Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20180301' into staging

target-arm queue:
 * update MAINTAINERS for Alistair's new email address
 * add Arm v8.2 FP16 arithmetic extension for linux-user
 * implement display connector emulation for vexpress board
 * xilinx_spips: Enable only two slaves when reading/writing with stripe
 * xilinx_spips: Use 8 dummy cycles with the QIOR/QIOR4 commands
 * hw: register: Run post_write hook on reset

# gpg: Signature made Thu 01 Mar 2018 11:22:46 GMT
# gpg:                using RSA key 3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20180301: (42 commits)
  MAINTAINERS: Update my email address
  linux-user: Report AArch64 FP16 support via hwcap bits
  target/arm: Enable ARM_V8_FP16 feature bit for the AArch64 "any" CPU
  arm/translate-a64: add all single op FP16 to handle_fp_1src_half
  arm/translate-a64: implement simd_scalar_three_reg_same_fp16
  arm/translate-a64: add all FP16 ops in simd_scalar_pairwise
  arm/translate-a64: add FP16 FMOV to simd_mod_imm
  arm/translate-a64: add FP16 FRSQRTE to simd_two_reg_misc_fp16
  arm/helper.c: re-factor rsqrte and add rsqrte_f16
  arm/translate-a64: add FP16 FSQRT to simd_two_reg_misc_fp16
  arm/translate-a64: add FP16 FRCPX to simd_two_reg_misc_fp16
  arm/translate-a64: add FP16 FRECPE
  arm/helper.c: re-factor recpe and add recepe_f16
  arm/translate-a64: add FP16 FNEG/FABS to simd_two_reg_misc_fp16
  arm/translate-a64: add FP16 SCVTF/UCVFT to simd_two_reg_misc_fp16
  arm/translate-a64: add FP16 FCMxx (zero) to simd_two_reg_misc_fp16
  arm/translate-a64: add FCVTxx to simd_two_reg_misc_fp16
  arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16
  arm/translate-a64: initial decode for simd_two_reg_misc_fp16
  arm/translate-a64: add FP16 x2 ops for simd_indexed
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

MAINTAINERS

@@ -556,7 +556,7 @@ F: hw/misc/arm_sysctl.c
 
 Xilinx Zynq
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-M: Alistair Francis <alistair.francis@xilinx.com>
+M: Alistair Francis <alistair@alistair23.me>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: hw/*/xilinx_*
@@ -566,7 +566,7 @@ F: include/hw/misc/zynq*
 X: hw/ssi/xilinx_*
 
 Xilinx ZynqMP
-M: Alistair Francis <alistair.francis@xilinx.com>
+M: Alistair Francis <alistair@alistair23.me>
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 L: qemu-arm@nongnu.org
 S: Maintained
@@ -1075,7 +1075,7 @@ T: git git://github.com/bonzini/qemu.git scsi-next
 
 SSI
 M: Peter Crosthwaite <crosthwaite.peter@gmail.com>
-M: Alistair Francis <alistair.francis@xilinx.com>
+M: Alistair Francis <alistair@alistair23.me>
 S: Maintained
 F: hw/ssi/*
 F: hw/block/m25p80.c
@@ -1084,7 +1084,7 @@ X: hw/ssi/xilinx_*
 F: tests/m25p80-test.c
 
 Xilinx SPI
-M: Alistair Francis <alistair.francis@xilinx.com>
+M: Alistair Francis <alistair@alistair23.me>
 M: Peter Crosthwaite <crosthwaite.peter@gmail.com>
 S: Maintained
 F: hw/ssi/xilinx_*
@@ -1254,7 +1254,7 @@ S: Maintained
 F: hw/net/eepro100.c
 
 Generic Loader
-M: Alistair Francis <alistair.francis@xilinx.com>
+M: Alistair Francis <alistair@alistair23.me>
 S: Maintained
 F: hw/core/generic-loader.c
 F: include/hw/core/generic-loader.h
@@ -1600,7 +1600,7 @@ F: tests/qmp-test.c
 T: git git://repo.or.cz/qemu/armbru.git qapi-next
 
 Register API
-M: Alistair Francis <alistair.francis@xilinx.com>
+M: Alistair Francis <alistair@alistair23.me>
 S: Maintained
 F: hw/core/register.c
 F: include/hw/register.h

default-configs/arm-softmmu.mak

@@ -21,6 +21,8 @@ CONFIG_STELLARIS_INPUT=y
 CONFIG_STELLARIS_ENET=y
 CONFIG_SSD0303=y
 CONFIG_SSD0323=y
+CONFIG_DDC=y
+CONFIG_SII9022=y
 CONFIG_ADS7846=y
 CONFIG_MAX111X=y
 CONFIG_SSI=y

hw/arm/vexpress.c

@@ -29,6 +29,7 @@
 #include "hw/arm/arm.h"
 #include "hw/arm/primecell.h"
 #include "hw/devices.h"
+#include "hw/i2c/i2c.h"
 #include "net/net.h"
 #include "sysemu/sysemu.h"
 #include "hw/boards.h"
@@ -537,6 +538,7 @@ static void vexpress_common_init(MachineState *machine)
     uint32_t sys_id;
     DriveInfo *dinfo;
     pflash_t *pflash0;
+    I2CBus *i2c;
     ram_addr_t vram_size, sram_size;
     MemoryRegion *sysmem = get_system_memory();
     MemoryRegion *vram = g_new(MemoryRegion, 1);
@@ -628,7 +630,9 @@ static void vexpress_common_init(MachineState *machine)
     sysbus_create_simple("sp804", map[VE_TIMER01], pic[2]);
     sysbus_create_simple("sp804", map[VE_TIMER23], pic[3]);
 
