu_write_msr(cpu_state->hvf->fd, MSR_FSBASE, env->segs[R_FS].base);
 }
 
 
@@ -XXX,XX +XXX,XX @@ void hvf_get_xsave(CPUState *cpu_state)
 
     xsave = X86_CPU(cpu_state)->env.xsave_buf;
 
-    if (hv_vcpu_read_fpstate(cpu_state->hvf_fd, (void*)xsave, 4096)) {
+    if (hv_vcpu_read_fpstate(cpu_state->hvf->fd, (void*)xsave, 4096)) {
         abort();
     }
 
@@ -XXX,XX +XXX,XX @@ void hvf_get_segments(CPUState *cpu_state)
     vmx_read_segment_descriptor(cpu_state, &seg, R_LDTR);
     hvf_get_segment(&env->ldt, &seg);
 
-    env->idt.limit = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_LIMIT);
-    env->idt.base = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IDTR_BASE);
-    env->gdt.limit = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_LIMIT);
-    env->gdt.base = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_GDTR_BASE);
+    env->idt.limit = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_LIMIT);
+    env->idt.base = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IDTR_BASE);
+    env->gdt.limit = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_LIMIT);
+    env->gdt.base = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_GDTR_BASE);
 
-    env->cr[0] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR0);
+    env->cr[0] = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR0);
     env->cr[2] = 0;
-    env->cr[3] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR3);
-    env->cr[4] = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_CR4);
+    env->cr[3] = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR3);
+    env->cr[4] = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_CR4);
     
-    env->efer = rvmcs(cpu_state->hvf_fd, VMCS_GUEST_IA32_EFER);
+    env->efer = rvmcs(cpu_state->hvf->fd, VMCS_GUEST_IA32_EFER);
 }
 
 void hvf_get_msrs(CPUState *cpu_state)
@@ -XXX,XX +XXX,XX @@ void hvf_get_msrs(CPUState *cpu_state)
     CPUX86State *env = &X86_CPU(cpu_state)->env;
     uint64_t tmp;
     
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_CS, &tmp);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_CS, &tmp);
     env->sysenter_cs = tmp;
     
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_ESP, &tmp);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_ESP, &tmp);
     env->sysenter_esp = tmp;
 
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_SYSENTER_EIP, &tmp);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_SYSENTER_EIP, &tmp);
     env->sysenter_eip = tmp;
 
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_STAR, &env->star);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_STAR, &env->star);
 
 #ifdef TARGET_X86_64
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_CSTAR, &env->cstar);
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_KERNELGSBASE, &env->kernelgsbase);
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_FMASK, &env->fmask);
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_LSTAR, &env->lstar);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_CSTAR, &env->cstar);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_KERNELGSBASE, &env->kernelgsbase);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_FMASK, &env->fmask);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_LSTAR, &env->lstar);
 #endif
 
-    hv_vcpu_read_msr(cpu_state->hvf_fd, MSR_IA32_APICBASE, &tmp);
+    hv_vcpu_read_msr(cpu_state->hvf->fd, MSR_IA32_APICBASE, &tmp);
     
-    env->tsc = rdtscp() + rvmcs(cpu_state->hvf_fd, VMCS_TSC_OFFSET);
+    env->tsc = rdtscp() + rvmcs(cpu_state->hvf->fd, VMCS_TSC_OFFSET);
 }
 
 int hvf_put_registers(CPUState *cpu_state)
@@ -XXX,XX +XXX,XX @@ int hvf_put_registers(CPUState *cpu_state)
     X86CPU *x86cpu = X86_CPU(cpu_state);
     CPUX86State *env = &x86cpu->env;
 
-    wreg(cpu_state->hvf_fd, HV_X86_RAX, env->regs[R_EAX]);
-    wreg(cpu_state->hvf_fd, HV_X86_RBX, env->regs[R_EBX]);
-    wreg(cpu_state->hvf_fd, HV_X86_RCX, env->regs[R_ECX]);
-    wreg(cpu_state->hvf_fd, HV_X86_RDX, env->regs[R_EDX]);
-    wreg(cpu_state->hvf_fd, HV_X86_RBP, env->regs[R_EBP]);
-    wreg(cpu_state->hvf_fd, HV_X86_RSP, env->regs[R_ESP]);
-    wreg(cpu_state->hvf_fd, HV_X86_RSI, env->regs[R_ESI]);
-    wreg(cpu_state->hvf_fd, HV_X86_RDI, env->regs[R_EDI]);
-    wreg(cpu_state->hvf_fd, HV_X86_R8, env->regs[8]);
-    wreg(cpu_state->hvf_fd, HV_X86_R9, env->regs[9]);
-    wreg(cpu_state->hvf_fd, HV_X86_R10, env->regs[10]);
-    wreg(cpu_state->hvf_fd, HV_X86_R11, env->regs[11]);
-    wreg(cpu_state->hvf_fd, HV_X86_R12, env->regs[12]);
-    wreg(cpu_state->hvf_fd, HV_X86_R13, env->regs[13]);
-    wreg(cpu_state->hvf_fd, HV_X86_R14, env->regs[14]);
-    wreg(cpu_state->hvf_fd, HV_X86_R15, env->regs[15]);
-    wreg(cpu_state->hvf_fd, HV_X86_RFLAGS, env->eflags);
-    wreg(cpu_state->hvf_fd, HV_X86_RIP, env->eip);
+    wreg(cpu_state->hvf->fd, HV_X86_RAX, env->regs[R_EAX]);
+    wreg(cpu_state->hvf->fd, HV_X86_RBX, env->regs[R_EBX]);
+    wreg(cpu_state->hvf->fd, HV_X86_RCX, env->regs[R_ECX]);
+    wreg(cpu_state->hvf->fd, HV_X86_RDX, env->regs[R_EDX]);
+    wreg(cpu_state->hvf->fd, HV_X86_RBP, env->regs[R_EBP]);
+    wreg(cpu_state->hvf->fd, HV_X86_RSP, env->regs[R_ESP]);
+    wreg(cpu_state->hvf->fd, HV_X86_RSI, env->regs[R_ESI]);
+    wreg(cpu_state->hvf->fd, HV_X86_RDI, env->regs[R_EDI]);
+    wreg(cpu_state->hvf->fd, HV_X86_R8, env->regs[8]);
+    wreg(cpu_state->hvf->fd, HV_X86_R9, env->regs[9]);
+    wreg(cpu_state->hvf->fd, HV_X86_R10, env->regs[10]);
+    wreg(cpu_state->hvf->fd, HV_X86_R11, env->regs[11]);
+    wreg(cpu_state->hvf->fd, HV_X86_R12, env->regs[12]);
+    wreg(cpu_state->hvf->fd, HV_X86_R13, env->regs[13]);
+    wreg(cpu_state->hvf->fd, HV_X86_R14, env->regs[14]);
+    wreg(cpu_state->hvf->fd, HV_X86_R15, env->regs[15]);
+    wreg(cpu_state->hvf->fd, HV_X86_RFLAGS, env->eflags);
+    wreg(cpu_state->hvf->fd, HV_X86_RIP, env->eip);
    
-    wreg(cpu_state->hvf_fd, HV_X86_XCR0, env->xcr0);
+    wreg(cpu_state->hvf->fd, HV_X86_XCR0, env->xcr0);
     
     hvf_put_xsave(cpu_state);
     
@@ -XXX,XX +XXX,XX @@ int hvf_put_registers(CPUState *cpu_state)
     
     hvf_put_msrs(cpu_state);
     
-    wreg(cpu_state->hvf_fd, HV_X86_DR0, env->dr[0]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR1, env->dr[1]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR2, env->dr[2]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR3, env->dr[3]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR4, env->dr[4]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR5, env->dr[5]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR6, env->dr[6]);
-    wreg(cpu_state->hvf_fd, HV_X86_DR7, env->dr[7]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR0, env->dr[0]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR1, env->dr[1]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR2, env->dr[2]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR3, env->dr[3]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR4, env->dr[4]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR5, env->dr[5]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR6, env->dr[6]);
+    wreg(cpu_state->hvf->fd, HV_X86_DR7, env->dr[7]);
     
     return 0;
 }
@@ -XXX,XX +XXX,XX @@ int hvf_get_registers(CPUState *cpu_state)
     X86CPU *x86cpu = X86_CPU(cpu_state);
     CPUX86State *env = &x86cpu->env;
 
-    env->regs[R_EAX] = rreg(cpu_state->hvf_fd, HV_X86_RAX);
-    env->regs[R_EBX] = rreg(cpu_state->hvf_fd, HV_X86_RBX);
-    env->regs[R_ECX] = rreg(cpu_state->hvf_fd, HV_X86_RCX);
-    env->regs[R_EDX] = rreg(cpu_state->hvf_fd, HV_X86_RDX);
-    env->regs[R_EBP] = rreg(cpu_state->hvf_fd, HV_X86_RBP);
-    env->regs[R_ESP] = rreg(cpu_state->hvf_fd, HV_X86_RSP);
-    env->regs[R_ESI] = rreg(cpu_state->hvf_fd, HV_X86_RSI);
-    env->regs[R_EDI] = rreg(cpu_state->hvf_fd, HV_X86_RDI);
-    env->regs[8] = rreg(cpu_state->hvf_fd, HV_X86_R8);
-    env->regs[9] = rreg(cpu_state->hvf_fd, HV_X86_R9);
-    env->regs[10] = rreg(cpu_state->hvf_fd, HV_X86_R10);
-    env->regs[11] = rreg(cpu_state->hvf_fd, HV_X86_R11);
-    env->regs[12] = rreg(cpu_state->hvf_fd, HV_X86_R12);
-    env->regs[13] = rreg(cpu_state->hvf_fd, HV_X86_R13);
-    env->regs[14] = rreg(cpu_state->hvf_fd, HV_X86_R14);
-    env->regs[15] = rreg(cpu_state->hvf_fd, HV_X86_R15);
+    env->regs[R_EAX] = rreg(cpu_state->hvf->fd, HV_X86_RAX);
+    env->regs[R_EBX] = rreg(cpu_state->hvf->fd, HV_X86_RBX);
+    env->regs[R_ECX] = rreg(cpu_state->hvf->fd, HV_X86_RCX);
+    env->regs[R_EDX] = rreg(cpu_state->hvf->fd, HV_X86_RDX);
+    env->regs[R_EBP] = rreg(cpu_state->hvf->fd, HV_X86_RBP);
+    env->regs[R_ESP] = rreg(cpu_state->hvf->fd, HV_X86_RSP);
+    env->regs[R_ESI] = rreg(cpu_state->hvf->fd, HV_X86_RSI);
+    env->regs[R_EDI] = rreg(cpu_state->hvf->fd, HV_X86_RDI);
+    env->regs[8] = rreg(cpu_state->hvf->fd, HV_X86_R8);
+    env->regs[9] = rreg(cpu_state->hvf->fd, HV_X86_R9);
+    env->regs[10] = rreg(cpu_state->hvf->fd, HV_X86_R10);
+    env->regs[11] = rreg(cpu_state->hvf->fd, HV_X86_R11);
+    env->regs[12] = rreg(cpu_state->hvf->fd, HV_X86_R12);
+    env->regs[13] = rreg(cpu_state->hvf->fd, HV_X86_R13);
+    env->regs[14] = rreg(cpu_state->hvf->fd, HV_X86_R14);
+    env->regs[15] = rreg(cpu_state->hvf->fd, HV_X86_R15);
     
-    env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS);
-    env->eip = rreg(cpu_state->hvf_fd, HV_X86_RIP);
+    env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS);
+    env->eip = rreg(cpu_state->hvf->fd, HV_X86_RIP);
    
     hvf_get_xsave(cpu_state);
-    env->xcr0 = rreg(cpu_state->hvf_fd, HV_X86_XCR0);
+    env->xcr0 = rreg(cpu_state->hvf->fd, HV_X86_XCR0);
     
     hvf_get_segments(cpu_state);
     hvf_get_msrs(cpu_state);
     
-    env->dr[0] = rreg(cpu_state->hvf_fd, HV_X86_DR0);
-    env->dr[1] = rreg(cpu_state->hvf_fd, HV_X86_DR1);
-    env->dr[2] = rreg(cpu_state->hvf_fd, HV_X86_DR2);
-    env->dr[3] = rreg(cpu_state->hvf_fd, HV_X86_DR3);
-    env->dr[4] = rreg(cpu_state->hvf_fd, HV_X86_DR4);
-    env->dr[5] = rreg(cpu_state->hvf_fd, HV_X86_DR5);
-    env->dr[6] = rreg(cpu_state->hvf_fd, HV_X86_DR6);
-    env->dr[7] = rreg(cpu_state->hvf_fd, HV_X86_DR7);
+    env->dr[0] = rreg(cpu_state->hvf->fd, HV_X86_DR0);
+    env->dr[1] = rreg(cpu_state->hvf->fd, HV_X86_DR1);
+    env->dr[2] = rreg(cpu_state->hvf->fd, HV_X86_DR2);
+    env->dr[3] = rreg(cpu_state->hvf->fd, HV_X86_DR3);
+    env->dr[4] = rreg(cpu_state->hvf->fd, HV_X86_DR4);
+    env->dr[5] = rreg(cpu_state->hvf->fd, HV_X86_DR5);
+    env->dr[6] = rreg(cpu_state->hvf->fd, HV_X86_DR6);
+    env->dr[7] = rreg(cpu_state->hvf->fd, HV_X86_DR7);
     
     x86_update_hflags(env);
     return 0;
@@ -XXX,XX +XXX,XX @@ int hvf_get_registers(CPUState *cpu_state)
 static void vmx_set_int_window_exiting(CPUState *cpu)
 {
      uint64_t val;
-     val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
-     wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val |
+     val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS);
+     wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val |
              VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING);
 }
 
 void vmx_clear_int_window_exiting(CPUState *cpu)
 {
      uint64_t val;
-     val = rvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS);
-     wvmcs(cpu->hvf_fd, VMCS_PRI_PROC_BASED_CTLS, val &
+     val = rvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS);
+     wvmcs(cpu->hvf->fd, VMCS_PRI_PROC_BASED_CTLS, val &
              ~VMCS_PRI_PROC_BASED_CTLS_INT_WINDOW_EXITING);
 }
 
@@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state)
     uint64_t info = 0;
     if (have_event) {
         info = vector | intr_type | VMCS_INTR_VALID;
-        uint64_t reason = rvmcs(cpu_state->hvf_fd, VMCS_EXIT_REASON);
+        uint64_t reason = rvmcs(cpu_state->hvf->fd, VMCS_EXIT_REASON);
         if (env->nmi_injected && reason != EXIT_REASON_TASK_SWITCH) {
             vmx_clear_nmi_blocking(cpu_state);
         }
@@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state)
             info &= ~(1 << 12); /* clear undefined bit */
             if (intr_type == VMCS_INTR_T_SWINTR ||
                 intr_type == VMCS_INTR_T_SWEXCEPTION) {
-                wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INST_LENGTH, env->ins_len);
+                wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INST_LENGTH, env->ins_len);
             }
             
             if (env->has_error_code) {
-                wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_EXCEPTION_ERROR,
+                wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_EXCEPTION_ERROR,
                       env->error_code);
                 /* Indicate that VMCS_ENTRY_EXCEPTION_ERROR is valid */
                 info |= VMCS_INTR_DEL_ERRCODE;
             }
             /*printf("reinject  %lx err %d\n", info, err);*/
-            wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info);
+            wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, info);
         };
     }
 
@@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state)
         if (!(env->hflags2 & HF2_NMI_MASK) && !(info & VMCS_INTR_VALID)) {
             cpu_state->interrupt_request &= ~CPU_INTERRUPT_NMI;
             info = VMCS_INTR_VALID | VMCS_INTR_T_NMI | EXCP02_NMI;
-            wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, info);
+            wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, info);
         } else {
             vmx_set_nmi_window_exiting(cpu_state);
         }
@@ -XXX,XX +XXX,XX @@ bool hvf_inject_interrupts(CPUState *cpu_state)
         int line = cpu_get_pic_interrupt(&x86cpu->env);
         cpu_state->interrupt_request &= ~CPU_INTERRUPT_HARD;
         if (line >= 0) {
-            wvmcs(cpu_state->hvf_fd, VMCS_ENTRY_INTR_INFO, line |
+            wvmcs(cpu_state->hvf->fd, VMCS_ENTRY_INTR_INFO, line |
                   VMCS_INTR_VALID | VMCS_INTR_T_HWINTR);
         }
     }
@@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state)
     X86CPU *cpu = X86_CPU(cpu_state);
     CPUX86State *env = &cpu->env;
 
-    env->eflags = rreg(cpu_state->hvf_fd, HV_X86_RFLAGS);
+    env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS);
 
     if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) {
         cpu_synchronize_state(cpu_state);
-- 
2.20.1

From: Alexander Graf <agraf@csgraf.de>

The hooks we have that call us after reset, init and loadvm really all
just want to say "The reference of all register state is in the QEMU
vcpu struct, please push it".

We already have a working pushing mechanism though called cpu->vcpu_dirty,
so we can just reuse that for all of the above, syncing state properly the
next time we actually execute a vCPU.

This fixes PSCI resets on ARM, as they modify CPU state even after the
post init call has completed, but before we execute the vCPU again.

To also make the scheme work for x86, we have to make sure we don't
move stale eflags into our env when the vcpu state is dirty.

Signed-off-by: Alexander Graf <agraf@csgraf.de>
Reviewed-by: Roman Bolshakov <r.bolshakov@yadro.com>
Tested-by: Roman Bolshakov <r.bolshakov@yadro.com>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-id: 20210519202253.76782-13-agraf@csgraf.de
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 accel/hvf/hvf-accel-ops.c | 27 +++++++--------------------
 target/i386/hvf/x86hvf.c  |  5 ++++-
 2 files changed, 11 insertions(+), 21 deletions(-)

diff --git a/accel/hvf/hvf-accel-ops.c b/accel/hvf/hvf-accel-ops.c
index XXXXXXX..XXXXXXX 100644
--- a/accel/hvf/hvf-accel-ops.c
+++ b/accel/hvf/hvf-accel-ops.c
@@ -XXX,XX +XXX,XX @@ static void hvf_cpu_synchronize_state(CPUState *cpu)
     }
 }
 
-static void do_hvf_cpu_synchronize_post_reset(CPUState *cpu,
-                                              run_on_cpu_data arg)
+static void do_hvf_cpu_synchronize_set_dirty(CPUState *cpu,
+                                             run_on_cpu_data arg)
 {
-    hvf_put_registers(cpu);
-    cpu->vcpu_dirty = false;
+    /* QEMU state is the reference, push it to HVF now and on next entry */
+    cpu->vcpu_dirty = true;
 }
 
 static void hvf_cpu_synchronize_post_reset(CPUState *cpu)
 {
-    run_on_cpu(cpu, do_hvf_cpu_synchronize_post_reset, RUN_ON_CPU_NULL);
-}
-
-static void do_hvf_cpu_synchronize_post_init(CPUState *cpu,
-                                             run_on_cpu_data arg)
-{
-    hvf_put_registers(cpu);
-    cpu->vcpu_dirty = false;
+    run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL);
 }
 
 static void hvf_cpu_synchronize_post_init(CPUState *cpu)
 {
-    run_on_cpu(cpu, do_hvf_cpu_synchronize_post_init, RUN_ON_CPU_NULL);
-}
-
-static void do_hvf_cpu_synchronize_pre_loadvm(CPUState *cpu,
-                                              run_on_cpu_data arg)
-{
-    cpu->vcpu_dirty = true;
+    run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL);
 }
 
 static void hvf_cpu_synchronize_pre_loadvm(CPUState *cpu)
 {
-    run_on_cpu(cpu, do_hvf_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL);
+    run_on_cpu(cpu, do_hvf_cpu_synchronize_set_dirty, RUN_ON_CPU_NULL);
 }
 
 static void hvf_set_dirty_tracking(MemoryRegionSection *section, bool on)
diff --git a/target/i386/hvf/x86hvf.c b/target/i386/hvf/x86hvf.c
index XXXXXXX..XXXXXXX 100644
--- a/target/i386/hvf/x86hvf.c
+++ b/target/i386/hvf/x86hvf.c
@@ -XXX,XX +XXX,XX @@ int hvf_process_events(CPUState *cpu_state)
     X86CPU *cpu = X86_CPU(cpu_state);
     CPUX86State *env = &cpu->env;
 
-    env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS);
+    if (!cpu_state->vcpu_dirty) {
+        /* light weight sync for CPU_INTERRUPT_HARD and IF_MASK */
+        env->eflags = rreg(cpu_state->hvf->fd, HV_X86_RFLAGS);
+    }
 
     if (cpu_state->interrupt_request & CPU_INTERRUPT_INIT) {
         cpu_synchronize_state(cpu_state);
-- 
2.20.1

Coverity notes that we don't check for dup2() failing.  Add some
assertions so that if it does ever happen we get some indication.
(This is similar to how we handle other "don't expect this syscall to
fail" checks in this test code.)

Fixes: Coverity CID 1432346
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Message-id: 20210525134458.6675-2-peter.maydell@linaro.org
---
 tests/qtest/bios-tables-test.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/bios-tables-test.c
+++ b/tests/qtest/bios-tables-test.c
@@ -XXX,XX +XXX,XX @@ static void test_acpi_asl(test_data *data)
                                                  exp_sdt->asl_file, sdt->asl_file);
                     int out = dup(STDOUT_FILENO);
                     int ret G_GNUC_UNUSED;
+                    int dupret;
 
-                    dup2(STDERR_FILENO, STDOUT_FILENO);
+                    g_assert(out >= 0);
+                    dupret = dup2(STDERR_FILENO, STDOUT_FILENO);
+                    g_assert(dupret >= 0);
                     ret = system(diff) ;
-                    dup2(out, STDOUT_FILENO);
+                    dupret = dup2(out, STDOUT_FILENO);
+                    g_assert(dupret >= 0);
                     close(out);
                     g_free(diff);
                 }
-- 
2.20.1

The e1000e_send_verify() test calls qemu_recv() but doesn't
check that the call succeeded, which annoys Coverity. Add
an explicit test check for the length of the data.

(This is a test check, not a "we assume this syscall always
succeeds", so we use g_assert_cmpint() rather than g_assert().)

Fixes: Coverity CID 1432324
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Message-id: 20210525134458.6675-3-peter.maydell@linaro.org
---
 tests/qtest/e1000e-test.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tests/qtest/e1000e-test.c b/tests/qtest/e1000e-test.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/e1000e-test.c
+++ b/tests/qtest/e1000e-test.c
@@ -XXX,XX +XXX,XX @@ static void e1000e_send_verify(QE1000E *d, int *test_sockets, QGuestAllocator *a
     /* Check data sent to the backend */
     ret = qemu_recv(test_sockets[0], &recv_len, sizeof(recv_len), 0);
     g_assert_cmpint(ret, == , sizeof(recv_len));
-    qemu_recv(test_sockets[0], buffer, 64, 0);
+    ret = qemu_recv(test_sockets[0], buffer, 64, 0);
+    g_assert_cmpint(ret, >=, 5);
     g_assert_cmpstr(buffer, == , "TEST");
 
     /* Free test data buffer */
-- 
2.20.1

Coverity notices that the checks against mkstemp() failing in
create_qcow2_with_mbr() are wrong: mkstemp returns -1 on failure but
the check is just "g_assert(fd)".  Fix to use "g_assert(fd >= 0)",
matching the correct check in create_test_img().

Fixes: Coverity CID 1432274
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Message-id: 20210525134458.6675-4-peter.maydell@linaro.org
---
 tests/qtest/hd-geo-test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/qtest/hd-geo-test.c b/tests/qtest/hd-geo-test.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/hd-geo-test.c
+++ b/tests/qtest/hd-geo-test.c
@@ -XXX,XX +XXX,XX @@ static char *create_qcow2_with_mbr(MBRpartitions mbr, uint64_t sectors)
     }
 
     fd = mkstemp(raw_path);
-    g_assert(fd);
+    g_assert(fd >= 0);
     close(fd);
 
     fd = open(raw_path, O_WRONLY);
@@ -XXX,XX +XXX,XX @@ static char *create_qcow2_with_mbr(MBRpartitions mbr, uint64_t sectors)
     close(fd);
 
     fd = mkstemp(qcow2_path);
-    g_assert(fd);
+    g_assert(fd >= 0);
     close(fd);
 
     qemu_img_path = getenv("QTEST_QEMU_IMG");
-- 
2.20.1

Coverity points out that we calculate a 64-bit value using 32-bit
arithmetic; add the cast to force the multiply to be done as 64-bits.
(The overflow will never happen with the current test data.)

Fixes: Coverity CID 1432320
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Message-id: 20210525134458.6675-5-peter.maydell@linaro.org
---
 tests/qtest/pflash-cfi02-test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/qtest/pflash-cfi02-test.c b/tests/qtest/pflash-cfi02-test.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/pflash-cfi02-test.c
+++ b/tests/qtest/pflash-cfi02-test.c
@@ -XXX,XX +XXX,XX @@ static void test_geometry(const void *opaque)
 
     for (int region = 0; region < nb_erase_regions; ++region) {
         for (uint32_t i = 0; i < c->nb_blocs[region]; ++i) {
-            uint64_t byte_addr = i * c->sector_len[region];
+            uint64_t byte_addr = (uint64_t)i * c->sector_len[region];
             g_assert_cmphex(flash_read(c, byte_addr), ==, bank_mask(c));
         }
     }
-- 
2.20.1

Coverity points out that in tpm_test_swtpm_migration_test() we
assume that src_tpm_addr and dst_tpm_addr are non-NULL (we
pass them to tpm_util_migration_start_qemu() which will
unconditionally dereference them) but then later explicitly
check them for NULL. Remove the pointless checks.

Fixes: Coverity CID 1432367, 1432359

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Message-id: 20210525134458.6675-6-peter.maydell@linaro.org
---
 tests/qtest/tpm-tests.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/tests/qtest/tpm-tests.c b/tests/qtest/tpm-tests.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/qtest/tpm-tests.c
+++ b/tests/qtest/tpm-tests.c
@@ -XXX,XX +XXX,XX @@ void tpm_test_swtpm_migration_test(const char *src_tpm_path,
     qtest_quit(src_qemu);
 
     tpm_util_swtpm_kill(dst_tpm_pid);
-    if (dst_tpm_addr) {
-        g_unlink(dst_tpm_addr->u.q_unix.path);
-        qapi_free_SocketAddress(dst_tpm_addr);
-    }
+    g_unlink(dst_tpm_addr->u.q_unix.path);
+    qapi_free_SocketAddress(dst_tpm_addr);
 
     tpm_util_swtpm_kill(src_tpm_pid);
-    if (src_tpm_addr) {
-        g_unlink(src_tpm_addr->u.q_unix.path);
-        qapi_free_SocketAddress(src_tpm_addr);
-    }
+    g_unlink(src_tpm_addr->u.q_unix.path);
+    qapi_free_SocketAddress(src_tpm_addr);
 }
-- 
2.20.1

Coverity complains that we don't check for failures from dup()
and mkstemp(); add asserts that these syscalls succeeded.

Fixes: Coverity CID 1432516, 1432574
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20210525134458.6675-7-peter.maydell@linaro.org
---
 tests/unit/test-vmstate.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tests/unit/test-vmstate.c b/tests/unit/test-vmstate.c
index XXXXXXX..XXXXXXX 100644
--- a/tests/unit/test-vmstate.c
+++ b/tests/unit/test-vmstate.c
@@ -XXX,XX +XXX,XX @@ static int temp_fd;
 /* Duplicate temp_fd and seek to the beginning of the file */
 static QEMUFile *open_test_file(bool write)
 {
-    int fd = dup(temp_fd);
+    int fd;
     QIOChannel *ioc;
     QEMUFile *f;
 
+    fd = dup(temp_fd);
+    g_assert(fd >= 0);
     lseek(fd, 0, SEEK_SET);
     if (write) {
         g_assert_cmpint(ftruncate(fd, 0), ==, 0);
@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv)
     g_autofree char *temp_file = g_strdup_printf("%s/vmst.test.XXXXXX",
                                                  g_get_tmp_dir());
     temp_fd = mkstemp(temp_file);
+    g_assert(temp_fd >= 0);
 
     module_call_init(MODULE_INIT_QOM);
 
-- 
2.20.1

Hi; here's a target-arm pullreq. Apologies for the size: this is
because it has all RTH's work to enable emulation of SME2p1 and
SVE2p1.

thanks
-- PMM

The following changes since commit c77283dd5d79149f4e7e9edd00f65416c648ee59:

Merge tag 'pull-request-2025-07-02' of https://gitlab.com/thuth/qemu into staging (2025-07-03 06:01:41 -0400)

are available in the Git repository at:

https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20250704

for you to fetch changes up to 083fef73585dfa03f72055ace6de8dec4912d0b0:

linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1 (2025-07-04 15:53:23 +0100)

----------------------------------------------------------------
target-arm queue:
 * Implement emulation of SME2p1 and SVE2p1
 * Correctly enforce alignment checks for v8M loads and
   stores done via helper functions
 * Mark the "highbank" and the "midway" machine as deprecated

----------------------------------------------------------------
Peter Maydell (4):
      target/arm: Rename FMOPA_h to FMOPA_w_h
      target/arm: Rename BFMOPA to BFMOPA_w
      target/arm: Implement FMOPA (non-widening) for fp16
      target/arm: Implement SME2 BFMOPA (non-widening)

Richard Henderson (103):
      target/arm: Fix SME vs AdvSIMD exception priority
      target/arm: Fix sve_access_check for SME
      target/arm: Fix 128-bit element ZIP, UZP, TRN
      target/arm: Replace @rda_rn_rm_e0 in sve.decode
      target/arm: Fix FMMLA (64-bit element) for 128-bit VL
      target/arm: Disable FEAT_F64MM if maximum SVE vector size too small
      target/arm: Fix PSEL size operands to tcg_gen_gvec_ands
      target/arm: Fix f16_dotadd vs nan selection
      target/arm: Fix bfdotadd_ebf vs nan selection
      target/arm: Remove CPUARMState.vfp.scratch
      target/arm: Introduce FPST_ZA, FPST_ZA_F16
      target/arm: Use FPST_ZA for sme_fmopa_[hsd]
      target/arm: Rename zarray to za_state.za
      target/arm: Add isar feature tests for SME2p1, SVE2p1
      target/arm: Add ZT0
      target/arm: Add zt0_excp_el to DisasContext
      target/arm: Implement SME2 ZERO ZT0
      target/arm: Add alignment argument to gen_sve_{ldr, str}
      target/arm: Implement SME2 LDR/STR ZT0
      target/arm: Implement SME2 MOVT
      target/arm: Split get_tile_rowcol argument tile_index
      target/arm: Rename MOVA for translate
      target/arm: Split out get_zarray
      target/arm: Introduce ARMCPU.sme_max_vq
      target/arm: Implement SME2 MOVA to/from tile, multiple registers
      target/arm: Implement SME2 MOVA to/from array, multiple registers
      target/arm: Implement SME2 BMOPA
      target/arm: Implement SME2 SMOPS, UMOPS (2-way)
      target/arm: Introduce gen_gvec_sve2_sqdmulh
      target/arm: Implement SME2 Multiple and Single SVE Destructive
      target/arm: Implement SME2 Multiple Vectors SVE Destructive
      target/arm: Implement SME2 ADD/SUB (array results, multiple and single vector)
      target/arm: Implement SME2 ADD/SUB (array results, multiple vectors)
      target/arm: Pass ZA to helper_sve2_fmlal_zz[zx]w_s
      target/arm: Add helper_gvec{_ah}_bfmlsl{_nx}
      target/arm: Implement SME2 FMLAL, BFMLAL
      target/arm: Implement SME2 FDOT
      target/arm: Implement SME2 BFDOT
      target/arm: Implement SME2 FVDOT, BFVDOT
      target/arm: Rename helper_gvec_*dot_[bh] to *_4[bh]
      target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT
      target/arm: Rename SVE SDOT and UDOT patterns
      target/arm: Tighten USDOT (vectors) decode
      target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1
      target/arm: Implement SME2 SVDOT, UVDOT, SUVDOT, USVDOT
      target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL
      target/arm: Rename gvec_fml[as]_[hs] with _nf_ infix
      target/arm: Implement SME2 FMLA, FMLS
      target/arm: Implement SME2 BFMLA, BFMLS
      target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB
      target/arm: Implement SME2 ADD/SUB (array accumulator)
      target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN
      target/arm: Implement SME2 FCVT (widening), FCVTL
      target/arm: Implement SME2 FCVTZS, FCVTZU
      target/arm: Implement SME2 SCVTF, UCVTF
      target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA
      target/arm: Introduce do_[us]sat_[bhs] macros
      target/arm: Use do_[us]sat_[bhs] in sve_helper.c
      target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU
      target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1
      target/arm: Implement SME2 SUNPK, UUNPK
      target/arm: Implement SME2 ZIP, UZP (four registers)
      target/arm: Move do_urshr, do_srshr to vec_internal.h
      target/arm: Implement SME2 SQRSHR, UQRSHR, SQRSHRN
      target/arm: Implement SME2 ZIP, UZP (two registers)
      target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP
      target/arm: Enable SCLAMP, UCLAMP for SVE2p1
      target/arm: Implement FCLAMP for SME2, SVE2p1
      target/arm: Implement SME2p1 Multiple Zero
      target/arm: Introduce pred_count_test
      target/arm: Fold predtest_ones into helper_sve_brkns
      target/arm: Expand do_zero inline
      target/arm: Split out do_whilel from helper_sve_whilel
      target/arm: Split out do_whileg from helper_sve_whileg
      target/arm: Move scale by esz into helper_sve_while*
      target/arm: Split trans_WHILE to lt and gt
      target/arm: Enable PSEL for SVE2p1
      target/arm: Implement SVE2p1 WHILE (predicate pair)
      target/arm: Implement SVE2p1 WHILE (predicate as counter)
      target/arm: Implement SVE2p1 PTRUE (predicate as counter)
      target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1
      target/arm: Implement SVE2p1 PEXT
      target/arm: Implement SME2 SEL
      target/arm: Implement ANDQV, ORQV, EORQV for SVE2p1
      target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV for SVE2p1
      target/arm: Implement BFMLSLB{L, T} for SME2/SVE2p1
      target/arm: Implement CNTP (predicate as counter) for SME2/SVE2p1
      target/arm: Implement DUPQ for SME2p1/SVE2p1
      target/arm: Implement EXTQ for SME2p1/SVE2p1
      target/arm: Implement PMOV for SME2p1/SVE2p1
      target/arm: Implement ZIPQ, UZPQ for SME2p1/SVE2p1
      target/arm: Implement TBLQ, TBXQ for SME2p1/SVE2p1
      target/arm: Implement SME2 counted predicate register load/store
      target/arm: Split the ST_zpri and ST_zprr patterns
      target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1
      target/arm: Move ld1qq and st1qq primitives to sve_ldst_internal.h
      target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1
      target/arm: Implement LD1Q, ST1Q for SVE2p1
      target/arm: Implement MOVAZ for SME2p1
      target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1
      target/arm: Support FPCR.AH in SME FMOPS, BFMOPS
      target/arm: Enable FEAT_SME2p1 on -cpu max
      linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1

Thomas Huth (1):
      hw/arm/highbank: Mark the "highbank" and the "midway" machine as deprecated

William Kosasih (11):
      target/arm: Bring VLSTM/VLLDM helper store/load closer to the ARM pseudocode
      target/arm: Fix BLXNS helper store alignment checks
      target/arm: Fix function_return helper load alignment checks
      target/arm: Fix VLDR helper load alignment checks
      target/arm: Fix VSTR helper store alignment checks
      target/arm: Fix VLDR_SG helper load alignment checks
      target/arm: Fix VSTR_SG helper store alignment checks
      target/arm: Fix VLD4 helper load alignment checks
      target/arm: Fix VLD2 helper load alignment checks
      target/arm: Fix VST4 helper store alignment checks
      target/arm: Fix VST2 helper store alignment checks

From: Thomas Huth <thuth@redhat.com>

We don't have any automatic regression tests for these machines and
when asking the usual suspects on the mailing list we came to the
conclusion that nobody tests these machines manually, too, so it seems
like this is currently just completely unused code. Mark them as depre-
cated to see whether anybody still speaks up during the deprecation
period, otherwise we can likely remove these two machines in a couple
of releases.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Message-id: 20250702113051.46483-1-thuth@redhat.com
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
[PMM: tweaked deprecation.rst text]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/about/deprecated.rst | 7 +++++++
 hw/arm/highbank.c         | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst
index XXXXXXX..XXXXXXX 100644
--- a/docs/about/deprecated.rst
+++ b/docs/about/deprecated.rst
@@ -XXX,XX +XXX,XX @@ they want to use and avoids confusion.  Existing users of the ``spike``
 machine must ensure that they're setting the ``spike`` machine in the
 command line (``-M spike``).
 
