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 Arm queue; not huge but I figured I might as well send it out since I've been doing code review today and there's no queue of unprocessed pullreqs... thanks -- PMM The following changes since commit b3f846c59d8405bb87c551187721fc92ff2f1b92: Merge remote-tracking branch 'remotes/huth-gitlab/tags/pull-request-2021-01-11v2' into staging (2021-01-11 15:15:35 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210112 for you to fetch changes up to 19d131395ccaf503db21dadd8257e6dc9fc1d7de: ui/cocoa: Fix openFile: deprecation on Big Sur (2021-01-12 11:38:37 +0000) ---------------------------------------------------------------- target-arm queue: * arm: Support emulation of ARMv8.4-TTST extension * arm: Update cpu.h ID register field definitions * arm: Fix breakage of XScale instruction emulation * hw/net/lan9118: Fix RX Status FIFO PEEK value * npcm7xx: Add ADC and PWM emulation * ui/cocoa: Make "open docs" help menu entry work again when binary is run from the build tree * ui/cocoa: Fix openFile: deprecation on Big Sur * docs: Add qemu-storage-daemon(1) manpage to meson.build * docs: Build and install all the docs in a single manual ---------------------------------------------------------------- Hao Wu (6): hw/misc: Add clock converter in NPCM7XX CLK module hw/timer: Refactor NPCM7XX Timer to use CLK clock hw/adc: Add an ADC module for NPCM7XX hw/misc: Add a PWM module for NPCM7XX hw/misc: Add QTest for NPCM7XX PWM Module hw/*: Use type casting for SysBusDevice in NPCM7XX Leif Lindholm (6): target/arm: fix typo in cpu.h ID_AA64PFR1 field name target/arm: make ARMCPU.clidr 64-bit target/arm: make ARMCPU.ctr 64-bit target/arm: add descriptions of CLIDR_EL1, CCSIDR_EL1, CTR_EL0 to cpu.h target/arm: add aarch64 ID register fields to cpu.h target/arm: add aarch32 ID register fields to cpu.h Peter Maydell (5): docs: Add qemu-storage-daemon(1) manpage to meson.build docs: Build and install all the docs in a single manual target/arm: Don't decode insns in the XScale/iWMMXt space as cp insns hw/net/lan9118: Fix RX Status FIFO PEEK value hw/net/lan9118: Add symbolic constants for register offsets Roman Bolshakov (2): ui/cocoa: Update path to docs in build tree ui/cocoa: Fix openFile: deprecation on Big Sur Rémi Denis-Courmont (2): target/arm: ARMv8.4-TTST extension target/arm: enable Small Translation tables in max CPU docs/conf.py | 46 ++- docs/devel/conf.py | 15 - docs/index.html.in | 17 - docs/interop/conf.py | 28 -- docs/meson.build | 65 ++-- docs/specs/conf.py | 16 - docs/system/arm/nuvoton.rst | 4 +- docs/system/conf.py | 28 -- docs/tools/conf.py | 37 -- docs/user/conf.py | 15 - meson.build | 1 + hw/adc/trace.h | 1 + include/hw/adc/npcm7xx_adc.h | 69 ++++ include/hw/arm/npcm7xx.h | 4 + include/hw/misc/npcm7xx_clk.h | 146 ++++++- include/hw/misc/npcm7xx_pwm.h | 105 +++++ include/hw/timer/npcm7xx_timer.h | 1 + target/arm/cpu.h | 85 ++++- hw/adc/npcm7xx_adc.c | 301 +++++++++++++++ hw/arm/npcm7xx.c | 55 ++- hw/arm/npcm7xx_boards.c | 2 +- hw/mem/npcm7xx_mc.c | 2 +- hw/misc/npcm7xx_clk.c | 807 ++++++++++++++++++++++++++++++++++++++- hw/misc/npcm7xx_gcr.c | 2 +- hw/misc/npcm7xx_pwm.c | 550 ++++++++++++++++++++++++++ hw/misc/npcm7xx_rng.c | 2 +- hw/net/lan9118.c | 26 +- hw/nvram/npcm7xx_otp.c | 2 +- hw/ssi/npcm7xx_fiu.c | 2 +- hw/timer/npcm7xx_timer.c | 39 +- target/arm/cpu64.c | 1 + target/arm/helper.c | 15 +- target/arm/translate.c | 7 + tests/qtest/npcm7xx_adc-test.c | 377 ++++++++++++++++++ tests/qtest/npcm7xx_pwm-test.c | 490 ++++++++++++++++++++++++ hw/adc/meson.build | 1 + hw/adc/trace-events | 5 + hw/misc/meson.build | 1 + hw/misc/trace-events | 6 + tests/qtest/meson.build | 4 +- ui/cocoa.m | 7 +- 41 files changed, 3124 insertions(+), 263 deletions(-) delete mode 100644 docs/devel/conf.py delete mode 100644 docs/index.html.in delete mode 100644 docs/interop/conf.py delete mode 100644 docs/specs/conf.py delete mode 100644 docs/system/conf.py delete mode 100644 docs/tools/conf.py delete mode 100644 docs/user/conf.py create mode 100644 hw/adc/trace.h create mode 100644 include/hw/adc/npcm7xx_adc.h create mode 100644 include/hw/misc/npcm7xx_pwm.h create mode 100644 hw/adc/npcm7xx_adc.c create mode 100644 hw/misc/npcm7xx_pwm.c create mode 100644 tests/qtest/npcm7xx_adc-test.c create mode 100644 tests/qtest/npcm7xx_pwm-test.c create mode 100644 hw/adc/trace-events From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> This adds for the Small Translation tables extension in AArch64 state. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++++ target/arm/helper.c | 15 +++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; } +static inline bool isar_feature_aa64_st(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, ST) != 0; +} + static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; 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 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; bool epd, hpd, using16k, using64k; - int select, tsz, tbi; + int select, tsz, tbi, max_tsz; if (!regime_has_2_ranges(mmu_idx)) { select = 0; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, hpd = extract64(tcr, 42, 1); } } - tsz = MIN(tsz, 39); /* TODO: ARMv8.4-TTST */ + + if (cpu_isar_feature(aa64_st, env_archcpu(env))) { + max_tsz = 48 - using64k; + } else { + max_tsz = 39; + } + + tsz = MIN(tsz, max_tsz); tsz = MAX(tsz, 16); /* TODO: ARMv8.2-LVA */ /* Present TBI as a composite with TBID. */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, uint64_t address, if (!aarch64 || stride == 9) { /* AArch32 or 4KB pages */ startlevel = 2 - sl0; + + if (cpu_isar_feature(aa64_st, cpu)) { + startlevel &= 3; + } } else { /* 16KB or 64KB pages */ startlevel = 3 - sl0; -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> 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_max_initfn(Object *obj) t = cpu->isar.id_aa64mmfr2; t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1); t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* TTCNP */ + t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* TTST */ cpu->isar.id_aa64mmfr2 = t; /* Replicate the same data to the 32-bit id registers. */ -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> SBSS -> SSBS Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20210108185154.8108-2-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- 1 file changed, 1 insertion(+), 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 @@ FIELD(ID_AA64PFR0, RAS, 28, 4) FIELD(ID_AA64PFR0, SVE, 32, 4) FIELD(ID_AA64PFR1, BT, 0, 4) -FIELD(ID_AA64PFR1, SBSS, 4, 4) +FIELD(ID_AA64PFR1, SSBS, 4, 4) FIELD(ID_AA64PFR1, MTE, 8, 4) FIELD(ID_AA64PFR1, RAS_FRAC, 12, 4) -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> The AArch64 view of CLIDR_EL1 extends the ICB field to include also bit 32, as well as adding a Ttype<n> field when FEAT_MTE is implemented. Extend the clidr field to be able to hold this context. Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20210108185154.8108-3-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- 1 file changed, 1 insertion(+), 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 ARMCPU { uint32_t id_afr0; uint64_t id_aa64afr0; uint64_t id_aa64afr1; - uint32_t clidr; + uint64_t clidr; uint64_t mp_affinity; /* MP ID without feature bits */ /* The elements of this array are the CCSIDR values for each cache, * in the order L1DCache, L1ICache, L2DCache, L2ICache, etc. -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> When FEAT_MTE is implemented, the AArch64 view of CTR_EL0 adds the TminLine field in bits [37:32]. Extend the ctr field to be able to hold this context. Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20210108185154.8108-4-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- 1 file changed, 1 insertion(+), 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 ARMCPU { uint64_t midr; uint32_t revidr; uint32_t reset_fpsid; - uint32_t ctr; + uint64_t ctr; uint32_t reset_sctlr; uint64_t pmceid0; uint64_t pmceid1; -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20210108185154.8108-5-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(V7M_FPCCR, ASPEN, 31, 1) /* * System register ID fields. */ +FIELD(CLIDR_EL1, CTYPE1, 0, 3) +FIELD(CLIDR_EL1, CTYPE2, 3, 3) +FIELD(CLIDR_EL1, CTYPE3, 6, 3) +FIELD(CLIDR_EL1, CTYPE4, 9, 3) +FIELD(CLIDR_EL1, CTYPE5, 12, 3) +FIELD(CLIDR_EL1, CTYPE6, 15, 3) +FIELD(CLIDR_EL1, CTYPE7, 18, 3) +FIELD(CLIDR_EL1, LOUIS, 21, 3) +FIELD(CLIDR_EL1, LOC, 24, 3) +FIELD(CLIDR_EL1, LOUU, 27, 3) +FIELD(CLIDR_EL1, ICB, 30, 3) + +/* When FEAT_CCIDX is implemented */ +FIELD(CCSIDR_EL1, CCIDX_LINESIZE, 0, 3) +FIELD(CCSIDR_EL1, CCIDX_ASSOCIATIVITY, 3, 21) +FIELD(CCSIDR_EL1, CCIDX_NUMSETS, 32, 24) + +/* When FEAT_CCIDX is not implemented */ +FIELD(CCSIDR_EL1, LINESIZE, 0, 3) +FIELD(CCSIDR_EL1, ASSOCIATIVITY, 3, 10) +FIELD(CCSIDR_EL1, NUMSETS, 13, 15) + +FIELD(CTR_EL0, IMINLINE, 0, 4) +FIELD(CTR_EL0, L1IP, 14, 2) +FIELD(CTR_EL0, DMINLINE, 16, 4) +FIELD(CTR_EL0, ERG, 20, 4) +FIELD(CTR_EL0, CWG, 24, 4) +FIELD(CTR_EL0, IDC, 28, 1) +FIELD(CTR_EL0, DIC, 29, 1) +FIELD(CTR_EL0, TMINLINE, 32, 6) + FIELD(MIDR_EL1, REVISION, 0, 4) FIELD(MIDR_EL1, PARTNUM, 4, 12) FIELD(MIDR_EL1, ARCHITECTURE, 16, 4) -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> Add entries present in ARM DDI 0487F.c (August 2020). Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20210108185154.8108-6-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR1, GPI, 28, 4) FIELD(ID_AA64ISAR1, FRINTTS, 32, 4) FIELD(ID_AA64ISAR1, SB, 36, 4) FIELD(ID_AA64ISAR1, SPECRES, 40, 4) +FIELD(ID_AA64ISAR1, BF16, 44, 4) +FIELD(ID_AA64ISAR1, DGH, 48, 4) +FIELD(ID_AA64ISAR1, I8MM, 52, 4) FIELD(ID_AA64PFR0, EL0, 0, 4) FIELD(ID_AA64PFR0, EL1, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64PFR0, ADVSIMD, 20, 4) FIELD(ID_AA64PFR0, GIC, 24, 4) FIELD(ID_AA64PFR0, RAS, 28, 4) FIELD(ID_AA64PFR0, SVE, 32, 4) +FIELD(ID_AA64PFR0, SEL2, 36, 4) +FIELD(ID_AA64PFR0, MPAM, 40, 4) +FIELD(ID_AA64PFR0, AMU, 44, 4) +FIELD(ID_AA64PFR0, DIT, 48, 4) +FIELD(ID_AA64PFR0, CSV2, 56, 4) +FIELD(ID_AA64PFR0, CSV3, 60, 4) FIELD(ID_AA64PFR1, BT, 0, 4) FIELD(ID_AA64PFR1, SSBS, 4, 4) FIELD(ID_AA64PFR1, MTE, 8, 4) FIELD(ID_AA64PFR1, RAS_FRAC, 12, 4) +FIELD(ID_AA64PFR1, MPAM_FRAC, 16, 4) FIELD(ID_AA64MMFR0, PARANGE, 0, 4) FIELD(ID_AA64MMFR0, ASIDBITS, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64MMFR0, TGRAN16_2, 32, 4) FIELD(ID_AA64MMFR0, TGRAN64_2, 36, 4) FIELD(ID_AA64MMFR0, TGRAN4_2, 40, 4) FIELD(ID_AA64MMFR0, EXS, 44, 4) +FIELD(ID_AA64MMFR0, FGT, 56, 4) +FIELD(ID_AA64MMFR0, ECV, 60, 4) FIELD(ID_AA64MMFR1, HAFDBS, 0, 4) FIELD(ID_AA64MMFR1, VMIDBITS, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64MMFR1, LO, 16, 4) FIELD(ID_AA64MMFR1, PAN, 20, 4) FIELD(ID_AA64MMFR1, SPECSEI, 24, 4) FIELD(ID_AA64MMFR1, XNX, 28, 4) +FIELD(ID_AA64MMFR1, TWED, 32, 4) +FIELD(ID_AA64MMFR1, ETS, 36, 4) FIELD(ID_AA64MMFR2, CNP, 0, 4) FIELD(ID_AA64MMFR2, UAO, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64DFR0, CTX_CMPS, 28, 4) FIELD(ID_AA64DFR0, PMSVER, 32, 4) FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4) FIELD(ID_AA64DFR0, TRACEFILT, 40, 4) +FIELD(ID_AA64DFR0, MTPMU, 48, 4) FIELD(ID_DFR0, COPDBG, 0, 4) FIELD(ID_DFR0, COPSDBG, 4, 4) -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> Add entries present in ARM DDI 0487F.c (August 2020). Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20210108185154.8108-7-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_ISAR6, DP, 4, 4) FIELD(ID_ISAR6, FHM, 8, 4) FIELD(ID_ISAR6, SB, 12, 4) FIELD(ID_ISAR6, SPECRES, 16, 4) +FIELD(ID_ISAR6, BF16, 20, 4) +FIELD(ID_ISAR6, I8MM, 24, 4) FIELD(ID_MMFR0, VMSA, 0, 4) FIELD(ID_MMFR0, PMSA, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_MMFR0, AUXREG, 20, 4) FIELD(ID_MMFR0, FCSE, 24, 4) FIELD(ID_MMFR0, INNERSHR, 28, 4) +FIELD(ID_MMFR1, L1HVDVA, 0, 4) +FIELD(ID_MMFR1, L1UNIVA, 4, 4) +FIELD(ID_MMFR1, L1HVDSW, 8, 4) +FIELD(ID_MMFR1, L1UNISW, 12, 4) +FIELD(ID_MMFR1, L1HVD, 16, 4) +FIELD(ID_MMFR1, L1UNI, 20, 4) +FIELD(ID_MMFR1, L1TSTCLN, 24, 4) +FIELD(ID_MMFR1, BPRED, 28, 4) + +FIELD(ID_MMFR2, L1HVDFG, 0, 4) +FIELD(ID_MMFR2, L1HVDBG, 4, 4) +FIELD(ID_MMFR2, L1HVDRNG, 8, 4) +FIELD(ID_MMFR2, HVDTLB, 12, 4) +FIELD(ID_MMFR2, UNITLB, 16, 4) +FIELD(ID_MMFR2, MEMBARR, 20, 4) +FIELD(ID_MMFR2, WFISTALL, 24, 4) +FIELD(ID_MMFR2, HWACCFLG, 28, 4) + FIELD(ID_MMFR3, CMAINTVA, 0, 4) FIELD(ID_MMFR3, CMAINTSW, 4, 4) FIELD(ID_MMFR3, BPMAINT, 8, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_MMFR4, LSM, 20, 4) FIELD(ID_MMFR4, CCIDX, 24, 4) FIELD(ID_MMFR4, EVT, 28, 4) +FIELD(ID_MMFR5, ETS, 0, 4) + FIELD(ID_PFR0, STATE0, 0, 4) FIELD(ID_PFR0, STATE1, 4, 4) FIELD(ID_PFR0, STATE2, 8, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_PFR1, SEC_FRAC, 20, 4) FIELD(ID_PFR1, VIRT_FRAC, 24, 4) FIELD(ID_PFR1, GIC, 28, 4) +FIELD(ID_PFR2, CSV3, 0, 4) +FIELD(ID_PFR2, SSBS, 4, 4) +FIELD(ID_PFR2, RAS_FRAC, 8, 4) + FIELD(ID_AA64ISAR0, AES, 4, 4) FIELD(ID_AA64ISAR0, SHA1, 8, 4) FIELD(ID_AA64ISAR0, SHA2, 12, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_DFR0, MPROFDBG, 20, 4) FIELD(ID_DFR0, PERFMON, 24, 4) FIELD(ID_DFR0, TRACEFILT, 28, 4) +FIELD(ID_DFR1, MTPMU, 0, 4) + FIELD(DBGDIDR, SE_IMP, 12, 1) FIELD(DBGDIDR, NSUHD_IMP, 14, 1) FIELD(DBGDIDR, VERSION, 16, 4) -- 2.20.1 From: Roman Bolshakov <r.bolshakov@yadro.com> QEMU documentation can't be opened if QEMU is run from build tree because executables are placed in the top of build tree after conversion to meson. Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com> Reported-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210108213815.64678-1-r.bolshakov@yadro.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- ui/cocoa.m | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ui/cocoa.m b/ui/cocoa.m index XXXXXXX..XXXXXXX 100644 --- a/ui/cocoa.m +++ b/ui/cocoa.m @@ -XXX,XX +XXX,XX @@ QemuCocoaView *cocoaView; - (void) openDocumentation: (NSString *) filename { /* Where to look for local files */ - NSString *path_array[] = {@"../share/doc/qemu/", @"../doc/qemu/", @"../docs/"}; + NSString *path_array[] = {@"../share/doc/qemu/", @"../doc/qemu/", @"docs/"}; NSString *full_file_path; /* iterate thru the possible paths until the file is found */ -- 2.20.1 In commit 1982e1602d15 we added a new qemu-storage-daemon(1) manpage. At the moment new manpages have to be listed both in the conf.py for Sphinx and also in docs/meson.build for Meson. We forgot the second of those -- correct the omission. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20210108161416.21129-2-peter.maydell@linaro.org --- docs/meson.build | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/meson.build b/docs/meson.build index XXXXXXX..XXXXXXX 100644 --- a/docs/meson.build +++ b/docs/meson.build @@ -XXX,XX +XXX,XX @@ if build_docs 'qemu-img.1': (have_tools ? 'man1' : ''), 'qemu-nbd.8': (have_tools ? 'man8' : ''), 'qemu-pr-helper.8': (have_tools ? 'man8' : ''), + 'qemu-storage-daemon.1': (have_tools ? 'man1' : ''), 'qemu-trace-stap.1': (config_host.has_key('CONFIG_TRACE_SYSTEMTAP') ? 'man1' : ''), 'virtfs-proxy-helper.1': (have_virtfs_proxy_helper ? 'man1' : ''), 'virtiofsd.1': (have_virtiofsd ? 'man1' : ''), -- 2.20.1 When we first converted our documentation to Sphinx, we split it into multiple manuals (system, interop, tools, etc), which are all built separately. The primary driver for this was wanting to be able to avoid shipping the 'devel' manual to end-users. However, this is working against the grain of the way Sphinx wants to be used and causes some annoyances: * Cross-references between documents become much harder or possibly impossible * There is no single index to the whole documentation * Within one manual there's no links or table-of-contents info that lets you easily navigate to the others * The devel manual doesn't get published on the QEMU website (it would be nice to able to refer to it there) Merely hiding our developer documentation from end users seems like it's not enough benefit for these costs. Combine all the documentation into a single manual (the same way that the readthedocs site builds it) and install the whole thing. The previous manual divisions remain as the new top level sections in the manual. * The per-manual conf.py files are no longer needed * The man_pages[] specifications previously in each per-manual conf.py move to the top level conf.py * docs/meson.build logic is simplified as we now only need to run Sphinx once for the HTML and then once for the manpages5B * The old index.html.in that produced the top-level page with links to each manual is no longer needed Unfortunately this means that we now have to build the HTML documentation into docs/manual in the build tree rather than directly into docs/; otherwise it is too awkward to ensure we install only the built manual and not also the dependency info, stamp file, etc. The manual still ends up in the same place in the final installed directory, but anybody who was consulting documentation from within the build tree will have to adjust where they're looking. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20210108161416.21129-3-peter.maydell@linaro.org --- docs/conf.py | 46 ++++++++++++++++++++++++++++++- docs/devel/conf.py | 15 ----------- docs/index.html.in | 17 ------------ docs/interop/conf.py | 28 ------------------- docs/meson.build | 64 +++++++++++++++++--------------------------- docs/specs/conf.py | 16 ----------- docs/system/conf.py | 28 ------------------- docs/tools/conf.py | 37 ------------------------- docs/user/conf.py | 15 ----------- 9 files changed, 70 insertions(+), 196 deletions(-) delete mode 100644 docs/devel/conf.py delete mode 100644 docs/index.html.in delete mode 100644 docs/interop/conf.py delete mode 100644 docs/specs/conf.py delete mode 100644 docs/system/conf.py delete mode 100644 docs/tools/conf.py delete mode 100644 docs/user/conf.py diff --git a/docs/conf.py b/docs/conf.py index XXXXXXX..XXXXXXX 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -XXX,XX +XXX,XX @@ latex_documents = [ # -- Options for manual page output --------------------------------------- # Individual manual/conf.py can override this to create man pages -man_pages = [] +man_pages = [ + ('interop/qemu-ga', 'qemu-ga', + 'QEMU Guest Agent', + ['Michael Roth <mdroth@linux.vnet.ibm.com>'], 8), + ('interop/qemu-ga-ref', 'qemu-ga-ref', + 'QEMU Guest Agent Protocol Reference', + [], 7), + ('interop/qemu-qmp-ref', 'qemu-qmp-ref', + 'QEMU QMP Reference Manual', + [], 7), + ('interop/qemu-storage-daemon-qmp-ref', 'qemu-storage-daemon-qmp-ref', + 'QEMU Storage Daemon QMP Reference Manual', + [], 7), + ('system/qemu-manpage', 'qemu', + 'QEMU User Documentation', + ['Fabrice Bellard'], 1), + ('system/qemu-block-drivers', 'qemu-block-drivers', + 'QEMU block drivers reference', + ['Fabrice Bellard and the QEMU Project developers'], 7), + ('system/qemu-cpu-models', 'qemu-cpu-models', + 'QEMU CPU Models', + ['The QEMU Project developers'], 7), + ('tools/qemu-img', 'qemu-img', + 'QEMU disk image utility', + ['Fabrice Bellard'], 1), + ('tools/qemu-nbd', 'qemu-nbd', + 'QEMU Disk Network Block Device Server', + ['Anthony Liguori <anthony@codemonkey.ws>'], 8), + ('tools/qemu-pr-helper', 'qemu-pr-helper', + 'QEMU persistent reservation helper', + [], 8), + ('tools/qemu-storage-daemon', 'qemu-storage-daemon', + 'QEMU storage daemon', + [], 1), + ('tools/qemu-trace-stap', 'qemu-trace-stap', + 'QEMU SystemTap trace tool', + [], 1), + ('tools/virtfs-proxy-helper', 'virtfs-proxy-helper', + 'QEMU 9p virtfs proxy filesystem helper', + ['M. Mohan Kumar'], 1), + ('tools/virtiofsd', 'virtiofsd', + 'QEMU virtio-fs shared file system daemon', + ['Stefan Hajnoczi <stefanha@redhat.com>', + 'Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>'], 1), +] # -- Options for Texinfo output ------------------------------------------- diff --git a/docs/devel/conf.py b/docs/devel/conf.py deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/devel/conf.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# -*- coding: utf-8 -*- -# -# QEMU documentation build configuration file for the 'devel' manual. -# -# This includes the top level conf file and then makes any necessary tweaks. -import sys -import os - -qemu_docdir = os.path.abspath("..") -parent_config = os.path.join(qemu_docdir, "conf.py") -exec(compile(open(parent_config, "rb").read(), parent_config, 'exec')) - -# This slightly misuses the 'description', but is the best way to get -# the manual title to appear in the sidebar. -html_theme_options['description'] = u'Developer''s Guide' diff --git a/docs/index.html.in b/docs/index.html.in deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/index.html.in +++ /dev/null @@ -XXX,XX +XXX,XX @@ -<!DOCTYPE html> -<html lang="en"> - <head> - <meta charset="UTF-8"> - <title>QEMU @VERSION@ Documentation</title> - </head> - <body> - <h1>QEMU @VERSION@ Documentation</h1> - <ul> - <li><a href="system/index.html">System Emulation User's Guide</a></li> - <li><a href="user/index.html">User Mode Emulation User's Guide</a></li> - <li><a href="tools/index.html">Tools Guide</a></li> - <li><a href="interop/index.html">System Emulation Management and Interoperability Guide</a></li> - <li><a href="specs/index.html">System Emulation Guest Hardware Specifications</a></li> - </ul> - </body> -</html> diff --git a/docs/interop/conf.py b/docs/interop/conf.py deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/interop/conf.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# -*- coding: utf-8 -*- -# -# QEMU documentation build configuration file for the 'interop' manual. -# -# This includes the top level conf file and then makes any necessary tweaks. -import sys -import os - -qemu_docdir = os.path.abspath("..") -parent_config = os.path.join(qemu_docdir, "conf.py") -exec(compile(open(parent_config, "rb").read(), parent_config, 'exec')) - -# This slightly misuses the 'description', but is the best way to get -# the manual title to appear in the sidebar. -html_theme_options['description'] = u'System Emulation Management and Interoperability Guide' - -# One entry per manual page. List of tuples -# (source start file, name, description, authors, manual section). -man_pages = [ - ('qemu-ga', 'qemu-ga', u'QEMU Guest Agent', - ['Michael Roth <mdroth@linux.vnet.ibm.com>'], 8), - ('qemu-ga-ref', 'qemu-ga-ref', 'QEMU Guest Agent Protocol Reference', - [], 7), - ('qemu-qmp-ref', 'qemu-qmp-ref', 'QEMU QMP Reference Manual', - [], 7), - ('qemu-storage-daemon-qmp-ref', 'qemu-storage-daemon-qmp-ref', - 'QEMU Storage Daemon QMP Reference Manual', [], 7), -] diff --git a/docs/meson.build b/docs/meson.build index XXXXXXX..XXXXXXX 100644 --- a/docs/meson.build +++ b/docs/meson.build @@ -XXX,XX +XXX,XX @@ if build_docs meson.source_root() / 'docs/sphinx/qmp_lexer.py', qapi_gen_depends ] - configure_file(output: 'index.html', - input: files('index.html.in'), - configuration: {'VERSION': meson.project_version()}, - install_dir: qemu_docdir) - manuals = [ 'devel', 'interop', 'tools', 'specs', 'system', 'user' ] man_pages = { - 'interop' : { 'qemu-ga.8': (have_tools ? 'man8' : ''), 'qemu-ga-ref.7': 'man7', 'qemu-qmp-ref.7': 'man7', 'qemu-storage-daemon-qmp-ref.7': (have_tools ? 'man7' : ''), - }, - 'tools': { 'qemu-img.1': (have_tools ? 'man1' : ''), 'qemu-nbd.8': (have_tools ? 'man8' : ''), 'qemu-pr-helper.8': (have_tools ? 'man8' : ''), @@ -XXX,XX +XXX,XX @@ if build_docs 'qemu-trace-stap.1': (config_host.has_key('CONFIG_TRACE_SYSTEMTAP') ? 'man1' : ''), 'virtfs-proxy-helper.1': (have_virtfs_proxy_helper ? 'man1' : ''), 'virtiofsd.1': (have_virtiofsd ? 'man1' : ''), - }, - 'system': { 'qemu.1': 'man1', 'qemu-block-drivers.7': 'man7', 'qemu-cpu-models.7': 'man7' - }, } sphinxdocs = [] sphinxmans = [] - foreach manual : manuals - private_dir = meson.current_build_dir() / (manual + '.p') - output_dir = meson.current_build_dir() / manual - input_dir = meson.current_source_dir() / manual - this_manual = custom_target(manual + ' manual', + private_dir = meson.current_build_dir() / 'manual.p' + output_dir = meson.current_build_dir() / 'manual' + input_dir = meson.current_source_dir() + + this_manual = custom_target('QEMU manual', build_by_default: build_docs, - output: [manual + '.stamp'], - input: [files('conf.py'), files(manual / 'conf.py')], - depfile: manual + '.d', + output: 'docs.stamp', + input: files('conf.py'), + depfile: 'docs.d', depend_files: sphinx_extn_depends, command: [SPHINX_ARGS, '-Ddepfile=@DEPFILE@', '-Ddepfile_stamp=@OUTPUT0@', '-b', 'html', '-d', private_dir, input_dir, output_dir]) - sphinxdocs += this_manual - if build_docs and manual != 'devel' - install_subdir(output_dir, install_dir: qemu_docdir) - endif + sphinxdocs += this_manual + install_subdir(output_dir, install_dir: qemu_docdir, strip_directory: true) - these_man_pages = [] - install_dirs = [] - foreach page, section : man_pages.get(manual, {}) - these_man_pages += page - install_dirs += section == '' ? false : get_option('mandir') / section - endforeach - if these_man_pages.length() > 0 - sphinxmans += custom_target(manual + ' man pages', - build_by_default: build_docs, - output: these_man_pages, - input: this_manual, - install: build_docs, - install_dir: install_dirs, - command: [SPHINX_ARGS, '-b', 'man', '-d', private_dir, - input_dir, meson.current_build_dir()]) - endif + these_man_pages = [] + install_dirs = [] + foreach page, section : man_pages + these_man_pages += page + install_dirs += section == '' ? false : get_option('mandir') / section endforeach + + sphinxmans += custom_target('QEMU man pages', + build_by_default: build_docs, + output: these_man_pages, + input: this_manual, + install: build_docs, + install_dir: install_dirs, + command: [SPHINX_ARGS, '-b', 'man', '-d', private_dir, + input_dir, meson.current_build_dir()]) + alias_target('sphinxdocs', sphinxdocs) alias_target('html', sphinxdocs) alias_target('man', sphinxmans) diff --git a/docs/specs/conf.py b/docs/specs/conf.py deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/specs/conf.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# -*- coding: utf-8 -*- -# -# QEMU documentation build configuration file for the 'specs' manual. -# -# This includes the top level conf file and then makes any necessary tweaks. -import sys -import os - -qemu_docdir = os.path.abspath("..") -parent_config = os.path.join(qemu_docdir, "conf.py") -exec(compile(open(parent_config, "rb").read(), parent_config, 'exec')) - -# This slightly misuses the 'description', but is the best way to get -# the manual title to appear in the sidebar. -html_theme_options['description'] = \ - u'System Emulation Guest Hardware Specifications' diff --git a/docs/system/conf.py b/docs/system/conf.py deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/system/conf.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# -*- coding: utf-8 -*- -# -# QEMU documentation build configuration file for the 'system' manual. -# -# This includes the top level conf file and then makes any necessary tweaks. -import sys -import os - -qemu_docdir = os.path.abspath("..") -parent_config = os.path.join(qemu_docdir, "conf.py") -exec(compile(open(parent_config, "rb").read(), parent_config, 'exec')) - -# This slightly misuses the 'description', but is the best way to get -# the manual title to appear in the sidebar. -html_theme_options['description'] = u'System Emulation User''s Guide' - -# One entry per manual page. List of tuples -# (source start file, name, description, authors, manual section). -man_pages = [ - ('qemu-manpage', 'qemu', u'QEMU User Documentation', - ['Fabrice Bellard'], 1), - ('qemu-block-drivers', 'qemu-block-drivers', - u'QEMU block drivers reference', - ['Fabrice Bellard and the QEMU Project developers'], 7), - ('qemu-cpu-models', 'qemu-cpu-models', - u'QEMU CPU Models', - ['The QEMU Project developers'], 7) -] diff --git a/docs/tools/conf.py b/docs/tools/conf.py deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/tools/conf.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# -*- coding: utf-8 -*- -# -# QEMU documentation build configuration file for the 'tools' manual. -# -# This includes the top level conf file and then makes any necessary tweaks. -import sys -import os - -qemu_docdir = os.path.abspath("..") -parent_config = os.path.join(qemu_docdir, "conf.py") -exec(compile(open(parent_config, "rb").read(), parent_config, 'exec')) - -# This slightly misuses the 'description', but is the best way to get -# the manual title to appear in the sidebar. -html_theme_options['description'] = \ - u'Tools Guide' - -# One entry per manual page. List of tuples -# (source start file, name, description, authors, manual section). -man_pages = [ - ('qemu-img', 'qemu-img', u'QEMU disk image utility', - ['Fabrice Bellard'], 1), - ('qemu-storage-daemon', 'qemu-storage-daemon', u'QEMU storage daemon', - [], 1), - ('qemu-nbd', 'qemu-nbd', u'QEMU Disk Network Block Device Server', - ['Anthony Liguori <anthony@codemonkey.ws>'], 8), - ('qemu-pr-helper', 'qemu-pr-helper', 'QEMU persistent reservation helper', - [], 8), - ('qemu-trace-stap', 'qemu-trace-stap', u'QEMU SystemTap trace tool', - [], 1), - ('virtfs-proxy-helper', 'virtfs-proxy-helper', - u'QEMU 9p virtfs proxy filesystem helper', - ['M. Mohan Kumar'], 1), - ('virtiofsd', 'virtiofsd', u'QEMU virtio-fs shared file system daemon', - ['Stefan Hajnoczi <stefanha@redhat.com>', - 'Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>'], 1), -] diff --git a/docs/user/conf.py b/docs/user/conf.py deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/docs/user/conf.py +++ /dev/null @@ -XXX,XX +XXX,XX @@ -# -*- coding: utf-8 -*- -# -# QEMU documentation build configuration file for the 'user' manual. -# -# This includes the top level conf file and then makes any necessary tweaks. -import sys -import os - -qemu_docdir = os.path.abspath("..") -parent_config = os.path.join(qemu_docdir, "conf.py") -exec(compile(open(parent_config, "rb").read(), parent_config, 'exec')) - -# This slightly misuses the 'description', but is the best way to get -# the manual title to appear in the sidebar. -html_theme_options['description'] = u'User Mode Emulation User''s Guide' -- 2.20.1 In commit cd8be50e58f63413c0 we converted the A32 coprocessor insns to decodetree. This accidentally broke XScale/iWMMXt insns, because it moved the handling of "cp insns which are handled by looking up the cp register in the hashtable" from after the call to the legacy disas_xscale_insn() decode to before it, with the result that all XScale/iWMMXt insns now UNDEF. Update valid_cp() so that it knows that on XScale cp 0 and 1 are not standard coprocessor instructions; this will cause the decodetree trans_ functions to ignore them, so that execution will correctly get through to the legacy decode again. Cc: qemu-stable@nongnu.org Reported-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210108195157.32067-1-peter.maydell@linaro.org --- target/arm/translate.c | 7 +++++++ 1 file changed, 7 insertions(+) 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 bool valid_cp(DisasContext *s, int cp) * only cp14 and cp15 are valid, and other values aren't considered * to be in the coprocessor-instruction space at all. v8M still * permits coprocessors 0..7. + * For XScale, we must not decode the XScale cp0, cp1 space as + * a standard coprocessor insn, because we want to fall through to + * the legacy disas_xscale_insn() decoder after decodetree is done. */ + if (arm_dc_feature(s, ARM_FEATURE_XSCALE) && (cp == 0 || cp == 1)) { + return false; + } + if (arm_dc_feature(s, ARM_FEATURE_V8) && !arm_dc_feature(s, ARM_FEATURE_M)) { return cp >= 14; -- 2.20.1 A copy-and-paste error meant that the return value for register offset 0x44 (the RX Status FIFO PEEK register) returned a byte from a bogus offset in the rx status FIFO. Fix the typo. Cc: qemu-stable@nongnu.org Fixes: https://bugs.launchpad.net/qemu/+bug/1904954 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210108180401.2263-2-peter.maydell@linaro.org --- hw/net/lan9118.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118.c +++ b/hw/net/lan9118.c @@ -XXX,XX +XXX,XX @@ static uint64_t lan9118_readl(void *opaque, hwaddr offset, case 0x40: return rx_status_fifo_pop(s); case 0x44: - return s->rx_status_fifo[s->tx_status_fifo_head]; + return s->rx_status_fifo[s->rx_status_fifo_head]; case 0x48: return tx_status_fifo_pop(s); case 0x4c: -- 2.20.1 The lan9118 code mostly uses symbolic constants for register offsets; the exceptions are those which the datasheet doesn't give an official symbolic name to. Add some names for the registers which don't already have them, based on the longer names they are given in the memory map. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210108180401.2263-3-peter.maydell@linaro.org --- hw/net/lan9118.