-    /* VE_SERIALDVI: not modelled */
+    dev = sysbus_create_simple("versatile_i2c", map[VE_SERIALDVI], NULL);
+    i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c");
+    i2c_create_slave(i2c, "sii9022", 0x39);
 
     sysbus_create_simple("pl031", map[VE_RTC], pic[4]); /* RTC */
 

hw/core/register.c

@@ -159,13 +159,21 @@ uint64_t register_read(RegisterInfo *reg, uint64_t re, const char* prefix,
 
 void register_reset(RegisterInfo *reg)
 {
+    const RegisterAccessInfo *ac;
+
     g_assert(reg);
 
     if (!reg->data || !reg->access) {
         return;
     }
 
+    ac = reg->access;
+
     register_write_val(reg, reg->access->reset);
+
+    if (ac->post_write) {
+        ac->post_write(reg, reg->access->reset);
+    }
 }
 
 void register_init(RegisterInfo *reg)

hw/display/Makefile.objs

@@ -3,6 +3,7 @@ common-obj-$(CONFIG_VGA_CIRRUS) += cirrus_vga.o
 common-obj-$(CONFIG_G364FB) += g364fb.o
 common-obj-$(CONFIG_JAZZ_LED) += jazz_led.o
 common-obj-$(CONFIG_PL110) += pl110.o
+common-obj-$(CONFIG_SII9022) += sii9022.o
 common-obj-$(CONFIG_SSD0303) += ssd0303.o
 common-obj-$(CONFIG_SSD0323) += ssd0323.o
 common-obj-$(CONFIG_XEN) += xenfb.o

hw/display/sii9022.c

+/*
+ * Silicon Image SiI9022
+ *
+ * This is a pretty hollow emulation: all we do is acknowledge that we
+ * exist (chip ID) and confirm that we get switched over into DDC mode
+ * so the emulated host can proceed to read out EDID data. All subsequent
+ * set-up of connectors etc will be acknowledged and ignored.
+ *
+ * Copyright (C) 2018 Linus Walleij
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "hw/i2c/i2c.h"
+#include "hw/i2c/i2c-ddc.h"
+#include "trace.h"
+
+#define SII9022_SYS_CTRL_DATA 0x1a
+#define SII9022_SYS_CTRL_PWR_DWN 0x10
+#define SII9022_SYS_CTRL_AV_MUTE 0x08
+#define SII9022_SYS_CTRL_DDC_BUS_REQ 0x04
+#define SII9022_SYS_CTRL_DDC_BUS_GRTD 0x02
+#define SII9022_SYS_CTRL_OUTPUT_MODE 0x01
+#define SII9022_SYS_CTRL_OUTPUT_HDMI 1
+#define SII9022_SYS_CTRL_OUTPUT_DVI 0
+#define SII9022_REG_CHIPID 0x1b
+#define SII9022_INT_ENABLE 0x3c
+#define SII9022_INT_STATUS 0x3d
+#define SII9022_INT_STATUS_HOTPLUG 0x01;
+#define SII9022_INT_STATUS_PLUGGED 0x04;
+
+#define TYPE_SII9022 "sii9022"
+#define SII9022(obj) OBJECT_CHECK(sii9022_state, (obj), TYPE_SII9022)
+
+typedef struct sii9022_state {
+    I2CSlave parent_obj;
+    uint8_t ptr;
+    bool addr_byte;
+    bool ddc_req;
+    bool ddc_skip_finish;
+    bool ddc;
+} sii9022_state;
+
+static const VMStateDescription vmstate_sii9022 = {
+    .name = "sii9022",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_I2C_SLAVE(parent_obj, sii9022_state),
+        VMSTATE_UINT8(ptr, sii9022_state),
+        VMSTATE_BOOL(addr_byte, sii9022_state),
+        VMSTATE_BOOL(ddc_req, sii9022_state),
+        VMSTATE_BOOL(ddc_skip_finish, sii9022_state),
+        VMSTATE_BOOL(ddc, sii9022_state),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static int sii9022_event(I2CSlave *i2c, enum i2c_event event)
+{
+    sii9022_state *s = SII9022(i2c);
+
+    switch (event) {
+    case I2C_START_SEND:
+        s->addr_byte = true;
+        break;
+    case I2C_START_RECV:
+        break;
+    case I2C_FINISH:
+        break;
+    case I2C_NACK:
+        break;
+    }
+
+    return 0;
+}
+
+static int sii9022_rx(I2CSlave *i2c)
+{
+    sii9022_state *s = SII9022(i2c);
+    uint8_t res = 0x00;
+
+    switch (s->ptr) {
+    case SII9022_SYS_CTRL_DATA:
+        if (s->ddc_req) {
+            /* Acknowledge DDC bus request */
+            res = SII9022_SYS_CTRL_DDC_BUS_GRTD | SII9022_SYS_CTRL_DDC_BUS_REQ;
+        }
+        break;
+    case SII9022_REG_CHIPID:
+        res = 0xb0;
+        break;
+    case SII9022_INT_STATUS:
+        /* Something is cold-plugged in, no interrupts */
+        res = SII9022_INT_STATUS_PLUGGED;
+        break;
+    default:
+        break;
+    }
+
+    trace_sii9022_read_reg(s->ptr, res);
+    s->ptr++;
+
+    return res;
+}
+
+static int sii9022_tx(I2CSlave *i2c, uint8_t data)
+{
+    sii9022_state *s = SII9022(i2c);
+
+    if (s->addr_byte) {
+        s->ptr = data;
+        s->addr_byte = false;
+        return 0;
+    }
+
+    switch (s->ptr) {
+    case SII9022_SYS_CTRL_DATA:
+        if (data & SII9022_SYS_CTRL_DDC_BUS_REQ) {
+            s->ddc_req = true;
+            if (data & SII9022_SYS_CTRL_DDC_BUS_GRTD) {
+                s->ddc = true;
+                /* Skip this finish since we just switched to DDC */
+                s->ddc_skip_finish = true;
+                trace_sii9022_switch_mode("DDC");
+            }
+        } else {
+            s->ddc_req = false;
+            s->ddc = false;
+            trace_sii9022_switch_mode("normal");
+        }
+        break;
+    default:
+        break;
+    }
+
+    trace_sii9022_write_reg(s->ptr, data);
+    s->ptr++;
+
+    return 0;
+}
+
+static void sii9022_reset(DeviceState *dev)
+{
+    sii9022_state *s = SII9022(dev);
+
+    s->ptr = 0;
+    s->addr_byte = false;
+    s->ddc_req = false;
+    s->ddc_skip_finish = false;
+    s->ddc = false;
+}
+
+static void sii9022_realize(DeviceState *dev, Error **errp)
+{
+    I2CBus *bus;
+
+    bus = I2C_BUS(qdev_get_parent_bus(dev));
+    i2c_create_slave(bus, TYPE_I2CDDC, 0x50);
+}
+
+static void sii9022_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    I2CSlaveClass *k = I2C_SLAVE_CLASS(klass);
+
+    k->event = sii9022_event;
+    k->recv = sii9022_rx;
+    k->send = sii9022_tx;
+    dc->reset = sii9022_reset;
+    dc->realize = sii9022_realize;
+    dc->vmsd = &vmstate_sii9022;
+}
+
+static const TypeInfo sii9022_info = {
+    .name          = TYPE_SII9022,
+    .parent        = TYPE_I2C_SLAVE,
+    .instance_size = sizeof(sii9022_state),
+    .class_init    = sii9022_class_init,
+};
+
+static void sii9022_register_types(void)
+{
+    type_register_static(&sii9022_info);
+}
+
+type_init(sii9022_register_types)

