Arm queue; some of the simpler stuff, things other have reviewed (thanks!), etc. -- PMM The following changes since commit 5d2f557b47dfbf8f23277a5bdd8473d4607c681a: Merge remote-tracking branch 'remotes/kraxel/tags/vga-20200605-pull-request' into staging (2020-06-05 13:53:05 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200605 for you to fetch changes up to 2c35a39eda0b16c2ed85c94cec204bf5efb97812: target/arm: Convert Neon one-register-and-immediate insns to decodetree (2020-06-05 17:23:10 +0100) ---------------------------------------------------------------- target-arm queue: hw/ssi/imx_spi: Handle tx burst lengths other than 8 correctly hw/input/pxa2xx_keypad: Replace hw_error() by qemu_log_mask() hw/arm/pxa2xx: Replace printf() call by qemu_log_mask() target/arm: Convert crypto insns to gvec hw/adc/stm32f2xx_adc: Correct memory region size and access size tests/acceptance: Add a boot test for the xlnx-versal-virt machine docs/system: Document Aspeed boards raspi: Add model of the USB controller target/arm: Convert 2-reg-and-shift and 1-reg-imm Neon insns to decodetree ---------------------------------------------------------------- Cédric Le Goater (1): docs/system: Document Aspeed boards Eden Mikitas (2): hw/ssi/imx_spi: changed while statement to prevent underflow hw/ssi/imx_spi: Removed unnecessary cast of rx data received from slave Paul Zimmerman (7): raspi: add BCM2835 SOC MPHI emulation dwc-hsotg (dwc2) USB host controller register definitions dwc-hsotg (dwc2) USB host controller state definitions dwc-hsotg (dwc2) USB host controller emulation usb: add short-packet handling to usb-storage driver wire in the dwc-hsotg (dwc2) USB host controller emulation raspi2 acceptance test: add test for dwc-hsotg (dwc2) USB host Peter Maydell (9): target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree target/arm: Convert Neon VSHR 2-reg-shift insns to decodetree target/arm: Convert Neon VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree target/arm: Convert VQSHLU, VQSHL 2-reg-shift insns to decodetree target/arm: Convert Neon narrowing shifts with op==8 to decodetree target/arm: Convert Neon narrowing shifts with op==9 to decodetree target/arm: Convert Neon VSHLL, VMOVL to decodetree target/arm: Convert VCVT fixed-point ops to decodetree target/arm: Convert Neon one-register-and-immediate insns to decodetree Philippe Mathieu-Daudé (3): hw/input/pxa2xx_keypad: Replace hw_error() by qemu_log_mask() hw/arm/pxa2xx: Replace printf() call by qemu_log_mask() hw/adc/stm32f2xx_adc: Correct memory region size and access size Richard Henderson (6): target/arm: Convert aes and sm4 to gvec helpers target/arm: Convert rax1 to gvec helpers target/arm: Convert sha512 and sm3 to gvec helpers target/arm: Convert sha1 and sha256 to gvec helpers target/arm: Split helper_crypto_sha1_3reg target/arm: Split helper_crypto_sm3tt Thomas Huth (1): tests/acceptance: Add a boot test for the xlnx-versal-virt machine docs/system/arm/aspeed.rst | 85 ++ docs/system/target-arm.rst | 1 + hw/usb/hcd-dwc2.h | 190 +++++ include/hw/arm/bcm2835_peripherals.h | 5 +- include/hw/misc/bcm2835_mphi.h | 44 + include/hw/usb/dwc2-regs.h | 899 ++++++++++++++++++++ target/arm/helper.h | 45 +- target/arm/translate-a64.h | 3 + target/arm/vec_internal.h | 33 + target/arm/neon-dp.decode | 214 ++++- hw/adc/stm32f2xx_adc.c | 4 +- hw/arm/bcm2835_peripherals.c | 38 +- hw/arm/pxa2xx.c | 66 +- hw/input/pxa2xx_keypad.c | 10 +- hw/misc/bcm2835_mphi.c | 191 +++++ hw/ssi/imx_spi.c | 4 +- hw/usb/dev-storage.c | 15 +- hw/usb/hcd-dwc2.c | 1417 ++++++++++++++++++++++++++++++++ target/arm/crypto_helper.c | 267 ++++-- target/arm/translate-a64.c | 198 ++--- target/arm/translate-neon.inc.c | 796 ++++++++++++++---- target/arm/translate.c | 539 +----------- target/arm/vec_helper.c | 12 +- hw/misc/Makefile.objs | 1 + hw/usb/Kconfig | 5 + hw/usb/Makefile.objs | 1 + hw/usb/trace-events | 50 ++ tests/acceptance/boot_linux_console.py | 35 +- 28 files changed, 4258 insertions(+), 910 deletions(-) create mode 100644 docs/system/arm/aspeed.rst create mode 100644 hw/usb/hcd-dwc2.h create mode 100644 include/hw/misc/bcm2835_mphi.h create mode 100644 include/hw/usb/dwc2-regs.h create mode 100644 target/arm/vec_internal.h create mode 100644 hw/misc/bcm2835_mphi.c create mode 100644 hw/usb/hcd-dwc2.c From: Eden Mikitas <e.mikitas@gmail.com> The while statement in question only checked if tx_burst is not 0. tx_burst is a signed int, which is assigned the value put by the guest driver in ECSPI_CONREG. The burst length can be anywhere between 1 and 4096, and since tx_burst is always decremented by 8 it could possibly underflow, causing an infinite loop. Signed-off-by: Eden Mikitas <e.mikitas@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/imx_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/imx_spi.c +++ b/hw/ssi/imx_spi.c @@ -XXX,XX +XXX,XX @@ static void imx_spi_flush_txfifo(IMXSPIState *s) rx = 0; - while (tx_burst) { + while (tx_burst > 0) { uint8_t byte = tx & 0xff; DPRINTF("writing 0x%02x\n", (uint32_t)byte); -- 2.20.1 From: Eden Mikitas <e.mikitas@gmail.com> When inserting the value retrieved (rx) from the spi slave, rx is pushed to rx_fifo after being cast to uint8_t. rx_fifo is a fifo32, and the rx register the driver uses is also 32 bit. This zeroes the 24 most significant bits of rx. This proved problematic with devices that expect to use the whole 32 bits of the rx register. Signed-off-by: Eden Mikitas <e.mikitas@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/imx_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/imx_spi.c +++ b/hw/ssi/imx_spi.c @@ -XXX,XX +XXX,XX @@ static void imx_spi_flush_txfifo(IMXSPIState *s) if (fifo32_is_full(&s->rx_fifo)) { s->regs[ECSPI_STATREG] |= ECSPI_STATREG_RO; } else { - fifo32_push(&s->rx_fifo, (uint8_t)rx); + fifo32_push(&s->rx_fifo, rx); } if (s->burst_length <= 0) { -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> hw_error() calls exit(). This a bit overkill when we can log the accesses as unimplemented or guest error. When fuzzing the devices, we don't want the whole process to exit. Replace some hw_error() calls by qemu_log_mask() (missed in commit 5a0001ec7e). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200525114123.21317-2-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/input/pxa2xx_keypad.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/input/pxa2xx_keypad.c b/hw/input/pxa2xx_keypad.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/pxa2xx_keypad.c +++ b/hw/input/pxa2xx_keypad.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "hw/hw.h" +#include "qemu/log.h" #include "hw/irq.h" #include "migration/vmstate.h" #include "hw/arm/pxa.h" @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_keypad_read(void *opaque, hwaddr offset, return s->kpkdi; break; default: - hw_error("%s: Bad offset " REG_FMT "\n", __func__, offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_keypad_write(void *opaque, hwaddr offset, break; default: - hw_error("%s: Bad offset " REG_FMT "\n", __func__, offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } } -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Replace printf() calls by qemu_log_mask(), which is disabled by default. This avoid flooding the terminal when fuzzing the device. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200525114123.21317-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx.c | 66 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 49 insertions(+), 17 deletions(-) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/blockdev.h" #include "sysemu/qtest.h" #include "qemu/cutils.h" +#include "qemu/log.h" static struct { hwaddr io_base; @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_pm_read(void *opaque, hwaddr addr, return s->pm_regs[addr >> 2]; default: fail: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pm_write(void *opaque, hwaddr addr, s->pm_regs[addr >> 2] = value; break; } - - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_cm_read(void *opaque, hwaddr addr, return s->cm_regs[CCCR >> 2] | (3 << 28); default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_cm_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_mm_read(void *opaque, hwaddr addr, return s->mm_regs[addr >> 2]; /* fall through */ default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_mm_write(void *opaque, hwaddr addr, } default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_ssp_read(void *opaque, hwaddr addr, case SSACD: return s->ssacd; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_ssp_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_rtc_read(void *opaque, hwaddr addr, else return s->last_swcr; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_rtc_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_i2c_read(void *opaque, hwaddr addr, s->ibmr = 0; return s->ibmr; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_i2c_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_i2s_read(void *opaque, hwaddr addr, } return 0; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_i2s_write(void *opaque, hwaddr addr, } break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_fir_read(void *opaque, hwaddr addr, case ICFOR: return s->rx_len; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_fir_write(void *opaque, hwaddr addr, case ICFOR: break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> With this conversion, we will be able to use the same helpers with sve. In particular, pass 3 vector parameters for the 3-operand operations; for advsimd the destination register is also an input. This also fixes a bug in which we failed to clear the high bits of the SVE register after an AdvSIMD operation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 6 ++-- target/arm/vec_internal.h | 33 +++++++++++++++++ target/arm/crypto_helper.c | 72 +++++++++++++++++++++++++++----------- target/arm/translate-a64.c | 55 ++++++++++++++++++----------- target/arm/translate.c | 27 +++++++------- target/arm/vec_helper.c | 12 +------ 6 files changed, 138 insertions(+), 67 deletions(-) create mode 100644 target/arm/vec_internal.h diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(neon_qzip8, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_2(neon_qzip16, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha1_3reg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) DEF_HELPER_FLAGS_3(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/vec_internal.h @@ -XXX,XX +XXX,XX @@ +/* + * ARM AdvSIMD / SVE Vector Helpers + * + * Copyright (c) 2020 Linaro + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_ARM_VEC_INTERNALS_H +#define TARGET_ARM_VEC_INTERNALS_H + +static inline void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) +{ + uint64_t *d = vd + opr_sz; + uintptr_t i; + + for (i = opr_sz; i < max_sz; i += 8) { + *d++ = 0; + } +} + +#endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" +#include "tcg/tcg-gvec-desc.h" #include "crypto/aes.h" +#include "vec_internal.h" union CRYPTO_STATE { uint8_t bytes[16]; @@ -XXX,XX +XXX,XX @@ union CRYPTO_STATE { #define CR_ST_WORD(state, i) (state.words[i]) #endif -void HELPER(crypto_aese)(void *vd, void *vm, uint32_t decrypt) +static void do_crypto_aese(uint64_t *rd, uint64_t *rn, + uint64_t *rm, bool decrypt) { static uint8_t const * const sbox[2] = { AES_sbox, AES_isbox }; static uint8_t const * const shift[2] = { AES_shifts, AES_ishifts }; - uint64_t *rd = vd; - uint64_t *rm = vm; union CRYPTO_STATE rk = { .l = { rm[0], rm[1] } }; - union CRYPTO_STATE st = { .l = { rd[0], rd[1] } }; + union CRYPTO_STATE st = { .l = { rn[0], rn[1] } }; int i; - assert(decrypt < 2); - /* xor state vector with round key */ rk.l[0] ^= st.l[0]; rk.l[1] ^= st.l[1]; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_aese)(void *vd, void *vm, uint32_t decrypt) rd[1] = st.l[1]; } -void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t decrypt) +void HELPER(crypto_aese)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + bool decrypt = simd_data(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_aese(vd + i, vn + i, vm + i, decrypt); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + +static void do_crypto_aesmc(uint64_t *rd, uint64_t *rm, bool decrypt) { static uint32_t const mc[][256] = { { /* MixColumns lookup table */ @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t decrypt) 0xbe805d9f, 0xb58d5491, 0xa89a4f83, 0xa397468d, } }; - uint64_t *rd = vd; - uint64_t *rm = vm; union CRYPTO_STATE st = { .l = { rm[0], rm[1] } }; int i; - assert(decrypt < 2); - for (i = 0; i < 16; i += 4) { CR_ST_WORD(st, i >> 2) = mc[decrypt][CR_ST_BYTE(st, i)] ^ @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t decrypt) rd[1] = st.l[1]; } +void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + bool decrypt = simd_data(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_aesmc(vd + i, vm + i, decrypt); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + /* * SHA-1 logical functions */ @@ -XXX,XX +XXX,XX @@ static uint8_t const sm4_sbox[] = { 0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48, }; -void HELPER(crypto_sm4e)(void *vd, void *vn) +static void do_crypto_sm4e(uint64_t *rd, uint64_t *rn, uint64_t *rm) { - uint64_t *rd = vd; - uint64_t *rn = vn; - union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; - union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE d = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE n = { .l = { rm[0], rm[1] } }; uint32_t t, i; for (i = 0; i < 4; i++) { @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm4e)(void *vd, void *vn) rd[1] = d.l[1]; } -void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm) +void HELPER(crypto_sm4e)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_sm4e(vd + i, vn + i, vm + i); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + +static void do_crypto_sm4ekey(uint64_t *rd, uint64_t *rn, uint64_t *rm) { - uint64_t *rd = vd; - uint64_t *rn = vn; - uint64_t *rm = vm; union CRYPTO_STATE d; union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm) rd[0] = d.l[0]; rd[1] = d.l[1]; } + +void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_sm4ekey(vd + i, vn + i, vm + i); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} 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 gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm, is_q ? 16 : 8, vec_full_reg_size(s)); } +/* Expand a 2-operand operation using an out-of-line helper. */ +static void gen_gvec_op2_ool(DisasContext *s, bool is_q, int rd, + int rn, int data, gen_helper_gvec_2 *fn) +{ + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); +} + /* Expand a 3-operand operation using an out-of-line helper. */ static void gen_gvec_op3_ool(DisasContext *s, bool is_q, int rd, int rn, int rm, int data, gen_helper_gvec_3 *fn) @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); int decrypt; - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; - TCGv_i32 tcg_decrypt; - CryptoThreeOpIntFn *genfn; + gen_helper_gvec_2 *genfn2 = NULL; + gen_helper_gvec_3 *genfn3 = NULL; if (!dc_isar_feature(aa64_aes, s) || size != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) switch (opcode) { case 0x4: /* AESE */ decrypt = 0; - genfn = gen_helper_crypto_aese; + genfn3 = gen_helper_crypto_aese; break; case 0x6: /* AESMC */ decrypt = 0; - genfn = gen_helper_crypto_aesmc; + genfn2 = gen_helper_crypto_aesmc; break; case 0x5: /* AESD */ decrypt = 1; - genfn = gen_helper_crypto_aese; + genfn3 = gen_helper_crypto_aese; break; case 0x7: /* AESIMC */ decrypt = 1; - genfn = gen_helper_crypto_aesmc; + genfn2 = gen_helper_crypto_aesmc; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_decrypt = tcg_const_i32(decrypt); - - genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_decrypt); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_i32(tcg_decrypt); + if (genfn2) { + gen_gvec_op2_ool(s, true, rd, rn, decrypt, genfn2); + } else { + gen_gvec_op3_ool(s, true, rd, rd, rn, decrypt, genfn3); + } } /* Crypto three-reg SHA @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); bool feature; - CryptoThreeOpFn *genfn; + CryptoThreeOpFn *genfn = NULL; + gen_helper_gvec_3 *oolfn = NULL; if (o == 0) { switch (opcode) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) break; case 2: /* SM4EKEY */ feature = dc_isar_feature(aa64_sm4, s); - genfn = gen_helper_crypto_sm4ekey; + oolfn = gen_helper_crypto_sm4ekey; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) return; } + if (oolfn) { + gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); + return; + } + if (genfn) { TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; bool feature; CryptoTwoOpFn *genfn; + gen_helper_gvec_3 *oolfn = NULL; switch (opcode) { case 0: /* SHA512SU0 */ @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) break; case 1: /* SM4E */ feature = dc_isar_feature(aa64_sm4, s); - genfn = gen_helper_crypto_sm4e; + oolfn = gen_helper_crypto_sm4e; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) return; } + if (oolfn) { + gen_gvec_op3_ool(s, true, rd, rd, rn, 0, oolfn); + return; + } + tcg_rd_ptr = vec_full_reg_ptr(s, rd); tcg_rn_ptr = vec_full_reg_ptr(s, rn); 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) { return 1; } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rm); - - /* Bit 6 is the lowest opcode bit; it distinguishes between - * encryption (AESE/AESMC) and decryption (AESD/AESIMC) - */ - tmp3 = tcg_const_i32(extract32(insn, 6, 1)); - + /* + * Bit 6 is the lowest opcode bit; it distinguishes + * between encryption (AESE/AESMC) and decryption + * (AESD/AESIMC). + */ if (op == NEON_2RM_AESE) { - gen_helper_crypto_aese(ptr1, ptr2, tmp3); + tcg_gen_gvec_3_ool(vfp_reg_offset(true, rd), + vfp_reg_offset(true, rd), + vfp_reg_offset(true, rm), + 16, 16, extract32(insn, 6, 1), + gen_helper_crypto_aese); } else { - gen_helper_crypto_aesmc(ptr1, ptr2, tmp3); + tcg_gen_gvec_2_ool(vfp_reg_offset(true, rd), + vfp_reg_offset(true, rm), + 16, 16, extract32(insn, 6, 1), + gen_helper_crypto_aesmc); } - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_i32(tmp3); break; case NEON_2RM_SHA1H: if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) { diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" - +#include "vec_internal.h" /* Note that vector data is stored in host-endian 64-bit chunks, so addressing units smaller than that needs a host-endian fixup. */ @@ -XXX,XX +XXX,XX @@ #define H4(x) (x) #endif -static void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) -{ - uint64_t *d = vd + opr_sz; - uintptr_t i; - - for (i = opr_sz; i < max_sz; i += 8) { - *d++ = 0; - } -} - /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ static int16_t inl_qrdmlah_s16(int16_t src1, int16_t src2, int16_t src3, uint32_t *sat) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> With this conversion, we will be able to use the same helpers with sve. This also fixes a bug in which we failed to clear the high bits of the SVE register after an AdvSIMD operation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 2 ++ target/arm/translate-a64.h | 3 ++ target/arm/crypto_helper.c | 11 +++++++ target/arm/translate-a64.c | 59 ++++++++++++++++++++------------------ 4 files changed, 47 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_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) bool disas_sve(DisasContext *, uint32_t); +void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm, uint32_t desc) } clear_tail(vd, opr_sz, simd_maxsz(desc)); } + +void HELPER(crypto_rax1)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = n[i] ^ rol64(m[i], 1); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} 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_crypto_two_reg_sha(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(tcg_rn_ptr); } +static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) +{ + tcg_gen_rotli_i64(d, m, 1); + tcg_gen_xor_i64(d, d, n); +} + +static void gen_rax1_vec(unsigned vece, TCGv_vec d, TCGv_vec n, TCGv_vec m) +{ + tcg_gen_rotli_vec(vece, d, m, 1); + tcg_gen_xor_vec(vece, d, d, n); +} + +void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_rotli_vec, 0 }; + static const GVecGen3 op = { + .fni8 = gen_rax1_i64, + .fniv = gen_rax1_vec, + .opt_opc = vecop_list, + .fno = gen_helper_crypto_rax1, + .vece = MO_64, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &op); +} + /* Crypto three-reg SHA512 * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 * +-----------------------+------+---+---+-----+--------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) bool feature; CryptoThreeOpFn *genfn = NULL; gen_helper_gvec_3 *oolfn = NULL; + GVecGen3Fn *gvecfn = NULL; if (o == 0) { switch (opcode) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) break; case 3: /* RAX1 */ feature = dc_isar_feature(aa64_sha3, s); - genfn = NULL; + gvecfn = gen_gvec_rax1; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) if (oolfn) { gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); - return; - } - - if (genfn) { + } else if (gvecfn) { + gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); + } else { TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; tcg_rd_ptr = vec_full_reg_ptr(s, rd); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(tcg_rd_ptr); tcg_temp_free_ptr(tcg_rn_ptr); tcg_temp_free_ptr(tcg_rm_ptr); - } else { - TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; - int pass; - - tcg_op1 = tcg_temp_new_i64(); - tcg_op2 = tcg_temp_new_i64(); - tcg_res[0] = tcg_temp_new_i64(); - tcg_res[1] = tcg_temp_new_i64(); - - for (pass = 0; pass < 2; pass++) { - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - - tcg_gen_rotli_i64(tcg_res[pass], tcg_op2, 1); - tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1); - } - write_vec_element(s, tcg_res[0], rd, 0, MO_64); - write_vec_element(s, tcg_res[1], rd, 1, MO_64); - - tcg_temp_free_i64(tcg_op1); - tcg_temp_free_i64(tcg_op2); - tcg_temp_free_i64(tcg_res[0]); - tcg_temp_free_i64(tcg_res[1]); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Do not yet convert the helpers to loop over opr_sz, but the descriptor allows the vector tail to be cleared. Which fixes an existing bug vs SVE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 15 +++++++----- target/arm/crypto_helper.c | 37 +++++++++++++++++++++++----- target/arm/translate-a64.c | 50 ++++++++++++-------------------------- 3 files changed, 55 insertions(+), 47 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_2(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_3(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha512su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) -DEF_HELPER_FLAGS_3(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ union CRYPTO_STATE { #define CR_ST_WORD(state, i) (state.words[i]) #endif +/* + * The caller has not been converted to full gvec, and so only + * modifies the low 16 bytes of the vector register. + */ +static void clear_tail_16(void *vd, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int max_sz = simd_maxsz(desc); + + assert(opr_sz == 16); + clear_tail(vd, opr_sz, max_sz); +} + static void do_crypto_aese(uint64_t *rd, uint64_t *rn, uint64_t *rm, bool decrypt) { @@ -XXX,XX +XXX,XX @@ static uint64_t s1_512(uint64_t x) return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6); } -void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm) rd[0] = d0; rd[1] = d1; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm) rd[0] = d0; rd[1] = d1; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha512su0)(void *vd, void *vn) +void HELPER(crypto_sha512su0)(void *vd, void *vn, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512su0)(void *vd, void *vn) rd[0] = d0; rd[1] = d1; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm) rd[0] += s1_512(rn[0]) + rm[0]; rd[1] += s1_512(rn[1]) + rm[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm) +void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm) +void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, 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_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); bool feature; - CryptoThreeOpFn *genfn = NULL; gen_helper_gvec_3 *oolfn = NULL; GVecGen3Fn *gvecfn = NULL; @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SHA512H */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512h; + oolfn = gen_helper_crypto_sha512h; break; case 1: /* SHA512H2 */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512h2; + oolfn = gen_helper_crypto_sha512h2; break; case 2: /* SHA512SU1 */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512su1; + oolfn = gen_helper_crypto_sha512su1; break; case 3: /* RAX1 */ feature = dc_isar_feature(aa64_sha3, s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SM3PARTW1 */ feature = dc_isar_feature(aa64_sm3, s); - genfn = gen_helper_crypto_sm3partw1; + oolfn = gen_helper_crypto_sm3partw1; break; case 1: /* SM3PARTW2 */ feature = dc_isar_feature(aa64_sm3, s); - genfn = gen_helper_crypto_sm3partw2; + oolfn = gen_helper_crypto_sm3partw2; break; case 2: /* SM4EKEY */ feature = dc_isar_feature(aa64_sm4, s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) if (oolfn) { gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); - } else if (gvecfn) { - gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); } else { - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_rm_ptr = vec_full_reg_ptr(s, rm); - - genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); + gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); } } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 10, 2); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; bool feature; - CryptoTwoOpFn *genfn; - gen_helper_gvec_3 *oolfn = NULL; switch (opcode) { case 0: /* SHA512SU0 */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512su0; break; case 1: /* SM4E */ feature = dc_isar_feature(aa64_sm4, s); - oolfn = gen_helper_crypto_sm4e; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) return; } - if (oolfn) { - gen_gvec_op3_ool(s, true, rd, rd, rn, 0, oolfn); - return; + switch (opcode) { + case 0: /* SHA512SU0 */ + gen_gvec_op2_ool(s, true, rd, rn, 0, gen_helper_crypto_sha512su0); + break; + case 1: /* SM4E */ + gen_gvec_op3_ool(s, true, rd, rd, rn, 0, gen_helper_crypto_sm4e); + break; + default: + g_assert_not_reached(); } - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - - genfn(tcg_rd_ptr, tcg_rn_ptr); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); } /* Crypto four-register -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Do not yet convert the helpers to loop over opr_sz, but the descriptor allows the vector tail to be cleared. Which fixes an existing bug vs SVE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 12 ++-- target/arm/neon-dp.decode | 12 ++-- target/arm/crypto_helper.c | 24 +++++-- target/arm/translate-a64.c | 34 ++++----- target/arm/translate-neon.inc.c | 124 +++++--------------------------- target/arm/translate.c | 24 ++----- 6 files changed, 67 insertions(+), 163 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha1_3reg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_2(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr, i32) -DEF_HELPER_FLAGS_3(crypto_sha256h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sha256h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VPADD_3s 1111 001 0 0 . .. .... .... 1011 . . . 1 .... @3same_q0 VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same +@3same_crypto .... .... .... .... .... .... .... .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 q=1 + SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp -SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp -SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp -SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto VFMA_fp_3s 1111 001 0 0 . 0 . .... .... 1100 ... 1 .... @3same_fp VFMS_fp_3s 1111 001 0 0 . 1 . .... .... 1100 ... 1 .... @3same_fp diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha1_3reg)(void *vd, void *vn, void *vm, uint32_t op) rd[1] = d.l[1]; } -void HELPER(crypto_sha1h)(void *vd, void *vm) +void HELPER(crypto_sha1h)(void *vd, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rm = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha1h)(void *vd, void *vm) rd[0] = m.l[0]; rd[1] = m.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha1su1)(void *vd, void *vm) +void HELPER(crypto_sha1su1)(void *vd, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rm = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha1su1)(void *vd, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } /* @@ -XXX,XX +XXX,XX @@ static uint32_t s1(uint32_t x) return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10); } -void HELPER(crypto_sha256h)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha256h)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256h)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha256h2)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha256h2)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256h2)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha256su0)(void *vd, void *vm) +void HELPER(crypto_sha256su0)(void *vd, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rm = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256su0)(void *vd, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } /* 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_crypto_three_reg_sha(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - CryptoThreeOpFn *genfn; - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; + gen_helper_gvec_3 *genfn; bool feature; if (size != 0) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) return; } - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_rm_ptr = vec_full_reg_ptr(s, rm); - if (genfn) { - genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr); + gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); } else { TCGv_i32 tcg_opcode = tcg_const_i32(opcode); + TCGv_ptr tcg_rd_ptr = vec_full_reg_ptr(s, rd); + TCGv_ptr tcg_rn_ptr = vec_full_reg_ptr(s, rn); + TCGv_ptr tcg_rm_ptr = vec_full_reg_ptr(s, rm); gen_helper_crypto_sha1_3reg(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr, tcg_opcode); - tcg_temp_free_i32(tcg_opcode); - } - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); + tcg_temp_free_i32(tcg_opcode); + tcg_temp_free_ptr(tcg_rd_ptr); + tcg_temp_free_ptr(tcg_rn_ptr); + tcg_temp_free_ptr(tcg_rm_ptr); + } } /* Crypto two-reg SHA @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 12, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - CryptoTwoOpFn *genfn; + gen_helper_gvec_2 *genfn; bool feature; - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; if (size != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - - genfn(tcg_rd_ptr, tcg_rn_ptr); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); + gen_gvec_op2_ool(s, true, rd, rn, 0, genfn); } static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_CMP(VCGE_S, TCG_COND_GE) DO_3SAME_CMP(VCGE_U, TCG_COND_GEU) DO_3SAME_CMP(VCEQ, TCG_COND_EQ) -static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) -{ - tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, - 0, gen_helper_gvec_pmul_b); -} +#define WRAP_OOL_FN(WRAPNAME, FUNC) \ + static void WRAPNAME(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, \ + uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) \ + { \ + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, 0, FUNC); \ + } + +WRAP_OOL_FN(gen_VMUL_p_3s, gen_helper_gvec_pmul_b) static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_SHA1_3s(DisasContext *s, arg_SHA1_3s *a) return true; } -static bool trans_SHA256H_3s(DisasContext *s, arg_SHA256H_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha2, s)) { - return false; +#define DO_SHA2(NAME, FUNC) \ + WRAP_OOL_FN(gen_##NAME##_3s, FUNC) \ + static bool trans_##NAME##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (!dc_isar_feature(aa32_sha2, s)) { \ + return false; \ + } \ + return do_3same(s, a, gen_##NAME##_3s); \ } - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - gen_helper_crypto_sha256h(ptr1, ptr2, ptr3); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} - -static bool trans_SHA256H2_3s(DisasContext *s, arg_SHA256H2_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha2, s)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - gen_helper_crypto_sha256h2(ptr1, ptr2, ptr3); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} - -static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha2, s)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - gen_helper_crypto_sha256su1(ptr1, ptr2, ptr3); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} +DO_SHA2(SHA256H, gen_helper_crypto_sha256h) +DO_SHA2(SHA256H2, gen_helper_crypto_sha256h2) +DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) #define DO_3SAME_64(INSN, FUNC) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) int vec_size; uint32_t imm; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; - TCGv_ptr ptr1, ptr2; + TCGv_ptr ptr1; TCGv_i64 tmp64; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) { return 1; } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rm); - - gen_helper_crypto_sha1h(ptr1, ptr2); - - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); + tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0, + gen_helper_crypto_sha1h); break; case NEON_2RM_SHA1SU1: if ((rm | rd) & 1) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } else if (!dc_isar_feature(aa32_sha1, s)) { return 1; } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rm); - if (q) { - gen_helper_crypto_sha256su0(ptr1, ptr2); - } else { - gen_helper_crypto_sha1su1(ptr1, ptr2); - } - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); + tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0, + q ? gen_helper_crypto_sha256su0 + : gen_helper_crypto_sha1su1); break; - case NEON_2RM_VMVN: tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size); break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than passing an opcode to a helper, fully decode the operation at translate time. Use clear_tail_16 to zap the balance of the SVE register with the AdvSIMD write. