diff mbox series

[v16,35/99] target/arm: split vfp state setting from tcg helpers

Message ID 20210604155312.15902-36-alex.bennee@linaro.org
State New
Headers show
Series arm tcg/kvm refactor and split with kvm only support | expand

Commit Message

Alex Bennée June 4, 2021, 3:52 p.m. UTC
From: Claudio Fontana <cfontana@suse.de>


cpu-vfp.c: vfp_get_fpsr and vfp_set_fpsr are needed also for KVM,
           so create a new cpu-vfp.c

tcg/cpu-vfp.c: vfp_get_fpscr_from_host and vv are TCG-only, so we
               move the implementation to tcg/cpu-vfp.c

Signed-off-by: Claudio Fontana <cfontana@suse.de>

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

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

---
 target/arm/cpu-vfp.h        |  29 +++++
 target/arm/cpu-vfp.c        |  97 +++++++++++++++++
 target/arm/tcg/cpu-vfp.c    | 146 +++++++++++++++++++++++++
 target/arm/tcg/vfp_helper.c | 210 +-----------------------------------
 target/arm/meson.build      |   1 +
 target/arm/tcg/meson.build  |   1 +
 6 files changed, 276 insertions(+), 208 deletions(-)
 create mode 100644 target/arm/cpu-vfp.h
 create mode 100644 target/arm/cpu-vfp.c
 create mode 100644 target/arm/tcg/cpu-vfp.c