hw/display/trace-events

@@ -132,3 +132,8 @@ vga_cirrus_read_io(uint32_t addr, uint32_t val) "addr 0x%x, val 0x%x"
 vga_cirrus_write_io(uint32_t addr, uint32_t val) "addr 0x%x, val 0x%x"
 vga_cirrus_read_blt(uint32_t offset, uint32_t val) "offset 0x%x, val 0x%x"
 vga_cirrus_write_blt(uint32_t offset, uint32_t val) "offset 0x%x, val 0x%x"
+
+# hw/display/sii9022.c
+sii9022_read_reg(uint8_t addr, uint8_t val) "addr 0x%02x, val 0x%02x"
+sii9022_write_reg(uint8_t addr, uint8_t val) "addr 0x%02x, val 0x%02x"
+sii9022_switch_mode(const char *mode) "mode: %s"

hw/i2c/core.c

@@ -10,31 +10,13 @@
 #include "qemu/osdep.h"
 #include "hw/i2c/i2c.h"
 
-typedef struct I2CNode I2CNode;
-
-struct I2CNode {
-    I2CSlave *elt;
-    QLIST_ENTRY(I2CNode) next;
-};
-
 #define I2C_BROADCAST 0x00
 
-struct I2CBus
-{
-    BusState qbus;
-    QLIST_HEAD(, I2CNode) current_devs;
-    uint8_t saved_address;
-    bool broadcast;
-};
-
 static Property i2c_props[] = {
     DEFINE_PROP_UINT8("address", struct I2CSlave, address, 0),
     DEFINE_PROP_END_OF_LIST(),
 };
 
-#define TYPE_I2C_BUS "i2c-bus"
-#define I2C_BUS(obj) OBJECT_CHECK(I2CBus, (obj), TYPE_I2C_BUS)
-
 static const TypeInfo i2c_bus_info = {
     .name = TYPE_I2C_BUS,
     .parent = TYPE_BUS,

hw/i2c/i2c-ddc.c

@@ -259,12 +259,12 @@ static int i2c_ddc_tx(I2CSlave *i2c, uint8_t data)
         s->reg = data;
         s->firstbyte = false;
         DPRINTF("[EDID] Written new pointer: %u\n", data);
-        return 1;
+        return 0;
     }
 
     /* Ignore all writes */
     s->reg++;
-    return 1;
+    return 0;
 }
 
 static void i2c_ddc_init(Object *obj)

hw/ssi/xilinx_spips.c

@@ -223,7 +223,7 @@ static void xilinx_spips_update_cs(XilinxSPIPS *s, int field)
 {
     int i;
 
-    for (i = 0; i < s->num_cs; i++) {
+    for (i = 0; i < s->num_cs * s->num_busses; i++) {
         bool old_state = s->cs_lines_state[i];
         bool new_state = field & (1 << i);
 
@@ -234,7 +234,7 @@ static void xilinx_spips_update_cs(XilinxSPIPS *s, int field)
         }
         qemu_set_irq(s->cs_lines[i], !new_state);
     }
-    if (!(field & ((1 << s->num_cs) - 1))) {
+    if (!(field & ((1 << (s->num_cs * s->num_busses)) - 1))) {
         s->snoop_state = SNOOP_CHECKING;
         s->cmd_dummies = 0;
         s->link_state = 1;
@@ -248,7 +248,40 @@ static void xlnx_zynqmp_qspips_update_cs_lines(XlnxZynqMPQSPIPS *s)
 {
     if (s->regs[R_GQSPI_GF_SNAPSHOT]) {
         int field = ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, CHIP_SELECT);
-        xilinx_spips_update_cs(XILINX_SPIPS(s), field);
+        bool upper_cs_sel = field & (1 << 1);
+        bool lower_cs_sel = field & 1;
+        bool bus0_enabled;
+        bool bus1_enabled;
+        uint8_t buses;
+        int cs = 0;
+
+        buses = ARRAY_FIELD_EX32(s->regs, GQSPI_GF_SNAPSHOT, DATA_BUS_SELECT);
+        bus0_enabled = buses & 1;
+        bus1_enabled = buses & (1 << 1);
+
+        if (bus0_enabled && bus1_enabled) {
+            if (lower_cs_sel) {
+                cs |= 1;
+            }
+            if (upper_cs_sel) {
+                cs |= 1 << 3;
+            }
+        } else if (bus0_enabled) {
+            if (lower_cs_sel) {
+                cs |= 1;
+            }
+            if (upper_cs_sel) {
+                cs |= 1 << 1;
+            }
+        } else if (bus1_enabled) {
+            if (lower_cs_sel) {
+                cs |= 1 << 2;
+            }
+            if (upper_cs_sel) {
+                cs |= 1 << 3;
+            }
+        }
+        xilinx_spips_update_cs(XILINX_SPIPS(s), cs);
     }
 }
 