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118.c +++ b/hw/net/lan9118.c @@ -XXX,XX +XXX,XX @@ do { hw_error("lan9118: error: " fmt , ## __VA_ARGS__);} while (0) do { fprintf(stderr, "lan9118: error: " fmt , ## __VA_ARGS__);} while (0) #endif +/* The tx and rx fifo ports are a range of aliased 32-bit registers */ +#define RX_DATA_FIFO_PORT_FIRST 0x00 +#define RX_DATA_FIFO_PORT_LAST 0x1f +#define TX_DATA_FIFO_PORT_FIRST 0x20 +#define TX_DATA_FIFO_PORT_LAST 0x3f + +#define RX_STATUS_FIFO_PORT 0x40 +#define RX_STATUS_FIFO_PEEK 0x44 +#define TX_STATUS_FIFO_PORT 0x48 +#define TX_STATUS_FIFO_PEEK 0x4c + #define CSR_ID_REV 0x50 #define CSR_IRQ_CFG 0x54 #define CSR_INT_STS 0x58 @@ -XXX,XX +XXX,XX @@ static void lan9118_writel(void *opaque, hwaddr offset, offset &= 0xff; //DPRINTF("Write reg 0x%02x = 0x%08x\n", (int)offset, val); - if (offset >= 0x20 && offset < 0x40) { + if (offset >= TX_DATA_FIFO_PORT_FIRST && + offset <= TX_DATA_FIFO_PORT_LAST) { /* TX FIFO */ tx_fifo_push(s, val); return; @@ -XXX,XX +XXX,XX @@ static uint64_t lan9118_readl(void *opaque, hwaddr offset, lan9118_state *s = (lan9118_state *)opaque; //DPRINTF("Read reg 0x%02x\n", (int)offset); - if (offset < 0x20) { + if (offset <= RX_DATA_FIFO_PORT_LAST) { /* RX FIFO */ return rx_fifo_pop(s); } switch (offset) { - case 0x40: + case RX_STATUS_FIFO_PORT: return rx_status_fifo_pop(s); - case 0x44: + case RX_STATUS_FIFO_PEEK: return s->rx_status_fifo[s->rx_status_fifo_head]; - case 0x48: + case TX_STATUS_FIFO_PORT: return tx_status_fifo_pop(s); - case 0x4c: + case TX_STATUS_FIFO_PEEK: return s->tx_status_fifo[s->tx_status_fifo_head]; case CSR_ID_REV: return 0x01180001; -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch allows NPCM7XX CLK module to compute clocks that are used by other NPCM7XX modules. Add a new struct NPCM7xxClockConverterState which represents a single converter. Each clock converter in CLK module represents one converter in NPCM7XX CLK Module(PLL, SEL or Divider). Each converter takes one or more input clocks and converts them into one output clock. They form a clock hierarchy in the CLK module and are responsible for outputing clocks for various other modules in an NPCM7XX SoC. Each converter has a function pointer called "convert" which represents the unique logic for that converter. The clock contains two initialization information: ConverterInitInfo and ConverterConnectionInfo. They represent the vertices and edges in the clock diagram respectively. Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210108190945.949196-2-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_clk.h | 140 +++++- hw/misc/npcm7xx_clk.c | 805 +++++++++++++++++++++++++++++++++- 2 files changed, 932 insertions(+), 13 deletions(-) diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_clk.h +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_CLK_H #include "exec/memory.h" +#include "hw/clock.h" #include "hw/sysbus.h" /* @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_WATCHDOG_RESET_GPIO_IN "npcm7xx-clk-watchdog-reset-gpio-in" -typedef struct NPCM7xxCLKState { +/* Maximum amount of clock inputs in a SEL module. */ +#define NPCM7XX_CLK_SEL_MAX_INPUT 5 + +/* PLLs in CLK module. */ +typedef enum NPCM7xxClockPLL { + NPCM7XX_CLOCK_PLL0, + NPCM7XX_CLOCK_PLL1, + NPCM7XX_CLOCK_PLL2, + NPCM7XX_CLOCK_PLLG, + NPCM7XX_CLOCK_NR_PLLS, +} NPCM7xxClockPLL; + +/* SEL/MUX in CLK module. */ +typedef enum NPCM7xxClockSEL { + NPCM7XX_CLOCK_PIXCKSEL, + NPCM7XX_CLOCK_MCCKSEL, + NPCM7XX_CLOCK_CPUCKSEL, + NPCM7XX_CLOCK_CLKOUTSEL, + NPCM7XX_CLOCK_UARTCKSEL, + NPCM7XX_CLOCK_TIMCKSEL, + NPCM7XX_CLOCK_SDCKSEL, + NPCM7XX_CLOCK_GFXMSEL, + NPCM7XX_CLOCK_SUCKSEL, + NPCM7XX_CLOCK_NR_SELS, +} NPCM7xxClockSEL; + +/* Dividers in CLK module. */ +typedef enum NPCM7xxClockDivider { + NPCM7XX_CLOCK_PLL1D2, /* PLL1/2 */ + NPCM7XX_CLOCK_PLL2D2, /* PLL2/2 */ + NPCM7XX_CLOCK_MC_DIVIDER, + NPCM7XX_CLOCK_AXI_DIVIDER, + NPCM7XX_CLOCK_AHB_DIVIDER, + NPCM7XX_CLOCK_AHB3_DIVIDER, + NPCM7XX_CLOCK_SPI0_DIVIDER, + NPCM7XX_CLOCK_SPIX_DIVIDER, + NPCM7XX_CLOCK_APB1_DIVIDER, + NPCM7XX_CLOCK_APB2_DIVIDER, + NPCM7XX_CLOCK_APB3_DIVIDER, + NPCM7XX_CLOCK_APB4_DIVIDER, + NPCM7XX_CLOCK_APB5_DIVIDER, + NPCM7XX_CLOCK_CLKOUT_DIVIDER, + NPCM7XX_CLOCK_UART_DIVIDER, + NPCM7XX_CLOCK_TIMER_DIVIDER, + NPCM7XX_CLOCK_ADC_DIVIDER, + NPCM7XX_CLOCK_MMC_DIVIDER, + NPCM7XX_CLOCK_SDHC_DIVIDER, + NPCM7XX_CLOCK_GFXM_DIVIDER, /* divide by 3 */ + NPCM7XX_CLOCK_UTMI_DIVIDER, + NPCM7XX_CLOCK_NR_DIVIDERS, +} NPCM7xxClockConverter; + +typedef struct NPCM7xxCLKState NPCM7xxCLKState; + +/** + * struct NPCM7xxClockPLLState - A PLL module in CLK module. + * @name: The name of the module. + * @clk: The CLK module that owns this module. + * @clock_in: The input clock of this module. + * @clock_out: The output clock of this module. + * @reg: The control registers for this PLL module. + */ +typedef struct NPCM7xxClockPLLState { + DeviceState parent; + + const char *name; + NPCM7xxCLKState *clk; + Clock *clock_in; + Clock *clock_out; + + int reg; +} NPCM7xxClockPLLState; + +/** + * struct NPCM7xxClockSELState - A SEL module in CLK module. + * @name: The name of the module. + * @clk: The CLK module that owns this module. + * @input_size: The size of inputs of this module. + * @clock_in: The input clocks of this module. + * @clock_out: The output clocks of this module. + * @offset: The offset of this module in the control register. + * @len: The length of this module in the control register. + */ +typedef struct NPCM7xxClockSELState { + DeviceState parent; + + const char *name; + NPCM7xxCLKState *clk; + uint8_t input_size; + Clock *clock_in[NPCM7XX_CLK_SEL_MAX_INPUT]; + Clock *clock_out; + + int offset; + int len; +} NPCM7xxClockSELState; + +/** + * struct NPCM7xxClockDividerState - A Divider module in CLK module. + * @name: The name of the module. + * @clk: The CLK module that owns this module. + * @clock_in: The input clock of this module. + * @clock_out: The output clock of this module. + * @divide: The function the divider uses to divide the input. + * @reg: The index of the control register that contains the divisor. + * @offset: The offset of the divisor in the control register. + * @len: The length of the divisor in the control register. + * @divisor: The divisor for a constant divisor + */ +typedef struct NPCM7xxClockDividerState { + DeviceState parent; + + const char *name; + NPCM7xxCLKState *clk; + Clock *clock_in; + Clock *clock_out; + + uint32_t (*divide)(struct NPCM7xxClockDividerState *s); + union { + struct { + int reg; + int offset; + int len; + }; + int divisor; + }; +} NPCM7xxClockDividerState; + +struct NPCM7xxCLKState { SysBusDevice parent; MemoryRegion iomem; + /* Clock converters */ + NPCM7xxClockPLLState plls[NPCM7XX_CLOCK_NR_PLLS]; + NPCM7xxClockSELState sels[NPCM7XX_CLOCK_NR_SELS]; + NPCM7xxClockDividerState dividers[NPCM7XX_CLOCK_NR_DIVIDERS]; + uint32_t regs[NPCM7XX_CLK_NR_REGS]; /* Time reference for SECCNT and CNTR25M, initialized by power on reset */ int64_t ref_ns; -} NPCM7xxCLKState; + + /* The incoming reference clock. */ + Clock *clkref; +}; #define TYPE_NPCM7XX_CLK "npcm7xx-clk" #define NPCM7XX_CLK(obj) OBJECT_CHECK(NPCM7xxCLKState, (obj), TYPE_NPCM7XX_CLK) diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_clk.c +++ b/hw/misc/npcm7xx_clk.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/npcm7xx_clk.h" #include "hw/timer/npcm7xx_timer.h" +#include "hw/qdev-clock.h" #include "migration/vmstate.h" #include "qemu/error-report.h" #include "qemu/log.h" @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include "sysemu/watchdog.h" +/* + * The reference clock hz, and the SECCNT and CNTR25M registers in this module, + * is always 25 MHz. + */ +#define NPCM7XX_CLOCK_REF_HZ (25000000) + +/* Register Field Definitions */ +#define NPCM7XX_CLK_WDRCR_CA9C BIT(0) /* Cortex A9 Cores */ + #define PLLCON_LOKI BIT(31) #define PLLCON_LOKS BIT(30) #define PLLCON_PWDEN BIT(12) +#define PLLCON_FBDV(con) extract32((con), 16, 12) +#define PLLCON_OTDV2(con) extract32((con), 13, 3) +#define PLLCON_OTDV1(con) extract32((con), 8, 3) +#define PLLCON_INDV(con) extract32((con), 0, 6) enum NPCM7xxCLKRegisters { NPCM7XX_CLK_CLKEN1, @@ -XXX,XX +XXX,XX @@ static const uint32_t cold_reset_values[NPCM7XX_CLK_NR_REGS] = { [NPCM7XX_CLK_AHBCKFI] = 0x000000c8, }; -/* Register Field Definitions */ -#define NPCM7XX_CLK_WDRCR_CA9C BIT(0) /* Cortex A9 Cores */ - /* The number of watchdogs that can trigger a reset. */ #define NPCM7XX_NR_WATCHDOGS (3) +/* Clock converter functions */ + +#define TYPE_NPCM7XX_CLOCK_PLL "npcm7xx-clock-pll" +#define NPCM7XX_CLOCK_PLL(obj) OBJECT_CHECK(NPCM7xxClockPLLState, \ + (obj), TYPE_NPCM7XX_CLOCK_PLL) +#define TYPE_NPCM7XX_CLOCK_SEL "npcm7xx-clock-sel" +#define NPCM7XX_CLOCK_SEL(obj) OBJECT_CHECK(NPCM7xxClockSELState, \ + (obj), TYPE_NPCM7XX_CLOCK_SEL) +#define TYPE_NPCM7XX_CLOCK_DIVIDER "npcm7xx-clock-divider" +#define NPCM7XX_CLOCK_DIVIDER(obj) OBJECT_CHECK(NPCM7xxClockDividerState, \ + (obj), TYPE_NPCM7XX_CLOCK_DIVIDER) + +static void npcm7xx_clk_update_pll(void *opaque) +{ + NPCM7xxClockPLLState *s = opaque; + uint32_t con = s->clk->regs[s->reg]; + uint64_t freq; + + /* The PLL is grounded if it is not locked yet. */ + if (con & PLLCON_LOKI) { + freq = clock_get_hz(s->clock_in); + freq *= PLLCON_FBDV(con); + freq /= PLLCON_INDV(con) * PLLCON_OTDV1(con) * PLLCON_OTDV2(con); + } else { + freq = 0; + } + + clock_update_hz(s->clock_out, freq); +} + +static void npcm7xx_clk_update_sel(void *opaque) +{ + NPCM7xxClockSELState *s = opaque; + uint32_t index = extract32(s->clk->regs[NPCM7XX_CLK_CLKSEL], s->offset, + s->len); + + if (index >= s->input_size) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: SEL index: %u out of range\n", + __func__, index); + index = 0; + } + clock_update_hz(s->clock_out, clock_get_hz(s->clock_in[index])); +} + +static void npcm7xx_clk_update_divider(void *opaque) +{ + NPCM7xxClockDividerState *s = opaque; + uint32_t freq; + + freq = s->divide(s); + clock_update_hz(s->clock_out, freq); +} + +static uint32_t divide_by_constant(NPCM7xxClockDividerState *s) +{ + return clock_get_hz(s->clock_in) / s->divisor; +} + +static uint32_t divide_by_reg_divisor(NPCM7xxClockDividerState *s) +{ + return clock_get_hz(s->clock_in) / + (extract32(s->clk->regs[s->reg], s->offset, s->len) + 1); +} + +static uint32_t divide_by_reg_divisor_times_2(NPCM7xxClockDividerState *s) +{ + return divide_by_reg_divisor(s) / 2; +} + +static uint32_t shift_by_reg_divisor(NPCM7xxClockDividerState *s) +{ + return clock_get_hz(s->clock_in) >> + extract32(s->clk->regs[s->reg], s->offset, s->len); +} + +static NPCM7xxClockPLL find_pll_by_reg(enum NPCM7xxCLKRegisters reg) +{ + switch (reg) { + case NPCM7XX_CLK_PLLCON0: + return NPCM7XX_CLOCK_PLL0; + case NPCM7XX_CLK_PLLCON1: + return NPCM7XX_CLOCK_PLL1; + case NPCM7XX_CLK_PLLCON2: + return NPCM7XX_CLOCK_PLL2; + case NPCM7XX_CLK_PLLCONG: + return NPCM7XX_CLOCK_PLLG; + default: + g_assert_not_reached(); + } +} + +static void npcm7xx_clk_update_all_plls(NPCM7xxCLKState *clk) +{ + int i; + + for (i = 0; i < NPCM7XX_CLOCK_NR_PLLS; ++i) { + npcm7xx_clk_update_pll(&clk->plls[i]); + } +} + +static void npcm7xx_clk_update_all_sels(NPCM7xxCLKState *clk) +{ + int i; + + for (i = 0; i < NPCM7XX_CLOCK_NR_SELS; ++i) { + npcm7xx_clk_update_sel(&clk->sels[i]); + } +} + +static void npcm7xx_clk_update_all_dividers(NPCM7xxCLKState *clk) +{ + int i; + + for (i = 0; i < NPCM7XX_CLOCK_NR_DIVIDERS; ++i) { + npcm7xx_clk_update_divider(&clk->dividers[i]); + } +} + +static void npcm7xx_clk_update_all_clocks(NPCM7xxCLKState *clk) +{ + clock_update_hz(clk->clkref, NPCM7XX_CLOCK_REF_HZ); + npcm7xx_clk_update_all_plls(clk); + npcm7xx_clk_update_all_sels(clk); + npcm7xx_clk_update_all_dividers(clk); +} + +/* Types of clock sources. */ +typedef enum ClockSrcType { + CLKSRC_REF, + CLKSRC_PLL, + CLKSRC_SEL, + CLKSRC_DIV, +} ClockSrcType; + +typedef struct PLLInitInfo { + const char *name; + ClockSrcType src_type; + int src_index; + int reg; + const char *public_name; +} PLLInitInfo; + +typedef struct SELInitInfo { + const char *name; + uint8_t input_size; + ClockSrcType src_type[NPCM7XX_CLK_SEL_MAX_INPUT]; + int src_index[NPCM7XX_CLK_SEL_MAX_INPUT]; + int offset; + int len; + const char *public_name; +} SELInitInfo; + +typedef struct DividerInitInfo { + const char *name; + ClockSrcType src_type; + int src_index; + uint32_t (*divide)(NPCM7xxClockDividerState *s); + int reg; /* not used when type == CONSTANT */ + int offset; /* not used when type == CONSTANT */ + int len; /* not used when type == CONSTANT */ + int divisor; /* used only when type == CONSTANT */ + const char *public_name; +} DividerInitInfo; + +static const PLLInitInfo pll_init_info_list[] = { + [NPCM7XX_CLOCK_PLL0] = { + .name = "pll0", + .src_type = CLKSRC_REF, + .reg = NPCM7XX_CLK_PLLCON0, + }, + [NPCM7XX_CLOCK_PLL1] = { + .name = "pll1", + .src_type = CLKSRC_REF, + .reg = NPCM7XX_CLK_PLLCON1, + }, + [NPCM7XX_CLOCK_PLL2] = { + .name = "pll2", + .src_type = CLKSRC_REF, + .reg = NPCM7XX_CLK_PLLCON2, + }, + [NPCM7XX_CLOCK_PLLG] = { + .name = "pllg", + .src_type = CLKSRC_REF, + .reg = NPCM7XX_CLK_PLLCONG, + }, +}; + +static const SELInitInfo sel_init_info_list[] = { + [NPCM7XX_CLOCK_PIXCKSEL] = { + .name = "pixcksel", + .input_size = 2, + .src_type = {CLKSRC_PLL, CLKSRC_REF}, + .src_index = {NPCM7XX_CLOCK_PLLG, 0}, + .offset = 5, + .len = 1, + .public_name = "pixel-clock", + }, + [NPCM7XX_CLOCK_MCCKSEL] = { + .name = "mccksel", + .input_size = 4, + .src_type = {CLKSRC_DIV, CLKSRC_REF, CLKSRC_REF, + /*MCBPCK, shouldn't be used in normal operation*/ + CLKSRC_REF}, + .src_index = {NPCM7XX_CLOCK_PLL1D2, 0, 0, 0}, + .offset = 12, + .len = 2, + .public_name = "mc-phy-clock", + }, + [NPCM7XX_CLOCK_CPUCKSEL] = { + .name = "cpucksel", + .input_size = 4, + .src_type = {CLKSRC_PLL, CLKSRC_DIV, CLKSRC_REF, + /*SYSBPCK, shouldn't be used in normal operation*/ + CLKSRC_REF}, + .src_index = {NPCM7XX_CLOCK_PLL0, NPCM7XX_CLOCK_PLL1D2, 0, 0}, + .offset = 0, + .len = 2, + .public_name = "system-clock", + }, + [NPCM7XX_CLOCK_CLKOUTSEL] = { + .name = "clkoutsel", + .input_size = 5, + .src_type = {CLKSRC_PLL, CLKSRC_DIV, CLKSRC_REF, + CLKSRC_PLL, CLKSRC_DIV}, + .src_index = {NPCM7XX_CLOCK_PLL0, NPCM7XX_CLOCK_PLL1D2, 0, + NPCM7XX_CLOCK_PLLG, NPCM7XX_CLOCK_PLL2D2}, + .offset = 18, + .len = 3, + .public_name = "tock", + }, + [NPCM7XX_CLOCK_UARTCKSEL] = { + .name = "uartcksel", + .input_size = 4, + .src_type = {CLKSRC_PLL, CLKSRC_DIV, CLKSRC_REF, CLKSRC_DIV}, + .src_index = {NPCM7XX_CLOCK_PLL0, NPCM7XX_CLOCK_PLL1D2, 0, + NPCM7XX_CLOCK_PLL2D2}, + .offset = 8, + .len = 2, + }, + [NPCM7XX_CLOCK_TIMCKSEL] = { + .name = "timcksel", + .input_size = 4, + .src_type = {CLKSRC_PLL, CLKSRC_DIV, CLKSRC_REF, CLKSRC_DIV}, + .src_index = {NPCM7XX_CLOCK_PLL0, NPCM7XX_CLOCK_PLL1D2, 0, + NPCM7XX_CLOCK_PLL2D2}, + .offset = 14, + .len = 2, + }, + [NPCM7XX_CLOCK_SDCKSEL] = { + .name = "sdcksel", + .input_size = 4, + .src_type = {CLKSRC_PLL, CLKSRC_DIV, CLKSRC_REF, CLKSRC_DIV}, + .src_index = {NPCM7XX_CLOCK_PLL0, NPCM7XX_CLOCK_PLL1D2, 0, + NPCM7XX_CLOCK_PLL2D2}, + .offset = 6, + .len = 2, + }, + [NPCM7XX_CLOCK_GFXMSEL] = { + .name = "gfxmksel", + .input_size = 2, + .src_type = {CLKSRC_REF, CLKSRC_PLL}, + .src_index = {0, NPCM7XX_CLOCK_PLL2}, + .offset = 21, + .len = 1, + }, + [NPCM7XX_CLOCK_SUCKSEL] = { + .name = "sucksel", + .input_size = 4, + .src_type = {CLKSRC_PLL, CLKSRC_DIV, CLKSRC_REF, CLKSRC_DIV}, + .src_index = {NPCM7XX_CLOCK_PLL0, NPCM7XX_CLOCK_PLL1D2, 0, + NPCM7XX_CLOCK_PLL2D2}, + .offset = 10, + .len = 2, + }, +}; + +static const DividerInitInfo divider_init_info_list[] = { + [NPCM7XX_CLOCK_PLL1D2] = { + .name = "pll1d2", + .src_type = CLKSRC_PLL, + .src_index = NPCM7XX_CLOCK_PLL1, + .divide = divide_by_constant, + .divisor = 2, + }, + [NPCM7XX_CLOCK_PLL2D2] = { + .name = "pll2d2", + .src_type = CLKSRC_PLL, + .src_index = NPCM7XX_CLOCK_PLL2, + .divide = divide_by_constant, + .divisor = 2, + }, + [NPCM7XX_CLOCK_MC_DIVIDER] = { + .name = "mc-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_MCCKSEL, + .divide = divide_by_constant, + .divisor = 2, + .public_name = "mc-clock" + }, + [NPCM7XX_CLOCK_AXI_DIVIDER] = { + .name = "axi-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_CPUCKSEL, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 0, + .len = 1, + .public_name = "clk2" + }, + [NPCM7XX_CLOCK_AHB_DIVIDER] = { + .name = "ahb-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AXI_DIVIDER, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 