Arm queue -- I have more stuff pending but I prefer to push this first lot out and keep the pull below 50 patches. Most of this is Alex's FP16 support work. -- PMM The following changes since commit 6697439794f72b3501ee16bb95d16854f9981421: Merge remote-tracking branch 'remotes/kraxel/tags/usb-20180227-pull-request' into staging (2018-02-27 17:50:46 +0000) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180301 for you to fetch changes up to c22e580c2ad1cccef582e1490e732f254d4ac064: MAINTAINERS: Update my email address (2018-03-01 11:13:59 +0000) ---------------------------------------------------------------- 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 ---------------------------------------------------------------- Alex Bennée (31): include/exec/helper-head.h: support f16 in helper calls target/arm/cpu64: introduce ARM_V8_FP16 feature bit target/arm/cpu.h: update comment for half-precision values target/arm/cpu.h: add additional float_status flags target/arm/helper: pass explicit fpst to set_rmode arm/translate-a64: implement half-precision F(MIN|MAX)(V|NMV) arm/translate-a64: handle_3same_64 comment fix arm/translate-a64: initial decode for simd_three_reg_same_fp16 arm/translate-a64: add FP16 FADD/FABD/FSUB/FMUL/FDIV to simd_three_reg_same_fp16 arm/translate-a64: add FP16 F[A]C[EQ/GE/GT] to simd_three_reg_same_fp16 arm/translate-a64: add FP16 FMULA/X/S to simd_three_reg_same_fp16 arm/translate-a64: add FP16 FR[ECP/SQRT]S to simd_three_reg_same_fp16 arm/translate-a64: add FP16 pairwise ops simd_three_reg_same_fp16 arm/translate-a64: add FP16 FMULX/MLS/FMLA to simd_indexed arm/translate-a64: add FP16 x2 ops for simd_indexed arm/translate-a64: initial decode for simd_two_reg_misc_fp16 arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16 arm/translate-a64: add FCVTxx to simd_two_reg_misc_fp16 arm/translate-a64: add FP16 FCMxx (zero) to simd_two_reg_misc_fp16 arm/translate-a64: add FP16 SCVTF/UCVFT to simd_two_reg_misc_fp16 arm/translate-a64: add FP16 FNEG/FABS to simd_two_reg_misc_fp16 arm/helper.c: re-factor recpe and add recepe_f16 arm/translate-a64: add FP16 FRECPE arm/translate-a64: add FP16 FRCPX to simd_two_reg_misc_fp16 arm/translate-a64: add FP16 FSQRT to simd_two_reg_misc_fp16 arm/helper.c: re-factor rsqrte and add rsqrte_f16 arm/translate-a64: add FP16 FRSQRTE to simd_two_reg_misc_fp16 arm/translate-a64: add FP16 FMOV to simd_mod_imm arm/translate-a64: add all FP16 ops in simd_scalar_pairwise arm/translate-a64: implement simd_scalar_three_reg_same_fp16 arm/translate-a64: add all single op FP16 to handle_fp_1src_half Alistair Francis (2): hw: register: Run post_write hook on reset MAINTAINERS: Update my email address Corey Minyard (2): i2c: Fix some brace style issues i2c: Move the bus class to i2c.h Francisco Iglesias (2): xilinx_spips: Enable only two slaves when reading/writing with stripe xilinx_spips: Use 8 dummy cycles with the QIOR/QIOR4 commands Linus Walleij (3): hw/i2c-ddc: Do not fail writes hw/sii9022: Add support for Silicon Image SII9022 arm/vexpress: Add proper display connector emulation Peter Maydell (2): target/arm: Enable ARM_V8_FP16 feature bit for the AArch64 "any" CPU linux-user: Report AArch64 FP16 support via hwcap bits hw/display/Makefile.objs | 1 + include/exec/helper-head.h | 3 + include/fpu/softfloat.h | 18 +- include/hw/i2c/i2c.h | 23 +- include/hw/register.h | 6 +- target/arm/cpu.h | 34 +- target/arm/helper-a64.h | 33 + target/arm/helper.h | 14 +- hw/arm/vexpress.c | 6 +- hw/core/register.c | 8 + hw/display/sii9022.c | 191 ++++++ hw/i2c/core.c | 18 - hw/i2c/i2c-ddc.c | 4 +- hw/ssi/xilinx_spips.c | 43 +- linux-user/elfload.c | 2 + target/arm/cpu64.c | 1 + target/arm/helper-a64.c | 269 +++++++++ target/arm/helper.c | 481 ++++++++------- target/arm/translate-a64.c | 1266 +++++++++++++++++++++++++++++++++------ target/arm/translate.c | 12 +- MAINTAINERS | 12 +- default-configs/arm-softmmu.mak | 2 + hw/display/trace-events | 5 + 23 files changed, 1981 insertions(+), 471 deletions(-) create mode 100644 hw/display/sii9022.c From: Alistair Francis <alistair.francis@xilinx.com> Ensure that the post write hook is called during reset. This allows us to rely on the post write functions instead of having to call them from the reset() function. Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: d131e24b911653a945e46ca2d8f90f572469e1dd.1517856214.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/register.h | 6 +++--- hw/core/register.c | 8 ++++++++ 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/include/hw/register.h b/include/hw/register.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/register.h +++ b/include/hw/register.h @@ -XXX,XX +XXX,XX @@ 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, @@ -XXX,XX +XXX,XX @@ 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); diff --git a/hw/core/register.c b/hw/core/register.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/register.c +++ b/hw/core/register.c @@ -XXX,XX +XXX,XX @@ 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) -- 2.16.2 From: Francisco Iglesias <frasse.iglesias@gmail.com> Assert only the lower cs on bus 0 and upper cs on bus 1 when both buses and chip selects are enabled (e.g reading/writing with stripe). Signed-off-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Tested-by: Alistair Francis <alistair.francis@xilinx.com> Message-id: 20180223232233.31482-2-frasse.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/xilinx_spips.c | 41 +++++++++++++++++++++++++++++++++++++---- 1 file changed, 37 insertions(+), 4 deletions(-) diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/xilinx_spips.c +++ b/hw/ssi/xilinx_spips.c @@ -XXX,XX +XXX,XX @@ 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); @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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); } } @@ -XXX,XX +XXX,XX @@ 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) { -- 2.16.2 From: Francisco Iglesias <frasse.iglesias@gmail.com> Use 8 dummy cycles (4 dummy bytes) with the QIOR/QIOR4 commands in legacy mode for matching what is expected by Micron (Numonyx) flashes (the default target flash type of the QSPI). Signed-off-by: Francisco Iglesias <frasse.iglesias@gmail.com> Tested-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Message-id: 20180223232233.31482-3-frasse.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/xilinx_spips.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/xilinx_spips.c +++ b/hw/ssi/xilinx_spips.c @@ -XXX,XX +XXX,XX @@ 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; } -- 2.16.2 From: Corey Minyard <cminyard@mvista.com> Signed-off-by: Corey Minyard <cminyard@mvista.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Message-id: 20180227104903.21353-2-linus.walleij@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/i2c/i2c.h | 6 ++---- hw/i2c/core.c | 3 +-- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/include/hw/i2c/i2c.h b/include/hw/i2c/i2c.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/i2c.h +++ b/include/hw/i2c/i2c.h @@ -XXX,XX +XXX,XX @@ 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. */ @@ -XXX,XX +XXX,XX @@ 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. */ diff --git a/hw/i2c/core.c b/hw/i2c/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/core.c +++ b/hw/i2c/core.c @@ -XXX,XX +XXX,XX @@ struct I2CNode { #define I2C_BROADCAST 0x00 -struct I2CBus -{ +struct I2CBus { BusState qbus; QLIST_HEAD(, I2CNode) current_devs; uint8_t saved_address; -- 2.16.2 From: Corey Minyard <cminyard@mvista.com> Some devices need access to it. Signed-off-by: Corey Minyard <cminyard@mvista.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Message-id: 20180227104903.21353-3-linus.walleij@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/i2c/i2c.h | 17 +++++++++++++++++ hw/i2c/core.c | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/include/hw/i2c/i2c.h b/include/hw/i2c/i2c.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/i2c.h +++ b/include/hw/i2c/i2c.h @@ -XXX,XX +XXX,XX @@ struct I2CSlave { 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); diff --git a/hw/i2c/core.c b/hw/i2c/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/core.c +++ b/hw/i2c/core.c @@ -XXX,XX +XXX,XX @@ #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, -- 2.16.2 From: Linus Walleij <linus.walleij@linaro.org> The tx function of the DDC I2C slave emulation was returning 1 on all writes resulting in NACK in the I2C bus. Changing it to 0 makes the DDC I2C work fine with bit-banged I2C such as the versatile I2C. I guess it was not affecting whatever I2C controller this was used with until now, but with the Versatile I2C it surely does not work. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Message-id: 20180227104903.21353-4-linus.walleij@linaro.org Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/i2c-ddc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/i2c/i2c-ddc.c b/hw/i2c/i2c-ddc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/i2c-ddc.c +++ b/hw/i2c/i2c-ddc.c @@ -XXX,XX +XXX,XX @@ 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) -- 2.16.2 From: Linus Walleij <linus.walleij@linaro.org> This adds support for emulating the Silicon Image SII9022 DVI/HDMI bridge. It's not very clever right now, it just acknowledges the switch into DDC I2C mode and back. Combining this with the existing DDC I2C emulation gives the right behavior on the Versatile Express emulation passing through the QEMU EDID to the emulated platform. Cc: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Message-id: 20180227104903.21353-5-linus.walleij@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: explictly reset ddc_req/ddc_skip_finish/ddc] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/Makefile.objs | 1 + hw/display/sii9022.c | 191 +++++++++++++++++++++++++++++++++++++++++++++++ hw/display/trace-events | 5 ++ 3 files changed, 197 insertions(+) create mode 100644 hw/display/sii9022.c diff --git a/hw/display/Makefile.objs b/hw/display/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/display/Makefile.objs +++ b/hw/display/Makefile.objs @@ -XXX,XX +XXX,XX @@ 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 diff --git a/hw/display/sii9022.c b/hw/display/sii9022.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/display/sii9022.c @@ -XXX,XX +XXX,XX @@ +/* + * 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) diff --git a/hw/display/trace-events b/hw/display/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/display/trace-events +++ b/hw/display/trace-events @@ -XXX,XX +XXX,XX @@ 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" -- 2.16.2 From: Linus Walleij <linus.walleij@linaro.org> This adds the SiI9022 (and implicitly EDID I2C) device to the ARM Versatile Express machine, and selects the two I2C devices necessary in the arm-softmmu.mak configuration so everything will build smoothly. I am implementing proper handling of the graphics in the Linux kernel and adding proper emulation of SiI9022 and EDID makes the driver probe as nicely as before, retrieving the resolutions supported by the "QEMU monitor" and overall just working nice. Cc: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Message-id: 20180227104903.21353-6-linus.walleij@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/vexpress.c | 6 +++++- default-configs/arm-softmmu.mak | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -XXX,XX +XXX,XX @@ #include "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" @@ -XXX,XX +XXX,XX @@ 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); @@ -XXX,XX +XXX,XX @@ 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 */ diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ 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 -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This allows us to explicitly pass float16 to helpers rather than assuming uint32_t and dealing with the result. Of course they will be passed in i32 sized registers by default. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-2-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/helper-head.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -XXX,XX +XXX,XX @@ #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 @@ -XXX,XX +XXX,XX @@ #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 * @@ -XXX,XX +XXX,XX @@ #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 -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-3-alex.bennee@linaro.org [PMM: postpone actually enabling feature until end of the patch series] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + 1 file changed, 1 insertion(+) 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 @@ 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) -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-4-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + 1 file changed, 1 insertion(+) 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 { * 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 -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Half-precision flush to zero behaviour is controlled by a separate FZ16 bit in the FPCR. To handle this we pass a pointer to fp_status_fp16 when working on half-precision operations. The value of the presented FPCR is calculated from an amalgam of the two when read. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-5-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 32 ++++++++++++++++++++++------ target/arm/helper.c | 26 ++++++++++++++++++----- target/arm/translate-a64.c | 53 +++++++++++++++++++++++++--------------------- 3 files changed, 75 insertions(+), 36 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 { /* 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] */ @@ -XXX,XX +XXX,XX @@ 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; 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 @@ uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) | (env->vfp.vec_stride << 20); i = get_float_exception_flags(&env->vfp.fp_status); i |= get_float_exception_flags(&env->vfp.standard_fp_status); + i |= get_float_exception_flags(&env->vfp.fp_status_f16); fpscr |= vfp_exceptbits_from_host(i); return fpscr; } @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) break; } set_float_rounding_mode(i, &env->vfp.fp_status); + set_float_rounding_mode(i, &env->vfp.fp_status_f16); } - if (changed & (1 << 24)) { - set_flush_to_zero((val & (1 << 24)) != 0, &env->vfp.fp_status); - set_flush_inputs_to_zero((val & (1 << 24)) != 0, &env->vfp.fp_status); + if (changed & FPCR_FZ16) { + bool ftz_enabled = val & FPCR_FZ16; + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.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); } - if (changed & (1 << 25)) - set_default_nan_mode((val & (1 << 25)) != 0, &env->vfp.fp_status); + /* 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); } 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 write_fp_sreg(DisasContext *s, int reg, TCGv_i32 v) tcg_temp_free_i64(tmp); } -static TCGv_ptr get_fpstatus_ptr(void) +static TCGv_ptr get_fpstatus_ptr(bool is_f16) { TCGv_ptr statusptr = tcg_temp_new_ptr(); int offset; - /* In A64 all instructions (both FP and Neon) use the FPCR; - * there is no equivalent of the A32 Neon "standard FPSCR value" - * and all operations use vfp.fp_status. + /* In A64 all instructions (both FP and Neon) use the FPCR; there + * is no equivalent of the A32 Neon "standard FPSCR value". + * However half-precision operations operate under a different + * FZ16 flag and use vfp.fp_status_f16 instead of vfp.fp_status. */ - offset = offsetof(CPUARMState, vfp.fp_status); + if (is_f16) { + offset = offsetof(CPUARMState, vfp.fp_status_f16); + } else { + offset = offsetof(CPUARMState, vfp.fp_status); + } tcg_gen_addi_ptr(statusptr, cpu_env, offset); return statusptr; } @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, bool is_double, bool cmp_with_zero, bool signal_all_nans) { TCGv_i64 tcg_flags = tcg_temp_new_i64(); - TCGv_ptr fpst = get_fpstatus_ptr(); + TCGv_ptr fpst = get_fpstatus_ptr(false); if (is_double) { TCGv_i64 tcg_vn, tcg_vm; @@ -XXX,XX +XXX,XX @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) TCGv_i32 tcg_op; TCGv_i32 tcg_res; - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); tcg_op = read_fp_sreg(s, rn); tcg_res = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) return; } - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); tcg_op = read_fp_dreg(s, rn); tcg_res = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_single(DisasContext *s, int opcode, TCGv_ptr fpst; tcg_res = tcg_temp_new_i32(); - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); tcg_op1 = read_fp_sreg(s, rn); tcg_op2 = read_fp_sreg(s, rm); @@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_double(DisasContext *s, int opcode, TCGv_ptr fpst; tcg_res = tcg_temp_new_i64(); - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); tcg_op1 = read_fp_dreg(s, rn); tcg_op2 = read_fp_dreg(s, rm); @@ -XXX,XX +XXX,XX @@ static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1, { TCGv_i32 tcg_op1, tcg_op2, tcg_op3; TCGv_i32 tcg_res = tcg_temp_new_i32(); - TCGv_ptr fpst = get_fpstatus_ptr(); + TCGv_ptr fpst = get_fpstatus_ptr(false); tcg_op1 = read_fp_sreg(s, rn); tcg_op2 = read_fp_sreg(s, rm); @@ -XXX,XX +XXX,XX @@ static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1, { TCGv_i64 tcg_op1, tcg_op2, tcg_op3; TCGv_i64 tcg_res = tcg_temp_new_i64(); - TCGv_ptr fpst = get_fpstatus_ptr(); + TCGv_ptr fpst = get_fpstatus_ptr(false); tcg_op1 = read_fp_dreg(s, rn); tcg_op2 = read_fp_dreg(s, rm); @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, TCGv_ptr tcg_fpstatus; TCGv_i32 tcg_shift; - tcg_fpstatus = get_fpstatus_ptr(); + tcg_fpstatus = get_fpstatus_ptr(false); tcg_shift = tcg_const_i32(64 - scale); @@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) TCGv_i32 tcg_elt1 = tcg_temp_new_i32(); TCGv_i32 tcg_elt2 = tcg_temp_new_i32(); TCGv_i32 tcg_elt3 = tcg_temp_new_i32(); - TCGv_ptr fpst = get_fpstatus_ptr(); + TCGv_ptr fpst = get_fpstatus_ptr(false); assert(esize == 32); assert(elements == 4); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) } size = extract32(size, 0, 1) ? 3 : 2; - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int fracbits, int size) { bool is_double = size == 3 ? true : false; - TCGv_ptr tcg_fpst = get_fpstatus_ptr(); + TCGv_ptr tcg_fpst = get_fpstatus_ptr(false); TCGv_i32 tcg_shift = tcg_const_i32(fracbits); TCGv_i64 tcg_int = tcg_temp_new_i64(); TCGMemOp mop = size | (is_signed ? MO_SIGN : 0); @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, tcg_rmode = tcg_const_i32(arm_rmode_to_sf(FPROUNDING_ZERO)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); - tcg_fpstatus = get_fpstatus_ptr(); + tcg_fpstatus = get_fpstatus_ptr(false); tcg_shift = tcg_const_i32(fracbits); if (is_double) { @@ -XXX,XX +XXX,XX @@ static void handle_3same_float(DisasContext *s, int size, int elements, int fpopcode, int rd, int rn, int rm) { int pass; - TCGv_ptr fpst = get_fpstatus_ptr(); + TCGv_ptr fpst = get_fpstatus_ptr(false); for (pass = 0; pass < elements; pass++) { if (size) { @@ -XXX,XX +XXX,XX @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, return; } - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); if (is_double) { TCGv_i64 tcg_op = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void handle_2misc_reciprocal(DisasContext *s, int opcode, int size, int rn, int rd) { bool is_double = (size == 3); - TCGv_ptr fpst = get_fpstatus_ptr(); + TCGv_ptr fpst = get_fpstatus_ptr(false); if (is_double) { TCGv_i64 tcg_op = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) if (is_fcvt) { tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); - tcg_fpstatus = get_fpstatus_ptr(); + tcg_fpstatus = get_fpstatus_ptr(false); } else { tcg_rmode = NULL; tcg_fpstatus = NULL; @@ -XXX,XX +XXX,XX @@ static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode, /* Floating point operations need fpst */ if (opcode >= 0x58) { - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); } else { fpst = NULL; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } if (need_fpstatus) { - tcg_fpstatus = get_fpstatus_ptr(); + tcg_fpstatus = get_fpstatus_ptr(false); } else { tcg_fpstatus = NULL; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } if (is_fp) { - fpst = get_fpstatus_ptr(); + fpst = get_fpstatus_ptr(false); } else { fpst = NULL; } -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> As the rounding mode is now split between FP16 and the rest of floating point we need to be explicit when tweaking it. Instead of passing the CPU env we now pass the appropriate fpst pointer directly. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-6-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 2 +- target/arm/helper.c | 4 ++-- target/arm/translate-a64.c | 26 +++++++++++++------------- target/arm/translate.c | 12 ++++++------ 4 files changed, 22 insertions(+), 22 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(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_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) 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 @@ VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) /* Set the current fp rounding mode and return the old one. * The argument is a softfloat float_round_ value. */ -uint32_t HELPER(set_rmode)(uint32_t rmode, CPUARMState *env) +uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp) { - float_status *fp_status = &env->vfp.fp_status; + float_status *fp_status = fpstp; uint32_t prev_rmode = get_float_rounding_mode(fp_status); set_float_rounding_mode(rmode, fp_status); 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) { TCGv_i32 tcg_rmode = tcg_const_i32(arm_rmode_to_sf(opcode & 7)); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rints(tcg_res, tcg_op, 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); break; } @@ -XXX,XX +XXX,XX @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) { TCGv_i32 tcg_rmode = tcg_const_i32(arm_rmode_to_sf(opcode & 7)); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rintd(tcg_res, tcg_op, 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); break; } @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); if (is_double) { TCGv_i64 tcg_double = read_fp_dreg(s, rn); @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, tcg_temp_free_i32(tcg_single); } - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); tcg_temp_free_i32(tcg_rmode); if (!sf) { @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, assert(!(is_scalar && is_q)); tcg_rmode = tcg_const_i32(arm_rmode_to_sf(FPROUNDING_ZERO)); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); tcg_fpstatus = get_fpstatus_ptr(false); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); tcg_shift = tcg_const_i32(fracbits); if (is_double) { @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, tcg_temp_free_ptr(tcg_fpstatus); tcg_temp_free_i32(tcg_shift); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); tcg_temp_free_i32(tcg_rmode); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) if (is_fcvt) { tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); tcg_fpstatus = get_fpstatus_ptr(false); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); } else { tcg_rmode = NULL; tcg_fpstatus = NULL; @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } if (is_fcvt) { - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_ptr(tcg_fpstatus); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } - if (need_fpstatus) { + if (need_fpstatus || need_rmode) { tcg_fpstatus = get_fpstatus_ptr(false); } else { tcg_fpstatus = NULL; } if (need_rmode) { tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); } else { tcg_rmode = NULL; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) clear_vec_high(s, is_q, rd); if (need_rmode) { - gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); tcg_temp_free_i32(tcg_rmode); } if (need_fpstatus) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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); @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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); @@ -XXX,XX +XXX,XX @@ 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; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This implements the half-precision variants of the across vector reduction operations. This involves a re-factor of the reduction code which more closely matches the ARM ARM order (and handles 8 element reductions). Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-7-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 4 ++ target/arm/helper-a64.c | 18 ++++++ target/arm/translate-a64.c | 140 ++++++++++++++++++++++++++++----------------- 3 files changed, 109 insertions(+), 53 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ 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(min) +ADVSIMD_HALFOP(max) +ADVSIMD_HALFOP(minnum) +ADVSIMD_HALFOP(maxnum) 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_zip_trn(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_resh); } -static void do_minmaxop(DisasContext *s, TCGv_i32 tcg_elt1, TCGv_i32 tcg_elt2, - int opc, bool is_min, TCGv_ptr fpst) +/* + * do_reduction_op helper + * + * This mirrors the Reduce() pseudocode in the ARM ARM. It is + * important for correct NaN propagation that we do these + * operations in exactly the order specified by the pseudocode. + * + * This is a recursive function, TCG temps should be freed by the + * calling function once it is done with the values. + */ +static TCGv_i32 do_reduction_op(DisasContext *s, int fpopcode, int rn, + int esize, int size, int vmap, TCGv_ptr fpst) { - /* Helper function for disas_simd_across_lanes: do a single precision - * min/max operation on the specified two inputs, - * and return the result in tcg_elt1. - */ - if (opc == 0xc) { - if (is_min) { - gen_helper_vfp_minnums(tcg_elt1, tcg_elt1, tcg_elt2, fpst); - } else { - gen_helper_vfp_maxnums(tcg_elt1, tcg_elt1, tcg_elt2, fpst); - } + if (esize == size) { + int element; + TCGMemOp msize = esize == 16 ? MO_16 : MO_32; + TCGv_i32 tcg_elem; + + /* We should have one register left here */ + assert(ctpop8(vmap) == 1); + element = ctz32(vmap); + assert(element < 8); + + tcg_elem = tcg_temp_new_i32(); + read_vec_element_i32(s, tcg_elem, rn, element, msize); + return tcg_elem; } else { - assert(opc == 0xf); - if (is_min) { - gen_helper_vfp_mins(tcg_elt1, tcg_elt1, tcg_elt2, fpst); - } else { - gen_helper_vfp_maxs(tcg_elt1, tcg_elt1, tcg_elt2, fpst); + int bits = size / 2; + int shift = ctpop8(vmap) / 2; + int vmap_lo = (vmap >> shift) & vmap; + int vmap_hi = (vmap & ~vmap_lo); + TCGv_i32 tcg_hi, tcg_lo, tcg_res; + + tcg_hi = do_reduction_op(s, fpopcode, rn, esize, bits, vmap_hi, fpst); + tcg_lo = do_reduction_op(s, fpopcode, rn, esize, bits, vmap_lo, fpst); + tcg_res = tcg_temp_new_i32(); + + switch (fpopcode) { + case 0x0c: /* fmaxnmv half-precision */ + gen_helper_advsimd_maxnumh(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x0f: /* fmaxv half-precision */ + gen_helper_advsimd_maxh(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x1c: /* fminnmv half-precision */ + gen_helper_advsimd_minnumh(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x1f: /* fminv half-precision */ + gen_helper_advsimd_minh(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x2c: /* fmaxnmv */ + gen_helper_vfp_maxnums(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x2f: /* fmaxv */ + gen_helper_vfp_maxs(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x3c: /* fminnmv */ + gen_helper_vfp_minnums(tcg_res, tcg_lo, tcg_hi, fpst); + break; + case 0x3f: /* fminv */ + gen_helper_vfp_mins(tcg_res, tcg_lo, tcg_hi, fpst); + break; + default: + g_assert_not_reached(); } + + tcg_temp_free_i32(tcg_hi); + tcg_temp_free_i32(tcg_lo); + return tcg_res; } } @@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) break; case 0xc: /* FMAXNMV, FMINNMV */ case 0xf: /* FMAXV, FMINV */ - if (!is_u || !is_q || extract32(size, 0, 1)) { - unallocated_encoding(s); - return; - } - /* Bit 1 of size field encodes min vs max, and actual size is always - * 32 bits: adjust the size variable so following code can rely on it + /* Bit 1 of size field encodes min vs max and the actual size + * depends on the encoding of the U bit. If not set (and FP16 + * enabled) then we do half-precision float instead of single + * precision. */ is_min = extract32(size, 1, 1); is_fp = true; - size = 2; + if (!is_u && arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + size = 1; + } else if (!is_u || !is_q || extract32(size, 0, 1)) { + unallocated_encoding(s); + return; + } else { + size = 2; + } break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) } } else { - /* Floating point ops which work on 32 bit (single) intermediates. + /* Floating point vector reduction ops which work across 32 + * bit (single) or 16 bit (half-precision) intermediates. * Note that correct NaN propagation requires that we do these * operations in exactly the order specified by the pseudocode. */ - TCGv_i32 tcg_elt1 = tcg_temp_new_i32(); - TCGv_i32 tcg_elt2 = tcg_temp_new_i32(); - TCGv_i32 tcg_elt3 = tcg_temp_new_i32(); - TCGv_ptr fpst = get_fpstatus_ptr(false); - - assert(esize == 32); - assert(elements == 4); - - read_vec_element(s, tcg_elt, rn, 0, MO_32); - tcg_gen_extrl_i64_i32(tcg_elt1, tcg_elt); - read_vec_element(s, tcg_elt, rn, 1, MO_32); - tcg_gen_extrl_i64_i32(tcg_elt2, tcg_elt); - - do_minmaxop(s, tcg_elt1, tcg_elt2, opcode, is_min, fpst); - - read_vec_element(s, tcg_elt, rn, 2, MO_32); - tcg_gen_extrl_i64_i32(tcg_elt2, tcg_elt); - read_vec_element(s, tcg_elt, rn, 3, MO_32); - tcg_gen_extrl_i64_i32(tcg_elt3, tcg_elt); - - do_minmaxop(s, tcg_elt2, tcg_elt3, opcode, is_min, fpst); - - do_minmaxop(s, tcg_elt1, tcg_elt2, opcode, is_min, fpst); - - tcg_gen_extu_i32_i64(tcg_res, tcg_elt1); - tcg_temp_free_i32(tcg_elt1); - tcg_temp_free_i32(tcg_elt2); - tcg_temp_free_i32(tcg_elt3); + TCGv_ptr fpst = get_fpstatus_ptr(size == MO_16); + int fpopcode = opcode | is_min << 4 | is_u << 5; + int vmap = (1 << elements) - 1; + TCGv_i32 tcg_res32 = do_reduction_op(s, fpopcode, rn, esize, + (is_q ? 128 : 64), vmap, fpst); + tcg_gen_extu_i32_i64(tcg_res, tcg_res32); + tcg_temp_free_i32(tcg_res32); tcg_temp_free_ptr(fpst); } -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> We do implement all the opcodes. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-8-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 3 +-- 1 file changed, 1 insertion(+), 2 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 handle_3same_64(DisasContext *s, int opcode, bool u, /* Handle 64x64->64 opcodes which are shared between the scalar * and vector 3-same groups. We cover every opcode where size == 3 * is valid in either the three-reg-same (integer, not pairwise) - * or scalar-three-reg-same groups. (Some opcodes are not yet - * implemented.) + * or scalar-three-reg-same groups. */ TCGCond cond; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This is the initial decode skeleton for the Advanced SIMD three same instruction group. The fprintf is purely to aid debugging as the additional instructions are added. It will be removed once the group is complete. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-9-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) 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(DisasContext *s, uint32_t insn) } } +/* + * Advanced SIMD three same (ARMv8.2 FP16 variants) + * + * 31 30 29 28 24 23 22 21 20 16 15 14 13 11 10 9 5 4 0 + * +---+---+---+-----------+---------+------+-----+--------+---+------+------+ + * | 0 | Q | U | 0 1 1 1 0 | a | 1 0 | Rm | 0 0 | opcode | 1 | Rn | Rd | + * +---+---+---+-----------+---------+------+-----+--------+---+------+------+ + * + * This includes FMULX, FCMEQ (register), FRECPS, FRSQRTS, FCMGE + * (register), FACGE, FABD, FCMGT (register) and FACGT. + * + */ +static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) +{ + int opcode, fpopcode; + int is_q, u, a, rm, rn, rd; + int datasize, elements; + int pass; + TCGv_ptr fpst; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + /* For these floating point ops, the U, a and opcode bits + * together indicate the operation. + */ + opcode = extract32(insn, 11, 3); + u = extract32(insn, 29, 1); + a = extract32(insn, 23, 1); + is_q = extract32(insn, 30, 1); + rm = extract32(insn, 16, 5); + rn = extract32(insn, 5, 5); + rd = extract32(insn, 0, 5); + + fpopcode = opcode | (a << 3) | (u << 4); + datasize = is_q ? 128 : 64; + elements = datasize / 16; + + fpst = get_fpstatus_ptr(true); + + for (pass = 0; pass < elements; pass++) { + TCGv_i32 tcg_op1 = tcg_temp_new_i32(); + TCGv_i32 tcg_op2 = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op1, rn, pass, MO_16); + read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); + + switch (fpopcode) { + default: + fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n", + __func__, insn, fpopcode, s->pc); + g_assert_not_reached(); + } + + write_vec_element_i32(s, tcg_res, rd, pass, MO_16); + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + } + + tcg_temp_free_ptr(fpst); + + clear_vec_high(s, is_q, rd); +} + static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, int size, int rn, int rd) { @@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = { { 0xce000000, 0xff808000, disas_crypto_four_reg }, { 0xce800000, 0xffe00000, disas_crypto_xar }, { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, + { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, { 0x00000000, 0x00000000, NULL } }; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> The fprintf is only there for debugging as the skeleton is added to, it will be removed once the skeleton is complete. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-10-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 4 ++++ target/arm/helper-a64.c | 4 ++++ target/arm/translate-a64.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 36 insertions(+) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ float16 ADVSIMD_HELPER(name, h)(float16 a, float16 b, void *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) 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_fp16(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); switch (fpopcode) { + case 0x0: /* FMAXNM */ + gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x2: /* FADD */ + gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x6: /* FMAX */ + gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x8: /* FMINNM */ + gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xa: /* FSUB */ + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xe: /* FMIN */ + gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x13: /* FMUL */ + gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x17: /* FDIV */ + gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1a: /* FABD */ + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); + tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); + break; default: fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n", __func__, insn, fpopcode, s->pc); -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> These use the generic float16_compare functionality which in turn uses the common float_compare code from the softfloat re-factor. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-11-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 5 +++++ target/arm/helper-a64.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++ target/arm/translate-a64.c | 15 ++++++++++++++ 3 files changed, 69 insertions(+) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ ADVSIMD_HALFOP(min) ADVSIMD_HALFOP(max) ADVSIMD_HALFOP(minnum) ADVSIMD_HALFOP(maxnum) + +/* + * 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); +} 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_fp16(DisasContext *s, uint32_t insn) case 0x2: /* FADD */ gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x4: /* FCMEQ */ + gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x6: /* FMAX */ gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x13: /* FMUL */ gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x14: /* FCMGE */ + gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x15: /* FACGE */ + gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x17: /* FDIV */ gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); break; + case 0x1c: /* FCMGT */ + gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1d: /* FACGT */ + gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; default: fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n", __func__, insn, fpopcode, s->pc); -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-12-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 ++ target/arm/helper-a64.c | 24 ++++++++++++++++++++++++ target/arm/translate-a64.c | 15 +++++++++++++++ 3 files changed, 41 insertions(+) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ ADVSIMD_HALFOP(max) ADVSIMD_HALFOP(minnum) ADVSIMD_HALFOP(maxnum) +/* Data processing - scalar floating-point and advanced SIMD */ +float16 HELPER(advsimd_mulxh)(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); +} + +/* 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); +} + /* * Floating point comparisons produce an integer result. Softfloat * routines return float_relation types which we convert to the 0/-1 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_fp16(DisasContext *s, uint32_t insn) case 0x0: /* FMAXNM */ gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x1: /* FMLA */ + read_vec_element_i32(s, tcg_res, rd, pass, MO_16); + gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, + fpst); + break; case 0x2: /* FADD */ gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x3: /* FMULX */ + gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x4: /* FCMEQ */ gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0x8: /* FMINNM */ gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x9: /* FMLS */ + /* As usual for ARM, separate negation for fused multiply-add */ + tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); + read_vec_element_i32(s, tcg_res, rd, pass, MO_16); + gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, + fpst); + break; case 0xa: /* FSUB */ gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); break; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> As some of the constants here will also be needed elsewhere (specifically for the upcoming SVE support) we move them out to softfloat.h. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-13-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/fpu/softfloat.h | 18 +++++++++++++----- target/arm/helper-a64.h | 2 ++ target/arm/helper-a64.c | 34 ++++++++++++++++++++++++++++++++++ target/arm/translate-a64.c | 6 ++++++ 4 files changed, 55 insertions(+), 5 deletions(-) diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -XXX,XX +XXX,XX @@ 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) /*---------------------------------------------------------------------------- @@ -XXX,XX +XXX,XX @@ 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. *----------------------------------------------------------------------------*/ @@ -XXX,XX +XXX,XX @@ static inline float64 float64_set_sign(float64 a, int sign) } #define float64_zero make_float64(0) -#define float64_one make_float64(0x3ff0000000000000LL) -#define float64_ln2 make_float64(0x3fe62e42fefa39efLL) #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_infinity make_float64(0x7ff0000000000000LL) /*---------------------------------------------------------------------------- diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ 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) @@ -XXX,XX +XXX,XX @@ 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; @@ -XXX,XX +XXX,XX @@ 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; 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_fp16(DisasContext *s, uint32_t insn) case 0x6: /* FMAX */ gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0x7: /* FRECPS */ + gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x8: /* FMINNM */ gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); break; @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) case 0xe: /* FMIN */ gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); break; + case 0xf: /* FRSQRTS */ + gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; case 0x13: /* FMUL */ gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); break; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This includes FMAXNMP, FADDP, FMAXP, FMINNMP, FMINP. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-14-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 208 +++++++++++++++++++++++++++++---------------- 1 file changed, 133 insertions(+), 75 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_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) int datasize, elements; int pass; TCGv_ptr fpst; + bool pairwise = false; if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) datasize = is_q ? 128 : 64; elements = datasize / 16; + switch (fpopcode) { + case 0x10: /* FMAXNMP */ + case 0x12: /* FADDP */ + case 0x16: /* FMAXP */ + case 0x18: /* FMINNMP */ + case 0x1e: /* FMINP */ + pairwise = true; + break; + } + fpst = get_fpstatus_ptr(true); - for (pass = 0; pass < elements; pass++) { + if (pairwise) { + int maxpass = is_q ? 8 : 4; TCGv_i32 tcg_op1 = tcg_temp_new_i32(); TCGv_i32 tcg_op2 = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); + TCGv_i32 tcg_res[8]; - read_vec_element_i32(s, tcg_op1, rn, pass, MO_16); - read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); + for (pass = 0; pass < maxpass; pass++) { + int passreg = pass < (maxpass / 2) ? rn : rm; + int passelt = (pass << 1) & (maxpass - 1); - switch (fpopcode) { - case 0x0: /* FMAXNM */ - gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1: /* FMLA */ - read_vec_element_i32(s, tcg_res, rd, pass, MO_16); - gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, - fpst); - break; - case 0x2: /* FADD */ - gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x3: /* FMULX */ - gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x4: /* FCMEQ */ - gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x6: /* FMAX */ - gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x7: /* FRECPS */ - gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x8: /* FMINNM */ - gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x9: /* FMLS */ - /* As usual for ARM, separate negation for fused multiply-add */ - tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); - read_vec_element_i32(s, tcg_res, rd, pass, MO_16); - gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, - fpst); - break; - case 0xa: /* FSUB */ - gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xe: /* FMIN */ - gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xf: /* FRSQRTS */ - gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x13: /* FMUL */ - gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x14: /* FCMGE */ - gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x15: /* FACGE */ - gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x17: /* FDIV */ - gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1a: /* FABD */ - gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); - tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); - break; - case 0x1c: /* FCMGT */ - gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x1d: /* FACGT */ - gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n", - __func__, insn, fpopcode, s->pc); - g_assert_not_reached(); + read_vec_element_i32(s, tcg_op1, passreg, passelt, MO_16); + read_vec_element_i32(s, tcg_op2, passreg, passelt + 1, MO_16); + tcg_res[pass] = tcg_temp_new_i32(); + + switch (fpopcode) { + case 0x10: /* FMAXNMP */ + gen_helper_advsimd_maxnumh(tcg_res[pass], tcg_op1, tcg_op2, + fpst); + break; + case 0x12: /* FADDP */ + gen_helper_advsimd_addh(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x16: /* FMAXP */ + gen_helper_advsimd_maxh(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + case 0x18: /* FMINNMP */ + gen_helper_advsimd_minnumh(tcg_res[pass], tcg_op1, tcg_op2, + fpst); + break; + case 0x1e: /* FMINP */ + gen_helper_advsimd_minh(tcg_res[pass], tcg_op1, tcg_op2, fpst); + break; + default: + g_assert_not_reached(); + } + } + + for (pass = 0; pass < maxpass; pass++) { + write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_16); + tcg_temp_free_i32(tcg_res[pass]); } - write_vec_element_i32(s, tcg_res, rd, pass, MO_16); - tcg_temp_free_i32(tcg_res); tcg_temp_free_i32(tcg_op1); tcg_temp_free_i32(tcg_op2); + + } else { + for (pass = 0; pass < elements; pass++) { + TCGv_i32 tcg_op1 = tcg_temp_new_i32(); + TCGv_i32 tcg_op2 = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op1, rn, pass, MO_16); + read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); + + switch (fpopcode) { + case 0x0: /* FMAXNM */ + gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1: /* FMLA */ + read_vec_element_i32(s, tcg_res, rd, pass, MO_16); + gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, + fpst); + break; + case 0x2: /* FADD */ + gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x3: /* FMULX */ + gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x4: /* FCMEQ */ + gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x6: /* FMAX */ + gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x7: /* FRECPS */ + gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x8: /* FMINNM */ + gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x9: /* FMLS */ + /* As usual for ARM, separate negation for fused multiply-add */ + tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); + read_vec_element_i32(s, tcg_res, rd, pass, MO_16); + gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, + fpst); + break; + case 0xa: /* FSUB */ + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xe: /* FMIN */ + gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xf: /* FRSQRTS */ + gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x13: /* FMUL */ + gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x14: /* FCMGE */ + gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x15: /* FACGE */ + gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x17: /* FDIV */ + gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1a: /* FABD */ + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); + tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); + break; + case 0x1c: /* FCMGT */ + gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1d: /* FACGT */ + gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + default: + fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n", + __func__, insn, fpopcode, s->pc); + g_assert_not_reached(); + } + + write_vec_element_i32(s, tcg_res, rd, pass, MO_16); + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + } } tcg_temp_free_ptr(fpst); -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> The helpers use the new re-factored muladd support in SoftFloat for the float16 work. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180227143852.11175-15-alex.bennee@linaro.org Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 82 +++++++++++++++++++++++++++++++++++++--------- 1 file changed, 66 insertions(+), 16 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_simd_indexed(DisasContext *s, uint32_t insn) int rd = extract32(insn, 0, 5); bool is_long = false; bool is_fp = false; + bool is_fp16 = false; int index; TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } /* fall through */ case 0x9: /* FMUL, FMULX */ - if (!extract32(size, 1, 1)) { + if (size == 1) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } if (is_fp) { - /* low bit of size indicates single/double */ - size = extract32(size, 0, 1) ? 3 : 2; - if (size == 2) { + /* convert insn encoded size to TCGMemOp size */ + switch (size) { + case 2: /* single precision */ + size = MO_32; index = h << 1 | l; - } else { + rm |= (m << 4); + break; + case 3: /* double precision */ + size = MO_64; if (l || !is_q) { unallocated_encoding(s); return; } index = h; + rm |= (m << 4); + break; + case 0: /* half precision */ + size = MO_16; + index = h << 2 | l << 1 | m; + is_fp16 = true; + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: /* unallocated */ + unallocated_encoding(s); + return; } - rm |= (m << 4); } else { switch (size) { case 1: @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } if (is_fp) { - fpst = get_fpstatus_ptr(false); + fpst = get_fpstatus_ptr(is_fp16); } else { fpst = NULL; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; } case 0x5: /* FMLS */ - /* As usual for ARM, separate negation for fused multiply-add */ - gen_helper_vfp_negs(tcg_op, tcg_op); - /* fall through */ case 0x1: /* FMLA */ - read_vec_element_i32(s, tcg_res, rd, pass, MO_32); - gen_helper_vfp_muladds(tcg_res, tcg_op, tcg_idx, tcg_res, fpst); + read_vec_element_i32(s, tcg_res, rd, pass, + is_scalar ? size : MO_32); + switch (size) { + case 1: + if (opcode == 0x5) { + /* As usual for ARM, separate negation for fused + * multiply-add */ + tcg_gen_xori_i32(tcg_op, tcg_op, 0x80008000); + } + gen_helper_advsimd_muladdh(tcg_res, tcg_op, tcg_idx, + tcg_res, fpst); + break; + case 2: + if (opcode == 0x5) { + /* As usual for ARM, separate negation for + * fused multiply-add */ + tcg_gen_xori_i32(tcg_op, tcg_op, 0x80000000); + } + gen_helper_vfp_muladds(tcg_res, tcg_op, tcg_idx, + tcg_res, fpst); + break; + default: + g_assert_not_reached(); + } break; case 0x9: /* FMUL, FMULX */ - if (u) { - gen_helper_vfp_mulxs(tcg_res, tcg_op, tcg_idx, fpst); - } else { - gen_helper_vfp_muls(tcg_res, tcg_op, tcg_idx, fpst); + switch (size) { + case 1: + if (u) { + gen_helper_advsimd_mulxh(tcg_res, tcg_op, tcg_idx, + fpst); + } else { + g_assert_not_reached(); + } + break; + case 2: + if (u) { + gen_helper_vfp_mulxs(tcg_res, tcg_op, tcg_idx, fpst); + } else { + gen_helper_vfp_muls(tcg_res, tcg_op, tcg_idx, fpst); + } + break; + default: + g_assert_not_reached(); } break; case 0xc: /* SQDMULH */ -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> A bunch of the vectorised bitwise operations just operate on larger chunks at a time. We can do the same for the new half-precision operations by introducing some TWOHALFOP helpers which work on each half of a pair of half-precision operations at once. Hopefully all this hoop jumping will get simpler once we have generically vectorised helpers here. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-16-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 10 ++++++++++ target/arm/helper-a64.c | 46 +++++++++++++++++++++++++++++++++++++++++++++- target/arm/translate-a64.c | 26 +++++++++++++++++++++----- 3 files changed, 76 insertions(+), 6 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ 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 */ -float16 HELPER(advsimd_mulxh)(float16 a, float16 b, void *fpstp) +static float16 float16_mulx(float16 a, float16 b, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ float16 HELPER(advsimd_mulxh)(float16 a, float16 b, void *fpstp) 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) { @@ -XXX,XX +XXX,XX @@ float16 HELPER(advsimd_muladdh)(float16 a, float16 b, float16 c, void *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 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) * multiply-add */ tcg_gen_xori_i32(tcg_op, tcg_op, 0x80008000); } - gen_helper_advsimd_muladdh(tcg_res, tcg_op, tcg_idx, - tcg_res, fpst); + if (is_scalar) { + gen_helper_advsimd_muladdh(tcg_res, tcg_op, tcg_idx, + tcg_res, fpst); + } else { + gen_helper_advsimd_muladd2h(tcg_res, tcg_op, tcg_idx, + tcg_res, fpst); + } break; case 2: if (opcode == 0x5) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (size) { case 1: if (u) { - gen_helper_advsimd_mulxh(tcg_res, tcg_op, tcg_idx, - fpst); + if (is_scalar) { + gen_helper_advsimd_mulxh(tcg_res, tcg_op, + tcg_idx, fpst); + } else { + gen_helper_advsimd_mulx2h(tcg_res, tcg_op, + tcg_idx, fpst); + } } else { - g_assert_not_reached(); + if (is_scalar) { + gen_helper_advsimd_mulh(tcg_res, tcg_op, + tcg_idx, fpst); + } else { + gen_helper_advsimd_mul2h(tcg_res, tcg_op, + tcg_idx, fpst); + } } break; case 2: -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This actually covers two different sections of the encoding table: Advanced SIMD scalar two-register miscellaneous FP16 Advanced SIMD two-register miscellaneous (FP16) The difference between the two is covered by a combination of Q (bit 30) and S (bit 28). Notably the FRINTx instructions are only available in the vector form. This is just the decode skeleton which will be filled out by later patches. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-17-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) 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_two_reg_misc(DisasContext *s, uint32_t insn) } } +/* AdvSIMD [scalar] two register miscellaneous (FP16) + * + * 31 30 29 28 27 24 23 22 21 17 16 12 11 10 9 5 4 0 + * +---+---+---+---+---------+---+-------------+--------+-----+------+------+ + * | 0 | Q | U | S | 1 1 1 0 | a | 1 1 1 1 0 0 | opcode | 1 0 | Rn | Rd | + * +---+---+---+---+---------+---+-------------+--------+-----+------+------+ + * mask: 1000 1111 0111 1110 0000 1100 0000 0000 0x8f7e 0c00 + * val: 0000 1110 0111 1000 0000 1000 0000 0000 0x0e78 0800 + * + * This actually covers two groups where scalar access is governed by + * bit 28. A bunch of the instructions (float to integral) only exist + * in the vector form and are un-allocated for the scalar decode. Also + * in the scalar decode Q is always 1. + */ +static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) +{ + int fpop, opcode, a; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + opcode = extract32(insn, 12, 4); + a = extract32(insn, 23, 1); + fpop = deposit32(opcode, 5, 1, a); + + switch (fpop) { + default: + fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop); + g_assert_not_reached(); + } + +} + /* AdvSIMD scalar x indexed element * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0 * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+ @@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = { { 0xce800000, 0xffe00000, disas_crypto_xar }, { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, + { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x00000000, 0x00000000, NULL } }; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This adds the full range of half-precision floating point to integral instructions. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-18-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 + target/arm/helper-a64.c | 22 ++++++++ target/arm/translate-a64.c | 123 +++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 142 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp) 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; +} 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_two_reg_misc(DisasContext *s, uint32_t insn) */ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) { - int fpop, opcode, a; + int fpop, opcode, a, u; + int rn, rd; + bool is_q; + bool is_scalar; + bool only_in_vector = false; + + int pass; + TCGv_i32 tcg_rmode = NULL; + TCGv_ptr tcg_fpstatus = NULL; + bool need_rmode = false; + int rmode; if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { unallocated_encoding(s); return; } - if (!fp_access_check(s)) { - return; - } + rd = extract32(insn, 0, 5); + rn = extract32(insn, 5, 5); - opcode = extract32(insn, 12, 4); a = extract32(insn, 23, 1); + u = extract32(insn, 29, 1); + is_scalar = extract32(insn, 28, 1); + is_q = extract32(insn, 30, 1); + + opcode = extract32(insn, 12, 5); fpop = deposit32(opcode, 5, 1, a); + fpop = deposit32(fpop, 6, 1, u); switch (fpop) { + case 0x18: /* FRINTN */ + need_rmode = true; + only_in_vector = true; + rmode = FPROUNDING_TIEEVEN; + break; + case 0x19: /* FRINTM */ + need_rmode = true; + only_in_vector = true; + rmode = FPROUNDING_NEGINF; + break; + case 0x38: /* FRINTP */ + need_rmode = true; + only_in_vector = true; + rmode = FPROUNDING_POSINF; + break; + case 0x39: /* FRINTZ */ + need_rmode = true; + only_in_vector = true; + rmode = FPROUNDING_ZERO; + break; + case 0x58: /* FRINTA */ + need_rmode = true; + only_in_vector = true; + rmode = FPROUNDING_TIEAWAY; + break; + case 0x59: /* FRINTX */ + case 0x79: /* FRINTI */ + only_in_vector = true; + /* current rounding mode */ + break; default: fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop); g_assert_not_reached(); } + + /* Check additional constraints for the scalar encoding */ + if (is_scalar) { + if (!is_q) { + unallocated_encoding(s); + return; + } + /* FRINTxx is only in the vector form */ + if (only_in_vector) { + unallocated_encoding(s); + return; + } + } + + if (!fp_access_check(s)) { + return; + } + + if (need_rmode) { + tcg_fpstatus = get_fpstatus_ptr(true); + } + + if (need_rmode) { + tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); + } + + if (is_scalar) { + /* no operations yet */ + } else { + for (pass = 0; pass < (is_q ? 8 : 4); pass++) { + TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op, rn, pass, MO_16); + + switch (fpop) { + case 0x18: /* FRINTN */ + case 0x19: /* FRINTM */ + case 0x38: /* FRINTP */ + case 0x39: /* FRINTZ */ + case 0x58: /* FRINTA */ + case 0x79: /* FRINTI */ + gen_helper_advsimd_rinth(tcg_res, tcg_op, tcg_fpstatus); + break; + case 0x59: /* FRINTX */ + gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, tcg_fpstatus); + break; + default: + g_assert_not_reached(); + } + + write_vec_element_i32(s, tcg_res, rd, pass, MO_16); + + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_op); + } + + clear_vec_high(s, is_q, rd); + } + + if (tcg_rmode) { + gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); + tcg_temp_free_i32(tcg_rmode); + } + + if (tcg_fpstatus) { + tcg_temp_free_ptr(tcg_fpstatus); + } } /* AdvSIMD scalar x indexed element -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This covers all the floating point convert operations. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-19-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 ++ target/arm/helper-a64.c | 32 +++++++++++++++++ target/arm/translate-a64.c | 85 +++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 118 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ float16 HELPER(advsimd_rinth)(float16 x, void *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); +} 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_two_reg_misc_fp16(DisasContext *s, uint32_t insn) only_in_vector = true; /* current rounding mode */ break; + case 0x1a: /* FCVTNS */ + need_rmode = true; + rmode = FPROUNDING_TIEEVEN; + break; + case 0x1b: /* FCVTMS */ + need_rmode = true; + rmode = FPROUNDING_NEGINF; + break; + case 0x1c: /* FCVTAS */ + need_rmode = true; + rmode = FPROUNDING_TIEAWAY; + break; + case 0x3a: /* FCVTPS */ + need_rmode = true; + rmode = FPROUNDING_POSINF; + break; + case 0x3b: /* FCVTZS */ + need_rmode = true; + rmode = FPROUNDING_ZERO; + break; + case 0x5a: /* FCVTNU */ + need_rmode = true; + rmode = FPROUNDING_TIEEVEN; + break; + case 0x5b: /* FCVTMU */ + need_rmode = true; + rmode = FPROUNDING_NEGINF; + break; + case 0x5c: /* FCVTAU */ + need_rmode = true; + rmode = FPROUNDING_TIEAWAY; + break; + case 0x7a: /* FCVTPU */ + need_rmode = true; + rmode = FPROUNDING_POSINF; + break; + case 0x7b: /* FCVTZU */ + need_rmode = true; + rmode = FPROUNDING_ZERO; + break; default: fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop); g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) } if (is_scalar) { - /* no operations yet */ + TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op, rn, 0, MO_16); + + switch (fpop) { + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus); + break; + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x5c: /* FCVTAU */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ + gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); + break; + default: + g_assert_not_reached(); + } + + /* limit any sign extension going on */ + tcg_gen_andi_i32(tcg_res, tcg_res, 0xffff); + write_fp_sreg(s, rd, tcg_res); + + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_op); } else { for (pass = 0; pass < (is_q ? 8 : 4); pass++) { TCGv_i32 tcg_op = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op, rn, pass, MO_16); switch (fpop) { + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus); + break; + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x5c: /* FCVTAU */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ + gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); + break; case 0x18: /* FRINTN */ case 0x19: /* FRINTM */ case 0x38: /* FRINTP */ -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> I re-use the existing handle_2misc_fcmp_zero handler and tweak it slightly to deal with the half-precision case. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-20-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 80 +++++++++++++++++++++++++++++++++------------- 1 file changed, 57 insertions(+), 23 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 handle_2misc_fcmp_zero(DisasContext *s, int opcode, bool is_scalar, bool is_u, bool is_q, int size, int rn, int rd) { - bool is_double = (size == 3); + bool is_double = (size == MO_64); TCGv_ptr fpst; if (!fp_access_check(s)) { return; } - fpst = get_fpstatus_ptr(false); + fpst = get_fpstatus_ptr(size == MO_16); if (is_double) { TCGv_i64 tcg_op = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, bool swap = false; int pass, maxpasses; - switch (opcode) { - case 0x2e: /* FCMLT (zero) */ - swap = true; - /* fall through */ - case 0x2c: /* FCMGT (zero) */ - genfn = gen_helper_neon_cgt_f32; - break; - case 0x2d: /* FCMEQ (zero) */ - genfn = gen_helper_neon_ceq_f32; - break; - case 0x6d: /* FCMLE (zero) */ - swap = true; - /* fall through */ - case 0x6c: /* FCMGE (zero) */ - genfn = gen_helper_neon_cge_f32; - break; - default: - g_assert_not_reached(); + if (size == MO_16) { + switch (opcode) { + case 0x2e: /* FCMLT (zero) */ + swap = true; + /* fall through */ + case 0x2c: /* FCMGT (zero) */ + genfn = gen_helper_advsimd_cgt_f16; + break; + case 0x2d: /* FCMEQ (zero) */ + genfn = gen_helper_advsimd_ceq_f16; + break; + case 0x6d: /* FCMLE (zero) */ + swap = true; + /* fall through */ + case 0x6c: /* FCMGE (zero) */ + genfn = gen_helper_advsimd_cge_f16; + break; + default: + g_assert_not_reached(); + } + } else { + switch (opcode) { + case 0x2e: /* FCMLT (zero) */ + swap = true; + /* fall through */ + case 0x2c: /* FCMGT (zero) */ + genfn = gen_helper_neon_cgt_f32; + break; + case 0x2d: /* FCMEQ (zero) */ + genfn = gen_helper_neon_ceq_f32; + break; + case 0x6d: /* FCMLE (zero) */ + swap = true; + /* fall through */ + case 0x6c: /* FCMGE (zero) */ + genfn = gen_helper_neon_cge_f32; + break; + default: + g_assert_not_reached(); + } } if (is_scalar) { maxpasses = 1; } else { - maxpasses = is_q ? 4 : 2; + int vector_size = 8 << is_q; + maxpasses = vector_size >> size; } for (pass = 0; pass < maxpasses; pass++) { - read_vec_element_i32(s, tcg_op, rn, pass, MO_32); + read_vec_element_i32(s, tcg_op, rn, pass, size); if (swap) { genfn(tcg_res, tcg_zero, tcg_op, fpst); } else { @@ -XXX,XX +XXX,XX @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, if (is_scalar) { write_fp_sreg(s, rd, tcg_res); } else { - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); + write_vec_element_i32(s, tcg_res, rd, pass, size); } } tcg_temp_free_i32(tcg_res); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) fpop = deposit32(opcode, 5, 1, a); fpop = deposit32(fpop, 6, 1, u); + rd = extract32(insn, 0, 5); + rn = extract32(insn, 5, 5); + switch (fpop) { + break; + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ + handle_2misc_fcmp_zero(s, fpop, is_scalar, 0, is_q, MO_16, rn, rd); + return; case 0x18: /* FRINTN */ need_rmode = true; only_in_vector = true; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> I've re-factored the handle_simd_intfp_conv helper to properly handle half-precision as well as call plain conversion helpers when we are not doing fixed point conversion. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-21-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 ++++ target/arm/helper.c | 4 ++ target/arm/translate-a64.c | 122 ++++++++++++++++++++++++++++++++++----------- 3 files changed, 108 insertions(+), 28 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(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) @@ -XXX,XX +XXX,XX @@ 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) @@ -XXX,XX +XXX,XX @@ 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, ptr) DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) 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 @@ CONV_ITOF(vfp_##name##to##p, fsz, sign) \ CONV_FTOI(vfp_to##name##p, fsz, sign, ) \ CONV_FTOI(vfp_to##name##z##p, fsz, sign, _round_to_zero) +FLOAT_CONVS(si, h, 16, ) FLOAT_CONVS(si, s, 32, ) FLOAT_CONVS(si, d, 64, ) +FLOAT_CONVS(ui, h, 16, u) FLOAT_CONVS(ui, s, 32, u) FLOAT_CONVS(ui, d, 64, u) @@ -XXX,XX +XXX,XX @@ VFP_CONV_FIX_A64(sq, s, 32, 64, int64) VFP_CONV_FIX(uh, s, 32, 32, uint16) VFP_CONV_FIX(ul, s, 32, 32, uint32) VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) +VFP_CONV_FIX_A64(sl, h, 16, 32, int32) +VFP_CONV_FIX_A64(ul, h, 16, 32, uint32) #undef VFP_CONV_FIX #undef VFP_CONV_FIX_FLOAT #undef VFP_CONV_FLOAT_FIX_ROUND 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_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, int fracbits, int size) { - bool is_double = size == 3 ? true : false; - TCGv_ptr tcg_fpst = get_fpstatus_ptr(false); - TCGv_i32 tcg_shift = tcg_const_i32(fracbits); - TCGv_i64 tcg_int = tcg_temp_new_i64(); + TCGv_ptr tcg_fpst = get_fpstatus_ptr(size == MO_16); + TCGv_i32 tcg_shift = NULL; + TCGMemOp mop = size | (is_signed ? MO_SIGN : 0); int pass; - for (pass = 0; pass < elements; pass++) { - read_vec_element(s, tcg_int, rn, pass, mop); + if (fracbits || size == MO_64) { + tcg_shift = tcg_const_i32(fracbits); + } + + if (size == MO_64) { + TCGv_i64 tcg_int64 = tcg_temp_new_i64(); + TCGv_i64 tcg_double = tcg_temp_new_i64(); + + for (pass = 0; pass < elements; pass++) { + read_vec_element(s, tcg_int64, rn, pass, mop); - if (is_double) { - TCGv_i64 tcg_double = tcg_temp_new_i64(); if (is_signed) { - gen_helper_vfp_sqtod(tcg_double, tcg_int, + gen_helper_vfp_sqtod(tcg_double, tcg_int64, tcg_shift, tcg_fpst); } else { - gen_helper_vfp_uqtod(tcg_double, tcg_int, + gen_helper_vfp_uqtod(tcg_double, tcg_int64, tcg_shift, tcg_fpst); } if (elements == 1) { @@ -XXX,XX +XXX,XX @@ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, } else { write_vec_element(s, tcg_double, rd, pass, MO_64); } - tcg_temp_free_i64(tcg_double); - } else { - TCGv_i32 tcg_single = tcg_temp_new_i32(); - if (is_signed) { - gen_helper_vfp_sqtos(tcg_single, tcg_int, - tcg_shift, tcg_fpst); - } else { - gen_helper_vfp_uqtos(tcg_single, tcg_int, - tcg_shift, tcg_fpst); - } - if (elements == 1) { - write_fp_sreg(s, rd, tcg_single); - } else { - write_vec_element_i32(s, tcg_single, rd, pass, MO_32); - } - tcg_temp_free_i32(tcg_single); } + + tcg_temp_free_i64(tcg_int64); + tcg_temp_free_i64(tcg_double); + + } else { + TCGv_i32 tcg_int32 = tcg_temp_new_i32(); + TCGv_i32 tcg_float = tcg_temp_new_i32(); + + for (pass = 0; pass < elements; pass++) { + read_vec_element_i32(s, tcg_int32, rn, pass, mop); + + switch (size) { + case MO_32: + if (fracbits) { + if (is_signed) { + gen_helper_vfp_sltos(tcg_float, tcg_int32, + tcg_shift, tcg_fpst); + } else { + gen_helper_vfp_ultos(tcg_float, tcg_int32, + tcg_shift, tcg_fpst); + } + } else { + if (is_signed) { + gen_helper_vfp_sitos(tcg_float, tcg_int32, tcg_fpst); + } else { + gen_helper_vfp_uitos(tcg_float, tcg_int32, tcg_fpst); + } + } + break; + case MO_16: + if (fracbits) { + if (is_signed) { + gen_helper_vfp_sltoh(tcg_float, tcg_int32, + tcg_shift, tcg_fpst); + } else { + gen_helper_vfp_ultoh(tcg_float, tcg_int32, + tcg_shift, tcg_fpst); + } + } else { + if (is_signed) { + gen_helper_vfp_sitoh(tcg_float, tcg_int32, tcg_fpst); + } else { + gen_helper_vfp_uitoh(tcg_float, tcg_int32, tcg_fpst); + } + } + break; + default: + g_assert_not_reached(); + } + + if (elements == 1) { + write_fp_sreg(s, rd, tcg_float); + } else { + write_vec_element_i32(s, tcg_float, rd, pass, size); + } + } + + tcg_temp_free_i32(tcg_int32); + tcg_temp_free_i32(tcg_float); } - tcg_temp_free_i64(tcg_int); tcg_temp_free_ptr(tcg_fpst); - tcg_temp_free_i32(tcg_shift); + if (tcg_shift) { + tcg_temp_free_i32(tcg_shift); + } clear_vec_high(s, elements << size == 16, rd); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) rn = extract32(insn, 5, 5); switch (fpop) { + case 0x1d: /* SCVTF */ + case 0x5d: /* UCVTF */ + { + int elements; + + if (is_scalar) { + elements = 1; + } else { + elements = (is_q ? 8 : 4); + } + + if (!fp_access_check(s)) { + return; + } + handle_simd_intfp_conv(s, rd, rn, elements, !u, 0, MO_16); + return; + } break; case 0x2c: /* FCMGT (zero) */ case 0x2d: /* FCMEQ (zero) */ -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Neither of these operations alter the floating point status registers so we can do a pure bitwise operation, either squashing any sign bit (ABS) or inverting it (NEG). Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-22-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) 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_two_reg_misc_fp16(DisasContext *s, uint32_t insn) TCGv_i32 tcg_rmode = NULL; TCGv_ptr tcg_fpstatus = NULL; bool need_rmode = false; + bool need_fpst = true; int rmode; if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) need_rmode = true; rmode = FPROUNDING_ZERO; break; + case 0x2f: /* FABS */ + case 0x6f: /* FNEG */ + need_fpst = false; + break; default: fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop); g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) return; } - if (need_rmode) { + if (need_rmode || need_fpst) { tcg_fpstatus = get_fpstatus_ptr(true); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x7b: /* FCVTZU */ gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); break; + case 0x6f: /* FNEG */ + tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); + break; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x59: /* FRINTX */ gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, tcg_fpstatus); break; + case 0x2f: /* FABS */ + tcg_gen_andi_i32(tcg_res, tcg_op, 0x7fff); + break; + case 0x6f: /* FNEG */ + tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); + break; default: g_assert_not_reached(); } -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> It looks like the ARM ARM has simplified the pseudo code for the calculation which is done on a fixed point 9 bit integer maths. So while adding f16 we can also clean this up to be a little less heavy on the floating point and just return the fractional part and leave the calle's to do the final packing of the result. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-23-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 1 + target/arm/helper.c | 226 +++++++++++++++++++++++++++++----------------------- 2 files changed, 129 insertions(+), 98 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_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_f32, TCG_CALL_NO_RWG, f32, f32, ptr) 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 @@ float32 HELPER(rsqrts_f32)(float32 a, float32 b, CPUARMState *env) * int->float conversions at run-time. */ #define float64_256 make_float64(0x4070000000000000LL) #define float64_512 make_float64(0x4080000000000000LL) +#define float16_maxnorm make_float16(0x7bff) #define float32_maxnorm make_float32(0x7f7fffff) #define float64_maxnorm make_float64(0x7fefffffffffffffLL) /* Reciprocal functions * * The algorithm that must be used to calculate the estimate - * is specified by the ARM ARM, see FPRecipEstimate() + * is specified by the ARM ARM, see FPRecipEstimate()/RecipEstimate */ -static float64 recip_estimate(float64 a, float_status *real_fp_status) +/* See RecipEstimate() + * + * input is a 9 bit fixed point number + * input range 256 .. 511 for a number from 0.5 <= x < 1.0. + * result range 256 .. 511 for a number from 1.0 to 511/256. + */ + +static int recip_estimate(int input) { - /* These calculations mustn't set any fp exception flags, - * so we use a local copy of the fp_status. - */ - float_status dummy_status = *real_fp_status; - float_status *s = &dummy_status; - /* q = (int)(a * 512.0) */ - float64 q = float64_mul(float64_512, a, s); - int64_t q_int = float64_to_int64_round_to_zero(q, s); - - /* r = 1.0 / (((double)q + 0.5) / 512.0) */ - q = int64_to_float64(q_int, s); - q = float64_add(q, float64_half, s); - q = float64_div(q, float64_512, s); - q = float64_div(float64_one, q, s); - - /* s = (int)(256.0 * r + 0.5) */ - q = float64_mul(q, float64_256, s); - q = float64_add(q, float64_half, s); - q_int = float64_to_int64_round_to_zero(q, s); - - /* return (double)s / 256.0 */ - return float64_div(int64_to_float64(q_int, s), float64_256, s); + int a, b, r; + assert(256 <= input && input < 512); + a = (input * 2) + 1; + b = (1 << 19) / a; + r = (b + 1) >> 1; + assert(256 <= r && r < 512); + return r; } -/* Common wrapper to call recip_estimate */ -static float64 call_recip_estimate(float64 num, int off, float_status *fpst) -{ - uint64_t val64 = float64_val(num); - uint64_t frac = extract64(val64, 0, 52); - int64_t exp = extract64(val64, 52, 11); - uint64_t sbit; - float64 scaled, estimate; +/* + * Common wrapper to call recip_estimate + * + * The parameters are exponent and 64 bit fraction (without implicit + * bit) where the binary point is nominally at bit 52. Returns a + * float64 which can then be rounded to the appropriate size by the + * callee. + */ - /* Generate the scaled number for the estimate function */ - if (exp == 0) { +static uint64_t call_recip_estimate(int *exp, int exp_off, uint64_t frac) +{ + uint32_t scaled, estimate; + uint64_t result_frac; + int result_exp; + + /* Handle sub-normals */ + if (*exp == 0) { if (extract64(frac, 51, 1) == 0) { - exp = -1; - frac = extract64(frac, 0, 50) << 2; + *exp = -1; + frac <<= 2; } else { - frac = extract64(frac, 0, 51) << 1; + frac <<= 1; } } - /* scaled = '0' : '01111111110' : fraction<51:44> : Zeros(44); */ - scaled = make_float64((0x3feULL << 52) - | extract64(frac, 44, 8) << 44); + /* scaled = UInt('1':fraction<51:44>) */ + scaled = deposit32(1 << 8, 0, 8, extract64(frac, 44, 8)); + estimate = recip_estimate(scaled); - estimate = recip_estimate(scaled, fpst); - - /* Build new result */ - val64 = float64_val(estimate); - sbit = 0x8000000000000000ULL & val64; - exp = off - exp; - frac = extract64(val64, 0, 52); - - if (exp == 0) { - frac = 1ULL << 51 | extract64(frac, 1, 51); - } else if (exp == -1) { - frac = 1ULL << 50 | extract64(frac, 2, 50); - exp = 0; + result_exp = exp_off - *exp; + result_frac = deposit64(0, 44, 8, estimate); + if (result_exp == 0) { + result_frac = deposit64(result_frac >> 1, 51, 1, 1); + } else if (result_exp == -1) { + result_frac = deposit64(result_frac >> 2, 50, 2, 1); + result_exp = 0; } - return make_float64(sbit | (exp << 52) | frac); + *exp = result_exp; + + return result_frac; } static bool round_to_inf(float_status *fpst, bool sign_bit) @@ -XXX,XX +XXX,XX @@ static bool round_to_inf(float_status *fpst, bool sign_bit) g_assert_not_reached(); } +float16 HELPER(recpe_f16)(float16 input, void *fpstp) +{ + float_status *fpst = fpstp; + float16 f16 = float16_squash_input_denormal(input, fpst); + uint32_t f16_val = float16_val(f16); + uint32_t f16_sign = float16_is_neg(f16); + int f16_exp = extract32(f16_val, 10, 5); + uint32_t f16_frac = extract32(f16_val, 0, 10); + uint64_t f64_frac; + + if (float16_is_any_nan(f16)) { + float16 nan = f16; + if (float16_is_signaling_nan(f16, fpst)) { + float_raise(float_flag_invalid, fpst); + nan = float16_maybe_silence_nan(f16, fpst); + } + if (fpst->default_nan_mode) { + nan = float16_default_nan(fpst); + } + return nan; + } else if (float16_is_infinity(f16)) { + return float16_set_sign(float16_zero, float16_is_neg(f16)); + } else if (float16_is_zero(f16)) { + float_raise(float_flag_divbyzero, fpst); + return float16_set_sign(float16_infinity, float16_is_neg(f16)); + } else if (float16_abs(f16) < (1 << 8)) { + /* Abs(value) < 2.0^-16 */ + float_raise(float_flag_overflow | float_flag_inexact, fpst); + if (round_to_inf(fpst, f16_sign)) { + return float16_set_sign(float16_infinity, f16_sign); + } else { + return float16_set_sign(float16_maxnorm, f16_sign); + } + } else if (f16_exp >= 29 && fpst->flush_to_zero) { + float_raise(float_flag_underflow, fpst); + return float16_set_sign(float16_zero, float16_is_neg(f16)); + } + + f64_frac = call_recip_estimate(&f16_exp, 29, + ((uint64_t) f16_frac) << (52 - 10)); + + /* result = sign : result_exp<4:0> : fraction<51:42> */ + f16_val = deposit32(0, 15, 1, f16_sign); + f16_val = deposit32(f16_val, 10, 5, f16_exp); + f16_val = deposit32(f16_val, 0, 10, extract64(f64_frac, 52 - 10, 10)); + return make_float16(f16_val); +} + float32 HELPER(recpe_f32)(float32 input, void *fpstp) { float_status *fpst = fpstp; float32 f32 = float32_squash_input_denormal(input, fpst); uint32_t f32_val = float32_val(f32); - uint32_t f32_sbit = 0x80000000ULL & f32_val; - int32_t f32_exp = extract32(f32_val, 23, 8); + bool f32_sign = float32_is_neg(f32); + int f32_exp = extract32(f32_val, 23, 8); uint32_t f32_frac = extract32(f32_val, 0, 23); - float64 f64, r64; - uint64_t r64_val; - int64_t r64_exp; - uint64_t r64_frac; + uint64_t f64_frac; if (float32_is_any_nan(f32)) { float32 nan = f32; @@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp) } else if (float32_is_zero(f32)) { float_raise(float_flag_divbyzero, fpst); return float32_set_sign(float32_infinity, float32_is_neg(f32)); - } else if ((f32_val & ~(1ULL << 31)) < (1ULL << 21)) { + } else if (float32_abs(f32) < (1ULL << 21)) { /* Abs(value) < 2.0^-128 */ float_raise(float_flag_overflow | float_flag_inexact, fpst); - if (round_to_inf(fpst, f32_sbit)) { - return float32_set_sign(float32_infinity, float32_is_neg(f32)); + if (round_to_inf(fpst, f32_sign)) { + return float32_set_sign(float32_infinity, f32_sign); } else { - return float32_set_sign(float32_maxnorm, float32_is_neg(f32)); + return float32_set_sign(float32_maxnorm, f32_sign); } } else if (f32_exp >= 253 && fpst->flush_to_zero) { float_raise(float_flag_underflow, fpst); return float32_set_sign(float32_zero, float32_is_neg(f32)); } + f64_frac = call_recip_estimate(&f32_exp, 253, + ((uint64_t) f32_frac) << (52 - 23)); - f64 = make_float64(((int64_t)(f32_exp) << 52) | (int64_t)(f32_frac) << 29); - r64 = call_recip_estimate(f64, 253, fpst); - r64_val = float64_val(r64); - r64_exp = extract64(r64_val, 52, 11); - r64_frac = extract64(r64_val, 0, 52); - - /* result = sign : result_exp<7:0> : fraction<51:29>; */ - return make_float32(f32_sbit | - (r64_exp & 0xff) << 23 | - extract64(r64_frac, 29, 24)); + /* result = sign : result_exp<7:0> : fraction<51:29> */ + f32_val = deposit32(0, 31, 1, f32_sign); + f32_val = deposit32(f32_val, 23, 8, f32_exp); + f32_val = deposit32(f32_val, 0, 23, extract64(f64_frac, 52 - 23, 23)); + return make_float32(f32_val); } float64 HELPER(recpe_f64)(float64 input, void *fpstp) @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) float_status *fpst = fpstp; float64 f64 = float64_squash_input_denormal(input, fpst); uint64_t f64_val = float64_val(f64); - uint64_t f64_sbit = 0x8000000000000000ULL & f64_val; - int64_t f64_exp = extract64(f64_val, 52, 11); - float64 r64; - uint64_t r64_val; - int64_t r64_exp; - uint64_t r64_frac; + bool f64_sign = float64_is_neg(f64); + int f64_exp = extract64(f64_val, 52, 11); + uint64_t f64_frac = extract64(f64_val, 0, 52); /* Deal with any special cases */ if (float64_is_any_nan(f64)) { @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) } else if ((f64_val & ~(1ULL << 63)) < (1ULL << 50)) { /* Abs(value) < 2.0^-1024 */ float_raise(float_flag_overflow | float_flag_inexact, fpst); - if (round_to_inf(fpst, f64_sbit)) { - return float64_set_sign(float64_infinity, float64_is_neg(f64)); + if (round_to_inf(fpst, f64_sign)) { + return float64_set_sign(float64_infinity, f64_sign); } else { - return float64_set_sign(float64_maxnorm, float64_is_neg(f64)); + return float64_set_sign(float64_maxnorm, f64_sign); } } else if (f64_exp >= 2045 && fpst->flush_to_zero) { float_raise(float_flag_underflow, fpst); return float64_set_sign(float64_zero, float64_is_neg(f64)); } - r64 = call_recip_estimate(f64, 2045, fpst); - r64_val = float64_val(r64); - r64_exp = extract64(r64_val, 52, 11); - r64_frac = extract64(r64_val, 0, 52); + f64_frac = call_recip_estimate(&f64_exp, 2045, f64_frac); - /* result = sign : result_exp<10:0> : fraction<51:0> */ - return make_float64(f64_sbit | - ((r64_exp & 0x7ff) << 52) | - r64_frac); + /* result = sign : result_exp<10:0> : fraction<51:0>; */ + f64_val = deposit64(0, 63, 1, f64_sign); + f64_val = deposit64(f64_val, 52, 11, f64_exp); + f64_val = deposit64(f64_val, 0, 52, f64_frac); + return make_float64(f64_val); } /* The algorithm that must be used to calculate the estimate @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) { - float_status *s = fpstp; - float64 f64; + /* float_status *s = fpstp; */ + int input, estimate; if ((a & 0x80000000) == 0) { return 0xffffffff; } - f64 = make_float64((0x3feULL << 52) - | ((int64_t)(a & 0x7fffffff) << 21)); + input = extract32(a, 23, 9); + estimate = recip_estimate(input); - f64 = recip_estimate(f64, s); - - return 0x80000000 | ((float64_val(f64) >> 21) & 0x7fffffff); + return deposit32(0, (32 - 9), 9, estimate); } uint32_t HELPER(rsqrte_u32)(uint32_t a, void *fpstp) -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Now we have added f16 during the re-factoring we can simply call the helper. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-24-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 8 ++++++++ 1 file changed, 8 insertions(+) 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_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x6d: /* FCMLE (zero) */ handle_2misc_fcmp_zero(s, fpop, is_scalar, 0, is_q, MO_16, rn, rd); return; + case 0x3d: /* FRECPE */ + break; case 0x18: /* FRINTN */ need_rmode = true; only_in_vector = true; @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x3b: /* FCVTZS */ gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus); break; + case 0x3d: /* FRECPE */ + gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); + break; case 0x5a: /* FCVTNU */ case 0x5b: /* FCVTMU */ case 0x5c: /* FCVTAU */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x3b: /* FCVTZS */ gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus); break; + case 0x3d: /* FRECPE */ + gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); + break; case 0x5a: /* FCVTNU */ case 0x5b: /* FCVTMU */ case 0x5c: /* FCVTAU */ -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> We go with the localised helper. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-25-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 1 + target/arm/helper-a64.c | 29 +++++++++++++++++++++++++++++ target/arm/translate-a64.c | 4 ++++ 3 files changed, 34 insertions(+) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ 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; 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_two_reg_misc_fp16(DisasContext *s, uint32_t insn) handle_2misc_fcmp_zero(s, fpop, is_scalar, 0, is_q, MO_16, rn, rd); return; case 0x3d: /* FRECPE */ + case 0x3f: /* FRECPX */ break; case 0x18: /* FRINTN */ need_rmode = true; @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x3d: /* FRECPE */ gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); break; + case 0x3f: /* FRECPX */ + gen_helper_frecpx_f16(tcg_res, tcg_op, tcg_fpstatus); + break; case 0x5a: /* FCVTNU */ case 0x5b: /* FCVTMU */ case 0x5c: /* FCVTAU */ -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-26-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 1 + target/arm/helper-a64.c | 13 +++++++++++++ target/arm/translate-a64.c | 5 +++++ 3 files changed, 19 insertions(+) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ 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) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_f16touinth)(float16 a, void *fpstp) } 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); +} + + 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_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x6f: /* FNEG */ need_fpst = false; break; + case 0x7f: /* FSQRT (vector) */ + break; default: fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop); g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x6f: /* FNEG */ tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); break; + case 0x7f: /* FSQRT */ + gen_helper_sqrt_f16(tcg_res, tcg_op, tcg_fpstatus); + break; default: g_assert_not_reached(); } -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Much like recpe the ARM ARM has simplified the pseudo code for the calculation which is done on a fixed point 9 bit integer maths. So while adding f16 we can also clean this up to be a little less heavy on the floating point and just return the fractional part and leave the calle's to do the final packing of the result. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-27-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 1 + target/arm/helper.c | 221 ++++++++++++++++++++++++---------------------------- 2 files changed, 104 insertions(+), 118 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(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) 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 @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) /* The algorithm that must be used to calculate the estimate * is specified by the ARM ARM. */ -static float64 recip_sqrt_estimate(float64 a, float_status *real_fp_status) + +static int do_recip_sqrt_estimate(int a) { - /* These calculations mustn't set any fp exception flags, - * so we use a local copy of the fp_status. - */ - float_status dummy_status = *real_fp_status; - float_status *s = &dummy_status; - float64 q; - int64_t q_int; + int b, estimate; - if (float64_lt(a, float64_half, s)) { - /* range 0.25 <= a < 0.5 */ - - /* a in units of 1/512 rounded down */ - /* q0 = (int)(a * 512.0); */ - q = float64_mul(float64_512, a, s); - q_int = float64_to_int64_round_to_zero(q, s); - - /* reciprocal root r */ - /* r = 1.0 / sqrt(((double)q0 + 0.5) / 512.0); */ - q = int64_to_float64(q_int, s); - q = float64_add(q, float64_half, s); - q = float64_div(q, float64_512, s); - q = float64_sqrt(q, s); - q = float64_div(float64_one, q, s); + assert(128 <= a && a < 512); + if (a < 256) { + a = a * 2 + 1; } else { - /* range 0.5 <= a < 1.0 */ - - /* a in units of 1/256 rounded down */ - /* q1 = (int)(a * 256.0); */ - q = float64_mul(float64_256, a, s); - int64_t q_int = float64_to_int64_round_to_zero(q, s); - - /* reciprocal root r */ - /* r = 1.0 /sqrt(((double)q1 + 0.5) / 256); */ - q = int64_to_float64(q_int, s); - q = float64_add(q, float64_half, s); - q = float64_div(q, float64_256, s); - q = float64_sqrt(q, s); - q = float64_div(float64_one, q, s); + a = (a >> 1) << 1; + a = (a + 1) * 2; } - /* r in units of 1/256 rounded to nearest */ - /* s = (int)(256.0 * r + 0.5); */ + b = 512; + while (a * (b + 1) * (b + 1) < (1 << 28)) { + b += 1; + } + estimate = (b + 1) / 2; + assert(256 <= estimate && estimate < 512); - q = float64_mul(q, float64_256,s ); - q = float64_add(q, float64_half, s); - q_int = float64_to_int64_round_to_zero(q, s); + return estimate; +} - /* return (double)s / 256.0;*/ - return float64_div(int64_to_float64(q_int, s), float64_256, s); + +static uint64_t recip_sqrt_estimate(int *exp , int exp_off, uint64_t frac) +{ + int estimate; + uint32_t scaled; + + if (*exp == 0) { + while (extract64(frac, 51, 1) == 0) { + frac = frac << 1; + *exp -= 1; + } + frac = extract64(frac, 0, 51) << 1; + } + + if (*exp & 1) { + /* scaled = UInt('01':fraction<51:45>) */ + scaled = deposit32(1 << 7, 0, 7, extract64(frac, 45, 7)); + } else { + /* scaled = UInt('1':fraction<51:44>) */ + scaled = deposit32(1 << 8, 0, 8, extract64(frac, 44, 8)); + } + estimate = do_recip_sqrt_estimate(scaled); + + *exp = (exp_off - *exp) / 2; + return extract64(estimate, 0, 8) << 44; +} + +float16 HELPER(rsqrte_f16)(float16 input, void *fpstp) +{ + float_status *s = fpstp; + float16 f16 = float16_squash_input_denormal(input, s); + uint16_t val = float16_val(f16); + bool f16_sign = float16_is_neg(f16); + int f16_exp = extract32(val, 10, 5); + uint16_t f16_frac = extract32(val, 0, 10); + uint64_t f64_frac; + + if (float16_is_any_nan(f16)) { + float16 nan = f16; + if (float16_is_signaling_nan(f16, s)) { + float_raise(float_flag_invalid, s); + nan = float16_maybe_silence_nan(f16, s); + } + if (s->default_nan_mode) { + nan = float16_default_nan(s); + } + return nan; + } else if (float16_is_zero(f16)) { + float_raise(float_flag_divbyzero, s); + return float16_set_sign(float16_infinity, f16_sign); + } else if (f16_sign) { + float_raise(float_flag_invalid, s); + return float16_default_nan(s); + } else if (float16_is_infinity(f16)) { + return float16_zero; + } + + /* Scale and normalize to a double-precision value between 0.25 and 1.0, + * preserving the parity of the exponent. */ + + f64_frac = ((uint64_t) f16_frac) << (52 - 10); + + f64_frac = recip_sqrt_estimate(&f16_exp, 44, f64_frac); + + /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(2) */ + val = deposit32(0, 15, 1, f16_sign); + val = deposit32(val, 10, 5, f16_exp); + val = deposit32(val, 2, 8, extract64(f64_frac, 52 - 8, 8)); + return make_float16(val); } float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) float_status *s = fpstp; float32 f32 = float32_squash_input_denormal(input, s); uint32_t val = float32_val(f32); - uint32_t f32_sbit = 0x80000000 & val; - int32_t f32_exp = extract32(val, 23, 8); + uint32_t f32_sign = float32_is_neg(f32); + int f32_exp = extract32(val, 23, 8); uint32_t f32_frac = extract32(val, 0, 23); uint64_t f64_frac; - uint64_t val64; - int result_exp; - float64 f64; if (float32_is_any_nan(f32)) { float32 nan = f32; @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) * preserving the parity of the exponent. */ f64_frac = ((uint64_t) f32_frac) << 29; - if (f32_exp == 0) { - while (extract64(f64_frac, 51, 1) == 0) { - f64_frac = f64_frac << 1; - f32_exp = f32_exp-1; - } - f64_frac = extract64(f64_frac, 0, 51) << 1; - } - if (extract64(f32_exp, 0, 1) == 0) { - f64 = make_float64(((uint64_t) f32_sbit) << 32 - | (0x3feULL << 52) - | f64_frac); - } else { - f64 = make_float64(((uint64_t) f32_sbit) << 32 - | (0x3fdULL << 52) - | f64_frac); - } + f64_frac = recip_sqrt_estimate(&f32_exp, 380, f64_frac); - result_exp = (380 - f32_exp) / 2; - - f64 = recip_sqrt_estimate(f64, s); - - val64 = float64_val(f64); - - val = ((result_exp & 0xff) << 23) - | ((val64 >> 29) & 0x7fffff); + /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(15) */ + val = deposit32(0, 31, 1, f32_sign); + val = deposit32(val, 23, 8, f32_exp); + val = deposit32(val, 15, 8, extract64(f64_frac, 52 - 8, 8)); return make_float32(val); } @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) float_status *s = fpstp; float64 f64 = float64_squash_input_denormal(input, s); uint64_t val = float64_val(f64); - uint64_t f64_sbit = 0x8000000000000000ULL & val; - int64_t f64_exp = extract64(val, 52, 11); + bool f64_sign = float64_is_neg(f64); + int f64_exp = extract64(val, 52, 11); uint64_t f64_frac = extract64(val, 0, 52); - int64_t result_exp; - uint64_t result_frac; if (float64_is_any_nan(f64)) { float64 nan = f64; @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) return float64_zero; } - /* Scale and normalize to a double-precision value between 0.25 and 1.0, - * preserving the parity of the exponent. */ + f64_frac = recip_sqrt_estimate(&f64_exp, 3068, f64_frac); - if (f64_exp == 0) { - while (extract64(f64_frac, 51, 1) == 0) { - f64_frac = f64_frac << 1; - f64_exp = f64_exp - 1; - } - f64_frac = extract64(f64_frac, 0, 51) << 1; - } - - if (extract64(f64_exp, 0, 1) == 0) { - f64 = make_float64(f64_sbit - | (0x3feULL << 52) - | f64_frac); - } else { - f64 = make_float64(f64_sbit - | (0x3fdULL << 52) - | f64_frac); - } - - result_exp = (3068 - f64_exp) / 2; - - f64 = recip_sqrt_estimate(f64, s); - - result_frac = extract64(float64_val(f64), 0, 52); - - return make_float64(f64_sbit | - ((result_exp & 0x7ff) << 52) | - result_frac); + /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(44) */ + val = deposit64(0, 61, 1, f64_sign); + val = deposit64(val, 52, 11, f64_exp); + val = deposit64(val, 44, 8, extract64(f64_frac, 52 - 8, 8)); + return make_float64(val); } uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) uint32_t HELPER(rsqrte_u32)(uint32_t a, void *fpstp) { - float_status *fpst = fpstp; - float64 f64; + int estimate; if ((a & 0xc0000000) == 0) { return 0xffffffff; } - if (a & 0x80000000) { - f64 = make_float64((0x3feULL << 52) - | ((uint64_t)(a & 0x7fffffff) << 21)); - } else { /* bits 31-30 == '01' */ - f64 = make_float64((0x3fdULL << 52) - | ((uint64_t)(a & 0x3fffffff) << 22)); - } + estimate = do_recip_sqrt_estimate(extract32(a, 23, 9)); - f64 = recip_sqrt_estimate(f64, fpst); - - return 0x80000000 | ((float64_val(f64) >> 21) & 0x7fffffff); + return deposit32(0, 23, 9, estimate); } /* VFPv4 fused multiply-accumulate */ -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-28-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 7 +++++++ 1 file changed, 7 insertions(+) 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_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x6f: /* FNEG */ need_fpst = false; break; + case 0x7d: /* FRSQRTE */ case 0x7f: /* FSQRT (vector) */ break; default: @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x6f: /* FNEG */ tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); break; + case 0x7d: /* FRSQRTE */ + gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); + break; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x6f: /* FNEG */ tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); break; + case 0x7d: /* FRSQRTE */ + gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); + break; case 0x7f: /* FSQRT */ gen_helper_sqrt_f16(tcg_res, tcg_op, tcg_fpstatus); break; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> Only one half-precision instruction has been added to this group. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-29-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 35 +++++++++++++++++++++++++---------- 1 file changed, 25 insertions(+), 10 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_simd_copy(DisasContext *s, uint32_t insn) * MVNI - move inverted (shifted) imm into register * ORR - bitwise OR of (shifted) imm with register * BIC - bitwise clear of (shifted) imm with register + * With ARMv8.2 we also have: + * FMOV half-precision */ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) uint64_t imm = 0; if (o2 != 0 || ((cmode == 0xf) && is_neg && !is_q)) { - unallocated_encoding(s); - return; + /* Check for FMOV (vector, immediate) - half-precision */ + if (!(arm_dc_feature(s, ARM_FEATURE_V8_FP16) && o2 && cmode == 0xf)) { + unallocated_encoding(s); + return; + } } if (!fp_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) imm |= 0x4000000000000000ULL; } } else { - imm = (abcdefgh & 0x3f) << 19; - if (abcdefgh & 0x80) { - imm |= 0x80000000; - } - if (abcdefgh & 0x40) { - imm |= 0x3e000000; + if (o2) { + /* FMOV (vector, immediate) - half-precision */ + imm = vfp_expand_imm(MO_16, abcdefgh); + /* now duplicate across the lanes */ + imm = bitfield_replicate(imm, 16); } else { - imm |= 0x40000000; + imm = (abcdefgh & 0x3f) << 19; + if (abcdefgh & 0x80) { + imm |= 0x80000000; + } + if (abcdefgh & 0x40) { + imm |= 0x3e000000; + } else { + imm |= 0x40000000; + } + imm |= (imm << 32); } - imm |= (imm << 32); } } break; + default: + fprintf(stderr, "%s: cmode_3_1: %x\n", __func__, cmode_3_1); + g_assert_not_reached(); } if (cmode_3_1 != 7 && is_neg) { -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> I only needed to do a little light re-factoring to support the half-precision helpers. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-30-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 80 +++++++++++++++++++++++++++++++--------------- 1 file changed, 54 insertions(+), 26 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_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0xf: /* FMAXP */ case 0x2c: /* FMINNMP */ case 0x2f: /* FMINP */ - /* FP op, size[0] is 32 or 64 bit */ + /* FP op, size[0] is 32 or 64 bit*/ if (!u) { - unallocated_encoding(s); - return; + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + return; + } else { + size = MO_16; + } + } else { + size = extract32(size, 0, 1) ? MO_64 : MO_32; } + if (!fp_access_check(s)) { return; } - size = extract32(size, 0, 1) ? 3 : 2; - fpst = get_fpstatus_ptr(false); + fpst = get_fpstatus_ptr(size == MO_16); break; default: unallocated_encoding(s); return; } - if (size == 3) { + if (size == MO_64) { TCGv_i64 tcg_op1 = tcg_temp_new_i64(); TCGv_i64 tcg_op2 = tcg_temp_new_i64(); TCGv_i64 tcg_res = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) TCGv_i32 tcg_op2 = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); - read_vec_element_i32(s, tcg_op1, rn, 0, MO_32); - read_vec_element_i32(s, tcg_op2, rn, 1, MO_32); + read_vec_element_i32(s, tcg_op1, rn, 0, size); + read_vec_element_i32(s, tcg_op2, rn, 1, size); - switch (opcode) { - case 0xc: /* FMAXNMP */ - gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xd: /* FADDP */ - gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0xf: /* FMAXP */ - gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2c: /* FMINNMP */ - gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst); - break; - case 0x2f: /* FMINP */ - gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); - break; - default: - g_assert_not_reached(); + if (size == MO_16) { + switch (opcode) { + case 0xc: /* FMAXNMP */ + gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xd: /* FADDP */ + gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xf: /* FMAXP */ + gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x2c: /* FMINNMP */ + gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x2f: /* FMINP */ + gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + default: + g_assert_not_reached(); + } + } else { + switch (opcode) { + case 0xc: /* FMAXNMP */ + gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xd: /* FADDP */ + gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0xf: /* FMAXP */ + gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x2c: /* FMINNMP */ + gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x2f: /* FMINP */ + gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst); + break; + default: + g_assert_not_reached(); + } } write_fp_sreg(s, rd, tcg_res); -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This covers the encoding group: Advanced SIMD scalar three same FP16 As all the helpers are already there it is simply a case of calling the existing helpers in the scalar context. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-31-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) 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_scalar_three_reg_same(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_rd); } +/* AdvSIMD scalar three same FP16 + * 31 30 29 28 24 23 22 21 20 16 15 14 13 11 10 9 5 4 0 + * +-----+---+-----------+---+-----+------+-----+--------+---+----+----+ + * | 0 1 | U | 1 1 1 1 0 | a | 1 0 | Rm | 0 0 | opcode | 1 | Rn | Rd | + * +-----+---+-----------+---+-----+------+-----+--------+---+----+----+ + * v: 0101 1110 0100 0000 0000 0100 0000 0000 => 5e400400 + * m: 1101 1111 0110 0000 1100 0100 0000 0000 => df60c400 + */ +static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, + uint32_t insn) +{ + int rd = extract32(insn, 0, 5); + int rn = extract32(insn, 5, 5); + int opcode = extract32(insn, 11, 3); + int rm = extract32(insn, 16, 5); + bool u = extract32(insn, 29, 1); + bool a = extract32(insn, 23, 1); + int fpopcode = opcode | (a << 3) | (u << 4); + TCGv_ptr fpst; + TCGv_i32 tcg_op1; + TCGv_i32 tcg_op2; + TCGv_i32 tcg_res; + + switch (fpopcode) { + case 0x03: /* FMULX */ + case 0x04: /* FCMEQ (reg) */ + case 0x07: /* FRECPS */ + case 0x0f: /* FRSQRTS */ + case 0x14: /* FCMGE (reg) */ + case 0x15: /* FACGE */ + case 0x1a: /* FABD */ + case 0x1c: /* FCMGT (reg) */ + case 0x1d: /* FACGT */ + break; + default: + unallocated_encoding(s); + return; + } + + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + } + + if (!fp_access_check(s)) { + return; + } + + fpst = get_fpstatus_ptr(true); + + tcg_op1 = tcg_temp_new_i32(); + tcg_op2 = tcg_temp_new_i32(); + tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op1, rn, 0, MO_16); + read_vec_element_i32(s, tcg_op2, rm, 0, MO_16); + + switch (fpopcode) { + case 0x03: /* FMULX */ + gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x04: /* FCMEQ (reg) */ + gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x07: /* FRECPS */ + gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x0f: /* FRSQRTS */ + gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x14: /* FCMGE (reg) */ + gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x15: /* FACGE */ + gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1a: /* FABD */ + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); + tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff); + break; + case 0x1c: /* FCMGT (reg) */ + gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1d: /* FACGT */ + gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst); + break; + default: + g_assert_not_reached(); + } + + write_fp_sreg(s, rd, tcg_res); + + + tcg_temp_free_i32(tcg_res); + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + tcg_temp_free_ptr(fpst); +} + static void handle_2misc_64(DisasContext *s, int opcode, bool u, TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i32 tcg_rmode, TCGv_ptr tcg_fpstatus) @@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = { { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 }, { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, + { 0x5e400400, 0xdf60c400, disas_simd_scalar_three_reg_same_fp16 }, { 0x00000000, 0x00000000, NULL } }; -- 2.16.2 From: Alex Bennée <alex.bennee@linaro.org> This includes FMOV, FABS, FNEG, FSQRT and FRINT[NPMZAXI]. We re-use existing helpers to achieve this. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180227143852.11175-32-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) 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_csel(DisasContext *s, uint32_t insn) tcg_temp_free_i64(t_true); } +/* Floating-point data-processing (1 source) - half precision */ +static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) +{ + TCGv_ptr fpst = NULL; + TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_res = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_op, rn, 0, MO_16); + + switch (opcode) { + case 0x0: /* FMOV */ + tcg_gen_mov_i32(tcg_res, tcg_op); + break; + case 0x1: /* FABS */ + tcg_gen_andi_i32(tcg_res, tcg_op, 0x7fff); + break; + case 0x2: /* FNEG */ + tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); + break; + case 0x3: /* FSQRT */ + gen_helper_sqrt_f16(tcg_res, tcg_op, cpu_env); + break; + case 0x8: /* FRINTN */ + case 0x9: /* FRINTP */ + case 0xa: /* FRINTM */ + case 0xb: /* FRINTZ */ + case 0xc: /* FRINTA */ + { + TCGv_i32 tcg_rmode = tcg_const_i32(arm_rmode_to_sf(opcode & 7)); + fpst = get_fpstatus_ptr(true); + + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); + gen_helper_advsimd_rinth(tcg_res, tcg_op, fpst); + + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); + tcg_temp_free_i32(tcg_rmode); + break; + } + case 0xe: /* FRINTX */ + fpst = get_fpstatus_ptr(true); + gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, fpst); + break; + case 0xf: /* FRINTI */ + fpst = get_fpstatus_ptr(true); + gen_helper_advsimd_rinth(tcg_res, tcg_op, fpst); + break; + default: + abort(); + } + + write_fp_sreg(s, rd, tcg_res); + + if (fpst) { + tcg_temp_free_ptr(fpst); + } + tcg_temp_free_i32(tcg_op); + tcg_temp_free_i32(tcg_res); +} + /* Floating-point data-processing (1 source) - single precision */ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) { @@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) handle_fp_1src_double(s, opcode, rd, rn); break; + case 3: + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + return; + } + + if (!fp_access_check(s)) { + return; + } + + handle_fp_1src_half(s, opcode, rd, rn); + break; default: unallocated_encoding(s); } -- 2.16.2 Now we have implemented FP16 we can enable it for the "any" CPU. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> [PMM: split out from an earlier patch in the series] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 1 + 1 file changed, 1 insertion(+) 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_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 */ } -- 2.16.2 Set the appropriate Linux hwcap bits to tell the guest binary if we have implemented half-precision floating point support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@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_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; -- 2.16.2 From: Alistair Francis <alistair.francis@xilinx.com> I am leaving Xilinx, so to avoid having an email address that bounces update my maintainer address to point to my personal email address. Signed-off-by: Alistair Francis <alistair.francis@xilinx.com> Signed-off-by: Alistair Francis <alistair@alistair23.me> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 7bb690382e3370aa1c1e047a84e36603c787ec0e.1519749987.git.alistair.francis@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ 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_* @@ -XXX,XX +XXX,XX @@ 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 @@ -XXX,XX +XXX,XX @@ 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 @@ -XXX,XX +XXX,XX @@ 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_* @@ -XXX,XX +XXX,XX @@ 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 @@ -XXX,XX +XXX,XX @@ 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 -- 2.16.2 Hi; here's the latest round of arm patches. I have included also my patchset for the RTC devices to avoid keeping time_t and time_t diffs in 32-bit variables. thanks -- PMM The following changes since commit 156618d9ea67f2f2e31d9dedd97f2dcccbe6808c: Merge tag 'block-pull-request' of https://gitlab.com/stefanha/qemu into staging (2023-08-30 09:20:27 -0400) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230831 for you to fetch changes up to e73b8bb8a3e9a162f70e9ffbf922d4fafc96bbfb: hw/arm: Set number of MPU regions correctly for an505, an521, an524 (2023-08-31 11:07:02 +0100) ---------------------------------------------------------------- target-arm queue: * Some of the preliminary patches for Cortex-A710 support * i.MX7 and i.MX6UL refactoring * Implement SRC device for i.MX7 * Catch illegal-exception-return from EL3 with bad NSE/NS * Use 64-bit offsets for holding time_t differences in RTC devices * Model correct number of MPU regions for an505, an521, an524 boards ---------------------------------------------------------------- Alex Bennée (1): target/arm: properly document FEAT_CRC32 Jean-Christophe Dubois (6): Remove i.MX7 IOMUX GPR device from i.MX6UL Refactor i.MX6UL processor code Add i.MX6UL missing devices. Refactor i.MX7 processor code Add i.MX7 missing TZ devices and memory regions Add i.MX7 SRC device implementation Peter Maydell (8): target/arm: Catch illegal-exception-return from EL3 with bad NSE/NS hw/rtc/m48t59: Use 64-bit arithmetic in set_alarm() hw/rtc/twl92230: Use int64_t for sec_offset and alm_sec hw/rtc/aspeed_rtc: Use 64-bit offset for holding time_t difference rtc: Use time_t for passing and returning time offsets target/arm: Do all "ARM_FEATURE_X implies Y" checks in post_init hw/arm/armv7m: Add mpu-ns-regions and mpu-s-regions properties hw/arm: Set number of MPU regions correctly for an505, an521, an524 Richard Henderson (9): target/arm: Reduce dcz_blocksize to uint8_t target/arm: Allow cpu to configure GM blocksize target/arm: Support more GM blocksizes target/arm: When tag memory is not present, set MTE=1 target/arm: Introduce make_ccsidr64 target/arm: Apply access checks to neoverse-n1 special registers target/arm: Apply access checks to neoverse-v1 special registers target/arm: Suppress FEAT_TRBE (Trace Buffer Extension) target/arm: Implement FEAT_HPDS2 as a no-op docs/system/arm/emulation.rst | 2 + include/hw/arm/armsse.h | 5 + include/hw/arm/armv7m.h | 8 + include/hw/arm/fsl-imx6ul.h | 158 ++++++++++++++++--- include/hw/arm/fsl-imx7.h | 338 ++++++++++++++++++++++++++++++----------- include/hw/misc/imx7_src.h | 66 ++++++++ include/hw/rtc/aspeed_rtc.h | 2 +- include/sysemu/rtc.h | 4 +- target/arm/cpregs.h | 2 + target/arm/cpu.h | 5 +- target/arm/internals.h | 6 - target/arm/tcg/translate.h | 2 + hw/arm/armsse.c | 16 ++ hw/arm/armv7m.c | 21 +++ hw/arm/fsl-imx6ul.c | 174 +++++++++++++-------- hw/arm/fsl-imx7.c | 201 +++++++++++++++++++----- hw/arm/mps2-tz.c | 29 ++++ hw/misc/imx7_src.c | 276 +++++++++++++++++++++++++++++++++ hw/rtc/aspeed_rtc.c | 5 +- hw/rtc/m48t59.c | 2 +- hw/rtc/twl92230.c | 4 +- softmmu/rtc.c | 4 +- target/arm/cpu.c | 207 ++++++++++++++----------- target/arm/helper.c | 15 +- target/arm/tcg/cpu32.c | 2 +- target/arm/tcg/cpu64.c | 102 +++++++++---- target/arm/tcg/helper-a64.c | 9 ++ target/arm/tcg/mte_helper.c | 90 ++++++++--- target/arm/tcg/translate-a64.c | 5 +- hw/misc/meson.build | 1 + hw/misc/trace-events | 4 + 31 files changed, 1393 insertions(+), 372 deletions(-) create mode 100644 include/hw/misc/imx7_src.h create mode 100644 hw/misc/imx7_src.c From: Richard Henderson <richard.henderson@linaro.org> This value is only 4 bits wide. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230811214031.171020-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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 { bool prop_lpa2; /* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ - uint32_t dcz_blocksize; + uint8_t dcz_blocksize; + uint64_t rvbar_prop; /* Property/input signals. */ /* Configurable aspects of GIC cpu interface (which is part of the CPU) */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Previously we hard-coded the blocksize with GMID_EL1_BS. But the value we choose for -cpu max does not match the value that cortex-a710 uses. Mirror the way we handle dcz_blocksize. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230811214031.171020-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/internals.h | 6 ----- target/arm/tcg/translate.h | 2 ++ target/arm/helper.c | 11 +++++--- target/arm/tcg/cpu64.c | 1 + target/arm/tcg/mte_helper.c | 46 ++++++++++++++++++++++------------ target/arm/tcg/translate-a64.c | 5 ++-- 7 files changed, 45 insertions(+), 28 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 @@ struct ArchCPU { /* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ uint8_t dcz_blocksize; + /* GM blocksize, in log_2(words), ie low 4 bits of GMID_EL0 */ + uint8_t gm_blocksize; uint64_t rvbar_prop; /* Property/input signals. */ diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ void arm_log_exception(CPUState *cs); #endif /* !CONFIG_USER_ONLY */ -/* - * The log2 of the words in the tag block, for GMID_EL1.BS. - * The is the maximum, 256 bytes, which manipulates 64-bits of tags. - */ -#define GMID_EL1_BS 6 - /* * SVE predicates are 1/8 the size of SVE vectors, and cannot use * the same simd_desc() encoding due to restrictions on size. 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 { int8_t btype; /* A copy of cpu->dcz_blocksize. */ uint8_t dcz_blocksize; + /* A copy of cpu->gm_blocksize. */ + uint8_t gm_blocksize; /* True if this page is guarded. */ bool guarded_page; /* Bottom two bits of XScale c15_cpar coprocessor access control reg */ 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 const ARMCPRegInfo mte_reginfo[] = { .opc0 = 3, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 6, .access = PL1_RW, .accessfn = access_mte, .fieldoffset = offsetof(CPUARMState, cp15.gcr_el1) }, - { .name = "GMID_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 0, .crm = 0, .opc2 = 4, - .access = PL1_R, .accessfn = access_aa64_tid5, - .type = ARM_CP_CONST, .resetvalue = GMID_EL1_BS }, { .name = "TCO", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 4, .crm = 2, .opc2 = 7, .type = ARM_CP_NO_RAW, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) * then define only a RAZ/WI version of PSTATE.TCO. */ if (cpu_isar_feature(aa64_mte, cpu)) { + ARMCPRegInfo gmid_reginfo = { + .name = "GMID_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 0, .crm = 0, .opc2 = 4, + .access = PL1_R, .accessfn = access_aa64_tid5, + .type = ARM_CP_CONST, .resetvalue = cpu->gm_blocksize, + }; + define_one_arm_cp_reg(cpu, &gmid_reginfo); define_arm_cp_regs(cpu, mte_reginfo); define_arm_cp_regs(cpu, mte_el0_cacheop_reginfo); } else if (cpu_isar_feature(aa64_mte_insn_reg, cpu)) { 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) cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ cpu->dcz_blocksize = 7; /* 512 bytes */ #endif + cpu->gm_blocksize = 6; /* 256 bytes */ cpu->sve_vq.supported = MAKE_64BIT_MASK(0, ARM_MAX_VQ); cpu->sme_vq.supported = SVE_VQ_POW2_MAP; diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(st2g_stub)(CPUARMState *env, uint64_t ptr) } } -#define LDGM_STGM_SIZE (4 << GMID_EL1_BS) - uint64_t HELPER(ldgm)(CPUARMState *env, uint64_t ptr) { int mmu_idx = cpu_mmu_index(env, false); uintptr_t ra = GETPC(); + int gm_bs = env_archcpu(env)->gm_blocksize; + int gm_bs_bytes = 4 << gm_bs; void *tag_mem; - ptr = QEMU_ALIGN_DOWN(ptr, LDGM_STGM_SIZE); + ptr = QEMU_ALIGN_DOWN(ptr, gm_bs_bytes); /* Trap if accessing an invalid page. */ tag_mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_LOAD, - LDGM_STGM_SIZE, MMU_DATA_LOAD, - LDGM_STGM_SIZE / (2 * TAG_GRANULE), ra); + gm_bs_bytes, MMU_DATA_LOAD, + gm_bs_bytes / (2 * TAG_GRANULE), ra); /* The tag is squashed to zero if the page does not support tags. */ if (!tag_mem) { return 0; } - QEMU_BUILD_BUG_ON(GMID_EL1_BS != 6); /* - * We are loading 64-bits worth of tags. The ordering of elements - * within the word corresponds to a 64-bit little-endian operation. + * The ordering of elements within the word corresponds to + * a little-endian operation. */ - return ldq_le_p(tag_mem); + switch (gm_bs) { + case 6: + /* 256 bytes -> 16 tags -> 64 result bits */ + return ldq_le_p(tag_mem); + default: + /* cpu configured with unsupported gm blocksize. */ + g_assert_not_reached(); + } } void HELPER(stgm)(CPUARMState *env, uint64_t ptr, uint64_t val) { int mmu_idx = cpu_mmu_index(env, false); uintptr_t ra = GETPC(); + int gm_bs = env_archcpu(env)->gm_blocksize; + int gm_bs_bytes = 4 << gm_bs; void *tag_mem; - ptr = QEMU_ALIGN_DOWN(ptr, LDGM_STGM_SIZE); + ptr = QEMU_ALIGN_DOWN(ptr, gm_bs_bytes); /* Trap if accessing an invalid page. */ tag_mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_STORE, - LDGM_STGM_SIZE, MMU_DATA_LOAD, - LDGM_STGM_SIZE / (2 * TAG_GRANULE), ra); + gm_bs_bytes, MMU_DATA_LOAD, + gm_bs_bytes / (2 * TAG_GRANULE), ra); /* * Tag store only happens if the page support tags, @@ -XXX,XX +XXX,XX @@ void HELPER(stgm)(CPUARMState *env, uint64_t ptr, uint64_t val) return; } - QEMU_BUILD_BUG_ON(GMID_EL1_BS != 6); /* - * We are storing 64-bits worth of tags. The ordering of elements - * within the word corresponds to a 64-bit little-endian operation. + * The ordering of elements within the word corresponds to + * a little-endian operation. */ - stq_le_p(tag_mem, val); + switch (gm_bs) { + case 6: + stq_le_p(tag_mem, val); + break; + default: + /* cpu configured with unsupported gm blocksize. */ + g_assert_not_reached(); + } } void HELPER(stzgm_tags)(CPUARMState *env, uint64_t ptr, uint64_t val) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_STGM(DisasContext *s, arg_ldst_tag *a) gen_helper_stgm(cpu_env, addr, tcg_rt); } else { MMUAccessType acc = MMU_DATA_STORE; - int size = 4 << GMID_EL1_BS; + int size = 4 << s->gm_blocksize; clean_addr = clean_data_tbi(s, addr); tcg_gen_andi_i64(clean_addr, clean_addr, -size); @@ -XXX,XX +XXX,XX @@ static bool trans_LDGM(DisasContext *s, arg_ldst_tag *a) gen_helper_ldgm(tcg_rt, cpu_env, addr); } else { MMUAccessType acc = MMU_DATA_LOAD; - int size = 4 << GMID_EL1_BS; + int size = 4 << s->gm_blocksize; clean_addr = clean_data_tbi(s, addr); tcg_gen_andi_i64(clean_addr, clean_addr, -size); @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->cp_regs = arm_cpu->cp_regs; dc->features = env->features; dc->dcz_blocksize = arm_cpu->dcz_blocksize; + dc->gm_blocksize = arm_cpu->gm_blocksize; #ifdef CONFIG_USER_ONLY /* In sve_probe_page, we assume TBI is enabled. */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Support all of the easy GM block sizes. Use direct memory operations, since the pointers are aligned. While BS=2 (16 bytes, 1 tag) is a legal setting, that requires an atomic store of one nibble. This is not difficult, but there is also no point in supporting it until required. Note that cortex-a710 sets GM blocksize to match its cacheline size of 64 bytes. I expect many implementations will also match the cacheline, which makes 16 bytes very unlikely. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 18 +++++++++--- target/arm/tcg/mte_helper.c | 56 +++++++++++++++++++++++++++++++------ 2 files changed, 62 insertions(+), 12 deletions(-) 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) ID_PFR1, VIRTUALIZATION, 0); } + if (cpu_isar_feature(aa64_mte, cpu)) { + /* + * The architectural range of GM blocksize is 2-6, however qemu + * doesn't support blocksize of 2 (see HELPER(ldgm)). + */ + if (tcg_enabled()) { + assert(cpu->gm_blocksize >= 3 && cpu->gm_blocksize <= 6); + } + #ifndef CONFIG_USER_ONLY - if (cpu->tag_memory == NULL && cpu_isar_feature(aa64_mte, cpu)) { /* * Disable the MTE feature bits if we do not have tag-memory * provided by the machine. */ - cpu->isar.id_aa64pfr1 = - FIELD_DP64(cpu->isar.id_aa64pfr1, ID_AA64PFR1, MTE, 0); - } + if (cpu->tag_memory == NULL) { + cpu->isar.id_aa64pfr1 = + FIELD_DP64(cpu->isar.id_aa64pfr1, ID_AA64PFR1, MTE, 0); + } #endif + } if (tcg_enabled()) { /* diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(ldgm)(CPUARMState *env, uint64_t ptr) int gm_bs = env_archcpu(env)->gm_blocksize; int gm_bs_bytes = 4 << gm_bs; void *tag_mem; + uint64_t ret; + int shift; ptr = QEMU_ALIGN_DOWN(ptr, gm_bs_bytes); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(ldgm)(CPUARMState *env, uint64_t ptr) /* * The ordering of elements within the word corresponds to - * a little-endian operation. + * a little-endian operation. Computation of shift comes from + * + * index = address<LOG2_TAG_GRANULE+3:LOG2_TAG_GRANULE> + * data<index*4+3:index*4> = tag + * + * Because of the alignment of ptr above, BS=6 has shift=0. + * All memory operations are aligned. Defer support for BS=2, + * requiring insertion or extraction of a nibble, until we + * support a cpu that requires it. */ switch (gm_bs) { + case 3: + /* 32 bytes -> 2 tags -> 8 result bits */ + ret = *(uint8_t *)tag_mem; + break; + case 4: + /* 64 bytes -> 4 tags -> 16 result bits */ + ret = cpu_to_le16(*(uint16_t *)tag_mem); + break; + case 5: + /* 128 bytes -> 8 tags -> 32 result bits */ + ret = cpu_to_le32(*(uint32_t *)tag_mem); + break; case 6: /* 256 bytes -> 16 tags -> 64 result bits */ - return ldq_le_p(tag_mem); + return cpu_to_le64(*(uint64_t *)tag_mem); default: - /* cpu configured with unsupported gm blocksize. */ + /* + * CPU configured with unsupported/invalid gm blocksize. + * This is detected early in arm_cpu_realizefn. + */ g_assert_not_reached(); } + shift = extract64(ptr, LOG2_TAG_GRANULE, 4) * 4; + return ret << shift; } void HELPER(stgm)(CPUARMState *env, uint64_t ptr, uint64_t val) @@ -XXX,XX +XXX,XX @@ void HELPER(stgm)(CPUARMState *env, uint64_t ptr, uint64_t val) int gm_bs = env_archcpu(env)->gm_blocksize; int gm_bs_bytes = 4 << gm_bs; void *tag_mem; + int shift; ptr = QEMU_ALIGN_DOWN(ptr, gm_bs_bytes); @@ -XXX,XX +XXX,XX @@ void HELPER(stgm)(CPUARMState *env, uint64_t ptr, uint64_t val) return; } - /* - * The ordering of elements within the word corresponds to - * a little-endian operation. - */ + /* See LDGM for comments on BS and on shift. */ + shift = extract64(ptr, LOG2_TAG_GRANULE, 4) * 4; + val >>= shift; switch (gm_bs) { + case 3: + /* 32 bytes -> 2 tags -> 8 result bits */ + *(uint8_t *)tag_mem = val; + break; + case 4: + /* 64 bytes -> 4 tags -> 16 result bits */ + *(uint16_t *)tag_mem = cpu_to_le16(val); + break; + case 5: + /* 128 bytes -> 8 tags -> 32 result bits */ + *(uint32_t *)tag_mem = cpu_to_le32(val); + break; case 6: - stq_le_p(tag_mem, val); + /* 256 bytes -> 16 tags -> 64 result bits */ + *(uint64_t *)tag_mem = cpu_to_le64(val); break; default: /* cpu configured with unsupported gm blocksize. */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> When the cpu support MTE, but the system does not, reduce cpu support to user instructions at EL0 instead of completely disabling MTE. If we encounter a cpu implementation which does something else, we can revisit this setting. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) 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) #ifndef CONFIG_USER_ONLY /* - * Disable the MTE feature bits if we do not have tag-memory - * provided by the machine. + * If we do not have tag-memory provided by the machine, + * reduce MTE support to instructions enabled at EL0. + * This matches Cortex-A710 BROADCASTMTE input being LOW. */ if (cpu->tag_memory == NULL) { cpu->isar.id_aa64pfr1 = - FIELD_DP64(cpu->isar.id_aa64pfr1, ID_AA64PFR1, MTE, 0); + FIELD_DP64(cpu->isar.id_aa64pfr1, ID_AA64PFR1, MTE, 1); } #endif } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Do not hard-code the constants for Neoverse V1. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/cpu64.c | 48 ++++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 16 deletions(-) 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 @@ #include "qemu/module.h" #include "qapi/visitor.h" #include "hw/qdev-properties.h" +#include "qemu/units.h" #include "internals.h" #include "cpregs.h" +static uint64_t make_ccsidr64(unsigned assoc, unsigned linesize, + unsigned cachesize) +{ + unsigned lg_linesize = ctz32(linesize); + unsigned sets; + + /* + * The 64-bit CCSIDR_EL1 format is: + * [55:32] number of sets - 1 + * [23:3] associativity - 1 + * [2:0] log2(linesize) - 4 + * so 0 == 16 bytes, 1 == 32 bytes, 2 == 64 bytes, etc + */ + assert(assoc != 0); + assert(is_power_of_2(linesize)); + assert(lg_linesize >= 4 && lg_linesize <= 7 + 4); + + /* sets * associativity * linesize == cachesize. */ + sets = cachesize / (assoc * linesize); + assert(cachesize % (assoc * linesize) == 0); + + return ((uint64_t)(sets - 1) << 32) + | ((assoc - 1) << 3) + | (lg_linesize - 4); +} + static void aarch64_a35_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_v1_initfn(Object *obj) * The Neoverse-V1 r1p2 TRM lists 32-bit format CCSIDR_EL1 values, * but also says it implements CCIDX, which means they should be * 64-bit format. So we here use values which are based on the textual - * information in chapter 2 of the TRM (and on the fact that - * sets * associativity * linesize == cachesize). - * - * The 64-bit CCSIDR_EL1 format is: - * [55:32] number of sets - 1 - * [23:3] associativity - 1 - * [2:0] log2(linesize) - 4 - * so 0 == 16 bytes, 1 == 32 bytes, 2 == 64 bytes, etc - * - * L1: 4-way set associative 64-byte line size, total size 64K, - * so sets is 256. + * information in chapter 2 of the TRM: * + * L1: 4-way set associative 64-byte line size, total size 64K. * L2: 8-way set associative, 64 byte line size, either 512K or 1MB. - * We pick 1MB, so this has 2048 sets. - * * L3: No L3 (this matches the CLIDR_EL1 value). */ - cpu->ccsidr[0] = 0x000000ff0000001aull; /* 64KB L1 dcache */ - cpu->ccsidr[1] = 0x000000ff0000001aull; /* 64KB L1 icache */ - cpu->ccsidr[2] = 0x000007ff0000003aull; /* 1MB L2 cache */ + cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB); /* L1 dcache */ + cpu->ccsidr[1] = cpu->ccsidr[0]; /* L1 icache */ + cpu->ccsidr[2] = make_ccsidr64(8, 64, 1 * MiB); /* L2 cache */ /* From 3.2.115 SCTLR_EL3 */ cpu->reset_sctlr = 0x30c50838; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Access to many of the special registers is enabled or disabled by ACTLR_EL[23], which we implement as constant 0, which means that all writes outside EL3 should trap. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpregs.h | 2 ++ target/arm/helper.c | 4 ++-- target/arm/tcg/cpu64.c | 46 +++++++++++++++++++++++++++++++++--------- 3 files changed, 41 insertions(+), 11 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -XXX,XX +XXX,XX @@ static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu); #endif +CPAccessResult access_tvm_trvm(CPUARMState *, const ARMCPRegInfo *, bool); + #endif /* TARGET_ARM_CPREGS_H */ 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 CPAccessResult access_tpm(CPUARMState *env, const ARMCPRegInfo *ri, } /* Check for traps from EL1 due to HCR_EL2.TVM and HCR_EL2.TRVM. */ -static CPAccessResult access_tvm_trvm(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) +CPAccessResult access_tvm_trvm(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) { if (arm_current_el(env) == 1) { uint64_t trap = isread ? HCR_TRVM : HCR_TVM; diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a64fx_initfn(Object *obj) /* TODO: Add A64FX specific HPC extension registers */ } +static CPAccessResult access_actlr_w(CPUARMState *env, const ARMCPRegInfo *r, + bool read) +{ + if (!read) { + int el = arm_current_el(env); + + /* Because ACTLR_EL2 is constant 0, writes below EL2 trap to EL2. */ + if (el < 2 && arm_is_el2_enabled(env)) { + return CP_ACCESS_TRAP_EL2; + } + /* Because ACTLR_EL3 is constant 0, writes below EL3 trap to EL3. */ + if (el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { + return CP_ACCESS_TRAP_EL3; + } + } + return CP_ACCESS_OK; +} + static const ARMCPRegInfo neoverse_n1_cp_reginfo[] = { { .name = "ATCR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 7, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + /* Traps and enables are the same as for TCR_EL1. */ + .accessfn = access_tvm_trvm, .fgt = FGT_TCR_EL1, }, { .name = "ATCR_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 15, .crm = 7, .opc2 = 0, .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo neoverse_n1_cp_reginfo[] = { .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, { .name = "CPUACTLR2_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, { .name = "CPUACTLR3_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, /* * Report CPUCFR_EL1.SCU as 1, as we do not implement the DSU * (and in particular its system registers). @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo neoverse_n1_cp_reginfo[] = { .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = 4 }, { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 4, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0x961563010 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0x961563010, + .accessfn = access_actlr_w }, { .name = "CPUPCR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 1, .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo neoverse_n1_cp_reginfo[] = { .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "CPUPWRCTLR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 7, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, { .name = "ERXPFGCDN_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, { .name = "ERXPFGCTL_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, { .name = "ERXPFGF_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, }; static void define_neoverse_n1_cp_reginfo(ARMCPU *cpu) -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> There is only one additional EL1 register modeled, which also needs to use access_actlr_w. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/cpu64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ static void define_neoverse_n1_cp_reginfo(ARMCPU *cpu) static const ARMCPRegInfo neoverse_v1_cp_reginfo[] = { { .name = "CPUECTLR2_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 5, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, { .name = "CPUPPMCR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 2, .opc2 = 0, .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Like FEAT_TRF (Self-hosted Trace Extension), suppress tracing external to the cpu, which is out of scope for QEMU. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 3 +++ 1 file changed, 3 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) /* FEAT_SPE (Statistical Profiling Extension) */ cpu->isar.id_aa64dfr0 = FIELD_DP64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, PMSVER, 0); + /* FEAT_TRBE (Trace Buffer Extension) */ + cpu->isar.id_aa64dfr0 = + FIELD_DP64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, TRACEBUFFER, 0); /* FEAT_TRF (Self-hosted Trace Extension) */ cpu->isar.id_aa64dfr0 = FIELD_DP64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, TRACEFILT, 0); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This feature allows the operating system to set TCR_ELx.HWU* to allow the implementation to use the PBHA bits from the block and page descriptors for for IMPLEMENTATION DEFINED purposes. Since QEMU has no need to use these bits, we may simply ignore them. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230811214031.171020-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu32.c | 2 +- target/arm/tcg/cpu64.c | 2 +- 3 files changed, 3 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_HAFDBS (Hardware management of the access flag and dirty bit state) - FEAT_HCX (Support for the HCRX_EL2 register) - FEAT_HPDS (Hierarchical permission disables) +- FEAT_HPDS2 (Translation table page-based hardware attributes) - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) - FEAT_IDST (ID space trap handling) - FEAT_IESB (Implicit error synchronization event) diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_mmfr3 = t; t = cpu->isar.id_mmfr4; - t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* FEAT_AA32HPD */ + t = FIELD_DP32(t, ID_MMFR4, HPDS, 2); /* FEAT_HPDS2 */ t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* FEAT_TTCNP */ t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* FEAT_XNX */ 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_AA64MMFR1, HAFDBS, 2); /* FEAT_HAFDBS */ t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* FEAT_VMID16 */ t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); /* FEAT_VHE */ - t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* FEAT_HPDS */ + t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 2); /* FEAT_HPDS2 */ t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1); /* FEAT_LOR */ t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 3); /* FEAT_PAN3 */ t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* FEAT_XNX */ -- 2.34.1 From: Alex Bennée <alex.bennee@linaro.org> This is a mandatory feature for Armv8.1 architectures but we don't state the feature clearly in our emulation list. Also include FEAT_CRC32 comment in aarch64_max_tcg_initfn for ease of grepping. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20230824075406.1515566-1-alex.bennee@linaro.org Cc: qemu-stable@nongnu.org Message-Id: <20230222110104.3996971-1-alex.bennee@linaro.org> [PMM: pluralize 'instructions' in docs] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) 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_BBM at level 2 (Translation table break-before-make levels) - FEAT_BF16 (AArch64 BFloat16 instructions) - FEAT_BTI (Branch Target Identification) +- FEAT_CRC32 (CRC32 instructions) - FEAT_CSV2 (Cache speculation variant 2) - FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) - FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) 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_AA64ISAR0, AES, 2); /* FEAT_PMULL */ t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); /* FEAT_SHA1 */ t = FIELD_DP64(t, ID_AA64ISAR0, SHA2, 2); /* FEAT_SHA512 */ - t = FIELD_DP64(t, ID_AA64ISAR0, CRC32, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, CRC32, 1); /* FEAT_CRC32 */ t = FIELD_DP64(t, ID_AA64ISAR0, ATOMIC, 2); /* FEAT_LSE */ t = FIELD_DP64(t, ID_AA64ISAR0, RDM, 1); /* FEAT_RDM */ t = FIELD_DP64(t, ID_AA64ISAR0, SHA3, 1); /* FEAT_SHA3 */ -- 2.34.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> i.MX7 IOMUX GPR device is not equivalent to i.MX6UL IOMUXC GPR device. In particular, register 22 is not present on i.MX6UL and this is actualy The only register that is really emulated in the i.MX7 IOMUX GPR device. Note: The i.MX6UL code is actually also implementing the IOMUX GPR device as an unimplemented device at the same bus adress and the 2 instantiations were actualy colliding. So we go back to the unimplemented device for now. Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Message-id: 48681bf51ee97646479bb261bee19abebbc8074e.1692964892.git.jcd@tribudubois.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6ul.h | 2 -- hw/arm/fsl-imx6ul.c | 11 ----------- 2 files changed, 13 deletions(-) diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx6ul_ccm.h" #include "hw/misc/imx6_src.h" #include "hw/misc/imx7_snvs.h" -#include "hw/misc/imx7_gpr.h" #include "hw/intc/imx_gpcv2.h" #include "hw/watchdog/wdt_imx2.h" #include "hw/gpio/imx_gpio.h" @@ -XXX,XX +XXX,XX @@ struct FslIMX6ULState { IMX6SRCState src; IMX7SNVSState snvs; IMXGPCv2State gpcv2; - IMX7GPRState gpr; IMXSPIState spi[FSL_IMX6UL_NUM_ECSPIS]; IMXI2CState i2c[FSL_IMX6UL_NUM_I2CS]; IMXSerialState uart[FSL_IMX6UL_NUM_UARTS]; diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) */ object_initialize_child(obj, "snvs", &s->snvs, TYPE_IMX7_SNVS); - /* - * GPR - */ - object_initialize_child(obj, "gpr", &s->gpr, TYPE_IMX7_GPR); - /* * GPIOs 1 to 5 */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_WDOGn_IRQ[i])); } - /* - * GPR - */ - sysbus_realize(SYS_BUS_DEVICE(&s->gpr), &error_abort); - sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpr), 0, FSL_IMX6UL_IOMUXC_GPR_ADDR); - /* * SDMA */ -- 2.34.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> * Add Addr and size definition for most i.MX6UL devices in i.MX6UL header file. * Use those newly defined named constants whenever possible. * Standardize the way we init a familly of unimplemented devices - SAI - PWM - CAN * Add/rework few comments Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Message-id: d579043fbd4e4b490370783fda43fc02c8e9be75.1692964892.git.jcd@tribudubois.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6ul.h | 156 +++++++++++++++++++++++++++++++----- hw/arm/fsl-imx6ul.c | 147 ++++++++++++++++++++++----------- 2 files changed, 232 insertions(+), 71 deletions(-) diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ #include "exec/memory.h" #include "cpu.h" #include "qom/object.h" +#include "qemu/units.h" #define TYPE_FSL_IMX6UL "fsl-imx6ul" OBJECT_DECLARE_SIMPLE_TYPE(FslIMX6ULState, FSL_IMX6UL) @@ -XXX,XX +XXX,XX @@ enum FslIMX6ULConfiguration { FSL_IMX6UL_NUM_ADCS = 2, FSL_IMX6UL_NUM_USB_PHYS = 2, FSL_IMX6UL_NUM_USBS = 2, + FSL_IMX6UL_NUM_SAIS = 3, + FSL_IMX6UL_NUM_CANS = 2, + FSL_IMX6UL_NUM_PWMS = 4, }; struct FslIMX6ULState { @@ -XXX,XX +XXX,XX @@ struct FslIMX6ULState { enum FslIMX6ULMemoryMap { FSL_IMX6UL_MMDC_ADDR = 0x80000000, - FSL_IMX6UL_MMDC_SIZE = 2 * 1024 * 1024 * 1024UL, + FSL_IMX6UL_MMDC_SIZE = (2 * GiB), FSL_IMX6UL_QSPI1_MEM_ADDR = 0x60000000, - FSL_IMX6UL_EIM_ALIAS_ADDR = 0x58000000, - FSL_IMX6UL_EIM_CS_ADDR = 0x50000000, - FSL_IMX6UL_AES_ENCRYPT_ADDR = 0x10000000, - FSL_IMX6UL_QSPI1_RX_ADDR = 0x0C000000, + FSL_IMX6UL_QSPI1_MEM_SIZE = (256 * MiB), - /* AIPS-2 */ + FSL_IMX6UL_EIM_ALIAS_ADDR = 0x58000000, + FSL_IMX6UL_EIM_ALIAS_SIZE = (128 * MiB), + + FSL_IMX6UL_EIM_CS_ADDR = 0x50000000, + FSL_IMX6UL_EIM_CS_SIZE = (128 * MiB), + + FSL_IMX6UL_AES_ENCRYPT_ADDR = 0x10000000, + FSL_IMX6UL_AES_ENCRYPT_SIZE = (1 * MiB), + + FSL_IMX6UL_QSPI1_RX_ADDR = 0x0C000000, + FSL_IMX6UL_QSPI1_RX_SIZE = (32 * MiB), + + /* AIPS-2 Begin */ FSL_IMX6UL_UART6_ADDR = 0x021FC000, + FSL_IMX6UL_I2C4_ADDR = 0x021F8000, + FSL_IMX6UL_UART5_ADDR = 0x021F4000, FSL_IMX6UL_UART4_ADDR = 0x021F0000, FSL_IMX6UL_UART3_ADDR = 0x021EC000, FSL_IMX6UL_UART2_ADDR = 0x021E8000, + FSL_IMX6UL_WDOG3_ADDR = 0x021E4000, + FSL_IMX6UL_QSPI_ADDR = 0x021E0000, + FSL_IMX6UL_QSPI_SIZE = 0x500, + FSL_IMX6UL_SYS_CNT_CTRL_ADDR = 0x021DC000, + FSL_IMX6UL_SYS_CNT_CTRL_SIZE = (16 * KiB), + FSL_IMX6UL_SYS_CNT_CMP_ADDR = 0x021D8000, + FSL_IMX6UL_SYS_CNT_CMP_SIZE = (16 * KiB), + FSL_IMX6UL_SYS_CNT_RD_ADDR = 0x021D4000, + FSL_IMX6UL_SYS_CNT_RD_SIZE = (16 * KiB), + FSL_IMX6UL_TZASC_ADDR = 0x021D0000, + FSL_IMX6UL_TZASC_SIZE = (16 * KiB), + FSL_IMX6UL_PXP_ADDR = 0x021CC000, + FSL_IMX6UL_PXP_SIZE = (16 * KiB), + FSL_IMX6UL_LCDIF_ADDR = 0x021C8000, + FSL_IMX6UL_LCDIF_SIZE = 0x100, + FSL_IMX6UL_CSI_ADDR = 0x021C4000, + FSL_IMX6UL_CSI_SIZE = 0x100, + FSL_IMX6UL_CSU_ADDR = 0x021C0000, + FSL_IMX6UL_CSU_SIZE = (16 * KiB), + FSL_IMX6UL_OCOTP_CTRL_ADDR = 0x021BC000, + FSL_IMX6UL_OCOTP_CTRL_SIZE = (4 * KiB), + FSL_IMX6UL_EIM_ADDR = 0x021B8000, + FSL_IMX6UL_EIM_SIZE = 0x100, + FSL_IMX6UL_SIM2_ADDR = 0x021B4000, + FSL_IMX6UL_MMDC_CFG_ADDR = 0x021B0000, + FSL_IMX6UL_MMDC_CFG_SIZE = (4 * KiB), + FSL_IMX6UL_ROMCP_ADDR = 0x021AC000, + FSL_IMX6UL_ROMCP_SIZE = 0x300, + FSL_IMX6UL_I2C3_ADDR = 0x021A8000, FSL_IMX6UL_I2C2_ADDR = 0x021A4000, FSL_IMX6UL_I2C1_ADDR = 0x021A0000, + FSL_IMX6UL_ADC2_ADDR = 0x0219C000, FSL_IMX6UL_ADC1_ADDR = 0x02198000, + FSL_IMX6UL_ADCn_SIZE = 0x100, + FSL_IMX6UL_USDHC2_ADDR = 0x02194000, FSL_IMX6UL_USDHC1_ADDR = 0x02190000, - FSL_IMX6UL_SIM1_ADDR = 0x0218C000, - FSL_IMX6UL_ENET1_ADDR = 0x02188000, - FSL_IMX6UL_USBO2_USBMISC_ADDR = 0x02184800, - FSL_IMX6UL_USBO2_USB_ADDR = 0x02184000, - FSL_IMX6UL_USBO2_PL301_ADDR = 0x02180000, - FSL_IMX6UL_AIPS2_CFG_ADDR = 0x0217C000, - FSL_IMX6UL_CAAM_ADDR = 0x02140000, - FSL_IMX6UL_A7MPCORE_DAP_ADDR = 0x02100000, - /* AIPS-1 */ + FSL_IMX6UL_SIM1_ADDR = 0x0218C000, + FSL_IMX6UL_SIMn_SIZE = (16 * KiB), + + FSL_IMX6UL_ENET1_ADDR = 0x02188000, + + FSL_IMX6UL_USBO2_USBMISC_ADDR = 0x02184800, + FSL_IMX6UL_USBO2_USB1_ADDR = 0x02184000, + FSL_IMX6UL_USBO2_USB2_ADDR = 0x02184200, + + FSL_IMX6UL_USBO2_PL301_ADDR = 0x02180000, + FSL_IMX6UL_USBO2_PL301_SIZE = (16 * KiB), + + FSL_IMX6UL_AIPS2_CFG_ADDR = 0x0217C000, + FSL_IMX6UL_AIPS2_CFG_SIZE = 0x100, + + FSL_IMX6UL_CAAM_ADDR = 0x02140000, + FSL_IMX6UL_CAAM_SIZE = (16 * KiB), + + FSL_IMX6UL_A7MPCORE_DAP_ADDR = 0x02100000, + FSL_IMX6UL_A7MPCORE_DAP_SIZE = (4 * KiB), + /* AIPS-2 End */ + + /* AIPS-1 Begin */ FSL_IMX6UL_PWM8_ADDR = 0x020FC000, FSL_IMX6UL_PWM7_ADDR = 0x020F8000, FSL_IMX6UL_PWM6_ADDR = 0x020F4000, FSL_IMX6UL_PWM5_ADDR = 0x020F0000, + FSL_IMX6UL_SDMA_ADDR = 0x020EC000, + FSL_IMX6UL_SDMA_SIZE = 0x300, + FSL_IMX6UL_GPT2_ADDR = 0x020E8000, + FSL_IMX6UL_IOMUXC_GPR_ADDR = 0x020E4000, + FSL_IMX6UL_IOMUXC_GPR_SIZE = 0x40, + FSL_IMX6UL_IOMUXC_ADDR = 0x020E0000, + FSL_IMX6UL_IOMUXC_SIZE = 0x700, + FSL_IMX6UL_GPC_ADDR = 0x020DC000, + FSL_IMX6UL_SRC_ADDR = 0x020D8000, + FSL_IMX6UL_EPIT2_ADDR = 0x020D4000, FSL_IMX6UL_EPIT1_ADDR = 0x020D0000, + FSL_IMX6UL_SNVS_HP_ADDR = 0x020CC000, + FSL_IMX6UL_USBPHY2_ADDR = 0x020CA000, - FSL_IMX6UL_USBPHY2_SIZE = (4 * 1024), FSL_IMX6UL_USBPHY1_ADDR = 0x020C9000, - FSL_IMX6UL_USBPHY1_SIZE = (4 * 1024), + FSL_IMX6UL_ANALOG_ADDR = 0x020C8000, + FSL_IMX6UL_ANALOG_SIZE = 0x300, + FSL_IMX6UL_CCM_ADDR = 0x020C4000, + FSL_IMX6UL_WDOG2_ADDR = 0x020C0000, FSL_IMX6UL_WDOG1_ADDR = 0x020BC000, + FSL_IMX6UL_KPP_ADDR = 0x020B8000, + FSL_IMX6UL_KPP_SIZE = 0x10, + FSL_IMX6UL_ENET2_ADDR = 0x020B4000, + FSL_IMX6UL_SNVS_LP_ADDR = 0x020B0000, + FSL_IMX6UL_SNVS_LP_SIZE = (16 * KiB), + FSL_IMX6UL_GPIO5_ADDR = 0x020AC000, FSL_IMX6UL_GPIO4_ADDR = 0x020A8000, FSL_IMX6UL_GPIO3_ADDR = 0x020A4000, FSL_IMX6UL_GPIO2_ADDR = 0x020A0000, FSL_IMX6UL_GPIO1_ADDR = 0x0209C000, + FSL_IMX6UL_GPT1_ADDR = 0x02098000, + FSL_IMX6UL_CAN2_ADDR = 0x02094000, FSL_IMX6UL_CAN1_ADDR = 0x02090000, + FSL_IMX6UL_CANn_SIZE = (4 * KiB), + FSL_IMX6UL_PWM4_ADDR = 0x0208C000, FSL_IMX6UL_PWM3_ADDR = 0x02088000, FSL_IMX6UL_PWM2_ADDR = 0x02084000, FSL_IMX6UL_PWM1_ADDR = 0x02080000, + FSL_IMX6UL_PWMn_SIZE = 0x20, + FSL_IMX6UL_AIPS1_CFG_ADDR = 0x0207C000, + FSL_IMX6UL_AIPS1_CFG_SIZE = (16 * KiB), + FSL_IMX6UL_BEE_ADDR = 0x02044000, + FSL_IMX6UL_BEE_SIZE = (16 * KiB), + FSL_IMX6UL_TOUCH_CTRL_ADDR = 0x02040000, + FSL_IMX6UL_TOUCH_CTRL_SIZE = 0x100, + FSL_IMX6UL_SPBA_ADDR = 0x0203C000, + FSL_IMX6UL_SPBA_SIZE = 0x100, + FSL_IMX6UL_ASRC_ADDR = 0x02034000, + FSL_IMX6UL_ASRC_SIZE = 0x100, + FSL_IMX6UL_SAI3_ADDR = 0x02030000, FSL_IMX6UL_SAI2_ADDR = 0x0202C000, FSL_IMX6UL_SAI1_ADDR = 0x02028000, + FSL_IMX6UL_SAIn_SIZE = 0x200, + FSL_IMX6UL_UART8_ADDR = 0x02024000, FSL_IMX6UL_UART1_ADDR = 0x02020000, FSL_IMX6UL_UART7_ADDR = 0x02018000, + FSL_IMX6UL_ECSPI4_ADDR = 0x02014000, FSL_IMX6UL_ECSPI3_ADDR = 0x02010000, FSL_IMX6UL_ECSPI2_ADDR = 0x0200C000, FSL_IMX6UL_ECSPI1_ADDR = 0x02008000, + FSL_IMX6UL_SPDIF_ADDR = 0x02004000, + FSL_IMX6UL_SPDIF_SIZE = 0x100, + /* AIPS-1 End */ + + FSL_IMX6UL_BCH_ADDR = 0x01808000, + FSL_IMX6UL_BCH_SIZE = 0x200, + + FSL_IMX6UL_GPMI_ADDR = 0x01806000, + FSL_IMX6UL_GPMI_SIZE = 0x200, FSL_IMX6UL_APBH_DMA_ADDR = 0x01804000, - FSL_IMX6UL_APBH_DMA_SIZE = (32 * 1024), + FSL_IMX6UL_APBH_DMA_SIZE = (4 * KiB), FSL_IMX6UL_A7MPCORE_ADDR = 0x00A00000, FSL_IMX6UL_OCRAM_ALIAS_ADDR = 0x00920000, - FSL_IMX6UL_OCRAM_ALIAS_SIZE = 0x00060000, + FSL_IMX6UL_OCRAM_ALIAS_SIZE = (384 * KiB), + FSL_IMX6UL_OCRAM_MEM_ADDR = 0x00900000, - FSL_IMX6UL_OCRAM_MEM_SIZE = 0x00020000, + FSL_IMX6UL_OCRAM_MEM_SIZE = (128 * KiB), + FSL_IMX6UL_CAAM_MEM_ADDR = 0x00100000, - FSL_IMX6UL_CAAM_MEM_SIZE = 0x00008000, + FSL_IMX6UL_CAAM_MEM_SIZE = (32 * KiB), + FSL_IMX6UL_ROM_ADDR = 0x00000000, - FSL_IMX6UL_ROM_SIZE = 0x00018000, + FSL_IMX6UL_ROM_SIZE = (96 * KiB), }; enum FslIMX6ULIRQs { diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) object_initialize_child(obj, "snvs", &s->snvs, TYPE_IMX7_SNVS); /* - * GPIOs 1 to 5 + * GPIOs */ for (i = 0; i < FSL_IMX6UL_NUM_GPIOS; i++) { snprintf(name, NAME_SIZE, "gpio%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * GPT 1, 2 + * GPTs */ for (i = 0; i < FSL_IMX6UL_NUM_GPTS; i++) { snprintf(name, NAME_SIZE, "gpt%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * EPIT 1, 2 + * EPITs */ for (i = 0; i < FSL_IMX6UL_NUM_EPITS; i++) { snprintf(name, NAME_SIZE, "epit%d", i + 1); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * eCSPI + * eCSPIs */ for (i = 0; i < FSL_IMX6UL_NUM_ECSPIS; i++) { snprintf(name, NAME_SIZE, "spi%d", i + 1); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * I2C + * I2Cs */ for (i = 0; i < FSL_IMX6UL_NUM_I2CS; i++) { snprintf(name, NAME_SIZE, "i2c%d", i + 1); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * UART + * UARTs */ for (i = 0; i < FSL_IMX6UL_NUM_UARTS; i++) { snprintf(name, NAME_SIZE, "uart%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * Ethernet + * Ethernets */ for (i = 0; i < FSL_IMX6UL_NUM_ETHS; i++) { snprintf(name, NAME_SIZE, "eth%d", i); object_initialize_child(obj, name, &s->eth[i], TYPE_IMX_ENET); } - /* USB */ + /* + * USB PHYs + */ for (i = 0; i < FSL_IMX6UL_NUM_USB_PHYS; i++) { snprintf(name, NAME_SIZE, "usbphy%d", i); object_initialize_child(obj, name, &s->usbphy[i], TYPE_IMX_USBPHY); } + + /* + * USBs + */ for (i = 0; i < FSL_IMX6UL_NUM_USBS; i++) { snprintf(name, NAME_SIZE, "usb%d", i); object_initialize_child(obj, name, &s->usb[i], TYPE_CHIPIDEA); } /* - * SDHCI + * SDHCIs */ for (i = 0; i < FSL_IMX6UL_NUM_USDHCS; i++) { snprintf(name, NAME_SIZE, "usdhc%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) } /* - * Watchdog + * Watchdogs */ for (i = 0; i < FSL_IMX6UL_NUM_WDTS; i++) { snprintf(name, NAME_SIZE, "wdt%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) * A7MPCORE DAP */ create_unimplemented_device("a7mpcore-dap", FSL_IMX6UL_A7MPCORE_DAP_ADDR, - 0x100000); + FSL_IMX6UL_A7MPCORE_DAP_SIZE); /* - * GPT 1, 2 + * GPTs */ for (i = 0; i < FSL_IMX6UL_NUM_GPTS; i++) { static const hwaddr FSL_IMX6UL_GPTn_ADDR[FSL_IMX6UL_NUM_GPTS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) } /* - * EPIT 1, 2 + * EPITs */ for (i = 0; i < FSL_IMX6UL_NUM_EPITS; i++) { static const hwaddr FSL_IMX6UL_EPITn_ADDR[FSL_IMX6UL_NUM_EPITS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) } /* - * GPIO + * GPIOs */ for (i = 0; i < FSL_IMX6UL_NUM_GPIOS; i++) { static const hwaddr FSL_IMX6UL_GPIOn_ADDR[FSL_IMX6UL_NUM_GPIOS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) } /* - * IOMUXC and IOMUXC_GPR + * IOMUXC */ - for (i = 0; i < 1; i++) { - static const hwaddr FSL_IMX6UL_IOMUXCn_ADDR[FSL_IMX6UL_NUM_IOMUXCS] = { - FSL_IMX6UL_IOMUXC_ADDR, - FSL_IMX6UL_IOMUXC_GPR_ADDR, - }; - - snprintf(name, NAME_SIZE, "iomuxc%d", i); - create_unimplemented_device(name, FSL_IMX6UL_IOMUXCn_ADDR[i], 0x4000); - } + create_unimplemented_device("iomuxc", FSL_IMX6UL_IOMUXC_ADDR, + FSL_IMX6UL_IOMUXC_SIZE); + create_unimplemented_device("iomuxc_gpr", FSL_IMX6UL_IOMUXC_GPR_ADDR, + FSL_IMX6UL_IOMUXC_GPR_SIZE); /* * CCM @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->gpcv2), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpcv2), 0, FSL_IMX6UL_GPC_ADDR); - /* Initialize all ECSPI */ + /* + * ECSPIs + */ for (i = 0; i < FSL_IMX6UL_NUM_ECSPIS; i++) { static const hwaddr FSL_IMX6UL_SPIn_ADDR[FSL_IMX6UL_NUM_ECSPIS] = { FSL_IMX6UL_ECSPI1_ADDR, @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) } /* - * I2C + * I2Cs */ for (i = 0; i < FSL_IMX6UL_NUM_I2CS; i++) { static const hwaddr FSL_IMX6UL_I2Cn_ADDR[FSL_IMX6UL_NUM_I2CS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) } /* - * UART + * UARTs */ for (i = 0; i < FSL_IMX6UL_NUM_UARTS; i++) { static const hwaddr FSL_IMX6UL_UARTn_ADDR[FSL_IMX6UL_NUM_UARTS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) } /* - * Ethernet + * Ethernets * * We must use two loops since phy_connected affects the other interface * and we have to set all properties before calling sysbus_realize(). @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_ENETn_TIMER_IRQ[i])); } - /* USB */ + /* + * USB PHYs + */ for (i = 0; i < FSL_IMX6UL_NUM_USB_PHYS; i++) { + static const hwaddr + FSL_IMX6UL_USB_PHYn_ADDR[FSL_IMX6UL_NUM_USB_PHYS] = { + FSL_IMX6UL_USBPHY1_ADDR, + FSL_IMX6UL_USBPHY2_ADDR, + }; + sysbus_realize(SYS_BUS_DEVICE(&s->usbphy[i]), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->usbphy[i]), 0, - FSL_IMX6UL_USBPHY1_ADDR + i * 0x1000); + FSL_IMX6UL_USB_PHYn_ADDR[i]); } + /* + * USBs + */ for (i = 0; i < FSL_IMX6UL_NUM_USBS; i++) { + static const hwaddr FSL_IMX6UL_USB02_USBn_ADDR[FSL_IMX6UL_NUM_USBS] = { + FSL_IMX6UL_USBO2_USB1_ADDR, + FSL_IMX6UL_USBO2_USB2_ADDR, + }; + static const int FSL_IMX6UL_USBn_IRQ[] = { FSL_IMX6UL_USB1_IRQ, FSL_IMX6UL_USB2_IRQ, }; + sysbus_realize(SYS_BUS_DEVICE(&s->usb[i]), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, - FSL_IMX6UL_USBO2_USB_ADDR + i * 0x200); + FSL_IMX6UL_USB02_USBn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i]), 0, qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX6UL_USBn_IRQ[i])); } /* - * USDHC + * USDHCs */ for (i = 0; i < FSL_IMX6UL_NUM_USDHCS; i++) { static const hwaddr FSL_IMX6UL_USDHCn_ADDR[FSL_IMX6UL_NUM_USDHCS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, FSL_IMX6UL_SNVS_HP_ADDR); /* - * Watchdog + * Watchdogs */ for (i = 0; i < FSL_IMX6UL_NUM_WDTS; i++) { static const hwaddr FSL_IMX6UL_WDOGn_ADDR[FSL_IMX6UL_NUM_WDTS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_WDOG2_ADDR, FSL_IMX6UL_WDOG3_ADDR, }; + static const int FSL_IMX6UL_WDOGn_IRQ[FSL_IMX6UL_NUM_WDTS] = { FSL_IMX6UL_WDOG1_IRQ, FSL_IMX6UL_WDOG2_IRQ, @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) /* * SDMA */ - create_unimplemented_device("sdma", FSL_IMX6UL_SDMA_ADDR, 0x4000); + create_unimplemented_device("sdma", FSL_IMX6UL_SDMA_ADDR, + FSL_IMX6UL_SDMA_SIZE); /* - * SAI (Audio SSI (Synchronous Serial Interface)) + * SAIs (Audio SSI (Synchronous Serial Interface)) */ - create_unimplemented_device("sai1", FSL_IMX6UL_SAI1_ADDR, 0x4000); - create_unimplemented_device("sai2", FSL_IMX6UL_SAI2_ADDR, 0x4000); - create_unimplemented_device("sai3", FSL_IMX6UL_SAI3_ADDR, 0x4000); + for (i = 0; i < FSL_IMX6UL_NUM_SAIS; i++) { + static const hwaddr FSL_IMX6UL_SAIn_ADDR[FSL_IMX6UL_NUM_SAIS] = { + FSL_IMX6UL_SAI1_ADDR, + FSL_IMX6UL_SAI2_ADDR, + FSL_IMX6UL_SAI3_ADDR, + }; + + snprintf(name, NAME_SIZE, "sai%d", i); + create_unimplemented_device(name, FSL_IMX6UL_SAIn_ADDR[i], + FSL_IMX6UL_SAIn_SIZE); + } /* - * PWM + * PWMs */ - create_unimplemented_device("pwm1", FSL_IMX6UL_PWM1_ADDR, 0x4000); - create_unimplemented_device("pwm2", FSL_IMX6UL_PWM2_ADDR, 0x4000); - create_unimplemented_device("pwm3", FSL_IMX6UL_PWM3_ADDR, 0x4000); - create_unimplemented_device("pwm4", FSL_IMX6UL_PWM4_ADDR, 0x4000); + for (i = 0; i < FSL_IMX6UL_NUM_PWMS; i++) { + static const hwaddr FSL_IMX6UL_PWMn_ADDR[FSL_IMX6UL_NUM_PWMS] = { + FSL_IMX6UL_PWM1_ADDR, + FSL_IMX6UL_PWM2_ADDR, + FSL_IMX6UL_PWM3_ADDR, + FSL_IMX6UL_PWM4_ADDR, + }; + + snprintf(name, NAME_SIZE, "pwm%d", i); + create_unimplemented_device(name, FSL_IMX6UL_PWMn_ADDR[i], + FSL_IMX6UL_PWMn_SIZE); + } /* * Audio ASRC (asynchronous sample rate converter) */ - create_unimplemented_device("asrc", FSL_IMX6UL_ASRC_ADDR, 0x4000); + create_unimplemented_device("asrc", FSL_IMX6UL_ASRC_ADDR, + FSL_IMX6UL_ASRC_SIZE); /* - * CAN + * CANs */ - create_unimplemented_device("can1", FSL_IMX6UL_CAN1_ADDR, 0x4000); - create_unimplemented_device("can2", FSL_IMX6UL_CAN2_ADDR, 0x4000); + for (i = 0; i < FSL_IMX6UL_NUM_CANS; i++) { + static const hwaddr FSL_IMX6UL_CANn_ADDR[FSL_IMX6UL_NUM_CANS] = { + FSL_IMX6UL_CAN1_ADDR, + FSL_IMX6UL_CAN2_ADDR, + }; + + snprintf(name, NAME_SIZE, "can%d", i); + create_unimplemented_device(name, FSL_IMX6UL_CANn_ADDR[i], + FSL_IMX6UL_CANn_SIZE); + } /* * APHB_DMA @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) }; snprintf(name, NAME_SIZE, "adc%d", i); - create_unimplemented_device(name, FSL_IMX6UL_ADCn_ADDR[i], 0x4000); + create_unimplemented_device(name, FSL_IMX6UL_ADCn_ADDR[i], + FSL_IMX6UL_ADCn_SIZE); } /* * LCD */ - create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR, 0x4000); + create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR, + FSL_IMX6UL_LCDIF_SIZE); /* * ROM memory -- 2.34.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> * Add TZASC as unimplemented device. - Allow bare metal application to access this (unimplemented) device * Add CSU as unimplemented device. - Allow bare metal application to access this (unimplemented) device * Add 4 missing PWM devices Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 59e4dc56e14eccfefd379275ec19048dff9c10b3.1692964892.git.jcd@tribudubois.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6ul.h | 2 +- hw/arm/fsl-imx6ul.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ enum FslIMX6ULConfiguration { FSL_IMX6UL_NUM_USBS = 2, FSL_IMX6UL_NUM_SAIS = 3, FSL_IMX6UL_NUM_CANS = 2, - FSL_IMX6UL_NUM_PWMS = 4, + FSL_IMX6UL_NUM_PWMS = 8, }; struct FslIMX6ULState { diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_PWM2_ADDR, FSL_IMX6UL_PWM3_ADDR, FSL_IMX6UL_PWM4_ADDR, + FSL_IMX6UL_PWM5_ADDR, + FSL_IMX6UL_PWM6_ADDR, + FSL_IMX6UL_PWM7_ADDR, + FSL_IMX6UL_PWM8_ADDR, }; snprintf(name, NAME_SIZE, "pwm%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR, FSL_IMX6UL_LCDIF_SIZE); + /* + * CSU + */ + create_unimplemented_device("csu", FSL_IMX6UL_CSU_ADDR, + FSL_IMX6UL_CSU_SIZE); + + /* + * TZASC + */ + create_unimplemented_device("tzasc", FSL_IMX6UL_TZASC_ADDR, + FSL_IMX6UL_TZASC_SIZE); + /* * ROM memory */ -- 2.34.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> * Add Addr and size definition for all i.MX7 devices in i.MX7 header file. * Use those newly defined named constants whenever possible. * Standardize the way we init a familly of unimplemented devices - SAI - PWM - CAN * Add/rework few comments Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Message-id: 59e195d33e4d486a8d131392acd46633c8c10ed7.1692964892.git.jcd@tribudubois.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 330 ++++++++++++++++++++++++++++---------- hw/arm/fsl-imx7.c | 130 ++++++++++----- 2 files changed, 335 insertions(+), 125 deletions(-) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_ccm.h" #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx7_gpr.h" -#include "hw/misc/imx6_src.h" #include "hw/watchdog/wdt_imx2.h" #include "hw/gpio/imx_gpio.h" #include "hw/char/imx_serial.h" @@ -XXX,XX +XXX,XX @@ #include "hw/usb/chipidea.h" #include "cpu.h" #include "qom/object.h" +#include "qemu/units.h" #define TYPE_FSL_IMX7 "fsl-imx7" OBJECT_DECLARE_SIMPLE_TYPE(FslIMX7State, FSL_IMX7) @@ -XXX,XX +XXX,XX @@ enum FslIMX7Configuration { FSL_IMX7_NUM_ECSPIS = 4, FSL_IMX7_NUM_USBS = 3, FSL_IMX7_NUM_ADCS = 2, + FSL_IMX7_NUM_SAIS = 3, + FSL_IMX7_NUM_CANS = 2, + FSL_IMX7_NUM_PWMS = 4, }; struct FslIMX7State { @@ -XXX,XX +XXX,XX @@ struct FslIMX7State { enum FslIMX7MemoryMap { FSL_IMX7_MMDC_ADDR = 0x80000000, - FSL_IMX7_MMDC_SIZE = 2 * 1024 * 1024 * 1024UL, + FSL_IMX7_MMDC_SIZE = (2 * GiB), - FSL_IMX7_GPIO1_ADDR = 0x30200000, - FSL_IMX7_GPIO2_ADDR = 0x30210000, - FSL_IMX7_GPIO3_ADDR = 0x30220000, - FSL_IMX7_GPIO4_ADDR = 0x30230000, - FSL_IMX7_GPIO5_ADDR = 0x30240000, - FSL_IMX7_GPIO6_ADDR = 0x30250000, - FSL_IMX7_GPIO7_ADDR = 0x30260000, + FSL_IMX7_QSPI1_MEM_ADDR = 0x60000000, + FSL_IMX7_QSPI1_MEM_SIZE = (256 * MiB), - FSL_IMX7_IOMUXC_LPSR_GPR_ADDR = 0x30270000, + FSL_IMX7_PCIE1_MEM_ADDR = 0x40000000, + FSL_IMX7_PCIE1_MEM_SIZE = (256 * MiB), - FSL_IMX7_WDOG1_ADDR = 0x30280000, - FSL_IMX7_WDOG2_ADDR = 0x30290000, - FSL_IMX7_WDOG3_ADDR = 0x302A0000, - FSL_IMX7_WDOG4_ADDR = 0x302B0000, + FSL_IMX7_QSPI1_RX_BUF_ADDR = 0x34000000, + FSL_IMX7_QSPI1_RX_BUF_SIZE = (32 * MiB), - FSL_IMX7_IOMUXC_LPSR_ADDR = 0x302C0000, + /* PCIe Peripherals */ + FSL_IMX7_PCIE_REG_ADDR = 0x33800000, - FSL_IMX7_GPT1_ADDR = 0x302D0000, - FSL_IMX7_GPT2_ADDR = 0x302E0000, - FSL_IMX7_GPT3_ADDR = 0x302F0000, - FSL_IMX7_GPT4_ADDR = 0x30300000, + /* MMAP Peripherals */ + FSL_IMX7_DMA_APBH_ADDR = 0x33000000, + FSL_IMX7_DMA_APBH_SIZE = 0x8000, - FSL_IMX7_IOMUXC_ADDR = 0x30330000, - FSL_IMX7_IOMUXC_GPR_ADDR = 0x30340000, - FSL_IMX7_IOMUXCn_SIZE = 0x1000, + /* GPV configuration */ + FSL_IMX7_GPV6_ADDR = 0x32600000, + FSL_IMX7_GPV5_ADDR = 0x32500000, + FSL_IMX7_GPV4_ADDR = 0x32400000, + FSL_IMX7_GPV3_ADDR = 0x32300000, + FSL_IMX7_GPV2_ADDR = 0x32200000, + FSL_IMX7_GPV1_ADDR = 0x32100000, + FSL_IMX7_GPV0_ADDR = 0x32000000, + FSL_IMX7_GPVn_SIZE = (1 * MiB), - FSL_IMX7_OCOTP_ADDR = 0x30350000, - FSL_IMX7_OCOTP_SIZE = 0x10000, + /* Arm Peripherals */ + FSL_IMX7_A7MPCORE_ADDR = 0x31000000, - FSL_IMX7_ANALOG_ADDR = 0x30360000, - FSL_IMX7_SNVS_ADDR = 0x30370000, - FSL_IMX7_CCM_ADDR = 0x30380000, + /* AIPS-3 Begin */ - FSL_IMX7_SRC_ADDR = 0x30390000, - FSL_IMX7_SRC_SIZE = 0x1000, + FSL_IMX7_ENET2_ADDR = 0x30BF0000, + FSL_IMX7_ENET1_ADDR = 0x30BE0000, - FSL_IMX7_ADC1_ADDR = 0x30610000, - FSL_IMX7_ADC2_ADDR = 0x30620000, - FSL_IMX7_ADCn_SIZE = 0x1000, + FSL_IMX7_SDMA_ADDR = 0x30BD0000, + FSL_IMX7_SDMA_SIZE = (4 * KiB), - FSL_IMX7_PWM1_ADDR = 0x30660000, - FSL_IMX7_PWM2_ADDR = 0x30670000, - FSL_IMX7_PWM3_ADDR = 0x30680000, - FSL_IMX7_PWM4_ADDR = 0x30690000, - FSL_IMX7_PWMn_SIZE = 0x10000, + FSL_IMX7_EIM_ADDR = 0x30BC0000, + FSL_IMX7_EIM_SIZE = (4 * KiB), - FSL_IMX7_PCIE_PHY_ADDR = 0x306D0000, - FSL_IMX7_PCIE_PHY_SIZE = 0x10000, + FSL_IMX7_QSPI_ADDR = 0x30BB0000, + FSL_IMX7_QSPI_SIZE = 0x8000, - FSL_IMX7_GPC_ADDR = 0x303A0000, + FSL_IMX7_SIM2_ADDR = 0x30BA0000, + FSL_IMX7_SIM1_ADDR = 0x30B90000, + FSL_IMX7_SIMn_SIZE = (4 * KiB), + + FSL_IMX7_USDHC3_ADDR = 0x30B60000, + FSL_IMX7_USDHC2_ADDR = 0x30B50000, + FSL_IMX7_USDHC1_ADDR = 0x30B40000, + + FSL_IMX7_USB3_ADDR = 0x30B30000, + FSL_IMX7_USBMISC3_ADDR = 0x30B30200, + FSL_IMX7_USB2_ADDR = 0x30B20000, + FSL_IMX7_USBMISC2_ADDR = 0x30B20200, + FSL_IMX7_USB1_ADDR = 0x30B10000, + FSL_IMX7_USBMISC1_ADDR = 0x30B10200, + FSL_IMX7_USBMISCn_SIZE = 0x200, + + FSL_IMX7_USB_PL301_ADDR = 0x30AD0000, + FSL_IMX7_USB_PL301_SIZE = (64 * KiB), + + FSL_IMX7_SEMAPHORE_HS_ADDR = 0x30AC0000, + FSL_IMX7_SEMAPHORE_HS_SIZE = (64 * KiB), + + FSL_IMX7_MUB_ADDR = 0x30AB0000, + FSL_IMX7_MUA_ADDR = 0x30AA0000, + FSL_IMX7_MUn_SIZE = (KiB), + + FSL_IMX7_UART7_ADDR = 0x30A90000, + FSL_IMX7_UART6_ADDR = 0x30A80000, + FSL_IMX7_UART5_ADDR = 0x30A70000, + FSL_IMX7_UART4_ADDR = 0x30A60000, + + FSL_IMX7_I2C4_ADDR = 0x30A50000, + FSL_IMX7_I2C3_ADDR = 0x30A40000, + FSL_IMX7_I2C2_ADDR = 0x30A30000, + FSL_IMX7_I2C1_ADDR = 0x30A20000, + + FSL_IMX7_CAN2_ADDR = 0x30A10000, + FSL_IMX7_CAN1_ADDR = 0x30A00000, + FSL_IMX7_CANn_SIZE = (4 * KiB), + + FSL_IMX7_AIPS3_CONF_ADDR = 0x309F0000, + FSL_IMX7_AIPS3_CONF_SIZE = (64 * KiB), FSL_IMX7_CAAM_ADDR = 0x30900000, - FSL_IMX7_CAAM_SIZE = 0x40000, + FSL_IMX7_CAAM_SIZE = (256 * KiB), - FSL_IMX7_CAN1_ADDR = 0x30A00000, - FSL_IMX7_CAN2_ADDR = 0x30A10000, - FSL_IMX7_CANn_SIZE = 0x10000, + FSL_IMX7_SPBA_ADDR = 0x308F0000, + FSL_IMX7_SPBA_SIZE = (4 * KiB), - FSL_IMX7_I2C1_ADDR = 0x30A20000, - FSL_IMX7_I2C2_ADDR = 0x30A30000, - FSL_IMX7_I2C3_ADDR = 0x30A40000, - FSL_IMX7_I2C4_ADDR = 0x30A50000, + FSL_IMX7_SAI3_ADDR = 0x308C0000, + FSL_IMX7_SAI2_ADDR = 0x308B0000, + FSL_IMX7_SAI1_ADDR = 0x308A0000, + FSL_IMX7_SAIn_SIZE = (4 * KiB), - FSL_IMX7_ECSPI1_ADDR = 0x30820000, - FSL_IMX7_ECSPI2_ADDR = 0x30830000, - FSL_IMX7_ECSPI3_ADDR = 0x30840000, - FSL_IMX7_ECSPI4_ADDR = 0x30630000, - - FSL_IMX7_LCDIF_ADDR = 0x30730000, - FSL_IMX7_LCDIF_SIZE = 0x1000, - - FSL_IMX7_UART1_ADDR = 0x30860000, + FSL_IMX7_UART3_ADDR = 0x30880000, /* * Some versions of the reference manual claim that UART2 is @ * 0x30870000, but experiments with HW + DT files in upstream @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { * actually located @ 0x30890000 */ FSL_IMX7_UART2_ADDR = 0x30890000, - FSL_IMX7_UART3_ADDR = 0x30880000, - FSL_IMX7_UART4_ADDR = 0x30A60000, - FSL_IMX7_UART5_ADDR = 0x30A70000, - FSL_IMX7_UART6_ADDR = 0x30A80000, - FSL_IMX7_UART7_ADDR = 0x30A90000, + FSL_IMX7_UART1_ADDR = 0x30860000, - FSL_IMX7_SAI1_ADDR = 0x308A0000, - FSL_IMX7_SAI2_ADDR = 0x308B0000, - FSL_IMX7_SAI3_ADDR = 0x308C0000, - FSL_IMX7_SAIn_SIZE = 0x10000, + FSL_IMX7_ECSPI3_ADDR = 0x30840000, + FSL_IMX7_ECSPI2_ADDR = 0x30830000, + FSL_IMX7_ECSPI1_ADDR = 0x30820000, + FSL_IMX7_ECSPIn_SIZE = (4 * KiB), - FSL_IMX7_ENET1_ADDR = 0x30BE0000, - FSL_IMX7_ENET2_ADDR = 0x30BF0000, + /* AIPS-3 End */ - FSL_IMX7_USB1_ADDR = 0x30B10000, - FSL_IMX7_USBMISC1_ADDR = 0x30B10200, - FSL_IMX7_USB2_ADDR = 0x30B20000, - FSL_IMX7_USBMISC2_ADDR = 0x30B20200, - FSL_IMX7_USB3_ADDR = 0x30B30000, - FSL_IMX7_USBMISC3_ADDR = 0x30B30200, - FSL_IMX7_USBMISCn_SIZE = 0x200, + /* AIPS-2 Begin */ - FSL_IMX7_USDHC1_ADDR = 0x30B40000, - FSL_IMX7_USDHC2_ADDR = 0x30B50000, - FSL_IMX7_USDHC3_ADDR = 0x30B60000, + FSL_IMX7_AXI_DEBUG_MON_ADDR = 0x307E0000, + FSL_IMX7_AXI_DEBUG_MON_SIZE = (64 * KiB), - FSL_IMX7_SDMA_ADDR = 0x30BD0000, - FSL_IMX7_SDMA_SIZE = 0x1000, + FSL_IMX7_PERFMON2_ADDR = 0x307D0000, + FSL_IMX7_PERFMON1_ADDR = 0x307C0000, + FSL_IMX7_PERFMONn_SIZE = (64 * KiB), + + FSL_IMX7_DDRC_ADDR = 0x307A0000, + FSL_IMX7_DDRC_SIZE = (4 * KiB), + + FSL_IMX7_DDRC_PHY_ADDR = 0x30790000, + FSL_IMX7_DDRC_PHY_SIZE = (4 * KiB), + + FSL_IMX7_TZASC_ADDR = 0x30780000, + FSL_IMX7_TZASC_SIZE = (64 * KiB), + + FSL_IMX7_MIPI_DSI_ADDR = 0x30760000, + FSL_IMX7_MIPI_DSI_SIZE = (4 * KiB), + + FSL_IMX7_MIPI_CSI_ADDR = 0x30750000, + FSL_IMX7_MIPI_CSI_SIZE = 0x4000, + + FSL_IMX7_LCDIF_ADDR = 0x30730000, + FSL_IMX7_LCDIF_SIZE = 0x8000, + + FSL_IMX7_CSI_ADDR = 0x30710000, + FSL_IMX7_CSI_SIZE = (4 * KiB), + + FSL_IMX7_PXP_ADDR = 0x30700000, + FSL_IMX7_PXP_SIZE = 0x4000, + + FSL_IMX7_EPDC_ADDR = 0x306F0000, + FSL_IMX7_EPDC_SIZE = (4 * KiB), + + FSL_IMX7_PCIE_PHY_ADDR = 0x306D0000, + FSL_IMX7_PCIE_PHY_SIZE = (4 * KiB), + + FSL_IMX7_SYSCNT_CTRL_ADDR = 0x306C0000, + FSL_IMX7_SYSCNT_CMP_ADDR = 0x306B0000, + FSL_IMX7_SYSCNT_RD_ADDR = 0x306A0000, + + FSL_IMX7_PWM4_ADDR = 0x30690000, + FSL_IMX7_PWM3_ADDR = 0x30680000, + FSL_IMX7_PWM2_ADDR = 0x30670000, + FSL_IMX7_PWM1_ADDR = 0x30660000, + FSL_IMX7_PWMn_SIZE = (4 * KiB), + + FSL_IMX7_FlEXTIMER2_ADDR = 0x30650000, + FSL_IMX7_FlEXTIMER1_ADDR = 0x30640000, + FSL_IMX7_FLEXTIMERn_SIZE = (4 * KiB), + + FSL_IMX7_ECSPI4_ADDR = 0x30630000, + + FSL_IMX7_ADC2_ADDR = 0x30620000, + FSL_IMX7_ADC1_ADDR = 0x30610000, + FSL_IMX7_ADCn_SIZE = (4 * KiB), + + FSL_IMX7_AIPS2_CONF_ADDR = 0x305F0000, + FSL_IMX7_AIPS2_CONF_SIZE = (64 * KiB), + + /* AIPS-2 End */ + + /* AIPS-1 Begin */ + + FSL_IMX7_CSU_ADDR = 0x303E0000, + FSL_IMX7_CSU_SIZE = (64 * KiB), + + FSL_IMX7_RDC_ADDR = 0x303D0000, + FSL_IMX7_RDC_SIZE = (4 * KiB), + + FSL_IMX7_SEMAPHORE2_ADDR = 0x303C0000, + FSL_IMX7_SEMAPHORE1_ADDR = 0x303B0000, + FSL_IMX7_SEMAPHOREn_SIZE = (4 * KiB), + + FSL_IMX7_GPC_ADDR = 0x303A0000, + + FSL_IMX7_SRC_ADDR = 0x30390000, + FSL_IMX7_SRC_SIZE = (4 * KiB), + + FSL_IMX7_CCM_ADDR = 0x30380000, + + FSL_IMX7_SNVS_HP_ADDR = 0x30370000, + + FSL_IMX7_ANALOG_ADDR = 0x30360000, + + FSL_IMX7_OCOTP_ADDR = 0x30350000, + FSL_IMX7_OCOTP_SIZE = 0x10000, + + FSL_IMX7_IOMUXC_GPR_ADDR = 0x30340000, + FSL_IMX7_IOMUXC_GPR_SIZE = (4 * KiB), + + FSL_IMX7_IOMUXC_ADDR = 0x30330000, + FSL_IMX7_IOMUXC_SIZE = (4 * KiB), + + FSL_IMX7_KPP_ADDR = 0x30320000, + FSL_IMX7_KPP_SIZE = (4 * KiB), + + FSL_IMX7_ROMCP_ADDR = 0x30310000, + FSL_IMX7_ROMCP_SIZE = (4 * KiB), + + FSL_IMX7_GPT4_ADDR = 0x30300000, + FSL_IMX7_GPT3_ADDR = 0x302F0000, + FSL_IMX7_GPT2_ADDR = 0x302E0000, + FSL_IMX7_GPT1_ADDR = 0x302D0000, + + FSL_IMX7_IOMUXC_LPSR_ADDR = 0x302C0000, + FSL_IMX7_IOMUXC_LPSR_SIZE = (4 * KiB), + + FSL_IMX7_WDOG4_ADDR = 0x302B0000, + FSL_IMX7_WDOG3_ADDR = 0x302A0000, + FSL_IMX7_WDOG2_ADDR = 0x30290000, + FSL_IMX7_WDOG1_ADDR = 0x30280000, + + FSL_IMX7_IOMUXC_LPSR_GPR_ADDR = 0x30270000, + + FSL_IMX7_GPIO7_ADDR = 0x30260000, + FSL_IMX7_GPIO6_ADDR = 0x30250000, + FSL_IMX7_GPIO5_ADDR = 0x30240000, + FSL_IMX7_GPIO4_ADDR = 0x30230000, + FSL_IMX7_GPIO3_ADDR = 0x30220000, + FSL_IMX7_GPIO2_ADDR = 0x30210000, + FSL_IMX7_GPIO1_ADDR = 0x30200000, + + FSL_IMX7_AIPS1_CONF_ADDR = 0x301F0000, + FSL_IMX7_AIPS1_CONF_SIZE = (64 * KiB), - FSL_IMX7_A7MPCORE_ADDR = 0x31000000, FSL_IMX7_A7MPCORE_DAP_ADDR = 0x30000000, + FSL_IMX7_A7MPCORE_DAP_SIZE = (1 * MiB), - FSL_IMX7_PCIE_REG_ADDR = 0x33800000, - FSL_IMX7_PCIE_REG_SIZE = 16 * 1024, + /* AIPS-1 End */ - FSL_IMX7_GPR_ADDR = 0x30340000, + FSL_IMX7_EIM_CS0_ADDR = 0x28000000, + FSL_IMX7_EIM_CS0_SIZE = (128 * MiB), - FSL_IMX7_DMA_APBH_ADDR = 0x33000000, - FSL_IMX7_DMA_APBH_SIZE = 0x2000, + FSL_IMX7_OCRAM_PXP_ADDR = 0x00940000, + FSL_IMX7_OCRAM_PXP_SIZE = (32 * KiB), + + FSL_IMX7_OCRAM_EPDC_ADDR = 0x00920000, + FSL_IMX7_OCRAM_EPDC_SIZE = (128 * KiB), + + FSL_IMX7_OCRAM_MEM_ADDR = 0x00900000, + FSL_IMX7_OCRAM_MEM_SIZE = (128 * KiB), + + FSL_IMX7_TCMU_ADDR = 0x00800000, + FSL_IMX7_TCMU_SIZE = (32 * KiB), + + FSL_IMX7_TCML_ADDR = 0x007F8000, + FSL_IMX7_TCML_SIZE = (32 * KiB), + + FSL_IMX7_OCRAM_S_ADDR = 0x00180000, + FSL_IMX7_OCRAM_S_SIZE = (32 * KiB), + + FSL_IMX7_CAAM_MEM_ADDR = 0x00100000, + FSL_IMX7_CAAM_MEM_SIZE = (32 * KiB), + + FSL_IMX7_ROM_ADDR = 0x00000000, + FSL_IMX7_ROM_SIZE = (96 * KiB), }; enum FslIMX7IRQs { diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) char name[NAME_SIZE]; int i; + /* + * CPUs + */ for (i = 0; i < MIN(ms->smp.cpus, FSL_IMX7_NUM_CPUS); i++) { snprintf(name, NAME_SIZE, "cpu%d", i); object_initialize_child(obj, name, &s->cpu[i], @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) TYPE_A15MPCORE_PRIV); /* - * GPIOs 1 to 7 + * GPIOs */ for (i = 0; i < FSL_IMX7_NUM_GPIOS; i++) { snprintf(name, NAME_SIZE, "gpio%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) } /* - * GPT1, 2, 3, 4 + * GPTs */ for (i = 0; i < FSL_IMX7_NUM_GPTS; i++) { snprintf(name, NAME_SIZE, "gpt%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) */ object_initialize_child(obj, "gpcv2", &s->gpcv2, TYPE_IMX_GPCV2); + /* + * ECSPIs + */ for (i = 0; i < FSL_IMX7_NUM_ECSPIS; i++) { snprintf(name, NAME_SIZE, "spi%d", i + 1); object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); } - + /* + * I2Cs + */ for (i = 0; i < FSL_IMX7_NUM_I2CS; i++) { snprintf(name, NAME_SIZE, "i2c%d", i + 1); object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C); } /* - * UART + * UARTs */ for (i = 0; i < FSL_IMX7_NUM_UARTS; i++) { snprintf(name, NAME_SIZE, "uart%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) } /* - * Ethernet + * Ethernets */ for (i = 0; i < FSL_IMX7_NUM_ETHS; i++) { snprintf(name, NAME_SIZE, "eth%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) } /* - * SDHCI + * SDHCIs */ for (i = 0; i < FSL_IMX7_NUM_USDHCS; i++) { snprintf(name, NAME_SIZE, "usdhc%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) object_initialize_child(obj, "snvs", &s->snvs, TYPE_IMX7_SNVS); /* - * Watchdog + * Watchdogs */ for (i = 0; i < FSL_IMX7_NUM_WDTS; i++) { snprintf(name, NAME_SIZE, "wdt%d", i); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) */ object_initialize_child(obj, "gpr", &s->gpr, TYPE_IMX7_GPR); + /* + * PCIE + */ object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); + /* + * USBs + */ for (i = 0; i < FSL_IMX7_NUM_USBS; i++) { snprintf(name, NAME_SIZE, "usb%d", i); object_initialize_child(obj, name, &s->usb[i], TYPE_CHIPIDEA); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) return; } + /* + * CPUs + */ for (i = 0; i < smp_cpus; i++) { o = OBJECT(&s->cpu[i]); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) * A7MPCORE DAP */ create_unimplemented_device("a7mpcore-dap", FSL_IMX7_A7MPCORE_DAP_ADDR, - 0x100000); + FSL_IMX7_A7MPCORE_DAP_SIZE); /* - * GPT1, 2, 3, 4 + * GPTs */ for (i = 0; i < FSL_IMX7_NUM_GPTS; i++) { static const hwaddr FSL_IMX7_GPTn_ADDR[FSL_IMX7_NUM_GPTS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_GPTn_IRQ[i])); } + /* + * GPIOs + */ for (i = 0; i < FSL_IMX7_NUM_GPIOS; i++) { static const hwaddr FSL_IMX7_GPIOn_ADDR[FSL_IMX7_NUM_GPIOS] = { FSL_IMX7_GPIO1_ADDR, @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) /* * IOMUXC and IOMUXC_LPSR */ - for (i = 0; i < FSL_IMX7_NUM_IOMUXCS; i++) { - static const hwaddr FSL_IMX7_IOMUXCn_ADDR[FSL_IMX7_NUM_IOMUXCS] = { - FSL_IMX7_IOMUXC_ADDR, - FSL_IMX7_IOMUXC_LPSR_ADDR, - }; - - snprintf(name, NAME_SIZE, "iomuxc%d", i); - create_unimplemented_device(name, FSL_IMX7_IOMUXCn_ADDR[i], - FSL_IMX7_IOMUXCn_SIZE); - } + create_unimplemented_device("iomuxc", FSL_IMX7_IOMUXC_ADDR, + FSL_IMX7_IOMUXC_SIZE); + create_unimplemented_device("iomuxc_lspr", FSL_IMX7_IOMUXC_LPSR_ADDR, + FSL_IMX7_IOMUXC_LPSR_SIZE); /* * CCM @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->gpcv2), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpcv2), 0, FSL_IMX7_GPC_ADDR); - /* Initialize all ECSPI */ + /* + * ECSPIs + */ for (i = 0; i < FSL_IMX7_NUM_ECSPIS; i++) { static const hwaddr FSL_IMX7_SPIn_ADDR[FSL_IMX7_NUM_ECSPIS] = { FSL_IMX7_ECSPI1_ADDR, @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_SPIn_IRQ[i])); } + /* + * I2Cs + */ for (i = 0; i < FSL_IMX7_NUM_I2CS; i++) { static const hwaddr FSL_IMX7_I2Cn_ADDR[FSL_IMX7_NUM_I2CS] = { FSL_IMX7_I2C1_ADDR, @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) } /* - * UART + * UARTs */ for (i = 0; i < FSL_IMX7_NUM_UARTS; i++) { static const hwaddr FSL_IMX7_UARTn_ADDR[FSL_IMX7_NUM_UARTS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) } /* - * Ethernet + * Ethernets * * We must use two loops since phy_connected affects the other interface * and we have to set all properties before calling sysbus_realize(). @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) } /* - * USDHC + * USDHCs */ for (i = 0; i < FSL_IMX7_NUM_USDHCS; i++) { static const hwaddr FSL_IMX7_USDHCn_ADDR[FSL_IMX7_NUM_USDHCS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) * SNVS */ sysbus_realize(SYS_BUS_DEVICE(&s->snvs), &error_abort); - sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, FSL_IMX7_SNVS_ADDR); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, FSL_IMX7_SNVS_HP_ADDR); /* * SRC @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("src", FSL_IMX7_SRC_ADDR, FSL_IMX7_SRC_SIZE); /* - * Watchdog + * Watchdogs */ for (i = 0; i < FSL_IMX7_NUM_WDTS; i++) { static const hwaddr FSL_IMX7_WDOGn_ADDR[FSL_IMX7_NUM_WDTS] = { @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("caam", FSL_IMX7_CAAM_ADDR, FSL_IMX7_CAAM_SIZE); /* - * PWM + * PWMs */ - create_unimplemented_device("pwm1", FSL_IMX7_PWM1_ADDR, FSL_IMX7_PWMn_SIZE); - create_unimplemented_device("pwm2", FSL_IMX7_PWM2_ADDR, FSL_IMX7_PWMn_SIZE); - create_unimplemented_device("pwm3", FSL_IMX7_PWM3_ADDR, FSL_IMX7_PWMn_SIZE); - create_unimplemented_device("pwm4", FSL_IMX7_PWM4_ADDR, FSL_IMX7_PWMn_SIZE); + for (i = 0; i < FSL_IMX7_NUM_PWMS; i++) { + static const hwaddr FSL_IMX7_PWMn_ADDR[FSL_IMX7_NUM_PWMS] = { + FSL_IMX7_PWM1_ADDR, + FSL_IMX7_PWM2_ADDR, + FSL_IMX7_PWM3_ADDR, + FSL_IMX7_PWM4_ADDR, + }; + + snprintf(name, NAME_SIZE, "pwm%d", i); + create_unimplemented_device(name, FSL_IMX7_PWMn_ADDR[i], + FSL_IMX7_PWMn_SIZE); + } /* - * CAN + * CANs */ - create_unimplemented_device("can1", FSL_IMX7_CAN1_ADDR, FSL_IMX7_CANn_SIZE); - create_unimplemented_device("can2", FSL_IMX7_CAN2_ADDR, FSL_IMX7_CANn_SIZE); + for (i = 0; i < FSL_IMX7_NUM_CANS; i++) { + static const hwaddr FSL_IMX7_CANn_ADDR[FSL_IMX7_NUM_CANS] = { + FSL_IMX7_CAN1_ADDR, + FSL_IMX7_CAN2_ADDR, + }; + + snprintf(name, NAME_SIZE, "can%d", i); + create_unimplemented_device(name, FSL_IMX7_CANn_ADDR[i], + FSL_IMX7_CANn_SIZE); + } /* - * SAI (Audio SSI (Synchronous Serial Interface)) + * SAIs (Audio SSI (Synchronous Serial Interface)) */ - create_unimplemented_device("sai1", FSL_IMX7_SAI1_ADDR, FSL_IMX7_SAIn_SIZE); - create_unimplemented_device("sai2", FSL_IMX7_SAI2_ADDR, FSL_IMX7_SAIn_SIZE); - create_unimplemented_device("sai2", FSL_IMX7_SAI3_ADDR, FSL_IMX7_SAIn_SIZE); + for (i = 0; i < FSL_IMX7_NUM_SAIS; i++) { + static const hwaddr FSL_IMX7_SAIn_ADDR[FSL_IMX7_NUM_SAIS] = { + FSL_IMX7_SAI1_ADDR, + FSL_IMX7_SAI2_ADDR, + FSL_IMX7_SAI3_ADDR, + }; + + snprintf(name, NAME_SIZE, "sai%d", i); + create_unimplemented_device(name, FSL_IMX7_SAIn_ADDR[i], + FSL_IMX7_SAIn_SIZE); + } /* * OCOTP @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("ocotp", FSL_IMX7_OCOTP_ADDR, FSL_IMX7_OCOTP_SIZE); + /* + * GPR + */ sysbus_realize(SYS_BUS_DEVICE(&s->gpr), &error_abort); - sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpr), 0, FSL_IMX7_GPR_ADDR); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpr), 0, FSL_IMX7_IOMUXC_GPR_ADDR); + /* + * PCIE + */ sysbus_realize(SYS_BUS_DEVICE(&s->pcie), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0, FSL_IMX7_PCIE_REG_ADDR); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTD_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3, irq); - + /* + * USBs + */ for (i = 0; i < FSL_IMX7_NUM_USBS; i++) { static const hwaddr FSL_IMX7_USBMISCn_ADDR[FSL_IMX7_NUM_USBS] = { FSL_IMX7_USBMISC1_ADDR, @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) */ create_unimplemented_device("pcie-phy", FSL_IMX7_PCIE_PHY_ADDR, FSL_IMX7_PCIE_PHY_SIZE); + } static Property fsl_imx7_properties[] = { -- 2.34.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> * Add TZASC as unimplemented device. - Allow bare metal application to access this (unimplemented) device * Add CSU as unimplemented device. - Allow bare metal application to access this (unimplemented) device * Add various memory segments - OCRAM - OCRAM EPDC - OCRAM PXP - OCRAM S - ROM - CAAM Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: f887a3483996ba06d40bd62ffdfb0ecf68621987.1692964892.git.jcd@tribudubois.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 7 +++++ hw/arm/fsl-imx7.c | 63 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ struct FslIMX7State { IMX7GPRState gpr; ChipideaState usb[FSL_IMX7_NUM_USBS]; DesignwarePCIEHost pcie; + MemoryRegion rom; + MemoryRegion caam; + MemoryRegion ocram; + MemoryRegion ocram_epdc; + MemoryRegion ocram_pxp; + MemoryRegion ocram_s; + uint32_t phy_num[FSL_IMX7_NUM_ETHS]; bool phy_connected[FSL_IMX7_NUM_ETHS]; }; diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("pcie-phy", FSL_IMX7_PCIE_PHY_ADDR, FSL_IMX7_PCIE_PHY_SIZE); + /* + * CSU + */ + create_unimplemented_device("csu", FSL_IMX7_CSU_ADDR, + FSL_IMX7_CSU_SIZE); + + /* + * TZASC + */ + create_unimplemented_device("tzasc", FSL_IMX7_TZASC_ADDR, + FSL_IMX7_TZASC_SIZE); + + /* + * OCRAM memory + */ + memory_region_init_ram(&s->ocram, NULL, "imx7.ocram", + FSL_IMX7_OCRAM_MEM_SIZE, + &error_abort); + memory_region_add_subregion(get_system_memory(), FSL_IMX7_OCRAM_MEM_ADDR, + &s->ocram); + + /* + * OCRAM EPDC memory + */ + memory_region_init_ram(&s->ocram_epdc, NULL, "imx7.ocram_epdc", + FSL_IMX7_OCRAM_EPDC_SIZE, + &error_abort); + memory_region_add_subregion(get_system_memory(), FSL_IMX7_OCRAM_EPDC_ADDR, + &s->ocram_epdc); + + /* + * OCRAM PXP memory + */ + memory_region_init_ram(&s->ocram_pxp, NULL, "imx7.ocram_pxp", + FSL_IMX7_OCRAM_PXP_SIZE, + &error_abort); + memory_region_add_subregion(get_system_memory(), FSL_IMX7_OCRAM_PXP_ADDR, + &s->ocram_pxp); + + /* + * OCRAM_S memory + */ + memory_region_init_ram(&s->ocram_s, NULL, "imx7.ocram_s", + FSL_IMX7_OCRAM_S_SIZE, + &error_abort); + memory_region_add_subregion(get_system_memory(), FSL_IMX7_OCRAM_S_ADDR, + &s->ocram_s); + + /* + * ROM memory + */ + memory_region_init_rom(&s->rom, OBJECT(dev), "imx7.rom", + FSL_IMX7_ROM_SIZE, &error_abort); + memory_region_add_subregion(get_system_memory(), FSL_IMX7_ROM_ADDR, + &s->rom); + + /* + * CAAM memory + */ + memory_region_init_rom(&s->caam, OBJECT(dev), "imx7.caam", + FSL_IMX7_CAAM_MEM_SIZE, &error_abort); + memory_region_add_subregion(get_system_memory(), FSL_IMX7_CAAM_MEM_ADDR, + &s->caam); } static Property fsl_imx7_properties[] = { -- 2.34.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> The SRC device is normally used to start the secondary CPU. When running Linux directly, QEMU is emulating a PSCI interface that UBOOT is installing at boot time and therefore the fact that the SRC device is unimplemented is hidden as Qemu respond directly to PSCI requets without using the SRC device. But if you try to run a more bare metal application (maybe uboot itself), then it is not possible to start the secondary CPU as the SRC is an unimplemented device. This patch adds the ability to start the secondary CPU through the SRC device so that you can use this feature in bare metal applications. Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: ce9a0162defd2acee5dc7f8a674743de0cded569.1692964892.git.jcd@tribudubois.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 3 +- include/hw/misc/imx7_src.h | 66 +++++++++ hw/arm/fsl-imx7.c | 8 +- hw/misc/imx7_src.c | 276 +++++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + hw/misc/trace-events | 4 + 6 files changed, 356 insertions(+), 2 deletions(-) create mode 100644 include/hw/misc/imx7_src.h create mode 100644 hw/misc/imx7_src.c diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_ccm.h" #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx7_gpr.h" +#include "hw/misc/imx7_src.h" #include "hw/watchdog/wdt_imx2.h" #include "hw/gpio/imx_gpio.h" #include "hw/char/imx_serial.h" @@ -XXX,XX +XXX,XX @@ struct FslIMX7State { IMX7CCMState ccm; IMX7AnalogState analog; IMX7SNVSState snvs; + IMX7SRCState src; IMXGPCv2State gpcv2; IMXSPIState spi[FSL_IMX7_NUM_ECSPIS]; IMXI2CState i2c[FSL_IMX7_NUM_I2CS]; @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_GPC_ADDR = 0x303A0000, FSL_IMX7_SRC_ADDR = 0x30390000, - FSL_IMX7_SRC_SIZE = (4 * KiB), FSL_IMX7_CCM_ADDR = 0x30380000, diff --git a/include/hw/misc/imx7_src.h b/include/hw/misc/imx7_src.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/imx7_src.h @@ -XXX,XX +XXX,XX @@ +/* + * IMX7 System Reset Controller + * + * Copyright (C) 2023 Jean-Christophe Dubois <jcd@tribudubois.net> + * + * 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 IMX7_SRC_H +#define IMX7_SRC_H + +#include "hw/sysbus.h" +#include "qemu/bitops.h" +#include "qom/object.h" + +#define SRC_SCR 0 +#define SRC_A7RCR0 1 +#define SRC_A7RCR1 2 +#define SRC_M4RCR 3 +#define SRC_ERCR 5 +#define SRC_HSICPHY_RCR 7 +#define SRC_USBOPHY1_RCR 8 +#define SRC_USBOPHY2_RCR 9 +#define SRC_MPIPHY_RCR 10 +#define SRC_PCIEPHY_RCR 11 +#define SRC_SBMR1 22 +#define SRC_SRSR 23 +#define SRC_SISR 26 +#define SRC_SIMR 27 +#define SRC_SBMR2 28 +#define SRC_GPR1 29 +#define SRC_GPR2 30 +#define SRC_GPR3 31 +#define SRC_GPR4 32 +#define SRC_GPR5 33 +#define SRC_GPR6 34 +#define SRC_GPR7 35 +#define SRC_GPR8 36 +#define SRC_GPR9 37 +#define SRC_GPR10 38 +#define SRC_MAX 39 + +/* SRC_A7SCR1 */ +#define R_CORE1_ENABLE_SHIFT 1 +#define R_CORE1_ENABLE_LENGTH 1 +/* SRC_A7SCR0 */ +#define R_CORE1_RST_SHIFT 5 +#define R_CORE1_RST_LENGTH 1 +#define R_CORE0_RST_SHIFT 4 +#define R_CORE0_RST_LENGTH 1 + +#define TYPE_IMX7_SRC "imx7.src" +OBJECT_DECLARE_SIMPLE_TYPE(IMX7SRCState, IMX7_SRC) + +struct IMX7SRCState { + /* <private> */ + SysBusDevice parent_obj; + + /* <public> */ + MemoryRegion iomem; + + uint32_t regs[SRC_MAX]; +}; + +#endif /* IMX7_SRC_H */ diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) */ object_initialize_child(obj, "gpcv2", &s->gpcv2, TYPE_IMX_GPCV2); + /* + * SRC + */ + object_initialize_child(obj, "src", &s->src, TYPE_IMX7_SRC); + /* * ECSPIs */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) /* * SRC */ - create_unimplemented_device("src", FSL_IMX7_SRC_ADDR, FSL_IMX7_SRC_SIZE); + sysbus_realize(SYS_BUS_DEVICE(&s->src), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->src), 0, FSL_IMX7_SRC_ADDR); /* * Watchdogs diff --git a/hw/misc/imx7_src.c b/hw/misc/imx7_src.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/imx7_src.c @@ -XXX,XX +XXX,XX @@ +/* + * IMX7 System Reset Controller + * + * Copyright (c) 2023 Jean-Christophe Dubois <jcd@tribudubois.net> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "hw/misc/imx7_src.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/main-loop.h" +#include "qemu/module.h" +#include "target/arm/arm-powerctl.h" +#include "hw/core/cpu.h" +#include "hw/registerfields.h" + +#include "trace.h" + +static const char *imx7_src_reg_name(uint32_t reg) +{ + static char unknown[20]; + + switch (reg) { + case SRC_SCR: + return "SRC_SCR"; + case SRC_A7RCR0: + return "SRC_A7RCR0"; + case SRC_A7RCR1: + return "SRC_A7RCR1"; + case SRC_M4RCR: + return "SRC_M4RCR"; + case SRC_ERCR: + return "SRC_ERCR"; + case SRC_HSICPHY_RCR: + return "SRC_HSICPHY_RCR"; + case SRC_USBOPHY1_RCR: + return "SRC_USBOPHY1_RCR"; + case SRC_USBOPHY2_RCR: + return "SRC_USBOPHY2_RCR"; + case SRC_PCIEPHY_RCR: + return "SRC_PCIEPHY_RCR"; + case SRC_SBMR1: + return "SRC_SBMR1"; + case SRC_SRSR: + return "SRC_SRSR"; + case SRC_SISR: + return "SRC_SISR"; + case SRC_SIMR: + return "SRC_SIMR"; + case SRC_SBMR2: + return "SRC_SBMR2"; + case SRC_GPR1: + return "SRC_GPR1"; + case SRC_GPR2: + return "SRC_GPR2"; + case SRC_GPR3: + return "SRC_GPR3"; + case SRC_GPR4: + return "SRC_GPR4"; + case SRC_GPR5: + return "SRC_GPR5"; + case SRC_GPR6: + return "SRC_GPR6"; + case SRC_GPR7: + return "SRC_GPR7"; + case SRC_GPR8: + return "SRC_GPR8"; + case SRC_GPR9: + return "SRC_GPR9"; + case SRC_GPR10: + return "SRC_GPR10"; + default: + sprintf(unknown, "%u ?", reg); + return unknown; + } +} + +static const VMStateDescription vmstate_imx7_src = { + .name = TYPE_IMX7_SRC, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, IMX7SRCState, SRC_MAX), + VMSTATE_END_OF_LIST() + }, +}; + +static void imx7_src_reset(DeviceState *dev) +{ + IMX7SRCState *s = IMX7_SRC(dev); + + memset(s->regs, 0, sizeof(s->regs)); + + /* Set reset values */ + s->regs[SRC_SCR] = 0xA0; + s->regs[SRC_SRSR] = 0x1; + s->regs[SRC_SIMR] = 0x1F; +} + +static uint64_t imx7_src_read(void *opaque, hwaddr offset, unsigned size) +{ + uint32_t value = 0; + IMX7SRCState *s = (IMX7SRCState *)opaque; + uint32_t index = offset >> 2; + + if (index < SRC_MAX) { + value = s->regs[index]; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%" + HWADDR_PRIx "\n", TYPE_IMX7_SRC, __func__, offset); + } + + trace_imx7_src_read(imx7_src_reg_name(index), value); + + return value; +} + + +/* + * The reset is asynchronous so we need to defer clearing the reset + * bit until the work is completed. + */ + +struct SRCSCRResetInfo { + IMX7SRCState *s; + uint32_t reset_bit; +}; + +static void imx7_clear_reset_bit(CPUState *cpu, run_on_cpu_data data) +{ + struct SRCSCRResetInfo *ri = data.host_ptr; + IMX7SRCState *s = ri->s; + + assert(qemu_mutex_iothread_locked()); + + s->regs[SRC_A7RCR0] = deposit32(s->regs[SRC_A7RCR0], ri->reset_bit, 1, 0); + + trace_imx7_src_write(imx7_src_reg_name(SRC_A7RCR0), s->regs[SRC_A7RCR0]); + + g_free(ri); +} + +static void imx7_defer_clear_reset_bit(uint32_t cpuid, + IMX7SRCState *s, + uint32_t reset_shift) +{ + struct SRCSCRResetInfo *ri; + CPUState *cpu = arm_get_cpu_by_id(cpuid); + + if (!cpu) { + return; + } + + ri = g_new(struct SRCSCRResetInfo, 1); + ri->s = s; + ri->reset_bit = reset_shift; + + async_run_on_cpu(cpu, imx7_clear_reset_bit, RUN_ON_CPU_HOST_PTR(ri)); +} + + +static void imx7_src_write(void *opaque, hwaddr offset, uint64_t value, + unsigned size) +{ + IMX7SRCState *s = (IMX7SRCState *)opaque; + uint32_t index = offset >> 2; + long unsigned int change_mask; + uint32_t current_value = value; + + if (index >= SRC_MAX) { + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad register at offset 0x%" + HWADDR_PRIx "\n", TYPE_IMX7_SRC, __func__, offset); + return; + } + + trace_imx7_src_write(imx7_src_reg_name(SRC_A7RCR0), s->regs[SRC_A7RCR0]); + + change_mask = s->regs[index] ^ (uint32_t)current_value; + + switch (index) { + case SRC_A7RCR0: + if (FIELD_EX32(change_mask, CORE0, RST)) { + arm_reset_cpu(0); + imx7_defer_clear_reset_bit(0, s, R_CORE0_RST_SHIFT); + } + if (FIELD_EX32(change_mask, CORE1, RST)) { + arm_reset_cpu(1); + imx7_defer_clear_reset_bit(1, s, R_CORE1_RST_SHIFT); + } + s->regs[index] = current_value; + break; + case SRC_A7RCR1: + /* + * On real hardware when the system reset controller starts a + * secondary CPU it runs through some boot ROM code which reads + * the SRC_GPRX registers controlling the start address and branches + * to it. + * Here we are taking a short cut and branching directly to the + * requested address (we don't want to run the boot ROM code inside + * QEMU) + */ + if (FIELD_EX32(change_mask, CORE1, ENABLE)) { + if (FIELD_EX32(current_value, CORE1, ENABLE)) { + /* CORE 1 is brought up */ + arm_set_cpu_on(1, s->regs[SRC_GPR3], s->regs[SRC_GPR4], + 3, false); + } else { + /* CORE 1 is shut down */ + arm_set_cpu_off(1); + } + /* We clear the reset bits as the processor changed state */ + imx7_defer_clear_reset_bit(1, s, R_CORE1_RST_SHIFT); + clear_bit(R_CORE1_RST_SHIFT, &change_mask); + } + s->regs[index] = current_value; + break; + default: + s->regs[index] = current_value; + break; + } +} + +static const struct MemoryRegionOps imx7_src_ops = { + .read = imx7_src_read, + .write = imx7_src_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + /* + * Our device would not work correctly if the guest was doing + * unaligned access. This might not be a limitation on the real + * device but in practice there is no reason for a guest to access + * this device unaligned. + */ + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx7_src_realize(DeviceState *dev, Error **errp) +{ + IMX7SRCState *s = IMX7_SRC(dev); + + memory_region_init_io(&s->iomem, OBJECT(dev), &imx7_src_ops, s, + TYPE_IMX7_SRC, 0x1000); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); +} + +static void imx7_src_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = imx7_src_realize; + dc->reset = imx7_src_reset; + dc->vmsd = &vmstate_imx7_src; + dc->desc = "i.MX6 System Reset Controller"; +} + +static const TypeInfo imx7_src_info = { + .name = TYPE_IMX7_SRC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX7SRCState), + .class_init = imx7_src_class_init, +}; + +static void imx7_src_register_types(void) +{ + type_register_static(&imx7_src_info); +} + +type_init(imx7_src_register_types) diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_IMX', if_true: files( 'imx6_src.c', 'imx6ul_ccm.c', 'imx7_ccm.c', + 'imx7_src.c', 'imx7_gpr.c', 'imx7_snvs.c', 'imx_ccm.c', diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ ccm_clock_freq(uint32_t clock, uint32_t freq) "(Clock = %d) = %d" ccm_read_reg(const char *reg_name, uint32_t value) "reg[%s] <= 0x%" PRIx32 ccm_write_reg(const char *reg_name, uint32_t value) "reg[%s] => 0x%" PRIx32 +# imx7_src.c +imx7_src_read(const char *reg_name, uint32_t value) "reg[%s] => 0x%" PRIx32 +imx7_src_write(const char *reg_name, uint32_t value) "reg[%s] <= 0x%" PRIx32 + # iotkit-sysinfo.c iotkit_sysinfo_read(uint64_t offset, uint64_t data, unsigned size) "IoTKit SysInfo read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" iotkit_sysinfo_write(uint64_t offset, uint64_t data, unsigned size) "IoTKit SysInfo write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" -- 2.34.1 The architecture requires (R_TYTWB) that an attempt to return from EL3 when SCR_EL3.