@@ -260,7 +293,7 @@ static void xilinx_spips_update_cs_lines(XilinxSPIPS *s)
     if (num_effective_busses(s) == 2) {
         /* Single bit chip-select for qspi */
         field &= 0x1;
-        field |= field << 1;
+        field |= field << 3;
     /* Dual stack U-Page */
     } else if (s->regs[R_LQSPI_CFG] & LQSPI_CFG_TWO_MEM &&
                s->regs[R_LQSPI_STS] & LQSPI_CFG_U_PAGE) {
@@ -544,7 +577,7 @@ static int xilinx_spips_num_dummies(XilinxQSPIPS *qs, uint8_t command)
         return 2;
     case QIOR:
     case QIOR_4:
-        return 5;
+        return 4;
     default:
         return -1;
     }

include/exec/helper-head.h

@@ -26,6 +26,7 @@
 #define dh_alias_int i32
 #define dh_alias_i64 i64
 #define dh_alias_s64 i64
+#define dh_alias_f16 i32
 #define dh_alias_f32 i32
 #define dh_alias_f64 i64
 #define dh_alias_ptr ptr
@@ -38,6 +39,7 @@
 #define dh_ctype_int int
 #define dh_ctype_i64 uint64_t
 #define dh_ctype_s64 int64_t
+#define dh_ctype_f16 float16
 #define dh_ctype_f32 float32
 #define dh_ctype_f64 float64
 #define dh_ctype_ptr void *
@@ -94,6 +96,7 @@
 #define dh_is_signed_s32 1
 #define dh_is_signed_i64 0
 #define dh_is_signed_s64 1
+#define dh_is_signed_f16 0
 #define dh_is_signed_f32 0
 #define dh_is_signed_f64 0
 #define dh_is_signed_tl  0

include/fpu/softfloat.h

@@ -306,8 +306,11 @@ static inline float16 float16_set_sign(float16 a, int sign)
 }
 
 #define float16_zero make_float16(0)
-#define float16_one make_float16(0x3c00)
 #define float16_half make_float16(0x3800)
+#define float16_one make_float16(0x3c00)
+#define float16_one_point_five make_float16(0x3e00)
+#define float16_two make_float16(0x4000)
+#define float16_three make_float16(0x4200)
 #define float16_infinity make_float16(0x7c00)
 
 /*----------------------------------------------------------------------------
@@ -415,11 +418,13 @@ static inline float32 float32_set_sign(float32 a, int sign)
 }
 
 #define float32_zero make_float32(0)
-#define float32_one make_float32(0x3f800000)
 #define float32_half make_float32(0x3f000000)
+#define float32_one make_float32(0x3f800000)
+#define float32_one_point_five make_float32(0x3fc00000)
+#define float32_two make_float32(0x40000000)
+#define float32_three make_float32(0x40400000)
 #define float32_infinity make_float32(0x7f800000)
 
-
 /*----------------------------------------------------------------------------
 | The pattern for a default generated single-precision NaN.
 *----------------------------------------------------------------------------*/
@@ -526,9 +531,12 @@ static inline float64 float64_set_sign(float64 a, int sign)
 }
 
 #define float64_zero make_float64(0)
+#define float64_half make_float64(0x3fe0000000000000LL)
 #define float64_one make_float64(0x3ff0000000000000LL)
+#define float64_one_point_five make_float64(0x3FF8000000000000ULL)
+#define float64_two make_float64(0x4000000000000000ULL)
+#define float64_three make_float64(0x4008000000000000ULL)
 #define float64_ln2 make_float64(0x3fe62e42fefa39efLL)
-#define float64_half make_float64(0x3fe0000000000000LL)
 #define float64_infinity make_float64(0x7ff0000000000000LL)
 
 /*----------------------------------------------------------------------------

include/hw/i2c/i2c.h

@@ -25,8 +25,7 @@ typedef struct I2CSlave I2CSlave;
 #define I2C_SLAVE_GET_CLASS(obj) \
      OBJECT_GET_CLASS(I2CSlaveClass, (obj), TYPE_I2C_SLAVE)
 
-typedef struct I2CSlaveClass
-{
+typedef struct I2CSlaveClass {
     DeviceClass parent_class;
 
     /* Callbacks provided by the device.  */
@@ -50,14 +49,30 @@ typedef struct I2CSlaveClass
     int (*event)(I2CSlave *s, enum i2c_event event);
 } I2CSlaveClass;
 
-struct I2CSlave
-{
+struct I2CSlave {
     DeviceState qdev;
 
     /* Remaining fields for internal use by the I2C code.  */
     uint8_t address;
 };
 