26, + .len = 2, + .public_name = "clk4" + }, + [NPCM7XX_CLOCK_AHB3_DIVIDER] = { + .name = "ahb3-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 6, + .len = 5, + .public_name = "ahb3-spi3-clock" + }, + [NPCM7XX_CLOCK_SPI0_DIVIDER] = { + .name = "spi0-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV3, + .offset = 6, + .len = 5, + .public_name = "spi0-clock", + }, + [NPCM7XX_CLOCK_SPIX_DIVIDER] = { + .name = "spix-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV3, + .offset = 1, + .len = 5, + .public_name = "spix-clock", + }, + [NPCM7XX_CLOCK_APB1_DIVIDER] = { + .name = "apb1-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 24, + .len = 2, + .public_name = "apb1-clock", + }, + [NPCM7XX_CLOCK_APB2_DIVIDER] = { + .name = "apb2-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 26, + .len = 2, + .public_name = "apb2-clock", + }, + [NPCM7XX_CLOCK_APB3_DIVIDER] = { + .name = "apb3-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 28, + .len = 2, + .public_name = "apb3-clock", + }, + [NPCM7XX_CLOCK_APB4_DIVIDER] = { + .name = "apb4-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 30, + .len = 2, + .public_name = "apb4-clock", + }, + [NPCM7XX_CLOCK_APB5_DIVIDER] = { + .name = "apb5-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_AHB_DIVIDER, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 22, + .len = 2, + .public_name = "apb5-clock", + }, + [NPCM7XX_CLOCK_CLKOUT_DIVIDER] = { + .name = "clkout-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_CLKOUTSEL, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 16, + .len = 5, + .public_name = "clkout", + }, + [NPCM7XX_CLOCK_UART_DIVIDER] = { + .name = "uart-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_UARTCKSEL, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 16, + .len = 5, + .public_name = "uart-clock", + }, + [NPCM7XX_CLOCK_TIMER_DIVIDER] = { + .name = "timer-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_TIMCKSEL, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 21, + .len = 5, + .public_name = "timer-clock", + }, + [NPCM7XX_CLOCK_ADC_DIVIDER] = { + .name = "adc-divider", + .src_type = CLKSRC_DIV, + .src_index = NPCM7XX_CLOCK_TIMER_DIVIDER, + .divide = shift_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 28, + .len = 3, + .public_name = "adc-clock", + }, + [NPCM7XX_CLOCK_MMC_DIVIDER] = { + .name = "mmc-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_SDCKSEL, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV1, + .offset = 11, + .len = 5, + .public_name = "mmc-clock", + }, + [NPCM7XX_CLOCK_SDHC_DIVIDER] = { + .name = "sdhc-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_SDCKSEL, + .divide = divide_by_reg_divisor_times_2, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 0, + .len = 4, + .public_name = "sdhc-clock", + }, + [NPCM7XX_CLOCK_GFXM_DIVIDER] = { + .name = "gfxm-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_GFXMSEL, + .divide = divide_by_constant, + .divisor = 3, + .public_name = "gfxm-clock", + }, + [NPCM7XX_CLOCK_UTMI_DIVIDER] = { + .name = "utmi-divider", + .src_type = CLKSRC_SEL, + .src_index = NPCM7XX_CLOCK_SUCKSEL, + .divide = divide_by_reg_divisor, + .reg = NPCM7XX_CLK_CLKDIV2, + .offset = 8, + .len = 5, + .public_name = "utmi-clock", + }, +}; + +static void npcm7xx_clk_pll_init(Object *obj) +{ + NPCM7xxClockPLLState *pll = NPCM7XX_CLOCK_PLL(obj); + + pll->clock_in = qdev_init_clock_in(DEVICE(pll), "clock-in", + npcm7xx_clk_update_pll, pll); + pll->clock_out = qdev_init_clock_out(DEVICE(pll), "clock-out"); +} + +static void npcm7xx_clk_sel_init(Object *obj) +{ + int i; + NPCM7xxClockSELState *sel = NPCM7XX_CLOCK_SEL(obj); + + for (i = 0; i < NPCM7XX_CLK_SEL_MAX_INPUT; ++i) { + sel->clock_in[i] = qdev_init_clock_in(DEVICE(sel), + g_strdup_printf("clock-in[%d]", i), + npcm7xx_clk_update_sel, sel); + } + sel->clock_out = qdev_init_clock_out(DEVICE(sel), "clock-out"); +} +static void npcm7xx_clk_divider_init(Object *obj) +{ + NPCM7xxClockDividerState *div = NPCM7XX_CLOCK_DIVIDER(obj); + + div->clock_in = qdev_init_clock_in(DEVICE(div), "clock-in", + npcm7xx_clk_update_divider, div); + div->clock_out = qdev_init_clock_out(DEVICE(div), "clock-out"); +} + +static void npcm7xx_init_clock_pll(NPCM7xxClockPLLState *pll, + NPCM7xxCLKState *clk, const PLLInitInfo *init_info) +{ + pll->name = init_info->name; + pll->clk = clk; + pll->reg = init_info->reg; + if (init_info->public_name != NULL) { + qdev_alias_clock(DEVICE(pll), "clock-out", DEVICE(clk), + init_info->public_name); + } +} + +static void npcm7xx_init_clock_sel(NPCM7xxClockSELState *sel, + NPCM7xxCLKState *clk, const SELInitInfo *init_info) +{ + int input_size = init_info->input_size; + + sel->name = init_info->name; + sel->clk = clk; + sel->input_size = init_info->input_size; + g_assert(input_size <= NPCM7XX_CLK_SEL_MAX_INPUT); + sel->offset = init_info->offset; + sel->len = init_info->len; + if (init_info->public_name != NULL) { + qdev_alias_clock(DEVICE(sel), "clock-out", DEVICE(clk), + init_info->public_name); + } +} + +static void npcm7xx_init_clock_divider(NPCM7xxClockDividerState *div, + NPCM7xxCLKState *clk, const DividerInitInfo *init_info) +{ + div->name = init_info->name; + div->clk = clk; + + div->divide = init_info->divide; + if (div->divide == divide_by_constant) { + div->divisor = init_info->divisor; + } else { + div->reg = init_info->reg; + div->offset = init_info->offset; + div->len = init_info->len; + } + if (init_info->public_name != NULL) { + qdev_alias_clock(DEVICE(div), "clock-out", DEVICE(clk), + init_info->public_name); + } +} + +static Clock *npcm7xx_get_clock(NPCM7xxCLKState *clk, ClockSrcType type, + int index) +{ + switch (type) { + case CLKSRC_REF: + return clk->clkref; + case CLKSRC_PLL: + return clk->plls[index].clock_out; + case CLKSRC_SEL: + return clk->sels[index].clock_out; + case CLKSRC_DIV: + return clk->dividers[index].clock_out; + default: + g_assert_not_reached(); + } +} + +static void npcm7xx_connect_clocks(NPCM7xxCLKState *clk) +{ + int i, j; + Clock *src; + + for (i = 0; i < NPCM7XX_CLOCK_NR_PLLS; ++i) { + src = npcm7xx_get_clock(clk, pll_init_info_list[i].src_type, + pll_init_info_list[i].src_index); + clock_set_source(clk->plls[i].clock_in, src); + } + for (i = 0; i < NPCM7XX_CLOCK_NR_SELS; ++i) { + for (j = 0; j < sel_init_info_list[i].input_size; ++j) { + src = npcm7xx_get_clock(clk, sel_init_info_list[i].src_type[j], + sel_init_info_list[i].src_index[j]); + clock_set_source(clk->sels[i].clock_in[j], src); + } + } + for (i = 0; i < NPCM7XX_CLOCK_NR_DIVIDERS; ++i) { + src = npcm7xx_get_clock(clk, divider_init_info_list[i].src_type, + divider_init_info_list[i].src_index); + clock_set_source(clk->dividers[i].clock_in, src); + } +} + static uint64_t npcm7xx_clk_read(void *opaque, hwaddr offset, unsigned size) { uint32_t reg = offset / sizeof(uint32_t); @@ -XXX,XX +XXX,XX @@ static uint64_t npcm7xx_clk_read(void *opaque, hwaddr offset, unsigned size) * * The 4 LSBs are always zero: (1e9 / 640) << 4 = 25000000. */ - value = (((now_ns - s->ref_ns) / 640) << 4) % NPCM7XX_TIMER_REF_HZ; + value = (((now_ns - s->ref_ns) / 640) << 4) % NPCM7XX_CLOCK_REF_HZ; break; default: @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_write(void *opaque, hwaddr offset, value |= (value & PLLCON_LOKS); } } + /* Only update PLL when it is locked. */ + if (value & PLLCON_LOKI) { + npcm7xx_clk_update_pll(&s->plls[find_pll_by_reg(reg)]); + } + break; + + case NPCM7XX_CLK_CLKSEL: + npcm7xx_clk_update_all_sels(s); + break; + + case NPCM7XX_CLK_CLKDIV1: + case NPCM7XX_CLK_CLKDIV2: + case NPCM7XX_CLK_CLKDIV3: + npcm7xx_clk_update_all_dividers(s); break; case NPCM7XX_CLK_CNTR25M: @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_enter_reset(Object *obj, ResetType type) case RESET_TYPE_COLD: memcpy(s->regs, cold_reset_values, sizeof(cold_reset_values)); s->ref_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + npcm7xx_clk_update_all_clocks(s); return; } @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_enter_reset(Object *obj, ResetType type) __func__, type); } +static void npcm7xx_clk_init_clock_hierarchy(NPCM7xxCLKState *s) +{ + int i; + + s->clkref = qdev_init_clock_in(DEVICE(s), "clkref", NULL, NULL); + + /* First pass: init all converter modules */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(pll_init_info_list) != NPCM7XX_CLOCK_NR_PLLS); + QEMU_BUILD_BUG_ON(ARRAY_SIZE(sel_init_info_list) != NPCM7XX_CLOCK_NR_SELS); + QEMU_BUILD_BUG_ON(ARRAY_SIZE(divider_init_info_list) + != NPCM7XX_CLOCK_NR_DIVIDERS); + for (i = 0; i < NPCM7XX_CLOCK_NR_PLLS; ++i) { + object_initialize_child(OBJECT(s), pll_init_info_list[i].name, + &s->plls[i], TYPE_NPCM7XX_CLOCK_PLL); + npcm7xx_init_clock_pll(&s->plls[i], s, + &pll_init_info_list[i]); + } + for (i = 0; i < NPCM7XX_CLOCK_NR_SELS; ++i) { + object_initialize_child(OBJECT(s), sel_init_info_list[i].name, + &s->sels[i], TYPE_NPCM7XX_CLOCK_SEL); + npcm7xx_init_clock_sel(&s->sels[i], s, + &sel_init_info_list[i]); + } + for (i = 0; i < NPCM7XX_CLOCK_NR_DIVIDERS; ++i) { + object_initialize_child(OBJECT(s), divider_init_info_list[i].name, + &s->dividers[i], TYPE_NPCM7XX_CLOCK_DIVIDER); + npcm7xx_init_clock_divider(&s->dividers[i], s, + &divider_init_info_list[i]); + } + + /* Second pass: connect converter modules */ + npcm7xx_connect_clocks(s); + + clock_update_hz(s->clkref, NPCM7XX_CLOCK_REF_HZ); +} + static void npcm7xx_clk_init(Object *obj) { NPCM7xxCLKState *s = NPCM7XX_CLK(obj); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_init(Object *obj) memory_region_init_io(&s->iomem, obj, &npcm7xx_clk_ops, s, TYPE_NPCM7XX_CLK, 4 * KiB); sysbus_init_mmio(&s->parent, &s->iomem); - qdev_init_gpio_in_named(DEVICE(s), npcm7xx_clk_perform_watchdog_reset, - NPCM7XX_WATCHDOG_RESET_GPIO_IN, NPCM7XX_NR_WATCHDOGS); } -static const VMStateDescription vmstate_npcm7xx_clk = { - .name = "npcm7xx-clk", +static int npcm7xx_clk_post_load(void *opaque, int version_id) +{ + if (version_id >= 1) { + NPCM7xxCLKState *clk = opaque; + + npcm7xx_clk_update_all_clocks(clk); + } + + return 0; +} + +static void npcm7xx_clk_realize(DeviceState *dev, Error **errp) +{ + int i; + NPCM7xxCLKState *s = NPCM7XX_CLK(dev); + + qdev_init_gpio_in_named(DEVICE(s), npcm7xx_clk_perform_watchdog_reset, + NPCM7XX_WATCHDOG_RESET_GPIO_IN, NPCM7XX_NR_WATCHDOGS); + npcm7xx_clk_init_clock_hierarchy(s); + + /* Realize child devices */ + for (i = 0; i < NPCM7XX_CLOCK_NR_PLLS; ++i) { + if (!qdev_realize(DEVICE(&s->plls[i]), NULL, errp)) { + return; + } + } + for (i = 0; i < NPCM7XX_CLOCK_NR_SELS; ++i) { + if (!qdev_realize(DEVICE(&s->sels[i]), NULL, errp)) { + return; + } + } + for (i = 0; i < NPCM7XX_CLOCK_NR_DIVIDERS; ++i) { + if (!qdev_realize(DEVICE(&s->dividers[i]), NULL, errp)) { + return; + } + } +} + +static const VMStateDescription vmstate_npcm7xx_clk_pll = { + .name = "npcm7xx-clock-pll", .version_id = 0, .minimum_version_id = 0, - .fields = (VMStateField[]) { - VMSTATE_UINT32_ARRAY(regs, NPCM7xxCLKState, NPCM7XX_CLK_NR_REGS), - VMSTATE_INT64(ref_ns, NPCM7xxCLKState), + .fields = (VMStateField[]) { + VMSTATE_CLOCK(clock_in, NPCM7xxClockPLLState), VMSTATE_END_OF_LIST(), }, }; +static const VMStateDescription vmstate_npcm7xx_clk_sel = { + .name = "npcm7xx-clock-sel", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_ARRAY_OF_POINTER_TO_STRUCT(clock_in, NPCM7xxClockSELState, + NPCM7XX_CLK_SEL_MAX_INPUT, 0, vmstate_clock, Clock), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_npcm7xx_clk_divider = { + .name = "npcm7xx-clock-divider", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_CLOCK(clock_in, NPCM7xxClockDividerState), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_npcm7xx_clk = { + .name = "npcm7xx-clk", + .version_id = 1, + .minimum_version_id = 1, + .post_load = npcm7xx_clk_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxCLKState, NPCM7XX_CLK_NR_REGS), + VMSTATE_INT64(ref_ns, NPCM7xxCLKState), + VMSTATE_CLOCK(clkref, NPCM7xxCLKState), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_clk_pll_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx Clock PLL Module"; + dc->vmsd = &vmstate_npcm7xx_clk_pll; +} + +static void npcm7xx_clk_sel_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx Clock SEL Module"; + dc->vmsd = &vmstate_npcm7xx_clk_sel; +} + +static void npcm7xx_clk_divider_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx Clock Divider Module"; + dc->vmsd = &vmstate_npcm7xx_clk_divider; +} + static void npcm7xx_clk_class_init(ObjectClass *klass, void *data) { ResettableClass *rc = RESETTABLE_CLASS(klass); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_class_init(ObjectClass *klass, void *data) dc->desc = "NPCM7xx Clock Control Registers"; dc->vmsd = &vmstate_npcm7xx_clk; + dc->realize = npcm7xx_clk_realize; rc->phases.enter = npcm7xx_clk_enter_reset; } +static const TypeInfo npcm7xx_clk_pll_info = { + .name = TYPE_NPCM7XX_CLOCK_PLL, + .parent = TYPE_DEVICE, + .instance_size = sizeof(NPCM7xxClockPLLState), + .instance_init = npcm7xx_clk_pll_init, + .class_init = npcm7xx_clk_pll_class_init, +}; + +static const TypeInfo npcm7xx_clk_sel_info = { + .name = TYPE_NPCM7XX_CLOCK_SEL, + .parent = TYPE_DEVICE, + .instance_size = sizeof(NPCM7xxClockSELState), + .instance_init = npcm7xx_clk_sel_init, + .class_init = npcm7xx_clk_sel_class_init, +}; + +static const TypeInfo npcm7xx_clk_divider_info = { + .name = TYPE_NPCM7XX_CLOCK_DIVIDER, + .parent = TYPE_DEVICE, + .instance_size = sizeof(NPCM7xxClockDividerState), + .instance_init = npcm7xx_clk_divider_init, + .class_init = npcm7xx_clk_divider_class_init, +}; + static const TypeInfo npcm7xx_clk_info = { .name = TYPE_NPCM7XX_CLK, .parent = TYPE_SYS_BUS_DEVICE, @@ -XXX,XX +XXX,XX @@ static const TypeInfo npcm7xx_clk_info = { static void npcm7xx_clk_register_type(void) { + type_register_static(&npcm7xx_clk_pll_info); + type_register_static(&npcm7xx_clk_sel_info); + type_register_static(&npcm7xx_clk_divider_info); type_register_static(&npcm7xx_clk_info); } type_init(npcm7xx_clk_register_type); -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch makes NPCM7XX Timer to use a the timer clock generated by the CLK module instead of the magic number TIMER_REF_HZ. Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210108190945.949196-3-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_clk.h | 6 ----- include/hw/timer/npcm7xx_timer.h | 1 + hw/arm/npcm7xx.c | 5 ++++ hw/timer/npcm7xx_timer.c | 39 +++++++++++++++----------------- 4 files changed, 24 insertions(+), 27 deletions(-) diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_clk.h +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ #include "hw/clock.h" #include "hw/sysbus.h" -/* - * The reference clock frequency for the timer modules, and the SECCNT and - * CNTR25M registers in this module, is always 25 MHz. - */ -#define NPCM7XX_TIMER_REF_HZ (25000000) - /* * Number of registers in our device state structure. Don't change this without * incrementing the version_id in the vmstate. diff --git a/include/hw/timer/npcm7xx_timer.h b/include/hw/timer/npcm7xx_timer.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/npcm7xx_timer.h +++ b/include/hw/timer/npcm7xx_timer.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxTimerCtrlState { uint32_t tisr; + Clock *clock; NPCM7xxTimer timer[NPCM7XX_TIMERS_PER_CTRL]; NPCM7xxWatchdogTimer watchdog_timer; }; diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/serial.h" #include "hw/loader.h" #include "hw/misc/unimp.h" +#include "hw/qdev-clock.h" #include "hw/qdev-properties.h" #include "qapi/error.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) int first_irq; int j; + /* Connect the timer clock. */ + qdev_connect_clock_in(DEVICE(&s->tim[i]), "clock", qdev_get_clock_out( + DEVICE(&s->clk), "timer-clock")); + sysbus_realize(sbd, &error_abort); sysbus_mmio_map(sbd, 0, npcm7xx_tim_addr[i]); diff --git a/hw/timer/npcm7xx_timer.c b/hw/timer/npcm7xx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/npcm7xx_timer.c +++ b/hw/timer/npcm7xx_timer.