+Arm ``highbank`` and ``midway`` machines (since 10.1)
+'''''''''''''''''''''''''''''''''''''''''''''''''''''
+
+There are no known users left for these machines (if you still use it,
+please write a mail to the qemu-devel mailing list). If you just want to
+boot a Cortex-A15 or Cortex-A9 Linux, use the ``virt`` machine instead.
+
 
 System emulator binaries
 ------------------------
diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/arm/highbank.c
+++ b/hw/arm/highbank.c
@@ -XXX,XX +XXX,XX @@ static void highbank_class_init(ObjectClass *oc, const void *data)
     mc->max_cpus = 4;
     mc->ignore_memory_transaction_failures = true;
     mc->default_ram_id = "highbank.dram";
+    mc->deprecation_reason = "no known users left for this machine";
 }
 
 static const TypeInfo highbank_type = {
@@ -XXX,XX +XXX,XX @@ static void midway_class_init(ObjectClass *oc, const void *data)
     mc->max_cpus = 4;
     mc->ignore_memory_transaction_failures = true;
     mc->default_ram_id = "highbank.dram";
+    mc->deprecation_reason = "no known users left for this machine";
 }
 
 static const TypeInfo midway_type = {
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch brings the VLSTM and VLLDM helper functions closer to the ARM
pseudocode by adding MO_ALIGN to the MemOpIdx of the associated store
(`cpu_stl_mmu`) operations and load (`cpu_ldl_mmu`) operations.

Note that this is not a bug fix: an 8-byte alignment check already exists
and remains in place, enforcing stricter alignment than the 4 bytes
requirement in the individual loads and stores. This change merely makes the
helper implementations closer to the ARM pseudocode.

That said, as a side effect, the MMU index is now resolved once instead of
on every `cpu_*_data_ra` call, reducing redundant lookups

Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-2-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 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_vlstm)(CPUARMState *env, uint32_t fptr)
     bool s = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK;
     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,
+                                 arm_to_core_mmu_idx(mmu_idx));
 
     assert(env->v7m.secure);
 
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
      * Note that we do not use v7m_stack_write() here, because the
      * accesses should not set the FSR bits for stacking errors if they
      * fail. (In pseudocode terms, they are AccType_NORMAL, not AccType_STACK
-     * or AccType_LAZYFP). Faults in cpu_stl_data_ra() will throw exceptions
+     * or AccType_LAZYFP). Faults in cpu_stl_mmu() will throw exceptions
      * and longjmp out.
      */
     if (!(env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_LSPEN_MASK)) {
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
             if (i >= 16) {
                 faddr += 8; /* skip the slot for the FPSCR */
             }
-            cpu_stl_data_ra(env, faddr, slo, ra);
-            cpu_stl_data_ra(env, faddr + 4, shi, ra);
+            cpu_stl_mmu(env, faddr, slo, oi, ra);
+            cpu_stl_mmu(env, faddr + 4, shi, oi, ra);
         }
-        cpu_stl_data_ra(env, fptr + 0x40, vfp_get_fpscr(env), ra);
+        cpu_stl_mmu(env, fptr + 0x40, vfp_get_fpscr(env), oi, ra);
         if (cpu_isar_feature(aa32_mve, cpu)) {
-            cpu_stl_data_ra(env, fptr + 0x44, env->v7m.vpr, ra);
+            cpu_stl_mmu(env, fptr + 0x44, env->v7m.vpr, oi, ra);
         }
 
         /*
@@ -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,
+                                 arm_to_core_mmu_idx(mmu_idx));
 
     /* fptr is the value of Rn, the frame pointer we load the FP regs from */
     assert(env->v7m.secure);
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
                 faddr += 8; /* skip the slot for the FPSCR and VPR */
             }
 
-            slo = cpu_ldl_data_ra(env, faddr, ra);
-            shi = cpu_ldl_data_ra(env, faddr + 4, ra);
+            slo = cpu_ldl_mmu(env, faddr, oi, ra);
+            shi = cpu_ldl_mmu(env, faddr + 4, oi, ra);
 
             dn = (uint64_t) shi << 32 | slo;
             *aa32_vfp_dreg(env, i / 2) = dn;
         }
-        fpscr = cpu_ldl_data_ra(env, fptr + 0x40, ra);
+        fpscr = cpu_ldl_mmu(env, fptr + 0x40, oi, ra);
         vfp_set_fpscr(env, fpscr);
         if (cpu_isar_feature(aa32_mve, cpu)) {
-            env->v7m.vpr = cpu_ldl_data_ra(env, fptr + 0x44, ra);
+            env->v7m.vpr = cpu_ldl_mmu(env, fptr + 0x44, oi, ra);
         }
     }
 
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations (when stacking the
return pc and psr) in the BLXNS instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-3-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 7 +++++--
 1 file changed, 5 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 @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
     }
 
     /* Note that these stores can throw exceptions on MPU faults */
-    cpu_stl_data_ra(env, sp, nextinst, GETPC());
-    cpu_stl_data_ra(env, sp + 4, saved_psr, GETPC());
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
+    MemOpIdx oi = make_memop_idx(MO_TEUL | 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());
 
     env->regs[13] = sp;
     env->regs[14] = 0xfeffffff;
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations (when unstacking the
return pc and psr) in the FunctionReturn pseudocode.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-4-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/m_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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 @@ static bool do_v7m_function_return(ARMCPU *cpu)
          * do them as secure, so work out what MMU index that is.
          */
         mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true);
-        oi = make_memop_idx(MO_LEUL, arm_to_core_mmu_idx(mmu_idx));
+        oi = make_memop_idx(MO_LEUL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx));
         newpc = cpu_ldl_mmu(env, frameptr, oi, 0);
         newpsr = cpu_ldl_mmu(env, frameptr + 4, oi, 0);
 
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLDR
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-5-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VSTR
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-6-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 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)
         mve_advance_vpt(env);                                           \
     }
 
-#define DO_VSTR(OP, MSIZE, STTYPE, ESIZE, TYPE)                         \
+#define DO_VSTR(OP, MFLAG, MSIZE, STTYPE, ESIZE, TYPE)                  \
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr)    \
     {                                                                   \
         TYPE *d = vd;                                                   \
         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(MFLAG | MO_ALIGN, mmu_idx);        \
         for (b = 0, e = 0; b < 16; b += ESIZE, e++) {                   \
             if (mask & (1 << b)) {                                      \
-                cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \
+                cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \
             }                                                           \
             addr += MSIZE;                                              \
         }                                                               \
@@ -XXX,XX +XXX,XX @@ 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_VSTR(vstrb, 1, stb, 1, uint8_t)
-DO_VSTR(vstrh, 2, stw, 2, uint16_t)
-DO_VSTR(vstrw, 4, stl, 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_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)
@@ -XXX,XX +XXX,XX @@ 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_VSTR(vstrb_h, 1, stb, 2, int16_t)
-DO_VSTR(vstrb_w, 1, stb, 4, int32_t)
-DO_VSTR(vstrh_w, 2, stw, 4, int32_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)
 
 #undef DO_VLDR
 #undef DO_VSTR
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLDR_SG
instructions.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-7-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 42 ++++++++++++++++++++++---------------
 1 file changed, 25 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 @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
  * For loads, predicated lanes are zeroed instead of retaining
  * their previous values.
  */
-#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)        \
+#define DO_VLDR_SG(OP, MFLAG, MTYPE, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)\
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm,         \
                           uint32_t base)                                \
     {                                                                   \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         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);        \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H##ESIZE(e)]);                        \
             d[H##ESIZE(e)] = (mask & 1) ?                               \
-                cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0;         \
+                (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0;  \
             if (WB) {                                                   \
                 m[H##ESIZE(e)] = addr;                                  \
             }                                                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         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);      \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H4(e & ~1)]);                         \
             addr += 4 * (e & 1);                                        \
-            d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \
+            d[H4(e)] = (mask & 1) ? cpu_ldl_mmu(env, addr, oi, GETPC()) : 0; \
             if (WB && (e & 1)) {                                        \
                 m[H4(e & ~1)] = addr - 4;                               \
             }                                                           \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
 #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2))
 #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3))
 
-DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false)
+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(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_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_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false)
+DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, 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,
+           uint16_t, uint16_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, 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,
+           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, stb, 1, uint8_t, ADDR_ADD, false)
@@ -XXX,XX +XXX,XX @@ DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false)
 DO_VSTR_SG(vstrw_sg_os_uw, 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, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, 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, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VSTR_SG
instructions.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-8-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 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_TEUW, 2, stw, 4, int32_t)
     }
 
 /* We know here TYPE is unsigned so always the same as the offset type */
-#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB)                 \
+#define DO_VSTR_SG(OP, MFLAG, STTYPE, ESIZE, TYPE, ADDRFN, WB)          \
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm,         \
                           uint32_t base)                                \
     {                                                                   \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         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);        \
         for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H##ESIZE(e)]);                        \
             if (mask & 1) {                                             \
-                cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \
+                cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \
             }                                                           \
             if (WB) {                                                   \
                 m[H##ESIZE(e)] = addr;                                  \
@@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         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);      \
         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)
             addr = ADDRFN(base, m[H4(e & ~1)]);                         \
             addr += 4 * (e & 1);                                        \
             if (mask & 1) {                                             \
-                cpu_stl_data_ra(env, addr, d[H4(e)], GETPC());          \
+                cpu_stl_mmu(env, addr, d[H4(e)], oi, GETPC());          \
             }                                                           \
             if (WB && (e & 1)) {                                        \
                 m[H4(e & ~1)] = addr - 4;                               \
@@ -XXX,XX +XXX,XX @@ DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, 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, stb, 1, uint8_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false)
-DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, 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_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false)
 
-DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false)
-DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, 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_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_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
-DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true)
+DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
 
 /*
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLD4
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-9-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 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_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint16_t mask = mve_eci_mask(env);                              \
         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);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 4;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             for (e = 0; e < 4; e++, data >>= 8) {                       \
                 uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \
                 qd[H1(off[beat])] = data;                               \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t addr, data;                                            \
         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);      \
         for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) {   \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 8 + (beat & 1) * 4;               \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y);             \
             qd[H2(off[beat])] = data;                                   \
             data >>= 16;                                                \
@@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
         uint32_t addr, data;                                            \
         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);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 4;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             y = (beat + (O1 & 2)) & 3;                                  \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y);             \
             qd[H4(off[beat] >> 2)] = data;                              \
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the load operations in the VLD2
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-10-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 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_VLD4W(vld43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         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);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 2;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             for (e = 0; e < 4; e++, data >>= 8) {                       \
                 qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1));    \
                 qd[H1(off[beat] + (e >> 1))] = data;                    \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         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);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat] * 4;                                \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             for (e = 0; e < 2; e++, data >>= 16) {                      \
                 qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e);         \
                 qd[H2(off[beat])] = data;                               \
@@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         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);      \
         for (beat = 0; beat < 4; beat++, mask >>= 4) {                  \
             if ((mask & 1) == 0) {                                      \
                 /* ECI says skip this beat */                           \
                 continue;                                               \
             }                                                           \
             addr = base + off[beat];                                    \
-            data = cpu_ldl_le_data_ra(env, addr, GETPC());              \
+            data = cpu_ldl_mmu(env, addr, oi, GETPC());                 \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1));    \
             qd[H4(off[beat] >> 3)] = data;                              \
         }                                                               \
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VST4
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-11-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 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_VLD2W(vld21w, 8, 12, 16, 20)
         uint16_t mask = mve_eci_mask(env);                              \
         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);      \
         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)
                 uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \
                 data = (data << 8) | qd[H1(off[beat])];                 \
             }                                                           \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t addr, data;                                            \
         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);      \
         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)
             data = qd[H2(off[beat])];                                   \
             qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1);         \
             data |= qd[H2(off[beat])] << 16;                            \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20)
         uint32_t addr, data;                                            \
         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);      \
         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)
             y = (beat + (O1 & 2)) & 3;                                  \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y);             \
             data = qd[H4(off[beat] >> 2)];                              \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
-- 
2.43.0

From: William Kosasih <kosasihwilliam4@gmail.com>

This patch adds alignment checks in the store operations in the VST2
instruction.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-12-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/mve_helper.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 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_VST4W(vst43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         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);      \
         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)
                 qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1));    \
                 data = (data << 8) | qd[H1(off[beat] + (e >> 1))];      \
             }                                                           \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         uint32_t addr, data;                                            \
         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);      \
         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)
                 qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e);         \
                 data = (data << 16) | qd[H2(off[beat])];                \
             }                                                           \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
@@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9)
         static const uint8_t off[4] = { O1, O2, O3, O4 };               \
         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);      \
         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)
             addr = base + off[beat];                                    \
             qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1));    \
             data = qd[H4(off[beat] >> 3)];                              \
-            cpu_stl_le_data_ra(env, addr, data, GETPC());               \
+            cpu_stl_mmu(env, addr, data, oi, GETPC());                  \
         }                                                               \
     }
 
-- 
2.43.0

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

We failed to raise an exception when
sme_excp_el == 0 and fp_excp_el == 1.

Cc: qemu-stable@nongnu.org
Fixes: 3d74825f4d6 ("target/arm: Add SME enablement checks")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

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 @@ bool sme_enabled_check(DisasContext *s)
      * to be zero when fp_excp_el has priority.  This is because we need
      * sme_excp_el by itself for cpregs access checks.
      */
-    if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) {
+    if (s->sme_excp_el
+        && (!s->fp_excp_el || s->sme_excp_el <= s->fp_excp_el)) {
         bool ret = sme_access_check(s);
         s->fp_access_checked = (ret ? 1 : -1);
         return ret;
-- 
2.43.0

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

Do not assume SME implies SVE.  Ensure that the non-streaming
check is present along the SME path, since it is not implied
by sme_*_enabled_check.

Cc: qemu-stable@nongnu.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 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 fp_access_check_only(DisasContext *s)
     return true;
 }
 
-static bool fp_access_check(DisasContext *s)
+static bool nonstreaming_check(DisasContext *s)
 {
-    if (!fp_access_check_only(s)) {
-        return false;
-    }
     if (s->sme_trap_nonstreaming && s->is_nonstreaming) {
         gen_exception_insn(s, 0, EXCP_UDEF,
                            syn_smetrap(SME_ET_Streaming, false));
@@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s)
     return true;
 }
 
+static bool fp_access_check(DisasContext *s)
+{
+    return fp_access_check_only(s) && nonstreaming_check(s);
+}
+
 /*
  * Return <0 for non-supported element sizes, with MO_16 controlled by
  * FEAT_FP16; return 0 for fp disabled; otherwise return >0 for success.
@@ -XXX,XX +XXX,XX @@ static int fp_access_check_vector_hsd(DisasContext *s, bool is_q, MemOp esz)
  */
 bool sve_access_check(DisasContext *s)
 {
-    if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) {
+    if (dc_isar_feature(aa64_sme, s)) {
         bool ret;
 
-        assert(dc_isar_feature(aa64_sme, s));
-        ret = sme_sm_enabled_check(s);
+        if (s->pstate_sm) {
+            ret = sme_enabled_check(s);
+        } else if (dc_isar_feature(aa64_sve, s)) {
+            goto continue_sve;
+        } else {
+            ret = sme_sm_enabled_check(s);
+        }
+        if (ret) {
+            ret = nonstreaming_check(s);
+        }
         s->sve_access_checked = (ret ? 1 : -1);
         return ret;
     }
+
+ continue_sve:
     if (s->sve_excp_el) {
         /* Assert that we only raise one exception per instruction. */
         assert(!s->sve_access_checked);
-- 
2.43.0

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

We missed the instructions UDEF when the vector size is too small.
We missed marking the instructions non-streaming with SME.

Cc: qemu-stable@nongnu.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-4-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 43 ++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 13 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 @@ TRANS_FEAT(PUNPKHI, aa64_sve, do_perm_pred2, a, 1, gen_helper_sve_punpk_p)
  *** SVE Permute - Interleaving Group
  */
 
+static bool do_interleave_q(DisasContext *s, gen_helper_gvec_3 *fn,
+                            arg_rrr_esz *a, int data)
+{
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        if (vsz < 32) {
+            unallocated_encoding(s);
+        } else {
+            tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd),
+                               vec_full_reg_offset(s, a->rn),
+                               vec_full_reg_offset(s, a->rm),
+                               vsz, vsz, data, fn);
+        }
+    }
+    return true;
+}
+
 static gen_helper_gvec_3 * const zip_fns[4] = {
     gen_helper_sve_zip_b, gen_helper_sve_zip_h,
     gen_helper_sve_zip_s, gen_helper_sve_zip_d,
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ZIP1_z, aa64_sve, gen_gvec_ool_arg_zzz,
 TRANS_FEAT(ZIP2_z, aa64_sve, gen_gvec_ool_arg_zzz,
            zip_fns[a->esz], a, vec_full_reg_size(s) / 2)
 
-TRANS_FEAT(ZIP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_zip_q, a, 0)
-TRANS_FEAT(ZIP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_zip_q, a,
-           QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2)
+TRANS_FEAT_NONSTREAMING(ZIP1_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_zip_q, a, 0)
+TRANS_FEAT_NONSTREAMING(ZIP2_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_zip_q, a,
+                        QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2)
 
 static gen_helper_gvec_3 * const uzp_fns[4] = {
     gen_helper_sve_uzp_b, gen_helper_sve_uzp_h,
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz,
 TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz,
            uzp_fns[a->esz], a, 1 << a->esz)
 
-TRANS_FEAT(UZP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_uzp_q, a, 0)
-TRANS_FEAT(UZP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_uzp_q, a, 16)
+TRANS_FEAT_NONSTREAMING(UZP1_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_uzp_q, a, 0)
+TRANS_FEAT_NONSTREAMING(UZP2_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_uzp_q, a, 16)
 
 static gen_helper_gvec_3 * const trn_fns[4] = {
     gen_helper_sve_trn_b, gen_helper_sve_trn_h,
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN1_z, aa64_sve, gen_gvec_ool_arg_zzz,
 TRANS_FEAT(TRN2_z, aa64_sve, gen_gvec_ool_arg_zzz,
            trn_fns[a->esz], a, 1 << a->esz)
 
-TRANS_FEAT(TRN1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_trn_q, a, 0)
-TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz,
-           gen_helper_sve2_trn_q, a, 16)
+TRANS_FEAT_NONSTREAMING(TRN1_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_trn_q, a, 0)
+TRANS_FEAT_NONSTREAMING(TRN2_q, aa64_sve_f64mm, do_interleave_q,
+                        gen_helper_sve2_trn_q, a, 16)
 
 /*
  *** SVE Permute Vector - Predicated Group
-- 
2.43.0

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

Replace @rda_rn_rm_e0 with @rda_rn_rm_ex, and require
users to supply an explicit esz.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode | 48 +++++++++++++++++++--------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@
 @rda_rn_rm      ........ esz:2 . rm:5 ... ... rn:5 rd:5 \
                 &rrrr_esz ra=%reg_movprfx
 
-# Four operand with unused vector element size
-@rda_rn_rm_e0   ........ ... rm:5 ... ... rn:5 rd:5 \
-                &rrrr_esz esz=0 ra=%reg_movprfx
-@rdn_ra_rm_e0   ........ ... rm:5 ... ... ra:5 rd:5 \
-                &rrrr_esz esz=0 rn=%reg_movprfx
+# Four operand with explicit vector element size
+@rda_rn_rm_ex   ........ ... rm:5 ... ... rn:5 rd:5 \
+                &rrrr_esz ra=%reg_movprfx
+@rdn_ra_rm_ex   ........ ... rm:5 ... ... ra:5 rd:5 \
+                &rrrr_esz rn=%reg_movprfx
 
 # Three operand with "memory" size, aka immediate left shift
 @rd_rn_msz_rm   ........ ... rm:5 .... imm:2 rn:5 rd:5          &rrri
@@ -XXX,XX +XXX,XX @@ XAR             00000100 .. 1 ..... 001 101 rm:5  rd:5   &rrri_esz \
                 rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr
 
 # SVE2 bitwise ternary operations
-EOR3            00000100 00 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
-BSL             00000100 00 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
-BCAX            00000100 01 1 ..... 001 110 ..... .....         @rdn_ra_rm_e0
-BSL1N           00000100 01 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
-BSL2N           00000100 10 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
-NBSL            00000100 11 1 ..... 001 111 ..... .....         @rdn_ra_rm_e0
+EOR3            00000100 00 1 ..... 001 110 ..... .....     @rdn_ra_rm_ex esz=0
+BSL             00000100 00 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
+BCAX            00000100 01 1 ..... 001 110 ..... .....     @rdn_ra_rm_ex esz=0
+BSL1N           00000100 01 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
+BSL2N           00000100 10 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
+NBSL            00000100 11 1 ..... 001 111 ..... .....     @rdn_ra_rm_ex esz=0
 
 ### SVE Index Generation Group
 
@@ -XXX,XX +XXX,XX @@ EORTB           01000101 .. 0 ..... 10010 1 ..... .....  @rd_rn_rm
 
 ## SVE integer matrix multiply accumulate
 
-SMMLA           01000101 00 0 ..... 10011 0 ..... .....  @rda_rn_rm_e0
-USMMLA          01000101 10 0 ..... 10011 0 ..... .....  @rda_rn_rm_e0
-UMMLA           01000101 11 0 ..... 10011 0 ..... .....  @rda_rn_rm_e0
+SMMLA           01000101 00 0 ..... 10011 0 ..... .....  @rda_rn_rm_ex esz=2
+USMMLA          01000101 10 0 ..... 10011 0 ..... .....  @rda_rn_rm_ex esz=2
+UMMLA           01000101 11 0 ..... 10011 0 ..... .....  @rda_rn_rm_ex esz=2
 
 ## SVE2 bitwise permute
 
@@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 USDOT_zzzz      01000100 .. 0 ..... 011 110 ..... .....  @rda_rn_rm
 
 ### SVE2 floating point matrix multiply accumulate
-BFMMLA          01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
-FMMLA_s         01100100 10 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
-FMMLA_d         01100100 11 1 ..... 111 001 ..... .....  @rda_rn_rm_e0
+BFMMLA          01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=1
+FMMLA_s         01100100 10 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=2
+FMMLA_d         01100100 11 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=3
 
 ### SVE2 Memory Gather Load Group
 
@@ -XXX,XX +XXX,XX @@ FCVTLT_sd       01100100 11 0010 11 101 ... ..... .....  @rd_pg_rn_e0
 FLOGB           01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5  &rpr_esz
 
 ### SVE2 floating-point multiply-add long (vectors)
-FMLALB_zzzw     01100100 10 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
-FMLALT_zzzw     01100100 10 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
-FMLSLB_zzzw     01100100 10 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_e0
-FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_e0
+FMLALB_zzzw     01100100 10 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
+FMLALT_zzzw     01100100 10 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_ex esz=2
+FMLSLB_zzzw     01100100 10 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_ex esz=2
+FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
-BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
-BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_e0
+BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
+BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point bfloat16 dot-product
-BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_e0
+BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point multiply-add long (indexed)
 FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
-- 
2.43.0

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: 20250704142112.1018902-6-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 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 @@ DO_ZPZZ_FP(FMINNMP, aa64_sve2, sve2_fminnmp_zpzz)
 DO_ZPZZ_FP(FMAXP, aa64_sve2, sve2_fmaxp_zpzz)
 DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz)
 
+static bool do_fmmla(DisasContext *s, arg_rrrr_esz *a,
+                     gen_helper_gvec_4_ptr *fn)
+{
+    if (sve_access_check(s)) {
+        if (vec_full_reg_size(s) < 4 * memop_size(a->esz)) {
+            unallocated_encoding(s);
+        } else {
+            gen_gvec_fpst_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, 0, FPST_A64);
+        }
+    }
+    return true;
+}
+
+TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, do_fmmla, a, gen_helper_fmmla_s)
+TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, do_fmmla, a, gen_helper_fmmla_d)
+
 /*
  * SVE Integer Multiply-Add (unpredicated)
  */
 
-TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz,
-                        gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra,
-                        0, FPST_A64)
-TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz,
-                        gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra,
-                        0, FPST_A64)
-
 static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = {
     NULL,                           gen_helper_sve2_sqdmlal_zzzw_h,
     gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d,
-- 
2.43.0

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

All F64MM instructions operate on a 256-bit vector.
If only 128-bit vectors is supported by the cpu,
then the cpu cannot enable F64MM.

Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-7-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu64.c | 7 +++++++
 1 file changed, 7 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 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
     /* From now on sve_max_vq is the actual maximum supported length. */
     cpu->sve_max_vq = max_vq;
     cpu->sve_vq.map = vq_map;
+
+    /* FEAT_F64MM requires the existence of a 256-bit vector size. */
+    if (max_vq < 2) {
+        uint64_t t = GET_IDREG(&cpu->isar, ID_AA64ZFR0);
+        t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 0);
+        SET_IDREG(&cpu->isar, ID_AA64ZFR0, t);
+    }
 }
 
 /*
-- 
2.43.0

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

Gvec only operates on size 8 and multiples of 16.
Predicates may be any multiple of 2.
Round up the size using the appropriate function.

Cc: qemu-stable@nongnu.org
Fixes: 598ab0b24c0 ("target/arm: Implement PSEL")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 1 +
 1 file changed, 1 insertion(+)

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 bool trans_PSEL(DisasContext *s, arg_psel *a)
     tcg_gen_neg_i64(tmp, tmp);
 
     /* Apply to either copy the source, or write zeros. */
+    pl = size_for_gvec(pl);
     tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd),
                       pred_full_reg_offset(s, a->pn), tmp, pl, pl);
     return true;
-- 
2.43.0

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

Implement FPProcessNaNs4 within f16_dotadd, rather than
simply letting NaNs propagate through the function.

Cc: qemu-stable@nongnu.org
Fixes: 3916841ac75 ("target/arm: Implement FMOPA, FMOPS (widening)")
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-9-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme_helper.c | 62 +++++++++++++++++++++++++++----------
 1 file changed, 46 insertions(+), 16 deletions(-)

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
      *  - 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;
+    float16 h1r = e1 & 0xffff;
+    float16 h1c = e1 >> 16;
+    float16 h2r = e2 & 0xffff;
+    float16 h2c = e2 >> 16;
     float32 t32;
 
-    /*
-     * The ARM pseudocode function FPDot performs both multiplies
-     * and the add with a single rounding operation.  Emulate this
-     * by performing the first multiply in round-to-odd, then doing
-     * the second multiply as fused multiply-add, and rounding to
-     * float32 all in one step.
-     */
-    t64 = float64_mul(e1r, e2r, s_odd);
-    t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std);
+    /* C.f. FPProcessNaNs4 */
+    if (float16_is_any_nan(h1r) || float16_is_any_nan(h1c) ||
+        float16_is_any_nan(h2r) || float16_is_any_nan(h2c)) {
+        float16 t16;
 
-    /* This conversion is exact, because we've already rounded. */
-    t32 = float64_to_float32(t64, s_std);
+        if (float16_is_signaling_nan(h1r, s_f16)) {
+            t16 = h1r;
+        } else if (float16_is_signaling_nan(h1c, s_f16)) {
+            t16 = h1c;
+        } else if (float16_is_signaling_nan(h2r, s_f16)) {
+            t16 = h2r;
+        } else if (float16_is_signaling_nan(h2c, s_f16)) {
+            t16 = h2c;
+        } else if (float16_is_any_nan(h1r)) {
+            t16 = h1r;
+        } else if (float16_is_any_nan(h1c)) {
+            t16 = h1c;
+        } else if (float16_is_any_nan(h2r)) {
+            t16 = h2r;
+        } else {
+            t16 = h2c;
+        }
+        t32 = float16_to_float32(t16, true, s_f16);
+    } else {
+        float64 e1r = float16_to_float64(h1r, true, s_f16);
+        float64 e1c = float16_to_float64(h1c, true, s_f16);
+        float64 e2r = float16_to_float64(h2r, true, s_f16);
+        float64 e2c = float16_to_float64(h2c, true, s_f16);
+        float64 t64;
+
+        /*
+         * The ARM pseudocode function FPDot performs both multiplies
+         * and the add with a single rounding operation.  Emulate this
+         * by performing the first multiply in round-to-odd, then doing
+         * the second multiply as fused multiply-add, and rounding to
+         * float32 all in one step.
+         */
+        t64 = float64_mul(e1r, e2r, s_odd);
+        t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std);
+
+        /* This conversion is exact, because we've already rounded. */
+        t32 = float64_to_float32(t64, s_std);
+    }
 
     /* The final accumulation step is not fused. */
     return float32_add(sum, t32, s_std);
-- 
2.43.0

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

Implement FPProcessNaNs4 within bfdotadd_ebf, rather than
simply letting NaNs propagate through the function.

Cc: qemu-stable@nongnu.org
Fixes: 0e1850182a1 ("target/arm: Implement FPCR.EBF=1 semantics for bfdotadd()")
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-10-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_helper.c | 75 ++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 22 deletions(-)

diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst)
 float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2,
                      float_status *fpst, float_status *fpst_odd)
 {
-    /*
-     * Compare f16_dotadd() in sme_helper.c, but here we have
-     * bfloat16 inputs. In particular that means that we do not
-     * want the FPCR.FZ16 flush semantics, so we use the normal
-     * float_status for the input handling here.
-     */
-    float64 e1r = float32_to_float64(e1 << 16, fpst);
-    float64 e1c = float32_to_float64(e1 & 0xffff0000u, fpst);
-    float64 e2r = float32_to_float64(e2 << 16, fpst);
-    float64 e2c = float32_to_float64(e2 & 0xffff0000u, fpst);
-    float64 t64;
+    float32 s1r = e1 << 16;
+    float32 s1c = e1 & 0xffff0000u;
+    float32 s2r = e2 << 16;
+    float32 s2c = e2 & 0xffff0000u;
     float32 t32;
 
-    /*
-     * The ARM pseudocode function FPDot performs both multiplies
-     * and the add with a single rounding operation.  Emulate this
-     * by performing the first multiply in round-to-odd, then doing
-     * the second multiply as fused multiply-add, and rounding to
-     * float32 all in one step.
-     */
-    t64 = float64_mul(e1r, e2r, fpst_odd);
-    t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst);
+    /* C.f. FPProcessNaNs4 */
+    if (float32_is_any_nan(s1r) || float32_is_any_nan(s1c) ||
+        float32_is_any_nan(s2r) || float32_is_any_nan(s2c)) {
+        if (float32_is_signaling_nan(s1r, fpst)) {
+            t32 = s1r;
+        } else if (float32_is_signaling_nan(s1c, fpst)) {
+            t32 = s1c;
+        } else if (float32_is_signaling_nan(s2r, fpst)) {
+            t32 = s2r;
+        } else if (float32_is_signaling_nan(s2c, fpst)) {
+            t32 = s2c;
+        } else if (float32_is_any_nan(s1r)) {
+            t32 = s1r;
+        } else if (float32_is_any_nan(s1c)) {
+            t32 = s1c;
+        } else if (float32_is_any_nan(s2r)) {
+            t32 = s2r;
+        } else {
+            t32 = s2c;
+        }
+        /*
+         * FPConvertNaN(FPProcessNaN(t32)) will be done as part
+         * of the final addition below.
+         */
+    } else {
+        /*
+         * Compare f16_dotadd() in sme_helper.c, but here we have
+         * bfloat16 inputs. In particular that means that we do not
+         * want the FPCR.FZ16 flush semantics, so we use the normal
+         * float_status for the input handling here.
+         */
+        float64 e1r = float32_to_float64(s1r, fpst);
+        float64 e1c = float32_to_float64(s1c, fpst);
+        float64 e2r = float32_to_float64(s2r, fpst);
+        float64 e2c = float32_to_float64(s2c, fpst);
+        float64 t64;
 
-    /* This conversion is exact, because we've already rounded. */
-    t32 = float64_to_float32(t64, fpst);
+        /*
+         * The ARM pseudocode function FPDot performs both multiplies
+         * and the add with a single rounding operation.  Emulate this
+         * by performing the first multiply in round-to-odd, then doing
+         * the second multiply as fused multiply-add, and rounding to
+         * float32 all in one step.
+         */
+        t64 = float64_mul(e1r, e2r, fpst_odd);
+        t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst);
+
+        /* This conversion is exact, because we've already rounded. */
+        t32 = float64_to_float32(t64, fpst);
+    }
 
     /* The final accumulation step is not fused. */
     return float32_add(sum, t32, fpst);
-- 
2.43.0

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

Rather than repeatedly copying FPST_FPCR to locals
and setting default nan mode, create dedicated float_status.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h            | 12 +++++++++++-
 target/arm/cpu.c            |  4 ++++
 target/arm/tcg/vfp_helper.c | 12 +++++++++++-
 3 files changed, 26 insertions(+), 2 deletions(-)

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 @@ typedef struct NVICState NVICState;
  *       when FPCR.AH == 1 (bfloat16 conversions and multiplies,
  *       and the reciprocal and square root estimate/step insns);
  *       for half-precision
+ * ZA: the "streaming sve" fp status.
+ * ZA_F16: likewise for half-precision.
  *
  * Half-precision operations are governed by a separate
  * flush-to-zero control bit in FPSCR:FZ16. We pass a separate
@@ -XXX,XX +XXX,XX @@ typedef struct NVICState NVICState;
  * they ignore FPCR.RMode. But they don't ignore FPCR.FZ16,
  * which means we need an FPST_AH_F16 as well.
  *
+ * The "ZA" float_status are for Streaming SVE operations which use
+ * default-NaN and do not generate fp exceptions, which means that they
+ * do not accumulate exception bits back into FPCR.
+ * See e.g. FPAdd vs FPAdd_ZA pseudocode functions, and the setting
+ * of fpcr.DN and fpexec parameters.
+ *
  * To avoid having to transfer exception bits around, we simply
  * say that the FPSCR cumulative exception flags are the logical
  * OR of the flags in the four fp statuses. This relies on the
@@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour {
     FPST_A64_F16,
     FPST_AH,
     FPST_AH_F16,
+    FPST_ZA,
+    FPST_ZA_F16,
     FPST_STD,
     FPST_STD_F16,
 } ARMFPStatusFlavour;
-#define FPST_COUNT  8
+#define FPST_COUNT  10
 
 typedef struct CPUArchState {
     /* Regs for current mode.  */
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 arm_cpu_reset_hold(Object *obj, ResetType type)
     set_flush_inputs_to_zero(1, &env->vfp.fp_status[FPST_STD]);
     set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD]);
     set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD_F16]);
+    set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA]);
+    set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA_F16]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
+    arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32_F16]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+    arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
     arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD_F16]);
     arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_AH]);
     set_flush_to_zero(1, &env->vfp.fp_status[FPST_AH]);
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 @@ uint32_t vfp_get_fpsr_from_host(CPUARMState *env)
     a64_flags |= (get_float_exception_flags(&env->vfp.fp_status[FPST_A64_F16])
           & ~(float_flag_input_denormal_flushed | float_flag_input_denormal_used));
     /*
-     * We do not merge in flags from FPST_AH or FPST_AH_F16, because
+     * We do not merge in flags from FPST_{AH,ZA} or FPST_{AH,ZA}_F16, because
      * they are used for insns that must not set the cumulative exception bits.
      */
 
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
         set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64]);
         set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A32_F16]);
         set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64_F16]);
+        set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA]);
+        set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA_F16]);
     }
     if (changed & FPCR_FZ16) {
         bool ftz_enabled = val & FPCR_FZ16;
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]);
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]);
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]);
+        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]);
+        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]);
     }
     if (changed & FPCR_FZ) {
         bool ftz_enabled = val & FPCR_FZ;
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]);
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64]);
+        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA]);
         /* FIZ is A64 only so FZ always makes A32 code flush inputs to zero */
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]);
     }
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
         bool fitz_enabled = (val & FPCR_FIZ) ||
             (val & (FPCR_FZ | FPCR_AH)) == FPCR_FZ;
         set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_A64]);
+        set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_ZA]);
     }
     if (changed & FPCR_DN) {
         bool dnan_enabled = val & FPCR_DN;
@@ -XXX,XX +XXX,XX @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
             /* Change behaviours for A64 FP operations */
             arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
             arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+            arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
+            arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
         } else {
             arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
             arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+            arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
+            arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
         }
     }
     /*
-- 
2.43.0

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: 20250704142112.1018902-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme_helper.c    | 37 ++++++++--------------------------
 target/arm/tcg/translate-sme.c |  4 ++--
 2 files changed, 10 insertions(+), 31 deletions(-)

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
 }
 
 void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
-                         void *vpm, float_status *fpst_in, uint32_t desc)
+                         void *vpm, float_status *fpst, uint32_t desc)
 {
     intptr_t row, col, oprsz = simd_maxsz(desc);
     uint32_t neg = simd_data(desc) << 31;
     uint16_t *pn = vpn, *pm = vpm;
-    float_status fpst;
-
-    /*
-     * Make a copy of float_status because this operation does not
-     * update the cumulative fp exception status.  It also produces
-     * default nans.
-     */
-    fpst = *fpst_in;
-    set_default_nan_mode(true, &fpst);
 
     for (row = 0; row < oprsz; ) {
         uint16_t pa = pn[H2(row >> 4)];
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
                         if (pb & 1) {
                             uint32_t *a = vza_row + H1_4(col);
                             uint32_t *m = vzm + H1_4(col);
-                            *a = float32_muladd(n, *m, *a, 0, &fpst);
+                            *a = float32_muladd(n, *m, *a, 0, fpst);
                         }
                         col += 4;
                         pb >>= 4;
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
 }
 
 void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
-                         void *vpm, float_status *fpst_in, uint32_t desc)
+                         void *vpm, float_status *fpst, uint32_t desc)
 {
     intptr_t row, col, oprsz = simd_oprsz(desc) / 8;
     uint64_t neg = (uint64_t)simd_data(desc) << 63;
     uint64_t *za = vza, *zn = vzn, *zm = vzm;
     uint8_t *pn = vpn, *pm = vpm;
-    float_status fpst = *fpst_in;
-
-    set_default_nan_mode(true, &fpst);
 
     for (row = 0; row < oprsz; ++row) {
         if (pn[H1(row)] & 1) {
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
             for (col = 0; col < oprsz; ++col) {
                 if (pm[H1(col)] & 1) {
                     uint64_t *a = &za_row[col];
-                    *a = float64_muladd(n, zm[col], *a, 0, &fpst);
+                    *a = float64_muladd(n, zm[col], *a, 0, fpst);
                 }
             }
         }
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
     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, fpst_f16;
+    float_status fpst_odd = env->vfp.fp_status[FPST_ZA];
 