-- 
2.20.1
diff mbox series

Patch

diff --git a/target/arm/cpu-vfp.h b/target/arm/cpu-vfp.h
new file mode 100644
index 0000000000..41e0d710a0
--- /dev/null
+++ b/target/arm/cpu-vfp.h
@@ -0,0 +1,29 @@ 
+/*
+ * ARM VFP floating-point operations internals
+ *
+ *  Copyright (c) 2003 Fabrice Bellard
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef CPU_VFP_H
+#define CPU_VFP_H
+
+#include "qemu/osdep.h"
+#include "cpu.h"
+
+uint32_t vfp_get_fpscr_from_host(CPUARMState *env);
+void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val);
+
+#endif /* CPU_VFP_H */
diff --git a/target/arm/cpu-vfp.c b/target/arm/cpu-vfp.c
new file mode 100644
index 0000000000..8ea615a916
--- /dev/null
+++ b/target/arm/cpu-vfp.c
@@ -0,0 +1,97 @@ 
+/*
+ * ARM VFP floating-point operations
+ *
+ *  Copyright (c) 2003 Fabrice Bellard
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "cpu-vfp.h"
+#include "sysemu/tcg.h"
+
+uint32_t vfp_get_fpscr(CPUARMState *env)
+{
+    uint32_t i, fpscr;
+
+    fpscr = env->vfp.xregs[ARM_VFP_FPSCR]
+            | (env->vfp.vec_len << 16)
+            | (env->vfp.vec_stride << 20);
+
+    /*
+     * M-profile LTPSIZE overlaps A-profile Stride; whichever of the
+     * two is not applicable to this CPU will always be zero.
+     */
+    fpscr |= env->v7m.ltpsize << 16;
+
+    if (tcg_enabled()) {
+        fpscr |= vfp_get_fpscr_from_host(env);
+    }
+
+    i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3];
+    fpscr |= i ? FPCR_QC : 0;
+
+    return fpscr;
+}
+
+void vfp_set_fpscr(CPUARMState *env, uint32_t val)
+{
+    /* When ARMv8.2-FP16 is not supported, FZ16 is RES0.  */
+    if (!cpu_isar_feature(any_fp16, env_archcpu(env))) {
+        val &= ~FPCR_FZ16;
+    }
+
+    if (tcg_enabled()) {
+        vfp_set_fpscr_to_host(env, val);
+    }
+
+    if (!arm_feature(env, ARM_FEATURE_M)) {
+        /*
+         * Short-vector length and stride; on M-profile these bits
+         * are used for different purposes.
+         * We can't make this conditional be "if MVFR0.FPShVec != 0",
+         * 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);
+    }
+
+    if (arm_feature(env, ARM_FEATURE_NEON)) {
+        /*
+         * The bit we set within fpscr_q is arbitrary; the register as a
+         * whole being zero/non-zero is what counts.
+         * TODO: M-profile MVE also has a QC bit.
+         */
+        env->vfp.qc[0] = val & FPCR_QC;
+        env->vfp.qc[1] = 0;
+        env->vfp.qc[2] = 0;
+        env->vfp.qc[3] = 0;
+    }
+
+    /*
+     * We don't implement trapped exception handling, so the
+     * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!)
+     *
+     * The exception flags IOC|DZC|OFC|UFC|IXC|IDC are stored in
+     * fp_status; QC, Len and Stride are stored separately earlier.
+     * Clear out all of those and the RES0 bits: only NZCV, AHP, DN,
+     * FZ, RMode and FZ16 are kept in vfp.xregs[FPSCR].
+     */
+    env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000;
+}
diff --git a/target/arm/tcg/cpu-vfp.c b/target/arm/tcg/cpu-vfp.c
new file mode 100644
index 0000000000..bb88abf1ba
--- /dev/null
+++ b/target/arm/tcg/cpu-vfp.c
@@ -0,0 +1,146 @@ 
+/*
+ * ARM VFP floating-point operations
+ *
+ *  Copyright (c) 2003 Fabrice Bellard
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "qemu/log.h"
+#include "internals.h"
+#include "fpu/softfloat.h"
+#include "cpu-vfp.h"
+
+/* Convert host exception flags to vfp form.  */
+static inline int vfp_exceptbits_from_host(int host_bits)
+{
+    int target_bits = 0;
+
+    if (host_bits & float_flag_invalid) {
+        target_bits |= 1;
+    }
+    if (host_bits & float_flag_divbyzero) {
+        target_bits |= 2;
+    }
+    if (host_bits & float_flag_overflow) {
+        target_bits |= 4;
+    }
+    if (host_bits & (float_flag_underflow | float_flag_output_denormal)) {
+        target_bits |= 8;
+    }
+    if (host_bits & float_flag_inexact) {
+        target_bits |= 0x10;
+    }
+    if (host_bits & float_flag_input_denormal) {
+        target_bits |= 0x80;
+    }
+    return target_bits;
+}
+
+/* Convert vfp exception flags to target form.  */
+static inline int vfp_exceptbits_to_host(int target_bits)
+{
+    int host_bits = 0;
+
+    if (target_bits & 1) {
+        host_bits |= float_flag_invalid;
+    }
+    if (target_bits & 2) {
+        host_bits |= float_flag_divbyzero;
+    }
+    if (target_bits & 4) {
+        host_bits |= float_flag_overflow;
+    }
+    if (target_bits & 8) {
+        host_bits |= float_flag_underflow;
+    }
+    if (target_bits & 0x10) {
+        host_bits |= float_flag_inexact;
+    }
+    if (target_bits & 0x80) {
+        host_bits |= float_flag_input_denormal;
+    }
+    return host_bits;
+}
+
+uint32_t vfp_get_fpscr_from_host(CPUARMState *env)
+{
+    uint32_t i;
+
+    i = get_float_exception_flags(&env->vfp.fp_status);
+    i |= get_float_exception_flags(&env->vfp.standard_fp_status);
+    /* FZ16 does not generate an input denormal exception.  */
+    i |= (get_float_exception_flags(&env->vfp.fp_status_f16)
+          & ~float_flag_input_denormal);
+    i |= (get_float_exception_flags(&env->vfp.standard_fp_status_f16)
+          & ~float_flag_input_denormal);
+    return vfp_exceptbits_from_host(i);
+}
+
+void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val)
+{
+    int i;
+    uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR];
+
+    changed ^= val;
+    if (changed & (3 << 22)) {
+        i = (val >> 22) & 3;
+        switch (i) {
+        case FPROUNDING_TIEEVEN:
+            i = float_round_nearest_even;
+            break;
+        case FPROUNDING_POSINF:
+            i = float_round_up;
+            break;
+        case FPROUNDING_NEGINF:
+            i = float_round_down;
+            break;
+        case FPROUNDING_ZERO:
+            i = float_round_to_zero;
+            break;
+        }
+        set_float_rounding_mode(i, &env->vfp.fp_status);
+        set_float_rounding_mode(i, &env->vfp.fp_status_f16);
+    }
+    if (changed & FPCR_FZ16) {
+        bool ftz_enabled = val & FPCR_FZ16;
+        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16);
+        set_flush_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16);
+        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16);
+        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16);
+    }
+    if (changed & FPCR_FZ) {
+        bool ftz_enabled = val & FPCR_FZ;
+        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status);
+        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status);
+    }
+    if (changed & FPCR_DN) {
+        bool dnan_enabled = val & FPCR_DN;
+        set_default_nan_mode(dnan_enabled, &env->vfp.fp_status);
+        set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16);
+    }
+
+    /*
+     * The exception flags are ORed together when we read fpscr so we
+     * only need to preserve the current state in one of our
+     * float_status values.
+     */
+    i = vfp_exceptbits_to_host(val);
+    set_float_exception_flags(i, &env->vfp.fp_status);
+    set_float_exception_flags(0, &env->vfp.fp_status_f16);
+    set_float_exception_flags(0, &env->vfp.standard_fp_status);
+    set_float_exception_flags(0, &env->vfp.standard_fp_status_f16);
+}
diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c
index 01b9d8557f..521719f327 100644
--- a/target/arm/tcg/vfp_helper.c
+++ b/target/arm/tcg/vfp_helper.c
@@ -30,220 +30,14 @@ 
    Single precision routines have a "s" suffix, double precision a
    "d" suffix.  */
 