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 5 +- target/arm/neon-dp.decode | 6 +- target/arm/crypto_helper.c | 99 +++++++++++++++++++++------------ target/arm/translate-a64.c | 29 ++++------ target/arm/translate-neon.inc.c | 46 ++++----------- 5 files changed, 93 insertions(+), 92 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(crypto_sha1_3reg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1su0, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1c, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1m, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same @3same_crypto .... .... .... .... .... .... .... .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 q=1 -SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA1C_3s 1111 001 0 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA1P_3s 1111 001 0 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA1M_3s 1111 001 0 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA1SU0_3s 1111 001 0 0 . 11 .... .... 1100 . 1 . 0 .... @3same_crypto SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ union CRYPTO_STATE { }; #ifdef HOST_WORDS_BIGENDIAN -#define CR_ST_BYTE(state, i) (state.bytes[(15 - (i)) ^ 8]) -#define CR_ST_WORD(state, i) (state.words[(3 - (i)) ^ 2]) +#define CR_ST_BYTE(state, i) ((state).bytes[(15 - (i)) ^ 8]) +#define CR_ST_WORD(state, i) ((state).words[(3 - (i)) ^ 2]) #else -#define CR_ST_BYTE(state, i) (state.bytes[i]) -#define CR_ST_WORD(state, i) (state.words[i]) +#define CR_ST_BYTE(state, i) ((state).bytes[i]) +#define CR_ST_WORD(state, i) ((state).words[i]) #endif /* @@ -XXX,XX +XXX,XX @@ static uint32_t maj(uint32_t x, uint32_t y, uint32_t z) return (x & y) | ((x | y) & z); } -void HELPER(crypto_sha1_3reg)(void *vd, void *vn, void *vm, uint32_t op) +void HELPER(crypto_sha1su0)(void *vd, void *vn, void *vm, uint32_t desc) +{ + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t d0, d1; + + d0 = d[1] ^ d[0] ^ m[0]; + d1 = n[0] ^ d[1] ^ m[1]; + d[0] = d0; + d[1] = d1; + + clear_tail_16(vd, desc); +} + +static inline void crypto_sha1_3reg(uint64_t *rd, uint64_t *rn, + uint64_t *rm, uint32_t desc, + uint32_t (*fn)(union CRYPTO_STATE *d)) { - uint64_t *rd = vd; - uint64_t *rn = vn; - uint64_t *rm = vm; union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + int i; - if (op == 3) { /* sha1su0 */ - d.l[0] ^= d.l[1] ^ m.l[0]; - d.l[1] ^= n.l[0] ^ m.l[1]; - } else { - int i; + for (i = 0; i < 4; i++) { + uint32_t t = fn(&d); - for (i = 0; i < 4; i++) { - uint32_t t; + t += rol32(CR_ST_WORD(d, 0), 5) + CR_ST_WORD(n, 0) + + CR_ST_WORD(m, i); - switch (op) { - case 0: /* sha1c */ - t = cho(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); - break; - case 1: /* sha1p */ - t = par(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); - break; - case 2: /* sha1m */ - t = maj(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); - break; - default: - g_assert_not_reached(); - } - t += rol32(CR_ST_WORD(d, 0), 5) + CR_ST_WORD(n, 0) - + CR_ST_WORD(m, i); - - CR_ST_WORD(n, 0) = CR_ST_WORD(d, 3); - CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); - CR_ST_WORD(d, 2) = ror32(CR_ST_WORD(d, 1), 2); - CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); - CR_ST_WORD(d, 0) = t; - } + CR_ST_WORD(n, 0) = CR_ST_WORD(d, 3); + CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); + CR_ST_WORD(d, 2) = ror32(CR_ST_WORD(d, 1), 2); + CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); + CR_ST_WORD(d, 0) = t; } rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(rd, desc); +} + +static uint32_t do_sha1c(union CRYPTO_STATE *d) +{ + return cho(CR_ST_WORD(*d, 1), CR_ST_WORD(*d, 2), CR_ST_WORD(*d, 3)); +} + +void HELPER(crypto_sha1c)(void *vd, void *vn, void *vm, uint32_t desc) +{ + crypto_sha1_3reg(vd, vn, vm, desc, do_sha1c); +} + +static uint32_t do_sha1p(union CRYPTO_STATE *d) +{ + return par(CR_ST_WORD(*d, 1), CR_ST_WORD(*d, 2), CR_ST_WORD(*d, 3)); +} + +void HELPER(crypto_sha1p)(void *vd, void *vn, void *vm, uint32_t desc) +{ + crypto_sha1_3reg(vd, vn, vm, desc, do_sha1p); +} + +static uint32_t do_sha1m(union CRYPTO_STATE *d) +{ + return maj(CR_ST_WORD(*d, 1), CR_ST_WORD(*d, 2), CR_ST_WORD(*d, 3)); +} + +void HELPER(crypto_sha1m)(void *vd, void *vn, void *vm, uint32_t desc) +{ + crypto_sha1_3reg(vd, vn, vm, desc, do_sha1m); } void HELPER(crypto_sha1h)(void *vd, void *vm, uint32_t desc) 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_crypto_three_reg_sha(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SHA1C */ + genfn = gen_helper_crypto_sha1c; + feature = dc_isar_feature(aa64_sha1, s); + break; case 1: /* SHA1P */ + genfn = gen_helper_crypto_sha1p; + feature = dc_isar_feature(aa64_sha1, s); + break; case 2: /* SHA1M */ + genfn = gen_helper_crypto_sha1m; + feature = dc_isar_feature(aa64_sha1, s); + break; case 3: /* SHA1SU0 */ - genfn = NULL; + genfn = gen_helper_crypto_sha1su0; feature = dc_isar_feature(aa64_sha1, s); break; case 4: /* SHA256H */ @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - if (genfn) { - gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); - } else { - TCGv_i32 tcg_opcode = tcg_const_i32(opcode); - TCGv_ptr tcg_rd_ptr = vec_full_reg_ptr(s, rd); - TCGv_ptr tcg_rn_ptr = vec_full_reg_ptr(s, rn); - TCGv_ptr tcg_rm_ptr = vec_full_reg_ptr(s, rm); - - gen_helper_crypto_sha1_3reg(tcg_rd_ptr, tcg_rn_ptr, - tcg_rm_ptr, tcg_opcode); - - tcg_temp_free_i32(tcg_opcode); - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); - } + gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); } /* Crypto two-reg SHA diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) DO_VQRDMLAH(VQRDMLAH, gen_gvec_sqrdmlah_qc) DO_VQRDMLAH(VQRDMLSH, gen_gvec_sqrdmlsh_qc) -static bool trans_SHA1_3s(DisasContext *s, arg_SHA1_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - TCGv_i32 tmp; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha1, s)) { - return false; +#define DO_SHA1(NAME, FUNC) \ + WRAP_OOL_FN(gen_##NAME##_3s, FUNC) \ + static bool trans_##NAME##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (!dc_isar_feature(aa32_sha1, s)) { \ + return false; \ + } \ + return do_3same(s, a, gen_##NAME##_3s); \ } - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - tmp = tcg_const_i32(a->optype); - gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp); - tcg_temp_free_i32(tmp); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} +DO_SHA1(SHA1C, gen_helper_crypto_sha1c) +DO_SHA1(SHA1P, gen_helper_crypto_sha1p) +DO_SHA1(SHA1M, gen_helper_crypto_sha1m) +DO_SHA1(SHA1SU0, gen_helper_crypto_sha1su0) #define DO_SHA2(NAME, FUNC) \ WRAP_OOL_FN(gen_##NAME##_3s, FUNC) \ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than passing an opcode to a helper, fully decode the operation at translate time. Use clear_tail_16 to zap the balance of the SVE register with the AdvSIMD write. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 5 ++++- target/arm/crypto_helper.c | 24 ++++++++++++++++++------ target/arm/translate-a64.c | 21 +++++---------------- 3 files changed, 27 insertions(+), 23 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt1a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt1b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt2a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt2b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG, diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail_16(vd, desc); } -void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, - uint32_t opcode) +static inline void QEMU_ALWAYS_INLINE +crypto_sm3tt(uint64_t *rd, uint64_t *rn, uint64_t *rm, + uint32_t desc, uint32_t opcode) { - uint64_t *rd = vd; - uint64_t *rn = vn; - uint64_t *rm = vm; union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + uint32_t imm2 = simd_data(desc); uint32_t t; assert(imm2 < 4); @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, /* SM3TT2B */ t = cho(CR_ST_WORD(d, 3), CR_ST_WORD(d, 2), CR_ST_WORD(d, 1)); } else { - g_assert_not_reached(); + qemu_build_not_reached(); } t += CR_ST_WORD(d, 0) + CR_ST_WORD(m, imm2); @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(rd, desc); } +#define DO_SM3TT(NAME, OPCODE) \ + void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ + { crypto_sm3tt(vd, vn, vm, desc, OPCODE); } + +DO_SM3TT(crypto_sm3tt1a, 0) +DO_SM3TT(crypto_sm3tt1b, 1) +DO_SM3TT(crypto_sm3tt2a, 2) +DO_SM3TT(crypto_sm3tt2b, 3) + +#undef DO_SM3TT + static uint8_t const sm4_sbox[] = { 0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7, 0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05, 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_crypto_xar(DisasContext *s, uint32_t insn) */ static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) { + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_crypto_sm3tt1a, gen_helper_crypto_sm3tt1b, + gen_helper_crypto_sm3tt2a, gen_helper_crypto_sm3tt2b, + }; int opcode = extract32(insn, 10, 2); int imm2 = extract32(insn, 12, 2); int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; - TCGv_i32 tcg_imm2, tcg_opcode; if (!dc_isar_feature(aa64_sm3, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) return; } - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_rm_ptr = vec_full_reg_ptr(s, rm); - tcg_imm2 = tcg_const_i32(imm2); - tcg_opcode = tcg_const_i32(opcode); - - gen_helper_crypto_sm3tt(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr, tcg_imm2, - tcg_opcode); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); - tcg_temp_free_i32(tcg_imm2); - tcg_temp_free_i32(tcg_opcode); + gen_gvec_op3_ool(s, true, rd, rn, rm, imm2, fns[opcode]); } /* C3.6 Data processing - SIMD, inc Crypto -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The ADC region size is 256B, split as: - [0x00 - 0x4f] defined - [0x50 - 0xff] reserved All registers are 32-bit (thus when the datasheet mentions the last defined register is 0x4c, it means its address range is 0x4c .. 0x4f. This model implementation is also 32-bit. Set MemoryRegionOps 'impl' fields. See: 'RM0033 Reference manual Rev 8', Table 10.13.18 "ADC register map". Reported-by: Seth Kintigh <skintigh@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200603055915.17678-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/adc/stm32f2xx_adc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/adc/stm32f2xx_adc.c b/hw/adc/stm32f2xx_adc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/adc/stm32f2xx_adc.c +++ b/hw/adc/stm32f2xx_adc.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps stm32f2xx_adc_ops = { .read = stm32f2xx_adc_read, .write = stm32f2xx_adc_write, .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 4, + .impl.max_access_size = 4, }; static const VMStateDescription vmstate_stm32f2xx_adc = { @@ -XXX,XX +XXX,XX @@ static void stm32f2xx_adc_init(Object *obj) sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); memory_region_init_io(&s->mmio, obj, &stm32f2xx_adc_ops, s, - TYPE_STM32F2XX_ADC, 0xFF); + TYPE_STM32F2XX_ADC, 0x100); sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); } -- 2.20.1 From: Thomas Huth <thuth@redhat.com> As described by Edgar here: https://www.mail-archive.com/qemu-devel@nongnu.org/msg605124.html we can use the Ubuntu kernel for testing the xlnx-versal-virt machine. So let's add a boot test for this now. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200525141237.15243-1-thuth@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(LinuxKernelTest): console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) + def test_aarch64_xlnx_versal_virt(self): + """ + :avocado: tags=arch:aarch64 + :avocado: tags=machine:xlnx-versal-virt + :avocado: tags=device:pl011 + :avocado: tags=device:arm_gicv3 + """ + kernel_url = ('http://ports.ubuntu.com/ubuntu-ports/dists/' + 'bionic-updates/main/installer-arm64/current/images/' + 'netboot/ubuntu-installer/arm64/linux') + kernel_hash = '5bfc54cf7ed8157d93f6e5b0241e727b6dc22c50' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + + initrd_url = ('http://ports.ubuntu.com/ubuntu-ports/dists/' + 'bionic-updates/main/installer-arm64/current/images/' + 'netboot/ubuntu-installer/arm64/initrd.gz') + initrd_hash = 'd385d3e88d53e2004c5d43cbe668b458a094f772' + initrd_path = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + + self.vm.set_console() + self.vm.add_args('-m', '2G', + '-kernel', kernel_path, + '-initrd', initrd_path) + self.vm.launch() + self.wait_for_console_pattern('Checked W+X mappings: passed') + def test_arm_virt(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200602135050.593692-1-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/aspeed.rst | 85 ++++++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 1 + 2 files changed, 86 insertions(+) create mode 100644 docs/system/arm/aspeed.rst diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/aspeed.rst @@ -XXX,XX +XXX,XX @@ +Aspeed family boards (``*-bmc``, ``ast2500-evb``, ``ast2600-evb``) +================================================================== + +The QEMU Aspeed machines model BMCs of various OpenPOWER systems and +Aspeed evaluation boards. They are based on different releases of the +Aspeed SoC : the AST2400 integrating an ARM926EJ-S CPU (400MHz), the +AST2500 with an ARM1176JZS CPU (800MHz) and more recently the AST2600 +with dual cores ARM Cortex A7 CPUs (1.2GHz). + +The SoC comes with RAM, Gigabit ethernet, USB, SD/MMC, USB, SPI, I2C, +etc. + +AST2400 SoC based machines : + +- ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC + +AST2500 SoC based machines : + +- ``ast2500-evb`` Aspeed AST2500 Evaluation board +- ``romulus-bmc`` OpenPOWER Romulus POWER9 BMC +- ``witherspoon-bmc`` OpenPOWER Witherspoon POWER9 BMC +- ``sonorapass-bmc`` OCP SonoraPass BMC +- ``swift-bmc`` OpenPOWER Swift BMC POWER9 + +AST2600 SoC based machines : + +- ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex A7) +- ``tacoma-bmc`` OpenPOWER Witherspoon POWER9 AST2600 BMC + +Supported devices +----------------- + + * SMP (for the AST2600 Cortex-A7) + * Interrupt Controller (VIC) + * Timer Controller + * RTC Controller + * I2C Controller + * System Control Unit (SCU) + * SRAM mapping + * X-DMA Controller (basic interface) + * Static Memory Controller (SMC or FMC) - Only SPI Flash support + * SPI Memory Controller + * USB 2.0 Controller + * SD/MMC storage controllers + * SDRAM controller (dummy interface for basic settings and training) + * Watchdog Controller + * GPIO Controller (Master only) + * UART + * Ethernet controllers + + +Missing devices +--------------- + + * Coprocessor support + * ADC (out of tree implementation) + * PWM and Fan Controller + * LPC Bus Controller + * Slave GPIO Controller + * Super I/O Controller + * Hash/Crypto Engine + * PCI-Express 1 Controller + * Graphic Display Controller + * PECI Controller + * MCTP Controller + * Mailbox Controller + * Virtual UART + * eSPI Controller + * I3C Controller + +Boot options +------------ + +The Aspeed machines can be started using the -kernel option to load a +Linux kernel or from a firmare image which can be downloaded from the +OpenPOWER jenkins : + + https://openpower.xyz/ + +The image should be attached as an MTD drive. Run : + +.. code-block:: bash + + $ qemu-system-arm -M romulus-bmc -nic user \ + -drive file=flash-romulus,format=raw,if=mtd -nographic diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/realview arm/versatile arm/vexpress + arm/aspeed arm/musicpal arm/nseries arm/orangepi -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add BCM2835 SOC MPHI (Message-based Parallel Host Interface) emulation. It is very basic, only providing the FIQ interrupt needed to allow the dwc-otg USB host controller driver in the Raspbian kernel to function. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Acked-by: Philippe Mathieu-Daude <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200520235349.21215-2-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 2 + include/hw/misc/bcm2835_mphi.h | 44 ++++++ hw/arm/bcm2835_peripherals.c | 17 +++ hw/misc/bcm2835_mphi.c | 191 +++++++++++++++++++++++++++ hw/misc/Makefile.objs | 1 + 5 files changed, 255 insertions(+) create mode 100644 include/hw/misc/bcm2835_mphi.h create mode 100644 hw/misc/bcm2835_mphi.c diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/bcm2835_property.h" #include "hw/misc/bcm2835_rng.h" #include "hw/misc/bcm2835_mbox.h" +#include "hw/misc/bcm2835_mphi.h" #include "hw/misc/bcm2835_thermal.h" #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { qemu_irq irq, fiq; BCM2835SystemTimerState systmr; + BCM2835MphiState mphi; UnimplementedDeviceState armtmr; UnimplementedDeviceState cprman; UnimplementedDeviceState a2w; diff --git a/include/hw/misc/bcm2835_mphi.h b/include/hw/misc/bcm2835_mphi.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/bcm2835_mphi.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 SOC MPHI state definitions + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * 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 HW_MISC_BCM2835_MPHI_H +#define HW_MISC_BCM2835_MPHI_H + +#include "hw/irq.h" +#include "hw/sysbus.h" + +#define MPHI_MMIO_SIZE 0x1000 + +typedef struct BCM2835MphiState BCM2835MphiState; + +struct BCM2835MphiState { + SysBusDevice parent_obj; + qemu_irq irq; + MemoryRegion iomem; + + uint32_t outdda; + uint32_t outddb; + uint32_t ctrl; + uint32_t intstat; + uint32_t swirq; +}; + +#define TYPE_BCM2835_MPHI "bcm2835-mphi" + +#define BCM2835_MPHI(obj) \ + OBJECT_CHECK(BCM2835MphiState, (obj), TYPE_BCM2835_MPHI) + +#endif diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) OBJECT(&s->sdhci.sdbus)); object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhost", OBJECT(&s->sdhost.sdbus)); + + /* Mphi */ + sysbus_init_child_obj(obj, "mphi", &s->mphi, sizeof(s->mphi), + TYPE_BCM2835_MPHI); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->gpio), "sd-bus"); + /* Mphi */ + object_property_set_bool(OBJECT(&s->mphi), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + memory_region_add_subregion(&s->peri_mr, MPHI_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->mphi), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mphi), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, + INTERRUPT_HOSTPORT)); + create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); create_unimp(s, &s->cprman, "bcm2835-cprman", CPRMAN_OFFSET, 0x1000); create_unimp(s, &s->a2w, "bcm2835-a2w", A2W_OFFSET, 0x1000); diff --git a/hw/misc/bcm2835_mphi.c b/hw/misc/bcm2835_mphi.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/bcm2835_mphi.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 SOC MPHI emulation + * + * Very basic emulation, only providing the FIQ interrupt needed to + * allow the dwc-otg USB host controller driver in the Raspbian kernel + * to function. + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * 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 "qapi/error.h" +#include "hw/misc/bcm2835_mphi.h" +#include "migration/vmstate.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/main-loop.h" + +static inline void mphi_raise_irq(BCM2835MphiState *s) +{ + qemu_set_irq(s->irq, 1); +} + +static inline void mphi_lower_irq(BCM2835MphiState *s) +{ + qemu_set_irq(s->irq, 0); +} + +static uint64_t mphi_reg_read(void *ptr, hwaddr addr, unsigned size) +{ + BCM2835MphiState *s = ptr; + uint32_t val = 0; + + switch (addr) { + case 0x28: /* outdda */ + val = s->outdda; + break; + case 0x2c: /* outddb */ + val = s->outddb; + break; + case 0x4c: /* ctrl */ + val = s->ctrl; + val |= 1 << 17; + break; + case 0x50: /* intstat */ + val = s->intstat; + break; + case 0x1f0: /* swirq_set */ + val = s->swirq; + break; + case 0x1f4: /* swirq_clr */ + val = s->swirq; + break; + default: + qemu_log_mask(LOG_UNIMP, "read from unknown register"); + break; + } + + return val; +} + +static void mphi_reg_write(void *ptr, hwaddr addr, uint64_t val, unsigned size) +{ + BCM2835MphiState *s = ptr; + int do_irq = 0; + + switch (addr) { + case 0x28: /* outdda */ + s->outdda = val; + break; + case 0x2c: /* outddb */ + s->outddb = val; + if (val & (1 << 29)) { + do_irq = 1; + } + break; + case 0x4c: /* ctrl */ + s->ctrl = val; + if (val & (1 << 16)) { + do_irq = -1; + } + break; + case 0x50: /* intstat */ + s->intstat = val; + if (val & ((1 << 16) | (1 << 29))) { + do_irq = -1; + } + break; + case 0x1f0: /* swirq_set */ + s->swirq |= val; + do_irq = 1; + break; + case 0x1f4: /* swirq_clr */ + s->swirq &= ~val; + do_irq = -1; + break; + default: + qemu_log_mask(LOG_UNIMP, "write to unknown register"); + return; + } + + if (do_irq > 0) { + mphi_raise_irq(s); + } else if (do_irq < 0) { + mphi_lower_irq(s); + } +} + +static const MemoryRegionOps mphi_mmio_ops = { + .read = mphi_reg_read, + .write = mphi_reg_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void mphi_reset(DeviceState *dev) +{ + BCM2835MphiState *s = BCM2835_MPHI(dev); + + s->outdda = 0; + s->outddb = 0; + s->ctrl = 0; + s->intstat = 0; + s->swirq = 0; +} + +static void mphi_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + BCM2835MphiState *s = BCM2835_MPHI(dev); + + sysbus_init_irq(sbd, &s->irq); +} + +static void mphi_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + BCM2835MphiState *s = BCM2835_MPHI(obj); + + memory_region_init_io(&s->iomem, obj, &mphi_mmio_ops, s, "mphi", MPHI_MMIO_SIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +const VMStateDescription vmstate_mphi_state = { + .name = "mphi", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(outdda, BCM2835MphiState), + VMSTATE_UINT32(outddb, BCM2835MphiState), + VMSTATE_UINT32(ctrl, BCM2835MphiState), + VMSTATE_UINT32(intstat, BCM2835MphiState), + VMSTATE_UINT32(swirq, BCM2835MphiState), + VMSTATE_END_OF_LIST() + } +}; + +static void mphi_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = mphi_realize; + dc->reset = mphi_reset; + dc->vmsd = &vmstate_mphi_state; +} + +static const TypeInfo bcm2835_mphi_type_info = { + .name = TYPE_BCM2835_MPHI, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835MphiState), + .instance_init = mphi_init, + .class_init = mphi_class_init, +}; + +static void bcm2835_mphi_register_types(void) +{ + type_register_static(&bcm2835_mphi_type_info); +} + +type_init(bcm2835_mphi_register_types) diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_OMAP) += omap_l4.o common-obj-$(CONFIG_OMAP) += omap_sdrc.o common-obj-$(CONFIG_OMAP) += omap_tap.o common-obj-$(CONFIG_RASPI) += bcm2835_mbox.o +common-obj-$(CONFIG_RASPI) += bcm2835_mphi.o common-obj-$(CONFIG_RASPI) += bcm2835_property.o common-obj-$(CONFIG_RASPI) += bcm2835_rng.o common-obj-$(CONFIG_RASPI) += bcm2835_thermal.o -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Import the dwc-hsotg (dwc2) register definitions file from the Linux kernel. This is a copy of drivers/usb/dwc2/hw.h from the mainline Linux kernel, the only changes being to the header, and two instances of 'u32' changed to 'uint32_t' to allow it to compile. Checkpatch throws a boatload of errors due to the tab indentation, but I would rather import it as-is than reformat it. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-3-pauldzim@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/usb/dwc2-regs.h | 899 +++++++++++++++++++++++++++++++++++++ 1 file changed, 899 insertions(+) create mode 100644 include/hw/usb/dwc2-regs.h diff --git a/include/hw/usb/dwc2-regs.h b/include/hw/usb/dwc2-regs.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/usb/dwc2-regs.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Imported from the Linux kernel file drivers/usb/dwc2/hw.h, commit + * a89bae709b3492b478480a2c9734e7e9393b279c ("usb: dwc2: Move + * UTMI_PHY_DATA defines closer") + * + * hw.h - DesignWare HS OTG Controller hardware definitions + * + * Copyright 2004-2013 Synopsys, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. The names of the above-listed copyright holders may not be used + * to endorse or promote products derived from this software without + * specific prior written permission. + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation; either version 2 of the License, or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS + * IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, + * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR + * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __DWC2_HW_H__ +#define __DWC2_HW_H__ + +#define HSOTG_REG(x) (x) + +#define GOTGCTL HSOTG_REG(0x000) +#define GOTGCTL_CHIRPEN BIT(27) +#define GOTGCTL_MULT_VALID_BC_MASK (0x1f << 22) +#define GOTGCTL_MULT_VALID_BC_SHIFT 22 +#define GOTGCTL_OTGVER BIT(20) +#define GOTGCTL_BSESVLD BIT(19) +#define GOTGCTL_ASESVLD BIT(18) +#define GOTGCTL_DBNC_SHORT BIT(17) +#define GOTGCTL_CONID_B BIT(16) +#define GOTGCTL_DBNCE_FLTR_BYPASS BIT(15) +#define GOTGCTL_DEVHNPEN BIT(11) +#define GOTGCTL_HSTSETHNPEN BIT(10) +#define GOTGCTL_HNPREQ BIT(9) +#define GOTGCTL_HSTNEGSCS BIT(8) +#define GOTGCTL_SESREQ BIT(1) +#define GOTGCTL_SESREQSCS BIT(0) + +#define GOTGINT HSOTG_REG(0x004) +#define GOTGINT_DBNCE_DONE BIT(19) +#define GOTGINT_A_DEV_TOUT_CHG BIT(18) +#define GOTGINT_HST_NEG_DET BIT(17) +#define GOTGINT_HST_NEG_SUC_STS_CHNG BIT(9) +#define GOTGINT_SES_REQ_SUC_STS_CHNG BIT(8) +#define GOTGINT_SES_END_DET BIT(2) + +#define GAHBCFG HSOTG_REG(0x008) +#define GAHBCFG_AHB_SINGLE BIT(23) +#define GAHBCFG_NOTI_ALL_DMA_WRIT BIT(22) +#define GAHBCFG_REM_MEM_SUPP BIT(21) +#define GAHBCFG_P_TXF_EMP_LVL BIT(8) +#define GAHBCFG_NP_TXF_EMP_LVL BIT(7) +#define GAHBCFG_DMA_EN BIT(5) +#define GAHBCFG_HBSTLEN_MASK (0xf << 1) +#define GAHBCFG_HBSTLEN_SHIFT 1 +#define GAHBCFG_HBSTLEN_SINGLE 0 +#define GAHBCFG_HBSTLEN_INCR 1 +#define GAHBCFG_HBSTLEN_INCR4 3 +#define GAHBCFG_HBSTLEN_INCR8 5 +#define GAHBCFG_HBSTLEN_INCR16 7 +#define GAHBCFG_GLBL_INTR_EN BIT(0) +#define GAHBCFG_CTRL_MASK (GAHBCFG_P_TXF_EMP_LVL | \ + GAHBCFG_NP_TXF_EMP_LVL | \ + GAHBCFG_DMA_EN | \ + GAHBCFG_GLBL_INTR_EN) + +#define GUSBCFG HSOTG_REG(0x00C) +#define GUSBCFG_FORCEDEVMODE BIT(30) +#define GUSBCFG_FORCEHOSTMODE BIT(29) +#define GUSBCFG_TXENDDELAY BIT(28) +#define GUSBCFG_ICTRAFFICPULLREMOVE BIT(27) +#define GUSBCFG_ICUSBCAP BIT(26) +#define GUSBCFG_ULPI_INT_PROT_DIS BIT(25) +#define GUSBCFG_INDICATORPASSTHROUGH BIT(24) +#define GUSBCFG_INDICATORCOMPLEMENT BIT(23) +#define GUSBCFG_TERMSELDLPULSE BIT(22) +#define GUSBCFG_ULPI_INT_VBUS_IND BIT(21) +#define GUSBCFG_ULPI_EXT_VBUS_DRV BIT(20) +#define GUSBCFG_ULPI_CLK_SUSP_M BIT(19) +#define GUSBCFG_ULPI_AUTO_RES BIT(18) +#define GUSBCFG_ULPI_FS_LS BIT(17) +#define GUSBCFG_OTG_UTMI_FS_SEL BIT(16) +#define GUSBCFG_PHY_LP_CLK_SEL BIT(15) +#define GUSBCFG_USBTRDTIM_MASK (0xf << 10) +#define GUSBCFG_USBTRDTIM_SHIFT 10 +#define GUSBCFG_HNPCAP BIT(9) +#define GUSBCFG_SRPCAP BIT(8) +#define GUSBCFG_DDRSEL BIT(7) +#define GUSBCFG_PHYSEL BIT(6) +#define GUSBCFG_FSINTF BIT(5) +#define GUSBCFG_ULPI_UTMI_SEL BIT(4) +#define GUSBCFG_PHYIF16 BIT(3) +#define GUSBCFG_PHYIF8 (0 << 3) +#define GUSBCFG_TOUTCAL_MASK (0x7 << 0) +#define GUSBCFG_TOUTCAL_SHIFT 0 +#define GUSBCFG_TOUTCAL_LIMIT 0x7 +#define GUSBCFG_TOUTCAL(_x) ((_x) << 0) + +#define GRSTCTL HSOTG_REG(0x010) +#define GRSTCTL_AHBIDLE BIT(31) +#define GRSTCTL_DMAREQ BIT(30) +#define GRSTCTL_TXFNUM_MASK (0x1f << 6) +#define GRSTCTL_TXFNUM_SHIFT 6 +#define GRSTCTL_TXFNUM_LIMIT 0x1f +#define GRSTCTL_TXFNUM(_x) ((_x) << 6) +#define GRSTCTL_TXFFLSH BIT(5) +#define GRSTCTL_RXFFLSH BIT(4) +#define GRSTCTL_IN_TKNQ_FLSH BIT(3) +#define GRSTCTL_FRMCNTRRST BIT(2) +#define GRSTCTL_HSFTRST BIT(1) +#define GRSTCTL_CSFTRST BIT(0) + +#define GINTSTS HSOTG_REG(0x014) +#define GINTMSK HSOTG_REG(0x018) +#define GINTSTS_WKUPINT BIT(31) +#define GINTSTS_SESSREQINT BIT(30) +#define GINTSTS_DISCONNINT BIT(29) +#define GINTSTS_CONIDSTSCHNG BIT(28) +#define GINTSTS_LPMTRANRCVD BIT(27) +#define GINTSTS_PTXFEMP BIT(26) +#define GINTSTS_HCHINT BIT(25) +#define GINTSTS_PRTINT BIT(24) +#define GINTSTS_RESETDET BIT(23) +#define GINTSTS_FET_SUSP BIT(22) +#define GINTSTS_INCOMPL_IP BIT(21) +#define GINTSTS_INCOMPL_SOOUT BIT(21) +#define GINTSTS_INCOMPL_SOIN BIT(20) +#define GINTSTS_OEPINT BIT(19) +#define GINTSTS_IEPINT BIT(18) +#define GINTSTS_EPMIS BIT(17) +#define GINTSTS_RESTOREDONE BIT(16) +#define GINTSTS_EOPF BIT(15) +#define GINTSTS_ISOUTDROP BIT(14) +#define GINTSTS_ENUMDONE BIT(13) +#define GINTSTS_USBRST BIT(12) +#define GINTSTS_USBSUSP BIT(11) +#define GINTSTS_ERLYSUSP BIT(10) +#define GINTSTS_I2CINT BIT(9) +#define GINTSTS_ULPI_CK_INT BIT(8) +#define GINTSTS_GOUTNAKEFF BIT(7) +#define GINTSTS_GINNAKEFF BIT(6) +#define GINTSTS_NPTXFEMP BIT(5) +#define GINTSTS_RXFLVL BIT(4) +#define GINTSTS_SOF BIT(3) +#define GINTSTS_OTGINT BIT(2) +#define GINTSTS_MODEMIS BIT(1) +#define GINTSTS_CURMODE_HOST BIT(0) + +#define GRXSTSR HSOTG_REG(0x01C) +#define GRXSTSP HSOTG_REG(0x020) +#define GRXSTS_FN_MASK (0x7f << 25) +#define GRXSTS_FN_SHIFT 25 +#define GRXSTS_PKTSTS_MASK (0xf << 17) +#define GRXSTS_PKTSTS_SHIFT 17 +#define GRXSTS_PKTSTS_GLOBALOUTNAK 1 +#define GRXSTS_PKTSTS_OUTRX 2 +#define GRXSTS_PKTSTS_HCHIN 2 +#define GRXSTS_PKTSTS_OUTDONE 3 +#define GRXSTS_PKTSTS_HCHIN_XFER_COMP 3 +#define GRXSTS_PKTSTS_SETUPDONE 4 +#define GRXSTS_PKTSTS_DATATOGGLEERR 5 +#define GRXSTS_PKTSTS_SETUPRX 6 +#define GRXSTS_PKTSTS_HCHHALTED 7 +#define GRXSTS_HCHNUM_MASK (0xf << 0) +#define GRXSTS_HCHNUM_SHIFT 0 +#define GRXSTS_DPID_MASK (0x3 << 15) +#define GRXSTS_DPID_SHIFT 15 +#define GRXSTS_BYTECNT_MASK (0x7ff << 4) +#define GRXSTS_BYTECNT_SHIFT 4 +#define GRXSTS_EPNUM_MASK (0xf << 0) +#define GRXSTS_EPNUM_SHIFT 0 + +#define GRXFSIZ HSOTG_REG(0x024) +#define GRXFSIZ_DEPTH_MASK (0xffff << 0) +#define GRXFSIZ_DEPTH_SHIFT 0 + +#define GNPTXFSIZ HSOTG_REG(0x028) +/* Use FIFOSIZE_* constants to access this register */ + +#define GNPTXSTS HSOTG_REG(0x02C) +#define GNPTXSTS_NP_TXQ_TOP_MASK (0x7f << 24) +#define GNPTXSTS_NP_TXQ_TOP_SHIFT 24 +#define GNPTXSTS_NP_TXQ_SPC_AVAIL_MASK (0xff << 16) +#define GNPTXSTS_NP_TXQ_SPC_AVAIL_SHIFT 16 +#define GNPTXSTS_NP_TXQ_SPC_AVAIL_GET(_v) (((_v) >> 16) & 0xff) +#define GNPTXSTS_NP_TXF_SPC_AVAIL_MASK (0xffff << 0) +#define GNPTXSTS_NP_TXF_SPC_AVAIL_SHIFT 0 +#define GNPTXSTS_NP_TXF_SPC_AVAIL_GET(_v) (((_v) >> 0) & 0xffff) + +#define GI2CCTL HSOTG_REG(0x0030) +#define GI2CCTL_BSYDNE BIT(31) +#define GI2CCTL_RW BIT(30) +#define GI2CCTL_I2CDATSE0 BIT(28) +#define GI2CCTL_I2CDEVADDR_MASK (0x3 << 26) +#define GI2CCTL_I2CDEVADDR_SHIFT 26 +#define GI2CCTL_I2CSUSPCTL BIT(25) +#define GI2CCTL_ACK BIT(24) +#define GI2CCTL_I2CEN BIT(23) +#define GI2CCTL_ADDR_MASK (0x7f << 16) +#define GI2CCTL_ADDR_SHIFT 16 +#define GI2CCTL_REGADDR_MASK (0xff << 8) +#define GI2CCTL_REGADDR_SHIFT 8 +#define GI2CCTL_RWDATA_MASK (0xff << 0) +#define GI2CCTL_RWDATA_SHIFT 0 + +#define GPVNDCTL HSOTG_REG(0x0034) +#define GGPIO HSOTG_REG(0x0038) +#define GGPIO_STM32_OTG_GCCFG_PWRDWN BIT(16) + +#define GUID HSOTG_REG(0x003c) +#define GSNPSID HSOTG_REG(0x0040) +#define GHWCFG1 HSOTG_REG(0x0044) +#define GSNPSID_ID_MASK GENMASK(31, 16) + +#define GHWCFG2 HSOTG_REG(0x0048) +#define GHWCFG2_OTG_ENABLE_IC_USB BIT(31) +#define GHWCFG2_DEV_TOKEN_Q_DEPTH_MASK (0x1f << 26) +#define GHWCFG2_DEV_TOKEN_Q_DEPTH_SHIFT 26 +#define GHWCFG2_HOST_PERIO_TX_Q_DEPTH_MASK (0x3 << 24) +#define GHWCFG2_HOST_PERIO_TX_Q_DEPTH_SHIFT 24 +#define GHWCFG2_NONPERIO_TX_Q_DEPTH_MASK (0x3 << 22) +#define GHWCFG2_NONPERIO_TX_Q_DEPTH_SHIFT 22 +#define GHWCFG2_MULTI_PROC_INT BIT(20) +#define GHWCFG2_DYNAMIC_FIFO BIT(19) +#define GHWCFG2_PERIO_EP_SUPPORTED BIT(18) +#define GHWCFG2_NUM_HOST_CHAN_MASK (0xf << 14) +#define GHWCFG2_NUM_HOST_CHAN_SHIFT 14 +#define GHWCFG2_NUM_DEV_EP_MASK (0xf << 10) +#define GHWCFG2_NUM_DEV_EP_SHIFT 10 +#define GHWCFG2_FS_PHY_TYPE_MASK (0x3 << 8) +#define GHWCFG2_FS_PHY_TYPE_SHIFT 8 +#define GHWCFG2_FS_PHY_TYPE_NOT_SUPPORTED 0 +#define GHWCFG2_FS_PHY_TYPE_DEDICATED 1 +#define GHWCFG2_FS_PHY_TYPE_SHARED_UTMI 2 +#define GHWCFG2_FS_PHY_TYPE_SHARED_ULPI 3 +#define GHWCFG2_HS_PHY_TYPE_MASK (0x3 << 6) +#define GHWCFG2_HS_PHY_TYPE_SHIFT 6 +#define GHWCFG2_HS_PHY_TYPE_NOT_SUPPORTED 0 +#define GHWCFG2_HS_PHY_TYPE_UTMI 1 +#define GHWCFG2_HS_PHY_TYPE_ULPI 2 +#define GHWCFG2_HS_PHY_TYPE_UTMI_ULPI 3 +#define GHWCFG2_POINT2POINT BIT(5) +#define GHWCFG2_ARCHITECTURE_MASK (0x3 << 3) +#define GHWCFG2_ARCHITECTURE_SHIFT 3 +#define GHWCFG2_SLAVE_ONLY_ARCH 0 +#define GHWCFG2_EXT_DMA_ARCH 1 +#define GHWCFG2_INT_DMA_ARCH 2 +#define GHWCFG2_OP_MODE_MASK (0x7 << 0) +#define GHWCFG2_OP_MODE_SHIFT 0 +#define GHWCFG2_OP_MODE_HNP_SRP_CAPABLE 0 +#define GHWCFG2_OP_MODE_SRP_ONLY_CAPABLE 1 +#define