+#define TYPE_I2C_BUS "i2c-bus"
+#define I2C_BUS(obj) OBJECT_CHECK(I2CBus, (obj), TYPE_I2C_BUS)
+
+typedef struct I2CNode I2CNode;
+
+struct I2CNode {
+    I2CSlave *elt;
+    QLIST_ENTRY(I2CNode) next;
+};
+
+struct I2CBus {
+    BusState qbus;
+    QLIST_HEAD(, I2CNode) current_devs;
+    uint8_t saved_address;
+    bool broadcast;
+};
+
 I2CBus *i2c_init_bus(DeviceState *parent, const char *name);
 void i2c_set_slave_address(I2CSlave *dev, uint8_t address);
 int i2c_bus_busy(I2CBus *bus);

include/hw/register.h

@@ -34,7 +34,7 @@ typedef struct RegisterInfoArray RegisterInfoArray;
  * immediately before the actual write. The returned value is what is written,
  * giving the handler a chance to modify the written value.
  * @post_write: Post write callback. Passed the written value. Most write side
- * effects should be implemented here.
+ * effects should be implemented here. This is called during device reset.
  *
  * @post_read: Post read callback. Passes the value that is about to be returned
  * for a read. The return value from this function is what is ultimately read,
@@ -135,8 +135,8 @@ uint64_t register_read(RegisterInfo *reg, uint64_t re, const char* prefix,
                        bool debug);
 
 /**
- * reset a register
- * @reg: register to reset
+ * Resets a register. This will also call the post_write hook if it exists.
+ * @reg: The register to reset.
  */
 
 void register_reset(RegisterInfo *reg);

linux-user/elfload.c

@@ -551,6 +551,8 @@ static uint32_t get_elf_hwcap(void)
     GET_FEATURE(ARM_FEATURE_V8_SM3, ARM_HWCAP_A64_SM3);
     GET_FEATURE(ARM_FEATURE_V8_SM4, ARM_HWCAP_A64_SM4);
     GET_FEATURE(ARM_FEATURE_V8_SHA512, ARM_HWCAP_A64_SHA512);
+    GET_FEATURE(ARM_FEATURE_V8_FP16,
+                ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP);
 #undef GET_FEATURE
 
     return hwcaps;

target/arm/cpu.h

@@ -168,6 +168,7 @@ typedef struct {
  *  Qn = regs[n].d[1]:regs[n].d[0]
  *  Dn = regs[n].d[0]
  *  Sn = regs[n].d[0] bits 31..0
+ *  Hn = regs[n].d[0] bits 15..0
  *
  * This corresponds to the architecturally defined mapping between
  * the two execution states, and means we do not need to explicitly
@@ -537,19 +538,29 @@ typedef struct CPUARMState {
         /* scratch space when Tn are not sufficient.  */
         uint32_t scratch[8];
 
-        /* fp_status is the "normal" fp status. standard_fp_status retains
-         * values corresponding to the ARM "Standard FPSCR Value", ie
-         * default-NaN, flush-to-zero, round-to-nearest and is used by
-         * any operations (generally Neon) which the architecture defines
-         * as controlled by the standard FPSCR value rather than the FPSCR.
+        /* There are a number of distinct float control structures:
+         *
+         *  fp_status: is the "normal" fp status.
+         *  fp_status_fp16: used for half-precision calculations
+         *  standard_fp_status : the ARM "Standard FPSCR Value"
+         *
+         * Half-precision operations are governed by a separate
+         * flush-to-zero control bit in FPSCR:FZ16. We pass a separate
+         * status structure to control this.
+         *
+         * The "Standard FPSCR", ie default-NaN, flush-to-zero,
+         * round-to-nearest and is used by any operations (generally
+         * Neon) which the architecture defines as controlled by the
+         * standard FPSCR value rather than the FPSCR.
          *
          * 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 two fp statuses. This relies on the
+         * OR of the flags in the three fp statuses. This relies on the
          * only thing which needs to read the exception flags being
          * an explicit FPSCR read.
          */
         float_status fp_status;
+        float_status fp_status_f16;
         float_status standard_fp_status;
 
         /* ZCR_EL[1-3] */
@@ -1189,12 +1200,20 @@ static inline void xpsr_write(CPUARMState *env, uint32_t val, uint32_t mask)
 uint32_t vfp_get_fpscr(CPUARMState *env);
 void vfp_set_fpscr(CPUARMState *env, uint32_t val);
 
-/* For A64 the FPSCR is split into two logically distinct registers,
+/* FPCR, Floating Point Control Register
+ * FPSR, Floating Poiht Status Register
+ *
+ * For A64 the FPSCR is split into two logically distinct registers,
  * FPCR and FPSR. However since they still use non-overlapping bits
  * we store the underlying state in fpscr and just mask on read/write.
  */
 #define FPSR_MASK 0xf800009f
 #define FPCR_MASK 0x07f79f00
+
+#define FPCR_FZ16   (1 << 19)   /* ARMv8.2+, FP16 flush-to-zero */
+#define FPCR_FZ     (1 << 24)   /* Flush-to-zero enable bit */
+#define FPCR_DN     (1 << 25)   /* Default NaN enable bit */
+
 static inline uint32_t vfp_get_fpsr(CPUARMState *env)
 {
     return vfp_get_fpscr(env) & FPSR_MASK;
@@ -1408,6 +1427,7 @@ enum arm_features {
     ARM_FEATURE_V8_SHA3, /* implements SHA3 part of v8 Crypto Extensions */
     ARM_FEATURE_V8_SM3, /* implements SM3 part of v8 Crypto Extensions */
     ARM_FEATURE_V8_SM4, /* implements SM4 part of v8 Crypto Extensions */
+    ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */
 };
 
 static inline int arm_feature(CPUARMState *env, int feature)

target/arm/cpu64.c

@@ -230,6 +230,7 @@ static void aarch64_any_initfn(Object *obj)
     set_feature(&cpu->env, ARM_FEATURE_V8_SM4);
     set_feature(&cpu->env, ARM_FEATURE_V8_PMULL);
     set_feature(&cpu->env, ARM_FEATURE_CRC);
+    set_feature(&cpu->env, ARM_FEATURE_V8_FP16);
     cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */
     cpu->dcz_blocksize = 7; /*  512 bytes */
 }

target/arm/helper-a64.c

@@ -192,6 +192,10 @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp)
  * versions, these do a fully fused multiply-add or
  * multiply-add-and-halve.
  */
+#define float16_two make_float16(0x4000)
+#define float16_three make_float16(0x4200)
+#define float16_one_point_five make_float16(0x3e00)
+
 #define float32_two make_float32(0x40000000)
 #define float32_three make_float32(0x40400000)
 #define float32_one_point_five make_float32(0x3fc00000)
@@ -200,6 +204,21 @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp)
 #define float64_three make_float64(0x4008000000000000ULL)
 #define float64_one_point_five make_float64(0x3FF8000000000000ULL)
 