-#ifdef CONFIG_TCG
-
-/* Convert host exception flags to vfp form.  */
-static inline int vfp_exceptbits_from_host(int host_bits)
-{
-    int target_bits = 0;
-
-    if (host_bits & float_flag_invalid) {
-        target_bits |= 1;
-    }
-    if (host_bits & float_flag_divbyzero) {
-        target_bits |= 2;
-    }
-    if (host_bits & float_flag_overflow) {
-        target_bits |= 4;
-    }
-    if (host_bits & (float_flag_underflow | float_flag_output_denormal)) {
-        target_bits |= 8;
-    }
-    if (host_bits & float_flag_inexact) {
-        target_bits |= 0x10;
-    }
-    if (host_bits & float_flag_input_denormal) {
-        target_bits |= 0x80;
-    }
-    return target_bits;
-}
-
-/* Convert vfp exception flags to target form.  */
-static inline int vfp_exceptbits_to_host(int target_bits)
-{
-    int host_bits = 0;
-
-    if (target_bits & 1) {
-        host_bits |= float_flag_invalid;
-    }
-    if (target_bits & 2) {
-        host_bits |= float_flag_divbyzero;
-    }
-    if (target_bits & 4) {
-        host_bits |= float_flag_overflow;
-    }
-    if (target_bits & 8) {
-        host_bits |= float_flag_underflow;
-    }
-    if (target_bits & 0x10) {
-        host_bits |= float_flag_inexact;
-    }
-    if (target_bits & 0x80) {
-        host_bits |= float_flag_input_denormal;
-    }
-    return host_bits;
-}
-
-static uint32_t vfp_get_fpscr_from_host(CPUARMState *env)
-{
-    uint32_t i;
-
-    i = get_float_exception_flags(&env->vfp.fp_status);
-    i |= get_float_exception_flags(&env->vfp.standard_fp_status);
-    /* FZ16 does not generate an input denormal exception.  */
-    i |= (get_float_exception_flags(&env->vfp.fp_status_f16)
-          & ~float_flag_input_denormal);
-    i |= (get_float_exception_flags(&env->vfp.standard_fp_status_f16)
-          & ~float_flag_input_denormal);
-    return vfp_exceptbits_from_host(i);
-}
-
-static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val)
-{
-    int i;
-    uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR];
-
-    changed ^= val;
-    if (changed & (3 << 22)) {
-        i = (val >> 22) & 3;
-        switch (i) {
-        case FPROUNDING_TIEEVEN:
-            i = float_round_nearest_even;
-            break;
-        case FPROUNDING_POSINF:
-            i = float_round_up;
-            break;
-        case FPROUNDING_NEGINF:
-            i = float_round_down;
-            break;
-        case FPROUNDING_ZERO:
-            i = float_round_to_zero;
-            break;
-        }
-        set_float_rounding_mode(i, &env->vfp.fp_status);
-        set_float_rounding_mode(i, &env->vfp.fp_status_f16);
-    }
-    if (changed & FPCR_FZ16) {
-        bool ftz_enabled = val & FPCR_FZ16;
-        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16);
-        set_flush_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16);
-        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16);
-        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16);
-    }
-    if (changed & FPCR_FZ) {
-        bool ftz_enabled = val & FPCR_FZ;
-        set_flush_to_zero(ftz_enabled, &env->vfp.fp_status);
-        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status);
-    }
-    if (changed & FPCR_DN) {
-        bool dnan_enabled = val & FPCR_DN;
-        set_default_nan_mode(dnan_enabled, &env->vfp.fp_status);
-        set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16);
-    }
-
-    /*
-     * The exception flags are ORed together when we read fpscr so we
-     * only need to preserve the current state in one of our
-     * float_status values.
-     */
-    i = vfp_exceptbits_to_host(val);
-    set_float_exception_flags(i, &env->vfp.fp_status);
-    set_float_exception_flags(0, &env->vfp.fp_status_f16);
-    set_float_exception_flags(0, &env->vfp.standard_fp_status);
-    set_float_exception_flags(0, &env->vfp.standard_fp_status_f16);
-}
-
-#else
-
-static uint32_t vfp_get_fpscr_from_host(CPUARMState *env)
-{
-    return 0;
-}
-
-static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val)
-{
-}
-
-#endif
-
 uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env)
 {
-    uint32_t i, fpscr;
-
-    fpscr = env->vfp.xregs[ARM_VFP_FPSCR]
-            | (env->vfp.vec_len << 16)
-            | (env->vfp.vec_stride << 20);
-
-    /*
-     * M-profile LTPSIZE overlaps A-profile Stride; whichever of the
-     * two is not applicable to this CPU will always be zero.
-     */
-    fpscr |= env->v7m.ltpsize << 16;
-
-    fpscr |= vfp_get_fpscr_from_host(env);
-
-    i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3];
-    fpscr |= i ? FPCR_QC : 0;
-
-    return fpscr;
-}
-
-uint32_t vfp_get_fpscr(CPUARMState *env)
-{
-    return HELPER(vfp_get_fpscr)(env);
+    return vfp_get_fpscr(env);
 }
 