-    /*
-     * Make copies of the fp status fields we use, 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_f16 = env->vfp.fp_status[FPST_A64_F16];
-    fpst_std = env->vfp.fp_status[FPST_A64];
-    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);
 
     for (row = 0; row < oprsz; ) {
@@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
 
                         m = f16mop_adj_pair(m, pcol, 0);
                         *a = f16_dotadd(*a, n, m,
-                                        &fpst_f16, &fpst_std, &fpst_odd);
+                                        &env->vfp.fp_status[FPST_ZA_F16],
+                                        &env->vfp.fp_status[FPST_ZA],
+                                        &fpst_odd);
                     }
                     col += 4;
                     pcol >>= 4;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
 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_A64, gen_helper_sme_fmopa_s)
+           MO_32, FPST_ZA, gen_helper_sme_fmopa_s)
 TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
-           MO_64, FPST_A64, gen_helper_sme_fmopa_d)
+           MO_64, FPST_ZA, gen_helper_sme_fmopa_d)
 
 TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa)
 
-- 
2.43.0

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

The whole ZA state will also contain ZT0.
Make things easier in aarch64_set_svcr to zero both
by wrapping them in a common structure.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h               | 48 +++++++++++++++++++---------------
 linux-user/aarch64/signal.c    |  4 +--
 target/arm/cpu.c               |  4 +--
 target/arm/helper.c            |  2 +-
 target/arm/machine.c           |  2 +-
 target/arm/tcg/sme_helper.c    |  6 ++---
 target/arm/tcg/translate-sme.c |  4 +--
 7 files changed, 38 insertions(+), 32 deletions(-)

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 @@ typedef struct CPUArchState {
 
     uint64_t scxtnum_el[4];
 
-    /*
-     * SME ZA storage -- 256 x 256 byte array, with bytes in host word order,
-     * as we do with vfp.zregs[].  This corresponds to the architectural ZA
-     * array, where ZA[N] is in the least-significant bytes of env->zarray[N].
-     * When SVL is less than the architectural maximum, the accessible
-     * storage is restricted, such that if the SVL is X bytes the guest can
-     * see only the bottom X elements of zarray[], and only the least
-     * significant X bytes of each element of the array. (In other words,
-     * the observable part is always square.)
-     *
-     * The ZA storage can also be considered as a set of square tiles of
-     * elements of different sizes. The mapping from tiles to the ZA array
-     * is architecturally defined, such that for tiles of elements of esz
-     * bytes, the Nth row (or "horizontal slice") of tile T is in
-     * ZA[T + N * esz]. Note that this means that each tile is not contiguous
-     * in the ZA storage, because its rows are striped through the ZA array.
-     *
-     * Because this is so large, keep this toward the end of the reset area,
-     * to keep the offsets into the rest of the structure smaller.
-     */
-    ARMVectorReg zarray[ARM_MAX_VQ * 16];
+    struct {
+        /*
+         * SME ZA storage -- 256 x 256 byte array, with bytes in host
+         * word order, as we do with vfp.zregs[].  This corresponds to
+         * the architectural ZA array, where ZA[N] is in the least
+         * significant bytes of env->za_state.za[N].
+         *
+         * When SVL is less than the architectural maximum, the accessible
+         * storage is restricted, such that if the SVL is X bytes the guest
+         * can see only the bottom X elements of zarray[], and only the least
+         * significant X bytes of each element of the array. (In other words,
+         * the observable part is always square.)
+         *
+         * The ZA storage can also be considered as a set of square tiles of
+         * elements of different sizes. The mapping from tiles to the ZA array
+         * is architecturally defined, such that for tiles of elements of esz
+         * bytes, the Nth row (or "horizontal slice") of tile T is in
+         * ZA[T + N * esz]. Note that this means that each tile is not
+         * contiguous in the ZA storage, because its rows are striped through
+         * the ZA array.
+         *
+         * Because this is so large, keep this toward the end of the
+         * reset area, to keep the offsets into the rest of the structure
+         * smaller.
+         */
+        ARMVectorReg za[ARM_MAX_VQ * 16];
+    } za_state;
 
     struct CPUBreakpoint *cpu_breakpoint[16];
     struct CPUWatchpoint *cpu_watchpoint[16];
diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/aarch64/signal.c
+++ b/linux-user/aarch64/signal.c
@@ -XXX,XX +XXX,XX @@ static void target_setup_za_record(struct target_za_context *za,
     for (i = 0; i < vl; ++i) {
         uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i);
         for (j = 0; j < vq * 2; ++j) {
-            __put_user_e(env->zarray[i].d[j], z + j, le);
+            __put_user_e(env->za_state.za[i].d[j], z + j, le);
         }
     }
 }
@@ -XXX,XX +XXX,XX @@ static bool target_restore_za_record(CPUARMState *env,
     for (i = 0; i < vl; ++i) {
         uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i);
         for (j = 0; j < vq * 2; ++j) {
-            __get_user_e(env->zarray[i].d[j], z + j, le);
+            __get_user_e(env->za_state.za[i].d[j], z + j, le);
         }
     }
     return true;
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_dump_state(CPUState *cs, FILE *f, int flags)
             qemu_fprintf(f, "ZA[%0*d]=", svl_lg10, i);
             for (j = zcr_len; j >= 0; --j) {
                 qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%c",
-                             env->zarray[i].d[2 * j + 1],
-                             env->zarray[i].d[2 * j],
+                             env->za_state.za[i].d[2 * j + 1],
+                             env->za_state.za[i].d[2 * j],
                              j ? ':' : '\n');
             }
         }
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 aarch64_set_svcr(CPUARMState *env, uint64_t new, uint64_t mask)
      * when disabled either.
      */
     if (change & new & R_SVCR_ZA_MASK) {
-        memset(env->zarray, 0, sizeof(env->zarray));
+        memset(&env->za_state, 0, sizeof(env->za_state));
     }
 
     if (tcg_enabled()) {
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 const VMStateDescription vmstate_za = {
     .minimum_version_id = 1,
     .needed = za_needed,
     .fields = (const VMStateField[]) {
-        VMSTATE_STRUCT_ARRAY(env.zarray, ARMCPU, ARM_MAX_VQ * 16, 0,
+        VMSTATE_STRUCT_ARRAY(env.za_state.za, ARMCPU, ARM_MAX_VQ * 16, 0,
                              vmstate_vreg, ARMVectorReg),
         VMSTATE_END_OF_LIST()
     }
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl)
     uint32_t i;
 
     /*
-     * Special case clearing the entire ZA space.
+     * Special case clearing the entire ZArray.
      * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any
      * parts of the ZA storage outside of SVL.
      */
     if (imm == 0xff) {
-        memset(env->zarray, 0, sizeof(env->zarray));
+        memset(env->za_state.za, 0, sizeof(env->za_state.za));
         return;
     }
 
@@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl)
      */
     for (i = 0; i < svl; i++) {
         if (imm & (1 << (i % 8))) {
-            memset(&env->zarray[i], 0, svl);
+            memset(&env->za_state.za[i], 0, svl);
         }
     }
 }
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     offset = tile * sizeof(ARMVectorReg);
 
     /* Include the byte offset of zarray to make this relative to env. */
-    offset += offsetof(CPUARMState, zarray);
+    offset += offsetof(CPUARMState, za_state.za);
     tcg_gen_addi_i32(tmp, tmp, offset);
 
     /* Add the byte offset to env to produce the final pointer. */
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile(DisasContext *s, int esz, int tile)
     TCGv_ptr addr = tcg_temp_new_ptr();
     int offset;
 
-    offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, zarray);
+    offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, za_state.za);
 
     tcg_gen_addi_ptr(addr, tcg_env, offset);
     return addr;
-- 
2.43.0

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: 20250704142112.1018902-15-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu-features.h | 63 +++++++++++++++++++++++++++++++++++++++
 target/arm/cpu.h          |  1 +
 2 files changed, 64 insertions(+)

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_rpres(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64ISAR2, RPRES);
 }
 
+static inline bool isar_feature_aa64_lut(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64ISAR2, LUT);
+}
+
 static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id)
 {
     /* We always set the AdvSIMD and FP fields identically.  */
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) != 0;
 }
 
+static inline bool isar_feature_aa64_sve2p1(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) >=2;
+}
+
 static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id)
 {
     return FIELD_EX64_IDREG(id, ID_AA64ZFR0, AES) != 0;
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64ZFR0, F64MM) != 0;
 }
 
+static inline bool isar_feature_aa64_sve_b16b16(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64ZFR0, B16B16);
+}
+
+static inline bool isar_feature_aa64_sme_b16b16(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, B16B16);
+}
+
+static inline bool isar_feature_aa64_sme_f16f16(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F16F16);
+}
+
 static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id)
 {
     return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F64F64);
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id)
     return FIELD_EX64_IDREG(id, ID_AA64SMFR0, FA64);
 }
 
+static inline bool isar_feature_aa64_sme2(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) != 0;
+}
+
+static inline bool isar_feature_aa64_sme2p1(const ARMISARegisters *id)
+{
+    return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) >= 2;
+}
+
+/*
+ * Combinations of feature tests, for ease of use with TRANS_FEAT.
+ */
+static inline bool isar_feature_aa64_sme_or_sve2p1(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2_or_sve2p1(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2p1_or_sve2p1(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2p1(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2_i16i64(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_i16i64(id);
+}
+
+static inline bool isar_feature_aa64_sme2_f64f64(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_f64f64(id);
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
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 @@ FIELD(ID_AA64ISAR2, SYSINSTR_128, 36, 4)
 FIELD(ID_AA64ISAR2, PRFMSLC, 40, 4)
 FIELD(ID_AA64ISAR2, RPRFM, 48, 4)
 FIELD(ID_AA64ISAR2, CSSC, 52, 4)
+FIELD(ID_AA64ISAR2, LUT, 56, 4)
 FIELD(ID_AA64ISAR2, ATS1A, 60, 4)
 
 FIELD(ID_AA64PFR0, EL0, 0, 4)
-- 
2.43.0

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

This is a 512-bit array introduced with SME2.
Save it only when ZA is in use.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-16-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h     |  3 +++
 target/arm/machine.c | 20 ++++++++++++++++++++
 2 files changed, 23 insertions(+)

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 @@ typedef struct CPUArchState {
     uint64_t scxtnum_el[4];
 
     struct {
+        /* SME2 ZT0 -- 512 bit array, with data ordered like ARMVectorReg. */
+        uint64_t zt0[512 / 64] QEMU_ALIGNED(16);
+
         /*
          * SME ZA storage -- 256 x 256 byte array, with bytes in host
          * word order, as we do with vfp.zregs[].  This corresponds to
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 const VMStateDescription vmstate_za = {
     }
 };
 
+static bool zt0_needed(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    return za_needed(cpu) && cpu_isar_feature(aa64_sme2, cpu);
+}
+
+static const VMStateDescription vmstate_zt0 = {
+    .name = "cpu/zt0",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = zt0_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64_ARRAY(env.za_state.zt0, ARMCPU,
+                             ARRAY_SIZE(((CPUARMState *)0)->za_state.zt0)),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static bool serror_needed(void *opaque)
 {
     ARMCPU *cpu = opaque;
@@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = {
         &vmstate_m_security,
         &vmstate_sve,
         &vmstate_za,
+        &vmstate_zt0,
         &vmstate_serror,
         &vmstate_irq_line_state,
         &vmstate_wfxt_timer,
-- 
2.43.0

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

Pipe the value through from SMCR_ELx through hflags and into
the disassembly context.  Enable EZT0 in smcr_write.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-17-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h               |  2 ++
 target/arm/tcg/translate.h     |  1 +
 target/arm/cpu.c               |  3 +++
 target/arm/helper.c            |  6 +++++-
 target/arm/tcg/hflags.c        | 34 +++++++++++++++++++++++++++++++++-
 target/arm/tcg/translate-a64.c |  1 +
 6 files changed, 45 insertions(+), 2 deletions(-)

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 @@ FIELD(SVCR, ZA, 1, 1)
 
 /* Fields for SMCR_ELx. */
 FIELD(SMCR, LEN, 0, 4)
+FIELD(SMCR, EZT0, 30, 1)
 FIELD(SMCR, FA64, 31, 1)
 
 /* Write a new value to v7m.exception, thus transitioning into or out
@@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, NV2_MEM_E20, 35, 1)
 FIELD(TBFLAG_A64, NV2_MEM_BE, 36, 1)
 FIELD(TBFLAG_A64, AH, 37, 1)   /* FPCR.AH */
 FIELD(TBFLAG_A64, NEP, 38, 1)   /* FPCR.NEP */
+FIELD(TBFLAG_A64, ZT0EXC_EL, 39, 2)
 
 /*
  * Helpers for using the above. Note that only the A64 accessors use
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 struct DisasContext {
     int fp_excp_el; /* FP exception EL or 0 if enabled */
     int sve_excp_el; /* SVE exception EL or 0 if enabled */
     int sme_excp_el; /* SME exception EL or 0 if enabled */
+    int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */
     int vl;          /* current vector length in bytes */
     int svl;         /* current streaming vector length in bytes */
     bool vfp_enabled; /* FP enabled via FPSCR.EN */
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_emulate_firmware_reset(CPUState *cpustate, int target_el)
                 env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK;
                 env->cp15.scr_el3 |= SCR_ENTP2;
                 env->vfp.smcr_el[3] = 0xf;
+                if (cpu_isar_feature(aa64_sme2, cpu)) {
+                    env->vfp.smcr_el[3] |= R_SMCR_EZT0_MASK;
+                }
             }
             if (cpu_isar_feature(aa64_hcx, cpu)) {
                 env->cp15.scr_el3 |= SCR_HXEN;
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 smcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
 {
     int cur_el = arm_current_el(env);
     int old_len = sve_vqm1_for_el(env, cur_el);
+    uint64_t valid_mask = R_SMCR_LEN_MASK | R_SMCR_FA64_MASK;
     int new_len;
 
     QEMU_BUILD_BUG_ON(ARM_MAX_VQ > R_SMCR_LEN_MASK + 1);
-    value &= R_SMCR_LEN_MASK | R_SMCR_FA64_MASK;
+    if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) {
+        valid_mask |= R_SMCR_EZT0_MASK;
+    }
+    value &= valid_mask;
     raw_write(env, ri, value);
 
     /*
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el,
     return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
 }
 
+/*
+ * Return the exception level to which exceptions should be taken for ZT0.
+ * C.f. the ARM pseudocode function CheckSMEZT0Enabled, after the ZA check.
+ */
+static int zt0_exception_el(CPUARMState *env, int el)
+{
+#ifndef CONFIG_USER_ONLY
+    if (el <= 1
+        && !el_is_in_host(env, el)
+        && !FIELD_EX64(env->vfp.smcr_el[1], SMCR, EZT0)) {
+        return 1;
+    }
+    if (el <= 2
+        && arm_is_el2_enabled(env)
+        && !FIELD_EX64(env->vfp.smcr_el[2], SMCR, EZT0)) {
+        return 2;
+    }
+    if (arm_feature(env, ARM_FEATURE_EL3)
+        && !FIELD_EX64(env->vfp.smcr_el[3], SMCR, EZT0)) {
+        return 3;
+    }
+#endif
+    return 0;
+}
+
 static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
                                         ARMMMUIdx mmu_idx)
 {
@@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
             DP_TBFLAG_A64(flags, PSTATE_SM, 1);
             DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el));
         }
-        DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA));
+
+        if (FIELD_EX64(env->svcr, SVCR, ZA)) {
+            DP_TBFLAG_A64(flags, PSTATE_ZA, 1);
+            if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) {
+                int zt0_el = zt0_exception_el(env, el);
+                DP_TBFLAG_A64(flags, ZT0EXC_EL, zt0_el);
+            }
+        }
     }
 
     sctlr = regime_sctlr(env, stage1);
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 aarch64_tr_init_disas_context(DisasContextBase *dcbase,
     dc->trap_eret = EX_TBFLAG_A64(tb_flags, TRAP_ERET);
     dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL);
     dc->sme_excp_el = EX_TBFLAG_A64(tb_flags, SMEEXC_EL);
+    dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL);
     dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16;
     dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16;
     dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE);
-- 
2.43.0

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: 20250704142112.1018902-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/syndrome.h          |  1 +
 target/arm/tcg/sme.decode      |  1 +
 target/arm/tcg/translate-sme.c | 26 ++++++++++++++++++++++++++
 3 files changed, 28 insertions(+)

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 {
     SME_ET_Streaming,
     SME_ET_NotStreaming,
     SME_ET_InactiveZA,
+    SME_ET_InaccessibleZT0,
 } SMEExceptionType;
 
 #define ARM_EL_EC_LENGTH 6
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@
 ### SME Misc
 
 ZERO            11000000 00 001 00000000000 imm:8
+ZERO_zt0        11000000 01 001 00000000000 00000001
 
 ### SME Move into/from Array
 
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@
 
 #include "decode-sme.c.inc"
 
+static bool sme2_zt0_enabled_check(DisasContext *s)
+{
+    if (!sme_za_enabled_check(s)) {
+        return false;
+    }
+    if (s->zt0_excp_el) {
+        gen_exception_insn_el(s, 0, EXCP_UDEF,
+                              syn_smetrap(SME_ET_InaccessibleZT0, false),
+                              s->zt0_excp_el);
+        return false;
+    }
+    return true;
+}
 
 /*
  * Resolve tile.size[index] to a host pointer, where tile and index
@@ -XXX,XX +XXX,XX @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a)
     return true;
 }
 
+static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
+{
+    if (!dc_isar_feature(aa64_sme2, s)) {
+        return false;
+    }
+    if (sme_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+        tcg_gen_gvec_dup_imm(MO_64, offsetof(CPUARMState, za_state.zt0),
+                             sizeof_field(CPUARMState, za_state.zt0),
+                             sizeof_field(CPUARMState, za_state.zt0), 0);
+    }
+    return true;
+}
+
 static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
-- 
2.43.0

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

Honor AlignmentEnforced() for LDR/STR (vector),
(predicate), and (array vector).

Within the expansion functions, clear @align when we're
done emitting loads at the largest size.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.h |  6 ++--
 target/arm/tcg/translate-sme.c |  5 ++--
 target/arm/tcg/translate-sve.c | 50 ++++++++++++++++++++++++----------
 3 files changed, 42 insertions(+), 19 deletions(-)

diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-a64.h
+++ b/target/arm/tcg/translate-a64.h
@@ -XXX,XX +XXX,XX @@ void gen_gvec_usqadd_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_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
-void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
+void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs,
+                 int len, int rn, int imm, MemOp align);
+void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs,
+                 int len, int rn, int imm, MemOp align);
 
 #endif /* TARGET_ARM_TRANSLATE_A64_H */
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
     return true;
 }
 
-typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int);
+typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp);
 
 static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
 {
@@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
     /* ZA[n] equates to ZA0H.B[n]. */
     base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
 
-    fn(s, base, 0, svl, a->rn, imm * svl);
+    fn(s, base, 0, svl, a->rn, imm * svl,
+       s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     return true;
 }
 
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 @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz,
  */
 
 void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
-                 int len, int rn, int imm)
+                 int len, int rn, int imm, MemOp align)
 {
     int len_align = QEMU_ALIGN_DOWN(len, 16);
     int len_remain = len % 16;
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
         for (i = 0; i < len_align; i += 16) {
             tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
-                                 MO_LE | MO_128 | MO_ATOM_NONE);
+                                 MO_LE | MO_128 | MO_ATOM_NONE | align);
             tcg_gen_extr_i128_i64(t0, t1, t16);
             tcg_gen_st_i64(t0, base, vofs + i);
             tcg_gen_st_i64(t1, base, vofs + i + 8);
             tcg_gen_addi_i64(clean_addr, clean_addr, 16);
         }
+        if (len_align) {
+            align = MO_UNALN;
+        }
     } else {
         TCGLabel *loop = gen_new_label();
         TCGv_ptr tp, i = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
         t16 = tcg_temp_new_i128();
         tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
-                             MO_LE | MO_128 | MO_ATOM_NONE);
+                             MO_LE | MO_128 | MO_ATOM_NONE | align);
         tcg_gen_addi_i64(clean_addr, clean_addr, 16);
 
         tp = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
         tcg_gen_st_i64(t1, tp, vofs + 8);
 
         tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
+        align = MO_UNALN;
     }
 
     /*
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
      */
     if (len_remain >= 8) {
         t0 = tcg_temp_new_i64();
-        tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+        tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
+                            MO_LEUQ | MO_ATOM_NONE | align);
+        align = MO_UNALN;
         tcg_gen_st_i64(t0, base, vofs + len_align);
         len_remain -= 8;
         len_align += 8;
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
         case 4:
         case 8:
             tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
-                                MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
+                                MO_LE | ctz32(len_remain)
+                                | MO_ATOM_NONE | align);
             break;
 
         case 6:
             t1 = tcg_temp_new_i64();
-            tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
+            tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
+                                MO_LEUL | MO_ATOM_NONE | align);
             tcg_gen_addi_i64(clean_addr, clean_addr, 4);
             tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
             tcg_gen_deposit_i64(t0, t0, t1, 32, 32);
@@ -XXX,XX +XXX,XX @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
 /* Similarly for stores.  */
 void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
-                 int len, int rn, int imm)
+                 int len, int rn, int imm, MemOp align)
 {
     int len_align = QEMU_ALIGN_DOWN(len, 16);
     int len_remain = len % 16;
@@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
             tcg_gen_ld_i64(t1, base, vofs + i + 8);
             tcg_gen_concat_i64_i128(t16, t0, t1);
             tcg_gen_qemu_st_i128(t16, clean_addr, midx,
-                                 MO_LE | MO_128 | MO_ATOM_NONE);
+                                 MO_LE | MO_128 | MO_ATOM_NONE | align);
             tcg_gen_addi_i64(clean_addr, clean_addr, 16);
         }
+        if (len_align) {
+            align = MO_UNALN;
+        }
     } else {
         TCGLabel *loop = gen_new_label();
         TCGv_ptr tp, i = tcg_temp_new_ptr();
@@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
         tcg_gen_addi_i64(clean_addr, clean_addr, 16);
 
         tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
+        align = MO_UNALN;
     }
 
     /* Predicate register stores can be any multiple of 2.  */
     if (len_remain >= 8) {
         t0 = tcg_temp_new_i64();
         tcg_gen_ld_i64(t0, base, vofs + len_align);
-        tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+        tcg_gen_qemu_st_i64(t0, clean_addr, midx,
+                            MO_LEUQ | MO_ATOM_NONE | align);
+        align = MO_UNALN;
         len_remain -= 8;
         len_align += 8;
         if (len_remain) {
@@ -XXX,XX +XXX,XX @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
         case 4:
         case 8:
             tcg_gen_qemu_st_i64(t0, clean_addr, midx,
-                                MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
+                                MO_LE | ctz32(len_remain)
+                                | MO_ATOM_NONE | align);
             break;
 
         case 6:
-            tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
+            tcg_gen_qemu_st_i64(t0, clean_addr, midx,
+                                MO_LEUL | MO_ATOM_NONE | align);
             tcg_gen_addi_i64(clean_addr, clean_addr, 4);
             tcg_gen_shri_i64(t0, t0, 32);
             tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
@@ -XXX,XX +XXX,XX @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = vec_full_reg_size(s);
         int off = vec_full_reg_offset(s, a->rd);
-        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     }
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = pred_full_reg_size(s);
         int off = pred_full_reg_offset(s, a->rd);
-        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_2 : MO_UNALN);
     }
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = vec_full_reg_size(s);
         int off = vec_full_reg_offset(s, a->rd);
-        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     }
     return true;
 }
@@ -XXX,XX +XXX,XX @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
     if (sve_access_check(s)) {
         int size = pred_full_reg_size(s);
         int off = pred_full_reg_offset(s, a->rd);
-        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size);
+        gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size,
+                    s->align_mem ? MO_ALIGN_2 : MO_UNALN);
     }
     return true;
 }
-- 
2.43.0

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: 20250704142112.1018902-20-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      |  6 ++++++
 target/arm/tcg/translate-sme.c | 13 +++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ LDST1           1110000 111     st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4  \
 LDR             1110000 100 0 000000 .. 000 ..... 0 ....        @ldstr
 STR             1110000 100 1 000000 .. 000 ..... 0 ....        @ldstr
 
+&ldstzt0        rn
+@ldstzt0        ....... ... . ...... .. ... rn:5  .....         &ldstzt0
+
+LDR_zt0         1110000 100 0 111111 00 000 ..... 00000         @ldstzt0
+STR_zt0         1110000 100 1 111111 00 000 ..... 00000         @ldstzt0
+
 ### SME Add Vector to Array
 
 &adda           zad zn pm pn
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
 TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr)
 TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str)
 
+static bool do_ldst_zt0(DisasContext *s, arg_ldstzt0 *a, GenLdStR *fn)
+{
+    if (sme2_zt0_enabled_check(s)) {
+        fn(s, tcg_env, offsetof(CPUARMState, za_state.zt0),
+           sizeof_field(CPUARMState, za_state.zt0), a->rn, 0,
+           s->align_mem ? MO_ALIGN_16 : MO_UNALN);
+    }
+    return true;
+}
+
+TRANS_FEAT(LDR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_ldr)
+TRANS_FEAT(STR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_str)
+
 static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz,
                     gen_helper_gvec_4 *fn)
 {
-- 
2.43.0

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: 20250704142112.1018902-21-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      |  5 +++++
 target/arm/tcg/translate-sme.c | 13 +++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ MOVA            11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5  \
 MOVA            11000000 11    00001 1 v:1 .. pg:3 0 za_imm:4 zr:5  \
                 &mova to_vec=1 rs=%mova_rs esz=4
 
+### SME Move into/from ZT0
+
+MOVT_rzt        1100 0000 0100 1100 0 off:3 00 11111 rt:5
+MOVT_ztr        1100 0000 0100 1110 0 off:3 00 11111 rt:5
+
 ### SME Memory
 
 &ldst           esz rs pg rn rm za_imm v:bool st:bool
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
     return true;
 }
 
+static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
+                    void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
+{
+    if (sme2_zt0_enabled_check(s)) {
+        func(cpu_reg(s, a->rt), tcg_env,
+             offsetof(CPUARMState, za_state.zt0) + a->off * 8);
+    }
+    return true;
+}
+
+TRANS_FEAT(MOVT_rzt, aa64_sme2, do_movt, a, tcg_gen_ld_i64)
+TRANS_FEAT(MOVT_ztr, aa64_sme2, do_movt, a, tcg_gen_st_i64)
+
 static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
 {
     typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32);
-- 
2.43.0

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

Decode tile number and index offset beforehand and separately.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-22-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 46 +++++++++++++++++++++++-----------
 target/arm/tcg/translate-sme.c | 17 +++++--------
 2 files changed, 38 insertions(+), 25 deletions(-)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_zt0        11000000 01 001 00000000000 00000001
 ### SME Move into/from Array
 
 %mova_rs        13:2 !function=plus_12
-&mova           esz rs pg zr za_imm v:bool to_vec:bool
+&mova           esz rs pg zr za off v:bool to_vec:bool
 
-MOVA            11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4  \
-                &mova to_vec=0 rs=%mova_rs
-MOVA            11000000 11    00000 1 v:1 .. pg:3 zr:5 0 za_imm:4  \
-                &mova to_vec=0 rs=%mova_rs esz=4
+MOVA            11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4  \
+                &mova to_vec=0 rs=%mova_rs esz=0 za=0
+MOVA            11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3  \
+                &mova to_vec=0 rs=%mova_rs esz=1
+MOVA            11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2  \
+                &mova to_vec=0 rs=%mova_rs esz=2
+MOVA            11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1  \
+                &mova to_vec=0 rs=%mova_rs esz=3
+MOVA            11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4  \
+                &mova to_vec=0 rs=%mova_rs esz=4 off=0
 
-MOVA            11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5  \
-                &mova to_vec=1 rs=%mova_rs
-MOVA            11000000 11    00001 1 v:1 .. pg:3 0 za_imm:4 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=4
+MOVA            11000000 00 00001 0 v:1 .. pg:3 0 off:4      zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=0 za=0
+MOVA            11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=1
+MOVA            11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=2
+MOVA            11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=3
+MOVA            11000000 11 00001 1 v:1 .. pg:3 0 za:4       zr:5  \
+                &mova to_vec=1 rs=%mova_rs esz=4 off=0
 
 ### SME Move into/from ZT0
 
@@ -XXX,XX +XXX,XX @@ MOVT_ztr        1100 0000 0100 1110 0 off:3 00 11111 rt:5
 
 ### SME Memory
 
-&ldst           esz rs pg rn rm za_imm v:bool st:bool
+&ldst           esz rs pg rn rm za off v:bool st:bool
 
-LDST1           1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4  \
-                &ldst rs=%mova_rs
-LDST1           1110000 111     st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4  \
-                &ldst esz=4 rs=%mova_rs
+LDST1           1110000 0 00 st:1 rm:5 v:1 .. pg:3 rn:5 0 off:4  \
+                &ldst rs=%mova_rs esz=0 za=0
+LDST1           1110000 0 01 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:1 off:3  \
+                &ldst rs=%mova_rs esz=1
+LDST1           1110000 0 10 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:2 off:2  \
+                &ldst rs=%mova_rs esz=2
+LDST1           1110000 0 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:3 off:1  \
+                &ldst rs=%mova_rs esz=3
+LDST1           1110000 1 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:4  \
+                &ldst rs=%mova_rs esz=4 off=0
 
 &ldstr          rv rn imm
 @ldstr          ....... ... . ...... .. ... rn:5 . imm:4 \
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool sme2_zt0_enabled_check(DisasContext *s)
     return true;
 }
 
-/*
- * Resolve tile.size[index] to a host pointer, where tile and index
- * are always decoded together, dependent on the element size.
- */
+/* Resolve tile.size[rs+imm] to a host pointer. */
 static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
-                                int tile_index, bool vertical)
+                                int tile, int imm, bool vertical)
 {
-    int tile = tile_index >> (4 - esz);
-    int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz);
     int pos, len, offset;
     TCGv_i32 tmp;
     TCGv_ptr addr;
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     /* Compute the final index, which is Rs+imm. */
     tmp = tcg_temp_new_i32();
     tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
-    tcg_gen_addi_i32(tmp, tmp, index);
+    tcg_gen_addi_i32(tmp, tmp, imm);
 
     /* Prepare a power-of-two modulo via extraction of @len bits. */
     len = ctz32(streaming_vec_reg_size(s)) - esz;
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
     t_zr = vec_full_reg_ptr(s, a->zr);
     t_pg = pred_full_reg_ptr(s, a->pg);
 
@@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
     t_pg = pred_full_reg_ptr(s, a->pg);
     addr = tcg_temp_new_i64();
 
@@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
     }
 
     /* ZA[n] equates to ZA0H.B[n]. */
-    base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
+    base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
 
     fn(s, base, 0, svl, a->rn, imm * svl,
        s->align_mem ? MO_ALIGN_16 : MO_UNALN);
-- 
2.43.0

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

Prepare for more kinds of MOVA from SME2 by renaming the
existing SME1 MOVA to indicate tile to/from vector.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-23-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 42 +++++++++++++++++-----------------
 target/arm/tcg/translate-sme.c | 12 +++++-----
 2 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_zt0        11000000 01 001 00000000000 00000001
 ### SME Move into/from Array
 
 %mova_rs        13:2 !function=plus_12
-&mova           esz rs pg zr za off v:bool to_vec:bool
+&mova_p         esz rs pg zr za off v:bool
 
-MOVA            11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4  \
-                &mova to_vec=0 rs=%mova_rs esz=0 za=0
-MOVA            11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3  \
-                &mova to_vec=0 rs=%mova_rs esz=1
-MOVA            11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2  \
-                &mova to_vec=0 rs=%mova_rs esz=2
-MOVA            11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1  \
-                &mova to_vec=0 rs=%mova_rs esz=3
-MOVA            11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4  \
-                &mova to_vec=0 rs=%mova_rs esz=4 off=0
+MOVA_tz         11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4  \
+                &mova_p rs=%mova_rs esz=0 za=0
+MOVA_tz         11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3  \
+                &mova_p rs=%mova_rs esz=1
+MOVA_tz         11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2  \
+                &mova_p rs=%mova_rs esz=2
+MOVA_tz         11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1  \
+                &mova_p rs=%mova_rs esz=3
+MOVA_tz         11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4  \
+                &mova_p rs=%mova_rs esz=4 off=0
 
-MOVA            11000000 00 00001 0 v:1 .. pg:3 0 off:4      zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=0 za=0
-MOVA            11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=1
-MOVA            11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=2
-MOVA            11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=3
-MOVA            11000000 11 00001 1 v:1 .. pg:3 0 za:4       zr:5  \
-                &mova to_vec=1 rs=%mova_rs esz=4 off=0
+MOVA_zt         11000000 00 00001 0 v:1 .. pg:3 0 off:4      zr:5  \
+                &mova_p rs=%mova_rs esz=0 za=0
+MOVA_zt         11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5  \
+                &mova_p rs=%mova_rs esz=1
+MOVA_zt         11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5  \
+                &mova_p rs=%mova_rs esz=2
+MOVA_zt         11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5  \
+                &mova_p rs=%mova_rs esz=3
+MOVA_zt         11000000 11 00001 1 v:1 .. pg:3 0 za:4       zr:5  \
+                &mova_p rs=%mova_rs esz=4 off=0
 
 ### SME Move into/from ZT0
 
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
     return true;
 }
 
-static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
+static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
         gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h,
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
     TCGv_i32 t_desc;
     int svl;
 
-    if (!dc_isar_feature(aa64_sme, s)) {
-        return false;
-    }
     if (!sme_smza_enabled_check(s)) {
         return true;
     }
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
 
     if (a->v) {
         /* Vertical slice -- use sme mova helpers. */
-        if (a->to_vec) {
+        if (to_vec) {
             zc_fns[a->esz](t_zr, t_za, t_pg, t_desc);
         } else {
             cz_fns[a->esz](t_za, t_zr, t_pg, t_desc);
         }
     } else {
         /* Horizontal slice -- reuse sve sel helpers. */
-        if (a->to_vec) {
+        if (to_vec) {
             h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc);
         } else {
             h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc);
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
     return true;
 }
 
+TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false)
+TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true)
+
 static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
                     void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
 {
-- 
2.43.0

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

Prepare for MOVA array to/from vector with multiple registers
by adding a div_len parameter, herein always 1, and a vec_mod
parameter, herein always 0.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-24-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sme.c | 47 +++++++++++++++++++++++-----------
 1 file changed, 32 insertions(+), 15 deletions(-)

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool sme2_zt0_enabled_check(DisasContext *s)
 
 /* Resolve tile.size[rs+imm] to a host pointer. */
 static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
-                                int tile, int imm, bool vertical)
+                                int tile, int imm, int div_len,
+                                int vec_mod, bool vertical)
 {
     int pos, len, offset;
     TCGv_i32 tmp;
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     /* Compute the final index, which is Rs+imm. */
     tmp = tcg_temp_new_i32();
     tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
+    /*
+     * Round the vector index down to a multiple of vec_mod if necessary.
+     * We do this before adding the offset, to handle cases like
+     * MOVA (tile to vector, 2 registers) where we want to call this
+     * several times in a loop with an increasing offset. We rely on
+     * the instruction encodings always forcing the initial offset in
+     * [rs + offset] to be a multiple of vec_mod. The pseudocode usually
+     * does the round-down after adding the offset rather than before,
+     * but MOVA is an exception.
+     */
+    if (vec_mod > 1) {
+        tcg_gen_andc_i32(tmp, tmp, tcg_constant_i32(vec_mod - 1));
+    }
     tcg_gen_addi_i32(tmp, tmp, imm);
 
     /* Prepare a power-of-two modulo via extraction of @len bits. */
-    len = ctz32(streaming_vec_reg_size(s)) - esz;
+    len = ctz32(streaming_vec_reg_size(s) / div_len) - esz;
 
     if (!len) {
         /*
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
     return addr;
 }
 
+/* Resolve ZArray[rs+imm] to a host pointer. */
+static TCGv_ptr get_zarray(DisasContext *s, int rs, int imm,
+                           int div_len, int vec_mod)
+{
+    /* ZA[n] equates to ZA0H.B[n]. */
+    return get_tile_rowcol(s, MO_8, rs, 0, imm, div_len, vec_mod, false);
+}
+
 /*
  * Resolve tile.size[0] to a host pointer.
  * Used by e.g. outer product insns where we require the entire tile.
@@ -XXX,XX +XXX,XX @@ static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v);
     t_zr = vec_full_reg_ptr(s, a->zr);
     t_pg = pred_full_reg_ptr(s, a->pg);
 
@@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
         return true;
     }
 
-    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
+    t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v);
     t_pg = pred_full_reg_ptr(s, a->pg);
     addr = tcg_temp_new_i64();
 
@@ -XXX,XX +XXX,XX @@ typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp);
 
 static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
 {
-    int svl = streaming_vec_reg_size(s);
-    int imm = a->imm;
-    TCGv_ptr base;
+    if (sme_za_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int imm = a->imm;
+        TCGv_ptr base = get_zarray(s, a->rv, imm, 1, 0);
 