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "hw/irq.h" +#include "hw/qdev-clock.h" #include "hw/qdev-properties.h" -#include "hw/misc/npcm7xx_clk.h" #include "hw/timer/npcm7xx_timer.h" #include "migration/vmstate.h" #include "qemu/bitops.h" @@ -XXX,XX +XXX,XX @@ static uint32_t npcm7xx_tcsr_prescaler(uint32_t tcsr) /* Convert a timer cycle count to a time interval in nanoseconds. */ static int64_t npcm7xx_timer_count_to_ns(NPCM7xxTimer *t, uint32_t count) { - int64_t ns = count; + int64_t ticks = count; - ns *= NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ; - ns *= npcm7xx_tcsr_prescaler(t->tcsr); + ticks *= npcm7xx_tcsr_prescaler(t->tcsr); - return ns; + return clock_ticks_to_ns(t->ctrl->clock, ticks); } /* Convert a time interval in nanoseconds to a timer cycle count. */ static uint32_t npcm7xx_timer_ns_to_count(NPCM7xxTimer *t, int64_t ns) { - int64_t count; - - count = ns / (NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ); - count /= npcm7xx_tcsr_prescaler(t->tcsr); - - return count; + return ns / clock_ticks_to_ns(t->ctrl->clock, + npcm7xx_tcsr_prescaler(t->tcsr)); } static uint32_t npcm7xx_watchdog_timer_prescaler(const NPCM7xxWatchdogTimer *t) @@ -XXX,XX +XXX,XX @@ static uint32_t npcm7xx_watchdog_timer_prescaler(const NPCM7xxWatchdogTimer *t) static void npcm7xx_watchdog_timer_reset_cycles(NPCM7xxWatchdogTimer *t, int64_t cycles) { - uint32_t prescaler = npcm7xx_watchdog_timer_prescaler(t); - int64_t ns = (NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ) * cycles; + int64_t ticks = cycles * npcm7xx_watchdog_timer_prescaler(t); + int64_t ns = clock_ticks_to_ns(t->ctrl->clock, ticks); /* * The reset function always clears the current timer. The caller of the @@ -XXX,XX +XXX,XX @@ static void npcm7xx_watchdog_timer_reset_cycles(NPCM7xxWatchdogTimer *t, */ npcm7xx_timer_clear(&t->base_timer); - ns *= prescaler; t->base_timer.remaining_ns = ns; } @@ -XXX,XX +XXX,XX @@ static void npcm7xx_timer_hold_reset(Object *obj) qemu_irq_lower(s->watchdog_timer.irq); } -static void npcm7xx_timer_realize(DeviceState *dev, Error **errp) +static void npcm7xx_timer_init(Object *obj) { - NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(dev); - SysBusDevice *sbd = &s->parent; + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(obj); + DeviceState *dev = DEVICE(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); int i; NPCM7xxWatchdogTimer *w; @@ -XXX,XX +XXX,XX @@ static void npcm7xx_timer_realize(DeviceState *dev, Error **errp) npcm7xx_watchdog_timer_expired, w); sysbus_init_irq(sbd, &w->irq); - memory_region_init_io(&s->iomem, OBJECT(s), &npcm7xx_timer_ops, s, + memory_region_init_io(&s->iomem, obj, &npcm7xx_timer_ops, s, TYPE_NPCM7XX_TIMER, 4 * KiB); sysbus_init_mmio(sbd, &s->iomem); qdev_init_gpio_out_named(dev, &w->reset_signal, NPCM7XX_WATCHDOG_RESET_GPIO_OUT, 1); + s->clock = qdev_init_clock_in(dev, "clock", NULL, NULL); } static const VMStateDescription vmstate_npcm7xx_base_timer = { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_npcm7xx_watchdog_timer = { static const VMStateDescription vmstate_npcm7xx_timer_ctrl = { .name = "npcm7xx-timer-ctrl", - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32(tisr, NPCM7xxTimerCtrlState), + VMSTATE_CLOCK(clock, NPCM7xxTimerCtrlState), VMSTATE_STRUCT_ARRAY(timer, NPCM7xxTimerCtrlState, NPCM7XX_TIMERS_PER_CTRL, 0, vmstate_npcm7xx_timer, NPCM7xxTimer), @@ -XXX,XX +XXX,XX @@ static void npcm7xx_timer_class_init(ObjectClass *klass, void *data) QEMU_BUILD_BUG_ON(NPCM7XX_TIMER_REGS_END > NPCM7XX_TIMER_NR_REGS); dc->desc = "NPCM7xx Timer Controller"; - dc->realize = npcm7xx_timer_realize; dc->vmsd = &vmstate_npcm7xx_timer_ctrl; rc->phases.enter = npcm7xx_timer_enter_reset; rc->phases.hold = npcm7xx_timer_hold_reset; @@ -XXX,XX +XXX,XX @@ static const TypeInfo npcm7xx_timer_info = { .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(NPCM7xxTimerCtrlState), .class_init = npcm7xx_timer_class_init, + .instance_init = npcm7xx_timer_init, }; static void npcm7xx_timer_register_type(void) -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> The ADC is part of NPCM7XX Module. Its behavior is controled by the ADC_CON register. It converts one of the eight analog inputs into a digital input and stores it in the ADC_DATA register when enabled. Users can alter input value by using qom-set QMP command. Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210108190945.949196-4-wuhaotsh@google.com [PMM: Added missing hw/adc/trace.h file] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 2 +- meson.build | 1 + hw/adc/trace.h | 1 + include/hw/adc/npcm7xx_adc.h | 69 ++++++ include/hw/arm/npcm7xx.h | 2 + hw/adc/npcm7xx_adc.c | 301 ++++++++++++++++++++++++++ hw/arm/npcm7xx.c | 24 ++- tests/qtest/npcm7xx_adc-test.c | 377 +++++++++++++++++++++++++++++++++ hw/adc/meson.build | 1 + hw/adc/trace-events | 5 + tests/qtest/meson.build | 3 +- 11 files changed, 783 insertions(+), 3 deletions(-) create mode 100644 hw/adc/trace.h create mode 100644 include/hw/adc/npcm7xx_adc.h create mode 100644 hw/adc/npcm7xx_adc.c create mode 100644 tests/qtest/npcm7xx_adc-test.c create mode 100644 hw/adc/trace-events diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ Supported devices * Random Number Generator (RNG) * USB host (USBH) * GPIO controller + * Analog to Digital Converter (ADC) Missing devices --------------- @@ -XXX,XX +XXX,XX @@ Missing devices * USB device (USBD) * SMBus controller (SMBF) * Peripheral SPI controller (PSPI) - * Analog to Digital Converter (ADC) * SD/MMC host * PECI interface * Pulse Width Modulation (PWM) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ if have_system 'chardev', 'hw/9pfs', 'hw/acpi', + 'hw/adc', 'hw/alpha', 'hw/arm', 'hw/audio', diff --git a/hw/adc/trace.h b/hw/adc/trace.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/adc/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_adc.h" diff --git a/include/hw/adc/npcm7xx_adc.h b/include/hw/adc/npcm7xx_adc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/adc/npcm7xx_adc.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx ADC Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_ADC_H +#define NPCM7XX_ADC_H + +#include "hw/clock.h" +#include "hw/irq.h" +#include "hw/sysbus.h" +#include "qemu/timer.h" + +#define NPCM7XX_ADC_NUM_INPUTS 8 +/** + * This value should not be changed unless write_adc_calibration function in + * hw/arm/npcm7xx.c is also changed. + */ +#define NPCM7XX_ADC_NUM_CALIB 2 + +/** + * struct NPCM7xxADCState - Analog to Digital Converter Module device state. + * @parent: System bus device. + * @iomem: Memory region through which registers are accessed. + * @conv_timer: The timer counts down remaining cycles for the conversion. + * @irq: GIC interrupt line to fire on expiration (if enabled). + * @con: The Control Register. + * @data: The Data Buffer. + * @clock: The ADC Clock. + * @adci: The input voltage in units of uV. 1uv = 1e-6V. + * @vref: The external reference voltage. + * @iref: The internal reference voltage, initialized at launch time. + * @rv: The calibrated output values of 0.5V and 1.5V for the ADC. + */ +typedef struct { + SysBusDevice parent; + + MemoryRegion iomem; + + QEMUTimer conv_timer; + + qemu_irq irq; + uint32_t con; + uint32_t data; + Clock *clock; + + /* Voltages are in unit of uV. 1V = 1000000uV. */ + uint32_t adci[NPCM7XX_ADC_NUM_INPUTS]; + uint32_t vref; + uint32_t iref; + + uint16_t calibration_r_values[NPCM7XX_ADC_NUM_CALIB]; +} NPCM7xxADCState; + +#define TYPE_NPCM7XX_ADC "npcm7xx-adc" +#define NPCM7XX_ADC(obj) \ + OBJECT_CHECK(NPCM7xxADCState, (obj), TYPE_NPCM7XX_ADC) + +#endif /* NPCM7XX_ADC_H */ diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_H #include "hw/boards.h" +#include "hw/adc/npcm7xx_adc.h" #include "hw/cpu/a9mpcore.h" #include "hw/gpio/npcm7xx_gpio.h" #include "hw/mem/npcm7xx_mc.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxGCRState gcr; NPCM7xxCLKState clk; NPCM7xxTimerCtrlState tim[3]; + NPCM7xxADCState adc; NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; NPCM7xxMCState mc; diff --git a/hw/adc/npcm7xx_adc.c b/hw/adc/npcm7xx_adc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/adc/npcm7xx_adc.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx ADC Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "hw/adc/npcm7xx_adc.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/registerfields.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qemu/units.h" +#include "trace.h" + +REG32(NPCM7XX_ADC_CON, 0x0) +REG32(NPCM7XX_ADC_DATA, 0x4) + +/* Register field definitions. */ +#define NPCM7XX_ADC_CON_MUX(rv) extract32(rv, 24, 4) +#define NPCM7XX_ADC_CON_INT_EN BIT(21) +#define NPCM7XX_ADC_CON_REFSEL BIT(19) +#define NPCM7XX_ADC_CON_INT BIT(18) +#define NPCM7XX_ADC_CON_EN BIT(17) +#define NPCM7XX_ADC_CON_RST BIT(16) +#define NPCM7XX_ADC_CON_CONV BIT(14) +#define NPCM7XX_ADC_CON_DIV(rv) extract32(rv, 1, 8) + +#define NPCM7XX_ADC_MAX_RESULT 1023 +#define NPCM7XX_ADC_DEFAULT_IREF 2000000 +#define NPCM7XX_ADC_CONV_CYCLES 20 +#define NPCM7XX_ADC_RESET_CYCLES 10 +#define NPCM7XX_ADC_R0_INPUT 500000 +#define NPCM7XX_ADC_R1_INPUT 1500000 + +static void npcm7xx_adc_reset(NPCM7xxADCState *s) +{ + timer_del(&s->conv_timer); + s->con = 0x000c0001; + s->data = 0x00000000; +} + +static uint32_t npcm7xx_adc_convert(uint32_t input, uint32_t ref) +{ + uint32_t result; + + result = input * (NPCM7XX_ADC_MAX_RESULT + 1) / ref; + if (result > NPCM7XX_ADC_MAX_RESULT) { + result = NPCM7XX_ADC_MAX_RESULT; + } + + return result; +} + +static uint32_t npcm7xx_adc_prescaler(NPCM7xxADCState *s) +{ + return 2 * (NPCM7XX_ADC_CON_DIV(s->con) + 1); +} + +static void npcm7xx_adc_start_timer(Clock *clk, QEMUTimer *timer, + uint32_t cycles, uint32_t prescaler) +{ + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + int64_t ticks = cycles; + int64_t ns; + + ticks *= prescaler; + ns = clock_ticks_to_ns(clk, ticks); + ns += now; + timer_mod(timer, ns); +} + +static void npcm7xx_adc_start_convert(NPCM7xxADCState *s) +{ + uint32_t prescaler = npcm7xx_adc_prescaler(s); + + npcm7xx_adc_start_timer(s->clock, &s->conv_timer, NPCM7XX_ADC_CONV_CYCLES, + prescaler); +} + +static void npcm7xx_adc_convert_done(void *opaque) +{ + NPCM7xxADCState *s = opaque; + uint32_t input = NPCM7XX_ADC_CON_MUX(s->con); + uint32_t ref = (s->con & NPCM7XX_ADC_CON_REFSEL) + ? s->iref : s->vref; + + if (input >= NPCM7XX_ADC_NUM_INPUTS) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid input: %u\n", + __func__, input); + return; + } + s->data = npcm7xx_adc_convert(s->adci[input], ref); + if (s->con & NPCM7XX_ADC_CON_INT_EN) { + s->con |= NPCM7XX_ADC_CON_INT; + qemu_irq_raise(s->irq); + } + s->con &= ~NPCM7XX_ADC_CON_CONV; +} + +static void npcm7xx_adc_calibrate(NPCM7xxADCState *adc) +{ + adc->calibration_r_values[0] = npcm7xx_adc_convert(NPCM7XX_ADC_R0_INPUT, + adc->iref); + adc->calibration_r_values[1] = npcm7xx_adc_convert(NPCM7XX_ADC_R1_INPUT, + adc->iref); +} + +static void npcm7xx_adc_write_con(NPCM7xxADCState *s, uint32_t new_con) +{ + uint32_t old_con = s->con; + + /* Write ADC_INT to 1 to clear it */ + if (new_con & NPCM7XX_ADC_CON_INT) { + new_con &= ~NPCM7XX_ADC_CON_INT; + qemu_irq_lower(s->irq); + } else if (old_con & NPCM7XX_ADC_CON_INT) { + new_con |= NPCM7XX_ADC_CON_INT; + } + + s->con = new_con; + + if (s->con & NPCM7XX_ADC_CON_RST) { + npcm7xx_adc_reset(s); + return; + } + + if ((s->con & NPCM7XX_ADC_CON_EN)) { + if (s->con & NPCM7XX_ADC_CON_CONV) { + if (!(old_con & NPCM7XX_ADC_CON_CONV)) { + npcm7xx_adc_start_convert(s); + } + } else { + timer_del(&s->conv_timer); + } + } +} + +static uint64_t npcm7xx_adc_read(void *opaque, hwaddr offset, unsigned size) +{ + uint64_t value = 0; + NPCM7xxADCState *s = opaque; + + switch (offset) { + case A_NPCM7XX_ADC_CON: + value = s->con; + break; + + case A_NPCM7XX_ADC_DATA: + value = s->data; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + break; + } + + trace_npcm7xx_adc_read(DEVICE(s)->canonical_path, offset, value); + return value; +} + +static void npcm7xx_adc_write(void *opaque, hwaddr offset, uint64_t v, + unsigned size) +{ + NPCM7xxADCState *s = opaque; + + trace_npcm7xx_adc_write(DEVICE(s)->canonical_path, offset, v); + switch (offset) { + case A_NPCM7XX_ADC_CON: + npcm7xx_adc_write_con(s, v); + break; + + case A_NPCM7XX_ADC_DATA: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + break; + } + +} + +static const struct MemoryRegionOps npcm7xx_adc_ops = { + .read = npcm7xx_adc_read, + .write = npcm7xx_adc_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_adc_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxADCState *s = NPCM7XX_ADC(obj); + + npcm7xx_adc_reset(s); +} + +static void npcm7xx_adc_hold_reset(Object *obj) +{ + NPCM7xxADCState *s = NPCM7XX_ADC(obj); + + qemu_irq_lower(s->irq); +} + +static void npcm7xx_adc_init(Object *obj) +{ + NPCM7xxADCState *s = NPCM7XX_ADC(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + int i; + + sysbus_init_irq(sbd, &s->irq); + + timer_init_ns(&s->conv_timer, QEMU_CLOCK_VIRTUAL, + npcm7xx_adc_convert_done, s); + memory_region_init_io(&s->iomem, obj, &npcm7xx_adc_ops, s, + TYPE_NPCM7XX_ADC, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); + s->clock = qdev_init_clock_in(DEVICE(s), "clock", NULL, NULL); + + for (i = 0; i < NPCM7XX_ADC_NUM_INPUTS; ++i) { + object_property_add_uint32_ptr(obj, "adci[*]", + &s->adci[i], OBJ_PROP_FLAG_WRITE); + } + object_property_add_uint32_ptr(obj, "vref", + &s->vref, OBJ_PROP_FLAG_WRITE); + npcm7xx_adc_calibrate(s); +} + +static const VMStateDescription vmstate_npcm7xx_adc = { + .name = "npcm7xx-adc", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_TIMER(conv_timer, NPCM7xxADCState), + VMSTATE_UINT32(con, NPCM7xxADCState), + VMSTATE_UINT32(data, NPCM7xxADCState), + VMSTATE_CLOCK(clock, NPCM7xxADCState), + VMSTATE_UINT32_ARRAY(adci, NPCM7xxADCState, NPCM7XX_ADC_NUM_INPUTS), + VMSTATE_UINT32(vref, NPCM7xxADCState), + VMSTATE_UINT32(iref, NPCM7xxADCState), + VMSTATE_UINT16_ARRAY(calibration_r_values, NPCM7xxADCState, + NPCM7XX_ADC_NUM_CALIB), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_timer_properties[] = { + DEFINE_PROP_UINT32("iref", NPCM7xxADCState, iref, NPCM7XX_ADC_DEFAULT_IREF), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_adc_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx ADC Module"; + dc->vmsd = &vmstate_npcm7xx_adc; + rc->phases.enter = npcm7xx_adc_enter_reset; + rc->phases.hold = npcm7xx_adc_hold_reset; + + device_class_set_props(dc, npcm7xx_timer_properties); +} + +static const TypeInfo npcm7xx_adc_info = { + .name = TYPE_NPCM7XX_ADC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxADCState), + .class_init = npcm7xx_adc_class_init, + .instance_init = npcm7xx_adc_init, +}; + +static void npcm7xx_adc_register_types(void) +{ + type_register_static(&npcm7xx_adc_info); +} + +type_init(npcm7xx_adc_register_types); diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_EHCI_BA (0xf0806000) #define NPCM7XX_OHCI_BA (0xf0807000) +/* ADC Module */ +#define NPCM7XX_ADC_BA (0xf000c000) + /* Internal AHB SRAM */ #define NPCM7XX_RAM3_BA (0xc0008000) #define NPCM7XX_RAM3_SZ (4 * KiB) @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_ROM_BA (0xffff0000) #define NPCM7XX_ROM_SZ (64 * KiB) + /* Clock configuration values to be fixed up when bypassing bootloader */ /* Run PLL1 at 1600 MHz */ @@ -XXX,XX +XXX,XX @@ * interrupts. */ enum NPCM7xxInterrupt { + NPCM7XX_ADC_IRQ = 0, NPCM7XX_UART0_IRQ = 2, NPCM7XX_UART1_IRQ, NPCM7XX_UART2_IRQ, @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init_fuses(NPCM7xxState *s) sizeof(value)); } +static void npcm7xx_write_adc_calibration(NPCM7xxState *s) +{ + /* Both ADC and the fuse array must have realized. */ + QEMU_BUILD_BUG_ON(sizeof(s->adc.calibration_r_values) != 4); + npcm7xx_otp_array_write(&s->fuse_array, s->adc.calibration_r_values, + NPCM7XX_FUSE_ADC_CALIB, sizeof(s->adc.calibration_r_values)); +} + static qemu_irq npcm7xx_irq(NPCM7xxState *s, int n) { return qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) TYPE_NPCM7XX_FUSE_ARRAY); object_initialize_child(obj, "mc", &s->mc, TYPE_NPCM7XX_MC); object_initialize_child(obj, "rng", &s->rng, TYPE_NPCM7XX_RNG); + object_initialize_child(obj, "adc", &s->adc, TYPE_NPCM7XX_ADC); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->mc), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->mc), 0, NPCM7XX_MC_BA); + /* ADC Modules. Cannot fail. */ + qdev_connect_clock_in(DEVICE(&s->adc), "clock", qdev_get_clock_out( + DEVICE(&s->clk), "adc-clock")); + sysbus_realize(SYS_BUS_DEVICE(&s->adc), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->adc), 0, NPCM7XX_ADC_BA); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->adc), 0, + npcm7xx_irq(s, NPCM7XX_ADC_IRQ)); + npcm7xx_write_adc_calibration(s); + /* Timer Modules (TIM). Cannot fail. */ QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) create_unimplemented_device("npcm7xx.vdmx", 0xe0800000, 4 * KiB); create_unimplemented_device("npcm7xx.pcierc", 0xe1000000, 64 * KiB); create_unimplemented_device("npcm7xx.kcs", 0xf0007000, 4 * KiB); - create_unimplemented_device("npcm7xx.adc", 0xf000c000, 4 * KiB); create_unimplemented_device("npcm7xx.gfxi", 0xf000e000, 4 * KiB); create_unimplemented_device("npcm7xx.gpio[0]", 0xf0010000, 4 * KiB); create_unimplemented_device("npcm7xx.gpio[1]", 0xf0011000, 4 * KiB); diff --git a/tests/qtest/npcm7xx_adc-test.c b/tests/qtest/npcm7xx_adc-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/npcm7xx_adc-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for Nuvoton NPCM7xx ADCModules. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "qemu/bitops.h" +#include "qemu/timer.h" +#include "libqos/libqtest.h" +#include "qapi/qmp/qdict.h" + +#define REF_HZ (25000000) + +#define CON_OFFSET 0x0 +#define DATA_OFFSET 0x4 + +#define NUM_INPUTS 8 +#define DEFAULT_IREF 2000000 +#define CONV_CYCLES 20 +#define RESET_CYCLES 10 +#define R0_INPUT 500000 +#define R1_INPUT 1500000 +#define MAX_RESULT 1023 + +#define DEFAULT_CLKDIV 5 + +#define FUSE_ARRAY_BA 0xf018a000 +#define FCTL_OFFSET 0x14 +#define FST_OFFSET 0x0 +#define FADDR_OFFSET 0x4 +#define FDATA_OFFSET 0x8 +#define ADC_CALIB_ADDR 24 +#define FUSE_READ 0x2 + +/* Register field definitions. */ +#define CON_MUX(rv) ((rv) << 24) +#define CON_INT_EN BIT(21) +#define CON_REFSEL BIT(19) +#define CON_INT BIT(18) +#define CON_EN BIT(17) +#define CON_RST BIT(16) +#define CON_CONV BIT(14) +#define CON_DIV(rv) extract32(rv, 1, 8) + +#define FST_RDST BIT(1) +#define FDATA_MASK 0xff + +#define MAX_ERROR 10000 +#define MIN_CALIB_INPUT 100000 +#define MAX_CALIB_INPUT 1800000 + +static const uint32_t input_list[] = { + 100000, + 500000, + 1000000, + 1500000, + 1800000, + 2000000, +}; + +static const uint32_t vref_list[] = { + 2000000, + 2200000, + 2500000, +}; + +static const uint32_t iref_list[] = { + 1800000, + 1900000, + 2000000, + 2100000, + 2200000, +}; + +static const uint32_t div_list[] = {0, 1, 3, 7, 15}; + +typedef struct ADC { + int irq; + uint64_t base_addr; +} ADC; + +ADC adc = { + .irq = 0, + .base_addr = 0xf000c000 +}; + +static uint32_t adc_read_con(QTestState *qts, const ADC *adc) +{ + return qtest_readl(qts, adc->base_addr + CON_OFFSET); +} + +static void adc_write_con(QTestState *qts, const ADC *adc, uint32_t value) +{ + qtest_writel(qts, adc->base_addr + CON_OFFSET, value); +} + +static uint32_t adc_read_data(QTestState *qts, const ADC *adc) +{ + return qtest_readl(qts, adc->base_addr + DATA_OFFSET); +} + +static uint32_t adc_calibrate(uint32_t measured, uint32_t *rv) +{ + return R0_INPUT + (R1_INPUT - R0_INPUT) * (int32_t)(measured - rv[0]) + / (int32_t)(rv[1] - rv[0]); +} + +static void adc_qom_set(QTestState *qts, const ADC *adc, + const char *name, uint32_t value) +{ + QDict *response; + const char *path = "/machine/soc/adc"; + + g_test_message("Setting properties %s of %s with value %u", + name, path, value); + response = qtest_qmp(qts, "{ 'execute': 'qom-set'," + " 'arguments': { 'path': %s, 'property': %s, 'value': %u}}", + path, name, value); + /* The qom set message returns successfully. */ + g_assert_true(qdict_haskey(response, "return")); +} + +static void adc_write_input(QTestState *qts, const ADC *adc, + uint32_t index, uint32_t value) +{ + char name[100]; + + sprintf(name, "adci[%u]", index); + adc_qom_set(qts, adc, name, value); +} + +static void adc_write_vref(QTestState *qts, const ADC *adc, uint32_t value) +{ + adc_qom_set(qts, adc, "vref", value); +} + +static uint32_t adc_calculate_output(uint32_t input, uint32_t ref) +{ + uint32_t output; + + g_assert_cmpuint(input, <=, ref); + output = (input * (MAX_RESULT + 1)) / ref; + if (output > MAX_RESULT) { + output = MAX_RESULT; + } + + return output; +} + +static uint32_t adc_prescaler(QTestState *qts, const ADC *adc) +{ + uint32_t div = extract32(adc_read_con(qts, adc), 1, 8); + + return 2 * (div + 1); +} + +static int64_t adc_calculate_steps(uint32_t cycles, uint32_t prescale, + uint32_t clkdiv) +{ + return (NANOSECONDS_PER_SECOND / (REF_HZ >> clkdiv)) * cycles * prescale; +} + +static void adc_wait_conv_finished(QTestState *qts, const ADC *adc, + uint32_t clkdiv) +{ + uint32_t prescaler = adc_prescaler(qts, adc); + + /* + * ADC should takes roughly 20 cycles to convert one sample. So we assert it + * should take 10~30 cycles here. + */ + qtest_clock_step(qts, adc_calculate_steps(CONV_CYCLES / 2, prescaler, + clkdiv)); + /* ADC is still converting. */ + g_assert_true(adc_read_con(qts, adc) & CON_CONV); + qtest_clock_step(qts, adc_calculate_steps(CONV_CYCLES, prescaler, clkdiv)); + /* ADC has finished conversion. */ + g_assert_false(adc_read_con(qts, adc) & CON_CONV); +} + +/* Check ADC can be reset to default value. */ +static void test_init(gconstpointer adc_p) +{ + const ADC *adc = adc_p; + + QTestState *qts = qtest_init("-machine quanta-gsj"); + adc_write_con(qts, adc, CON_REFSEL | CON_INT); + g_assert_cmphex(adc_read_con(qts, adc), ==, CON_REFSEL); + qtest_quit(qts); +} + +/* Check ADC can convert from an internal reference. */ +static void test_convert_internal(gconstpointer adc_p) +{ + const ADC *adc = adc_p; + uint32_t index, input, output, expected_output; + QTestState *qts = qtest_init("-machine quanta-gsj"); + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + + for (index = 0; index < NUM_INPUTS; ++index) { + for (size_t i = 0; i < ARRAY_SIZE(input_list); ++i) { + input = input_list[i]; + expected_output = adc_calculate_output(input, DEFAULT_IREF); + + adc_write_input(qts, adc, index, input); + adc_write_con(qts, adc, CON_MUX(index) | CON_REFSEL | CON_INT | + CON_EN | CON_CONV); + adc_wait_conv_finished(qts, adc, DEFAULT_CLKDIV); + g_assert_cmphex(adc_read_con(qts, adc), ==, CON_MUX(index) | + CON_REFSEL | CON_EN); + g_assert_false(qtest_get_irq(qts, adc->irq)); + output = adc_read_data(qts, adc); + g_assert_cmpuint(output, ==, expected_output); + } + } + + qtest_quit(qts); +} + +/* Check ADC can convert from an external reference. */ +static void test_convert_external(gconstpointer adc_p) +{ + const ADC *adc = adc_p; + uint32_t index, input, vref, output, expected_output; + QTestState *qts = qtest_init("-machine quanta-gsj"); + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + + for (index = 0; index < NUM_INPUTS; ++index) { + for (size_t i = 0; i < ARRAY_SIZE(input_list); ++i) { + for (size_t j = 0; j < ARRAY_SIZE(vref_list); ++j) { + input = input_list[i]; + vref = vref_list[j]; + expected_output = adc_calculate_output(input, vref); + + adc_write_input(qts, adc, index, input); + adc_write_vref(qts, adc, vref); + adc_write_con(qts, adc, CON_MUX(index) | CON_INT | CON_EN | + CON_CONV); + adc_wait_conv_finished(qts, adc, DEFAULT_CLKDIV); + g_assert_cmphex(adc_read_con(qts, adc), ==, + CON_MUX(index) | CON_EN); + g_assert_false(qtest_get_irq(qts, adc->irq)); + output = adc_read_data(qts, adc); + g_assert_cmpuint(output, ==, expected_output); + } + } + } + + qtest_quit(qts); +} + +/* Check ADC interrupt files if and only if CON_INT_EN is set. */ +static void test_interrupt(gconstpointer adc_p) +{ + const ADC *adc = adc_p; + uint32_t index, input, output, expected_output; + QTestState *qts = qtest_init("-machine quanta-gsj"); + + index = 1; + input = input_list[1]; + expected_output = adc_calculate_output(input, DEFAULT_IREF); + + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + adc_write_input(qts, adc, index, input); + g_assert_false(qtest_get_irq(qts, adc->irq)); + adc_write_con(qts, adc, CON_MUX(index) | CON_INT_EN | CON_REFSEL | CON_INT + | CON_EN | CON_CONV); + adc_wait_conv_finished(qts, adc, DEFAULT_CLKDIV); + g_assert_cmphex(adc_read_con(qts, adc), ==, CON_MUX(index) | CON_INT_EN + | CON_REFSEL | CON_INT | CON_EN); + g_assert_true(qtest_get_irq(qts, adc->irq)); + output = adc_read_data(qts, adc); + g_assert_cmpuint(output, ==, expected_output); + + qtest_quit(qts); +} + +/* Check ADC is reset after setting ADC_RST for 10 ADC cycles. */ +static void test_reset(gconstpointer adc_p) +{ + const ADC *adc = adc_p; + QTestState *qts = qtest_init("-machine quanta-gsj"); + + for (size_t i = 0; i < ARRAY_SIZE(div_list); ++i) { + uint32_t div = div_list[i]; + + adc_write_con(qts, adc, CON_INT | CON_EN | CON_RST | CON_DIV(div)); + qtest_clock_step(qts, adc_calculate_steps(RESET_CYCLES, + adc_prescaler(qts, adc), DEFAULT_CLKDIV)); + g_assert_false(adc_read_con(qts, adc) & CON_EN); + } + qtest_quit(qts); +} + +/* Check ADC Calibration works as desired. */ +static void test_calibrate(gconstpointer adc_p) +{ + int i, j; + const ADC *adc = adc_p; + + for (j = 0; j < ARRAY_SIZE(iref_list); ++j) { + uint32_t iref = iref_list[j]; + uint32_t expected_rv[] = { + adc_calculate_output(R0_INPUT, iref), + adc_calculate_output(R1_INPUT, iref), + }; + char buf[100]; + QTestState *qts; + + sprintf(buf, "-machine quanta-gsj -global npcm7xx-adc.iref=%u", iref); + qts = qtest_init(buf); + + /* Check the converted value is correct using the calibration value. */ + for (i = 0; i < ARRAY_SIZE(input_list); ++i) { + uint32_t input; + uint32_t output; + uint32_t expected_output; + uint32_t calibrated_voltage; + uint32_t index = 0; + + input = input_list[i]; + /* Calibration only works for input range 0.1V ~ 1.8V. */ + if (input < MIN_CALIB_INPUT || input > MAX_CALIB_INPUT) { + continue; + } + expected_output = adc_calculate_output(input, iref); + + adc_write_input(qts, adc, index, input); + adc_write_con(qts, adc, CON_MUX(index) | CON_REFSEL | CON_INT | + CON_EN | CON_CONV); + adc_wait_conv_finished(qts, adc, DEFAULT_CLKDIV); + g_assert_cmphex(adc_read_con(qts, adc), ==, + CON_REFSEL | CON_MUX(index) | CON_EN); + output = adc_read_data(qts, adc); + g_assert_cmpuint(output, ==, expected_output); + + calibrated_voltage = adc_calibrate(output, expected_rv); + g_assert_cmpuint(calibrated_voltage, >, input - MAX_ERROR); + g_assert_cmpuint(calibrated_voltage, <, input + MAX_ERROR); + } + + qtest_quit(qts); + } +} + +static void adc_add_test(const char *name, const ADC* wd, + GTestDataFunc fn) +{ + g_autofree char *full_name = g_strdup_printf("npcm7xx_adc/%s", name); + qtest_add_data_func(full_name, wd, fn); +} +#define add_test(name, td) adc_add_test(#name, td, test_##name) + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + + add_test(init, &adc); + add_test(convert_internal, &adc); + add_test(convert_external, &adc); + add_test(interrupt, &adc); + add_test(reset, &adc); + add_test(calibrate, &adc); + + return g_test_run(); +} diff --git a/hw/adc/meson.build b/hw/adc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/adc/meson.build +++ b/hw/adc/meson.build @@ -1 +1,2 @@ softmmu_ss.add(when: 'CONFIG_STM32F2XX_ADC', if_true: files('stm32f2xx_adc.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_adc.c')) diff --git a/hw/adc/trace-events b/hw/adc/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/adc/trace-events @@ -XXX,XX +XXX,XX @@ +# See docs/devel/tracing.txt for syntax documentation. + +# npcm7xx_adc.c +npcm7xx_adc_read(const char *id, uint64_t offset, uint32_t value) " %s offset: 0x%04" PRIx64 " value 0x%04" PRIx32 +npcm7xx_adc_write(const char *id, uint64_t offset, uint32_t value) "%s offset: 0x%04" PRIx64 " value 0x%04" PRIx32 diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_sparc64 = \ ['prom-env-test', 'boot-serial-test'] qtests_npcm7xx = \ - ['npcm7xx_gpio-test', + ['npcm7xx_adc-test', + 'npcm7xx_gpio-test', 'npcm7xx_rng-test', 'npcm7xx_timer-test', 'npcm7xx_watchdog_timer-test'] -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> The PWM module is part of NPCM7XX module. Each NPCM7XX module has two identical PWM modules. Each module contains 4 PWM entries. Each PWM has two outputs: frequency and duty_cycle. Both are computed using inputs from software side. This module does not model detail pulse signals since it is expensive. It also does not model interrupts and watchdogs that are dependant on the detail models. The interfaces for these are left in the module so that anyone in need for these functionalities can implement on their own. The user can read the duty cycle and frequency using qom-get command. Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210108190945.949196-5-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 2 +- include/hw/arm/npcm7xx.h | 2 + include/hw/misc/npcm7xx_pwm.h | 105 +++++++ hw/arm/npcm7xx.c | 26 +- hw/misc/npcm7xx_pwm.c | 550 ++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + hw/misc/trace-events | 6 + 7 files changed, 689 insertions(+), 3 deletions(-) create mode 100644 include/hw/misc/npcm7xx_pwm.h create mode 100644 hw/misc/npcm7xx_pwm.c diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ Supported devices * USB host (USBH) * GPIO controller * Analog to Digital Converter (ADC) + * Pulse Width Modulation (PWM) Missing devices --------------- @@ -XXX,XX +XXX,XX @@ Missing devices * Peripheral SPI controller (PSPI) * SD/MMC host * PECI interface - * Pulse Width Modulation (PWM) * Tachometer * PCI and PCIe root complex and bridges * VDM and MCTP support diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/mem/npcm7xx_mc.h" #include "hw/misc/npcm7xx_clk.h" #include "hw/misc/npcm7xx_gcr.h" +#include "hw/misc/npcm7xx_pwm.h" #include "hw/misc/npcm7xx_rng.h" #include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxCLKState clk; NPCM7xxTimerCtrlState tim[3]; NPCM7xxADCState adc; + NPCM7xxPWMState pwm[2]; NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; NPCM7xxMCState mc; diff --git a/include/hw/misc/npcm7xx_pwm.h b/include/hw/misc/npcm7xx_pwm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/npcm7xx_pwm.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx PWM Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_PWM_H +#define NPCM7XX_PWM_H + +#include "hw/clock.h" +#include "hw/sysbus.h" +#include "hw/irq.h" + +/* Each PWM module holds 4 PWM channels. */ +#define NPCM7XX_PWM_PER_MODULE 4 + +/* + * Number of registers in one pwm module. Don't change this without increasing + * the version_id in vmstate. + */ +#define NPCM7XX_PWM_NR_REGS (0x54 / sizeof(uint32_t)) + +/* + * The maximum duty values. Each duty unit represents 1/NPCM7XX_PWM_MAX_DUTY + * cycles. For example, if NPCM7XX_PWM_MAX_DUTY=1,000,000 and a PWM has a duty + * value of 100,000 the duty cycle for that PWM is 10%. + */ +#define NPCM7XX_PWM_MAX_DUTY 1000000 + +typedef struct NPCM7xxPWMState NPCM7xxPWMState; + +/** + * struct NPCM7xxPWM - The state of a single PWM channel. + * @module: The PWM module that contains this channel. + * @irq: GIC interrupt line to fire on expiration if enabled. + * @running: Whether this PWM channel is generating output. + * @inverted: Whether this PWM channel is inverted. + * @index: The index of this PWM channel. + * @cnr: The counter register. + * @cmr: The comparator register. + * @pdr: The data register. + * @pwdr: The watchdog register. + * @freq: The frequency of this PWM channel. + * @duty: The duty cycle of this PWM channel. One unit represents + * 1/NPCM7XX_MAX_DUTY cycles. + */ +typedef struct NPCM7xxPWM { + NPCM7xxPWMState *module; + + qemu_irq irq; + + bool running; + bool inverted; + + uint8_t index; + uint32_t cnr; + uint32_t cmr; + uint32_t pdr; + uint32_t pwdr; + + uint32_t freq; + uint32_t duty; +} NPCM7xxPWM; + +/** + * struct NPCM7xxPWMState - Pulse Width Modulation device state. + * @parent: System bus device. + * @iomem: Memory region through which registers are accessed. + * @clock: The PWM clock. + * @pwm: The PWM channels owned by this module. + * @ppr: The prescaler register. + * @csr: The clock selector register. + * @pcr: The control register. + * @pier: The interrupt enable register. + * @piir: The interrupt indication register. + */ +struct NPCM7xxPWMState { + SysBusDevice parent; + + MemoryRegion iomem; + + Clock *clock; + NPCM7xxPWM pwm[NPCM7XX_PWM_PER_MODULE]; + + uint32_t ppr; + uint32_t csr; + uint32_t pcr; + uint32_t pier; + uint32_t piir; +}; + +#define TYPE_NPCM7XX_PWM "npcm7xx-pwm" +#define NPCM7XX_PWM(obj) \ + OBJECT_CHECK(NPCM7xxPWMState, (obj), TYPE_NPCM7XX_PWM) + +#endif /* NPCM7XX_PWM_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ enum NPCM7xxInterrupt { NPCM7XX_WDG2_IRQ, /* Timer Module 2 Watchdog */ NPCM7XX_EHCI_IRQ = 61, NPCM7XX_OHCI_IRQ = 62, + NPCM7XX_PWM0_IRQ = 93, /* PWM module 0 */ + NPCM7XX_PWM1_IRQ, /* PWM module 1 */ NPCM7XX_GPIO0_IRQ = 116, NPCM7XX_GPIO1_IRQ, NPCM7XX_GPIO2_IRQ, @@ -XXX,XX +XXX,XX @@ static const hwaddr npcm7xx_fiu3_flash_addr[] = { 0xb8000000, /* CS3 */ }; +/* Register base address for each PWM Module */ +static const hwaddr npcm7xx_pwm_addr[] = { + 0xf0103000, + 0xf0104000, +}; + static const struct { hwaddr regs_addr; uint32_t unconnected_pins; @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) object_initialize_child(obj, npcm7xx_fiu[i].name, &s->fiu[i], TYPE_NPCM7XX_FIU); } + + for (i = 0; i < ARRAY_SIZE(s->pwm); i++) { + object_initialize_child(obj, "pwm[*]", &s->pwm[i], TYPE_NPCM7XX_PWM); + } } static void npcm7xx_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->ohci), 0, npcm7xx_irq(s, NPCM7XX_OHCI_IRQ)); + /* PWM Modules. Cannot fail. */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_pwm_addr) != ARRAY_SIZE(s->pwm)); + for (i = 0; i < ARRAY_SIZE(s->pwm); i++) { + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->pwm[i]); + + qdev_connect_clock_in(DEVICE(&s->pwm[i]), "clock", qdev_get_clock_out( + DEVICE(&s->clk), "apb3-clock")); + sysbus_realize(sbd, &error_abort); + sysbus_mmio_map(sbd, 0, npcm7xx_pwm_addr[i]); + sysbus_connect_irq(sbd, i, npcm7xx_irq(s, NPCM7XX_PWM0_IRQ + i)); + } + /* * Flash Interface Unit (FIU). Can fail if incorrect number of chip selects * specified, but this is a programming error. @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) create_unimplemented_device("npcm7xx.peci", 0xf0100000, 4 * KiB); create_unimplemented_device("npcm7xx.siox[1]", 0xf0101000, 4 * KiB); create_unimplemented_device("npcm7xx.siox[2]", 0xf0102000, 4 * KiB); - create_unimplemented_device("npcm7xx.pwm[0]", 0xf0103000, 4 * KiB); - create_unimplemented_device("npcm7xx.pwm[1]", 0xf0104000, 4 * KiB); create_unimplemented_device("npcm7xx.mft[0]", 0xf0180000, 4 * KiB); create_unimplemented_device("npcm7xx.mft[1]", 0xf0181000, 4 * KiB); create_unimplemented_device("npcm7xx.mft[2]", 0xf0182000, 4 * KiB); diff --git a/hw/misc/npcm7xx_pwm.c b/hw/misc/npcm7xx_pwm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/npcm7xx_pwm.