+float16 HELPER(recpsf_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+
+    a = float16_squash_input_denormal(a, fpst);
+    b = float16_squash_input_denormal(b, fpst);
+
+    a = float16_chs(a);
+    if ((float16_is_infinity(a) && float16_is_zero(b)) ||
+        (float16_is_infinity(b) && float16_is_zero(a))) {
+        return float16_two;
+    }
+    return float16_muladd(a, b, float16_two, 0, fpst);
+}
+
 float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp)
 {
     float_status *fpst = fpstp;
@@ -230,6 +249,21 @@ float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp)
     return float64_muladd(a, b, float64_two, 0, fpst);
 }
 
+float16 HELPER(rsqrtsf_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+
+    a = float16_squash_input_denormal(a, fpst);
+    b = float16_squash_input_denormal(b, fpst);
+
+    a = float16_chs(a);
+    if ((float16_is_infinity(a) && float16_is_zero(b)) ||
+        (float16_is_infinity(b) && float16_is_zero(a))) {
+        return float16_one_point_five;
+    }
+    return float16_muladd(a, b, float16_three, float_muladd_halve_result, fpst);
+}
+
 float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp)
 {
     float_status *fpst = fpstp;
@@ -322,6 +356,35 @@ uint64_t HELPER(neon_addlp_u16)(uint64_t a)
 }
 