-    if (!sme_za_enabled_check(s)) {
-        return true;
+        fn(s, base, 0, svl, a->rn, imm * svl,
+           s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     }
-
-    /* ZA[n] equates to ZA0H.B[n]. */
-    base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
-
-    fn(s, base, 0, svl, a->rn, imm * svl,
-       s->align_mem ? MO_ALIGN_16 : MO_UNALN);
     return true;
 }
 
-- 
2.43.0

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: 20250704142112.1018902-25-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h   | 1 +
 target/arm/cpu64.c | 1 +
 2 files changed, 2 insertions(+)

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 {
 
     /* Used to set the maximum vector length the cpu will support.  */
     uint32_t sve_max_vq;
+    uint32_t sme_max_vq;
 
 #ifdef CONFIG_USER_ONLY
     /* Used to set the default vector length at process start. */
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 @@ void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp)
     }
 
     cpu->sme_vq.map = vq_map;
+    cpu->sme_max_vq = 32 - clz32(vq_map);
 }
 
 static bool cpu_arm_get_sme(Object *obj, Error **errp)
-- 
2.43.0

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: 20250704142112.1018902-26-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  9 +++++
 target/arm/tcg/translate.h     |  1 +
 target/arm/tcg/sme.decode      | 37 ++++++++++++++++++
 target/arm/tcg/sme_helper.c    | 64 ++++++++++++++++++++++++++++++
 target/arm/tcg/translate-a64.c |  1 +
 target/arm/tcg/translate-sme.c | 71 ++++++++++++++++++++++++++++++++++
 6 files changed, 183 insertions(+)

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: 20250704142112.1018902-27-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate.h     |  5 +++++
 target/arm/tcg/sme.decode      | 12 ++++++++++++
 target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

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 @@ static inline int plus_2(DisasContext *s, int x)
     return x + 2;
 }
 
+static inline int plus_8(DisasContext *s, int x)
+{
+    return x + 8;
+}
+
 static inline int plus_12(DisasContext *s, int x)
 {
     return x + 12;
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_zt0        11000000 01 001 00000000000 00000001
 ### SME Move into/from Array
 
 %mova_rs        13:2 !function=plus_12
+%mova_rv        13:2 !function=plus_8
+&mova_a         rv zr off
 &mova_p         esz rs pg zr za off v:bool
 &mova_t         esz rs zr za off v:bool
 
@@ -XXX,XX +XXX,XX @@ MOVA_zt4        11000000 10 00011 0 v:1 .. 001 000 za:2       zr:3 00 \
 MOVA_zt4        11000000 11 00011 0 v:1 .. 001 00 za:3        zr:3 00 \
                 &mova_t rs=%mova_rs esz=3 off=0
 
+MOVA_az2        11000000 00 00010 00 .. 010 zr:4  000 off:3  \
+                &mova_a rv=%mova_rv
+MOVA_az4        11000000 00 00010 00 .. 011 zr:3 0000 off:3  \
+                &mova_a rv=%mova_rv
+
+MOVA_za2        11000000 00 00011 00 .. 010 00 off:3 zr:4 0  \
+                &mova_a rv=%mova_rv
+MOVA_za4        11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \
+                &mova_a rv=%mova_rv
+
 ### SME Move into/from ZT0
 
 MOVT_rzt        1100 0000 0100 1100 0 off:3 00 11111 rt:5
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false)
 TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true)
 TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true)
 
+static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
+{
+    TCGv_ptr t_za;
+    int svl;
+
+    if (!sme_smza_enabled_check(s)) {
+        return true;
+    }
+
+    svl = streaming_vec_reg_size(s);
+    t_za = get_zarray(s, a->rv, a->off, n, 0);
+
+    for (int i = 0; i < n; ++i) {
+        int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+        int o_zr = vec_full_reg_offset(s, a->zr * n + i);
+
+        if (to_vec) {
+            tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl);
+        } else {
+            tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl);
+        }
+    }
+    return true;
+}
+
+TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false)
+TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false)
+TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true)
+TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true)
+
 static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
                     void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
 {
-- 
2.43.0

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: 20250704142112.1018902-28-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  3 +++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 34 ++++++++++++++++++++++++----------
 target/arm/tcg/translate-sme.c |  2 ++
 4 files changed, 31 insertions(+), 10 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: 20250704142112.1018902-29-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  4 ++++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 37 +++++++++++++++++++++++++---------
 target/arm/tcg/translate-sme.c |  2 ++
 4 files changed, 35 insertions(+), 10 deletions(-)

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

To be used by both SVE2 and SME2.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-30-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-a64.h |  4 ++++
 target/arm/tcg/gengvec64.c     | 11 +++++++++++
 target/arm/tcg/translate-sve.c |  8 +-------
 3 files changed, 16 insertions(+), 7 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: 20250704142112.1018902-31-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  13 ++++
 target/arm/tcg/helper.h        |   8 ++
 target/arm/tcg/vec_internal.h  |   4 +
 target/arm/tcg/sme.decode      |  40 ++++++++++
 target/arm/tcg/helper-a64.c    |   2 +
 target/arm/tcg/neon_helper.c   |  30 ++++++++
 target/arm/tcg/translate-sme.c | 137 +++++++++++++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    |   7 ++
 8 files changed, 241 insertions(+)

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: 20250704142112.1018902-32-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 36 +++++++++++++++++++
 target/arm/tcg/translate-sme.c | 65 ++++++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ADD_n1         1100000 1 .. 10 .... 1010.0 11000 .... 0    @z2z_4x1
 
 SQDMULH_n1     1100000 1 .. 10 .... 1010.1 00000 .... 0    @z2z_2x1
 SQDMULH_n1     1100000 1 .. 10 .... 1010.1 00000 .... 0    @z2z_4x1
+
+### SME2 Multi-vector Multiple Vectors SVE Destructive
+
+%zm_ax2         17:4 !function=times_2
+%zm_ax4         18:3 !function=times_4
+
+@z2z_2x2        ....... . esz:2 . ....0 ....0. ..... .... . \
+                &z2z_en n=2 zdn=%zd_ax2 zm=%zm_ax2
+@z2z_4x4        ....... . esz:2 . ...00 ....1. ..... ...0 . \
+                &z2z_en n=4 zdn=%zd_ax4 zm=%zm_ax4
+
+SMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 0    @z2z_2x2
+SMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 0    @z2z_4x4
+UMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 1    @z2z_2x2
+UMAX_nn        1100000 1 .. 1 ..... 1011.0 00000 .... 1    @z2z_4x4
+SMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 0    @z2z_2x2
+SMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 0    @z2z_4x4
+UMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 1    @z2z_2x2
+UMIN_nn        1100000 1 .. 1 ..... 1011.0 00001 .... 1    @z2z_4x4
+
+FMAX_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 0    @z2z_2x2
+FMAX_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 0    @z2z_4x4
+FMIN_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 1    @z2z_2x2
+FMIN_nn        1100000 1 .. 1 ..... 1011.0 01000 .... 1    @z2z_4x4
+FMAXNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 0    @z2z_2x2
+FMAXNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 0    @z2z_4x4
+FMINNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 1    @z2z_2x2
+FMINNM_nn      1100000 1 .. 1 ..... 1011.0 01001 .... 1    @z2z_4x4
+
+SRSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 0    @z2z_2x2
+SRSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 0    @z2z_4x4
+URSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 1    @z2z_2x2
+URSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 1    @z2z_4x4
+
+SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_2x2
+SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_4x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl)
 TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl)
 TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh)
 
+static bool do_z2z_nn(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn)
+{
+    int esz, dn, dm, vsz, n;
+
+    if (!sme_sm_enabled_check(s)) {
+        return true;
+    }
+
+    esz = a->esz;
+    n = a->n;
+    dn = a->zdn;
+    dm = a->zm;
+    vsz = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; i++) {
+        int dofs = vec_full_reg_offset(s, dn + i);
+        int mofs = vec_full_reg_offset(s, dm + i);
+
+        fn(esz, dofs, dofs, mofs, vsz, vsz);
+    }
+    return true;
+}
+
+TRANS_FEAT(SMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smax)
+TRANS_FEAT(SMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smin)
+TRANS_FEAT(UMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umax)
+TRANS_FEAT(UMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umin)
+TRANS_FEAT(SRSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_srshl)
+TRANS_FEAT(URSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_urshl)
+TRANS_FEAT(SQDMULH_nn, aa64_sme2, do_z2z_nn, a, gen_gvec_sve2_sqdmulh)
+
 static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
                            gen_helper_gvec_3_ptr * const fns[4])
 {
@@ -XXX,XX +XXX,XX @@ static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
     return true;
 }
 
+static bool do_z2z_nn_fpst(DisasContext *s, arg_z2z_en *a,
+                           gen_helper_gvec_3_ptr * const fns[4])
+{
+    int esz = a->esz, n, dn, dm, vsz;
+    gen_helper_gvec_3_ptr *fn;
+    TCGv_ptr fpst;
+
+    if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) {
+        return false;
+    }
+    if (!sme_sm_enabled_check(s)) {
+        return true;
+    }
+
+    fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+    fn = fns[esz];
+    n = a->n;
+    dn = a->zdn;
+    dm = a->zm;
+    vsz = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; i++) {
+        int dofs = vec_full_reg_offset(s, dn + i);
+        int mofs = vec_full_reg_offset(s, dm + i);
+
+        tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn);
+    }
+    return true;
+}
+
 static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
     { gen_helper_gvec_fmax_b16,
       gen_helper_gvec_fmax_h,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
       gen_helper_gvec_ah_fmax_d },
 };
 TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah])
+TRANS_FEAT(FMAX_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmax[s->fpcr_ah])
 
 static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
     { gen_helper_gvec_fmin_b16,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
       gen_helper_gvec_ah_fmin_d },
 };
 TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah])
+TRANS_FEAT(FMIN_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmin[s->fpcr_ah])
 
 static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
     gen_helper_gvec_fmaxnum_b16,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
     gen_helper_gvec_fmaxnum_d,
 };
 TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm)
+TRANS_FEAT(FMAXNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmaxnm)
 
 static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
     gen_helper_gvec_fminnum_b16,
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
     gen_helper_gvec_fminnum_d,
 };
 TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
+TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm)
-- 
2.43.0

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: 20250704142112.1018902-33-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate.h     |  2 ++
 target/arm/tcg/sme.decode      | 15 +++++++++++++++
 target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

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 GVecGen3Fn(unsigned, uint32_t, uint32_t,
                         uint32_t, uint32_t, uint32_t);
 typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
                         uint32_t, uint32_t, uint32_t);
+typedef void GVecGen3FnVar(unsigned, TCGv_ptr, uint32_t, TCGv_ptr, uint32_t,
+                           TCGv_ptr, uint32_t, uint32_t, uint32_t);
 
 /* Function prototype for gen_ functions for calling Neon helpers */
 typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32);
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ URSHL_nn       1100000 1 .. 1 ..... 1011.0 10001 .... 1    @z2z_4x4
 
 SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_2x2
 SQDMULH_nn     1100000 1 .. 1 ..... 1011.1 00000 .... 0    @z2z_4x4
+
+### SME2 Multi-vector Multiple and Single Array Vectors
+
+&azz_n          n off rv zn zm
+@azz_nx1_o3     ........ .... zm:4 ...... zn:5 .. off:3     &azz_n rv=%mova_rv
+
+ADD_azz_n1_s    11000001 0010 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=2
+ADD_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=4
+ADD_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=2
+ADD_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 10 ...    @azz_nx1_o3 n=4
+
+SUB_azz_n1_s    11000001 0010 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
+SUB_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
+SUB_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
+SUB_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
 };
 TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
 TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm)
+
+/* Add/Sub vector Z[m] to each Z[n*N] with result in ZA[d*N]. */
+static bool do_azz_n1(DisasContext *s, arg_azz_n *a, int esz,
+                      GVecGen3FnVar *fn)
+{
+    TCGv_ptr t_za;
+    int svl, n, o_zm;
+
+    if (!sme_smza_enabled_check(s)) {
+        return true;
+    }
+
+    n = a->n;
+    t_za = get_zarray(s, a->rv, a->off, n, 0);
+    o_zm = vec_full_reg_offset(s, a->zm);
+    svl = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; ++i) {
+        int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+        int o_zn = vec_full_reg_offset(s, (a->zn + i) % 32);
+
+        fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl);
+    }
+    return true;
+}
+
+TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var)
+TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var)
-- 
2.43.0

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: 20250704142112.1018902-34-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 20 ++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)

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

Indicate whether to use FPST_FPCR or FPST_ZA via bit 2 of
simd_data(desc).  For SVE, this bit remains zero.
For do_FMLAL_zzzw, this requires no change.
For do_FMLAL_zzxw, move the index up one bit.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-35-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 2 +-
 target/arm/tcg/vec_helper.c    | 8 +++++---
 2 files changed, 6 insertions(+), 4 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 bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel)
 {
     return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzxw_s,
                              a->rd, a->rn, a->rm, a->ra,
-                             (a->index << 2) | (sel << 1) | sub, tcg_env);
+                             (a->index << 3) | (sel << 1) | sub, tcg_env);
 }
 
 TRANS_FEAT(FMLALB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, false)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va,
     intptr_t i, oprsz = simd_oprsz(desc);
     bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
     intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
-    float_status *status = &env->vfp.fp_status[FPST_A64];
+    bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+    float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
     bool fz16 = env->vfp.fpcr & FPCR_FZ16;
     int negx = 0, negf = 0;
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va,
     intptr_t i, j, oprsz = simd_oprsz(desc);
     bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
     intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
-    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16);
-    float_status *status = &env->vfp.fp_status[FPST_A64];
+    bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 3, 3) * sizeof(float16);
+    float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
     bool fz16 = env->vfp.fpcr & FPCR_FZ16;
     int negx = 0, negf = 0;
 
-- 
2.43.0

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: 20250704142112.1018902-36-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h     |  8 +++++
 target/arm/tcg/vec_helper.c | 58 ++++++++++++++++++++++++++++---------
 2 files changed, 53 insertions(+), 13 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: 20250704142112.1018902-37-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 71 ++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 98 ++++++++++++++++++++++++++++++++++
 2 files changed, 169 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ SUB_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
 SUB_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
 SUB_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
 
+%off3_x2        0:3 !function=times_2
+%off2_x2        0:2 !function=times_2
+
+@azz_nx1_o3x2   ........ ... . zm:4 . .. ... zn:5 .. ...    \
+                &azz_n off=%off3_x2 rv=%mova_rv
+@azz_nx1_o2x2   ........ ... . zm:4 . .. ... zn:5 ... ..    \
+                &azz_n off=%off2_x2 rv=%mova_rv
+
+FMLAL_n1        11000001 001 0 .... 0 .. 011 ..... 00 ...   @azz_nx1_o3x2 n=1
+FMLAL_n1        11000001 001 0 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=2
+FMLAL_n1        11000001 001 1 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=4
+
+FMLSL_n1        11000001 001 0 .... 0 .. 011 ..... 01 ...   @azz_nx1_o3x2 n=1
+FMLSL_n1        11000001 001 0 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=2
+FMLSL_n1        11000001 001 1 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=4
+
+BFMLAL_n1       11000001 001 0 .... 0 .. 011 ..... 10 ...   @azz_nx1_o3x2 n=1
+BFMLAL_n1       11000001 001 0 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=2
+BFMLAL_n1       11000001 001 1 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=4
+
+BFMLSL_n1       11000001 001 0 .... 0 .. 011 ..... 11 ...   @azz_nx1_o3x2 n=1
+BFMLSL_n1       11000001 001 0 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=2
+BFMLSL_n1       11000001 001 1 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ SUB_azz_nn_s    11000001 101 ....0 0 .. 110 ....0 11 ...    @azz_2x2_o3
 SUB_azz_nn_s    11000001 101 ...01 0 .. 110 ...00 11 ...    @azz_4x4_o3
 SUB_azz_nn_d    11000001 111 ....0 0 .. 110 ....0 11 ...    @azz_2x2_o3
 SUB_azz_nn_d    11000001 111 ...01 0 .. 110 ...00 11 ...    @azz_4x4_o3
+
+@azz_2x2_o2x2   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off2_x2
+@azz_4x4_o2x2   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off2_x2
+
+FMLAL_nn        11000001 101 ....0 0 .. 010 ....0 000 ..    @azz_2x2_o2x2
+FMLAL_nn        11000001 101 ...01 0 .. 010 ...00 000 ..    @azz_4x4_o2x2
+
+FMLSL_nn        11000001 101 ....0 0 .. 010 ....0 010 ..    @azz_2x2_o2x2
+FMLSL_nn        11000001 101 ...01 0 .. 010 ...00 010 ..    @azz_4x4_o2x2
+
+BFMLAL_nn       11000001 101 ....0 0 .. 010 ....0 100 ..    @azz_2x2_o2x2
+BFMLAL_nn       11000001 101 ...01 0 .. 010 ...00 100 ..    @azz_4x4_o2x2
+
+BFMLSL_nn       11000001 101 ....0 0 .. 010 ....0 110 ..    @azz_2x2_o2x2
+BFMLSL_nn       11000001 101 ...01 0 .. 010 ...00 110 ..    @azz_4x4_o2x2
+
+### SME2 Multi-vector Indexed
+
+&azx_n          n off rv zn zm idx
+
+%idx3_15_10     15:1 10:2
+%idx2_10_2      10:2 2:1
+
+@azx_1x1_o3x2   ........ .... zm:4 . .. . .. zn:5 .. ...    \
+                &azx_n n=1 rv=%mova_rv off=%off3_x2 idx=%idx3_15_10
+@azx_2x1_o2x2   ........ .... zm:4 . .. . .. ..... .. ...   \
+                &azx_n n=2 rv=%mova_rv off=%off2_x2 zn=%zn_ax2 idx=%idx2_10_2
+@azx_4x1_o2x2   ........ .... zm:4 . .. . .. ..... .. ...   \
+                &azx_n n=4 rv=%mova_rv off=%off2_x2 zn=%zn_ax4 idx=%idx2_10_2
+
+FMLAL_nx        11000001 1000 .... . .. 1 .. ..... 00 ...   @azx_1x1_o3x2
+FMLAL_nx        11000001 1001 .... 0 .. 1 .. ....0 00 ...   @azx_2x1_o2x2
+FMLAL_nx        11000001 1001 .... 1 .. 1 .. ...00 00 ...   @azx_4x1_o2x2
+
+FMLSL_nx        11000001 1000 .... . .. 1 .. ..... 01 ...   @azx_1x1_o3x2
+FMLSL_nx        11000001 1001 .... 0 .. 1 .. ....0 01 ...   @azx_2x1_o2x2
+FMLSL_nx        11000001 1001 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_o2x2
+
+BFMLAL_nx       11000001 1000 .... . .. 1 .. ..... 10 ...   @azx_1x1_o3x2
+BFMLAL_nx       11000001 1001 .... 0 .. 1 .. ....0 10 ...   @azx_2x1_o2x2
+BFMLAL_nx       11000001 1001 .... 1 .. 1 .. ...00 10 ...   @azx_4x1_o2x2
+
+BFMLSL_nx       11000001 1000 .... . .. 1 .. ..... 11 ...   @azx_1x1_o3x2
+BFMLSL_nx       11000001 1001 .... 0 .. 1 .. ....0 11 ...   @azx_2x1_o2x2
+BFMLSL_nx       11000001 1001 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_o2x2
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var)
 TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var)
 TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var)
 TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var)
+
+/*
+ * Expand array multi-vector single (n1), array multi-vector (nn),
+ * and array multi-vector indexed (nx), for floating-point accumulate.
+ *   multi: true for nn, false for n1.
+ *   fpst: >= 0 to set ptr argument for FPST_*, < 0 for ENV.
+ *   data: stuff for simd_data, including any index.
+ */
+#define FPST_ENV  -1
+
+static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel,
+                          int rv, int off, int zn, int zm,
+                          int data, int shsel, bool multi, int fpst,
+                          gen_helper_gvec_4_ptr *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / nreg;
+        TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+        TCGv_ptr t, ptr;
+
+        if (fpst >= 0) {
+            ptr = fpstatus_ptr(fpst);
+        } else {
+            ptr = tcg_env;
+        }
+        t = tcg_temp_new_ptr();
+
+        for (int r = 0; r < nreg; ++r) {
+            TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+            TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+            for (int i = 0; i < nsel; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                int desc = simd_desc(svl, svl, data | (i << shsel));
+
+                tcg_gen_addi_ptr(t, t_za, o_za);
+                fn(t, t_zn, t_zm, t, ptr, tcg_constant_i32(desc));
+            }
+
+            /*
+             * For multiple-and-single vectors, Zn may wrap.
+             * For multiple vectors, both Zn and Zm are aligned.
+             */
+            zn = (zn + 1) % 32;
+            zm += multi;
+        }
+    }
+    return true;
+}
+
+static bool do_fmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         (1 << 2) | sub, 1,
+                         multi, FPST_ENV, gen_helper_sve2_fmlal_zzzw_s);
+}
+
+TRANS_FEAT(FMLAL_n1, aa64_sme2, do_fmlal, a, false, false)
+TRANS_FEAT(FMLSL_n1, aa64_sme2, do_fmlal, a, true, false)
+TRANS_FEAT(FMLAL_nn, aa64_sme2, do_fmlal, a, false, true)
+TRANS_FEAT(FMLSL_nn, aa64_sme2, do_fmlal, a, true, true)
+
+static bool do_fmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         (a->idx << 3) | (1 << 2) | sub, 1,
+                         false, FPST_ENV, gen_helper_sve2_fmlal_zzxw_s);
+}
+
+TRANS_FEAT(FMLAL_nx, aa64_sme2, do_fmlal_nx, a, false)
+TRANS_FEAT(FMLSL_nx, aa64_sme2, do_fmlal_nx, a, true)
+
+static bool do_bfmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         0, 0, multi, FPST_ZA,
+                         (!sub ? gen_helper_gvec_bfmlal
+                          : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl
+                          : gen_helper_gvec_bfmlsl));
+}
+
+TRANS_FEAT(BFMLAL_n1, aa64_sme2, do_bfmlal, a, false, false)
+TRANS_FEAT(BFMLSL_n1, aa64_sme2, do_bfmlal, a, true, false)
+TRANS_FEAT(BFMLAL_nn, aa64_sme2, do_bfmlal, a, false, true)
+TRANS_FEAT(BFMLSL_nn, aa64_sme2, do_bfmlal, a, true, true)
+
+static bool do_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
+{
+    return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                         a->idx << 1, 0, false, FPST_ZA,
+                         !sub ? gen_helper_gvec_bfmlal_idx
+                         : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl_idx
+                         : gen_helper_gvec_bfmlsl_idx);
+}
+
+TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false)
+TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true)
-- 
2.43.0

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: 20250704142112.1018902-38-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  5 ++++
 target/arm/tcg/sme.decode      | 14 +++++++++++
 target/arm/tcg/sve.decode      |  7 ++++--
 target/arm/tcg/sme_helper.c    | 44 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 18 ++++++++++++++
 target/arm/tcg/translate-sve.c |  5 ++++
 6 files changed, 91 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: 20250704142112.1018902-39-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      |  9 +++++++++
 target/arm/tcg/translate-sme.c | 17 +++++++++++++++++
 2 files changed, 26 insertions(+)

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: 20250704142112.1018902-40-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  2 ++
 target/arm/tcg/helper.h        |  2 ++
 target/arm/tcg/sme.decode      |  3 +++
 target/arm/tcg/sme_helper.c    | 30 ++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 24 +++++++++++++++++++++
 target/arm/tcg/vec_helper.c    | 39 ++++++++++++++++++++++++++++++++++
 6 files changed, 100 insertions(+)

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

Emphasize that these are 4-way dot products.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-41-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h         | 22 +++++++++++-----------
 target/arm/tcg/translate-a64.c  | 14 +++++++-------
 target/arm/tcg/translate-neon.c | 14 +++++++-------
 target/arm/tcg/translate-sve.c  | 18 +++++++++---------
 target/arm/tcg/vec_helper.c     | 22 +++++++++++-----------
 5 files changed, 45 insertions(+), 45 deletions(-)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_4h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_udot_idx_4h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
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_dot_vector_env(DisasContext *s, arg_qrrr_e *a,
     return true;
 }
 
-TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b)
-TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b)
-TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b)
+TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_4b)
+TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_4b)
 TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfdot)
 TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfmmla)
 TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b)
@@ -XXX,XX +XXX,XX @@ static bool do_dot_vector_idx_env(DisasContext *s, arg_qrrx_e *a,
     return true;
 }
 
-TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b)
-TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b)
+TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_4b)
 TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
-           gen_helper_gvec_sudot_idx_b)
+           gen_helper_gvec_sudot_idx_4b)
 TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
-           gen_helper_gvec_usdot_idx_b)
+           gen_helper_gvec_usdot_idx_4b)
 TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx_env, a,
            gen_helper_gvec_bfdot_idx)
 
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 @@ static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
-                        gen_helper_gvec_sdot_b);
+                        gen_helper_gvec_sdot_4b);
 }
 
 static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
-                        gen_helper_gvec_udot_b);
+                        gen_helper_gvec_udot_4b);
 }
 
 static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
-                        gen_helper_gvec_usdot_b);
+                        gen_helper_gvec_usdot_4b);
 }
 
 static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_sdot_idx_b);
+                        gen_helper_gvec_sdot_idx_4b);
 }
 
 static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_udot_idx_b);
+                        gen_helper_gvec_udot_idx_4b);
 }
 
 static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_usdot_idx_b);
+                        gen_helper_gvec_usdot_idx_4b);
 }
 
 static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
@@ -XXX,XX +XXX,XX @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
         return false;
     }
     return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
-                        gen_helper_gvec_sudot_idx_b);
+                        gen_helper_gvec_sudot_idx_4b);
 }
 
 static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a)
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 @@ DO_ZZI(UMIN, umin)
 #undef DO_ZZI
 
 static gen_helper_gvec_4 * const dot_fns[2][2] = {
-    { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h },
-    { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h }
+    { gen_helper_gvec_sdot_4b, gen_helper_gvec_sdot_4h },
+    { gen_helper_gvec_udot_4b, gen_helper_gvec_udot_4h }
 };
 TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
            dot_fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0)
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
  */
 
 TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_sdot_idx_b, a)
+           gen_helper_gvec_sdot_idx_4b, a)
 TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_sdot_idx_h, a)
+           gen_helper_gvec_sdot_idx_4h, a)
 TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_udot_idx_b, a)
+           gen_helper_gvec_udot_idx_4b, a)
 TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_udot_idx_h, a)
+           gen_helper_gvec_udot_idx_4h, a)
 
 TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_sudot_idx_b, a)
+           gen_helper_gvec_sudot_idx_4b, a)
 TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
-           gen_helper_gvec_usdot_idx_b, a)
+           gen_helper_gvec_usdot_idx_4b, a)
 
 #define DO_SVE2_RRX(NAME, FUNC) \
     TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC,          \
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
            sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot)
 
 TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
-           a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0)
+           a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0)
 
 TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
                         gen_helper_crypto_aesmc, a->rd, a->rd, 0)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
     clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
 
-DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t)
-DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t)
-DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t)
-DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t)
-DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t)
+DO_DOT(gvec_sdot_4b, int32_t, int8_t, int8_t)
+DO_DOT(gvec_udot_4b, uint32_t, uint8_t, uint8_t)
+DO_DOT(gvec_usdot_4b, uint32_t, uint8_t, int8_t)
+DO_DOT(gvec_sdot_4h, int64_t, int16_t, int16_t)
+DO_DOT(gvec_udot_4h, uint64_t, uint16_t, uint16_t)
 
 #define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
     clear_tail(d, opr_sz, simd_maxsz(desc));                              \
 }
 
-DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4)
-DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4)
-DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4)
-DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4)
-DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, H8)
-DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, H8)
+DO_DOT_IDX(gvec_sdot_idx_4b, int32_t, int8_t, int8_t, H4)
+DO_DOT_IDX(gvec_udot_idx_4b, uint32_t, uint8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_sudot_idx_4b, int32_t, int8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4)
+DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8)
+DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8)
 
 void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
                          float_status *fpst, uint32_t desc)
-- 
2.43.0

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-42-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        |  8 ++++
 target/arm/tcg/sme.decode      | 63 ++++++++++++++++++++++++-
 target/arm/tcg/translate-sme.c | 85 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    | 51 ++++++++++++++++++++
 4 files changed, 206 insertions(+), 1 deletion(-)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_sdot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG,
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_2h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_2h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ FDOT_n1         11000001 001 1 .... 0 .. 100 ..... 00 ...   @azz_nx1_o3 n=4
 BFDOT_n1        11000001 001 0 .... 0 .. 100 ..... 10 ...   @azz_nx1_o3 n=2
 BFDOT_n1        11000001 001 1 .... 0 .. 100 ..... 10 ...   @azz_nx1_o3 n=4
 
+USDOT_n1        11000001 001 0 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=2
+USDOT_n1        11000001 001 1 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=4
+
+SUDOT_n1        11000001 001 0 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=2
+SUDOT_n1        11000001 001 1 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=4
+
+SDOT_n1_4b      11000001 001 0 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=2
+SDOT_n1_4b      11000001 001 1 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=4
+SDOT_n1_4h      11000001 011 0 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=2
+SDOT_n1_4h      11000001 011 1 .... 0 .. 101 ..... 00 ...   @azz_nx1_o3 n=4
+SDOT_n1_2h      11000001 011 0 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=2
+SDOT_n1_2h      11000001 011 1 .... 0 .. 101 ..... 01 ...   @azz_nx1_o3 n=4
+
+UDOT_n1_4b      11000001 001 0 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=2
+UDOT_n1_4b      11000001 001 1 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=4
+UDOT_n1_4h      11000001 011 0 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=2
+UDOT_n1_4h      11000001 011 1 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=4
+UDOT_n1_2h      11000001 011 0 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=2
+UDOT_n1_2h      11000001 011 1 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ FDOT_nn         11000001 101 ...01 0 .. 100 ...00 00 ...    @azz_4x4_o3
 BFDOT_nn        11000001 101 ....0 0 .. 100 ....0 10 ...    @azz_2x2_o3
 BFDOT_nn        11000001 101 ...01 0 .. 100 ...00 10 ...    @azz_4x4_o3
 
+USDOT_nn        11000001 101 ....0 0 .. 101 ....0 01 ...    @azz_2x2_o3
+USDOT_nn        11000001 101 ...01 0 .. 101 ...00 01 ...    @azz_4x4_o3
+
+SDOT_nn_4b      11000001 101 ....0 0 .. 101 ....0 00 ...    @azz_2x2_o3
+SDOT_nn_4b      11000001 101 ...01 0 .. 101 ...00 00 ...    @azz_4x4_o3
+SDOT_nn_4h      11000001 111 ....0 0 .. 101 ....0 00 ...    @azz_2x2_o3
+SDOT_nn_4h      11000001 111 ...01 0 .. 101 ...00 00 ...    @azz_4x4_o3
+SDOT_nn_2h      11000001 111 ....0 0 .. 101 ....0 01 ...    @azz_2x2_o3
+SDOT_nn_2h      11000001 111 ...01 0 .. 101 ...00 01 ...    @azz_4x4_o3
+
+UDOT_nn_4b      11000001 101 ....0 0 .. 101 ....0 10 ...    @azz_2x2_o3
+UDOT_nn_4b      11000001 101 ...01 0 .. 101 ...00 10 ...    @azz_4x4_o3
+UDOT_nn_4h      11000001 111 ....0 0 .. 101 ....0 10 ...    @azz_2x2_o3
+UDOT_nn_4h      11000001 111 ...01 0 .. 101 ...00 10 ...    @azz_4x4_o3
+UDOT_nn_2h      11000001 111 ....0 0 .. 101 ....0 11 ...    @azz_2x2_o3
+UDOT_nn_2h      11000001 111 ...01 0 .. 101 ...00 11 ...    @azz_4x4_o3
+
 ### SME2 Multi-vector Indexed
 
 &azx_n          n off rv zn zm idx
@@ -XXX,XX +XXX,XX @@ BFMLSL_nx       11000001 1001 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_o2x2
 @azx_2x1_i2_o3  ........ .... zm:4 . .. . idx:2 .... ... off:3 \
                 &azx_n n=2 rv=%mova_rv zn=%zn_ax2
 @azx_4x1_i2_o3  ........ .... zm:4 . .. . idx:2 .... ... off:3 \
-                &azx_n n=2 rv=%mova_rv zn=%zn_ax4
+                &azx_n n=4 rv=%mova_rv zn=%zn_ax4
+@azx_2x1_i1_o3  ........ .... zm:4 . .. .. idx:1 .... ... off:3 \
+                &azx_n n=2 rv=%mova_rv zn=%zn_ax2
+@azx_4x1_i1_o3  ........ .... zm:4 . .. .. idx:1 .... ... off:3 \
+                &azx_n n=4 rv=%mova_rv zn=%zn_ax4
 
 FDOT_nx         11000001 0101 .... 0 .. 1 .. ....0 01 ...   @azx_2x1_i2_o3
 FDOT_nx         11000001 0101 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_i2_o3
@@ -XXX,XX +XXX,XX @@ BFDOT_nx        11000001 0101 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_i2_o3
 
 FVDOT           11000001 0101 .... 0 .. 0 .. ....0 01 ...   @azx_2x1_i2_o3
 BFVDOT          11000001 0101 .... 0 .. 0 .. ....0 11 ...   @azx_2x1_i2_o3
+
+SDOT_nx_2h      11000001 0101 .... 0 .. 1 .. ....0 00 ...   @azx_2x1_i2_o3
+SDOT_nx_2h      11000001 0101 .... 1 .. 1 .. ...00 00 ...   @azx_4x1_i2_o3
+SDOT_nx_4b      11000001 0101 .... 0 .. 1 .. ....1 00 ...   @azx_2x1_i2_o3
+SDOT_nx_4b      11000001 0101 .... 1 .. 1 .. ...01 00 ...   @azx_4x1_i2_o3
+SDOT_nx_4h      11000001 1101 .... 0 .. 00 . ....0 01 ...   @azx_2x1_i1_o3
+SDOT_nx_4h      11000001 1101 .... 1 .. 00 . ...00 01 ...   @azx_4x1_i1_o3
+
+UDOT_nx_2h      11000001 0101 .... 0 .. 1 .. ....0 10 ...   @azx_2x1_i2_o3
+UDOT_nx_2h      11000001 0101 .... 1 .. 1 .. ...00 10 ...   @azx_4x1_i2_o3
+UDOT_nx_4b      11000001 0101 .... 0 .. 1 .. ....1 10 ...   @azx_2x1_i2_o3
+UDOT_nx_4b      11000001 0101 .... 1 .. 1 .. ...01 10 ...   @azx_4x1_i2_o3
+UDOT_nx_4h      11000001 1101 .... 0 .. 00 . ....0 11 ...   @azx_2x1_i1_o3
+UDOT_nx_4h      11000001 1101 .... 1 .. 00 . ...00 11 ...   @azx_4x1_i1_o3
+
+USDOT_nx        11000001 0101 .... 0 .. 1 .. ....1 01 ...   @azx_2x1_i2_o3
+USDOT_nx        11000001 0101 .... 1 .. 1 .. ...01 01 ...   @azx_4x1_i2_o3
+
+SUDOT_nx        11000001 0101 .... 0 .. 1 .. ....1 11 ...   @azx_2x1_i2_o3
+SUDOT_nx        11000001 0101 .... 1 .. 1 .. ...01 11 ...   @azx_4x1_i2_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
 
 TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
 TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
+
+/*
+ * Expand array multi-vector single (n1), array multi-vector (nn),
+ * and array multi-vector indexed (nx), for integer accumulate.
+ *   multi: true for nn, false for n1.
+ *   data: stuff for simd_data, including any index.
+ */
+static bool do_azz_acc(DisasContext *s, int nreg, int nsel,
+                       int rv, int off, int zn, int zm,
+                       int data, int shsel, bool multi,
+                       gen_helper_gvec_4 *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / nreg;
+        TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+        TCGv_ptr t = tcg_temp_new_ptr();
+
+        for (int r = 0; r < nreg; ++r) {
+            TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+            TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+            for (int i = 0; i < nsel; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                int desc = simd_desc(svl, svl, data | (i << shsel));
+
+                tcg_gen_addi_ptr(t, t_za, o_za);
+                fn(t, t_zn, t_zm, t, tcg_constant_i32(desc));
+            }
+
+            /*
+             * For multiple-and-single vectors, Zn may wrap.
+             * For multiple vectors, both Zn and Zm are aligned.
+             */
+            zn = (zn + 1) % 32;
+            zm += multi;
+        }
+    }
+    return true;
+}
+
+static bool do_dot(DisasContext *s, arg_azz_n *a, bool multi,
+                   gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                      0, 0, multi, fn);
+}
+
+static void gen_helper_gvec_sudot_4b(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m,
+                                     TCGv_ptr a, TCGv_i32 desc)
+{
+    gen_helper_gvec_usdot_4b(d, m, n, a, desc);
+}
+
+TRANS_FEAT(USDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_usdot_4b)
+TRANS_FEAT(SUDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_sudot_4b)
+TRANS_FEAT(SDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_2h)
+TRANS_FEAT(UDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_2h)
+TRANS_FEAT(SDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_4b)
+TRANS_FEAT(SDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_sdot_4h)
+TRANS_FEAT(UDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_udot_4h)
+
+TRANS_FEAT(USDOT_nn, aa64_sme2, do_dot, a, true, gen_helper_gvec_usdot_4b)
+TRANS_FEAT(SDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_2h)
+TRANS_FEAT(UDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_2h)
+TRANS_FEAT(SDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_4b)
+TRANS_FEAT(SDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_sdot_4h)
+TRANS_FEAT(UDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_udot_4h)
+
+static bool do_dot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                      a->idx, 0, false, fn);
+}
+
+TRANS_FEAT(USDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_usdot_idx_4b)
+TRANS_FEAT(SUDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sudot_idx_4b)
+TRANS_FEAT(SDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_2h)
+TRANS_FEAT(UDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_2h)
+TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b)
+TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h)
+TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4)
 DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8)
 DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8)
 