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx PWM Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/misc/npcm7xx_pwm.h" +#include "hw/registerfields.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "trace.h" + +REG32(NPCM7XX_PWM_PPR, 0x00); +REG32(NPCM7XX_PWM_CSR, 0x04); +REG32(NPCM7XX_PWM_PCR, 0x08); +REG32(NPCM7XX_PWM_CNR0, 0x0c); +REG32(NPCM7XX_PWM_CMR0, 0x10); +REG32(NPCM7XX_PWM_PDR0, 0x14); +REG32(NPCM7XX_PWM_CNR1, 0x18); +REG32(NPCM7XX_PWM_CMR1, 0x1c); +REG32(NPCM7XX_PWM_PDR1, 0x20); +REG32(NPCM7XX_PWM_CNR2, 0x24); +REG32(NPCM7XX_PWM_CMR2, 0x28); +REG32(NPCM7XX_PWM_PDR2, 0x2c); +REG32(NPCM7XX_PWM_CNR3, 0x30); +REG32(NPCM7XX_PWM_CMR3, 0x34); +REG32(NPCM7XX_PWM_PDR3, 0x38); +REG32(NPCM7XX_PWM_PIER, 0x3c); +REG32(NPCM7XX_PWM_PIIR, 0x40); +REG32(NPCM7XX_PWM_PWDR0, 0x44); +REG32(NPCM7XX_PWM_PWDR1, 0x48); +REG32(NPCM7XX_PWM_PWDR2, 0x4c); +REG32(NPCM7XX_PWM_PWDR3, 0x50); + +/* Register field definitions. */ +#define NPCM7XX_PPR(rv, index) extract32((rv), npcm7xx_ppr_base[index], 8) +#define NPCM7XX_CSR(rv, index) extract32((rv), npcm7xx_csr_base[index], 3) +#define NPCM7XX_CH(rv, index) extract32((rv), npcm7xx_ch_base[index], 4) +#define NPCM7XX_CH_EN BIT(0) +#define NPCM7XX_CH_INV BIT(2) +#define NPCM7XX_CH_MOD BIT(3) + +/* Offset of each PWM channel's prescaler in the PPR register. */ +static const int npcm7xx_ppr_base[] = { 0, 0, 8, 8 }; +/* Offset of each PWM channel's clock selector in the CSR register. */ +static const int npcm7xx_csr_base[] = { 0, 4, 8, 12 }; +/* Offset of each PWM channel's control variable in the PCR register. */ +static const int npcm7xx_ch_base[] = { 0, 8, 12, 16 }; + +static uint32_t npcm7xx_pwm_calculate_freq(NPCM7xxPWM *p) +{ + uint32_t ppr; + uint32_t csr; + uint32_t freq; + + if (!p->running) { + return 0; + } + + csr = NPCM7XX_CSR(p->module->csr, p->index); + ppr = NPCM7XX_PPR(p->module->ppr, p->index); + freq = clock_get_hz(p->module->clock); + freq /= ppr + 1; + /* csr can only be 0~4 */ + if (csr > 4) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid csr value %u\n", + __func__, csr); + csr = 4; + } + /* freq won't be changed if csr == 4. */ + if (csr < 4) { + freq >>= csr + 1; + } + + return freq / (p->cnr + 1); +} + +static uint32_t npcm7xx_pwm_calculate_duty(NPCM7xxPWM *p) +{ + uint64_t duty; + + if (p->running) { + if (p->cnr == 0) { + duty = 0; + } else if (p->cmr >= p->cnr) { + duty = NPCM7XX_PWM_MAX_DUTY; + } else { + duty = NPCM7XX_PWM_MAX_DUTY * (p->cmr + 1) / (p->cnr + 1); + } + } else { + duty = 0; + } + + if (p->inverted) { + duty = NPCM7XX_PWM_MAX_DUTY - duty; + } + + return duty; +} + +static void npcm7xx_pwm_update_freq(NPCM7xxPWM *p) +{ + uint32_t freq = npcm7xx_pwm_calculate_freq(p); + + if (freq != p->freq) { + trace_npcm7xx_pwm_update_freq(DEVICE(p->module)->canonical_path, + p->index, p->freq, freq); + p->freq = freq; + } +} + +static void npcm7xx_pwm_update_duty(NPCM7xxPWM *p) +{ + uint32_t duty = npcm7xx_pwm_calculate_duty(p); + + if (duty != p->duty) { + trace_npcm7xx_pwm_update_duty(DEVICE(p->module)->canonical_path, + p->index, p->duty, duty); + p->duty = duty; + } +} + +static void npcm7xx_pwm_update_output(NPCM7xxPWM *p) +{ + npcm7xx_pwm_update_freq(p); + npcm7xx_pwm_update_duty(p); +} + +static void npcm7xx_pwm_write_ppr(NPCM7xxPWMState *s, uint32_t new_ppr) +{ + int i; + uint32_t old_ppr = s->ppr; + + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_ppr_base) != NPCM7XX_PWM_PER_MODULE); + s->ppr = new_ppr; + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; ++i) { + if (NPCM7XX_PPR(old_ppr, i) != NPCM7XX_PPR(new_ppr, i)) { + npcm7xx_pwm_update_freq(&s->pwm[i]); + } + } +} + +static void npcm7xx_pwm_write_csr(NPCM7xxPWMState *s, uint32_t new_csr) +{ + int i; + uint32_t old_csr = s->csr; + + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_csr_base) != NPCM7XX_PWM_PER_MODULE); + s->csr = new_csr; + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; ++i) { + if (NPCM7XX_CSR(old_csr, i) != NPCM7XX_CSR(new_csr, i)) { + npcm7xx_pwm_update_freq(&s->pwm[i]); + } + } +} + +static void npcm7xx_pwm_write_pcr(NPCM7xxPWMState *s, uint32_t new_pcr) +{ + int i; + bool inverted; + uint32_t pcr; + NPCM7xxPWM *p; + + s->pcr = new_pcr; + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_ch_base) != NPCM7XX_PWM_PER_MODULE); + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; ++i) { + p = &s->pwm[i]; + pcr = NPCM7XX_CH(new_pcr, i); + inverted = pcr & NPCM7XX_CH_INV; + + /* + * We only run a PWM channel with toggle mode. Single-shot mode does not + * generate frequency and duty-cycle values. + */ + if ((pcr & NPCM7XX_CH_EN) && (pcr & NPCM7XX_CH_MOD)) { + if (p->running) { + /* Re-run this PWM channel if inverted changed. */ + if (p->inverted ^ inverted) { + p->inverted = inverted; + npcm7xx_pwm_update_duty(p); + } + } else { + /* Run this PWM channel. */ + p->running = true; + p->inverted = inverted; + npcm7xx_pwm_update_output(p); + } + } else { + /* Clear this PWM channel. */ + p->running = false; + p->inverted = inverted; + npcm7xx_pwm_update_output(p); + } + } + +} + +static hwaddr npcm7xx_cnr_index(hwaddr offset) +{ + switch (offset) { + case A_NPCM7XX_PWM_CNR0: + return 0; + case A_NPCM7XX_PWM_CNR1: + return 1; + case A_NPCM7XX_PWM_CNR2: + return 2; + case A_NPCM7XX_PWM_CNR3: + return 3; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_cmr_index(hwaddr offset) +{ + switch (offset) { + case A_NPCM7XX_PWM_CMR0: + return 0; + case A_NPCM7XX_PWM_CMR1: + return 1; + case A_NPCM7XX_PWM_CMR2: + return 2; + case A_NPCM7XX_PWM_CMR3: + return 3; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_pdr_index(hwaddr offset) +{ + switch (offset) { + case A_NPCM7XX_PWM_PDR0: + return 0; + case A_NPCM7XX_PWM_PDR1: + return 1; + case A_NPCM7XX_PWM_PDR2: + return 2; + case A_NPCM7XX_PWM_PDR3: + return 3; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_pwdr_index(hwaddr offset) +{ + switch (offset) { + case A_NPCM7XX_PWM_PWDR0: + return 0; + case A_NPCM7XX_PWM_PWDR1: + return 1; + case A_NPCM7XX_PWM_PWDR2: + return 2; + case A_NPCM7XX_PWM_PWDR3: + return 3; + default: + g_assert_not_reached(); + } +} + +static uint64_t npcm7xx_pwm_read(void *opaque, hwaddr offset, unsigned size) +{ + NPCM7xxPWMState *s = opaque; + uint64_t value = 0; + + switch (offset) { + case A_NPCM7XX_PWM_CNR0: + case A_NPCM7XX_PWM_CNR1: + case A_NPCM7XX_PWM_CNR2: + case A_NPCM7XX_PWM_CNR3: + value = s->pwm[npcm7xx_cnr_index(offset)].cnr; + break; + + case A_NPCM7XX_PWM_CMR0: + case A_NPCM7XX_PWM_CMR1: + case A_NPCM7XX_PWM_CMR2: + case A_NPCM7XX_PWM_CMR3: + value = s->pwm[npcm7xx_cmr_index(offset)].cmr; + break; + + case A_NPCM7XX_PWM_PDR0: + case A_NPCM7XX_PWM_PDR1: + case A_NPCM7XX_PWM_PDR2: + case A_NPCM7XX_PWM_PDR3: + value = s->pwm[npcm7xx_pdr_index(offset)].pdr; + break; + + case A_NPCM7XX_PWM_PWDR0: + case A_NPCM7XX_PWM_PWDR1: + case A_NPCM7XX_PWM_PWDR2: + case A_NPCM7XX_PWM_PWDR3: + value = s->pwm[npcm7xx_pwdr_index(offset)].pwdr; + break; + + case A_NPCM7XX_PWM_PPR: + value = s->ppr; + break; + + case A_NPCM7XX_PWM_CSR: + value = s->csr; + break; + + case A_NPCM7XX_PWM_PCR: + value = s->pcr; + break; + + case A_NPCM7XX_PWM_PIER: + value = s->pier; + break; + + case A_NPCM7XX_PWM_PIIR: + value = s->piir; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + break; + } + + trace_npcm7xx_pwm_read(DEVICE(s)->canonical_path, offset, value); + return value; +} + +static void npcm7xx_pwm_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + NPCM7xxPWMState *s = opaque; + NPCM7xxPWM *p; + uint32_t value = v; + + trace_npcm7xx_pwm_write(DEVICE(s)->canonical_path, offset, value); + switch (offset) { + case A_NPCM7XX_PWM_CNR0: + case A_NPCM7XX_PWM_CNR1: + case A_NPCM7XX_PWM_CNR2: + case A_NPCM7XX_PWM_CNR3: + p = &s->pwm[npcm7xx_cnr_index(offset)]; + p->cnr = value; + npcm7xx_pwm_update_output(p); + break; + + case A_NPCM7XX_PWM_CMR0: + case A_NPCM7XX_PWM_CMR1: + case A_NPCM7XX_PWM_CMR2: + case A_NPCM7XX_PWM_CMR3: + p = &s->pwm[npcm7xx_cmr_index(offset)]; + p->cmr = value; + npcm7xx_pwm_update_output(p); + break; + + case A_NPCM7XX_PWM_PDR0: + case A_NPCM7XX_PWM_PDR1: + case A_NPCM7XX_PWM_PDR2: + case A_NPCM7XX_PWM_PDR3: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + break; + + case A_NPCM7XX_PWM_PWDR0: + case A_NPCM7XX_PWM_PWDR1: + case A_NPCM7XX_PWM_PWDR2: + case A_NPCM7XX_PWM_PWDR3: + qemu_log_mask(LOG_UNIMP, + "%s: register @ 0x%04" HWADDR_PRIx " is not implemented\n", + __func__, offset); + break; + + case A_NPCM7XX_PWM_PPR: + npcm7xx_pwm_write_ppr(s, value); + break; + + case A_NPCM7XX_PWM_CSR: + npcm7xx_pwm_write_csr(s, value); + break; + + case A_NPCM7XX_PWM_PCR: + npcm7xx_pwm_write_pcr(s, value); + break; + + case A_NPCM7XX_PWM_PIER: + qemu_log_mask(LOG_UNIMP, + "%s: register @ 0x%04" HWADDR_PRIx " is not implemented\n", + __func__, offset); + break; + + case A_NPCM7XX_PWM_PIIR: + qemu_log_mask(LOG_UNIMP, + "%s: register @ 0x%04" HWADDR_PRIx " is not implemented\n", + __func__, offset); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + break; + } +} + +static const struct MemoryRegionOps npcm7xx_pwm_ops = { + .read = npcm7xx_pwm_read, + .write = npcm7xx_pwm_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_pwm_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxPWMState *s = NPCM7XX_PWM(obj); + int i; + + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; i++) { + NPCM7xxPWM *p = &s->pwm[i]; + + p->cnr = 0x00000000; + p->cmr = 0x00000000; + p->pdr = 0x00000000; + p->pwdr = 0x00000000; + } + + s->ppr = 0x00000000; + s->csr = 0x00000000; + s->pcr = 0x00000000; + s->pier = 0x00000000; + s->piir = 0x00000000; +} + +static void npcm7xx_pwm_hold_reset(Object *obj) +{ + NPCM7xxPWMState *s = NPCM7XX_PWM(obj); + int i; + + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; i++) { + qemu_irq_lower(s->pwm[i].irq); + } +} + +static void npcm7xx_pwm_init(Object *obj) +{ + NPCM7xxPWMState *s = NPCM7XX_PWM(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + int i; + + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; i++) { + NPCM7xxPWM *p = &s->pwm[i]; + p->module = s; + p->index = i; + sysbus_init_irq(sbd, &p->irq); + } + + memory_region_init_io(&s->iomem, obj, &npcm7xx_pwm_ops, s, + TYPE_NPCM7XX_PWM, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); + s->clock = qdev_init_clock_in(DEVICE(s), "clock", NULL, NULL); + + for (i = 0; i < NPCM7XX_PWM_PER_MODULE; ++i) { + object_property_add_uint32_ptr(obj, "freq[*]", + &s->pwm[i].freq, OBJ_PROP_FLAG_READ); + object_property_add_uint32_ptr(obj, "duty[*]", + &s->pwm[i].duty, OBJ_PROP_FLAG_READ); + } +} + +static const VMStateDescription vmstate_npcm7xx_pwm = { + .name = "npcm7xx-pwm", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_BOOL(running, NPCM7xxPWM), + VMSTATE_BOOL(inverted, NPCM7xxPWM), + VMSTATE_UINT8(index, NPCM7xxPWM), + VMSTATE_UINT32(cnr, NPCM7xxPWM), + VMSTATE_UINT32(cmr, NPCM7xxPWM), + VMSTATE_UINT32(pdr, NPCM7xxPWM), + VMSTATE_UINT32(pwdr, NPCM7xxPWM), + VMSTATE_UINT32(freq, NPCM7xxPWM), + VMSTATE_UINT32(duty, NPCM7xxPWM), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_npcm7xx_pwm_module = { + .name = "npcm7xx-pwm-module", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_CLOCK(clock, NPCM7xxPWMState), + VMSTATE_STRUCT_ARRAY(pwm, NPCM7xxPWMState, + NPCM7XX_PWM_PER_MODULE, 0, vmstate_npcm7xx_pwm, + NPCM7xxPWM), + VMSTATE_UINT32(ppr, NPCM7xxPWMState), + VMSTATE_UINT32(csr, NPCM7xxPWMState), + VMSTATE_UINT32(pcr, NPCM7xxPWMState), + VMSTATE_UINT32(pier, NPCM7xxPWMState), + VMSTATE_UINT32(piir, NPCM7xxPWMState), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_pwm_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx PWM Controller"; + dc->vmsd = &vmstate_npcm7xx_pwm_module; + rc->phases.enter = npcm7xx_pwm_enter_reset; + rc->phases.hold = npcm7xx_pwm_hold_reset; +} + +static const TypeInfo npcm7xx_pwm_info = { + .name = TYPE_NPCM7XX_PWM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxPWMState), + .class_init = npcm7xx_pwm_class_init, + .instance_init = npcm7xx_pwm_init, +}; + +static void npcm7xx_pwm_register_type(void) +{ + type_register_static(&npcm7xx_pwm_info); +} +type_init(npcm7xx_pwm_register_type); 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 @@ softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( 'npcm7xx_clk.c', 'npcm7xx_gcr.c', + 'npcm7xx_pwm.c', 'npcm7xx_rng.c', )) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files( 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 @@ npcm7xx_gcr_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " valu npcm7xx_rng_read(uint64_t offset, uint64_t value, unsigned size) "offset: 0x%04" PRIx64 " value: 0x%02" PRIx64 " size: %u" npcm7xx_rng_write(uint64_t offset, uint64_t value, unsigned size) "offset: 0x%04" PRIx64 " value: 0x%02" PRIx64 " size: %u" +# npcm7xx_pwm.c +npcm7xx_pwm_read(const char *id, uint64_t offset, uint32_t value) "%s offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_pwm_write(const char *id, uint64_t offset, uint32_t value) "%s offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_pwm_update_freq(const char *id, uint8_t index, uint32_t old_value, uint32_t new_value) "%s pwm[%u] Update Freq: old_freq: %u, new_freq: %u" +npcm7xx_pwm_update_duty(const char *id, uint8_t index, uint32_t old_value, uint32_t new_value) "%s pwm[%u] Update Duty: old_duty: %u, new_duty: %u" + # stm32f4xx_syscfg.c stm32f4xx_syscfg_set_irq(int gpio, int line, int level) "Interupt: GPIO: %d, Line: %d; Level: %d" stm32f4xx_pulse_exti(int irq) "Pulse EXTI: %d" -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> We add a qtest for the PWM in the previous patch. It proves it works as expected. Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210108190945.949196-6-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_pwm-test.c | 490 +++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 491 insertions(+) create mode 100644 tests/qtest/npcm7xx_pwm-test.c diff --git a/tests/qtest/npcm7xx_pwm-test.c b/tests/qtest/npcm7xx_pwm-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/npcm7xx_pwm-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for Nuvoton NPCM7xx PWM Modules. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "qemu/bitops.h" +#include "libqos/libqtest.