GHWCFG2_OP_MODE_NO_HNP_SRP_CAPABLE 2 +#define GHWCFG2_OP_MODE_SRP_CAPABLE_DEVICE 3 +#define GHWCFG2_OP_MODE_NO_SRP_CAPABLE_DEVICE 4 +#define GHWCFG2_OP_MODE_SRP_CAPABLE_HOST 5 +#define GHWCFG2_OP_MODE_NO_SRP_CAPABLE_HOST 6 +#define GHWCFG2_OP_MODE_UNDEFINED 7 + +#define GHWCFG3 HSOTG_REG(0x004c) +#define GHWCFG3_DFIFO_DEPTH_MASK (0xffff << 16) +#define GHWCFG3_DFIFO_DEPTH_SHIFT 16 +#define GHWCFG3_OTG_LPM_EN BIT(15) +#define GHWCFG3_BC_SUPPORT BIT(14) +#define GHWCFG3_OTG_ENABLE_HSIC BIT(13) +#define GHWCFG3_ADP_SUPP BIT(12) +#define GHWCFG3_SYNCH_RESET_TYPE BIT(11) +#define GHWCFG3_OPTIONAL_FEATURES BIT(10) +#define GHWCFG3_VENDOR_CTRL_IF BIT(9) +#define GHWCFG3_I2C BIT(8) +#define GHWCFG3_OTG_FUNC BIT(7) +#define GHWCFG3_PACKET_SIZE_CNTR_WIDTH_MASK (0x7 << 4) +#define GHWCFG3_PACKET_SIZE_CNTR_WIDTH_SHIFT 4 +#define GHWCFG3_XFER_SIZE_CNTR_WIDTH_MASK (0xf << 0) +#define GHWCFG3_XFER_SIZE_CNTR_WIDTH_SHIFT 0 + +#define GHWCFG4 HSOTG_REG(0x0050) +#define GHWCFG4_DESC_DMA_DYN BIT(31) +#define GHWCFG4_DESC_DMA BIT(30) +#define GHWCFG4_NUM_IN_EPS_MASK (0xf << 26) +#define GHWCFG4_NUM_IN_EPS_SHIFT 26 +#define GHWCFG4_DED_FIFO_EN BIT(25) +#define GHWCFG4_DED_FIFO_SHIFT 25 +#define GHWCFG4_SESSION_END_FILT_EN BIT(24) +#define GHWCFG4_B_VALID_FILT_EN BIT(23) +#define GHWCFG4_A_VALID_FILT_EN BIT(22) +#define GHWCFG4_VBUS_VALID_FILT_EN BIT(21) +#define GHWCFG4_IDDIG_FILT_EN BIT(20) +#define GHWCFG4_NUM_DEV_MODE_CTRL_EP_MASK (0xf << 16) +#define GHWCFG4_NUM_DEV_MODE_CTRL_EP_SHIFT 16 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_MASK (0x3 << 14) +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_SHIFT 14 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_8 0 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_16 1 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_8_OR_16 2 +#define GHWCFG4_ACG_SUPPORTED BIT(12) +#define GHWCFG4_IPG_ISOC_SUPPORTED BIT(11) +#define GHWCFG4_SERVICE_INTERVAL_SUPPORTED BIT(10) +#define GHWCFG4_XHIBER BIT(7) +#define GHWCFG4_HIBER BIT(6) +#define GHWCFG4_MIN_AHB_FREQ BIT(5) +#define GHWCFG4_POWER_OPTIMIZ BIT(4) +#define GHWCFG4_NUM_DEV_PERIO_IN_EP_MASK (0xf << 0) +#define GHWCFG4_NUM_DEV_PERIO_IN_EP_SHIFT 0 + +#define GLPMCFG HSOTG_REG(0x0054) +#define GLPMCFG_INVSELHSIC BIT(31) +#define GLPMCFG_HSICCON BIT(30) +#define GLPMCFG_RSTRSLPSTS BIT(29) +#define GLPMCFG_ENBESL BIT(28) +#define GLPMCFG_LPM_RETRYCNT_STS_MASK (0x7 << 25) +#define GLPMCFG_LPM_RETRYCNT_STS_SHIFT 25 +#define GLPMCFG_SNDLPM BIT(24) +#define GLPMCFG_RETRY_CNT_MASK (0x7 << 21) +#define GLPMCFG_RETRY_CNT_SHIFT 21 +#define GLPMCFG_LPM_REJECT_CTRL_CONTROL BIT(21) +#define GLPMCFG_LPM_ACCEPT_CTRL_ISOC BIT(22) +#define GLPMCFG_LPM_CHNL_INDX_MASK (0xf << 17) +#define GLPMCFG_LPM_CHNL_INDX_SHIFT 17 +#define GLPMCFG_L1RESUMEOK BIT(16) +#define GLPMCFG_SLPSTS BIT(15) +#define GLPMCFG_COREL1RES_MASK (0x3 << 13) +#define GLPMCFG_COREL1RES_SHIFT 13 +#define GLPMCFG_HIRD_THRES_MASK (0x1f << 8) +#define GLPMCFG_HIRD_THRES_SHIFT 8 +#define GLPMCFG_HIRD_THRES_EN (0x10 << 8) +#define GLPMCFG_ENBLSLPM BIT(7) +#define GLPMCFG_BREMOTEWAKE BIT(6) +#define GLPMCFG_HIRD_MASK (0xf << 2) +#define GLPMCFG_HIRD_SHIFT 2 +#define GLPMCFG_APPL1RES BIT(1) +#define GLPMCFG_LPMCAP BIT(0) + +#define GPWRDN HSOTG_REG(0x0058) +#define GPWRDN_MULT_VAL_ID_BC_MASK (0x1f << 24) +#define GPWRDN_MULT_VAL_ID_BC_SHIFT 24 +#define GPWRDN_ADP_INT BIT(23) +#define GPWRDN_BSESSVLD BIT(22) +#define GPWRDN_IDSTS BIT(21) +#define GPWRDN_LINESTATE_MASK (0x3 << 19) +#define GPWRDN_LINESTATE_SHIFT 19 +#define GPWRDN_STS_CHGINT_MSK BIT(18) +#define GPWRDN_STS_CHGINT BIT(17) +#define GPWRDN_SRP_DET_MSK BIT(16) +#define GPWRDN_SRP_DET BIT(15) +#define GPWRDN_CONNECT_DET_MSK BIT(14) +#define GPWRDN_CONNECT_DET BIT(13) +#define GPWRDN_DISCONN_DET_MSK BIT(12) +#define GPWRDN_DISCONN_DET BIT(11) +#define GPWRDN_RST_DET_MSK BIT(10) +#define GPWRDN_RST_DET BIT(9) +#define GPWRDN_LNSTSCHG_MSK BIT(8) +#define GPWRDN_LNSTSCHG BIT(7) +#define GPWRDN_DIS_VBUS BIT(6) +#define GPWRDN_PWRDNSWTCH BIT(5) +#define GPWRDN_PWRDNRSTN BIT(4) +#define GPWRDN_PWRDNCLMP BIT(3) +#define GPWRDN_RESTORE BIT(2) +#define GPWRDN_PMUACTV BIT(1) +#define GPWRDN_PMUINTSEL BIT(0) + +#define GDFIFOCFG HSOTG_REG(0x005c) +#define GDFIFOCFG_EPINFOBASE_MASK (0xffff << 16) +#define GDFIFOCFG_EPINFOBASE_SHIFT 16 +#define GDFIFOCFG_GDFIFOCFG_MASK (0xffff << 0) +#define GDFIFOCFG_GDFIFOCFG_SHIFT 0 + +#define ADPCTL HSOTG_REG(0x0060) +#define ADPCTL_AR_MASK (0x3 << 27) +#define ADPCTL_AR_SHIFT 27 +#define ADPCTL_ADP_TMOUT_INT_MSK BIT(26) +#define ADPCTL_ADP_SNS_INT_MSK BIT(25) +#define ADPCTL_ADP_PRB_INT_MSK BIT(24) +#define ADPCTL_ADP_TMOUT_INT BIT(23) +#define ADPCTL_ADP_SNS_INT BIT(22) +#define ADPCTL_ADP_PRB_INT BIT(21) +#define ADPCTL_ADPENA BIT(20) +#define ADPCTL_ADPRES BIT(19) +#define ADPCTL_ENASNS BIT(18) +#define ADPCTL_ENAPRB BIT(17) +#define ADPCTL_RTIM_MASK (0x7ff << 6) +#define ADPCTL_RTIM_SHIFT 6 +#define ADPCTL_PRB_PER_MASK (0x3 << 4) +#define ADPCTL_PRB_PER_SHIFT 4 +#define ADPCTL_PRB_DELTA_MASK (0x3 << 2) +#define ADPCTL_PRB_DELTA_SHIFT 2 +#define ADPCTL_PRB_DSCHRG_MASK (0x3 << 0) +#define ADPCTL_PRB_DSCHRG_SHIFT 0 + +#define GREFCLK HSOTG_REG(0x0064) +#define GREFCLK_REFCLKPER_MASK (0x1ffff << 15) +#define GREFCLK_REFCLKPER_SHIFT 15 +#define GREFCLK_REF_CLK_MODE BIT(14) +#define GREFCLK_SOF_CNT_WKUP_ALERT_MASK (0x3ff) +#define GREFCLK_SOF_CNT_WKUP_ALERT_SHIFT 0 + +#define GINTMSK2 HSOTG_REG(0x0068) +#define GINTMSK2_WKUP_ALERT_INT_MSK BIT(0) + +#define GINTSTS2 HSOTG_REG(0x006c) +#define GINTSTS2_WKUP_ALERT_INT BIT(0) + +#define HPTXFSIZ HSOTG_REG(0x100) +/* Use FIFOSIZE_* constants to access this register */ + +#define DPTXFSIZN(_a) HSOTG_REG(0x104 + (((_a) - 1) * 4)) +/* Use FIFOSIZE_* constants to access this register */ + +/* These apply to the GNPTXFSIZ, HPTXFSIZ and DPTXFSIZN registers */ +#define FIFOSIZE_DEPTH_MASK (0xffff << 16) +#define FIFOSIZE_DEPTH_SHIFT 16 +#define FIFOSIZE_STARTADDR_MASK (0xffff << 0) +#define FIFOSIZE_STARTADDR_SHIFT 0 +#define FIFOSIZE_DEPTH_GET(_x) (((_x) >> 16) & 0xffff) + +/* Device mode registers */ + +#define DCFG HSOTG_REG(0x800) +#define DCFG_DESCDMA_EN BIT(23) +#define DCFG_EPMISCNT_MASK (0x1f << 18) +#define DCFG_EPMISCNT_SHIFT 18 +#define DCFG_EPMISCNT_LIMIT 0x1f +#define DCFG_EPMISCNT(_x) ((_x) << 18) +#define DCFG_IPG_ISOC_SUPPORDED BIT(17) +#define DCFG_PERFRINT_MASK (0x3 << 11) +#define DCFG_PERFRINT_SHIFT 11 +#define DCFG_PERFRINT_LIMIT 0x3 +#define DCFG_PERFRINT(_x) ((_x) << 11) +#define DCFG_DEVADDR_MASK (0x7f << 4) +#define DCFG_DEVADDR_SHIFT 4 +#define DCFG_DEVADDR_LIMIT 0x7f +#define DCFG_DEVADDR(_x) ((_x) << 4) +#define DCFG_NZ_STS_OUT_HSHK BIT(2) +#define DCFG_DEVSPD_MASK (0x3 << 0) +#define DCFG_DEVSPD_SHIFT 0 +#define DCFG_DEVSPD_HS 0 +#define DCFG_DEVSPD_FS 1 +#define DCFG_DEVSPD_LS 2 +#define DCFG_DEVSPD_FS48 3 + +#define DCTL HSOTG_REG(0x804) +#define DCTL_SERVICE_INTERVAL_SUPPORTED BIT(19) +#define DCTL_PWRONPRGDONE BIT(11) +#define DCTL_CGOUTNAK BIT(10) +#define DCTL_SGOUTNAK BIT(9) +#define DCTL_CGNPINNAK BIT(8) +#define DCTL_SGNPINNAK BIT(7) +#define DCTL_TSTCTL_MASK (0x7 << 4) +#define DCTL_TSTCTL_SHIFT 4 +#define DCTL_GOUTNAKSTS BIT(3) +#define DCTL_GNPINNAKSTS BIT(2) +#define DCTL_SFTDISCON BIT(1) +#define DCTL_RMTWKUPSIG BIT(0) + +#define DSTS HSOTG_REG(0x808) +#define DSTS_SOFFN_MASK (0x3fff << 8) +#define DSTS_SOFFN_SHIFT 8 +#define DSTS_SOFFN_LIMIT 0x3fff +#define DSTS_SOFFN(_x) ((_x) << 8) +#define DSTS_ERRATICERR BIT(3) +#define DSTS_ENUMSPD_MASK (0x3 << 1) +#define DSTS_ENUMSPD_SHIFT 1 +#define DSTS_ENUMSPD_HS 0 +#define DSTS_ENUMSPD_FS 1 +#define DSTS_ENUMSPD_LS 2 +#define DSTS_ENUMSPD_FS48 3 +#define DSTS_SUSPSTS BIT(0) + +#define DIEPMSK HSOTG_REG(0x810) +#define DIEPMSK_NAKMSK BIT(13) +#define DIEPMSK_BNAININTRMSK BIT(9) +#define DIEPMSK_TXFIFOUNDRNMSK BIT(8) +#define DIEPMSK_TXFIFOEMPTY BIT(7) +#define DIEPMSK_INEPNAKEFFMSK BIT(6) +#define DIEPMSK_INTKNEPMISMSK BIT(5) +#define DIEPMSK_INTKNTXFEMPMSK BIT(4) +#define DIEPMSK_TIMEOUTMSK BIT(3) +#define DIEPMSK_AHBERRMSK BIT(2) +#define DIEPMSK_EPDISBLDMSK BIT(1) +#define DIEPMSK_XFERCOMPLMSK BIT(0) + +#define DOEPMSK HSOTG_REG(0x814) +#define DOEPMSK_BNAMSK BIT(9) +#define DOEPMSK_BACK2BACKSETUP BIT(6) +#define DOEPMSK_STSPHSERCVDMSK BIT(5) +#define DOEPMSK_OUTTKNEPDISMSK BIT(4) +#define DOEPMSK_SETUPMSK BIT(3) +#define DOEPMSK_AHBERRMSK BIT(2) +#define DOEPMSK_EPDISBLDMSK BIT(1) +#define DOEPMSK_XFERCOMPLMSK BIT(0) + +#define DAINT HSOTG_REG(0x818) +#define DAINTMSK HSOTG_REG(0x81C) +#define DAINT_OUTEP_SHIFT 16 +#define DAINT_OUTEP(_x) (1 << ((_x) + 16)) +#define DAINT_INEP(_x) (1 << (_x)) + +#define DTKNQR1 HSOTG_REG(0x820) +#define DTKNQR2 HSOTG_REG(0x824) +#define DTKNQR3 HSOTG_REG(0x830) +#define DTKNQR4 HSOTG_REG(0x834) +#define DIEPEMPMSK HSOTG_REG(0x834) + +#define DVBUSDIS HSOTG_REG(0x828) +#define DVBUSPULSE HSOTG_REG(0x82C) + +#define DIEPCTL0 HSOTG_REG(0x900) +#define DIEPCTL(_a) HSOTG_REG(0x900 + ((_a) * 0x20)) + +#define DOEPCTL0 HSOTG_REG(0xB00) +#define DOEPCTL(_a) HSOTG_REG(0xB00 + ((_a) * 0x20)) + +/* EP0 specialness: + * bits[29..28] - reserved (no SetD0PID, SetD1PID) + * bits[25..22] - should always be zero, this isn't a periodic endpoint + * bits[10..0] - MPS setting different for EP0 + */ +#define D0EPCTL_MPS_MASK (0x3 << 0) +#define D0EPCTL_MPS_SHIFT 0 +#define D0EPCTL_MPS_64 0 +#define D0EPCTL_MPS_32 1 +#define D0EPCTL_MPS_16 2 +#define D0EPCTL_MPS_8 3 + +#define DXEPCTL_EPENA BIT(31) +#define DXEPCTL_EPDIS BIT(30) +#define DXEPCTL_SETD1PID BIT(29) +#define DXEPCTL_SETODDFR BIT(29) +#define DXEPCTL_SETD0PID BIT(28) +#define DXEPCTL_SETEVENFR BIT(28) +#define DXEPCTL_SNAK BIT(27) +#define DXEPCTL_CNAK BIT(26) +#define DXEPCTL_TXFNUM_MASK (0xf << 22) +#define DXEPCTL_TXFNUM_SHIFT 22 +#define DXEPCTL_TXFNUM_LIMIT 0xf +#define DXEPCTL_TXFNUM(_x) ((_x) << 22) +#define DXEPCTL_STALL BIT(21) +#define DXEPCTL_SNP BIT(20) +#define DXEPCTL_EPTYPE_MASK (0x3 << 18) +#define DXEPCTL_EPTYPE_CONTROL (0x0 << 18) +#define DXEPCTL_EPTYPE_ISO (0x1 << 18) +#define DXEPCTL_EPTYPE_BULK (0x2 << 18) +#define DXEPCTL_EPTYPE_INTERRUPT (0x3 << 18) + +#define DXEPCTL_NAKSTS BIT(17) +#define DXEPCTL_DPID BIT(16) +#define DXEPCTL_EOFRNUM BIT(16) +#define DXEPCTL_USBACTEP BIT(15) +#define DXEPCTL_NEXTEP_MASK (0xf << 11) +#define DXEPCTL_NEXTEP_SHIFT 11 +#define DXEPCTL_NEXTEP_LIMIT 0xf +#define DXEPCTL_NEXTEP(_x) ((_x) << 11) +#define DXEPCTL_MPS_MASK (0x7ff << 0) +#define DXEPCTL_MPS_SHIFT 0 +#define DXEPCTL_MPS_LIMIT 0x7ff +#define DXEPCTL_MPS(_x) ((_x) << 0) + +#define DIEPINT(_a) HSOTG_REG(0x908 + ((_a) * 0x20)) +#define DOEPINT(_a) HSOTG_REG(0xB08 + ((_a) * 0x20)) +#define DXEPINT_SETUP_RCVD BIT(15) +#define DXEPINT_NYETINTRPT BIT(14) +#define DXEPINT_NAKINTRPT BIT(13) +#define DXEPINT_BBLEERRINTRPT BIT(12) +#define DXEPINT_PKTDRPSTS BIT(11) +#define DXEPINT_BNAINTR BIT(9) +#define DXEPINT_TXFIFOUNDRN BIT(8) +#define DXEPINT_OUTPKTERR BIT(8) +#define DXEPINT_TXFEMP BIT(7) +#define DXEPINT_INEPNAKEFF BIT(6) +#define DXEPINT_BACK2BACKSETUP BIT(6) +#define DXEPINT_INTKNEPMIS BIT(5) +#define DXEPINT_STSPHSERCVD BIT(5) +#define DXEPINT_INTKNTXFEMP BIT(4) +#define DXEPINT_OUTTKNEPDIS BIT(4) +#define DXEPINT_TIMEOUT BIT(3) +#define DXEPINT_SETUP BIT(3) +#define DXEPINT_AHBERR BIT(2) +#define DXEPINT_EPDISBLD BIT(1) +#define DXEPINT_XFERCOMPL BIT(0) + +#define DIEPTSIZ0 HSOTG_REG(0x910) +#define DIEPTSIZ0_PKTCNT_MASK (0x3 << 19) +#define DIEPTSIZ0_PKTCNT_SHIFT 19 +#define DIEPTSIZ0_PKTCNT_LIMIT 0x3 +#define DIEPTSIZ0_PKTCNT(_x) ((_x) << 19) +#define DIEPTSIZ0_XFERSIZE_MASK (0x7f << 0) +#define DIEPTSIZ0_XFERSIZE_SHIFT 0 +#define DIEPTSIZ0_XFERSIZE_LIMIT 0x7f +#define DIEPTSIZ0_XFERSIZE(_x) ((_x) << 0) + +#define DOEPTSIZ0 HSOTG_REG(0xB10) +#define DOEPTSIZ0_SUPCNT_MASK (0x3 << 29) +#define DOEPTSIZ0_SUPCNT_SHIFT 29 +#define DOEPTSIZ0_SUPCNT_LIMIT 0x3 +#define DOEPTSIZ0_SUPCNT(_x) ((_x) << 29) +#define DOEPTSIZ0_PKTCNT BIT(19) +#define DOEPTSIZ0_XFERSIZE_MASK (0x7f << 0) +#define DOEPTSIZ0_XFERSIZE_SHIFT 0 + +#define DIEPTSIZ(_a) HSOTG_REG(0x910 + ((_a) * 0x20)) +#define DOEPTSIZ(_a) HSOTG_REG(0xB10 + ((_a) * 0x20)) +#define DXEPTSIZ_MC_MASK (0x3 << 29) +#define DXEPTSIZ_MC_SHIFT 29 +#define DXEPTSIZ_MC_LIMIT 0x3 +#define DXEPTSIZ_MC(_x) ((_x) << 29) +#define DXEPTSIZ_PKTCNT_MASK (0x3ff << 19) +#define DXEPTSIZ_PKTCNT_SHIFT 19 +#define DXEPTSIZ_PKTCNT_LIMIT 0x3ff +#define DXEPTSIZ_PKTCNT_GET(_v) (((_v) >> 19) & 0x3ff) +#define DXEPTSIZ_PKTCNT(_x) ((_x) << 19) +#define DXEPTSIZ_XFERSIZE_MASK (0x7ffff << 0) +#define DXEPTSIZ_XFERSIZE_SHIFT 0 +#define DXEPTSIZ_XFERSIZE_LIMIT 0x7ffff +#define DXEPTSIZ_XFERSIZE_GET(_v) (((_v) >> 0) & 0x7ffff) +#define DXEPTSIZ_XFERSIZE(_x) ((_x) << 0) + +#define DIEPDMA(_a) HSOTG_REG(0x914 + ((_a) * 0x20)) +#define DOEPDMA(_a) HSOTG_REG(0xB14 + ((_a) * 0x20)) + +#define DTXFSTS(_a) HSOTG_REG(0x918 + ((_a) * 0x20)) + +#define PCGCTL HSOTG_REG(0x0e00) +#define PCGCTL_IF_DEV_MODE BIT(31) +#define PCGCTL_P2HD_PRT_SPD_MASK (0x3 << 29) +#define PCGCTL_P2HD_PRT_SPD_SHIFT 29 +#define PCGCTL_P2HD_DEV_ENUM_SPD_MASK (0x3 << 27) +#define PCGCTL_P2HD_DEV_ENUM_SPD_SHIFT 27 +#define PCGCTL_MAC_DEV_ADDR_MASK (0x7f << 20) +#define PCGCTL_MAC_DEV_ADDR_SHIFT 20 +#define PCGCTL_MAX_TERMSEL BIT(19) +#define PCGCTL_MAX_XCVRSELECT_MASK (0x3 << 17) +#define PCGCTL_MAX_XCVRSELECT_SHIFT 17 +#define PCGCTL_PORT_POWER BIT(16) +#define PCGCTL_PRT_CLK_SEL_MASK (0x3 << 14) +#define PCGCTL_PRT_CLK_SEL_SHIFT 14 +#define PCGCTL_ESS_REG_RESTORED BIT(13) +#define PCGCTL_EXTND_HIBER_SWITCH BIT(12) +#define PCGCTL_EXTND_HIBER_PWRCLMP BIT(11) +#define PCGCTL_ENBL_EXTND_HIBER BIT(10) +#define PCGCTL_RESTOREMODE BIT(9) +#define PCGCTL_RESETAFTSUSP BIT(8) +#define PCGCTL_DEEP_SLEEP BIT(7) +#define PCGCTL_PHY_IN_SLEEP BIT(6) +#define PCGCTL_ENBL_SLEEP_GATING BIT(5) +#define PCGCTL_RSTPDWNMODULE BIT(3) +#define PCGCTL_PWRCLMP BIT(2) +#define PCGCTL_GATEHCLK BIT(1) +#define PCGCTL_STOPPCLK BIT(0) + +#define PCGCCTL1 HSOTG_REG(0xe04) +#define PCGCCTL1_TIMER (0x3 << 1) +#define PCGCCTL1_GATEEN BIT(0) + +#define EPFIFO(_a) HSOTG_REG(0x1000 + ((_a) * 0x1000)) + +/* Host Mode Registers */ + +#define HCFG HSOTG_REG(0x0400) +#define HCFG_MODECHTIMEN BIT(31) +#define HCFG_PERSCHEDENA BIT(26) +#define HCFG_FRLISTEN_MASK (0x3 << 24) +#define HCFG_FRLISTEN_SHIFT 24 +#define HCFG_FRLISTEN_8 (0 << 24) +#define FRLISTEN_8_SIZE 8 +#define HCFG_FRLISTEN_16 BIT(24) +#define FRLISTEN_16_SIZE 16 +#define HCFG_FRLISTEN_32 (2 << 24) +#define FRLISTEN_32_SIZE 32 +#define HCFG_FRLISTEN_64 (3 << 24) +#define FRLISTEN_64_SIZE 64 +#define HCFG_DESCDMA BIT(23) +#define HCFG_RESVALID_MASK (0xff << 8) +#define HCFG_RESVALID_SHIFT 8 +#define HCFG_ENA32KHZ BIT(7) +#define HCFG_FSLSSUPP BIT(2) +#define HCFG_FSLSPCLKSEL_MASK (0x3 << 0) +#define HCFG_FSLSPCLKSEL_SHIFT 0 +#define HCFG_FSLSPCLKSEL_30_60_MHZ 0 +#define HCFG_FSLSPCLKSEL_48_MHZ 1 +#define HCFG_FSLSPCLKSEL_6_MHZ 2 + +#define HFIR HSOTG_REG(0x0404) +#define HFIR_FRINT_MASK (0xffff << 0) +#define HFIR_FRINT_SHIFT 0 +#define HFIR_RLDCTRL BIT(16) + +#define HFNUM HSOTG_REG(0x0408) +#define HFNUM_FRREM_MASK (0xffff << 16) +#define HFNUM_FRREM_SHIFT 16 +#define HFNUM_FRNUM_MASK (0xffff << 0) +#define HFNUM_FRNUM_SHIFT 0 +#define HFNUM_MAX_FRNUM 0x3fff + +#define HPTXSTS HSOTG_REG(0x0410) +#define TXSTS_QTOP_ODD BIT(31) +#define TXSTS_QTOP_CHNEP_MASK (0xf << 27) +#define TXSTS_QTOP_CHNEP_SHIFT 27 +#define TXSTS_QTOP_TOKEN_MASK (0x3 << 25) +#define TXSTS_QTOP_TOKEN_SHIFT 25 +#define TXSTS_QTOP_TERMINATE BIT(24) +#define TXSTS_QSPCAVAIL_MASK (0xff << 16) +#define TXSTS_QSPCAVAIL_SHIFT 16 +#define TXSTS_FSPCAVAIL_MASK (0xffff << 0) +#define TXSTS_FSPCAVAIL_SHIFT 0 + +#define HAINT HSOTG_REG(0x0414) +#define HAINTMSK HSOTG_REG(0x0418) +#define HFLBADDR HSOTG_REG(0x041c) + +#define HPRT0 HSOTG_REG(0x0440) +#define HPRT0_SPD_MASK (0x3 << 17) +#define HPRT0_SPD_SHIFT 17 +#define HPRT0_SPD_HIGH_SPEED 0 +#define HPRT0_SPD_FULL_SPEED 1 +#define HPRT0_SPD_LOW_SPEED 2 +#define HPRT0_TSTCTL_MASK (0xf << 13) +#define HPRT0_TSTCTL_SHIFT 13 +#define HPRT0_PWR BIT(12) +#define HPRT0_LNSTS_MASK (0x3 << 10) +#define HPRT0_LNSTS_SHIFT 10 +#define HPRT0_RST BIT(8) +#define HPRT0_SUSP BIT(7) +#define HPRT0_RES BIT(6) +#define HPRT0_OVRCURRCHG BIT(5) +#define HPRT0_OVRCURRACT BIT(4) +#define HPRT0_ENACHG BIT(3) +#define HPRT0_ENA BIT(2) +#define HPRT0_CONNDET BIT(1) +#define HPRT0_CONNSTS BIT(0) + +#define HCCHAR(_ch) HSOTG_REG(0x0500 + 0x20 * (_ch)) +#define HCCHAR_CHENA BIT(31) +#define HCCHAR_CHDIS BIT(30) +#define HCCHAR_ODDFRM BIT(29) +#define HCCHAR_DEVADDR_MASK (0x7f << 22) +#define HCCHAR_DEVADDR_SHIFT 22 +#define HCCHAR_MULTICNT_MASK (0x3 << 20) +#define HCCHAR_MULTICNT_SHIFT 20 +#define HCCHAR_EPTYPE_MASK (0x3 << 18) +#define HCCHAR_EPTYPE_SHIFT 18 +#define HCCHAR_LSPDDEV BIT(17) +#define HCCHAR_EPDIR BIT(15) +#define HCCHAR_EPNUM_MASK (0xf << 11) +#define HCCHAR_EPNUM_SHIFT 11 +#define HCCHAR_MPS_MASK (0x7ff << 0) +#define HCCHAR_MPS_SHIFT 0 + +#define HCSPLT(_ch) HSOTG_REG(0x0504 + 0x20 * (_ch)) +#define HCSPLT_SPLTENA BIT(31) +#define HCSPLT_COMPSPLT BIT(16) +#define HCSPLT_XACTPOS_MASK (0x3 << 14) +#define HCSPLT_XACTPOS_SHIFT 14 +#define HCSPLT_XACTPOS_MID 0 +#define HCSPLT_XACTPOS_END 1 +#define HCSPLT_XACTPOS_BEGIN 2 +#define HCSPLT_XACTPOS_ALL 3 +#define HCSPLT_HUBADDR_MASK (0x7f << 7) +#define HCSPLT_HUBADDR_SHIFT 7 +#define HCSPLT_PRTADDR_MASK (0x7f << 0) +#define HCSPLT_PRTADDR_SHIFT 0 + +#define HCINT(_ch) HSOTG_REG(0x0508 + 0x20 * (_ch)) +#define HCINTMSK(_ch) HSOTG_REG(0x050c + 0x20 * (_ch)) +#define HCINTMSK_RESERVED14_31 (0x3ffff << 14) +#define HCINTMSK_FRM_LIST_ROLL BIT(13) +#define HCINTMSK_XCS_XACT BIT(12) +#define HCINTMSK_BNA BIT(11) +#define HCINTMSK_DATATGLERR BIT(10) +#define HCINTMSK_FRMOVRUN BIT(9) +#define HCINTMSK_BBLERR BIT(8) +#define HCINTMSK_XACTERR BIT(7) +#define HCINTMSK_NYET BIT(6) +#define HCINTMSK_ACK BIT(5) +#define HCINTMSK_NAK BIT(4) +#define HCINTMSK_STALL BIT(3) +#define HCINTMSK_AHBERR BIT(2) +#define HCINTMSK_CHHLTD BIT(1) +#define HCINTMSK_XFERCOMPL BIT(0) + +#define HCTSIZ(_ch) HSOTG_REG(0x0510 + 0x20 * (_ch)) +#define TSIZ_DOPNG BIT(31) +#define TSIZ_SC_MC_PID_MASK (0x3 << 29) +#define TSIZ_SC_MC_PID_SHIFT 29 +#define TSIZ_SC_MC_PID_DATA0 0 +#define TSIZ_SC_MC_PID_DATA2 1 +#define TSIZ_SC_MC_PID_DATA1 2 +#define TSIZ_SC_MC_PID_MDATA 3 +#define TSIZ_SC_MC_PID_SETUP 3 +#define TSIZ_PKTCNT_MASK (0x3ff << 19) +#define TSIZ_PKTCNT_SHIFT 19 +#define TSIZ_NTD_MASK (0xff << 8) +#define TSIZ_NTD_SHIFT 8 +#define TSIZ_SCHINFO_MASK (0xff << 0) +#define TSIZ_SCHINFO_SHIFT 0 +#define TSIZ_XFERSIZE_MASK (0x7ffff << 0) +#define TSIZ_XFERSIZE_SHIFT 0 + +#define HCDMA(_ch) HSOTG_REG(0x0514 + 0x20 * (_ch)) + +#define HCDMAB(_ch) HSOTG_REG(0x051c + 0x20 * (_ch)) + +#define HCFIFO(_ch) HSOTG_REG(0x1000 + 0x1000 * (_ch)) + +/** + * struct dwc2_dma_desc - DMA descriptor structure, + * used for both host and gadget modes + * + * @status: DMA descriptor status quadlet + * @buf: DMA descriptor data buffer pointer + * + * DMA Descriptor structure contains two quadlets: + * Status quadlet and Data buffer pointer. + */ +struct dwc2_dma_desc { + uint32_t status; + uint32_t buf; +} __packed; + +/* Host Mode DMA descriptor status quadlet */ + +#define HOST_DMA_A BIT(31) +#define HOST_DMA_STS_MASK (0x3 << 28) +#define HOST_DMA_STS_SHIFT 28 +#define HOST_DMA_STS_PKTERR BIT(28) +#define HOST_DMA_EOL BIT(26) +#define HOST_DMA_IOC BIT(25) +#define HOST_DMA_SUP BIT(24) +#define HOST_DMA_ALT_QTD BIT(23) +#define HOST_DMA_QTD_OFFSET_MASK (0x3f << 17) +#define HOST_DMA_QTD_OFFSET_SHIFT 17 +#define HOST_DMA_ISOC_NBYTES_MASK (0xfff << 0) +#define HOST_DMA_ISOC_NBYTES_SHIFT 0 +#define HOST_DMA_NBYTES_MASK (0x1ffff << 0) +#define HOST_DMA_NBYTES_SHIFT 0 +#define HOST_DMA_NBYTES_LIMIT 131071 + +/* Device Mode DMA descriptor status quadlet */ + +#define DEV_DMA_BUFF_STS_MASK (0x3 << 30) +#define DEV_DMA_BUFF_STS_SHIFT 30 +#define DEV_DMA_BUFF_STS_HREADY 0 +#define DEV_DMA_BUFF_STS_DMABUSY 1 +#define DEV_DMA_BUFF_STS_DMADONE 2 +#define DEV_DMA_BUFF_STS_HBUSY 3 +#define DEV_DMA_STS_MASK (0x3 << 28) +#define DEV_DMA_STS_SHIFT 28 +#define DEV_DMA_STS_SUCC 0 +#define DEV_DMA_STS_BUFF_FLUSH 1 +#define DEV_DMA_STS_BUFF_ERR 3 +#define DEV_DMA_L BIT(27) +#define DEV_DMA_SHORT BIT(26) +#define DEV_DMA_IOC BIT(25) +#define DEV_DMA_SR BIT(24) +#define DEV_DMA_MTRF BIT(23) +#define DEV_DMA_ISOC_PID_MASK (0x3 << 23) +#define DEV_DMA_ISOC_PID_SHIFT 23 +#define DEV_DMA_ISOC_PID_DATA0 0 +#define DEV_DMA_ISOC_PID_DATA2 1 +#define DEV_DMA_ISOC_PID_DATA1 2 +#define DEV_DMA_ISOC_PID_MDATA 3 +#define DEV_DMA_ISOC_FRNUM_MASK (0x7ff << 12) +#define DEV_DMA_ISOC_FRNUM_SHIFT 12 +#define DEV_DMA_ISOC_TX_NBYTES_MASK (0xfff << 0) +#define DEV_DMA_ISOC_TX_NBYTES_LIMIT 0xfff +#define DEV_DMA_ISOC_RX_NBYTES_MASK (0x7ff << 0) +#define DEV_DMA_ISOC_RX_NBYTES_LIMIT 0x7ff +#define DEV_DMA_ISOC_NBYTES_SHIFT 0 +#define DEV_DMA_NBYTES_MASK (0xffff << 0) +#define DEV_DMA_NBYTES_SHIFT 0 +#define DEV_DMA_NBYTES_LIMIT 0xffff + +#define MAX_DMA_DESC_NUM_GENERIC 64 +#define MAX_DMA_DESC_NUM_HS_ISOC 256 + +#endif /* __DWC2_HW_H__ */ -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add the dwc-hsotg (dwc2) USB host controller state definitions. Mostly based on hw/usb/hcd-ehci.h. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-4-pauldzim@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-dwc2.h | 190 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 190 insertions(+) create mode 100644 hw/usb/hcd-dwc2.h diff --git a/hw/usb/hcd-dwc2.h b/hw/usb/hcd-dwc2.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/hcd-dwc2.h @@ -XXX,XX +XXX,XX @@ +/* + * dwc-hsotg (dwc2) USB host controller state definitions + * + * Based on hw/usb/hcd-ehci.h + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * 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 HW_USB_DWC2_H +#define HW_USB_DWC2_H + +#include "qemu/timer.h" +#include "hw/irq.h" +#include "hw/sysbus.h" +#include "hw/usb.h" +#include "sysemu/dma.h" + +#define DWC2_MMIO_SIZE 0x11000 + +#define DWC2_NB_CHAN 8 /* Number of host channels */ +#define DWC2_MAX_XFER_SIZE 65536 /* Max transfer size expected in HCTSIZ */ + +typedef struct DWC2Packet DWC2Packet; +typedef struct DWC2State DWC2State; +typedef struct DWC2Class DWC2Class; + +enum async_state { + DWC2_ASYNC_NONE = 0, + DWC2_ASYNC_INITIALIZED, + DWC2_ASYNC_INFLIGHT, + DWC2_ASYNC_FINISHED, +}; + +struct DWC2Packet { + USBPacket packet; + uint32_t devadr; + uint32_t epnum; + uint32_t epdir; + uint32_t mps; + uint32_t pid; + uint32_t index; + uint32_t pcnt; + uint32_t len; + int32_t async; + bool small; + bool needs_service; +}; + +struct DWC2State { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + USBBus bus; + qemu_irq irq; + MemoryRegion *dma_mr; + AddressSpace dma_as; + MemoryRegion container; + MemoryRegion hsotg; + MemoryRegion fifos; + + union { +#define DWC2_GLBREG_SIZE 0x70 + uint32_t glbreg[DWC2_GLBREG_SIZE / sizeof(uint32_t)]; + struct { + uint32_t gotgctl; /* 00 */ + uint32_t gotgint; /* 04 */ + uint32_t gahbcfg; /* 08 */ + uint32_t gusbcfg; /* 0c */ + uint32_t grstctl; /* 10 */ + uint32_t gintsts; /* 14 */ + uint32_t gintmsk; /* 18 */ + uint32_t grxstsr; /* 1c */ + uint32_t grxstsp; /* 20 */ + uint32_t grxfsiz; /* 24 */ + uint32_t gnptxfsiz; /* 28 */ + uint32_t gnptxsts; /* 2c */ + uint32_t gi2cctl; /* 30 */ + uint32_t gpvndctl; /* 34 */ + uint32_t ggpio; /* 38 */ + uint32_t guid; /* 3c */ + uint32_t gsnpsid; /* 40 */ + uint32_t ghwcfg1; /* 44 */ + uint32_t ghwcfg2; /* 48 */ + uint32_t ghwcfg3; /* 4c */ + uint32_t ghwcfg4; /* 50 */ + uint32_t glpmcfg; /* 54 */ + uint32_t gpwrdn; /* 58 */ + uint32_t gdfifocfg; /* 5c */ + uint32_t gadpctl; /* 60 */ + uint32_t grefclk; /* 64 */ + uint32_t gintmsk2; /* 68 */ + uint32_t gintsts2; /* 6c */ + }; + }; + + union { +#define DWC2_FSZREG_SIZE 0x04 + uint32_t fszreg[DWC2_FSZREG_SIZE / sizeof(uint32_t)]; + struct { + uint32_t hptxfsiz; /* 100 */ + }; + }; + + union { +#define DWC2_HREG0_SIZE 0x44 + uint32_t hreg0[DWC2_HREG0_SIZE / sizeof(uint32_t)]; + struct { + uint32_t hcfg; /* 400 */ + uint32_t hfir; /* 404 */ + uint32_t hfnum; /* 408 */ + uint32_t rsvd0; /* 40c */ + uint32_t hptxsts; /* 410 */ + uint32_t haint; /* 414 */ + uint32_t haintmsk; /* 418 */ + uint32_t hflbaddr; /* 41c */ + uint32_t rsvd1[8]; /* 420-43c */ + uint32_t hprt0; /* 440 */ + }; + }; + +#define DWC2_HREG1_SIZE (0x20 * DWC2_NB_CHAN) + uint32_t hreg1[DWC2_HREG1_SIZE / sizeof(uint32_t)]; + +#define hcchar(_ch) hreg1[((_ch) << 3) + 0] /* 500, 520, ... */ +#define hcsplt(_ch) hreg1[((_ch) << 3) + 1] /* 504, 524, ... */ +#define hcint(_ch) hreg1[((_ch) << 3) + 2] /* 508, 528, ... */ +#define hcintmsk(_ch) hreg1[((_ch) << 3) + 3] /* 50c, 52c, ... */ +#define hctsiz(_ch) hreg1[((_ch) << 3) + 4] /* 510, 530, ... */ +#define hcdma(_ch) hreg1[((_ch) << 3) + 5] /* 514, 534, ... */ +#define hcdmab(_ch) hreg1[((_ch) << 3) + 7] /* 51c, 53c, ... */ + + union { +#define DWC2_PCGREG_SIZE 0x08 + uint32_t pcgreg[DWC2_PCGREG_SIZE / sizeof(uint32_t)]; + struct { + uint32_t pcgctl; /* e00 */ + uint32_t pcgcctl1; /* e04 */ + }; + }; + + /* TODO - implement FIFO registers for slave mode */ +#define DWC2_HFIFO_SIZE (0x1000 * DWC2_NB_CHAN) + + /* + * Internal state + */ + QEMUTimer *eof_timer; + QEMUTimer *frame_timer; + QEMUBH *async_bh; + int64_t sof_time; + int64_t usb_frame_time; + int64_t usb_bit_time; + uint32_t usb_version; + uint16_t frame_number; + uint16_t fi; + uint16_t next_chan; + bool working; + USBPort uport; + DWC2Packet packet[DWC2_NB_CHAN]; /* one packet per chan */ + uint8_t usb_buf[DWC2_NB_CHAN][DWC2_MAX_XFER_SIZE]; /* one buffer per chan */ +}; + +struct DWC2Class { + /*< private >*/ + SysBusDeviceClass parent_class; + ResettablePhases parent_phases; + + /*< public >*/ +}; + +#define TYPE_DWC2_USB "dwc2-usb" +#define DWC2_USB(obj) \ + OBJECT_CHECK(DWC2State, (obj), TYPE_DWC2_USB) +#define DWC2_CLASS(klass) \ + OBJECT_CLASS_CHECK(DWC2Class, (klass), TYPE_DWC2_USB) +#define DWC2_GET_CLASS(obj) \ + OBJECT_GET_CLASS(DWC2Class, (obj), TYPE_DWC2_USB) + +#endif -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add the dwc-hsotg (dwc2) USB host controller emulation code. Based on hw/usb/hcd-ehci.c and hw/usb/hcd-ohci.c. Note that to use this with the dwc-otg driver in the Raspbian kernel, you must pass the option "dwc_otg.fiq_fsm_enable=0" on the kernel command line. Emulation of slave mode and of descriptor-DMA mode has not been implemented yet. These modes are seldom used. I have used some on-line sources of information while developing this emulation, including: http://www.capital-micro.com/PDF/CME-M7_Family_User_Guide_EN.pdf which has a pretty complete description of the controller starting on page 370. https://sourceforge.net/p/wive-ng/wive-ng-mt/ci/master/tree/docs/DataSheets/RT3050_5x_V2.0_081408_0902.pdf which has a description of the controller registers starting on page 130. Thanks to Felippe Mathieu-Daude for providing a cleaner method of implementing the memory regions for the controller registers. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-5-pauldzim@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-dwc2.c | 1417 ++++++++++++++++++++++++++++++++++++++++++ hw/usb/Kconfig | 5 + hw/usb/Makefile.objs | 1 + hw/usb/trace-events | 50 ++ 4 files changed, 1473 insertions(+) create mode 100644 hw/usb/hcd-dwc2.c diff --git a/hw/usb/hcd-dwc2.c b/hw/usb/hcd-dwc2.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/hcd-dwc2.c @@ -XXX,XX +XXX,XX @@ +/* + * dwc-hsotg (dwc2) USB host controller emulation + * + * Based on hw/usb/hcd-ehci.c and hw/usb/hcd-ohci.c + * + * Note that to use this emulation with the dwc-otg driver in the + * Raspbian kernel, you must pass the option "dwc_otg.fiq_fsm_enable=0" + * on the kernel command line. + * + * Some useful documentation used to develop this emulation can be + * found online (as of April 2020) at: + * + * http://www.capital-micro.com/PDF/CME-M7_Family_User_Guide_EN.pdf + * which has a pretty complete description of the controller starting + * on page 370. + * + * https://sourceforge.net/p/wive-ng/wive-ng-mt/ci/master/tree/docs/DataSheets/RT3050_5x_V2.0_081408_0902.pdf + * which has a description of the controller registers starting on + * page 130. + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * 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/units.h" +#include "qapi/error.h" +#include "hw/usb/dwc2-regs.h" +#include "hw/usb/hcd-dwc2.h" +#include "migration/vmstate.h" +#include "trace.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "hw/qdev-properties.h" + +#define USB_HZ_FS 12000000 +#define USB_HZ_HS 96000000 +#define USB_FRMINTVL 12000 + +/* nifty macros from Arnon's EHCI version */ +#define get_field(data, field) \ + (((data) & field##_MASK) >> field##_SHIFT) + +#define set_field(data, newval, field) do { \ + uint32_t val = *(data); \ + val &= ~field##_MASK; \ + val |= ((newval) << field##_SHIFT) & field##_MASK; \ + *(data) = val; \ +} while (0) + +#define get_bit(data, bitmask) \ + (!!((data) & (bitmask))) + +/* update irq line */ +static inline void dwc2_update_irq(DWC2State *s) +{ + static int oldlevel; + int level = 0; + + if ((s->gintsts & s->gintmsk) && (s->gahbcfg & GAHBCFG_GLBL_INTR_EN)) { + level = 1; + } + if (level != oldlevel) { + oldlevel = level; + trace_usb_dwc2_update_irq(level); + qemu_set_irq(s->irq, level); + } +} + +/* flag interrupt condition */ +static inline void dwc2_raise_global_irq(DWC2State *s, uint32_t intr) +{ + if (!(s->gintsts & intr)) { + s->gintsts |= intr; + trace_usb_dwc2_raise_global_irq(intr); + dwc2_update_irq(s); + } +} + +static inline void dwc2_lower_global_irq(DWC2State *s, uint32_t intr) +{ + if (s->gintsts & intr) { + s->gintsts &= ~intr; + trace_usb_dwc2_lower_global_irq(intr); + dwc2_update_irq(s); + } +} + +static inline void dwc2_raise_host_irq(DWC2State *s, uint32_t host_intr) +{ + if (!(s->haint & host_intr)) { + s->haint |= host_intr; + s->haint &= 0xffff; + trace_usb_dwc2_raise_host_irq(host_intr); + if (s->haint & s->haintmsk) { + dwc2_raise_global_irq(s, GINTSTS_HCHINT); + } + } +} + +static inline void dwc2_lower_host_irq(DWC2State *s, uint32_t host_intr) +{ + if (s->haint & host_intr) { + s->haint &= ~host_intr; + trace_usb_dwc2_lower_host_irq(host_intr); + if (!(s->haint & s->haintmsk)) { + dwc2_lower_global_irq(s, GINTSTS_HCHINT); + } + } +} + +static inline void dwc2_update_hc_irq(DWC2State *s, int index) +{ + uint32_t host_intr = 1 << (index >> 3); + + if (s->hreg1[index + 2] & s->hreg1[index + 3]) { + dwc2_raise_host_irq(s, host_intr); + } else { + dwc2_lower_host_irq(s, host_intr); + } +} + +/* set a timer for EOF */ +static void dwc2_eof_timer(DWC2State *s) +{ + timer_mod(s->eof_timer, s->sof_time + s->usb_frame_time); +} + +/* Set a timer for EOF and generate SOF event */ +static void dwc2_sof(DWC2State *s) +{ + s->sof_time += s->usb_frame_time; + trace_usb_dwc2_sof(s->sof_time); + dwc2_eof_timer(s); + dwc2_raise_global_irq(s, GINTSTS_SOF); +} + +/* Do frame processing on frame boundary */ +static void dwc2_frame_boundary(void *opaque) +{ + DWC2State *s = opaque; + int64_t now; + uint16_t frcnt; + + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + /* Frame boundary, so do EOF stuff here */ + + /* Increment frame number */ + frcnt = (uint16_t)((now - s->sof_time) / s->fi); + s->frame_number = (s->frame_number + frcnt) & 0xffff; + s->hfnum = s->frame_number & HFNUM_MAX_FRNUM; + + /* Do SOF stuff here */ + dwc2_sof(s); +} + +/* Start sending SOF tokens on the USB bus */ +static void dwc2_bus_start(DWC2State *s) +{ + trace_usb_dwc2_bus_start(); + s->sof_time = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + dwc2_eof_timer(s); +} + +/* Stop sending SOF tokens on the USB bus */ +static void dwc2_bus_stop(DWC2State *s) +{ + trace_usb_dwc2_bus_stop(); + timer_del(s->eof_timer); +} + +static USBDevice *dwc2_find_device(DWC2State *s, uint8_t addr) +{ + USBDevice *dev; + + trace_usb_dwc2_find_device(addr); + + if (!