 /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */
+float16 HELPER(frecpx_f16)(float16 a, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    uint16_t val16, sbit;
+    int16_t exp;
+
+    if (float16_is_any_nan(a)) {
+        float16 nan = a;
+        if (float16_is_signaling_nan(a, fpst)) {
+            float_raise(float_flag_invalid, fpst);
+            nan = float16_maybe_silence_nan(a, fpst);
+        }
+        if (fpst->default_nan_mode) {
+            nan = float16_default_nan(fpst);
+        }
+        return nan;
+    }
+
+    val16 = float16_val(a);
+    sbit = 0x8000 & val16;
+    exp = extract32(val16, 10, 5);
+
+    if (exp == 0) {
+        return make_float16(deposit32(sbit, 10, 5, 0x1e));
+    } else {
+        return make_float16(deposit32(sbit, 10, 5, ~exp));
+    }
+}
+
 float32 HELPER(frecpx_f32)(float32 a, void *fpstp)
 {
     float_status *fpst = fpstp;
@@ -572,3 +635,209 @@ uint64_t HELPER(paired_cmpxchg64_be_parallel)(CPUARMState *env, uint64_t addr,
 {
     return do_paired_cmpxchg64_be(env, addr, new_lo, new_hi, true, GETPC());
 }
+
+/*
+ * AdvSIMD half-precision
+ */
+
+#define ADVSIMD_HELPER(name, suffix) HELPER(glue(glue(advsimd_, name), suffix))
+
+#define ADVSIMD_HALFOP(name) \
+float16 ADVSIMD_HELPER(name, h)(float16 a, float16 b, void *fpstp) \
+{ \
+    float_status *fpst = fpstp; \
+    return float16_ ## name(a, b, fpst);    \
+}
+
+ADVSIMD_HALFOP(add)
+ADVSIMD_HALFOP(sub)
+ADVSIMD_HALFOP(mul)
+ADVSIMD_HALFOP(div)
+ADVSIMD_HALFOP(min)
+ADVSIMD_HALFOP(max)
+ADVSIMD_HALFOP(minnum)
+ADVSIMD_HALFOP(maxnum)
+
+#define ADVSIMD_TWOHALFOP(name)                                         \
+uint32_t ADVSIMD_HELPER(name, 2h)(uint32_t two_a, uint32_t two_b, void *fpstp) \
+{ \
+    float16  a1, a2, b1, b2;                        \
+    uint32_t r1, r2;                                \
+    float_status *fpst = fpstp;                     \
+    a1 = extract32(two_a, 0, 16);                   \
+    a2 = extract32(two_a, 16, 16);                  \
+    b1 = extract32(two_b, 0, 16);                   \
+    b2 = extract32(two_b, 16, 16);                  \
+    r1 = float16_ ## name(a1, b1, fpst);            \
+    r2 = float16_ ## name(a2, b2, fpst);            \
+    return deposit32(r1, 16, 16, r2);               \
+}
+
+ADVSIMD_TWOHALFOP(add)
+ADVSIMD_TWOHALFOP(sub)
+ADVSIMD_TWOHALFOP(mul)
+ADVSIMD_TWOHALFOP(div)
+ADVSIMD_TWOHALFOP(min)
+ADVSIMD_TWOHALFOP(max)
+ADVSIMD_TWOHALFOP(minnum)
+ADVSIMD_TWOHALFOP(maxnum)
+
+/* Data processing - scalar floating-point and advanced SIMD */
+static float16 float16_mulx(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+
+    a = float16_squash_input_denormal(a, fpst);
+    b = float16_squash_input_denormal(b, fpst);
+
+    if ((float16_is_zero(a) && float16_is_infinity(b)) ||
+        (float16_is_infinity(a) && float16_is_zero(b))) {
+        /* 2.0 with the sign bit set to sign(A) XOR sign(B) */
+        return make_float16((1U << 14) |
+                            ((float16_val(a) ^ float16_val(b)) & (1U << 15)));
+    }
+    return float16_mul(a, b, fpst);
+}
+
+ADVSIMD_HALFOP(mulx)
+ADVSIMD_TWOHALFOP(mulx)
+
+/* fused multiply-accumulate */
+float16 HELPER(advsimd_muladdh)(float16 a, float16 b, float16 c, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    return float16_muladd(a, b, c, 0, fpst);
+}
+
+uint32_t HELPER(advsimd_muladd2h)(uint32_t two_a, uint32_t two_b,
+                                  uint32_t two_c, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    float16  a1, a2, b1, b2, c1, c2;
+    uint32_t r1, r2;
+    a1 = extract32(two_a, 0, 16);
+    a2 = extract32(two_a, 16, 16);
+    b1 = extract32(two_b, 0, 16);
+    b2 = extract32(two_b, 16, 16);
+    c1 = extract32(two_c, 0, 16);
+    c2 = extract32(two_c, 16, 16);
+    r1 = float16_muladd(a1, b1, c1, 0, fpst);
+    r2 = float16_muladd(a2, b2, c2, 0, fpst);
+    return deposit32(r1, 16, 16, r2);
+}
+
+/*
+ * Floating point comparisons produce an integer result. Softfloat
+ * routines return float_relation types which we convert to the 0/-1
+ * Neon requires.
+ */
+
+#define ADVSIMD_CMPRES(test) (test) ? 0xffff : 0
+
+uint32_t HELPER(advsimd_ceq_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    int compare = float16_compare_quiet(a, b, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_equal);
+}
+
+uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    int compare = float16_compare(a, b, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater ||
+                          compare == float_relation_equal);
+}
+
+uint32_t HELPER(advsimd_cgt_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    int compare = float16_compare(a, b, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater);
+}
+
+uint32_t HELPER(advsimd_acge_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    float16 f0 = float16_abs(a);
+    float16 f1 = float16_abs(b);
+    int compare = float16_compare(f0, f1, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater ||
+                          compare == float_relation_equal);
+}
+
+uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    float16 f0 = float16_abs(a);
+    float16 f1 = float16_abs(b);
+    int compare = float16_compare(f0, f1, fpst);
+    return ADVSIMD_CMPRES(compare == float_relation_greater);
+}
+
+/* round to integral */
+float16 HELPER(advsimd_rinth_exact)(float16 x, void *fp_status)
+{
+    return float16_round_to_int(x, fp_status);
+}
+
+float16 HELPER(advsimd_rinth)(float16 x, void *fp_status)
+{
+    int old_flags = get_float_exception_flags(fp_status), new_flags;
+    float16 ret;
+
+    ret = float16_round_to_int(x, fp_status);
+
+    /* Suppress any inexact exceptions the conversion produced */
+    if (!(old_flags & float_flag_inexact)) {
+        new_flags = get_float_exception_flags(fp_status);
+        set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status);
+    }
+
+    return ret;
+}
+
+/*
+ * Half-precision floating point conversion functions
+ *
+ * There are a multitude of conversion functions with various
+ * different rounding modes. This is dealt with by the calling code
+ * setting the mode appropriately before calling the helper.
+ */
+
+uint32_t HELPER(advsimd_f16tosinth)(float16 a, void *fpstp)
+{
+    float_status *fpst = fpstp;
+
+    /* Invalid if we are passed a NaN */
+    if (float16_is_any_nan(a)) {
+        float_raise(float_flag_invalid, fpst);
+        return 0;
+    }
+    return float16_to_int16(a, fpst);
+}
+
+uint32_t HELPER(advsimd_f16touinth)(float16 a, void *fpstp)
+{
+    float_status *fpst = fpstp;
+
+    /* Invalid if we are passed a NaN */
+    if (float16_is_any_nan(a)) {
+        float_raise(float_flag_invalid, fpst);
+        return 0;
+    }
+    return float16_to_uint16(a, fpst);
+}
+
+/*
+ * Square Root and Reciprocal square root
+ */
+
+float16 HELPER(sqrt_f16)(float16 a, void *fpstp)
+{
+    float_status *s = fpstp;
+
+    return float16_sqrt(a, s);
+}
+
+

target/arm/helper-a64.h

@@ -29,8 +29,10 @@ DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
 DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
 DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
 DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr)
+DEF_HELPER_FLAGS_3(recpsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
 DEF_HELPER_FLAGS_3(recpsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
 DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
+DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
 DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr)
 DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr)
 DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64)
@@ -39,6 +41,7 @@ DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64)
 DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64)
 DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
 DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
+DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, ptr)
 DEF_HELPER_FLAGS_2(fcvtx_f64_to_f32, TCG_CALL_NO_RWG, f32, f64, env)
 DEF_HELPER_FLAGS_3(crc32_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32)
 DEF_HELPER_FLAGS_3(crc32c_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32)
@@ -48,3 +51,33 @@ DEF_HELPER_FLAGS_4(paired_cmpxchg64_le_parallel, TCG_CALL_NO_WG,
 DEF_HELPER_FLAGS_4(paired_cmpxchg64_be, TCG_CALL_NO_WG, i64, env, i64, i64, i64)
 DEF_HELPER_FLAGS_4(paired_cmpxchg64_be_parallel, TCG_CALL_NO_WG,
                    i64, env, i64, i64, i64)
+DEF_HELPER_FLAGS_3(advsimd_maxh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
+DEF_HELPER_FLAGS_3(advsimd_minh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
+DEF_HELPER_FLAGS_3(advsimd_maxnumh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
+DEF_HELPER_FLAGS_3(advsimd_minnumh, TCG_CALL_NO_RWG, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_addh, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_subh, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_mulh, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_divh, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_ceq_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_cge_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_cgt_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_acge_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_acgt_f16, i32, f16, f16, ptr)
+DEF_HELPER_3(advsimd_mulxh, f16, f16, f16, ptr)
+DEF_HELPER_4(advsimd_muladdh, f16, f16, f16, f16, ptr)
+DEF_HELPER_3(advsimd_add2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_sub2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_mul2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_div2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_max2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_min2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_maxnum2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_minnum2h, i32, i32, i32, ptr)
+DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, ptr)
+DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, ptr)
+DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr)
+DEF_HELPER_2(advsimd_rinth, f16, f16, ptr)
+DEF_HELPER_2(advsimd_f16tosinth, i32, f16, ptr)
+DEF_HELPER_2(advsimd_f16touinth, i32, f16, ptr)
+DEF_HELPER_2(sqrt_f16, f16, f16, ptr)