 void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val)
 {
-    /* When ARMv8.2-FP16 is not supported, FZ16 is RES0.  */
-    if (!cpu_isar_feature(any_fp16, env_archcpu(env))) {
-        val &= ~FPCR_FZ16;
-    }
-
-    vfp_set_fpscr_to_host(env, val);
-
-    if (!arm_feature(env, ARM_FEATURE_M)) {
-        /*
-         * Short-vector length and stride; on M-profile these bits
-         * are used for different purposes.
-         * We can't make this conditional be "if MVFR0.FPShVec != 0",
-         * 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);
-    }
-
-    if (arm_feature(env, ARM_FEATURE_NEON)) {
-        /*
-         * The bit we set within fpscr_q is arbitrary; the register as a
-         * whole being zero/non-zero is what counts.
-         * TODO: M-profile MVE also has a QC bit.
-         */
-        env->vfp.qc[0] = val & FPCR_QC;
-        env->vfp.qc[1] = 0;
-        env->vfp.qc[2] = 0;
-        env->vfp.qc[3] = 0;
-    }
-
-    /*
-     * We don't implement trapped exception handling, so the
-     * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!)
-     *
-     * The exception flags IOC|DZC|OFC|UFC|IXC|IDC are stored in
-     * fp_status; QC, Len and Stride are stored separately earlier.
-     * Clear out all of those and the RES0 bits: only NZCV, AHP, DN,
-     * FZ, RMode and FZ16 are kept in vfp.xregs[FPSCR].
-     */
-    env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000;
-}
-
-void vfp_set_fpscr(CPUARMState *env, uint32_t val)
-{
-    HELPER(vfp_set_fpscr)(env, val);
+    vfp_set_fpscr(env, val);
 }
 
 #ifdef CONFIG_TCG
diff --git a/target/arm/meson.build b/target/arm/meson.build
index 1f7375375e..4bc44e1db2 100644
--- a/target/arm/meson.build
+++ b/target/arm/meson.build
@@ -4,6 +4,7 @@  arm_ss.add(files(
   'cpu.c',
   'cpu-common.c',
   'cpu-mmu.c',
+  'cpu-vfp.c',
   'cpustate-list.c',
   'gdbstub.c',
   'cpu_tcg.c',
diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build
index 78c34742ec..64a86fd94c 100644
--- a/target/arm/tcg/meson.build
+++ b/target/arm/tcg/meson.build
@@ -21,6 +21,7 @@  arm_ss.add(when: 'CONFIG_TCG', if_true: files(
   'translate-vfp.c',
   'helper.c',
   'cpregs.c',
+  'cpu-vfp.c',
   'iwmmxt_helper.c',
   'm_helper.c',
   'neon_helper.c',