(s->hprt0 & HPRT0_ENA)) { + trace_usb_dwc2_port_disabled(0); + } else { + dev = usb_find_device(&s->uport, addr); + if (dev != NULL) { + trace_usb_dwc2_device_found(0); + return dev; + } + } + + trace_usb_dwc2_device_not_found(); + return NULL; +} + +static const char *pstatus[] = { + "USB_RET_SUCCESS", "USB_RET_NODEV", "USB_RET_NAK", "USB_RET_STALL", + "USB_RET_BABBLE", "USB_RET_IOERROR", "USB_RET_ASYNC", + "USB_RET_ADD_TO_QUEUE", "USB_RET_REMOVE_FROM_QUEUE" +}; + +static uint32_t pintr[] = { + HCINTMSK_XFERCOMPL, HCINTMSK_XACTERR, HCINTMSK_NAK, HCINTMSK_STALL, + HCINTMSK_BBLERR, HCINTMSK_XACTERR, HCINTMSK_XACTERR, HCINTMSK_XACTERR, + HCINTMSK_XACTERR +}; + +static const char *types[] = { + "Ctrl", "Isoc", "Bulk", "Intr" +}; + +static const char *dirs[] = { + "Out", "In" +}; + +static void dwc2_handle_packet(DWC2State *s, uint32_t devadr, USBDevice *dev, + USBEndpoint *ep, uint32_t index, bool send) +{ + DWC2Packet *p; + uint32_t hcchar = s->hreg1[index]; + uint32_t hctsiz = s->hreg1[index + 4]; + uint32_t hcdma = s->hreg1[index + 5]; + uint32_t chan, epnum, epdir, eptype, mps, pid, pcnt, len, tlen, intr = 0; + uint32_t tpcnt, stsidx, actual = 0; + bool do_intr = false, done = false; + + epnum = get_field(hcchar, HCCHAR_EPNUM); + epdir = get_bit(hcchar, HCCHAR_EPDIR); + eptype = get_field(hcchar, HCCHAR_EPTYPE); + mps = get_field(hcchar, HCCHAR_MPS); + pid = get_field(hctsiz, TSIZ_SC_MC_PID); + pcnt = get_field(hctsiz, TSIZ_PKTCNT); + len = get_field(hctsiz, TSIZ_XFERSIZE); + assert(len <= DWC2_MAX_XFER_SIZE); + chan = index >> 3; + p = &s->packet[chan]; + + trace_usb_dwc2_handle_packet(chan, dev, &p->packet, epnum, types[eptype], + dirs[epdir], mps, len, pcnt); + + if (eptype == USB_ENDPOINT_XFER_CONTROL && pid == TSIZ_SC_MC_PID_SETUP) { + pid = USB_TOKEN_SETUP; + } else { + pid = epdir ? USB_TOKEN_IN : USB_TOKEN_OUT; + } + + if (send) { + tlen = len; + if (p->small) { + if (tlen > mps) { + tlen = mps; + } + } + + if (pid != USB_TOKEN_IN) { + trace_usb_dwc2_memory_read(hcdma, tlen); + if (dma_memory_read(&s->dma_as, hcdma, + s->usb_buf[chan], tlen) != MEMTX_OK) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: dma_memory_read failed\n", + __func__); + } + } + + usb_packet_init(&p->packet); + usb_packet_setup(&p->packet, pid, ep, 0, hcdma, + pid != USB_TOKEN_IN, true); + usb_packet_addbuf(&p->packet, s->usb_buf[chan], tlen); + p->async = DWC2_ASYNC_NONE; + usb_handle_packet(dev, &p->packet); + } else { + tlen = p->len; + } + + stsidx = -p->packet.status; + assert(stsidx < sizeof(pstatus) / sizeof(*pstatus)); + actual = p->packet.actual_length; + trace_usb_dwc2_packet_status(pstatus[stsidx], actual); + +babble: + if (p->packet.status != USB_RET_SUCCESS && + p->packet.status != USB_RET_NAK && + p->packet.status != USB_RET_STALL && + p->packet.status != USB_RET_ASYNC) { + trace_usb_dwc2_packet_error(pstatus[stsidx]); + } + + if (p->packet.status == USB_RET_ASYNC) { + trace_usb_dwc2_async_packet(&p->packet, chan, dev, epnum, + dirs[epdir], tlen); + usb_device_flush_ep_queue(dev, ep); + assert(p->async != DWC2_ASYNC_INFLIGHT); + p->devadr = devadr; + p->epnum = epnum; + p->epdir = epdir; + p->mps = mps; + p->pid = pid; + p->index = index; + p->pcnt = pcnt; + p->len = tlen; + p->async = DWC2_ASYNC_INFLIGHT; + p->needs_service = false; + return; + } + + if (p->packet.status == USB_RET_SUCCESS) { + if (actual > tlen) { + p->packet.status = USB_RET_BABBLE; + goto babble; + } + + if (pid == USB_TOKEN_IN) { + trace_usb_dwc2_memory_write(hcdma, actual); + if (dma_memory_write(&s->dma_as, hcdma, s->usb_buf[chan], + actual) != MEMTX_OK) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: dma_memory_write failed\n", + __func__); + } + } + + tpcnt = actual / mps; + if (actual % mps) { + tpcnt++; + if (pid == USB_TOKEN_IN) { + done = true; + } + } + + pcnt -= tpcnt < pcnt ? tpcnt : pcnt; + set_field(&hctsiz, pcnt, TSIZ_PKTCNT); + len -= actual < len ? actual : len; + set_field(&hctsiz, len, TSIZ_XFERSIZE); + s->hreg1[index + 4] = hctsiz; + hcdma += actual; + s->hreg1[index + 5] = hcdma; + + if (!pcnt || len == 0 || actual == 0) { + done = true; + } + } else { + intr |= pintr[stsidx]; + if (p->packet.status == USB_RET_NAK && + (eptype == USB_ENDPOINT_XFER_CONTROL || + eptype == USB_ENDPOINT_XFER_BULK)) { + /* + * for ctrl/bulk, automatically retry on NAK, + * but send the interrupt anyway + */ + intr &= ~HCINTMSK_RESERVED14_31; + s->hreg1[index + 2] |= intr; + do_intr = true; + } else { + intr |= HCINTMSK_CHHLTD; + done = true; + } + } + + usb_packet_cleanup(&p->packet); + + if (done) { + hcchar &= ~HCCHAR_CHENA; + s->hreg1[index] = hcchar; + if (!(intr & HCINTMSK_CHHLTD)) { + intr |= HCINTMSK_CHHLTD | HCINTMSK_XFERCOMPL; + } + intr &= ~HCINTMSK_RESERVED14_31; + s->hreg1[index + 2] |= intr; + p->needs_service = false; + trace_usb_dwc2_packet_done(pstatus[stsidx], actual, len, pcnt); + dwc2_update_hc_irq(s, index); + return; + } + + p->devadr = devadr; + p->epnum = epnum; + p->epdir = epdir; + p->mps = mps; + p->pid = pid; + p->index = index; + p->pcnt = pcnt; + p->len = len; + p->needs_service = true; + trace_usb_dwc2_packet_next(pstatus[stsidx], len, pcnt); + if (do_intr) { + dwc2_update_hc_irq(s, index); + } +} + +/* Attach or detach a device on root hub */ + +static const char *speeds[] = { + "low", "full", "high" +}; + +static void dwc2_attach(USBPort *port) +{ + DWC2State *s = port->opaque; + int hispd = 0; + + trace_usb_dwc2_attach(port); + assert(port->index == 0); + + if (!port->dev || !port->dev->attached) { + return; + } + + assert(port->dev->speed <= USB_SPEED_HIGH); + trace_usb_dwc2_attach_speed(speeds[port->dev->speed]); + s->hprt0 &= ~HPRT0_SPD_MASK; + + switch (port->dev->speed) { + case USB_SPEED_LOW: + s->hprt0 |= HPRT0_SPD_LOW_SPEED << HPRT0_SPD_SHIFT; + break; + case USB_SPEED_FULL: + s->hprt0 |= HPRT0_SPD_FULL_SPEED << HPRT0_SPD_SHIFT; + break; + case USB_SPEED_HIGH: + s->hprt0 |= HPRT0_SPD_HIGH_SPEED << HPRT0_SPD_SHIFT; + hispd = 1; + break; + } + + if (hispd) { + s->usb_frame_time = NANOSECONDS_PER_SECOND / 8000; /* 125000 */ + if (NANOSECONDS_PER_SECOND >= USB_HZ_HS) { + s->usb_bit_time = NANOSECONDS_PER_SECOND / USB_HZ_HS; /* 10.4 */ + } else { + s->usb_bit_time = 1; + } + } else { + s->usb_frame_time = NANOSECONDS_PER_SECOND / 1000; /* 1000000 */ + if (NANOSECONDS_PER_SECOND >= USB_HZ_FS) { + s->usb_bit_time = NANOSECONDS_PER_SECOND / USB_HZ_FS; /* 83.3 */ + } else { + s->usb_bit_time = 1; + } + } + + s->fi = USB_FRMINTVL - 1; + s->hprt0 |= HPRT0_CONNDET | HPRT0_CONNSTS; + + dwc2_bus_start(s); + dwc2_raise_global_irq(s, GINTSTS_PRTINT); +} + +static void dwc2_detach(USBPort *port) +{ + DWC2State *s = port->opaque; + + trace_usb_dwc2_detach(port); + assert(port->index == 0); + + dwc2_bus_stop(s); + + s->hprt0 &= ~(HPRT0_SPD_MASK | HPRT0_SUSP | HPRT0_ENA | HPRT0_CONNSTS); + s->hprt0 |= HPRT0_CONNDET | HPRT0_ENACHG; + + dwc2_raise_global_irq(s, GINTSTS_PRTINT); +} + +static void dwc2_child_detach(USBPort *port, USBDevice *child) +{ + trace_usb_dwc2_child_detach(port, child); + assert(port->index == 0); +} + +static void dwc2_wakeup(USBPort *port) +{ + DWC2State *s = port->opaque; + + trace_usb_dwc2_wakeup(port); + assert(port->index == 0); + + if (s->hprt0 & HPRT0_SUSP) { + s->hprt0 |= HPRT0_RES; + dwc2_raise_global_irq(s, GINTSTS_PRTINT); + } + + qemu_bh_schedule(s->async_bh); +} + +static void dwc2_async_packet_complete(USBPort *port, USBPacket *packet) +{ + DWC2State *s = port->opaque; + DWC2Packet *p; + USBDevice *dev; + USBEndpoint *ep; + + assert(port->index == 0); + p = container_of(packet, DWC2Packet, packet); + dev = dwc2_find_device(s, p->devadr); + ep = usb_ep_get(dev, p->pid, p->epnum); + trace_usb_dwc2_async_packet_complete(port, packet, p->index >> 3, dev, + p->epnum, dirs[p->epdir], p->len); + assert(p->async == DWC2_ASYNC_INFLIGHT); + + if (packet->status == USB_RET_REMOVE_FROM_QUEUE) { + usb_cancel_packet(packet); + usb_packet_cleanup(packet); + return; + } + + dwc2_handle_packet(s, p->devadr, dev, ep, p->index, false); + + p->async = DWC2_ASYNC_FINISHED; + qemu_bh_schedule(s->async_bh); +} + +static USBPortOps dwc2_port_ops = { + .attach = dwc2_attach, + .detach = dwc2_detach, + .child_detach = dwc2_child_detach, + .wakeup = dwc2_wakeup, + .complete = dwc2_async_packet_complete, +}; + +static uint32_t dwc2_get_frame_remaining(DWC2State *s) +{ + uint32_t fr = 0; + int64_t tks; + + tks = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - s->sof_time; + if (tks < 0) { + tks = 0; + } + + /* avoid muldiv if possible */ + if (tks >= s->usb_frame_time) { + goto out; + } + if (tks < s->usb_bit_time) { + fr = s->fi; + goto out; + } + + /* tks = number of ns since SOF, divided by 83 (fs) or 10 (hs) */ + tks = tks / s->usb_bit_time; + if (tks >= (int64_t)s->fi) { + goto out; + } + + /* remaining = frame interval minus tks */ + fr = (uint32_t)((int64_t)s->fi - tks); + +out: + return fr; +} + +static void dwc2_work_bh(void *opaque) +{ + DWC2State *s = opaque; + DWC2Packet *p; + USBDevice *dev; + USBEndpoint *ep; + int64_t t_now, expire_time; + int chan; + bool found = false; + + trace_usb_dwc2_work_bh(); + if (s->working) { + return; + } + s->working = true; + + t_now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + chan = s->next_chan; + + do { + p = &s->packet[chan]; + if (p->needs_service) { + dev = dwc2_find_device(s, p->devadr); + ep = usb_ep_get(dev, p->pid, p->epnum); + trace_usb_dwc2_work_bh_service(s->next_chan, chan, dev, p->epnum); + dwc2_handle_packet(s, p->devadr, dev, ep, p->index, true); + found = true; + } + if (++chan == DWC2_NB_CHAN) { + chan = 0; + } + if (found) { + s->next_chan = chan; + trace_usb_dwc2_work_bh_next(chan); + } + } while (chan != s->next_chan); + + if (found) { + expire_time = t_now + NANOSECONDS_PER_SECOND / 4000; + timer_mod(s->frame_timer, expire_time); + } + s->working = false; +} + +static void dwc2_enable_chan(DWC2State *s, uint32_t index) +{ + USBDevice *dev; + USBEndpoint *ep; + uint32_t hcchar; + uint32_t hctsiz; + uint32_t devadr, epnum, epdir, eptype, pid, len; + DWC2Packet *p; + + assert((index >> 3) < DWC2_NB_CHAN); + p = &s->packet[index >> 3]; + hcchar = s->hreg1[index]; + hctsiz = s->hreg1[index + 4]; + devadr = get_field(hcchar, HCCHAR_DEVADDR); + epnum = get_field(hcchar, HCCHAR_EPNUM); + epdir = get_bit(hcchar, HCCHAR_EPDIR); + eptype = get_field(hcchar, HCCHAR_EPTYPE); + pid = get_field(hctsiz, TSIZ_SC_MC_PID); + len = get_field(hctsiz, TSIZ_XFERSIZE); + + dev = dwc2_find_device(s, devadr); + + trace_usb_dwc2_enable_chan(index >> 3, dev, &p->packet, epnum); + if (dev == NULL) { + return; + } + + if (eptype == USB_ENDPOINT_XFER_CONTROL && pid == TSIZ_SC_MC_PID_SETUP) { + pid = USB_TOKEN_SETUP; + } else { + pid = epdir ? USB_TOKEN_IN : USB_TOKEN_OUT; + } + + ep = usb_ep_get(dev, pid, epnum); + + /* + * Hack: Networking doesn't like us delivering large transfers, it kind + * of works but the latency is horrible. So if the transfer is <= the mtu + * size, we take that as a hint that this might be a network transfer, + * and do the transfer packet-by-packet. + */ + if (len > 1536) { + p->small = false; + } else { + p->small = true; + } + + dwc2_handle_packet(s, devadr, dev, ep, index, true); + qemu_bh_schedule(s->async_bh); +} + +static const char *glbregnm[] = { + "GOTGCTL ", "GOTGINT ", "GAHBCFG ", "GUSBCFG ", "GRSTCTL ", + "GINTSTS ", "GINTMSK ", "GRXSTSR ", "GRXSTSP ", "GRXFSIZ ", + "GNPTXFSIZ", "GNPTXSTS ", "GI2CCTL ", "GPVNDCTL ", "GGPIO ", + "GUID ", "GSNPSID ", "GHWCFG1 ", "GHWCFG2 ", "GHWCFG3 ", + "GHWCFG4 ", "GLPMCFG ", "GPWRDN ", "GDFIFOCFG", "GADPCTL ", + "GREFCLK ", "GINTMSK2 ", "GINTSTS2 " +}; + +static uint64_t dwc2_glbreg_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr <= GINTSTS2); + val = s->glbreg[index]; + + switch (addr) { + case GRSTCTL: + /* clear any self-clearing bits that were set */ + val &= ~(GRSTCTL_TXFFLSH | GRSTCTL_RXFFLSH | GRSTCTL_IN_TKNQ_FLSH | + GRSTCTL_FRMCNTRRST | GRSTCTL_HSFTRST | GRSTCTL_CSFTRST); + s->glbreg[index] = val; + break; + default: + break; + } + + trace_usb_dwc2_glbreg_read(addr, glbregnm[index], val); + return val; +} + +static void dwc2_glbreg_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + int iflg = 0; + + assert(addr <= GINTSTS2); + mmio = &s->glbreg[index]; + old = *mmio; + + switch (addr) { + case GOTGCTL: + /* don't allow setting of read-only bits */ + val &= ~(GOTGCTL_MULT_VALID_BC_MASK | GOTGCTL_BSESVLD | + GOTGCTL_ASESVLD | GOTGCTL_DBNC_SHORT | GOTGCTL_CONID_B | + GOTGCTL_HSTNEGSCS | GOTGCTL_SESREQSCS); + /* don't allow clearing of read-only bits */ + val |= old & (GOTGCTL_MULT_VALID_BC_MASK | GOTGCTL_BSESVLD | + GOTGCTL_ASESVLD | GOTGCTL_DBNC_SHORT | GOTGCTL_CONID_B | + GOTGCTL_HSTNEGSCS | GOTGCTL_SESREQSCS); + break; + case GAHBCFG: + if ((val & GAHBCFG_GLBL_INTR_EN) && !(old & GAHBCFG_GLBL_INTR_EN)) { + iflg = 1; + } + break; + case GRSTCTL: + val |= GRSTCTL_AHBIDLE; + val &= ~GRSTCTL_DMAREQ; + if (!(old & GRSTCTL_TXFFLSH) && (val & GRSTCTL_TXFFLSH)) { + /* TODO - TX fifo flush */ + qemu_log_mask(LOG_UNIMP, "Tx FIFO flush not implemented\n"); + } + if (!(old & GRSTCTL_RXFFLSH) && (val & GRSTCTL_RXFFLSH)) { + /* TODO - RX fifo flush */ + qemu_log_mask(LOG_UNIMP, "Rx FIFO flush not implemented\n"); + } + if (!(old & GRSTCTL_IN_TKNQ_FLSH) && (val & GRSTCTL_IN_TKNQ_FLSH)) { + /* TODO - device IN token queue flush */ + qemu_log_mask(LOG_UNIMP, "Token queue flush not implemented\n"); + } + if (!(old & GRSTCTL_FRMCNTRRST) && (val & GRSTCTL_FRMCNTRRST)) { + /* TODO - host frame counter reset */ + qemu_log_mask(LOG_UNIMP, "Frame counter reset not implemented\n"); + } + if (!(old & GRSTCTL_HSFTRST) && (val & GRSTCTL_HSFTRST)) { + /* TODO - host soft reset */ + qemu_log_mask(LOG_UNIMP, "Host soft reset not implemented\n"); + } + if (!(old & GRSTCTL_CSFTRST) && (val & GRSTCTL_CSFTRST)) { + /* TODO - core soft reset */ + qemu_log_mask(LOG_UNIMP, "Core soft reset not implemented\n"); + } + /* don't allow clearing of self-clearing bits */ + val |= old & (GRSTCTL_TXFFLSH | GRSTCTL_RXFFLSH | + GRSTCTL_IN_TKNQ_FLSH | GRSTCTL_FRMCNTRRST | + GRSTCTL_HSFTRST | GRSTCTL_CSFTRST); + break; + case GINTSTS: + /* clear the write-1-to-clear bits */ + val |= ~old; + val = ~val; + /* don't allow clearing of read-only bits */ + val |= old & (GINTSTS_PTXFEMP | GINTSTS_HCHINT | GINTSTS_PRTINT | + GINTSTS_OEPINT | GINTSTS_IEPINT | GINTSTS_GOUTNAKEFF | + GINTSTS_GINNAKEFF | GINTSTS_NPTXFEMP | GINTSTS_RXFLVL | + GINTSTS_OTGINT | GINTSTS_CURMODE_HOST); + iflg = 1; + break; + case GINTMSK: + iflg = 1; + break; + default: + break; + } + + trace_usb_dwc2_glbreg_write(addr, glbregnm[index], orig, old, val); + *mmio = val; + + if (iflg) { + dwc2_update_irq(s); + } +} + +static uint64_t dwc2_fszreg_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr == HPTXFSIZ); + val = s->fszreg[index]; + + trace_usb_dwc2_fszreg_read(addr, val); + return val; +} + +static void dwc2_fszreg_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + + assert(addr == HPTXFSIZ); + mmio = &s->fszreg[index]; + old = *mmio; + + trace_usb_dwc2_fszreg_write(addr, orig, old, val); + *mmio = val; +} + +static const char *hreg0nm[] = { + "HCFG ", "HFIR ", "HFNUM ", "<rsvd> ", "HPTXSTS ", + "HAINT ", "HAINTMSK ", "HFLBADDR ", "<rsvd> ", "<rsvd> ", + "<rsvd> ", "<rsvd> ", "<rsvd> ", "<rsvd> ", "<rsvd> ", + "<rsvd> ", "HPRT0 " +}; + +static uint64_t dwc2_hreg0_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr >= HCFG && addr <= HPRT0); + val = s->hreg0[index]; + + switch (addr) { + case HFNUM: + val = (dwc2_get_frame_remaining(s) << HFNUM_FRREM_SHIFT) | + (s->hfnum << HFNUM_FRNUM_SHIFT); + break; + default: + break; + } + + trace_usb_dwc2_hreg0_read(addr, hreg0nm[index], val); + return val; +} + +static void dwc2_hreg0_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + USBDevice *dev = s->uport.dev; + uint64_t orig = val; + uint32_t *mmio; + uint32_t tval, told, old; + int prst = 0; + int iflg = 0; + + assert(addr >= HCFG && addr <= HPRT0); + mmio = &s->hreg0[index]; + old = *mmio; + + switch (addr) { + case HFIR: + break; + case HFNUM: + case HPTXSTS: + case HAINT: + qemu_log_mask(LOG_GUEST_ERROR, "%s: write to read-only register\n", + __func__); + return; + case HAINTMSK: + val &= 0xffff; + break; + case HPRT0: + /* don't allow clearing of read-only bits */ + val |= old & (HPRT0_SPD_MASK | HPRT0_LNSTS_MASK | HPRT0_OVRCURRACT | + HPRT0_CONNSTS); + /* don't allow clearing of self-clearing bits */ + val |= old & (HPRT0_SUSP | HPRT0_RES); + /* don't allow setting of self-setting bits */ + if (!(old & HPRT0_ENA) && (val & HPRT0_ENA)) { + val &= ~HPRT0_ENA; + } + /* clear the write-1-to-clear bits */ + tval = val & (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + told = old & (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + tval |= ~told; + tval = ~tval; + tval &= (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + val &= ~(HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + val |= tval; + if (!(val & HPRT0_RST) && (old & HPRT0_RST)) { + if (dev && dev->attached) { + val |= HPRT0_ENA | HPRT0_ENACHG; + prst = 1; + } + } + if (val & (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_CONNDET)) { + iflg = 1; + } else { + iflg = -1; + } + break; + default: + break; + } + + if (prst) { + trace_usb_dwc2_hreg0_write(addr, hreg0nm[index], orig, old, + val & ~HPRT0_CONNDET); + trace_usb_dwc2_hreg0_action("call usb_port_reset"); + usb_port_reset(&s->uport); + val &= ~HPRT0_CONNDET; + } else { + trace_usb_dwc2_hreg0_write(addr, hreg0nm[index], orig, old, val); + } + + *mmio = val; + + if (iflg > 0) { + trace_usb_dwc2_hreg0_action("enable PRTINT"); + dwc2_raise_global_irq(s, GINTSTS_PRTINT); + } else if (iflg < 0) { + trace_usb_dwc2_hreg0_action("disable PRTINT"); + dwc2_lower_global_irq(s, GINTSTS_PRTINT); + } +} + +static const char *hreg1nm[] = { + "HCCHAR ", "HCSPLT ", "HCINT ", "HCINTMSK", "HCTSIZ ", "HCDMA ", + "<rsvd> ", "HCDMAB " +}; + +static uint64_t dwc2_hreg1_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr >= HCCHAR(0) && addr <= HCDMAB(DWC2_NB_CHAN - 1)); + val = s->hreg1[index]; + + trace_usb_dwc2_hreg1_read(addr, hreg1nm[index & 7], addr >> 5, val); + return val; +} + +static void dwc2_hreg1_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + int iflg = 0; + int enflg = 0; + int disflg = 0; + + assert(addr >= HCCHAR(0) && addr <= HCDMAB(DWC2_NB_CHAN - 1)); + mmio = &s->hreg1[index]; + old = *mmio; + + switch (HSOTG_REG(0x500) + (addr & 0x1c)) { + case HCCHAR(0): + if ((val & HCCHAR_CHDIS) && !(old & HCCHAR_CHDIS)) { + val &= ~(HCCHAR_CHENA | HCCHAR_CHDIS); + disflg = 1; + } else { + val |= old & HCCHAR_CHDIS; + if ((val & HCCHAR_CHENA) && !(old & HCCHAR_CHENA)) { + val &= ~HCCHAR_CHDIS; + enflg = 1; + } else { + val |= old & HCCHAR_CHENA; + } + } + break; + case HCINT(0): + /* clear the write-1-to-clear bits */ + val |= ~old; + val = ~val; + val &= ~HCINTMSK_RESERVED14_31; + iflg = 1; + break; + case HCINTMSK(0): + val &= ~HCINTMSK_RESERVED14_31; + iflg = 1; + break; + case HCDMAB(0): + qemu_log_mask(LOG_GUEST_ERROR, "%s: write to read-only register\n", + __func__); + return; + default: + break; + } + + trace_usb_dwc2_hreg1_write(addr, hreg1nm[index & 7], index >> 3, orig, + old, val); + *mmio = val; + + if (disflg) { + /* set ChHltd in HCINT */ + s->hreg1[(index & ~7) + 2] |= HCINTMSK_CHHLTD; + iflg = 1; + } + + if (enflg) { + dwc2_enable_chan(s, index & ~7); + } + + if (iflg) { + dwc2_update_hc_irq(s, index & ~7); + } +} + +static const char *pcgregnm[] = { + "PCGCTL ", "PCGCCTL1 " +}; + +static uint64_t dwc2_pcgreg_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr >= PCGCTL && addr <= PCGCCTL1); + val = s->pcgreg[index]; + + trace_usb_dwc2_pcgreg_read(addr, pcgregnm[index], val); + return val; +} + +static void dwc2_pcgreg_write(void *ptr, hwaddr addr, int index, + uint64_t val, unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + + assert(addr >= PCGCTL && addr <= PCGCCTL1); + mmio = &s->pcgreg[index]; + old = *mmio; + + trace_usb_dwc2_pcgreg_write(addr, pcgregnm[index], orig, old, val); + *mmio = val; +} + +static uint64_t dwc2_hsotg_read(void *ptr, hwaddr addr, unsigned size) +{ + uint64_t val; + + switch (addr) { + case HSOTG_REG(0x000) ... HSOTG_REG(0x0fc): + val = dwc2_glbreg_read(ptr, addr, (addr - HSOTG_REG(0x000)) >> 2, size); + break; + case HSOTG_REG(0x100): + val = dwc2_fszreg_read(ptr, addr, (addr - HSOTG_REG(0x100)) >> 2, size); + break; + case HSOTG_REG(0x104) ... HSOTG_REG(0x3fc): + /* Gadget-mode registers, just return 0 for now */ + val = 0; + break; + case HSOTG_REG(0x400) ... HSOTG_REG(0x4fc): + val = dwc2_hreg0_read(ptr, addr, (addr - HSOTG_REG(0x400)) >> 2, size); + break; + case HSOTG_REG(0x500) ... HSOTG_REG(0x7fc): + val = dwc2_hreg1_read(ptr, addr, (addr - HSOTG_REG(0x500)) >> 2, size); + break; + case HSOTG_REG(0x800) ... HSOTG_REG(0xdfc): + /* Gadget-mode registers, just return 0 for now */ + val = 0; + break; + case HSOTG_REG(0xe00) ... HSOTG_REG(0xffc): + val = dwc2_pcgreg_read(ptr, addr, (addr - HSOTG_REG(0xe00)) >> 2, size); + break; + default: + g_assert_not_reached(); + } + + return val; +} + +static void dwc2_hsotg_write(void *ptr, hwaddr addr, uint64_t val, + unsigned size) +{ + switch (addr) { + case HSOTG_REG(0x000) ... HSOTG_REG(0x0fc): + dwc2_glbreg_write(ptr, addr, (addr - HSOTG_REG(0x000)) >> 2, val, size); + break; + case HSOTG_REG(0x100): + dwc2_fszreg_write(ptr, addr, (addr - HSOTG_REG(0x100)) >> 2, val, size); + break; + case HSOTG_REG(0x104) ... HSOTG_REG(0x3fc): + /* Gadget-mode registers, do nothing for now */ + break; + case HSOTG_REG(0x400) ... HSOTG_REG(0x4fc): + dwc2_hreg0_write(ptr, addr, (addr - HSOTG_REG(0x400)) >> 2, val, size); + break; + case HSOTG_REG(0x500) ... HSOTG_REG(0x7fc): + dwc2_hreg1_write(ptr, addr, (addr - HSOTG_REG(0x500)) >> 2, val, size); + break; + case HSOTG_REG(0x800) ... HSOTG_REG(0xdfc): + /* Gadget-mode registers, do nothing for now */ + break; + case HSOTG_REG(0xe00) ... HSOTG_REG(0xffc): + dwc2_pcgreg_write(ptr, addr, (addr - HSOTG_REG(0xe00)) >> 2, val, size); + break; + default: + g_assert_not_reached(); + } +} + +static const MemoryRegionOps dwc2_mmio_hsotg_ops = { + .read = dwc2_hsotg_read, + .write = dwc2_hsotg_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static uint64_t dwc2_hreg2_read(void *ptr, hwaddr addr, unsigned size) +{ + /* TODO - implement FIFOs to support slave mode */ + trace_usb_dwc2_hreg2_read(addr, addr >> 12, 0); + qemu_log_mask(LOG_UNIMP, "FIFO read not implemented\n"); + return 0; +} + +static void dwc2_hreg2_write(void *ptr, hwaddr addr, uint64_t val, + unsigned size) +{ + uint64_t orig = val; + + /* TODO - implement FIFOs to support slave mode */ + trace_usb_dwc2_hreg2_write(addr, addr >> 12, orig, 0, val); + qemu_log_mask(LOG_UNIMP, "FIFO write not implemented\n"); +} + +static const MemoryRegionOps dwc2_mmio_hreg2_ops = { + .read = dwc2_hreg2_read, + .write = dwc2_hreg2_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void dwc2_wakeup_endpoint(USBBus *bus, USBEndpoint *ep, + unsigned int stream) +{ + DWC2State *s = container_of(bus, DWC2State, bus); + + trace_usb_dwc2_wakeup_endpoint(ep, stream); + + /* TODO - do something here? */ + qemu_bh_schedule(s->async_bh); +} + +static USBBusOps dwc2_bus_ops = { + .wakeup_endpoint = dwc2_wakeup_endpoint, +}; + +static void dwc2_work_timer(void *opaque) +{ + DWC2State *s = opaque; + + trace_usb_dwc2_work_timer(); + qemu_bh_schedule(s->async_bh); +} + +static void dwc2_reset_enter(Object *obj, ResetType type) +{ + DWC2Class *c = DWC2_GET_CLASS(obj); + DWC2State *s = DWC2_USB(obj); + int i; + + trace_usb_dwc2_reset_enter(); + + if (c->parent_phases.enter) { + c->parent_phases.enter(obj, type); + } + + timer_del(s->frame_timer); + qemu_bh_cancel(s->async_bh); + + if (s->uport.dev && s->uport.dev->attached) { + usb_detach(&s->uport); + } + + dwc2_bus_stop(s); + + s->gotgctl = GOTGCTL_BSESVLD | GOTGCTL_ASESVLD | GOTGCTL_CONID_B; + s->gotgint = 0; + s->gahbcfg = 0; + s->gusbcfg = 5 << GUSBCFG_USBTRDTIM_SHIFT; + s->grstctl = GRSTCTL_AHBIDLE; + s->gintsts = GINTSTS_CONIDSTSCHNG | GINTSTS_PTXFEMP | GINTSTS_NPTXFEMP | + GINTSTS_CURMODE_HOST; + s->gintmsk = 0; + s->grxstsr = 0; + s->grxstsp = 0; + s->grxfsiz = 1024; + s->gnptxfsiz = 1024 << FIFOSIZE_DEPTH_SHIFT; + s->gnptxsts = (4 << FIFOSIZE_DEPTH_SHIFT) | 1024; + s->gi2cctl = GI2CCTL_I2CDATSE0 | GI2CCTL_ACK; + s->gpvndctl = 0; + s->ggpio = 0; + s->guid = 0; + s->gsnpsid = 0x4f54294a; + s->ghwcfg1 = 0; + s->ghwcfg2 = (8 << GHWCFG2_DEV_TOKEN_Q_DEPTH_SHIFT) | + (4 << GHWCFG2_HOST_PERIO_TX_Q_DEPTH_SHIFT) | + (4 << GHWCFG2_NONPERIO_TX_Q_DEPTH_SHIFT) | + GHWCFG2_DYNAMIC_FIFO | + GHWCFG2_PERIO_EP_SUPPORTED | + ((DWC2_NB_CHAN - 1) << GHWCFG2_NUM_HOST_CHAN_SHIFT) | + (GHWCFG2_INT_DMA_ARCH << GHWCFG2_ARCHITECTURE_SHIFT) | + (GHWCFG2_OP_MODE_NO_SRP_CAPABLE_HOST << GHWCFG2_OP_MODE_SHIFT); + s->ghwcfg3 = (4096 << GHWCFG3_DFIFO_DEPTH_SHIFT) | + (4 << GHWCFG3_PACKET_SIZE_CNTR_WIDTH_SHIFT) | + (4 << GHWCFG3_XFER_SIZE_CNTR_WIDTH_SHIFT); + s->ghwcfg4 = 0; + s->glpmcfg = 0; + s->gpwrdn = GPWRDN_PWRDNRSTN; + s->gdfifocfg = 0; + s->gadpctl = 0; + s->grefclk = 0; + s->gintmsk2 = 0; + s->gintsts2 = 0; + + s->hptxfsiz = 500 << FIFOSIZE_DEPTH_SHIFT; + + s->hcfg = 2 << HCFG_RESVALID_SHIFT; + s->hfir = 60000; + s->hfnum = 0x3fff; + s->hptxsts = (16 << TXSTS_QSPCAVAIL_SHIFT) | 32768; + s->haint = 0; + s->haintmsk = 0; + s->hprt0 = 0; + + memset(s->hreg1, 0, sizeof(s->hreg1)); + memset(s->pcgreg, 0, sizeof(s->pcgreg)); + + s->sof_time = 0; + s->frame_number = 0; + s->fi = USB_FRMINTVL - 1; + s->next_chan = 0; + s->working = false; + + for (i = 0; i < DWC2_NB_CHAN; i++) { + s->packet[i].needs_service = false; + } +} + +static void dwc2_reset_hold(Object *obj) +{ + DWC2Class *c = DWC2_GET_CLASS(obj); + DWC2State *s = DWC2_USB(obj); + + trace_usb_dwc2_reset_hold(); + + if (c->parent_phases.hold) { + c->parent_phases.hold(obj); + } + + dwc2_update_irq(s); +} + +static void dwc2_reset_exit(Object *obj) +{ + DWC2Class *c = DWC2_GET_CLASS(obj); + DWC2State *s = DWC2_USB(obj); + + trace_usb_dwc2_reset_exit(); + + if (c->parent_phases.exit) { + c->parent_phases.exit(obj); + } + + s->hprt0 = HPRT0_PWR; + if (s->uport.dev && s->uport.dev->attached) { + usb_attach(&s->uport); + usb_device_reset(s->uport.dev); + } +} + +static void dwc2_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + DWC2State *s = DWC2_USB(dev); + Object *obj; + Error *err = NULL; + + obj = object_property_get_link(OBJECT(dev), "dma-mr", &err); + if (err) { + error_setg(errp, "dwc2: required dma-mr link not found: %s", + error_get_pretty(err)); + return; + } + assert(obj != NULL); + + s->dma_mr = MEMORY_REGION(obj); + address_space_init(&s->dma_as, s->dma_mr, "dwc2"); + + usb_bus_new(&s->bus, sizeof(s->bus), &dwc2_bus_ops, dev); + usb_register_port(&s->bus, &s->uport, s, 0, &dwc2_port_ops, + USB_SPEED_MASK_LOW | USB_SPEED_MASK_FULL | + (s->usb_version == 2 ? USB_SPEED_MASK_HIGH : 0)); + s->uport.dev = 0; + + s->usb_frame_time = NANOSECONDS_PER_SECOND / 1000; /* 1000000 */ + if (NANOSECONDS_PER_SECOND >= USB_HZ_FS) { + s->usb_bit_time = NANOSECONDS_PER_SECOND / USB_HZ_FS; /* 83.3 */ + } else { + s->usb_bit_time = 1; + } + + s->fi = USB_FRMINTVL - 1; + s->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, dwc2_frame_boundary, s); + s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, dwc2_work_timer, s); + s->async_bh = qemu_bh_new(dwc2_work_bh, s); + + sysbus_init_irq(sbd, &s->irq); +} + +static void dwc2_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + DWC2State *s = DWC2_USB(obj); + + memory_region_init(&s->container, obj, "dwc2", DWC2_MMIO_SIZE); + sysbus_init_mmio(sbd, &s->container); + + memory_region_init_io(&s->hsotg, obj, &dwc2_mmio_hsotg_ops, s, + "dwc2-io", 4 * KiB); + memory_region_add_subregion(&s->container, 0x0000, &s->hsotg); + + memory_region_init_io(&s->fifos, obj, &dwc2_mmio_hreg2_ops, s, + "dwc2-fifo", 64 * KiB); + memory_region_add_subregion(&s->container, 0x1000, &s->fifos); +} + +static const VMStateDescription vmstate_dwc2_state_packet = { + .name = "dwc2/packet", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(devadr, DWC2Packet), + VMSTATE_UINT32(epnum, DWC2Packet), + VMSTATE_UINT32(epdir, DWC2Packet), + VMSTATE_UINT32(mps, DWC2Packet), + VMSTATE_UINT32(pid, DWC2Packet), + VMSTATE_UINT32(index, DWC2Packet), + VMSTATE_UINT32(pcnt, DWC2Packet), + VMSTATE_UINT32(len, DWC2Packet), + VMSTATE_INT32(async, DWC2Packet), + VMSTATE_BOOL(small, DWC2Packet), + VMSTATE_BOOL(needs_service, DWC2Packet), + VMSTATE_END_OF_LIST() + }, +}; + +const VMStateDescription vmstate_dwc2_state = { + .name = "dwc2", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(glbreg, DWC2State, + DWC2_GLBREG_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(fszreg, DWC2State, + DWC2_FSZREG_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(hreg0, DWC2State, + DWC2_HREG0_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(hreg1, DWC2State, + DWC2_HREG1_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(pcgreg, DWC2State, + DWC2_PCGREG_SIZE / sizeof(uint32_t)), + + VMSTATE_TIMER_PTR(eof_timer, DWC2State), + VMSTATE_TIMER_PTR(frame_timer, DWC2State), + VMSTATE_INT64(sof_time, DWC2State), + VMSTATE_INT64(usb_frame_time, DWC2State), + VMSTATE_INT64(usb_bit_time, DWC2State), + VMSTATE_UINT32(usb_version, DWC2State), + VMSTATE_UINT16(frame_number, DWC2State), + VMSTATE_UINT16(fi, DWC2State), + VMSTATE_UINT16(next_chan, DWC2State), + VMSTATE_BOOL(working, DWC2State), + + VMSTATE_STRUCT_ARRAY(packet, DWC2State, DWC2_NB_CHAN, 1, + vmstate_dwc2_state_packet, DWC2Packet), + VMSTATE_UINT8_2DARRAY(usb_buf, DWC2State, DWC2_NB_CHAN, + DWC2_MAX_XFER_SIZE), + + VMSTATE_END_OF_LIST() + } +}; + +static Property dwc2_usb_properties[] = { + DEFINE_PROP_UINT32("usb_version", DWC2State, usb_version, 2), + DEFINE_PROP_END_OF_LIST(), +}; + +static void dwc2_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + DWC2Class *c = DWC2_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + dc->realize = dwc2_realize; + dc->vmsd = &vmstate_dwc2_state; + set_bit(DEVICE_CATEGORY_USB, dc->categories); + device_class_set_props(dc, dwc2_usb_properties); + resettable_class_set_parent_phases(rc, dwc2_reset_enter, dwc2_reset_hold, + dwc2_reset_exit, &c->parent_phases); +} + +static const TypeInfo dwc2_usb_type_info = { + .name = TYPE_DWC2_USB, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(DWC2State), + .instance_init = dwc2_init, + .class_size = sizeof(DWC2Class), + .class_init = dwc2_class_init, +}; + +static void dwc2_usb_register_types(void) +{ + type_register_static(&dwc2_usb_type_info); +} + +type_init(dwc2_usb_register_types) diff --git a/hw/usb/Kconfig b/hw/usb/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Kconfig +++ b/hw/usb/Kconfig @@ -XXX,XX +XXX,XX @@ config USB_MUSB bool select USB +config USB_DWC2 + bool + default y + select USB + config TUSB6010 bool select USB_MUSB diff --git a/hw/usb/Makefile.objs b/hw/usb/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Makefile.objs +++ b/hw/usb/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_USB_EHCI_SYSBUS) += hcd-ehci-sysbus.o common-obj-$(CONFIG_USB_XHCI) += hcd-xhci.o common-obj-$(CONFIG_USB_XHCI_NEC) += hcd-xhci-nec.o common-obj-$(CONFIG_USB_MUSB) += hcd-musb.o +common-obj-$(CONFIG_USB_DWC2) += hcd-dwc2.o common-obj-$(CONFIG_TUSB6010) += tusb6010.o common-obj-$(CONFIG_IMX) += chipidea.o diff --git a/hw/usb/trace-events b/hw/usb/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/trace-events +++ b/hw/usb/trace-events @@ -XXX,XX +XXX,XX @@ usb_xhci_xfer_error(void *xfer, uint32_t ret) "%p: ret %d" usb_xhci_unimplemented(const char *item, int nr) "%s (0x%x)" usb_xhci_enforced_limit(const char *item) "%s" +# hcd-dwc2.c +usb_dwc2_update_irq(uint32_t level) "level=%d" +usb_dwc2_raise_global_irq(uint32_t intr) "0x%08x" +usb_dwc2_lower_global_irq(uint32_t intr) "0x%08x" +usb_dwc2_raise_host_irq(uint32_t intr) "0x%04x" +usb_dwc2_lower_host_irq(uint32_t intr) "0x%04x" +usb_dwc2_sof(int64_t next) "next SOF %" PRId64 +usb_dwc2_bus_start(void) "start SOFs" +usb_dwc2_bus_stop(void) "stop SOFs" +usb_dwc2_find_device(uint8_t addr) "%d" +usb_dwc2_port_disabled(uint32_t pnum) "port %d disabled" +usb_dwc2_device_found(uint32_t pnum) "device found on port %d" +usb_dwc2_device_not_found(void) "device not found" +usb_dwc2_handle_packet(uint32_t chan, void *dev, void *pkt, uint32_t ep, const char *type, const char *dir, uint32_t mps, uint32_t len, uint32_t pcnt) "ch %d dev %p pkt %p ep %d type %s dir %s mps %d len %d pcnt %d" +usb_dwc2_memory_read(uint32_t addr, uint32_t len) "addr %d len %d" +usb_dwc2_packet_status(const char *status, uint32_t len) "status %s len %d" +usb_dwc2_packet_error(const char *status) "ERROR %s" +usb_dwc2_async_packet(void *pkt, uint32_t chan, void *dev, uint32_t ep, const char *dir, uint32_t len) "pkt %p ch %d dev %p ep %d %s len %d" +usb_dwc2_memory_write(uint32_t addr, uint32_t len) "addr %d len %d" +usb_dwc2_packet_done(const char *status, uint32_t actual, uint32_t len, uint32_t pcnt) "status %s actual %d len %d pcnt %d" +usb_dwc2_packet_next(const char *status, uint32_t len, uint32_t pcnt) "status %s len %d pcnt %d" +usb_dwc2_attach(void *port) "port %p" +usb_dwc2_attach_speed(const char *speed) "%s-speed device attached" +usb_dwc2_detach(void *port) "port %p" +usb_dwc2_child_detach(void *port, void *child) "port %p child %p" +usb_dwc2_wakeup(void *port) "port %p" +usb_dwc2_async_packet_complete(void *port, void *pkt, uint32_t chan, void *dev, uint32_t ep, const char *dir, uint32_t len) "port %p packet %p ch %d dev %p ep %d %s len %d" +usb_dwc2_work_bh(void) "" +usb_dwc2_work_bh_service(uint32_t first, uint32_t current, void *dev, uint32_t ep) "first %d servicing %d dev %p ep %d" +usb_dwc2_work_bh_next(uint32_t chan) "next %d" +usb_dwc2_enable_chan(uint32_t chan, void *dev, void *pkt, uint32_t ep) "ch %d dev %p pkt %p ep %d" +usb_dwc2_glbreg_read(uint64_t addr, const char *reg, uint32_t val) " 0x%04" PRIx64 " %s val 0x%08x" +usb_dwc2_glbreg_write(uint64_t addr, const char *reg, uint64_t val, uint32_t old, uint64_t result) "0x%04" PRIx64 " %s val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_fszreg_read(uint64_t addr, uint32_t val) " 0x%04" PRIx64 " HPTXFSIZ val 0x%08x" +usb_dwc2_fszreg_write(uint64_t addr, uint64_t val, uint32_t old, uint64_t result) "0x%04" PRIx64 " HPTXFSIZ val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg0_read(uint64_t addr, const char *reg, uint32_t val) " 0x%04" PRIx64 " %s val 0x%08x" +usb_dwc2_hreg0_write(uint64_t addr, const char *reg, uint64_t val, uint32_t old, uint64_t result) " 0x%04" PRIx64 " %s val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg1_read(uint64_t addr, const char *reg, uint64_t chan, uint32_t val) " 0x%04" PRIx64 " %s%" PRId64 " val 0x%08x" +usb_dwc2_hreg1_write(uint64_t addr, const char *reg, uint64_t chan, uint64_t val, uint32_t old, uint64_t result) " 0x%04" PRIx64 " %s%" PRId64 " val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_pcgreg_read(uint64_t addr, const char *reg, uint32_t val) " 0x%04" PRIx64 " %s val 0x%08x" +usb_dwc2_pcgreg_write(uint64_t addr, const char *reg, uint64_t val, uint32_t old, uint64_t result) "0x%04" PRIx64 " %s val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg2_read(uint64_t addr, uint64_t fifo, uint32_t val) " 0x%04" PRIx64 " FIFO%" PRId64 " val 0x%08x" +usb_dwc2_hreg2_write(uint64_t addr, uint64_t fifo, uint64_t val, uint32_t old, uint64_t result) " 0x%04" PRIx64 " FIFO%" PRId64 " val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg0_action(const char *s) "%s" +usb_dwc2_wakeup_endpoint(void *ep, uint32_t stream) "endp %p stream %d" +usb_dwc2_work_timer(void) "" +usb_dwc2_reset_enter(void) "=== RESET enter ===" +usb_dwc2_reset_hold(void) "=== RESET hold ===" +usb_dwc2_reset_exit(void) "=== RESET exit ===" + # desc.c usb_desc_device(int addr, int len, int ret) "dev %d query device, len %d, ret %d" usb_desc_device_qualifier(int addr, int len, int ret) "dev %d query device qualifier, len %d, ret %d" -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> The dwc-hsotg (dwc2) USB host depends on a short packet to indicate the end of an IN transfer. The usb-storage driver currently doesn't provide this, so fix it. I have tested this change rather extensively using a PC emulation with xhci, ehci, and uhci controllers, and have not observed any regressions. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-6-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/dev-storage.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/hw/usb/dev-storage.c b/hw/usb/dev-storage.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/dev-storage.c +++ b/hw/usb/dev-storage.c @@ -XXX,XX +XXX,XX @@ static void usb_msd_copy_data(MSDState *s, USBPacket *p) usb_packet_copy(p, scsi_req_get_buf(s->req) + s->scsi_off, len); s->scsi_len -= len; s->scsi_off += len; + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; if (s->scsi_len == 0 || s->data_len == 0) { scsi_req_continue(s->req); @@ -XXX,XX +XXX,XX @@ static void usb_msd_command_complete(SCSIRequest *req, uint32_t status, size_t r if (s->data_len) { int len = (p->iov.size - p->actual_length); usb_packet_skip(p, len); + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; } if (s->data_len == 0) { @@ -XXX,XX +XXX,XX @@ static void usb_msd_handle_data(USBDevice *dev, USBPacket *p) int len = p->iov.size - p->actual_length; if (len) { usb_packet_skip(p, len); + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; if (s->data_len == 0) { s->mode = USB_MSDM_CSW; @@ -XXX,XX +XXX,XX @@ static void usb_msd_handle_data(USBDevice *dev, USBPacket *p) int len = p->iov.size - p->actual_length; if (len) { usb_packet_skip(p, len); + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; if (s->data_len == 0) { s->mode = USB_MSDM_CSW; } } } - if (p->actual_length < p->iov.size) { + if (p->actual_length < p->iov.size && (p->short_not_ok || + s->scsi_len >= p->ep->max_packet_size)) { DPRINTF("Deferring packet %p [wait data-in]\n", p); s->packet = p; p->status = USB_RET_ASYNC; -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Wire the dwc-hsotg (dwc2) emulation into Qemu Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Reviewed-by: Philippe Mathieu-Daude <f4bug@amsat.org> Message-id: 20200520235349.21215-7-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 3 ++- hw/arm/bcm2835_peripherals.c | 21 ++++++++++++++++++++- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" #include "hw/timer/bcm2835_systmr.h" +#include "hw/usb/hcd-dwc2.h" #include "hw/misc/unimp.h" #define TYPE_BCM2835_PERIPHERALS "bcm2835-peripherals" @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { UnimplementedDeviceState ave0; UnimplementedDeviceState bscsl; UnimplementedDeviceState smi; - UnimplementedDeviceState dwc2; + DWC2State dwc2; UnimplementedDeviceState sdramc; } BCM2835PeripheralState; diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) /* Mphi */ sysbus_init_child_obj(obj, "mphi", &s->mphi, sizeof(s->mphi), TYPE_BCM2835_MPHI); + + /* DWC2 */ + sysbus_init_child_obj(obj, "dwc2", &s->dwc2, sizeof(s->dwc2), + TYPE_DWC2_USB); + + object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", + OBJECT(&s->gpu_bus_mr)); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, INTERRUPT_HOSTPORT)); + /* DWC2 */ + object_property_set_bool(OBJECT(&s->dwc2), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + memory_region_add_subregion(&s->peri_mr, USB_OTG_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->dwc2), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->dwc2), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, + INTERRUPT_USB)); + create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); create_unimp(s, &s->cprman, "bcm2835-cprman", CPRMAN_OFFSET, 0x1000); create_unimp(s, &s->a2w, "bcm2835-a2w", A2W_OFFSET, 0x1000); @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) create_unimp(s, &s->otp, "bcm2835-otp", OTP_OFFSET, 0x80); create_unimp(s, &s->dbus, "bcm2835-dbus", DBUS_OFFSET, 0x8000); create_unimp(s, &s->ave0, "bcm2835-ave0", AVE0_OFFSET, 0x8000); - create_unimp(s, &s->dwc2, "dwc-usb2", USB_OTG_OFFSET, 0x1000); create_unimp(s, &s->sdramc, "bcm2835-sdramc", SDRAMC_OFFSET, 0x100); } -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add a check for functional dwc-hsotg (dwc2) USB host emulation to the Raspi 2 acceptance test Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Reviewed-by: Philippe Mathieu-Daude <f4bug@amsat.org> Message-id: 20200520235349.21215-8-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(LinuxKernelTest): self.vm.set_console() kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + - serial_kernel_cmdline[uart_id]) + serial_kernel_cmdline[uart_id] + + ' root=/dev/mmcblk0p2 rootwait ' + + 'dwc_otg.fiq_fsm_enable=0') self.vm.add_args('-kernel', kernel_path, '-dtb', dtb_path, - '-append', kernel_command_line) + '-append', kernel_command_line, + '-device', 'usb-kbd') self.vm.launch() console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) + console_pattern = 'Product: QEMU USB Keyboard' + self.wait_for_console_pattern(console_pattern) def test_arm_raspi2_uart0(self): """ -- 2.20.1 Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-2-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 25 ++++++++++++++++++++++ target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 18 +++++++--------- 3 files changed, 71 insertions(+), 10 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VRECPS_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 1 .... @3same_fp VRSQRTS_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 1 .... @3same_fp VMAXNM_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 1 .... @3same_fp VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp + +###################################################################### +# 2-reg-and-shift grouping: +# 1111 001 U 1 D immH:3 immL:3 Vd:4 opc:4 L Q M 1 Vm:4 +###################################################################### +&2reg_shift vm vd q shift size + +@2reg_shl_d .... ... . . . shift:6 .... .... 1 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=3 +@2reg_shl_s .... ... . . . 1 shift:5 .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 +@2reg_shl_h .... ... . . . 01 shift:4 .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 +@2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 + +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b + +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) DO_3S_FP_PAIR(VPADD, gen_helper_vfp_adds) DO_3S_FP_PAIR(VPMAX, gen_helper_vfp_maxs) DO_3S_FP_PAIR(VPMIN, gen_helper_vfp_mins) + +static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) +{ + /* Handle a 2-reg-shift insn which can be vectorized. */ + int vec_size = a->q ? 16 : 8; + int rd_ofs = neon_reg_offset(a->vd, 0); + int rm_ofs = neon_reg_offset(a->vm, 0); + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fn(a->size, rd_ofs, rm_ofs, a->shift, vec_size, vec_size); + return true; +} + +#define DO_2SH(INSN, FUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_vector_2sh(s, a, FUNC); \ + } \ + +DO_2SH(VSHL, tcg_gen_gvec_shli) +DO_2SH(VSLI, gen_gvec_sli) 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) if ((insn & 0x00380080) != 0) { /* Two registers and shift. */ op = (insn >> 8) & 0xf; + + switch (op) { + case 5: /* VSHL, VSLI */ + return 1; /* handled by decodetree */ + default: + break; + } + if (insn & (1 << 7)) { /* 64-bit shift. */ if (op > 7) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) gen_gvec_sri(size, rd_ofs, rm_ofs, shift, vec_size, vec_size); return 0; - - case 5: /* VSHL, VSLI */ - if (u) { /* VSLI */ - gen_gvec_sli(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { /* VSHL */ - tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; } if (size == 3) { -- 2.20.1 Convert the VSHR 2-reg-shift insns to decodetree. Note that unlike the legacy decoder, we present the right shift amount to the trans_ function as a positive integer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-3-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 25 ++++++++++++++++++++ target/arm/translate-neon.inc.c | 41 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 21 +---------------- 3 files changed, 67 insertions(+), 20 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp ###################################################################### &2reg_shift vm vd q shift size +# Right shifts are encoded as N - shift, where N is the element size in bits. +%neon_rshift_i6 16:6 !function=rsub_64 +%neon_rshift_i5 16:5 !function=rsub_32 +%neon_rshift_i4 16:4 !function=rsub_16 +%neon_rshift_i3 16:3 !function=rsub_8 + +@2reg_shr_d .... ... . . . ...... .... .... 1 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=3 shift=%neon_rshift_i6 +@2reg_shr_s .... ... . . . 1 ..... .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 shift=%neon_rshift_i5 +@2reg_shr_h .... ... . . . 01 .... .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 +@2reg_shr_b .... ... . . . 001 ... .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i3 + @2reg_shl_d .... ... . . . shift:6 .... .... 1 q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=3 @2reg_shl_s .... ... . . . 1 shift:5 .... .... 0 q:1 . . .... \ @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b + +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b + VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static inline int plus1(DisasContext *s, int x) return x + 1; } +static inline int rsub_64(DisasContext *s, int x) +{ + return 64 - x; +} + +static inline int rsub_32(DisasContext *s, int x) +{ + return 32 - x; +} +static inline int rsub_16(DisasContext *s, int x) +{ + return 16 - x; +} +static inline int rsub_8(DisasContext *s, int x) +{ + return 8 - x; +} + /* Include the generated Neon decoder */ #include "decode-neon-dp.inc.c" #include "decode-neon-ls.inc.c" @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) DO_2SH(VSHL, tcg_gen_gvec_shli) DO_2SH(VSLI, gen_gvec_sli) + +static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a) +{ + /* Signed shift out of range results in all-sign-bits */ + a->shift = MIN(a->shift, (8 << a->size) - 1); + return do_vector_2sh(s, a, tcg_gen_gvec_sari); +} + +static void gen_zero_rd_2sh(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_dup_imm(vece, rd_ofs, oprsz, maxsz, 0); +} + +static bool trans_VSHR_U_2sh(DisasContext *s, arg_2reg_shift *a) +{ + /* Shift out of range is architecturally valid and results in zero. */ + if (a->shift >= (8 << a->size)) { + return do_vector_2sh(s, a, gen_zero_rd_2sh); + } else { + return do_vector_2sh(s, a, tcg_gen_gvec_shri); + } +} 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) op = (insn >> 8) & 0xf; switch (op) { + case 0: /* VSHR */ case 5: /* VSHL, VSLI */ return 1; /* handled by decodetree */ default: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } switch (op) { - case 0: /* VSHR */ - /* Right shift comes here negative. */ - shift = -shift; - /* Shifts larger than the element size are architecturally - * valid. Unsigned results in all zeros; signed results - * in all sign bits. - */ - if (!u) { - tcg_gen_gvec_sari(size, rd_ofs, rm_ofs, - MIN(shift, (8 << size) - 1), - vec_size, vec_size); - } else if (shift >= 8 << size) { - tcg_gen_gvec_dup_imm(MO_8, rd_ofs, vec_size, - vec_size, 0); - } else { - tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - case 1: /* VSRA */ /* Right shift comes here negative. */ shift = -shift; -- 2.20.1 Convert the VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree. (These are the last instructions in the group that are vectorized; the rest all require looping over each element.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-4-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 35 ++++++++++++++++++++++ target/arm/translate-neon.inc.c | 7 +++++ target/arm/translate.c | 52 +++------------------------------ 3 files changed, 46 insertions(+), 48 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_d +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_s +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_h +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_b + +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_d +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_s +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_h +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_b + +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_d +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_s +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_h +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_b + +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_d +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_s +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_h +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_b + +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_d +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_s +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_h +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_b + +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_d +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_s +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_h +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_b + +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_d +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_s +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_h +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_b + VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) DO_2SH(VSHL, tcg_gen_gvec_shli) DO_2SH(VSLI, gen_gvec_sli) +DO_2SH(VSRI, gen_gvec_sri) +DO_2SH(VSRA_S, gen_gvec_ssra) +DO_2SH(VSRA_U, gen_gvec_usra) +DO_2SH(VRSHR_S, gen_gvec_srshr) +DO_2SH(VRSHR_U, gen_gvec_urshr) +DO_2SH(VRSRA_S, gen_gvec_srsra) +DO_2SH(VRSRA_U, gen_gvec_ursra) static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a) { 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) switch (op) { case 0: /* VSHR */ + case 1: /* VSRA */ + case 2: /* VRSHR */ + case 3: /* VRSRA */ + case 4: /* VSRI */ case 5: /* VSHL, VSLI */ return 1; /* handled by decodetree */ default: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) shift = shift - (1 << (size + 3)); } - switch (op) { - case 1: /* VSRA */ - /* Right shift comes here negative. */ - shift = -shift; - if (u) { - gen_gvec_usra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { - gen_gvec_ssra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - - case 2: /* VRSHR */ - /* Right shift comes here negative. */ - shift = -shift; - if (u) { - gen_gvec_urshr(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { - gen_gvec_srshr(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - - case 3: /* VRSRA */ - /* Right shift comes here negative. */ - shift = -shift; - if (u) { - gen_gvec_ursra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { - gen_gvec_srsra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - - case 4: /* VSRI */ - if (!u) { - return 1; - } - /* Right shift comes here negative. */ - shift = -shift; - gen_gvec_sri(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - return 0; - } - if (size == 3) { count = q + 1; } else { -- 2.20.1 Convert the VQSHLU and QVSHL 2-reg-shift insns to decodetree. These are the last of the simple shift-by-immediate insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-5-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 15 +++++ target/arm/translate-neon.inc.c | 108 +++++++++++++++++++++++++++++++ target/arm/translate.c | 110 +------------------------------- 3 files changed, 126 insertions(+), 107 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b + +VQSHLU_64_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d +VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_s +VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_h +VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_b + +VQSHL_S_64_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d +VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s +VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h +VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b + +VQSHL_U_64_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d +VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s +VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h +VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSHR_U_2sh(DisasContext *s, arg_2reg_shift *a) return do_vector_2sh(s, a, tcg_gen_gvec_shri); } } + +static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, + NeonGenTwo64OpEnvFn *fn) +{ + /* + * 2-reg-and-shift operations, size == 3 case, where the + * function needs to be passed cpu_env. + */ + TCGv_i64 constimm; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * To avoid excessive duplication of ops we implement shift + * by immediate using the variable shift operations. + */ + constimm = tcg_const_i64(dup_const(a->size, a->shift)); + + for (pass = 0; pass < a->q + 1; pass++) { + TCGv_i64 tmp = tcg_temp_new_i64(); + + neon_load_reg64(tmp, a->vm + pass); + fn(tmp, cpu_env, tmp, constimm); + neon_store_reg64(tmp, a->vd + pass); + } + tcg_temp_free_i64(constimm); + return true; +} + +static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, + NeonGenTwoOpEnvFn *fn) +{ + /* + * 2-reg-and-shift operations, size < 3 case, where the + * helper needs to be passed cpu_env. + */ + TCGv_i32 constimm; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * To avoid excessive duplication of ops we implement shift + * by immediate using the variable shift operations. + */ + constimm = tcg_const_i32(dup_const(a->size, a->shift)); + + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + fn(tmp, cpu_env, tmp, constimm); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_i32(constimm); + return true; +} + +#define DO_2SHIFT_ENV(INSN, FUNC) \ + static bool trans_##INSN##_64_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_2shift_env_64(s, a, gen_helper_neon_##FUNC##64); \ + } \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + static NeonGenTwoOpEnvFn * const fns[] = { \ + gen_helper_neon_##FUNC##8, \ + gen_helper_neon_##FUNC##16, \ + gen_helper_neon_##FUNC##32, \ + }; \ + assert(a->size < ARRAY_SIZE(fns)); \ + return do_2shift_env_32(s, a, fns[a->size]); \ + } + +DO_2SHIFT_ENV(VQSHLU, qshlu_s) +DO_2SHIFT_ENV(VQSHL_U, qshl_u) +DO_2SHIFT_ENV(VQSHL_S, qshl_s) 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 inline void gen_neon_rsb(int size, TCGv_i32 t0, TCGv_i32 t1) } } -#define GEN_NEON_INTEGER_OP_ENV(name) do { \ - switch ((size << 1) | u) { \ - case 0: \ - gen_helper_neon_##name##_s8(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 1: \ - gen_helper_neon_##name##_u8(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 2: \ - gen_helper_neon_##name##_s16(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 3: \ - gen_helper_neon_##name##_u16(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 4: \ - gen_helper_neon_##name##_s32(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 5: \ - gen_helper_neon_##name##_u32(tmp, cpu_env, tmp, tmp2); \ - break; \ - default: return 1; \ - }} while (0) - static TCGv_i32 neon_load_scratch(int scratch) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int size; int shift; int pass; - int count; int u; int vec_size; uint32_t imm; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 3: /* VRSRA */ case 4: /* VSRI */ case 5: /* VSHL, VSLI */ + case 6: /* VQSHLU */ + case 7: /* VQSHL */ return 1; /* handled by decodetree */ default: break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op < 8) { - /* Shift by immediate: - VSHR, VSRA, VRSHR, VRSRA, VSRI, VSHL, VQSHL, VQSHLU. */ - if (q && ((rd | rm) & 1)) { - return 1; - } - if (!u && (op == 4 || op == 6)) { - return 1; - } - /* Right shifts are encoded as N - shift, where N is the - element size in bits. */ - if (op <= 4) { - shift = shift - (1 << (size + 3)); - } - - if (size == 3) { - count = q + 1; - } else { - count = q ? 4: 2; - } - - /* To avoid excessive duplication of ops we implement shift - * by immediate using the variable shift operations. - */ - imm = dup_const(size, shift); - - for (pass = 0; pass < count; pass++) { - if (size == 3) { - neon_load_reg64(cpu_V0, rm + pass); - tcg_gen_movi_i64(cpu_V1, imm); - switch (op) { - case 6: /* VQSHLU */ - gen_helper_neon_qshlu_s64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - break; - case 7: /* VQSHL */ - if (u) { - gen_helper_neon_qshl_u64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } else { - gen_helper_neon_qshl_s64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } - break; - default: - g_assert_not_reached(); - } - neon_store_reg64(cpu_V0, rd + pass); - } else { /* size < 3 */ - /* Operands in T0 and T1. */ - tmp = neon_load_reg(rm, pass); - tmp2 = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp2, imm); - switch (op) { - case 6: /* VQSHLU */ - switch (size) { - case 0: - gen_helper_neon_qshlu_s8(tmp, cpu_env, - tmp, tmp2); - break; - case 1: - gen_helper_neon_qshlu_s16(tmp, cpu_env, - tmp, tmp2); - break; - case 2: - gen_helper_neon_qshlu_s32(tmp, cpu_env, - tmp, tmp2); - break; - default: - abort(); - } - break; - case 7: /* VQSHL */ - GEN_NEON_INTEGER_OP_ENV(qshl); - break; - default: - g_assert_not_reached(); - } - tcg_temp_free_i32(tmp2); - neon_store_reg(rd, pass, tmp); - } - } /* for pass */ - } else if (op < 10) { + if (op < 10) { /* Shift by immediate and narrow: VSHRN, VRSHRN, VQSHRN, VQRSHRN. */ int input_unsigned = (op == 8) ? !u : u; -- 2.20.1 Convert the Neon narrowing shifts where op==8 to decodetree: * VSHRN * VRSHRN * VQSHRUN * VQRSHRUN Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-6-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 27 ++++++ target/arm/translate-neon.inc.c | 167 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 1 + 3 files changed, 195 insertions(+) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 +# Narrowing right shifts: here the Q bit is part of the opcode decode +@2reg_shrn_d .... ... . . . 1 ..... .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=3 q=0 \ + shift=%neon_rshift_i5 +@2reg_shrn_s .... ... . . . 01 .... .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 q=0 \ + shift=%neon_rshift_i4 +@2reg_shrn_h .... ... . . . 001 ... .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 \ + shift=%neon_rshift_i3 + VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h @@ -XXX,XX +XXX,XX @@ VQSHL_U_64_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b + +VSHRN_64_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_d +VSHRN_32_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_s +VSHRN_16_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h + +VRSHRN_64_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d +VRSHRN_32_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s +VRSHRN_16_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h + +VQSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_d +VQSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_s +VQSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h + +VQRSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d +VQRSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s +VQRSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, DO_2SHIFT_ENV(VQSHLU, qshlu_s) DO_2SHIFT_ENV(VQSHL_U, qshl_u) DO_2SHIFT_ENV(VQSHL_S, qshl_s) + +static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, + NeonGenTwo64OpFn *shiftfn, + NeonGenNarrowEnvFn *narrowfn) +{ + /* 2-reg-and-shift narrowing-shift operations, size == 3 case */ + TCGv_i64 constimm, rm1, rm2; + TCGv_i32 rd; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vm & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * This is always a right shift, and the shiftfn is always a + * left-shift helper, which thus needs the negated shift count. + */ + constimm = tcg_const_i64(-a->shift); + rm1 = tcg_temp_new_i64(); + rm2 = tcg_temp_new_i64(); + + /* Load both inputs first to avoid potential overwrite if rm == rd */ + neon_load_reg64(rm1, a->vm); + neon_load_reg64(rm2, a->vm + 1); + + shiftfn(rm1, rm1, constimm); + rd = tcg_temp_new_i32(); + narrowfn(rd, cpu_env, rm1); + neon_store_reg(a->vd, 0, rd); + + shiftfn(rm2, rm2, constimm); + rd = tcg_temp_new_i32(); + narrowfn(rd, cpu_env, rm2); + neon_store_reg(a->vd, 1, rd); + + tcg_temp_free_i64(rm1); + tcg_temp_free_i64(rm2); + tcg_temp_free_i64(constimm); + + return true; +} + +static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, + NeonGenTwoOpFn *shiftfn, + NeonGenNarrowEnvFn *narrowfn) +{ + /* 2-reg-and-shift narrowing-shift operations, size < 3 case */ + TCGv_i32 constimm, rm1, rm2, rm3, rm4; + TCGv_i64 rtmp; + uint32_t imm; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vm & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * This is always a right shift, and the shiftfn is always a + * left-shift helper, which thus needs the negated shift count + * duplicated into each lane of the immediate value. + */ + if (a->size == 1) { + imm = (uint16_t)(-a->shift); + imm |= imm << 16; + } else { + /* size == 2 */ + imm = -a->shift; + } + constimm = tcg_const_i32(imm); + + /* Load all inputs first to avoid potential overwrite */ + rm1 = neon_load_reg(a->vm, 0); + rm2 = neon_load_reg(a->vm, 1); + rm3 = neon_load_reg(a->vm + 1, 0); + rm4 = neon_load_reg(a->vm + 1, 1); + rtmp = tcg_temp_new_i64(); + + shiftfn(rm1, rm1, constimm); + shiftfn(rm2, rm2, constimm); + + tcg_gen_concat_i32_i64(rtmp, rm1, rm2); + tcg_temp_free_i32(rm2); + + narrowfn(rm1, cpu_env, rtmp); + neon_store_reg(a->vd, 0, rm1); + + shiftfn(rm3, rm3, constimm); + shiftfn(rm4, rm4, constimm); + tcg_temp_free_i32(constimm); + + tcg_gen_concat_i32_i64(rtmp, rm3, rm4); + tcg_temp_free_i32(rm4); + + narrowfn(rm3, cpu_env, rtmp); + tcg_temp_free_i64(rtmp); + neon_store_reg(a->vd, 1, rm3); + return true; +} + +#define DO_2SN_64(INSN, FUNC, NARROWFUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_2shift_narrow_64(s, a, FUNC, NARROWFUNC); \ + } +#define DO_2SN_32(INSN, FUNC, NARROWFUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_2shift_narrow_32(s, a, FUNC, NARROWFUNC); \ + } + +static void gen_neon_narrow_u32(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src) +{ + tcg_gen_extrl_i64_i32(dest, src); +} + +static void gen_neon_narrow_u16(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src) +{ + gen_helper_neon_narrow_u16(dest, src); +} + +static void gen_neon_narrow_u8(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src) +{ + gen_helper_neon_narrow_u8(dest, src); +} + +DO_2SN_64(VSHRN_64, gen_ushl_i64, gen_neon_narrow_u32) +DO_2SN_32(VSHRN_32, gen_ushl_i32, gen_neon_narrow_u16) +DO_2SN_32(VSHRN_16, gen_helper_neon_shl_u16, gen_neon_narrow_u8) + +DO_2SN_64(VRSHRN_64, gen_helper_neon_rshl_u64, gen_neon_narrow_u32) +DO_2SN_32(VRSHRN_32, gen_helper_neon_rshl_u32, gen_neon_narrow_u16) +DO_2SN_32(VRSHRN_16, gen_helper_neon_rshl_u16, gen_neon_narrow_u8) + +DO_2SN_64(VQSHRUN_64, gen_sshl_i64, gen_helper_neon_unarrow_sat32) +DO_2SN_32(VQSHRUN_32, gen_sshl_i32, gen_helper_neon_unarrow_sat16) +DO_2SN_32(VQSHRUN_16, gen_helper_neon_shl_s16, gen_helper_neon_unarrow_sat8) + +DO_2SN_64(VQRSHRUN_64, gen_helper_neon_rshl_s64, gen_helper_neon_unarrow_sat32) +DO_2SN_32(VQRSHRUN_32, gen_helper_neon_rshl_s32, gen_helper_neon_unarrow_sat16) +DO_2SN_32(VQRSHRUN_16, gen_helper_neon_rshl_s16, gen_helper_neon_unarrow_sat8) 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) case 5: /* VSHL, VSLI */ case 6: /* VQSHLU */ case 7: /* VQSHL */ + case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ return 1; /* handled by decodetree */ default: break; -- 2.20.1 Convert the remaining Neon narrowing shifts to decodetree: * VQSHRN * VQRSHRN Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-7-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 20 ++++++ target/arm/translate-neon.inc.c | 15 +++++ target/arm/translate.c | 110 +------------------------------- 3 files changed, 37 insertions(+), 108 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VQSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h VQRSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d VQRSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s VQRSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h + +# VQSHRN with signed input +VQSHRN_S64_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_d +VQSHRN_S32_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_s +VQSHRN_S16_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h + +# VQRSHRN with signed input +VQRSHRN_S64_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d +VQRSHRN_S32_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s +VQRSHRN_S16_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h + +# VQSHRN with unsigned input +VQSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_d +VQSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_s +VQSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h + +# VQRSHRN with unsigned input +VQRSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d +VQRSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s +VQRSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_2SN_32(VQSHRUN_16, gen_helper_neon_shl_s16, gen_helper_neon_unarrow_sat8) DO_2SN_64(VQRSHRUN_64, gen_helper_neon_rshl_s64, gen_helper_neon_unarrow_sat32) DO_2SN_32(VQRSHRUN_32, gen_helper_neon_rshl_s32, gen_helper_neon_unarrow_sat16) DO_2SN_32(VQRSHRUN_16, gen_helper_neon_rshl_s16, gen_helper_neon_unarrow_sat8) +DO_2SN_64(VQSHRN_S64, gen_sshl_i64, gen_helper_neon_narrow_sat_s32) +DO_2SN_32(VQSHRN_S32, gen_sshl_i32, gen_helper_neon_narrow_sat_s16) +DO_2SN_32(VQSHRN_S16, gen_helper_neon_shl_s16, gen_helper_neon_narrow_sat_s8) + +DO_2SN_64(VQRSHRN_S64, gen_helper_neon_rshl_s64, gen_helper_neon_narrow_sat_s32) +DO_2SN_32(VQRSHRN_S32, gen_helper_neon_rshl_s32, gen_helper_neon_narrow_sat_s16) +DO_2SN_32(VQRSHRN_S16, gen_helper_neon_rshl_s16, gen_helper_neon_narrow_sat_s8) + +DO_2SN_64(VQSHRN_U64, gen_ushl_i64, gen_helper_neon_narrow_sat_u32) +DO_2SN_32(VQSHRN_U32, gen_ushl_i32, gen_helper_neon_narrow_sat_u16) +DO_2SN_32(VQSHRN_U16, gen_helper_neon_shl_u16, gen_helper_neon_narrow_sat_u8) + +DO_2SN_64(VQRSHRN_U64, gen_helper_neon_rshl_u64, gen_helper_neon_narrow_sat_u32) +DO_2SN_32(VQRSHRN_U32, gen_helper_neon_rshl_u32, gen_helper_neon_narrow_sat_u16) +DO_2SN_32(VQRSHRN_U16, gen_helper_neon_rshl_u16, gen_helper_neon_narrow_sat_u8) 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 inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src) } } -static inline void gen_neon_shift_narrow(int size, TCGv_i32 var, TCGv_i32 shift, - int q, int u) -{ - if (q) { - if (u) { - switch (size) { - case 1: gen_helper_neon_rshl_u16(var, var, shift); break; - case 2: gen_helper_neon_rshl_u32(var, var, shift); break; - default: abort(); - } - } else { - switch (size) { - case 1: gen_helper_neon_rshl_s16(var, var, shift); break; - case 2: gen_helper_neon_rshl_s32(var, var, shift); break; - default: abort(); - } - } - } else { - if (u) { - switch (size) { - case 1: gen_helper_neon_shl_u16(var, var, shift); break; - case 2: gen_ushl_i32(var, var, shift); break; - default: abort(); - } - } else { - switch (size) { - case 1: gen_helper_neon_shl_s16(var, var, shift); break; - case 2: gen_sshl_i32(var, var, shift); break; - default: abort(); - } - } - } -} - static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u) { if (u) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 6: /* VQSHLU */ case 7: /* VQSHL */ case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ + case 9: /* VQSHRN, VQRSHRN */ return 1; /* handled by decodetree */ default: break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op < 10) { - /* Shift by immediate and narrow: - VSHRN, VRSHRN, VQSHRN, VQRSHRN. */ - int input_unsigned = (op == 8) ? !u : u; - if (rm & 1) { - return 1; - } - shift = shift - (1 << (size + 3)); - size++; - if (size == 3) { - tmp64 = tcg_const_i64(shift); - neon_load_reg64(cpu_V0, rm); - neon_load_reg64(cpu_V1, rm + 1); - for (pass = 0; pass < 2; pass++) { - TCGv_i64 in; - if (pass == 0) { - in = cpu_V0; - } else { - in = cpu_V1; - } - if (q) { - if (input_unsigned) { - gen_helper_neon_rshl_u64(cpu_V0, in, tmp64); - } else { - gen_helper_neon_rshl_s64(cpu_V0, in, tmp64); - } - } else { - if (input_unsigned) { - gen_ushl_i64(cpu_V0, in, tmp64); - } else { - gen_sshl_i64(cpu_V0, in, tmp64); - } - } - tmp = tcg_temp_new_i32(); - gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); - neon_store_reg(rd, pass, tmp); - } /* for pass */ - tcg_temp_free_i64(tmp64); - } else { - if (size == 1) { - imm = (uint16_t)shift; - imm |= imm << 16; - } else { - /* size == 2 */ - imm = (uint32_t)shift; - } - tmp2 = tcg_const_i32(imm); - tmp4 = neon_load_reg(rm + 1, 0); - tmp5 = neon_load_reg(rm + 1, 1); - for (pass = 0; pass < 2; pass++) { - if (pass == 0) { - tmp = neon_load_reg(rm, 0); - } else { - tmp = tmp4; - } - gen_neon_shift_narrow(size, tmp, tmp2, q, - input_unsigned); - if (pass == 0) { - tmp3 = neon_load_reg(rm, 1); - } else { - tmp3 = tmp5; - } - gen_neon_shift_narrow(size, tmp3, tmp2, q, - input_unsigned); - tcg_gen_concat_i32_i64(cpu_V0, tmp, tmp3); - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(tmp3); - tmp = tcg_temp_new_i32(); - gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); - neon_store_reg(rd, pass, tmp); - } /* for pass */ - tcg_temp_free_i32(tmp2); - } - } else if (op == 10) { + if (op == 10) { /* VSHLL, VMOVL */ if (q || (rd & 1)) { return 1; -- 2.20.1 Convert the VSHLL and VMOVL insns from the 2-reg-shift group to decodetree. Since the loop always has two passes, we unroll it to avoid the awkward reassignment of one TCGv to another. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-8-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 16 +++++++ target/arm/translate-neon.inc.c | 81 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 46 +------------------ 3 files changed, 99 insertions(+), 44 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp &2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 \ shift=%neon_rshift_i3 +# Long left shifts: again Q is part of opcode decode +@2reg_shll_s .... ... . . . 1 shift:5 .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 q=0 +@2reg_shll_h .... ... . . . 01 shift:4 .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 +@2reg_shll_b .... ... . . . 001 shift:3 .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0 + VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h @@ -XXX,XX +XXX,XX @@ VQSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h VQRSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d VQRSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s VQRSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h + +VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s +VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h +VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b + +VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s +VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h +VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_2SN_32(VQSHRN_U16, gen_helper_neon_shl_u16, gen_helper_neon_narrow_sat_u8) DO_2SN_64(VQRSHRN_U64, gen_helper_neon_rshl_u64, gen_helper_neon_narrow_sat_u32) DO_2SN_32(VQRSHRN_U32, gen_helper_neon_rshl_u32, gen_helper_neon_narrow_sat_u16) DO_2SN_32(VQRSHRN_U16, gen_helper_neon_rshl_u16, gen_helper_neon_narrow_sat_u8) + +static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, + NeonGenWidenFn *widenfn, bool u) +{ + TCGv_i64 tmp; + TCGv_i32 rm0, rm1; + uint64_t widen_mask = 0; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vd & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * This is a widen-and-shift operation. The shift is always less + * than the width of the source type, so after widening the input + * vector we can simply shift the whole 64-bit widened register, + * and then clear the potential overflow bits resulting from left + * bits of the narrow input appearing as right bits of the left + * neighbour narrow input. Calculate a mask of bits to clear. + */ + if ((a->shift != 0) && (a->size < 2 || u)) { + int esize = 8 << a->size; + widen_mask = MAKE_64BIT_MASK(0, esize); + widen_mask >>= esize - a->shift; + widen_mask = dup_const(a->size + 1, widen_mask); + } + + rm0 = neon_load_reg(a->vm, 0); + rm1 = neon_load_reg(a->vm, 1); + tmp = tcg_temp_new_i64(); + + widenfn(tmp, rm0); + if (a->shift != 0) { + tcg_gen_shli_i64(tmp, tmp, a->shift); + tcg_gen_andi_i64(tmp, tmp, ~widen_mask); + } + neon_store_reg64(tmp, a->vd); + + widenfn(tmp, rm1); + if (a->shift != 0) { + tcg_gen_shli_i64(tmp, tmp, a->shift); + tcg_gen_andi_i64(tmp, tmp, ~widen_mask); + } + neon_store_reg64(tmp, a->vd + 1); + tcg_temp_free_i64(tmp); + return true; +} + +static bool trans_VSHLL_S_2sh(DisasContext *s, arg_2reg_shift *a) +{ + NeonGenWidenFn *widenfn[] = { + gen_helper_neon_widen_s8, + gen_helper_neon_widen_s16, + tcg_gen_ext_i32_i64, + }; + return do_vshll_2sh(s, a, widenfn[a->size], false); +} + +static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) +{ + NeonGenWidenFn *widenfn[] = { + gen_helper_neon_widen_u8, + gen_helper_neon_widen_u16, + tcg_gen_extu_i32_i64, + }; + return do_vshll_2sh(s, a, widenfn[a->size], true); +} 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) case 7: /* VQSHL */ case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ case 9: /* VQSHRN, VQRSHRN */ + case 10: /* VSHLL, including VMOVL */ return 1; /* handled by decodetree */ default: break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op == 10) { - /* VSHLL, VMOVL */ - if (q || (rd & 1)) { - return 1; - } - tmp = neon_load_reg(rm, 0); - tmp2 = neon_load_reg(rm, 1); - for (pass = 0; pass < 2; pass++) { - if (pass == 1) - tmp = tmp2; - - gen_neon_widen(cpu_V0, tmp, size, u); - - if (shift != 0) { - /* The shift is less than the width of the source - type, so we can just shift the whole register. */ - tcg_gen_shli_i64(cpu_V0, cpu_V0, shift); - /* Widen the result of shift: we need to clear - * the potential overflow bits resulting from - * left bits of the narrow input appearing as - * right bits of left the neighbour narrow - * input. */ - if (size < 2 || !u) { - uint64_t imm64; - if (size == 0) { - imm = (0xffu >> (8 - shift)); - imm |= imm << 16; - } else if (size == 1) { - imm = 0xffff >> (16 - shift); - } else { - /* size == 2 */ - imm = 0xffffffff >> (32 - shift); - } - if (size < 2) { - imm64 = imm | (((uint64_t)imm) << 32); - } else { - imm64 = imm; - } - tcg_gen_andi_i64(cpu_V0, cpu_V0, ~imm64); - } - } - neon_store_reg64(cpu_V0, rd + pass); - } - } else if (op >= 14) { + if (op >= 14) { /* VCVT fixed-point. */ TCGv_ptr fpst; TCGv_i32 shiftv; -- 2.20.1 Convert the VCVT fixed-point conversion operations in the Neon 2-regs-and-shift group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-9-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 11 +++++ target/arm/translate-neon.inc.c | 49 +++++++++++++++++++++ target/arm/translate.c | 75 +-------------------------------- 3 files changed, 62 insertions(+), 73 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shll_b .... ... . . . 001 shift:3 .... .... 0 . . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0 +# We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings. +@2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5 + VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h @@ -XXX,XX +XXX,XX @@ VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b + +# VCVT fixed<->float conversions +# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101 +VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt +VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt +VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt +VCVT_FU_2sh 1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) }; return do_vshll_2sh(s, a, widenfn[a->size], true); } + +static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, + NeonGenTwoSingleOPFn *fn) +{ + /* FP operations in 2-reg-and-shift group */ + TCGv_i32 tmp, shiftv; + TCGv_ptr fpstatus; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpstatus = get_fpstatus_ptr(1); + shiftv = tcg_const_i32(a->shift); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + tmp = neon_load_reg(a->vm, pass); + fn(tmp, tmp, shiftv, fpstatus); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_ptr(fpstatus); + tcg_temp_free_i32(shiftv); + return true; +} + +#define DO_FP_2SH(INSN, FUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_fp_2sh(s, a, FUNC); \ + } + +DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos) +DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos) +DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero) +DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero) 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) int q; int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs; int size; - int shift; int pass; int u; int vec_size; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } else if (insn & (1 << 4)) { if ((insn & 0x00380080) != 0) { - /* Two registers and shift. */ - op = (insn >> 8) & 0xf; - - switch (op) { - case 0: /* VSHR */ - case 1: /* VSRA */ - case 2: /* VRSHR */ - case 3: /* VRSRA */ - case 4: /* VSRI */ - case 5: /* VSHL, VSLI */ - case 6: /* VQSHLU */ - case 7: /* VQSHL */ - case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ - case 9: /* VQSHRN, VQRSHRN */ - case 10: /* VSHLL, including VMOVL */ - return 1; /* handled by decodetree */ - default: - break; - } - - if (insn & (1 << 7)) { - /* 64-bit shift. */ - if (op > 7) { - return 1; - } - size = 3; - } else { - size = 2; - while ((insn & (1 << (size + 19))) == 0) - size--; - } - shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op >= 14) { - /* VCVT fixed-point. */ - TCGv_ptr fpst; - TCGv_i32 shiftv; - VFPGenFixPointFn *fn; - - if (!(insn & (1 << 21)) || (q && ((rd | rm) & 1))) { - return 1; - } - - if (!(op & 1)) { - if (u) { - fn = gen_helper_vfp_ultos; - } else { - fn = gen_helper_vfp_sltos; - } - } else { - if (u) { - fn = gen_helper_vfp_touls_round_to_zero; - } else { - fn = gen_helper_vfp_tosls_round_to_zero; - } - } - - /* We have already masked out the must-be-1 top bit of imm6, - * hence this 32-shift where the ARM ARM has 64-imm6. - */ - shift = 32 - shift; - fpst = get_fpstatus_ptr(1); - shiftv = tcg_const_i32(shift); - for (pass = 0; pass < (q ? 4 : 2); pass++) { - TCGv_i32 tmpf = neon_load_reg(rm, pass); - fn(tmpf, tmpf, shiftv, fpst); - neon_store_reg(rd, pass, tmpf); - } - tcg_temp_free_ptr(fpst); - tcg_temp_free_i32(shiftv); - } else { - return 1; - } + /* Two registers and shift: handled by decodetree */ + return 1; } else { /* (insn & 0x00380080) == 0 */ int invert, reg_ofs, vec_size; -- 2.20.1 Convert the insns in the one-register-and-immediate group to decodetree. In the new decode, our asimd_imm_const() function returns a 64-bit value rather than a 32-bit one, which means we don't need to treat cmode=14 op=1 as a special case in the decoder (it is the only encoding where the two halves of the 64-bit value are different). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-10-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 22 ++++++ target/arm/translate-neon.inc.c | 118 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 101 +-------------------------- 3 files changed, 142 insertions(+), 99 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt VCVT_FU_2sh 1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt + +###################################################################### +# 1-reg-and-modified-immediate grouping: +# 1111 001 i 1 D 000 imm:3 Vd:4 cmode:4 0 Q op 1 Vm:4 +###################################################################### + +&1reg_imm vd q imm cmode op + +%asimd_imm_value 24:1 16:3 0:4 + +@1reg_imm .... ... . . . ... ... .... .... . q:1 . . .... \ + &1reg_imm imm=%asimd_imm_value vd=%vd_dp + +# The cmode/op bits here decode VORR/VBIC/VMOV/VMNV, but +# not in a way we can conveniently represent in decodetree without +# a lot of repetition: +# VORR: op=0, (cmode & 1) && cmode < 12 +# VBIC: op=1, (cmode & 1) && cmode < 12 +# VMOV: everything else +# So we have a single decode line and check the cmode/op in the +# trans function. +Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos) DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos) DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero) DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero) + +static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) +{ + /* + * Expand the encoded constant. + * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. + * We choose to not special-case this and will behave as if a + * valid constant encoding of 0 had been given. + * cmode = 15 op = 1 must UNDEF; we assume decode has handled that. + */ + switch (cmode) { + case 0: case 1: + /* no-op */ + break; + case 2: case 3: + imm <<= 8; + break; + case 4: case 5: + imm <<= 16; + break; + case 6: case 7: + imm <<= 24; + break; + case 8: case 9: + imm |= imm << 16; + break; + case 10: case 11: + imm = (imm << 8) | (imm << 24); + break; + case 12: + imm = (imm << 8) | 0xff; + break; + case 13: + imm = (imm << 16) | 0xffff; + break; + case 14: + if (op) { + /* + * This is the only case where the top and bottom 32 bits + * of the encoded constant differ. + */ + uint64_t imm64 = 0; + int n; + + for (n = 0; n < 8; n++) { + if (imm & (1 << n)) { + imm64 |= (0xffULL << (n * 8)); + } + } + return imm64; + } + imm |= (imm << 8) | (imm << 16) | (imm << 24); + break; + case 15: + imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) + | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); + break; + } + if (op) { + imm = ~imm; + } + return dup_const(MO_32, imm); +} + +static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, + GVecGen2iFn *fn) +{ + uint64_t imm; + int reg_ofs, vec_size; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + return false; + } + + if (a->vd & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + reg_ofs = neon_reg_offset(a->vd, 0); + vec_size = a->q ? 16 : 8; + imm = asimd_imm_const(a->imm, a->cmode, a->op); + + fn(MO_64, reg_ofs, reg_ofs, imm, vec_size, vec_size); + return true; +} + +static void gen_VMOV_1r(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, c); +} + +static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a) +{ + /* Handle decode of cmode/op here between VORR/VBIC/VMOV */ + GVecGen2iFn *fn; + + if ((a->cmode & 1) && a->cmode < 12) { + /* for op=1, the imm will be inverted, so BIC becomes AND. */ + fn = a->op ? tcg_gen_gvec_andi : tcg_gen_gvec_ori; + } else { + /* There is one unallocated cmode/op combination in this space */ + if (a->cmode == 15 && a->op == 1) { + return false; + } + fn = gen_VMOV_1r; + } + return do_1reg_imm(s, a, fn); +} 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 disas_neon_data_insn(DisasContext *s, uint32_t insn) /* Three register same length: handled by decodetree */ return 1; } else if (insn & (1 << 4)) { - if ((insn & 0x00380080) != 0) { - /* Two registers and shift: handled by decodetree */ - return 1; - } else { /* (insn & 0x00380080) == 0 */ - int invert, reg_ofs, vec_size; - - if (q && (rd & 1)) { - return 1; - } - - op = (insn >> 8) & 0xf; - /* One register and immediate. */ - imm = (u << 7) | ((insn >> 12) & 0x70) | (insn & 0xf); - invert = (insn & (1 << 5)) != 0; - /* Note that op = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. - * We choose to not special-case this and will behave as if a - * valid constant encoding of 0 had been given. - */ - switch (op) { - case 0: case 1: - /* no-op */ - break; - case 2: case 3: - imm <<= 8; - break; - case 4: case 5: - imm <<= 16; - break; - case 6: case 7: - imm <<= 24; - break; - case 8: case 9: - imm |= imm << 16; - break; - case 10: case 11: - imm = (imm << 8) | (imm << 24); - break; - case 12: - imm = (imm << 8) | 0xff; - break; - case 13: - imm = (imm << 16) | 0xffff; - break; - case 14: - imm |= (imm << 8) | (imm << 16) | (imm << 24); - if (invert) { - imm = ~imm; - } - break; - case 15: - if (invert) { - return 1; - } - imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) - | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); - break; - } - if (invert) { - imm = ~imm; - } - - reg_ofs = neon_reg_offset(rd, 0); - vec_size = q ? 16 : 8; - - if (op & 1 && op < 12) { - if (invert) { - /* The immediate value has already been inverted, - * so BIC becomes AND. - */ - tcg_gen_gvec_andi(MO_32, reg_ofs, reg_ofs, imm, - vec_size, vec_size); - } else { - tcg_gen_gvec_ori(MO_32, reg_ofs, reg_ofs, imm, - vec_size, vec_size); - } - } else { - /* VMOV, VMVN. */ - if (op == 14 && invert) { - TCGv_i64 t64 = tcg_temp_new_i64(); - - for (pass = 0; pass <= q; ++pass) { - uint64_t val = 0; - int n; - - for (n = 0; n < 8; n++) { - if (imm & (1 << (n + pass * 8))) { - val |= 0xffull << (n * 8); - } - } - tcg_gen_movi_i64(t64, val); - neon_store_reg64(t64, rd + pass); - } - tcg_temp_free_i64(t64); - } else { - tcg_gen_gvec_dup_imm(MO_32, reg_ofs, vec_size, - vec_size, imm); - } - } - } + /* Two registers and shift or reg and imm: handled by decodetree */ + return 1; } else { /* (insn & 0x00800010 == 0x00800000) */ if (size != 3) { op = (insn >> 8) & 0xf; -- 2.20.1 First set of arm patches for 6.2. I have a lot more in my to-review queue still... -- PMM The following changes since commit d42685765653ec155fdf60910662f8830bdb2cef: Open 6.2 development tree (2021-08-25 10:25:12 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210825 for you to fetch changes up to 24b1a6aa43615be22c7ee66bd68ec5675f6a6a9a: docs: Document how to use gdb with unix sockets (2021-08-25 10:48:51 +0100) ---------------------------------------------------------------- target-arm queue: * More MVE emulation work * Implement M-profile trapping on division by zero * kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() * hw/char/pl011: add support for sending break * fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices * hw/dma/pl330: Add memory region to replace default * sbsa-ref: Rename SBSA_GWDT enum value * fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices * docs: Document how to use gdb with unix sockets ---------------------------------------------------------------- Eduardo Habkost (1): sbsa-ref: Rename SBSA_GWDT enum value Guenter Roeck (2): fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices Hamza Mahfooz (1): target/arm: kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() Jan Luebbe (1): hw/char/pl011: add support for sending break Peter Maydell (37): target/arm: Note that we handle VMOVL as a special case of VSHLL target/arm: Print MVE VPR in CPU dumps target/arm: Fix MVE VSLI by 0 and VSRI by <dt> target/arm: Fix signed VADDV target/arm: Fix mask handling for MVE narrowing operations target/arm: Fix 48-bit saturating shifts target/arm: Fix MVE 48-bit SQRSHRL for small right shifts target/arm: Fix calculation of LTP mask when LR is 0 target/arm: Factor out mve_eci_mask() target/arm: Fix VPT advance when ECI is non-zero target/arm: Fix VLDRB/H/W for predicated elements target/arm: Implement MVE VMULL (polynomial) target/arm: Implement MVE incrementing/decrementing dup insns target/arm: Factor out gen_vpst() target/arm: Implement MVE integer vector comparisons target/arm: Implement MVE integer vector-vs-scalar comparisons target/arm: Implement MVE VPSEL target/arm: Implement MVE VMLAS target/arm: Implement MVE shift-by-scalar target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats target/arm: Implement MVE integer min/max across vector target/arm: Implement MVE VABAV target/arm: Implement MVE narrowing moves target/arm: Rename MVEGenDualAccOpFn to MVEGenLongDualAccOpFn target/arm: Implement MVE VMLADAV and VMLSLDAV target/arm: Implement MVE VMLA target/arm: Implement MVE saturating doubling multiply accumulates target/arm: Implement MVE VQABS, VQNEG target/arm: Implement MVE VMAXA, VMINA target/arm: Implement MVE VMOV to/from 2 general-purpose registers target/arm: Implement MVE VPNOT target/arm: Implement MVE VCTP target/arm: Implement MVE scatter-gather insns target/arm: Implement MVE scatter-gather immediate forms target/arm: Implement MVE interleaving loads/stores target/arm: Re-indent sdiv and udiv helpers target/arm: Implement M-profile trapping on division by zero Sebastian Meyer (1): docs: Document how to use gdb with unix sockets Wen, Jianxian (1): hw/dma/pl330: Add memory region to replace default docs/system/gdb.rst | 26 +- include/hw/arm/fsl-imx7.h | 5 + target/arm/cpu.h | 1 + target/arm/helper-mve.h | 283 ++++++++++ target/arm/helper.h | 4 +- target/arm/translate-a32.h | 2 + target/arm/vec_internal.h | 11 + target/arm/mve.decode | 226 +++++++- target/arm/t32.decode | 1 + hw/arm/exynos4210.c | 3 + hw/arm/fsl-imx6ul.c | 12 + hw/arm/fsl-imx7.c | 7 + hw/arm/sbsa-ref.c | 6 +- hw/arm/xilinx_zynq.c | 3 + hw/char/pl011.c | 6 + hw/dma/pl330.c | 26 +- target/arm/cpu.c | 3 + target/arm/helper.c | 34 +- target/arm/kvm.c | 17 +- target/arm/m_helper.c | 4 + target/arm/mve_helper.c | 1254 ++++++++++++++++++++++++++++++++++++++++++-- target/arm/translate-mve.c | 877 ++++++++++++++++++++++++++++++- target/arm/translate-vfp.c | 2 +- target/arm/translate.c | 37 +- target/arm/vec_helper.c | 14 +- 25 files changed, 2746 insertions(+), 118 deletions(-) Although the architecture doesn't define it as an alias, VMOVL (vector move long) is encoded as a VSHLL with a zero shift. Add a comment in the decode file noting that we handle VMOVL as part of VSHLL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w # VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file +# Note that VMOVL is encoded as "VSHLL with a zero shift count"; we +# implement it that way rather than special-casing it in the decode. VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h -- 2.20.1 Include the MVE VPR register value in the CPU dumps produced by arm_cpu_dump_state() if we are printing FPU information. This makes it easier to interpret debug logs when predication is active. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) i, v); } qemu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); + if (cpu_isar_feature(aa32_mve, cpu)) { + qemu_fprintf(f, "VPR: %08x\n", env->v7m.vpr); + } } } -- 2.20.1 In the MVE shift-and-insert insns, we special case VSLI by 0 and VSRI by <dt>. VSRI by <dt> means "don't update the destination", which is what we've implemented. However VSLI by 0 is "set destination to the input", so we don't want to use the same special-casing that we do for VSRI by <dt>. Since the generic logic gives the right answer for a shift by 0, just use that. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_S(vrshli_s, DO_VRSHLS) uint16_t mask; \ uint64_t shiftmask; \ unsigned e; \ - if (shift == 0 || shift == ESIZE * 8) { \ + if (shift == ESIZE * 8) { \ /* \ - * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ - * The generic logic would give the right answer for 0 but \ - * fails for <dt>. \ + * Only VSRI can shift by <dt>; it should mean "don't \ + * update the destination". The generic logic can't handle \ + * this because it would try to shift by an out-of-range \ + * amount, so special case it here. \ */ \ goto done; \ } \ -- 2.20.1 A cut-and-paste error meant we handled signed VADDV like unsigned VADDV; fix the type used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true) return ra; \ } \ -DO_VADDV(vaddvsb, 1, uint8_t) -DO_VADDV(vaddvsh, 2, uint16_t) -DO_VADDV(vaddvsw, 4, uint32_t) +DO_VADDV(vaddvsb, 1, int8_t) +DO_VADDV(vaddvsh, 2, int16_t) +DO_VADDV(vaddvsw, 4, int32_t) DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) -- 2.20.1 In the MVE helpers for the narrowing operations (DO_VSHRN and DO_VSHRN_SAT) we were using the wrong bits of the predicate mask for the 'top' versions of the insn. This is because the loop works over the double-sized input elements and shifts the predicate mask by that many bits each time, but when we write out the half-sized output we must look at the mask bits for whichever half of the element we are writing to. Correct this by shifting the whole mask right by ESIZE bits for the 'top' insns. This allows us also to simplify the saturation bit checking (where we had noticed that we needed to look at a different mask bit for the 'top' insn.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL_ALL(vshllt, true) TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ TYPE r = FN(m[H##LESIZE(le)], shift); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ @@ -XXX,XX +XXX,XX @@ static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, uint16_t mask = mve_element_mask(env); \ bool qc = false; \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ bool sat = false; \ TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ - qc |= sat && (mask & 1 << (TOP * ESIZE)); \ + qc |= sat & mask & 1; \ } \ if (qc) { \ env->vfp.qc[0] = qc; \ -- 2.20.1 In do_sqrshl48_d() and do_uqrshl48_d() we got some of the edge cases wrong and failed to saturate correctly: (1) In do_sqrshl48_d() we used the same code that do_shrshl_bhs() does to obtain the saturated most-negative and most-positive 48-bit signed values for the large-shift-left case. This gives (1 << 47) for saturate-to-most-negative, but we weren't sign-extending this value to the 64-bit output as the pseudocode requires. (2) For left shifts by less than 48, we copied the "8/16 bit" code from do_sqrshl_bhs() and do_uqrshl_bhs(). This doesn't do the right thing because it assumes the C type we're working with is at least twice the number of bits we're saturating to (so that a shift left by bits-1 can't shift anything off the top of the value). This isn't true for bits == 48, so we would incorrectly return 0 rather than the most-positive value for situations like "shift (1 << 44) right by 20". Instead check for saturation by doing the shift and signextend and then testing whether shifting back left again gives the original value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } return src >> -shift; } else if (shift < 48) { - int64_t val = src << shift; - int64_t extval = sextract64(val, 0, 48); - if (!sat || val == extval) { + int64_t extval = sextract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } *sat = 1; - return (1ULL << 47) - (src >= 0); + return src >= 0 ? MAKE_64BIT_MASK(0, 47) : MAKE_64BIT_MASK(47, 17); } /* Operate on 64-bit values, but saturate at 48 bits */ @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, return extval; } } else if (shift < 48) { - uint64_t val = src << shift; - uint64_t extval = extract64(val, 0, 48); - if (!sat || val == extval) { + uint64_t extval = extract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { -- 2.20.1 We got an edge case wrong in the 48-bit SQRSHRL implementation: if the shift is to the right, although it always makes the result smaller than the input value it might not be within the 48-bit range the result is supposed to be if the input had some bits in [63..48] set and the shift didn't bring all of those within the [47..0] range. Handle this similarly to the way we already do for this case in do_uqrshl48_d(): extend the calculated result from 48 bits, and return that if not saturating or if it doesn't change the result; otherwise fall through to return a saturated value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, bool round, uint32_t *sat) { + int64_t val, extval; + if (shift <= -48) { /* Rounding the sign bit always produces 0. */ if (round) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } else if (shift < 0) { if (round) { src >>= -shift - 1; - return (src >> 1) + (src & 1); + val = (src >> 1) + (src & 1); + } else { + val = src >> -shift; + } + extval = sextract64(val, 0, 48); + if (!sat || val == extval) { + return extval; } - return src >> -shift; } else if (shift < 48) { int64_t extval = sextract64(src << shift, 0, 48); if (!sat || src == (extval >> shift)) { -- 2.20.1 In mve_element_mask(), we calculate a mask for tail predication which should have a number of 1 bits based on the value of LR. However, our MAKE_64BIT_MASK() macro has undefined behaviour when passed a zero length. Special case this to give the all-zeroes mask we require. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) */ int masklen = env->regs[14] << env->v7m.ltpsize; assert(masklen <= 16); - mask &= MAKE_64BIT_MASK(0, masklen); + uint16_t ltpmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + mask &= ltpmask; } if ((env->condexec_bits & 0xf) == 0) { -- 2.20.1 In some situations we need a mask telling us which parts of the vector correspond to beats that are not being executed because of ECI, separately from the combined "which bytes are predicated away" mask. Factor this mask calculation out of mve_element_mask() into its own function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 58 ++++++++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "tcg/tcg.h" +static uint16_t mve_eci_mask(CPUARMState *env) +{ + /* + * Return the mask of which elements in the MVE vector correspond + * to beats being executed. The mask has 1 bits for executed lanes + * and 0 bits where ECI says this beat was already executed. + */ + int eci; + + if ((env->condexec_bits & 0xf) != 0) { + return 0xffff; + } + + eci = env->condexec_bits >> 4; + switch (eci) { + case ECI_NONE: + return 0xffff; + case ECI_A0: + return 0xfff0; + case ECI_A0A1: + return 0xff00; + case ECI_A0A1A2: + case ECI_A0A1A2B0: + return 0xf000; + default: + g_assert_not_reached(); + } +} + static uint16_t mve_element_mask(CPUARMState *env) { /* @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) mask &= ltpmask; } - if ((env->condexec_bits & 0xf) == 0) { - /* - * ECI bits indicate which beats are already executed; - * we handle this by effectively predicating them out. - */ - int eci = env->condexec_bits >> 4; - switch (eci) { - case ECI_NONE: - break; - case ECI_A0: - mask &= 0xfff0; - break; - case ECI_A0A1: - mask &= 0xff00; - break; - case ECI_A0A1A2: - case ECI_A0A1A2B0: - mask &= 0xf000; - break; - default: - g_assert_not_reached(); - } - } - + /* + * ECI bits indicate which beats are already executed; + * we handle this by effectively predicating them out. + */ + mask &= mve_eci_mask(env); return mask; } -- 2.20.1 We were not paying attention to the ECI state when advancing the VPT state. Architecturally, VPT state advance happens for every beat (see the pseudocode VPTAdvance()), so on every beat the 4 bits of VPR.P0 corresponding to the current beat are inverted if required, and at the end of beats 1 and 3 the VPR MASK fields are updated. This means that if the ECI state says we should not be executing all 4 beats then we need to skip some of the updating of the VPR that we currently do in mve_advance_vpt(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) /* Advance the VPT and ECI state if necessary */ uint32_t vpr = env->v7m.vpr; unsigned mask01, mask23; + uint16_t inv_mask; + uint16_t eci_mask = mve_eci_mask(env); if ((env->condexec_bits & 0xf) == 0) { env->condexec_bits = (env->condexec_bits == (ECI_A0A1A2B0 << 4)) ? @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) return; } + /* Invert P0 bits if needed, but only for beats we actually executed */ mask01 = FIELD_EX32(vpr, V7M_VPR, MASK01); mask23 = FIELD_EX32(vpr, V7M_VPR, MASK23); - if (mask01 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff; + /* Start by assuming we invert all bits corresponding to executed beats */ + inv_mask = eci_mask; + if (mask01 <= 8) { + /* MASK01 says don't invert low half of P0 */ + inv_mask &= ~0xff; } - if (mask23 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff00; + if (mask23 <= 8) { + /* MASK23 says don't invert high half of P0 */ + inv_mask &= ~0xff00; } - vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + vpr ^= inv_mask; + /* Only update MASK01 if beat 1 executed */ + if (eci_mask & 0xf0) { + vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + } + /* Beat 3 always executes, so update MASK23 */ vpr = FIELD_DP32(vpr, V7M_VPR, MASK23, mask23 << 1); env->v7m.vpr = vpr; } -- 2.20.1 For vector loads, predicated elements are zeroed, instead of retaining their previous values (as happens for most data processing operations). This means we need to distinguish "beat not executed due to ECI" (don't touch destination element) from "beat executed but predicated out" (zero destination element). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) env->v7m.vpr = vpr; } - +/* For loads, predicated lanes are zeroed instead of keeping their old values */ #define DO_VLDR(OP, MSIZE, LDTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) * then take an exception. \ */ \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ - if (mask & (1 << b)) { \ - d[H##ESIZE(e)] = cpu_##LDTYPE##_data_ra(env, addr, GETPC()); \ + if (eci_mask & (1 << b)) { \ + d[H##ESIZE(e)] = (mask & (1 << b)) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ } \ addr += MSIZE; \ } \ -- 2.20.1 Implement the MVE VMULL (polynomial) insn. Unlike Neon, this comes in two flavours: 8x8->16 and a 16x16->32. Also unlike Neon, the inputs are in either the low or the high half of each double-width element. The assembler for this insn indicates the size with "P8" or "P16", encoded into bit 28 as size = 0 or 1. We choose to follow the same encoding as VQDMULL and decode this into a->size as MO_16 or MO_32 indicating the size of the result elements. This then carries through to the helper function names where it then matches up with the existing pmull_h() which does an 8x8->16 operation and a new pmull_w() which does the 16x16->32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++++ target/arm/vec_internal.h | 11 +++++++++++ target/arm/mve.decode | 14 ++++++++++---- target/arm/mve_helper.c | 16 ++++++++++++++++ target/arm/translate-mve.c | 28 ++++++++++++++++++++++++++++ target/arm/vec_helper.c | 14 +++++++++++++- 6 files changed, 83 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmulltub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpth, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullptw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vqdmulhb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_internal.h +++ b/target/arm/vec_internal.h @@ -XXX,XX +XXX,XX @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); +/* + * 8 x 8 -> 16 vector polynomial multiply where the inputs are + * in the low 8 bits of each 16-bit element +*/ +uint64_t pmull_h(uint64_t op1, uint64_t op2); +/* + * 16 x 16 -> 32 vector polynomial multiply where the inputs are + * in the low 16 bits of each 32-bit element + */ +uint64_t pmull_w(uint64_t op1, uint64_t op2); + #endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VHADD_U 111 1 1111 0 . .. ... 0 ... 0 0000 . 1 . 0 ... 0 @2op VHSUB_S 111 0 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op VHSUB_U 111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op -VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op -VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +{ + VMULLP_B 111 . 1110 0 . 11 ... 1 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op + VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op +} +{ + VMULLP_T 111 . 1110 0 . 11 ... 1 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op + VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +} VQDMULH 1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op VQRDMULH 1111 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_L(vmulltub, 1, 1, uint8_t, 2, uint16_t, DO_MUL) DO_2OP_L(vmulltuh, 1, 2, uint16_t, 4, uint32_t, DO_MUL) DO_2OP_L(vmulltuw, 1, 4, uint32_t, 8, uint64_t, DO_MUL) +/* + * Polynomial multiply. We can always do this generating 64 bits + * of the result at a time, so we don't need to use DO_2OP_L. + */ +#define VMULLPH_MASK 0x00ff00ff00ff00ffULL +#define VMULLPW_MASK 0x0000ffff0000ffffULL +#define DO_VMULLPBH(N, M) pmull_h((N) & VMULLPH_MASK, (M) & VMULLPH_MASK) +#define DO_VMULLPTH(N, M) DO_VMULLPBH((N) >> 8, (M) >> 8) +#define DO_VMULLPBW(N, M) pmull_w((N) & VMULLPW_MASK, (M) & VMULLPW_MASK) +#define DO_VMULLPTW(N, M) DO_VMULLPBW((N) >> 16, (M) >> 16) + +DO_2OP(vmullpbh, 8, uint64_t, DO_VMULLPBH) +DO_2OP(vmullpth, 8, uint64_t, DO_VMULLPTH) +DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW) +DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW) + /* * Because the computation type is at least twice as large as required, * these work for both signed and unsigned source types. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT(DisasContext *s, arg_2op *a) return do_2op(s, a, fns[a->size]); } +static bool trans_VMULLP_B(DisasContext *s, arg_2op *a) +{ + /* + * Note that a->size indicates the output size, ie VMULL.P8 + * is the 8x8->16 operation and a->size is MO_16; VMULL.P16 + * is the 16x16->32 operation and a->size is MO_32. + */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpbh, + gen_helper_mve_vmullpbw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + +static bool trans_VMULLP_T(DisasContext *s, arg_2op *a) +{ + /* a->size is as for trans_VMULLP_B */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpth, + gen_helper_mve_vmullptw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + /* * VADC and VSBC: these perform an add-with-carry or subtract-with-carry * of the 32-bit elements in each lane of the input vectors, where the diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t expand_byte_to_half(uint64_t x) | ((x & 0xff000000) << 24); } -static uint64_t pmull_h(uint64_t op1, uint64_t op2) +uint64_t pmull_w(uint64_t op1, uint64_t op2) { uint64_t result = 0; int i; + for (i = 0; i < 16; ++i) { + uint64_t mask = (op1 & 0x0000000100000001ull) * 0xffffffff; + result ^= op2 & mask; + op1 >>= 1; + op2 <<= 1; + } + return result; +} +uint64_t pmull_h(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; for (i = 0; i < 8; ++i) { uint64_t mask = (op1 & 0x0001000100010001ull) * 0xffff; result ^= op2 & mask; -- 2.20.1 Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 12 ++++ target/arm/mve.decode | 25 ++++++++ target/arm/mve_helper.c | 63 +++++++++++++++++++ target/arm/translate-mve.c | 120 +++++++++++++++++++++++++++++++++++++ 4 files changed, 220 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_viduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_vidupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) + +DEF_HELPER_FLAGS_5(mve_viwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + +DEF_HELPER_FLAGS_5(mve_vdwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + DEF_HELPER_FLAGS_3(mve_vclsb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsw, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2scalar qd qn rm size &1imm qd imm cmode op &2shift qd qm shift size +&vidup qd rn size imm +&viwdup qd rn rm size imm @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 1 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=0 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 1 1 0000 @vdup size=1 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 +# Incrementing and decrementing dup + +# VIDUP, VDDUP format immediate: 1 << (immh:imml) +%imm_vidup 7:1 0:1 !function=vidup_imm + +# VIDUP, VDDUP registers: Rm bits [3:1] from insn, bit 0 is 1; +# Rn bits [3:1] from insn, bit 0 is 0 +%vidup_rm 1:3 !function=times_2_plus_1 +%vidup_rn 17:3 !function=times_2 + +@vidup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rn=%vidup_rn &vidup +@viwdup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rm=%vidup_rm rn=%vidup_rn &viwdup +{ + VIDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 111 . @vidup + VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup +} +{ + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup +} + # multiply-add long dual accumulate # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) { return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); } + +#define DO_VIDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIWDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t wrap, \ + uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, wrap, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIDUP_ALL(OP, FN) \ + DO_VIDUP(OP##b, 1, int8_t, FN) \ + DO_VIDUP(OP##h, 2, int16_t, FN) \ + DO_VIDUP(OP##w, 4, int32_t, FN) + +#define DO_VIWDUP_ALL(OP, FN) \ + DO_VIWDUP(OP##b, 1, int8_t, FN) \ + DO_VIWDUP(OP##h, 2, int16_t, FN) \ + DO_VIWDUP(OP##w, 4, int32_t, FN) + +static uint32_t do_add_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + offset += imm; + if (offset == wrap) { + offset = 0; + } + return offset; +} + +static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + if (offset == 0) { + offset = wrap; + } + offset -= imm; + return offset; +} + +DO_VIDUP_ALL(vidup, DO_ADD) +DO_VIWDUP_ALL(viwdup, do_add_wrap) +DO_VIWDUP_ALL(vdwdup, do_sub_wrap) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "translate-a32.h" +static inline int vidup_imm(DisasContext *s, int x) +{ + return 1 << x; +} + /* Include the generated decoder */ #include "decode-mve.c.inc" @@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) mve_update_eci(s); return true; } + +static bool do_vidup(DisasContext *s, arg_vidup *a, MVEGenVIDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn; + + /* + * Vector increment/decrement with wrap and duplicate (VIDUP, VDDUP). + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (a->size == MO_64) { + /* size 0b11 is another encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + fn(rn, cpu_env, qd, rn, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} + +static bool do_viwdup(DisasContext *s, arg_viwdup *a, MVEGenVIWDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn, rm; + + /* + * Vector increment/decrement with wrap and duplicate (VIWDUp, VDWDUP) + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. Rm specifies a point where + * the count wraps back around to 0. The updated offset is written back + * to Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (!fn || a->rm == 13 || a->rm == 15) { + /* + * size 0b11 is another encoding; Rm == 13 is UNPREDICTABLE; + * Rm == 13 is VIWDUP, VDWDUP. + */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + rm = load_reg(s, a->rm); + fn(rn, cpu_env, qd, rn, rm, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +static bool trans_VIDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VDDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + /* VDDUP is just like VIDUP but with a negative immediate */ + a->imm = -a->imm; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VIWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_viwdupb, + gen_helper_mve_viwduph, + gen_helper_mve_viwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} + +static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_vdwdupb, + gen_helper_mve_vdwduph, + gen_helper_mve_vdwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} -- 2.20.1 Factor out the "generate code to update VPR.MASK01/MASK23" part of trans_VPST(); we are going to want to reuse it for the VPT insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } -static bool trans_VPST(DisasContext *s, arg_VPST *a) +static void gen_vpst(DisasContext *s, uint32_t mask) { - TCGv_i32 vpr; - - /* mask == 0 is a "related encoding" */ - if (!dc_isar_feature(aa32_mve, s) || !a->mask) { - return false; - } - if (!mve_eci_check(s) || !vfp_access_check(s)) { - return true; - } /* * Set the VPR mask fields. We take advantage of MASK01 and MASK23 * being adjacent fields in the register. * - * This insn is not predicated, but it is subject to beat-wise + * Updating the masks is not predicated, but it is subject to beat-wise * execution, and the mask is updated on the odd-numbered beats. * So if PSR.ECI says we should skip beat 1, we mustn't update the * 01 mask field. */ - vpr = load_cpu_field(v7m.vpr); + TCGv_i32 vpr = load_cpu_field(v7m.vpr); switch (s->eci) { case ECI_NONE: case ECI_A0: /* Update both 01 and 23 fields */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask | (a->mask << 4)), + tcg_constant_i32(mask | (mask << 4)), R_V7M_VPR_MASK01_SHIFT, R_V7M_VPR_MASK01_LENGTH + R_V7M_VPR_MASK23_LENGTH); break; @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) case ECI_A0A1A2B0: /* Update only the 23 mask field */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask), + tcg_constant_i32(mask), R_V7M_VPR_MASK23_SHIFT, R_V7M_VPR_MASK23_LENGTH); break; default: g_assert_not_reached(); } store_cpu_field(vpr, v7m.vpr); +} + +static bool trans_VPST(DisasContext *s, arg_VPST *a) +{ + /* mask == 0 is a "related encoding" */ + if (!dc_isar_feature(aa32_mve, s) || !a->mask) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + gen_vpst(s, a->mask); mve_update_and_store_eci(s); return true; } -- 2.20.1 Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 ++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++- target/arm/mve_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 47 ++++++++++++++++++++++++++++++++ 4 files changed, 152 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpeqb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpneb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpnew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpcsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmphib, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphih, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphiw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgeb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpltb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpltw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgtb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2shift qd qm shift size &vidup qd rn size imm &viwdup qd rn rm size imm +&vcmp qm qn size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +# Vector comparison; 4-bit Qm but 3-bit Qn +%mask_22_13 22:1 13:3 +@vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar } # Predicate operations -%mask_22_13 22:1 13:3 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 # Logical immediate operations (1 reg and modified-immediate) @@ -XXX,XX +XXX,XX @@ VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd + +# Comparisons. We expand out the conditions which are split across +# encodings T1, T2, T3 and the fc bits. These include VPT, which is +# effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. +VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp +VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) DO_VIDUP_ALL(vidup, DO_ADD) DO_VIWDUP_ALL(viwdup, do_add_wrap) DO_VIWDUP_ALL(vdwdup, do_sub_wrap) + +/* + * Vector comparison. + * P0 bits for non-executed beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed beats (where mask is 0) are 0. + * P0 bits otherwise are updated with the results of the comparisons. + * We must also keep unchanged the MASK fields at the top of v7m.vpr. + */ +#define DO_VCMP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)]); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) + +#define DO_EQ(N, M) ((N) == (M)) +#define DO_NE(N, M) ((N) != (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_GE(N, M) ((N) >= (M)) +#define DO_LT(N, M) ((N) < (M)) +#define DO_GT(N, M) ((N) > (M)) +#define DO_LE(N, M) ((N) <= (M)) + +DO_VCMP_U(vcmpeq, DO_EQ) +DO_VCMP_U(vcmpne, DO_NE) +DO_VCMP_U(vcmpcs, DO_GE) +DO_VCMP_U(vcmphi, DO_GT) +DO_VCMP_S(vcmpge, DO_GE) +DO_VCMP_S(vcmplt, DO_LT) +DO_VCMP_S(vcmpgt, DO_GT) +DO_VCMP_S(vcmple, DO_LE) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); +typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) }; return do_viwdup(s, a, fns[a->size]); } + +static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) +{ + TCGv_ptr qn, qm; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qn, qm); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + +#define DO_VCMP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vcmp(s, a, fns[a->size]); \ + } + +DO_VCMP(VCMPEQ, vcmpeq) +DO_VCMP(VCMPNE, vcmpne) +DO_VCMP(VCMPCS, vcmpcs) +DO_VCMP(VCMPHI, vcmphi) +DO_VCMP(VCMPGE, vcmpge) +DO_VCMP(VCMPLT, vcmplt) +DO_VCMP(VCMPGT, vcmpgt) +DO_VCMP(VCMPLE, vcmple) -- 2.20.1 Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++++--- target/arm/mve_helper.c | 44 +++++++++++++++++++++++++++++++------- target/arm/translate-mve.c | 43 +++++++++++++++++++++++++++++++++++++ 4 files changed, 126 insertions(+), 11 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vidup qd rn size imm &viwdup qd rn rm size imm &vcmp qm qn size mask +&vcmp_scalar qn rm size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 +@vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 # Vector loads and stores @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar rdahi=%rdahi rdalo=%rdalo } -# Predicate operations -VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but @@ -XXX,XX +XXX,XX @@ VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp + +{ + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar +} +VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar +VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar +VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar +VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar +VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar +VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar +VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VIWDUP_ALL(vdwdup, do_sub_wrap) mve_advance_vpt(env); \ } -#define DO_VCMP_S(OP, FN) \ - DO_VCMP(OP##b, 1, int8_t, FN) \ - DO_VCMP(OP##h, 2, int16_t, FN) \ - DO_VCMP(OP##w, 4, int32_t, FN) +#define DO_VCMP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], (TYPE)rm); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } -#define DO_VCMP_U(OP, FN) \ - DO_VCMP(OP##b, 1, uint8_t, FN) \ - DO_VCMP(OP##h, 2, uint16_t, FN) \ - DO_VCMP(OP##w, 4, uint32_t, FN) +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, int8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, int16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, uint8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, uint16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, uint32_t, FN) #define DO_EQ(N, M) ((N) == (M)) #define DO_NE(N, M) ((N) != (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); +typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) return true; } +static bool do_vcmp_scalar(DisasContext *s, arg_vcmp_scalar *a, + MVEGenScalarCmpFn *fn) +{ + TCGv_ptr qn; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || !fn || a->rm == 13) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + if (a->rm == 15) { + /* Encoding Rm=0b1111 means "constant zero" */ + rm = tcg_constant_i32(0); + } else { + rm = load_reg(s, a->rm); + } + fn(cpu_env, qn, rm); + tcg_temp_free_ptr(qn); + tcg_temp_free_i32(rm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + #define DO_VCMP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) NULL, \ }; \ return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + gen_helper_mve_##FN##_scalarb, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalarw, \ + NULL, \ + }; \ + return do_vcmp_scalar(s, a, fns[a->size]); \ } DO_VCMP(VCMPEQ, vcmpeq) -- 2.20.1 Implement the MVE VPSEL insn, which sets each byte of the destination vector Qd to the byte from either Qn or Qm depending on the value of the corresponding bit in VPR.P0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/mve.decode | 7 +++++-- target/arm/mve_helper.c | 19 +++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 28 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp -VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp -VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +{ + VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz + VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp + VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +} VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMP_S(vcmpge, DO_GE) DO_VCMP_S(vcmplt, DO_LT) DO_VCMP_S(vcmpgt, DO_GT) DO_VCMP_S(vcmple, DO_LE) + +void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) +{ + /* + * Qd[n] = VPR.P0[n] ? Qn[n] : Qm[n] + * but note that whether bytes are written to Qd is still subject + * to (all forms of) predication in the usual way. + */ + uint64_t *d = vd, *n = vn, *m = vm; + uint16_t mask = mve_element_mask(env); + uint16_t p0 = FIELD_EX32(env->v7m.vpr, V7M_VPR, P0); + unsigned e; + for (e = 0; e < 16 / 8; e++, mask >>= 8, p0 >>= 8) { + uint64_t r = m[H8(e)]; + mergemask(&r, n[H8(e)], p0); + mergemask(&d[H8(e)], r, mask); + } + mve_advance_vpt(env); +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_LOGIC(VORR, gen_helper_mve_vorr) DO_LOGIC(VORN, gen_helper_mve_vorn) DO_LOGIC(VEOR, gen_helper_mve_veor) +DO_LOGIC(VPSEL, gen_helper_mve_vpsel) + #define DO_2OP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2op *a) \ { \ -- 2.20.1 Implement the MVE VMLAS insn, which multiplies a vector by a vector and adds a scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 1 + 4 files changed, 34 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +# The U bit (28) is don't-care because it does not affect the result +VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +/* "accumulating" version where FN takes d as well as n and m */ +#define DO_2OP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m), mask); \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) DO_2OP_SCALAR(OP##h, 2, int16_t, FN) \ DO_2OP_SCALAR(OP##w, 4, int32_t, FN) +#define DO_2OP_ACC_SCALAR_U(OP, FN) \ + DO_2OP_ACC_SCALAR(OP##b, 1, uint8_t, FN) \ + DO_2OP_ACC_SCALAR(OP##h, 2, uint16_t, FN) \ + DO_2OP_ACC_SCALAR(OP##w, 4, uint32_t, FN) + DO_2OP_SCALAR_U(vadd_scalar, DO_ADD) DO_2OP_SCALAR_U(vsub_scalar, DO_SUB) DO_2OP_SCALAR_U(vmul_scalar, DO_MUL) @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by vector plus scalar */ +#define DO_VMLAS(D, N, M) ((N) * (D) + (M)) + +DO_2OP_ACC_SCALAR_U(vmlas, DO_VMLAS) + /* * Long saturating scalar ops. As with DO_2OP_L, TYPE and H are for the * input (smaller) type and LESIZE, LTYPE, LH for the output (long) type. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 +++++++ target/arm/mve.decode | 23 ++++++++++++++++--- target/arm/mve_helper.c | 2 ++ target/arm/translate-mve.c | 46 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 76 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &viwdup qd rn rm size imm &vcmp qm qn size mask &vcmp_scalar qn rm size mask +&shl_scalar qda rm size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +@shl_scalar .... .... .... size:2 .. .... .... .... rm:4 &shl_scalar qda=%qd + # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 @@ -XXX,XX +XXX,XX @@ VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_no VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar -VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar + +{ + VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + +{ + VSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar @@ -XXX,XX +XXX,XX @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar - VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) +DO_2SHIFT_SAT_U(vqrshli_u, DO_UQRSHL_OP) +DO_2SHIFT_SAT_S(vqrshli_s, DO_SQRSHL_OP) /* Shift-and-insert; we always work with 64 bits at a time */ #define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, + MVEGenTwoOpShiftFn *fn) +{ + TCGv_ptr qda; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qda) || + a->rm == 13 || a->rm == 15 || !fn) { + /* Rm cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qda = mve_qreg_ptr(a->qda); + rm = load_reg(s, a->rm); + fn(cpu_env, qda, qda, rm); + tcg_temp_free_ptr(qda); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +#define DO_2SHIFT_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_shl_scalar *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_2shift_scalar(s, a, fns[a->size]); \ + } + +DO_2SHIFT_SCALAR(VSHL_S_scalar, vshli_s) +DO_2SHIFT_SCALAR(VSHL_U_scalar, vshli_u) +DO_2SHIFT_SCALAR(VRSHL_S_scalar, vrshli_s) +DO_2SHIFT_SCALAR(VRSHL_U_scalar, vrshli_u) +DO_2SHIFT_SCALAR(VQSHL_S_scalar, vqshli_s) +DO_2SHIFT_SCALAR(VQSHL_U_scalar, vqshli_u) +DO_2SHIFT_SCALAR(VQRSHL_S_scalar, vqrshli_s) +DO_2SHIFT_SCALAR(VQRSHL_U_scalar, vqrshli_u) + #define DO_VSHLL(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ { \ -- 2.20.1 All the users of the vmlaldav formats have an 'x bit in bit 12 and an 'a' bit in bit 5; move these to the format rather than specifying them in each insn pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 &vmlaldav rdahi rdalo size qn qm x a -@vmlaldav .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav -@vmlaldav_nosz .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav +VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLSLDAV 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav +VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_nosz +VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz # Scalar operations -- 2.20.1 Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++++ target/arm/mve.decode | 18 +++++++++-- target/arm/mve_helper.c | 66 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 48 +++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp qm qn size mask &vcmp_scalar qn rm size mask &shl_scalar qda rm size +&vmaxv qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +{ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} + +{ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) +/* + * Vector max/min across vector. Unlike VADDV, we must + * read ra as the element size, not its full width. + * We work with int64_t internally for simplicity. + */ +#define DO_VMAXMINV(OP, ESIZE, TYPE, RATYPE, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + int64_t ra = (RATYPE)ra_in; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + ra = FN(ra, m[H##ESIZE(e)]); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define DO_VMAXMINV_U(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, uint8_t, uint8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, uint16_t, uint16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, uint32_t, uint32_t, FN) +#define DO_VMAXMINV_S(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, int8_t, int8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, int16_t, int16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, int32_t, int32_t, FN) + +/* + * Helpers for max and min of absolute values across vector: + * note that we only take the absolute value of 'm', not 'n' + */ +static int64_t do_maxa(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MAX(n, m); +} + +static int64_t do_mina(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MIN(n, m); +} + +DO_VMAXMINV_S(vmaxvs, DO_MAX) +DO_VMAXMINV_U(vmaxvu, DO_MAX) +DO_VMAXMINV_S(vminvs, DO_MIN) +DO_VMAXMINV_U(vminvu, DO_MIN) +/* + * VMAXAV, VMINAV treat the general purpose input as unsigned + * and the vector elements as signed. + */ +DO_VMAXMINV(vmaxavb, 1, int8_t, uint8_t, do_maxa) +DO_VMAXMINV(vmaxavh, 2, int16_t, uint16_t, do_maxa) +DO_VMAXMINV(vmaxavw, 4, int32_t, uint32_t, do_maxa) +DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) +DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) +DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCMP(VCMPGE, vcmpge) DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) + +static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) +{ + /* + * MIN/MAX operations across a vector: compute the min or + * max of the initial value in a general purpose register + * and all the elements in the vector, and store it back + * into the general purpose register. + */ + TCGv_ptr qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VMAXV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV(VMAXV_S, vmaxvs) +DO_VMAXV(VMAXV_U, vmaxvu) +DO_VMAXV(VMAXAV, vmaxav) +DO_VMAXV(VMINV_S, vminvs) +DO_VMAXV(VMINV_U, vminvu) +DO_VMAXV(VMINAV, vminav) -- 2.20.1 Implement the MVE VABAV insn, which computes absolute differences between elements of two vectors and accumulates the result into a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 7 +++++++ target/arm/mve.decode | 6 ++++++ target/arm/mve_helper.c | 26 +++++++++++++++++++++++ target/arm/translate-mve.c | 43 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vabavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp_scalar qn rm size mask &shl_scalar qda rm size &vmaxv qm rda size +&vabav qn qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar rdahi=%rdahi rdalo=%rdalo } +@vabav .... .... .. size:2 .... rda:4 .... .... .... &vabav qn=%qn qm=%qm + +VABAV_S 111 0 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav +VABAV_U 111 1 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav + # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) +#define DO_VABAV(OP, ESIZE, TYPE) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t ra) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm, *n = vn; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + int64_t n0 = n[H##ESIZE(e)]; \ + int64_t m0 = m[H##ESIZE(e)]; \ + uint32_t r = n0 >= m0 ? (n0 - m0) : (m0 - n0); \ + ra += r; \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } + +DO_VABAV(vabavsb, 1, int8_t) +DO_VABAV(vabavsh, 2, int16_t) +DO_VABAV(vabavsw, 4, int32_t) +DO_VABAV(vabavub, 1, uint8_t) +DO_VABAV(vabavuh, 2, uint16_t) +DO_VABAV(vabavuw, 4, uint32_t) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ DO_VMAXV(VMAXAV, vmaxav) DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) + +static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) +{ + /* Absolute difference accumulated across vector */ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qm | a->qn) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + qn = mve_qreg_ptr(a->qn); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + tcg_temp_free_ptr(qn); + mve_update_eci(s); + return true; +} + +#define DO_VABAV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vabav *a) \ + { \ + static MVEGenVABAVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vabav(s, a, fns[a->size]); \ + } + +DO_VABAV(VABAV_S, vabavs) +DO_VABAV(VABAV_U, vabavu) -- 2.20.1 Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++ target/arm/mve.decode | 12 ++++++ target/arm/mve_helper.c | 78 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 22 +++++++++++ 4 files changed, 132 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovunbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovuntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsh, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbuh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntuh, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vand, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vbic, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNB 111 1 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BU 111 1 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNT 111 1 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TU 111 1 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) +#define DO_VMOVN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], \ + m[H##LESIZE(le)], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMOVN(vmovnbb, false, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnbh, false, 2, uint16_t, 4, uint32_t) +DO_VMOVN(vmovntb, true, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnth, true, 2, uint16_t, 4, uint32_t) + +#define DO_VMOVN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + bool qc = false; \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + bool sat = false; \ + TYPE r = FN(m[H##LESIZE(le)], &sat); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VMOVN_SAT_UB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) + +#define DO_VMOVN_SAT_UH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) + +#define DO_VMOVN_SAT_SB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) + +#define DO_VMOVN_SAT_SH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) + +#define DO_VQMOVN_SB(N, SATP) \ + do_sat_bhs((int64_t)(N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQMOVN_UB(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT8_MAX, SATP) +#define DO_VQMOVUN_B(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT8_MAX, SATP) + +#define DO_VQMOVN_SH(N, SATP) \ + do_sat_bhs((int64_t)(N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQMOVN_UH(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT16_MAX, SATP) +#define DO_VQMOVUN_H(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT16_MAX, SATP) + +DO_VMOVN_SAT_SB(vqmovnbsb, vqmovntsb, DO_VQMOVN_SB) +DO_VMOVN_SAT_SH(vqmovnbsh, vqmovntsh, DO_VQMOVN_SH) +DO_VMOVN_SAT_UB(vqmovnbub, vqmovntub, DO_VQMOVN_UB) +DO_VMOVN_SAT_UH(vqmovnbuh, vqmovntuh, DO_VQMOVN_UH) +DO_VMOVN_SAT_SB(vqmovunbb, vqmovuntb, DO_VQMOVUN_B) +DO_VMOVN_SAT_SH(vqmovunbh, vqmovunth, DO_VQMOVUN_H) + uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, uint32_t shift) { diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +/* Narrowing moves: only size 0 and 1 are valid */ +#define DO_VMOVN(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + NULL, \ + NULL, \ + }; \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VMOVN(VMOVNB, vmovnb) +DO_VMOVN(VMOVNT, vmovnt) +DO_VMOVN(VQMOVUNB, vqmovunb) +DO_VMOVN(VQMOVUNT, vqmovunt) +DO_VMOVN(VQMOVN_BS, vqmovnbs) +DO_VMOVN(VQMOVN_TS, vqmovnts) +DO_VMOVN(VQMOVN_BU, vqmovnbu) +DO_VMOVN(VQMOVN_TU, vqmovntu) + static bool trans_VREV16(DisasContext *s, arg_1op *a) { static MVEGenOneOpFn * const fns[] = { -- 2.20.1 The MVEGenDualAccOpFn is a bit misnamed, since it is used for the "long dual accumulate" operations that use a 64-bit accumulator. Rename it to MVEGenLongDualAccOpFn so we can use the former name for the 32-bit accumulator insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenLongDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) } static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, - MVEGenDualAccOpFn *fn) + MVEGenLongDualAccOpFn *fn) { TCGv_ptr qn, qm; TCGv_i64 rda; @@ -XXX,XX +XXX,XX @@ static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavsh, gen_helper_mve_vmlaldavxsh }, { gen_helper_mve_vmlaldavsw, gen_helper_mve_vmlaldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavuh, NULL }, { gen_helper_mve_vmlaldavuw, NULL }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlsldavsh, gen_helper_mve_vmlsldavxsh }, { gen_helper_mve_vmlsldavsw, gen_helper_mve_vmlsldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhsw, gen_helper_mve_vrmlaldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhuw, NULL, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlsldavhsw, gen_helper_mve_vrmlsldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); -- 2.20.1 Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 17 ++++++++++ target/arm/mve.decode | 33 +++++++++++++++++--- target/arm/mve_helper.c | 41 ++++++++++++++++++++++++ target/arm/translate-mve.c | 64 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrmlaldavhuw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhxsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vmladavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vmladavsxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvub, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 %size_16 16:1 !function=plus_1 &vmlaldav rdahi rdalo size qn qm x a +&vmladav rda size qn qm x a @vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav @vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +@vmladav .