+#undef DO_DOT
+#undef DO_DOT_IDX
+
+/* Similar for 2-way dot product */
+#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i, opr_sz = simd_oprsz(desc);                                \
+    TYPED *d = vd, *a = va;                                               \
+    TYPEN *n = vn;                                                        \
+    TYPEM *m = vm;                                                        \
+    for (i = 0; i < opr_sz / sizeof(TYPED); ++i) {                        \
+        d[i] = (a[i] +                                                    \
+                (TYPED)n[i * 2 + 0] * m[i * 2 + 0] +                      \
+                (TYPED)n[i * 2 + 1] * m[i * 2 + 1]);                      \
+    }                                                                     \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                              \
+}
+
+#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)  \
+{                                                                         \
+    intptr_t i = 0, opr_sz = simd_oprsz(desc);                            \
+    intptr_t opr_sz_n = opr_sz / sizeof(TYPED);                           \
+    intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n);                  \
+    intptr_t index = simd_data(desc);                                     \
+    TYPED *d = vd, *a = va;                                               \
+    TYPEN *n = vn;                                                        \
+    TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 2;                       \
+    do {                                                                  \
+        TYPED m0 = m_indexed[i * 2 + 0];                                  \
+        TYPED m1 = m_indexed[i * 2 + 1];                                  \
+        do {                                                              \
+            d[i] = (a[i] +                                                \
+                    n[i * 2 + 0] * m0 +                                   \
+                    n[i * 2 + 1] * m1);                                   \
+        } while (++i < segend);                                           \
+        segend = i + (16 / sizeof(TYPED));                                \
+    } while (i < opr_sz_n);                                               \
+    clear_tail(d, opr_sz, simd_maxsz(desc));                              \
+}
+
+DO_DOT(gvec_sdot_2h, int32_t, int16_t, int16_t)
+DO_DOT(gvec_udot_2h, uint32_t, uint16_t, uint16_t)
+
+DO_DOT_IDX(gvec_sdot_idx_2h, int32_t, int16_t, int16_t, H4)
+DO_DOT_IDX(gvec_udot_idx_2h, uint32_t, uint16_t, uint16_t, H4)
+
+#undef DO_DOT
+#undef DO_DOT_IDX
+
 void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
                          float_status *fpst, uint32_t desc)
 {
-- 
2.43.0

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

Emphasize the 4-way nature of these dot products.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-43-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      | 12 ++++++------
 target/arm/tcg/translate-sve.c | 12 ++++++------
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ CDOT_zzzz       01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5  ra=%reg_movprfx
 #### SVE Multiply - Indexed
 
 # SVE integer dot product (indexed)
-SDOT_zzxw_s     01000100 10 1 ..... 000000 ..... .....   @rrxr_2 esz=2
-SDOT_zzxw_d     01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
-UDOT_zzxw_s     01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
-UDOT_zzxw_d     01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
+SDOT_zzxw_4s    01000100 10 1 ..... 000000 ..... .....   @rrxr_2 esz=2
+SDOT_zzxw_4d    01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
+UDOT_zzxw_4s    01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
+UDOT_zzxw_4d    01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
 # SVE2 integer multiply-add (indexed)
 MLA_zzxz_h      01000100 0. 1 ..... 000010 ..... .....   @rrxr_3 esz=1
@@ -XXX,XX +XXX,XX @@ SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... .....   @rrxr_2 esz=2
 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... .....   @rrxr_1 esz=3
 
 # SVE mixed sign dot product (indexed)
-USDOT_zzxw_s    01000100 10 1 ..... 000110 ..... .....   @rrxr_2 esz=2
-SUDOT_zzxw_s    01000100 10 1 ..... 000111 ..... .....   @rrxr_2 esz=2
+USDOT_zzxw_4s   01000100 10 1 ..... 000110 ..... .....   @rrxr_2 esz=2
+SUDOT_zzxw_4s   01000100 10 1 ..... 000111 ..... .....   @rrxr_2 esz=2
 
 # SVE2 saturating multiply-add (indexed)
 SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... .....   @rrxr_3a esz=2
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 @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
  * SVE Multiply - Indexed
  */
 
-TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_sdot_idx_4b, a)
-TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_sdot_idx_4h, a)
-TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(UDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_udot_idx_4b, a)
-TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(UDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_udot_idx_4h, a)
 
-TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_sudot_idx_4b, a)
-TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_usdot_idx_4b, a)
 
 #define DO_SVE2_RRX(NAME, FUNC) \
-- 
2.43.0

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

Rename to USDOT_zzzz_4s and force size=2 during decode.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-44-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      | 2 +-
 target/arm/tcg/translate-sve.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 
 ## SVE mixed sign dot product
 
-USDOT_zzzz      01000100 .. 0 ..... 011 110 ..... .....  @rda_rn_rm
+USDOT_zzzz_4s   01000100 10 0 ..... 011 110 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating point matrix multiply accumulate
 BFMMLA          01100100 01 1 ..... 111 001 ..... .....  @rda_rn_rm_ex esz=1
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 gen_helper_gvec_4 * const sqrdcmlah_fns[] = {
 TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
            sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot)
 
-TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
-           a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0)
+TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
+           gen_helper_gvec_usdot_4b, a, 0)
 
 TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
                         gen_helper_crypto_aesmc, a->rd, a->rd, 0)
-- 
2.43.0

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: 20250704142112.1018902-45-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  8 +++++++-
 target/arm/tcg/translate-sve.c | 10 ++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SDOT_zzxw_4d    01000100 11 1 ..... 000000 ..... .....   @rrxr_1 esz=3
 UDOT_zzxw_4s    01000100 10 1 ..... 000001 ..... .....   @rrxr_2 esz=2
 UDOT_zzxw_4d    01000100 11 1 ..... 000001 ..... .....   @rrxr_1 esz=3
 
+SDOT_zzxw_2s    01000100 10 0 ..... 110010 ..... .....   @rrxr_2 esz=2
+UDOT_zzxw_2s    01000100 10 0 ..... 110011 ..... .....   @rrxr_2 esz=2
+
 # SVE2 integer multiply-add (indexed)
 MLA_zzxz_h      01000100 0. 1 ..... 000010 ..... .....   @rrxr_3 esz=1
 MLA_zzxz_s      01000100 10 1 ..... 000010 ..... .....   @rrxr_2 esz=2
@@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw     01000100 .. 0 ..... 010 111 ..... .....  @rda_rn_rm
 CMLA_zzzz       01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5  ra=%reg_movprfx
 SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
 
-## SVE mixed sign dot product
+## SVE dot product
+
+SDOT_zzzz_2s    01000100 00 0 ..... 110 010 ..... .....  @rda_rn_rm_ex esz=2
+UDOT_zzzz_2s    01000100 00 0 ..... 110 011 ..... .....  @rda_rn_rm_ex esz=2
 
 USDOT_zzzz_4s   01000100 10 0 ..... 011 110 ..... .....  @rda_rn_rm_ex esz=2
 
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 @@ TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
 TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
            gen_helper_gvec_usdot_idx_4b, a)
 
+TRANS_FEAT(SDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz,
+           gen_helper_gvec_sdot_idx_2h, a)
+TRANS_FEAT(UDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz,
+           gen_helper_gvec_udot_idx_2h, a)
+
 #define DO_SVE2_RRX(NAME, FUNC) \
     TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC,          \
                a->rd, a->rn, a->rm, a->index)
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
 TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
            gen_helper_gvec_usdot_4b, a, 0)
 
+TRANS_FEAT(SDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz,
+           gen_helper_gvec_sdot_2h, a, 0)
+TRANS_FEAT(UDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz,
+           gen_helper_gvec_udot_2h, a, 0)
+
 TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
                         gen_helper_crypto_aesmc, a->rd, a->rd, 0)
 TRANS_FEAT_NONSTREAMING(AESIMC, aa64_sve2_aes, gen_gvec_ool_zz,
-- 
2.43.0

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: 20250704142112.1018902-46-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 11 +++++++++
 target/arm/tcg/sme.decode      | 11 +++++++++
 target/arm/tcg/sme_helper.c    | 42 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 23 +++++++++++++++++++
 4 files changed, 87 insertions(+)

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: 20250704142112.1018902-47-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  21 +++++
 target/arm/tcg/sme.decode      | 168 +++++++++++++++++++++++++++++++++
 target/arm/tcg/sme_helper.c    |  59 ++++++++++++
 target/arm/tcg/translate-sme.c |  84 +++++++++++++++++
 4 files changed, 332 insertions(+)

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_smlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_usmlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_smlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ UDOT_n1_4h      11000001 011 1 .... 0 .. 101 ..... 10 ...   @azz_nx1_o3 n=4
 UDOT_n1_2h      11000001 011 0 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=2
 UDOT_n1_2h      11000001 011 1 .... 0 .. 101 ..... 11 ...   @azz_nx1_o3 n=4
 
+SMLAL_n1        11000001 011 0 .... 0 .. 011 ..... 00 ...   @azz_nx1_o3x2 n=1
+SMLAL_n1        11000001 011 0 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=2
+SMLAL_n1        11000001 011 1 .... 0 .. 010 ..... 000 ..   @azz_nx1_o2x2 n=4
+
+SMLSL_n1        11000001 011 0 .... 0 .. 011 ..... 01 ...   @azz_nx1_o3x2 n=1
+SMLSL_n1        11000001 011 0 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=2
+SMLSL_n1        11000001 011 1 .... 0 .. 010 ..... 010 ..   @azz_nx1_o2x2 n=4
+
+UMLAL_n1        11000001 011 0 .... 0 .. 011 ..... 10 ...   @azz_nx1_o3x2 n=1
+UMLAL_n1        11000001 011 0 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=2
+UMLAL_n1        11000001 011 1 .... 0 .. 010 ..... 100 ..   @azz_nx1_o2x2 n=4
+
+UMLSL_n1        11000001 011 0 .... 0 .. 011 ..... 11 ...   @azz_nx1_o3x2 n=1
+UMLSL_n1        11000001 011 0 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=2
+UMLSL_n1        11000001 011 1 .... 0 .. 010 ..... 110 ..   @azz_nx1_o2x2 n=4
+
+%off2_x4        0:2 !function=times_4
+%off1_x4        0:1 !function=times_4
+
+@azz_nx1_o2x4   ........ ... . zm:4 . .. ... zn:5 ... ..    \
+                &azz_n off=%off2_x4 rv=%mova_rv
+@azz_nx1_o1x4   ........ ... . zm:4 . .. ... zn:5 .... .    \
+                &azz_n off=%off1_x4 rv=%mova_rv
+
+SMLALL_n1_s     11000001 001 0 .... 0 .. 001 ..... 000 ..   @azz_nx1_o2x4 n=1
+SMLALL_n1_d     11000001 011 0 .... 0 .. 001 ..... 000 ..   @azz_nx1_o2x4 n=1
+SMLALL_n1_s     11000001 001 0 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=2
+SMLALL_n1_d     11000001 011 0 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=2
+SMLALL_n1_s     11000001 001 1 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=4
+SMLALL_n1_d     11000001 011 1 .... 0 .. 000 ..... 0000 .   @azz_nx1_o1x4 n=4
+
+SMLSLL_n1_s     11000001 001 0 .... 0 .. 001 ..... 010 ..   @azz_nx1_o2x4 n=1
+SMLSLL_n1_d     11000001 011 0 .... 0 .. 001 ..... 010 ..   @azz_nx1_o2x4 n=1
+SMLSLL_n1_s     11000001 001 0 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=2
+SMLSLL_n1_d     11000001 011 0 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=2
+SMLSLL_n1_s     11000001 001 1 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=4
+SMLSLL_n1_d     11000001 011 1 .... 0 .. 000 ..... 0100 .   @azz_nx1_o1x4 n=4
+
+UMLALL_n1_s     11000001 001 0 .... 0 .. 001 ..... 100 ..   @azz_nx1_o2x4 n=1
+UMLALL_n1_d     11000001 011 0 .... 0 .. 001 ..... 100 ..   @azz_nx1_o2x4 n=1
+UMLALL_n1_s     11000001 001 0 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=2
+UMLALL_n1_d     11000001 011 0 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=2
+UMLALL_n1_s     11000001 001 1 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=4
+UMLALL_n1_d     11000001 011 1 .... 0 .. 000 ..... 1000 .   @azz_nx1_o1x4 n=4
+
+UMLSLL_n1_s     11000001 001 0 .... 0 .. 001 ..... 110 ..   @azz_nx1_o2x4 n=1
+UMLSLL_n1_d     11000001 011 0 .... 0 .. 001 ..... 110 ..   @azz_nx1_o2x4 n=1
+UMLSLL_n1_s     11000001 001 0 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=2
+UMLSLL_n1_d     11000001 011 0 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=2
+UMLSLL_n1_s     11000001 001 1 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=4
+UMLSLL_n1_d     11000001 011 1 .... 0 .. 000 ..... 1100 .   @azz_nx1_o1x4 n=4
+
+USMLALL_n1_s    11000001 001 0 .... 0 .. 001 ..... 001 ..   @azz_nx1_o2x4 n=1
+USMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=2
+USMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=4
+
+SUMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=2
+SUMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ UDOT_nn_4h      11000001 111 ...01 0 .. 101 ...00 10 ...    @azz_4x4_o3
 UDOT_nn_2h      11000001 111 ....0 0 .. 101 ....0 11 ...    @azz_2x2_o3
 UDOT_nn_2h      11000001 111 ...01 0 .. 101 ...00 11 ...    @azz_4x4_o3
 
+SMLAL_nn        11000001 111 ....0 0 .. 010 ....0 000 ..    @azz_2x2_o2x2
+SMLAL_nn        11000001 111 ...01 0 .. 010 ...00 000 ..    @azz_4x4_o2x2
+
+SMLSL_nn        11000001 111 ....0 0 .. 010 ....0 010 ..    @azz_2x2_o2x2
+SMLSL_nn        11000001 111 ...01 0 .. 010 ...00 010 ..    @azz_4x4_o2x2
+
+UMLAL_nn        11000001 111 ....0 0 .. 010 ....0 100 ..    @azz_2x2_o2x2
+UMLAL_nn        11000001 111 ...01 0 .. 010 ...00 100 ..    @azz_4x4_o2x2
+
+UMLSL_nn        11000001 111 ....0 0 .. 010 ....0 110 ..    @azz_2x2_o2x2
+UMLSL_nn        11000001 111 ...01 0 .. 010 ...00 110 ..    @azz_4x4_o2x2
+
+@azz_2x2_o1x4   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off1_x4
+@azz_4x4_o1x4   ........ ... ..... . .. ... ..... ... ..    \
+                &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off1_x4
+
+SMLALL_nn_s     11000001 101 ....0 0 .. 000 ....0 0000 .    @azz_2x2_o1x4
+SMLALL_nn_d     11000001 111 ....0 0 .. 000 ....0 0000 .    @azz_2x2_o1x4
+SMLALL_nn_s     11000001 101 ...01 0 .. 000 ...00 0000 .    @azz_4x4_o1x4
+SMLALL_nn_d     11000001 111 ...01 0 .. 000 ...00 0000 .    @azz_4x4_o1x4
+
+SMLSLL_nn_s     11000001 101 ....0 0 .. 000 ....0 0100 .    @azz_2x2_o1x4
+SMLSLL_nn_d     11000001 111 ....0 0 .. 000 ....0 0100 .    @azz_2x2_o1x4
+SMLSLL_nn_s     11000001 101 ...01 0 .. 000 ...00 0100 .    @azz_4x4_o1x4
+SMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 0100 .    @azz_4x4_o1x4
+
+UMLALL_nn_s     11000001 101 ....0 0 .. 000 ....0 1000 .    @azz_2x2_o1x4
+UMLALL_nn_d     11000001 111 ....0 0 .. 000 ....0 1000 .    @azz_2x2_o1x4
+UMLALL_nn_s     11000001 101 ...01 0 .. 000 ...00 1000 .    @azz_4x4_o1x4
+UMLALL_nn_d     11000001 111 ...01 0 .. 000 ...00 1000 .    @azz_4x4_o1x4
+
+UMLSLL_nn_s     11000001 101 ....0 0 .. 000 ....0 1100 .    @azz_2x2_o1x4
+UMLSLL_nn_d     11000001 111 ....0 0 .. 000 ....0 1100 .    @azz_2x2_o1x4
+UMLSLL_nn_s     11000001 101 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
+UMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
+
+USMLALL_nn_s    11000001 101 ....0 0 .. 000 ....0 0010 .    @azz_2x2_o1x4
+USMLALL_nn_s    11000001 101 ...01 0 .. 000 ...00 0010 .    @azz_4x4_o1x4
+
 ### SME2 Multi-vector Indexed
 
 &azx_n          n off rv zn zm idx
@@ -XXX,XX +XXX,XX @@ UVDOT_nx_4h     11000001 1101 .... 1 .. 01 . ...00 11 ...   @azx_4x1_i1_o3
 
 SUVDOT_nx_4b    11000001 0101 .... 1 .. 0 .. ...01 11 ...   @azx_4x1_i2_o3
 USVDOT_nx_4b    11000001 0101 .... 1 .. 0 .. ...01 01 ...   @azx_4x1_i2_o3
+
+SMLAL_nx        11000001 1100 .... . .. 1 .. ..... 00 ...   @azx_1x1_o3x2
+SMLAL_nx        11000001 1101 .... 0 .. 1 .. ....0 00 ...   @azx_2x1_o2x2
+SMLAL_nx        11000001 1101 .... 1 .. 1 .. ...00 00 ...   @azx_4x1_o2x2
+
+SMLSL_nx        11000001 1100 .... . .. 1 .. ..... 01 ...   @azx_1x1_o3x2
+SMLSL_nx        11000001 1101 .... 0 .. 1 .. ....0 01 ...   @azx_2x1_o2x2
+SMLSL_nx        11000001 1101 .... 1 .. 1 .. ...00 01 ...   @azx_4x1_o2x2
+
+UMLAL_nx        11000001 1100 .... . .. 1 .. ..... 10 ...   @azx_1x1_o3x2
+UMLAL_nx        11000001 1101 .... 0 .. 1 .. ....0 10 ...   @azx_2x1_o2x2
+UMLAL_nx        11000001 1101 .... 1 .. 1 .. ...00 10 ...   @azx_4x1_o2x2
+
+UMLSL_nx        11000001 1100 .... . .. 1 .. ..... 11 ...   @azx_1x1_o3x2
+UMLSL_nx        11000001 1101 .... 0 .. 1 .. ....0 11 ...   @azx_2x1_o2x2
+UMLSL_nx        11000001 1101 .... 1 .. 1 .. ...00 11 ...   @azx_4x1_o2x2
+
+%idx4_15_10     15:1 10:3
+%idx4_10_1      10:2 1:2
+%idx3_10_1      10:1 1:2
+
+@azx_1x1_i4_o2  ........ .... zm:4 . .. ... zn:5 ... ..     \
+                &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx4_15_10
+@azx_1x1_i3_o2  ........ .... zm:4 . .. ... zn:5 ... ..     \
+                &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx3_15_10
+@azx_2x1_i4_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx4_10_1
+@azx_2x1_i3_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx3_10_1
+@azx_4x1_i4_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx4_10_1
+@azx_4x1_i3_o1  ........ .... zm:4 . .. ... ..... ... ..     \
+                &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx3_10_1
+
+SMLALL_nx_s     11000001 0000 .... . .. ... ..... 000 ..    @azx_1x1_i4_o2
+SMLALL_nx_d     11000001 1000 .... . .. 0.. ..... 000 ..    @azx_1x1_i3_o2
+SMLALL_nx_s     11000001 0001 .... 0 .. 0.. ....0 00 ...    @azx_2x1_i4_o1
+SMLALL_nx_d     11000001 1001 .... 0 .. 00. ....0 00 ...    @azx_2x1_i3_o1
+SMLALL_nx_s     11000001 0001 .... 1 .. 0.. ...00 00 ...    @azx_4x1_i4_o1
+SMLALL_nx_d     11000001 1001 .... 1 .. 00. ...00 00 ...    @azx_4x1_i3_o1
+
+SMLSLL_nx_s     11000001 0000 .... . .. ... ..... 010 ..    @azx_1x1_i4_o2
+SMLSLL_nx_d     11000001 1000 .... . .. 0.. ..... 010 ..    @azx_1x1_i3_o2
+SMLSLL_nx_s     11000001 0001 .... 0 .. 0.. ....0 01 ...    @azx_2x1_i4_o1
+SMLSLL_nx_d     11000001 1001 .... 0 .. 00. ....0 01 ...    @azx_2x1_i3_o1
+SMLSLL_nx_s     11000001 0001 .... 1 .. 0.. ...00 01 ...    @azx_4x1_i4_o1
+SMLSLL_nx_d     11000001 1001 .... 1 .. 00. ...00 01 ...    @azx_4x1_i3_o1
+
+UMLALL_nx_s     11000001 0000 .... . .. ... ..... 100 ..    @azx_1x1_i4_o2
+UMLALL_nx_d     11000001 1000 .... . .. 0.. ..... 100 ..    @azx_1x1_i3_o2
+UMLALL_nx_s     11000001 0001 .... 0 .. 0.. ....0 10 ...    @azx_2x1_i4_o1
+UMLALL_nx_d     11000001 1001 .... 0 .. 00. ....0 10 ...    @azx_2x1_i3_o1
+UMLALL_nx_s     11000001 0001 .... 1 .. 0.. ...00 10 ...    @azx_4x1_i4_o1
+UMLALL_nx_d     11000001 1001 .... 1 .. 00. ...00 10 ...    @azx_4x1_i3_o1
+
+UMLSLL_nx_s     11000001 0000 .... . .. ... ..... 110 ..    @azx_1x1_i4_o2
+UMLSLL_nx_d     11000001 1000 .... . .. 0.. ..... 110 ..    @azx_1x1_i3_o2
+UMLSLL_nx_s     11000001 0001 .... 0 .. 0.. ....0 11 ...    @azx_2x1_i4_o1
+UMLSLL_nx_d     11000001 1001 .... 0 .. 00. ....0 11 ...    @azx_2x1_i3_o1
+UMLSLL_nx_s     11000001 0001 .... 1 .. 0.. ...00 11 ...    @azx_4x1_i4_o1
+UMLSLL_nx_d     11000001 1001 .... 1 .. 00. ...00 11 ...    @azx_4x1_i3_o1
+
+USMLALL_nx_s    11000001 0000 .... . .. ... ..... 001 ..    @azx_1x1_i4_o2
+USMLALL_nx_s    11000001 0001 .... 0 .. 0.. ....1 00 ...    @azx_2x1_i4_o1
+USMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 00 ...    @azx_4x1_i4_o1
+
+SUMLALL_nx_s    11000001 0000 .... . .. ... ..... 101 ..    @azx_1x1_i4_o2
+SUMLALL_nx_s    11000001 0001 .... 0 .. 0.. ....1 10 ...    @azx_2x1_i4_o1
+SUMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 10 ...    @azx_4x1_i4_o1
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2)
 DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2)
 
 #undef DO_VDOT_IDX
+
+#define DO_MLALL(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                               \
+    intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW);       \
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2);         \
+    TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm;       \
+    for (intptr_t i = 0; i < elements; ++i) {                   \
+        TYPEW nn = n[HN(i * 4 + sel)];                          \
+        TYPEM mm = m[HN(i * 4 + sel)];                          \
+        d[HW(i)] = a[HW(i)] OP (nn * mm);                       \
+    }                                                           \
+}
+
+DO_MLALL(sme2_smlall_s, int32_t, int8_t, int8_t, H4, H1, +)
+DO_MLALL(sme2_smlall_d, int64_t, int16_t, int16_t, H8, H2, +)
+DO_MLALL(sme2_smlsll_s, int32_t, int8_t, int8_t, H4, H1, -)
+DO_MLALL(sme2_smlsll_d, int64_t, int16_t, int16_t, H8, H2, -)
+
+DO_MLALL(sme2_umlall_s, uint32_t, uint8_t, uint8_t, H4, H1, +)
+DO_MLALL(sme2_umlall_d, uint64_t, uint16_t, uint16_t, H8, H2, +)
+DO_MLALL(sme2_umlsll_s, uint32_t, uint8_t, uint8_t, H4, H1, -)
+DO_MLALL(sme2_umlsll_d, uint64_t, uint16_t, uint16_t, H8, H2, -)
+
+DO_MLALL(sme2_usmlall_s, uint32_t, uint8_t, int8_t, H4, H1, +)
+
+#undef DO_MLALL
+
+#define DO_MLALL_IDX(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                               \
+    intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW);       \
+    intptr_t eltspersegment = 16 / sizeof(TYPEW);               \
+    intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2);         \
+    intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 4);     \
+    TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm;       \
+    for (intptr_t i = 0; i < elements; i += eltspersegment) {   \
+        TYPEW mm = m[HN(i * 4 + idx)];                          \
+        for (intptr_t j = 0; j < eltspersegment; ++j) {         \
+            TYPEN nn = n[HN((i + j) * 4 + sel)];                \
+            d[HW(i + j)] = a[HW(i + j)] OP (nn * mm);           \
+        }                                                       \
+    }                                                           \
+}
+
+DO_MLALL_IDX(sme2_smlall_idx_s, int32_t, int8_t, int8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_smlall_idx_d, int64_t, int16_t, int16_t, H8, H2, +)
+DO_MLALL_IDX(sme2_smlsll_idx_s, int32_t, int8_t, int8_t, H4, H1, -)
+DO_MLALL_IDX(sme2_smlsll_idx_d, int64_t, int16_t, int16_t, H8, H2, -)
+
+DO_MLALL_IDX(sme2_umlall_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_umlall_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, +)
+DO_MLALL_IDX(sme2_umlsll_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, -)
+DO_MLALL_IDX(sme2_umlsll_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, -)
+
+DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +)
+
+#undef DO_MLALL_IDX
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h)
 
 TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b)
 TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b)
+
+static bool do_smlal(DisasContext *s, arg_azz_n *a, bool multi,
+                     gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                      0, 0, multi, fn);
+}
+
+TRANS_FEAT(SMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlal_zzzw_s)
+TRANS_FEAT(SMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlsl_zzzw_s)
+TRANS_FEAT(UMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlal_zzzw_s)
+TRANS_FEAT(UMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlsl_zzzw_s)
+
+TRANS_FEAT(SMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlal_zzzw_s)
+TRANS_FEAT(SMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlsl_zzzw_s)
+TRANS_FEAT(UMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlal_zzzw_s)
+TRANS_FEAT(UMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlsl_zzzw_s)
+
+static bool do_smlal_nx(DisasContext *s, arg_azx_n *a,
+                         gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+                      a->idx << 1, 0, false, fn);
+}
+
+TRANS_FEAT(SMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlal_idx_s)
+TRANS_FEAT(SMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlsl_idx_s)
+TRANS_FEAT(UMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlal_idx_s)
+TRANS_FEAT(UMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlsl_idx_s)
+
+static bool do_smlall(DisasContext *s, arg_azz_n *a, bool multi,
+                     gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm,
+                      0, 0, multi, fn);
+}
+
+static void gen_helper_sme2_sumlall_s(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m,
+                                      TCGv_ptr a, TCGv_i32 desc)
+{
+    gen_helper_sme2_usmlall_s(d, m, n, a, desc);
+}
+
+TRANS_FEAT(SMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlall_s)
+TRANS_FEAT(SMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlsll_s)
+TRANS_FEAT(UMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlall_s)
+TRANS_FEAT(UMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlsll_s)
+TRANS_FEAT(USMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_usmlall_s)
+TRANS_FEAT(SUMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_sumlall_s)
+
+TRANS_FEAT(SMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlall_d)
+TRANS_FEAT(SMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlsll_d)
+TRANS_FEAT(UMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlall_d)
+TRANS_FEAT(UMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlsll_d)
+
+TRANS_FEAT(SMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlall_s)
+TRANS_FEAT(SMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlsll_s)
+TRANS_FEAT(UMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlall_s)
+TRANS_FEAT(UMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlsll_s)
+TRANS_FEAT(USMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_usmlall_s)
+
+TRANS_FEAT(SMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlall_d)
+TRANS_FEAT(SMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlsll_d)
+TRANS_FEAT(UMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlall_d)
+TRANS_FEAT(UMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlsll_d)
+
+static bool do_smlall_nx(DisasContext *s, arg_azx_n *a,
+                        gen_helper_gvec_4 *fn)
+{
+    return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm,
+                      a->idx << 2, 0, false, fn);
+}
+
+TRANS_FEAT(SMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlall_idx_s)
+TRANS_FEAT(SMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_s)
+TRANS_FEAT(UMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlall_idx_s)
+TRANS_FEAT(UMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_s)
+TRANS_FEAT(USMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_usmlall_idx_s)
+TRANS_FEAT(SUMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_sumlall_idx_s)
+
+TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlall_idx_d)
+TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d)
+TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d)
+TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d)
-- 
2.43.0

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

Emphasize the non-fused nature of these multiply-add.
Matches other helpers such as gvec_rsqrts_nf_[hs].

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-48-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h         | 8 ++++----
 target/arm/tcg/translate-neon.c | 4 ++--
 target/arm/tcg/vec_helper.c     | 8 ++++----
 3 files changed, 10 insertions(+), 10 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: 20250704142112.1018902-49-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 48 +++++++++++++++++
 target/arm/tcg/translate-sme.c | 95 ++++++++++++++++++++++++++++++++++
 2 files changed, 143 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ USMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=4
 SUMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=2
 SUMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=4
 
+FMLA_n1_h       11000001 001 0 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=2
+FMLA_n1_s       11000001 001 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
+FMLA_n1_d       11000001 011 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
+FMLA_n1_h       11000001 001 1 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=4
+FMLA_n1_s       11000001 001 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
+FMLA_n1_d       11000001 011 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
+
+FMLS_n1_h       11000001 001 0 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=2
+FMLS_n1_s       11000001 001 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
+FMLS_n1_d       11000001 011 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
+FMLS_n1_h       11000001 001 1 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=4
+FMLS_n1_s       11000001 001 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
+FMLS_n1_d       11000001 011 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
+
 ### SME2 Multi-vector Multiple Array Vectors
 
 %zn_ax2         6:4 !function=times_2
@@ -XXX,XX +XXX,XX @@ UMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
 USMLALL_nn_s    11000001 101 ....0 0 .. 000 ....0 0010 .    @azz_2x2_o1x4
 USMLALL_nn_s    11000001 101 ...01 0 .. 000 ...00 0010 .    @azz_4x4_o1x4
 
+FMLA_nn_h       11000001 101 ....0 0 .. 100 ....0 01 ...    @azz_2x2_o3
+FMLA_nn_s       11000001 101 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
+FMLA_nn_d       11000001 111 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
+FMLA_nn_h       11000001 101 ...01 0 .. 100 ...00 01 ...    @azz_4x4_o3
+FMLA_nn_s       11000001 101 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
+FMLA_nn_d       11000001 111 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
+
+FMLS_nn_h       11000001 101 ....0 0 .. 100 ....0 11 ...    @azz_2x2_o3
+FMLS_nn_s       11000001 101 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
+FMLS_nn_d       11000001 111 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
+FMLS_nn_h       11000001 101 ...01 0 .. 100 ...00 11 ...    @azz_4x4_o3
+FMLS_nn_s       11000001 101 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
+FMLS_nn_d       11000001 111 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
+
 ### SME2 Multi-vector Indexed
 
 &azx_n          n off rv zn zm idx
@@ -XXX,XX +XXX,XX @@ USMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 00 ...    @azx_4x1_i4_o1
 SUMLALL_nx_s    11000001 0000 .... . .. ... ..... 101 ..    @azx_1x1_i4_o2
 SUMLALL_nx_s    11000001 0001 .... 0 .. 0.. ....1 10 ...    @azx_2x1_i4_o1
 SUMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 10 ...    @azx_4x1_i4_o1
+
+%idx3_10_3      10:2 3:1
+@azx_2x1_i3_o3  ........ .... zm:4 . .. ... ..... .. off:3  \
+                &azx_n n=2 rv=%mova_rv zn=%zn_ax2 idx=%idx3_10_3
+@azx_4x1_i3_o3  ........ .... zm:4 . .. ... ..... .. off:3  \
+                &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3
+
+FMLA_nx_h       11000001 0001 .... 0 .. 1.. ....0 0 ....    @azx_2x1_i3_o3
+FMLA_nx_s       11000001 0101 .... 0 .. 0.. ....0 00 ...    @azx_2x1_i2_o3
+FMLA_nx_d       11000001 1101 .... 0 .. 00. ....0 00 ...    @azx_2x1_i1_o3
+FMLA_nx_h       11000001 0001 .... 1 .. 1.. ...00 0 ....    @azx_4x1_i3_o3
+FMLA_nx_s       11000001 0101 .... 1 .. 0.. ...00 00 ...    @azx_4x1_i2_o3
+FMLA_nx_d       11000001 1101 .... 1 .. 00. ...00 00 ...    @azx_4x1_i1_o3
+
+FMLS_nx_h       11000001 0001 .... 0 .. 1.. ....0 1 ....    @azx_2x1_i3_o3
+FMLS_nx_s       11000001 0101 .... 0 .. 0.. ....0 10 ...    @azx_2x1_i2_o3
+FMLS_nx_d       11000001 1101 .... 0 .. 00. ....0 10 ...    @azx_2x1_i1_o3
+FMLS_nx_h       11000001 0001 .... 1 .. 1.. ...00 1 ....    @azx_4x1_i3_o3
+FMLS_nx_s       11000001 0101 .... 1 .. 0.. ...00 10 ...    @azx_4x1_i2_o3
+FMLS_nx_d       11000001 1101 .... 1 .. 00. ...00 10 ...    @azx_4x1_i1_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub
  */
 #define FPST_ENV  -1
 
+static bool do_azz_fp(DisasContext *s, int nreg, int nsel,
+                      int rv, int off, int zn, int zm,
+                      int data, int shsel, bool multi, int fpst,
+                      gen_helper_gvec_3_ptr *fn)
+{
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / nreg;
+        TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+        TCGv_ptr t, ptr;
+
+        if (fpst >= 0) {
+            ptr = fpstatus_ptr(fpst);
+        } else {
+            ptr = tcg_env;
+        }
+        t = tcg_temp_new_ptr();
+
+        for (int r = 0; r < nreg; ++r) {
+            TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+            TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+            for (int i = 0; i < nsel; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                int desc = simd_desc(svl, svl, data | (i << shsel));
+
+                tcg_gen_addi_ptr(t, t_za, o_za);
+                fn(t, t_zn, t_zm, ptr, tcg_constant_i32(desc));
+            }
+
+            /*
+             * For multiple-and-single vectors, Zn may wrap.
+             * For multiple vectors, both Zn and Zm are aligned.
+             */
+            zn = (zn + 1) % 32;
+            zm += multi;
+        }
+    }
+    return true;
+}
+
 static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel,
                           int rv, int off, int zn, int zm,
                           int data, int shsel, bool multi, int fpst,
@@ -XXX,XX +XXX,XX @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
 TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
 TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
 
+static bool do_fmla(DisasContext *s, arg_azz_n *a, bool multi,
+                    ARMFPStatusFlavour fpst, gen_helper_gvec_3_ptr *fn)
+{
+    return do_azz_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                     0, 0, multi, fpst, fn);
+}
+
+TRANS_FEAT(FMLA_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16,
+           gen_helper_gvec_vfma_h)
+TRANS_FEAT(FMLS_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h)
+TRANS_FEAT(FMLA_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16,
+           gen_helper_gvec_vfma_h)
+TRANS_FEAT(FMLS_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h)
+
+TRANS_FEAT(FMLA_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA,
+           gen_helper_gvec_vfma_s)
+TRANS_FEAT(FMLS_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s)
+TRANS_FEAT(FMLA_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA,
+           gen_helper_gvec_vfma_s)
+TRANS_FEAT(FMLS_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s)
+
+TRANS_FEAT(FMLA_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA,
+           gen_helper_gvec_vfma_d)
+TRANS_FEAT(FMLS_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
+           gen_helper_gvec_vfma_d)
+TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+
+static bool do_fmla_nx(DisasContext *s, arg_azx_n *a,
+                       ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn)
+{
+    return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+                         a->idx, 0, false, fpst, fn);
+}
+
+TRANS_FEAT(FMLA_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16,
+           gen_helper_gvec_fmla_idx_h)
+TRANS_FEAT(FMLS_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16,
+           s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_h : gen_helper_gvec_fmls_idx_h)
+TRANS_FEAT(FMLA_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA,
+           gen_helper_gvec_fmla_idx_s)
+TRANS_FEAT(FMLS_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_s : gen_helper_gvec_fmls_idx_s)
+TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
+           gen_helper_gvec_fmla_idx_d)
+TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d)
+
 /*
  * Expand array multi-vector single (n1), array multi-vector (nn),
  * and array multi-vector indexed (nx), for integer accumulate.
-- 
2.43.0

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: 20250704142112.1018902-50-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        |  9 +++++++++
 target/arm/tcg/sme.decode      | 18 ++++++++++++++++++
 target/arm/tcg/translate-sme.c | 14 ++++++++++++++
 target/arm/tcg/vec_helper.c    | 26 ++++++++++++++++++++++++++
 4 files changed, 67 insertions(+)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i
 DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_ah_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, fpst, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmla_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_6(gvec_fmls_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmls_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_fmls_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmls_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmls_idx, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, fpst, i32)
 
 DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ USMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 0010 .   @azz_nx1_o1x4 n=4
 SUMLALL_n1_s    11000001 001 0 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=2
 SUMLALL_n1_s    11000001 001 1 .... 0 .. 000 ..... 1010 .   @azz_nx1_o1x4 n=4
 
+BFMLA_n1        11000001 011 0 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=2
 FMLA_n1_h       11000001 001 0 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=2
 FMLA_n1_s       11000001 001 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
 FMLA_n1_d       11000001 011 0 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=2
+
+BFMLA_n1        11000001 011 1 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=4
 FMLA_n1_h       11000001 001 1 .... 0 .. 111 ..... 00 ...   @azz_nx1_o3 n=4
 FMLA_n1_s       11000001 001 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
 FMLA_n1_d       11000001 011 1 .... 0 .. 110 ..... 00 ...   @azz_nx1_o3 n=4
 
+BFMLS_n1        11000001 011 0 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=2
 FMLS_n1_h       11000001 001 0 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=2
 FMLS_n1_s       11000001 001 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
 FMLS_n1_d       11000001 011 0 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=2
+
+BFMLS_n1        11000001 011 1 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=4
 FMLS_n1_h       11000001 001 1 .... 0 .. 111 ..... 01 ...   @azz_nx1_o3 n=4
 FMLS_n1_s       11000001 001 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
 FMLS_n1_d       11000001 011 1 .... 0 .. 110 ..... 01 ...   @azz_nx1_o3 n=4
@@ -XXX,XX +XXX,XX @@ UMLSLL_nn_d     11000001 111 ...01 0 .. 000 ...00 1100 .    @azz_4x4_o1x4
 USMLALL_nn_s    11000001 101 ....0 0 .. 000 ....0 0010 .    @azz_2x2_o1x4
 USMLALL_nn_s    11000001 101 ...01 0 .. 000 ...00 0010 .    @azz_4x4_o1x4
 
+BFMLA_nn        11000001 111 ....0 0 .. 100 ....0 01 ...    @azz_2x2_o3
 FMLA_nn_h       11000001 101 ....0 0 .. 100 ....0 01 ...    @azz_2x2_o3
 FMLA_nn_s       11000001 101 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
 FMLA_nn_d       11000001 111 ....0 0 .. 110 ....0 00 ...    @azz_2x2_o3
+
+BFMLA_nn        11000001 111 ...01 0 .. 100 ...00 01 ...    @azz_4x4_o3
 FMLA_nn_h       11000001 101 ...01 0 .. 100 ...00 01 ...    @azz_4x4_o3
 FMLA_nn_s       11000001 101 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
 FMLA_nn_d       11000001 111 ...01 0 .. 110 ...00 00 ...    @azz_4x4_o3
 
+BFMLS_nn        11000001 111 ....0 0 .. 100 ....0 11 ...    @azz_2x2_o3
 FMLS_nn_h       11000001 101 ....0 0 .. 100 ....0 11 ...    @azz_2x2_o3
 FMLS_nn_s       11000001 101 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
 FMLS_nn_d       11000001 111 ....0 0 .. 110 ....0 01 ...    @azz_2x2_o3
+
+BFMLS_nn        11000001 111 ...01 0 .. 100 ...00 11 ...    @azz_4x4_o3
 FMLS_nn_h       11000001 101 ...01 0 .. 100 ...00 11 ...    @azz_4x4_o3
 FMLS_nn_s       11000001 101 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
 FMLS_nn_d       11000001 111 ...01 0 .. 110 ...00 01 ...    @azz_4x4_o3
@@ -XXX,XX +XXX,XX @@ SUMLALL_nx_s    11000001 0001 .... 1 .. 0.. ...01 10 ...    @azx_4x1_i4_o1
 @azx_4x1_i3_o3  ........ .... zm:4 . .. ... ..... .. off:3  \
                 &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3
 
+BFMLA_nx        11000001 0001 .... 0 .. 1.. ....1 0 ....    @azx_2x1_i3_o3
 FMLA_nx_h       11000001 0001 .... 0 .. 1.. ....0 0 ....    @azx_2x1_i3_o3
 FMLA_nx_s       11000001 0101 .... 0 .. 0.. ....0 00 ...    @azx_2x1_i2_o3
 FMLA_nx_d       11000001 1101 .... 0 .. 00. ....0 00 ...    @azx_2x1_i1_o3
+
+BFMLA_nx        11000001 0001 .... 1 .. 1.. ...01 0 ....    @azx_4x1_i3_o3
 FMLA_nx_h       11000001 0001 .... 1 .. 1.. ...00 0 ....    @azx_4x1_i3_o3
 FMLA_nx_s       11000001 0101 .... 1 .. 0.. ...00 00 ...    @azx_4x1_i2_o3
 FMLA_nx_d       11000001 1101 .... 1 .. 00. ...00 00 ...    @azx_4x1_i1_o3
 
+BFMLS_nx        11000001 0001 .... 0 .. 1.. ....1 1 ....    @azx_2x1_i3_o3
 FMLS_nx_h       11000001 0001 .... 0 .. 1.. ....0 1 ....    @azx_2x1_i3_o3
 FMLS_nx_s       11000001 0101 .... 0 .. 0.. ....0 10 ...    @azx_2x1_i2_o3
 FMLS_nx_d       11000001 1101 .... 0 .. 00. ....0 10 ...    @azx_2x1_i1_o3
+
+BFMLS_nx        11000001 0001 .... 1 .. 1.. ...01 1 ....    @azx_4x1_i3_o3
 FMLS_nx_h       11000001 0001 .... 1 .. 1.. ...00 1 ....    @azx_4x1_i3_o3
 FMLS_nx_s       11000001 0101 .... 1 .. 0.. ...00 10 ...    @azx_4x1_i2_o3
 FMLS_nx_d       11000001 1101 .... 1 .. 00. ...00 10 ...    @azx_4x1_i1_o3
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
 TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
            s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
 
+TRANS_FEAT(BFMLA_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA,
+           gen_helper_gvec_bfmla)
+TRANS_FEAT(BFMLS_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls)
+TRANS_FEAT(BFMLA_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA,
+           gen_helper_gvec_bfmla)
+TRANS_FEAT(BFMLS_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls)
+
 static bool do_fmla_nx(DisasContext *s, arg_azx_n *a,
                        ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn)
 {
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
 TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
            s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d)
 
+TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
+           gen_helper_gvec_bfmla_idx)
+TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
+           s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx)
+
 /*
  * Expand array multi-vector single (n1), array multi-vector (nn),
  * and array multi-vector indexed (nx), for integer accumulate.
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2,
     return float16_muladd(op1, op2, dest, 0, stat);
 }
 
+static bfloat16 bfloat16_muladd_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+                                  float_status *stat)
+{
+    return bfloat16_muladd(op1, op2, dest, 0, stat);
+}
+
 static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2,
                                  float_status *stat)
 {
@@ -XXX,XX +XXX,XX @@ static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2,
     return float16_muladd(float16_chs(op1), op2, dest, 0, stat);
 }
 
+static bfloat16 bfloat16_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+                                  float_status *stat)
+{
+    return bfloat16_muladd(bfloat16_chs(op1), op2, dest, 0, stat);
+}
+
 static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2,
                                  float_status *stat)
 {
@@ -XXX,XX +XXX,XX @@ static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2,
     return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
 }
 
+static bfloat16 bfloat16_ah_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+                                     float_status *stat)
+{
+    return bfloat16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
+}
+
 static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2,
                                  float_status *stat)
 {
@@ -XXX,XX +XXX,XX @@ DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32)
 DO_MULADD(gvec_vfma_h, float16_muladd_f, float16)
 DO_MULADD(gvec_vfma_s, float32_muladd_f, float32)
 DO_MULADD(gvec_vfma_d, float64_muladd_f, float64)
+DO_MULADD(gvec_bfmla, bfloat16_muladd_f, bfloat16)
 
 DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
 DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
 DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64)
+DO_MULADD(gvec_bfmls, bfloat16_mulsub_f, bfloat16)
 
 DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16)
 DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32)
 DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64)
+DO_MULADD(gvec_ah_bfmls, bfloat16_ah_mulsub_f, bfloat16)
+
+#undef DO_MULADD
 
 /* For the indexed ops, SVE applies the index per 128-bit vector segment.
  * For AdvSIMD, there is of course only one such vector segment.
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va,                  \
 DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2, 0, 0)
 DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4, 0, 0)
 DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8, 0, 0)
+DO_FMLA_IDX(gvec_bfmla_idx, bfloat16, H2, 0, 0)
 
 DO_FMLA_IDX(gvec_fmls_idx_h, float16, H2, INT16_MIN, 0)
 DO_FMLA_IDX(gvec_fmls_idx_s, float32, H4, INT32_MIN, 0)
 DO_FMLA_IDX(gvec_fmls_idx_d, float64, H8, INT64_MIN, 0)
+DO_FMLA_IDX(gvec_bfmls_idx, bfloat16, H2, INT16_MIN, 0)
 
 DO_FMLA_IDX(gvec_ah_fmls_idx_h, float16, H2, 0, float_muladd_negate_product)
 DO_FMLA_IDX(gvec_ah_fmls_idx_s, float32, H4, 0, float_muladd_negate_product)
 DO_FMLA_IDX(gvec_ah_fmls_idx_d, float64, H8, 0, float_muladd_negate_product)
+DO_FMLA_IDX(gvec_ah_bfmls_idx, bfloat16, H2, 0, float_muladd_negate_product)
 
 #undef DO_FMLA_IDX
 
-- 
2.43.0

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: 20250704142112.1018902-51-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        |  2 ++
 target/arm/tcg/sme.decode      | 25 +++++++++++++++++++
 target/arm/tcg/translate-sme.c | 44 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    |  2 ++
 4 files changed, 73 insertions(+)

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: 20250704142112.1018902-52-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 12 ++++++++++++
 target/arm/tcg/translate-sme.c | 28 ++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

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: 20250704142112.1018902-53-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  5 +++
 target/arm/tcg/vec_internal.h  |  2 +
 target/arm/tcg/sme.decode      | 12 ++++++
 target/arm/tcg/sme_helper.c    | 74 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/sve_helper.c    |  2 +-
 target/arm/tcg/translate-sme.c | 25 ++++++++++++
 6 files changed, 119 insertions(+), 1 deletion(-)

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: 20250704142112.1018902-54-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  2 ++
 target/arm/tcg/vec_internal.h  |  1 +
 target/arm/tcg/sme.decode      |  5 ++++
 target/arm/tcg/sme_helper.c    | 45 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/sve_helper.c    |  2 +-
 target/arm/tcg/translate-sme.c |  5 ++++
 6 files changed, 59 insertions(+), 1 deletion(-)

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: 20250704142112.1018902-55-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 9 +++++++++
 target/arm/tcg/translate-sme.c | 5 +++++
 2 files changed, 14 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ SUB_aaz_d       11000001 111 000010 .. 111 ...00 11 ...     @az_4x4_o3
                 &zz_n n=1 zn=%zn_ax2
 @zz_2x1         ........ ... ..... ...... zn:5  .....       \
                 &zz_n n=1 zd=%zd_ax2
+@zz_2x2         ........ ... ..... ...... .... . .....      \
+                &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2
+@zz_4x4         ........ ... ..... ...... .... . .....      \
+                &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4
 
 BFCVT           11000001 011 00000 111000 ....0 .....       @zz_1x2
 BFCVTN          11000001 011 00000 111000 ....1 .....       @zz_1x2
@@ -XXX,XX +XXX,XX @@ FCVTN           11000001 001 00000 111000 ....1 .....       @zz_1x2
 
 FCVT_w          11000001 101 00000 111000 ..... ....0       @zz_2x1
 FCVTL           11000001 101 00000 111000 ..... ....1       @zz_2x1
+
+FCVTZS          11000001 001 00001 111000 ....0 ....0       @zz_2x2
+FCVTZS          11000001 001 10001 111000 ...00 ...00       @zz_4x4
+FCVTZU          11000001 001 00001 111000 ....1 ....0       @zz_2x2
+FCVTZU          11000001 001 10001 111000 ...01 ...00       @zz_4x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0,
            FPST_A64_F16, gen_helper_sme2_fcvt_w)
 TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0,
            FPST_A64_F16, gen_helper_sme2_fcvtl)
+
+TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_gvec_vcvt_rz_fs)
+TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0,
+           FPST_A64, gen_helper_gvec_vcvt_rz_fu)
-- 
2.43.0

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: 20250704142112.1018902-56-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  2 ++
 target/arm/tcg/sme.decode      |  5 +++++
 target/arm/tcg/sme_helper.c    | 22 ++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  5 +++++
 4 files changed, 34 insertions(+)

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: 20250704142112.1018902-57-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 9 +++++++++
 target/arm/tcg/translate-sme.c | 9 +++++++++
 2 files changed, 18 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ SCVTF           11000001 001 00010 111000 ....0 ....0       @zz_2x2
 SCVTF           11000001 001 10010 111000 ...00 ...00       @zz_4x4
 UCVTF           11000001 001 00010 111000 ....1 ....0       @zz_2x2
 UCVTF           11000001 001 10010 111000 ...01 ...00       @zz_4x4
+
+FRINTN          11000001 101 01000 111000 ....0 ....0       @zz_2x2
+FRINTN          11000001 101 11000 111000 ...00 ...00       @zz_4x4
+FRINTP          11000001 101 01001 111000 ....0 ....0       @zz_2x2
+FRINTP          11000001 101 11001 111000 ...00 ...00       @zz_4x4
+FRINTM          11000001 101 01010 111000 ....0 ....0       @zz_2x2
+FRINTM          11000001 101 11010 111000 ...00 ...00       @zz_4x4
+FRINTA          11000001 101 01100 111000 ....0 ....0       @zz_2x2
+FRINTA          11000001 101 11100 111000 ...00 ...00       @zz_4x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0,
            FPST_A64, gen_helper_sme2_scvtf)
 TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0,
            FPST_A64, gen_helper_sme2_ucvtf)
+
+TRANS_FEAT(FRINTN, aa64_sme2, do_zz_fpst, a, float_round_nearest_even,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTP, aa64_sme2, do_zz_fpst, a, float_round_up,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away,
+           FPST_A64, gen_helper_gvec_vrint_rm_s)
-- 
2.43.0

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

Inputs are a wider type of indeterminate sign.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-58-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_internal.h | 7 +++++++
 1 file changed, 7 insertions(+)

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

Replace and remove do_sat_bhs.
This avoids multiple repetitions of INT*_MIN/MAX.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-59-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 116 +++++++++++++++---------------------
 1 file changed, 48 insertions(+), 68 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS)
 DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS)
 DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D)
 
-static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max)
-{
-    return val >= max ? max : val <= min ? min : val;
-}
-
-#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX)
-#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX)
-#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX)
+#define DO_SQADD_B(n, m) do_ssat_b((int64_t)n + m)
+#define DO_SQADD_H(n, m) do_ssat_h((int64_t)n + m)
+#define DO_SQADD_S(n, m) do_ssat_s((int64_t)n + m)
 
 static inline int64_t do_sqadd_d(int64_t n, int64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H)
 DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S)
 DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d)
 
-#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX)
-#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX)
-#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX)
+#define DO_UQADD_B(n, m) do_usat_b((int64_t)n + m)
+#define DO_UQADD_H(n, m) do_usat_h((int64_t)n + m)
+#define DO_UQADD_S(n, m) do_usat_s((int64_t)n + m)
 
 static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H)
 DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S)
 DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d)
 
-#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX)
-#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX)
-#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX)
+#define DO_SQSUB_B(n, m) do_ssat_b((int64_t)n - m)
+#define DO_SQSUB_H(n, m) do_ssat_h((int64_t)n - m)
+#define DO_SQSUB_S(n, m) do_ssat_s((int64_t)n - m)
 
 static inline int64_t do_sqsub_d(int64_t n, int64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H)
 DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S)
 DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d)
 
-#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX)
-#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX)
-#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX)
+#define DO_UQSUB_B(n, m) do_usat_b((int64_t)n - m)
+#define DO_UQSUB_H(n, m) do_usat_h((int64_t)n - m)
+#define DO_UQSUB_S(n, m) do_usat_s((int64_t)n - m)
 
 static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H)
 DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S)
 DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d)
 
-#define DO_SUQADD_B(n, m) \
-    do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX)
-#define DO_SUQADD_H(n, m) \
-    do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX)
-#define DO_SUQADD_S(n, m) \
-    do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX)
+#define DO_SUQADD_B(n, m) do_ssat_b((int64_t)(int8_t)n + m)
+#define DO_SUQADD_H(n, m) do_ssat_h((int64_t)(int16_t)n + m)
+#define DO_SUQADD_S(n, m) do_ssat_s((int64_t)(int32_t)n + m)
 
 static inline int64_t do_suqadd_d(int64_t n, uint64_t m)
 {
@@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H)
 DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S)
 DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d)
 
-#define DO_USQADD_B(n, m) \
-    do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX)
-#define DO_USQADD_H(n, m) \
-    do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX)
-#define DO_USQADD_S(n, m) \
-    do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX)
+#define DO_USQADD_B(n, m) do_usat_b((int64_t)n + (int8_t)m)
+#define DO_USQADD_H(n, m) do_usat_h((int64_t)n + (int16_t)m)
+#define DO_USQADD_S(n, m) do_usat_s((int64_t)n + (int32_t)m)
 
 static inline uint64_t do_usqadd_d(uint64_t n, int64_t m)
 {
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, uint32_t desc)                    \
     }                                                                   \
 }
 
-#define DO_SQXTN_H(n)  do_sat_bhs(n, INT8_MIN, INT8_MAX)
-#define DO_SQXTN_S(n)  do_sat_bhs(n, INT16_MIN, INT16_MAX)
-#define DO_SQXTN_D(n)  do_sat_bhs(n, INT32_MIN, INT32_MAX)
+DO_XTNB(sve2_sqxtnb_h, int16_t, do_ssat_b)
+DO_XTNB(sve2_sqxtnb_s, int32_t, do_ssat_h)
+DO_XTNB(sve2_sqxtnb_d, int64_t, do_ssat_s)
 
-DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H)
-DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S)
-DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D)
+DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, do_ssat_b)
+DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, do_ssat_h)
+DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, do_ssat_s)
 
-DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H)
-DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S)
-DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D)
+DO_XTNB(sve2_uqxtnb_h, uint16_t, do_usat_b)
+DO_XTNB(sve2_uqxtnb_s, uint32_t, do_usat_h)
+DO_XTNB(sve2_uqxtnb_d, uint64_t, do_usat_s)
 
-#define DO_UQXTN_H(n)  do_sat_bhs(n, 0, UINT8_MAX)
-#define DO_UQXTN_S(n)  do_sat_bhs(n, 0, UINT16_MAX)
-#define DO_UQXTN_D(n)  do_sat_bhs(n, 0, UINT32_MAX)
+DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, do_usat_b)
+DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, do_usat_h)
+DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, do_usat_s)
 
-DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H)
-DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S)
-DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D)
+DO_XTNB(sve2_sqxtunb_h, int16_t, do_usat_b)
+DO_XTNB(sve2_sqxtunb_s, int32_t, do_usat_h)
+DO_XTNB(sve2_sqxtunb_d, int64_t, do_usat_s)
 
-DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H)
-DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S)
-DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D)
-
-DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H)
-DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S)
-DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D)
-
-DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H)
-DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S)
-DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D)
+DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, do_usat_b)
+DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, do_usat_h)
+DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, do_usat_s)
 
 #undef DO_XTNB
 #undef DO_XTNT
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr)
 DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr)
 DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, H1_8, H1_4, do_urshr)
 
-#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX)
-#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX)
-#define DO_SQSHRUN_D(x, sh) \
-    do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX)
+#define DO_SQSHRUN_H(x, sh) do_usat_b((int64_t)(x) >> sh)
+#define DO_SQSHRUN_S(x, sh) do_usat_h((int64_t)(x) >> sh)
+#define DO_SQSHRUN_D(x, sh) do_usat_s((int64_t)(x) >> (sh < 64 ? sh : 63))
 
 DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H)
 DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S)
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H)
 DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S)
 DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRUN_D)
 
-#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX)
-#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX)
-#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX)
+#define DO_SQRSHRUN_H(x, sh) do_usat_b(do_srshr(x, sh))
+#define DO_SQRSHRUN_S(x, sh) do_usat_h(do_srshr(x, sh))
+#define DO_SQRSHRUN_D(x, sh) do_usat_s(do_srshr(x, sh))
 
 DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H)
 DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S)
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H)
 DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S)
 DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQRSHRUN_D)
 
-#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX)
-#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX)
-#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX)
+#define DO_SQSHRN_H(x, sh) do_ssat_b(x >> sh)
+#define DO_SQSHRN_S(x, sh) do_ssat_h(x >> sh)
+#define DO_SQSHRN_D(x, sh) do_ssat_s(x >> sh)
 
 DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H)
 DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S)
@@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H)
 DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S)
 DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRN_D)
 
-#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX)
-#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX)
-#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX)
+#define DO_SQRSHRN_H(x, sh) do_ssat_b(do_srshr(x, sh))
+#define DO_SQRSHRN_S(x, sh) do_ssat_h(do_srshr(x, sh))
+#define DO_SQRSHRN_D(x, sh) do_ssat_s(do_srshr(x, sh))
 
 DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H)
 DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S)
-- 
2.43.0

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-60-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  20 ++++++
 target/arm/tcg/sme.decode      |  22 +++++++
 target/arm/tcg/sme_helper.c    | 116 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  35 ++++++++++
 4 files changed, 193 insertions(+)

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: 20250704142112.1018902-61-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      | 20 ++++++++++++++++----
 target/arm/tcg/translate-sve.c |  7 +++++++
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@
 # as propagated via the MOVPRFX instruction.
 %reg_movprfx    0:5
 
+%rn_ax2         6:4 !function=times_2
+
 ###########################################################################
 # Named attribute sets.  These are used to make nice(er) names
 # when creating helpers common to those for the individual
@@ -XXX,XX +XXX,XX @@
 # Two operand
 @pd_pn          ........ esz:2 .. .... ....... rn:4 . rd:4      &rr_esz
 @rd_rn          ........ esz:2 ...... ...... rn:5 rd:5          &rr_esz
+@rd_rnx2        ........ ... ..... ...... ..... rd:5            &rr_esz rn=%rn_ax2
 
 # Two operand with governing predicate, flags setting
 @pd_pg_pn_s     ........ . s:1 ...... .. pg:4 . rn:4 . rd:4     &rpr_s
@@ -XXX,XX +XXX,XX @@ UABA            01000101 .. 0 ..... 11111 1 ..... .....  @rd_rn_rm
 #### SVE2 Narrowing
 
 ## SVE2 saturating extract narrow
-
 # Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0.
-SQXTNB          01000101 .. 1 ..... 010 000 ..... .....  @rd_rn_tszimm_shl
+
+{
+  SQCVTN_sh     01000101 00 1 10001 010 000 ....0 .....  @rd_rnx2 esz=1
+  SQXTNB        01000101 .. 1 ..... 010 000 ..... .....  @rd_rn_tszimm_shl
+}
 SQXTNT          01000101 .. 1 ..... 010 001 ..... .....  @rd_rn_tszimm_shl
-UQXTNB          01000101 .. 1 ..... 010 010 ..... .....  @rd_rn_tszimm_shl
+{
+  UQCVTN_sh     01000101 00 1 10001 010 010 ....0 .....  @rd_rnx2 esz=1
+  UQXTNB        01000101 .. 1 ..... 010 010 ..... .....  @rd_rn_tszimm_shl
+}
 UQXTNT          01000101 .. 1 ..... 010 011 ..... .....  @rd_rn_tszimm_shl
-SQXTUNB         01000101 .. 1 ..... 010 100 ..... .....  @rd_rn_tszimm_shl
+{
+  SQCVTUN_sh    01000101 00 1 10001 010 100 ....0 .....  @rd_rnx2 esz=1
+  SQXTUNB       01000101 .. 1 ..... 010 100 ..... .....  @rd_rn_tszimm_shl
+}
 SQXTUNT         01000101 .. 1 ..... 010 101 ..... .....  @rd_rn_tszimm_shl
 
 ## SVE2 bitwise shift right narrow
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_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
 }
 
 TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+
+TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+           gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
+TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+           gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0)
+TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+           gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0)
-- 
2.43.0

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-62-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 13 ++++++++++++
 target/arm/tcg/sme.decode      | 18 ++++++++++++++++
 target/arm/tcg/sme_helper.c    | 38 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 16 ++++++++++++++
 4 files changed, 85 insertions(+)

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: 20250704142112.1018902-63-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 12 ++++++
 target/arm/tcg/sme.decode      | 11 ++++++
 target/arm/tcg/sme_helper.c    | 68 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 39 +++++++++++++++++++
 4 files changed, 130 insertions(+)

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

Unify two copies of these inline functions.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-64-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_internal.h | 21 +++++++++++++++++++++
 target/arm/tcg/mve_helper.c   | 21 ---------------------
 target/arm/tcg/sve_helper.c   | 21 ---------------------
 3 files changed, 21 insertions(+), 42 deletions(-)

diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -XXX,XX +XXX,XX @@ int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool);
 #define do_usat_h(val)  MIN(MAX(val, 0), UINT16_MAX)
 #define do_usat_s(val)  MIN(MAX(val, 0), UINT32_MAX)
 
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
+{
+    if (likely(sh < 64)) {
+        return (x >> sh) + ((x >> (sh - 1)) & 1);
+    } else if (sh == 64) {
+        return x >> 63;
+    } else {
+        return 0;
+    }
+}
+
+static inline int64_t do_srshr(int64_t x, unsigned sh)
+{
+    if (likely(sh < 64)) {
+        return (x >> sh) + ((x >> (sh - 1)) & 1);
+    } else {
+        /* Rounding the sign bit always produces 0. */
+        return 0;
+    }
+}
+
 /**
  * bfdotadd:
  * @sum: addend
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_VSHLL_ALL(vshllt, true)
     DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN)         \
     DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
 
-static inline uint64_t do_urshr(uint64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else if (sh == 64) {
-        return x >> 63;
-    } else {
-        return 0;
-    }
-}
-
-static inline int64_t do_srshr(int64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else {
-        /* Rounding the sign bit always produces 0. */
-        return 0;
-    }
-}
-
 DO_VSHRN_ALL(vshrn, DO_SHR)
 DO_VSHRN_ALL(vrshrn, do_urshr)
 
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc)  \
    when N is negative, add 2**M-1.  */
 #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M)
 
-static inline uint64_t do_urshr(uint64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else if (sh == 64) {
-        return x >> 63;
-    } else {
-        return 0;
-    }
-}
-
-static inline int64_t do_srshr(int64_t x, unsigned sh)
-{
-    if (likely(sh < 64)) {
-        return (x >> sh) + ((x >> (sh - 1)) & 1);
-    } else {
-        /* Rounding the sign bit always produces 0. */
-        return 0;
-    }
-}
-
 DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR)
 DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR)
 DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR)
-- 
2.43.0

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-65-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  20 ++++++
 target/arm/tcg/sme.decode      |  37 ++++++++++
 target/arm/tcg/sme_helper.c    | 120 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  33 +++++++++
 4 files changed, 210 insertions(+)

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: 20250704142112.1018902-66-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 12 +++++++
 target/arm/tcg/sme.decode      | 12 +++++++
 target/arm/tcg/sme_helper.c    | 62 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 40 ++++++++++++++++++++++
 4 files changed, 126 insertions(+)

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: 20250704142112.1018902-67-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 15 +++++++
 target/arm/tcg/sme.decode      | 17 ++++++++
 target/arm/tcg/sme_helper.c    | 56 +++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 75 ++++++++++++++++++++++++++++++++++
 4 files changed, 163 insertions(+)

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

These instructions are present in both SME(1) and SVE2.1 extensions.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-68-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/translate-sve.c | 4 ++--
 1 file changed, 2 insertions(+), 2 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_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
     tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
 }
 
-TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
+TRANS_FEAT(SCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
 
 static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a)
 {
@@ -XXX,XX +XXX,XX @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
     tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
 }
 
-TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
 
 TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
-- 
2.43.0

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

This is the single vector version within SVE decode space.

Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-69-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  2 ++
 target/arm/tcg/translate-sve.c | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ PSEL            00100101 .1 1 000 .. 01 .... 0 .... 0 ....  \
 
 SCLAMP          01000100 .. 0 ..... 110000 ..... .....          @rda_rn_rm
 UCLAMP          01000100 .. 0 ..... 110001 ..... .....          @rda_rn_rm
+
+FCLAMP          01100100 .. 1 ..... 001001 ..... .....          @rda_rn_rm
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_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
 
 TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
 
+static bool trans_FCLAMP(DisasContext *s, arg_FCLAMP *a)
+{
+    static gen_helper_gvec_3_ptr * const fn[] = {
+        gen_helper_sme2_bfclamp,
+        gen_helper_sme2_fclamp_h,
+        gen_helper_sme2_fclamp_s,
+        gen_helper_sme2_fclamp_d,
+    };
+
+    /* This insn uses MO_8 to encode BFloat16. */
+    if (a->esz == MO_8
+        ? !dc_isar_feature(aa64_sve_b16b16, s)
+        : !dc_isar_feature(aa64_sme2_or_sve2p1, s)) {
+        return false;
+    }
+
+    /* So far we never optimize rda with MOVPRFX */
+    assert(a->rd == a->ra);
+    return gen_gvec_fpst_zzz(s, fn[a->esz], a->rd, a->rn, a->rm, 1,
+                             a->esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+}
+
 TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
 TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
-- 
2.43.0

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: 20250704142112.1018902-70-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sme.decode      | 23 +++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 20 ++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ UCLAMP          11000001 esz:2 1 zm:5 110001 zn:5 .... 1    \
                 &zzz_en zd=%zd_ax2 n=2
 UCLAMP          11000001 esz:2 1 zm:5 110011 zn:5 ...0 1    \
                 &zzz_en zd=%zd_ax4 n=4
+
+### SME Multiple Zero
+
+&zero_za        rv off ngrp nvec
+
+ZERO_za         11000000 000011 000 .. 0000000000 off:3 \
+                &zero_za ngrp=2 nvec=1 rv=%mova_rv
+ZERO_za         11000000 000011 100 .. 0000000000 off:3 \
+                &zero_za ngrp=4 nvec=1 rv=%mova_rv
+
+ZERO_za         11000000 000011 001 .. 0000000000 ...   \
+                &zero_za ngrp=1 nvec=2 rv=%mova_rv off=%off3_x2
+ZERO_za         11000000 000011 010 .. 0000000000 0..   \
+                &zero_za ngrp=2 nvec=2 rv=%mova_rv off=%off2_x2
+ZERO_za         11000000 000011 011 .. 0000000000 0..   \
+                &zero_za ngrp=4 nvec=2 rv=%mova_rv off=%off2_x2
+
+ZERO_za         11000000 000011 101 .. 0000000000 0..   \
+                &zero_za ngrp=1 nvec=4 rv=%mova_rv off=%off2_x4
+ZERO_za         11000000 000011 110 .. 0000000000 00.   \
+                &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
+ZERO_za         11000000 000011 111 .. 0000000000 00.   \
+                &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
     return true;
 }
 
+static bool trans_ZERO_za(DisasContext *s, arg_ZERO_za *a)
+{
+    if (!dc_isar_feature(aa64_sme2p1, s)) {
+        return false;
+    }
+    if (sme_smza_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / a->ngrp;
+        TCGv_ptr t_za = get_zarray(s, a->rv, a->off, a->ngrp, a->nvec);
+
+        for (int r = 0; r < a->ngrp; ++r) {
+            for (int i = 0; i < a->nvec; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                tcg_gen_gvec_dup_imm_var(MO_64, t_za, o_za, svl, svl, 0);
+            }
+        }
+    }
+    return true;
+}
+
 static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
-- 
2.43.0

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

For WHILE, we have the count of enabled predicates, so we don't
need to search to compute the PredTest result.  Reuse the logic
that will shortly be required for counted predicates.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-71-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 81 +++++++++++++++++++++----------------
 1 file changed, 46 insertions(+), 35 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
     return sum;
 }
 
+/* C.f. Arm pseudocode PredCountTest */
+static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
+{
+    uint32_t flags;
+
+    if (count == 0) {
+        flags = 1;                              /* !N, Z, C */
+    } else if (!invert) {
+        flags = (1u << 31) | 2;                 /* N, !Z */
+        flags |= count != elements;             /* C */
+    } else {
+        flags = 2;                              /* !Z, !C */
+        flags |= (count == elements) << 31;     /* N */
+    }
+    return flags;
+}
+
 uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
 {
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
-    uint32_t flags;
-    intptr_t i;
+    intptr_t i, oprbits = oprsz * 8;
+
+    tcg_debug_assert(count <= oprbits);
 
     /* Begin with a zero predicate register.  */
-    flags = do_zero(d, oprsz);
-    if (count == 0) {
-        return flags;
+    do_zero(d, oprsz);
+    if (count) {
+        /* Set all of the requested bits.  */
+        for (i = 0; i < count / 64; ++i) {
+            d->p[i] = esz_mask;
+        }
+        if (count & 63) {
+            d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
+        }
     }
 
-    /* Set all of the requested bits.  */
-    for (i = 0; i < count / 64; ++i) {
-        d->p[i] = esz_mask;
-    }
-    if (count & 63) {
-        d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
-    }
-
-    return predtest_ones(d, oprsz, esz_mask);
+    return pred_count_test(oprbits, count, false);
 }
 
 uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
-    intptr_t i, invcount, oprbits;
+    intptr_t i, invcount, oprbits = oprsz * 8;
     uint64_t bits;
 
-    if (count == 0) {
-        return do_zero(d, oprsz);
-    }
-
-    oprbits = oprsz * 8;
     tcg_debug_assert(count <= oprbits);
 
-    bits = esz_mask;
-    if (oprbits & 63) {
-        bits &= MAKE_64BIT_MASK(0, oprbits & 63);
-    }
-
-    invcount = oprbits - count;
-    for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
-        d->p[i] = bits;
+    /* Begin with a zero predicate register.  */
+    do_zero(d, oprsz);
+    if (count) {
+        /* Set all of the requested bits.  */
         bits = esz_mask;
+        if (oprbits & 63) {
+            bits &= MAKE_64BIT_MASK(0, oprbits & 63);
+        }
+
+        invcount = oprbits - count;
+        for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
+            d->p[i] = bits;
+            bits = esz_mask;
+        }
+        d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
     }
 
-    d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
-
-    while (--i >= 0) {
-        d->p[i] = 0;
-    }
-
-    return predtest_ones(d, oprsz, esz_mask);
+    return pred_count_test(oprbits, count, true);
 }
 
 /* Recursive reduction on a function;
-- 
2.43.0

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

Merge predtest_ones into its only caller.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-72-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc)
     }
 }
 
-/* As if PredTest(Ones(PL), D, esz).  */
-static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz,
-                              uint64_t esz_mask)
-{
-    uint32_t flags = PREDTEST_INIT;
-    intptr_t i;
-
-    for (i = 0; i < oprsz / 8; i++) {
-        flags = iter_predtest_fwd(d->p[i], esz_mask, flags);
-    }
-    if (oprsz & 7) {
-        uint64_t mask = ~(-1ULL << (8 * (oprsz & 7)));
-        flags = iter_predtest_fwd(d->p[i], esz_mask & mask, flags);
-    }
-    return flags;
-}
-
 uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc)
 {
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     if (last_active_pred(vn, vg, oprsz)) {
-        return predtest_ones(vd, oprsz, -1);
-    } else {
-        return do_zero(vd, oprsz);
+        ARMPredicateReg *d = vd;
+        uint32_t flags = PREDTEST_INIT;
+        intptr_t i;
+
+        /* As if PredTest(Ones(PL), D, MO_8).  */
+        for (i = 0; i < oprsz / 8; i++) {
+            flags = iter_predtest_fwd(d->p[i], -1, flags);
+        }
+        if (oprsz & 7) {
+            uint64_t mask = ~(-1ULL << (8 * (oprsz & 7)));
+            flags = iter_predtest_fwd(d->p[i], mask, flags);
+        }
+        return flags;
     }
+    return do_zero(vd, oprsz);
 }
 
 uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
-- 
2.43.0

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

Expand to memset plus the return value, when used.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-73-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ static uint32_t compute_brks_m(uint64_t *d, uint64_t *n, uint64_t *g,
     return flags;
 }
 
-static uint32_t do_zero(ARMPredicateReg *d, intptr_t oprsz)
-{
-    /* It is quicker to zero the whole predicate than loop on OPRSZ.
-     * The compiler should turn this into 4 64-bit integer stores.
-     */
-    memset(d, 0, sizeof(ARMPredicateReg));
-    return PREDTEST_INIT;
-}
-
 void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg,
                        uint32_t pred_desc)
 {
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         compute_brk_z(vd, vm, vg, oprsz, true);
     } else {
-        do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         return compute_brks_z(vd, vm, vg, oprsz, true);
     } else {
-        return do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
+        return PREDTEST_INIT;
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         compute_brk_z(vd, vm, vg, oprsz, false);
     } else {
-        do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg,
     if (last_active_pred(vn, vg, oprsz)) {
         return compute_brks_z(vd, vm, vg, oprsz, false);
     } else {
-        return do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
+        return PREDTEST_INIT;
     }
 }
 