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qnum.h" + +#define REF_HZ 25000000 + +/* Register field definitions. */ +#define CH_EN BIT(0) +#define CH_INV BIT(2) +#define CH_MOD BIT(3) + +/* Registers shared between all PWMs in a module */ +#define PPR 0x00 +#define CSR 0x04 +#define PCR 0x08 +#define PIER 0x3c +#define PIIR 0x40 + +/* CLK module related */ +#define CLK_BA 0xf0801000 +#define CLKSEL 0x04 +#define CLKDIV1 0x08 +#define CLKDIV2 0x2c +#define PLLCON0 0x0c +#define PLLCON1 0x10 +#define PLL_INDV(rv) extract32((rv), 0, 6) +#define PLL_FBDV(rv) extract32((rv), 16, 12) +#define PLL_OTDV1(rv) extract32((rv), 8, 3) +#define PLL_OTDV2(rv) extract32((rv), 13, 3) +#define APB3CKDIV(rv) extract32((rv), 28, 2) +#define CLK2CKDIV(rv) extract32((rv), 0, 1) +#define CLK4CKDIV(rv) extract32((rv), 26, 2) +#define CPUCKSEL(rv) extract32((rv), 0, 2) + +#define MAX_DUTY 1000000 + +typedef struct PWMModule { + int irq; + uint64_t base_addr; +} PWMModule; + +typedef struct PWM { + uint32_t cnr_offset; + uint32_t cmr_offset; + uint32_t pdr_offset; + uint32_t pwdr_offset; +} PWM; + +typedef struct TestData { + const PWMModule *module; + const PWM *pwm; +} TestData; + +static const PWMModule pwm_module_list[] = { + { + .irq = 93, + .base_addr = 0xf0103000 + }, + { + .irq = 94, + .base_addr = 0xf0104000 + } +}; + +static const PWM pwm_list[] = { + { + .cnr_offset = 0x0c, + .cmr_offset = 0x10, + .pdr_offset = 0x14, + .pwdr_offset = 0x44, + }, + { + .cnr_offset = 0x18, + .cmr_offset = 0x1c, + .pdr_offset = 0x20, + .pwdr_offset = 0x48, + }, + { + .cnr_offset = 0x24, + .cmr_offset = 0x28, + .pdr_offset = 0x2c, + .pwdr_offset = 0x4c, + }, + { + .cnr_offset = 0x30, + .cmr_offset = 0x34, + .pdr_offset = 0x38, + .pwdr_offset = 0x50, + }, +}; + +static const int ppr_base[] = { 0, 0, 8, 8 }; +static const int csr_base[] = { 0, 4, 8, 12 }; +static const int pcr_base[] = { 0, 8, 12, 16 }; + +static const uint32_t ppr_list[] = { + 0, + 1, + 10, + 100, + 255, /* Max possible value. */ +}; + +static const uint32_t csr_list[] = { + 0, + 1, + 2, + 3, + 4, /* Max possible value. */ +}; + +static const uint32_t cnr_list[] = { + 0, + 1, + 50, + 100, + 150, + 200, + 1000, + 10000, + 65535, /* Max possible value. */ +}; + +static const uint32_t cmr_list[] = { + 0, + 1, + 10, + 50, + 100, + 150, + 200, + 1000, + 10000, + 65535, /* Max possible value. */ +}; + +/* Returns the index of the PWM module. */ +static int pwm_module_index(const PWMModule *module) +{ + ptrdiff_t diff = module - pwm_module_list; + + g_assert_true(diff >= 0 && diff < ARRAY_SIZE(pwm_module_list)); + + return diff; +} + +/* Returns the index of the PWM entry. */ +static int pwm_index(const PWM *pwm) +{ + ptrdiff_t diff = pwm - pwm_list; + + g_assert_true(diff >= 0 && diff < ARRAY_SIZE(pwm_list)); + + return diff; +} + +static uint64_t pwm_qom_get(QTestState *qts, const char *path, const char *name) +{ + QDict *response; + + g_test_message("Getting properties %s from %s", name, path); + response = qtest_qmp(qts, "{ 'execute': 'qom-get'," + " 'arguments': { 'path': %s, 'property': %s}}", + path, name); + /* The qom set message returns successfully. */ + g_assert_true(qdict_haskey(response, "return")); + return qnum_get_uint(qobject_to(QNum, qdict_get(response, "return"))); +} + +static uint64_t pwm_get_freq(QTestState *qts, int module_index, int pwm_index) +{ + char path[100]; + char name[100]; + + sprintf(path, "/machine/soc/pwm[%d]", module_index); + sprintf(name, "freq[%d]", pwm_index); + + return pwm_qom_get(qts, path, name); +} + +static uint64_t pwm_get_duty(QTestState *qts, int module_index, int pwm_index) +{ + char path[100]; + char name[100]; + + sprintf(path, "/machine/soc/pwm[%d]", module_index); + sprintf(name, "duty[%d]", pwm_index); + + return pwm_qom_get(qts, path, name); +} + +static uint32_t get_pll(uint32_t con) +{ + return REF_HZ * PLL_FBDV(con) / (PLL_INDV(con) * PLL_OTDV1(con) + * PLL_OTDV2(con)); +} + +static uint64_t read_pclk(QTestState *qts) +{ + uint64_t freq = REF_HZ; + uint32_t clksel = qtest_readl(qts, CLK_BA + CLKSEL); + uint32_t pllcon; + uint32_t clkdiv1 = qtest_readl(qts, CLK_BA + CLKDIV1); + uint32_t clkdiv2 = qtest_readl(qts, CLK_BA + CLKDIV2); + + switch (CPUCKSEL(clksel)) { + case 0: + pllcon = qtest_readl(qts, CLK_BA + PLLCON0); + freq = get_pll(pllcon); + break; + case 1: + pllcon = qtest_readl(qts, CLK_BA + PLLCON1); + freq = get_pll(pllcon); + break; + case 2: + break; + case 3: + break; + default: + g_assert_not_reached(); + } + + freq >>= (CLK2CKDIV(clkdiv1) + CLK4CKDIV(clkdiv1) + APB3CKDIV(clkdiv2)); + + return freq; +} + +static uint32_t pwm_selector(uint32_t csr) +{ + switch (csr) { + case 0: + return 2; + case 1: + return 4; + case 2: + return 8; + case 3: + return 16; + case 4: + return 1; + default: + g_assert_not_reached(); + } +} + +static uint64_t pwm_compute_freq(QTestState *qts, uint32_t ppr, uint32_t csr, + uint32_t cnr) +{ + return read_pclk(qts) / ((ppr + 1) * pwm_selector(csr) * (cnr + 1)); +} + +static uint64_t pwm_compute_duty(uint32_t cnr, uint32_t cmr, bool inverted) +{ + uint64_t duty; + + if (cnr == 0) { + /* PWM is stopped. */ + duty = 0; + } else if (cmr >= cnr) { + duty = MAX_DUTY; + } else { + duty = MAX_DUTY * (cmr + 1) / (cnr + 1); + } + + if (inverted) { + duty = MAX_DUTY - duty; + } + + return duty; +} + +static uint32_t pwm_read(QTestState *qts, const TestData *td, unsigned offset) +{ + return qtest_readl(qts, td->module->base_addr + offset); +} + +static void pwm_write(QTestState *qts, const TestData *td, unsigned offset, + uint32_t value) +{ + qtest_writel(qts, td->module->base_addr + offset, value); +} + +static uint32_t pwm_read_ppr(QTestState *qts, const TestData *td) +{ + return extract32(pwm_read(qts, td, PPR), ppr_base[pwm_index(td->pwm)], 8); +} + +static void pwm_write_ppr(QTestState *qts, const TestData *td, uint32_t value) +{ + pwm_write(qts, td, PPR, value << ppr_base[pwm_index(td->pwm)]); +} + +static uint32_t pwm_read_csr(QTestState *qts, const TestData *td) +{ + return extract32(pwm_read(qts, td, CSR), csr_base[pwm_index(td->pwm)], 3); +} + +static void pwm_write_csr(QTestState *qts, const TestData *td, uint32_t value) +{ + pwm_write(qts, td, CSR, value << csr_base[pwm_index(td->pwm)]); +} + +static uint32_t pwm_read_pcr(QTestState *qts, const TestData *td) +{ + return extract32(pwm_read(qts, td, PCR), pcr_base[pwm_index(td->pwm)], 4); +} + +static void pwm_write_pcr(QTestState *qts, const TestData *td, uint32_t value) +{ + pwm_write(qts, td, PCR, value << pcr_base[pwm_index(td->pwm)]); +} + +static uint32_t pwm_read_cnr(QTestState *qts, const TestData *td) +{ + return pwm_read(qts, td, td->pwm->cnr_offset); +} + +static void pwm_write_cnr(QTestState *qts, const TestData *td, uint32_t value) +{ + pwm_write(qts, td, td->pwm->cnr_offset, value); +} + +static uint32_t pwm_read_cmr(QTestState *qts, const TestData *td) +{ + return pwm_read(qts, td, td->pwm->cmr_offset); +} + +static void pwm_write_cmr(QTestState *qts, const TestData *td, uint32_t value) +{ + pwm_write(qts, td, td->pwm->cmr_offset, value); +} + +/* Check pwm registers can be reset to default value */ +static void test_init(gconstpointer test_data) +{ + const TestData *td = test_data; + QTestState *qts = qtest_init("-machine quanta-gsj"); + int module = pwm_module_index(td->module); + int pwm = pwm_index(td->pwm); + + g_assert_cmpuint(pwm_get_freq(qts, module, pwm), ==, 0); + g_assert_cmpuint(pwm_get_duty(qts, module, pwm), ==, 0); + + qtest_quit(qts); +} + +/* One-shot mode should not change frequency and duty cycle. */ +static void test_oneshot(gconstpointer test_data) +{ + const TestData *td = test_data; + QTestState *qts = qtest_init("-machine quanta-gsj"); + int module = pwm_module_index(td->module); + int pwm = pwm_index(td->pwm); + uint32_t ppr, csr, pcr; + int i, j; + + pcr = CH_EN; + for (i = 0; i < ARRAY_SIZE(ppr_list); ++i) { + ppr = ppr_list[i]; + pwm_write_ppr(qts, td, ppr); + + for (j = 0; j < ARRAY_SIZE(csr_list); ++j) { + csr = csr_list[j]; + pwm_write_csr(qts, td, csr); + pwm_write_pcr(qts, td, pcr); + + g_assert_cmpuint(pwm_read_ppr(qts, td), ==, ppr); + g_assert_cmpuint(pwm_read_csr(qts, td), ==, csr); + g_assert_cmpuint(pwm_read_pcr(qts, td), ==, pcr); + g_assert_cmpuint(pwm_get_freq(qts, module, pwm), ==, 0); + g_assert_cmpuint(pwm_get_duty(qts, module, pwm), ==, 0); + } + } + + qtest_quit(qts); +} + +/* In toggle mode, the PWM generates correct outputs. */ +static void test_toggle(gconstpointer test_data) +{ + const TestData *td = test_data; + QTestState *qts = qtest_init("-machine quanta-gsj"); + int module = pwm_module_index(td->module); + int pwm = pwm_index(td->pwm); + uint32_t ppr, csr, pcr, cnr, cmr; + int i, j, k, l; + uint64_t expected_freq, expected_duty; + + pcr = CH_EN | CH_MOD; + for (i = 0; i < ARRAY_SIZE(ppr_list); ++i) { + ppr = ppr_list[i]; + pwm_write_ppr(qts, td, ppr); + + for (j = 0; j < ARRAY_SIZE(csr_list); ++j) { + csr = csr_list[j]; + pwm_write_csr(qts, td, csr); + + for (k = 0; k < ARRAY_SIZE(cnr_list); ++k) { + cnr = cnr_list[k]; + pwm_write_cnr(qts, td, cnr); + + for (l = 0; l < ARRAY_SIZE(cmr_list); ++l) { + cmr = cmr_list[l]; + pwm_write_cmr(qts, td, cmr); + expected_freq = pwm_compute_freq(qts, ppr, csr, cnr); + expected_duty = pwm_compute_duty(cnr, cmr, false); + + pwm_write_pcr(qts, td, pcr); + g_assert_cmpuint(pwm_read_ppr(qts, td), ==, ppr); + g_assert_cmpuint(pwm_read_csr(qts, td), ==, csr); + g_assert_cmpuint(pwm_read_pcr(qts, td), ==, pcr); + g_assert_cmpuint(pwm_read_cnr(qts, td), ==, cnr); + g_assert_cmpuint(pwm_read_cmr(qts, td), ==, cmr); + g_assert_cmpuint(pwm_get_duty(qts, module, pwm), + ==, expected_duty); + if (expected_duty != 0 && expected_duty != 100) { + /* Duty cycle with 0 or 100 doesn't need frequency. */ + g_assert_cmpuint(pwm_get_freq(qts, module, pwm), + ==, expected_freq); + } + + /* Test inverted mode */ + expected_duty = pwm_compute_duty(cnr, cmr, true); + pwm_write_pcr(qts, td, pcr | CH_INV); + g_assert_cmpuint(pwm_read_pcr(qts, td), ==, pcr | CH_INV); + g_assert_cmpuint(pwm_get_duty(qts, module, pwm), + ==, expected_duty); + if (expected_duty != 0 && expected_duty != 100) { + /* Duty cycle with 0 or 100 doesn't need frequency. */ + g_assert_cmpuint(pwm_get_freq(qts, module, pwm), + ==, expected_freq); + } + + } + } + } + } + + qtest_quit(qts); +} + +static void pwm_add_test(const char *name, const TestData* td, + GTestDataFunc fn) +{ + g_autofree char *full_name = g_strdup_printf( + "npcm7xx_pwm/module[%d]/pwm[%d]/%s", pwm_module_index(td->module), + pwm_index(td->pwm), name); + qtest_add_data_func(full_name, td, fn); +} +#define add_test(name, td) pwm_add_test(#name, td, test_##name) + +int main(int argc, char **argv) +{ + TestData test_data_list[ARRAY_SIZE(pwm_module_list) * ARRAY_SIZE(pwm_list)]; + + g_test_init(&argc, &argv, NULL); + + for (int i = 0; i < ARRAY_SIZE(pwm_module_list); ++i) { + for (int j = 0; j < ARRAY_SIZE(pwm_list); ++j) { + TestData *td = &test_data_list[i * ARRAY_SIZE(pwm_list) + j]; + + td->module = &pwm_module_list[i]; + td->pwm = &pwm_list[j]; + + add_test(init, td); + add_test(oneshot, td); + add_test(toggle, td); + } + } + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_sparc64 = \ qtests_npcm7xx = \ ['npcm7xx_adc-test', 'npcm7xx_gpio-test', + 'npcm7xx_pwm-test', 'npcm7xx_rng-test', 'npcm7xx_timer-test', 'npcm7xx_watchdog_timer-test'] -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> A device shouldn't access its parent object which is QOM internal. Instead it should use type cast for this purporse. This patch fixes this issue for all NPCM7XX Devices. Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210108190945.949196-7-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 2 +- hw/mem/npcm7xx_mc.c | 2 +- hw/misc/npcm7xx_clk.c | 2 +- hw/misc/npcm7xx_gcr.c | 2 +- hw/misc/npcm7xx_rng.c | 2 +- hw/nvram/npcm7xx_otp.c | 2 +- hw/ssi/npcm7xx_fiu.c | 2 +- 7 files changed, 7 insertions(+), 7 deletions(-) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ static NPCM7xxState *npcm7xx_create_soc(MachineState *machine, uint32_t hw_straps) { NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_GET_CLASS(machine); - MachineClass *mc = &nmc->parent; + MachineClass *mc = MACHINE_CLASS(nmc); Object *obj; if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { diff --git a/hw/mem/npcm7xx_mc.c b/hw/mem/npcm7xx_mc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/mem/npcm7xx_mc.c +++ b/hw/mem/npcm7xx_mc.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_mc_realize(DeviceState *dev, Error **errp) memory_region_init_io(&s->mmio, OBJECT(s), &npcm7xx_mc_ops, s, "regs", NPCM7XX_MC_REGS_SIZE); - sysbus_init_mmio(&s->parent, &s->mmio); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->mmio); } static void npcm7xx_mc_class_init(ObjectClass *klass, void *data) diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_clk.c +++ b/hw/misc/npcm7xx_clk.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_init(Object *obj) memory_region_init_io(&s->iomem, obj, &npcm7xx_clk_ops, s, TYPE_NPCM7XX_CLK, 4 * KiB); - sysbus_init_mmio(&s->parent, &s->iomem); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); } static int npcm7xx_clk_post_load(void *opaque, int version_id) diff --git a/hw/misc/npcm7xx_gcr.c b/hw/misc/npcm7xx_gcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_gcr.c +++ b/hw/misc/npcm7xx_gcr.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_gcr_init(Object *obj) memory_region_init_io(&s->iomem, obj, &npcm7xx_gcr_ops, s, TYPE_NPCM7XX_GCR, 4 * KiB); - sysbus_init_mmio(&s->parent, &s->iomem); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); } static const VMStateDescription vmstate_npcm7xx_gcr = { diff --git a/hw/misc/npcm7xx_rng.c b/hw/misc/npcm7xx_rng.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_rng.c +++ b/hw/misc/npcm7xx_rng.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_rng_init(Object *obj) memory_region_init_io(&s->iomem, obj, &npcm7xx_rng_ops, s, "regs", NPCM7XX_RNG_REGS_SIZE); - sysbus_init_mmio(&s->parent, &s->iomem); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); } static const VMStateDescription vmstate_npcm7xx_rng = { diff --git a/hw/nvram/npcm7xx_otp.c b/hw/nvram/npcm7xx_otp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/npcm7xx_otp.c +++ b/hw/nvram/npcm7xx_otp.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_otp_realize(DeviceState *dev, Error **errp) { NPCM7xxOTPClass *oc = NPCM7XX_OTP_GET_CLASS(dev); NPCM7xxOTPState *s = NPCM7XX_OTP(dev); - SysBusDevice *sbd = &s->parent; + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); memset(s->array, 0, sizeof(s->array)); diff --git a/hw/ssi/npcm7xx_fiu.c b/hw/ssi/npcm7xx_fiu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/npcm7xx_fiu.c +++ b/hw/ssi/npcm7xx_fiu.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_fiu_hold_reset(Object *obj) static void npcm7xx_fiu_realize(DeviceState *dev, Error **errp) { NPCM7xxFIUState *s = NPCM7XX_FIU(dev); - SysBusDevice *sbd = &s->parent; + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); int i; if (s->cs_count <= 0) { -- 2.20.1 From: Roman Bolshakov <r.bolshakov@yadro.com> ui/cocoa.m:1188:44: warning: 'openFile:' is deprecated: first deprecated in macOS 11.0 - Use -[NSWorkspace openURL:] instead. [-Wdeprecated-declarations] if ([[NSWorkspace sharedWorkspace] openFile: full_file_path] == YES) { ^ /Library/Developer/CommandLineTools/SDKs/MacOSX.sdk/System/Library/Frameworks/AppKit.framework/Headers/NSWorkspace.h:350:1: note: 'openFile:' has been explicitly marked deprecated here - (BOOL)openFile:(NSString *)fullPath API_DEPRECATED("Use -[NSWorkspace openURL:] instead.", macos(10.0, 11.0)); ^ Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210102150718.47618-1-r.bolshakov@yadro.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- ui/cocoa.m | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/ui/cocoa.m b/ui/cocoa.m index XXXXXXX..XXXXXXX 100644 --- a/ui/cocoa.m +++ b/ui/cocoa.m @@ -XXX,XX +XXX,XX @@ QemuCocoaView *cocoaView; /* Where to look for local files */ NSString *path_array[] = {@"../share/doc/qemu/", @"../doc/qemu/", @"docs/"}; NSString *full_file_path; + NSURL *full_file_url; /* iterate thru the possible paths until the file is found */ int index; @@ -XXX,XX +XXX,XX @@ QemuCocoaView *cocoaView; full_file_path = [full_file_path stringByDeletingLastPathComponent]; full_file_path = [NSString stringWithFormat: @"%@/%@%@", full_file_path, path_array[index], filename]; - if ([[NSWorkspace sharedWorkspace] openFile: full_file_path] == YES) { + full_file_url = [NSURL fileURLWithPath: full_file_path + isDirectory: false]; + if ([[NSWorkspace sharedWorkspace] openURL: full_file_url] == YES) { return; } } -- 2.20.1