target/arm/helper.h

@@ -120,17 +120,23 @@ 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_2(vfp_uitoh, f16, i32, ptr)
 DEF_HELPER_2(vfp_uitos, f32, i32, ptr)
 DEF_HELPER_2(vfp_uitod, f64, i32, ptr)
+DEF_HELPER_2(vfp_sitoh, f16, i32, ptr)
 DEF_HELPER_2(vfp_sitos, f32, i32, ptr)
 DEF_HELPER_2(vfp_sitod, f64, i32, ptr)
 
+DEF_HELPER_2(vfp_touih, i32, f16, ptr)
 DEF_HELPER_2(vfp_touis, i32, f32, ptr)
 DEF_HELPER_2(vfp_touid, i32, f64, ptr)
+DEF_HELPER_2(vfp_touizh, i32, f16, ptr)
 DEF_HELPER_2(vfp_touizs, i32, f32, ptr)
 DEF_HELPER_2(vfp_touizd, i32, f64, ptr)
+DEF_HELPER_2(vfp_tosih, i32, f16, ptr)
 DEF_HELPER_2(vfp_tosis, i32, f32, ptr)
 DEF_HELPER_2(vfp_tosid, i32, f64, ptr)
+DEF_HELPER_2(vfp_tosizh, i32, f16, ptr)
 DEF_HELPER_2(vfp_tosizs, i32, f32, ptr)
 DEF_HELPER_2(vfp_tosizd, i32, f64, ptr)
 
@@ -142,6 +148,8 @@ DEF_HELPER_3(vfp_toshd_round_to_zero, i64, f64, i32, ptr)
 DEF_HELPER_3(vfp_tosld_round_to_zero, i64, f64, i32, ptr)
 DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, ptr)
 DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, ptr)
+DEF_HELPER_3(vfp_toulh, i32, f16, i32, ptr)
+DEF_HELPER_3(vfp_toslh, i32, f16, i32, ptr)
 DEF_HELPER_3(vfp_toshs, i32, f32, i32, ptr)
 DEF_HELPER_3(vfp_tosls, i32, f32, i32, ptr)
 DEF_HELPER_3(vfp_tosqs, i64, f32, i32, ptr)
@@ -166,8 +174,10 @@ DEF_HELPER_3(vfp_sqtod, f64, i64, i32, ptr)
 DEF_HELPER_3(vfp_uhtod, f64, i64, i32, ptr)
 DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr)
 DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr)
+DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr)
+DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr)
 
-DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, env)
+DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr)
 DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env)
 
 DEF_HELPER_2(vfp_fcvt_f16_to_f32, f32, i32, env)
@@ -182,8 +192,10 @@ DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr)
 
 DEF_HELPER_3(recps_f32, f32, f32, f32, env)
 DEF_HELPER_3(rsqrts_f32, f32, f32, f32, env)
+DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr)
 DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
 DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
+DEF_HELPER_FLAGS_2(rsqrte_f16, TCG_CALL_NO_RWG, f16, f16, ptr)
 DEF_HELPER_FLAGS_2(rsqrte_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
 DEF_HELPER_FLAGS_2(rsqrte_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
 DEF_HELPER_2(recpe_u32, i32, i32, ptr)

target/arm/translate.c

@@ -3143,7 +3143,7 @@ static int handle_vrint(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
     TCGv_i32 tcg_rmode;
 
     tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding));
-    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
 
     if (dp) {
         TCGv_i64 tcg_op;
@@ -3167,7 +3167,7 @@ static int handle_vrint(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
         tcg_temp_free_i32(tcg_res);
     }
 
-    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
     tcg_temp_free_i32(tcg_rmode);
 
     tcg_temp_free_ptr(fpst);
@@ -3184,7 +3184,7 @@ static int handle_vcvt(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
     tcg_shift = tcg_const_i32(0);
 
     tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding));
-    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
 
     if (dp) {
         TCGv_i64 tcg_double, tcg_res;
@@ -3222,7 +3222,7 @@ static int handle_vcvt(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
         tcg_temp_free_i32(tcg_single);
     }
 
-    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
     tcg_temp_free_i32(tcg_rmode);
 
     tcg_temp_free_i32(tcg_shift);
@@ -3892,13 +3892,13 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
                         TCGv_ptr fpst = get_fpstatus_ptr(0);
                         TCGv_i32 tcg_rmode;
                         tcg_rmode = tcg_const_i32(float_round_to_zero);
-                        gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+                        gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
                         if (dp) {
                             gen_helper_rintd(cpu_F0d, cpu_F0d, fpst);
                         } else {
                             gen_helper_rints(cpu_F0s, cpu_F0s, fpst);
                         }
-                        gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+                        gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst);
                         tcg_temp_free_i32(tcg_rmode);
                         tcg_temp_free_ptr(fpst);
                         break;