@@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc)
 {
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     if (!last_active_pred(vn, vg, oprsz)) {
-        do_zero(vd, oprsz);
+        memset(vd, 0, sizeof(ARMPredicateReg));
     }
 }
 
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc)
         }
         return flags;
     }
-    return do_zero(vd, oprsz);
+    memset(vd, 0, sizeof(ARMPredicateReg));
+    return PREDTEST_INIT;
 }
 
 uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     tcg_debug_assert(count <= oprbits);
 
     /* Begin with a zero predicate register.  */
-    do_zero(d, oprsz);
+    memset(d, 0, sizeof(*d));
     if (count) {
         /* Set all of the requested bits.  */
         for (i = 0; i < count / 64; ++i) {
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     tcg_debug_assert(count <= oprbits);
 
     /* Begin with a zero predicate register.  */
-    do_zero(d, oprsz);
+    memset(d, 0, sizeof(*d));
     if (count) {
         /* Set all of the requested bits.  */
         bits = esz_mask;
-- 
2.43.0

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: 20250704142112.1018902-74-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
     return flags;
 }
 
-uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
+/* D must be cleared on entry. */
+static void do_whilel(ARMPredicateReg *d, uint64_t esz_mask,
+                      uint32_t count, uint32_t oprbits)
 {
-    intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
-    intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
-    uint64_t esz_mask = pred_esz_masks[esz];
-    ARMPredicateReg *d = vd;
-    intptr_t i, oprbits = oprsz * 8;
-
     tcg_debug_assert(count <= oprbits);
-
-    /* Begin with a zero predicate register.  */
-    memset(d, 0, sizeof(*d));
     if (count) {
+        uint32_t i;
+
         /* Set all of the requested bits.  */
         for (i = 0; i < count / 64; ++i) {
             d->p[i] = esz_mask;
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
             d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
         }
     }
+}
 
+uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+    uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+    uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+    uint32_t oprbits = oprsz * 8;
+    uint64_t esz_mask = pred_esz_masks[esz];
+    ARMPredicateReg *d = vd;
+
+    memset(d, 0, sizeof(*d));
+    do_whilel(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, false);
 }
 
-- 
2.43.0

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20250704142112.1018902-75-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c | 39 +++++++++++++++++++------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     return pred_count_test(oprbits, count, false);
 }
 
-uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
+/* D must be cleared on entry. */
+static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask,
+                      uint32_t count, uint32_t oprbits)
 {
-    intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
-    intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
-    uint64_t esz_mask = pred_esz_masks[esz];
-    ARMPredicateReg *d = vd;
-    intptr_t i, invcount, oprbits = oprsz * 8;
-    uint64_t bits;
-
     tcg_debug_assert(count <= oprbits);
-
-    /* Begin with a zero predicate register.  */
-    memset(d, 0, sizeof(*d));
     if (count) {
-        /* Set all of the requested bits.  */
-        bits = esz_mask;
-        if (oprbits & 63) {
-            bits &= MAKE_64BIT_MASK(0, oprbits & 63);
-        }
+        uint32_t i, invcount = oprbits - count;
+        uint64_t bits = esz_mask & MAKE_64BIT_MASK(invcount & 63, 64);
 
-        invcount = oprbits - count;
-        for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
+        for (i = invcount / 64; i < oprbits / 64; ++i) {
             d->p[i] = bits;
             bits = esz_mask;
         }
-        d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
+        if (oprbits & 63) {
+            d->p[i] = bits & MAKE_64BIT_MASK(0, oprbits & 63);
+        }
     }
+}
 
+uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+    uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+    uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+    uint32_t oprbits = oprsz * 8;
+    uint64_t esz_mask = pred_esz_masks[esz];
+    ARMPredicateReg *d = vd;
+
+    memset(d, 0, sizeof(*d));
+    do_whileg(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, true);
 }
 
-- 
2.43.0

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

Change the API to pass element count rather than bit count.
This will be helpful later for predicate as counter.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-76-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_helper.c    |  2 ++
 target/arm/tcg/translate-sve.c | 13 +++++--------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
 
+    count <<= esz;
     memset(d, 0, sizeof(*d));
     do_whilel(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, false);
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
 
+    count <<= esz;
     memset(d, 0, sizeof(*d));
     do_whileg(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, true);
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 bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     t2 = tcg_temp_new_i32();
     tcg_gen_extrl_i64_i32(t2, t0);
 
-    /* Scale elements to bits.  */
-    tcg_gen_shli_i32(t2, t2, a->esz);
-
     desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8);
     desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
 
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
     op0 = read_cpu_reg(s, a->rn, 1);
     op1 = read_cpu_reg(s, a->rm, 1);
 
-    tmax = tcg_constant_i64(vsz);
+    tmax = tcg_constant_i64(vsz >> a->esz);
     diff = tcg_temp_new_i64();
 
     if (a->rw) {
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
         tcg_gen_sub_i64(diff, op0, op1);
         tcg_gen_sub_i64(t1, op1, op0);
         tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1);
-        /* Round down to a multiple of ESIZE.  */
-        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* Divide, rounding down, by ESIZE.  */
+        tcg_gen_shri_i64(diff, diff, a->esz);
         /* If op1 == op0, diff == 0, and the condition is always true. */
         tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff);
     } else {
         /* WHILEWR */
         tcg_gen_sub_i64(diff, op1, op0);
-        /* Round down to a multiple of ESIZE.  */
-        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* Divide, rounding down, by ESIZE.  */
+        tcg_gen_shri_i64(diff, diff, a->esz);
         /* If op0 >= op1, diff <= 0, the condition is always true. */
         tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff);
     }
-- 
2.43.0

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

Use TRANS_FEAT to select the correct predicate.
Pass the helper and a boolean to do_WHILE.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-77-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  4 +++-
 target/arm/tcg/translate-sve.c | 23 +++++++++--------------
 2 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SINCDECP_z      00100101 .. 1010 d:1 u:1 10000 00 .... .....    @incdec2_pred
 CTERM           00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000
 
 # SVE integer compare scalar count and limit
-WHILE           00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4
+&while          esz rd rn rm sf u eq
+WHILE_lt        00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4  &while
+WHILE_gt        00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4  &while
 
 # SVE2 pointer conflict compare
 WHILE_ptr       00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
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 bool trans_CTERM(DisasContext *s, arg_CTERM *a)
     return true;
 }
 
-static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
+typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
+static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
 {
     TCGv_i64 op0, op1, t0, t1, tmax;
     TCGv_i32 t2;
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     TCGCond cond;
     uint64_t maxval;
     /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */
-    bool eq = a->eq == a->lt;
+    bool eq = a->eq == lt;
 
-    /* The greater-than conditions are all SVE2. */
-    if (a->lt
-        ? !dc_isar_feature(aa64_sve, s)
-        : !dc_isar_feature(aa64_sve2, s)) {
-        return false;
-    }
     if (!sve_access_check(s)) {
         return true;
     }
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     t0 = tcg_temp_new_i64();
     t1 = tcg_temp_new_i64();
 
-    if (a->lt) {
+    if (lt) {
         tcg_gen_sub_i64(t0, op1, op0);
         if (a->u) {
             maxval = a->sf ? UINT64_MAX : UINT32_MAX;
@@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     ptr = tcg_temp_new_ptr();
     tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd));
 
-    if (a->lt) {
-        gen_helper_sve_whilel(t2, ptr, t2, tcg_constant_i32(desc));
-    } else {
-        gen_helper_sve_whileg(t2, ptr, t2, tcg_constant_i32(desc));
-    }
+    fn(t2, ptr, t2, tcg_constant_i32(desc));
+
     do_pred_flags(t2);
     return true;
 }
 
+TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel)
+TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg)
+
 static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
 {
     TCGv_i64 op0, op1, diff, t1, tmax;
-- 
2.43.0

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: 20250704142112.1018902-79-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  3 +++
 target/arm/tcg/sve.decode      |  8 +++++++
 target/arm/tcg/sve_helper.c    | 40 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 14 ++++++++----
 4 files changed, 61 insertions(+), 4 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: 20250704142112.1018902-80-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  3 ++
 target/arm/tcg/sve.decode      | 11 +++++++
 target/arm/tcg/sve_helper.c    | 53 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 22 ++++++++++----
 4 files changed, 84 insertions(+), 5 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: 20250704142112.1018902-81-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  1 +
 target/arm/tcg/translate-sve.c | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ PTEST           00100101 01 010000 11 pg:4 0 rn:4 0 0000
 
 # SVE predicate initialize
 PTRUE           00100101 esz:2 01100 s:1 111000 pat:5 0 rd:4
+PTRUE_cnt       00100101 esz:2 1000000111100000010 ...          rd=%pnd
 
 # SVE initialize FFR
 SETFFR          00100101 0010 1100 1001 0000 0000 0000
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 bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag)
 
 TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s)
 
+static bool trans_PTRUE_cnt(DisasContext *s, arg_PTRUE_cnt *a)
+{
+    if (!dc_isar_feature(aa64_sme2_or_sve2p1, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        /* Canonical TRUE is 0 count, invert bit, plus element size. */
+        int val = (1 << 15) | (1 << a->esz);
+
+        /* Write val to the first uint64_t; clear all of the rest. */
+        tcg_gen_gvec_dup_imm(MO_64, pred_full_reg_offset(s, a->rd),
+                             8, size_for_gvec(pred_full_reg_size(s)), val);
+    }
+    return true;
+}
+
 /* Note pat == 31 is #all, to set all elements.  */
 TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve,
                         do_predset, 0, FFR_PRED_NUM, 31, false)
-- 
2.43.0

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: 20250704142112.1018902-82-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 25 ++++++++++++++++++
 target/arm/tcg/sve.decode      |  7 ++++++
 target/arm/tcg/sve_helper.c    | 46 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 35 ++++++++++++++++++++++++++
 4 files changed, 113 insertions(+)

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: 20250704142112.1018902-83-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  2 +
 target/arm/tcg/vec_internal.h  | 74 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/sve.decode      |  6 +++
 target/arm/tcg/sve_helper.c    | 28 +++++++++++++
 target/arm/tcg/translate-sve.c | 36 +++++++++++++++++
 5 files changed, 146 insertions(+)

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: 20250704142112.1018902-84-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |   5 +
 target/arm/tcg/sme.decode      |   9 +
 target/arm/tcg/sme_helper.c    | 317 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  31 ++++
 4 files changed, 362 insertions(+)

diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i3
 DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
 DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sme2_sel_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ UCLAMP          11000001 esz:2 1 zm:5 110001 zn:5 .... 1    \
 UCLAMP          11000001 esz:2 1 zm:5 110011 zn:5 ...0 1    \
                 &zzz_en zd=%zd_ax4 n=4
 
+### SME2 Multi-vector SVE Select
+
+%sel_pg         10:3 !function=plus_8
+
+SEL             11000001 esz:2 1 ....0 100 ... ....0 ....0  \
+                n=2 zd=%zd_ax2 zn=%zn_ax2 zm=%zm_ax2 pg=%sel_pg
+SEL             11000001 esz:2 1 ...01 100 ... ...00 ...00  \
+                n=4 zd=%zd_ax4 zn=%zn_ax4 zm=%zm_ax4 pg=%sel_pg
+
 ### SME Multiple Zero
 
 &zero_za        rv off ngrp nvec
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ FCLAMP(sme2_fclamp_d, float64, H8)
 FCLAMP(sme2_bfclamp, bfloat16, H2)
 
 #undef FCLAMP
+
+void HELPER(sme2_sel_b)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint8_t);
+    DecodeCounter p = decode_counter(png, vl, MO_8);
+
+    if (p.lg2_stride == 0) {
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, n, vl);  /* all true */
+                } else if (elements <= split) {
+                    memcpy(d, m, vl);  /* all false */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H1(e)] = m[H1(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H1(e)] = n[H1(e)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, m, vl);  /* all false */
+                } else if (elements <= split) {
+                    memcpy(d, n, vl);  /* all true */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H1(e)] = n[H1(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H1(e)] = m[H1(e)];
+                    }
+                }
+            }
+        }
+    } else {
+        int estride = 1 << p.lg2_stride;
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e++) {
+                    d[H1(e)] = m[H1(e)];
+                }
+                for (; e < elements; e += estride) {
+                    d[H1(e)] = n[H1(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H1(e + i)] = m[H1(e + i)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint8_t *d = vd + r * sizeof(ARMVectorReg);
+                uint8_t *n = vn + r * sizeof(ARMVectorReg);
+                uint8_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e += estride) {
+                    d[H1(e)] = n[H1(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H1(e + i)] = m[H1(e + i)];
+                    }
+                }
+                for (; e < elements; e++) {
+                    d[H1(e)] = m[H1(e)];
+                }
+            }
+        }
+    }
+}
+
+void HELPER(sme2_sel_h)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint16_t);
+    DecodeCounter p = decode_counter(png, vl, MO_16);
+
+    if (p.lg2_stride == 0) {
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, n, vl);  /* all true */
+                } else if (elements <= split) {
+                    memcpy(d, m, vl);  /* all false */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H2(e)] = m[H2(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H2(e)] = n[H2(e)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, m, vl);  /* all false */
+                } else if (elements <= split) {
+                    memcpy(d, n, vl);  /* all true */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H2(e)] = n[H2(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H2(e)] = m[H2(e)];
+                    }
+                }
+            }
+        }
+    } else {
+        int estride = 1 << p.lg2_stride;
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e++) {
+                    d[H2(e)] = m[H2(e)];
+                }
+                for (; e < elements; e += estride) {
+                    d[H2(e)] = n[H2(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H2(e + i)] = m[H2(e + i)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint16_t *d = vd + r * sizeof(ARMVectorReg);
+                uint16_t *n = vn + r * sizeof(ARMVectorReg);
+                uint16_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e += estride) {
+                    d[H2(e)] = n[H2(e)];
+                    for (int i = 1; i < estride; i++) {
+                        d[H2(e + i)] = m[H2(e + i)];
+                    }
+                }
+                for (; e < elements; e++) {
+                    d[H2(e)] = m[H2(e)];
+                }
+            }
+        }
+    }
+}
+
+void HELPER(sme2_sel_s)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint32_t);
+    DecodeCounter p = decode_counter(png, vl, MO_32);
+
+    if (p.lg2_stride == 0) {
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, n, vl);  /* all true */
+                } else if (elements <= split) {
+                    memcpy(d, m, vl);  /* all false */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H4(e)] = m[H4(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H4(e)] = n[H4(e)];
+                    }
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+
+                if (split <= 0) {
+                    memcpy(d, m, vl);  /* all false */
+                } else if (elements <= split) {
+                    memcpy(d, n, vl);  /* all true */
+                } else {
+                    for (int e = 0; e < split; e++) {
+                        d[H4(e)] = n[H4(e)];
+                    }
+                    for (int e = split; e < elements; e++) {
+                        d[H4(e)] = m[H4(e)];
+                    }
+                }
+            }
+        }
+    } else {
+        /* p.esz must be MO_64, so stride must be 2. */
+        if (p.invert) {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e++) {
+                    d[H4(e)] = m[H4(e)];
+                }
+                for (; e < elements; e += 2) {
+                    d[H4(e)] = n[H4(e)];
+                    d[H4(e + 1)] = m[H4(e + 1)];
+                }
+            }
+        } else {
+            for (int r = 0; r < nreg; r++) {
+                uint32_t *d = vd + r * sizeof(ARMVectorReg);
+                uint32_t *n = vn + r * sizeof(ARMVectorReg);
+                uint32_t *m = vm + r * sizeof(ARMVectorReg);
+                int split = p.count - r * elements;
+                int e = 0;
+
+                for (; e < MIN(split, elements); e += 2) {
+                    d[H4(e)] = n[H4(e)];
+                    d[H4(e + 1)] = m[H4(e + 1)];
+                }
+                for (; e < elements; e++) {
+                    d[H4(e)] = m[H4(e)];
+                }
+            }
+        }
+    }
+}
+
+void HELPER(sme2_sel_d)(void *vd, void *vn, void *vm,
+                        uint32_t png, uint32_t desc)
+{
+    int vl = simd_oprsz(desc);
+    int nreg = simd_data(desc);
+    int elements = vl / sizeof(uint64_t);
+    DecodeCounter p = decode_counter(png, vl, MO_64);
+
+    if (p.invert) {
+        for (int r = 0; r < nreg; r++) {
+            uint64_t *d = vd + r * sizeof(ARMVectorReg);
+            uint64_t *n = vn + r * sizeof(ARMVectorReg);
+            uint64_t *m = vm + r * sizeof(ARMVectorReg);
+            int split = p.count - r * elements;
+
+            if (split <= 0) {
+                memcpy(d, n, vl);  /* all true */
+            } else if (elements <= split) {
+                memcpy(d, m, vl);  /* all false */
+            } else {
+                memcpy(d, m, split * sizeof(uint64_t));
+                memcpy(d + split, n + split,
+                       (elements - split) * sizeof(uint64_t));
+            }
+        }
+    } else {
+        for (int r = 0; r < nreg; r++) {
+            uint64_t *d = vd + r * sizeof(ARMVectorReg);
+            uint64_t *n = vn + r * sizeof(ARMVectorReg);
+            uint64_t *m = vm + r * sizeof(ARMVectorReg);
+            int split = p.count - r * elements;
+
+            if (split <= 0) {
+                memcpy(d, m, vl);  /* all false */
+            } else if (elements <= split) {
+                memcpy(d, n, vl);  /* all true */
+            } else {
+                memcpy(d, n, split * sizeof(uint64_t));
+                memcpy(d + split, m + split,
+                       (elements - split) * sizeof(uint64_t));
+            }
+        }
+    }
+}
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const uclamp_fns[] = {
     gen_helper_sme2_uclamp_d,
 };
 TRANS(UCLAMP, do_clamp, a, uclamp_fns)
+
+static bool trans_SEL(DisasContext *s, arg_SEL *a)
+{
+    typedef void sme_sel_fn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32);
+    static sme_sel_fn * const fns[4] = {
+        gen_helper_sme2_sel_b, gen_helper_sme2_sel_h,
+        gen_helper_sme2_sel_s, gen_helper_sme2_sel_d
+    };
+
+    if (!dc_isar_feature(aa64_sme2, s)) {
+        return false;
+    }
+    if (sme_sm_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        uint32_t desc = simd_desc(svl, svl, a->n);
+        TCGv_ptr t_d = tcg_temp_new_ptr();
+        TCGv_ptr t_n = tcg_temp_new_ptr();
+        TCGv_ptr t_m = tcg_temp_new_ptr();
+        TCGv_i32 png = tcg_temp_new_i32();
+
+        tcg_gen_addi_ptr(t_d, tcg_env, vec_full_reg_offset(s, a->zd));
+        tcg_gen_addi_ptr(t_n, tcg_env, vec_full_reg_offset(s, a->zn));
+        tcg_gen_addi_ptr(t_m, tcg_env, vec_full_reg_offset(s, a->zm));
+
+        tcg_gen_ld16u_i32(png, tcg_env, pred_full_reg_offset(s, a->pg)
+                          ^ (HOST_BIG_ENDIAN ? 6 : 0));
+
+        fns[a->esz](t_d, t_n, t_m, png, tcg_constant_i32(desc));
+    }
+    return true;
+}
-- 
2.43.0

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: 20250704142112.1018902-85-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 15 ++++++++++++
 target/arm/tcg/sve.decode      |  5 ++++
 target/arm/tcg/sve_helper.c    | 42 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c |  3 +++
 4 files changed, 65 insertions(+)

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: 20250704142112.1018902-86-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 49 ++++++++++++++++++++++++
 target/arm/tcg/sve.decode      |  8 ++++
 target/arm/tcg/sve_helper.c    | 70 +++++++++++++++++++++-------------
 target/arm/tcg/translate-sve.c | 48 +++++++++++++++++++++++
 4 files changed, 148 insertions(+), 27 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: 20250704142112.1018902-87-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  6 ++++++
 target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ FMLSLT_zzzw     01100100 10 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
 BFMLALB_zzzw    01100100 11 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 BFMLALT_zzzw    01100100 11 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm_ex esz=2
+BFMLSLB_zzzw    01100100 11 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm_ex esz=2
+BFMLSLT_zzzw    01100100 11 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point dot-product
 FDOT_zzzz       01100100 00 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 BFDOT_zzzz      01100100 01 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm_ex esz=2
 
 ### SVE2 floating-point multiply-add long (indexed)
+
 FMLALB_zzxw     01100100 10 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 FMLALT_zzxw     01100100 10 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
 FMLSLB_zzxw     01100100 10 1 ..... 0110.0 ..... .....     @rrxr_3a esz=2
 FMLSLT_zzxw     01100100 10 1 ..... 0110.1 ..... .....     @rrxr_3a esz=2
+
 BFMLALB_zzxw    01100100 11 1 ..... 0100.0 ..... .....     @rrxr_3a esz=2
 BFMLALT_zzxw    01100100 11 1 ..... 0100.1 ..... .....     @rrxr_3a esz=2
+BFMLSLB_zzxw    01100100 11 1 ..... 0110.0 ..... .....     @rrxr_3a esz=2
+BFMLSLT_zzxw    01100100 11 1 ..... 0110.1 ..... .....     @rrxr_3a esz=2
 
 ### SVE2 floating-point dot-product (indexed)
 
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 bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
 TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false)
 TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true)
 
+static bool do_BFMLSL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel)
+{
+    if (s->fpcr_ah) {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl,
+                                  a->rd, a->rn, a->rm, a->ra, sel, FPST_AH);
+    } else {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl,
+                                  a->rd, a->rn, a->rm, a->ra, sel, FPST_A64);
+    }
+}
+
+TRANS_FEAT(BFMLSLB_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, false)
+TRANS_FEAT(BFMLSLT_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, true)
+
+static bool do_BFMLSL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
+{
+    if (s->fpcr_ah) {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl_idx,
+                                  a->rd, a->rn, a->rm, a->ra,
+                                  (a->index << 1) | sel, FPST_AH);
+    } else {
+        return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl_idx,
+                                  a->rd, a->rn, a->rm, a->ra,
+                                  (a->index << 1) | sel, FPST_A64);
+    }
+}
+
+TRANS_FEAT(BFMLSLB_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, false)
+TRANS_FEAT(BFMLSLT_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, true)
+
 static bool trans_PSEL(DisasContext *s, arg_psel *a)
 {
     int vl = vec_full_reg_size(s);
-- 
2.43.0

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: 20250704142112.1018902-88-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  1 +
 target/arm/tcg/sve.decode      |  3 ++-
 target/arm/tcg/sve_helper.c    | 21 +++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++
 4 files changed, 54 insertions(+), 1 deletion(-)

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: 20250704142112.1018902-89-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  6 ++++++
 target/arm/tcg/translate-sve.c | 21 +++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ DUP_s           00000101 .. 1 00000 001110 ..... .....          @rd_rn
 DUP_x           00000101 .. 1 ..... 001000 rn:5 rd:5 \
                 &rri imm=%imm7_22_16
 
+# SVE Permute Vector - one source quadwords
+DUPQ            00000101 001 imm:4    1 001001 rn:5 rd:5        &rri_esz esz=0
+DUPQ            00000101 001 imm:3   10 001001 rn:5 rd:5        &rri_esz esz=1
+DUPQ            00000101 001 imm:2  100 001001 rn:5 rd:5        &rri_esz esz=2
+DUPQ            00000101 001 imm:1 1000 001001 rn:5 rd:5        &rri_esz esz=3
+
 # SVE insert SIMD&FP scalar register
 INSR_f          00000101 .. 1 10100 001110 ..... .....          @rdn_rm
 
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 bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
     return true;
 }
 
+static bool trans_DUPQ(DisasContext *s, arg_DUPQ *a)
+{
+    unsigned vl, dofs, nofs;
+
+    if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    vl = vec_full_reg_size(s);
+    dofs = vec_full_reg_offset(s, a->rd);
+    nofs = vec_reg_offset(s, a->rn, a->imm, a->esz);
+
+    for (unsigned i = 0; i < vl; i += 16) {
+        tcg_gen_gvec_dup_mem(a->esz, dofs + i, nofs + i, 16, 16);
+    }
+    return true;
+}
+
 static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val)
 {
     typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32);
-- 
2.43.0

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: 20250704142112.1018902-90-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode      |  2 ++
 target/arm/tcg/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ DUPQ            00000101 001 imm:3   10 001001 rn:5 rd:5        &rri_esz esz=1
 DUPQ            00000101 001 imm:2  100 001001 rn:5 rd:5        &rri_esz esz=2
 DUPQ            00000101 001 imm:1 1000 001001 rn:5 rd:5        &rri_esz esz=3
 
+EXTQ            00000101 0110 imm:4 001001 rn:5 rd:5            &rri
+
 # SVE insert SIMD&FP scalar register
 INSR_f          00000101 .. 1 10100 001110 ..... .....          @rdn_rm
 
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 bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm)
 TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm)
 TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm)
 
+static bool trans_EXTQ(DisasContext *s, arg_EXTQ *a)
+{
+    unsigned vl, dofs, sofs0, sofs1, sofs2, imm;
+
+    if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    imm = a->imm;
+    if (imm == 0) {
+        /* So far we never optimize Zdn with MOVPRFX, so zd = zn is a nop. */
+        return true;
+    }
+
+    vl = vec_full_reg_size(s);
+    dofs = vec_full_reg_offset(s, a->rd);
+    sofs2 = vec_full_reg_offset(s, a->rn);
+
+    if (imm & 8) {
+        sofs0 = dofs + 8;
+        sofs1 = sofs2;
+        sofs2 += 8;
+    } else {
+        sofs0 = dofs;
+        sofs1 = dofs + 8;
+    }
+    imm = (imm & 7) << 3;
+
+    for (unsigned i = 0; i < vl; i += 16) {
+        TCGv_i64 s0 = tcg_temp_new_i64();
+        TCGv_i64 s1 = tcg_temp_new_i64();
+        TCGv_i64 s2 = tcg_temp_new_i64();
+
+        tcg_gen_ld_i64(s0, tcg_env, sofs0 + i);
+        tcg_gen_ld_i64(s1, tcg_env, sofs1 + i);
+        tcg_gen_ld_i64(s2, tcg_env, sofs2 + i);
+
+        tcg_gen_extract2_i64(s0, s0, s1, imm);
+        tcg_gen_extract2_i64(s1, s1, s2, imm);
+
+        tcg_gen_st_i64(s0, tcg_env, dofs + i);
+        tcg_gen_st_i64(s1, tcg_env, dofs + i + 8);
+    }
+    return true;
+}
+
 /*
  *** SVE Permute - Unpredicated Group
  */
-- 
2.43.0

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-91-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  8 +++
 target/arm/tcg/vec_internal.h  | 34 ++++++++++++
 target/arm/tcg/sve.decode      | 17 ++++++
 target/arm/tcg/sve_helper.c    | 50 +++++++++++++++++
 target/arm/tcg/translate-sve.c | 98 ++++++++++++++++++++++++++++++++++
 5 files changed, 207 insertions(+)

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: 20250704142112.1018902-92-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 10 ++++++++++
 target/arm/tcg/sve.decode      |  6 ++++++
 target/arm/tcg/sve_helper.c    | 29 +++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 19 ++++++++++++++++++-
 4 files changed, 63 insertions(+), 1 deletion(-)

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: 20250704142112.1018902-93-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 10 ++++++++++
 target/arm/tcg/sve.decode      |  3 +++
 target/arm/tcg/sve_helper.c    | 10 ++++++++++
 target/arm/tcg/translate-sve.c | 14 ++++++++++++++
 4 files changed, 37 insertions(+)

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

Implement the SVE2p1 consecutive register LD1/ST1,
and the SME2 strided register LD1/ST1.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-94-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  16 ++
 target/arm/tcg/sve.decode      |  50 ++++
 target/arm/tcg/sve_helper.c    | 493 +++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 103 +++++++
 4 files changed, 662 insertions(+)

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_ld1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_st1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@ SCLAMP          01000100 .. 0 ..... 110000 ..... .....          @rda_rn_rm
 UCLAMP          01000100 .. 0 ..... 110001 ..... .....          @rda_rn_rm
 
 FCLAMP          01100100 .. 1 ..... 001001 ..... .....          @rda_rn_rm
+
+### SVE2p1 multi-vec contiguous load
+
+&zcrr_ldst      rd png rn rm esz nreg
+&zcri_ldst      rd png rn imm esz nreg
+%png            10:3 !function=plus_8
+%zd_ax2         1:4 !function=times_2
+%zd_ax4         2:3 !function=times_4
+
+LD1_zcrr        10100000000 rm:5 0 esz:2 ... rn:5 .... - \
+                &zcrr_ldst %png rd=%zd_ax2 nreg=2
+LD1_zcrr        10100000000 rm:5 1 esz:2 ... rn:5 ... 0- \
+                &zcrr_ldst %png rd=%zd_ax4 nreg=4
+
+ST1_zcrr        10100000001 rm:5 0 esz:2 ... rn:5 .... - \
+                &zcrr_ldst %png rd=%zd_ax2 nreg=2
+ST1_zcrr        10100000001 rm:5 1 esz:2 ... rn:5 ... 0- \
+                &zcrr_ldst %png rd=%zd_ax4 nreg=4
+
+LD1_zcri        101000000100 imm:s4 0 esz:2 ... rn:5 .... - \
+                &zcri_ldst %png rd=%zd_ax2 nreg=2
+LD1_zcri        101000000100 imm:s4 1 esz:2 ... rn:5 ... 0- \
+                &zcri_ldst %png rd=%zd_ax4 nreg=4
+
+ST1_zcri        101000000110 imm:s4 0 esz:2 ... rn:5 .... - \
+                &zcri_ldst %png rd=%zd_ax2 nreg=2
+ST1_zcri        101000000110 imm:s4 1 esz:2 ... rn:5 ... 0- \
+                &zcri_ldst %png rd=%zd_ax4 nreg=4
+
+# Note: N bit and 0 bit (for nreg4) still mashed in rd.
+# This is handled within gen_ldst_c().
+LD1_zcrr_stride 10100001000 rm:5 0 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=2
+LD1_zcrr_stride 10100001000 rm:5 1 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=4
+
+ST1_zcrr_stride 10100001001 rm:5 0 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=2
+ST1_zcrr_stride 10100001001 rm:5 1 esz:2 ... rn:5 rd:5 \
+                &zcrr_ldst %png nreg=4
+
+LD1_zcri_stride 101000010100 imm:s4 0 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=2
+LD1_zcri_stride 101000010100 imm:s4 1 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=4
+
+ST1_zcri_stride 101000010110 imm:s4 0 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=2
+ST1_zcri_stride 101000010110 imm:s4 1 esz:2 ... rn:5 rd:5 \
+                &zcri_ldst %png nreg=4
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -XXX,XX +XXX,XX @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64)
 #undef DO_ST1_ZPZ_S
 #undef DO_ST1_ZPZ_D
 