{NSE,NS} are {1,0} is an illegal exception return. (This enforces that the CPU can't ever be executing below EL3 with the NSE,NS bits indicating an invalid security state.) We were missing this check; add it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230807150618.101357-1-peter.maydell@linaro.org --- target/arm/tcg/helper-a64.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) spsr &= ~PSTATE_SS; } + /* + * FEAT_RME forbids return from EL3 with an invalid security state. + * We don't need an explicit check for FEAT_RME here because we enforce + * in scr_write() that you can't set the NSE bit without it. + */ + if (cur_el == 3 && (env->cp15.scr_el3 & (SCR_NS | SCR_NSE)) == SCR_NSE) { + goto illegal_return; + } + new_el = el_from_spsr(spsr); if (new_el == -1) { goto illegal_return; -- 2.34.1 In the m48t59 device we almost always use 64-bit arithmetic when dealing with time_t deltas. The one exception is in set_alarm(), which currently uses a plain 'int' to hold the difference between two time_t values. Switch to int64_t instead to avoid any possible overflow issues. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- hw/rtc/m48t59.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/rtc/m48t59.c b/hw/rtc/m48t59.c index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/m48t59.c +++ b/hw/rtc/m48t59.c @@ -XXX,XX +XXX,XX @@ static void alarm_cb (void *opaque) static void set_alarm(M48t59State *NVRAM) { - int diff; + int64_t diff; if (NVRAM->alrm_timer != NULL) { timer_del(NVRAM->alrm_timer); diff = qemu_timedate_diff(&NVRAM->alarm) - NVRAM->time_offset; -- 2.34.1 In the twl92230 device, use int64_t for the two state fields sec_offset and alm_sec, because we set these to values that are either time_t or differences between two time_t values. These fields aren't saved in vmstate anywhere, so we can safely widen them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- hw/rtc/twl92230.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/rtc/twl92230.c b/hw/rtc/twl92230.c index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/twl92230.c +++ b/hw/rtc/twl92230.c @@ -XXX,XX +XXX,XX @@ struct MenelausState { struct tm tm; struct tm new; struct tm alm; - int sec_offset; - int alm_sec; + int64_t sec_offset; + int64_t alm_sec; int next_comp; } rtc; uint16_t rtc_next_vmstate; -- 2.34.1 In the aspeed_rtc device we store a difference between two time_t values in an 'int'. This is not really correct when time_t could be 64 bits. Enlarge the field to 'int64_t'. This is a migration compatibility break for the aspeed boards. While we are changing the vmstate, remove the accidental duplicate of the offset field. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Cédric Le Goater <clg@kaod.org> --- include/hw/rtc/aspeed_rtc.h | 2 +- hw/rtc/aspeed_rtc.c | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/include/hw/rtc/aspeed_rtc.h b/include/hw/rtc/aspeed_rtc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/rtc/aspeed_rtc.h +++ b/include/hw/rtc/aspeed_rtc.h @@ -XXX,XX +XXX,XX @@ struct AspeedRtcState { qemu_irq irq; uint32_t reg[0x18]; - int offset; + int64_t offset; }; diff --git a/hw/rtc/aspeed_rtc.c b/hw/rtc/aspeed_rtc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/aspeed_rtc.c +++ b/hw/rtc/aspeed_rtc.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps aspeed_rtc_ops = { static const VMStateDescription vmstate_aspeed_rtc = { .name = TYPE_ASPEED_RTC, - .version_id = 1, + .version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(reg, AspeedRtcState, 0x18), - VMSTATE_INT32(offset, AspeedRtcState), - VMSTATE_INT32(offset, AspeedRtcState), + VMSTATE_INT64(offset, AspeedRtcState), VMSTATE_END_OF_LIST() } }; -- 2.34.1 The functions qemu_get_timedate() and qemu_timedate_diff() take and return a time offset as an integer. Coverity points out that means that when an RTC device implementation holds an offset as a time_t, as the m48t59 does, the time_t will get truncated. (CID 1507157, 1517772). The functions work with time_t internally, so make them use that type in their APIs. Note that this won't help any Y2038 issues where either the device model itself is keeping the offset in a 32-bit integer, or where the hardware under emulation has Y2038 or other rollover problems. If we missed any cases of the former then hopefully Coverity will warn us about them since after this patch we'd be truncating a time_t in assignments from qemu_timedate_diff().) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- include/sysemu/rtc.h | 4 ++-- softmmu/rtc.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/sysemu/rtc.h b/include/sysemu/rtc.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/rtc.h +++ b/include/sysemu/rtc.h @@ -XXX,XX +XXX,XX @@ * The behaviour of the clock whose value this function returns will * depend on the -rtc command line option passed by the user. */ -void qemu_get_timedate(struct tm *tm, int offset); +void qemu_get_timedate(struct tm *tm, time_t offset); /** * qemu_timedate_diff: Return difference between a struct tm and the RTC @@ -XXX,XX +XXX,XX @@ void qemu_get_timedate(struct tm *tm, int offset); * a timestamp one hour further ahead than the current RTC time * then this function will return 3600. */ -int qemu_timedate_diff(struct tm *tm); +time_t qemu_timedate_diff(struct tm *tm); #endif diff --git a/softmmu/rtc.c b/softmmu/rtc.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/rtc.c +++ b/softmmu/rtc.c @@ -XXX,XX +XXX,XX @@ static time_t qemu_ref_timedate(QEMUClockType clock) return value; } -void qemu_get_timedate(struct tm *tm, int offset) +void qemu_get_timedate(struct tm *tm, time_t offset) { time_t ti = qemu_ref_timedate(rtc_clock); @@ -XXX,XX +XXX,XX @@ void qemu_get_timedate(struct tm *tm, int offset) } } -int qemu_timedate_diff(struct tm *tm) +time_t qemu_timedate_diff(struct tm *tm) { time_t seconds; -- 2.34.1 Where architecturally one ARM_FEATURE_X flag implies another ARM_FEATURE_Y, we allow the CPU init function to only set X, and then set Y for it. Currently we do this in two places -- we set a few flags in arm_cpu_post_init() because we need them to decide which properties to create on the CPU object, and then we do the rest in arm_cpu_realizefn(). However, this is fragile, because it's easy to add a new property and not notice that this means that an X-implies-Y check now has to move from realize to post-init. As a specific example, the pmsav7-dregion property is conditional on ARM_FEATURE_PMSA && ARM_FEATURE_V7, which means it won't appear on the Cortex-M33 and -M55, because they set ARM_FEATURE_V8 and rely on V8-implies-V7, which doesn't happen until the realizefn. Move all of these X-implies-Y checks into a new function, which we call at the top of arm_cpu_post_init(), so the feature bits are available at that point. This does now give us the reverse issue, that if there's a feature bit which is enabled or disabled by the setting of a property then then X-implies-Y features that are dependent on that property need to be in realize, not in this new function. But the only one of those is the "EL3 implies VBAR" which is already in the right place, so putting things this way round seems better to me. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230724174335.2150499-2-peter.maydell@linaro.org --- target/arm/cpu.c | 179 +++++++++++++++++++++++++---------------------- 1 file changed, 97 insertions(+), 82 deletions(-) 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 @@ unsigned int gt_cntfrq_period_ns(ARMCPU *cpu) NANOSECONDS_PER_SECOND / cpu->gt_cntfrq_hz : 1; } +static void arm_cpu_propagate_feature_implications(ARMCPU *cpu) +{ + CPUARMState *env = &cpu->env; + bool no_aa32 = false; + + /* + * Some features automatically imply others: set the feature + * bits explicitly for these cases. + */ + + if (arm_feature(env, ARM_FEATURE_M)) { + set_feature(env, ARM_FEATURE_PMSA); + } + + if (arm_feature(env, ARM_FEATURE_V8)) { + if (arm_feature(env, ARM_FEATURE_M)) { + set_feature(env, ARM_FEATURE_V7); + } else { + set_feature(env, ARM_FEATURE_V7VE); + } + } + + /* + * There exist AArch64 cpus without AArch32 support. When KVM + * queries ID_ISAR0_EL1 on such a host, the value is UNKNOWN. + * Similarly, we cannot check ID_AA64PFR0 without AArch64 support. + * As a general principle, we also do not make ID register + * consistency checks anywhere unless using TCG, because only + * for TCG would a consistency-check failure be a QEMU bug. + */ + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + no_aa32 = !cpu_isar_feature(aa64_aa32, cpu); + } + + if (arm_feature(env, ARM_FEATURE_V7VE)) { + /* + * v7 Virtualization Extensions. In real hardware this implies + * EL2 and also the presence of the Security Extensions. + * For QEMU, for backwards-compatibility we implement some + * CPUs or CPU configs which have no actual EL2 or EL3 but do + * include the various other features that V7VE implies. + * Presence of EL2 itself is ARM_FEATURE_EL2, and of the + * Security Extensions is ARM_FEATURE_EL3. + */ + assert(!tcg_enabled() || no_aa32 || + cpu_isar_feature(aa32_arm_div, cpu)); + set_feature(env, ARM_FEATURE_LPAE); + set_feature(env, ARM_FEATURE_V7); + } + if (arm_feature(env, ARM_FEATURE_V7)) { + set_feature(env, ARM_FEATURE_VAPA); + set_feature(env, ARM_FEATURE_THUMB2); + set_feature(env, ARM_FEATURE_MPIDR); + if (!arm_feature(env, ARM_FEATURE_M)) { + set_feature(env, ARM_FEATURE_V6K); + } else { + set_feature(env, ARM_FEATURE_V6); + } + + /* + * Always define VBAR for V7 CPUs even if it doesn't exist in + * non-EL3 configs. This is needed by some legacy boards. + */ + set_feature(env, ARM_FEATURE_VBAR); + } + if (arm_feature(env, ARM_FEATURE_V6K)) { + set_feature(env, ARM_FEATURE_V6); + set_feature(env, ARM_FEATURE_MVFR); + } + if (arm_feature(env, ARM_FEATURE_V6)) { + set_feature(env, ARM_FEATURE_V5); + if (!arm_feature(env, ARM_FEATURE_M)) { + assert(!tcg_enabled() || no_aa32 || + cpu_isar_feature(aa32_jazelle, cpu)); + set_feature(env, ARM_FEATURE_AUXCR); + } + } + if (arm_feature(env, ARM_FEATURE_V5)) { + set_feature(env, ARM_FEATURE_V4T); + } + if (arm_feature(env, ARM_FEATURE_LPAE)) { + set_feature(env, ARM_FEATURE_V7MP); + } + if (arm_feature(env, ARM_FEATURE_CBAR_RO)) { + set_feature(env, ARM_FEATURE_CBAR); + } + if (arm_feature(env, ARM_FEATURE_THUMB2) && + !arm_feature(env, ARM_FEATURE_M)) { + set_feature(env, ARM_FEATURE_THUMB_DSP); + } +} + void arm_cpu_post_init(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - /* M profile implies PMSA. We have to do this here rather than - * in realize with the other feature-implication checks because - * we look at the PMSA bit to see if we should add some properties. + /* + * Some features imply others. Figure this out now, because we + * are going to look at the feature bits in deciding which + * properties to add. */ - if (arm_feature(&cpu->env, ARM_FEATURE_M)) { - set_feature(&cpu->env, ARM_FEATURE_PMSA); - } + arm_cpu_propagate_feature_implications(cpu); if (arm_feature(&cpu->env, ARM_FEATURE_CBAR) || arm_feature(&cpu->env, ARM_FEATURE_CBAR_RO)) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) CPUARMState *env = &cpu->env; int pagebits; Error *local_err = NULL; - bool no_aa32 = false; /* Use pc-relative instructions in system-mode */ #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) cpu->isar.id_isar3 = u; } - /* Some features automatically imply others: */ - if (arm_feature(env, ARM_FEATURE_V8)) { - if (arm_feature(env, ARM_FEATURE_M)) { - set_feature(env, ARM_FEATURE_V7); - } else { - set_feature(env, ARM_FEATURE_V7VE); - } - } - - /* - * There exist AArch64 cpus without AArch32 support. When KVM - * queries ID_ISAR0_EL1 on such a host, the value is UNKNOWN. - * Similarly, we cannot check ID_AA64PFR0 without AArch64 support. - * As a general principle, we also do not make ID register - * consistency checks anywhere unless using TCG, because only - * for TCG would a consistency-check failure be a QEMU bug. - */ - if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { - no_aa32 = !cpu_isar_feature(aa64_aa32, cpu); - } - - if (arm_feature(env, ARM_FEATURE_V7VE)) { - /* v7 Virtualization Extensions. In real hardware this implies - * EL2 and also the presence of the Security Extensions. - * For QEMU, for backwards-compatibility we implement some - * CPUs or CPU configs which have no actual EL2 or EL3 but do - * include the various other features that V7VE implies. - * Presence of EL2 itself is ARM_FEATURE_EL2, and of the - * Security Extensions is ARM_FEATURE_EL3. - */ - assert(!tcg_enabled() || no_aa32 || - cpu_isar_feature(aa32_arm_div, cpu)); - set_feature(env, ARM_FEATURE_LPAE); - set_feature(env, ARM_FEATURE_V7); - } - if (arm_feature(env, ARM_FEATURE_V7)) { - set_feature(env, ARM_FEATURE_VAPA); - set_feature(env, ARM_FEATURE_THUMB2); - set_feature(env, ARM_FEATURE_MPIDR); - if (!arm_feature(env, ARM_FEATURE_M)) { - set_feature(env, ARM_FEATURE_V6K); - } else { - set_feature(env, ARM_FEATURE_V6); - } - - /* Always define VBAR for V7 CPUs even if it doesn't exist in - * non-EL3 configs. This is needed by some legacy boards. - */ - set_feature(env, ARM_FEATURE_VBAR); - } - if (arm_feature(env, ARM_FEATURE_V6K)) { - set_feature(env, ARM_FEATURE_V6); - set_feature(env, ARM_FEATURE_MVFR); - } - if (arm_feature(env, ARM_FEATURE_V6)) { - set_feature(env, ARM_FEATURE_V5); - if (!arm_feature(env, ARM_FEATURE_M)) { - assert(!tcg_enabled() || no_aa32 || - cpu_isar_feature(aa32_jazelle, cpu)); - set_feature(env, ARM_FEATURE_AUXCR); - } - } - if (arm_feature(env, ARM_FEATURE_V5)) { - set_feature(env, ARM_FEATURE_V4T); - } - if (arm_feature(env, ARM_FEATURE_LPAE)) { - set_feature(env, ARM_FEATURE_V7MP); - } - if (arm_feature(env, ARM_FEATURE_CBAR_RO)) { - set_feature(env, ARM_FEATURE_CBAR); - } - if (arm_feature(env, ARM_FEATURE_THUMB2) && - !arm_feature(env, ARM_FEATURE_M)) { - set_feature(env, ARM_FEATURE_THUMB_DSP); - } /* * We rely on no XScale CPU having VFP so we can use the same bits in the -- 2.34.1 M-profile CPUs generally allow configuration of the number of MPU regions that they have. We don't currently model this, so our implementations of some of the board models provide CPUs with the wrong number of regions. RTOSes like Zephyr that hardcode the expected number of regions may therefore not run on the model if they are set up to run on real hardware. Add properties mpu-ns-regions and mpu-s-regions to the ARMV7M object, matching the ability of hardware to configure the number of Secure and NonSecure regions separately. Our actual CPU implementation doesn't currently support that, and it happens that none of the MPS boards we model set the number of regions differently for Secure vs NonSecure, so we provide an interface to the boards and SoCs that won't need to change if we ever do add that functionality in future, but make it an error to configure the two properties to different values. (The property name on the CPU is the somewhat misnamed-for-M-profile "pmsav7-dregion", so we don't follow that naming convention for the properties here. The TRM doesn't say what the CPU configuration variable names are, so we pick something, and follow the lowercase convention we already have for properties here.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230724174335.2150499-3-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 8 ++++++++ hw/arm/armv7m.c | 21 +++++++++++++++++++++ 2 files changed, 29 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) * + Property "vfp": enable VFP (forwarded to CPU object) * + Property "dsp": enable DSP (forwarded to CPU object) * + Property "enable-bitband": expose bitbanded IO + * + Property "mpu-ns-regions": number of Non-Secure MPU regions (forwarded + * to CPU object pmsav7-dregion property; default is whatever the default + * for the CPU is) + * + Property "mpu-s-regions": number of Secure MPU regions (default is + * whatever the default for the CPU is; must currently be set to the same + * value as mpu-ns-regions if the CPU implements the Security Extension) * + Clock input "refclk" is the external reference clock for the systick timers * + Clock input "cpuclk" is the main CPU clock */ @@ -XXX,XX +XXX,XX @@ struct ARMv7MState { Object *idau; uint32_t init_svtor; uint32_t init_nsvtor; + uint32_t mpu_ns_regions; + uint32_t mpu_s_regions; bool enable_bitband; bool start_powered_off; bool vfp; 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) } } + /* + * Real M-profile hardware can be configured with a different number of + * MPU regions for Secure vs NonSecure. QEMU's CPU implementation doesn't + * support that yet, so catch attempts to select that. + */ + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY) && + s->mpu_ns_regions != s->mpu_s_regions) { + error_setg(errp, + "mpu-ns-regions and mpu-s-regions properties must have the same value"); + return; + } + if (s->mpu_ns_regions != UINT_MAX && + object_property_find(OBJECT(s->cpu), "pmsav7-dregion")) { + if (!object_property_set_uint(OBJECT(s->cpu), "pmsav7-dregion", + s->mpu_ns_regions, errp)) { + return; + } + } + /* * Tell the CPU where the NVIC is; it will fail realize if it doesn't * have one. Similarly, tell the NVIC where its CPU is. @@ -XXX,XX +XXX,XX @@ static Property armv7m_properties[] = { false), DEFINE_PROP_BOOL("vfp", ARMv7MState, vfp, true), DEFINE_PROP_BOOL("dsp", ARMv7MState, dsp, true), + DEFINE_PROP_UINT32("mpu-ns-regions", ARMv7MState, mpu_ns_regions, UINT_MAX), + DEFINE_PROP_UINT32("mpu-s-regions", ARMv7MState, mpu_s_regions, UINT_MAX), DEFINE_PROP_END_OF_LIST(), }; -- 2.34.1 The IoTKit, SSE200 and SSE300 all default to 8 MPU regions. The MPS2/MPS3 FPGA images don't override these except in the case of AN547, which uses 16 MPU regions. Define properties on the ARMSSE object for the MPU regions (using the same names as the documented RTL configuration settings, and following the pattern we already have for this device of using all-caps names as the RTL does), and set them in the board code. We don't actually need to override the default except on AN547, but it's simpler code to have the board code set them always rather than tracking which board subtypes want to set them to a non-default value separately from what that value is. Tho overall effect is that for mps2-an505, mps2-an521 and mps3-an524 we now correctly use 8 MPU regions, while mps3-an547 stays at its current 16 regions. It's possible some guest code wrongly depended on the previous incorrectly modeled number of memory regions. (Such guest code should ideally check the number of regions via the MPU_TYPE register.) The old behaviour can be obtained with additional -global arguments to QEMU: For mps2-an521 and mps2-an524: -global sse-200.CPU0_MPU_NS=16 -global sse-200.CPU0_MPU_S=16 -global sse-200.CPU1_MPU_NS=16 -global sse-200.CPU1_MPU_S=16 For mps2-an505: -global sse-200.CPU0_MPU_NS=16 -global sse-200.CPU0_MPU_S=16 NB that the way the implementation allows this use of -global is slightly fragile: if the board code explicitly sets the properties on the sse-200 object, this overrides the -global command line option. So we rely on: - the boards that need fixing all happen to use the SSE defaults - we can write the board code to only set the property if it is different from the default, rather than having all boards explicitly set the property - the board that does need to use a non-default value happens to need to set it to the same value (16) we previously used This works, but there are some kinds of refactoring of the mps2-tz.c code that would break the support for -global here. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1772 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230724174335.2150499-4-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 5 +++++ hw/arm/armsse.c | 16 ++++++++++++++++ hw/arm/mps2-tz.c | 29 +++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+) diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armsse.h +++ b/include/hw/arm/armsse.h @@ -XXX,XX +XXX,XX @@ * (matching the hardware) is that for CPU0 in an IoTKit and CPU1 in an * SSE-200 both are present; CPU0 in an SSE-200 has neither. * Since the IoTKit has only one CPU, it does not have the CPU1_* properties. + * + QOM properties "CPU0_MPU_NS", "CPU0_MPU_S", "CPU1_MPU_NS" and "CPU1_MPU_S" + * which set the number of MPU regions on the CPUs. If there is only one + * CPU the CPU1 properties are not present. * + Named GPIO inputs "EXP_IRQ" 0..n are the expansion interrupts for CPU 0, * which are wired to its NVIC lines 32 .. n+32 * + Named GPIO inputs "EXP_CPU1_IRQ" 0..n are the expansion interrupts for @@ -XXX,XX +XXX,XX @@ struct ARMSSE { uint32_t exp_numirq; uint32_t sram_addr_width; uint32_t init_svtor; + uint32_t cpu_mpu_ns[SSE_MAX_CPUS]; + uint32_t cpu_mpu_s[SSE_MAX_CPUS]; bool cpu_fpu[SSE_MAX_CPUS]; bool cpu_dsp[SSE_MAX_CPUS]; }; diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static Property iotkit_properties[] = { DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true), DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true), + DEFINE_PROP_UINT32("CPU0_MPU_NS", ARMSSE, cpu_mpu_ns[0], 8), + DEFINE_PROP_UINT32("CPU0_MPU_S", ARMSSE, cpu_mpu_s[0], 8), DEFINE_PROP_END_OF_LIST() }; @@ -XXX,XX +XXX,XX @@ static Property sse200_properties[] = { DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], false), DEFINE_PROP_BOOL("CPU1_FPU", ARMSSE, cpu_fpu[1], true), DEFINE_PROP_BOOL("CPU1_DSP", ARMSSE, cpu_dsp[1], true), + DEFINE_PROP_UINT32("CPU0_MPU_NS", ARMSSE, cpu_mpu_ns[0], 8), + DEFINE_PROP_UINT32("CPU0_MPU_S", ARMSSE, cpu_mpu_s[0], 8), + DEFINE_PROP_UINT32("CPU1_MPU_NS", ARMSSE, cpu_mpu_ns[1], 8), + DEFINE_PROP_UINT32("CPU1_MPU_S", ARMSSE, cpu_mpu_s[1], 8), DEFINE_PROP_END_OF_LIST() }; @@ -XXX,XX +XXX,XX @@ static Property sse300_properties[] = { DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true), DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true), + DEFINE_PROP_UINT32("CPU0_MPU_NS", ARMSSE, cpu_mpu_ns[0], 8), + DEFINE_PROP_UINT32("CPU0_MPU_S", ARMSSE, cpu_mpu_s[0], 8), DEFINE_PROP_END_OF_LIST() }; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } } + if (!object_property_set_uint(cpuobj, "mpu-ns-regions", + s->cpu_mpu_ns[i], errp)) { + return; + } + if (!object_property_set_uint(cpuobj, "mpu-s-regions", + s->cpu_mpu_s[i], errp)) { + return; + } if (i > 0) { memory_region_add_subregion_overlap(&s->cpu_container[i], 0, diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { int uart_overflow_irq; /* number of the combined UART overflow IRQ */ uint32_t init_svtor; /* init-svtor setting for SSE */ uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */ + uint32_t cpu0_mpu_ns; /* CPU0_MPU_NS setting for SSE */ + uint32_t cpu0_mpu_s; /* CPU0_MPU_S setting for SSE */ + uint32_t cpu1_mpu_ns; /* CPU1_MPU_NS setting for SSE */ + uint32_t cpu1_mpu_s; /* CPU1_MPU_S setting for SSE */ const RAMInfo *raminfo; const char *armsse_type; uint32_t boot_ram_size; /* size of ram at address 0; 0 == find in raminfo */ @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) #define MPS3_DDR_SIZE (2 * GiB) #endif +/* For cpu{0,1}_mpu_{ns,s}, means "leave at SSE's default value" */ +#define MPU_REGION_DEFAULT UINT32_MAX + static const uint32_t an505_oscclk[] = { 40000000, 24580000, @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) OBJECT(system_memory), &error_abort); qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq); qdev_prop_set_uint32(iotkitdev, "init-svtor", mmc->init_svtor); + if (mmc->cpu0_mpu_ns != MPU_REGION_DEFAULT) { + qdev_prop_set_uint32(iotkitdev, "CPU0_MPU_NS", mmc->cpu0_mpu_ns); + } + if (mmc->cpu0_mpu_s != MPU_REGION_DEFAULT) { + qdev_prop_set_uint32(iotkitdev, "CPU0_MPU_S", mmc->cpu0_mpu_s); + } + if (object_property_find(OBJECT(iotkitdev), "CPU1_MPU_NS")) { + if (mmc->cpu1_mpu_ns != MPU_REGION_DEFAULT) { + qdev_prop_set_uint32(iotkitdev, "CPU1_MPU_NS", mmc->cpu1_mpu_ns); + } + if (mmc->cpu1_mpu_s != MPU_REGION_DEFAULT) { + qdev_prop_set_uint32(iotkitdev, "CPU1_MPU_S", mmc->cpu1_mpu_s); + } + } qdev_prop_set_uint32(iotkitdev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width); qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk); qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk); @@ -XXX,XX +XXX,XX @@ static void mps2tz_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(oc); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_CLASS(oc); mc->init = mps2tz_common_init; mc->reset = mps2_machine_reset; iic->check = mps2_tz_idau_check; + + /* Most machines leave these at the SSE defaults */ + mmc->cpu0_mpu_ns = MPU_REGION_DEFAULT; + mmc->cpu0_mpu_s = MPU_REGION_DEFAULT; + mmc->cpu1_mpu_ns = MPU_REGION_DEFAULT; + mmc->cpu1_mpu_s = MPU_REGION_DEFAULT; } static void mps2tz_set_default_ram_info(MPS2TZMachineClass *mmc) @@ -XXX,XX +XXX,XX @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data) mmc->numirq = 96; mmc->uart_overflow_irq = 48; mmc->init_svtor = 0x00000000; + mmc->cpu0_mpu_s = mmc->cpu0_mpu_ns = 16; mmc->sram_addr_width = 21; mmc->raminfo = an547_raminfo; mmc->armsse_type = TYPE_SSE300; -- 2.34.1