+/*
+ * SVE2.1 consecutive register load/store
+ */
+
+static unsigned sve2p1_cont_ldst_elements(SVEContLdSt *info, vaddr addr,
+                                          uint32_t png, intptr_t reg_max,
+                                          int N, int v_esz)
+{
+    const int esize = 1 << v_esz;
+    intptr_t reg_off_first = -1, reg_off_last = -1, reg_off_split;
+    DecodeCounter p = decode_counter(png, reg_max, v_esz);
+    unsigned b_count = p.count << v_esz;
+    unsigned b_stride = 1 << (v_esz + p.lg2_stride);
+    intptr_t page_split;
+
+    /* Set all of the element indices to -1, and the TLB data to 0. */
+    memset(info, -1, offsetof(SVEContLdSt, page));
+    memset(info->page, 0, sizeof(info->page));
+
+    if (p.invert) {
+        if (b_count >= reg_max * N) {
+            return 0;
+        }
+        reg_off_first = b_count;
+        reg_off_last = reg_max * N - b_stride;
+    } else {
+        if (b_count == 0) {
+            return 0;
+        }
+        reg_off_first = 0;
+        reg_off_last = MIN(b_count - esize, reg_max * N - b_stride);
+    }
+
+    info->reg_off_first[0] = reg_off_first;
+    info->mem_off_first[0] = reg_off_first;
+
+    page_split = -(addr | TARGET_PAGE_MASK);
+    if (reg_off_last + esize <= page_split || reg_off_first >= page_split) {
+        /* The entire operation fits within a single page. */
+        info->reg_off_last[0] = reg_off_last;
+        return b_stride;
+    }
+
+    info->page_split = page_split;
+    reg_off_split = ROUND_DOWN(page_split, esize);
+
+    /*
+     * This is the last full element on the first page, but it is not
+     * necessarily active.  If there is no full element, i.e. the first
+     * active element is the one that's split, this value remains -1.
+     * It is useful as iteration bounds.
+     */
+    if (reg_off_split != 0) {
+        info->reg_off_last[0] = ROUND_DOWN(reg_off_split - esize, b_stride);
+    }
+
+    /* Determine if an unaligned element spans the pages.  */
+    if (page_split & (esize - 1)) {
+        /* It is helpful to know if the split element is active. */
+        if ((reg_off_split & (b_stride - 1)) == 0) {
+            info->reg_off_split = reg_off_split;
+            info->mem_off_split = reg_off_split;
+        }
+        reg_off_split += esize;
+    }
+
+    /*
+     * We do want the first active element on the second page, because
+     * this may affect the address reported in an exception.
+     */
+    reg_off_split = ROUND_UP(reg_off_split, b_stride);
+    if (reg_off_split <= reg_off_last) {
+        info->reg_off_first[1] = reg_off_split;
+        info->mem_off_first[1] = reg_off_split;
+        info->reg_off_last[1] = reg_off_last;
+    }
+    return b_stride;
+}
+
+static void sve2p1_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env,
+                                         target_ulong addr, unsigned estride,
+                                         int esize, int wp_access, uintptr_t ra)
+{
+#ifndef CONFIG_USER_ONLY
+    intptr_t count_off, count_last;
+    int flags0 = info->page[0].flags;
+    int flags1 = info->page[1].flags;
+
+    if (likely(!((flags0 | flags1) & TLB_WATCHPOINT))) {
+        return;
+    }
+
+    /* Indicate that watchpoints are handled. */
+    info->page[0].flags = flags0 & ~TLB_WATCHPOINT;
+    info->page[1].flags = flags1 & ~TLB_WATCHPOINT;
+
+    if (flags0 & TLB_WATCHPOINT) {
+        count_off = info->reg_off_first[0];
+        count_last = info->reg_off_split;
+        if (count_last < 0) {
+            count_last = info->reg_off_last[0];
+        }
+        do {
+            cpu_check_watchpoint(env_cpu(env), addr + count_off,
+                                 esize, info->page[0].attrs, wp_access, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+
+    count_off = info->reg_off_first[1];
+    if ((flags1 & TLB_WATCHPOINT) && count_off >= 0) {
+        count_last = info->reg_off_last[1];
+        do {
+            cpu_check_watchpoint(env_cpu(env), addr + count_off,
+                                 esize, info->page[1].attrs,
+                                 wp_access, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+#endif
+}
+
+static void sve2p1_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env,
+                                       target_ulong addr, unsigned estride,
+                                       int esize, uint32_t mtedesc,
+                                       uintptr_t ra)
+{
+    intptr_t count_off, count_last;
+
+    /*
+     * TODO: estride is always a small power of two, <= 8.
+     * Manipulate the stride within the loops such that
+     *   - first iteration hits addr + off, as required,
+     *   - second iteration hits ALIGN_UP(addr, 16),
+     *   - other iterations advance addr by 16.
+     * This will minimize the probing to once per MTE granule.
+     */
+
+    /* Process the page only if MemAttr == Tagged. */
+    if (info->page[0].tagged) {
+        count_off = info->reg_off_first[0];
+        count_last = info->reg_off_split;
+        if (count_last < 0) {
+            count_last = info->reg_off_last[0];
+        }
+
+        do {
+            mte_check(env, mtedesc, addr + count_off, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+
+    count_off = info->reg_off_first[1];
+    if (count_off >= 0 && info->page[1].tagged) {
+        count_last = info->reg_off_last[1];
+        do {
+            mte_check(env, mtedesc, addr + count_off, ra);
+            count_off += estride;
+        } while (count_off <= count_last);
+    }
+}
+
+static inline QEMU_ALWAYS_INLINE
+void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr,
+                  uint32_t png, uint32_t desc,
+                  const uintptr_t ra, const MemOp esz,
+                  sve_ldst1_host_fn *host_fn,
+                  sve_ldst1_tlb_fn *tlb_fn)
+{
+    const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2;
+    const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4);
+    uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT);
+    const intptr_t reg_max = simd_oprsz(desc);
+    const unsigned esize = 1 << esz;
+    intptr_t count_off, count_last;
+    intptr_t reg_off, reg_last, reg_n;
+    SVEContLdSt info;
+    unsigned estride, flags;
+    void *host;
+
+    estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz);
+    if (estride == 0) {
+        /* The entire predicate was false; no load occurs.  */
+        for (unsigned n = 0; n < N; n++) {
+            memset(zd + n * rstride, 0, reg_max);
+        }
+        return;
+    }
+
+    /* Probe the page(s).  Exit with exception for any invalid page. */
+    sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra);
+
+    /* Handle watchpoints for all active elements. */
+    sve2p1_cont_ldst_watchpoints(&info, env, addr, estride,
+                                 esize, BP_MEM_READ, ra);
+
+    /*
+     * Handle mte checks for all active elements.
+     * Since TBI must be set for MTE, !mtedesc => !mte_active.
+     */
+    if (mtedesc) {
+        sve2p1_cont_ldst_mte_check(&info, env, estride, addr,
+                                   esize, mtedesc, ra);
+    }
+
+    flags = info.page[0].flags | info.page[1].flags;
+    if (unlikely(flags != 0)) {
+        /*
+         * At least one page includes MMIO.
+         * Any bus operation can fail with cpu_transaction_failed,
+         * which for ARM will raise SyncExternal.  Perform the load
+         * into scratch memory to preserve register state until the end.
+         */
+        ARMVectorReg scratch[4] = { };
+
+        count_off = info.reg_off_first[0];
+        count_last = info.reg_off_last[1];
+        if (count_last < 0) {
+            count_last = info.reg_off_split;
+            if (count_last < 0) {
+                count_last = info.reg_off_last[0];
+            }
+        }
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+
+        do {
+            reg_last = MIN(count_last - count_off, reg_max - esize);
+            do {
+                tlb_fn(env, &scratch[reg_n], reg_off, addr + count_off, ra);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+
+        for (unsigned n = 0; n < N; ++n) {
+            memcpy(&zd[n * rstride], &scratch[n], reg_max);
+        }
+        return;
+    }
+
+    /* The entire operation is in RAM, on valid pages. */
+
+    for (unsigned n = 0; n < N; ++n) {
+        memset(&zd[n * rstride], 0, reg_max);
+    }
+
+    count_off = info.reg_off_first[0];
+    count_last = info.reg_off_last[0];
+    reg_off = count_off % reg_max;
+    reg_n = count_off / reg_max;
+    host = info.page[0].host;
+
+    set_helper_retaddr(ra);
+
+    do {
+        reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+        do {
+            host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+            reg_off += estride;
+            count_off += estride;
+        } while (reg_off <= reg_last);
+        reg_off = 0;
+        reg_n++;
+    } while (count_off <= count_last);
+
+    clear_helper_retaddr();
+
+    /*
+     * Use the slow path to manage the cross-page misalignment.
+     * But we know this is RAM and cannot trap.
+     */
+    count_off = info.reg_off_split;
+    if (unlikely(count_off >= 0)) {
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+    }
+
+    count_off = info.reg_off_first[1];
+    if (unlikely(count_off >= 0)) {
+        count_last = info.reg_off_last[1];
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        host = info.page[1].host;
+
+        set_helper_retaddr(ra);
+
+        do {
+            reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+            do {
+                host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+
+        clear_helper_retaddr();
+    }
+}
+
+void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr,
+                            uint32_t png, uint32_t desc)
+{
+    sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), MO_8,
+                 sve_ld1bb_host, sve_ld1bb_tlb);
+}
+
+#define DO_LD1_2(NAME, ESZ)                                             \
+void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_le_host, sve_##NAME##_le_tlb);            \
+}                                                                       \
+void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_be_host, sve_##NAME##_be_tlb);            \
+}
+
+DO_LD1_2(ld1hh, MO_16)
+DO_LD1_2(ld1ss, MO_32)
+DO_LD1_2(ld1dd, MO_64)
+
+#undef DO_LD1_2
+
+static inline QEMU_ALWAYS_INLINE
+void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr,
+                  uint32_t png, uint32_t desc,
+                  const uintptr_t ra, const int esz,
+                  sve_ldst1_host_fn *host_fn,
+                  sve_ldst1_tlb_fn *tlb_fn)
+{
+    const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2;
+    const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4);
+    uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT);
+    const intptr_t reg_max = simd_oprsz(desc);
+    const unsigned esize = 1 << esz;
+    intptr_t count_off, count_last;
+    intptr_t reg_off, reg_last, reg_n;
+    SVEContLdSt info;
+    unsigned estride, flags;
+    void *host;
+
+    estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz);
+    if (estride == 0) {
+        /* The entire predicate was false; no store occurs.  */
+        return;
+    }
+
+    /* Probe the page(s).  Exit with exception for any invalid page. */
+    sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra);
+
+    /* Handle watchpoints for all active elements. */
+    sve2p1_cont_ldst_watchpoints(&info, env, addr, estride,
+                                 esize, BP_MEM_WRITE, ra);
+
+    /*
+     * Handle mte checks for all active elements.
+     * Since TBI must be set for MTE, !mtedesc => !mte_active.
+     */
+    if (mtedesc) {
+        sve2p1_cont_ldst_mte_check(&info, env, estride, addr,
+                                   esize, mtedesc, ra);
+    }
+
+    flags = info.page[0].flags | info.page[1].flags;
+    if (unlikely(flags != 0)) {
+        /*
+         * At least one page includes MMIO.
+         * Any bus operation can fail with cpu_transaction_failed,
+         * which for ARM will raise SyncExternal.  Perform the load
+         * into scratch memory to preserve register state until the end.
+         */
+        count_off = info.reg_off_first[0];
+        count_last = info.reg_off_last[1];
+        if (count_last < 0) {
+            count_last = info.reg_off_split;
+            if (count_last < 0) {
+                count_last = info.reg_off_last[0];
+            }
+        }
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+
+        do {
+            reg_last = MIN(count_last - count_off, reg_max - esize);
+            do {
+                tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+        return;
+    }
+
+    /* The entire operation is in RAM, on valid pages. */
+
+    count_off = info.reg_off_first[0];
+    count_last = info.reg_off_last[0];
+    reg_off = count_off % reg_max;
+    reg_n = count_off / reg_max;
+    host = info.page[0].host;
+
+    set_helper_retaddr(ra);
+
+    do {
+        reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+        do {
+            host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+            reg_off += estride;
+            count_off += estride;
+        } while (reg_off <= reg_last);
+        reg_off = 0;
+        reg_n++;
+    } while (count_off <= count_last);
+
+    clear_helper_retaddr();
+
+    /*
+     * Use the slow path to manage the cross-page misalignment.
+     * But we know this is RAM and cannot trap.
+     */
+    count_off = info.reg_off_split;
+    if (unlikely(count_off >= 0)) {
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+    }
+
+    count_off = info.reg_off_first[1];
+    if (unlikely(count_off >= 0)) {
+        count_last = info.reg_off_last[1];
+        reg_off = count_off % reg_max;
+        reg_n = count_off / reg_max;
+        host = info.page[1].host;
+
+        set_helper_retaddr(ra);
+
+        do {
+            reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+            do {
+                host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+                reg_off += estride;
+                count_off += estride;
+            } while (reg_off <= reg_last);
+            reg_off = 0;
+            reg_n++;
+        } while (count_off <= count_last);
+
+        clear_helper_retaddr();
+    }
+}
+
+void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr,
+                           uint32_t png, uint32_t desc)
+{
+    sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), MO_8,
+                 sve_st1bb_host, sve_st1bb_tlb);
+}
+
+#define DO_ST1_2(NAME, ESZ)                                             \
+void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_le_host, sve_##NAME##_le_tlb);            \
+}                                                                       \
+void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd,           \
+                                  target_ulong addr, uint32_t png,      \
+                                  uint32_t desc)                        \
+{                                                                       \
+    sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ,                \
+                 sve_##NAME##_be_host, sve_##NAME##_be_tlb);            \
+}
+
+DO_ST1_2(st1hh, MO_16)
+DO_ST1_2(st1ss, MO_32)
+DO_ST1_2(st1dd, MO_64)
+
+#undef DO_ST1_2
+
 void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
 {
     intptr_t i, opr_sz = simd_oprsz(desc) / 8;
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 @@ TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0)
 TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
            gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0)
+
+static bool gen_ldst_c(DisasContext *s, TCGv_i64 addr, int zd, int png,
+                       MemOp esz, bool is_write, int n, bool strided)
+{
+    typedef void ldst_c_fn(TCGv_env, TCGv_ptr, TCGv_i64,
+                           TCGv_i32, TCGv_i32);
+    static ldst_c_fn * const f_ldst[2][2][4] = {
+        { { gen_helper_sve2p1_ld1bb_c,
+            gen_helper_sve2p1_ld1hh_le_c,
+            gen_helper_sve2p1_ld1ss_le_c,
+            gen_helper_sve2p1_ld1dd_le_c, },
+          { gen_helper_sve2p1_ld1bb_c,
+            gen_helper_sve2p1_ld1hh_be_c,
+            gen_helper_sve2p1_ld1ss_be_c,
+            gen_helper_sve2p1_ld1dd_be_c, } },
+
+        { { gen_helper_sve2p1_st1bb_c,
+            gen_helper_sve2p1_st1hh_le_c,
+            gen_helper_sve2p1_st1ss_le_c,
+            gen_helper_sve2p1_st1dd_le_c, },
+          { gen_helper_sve2p1_st1bb_c,
+            gen_helper_sve2p1_st1hh_be_c,
+            gen_helper_sve2p1_st1ss_be_c,
+            gen_helper_sve2p1_st1dd_be_c, } }
+    };
+
+    TCGv_i32 t_png, t_desc;
+    TCGv_ptr t_zd;
+    uint32_t desc, lg2_rstride = 0;
+    bool be = s->be_data == MO_BE;
+
+    assert(n == 2 || n == 4);
+    if (strided) {
+        lg2_rstride = 3;
+        if (n == 4) {
+            /* Validate ZD alignment. */
+            if (zd & 4) {
+                return false;
+            }
+            lg2_rstride = 2;
+        }
+        /* Ignore non-temporal bit */
+        zd &= ~8;
+    }
+
+    if (strided || !dc_isar_feature(aa64_sve2p1, s)
+        ? !sme_sm_enabled_check(s)
+        : !sve_access_check(s)) {
+        return true;
+    }
+
+    if (!s->mte_active[0]) {
+        addr = clean_data_tbi(s, addr);
+    }
+
+    desc = n == 2 ? 0 : 1;
+    desc = desc | (lg2_rstride << 1);
+    desc = make_svemte_desc(s, vec_full_reg_size(s), 1, esz, is_write, desc);
+    t_desc = tcg_constant_i32(desc);
+
+    t_png = tcg_temp_new_i32();
+    tcg_gen_ld16u_i32(t_png, tcg_env,
+                      pred_full_reg_offset(s, png) ^
+                      (HOST_BIG_ENDIAN ? 6 : 0));
+
+    t_zd = tcg_temp_new_ptr();
+    tcg_gen_addi_ptr(t_zd, tcg_env, vec_full_reg_offset(s, zd));
+
+    f_ldst[is_write][be][esz](tcg_env, t_zd, addr, t_png, t_desc);
+    return true;
+}
+
+static bool gen_ldst_zcrr_c(DisasContext *s, arg_zcrr_ldst *a,
+                            bool is_write, bool strided)
+{
+    TCGv_i64 addr = tcg_temp_new_i64();
+
+    tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz);
+    tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn));
+    return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write,
+                      a->nreg, strided);
+}
+
+static bool gen_ldst_zcri_c(DisasContext *s, arg_zcri_ldst *a,
+                            bool is_write, bool strided)
+{
+    TCGv_i64 addr = tcg_temp_new_i64();
+
+    tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn),
+                     a->imm * a->nreg * vec_full_reg_size(s));
+    return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write,
+                      a->nreg, strided);
+}
+
+TRANS_FEAT(LD1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, false, false)
+TRANS_FEAT(LD1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, false, false)
+TRANS_FEAT(ST1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, true, false)
+TRANS_FEAT(ST1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, true, false)
+
+TRANS_FEAT(LD1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, false, true)
+TRANS_FEAT(LD1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, false, true)
+TRANS_FEAT(ST1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, true, true)
+TRANS_FEAT(ST1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, true, true)
-- 
2.43.0

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

The msz > esz encodings are reserved, and some of
them are about to be reused.  Split these patterns
so that the new insns do not overlap.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-95-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve.decode | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -XXX,XX +XXX,XX @@
 
 # Stores; user must fill in ESZ, MSZ, NREG as needed.
 @rprr_store         ....... ..    ..     rm:5 ... pg:3 rn:5 rd:5    &rprr_store
-@rpri_store_msz     ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5    &rpri_store
+@rpri_store         ....... ..    .. . imm:s4 ... pg:3 rn:5 rd:5    &rpri_store
 @rprr_store_esz_n0  ....... ..    esz:2  rm:5 ... pg:3 rn:5 rd:5 \
                     &rprr_store nreg=0
 @rprr_scatter_store ....... msz:2 ..     rm:5 ... pg:3 rn:5 rd:5 \
@@ -XXX,XX +XXX,XX @@ STR_zri         1110010 11 0.     ..... 010 ... ..... .....     @rd_rn_i9
 
 # SVE contiguous store (scalar plus immediate)
 # ST1B, ST1H, ST1W, ST1D; require msz <= esz
-ST_zpri         1110010 .. esz:2  0.... 111 ... ..... ..... \
-                @rpri_store_msz nreg=0
+ST_zpri         1110010 00 esz:2  0.... 111 ... ..... ..... \
+                @rpri_store msz=0 nreg=0
+ST_zpri         1110010 01 esz:2  0.... 111 ... ..... ..... \
+                @rpri_store msz=1 nreg=0
+ST_zpri         1110010 10 10     0.... 111 ... ..... ..... \
+                @rpri_store msz=2 esz=2 nreg=0
+ST_zpri         1110010 10 11     0.... 111 ... ..... ..... \
+                @rpri_store msz=2 esz=3 nreg=0
+ST_zpri         1110010 11 11     0.... 111 ... ..... ..... \
+                @rpri_store msz=3 esz=3 nreg=0
 
 # SVE contiguous store (scalar plus scalar)
 # ST1B, ST1H, ST1W, ST1D; require msz <= esz
@@ -XXX,XX +XXX,XX @@ ST_zprr         1110010 00 ..     ..... 010 ... ..... ..... \
                 @rprr_store_esz_n0 msz=0
 ST_zprr         1110010 01 ..     ..... 010 ... ..... ..... \
                 @rprr_store_esz_n0 msz=1
-ST_zprr         1110010 10 ..     ..... 010 ... ..... ..... \
-                @rprr_store_esz_n0 msz=2
+ST_zprr         1110010 10 10     ..... 010 ... ..... ..... \
+                @rprr_store msz=2 esz=2 nreg=0
+ST_zprr         1110010 10 11     ..... 010 ... ..... ..... \
+                @rprr_store msz=2 esz=3 nreg=0
 ST_zprr         1110010 11 11     ..... 010 ... ..... ..... \
                 @rprr_store msz=3 esz=3 nreg=0
 
 # SVE contiguous non-temporal store (scalar plus immediate)  (nreg == 0)
 # SVE store multiple structures (scalar plus immediate)      (nreg != 0)
 ST_zpri         1110010 .. nreg:2 1.... 111 ... ..... ..... \
-                @rpri_store_msz esz=%size_23
+                @rpri_store msz=%size_23 esz=%size_23
 
 # SVE contiguous non-temporal store (scalar plus scalar)     (nreg == 0)
 # SVE store multiple structures (scalar plus scalar)         (nreg != 0)
-ST_zprr         1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \
-                @rprr_store esz=%size_23
+ST_zprr         1110010 .. nreg:2 ..... 011 ... ..... ..... \
+                @rprr_store msz=%size_23 esz=%size_23
 
 # SVE 32-bit scatter store (scalar plus 32-bit scaled offsets)
 # Require msz > 0 && msz <= esz.
-- 
2.43.0

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: 20250704142112.1018902-96-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h        |  22 +++++
 target/arm/tcg/sve_ldst_internal.h |  26 ++++++
 target/arm/tcg/sve.decode          |  20 +++++
 target/arm/tcg/sve_helper.c        |   6 ++
 target/arm/tcg/translate-sve.c     | 136 +++++++++++++++++++++++------
 5 files changed, 183 insertions(+), 27 deletions(-)

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

Move from sme_helper.c to the shared header.
Add a comment noting the lack of atomicity.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-97-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/sve_ldst_internal.h | 63 ++++++++++++++++++++++++++++++
 target/arm/tcg/sme_helper.c        | 44 +++------------------
 2 files changed, 69 insertions(+), 38 deletions(-)

diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sve_ldst_internal.h
+++ b/target/arm/tcg/sve_ldst_internal.h
@@ -XXX,XX +XXX,XX @@ DO_LD_PRIM_3(ld1dqu_le, ld1dd_le)
 #define sve_st1dq_be_tlb   sve_st1dd_be_tlb
 #define sve_st1dq_le_tlb   sve_st1dd_le_tlb
 
+/*
+ * The ARMVectorReg elements are stored in host-endian 64-bit units.
+ * For 128-bit quantities, the sequence defined by the Elem[] pseudocode
+ * corresponds to storing the two 64-bit pieces in little-endian order.
+ */
+/* FIXME: Nothing in this file makes any effort at atomicity. */
+
+static inline void sve_ld1qq_be_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_ld1dd_be_host(vd, reg_off + 8, host);
+    sve_ld1dd_be_host(vd, reg_off, host + 8);
+}
+
+static inline void sve_ld1qq_le_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_ld1dd_le_host(vd, reg_off, host);
+    sve_ld1dd_le_host(vd, reg_off + 8, host + 8);
+}
+
+static inline void
+sve_ld1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_ld1dd_be_tlb(env, vd, reg_off + 8, addr, ra);
+    sve_ld1dd_be_tlb(env, vd, reg_off, addr + 8, ra);
+}
+
+static inline void
+sve_ld1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_ld1dd_le_tlb(env, vd, reg_off, addr, ra);
+    sve_ld1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra);
+}
+
+static inline void sve_st1qq_be_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_st1dd_be_host(vd, reg_off + 8, host);
+    sve_st1dd_be_host(vd, reg_off, host + 8);
+}
+
+static inline void sve_st1qq_le_host(void *vd, intptr_t reg_off, void *host)
+{
+    sve_st1dd_le_host(vd, reg_off, host);
+    sve_st1dd_le_host(vd, reg_off + 8, host + 8);
+}
+
+static inline void
+sve_st1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_st1dd_be_tlb(env, vd, reg_off + 8, addr, ra);
+    sve_st1dd_be_tlb(env, vd, reg_off, addr + 8, ra);
+}
+
+static inline void
+sve_st1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+                 target_ulong addr, uintptr_t ra)
+{
+    sve_st1dd_le_tlb(env, vd, reg_off, addr, ra);
+    sve_st1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra);
+}
+
 #undef DO_LD_TLB
 #undef DO_ST_TLB
 #undef DO_LD_HOST
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -XXX,XX +XXX,XX @@ static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za,           \
     TLB(env, useronly_clean_ptr(addr), val, ra);                            \
 }
 
-/*
- * The ARMVectorReg elements are stored in host-endian 64-bit units.
- * For 128-bit quantities, the sequence defined by the Elem[] pseudocode
- * corresponds to storing the two 64-bit pieces in little-endian order.
- */
-#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB)                                 \
-static inline void HNAME##_host(void *za, intptr_t off, void *host)         \
-{                                                                           \
-    uint64_t val0 = HOST(host), val1 = HOST(host + 8);                      \
-    uint64_t *ptr = za + off;                                               \
-    ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1;                   \
-}                                                                           \
+#define DO_LDQ(HNAME, VNAME) \
 static inline void VNAME##_v_host(void *za, intptr_t off, void *host)       \
 {                                                                           \
     HNAME##_host(za, tile_vslice_offset(off), host);                        \
 }                                                                           \
-static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off,    \
-                               target_ulong addr, uintptr_t ra)             \
-{                                                                           \
-    uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra);                 \
-    uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra);             \
-    uint64_t *ptr = za + off;                                               \
-    ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1;                   \
-}                                                                           \
 static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off,  \
                                target_ulong addr, uintptr_t ra)             \
 {                                                                           \
     HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra);                \
 }
 
-#define DO_STQ(HNAME, VNAME, BE, HOST, TLB)                                 \
-static inline void HNAME##_host(void *za, intptr_t off, void *host)         \
-{                                                                           \
-    uint64_t *ptr = za + off;                                               \
-    HOST(host, ptr[BE]);                                                    \
-    HOST(host + 8, ptr[!BE]);                                               \
-}                                                                           \
+#define DO_STQ(HNAME, VNAME) \
 static inline void VNAME##_v_host(void *za, intptr_t off, void *host)       \
 {                                                                           \
     HNAME##_host(za, tile_vslice_offset(off), host);                        \
 }                                                                           \
-static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off,    \
-                               target_ulong addr, uintptr_t ra)             \
-{                                                                           \
-    uint64_t *ptr = za + off;                                               \
-    TLB(env, useronly_clean_ptr(addr), ptr[BE], ra);                        \
-    TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra);                   \
-}                                                                           \
 static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off,  \
                                target_ulong addr, uintptr_t ra)             \
 {                                                                           \
@@ -XXX,XX +XXX,XX @@ DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra)
 DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra)
 DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra)
 
-DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra)
-DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra)
+DO_LDQ(sve_ld1qq_be, sme_ld1q_be)
+DO_LDQ(sve_ld1qq_le, sme_ld1q_le)
 
 DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra)
 DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra)
@@ -XXX,XX +XXX,XX @@ DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra)
 DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra)
 DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra)
 
-DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra)
-DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra)
+DO_STQ(sve_st1qq_be, sme_st1q_be)
+DO_STQ(sve_st1qq_le, sme_st1q_le)
 
 #undef DO_LD
 #undef DO_ST
-- 
2.43.0

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: 20250704142112.1018902-98-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    |  32 +++++++++
 target/arm/tcg/sve.decode      |  31 +++++++++
 target/arm/tcg/sve_helper.c    |   8 +++
 target/arm/tcg/translate-sve.c | 116 ++++++++++++++++++++++++---------
 4 files changed, 156 insertions(+), 31 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: 20250704142112.1018902-99-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 16 ++++++++++++++++
 target/arm/tcg/sve.decode      |  8 ++++++++
 target/arm/tcg/sve_helper.c    |  6 ++++++
 target/arm/tcg/translate-sve.c | 34 ++++++++++++++++++++++++++++++++--
 4 files changed, 62 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: 20250704142112.1018902-100-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme.decode      | 36 ++++++++++++++++++++
 target/arm/tcg/sme_helper.c    | 60 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c | 46 +++++++++++++++++++-------
 4 files changed, 137 insertions(+), 11 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: 20250704142112.1018902-101-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper.h        | 24 ++++++++++
 target/arm/tcg/sme.decode      | 42 ++++++++++++++++
 target/arm/tcg/translate-sme.c | 56 ++++++++++++++++++++++
 target/arm/tcg/vec_helper.c    | 88 ++++++++++++++++++++++++++++++++++
 4 files changed, 210 insertions(+)

diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -XXX,XX +XXX,XX @@ ZERO_za         11000000 000011 110 .. 0000000000 00.   \
                 &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
 ZERO_za         11000000 000011 111 .. 0000000000 00.   \
                 &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
+
+### SME Lookup Table Read
+
+&lut            zd zn idx
+
+# LUTI2, consecutive
+LUTI2_c_1b      1100 0000 1100 11 idx:4    00 00 zn:5 zd:5      &lut
+LUTI2_c_1h      1100 0000 1100 11 idx:4    01 00 zn:5 zd:5      &lut
+LUTI2_c_1s      1100 0000 1100 11 idx:4    10 00 zn:5 zd:5      &lut
+
+LUTI2_c_2b      1100 0000 1000 11 idx:3  1 00 00 zn:5 .... 0    &lut zd=%zd_ax2
+LUTI2_c_2h      1100 0000 1000 11 idx:3  1 01 00 zn:5 .... 0    &lut zd=%zd_ax2
+LUTI2_c_2s      1100 0000 1000 11 idx:3  1 10 00 zn:5 .... 0    &lut zd=%zd_ax2
+
+LUTI2_c_4b      1100 0000 1000 11 idx:2 10 00 00 zn:5 ... 00    &lut zd=%zd_ax4
+LUTI2_c_4h      1100 0000 1000 11 idx:2 10 01 00 zn:5 ... 00    &lut zd=%zd_ax4
+LUTI2_c_4s      1100 0000 1000 11 idx:2 10 10 00 zn:5 ... 00    &lut zd=%zd_ax4
+
+# LUTI2, strided (must check zd alignment)
+LUTI2_s_2b      1100 0000 1001 11 idx:3  1 00 00 zn:5 zd:5      &lut
+LUTI2_s_2h      1100 0000 1001 11 idx:3  1 01 00 zn:5 zd:5      &lut
+
+LUTI2_s_4b      1100 0000 1001 11 idx:2 10 00 00 zn:5 zd:5      &lut
+LUTI2_s_4h      1100 0000 1001 11 idx:2 10 01 00 zn:5 zd:5      &lut
+
+# LUTI4, consecutive
+LUTI4_c_1b      1100 0000 1100 101 idx:3    00 00 zn:5 zd:5     &lut
+LUTI4_c_1h      1100 0000 1100 101 idx:3    01 00 zn:5 zd:5     &lut
+LUTI4_c_1s      1100 0000 1100 101 idx:3    10 00 zn:5 zd:5     &lut
+
+LUTI4_c_2b      1100 0000 1000 101 idx:2  1 00 00 zn:5 .... 0   &lut zd=%zd_ax2
+LUTI4_c_2h      1100 0000 1000 101 idx:2  1 01 00 zn:5 .... 0   &lut zd=%zd_ax2
+LUTI4_c_2s      1100 0000 1000 101 idx:2  1 10 00 zn:5 .... 0   &lut zd=%zd_ax2
+
+LUTI4_c_4h      1100 0000 1000 101 idx:1 10 01 00 zn:5 ... 00   &lut zd=%zd_ax4
+LUTI4_c_4s      1100 0000 1000 101 idx:1 10 10 00 zn:5 ... 00   &lut zd=%zd_ax4
+
+# LUTI4, strided (must check zd alignment)
+LUTI4_s_2b      1100 0000 1001 101 idx:2  1 00 00 zn:5 zd:5     &lut
+LUTI4_s_2h      1100 0000 1001 101 idx:2  1 01 00 zn:5 zd:5     &lut
+
+LUTI4_s_4h      1100 0000 1001 101 idx:1 10 01 00 zn:5 zd:5     &lut
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -XXX,XX +XXX,XX @@ static bool trans_SEL(DisasContext *s, arg_SEL *a)
     }
     return true;
 }
+
+static bool do_lut(DisasContext *s, arg_lut *a,
+                   gen_helper_gvec_2_ptr *fn, bool strided)
+{
+    if (sme_sm_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd),
+                           vec_full_reg_offset(s, a->zn),
+                           tcg_env, svl, svl, strided | (a->idx << 1), fn);
+    }
+    return true;
+}
+
+TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, false)
+TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, false)
+TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, false)
+
+TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, false)
+TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, false)
+TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, false)
+
+TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, false)
+TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, false)
+TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, false)
+
+TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, false)
+TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, false)
+TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, false)
+
+TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, false)
+TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, false)
+TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, false)
+
+TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, false)
+TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, false)
+
+static bool do_lut_s4(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+    return !(a->zd & 0b01100) && do_lut(s, a, fn, true);
+}
+
+static bool do_lut_s8(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+    return !(a->zd & 0b01000) && do_lut(s, a, fn, true);
+}
+
+TRANS_FEAT(LUTI2_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2b)
+TRANS_FEAT(LUTI2_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2h)
+
+TRANS_FEAT(LUTI2_s_4b, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4b)
+TRANS_FEAT(LUTI2_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4h)
+
+TRANS_FEAT(LUTI4_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2b)
+TRANS_FEAT(LUTI4_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2h)
+
+TRANS_FEAT(LUTI4_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti4_4h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index XXXXXXX..XXXXXXX 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -XXX,XX +XXX,XX @@ void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+static inline void do_lut_b(void *zd, uint64_t *indexes, uint64_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint8_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H1(e)] = extractn(table, index * tsize, 8);
+        }
+    }
+}
+
+static inline void do_lut_h(void *zd, uint64_t *indexes, uint64_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint16_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H2(e)] = extractn(table, index * tsize, 16);
+        }
+    }
+}
+
+static inline void do_lut_s(void *zd, uint64_t *indexes, uint32_t *table,
+                            unsigned elements, unsigned segbase,
+                            unsigned dstride, unsigned isize,
+                            unsigned tsize, unsigned nreg)
+{
+    for (unsigned r = 0; r < nreg; ++r) {
+        uint32_t *dst = zd + dstride * r;
+        unsigned base = segbase + r * elements;
+
+        for (unsigned e = 0; e < elements; ++e) {
+            unsigned index = extractn(indexes, (base + e) * isize, isize);
+            dst[H4(e)] = table[H4(index)];
+        }
+    }
+}
+
+#define DO_SME2_LUT(ISIZE, NREG, SUFF, ESIZE) \
+void helper_sme2_luti##ISIZE##_##NREG##SUFF                             \
+    (void *zd, void *zn, CPUARMState *env, uint32_t desc)               \
+{                                                                       \
+    unsigned vl = simd_oprsz(desc);                                     \
+    unsigned strided = extract32(desc, SIMD_DATA_SHIFT, 1);             \
+    unsigned idx = extract32(desc, SIMD_DATA_SHIFT + 1, 4);             \
+    unsigned elements = vl / ESIZE;                                     \
+    unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8);              \
+    unsigned segments = (ESIZE * 8) / (ISIZE * NREG);                   \
+    unsigned segment = idx & (segments - 1);                            \
+    ARMVectorReg indexes;                                               \
+    memcpy(&indexes, zn, vl);                                           \
+    do_lut_##SUFF(zd, indexes.d, (void *)env->za_state.zt0, elements,   \
+                  segment * NREG * elements,                            \
+                  dstride * sizeof(ARMVectorReg), ISIZE, 32, NREG);     \
+}
+
+DO_SME2_LUT(2,1,b, 1)
+DO_SME2_LUT(2,1,h, 2)
+DO_SME2_LUT(2,1,s, 4)
+DO_SME2_LUT(2,2,b, 1)
+DO_SME2_LUT(2,2,h, 2)
+DO_SME2_LUT(2,2,s, 4)
+DO_SME2_LUT(2,4,b, 1)
+DO_SME2_LUT(2,4,h, 2)
+DO_SME2_LUT(2,4,s, 4)
+
+DO_SME2_LUT(4,1,b, 1)
+DO_SME2_LUT(4,1,h, 2)
+DO_SME2_LUT(4,1,s, 4)
+DO_SME2_LUT(4,2,b, 1)
+DO_SME2_LUT(4,2,h, 2)
+DO_SME2_LUT(4,2,s, 4)
+DO_SME2_LUT(4,4,b, 1)
+DO_SME2_LUT(4,4,h, 2)
+DO_SME2_LUT(4,4,s, 4)
+
+#undef DO_SME2_LUT
-- 
2.43.0

The pattern we currently have as FMOPA_h is the "widening" insn
that takes fp16 inputs and produces single-precision outputs.
This is unlike FMOPA_s and FMOPA_d, which are non-widening
produce outputs the same size as their inputs.

SME2 introduces a non-widening fp16 FMOPA operation; rename
FMOPA_h to FMOPA_w_h (for 'widening'), so we can use FMOPA_h
for the non-widening version, giving it a name in line with
the other non-widening ops FMOPA_s and FMOPA_d.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-102-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 2 +-
 target/arm/tcg/sme.decode      | 2 +-
 target/arm/tcg/sme_helper.c    | 4 ++--
 target/arm/tcg/translate-sme.c | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

Our current BFMOPA opcode pattern is the widening version
of the insn. Rename it to BFMOPA_w, to make way for
the non-widening version added in SME2.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-103-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    | 2 +-
 target/arm/tcg/sme.decode      | 2 +-
 target/arm/tcg/sme_helper.c    | 4 ++--
 target/arm/tcg/translate-sme.c | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

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

For non-widening, we can use float_muladd_negate_product,
For widening, which uses dot-product, we need to handle
the negation explicitly.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-104-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  19 +++++
 target/arm/tcg/vec_internal.h  |   5 ++
 target/arm/tcg/sme_helper.c    | 141 +++++++++++++++++++++++++++------
 target/arm/tcg/translate-sme.c |  27 ++++---
 4 files changed, 160 insertions(+), 32 deletions(-)

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-105-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 51 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  4 +++
 4 files changed, 63 insertions(+)

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-106-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/helper-sme.h    |  6 ++++
 target/arm/tcg/sme.decode      |  2 ++
 target/arm/tcg/sme_helper.c    | 51 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sme.c |  5 ++++
 4 files changed, 64 insertions(+)

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: 20250704142112.1018902-107-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 docs/system/arm/emulation.rst |  6 ++++++
 target/arm/tcg/cpu64.c        | 10 ++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

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 @@ the following architecture extensions:
 - FEAT_SM3 (Advanced SIMD SM3 instructions)
 - FEAT_SM4 (Advanced SIMD SM4 instructions)
 - FEAT_SME (Scalable Matrix Extension)
+- FEAT_SME2 (Scalable Matrix Extension version 2)
+- FEAT_SME2p1 (Scalable Matrix Extension version 2.1)
+- FEAT_SME_B16B16 (Non-widening BFloat16 arithmetic for SME2)
 - FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode)
+- FEAT_SME_F16F16 (Non-widening half-precision FP16 arithmetic for SME2)
 - FEAT_SME_F64F64 (Double-precision floating-point outer product instructions)
 - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions)
 - FEAT_SVE (Scalable Vector Extension)
 - FEAT_SVE_AES (Scalable Vector AES instructions)
+- FEAT_SVE_B16B16 (Non-widening BFloat16 arithmetic for SVE2)
 - FEAT_SVE_BitPerm (Scalable Vector Bit Permutes instructions)
 - FEAT_SVE_PMULL128 (Scalable Vector PMULL instructions)
 - FEAT_SVE_SHA3 (Scalable Vector SHA3 instructions)
 - FEAT_SVE_SM4 (Scalable Vector SM4 instructions)
 - FEAT_SVE2 (Scalable Vector Extension version 2)
+- FEAT_SVE2p1 (Scalable Vector Extension version 2.1)
 - FEAT_SPECRES (Speculation restriction instructions)
 - FEAT_SSBS (Speculative Store Bypass Safe)
 - FEAT_SSBS2 (MRS and MSR instructions for SSBS version 2)
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 @@ void aarch64_max_tcg_initfn(Object *obj)
      */
     t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3);       /* FEAT_MTE3 */
     t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0);  /* FEAT_RASv1p1 + FEAT_DoubleFault */
-    t = FIELD_DP64(t, ID_AA64PFR1, SME, 1);       /* FEAT_SME */
+    t = FIELD_DP64(t, ID_AA64PFR1, SME, 2);       /* FEAT_SME2 */
     t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_3 */
     t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1);       /* FEAT_NMI */
     SET_IDREG(isar, ID_AA64PFR1, t);
@@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj)
     FIELD_DP64_IDREG(isar, ID_AA64MMFR3, SPEC_FPACC, 1); /* FEAT_FPACC_SPEC */
 
     t = GET_IDREG(isar, ID_AA64ZFR0);
-    t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1);
+    t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 2);    /* FEAT_SVE2p1 */
     t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2);       /* FEAT_SVE_PMULL128 */
     t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1);   /* FEAT_SVE_BitPerm */
     t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 2);  /* FEAT_BF16, FEAT_EBF16 */
+    t = FIELD_DP64(t, ID_AA64ZFR0, B16B16, 1);    /* FEAT_SVE_B16B16 */
     t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1);      /* FEAT_SVE_SHA3 */
     t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1);       /* FEAT_SVE_SM4 */
     t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1);      /* FEAT_I8MM */
@@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj)
 
     t = GET_IDREG(isar, ID_AA64SMFR0);
     t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1);   /* FEAT_SME */
+    t = FIELD_DP64(t, ID_AA64SMFR0, BI32I32, 1);  /* FEAT_SME2 */
     t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1);   /* FEAT_SME */
     t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1);   /* FEAT_SME */
     t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf);  /* FEAT_SME */
+    t = FIELD_DP64(t, ID_AA64SMFR0, F16F16, 1);   /* FEAT_SME_F16F16 */
+    t = FIELD_DP64(t, ID_AA64SMFR0, B16B16, 1);   /* FEAT_SME_B16B16 */
+    t = FIELD_DP64(t, ID_AA64SMFR0, I16I32, 5);   /* FEAT_SME2 */
     t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1);   /* FEAT_SME_F64F64 */
     t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */
+    t = FIELD_DP64(t, ID_AA64SMFR0, SMEVER, 2);   /* FEAT_SME2p1 */
     t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1);     /* FEAT_SME_FA64 */
     SET_IDREG(isar, ID_AA64SMFR0, t);
 
-- 
2.43.0

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: 20250704142112.1018902-108-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 linux-user/elfload.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index XXXXXXX..XXXXXXX 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -XXX,XX +XXX,XX @@ uint64_t get_elf_hwcap2(void)
     GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64);
     GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC);
     GET_FEATURE_ID(aa64_mops, ARM_HWCAP2_A64_MOPS);
+    GET_FEATURE_ID(aa64_sve2p1, ARM_HWCAP2_A64_SVE2P1);
+    GET_FEATURE_ID(aa64_sme2, (ARM_HWCAP2_A64_SME2 |
+                               ARM_HWCAP2_A64_SME_I16I32 |
+                               ARM_HWCAP2_A64_SME_BI32I32));
+    GET_FEATURE_ID(aa64_sme2p1, ARM_HWCAP2_A64_SME2P1);
+    GET_FEATURE_ID(aa64_sme_b16b16, ARM_HWCAP2_A64_SME_B16B16);
+    GET_FEATURE_ID(aa64_sme_f16f16, ARM_HWCAP2_A64_SME_F16F16);
+    GET_FEATURE_ID(aa64_sve_b16b16, ARM_HWCAP2_A64_SVE_B16B16);
 
     return hwcaps;
 }
-- 
2.43.0