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=%size_16 &vmladav +@vmladav_nosz .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=0 &vmladav -VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +{ + VMLADAV_S 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} +{ + VMLADAV_U 1111 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} + +{ + VMLSDAV 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 1 @vmladav + VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +} + +{ + VMLSDAV 1111 1110 1111 ... 0 ... . 1110 . 0 . 0 ... 1 @vmladav_nosz + VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz +} + +VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz +VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } -VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz - # Scalar operations VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavxsh, 2, int16_t, true, +=, -=) DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) +/* + * Multiply add dual accumulate ops + */ +#define DO_DAV(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t a) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *n = vn, *m = vm; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + if (e & 1) { \ + a ODDACC \ + n[H##ESIZE(e - 1 * XCHG)] * m[H##ESIZE(e)]; \ + } else { \ + a EVENACC \ + n[H##ESIZE(e + 1 * XCHG)] * m[H##ESIZE(e)]; \ + } \ + } \ + } \ + mve_advance_vpt(env); \ + return a; \ + } + +#define DO_DAV_S(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, int8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, int16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, int32_t, XCHG, EVENACC, ODDACC) + +#define DO_DAV_U(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, uint8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, uint16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, uint32_t, XCHG, EVENACC, ODDACC) + +DO_DAV_S(vmladavs, false, +=, +=) +DO_DAV_U(vmladavu, false, +=, +=) +DO_DAV_S(vmlsdav, false, +=, -=) +DO_DAV_S(vmladavsx, true, +=, +=) +DO_DAV_S(vmlsdavx, true, +=, -=) + /* * Rounding multiply add long dual accumulate high. In the pseudocode * this is implemented with a 72-bit internal accumulator value of which diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TC typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } +static bool do_dual_acc(DisasContext *s, arg_vmladav *a, MVEGenDualAccOpFn *fn) +{ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qn) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + + /* + * This insn is subject to beat-wise execution. Partial execution + * of an A=0 (no-accumulate) insn which does not execute the first + * beat must start with the current rda value, not 0. + */ + if (a->a || mve_skip_first_beat(s)) { + rda = load_reg(s, a->rda); + } else { + rda = tcg_const_i32(0); + } + + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + + mve_update_eci(s); + return true; +} + +#define DO_DUAL_ACC(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmladav *a) \ + { \ + static MVEGenDualAccOpFn * const fns[4][2] = { \ + { gen_helper_mve_##FN##b, gen_helper_mve_##FN##xb }, \ + { gen_helper_mve_##FN##h, gen_helper_mve_##FN##xh }, \ + { gen_helper_mve_##FN##w, gen_helper_mve_##FN##xw }, \ + { NULL, NULL }, \ + }; \ + return do_dual_acc(s, a, fns[a->size][a->x]); \ + } + +DO_DUAL_ACC(VMLADAV_S, vmladavs) +DO_DUAL_ACC(VMLSDAV, vmlsdav) + +static bool trans_VMLADAV_U(DisasContext *s, arg_vmladav *a) +{ + static MVEGenDualAccOpFn * const fns[4][2] = { + { gen_helper_mve_vmladavub, NULL }, + { gen_helper_mve_vmladavuh, NULL }, + { gen_helper_mve_vmladavuw, NULL }, + { NULL, NULL }, + }; + return do_dual_acc(s, a, fns[a->size][a->x]); +} + static void gen_vpst(DisasContext *s, uint32_t mask) { /* -- 2.20.1 Implement the MVE VMLA insn, which multiplies a vector by a scalar and accumulates into another vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 1 + target/arm/mve_helper.c | 5 +++++ target/arm/translate-mve.c | 1 + 4 files changed, 11 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlab, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlah, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlaw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar # The U bit (28) is don't-care because it does not affect the result +VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar # Vector add across vector diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by scalar plus vector */ +#define DO_VMLA(D, N, M) ((N) * (M) + (D)) + +DO_2OP_ACC_SCALAR_U(vmla, DO_VMLA) + /* Vector by vector plus scalar */ #define DO_VMLAS(D, N, M) ((N) * (D) + (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) -- 2.20.1 Implement the MVE saturating doubling multiply accumulate insns VQDMLAH, VQRDMLAH, VQDMLASH and VQRDMLASH. These perform a multiply, double, add the accumulator shifted by the element size, possibly round, saturate to twice the element size, then take the high half of the result. The *MLAH insns do vector * scalar + vector, and the *MLASH insns do vector * vector + scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 16 +++++++ target/arm/mve.decode | 5 ++ target/arm/mve_helper.c | 95 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 4 ++ 4 files changed, 120 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar +VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar +VQDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 110 .... @2scalar +VQDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 110 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +#define DO_2OP_SAT_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m, &sat), \ + mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +static int8_t do_vqdmlah_b(int8_t a, int8_t b, int8_t c, int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 8) + (round << 7); + return do_sat_bhw(r, INT16_MIN, INT16_MAX, sat) >> 8; +} + +static int16_t do_vqdmlah_h(int16_t a, int16_t b, int16_t c, + int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 16) + (round << 15); + return do_sat_bhw(r, INT32_MIN, INT32_MAX, sat) >> 16; +} + +static int32_t do_vqdmlah_w(int32_t a, int32_t b, int32_t c, + int round, bool *sat) +{ + /* + * Architecturally we should do the entire add, double, round + * and then check for saturation. We do three saturating adds, + * but we need to be careful about the order. If the first + * m1 + m2 saturates then it's impossible for the *2+rc to + * bring it back into the non-saturated range. However, if + * m1 + m2 is negative then it's possible that doing the doubling + * would take the intermediate result below INT64_MAX and the + * addition of the rounding constant then brings it back in range. + * So we add half the rounding constant and half the "c << esize" + * before doubling rather than adding the rounding constant after + * the doubling. + */ + int64_t m1 = (int64_t)a * b; + int64_t m2 = (int64_t)c << 31; + int64_t r; + if (sadd64_overflow(m1, m2, &r) || + sadd64_overflow(r, (round << 30), &r) || + sadd64_overflow(r, r, &r)) { + *sat = true; + return r < 0 ? INT32_MAX : INT32_MIN; + } + return r >> 32; +} + +/* + * The *MLAH insns are vector * scalar + vector; + * the *MLASH insns are vector * vector + scalar + */ +#define DO_VQDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 0, S) +#define DO_VQDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 0, S) +#define DO_VQDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 0, S) +#define DO_VQRDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 1, S) +#define DO_VQRDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 1, S) +#define DO_VQRDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 1, S) + +#define DO_VQDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 0, S) +#define DO_VQDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 0, S) +#define DO_VQDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 0, S) +#define DO_VQRDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 1, S) +#define DO_VQRDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 1, S) +#define DO_VQRDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 1, S) + +DO_2OP_SAT_ACC_SCALAR(vqdmlahb, 1, int8_t, DO_VQDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlahh, 2, int16_t, DO_VQDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlahw, 4, int32_t, DO_VQDMLAH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahb, 1, int8_t, DO_VQRDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahh, 2, int16_t, DO_VQRDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahw, 4, int32_t, DO_VQRDMLAH_W) + +DO_2OP_SAT_ACC_SCALAR(vqdmlashb, 1, int8_t, DO_VQDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlashh, 2, int16_t, DO_VQDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlashw, 4, int32_t, DO_VQDMLASH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashb, 1, int8_t, DO_VQRDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashh, 2, int16_t, DO_VQRDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashw, 4, int32_t, DO_VQRDMLASH_W) + /* Vector by scalar plus vector */ #define DO_VMLA(D, N, M) ((N) * (M) + (D)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) +DO_2OP_SCALAR(VQDMLAH, vqdmlah) +DO_2OP_SCALAR(VQRDMLAH, vqrdmlah) +DO_2OP_SCALAR(VQDMLASH, vqdmlash) +DO_2OP_SCALAR(VQRDMLASH, vqrdmlash) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE 1-operand saturating operations VQABS and VQNEG. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 50 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VABS_fp 1111 1111 1 . 11 .. 01 ... 0 0111 01 . 0 ... 0 @1op VNEG 1111 1111 1 . 11 .. 01 ... 0 0011 11 . 0 ... 0 @1op VNEG_fp 1111 1111 1 . 11 .. 01 ... 0 0111 11 . 0 ... 0 @1op +VQABS 1111 1111 1 . 11 .. 00 ... 0 0111 01 . 0 ... 0 @1op +VQNEG 1111 1111 1 . 11 .. 00 ... 0 0111 11 . 0 ... 0 @1op + &vdup qd rt size # Qd is in the fields usually named Qn @vdup .... .... . . .. ... . rt:4 .... . . . . .... qd=%qn &vdup diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) } mve_advance_vpt(env); } + +#define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], FN(m[H##ESIZE(e)], &sat), mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VQABS_B(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQABS_H(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQABS_W(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT32_MIN, INT32_MAX, SATP) + +#define DO_VQNEG_B(N, SATP) do_sat_bhs(-(int64_t)N, INT8_MIN, INT8_MAX, SATP) +#define DO_VQNEG_H(N, SATP) do_sat_bhs(-(int64_t)N, INT16_MIN, INT16_MAX, SATP) +#define DO_VQNEG_W(N, SATP) do_sat_bhs(-(int64_t)N, INT32_MIN, INT32_MAX, SATP) + +DO_1OP_SAT(vqabsb, 1, int8_t, DO_VQABS_B) +DO_1OP_SAT(vqabsh, 2, int16_t, DO_VQABS_H) +DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) + +DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) +DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) +DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLZ, vclz) DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +DO_1OP(VQABS, vqabs) +DO_1OP(VQNEG, vqneg) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMAXA and VMINA insns, which take the absolute value of the signed elements in the input vector and then accumulate the unsigned max or min into the destination vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 4 ++++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 40 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMAXA 111 0 1110 0 . 11 .. 11 ... 0 1110 1 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VMINA 111 0 1110 0 . 11 .. 11 ... 1 1110 1 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) + +/* + * VMAXA, VMINA: vd is unsigned; vm is signed, and we take its + * absolute value; we then do an unsigned comparison. + */ +#define DO_VMAXMINA(OP, ESIZE, STYPE, UTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + UTYPE *d = vd; \ + STYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + UTYPE r = DO_ABS(m[H##ESIZE(e)]); \ + r = FN(d[H##ESIZE(e)], r); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMAXMINA(vmaxab, 1, int8_t, uint8_t, DO_MAX) +DO_VMAXMINA(vmaxah, 2, int16_t, uint16_t, DO_MAX) +DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) +DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) +DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) +DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) DO_1OP(VQABS, vqabs) DO_1OP(VQNEG, vqneg) +DO_1OP(VMAXA, vmaxa) +DO_1OP(VMINA, vmina) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMOV forms that move data between 2 general-purpose registers and 2 32-bit lanes in a vector register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-a32.h | 1 + target/arm/mve.decode | 4 ++ target/arm/translate-mve.c | 85 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-vfp.c | 2 +- 4 files changed, 91 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); static inline TCGv_i32 load_cpu_offset(int offset) { diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# Moves between 2 32-bit vector lanes and 2 general purpose registers +VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd +VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd + # Vector 2-op VAND 1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz VBIC 1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) DO_VABAV(VABAV_S, vabavs) DO_VABAV(VABAV_U, vabavu) + +static bool trans_VMOV_to_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two 32-bit vector lanes to two general-purpose registers. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15 || + a->rt == a->rt2) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg index to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd, a->idx, MO_32); + store_reg(s, a->rt, tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd + 1, a->idx, MO_32); + store_reg(s, a->rt2, tmp); + } + + mve_update_and_store_eci(s); + return true; +} + +static bool trans_VMOV_from_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two general-purpose registers to two 32-bit vector lanes. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg idx to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = load_reg(s, a->rt); + write_neon_element32(tmp, vd, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = load_reg(s, a->rt2); + write_neon_element32(tmp, vd + 1, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + + mve_update_and_store_eci(s); + return true; +} diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return true; } -static bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) { /* * In a CPU with MVE, the VMOV (vector lane to general-purpose register) -- 2.20.1 Implement the MVE VPNOT insn, which inverts the bits in VPR.P0 (subject to both predication and to beatwise execution). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 1 + target/arm/mve.decode | 1 + target/arm/mve_helper.c | 17 +++++++++++++++++ target/arm/translate-mve.c | 19 +++++++++++++++++++ 4 files changed, 38 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) mve_advance_vpt(env); } +void HELPER(mve_vpnot)(CPUARMState *env) +{ + /* + * P0 bits for unexecuted beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed bits (where mask is 0) are 0. + * P0 bits otherwise are inverted. + * (This is the same logic as VCMP.) + * This insn is itself subject to predication and to beat-wise execution, + * and after it executes VPT state advances in the usual way. + */ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t beatpred = ~env->v7m.vpr & mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (beatpred & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) return true; } +static bool trans_VPNOT(DisasContext *s, arg_VPNOT *a) +{ + /* + * Invert the predicate in VPR.P0. We have call out to + * a helper because this insn itself is beatwise and can + * be predicated. + */ + if (!dc_isar_feature(aa32_mve, s)) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + gen_helper_mve_vpnot(cpu_env); + mve_update_eci(s); + return true; +} + static bool trans_VADDV(DisasContext *s, arg_VADDV *a) { /* VADDV: vector add across vector */ -- 2.20.1 Implement the MVE VCTP insn, which sets the VPR.P0 predicate bits so as to predicate any element at index Rn or greater is predicated. As with VPNOT, this insn itself is predicable and subject to beatwise execution. The calculation of the mask is the same as is used to determine ltpmask in mve_element_mask(), but we precalculate masklen in generated code to avoid having to have 4 helpers specialized by size. We put the decode line in with the low-overhead-loop insns in t32.decode because it's logically part of that collection of insn patterns, even though it is an MVE only insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/translate-a32.h | 1 + target/arm/t32.decode | 1 + target/arm/mve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-mve.c | 2 +- target/arm/translate.c | 33 +++++++++++++++++++++++++++++++++ 6 files changed, 58 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) +DEF_HELPER_FLAGS_2(mve_vctp, TCG_CALL_NO_WG, void, env, i32) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ long neon_element_offset(int reg, int element, MemOp memop); void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); +void mve_update_eci(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ BL 1111 0. .......... 11.1 ............ @branch24 # This is DLSTP DLS 1111 0 0000 0 size:2 rn:4 1110 0000 0000 0001 } + VCTP 1111 0 0000 0 size:2 rn:4 1110 1000 0000 0001 ] } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpnot)(CPUARMState *env) mve_advance_vpt(env); } +/* + * VCTP: P0 unexecuted bits unchanged, predicated bits zeroed, + * otherwise set according to value of Rn. The calculation of + * newmask here works in the same way as the calculation of the + * ltpmask in mve_element_mask(), but we have pre-calculated + * the masklen in the generated code. + */ +void HELPER(mve_vctp)(CPUARMState *env, uint32_t masklen) +{ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t newmask; + + assert(masklen <= 16); + newmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + newmask &= mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (newmask & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ bool mve_eci_check(DisasContext *s) } } -static void mve_update_eci(DisasContext *s) +void mve_update_eci(DisasContext *s) { /* * The helper function will always update the CPUState field, 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 trans_LCTP(DisasContext *s, arg_LCTP *a) return true; } +static bool trans_VCTP(DisasContext *s, arg_VCTP *a) +{ + /* + * M-profile Create Vector Tail Predicate. This insn is itself + * predicated and is subject to beatwise execution. + */ + TCGv_i32 rn_shifted, masklen; + + if (!dc_isar_feature(aa32_mve, s) || a->rn == 13 || a->rn == 15) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * We pre-calculate the mask length here to avoid having + * to have multiple helpers specialized for size. + * We pass the helper "rn <= (1 << (4 - size)) ? (rn << size) : 16". + */ + rn_shifted = tcg_temp_new_i32(); + masklen = load_reg(s, a->rn); + tcg_gen_shli_i32(rn_shifted, masklen, a->size); + tcg_gen_movcond_i32(TCG_COND_LEU, masklen, + masklen, tcg_constant_i32(1 << (4 - a->size)), + rn_shifted, tcg_constant_i32(16)); + gen_helper_mve_vctp(cpu_env, masklen); + tcg_temp_free_i32(masklen); + tcg_temp_free_i32(rn_shifted); + mve_update_eci(s); + return true; +} static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half) { -- 2.20.1 Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++ target/arm/mve.decode | 12 ++++ target/arm/mve_helper.c | 129 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 97 ++++++++++++++++++++++++++++ 4 files changed, 270 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrb_h, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrb_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &shl_scalar qda rm size &vmaxv qm rda size &vabav qn qm rda size +&vldst_sg qd qm rn size msize os + +# scatter-gather memory size is in bits 6:4 +%sg_msize 6:1 4:1 @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @vldst_wn ... u:1 ... . . . . l:1 . rn:3 qd:3 . ... .. imm:7 &vldr_vstr +@vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ + qd=%qd qm=%qm msize=%sg_msize + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# gather loads/scatter stores +VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR +/* + * Gather loads/scatter stores. Here each element of Qm specifies + * an offset to use from the base register Rm. In the _os_ versions + * that offset is scaled by the element size. + * For loads, predicated lanes are zeroed instead of retaining + * their previous values. + */ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + OFFTYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + d[H##ESIZE(e)] = (mask & 1) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +/* We know here TYPE is unsigned so always the same as the offset type */ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + TYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + if (mask & 1) { \ + cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +/* + * 64-bit accesses are slightly different: they are done as two 32-bit + * accesses, controlled by the predicate mask for the relevant beat, + * and with a single 32-bit offset in the first of the two Qm elements. + * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + */ +#define DO_VLDR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSTR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + if (mask & 1) { \ + cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +#define ADDR_ADD(BASE, OFFSET) ((BASE) + (OFFSET)) +#define ADDR_ADD_OSH(BASE, OFFSET) ((BASE) + ((OFFSET) << 1)) +#define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) +#define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) + +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) + +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) + +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) + +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) + +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) #include "decode-mve.c.inc" typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) +static bool do_ldst_sg(DisasContext *s, arg_vldst_sg *a, MVEGenLdStSGFn fn) +{ + TCGv_i32 addr; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn || a->rn == 15) { + /* Rn case is UNPREDICTABLE */ + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + addr = load_reg(s, a->rn); + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, addr); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + tcg_temp_free_i32(addr); + mve_update_eci(s); + return true; +} + +/* + * The naming scheme here is "vldrb_sg_sh == in-memory byte loads + * signextended to halfword elements in register". _os_ indicates that + * the offsets in Qm should be scaled by the element size. + */ +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +/* VLDRB/VSTRB (ie msize 1) with OS=1 is UNPREDICTABLE; we UNDEF */ +static bool trans_VLDR_S_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { NULL, F(vldrb_sg_sh), F(vldrb_sg_sw), NULL }, + { NULL, NULL, F(vldrh_sg_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, NULL, F(vldrh_sg_os_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VLDR_U_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vldrb_sg_ub), F(vldrb_sg_uh), F(vldrb_sg_uw), NULL }, + { NULL, F(vldrh_sg_uh), F(vldrh_sg_uw), NULL }, + { NULL, NULL, F(vldrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vldrh_sg_os_uh), F(vldrh_sg_os_uw), NULL }, + { NULL, NULL, F(vldrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_os_ud) } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vstrb_sg_ub), F(vstrb_sg_uh), F(vstrb_sg_uw), NULL }, + { NULL, F(vstrh_sg_uh), F(vstrh_sg_uw), NULL }, + { NULL, NULL, F(vstrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vstrh_sg_os_uh), F(vstrh_sg_os_uw), NULL }, + { NULL, NULL, F(vstrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_os_ud) } + } + }; + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++ target/arm/mve.decode | 10 +++++ target/arm/mve_helper.c | 91 ++++++++++++++++++++++++-------------- target/arm/translate-mve.c | 72 ++++++++++++++++++++++++++++++ 4 files changed, 146 insertions(+), 32 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vmaxv qm rda size &vabav qn qm rda size &vldst_sg qd qm rn size msize os +&vldst_sg_imm qd qm a w imm # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ qd=%qd qm=%qm msize=%sg_msize +# Qm is in the fields usually labeled Qn +@vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ + qd=%qd qm=%qn + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg +VLDRW_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm +VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * For loads, predicated lanes are zeroed instead of retaining * their previous values. */ -#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H##ESIZE(e)]); \ d[H##ESIZE(e)] = (mask & 1) ? \ cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } /* We know here TYPE is unsigned so always the same as the offset type */ -#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ TYPE *d = vd; \ TYPE *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ if (mask & 1) { \ cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ } \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * accesses, controlled by the predicate mask for the relevant beat, * and with a single 32-bit offset in the first of the two Qm elements. * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + * Address writeback happens on the odd beats and updates the address + * stored in the even-beat element. */ -#define DO_VLDR64_SG(OP, ADDRFN) \ +#define DO_VLDR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } -#define DO_VSTR64_SG(OP, ADDRFN) \ +#define DO_VSTR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ uint32_t *d = vd; \ uint32_t *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ if (mask & 1) { \ cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ } \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) -DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) -DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) -DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) -DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) + +DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* * The mergemask(D, R, M) macro performs the operation "*D = R" but diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) #undef F +static bool do_ldst_sg_imm(DisasContext *s, arg_vldst_sg_imm *a, + MVEGenLdStSGFn *fn, unsigned msize) +{ + uint32_t offset; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + offset = a->imm << msize; + if (!a->a) { + offset = -offset; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(offset)); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +static bool trans_VLDRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrw_sg_uw, + gen_helper_mve_vldrw_sg_wb_uw, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VLDRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrd_sg_ud, + gen_helper_mve_vldrd_sg_wb_ud, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + +static bool trans_VSTRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrw_sg_uw, + gen_helper_mve_vstrw_sg_wb_uw, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrd_sg_ud, + gen_helper_mve_vstrd_sg_wb_ud, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE interleaving load/store functions VLD2, VLD4, VST2 and VST4. VLD2 loads 16 bytes of data from memory and writes to 2 consecutive Qregs; VLD4 loads 16 bytes of data from memory and writes to 4 consecutive Qregs. The 'pattern' field in the encoding determines the offset into memory which is accessed and also which elements in the Qregs are written to. (The intention is that a sequence of four consecutive VLD4 with different pattern values performs a complete de-interleaving load of 64 bytes into all elements of the 4 Qregs.) VST2 and VST4 do the same, but for stores. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 48 ++++++ target/arm/mve.decode | 11 ++ target/arm/mve_helper.c | 342 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 94 ++++++++++ 4 files changed, 495 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vld20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43w, TCG_CALL_NO_WG, void, env, i32, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vabav qn qm rda size &vldst_sg qd qm rn size msize os &vldst_sg_imm qd qm a w imm +&vldst_il qd rn size pat w # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ qd=%qd qm=%qn +# Deinterleaving load/interleaving store +@vldst_il .... .... .. w:1 . rn:4 .... ... size:2 pat:2 ..... &vldst_il \ + qd=%qd + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm +# deinterleaving loads/interleaving stores +VLD2 1111 1100 1 .. 1 .... ... 1 111 .. .. 00000 @vldst_il +VLD4 1111 1100 1 .. 1 .... ... 1 111 .. .. 00001 @vldst_il +VST2 1111 1100 1 .. 0 .... ... 1 111 .. .. 00000 @vldst_il +VST4 1111 1100 1 .. 0 .... ... 1 111 .. .. 00001 @vldst_il + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) +/* + * Deinterleaving loads/interleaving stores. + * + * For these helpers we are passed the index of the first Qreg + * (VLD2/VST2 will also access Qn+1, VLD4/VST4 access Qn .. Qn+3) + * and the value of the base address register Rn. + * The helpers are specialized for pattern and element size, so + * for instance vld42h is VLD4 with pattern 2, element size MO_16. + * + * These insns are beatwise but not predicated, so we must honour ECI, + * but need not look at mve_element_mask(). + * + * The pseudocode implements these insns with multiple memory accesses + * of the element size, but rules R_VVVG and R_FXDM permit us to make + * one 32-bit memory access per beat. + */ +#define DO_VLD4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H1(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H2(off[beat])] = data; \ + data >>= 16; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + qd[H2(off[beat])] = data; \ + } \ + } + +#define DO_VLD4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H4(off[beat] >> 2)] = data; \ + } \ + } + +DO_VLD4B(vld40b, 0, 1, 10, 11) +DO_VLD4B(vld41b, 2, 3, 12, 13) +DO_VLD4B(vld42b, 4, 5, 14, 15) +DO_VLD4B(vld43b, 6, 7, 8, 9) + +DO_VLD4H(vld40h, 0, 5) +DO_VLD4H(vld41h, 1, 6) +DO_VLD4H(vld42h, 2, 7) +DO_VLD4H(vld43h, 3, 4) + +DO_VLD4W(vld40w, 0, 1, 10, 11) +DO_VLD4W(vld41w, 2, 3, 12, 13) +DO_VLD4W(vld42w, 4, 5, 14, 15) +DO_VLD4W(vld43w, 6, 7, 8, 9) + +#define DO_VLD2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + qd[H1(off[beat] + (e >> 1))] = data; \ + } \ + } \ + } + +#define DO_VLD2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 2; e++, data >>= 16) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H2(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + qd[H4(off[beat] >> 3)] = data; \ + } \ + } + +DO_VLD2B(vld20b, 0, 2, 12, 14) +DO_VLD2B(vld21b, 4, 6, 8, 10) + +DO_VLD2H(vld20h, 0, 1, 6, 7) +DO_VLD2H(vld21h, 2, 3, 4, 5) + +DO_VLD2W(vld20w, 0, 4, 24, 28) +DO_VLD2W(vld21w, 8, 12, 16, 20) + +#define DO_VST4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 8) | qd[H1(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H2(off[beat])]; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + data |= qd[H2(off[beat])] << 16; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H4(off[beat] >> 2)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST4B(vst40b, 0, 1, 10, 11) +DO_VST4B(vst41b, 2, 3, 12, 13) +DO_VST4B(vst42b, 4, 5, 14, 15) +DO_VST4B(vst43b, 6, 7, 8, 9) + +DO_VST4H(vst40h, 0, 5) +DO_VST4H(vst41h, 1, 6) +DO_VST4H(vst42h, 2, 7) +DO_VST4H(vst43h, 3, 4) + +DO_VST4W(vst40w, 0, 1, 10, 11) +DO_VST4W(vst41w, 2, 3, 12, 13) +DO_VST4W(vst42w, 4, 5, 14, 15) +DO_VST4W(vst43w, 6, 7, 8, 9) + +#define DO_VST2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + data = (data << 8) | qd[H1(off[beat] + (e >> 1))]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 1; e >= 0; e--) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 16) | qd[H2(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + data = qd[H4(off[beat] >> 3)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST2B(vst20b, 0, 2, 12, 14) +DO_VST2B(vst21b, 4, 6, 8, 10) + +DO_VST2H(vst20h, 0, 1, 6, 7) +DO_VST2H(vst21h, 2, 3, 4, 5) + +DO_VST2W(vst20w, 0, 4, 24, 28) +DO_VST2W(vst21w, 8, 12, 16, 20) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStIlFn(TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) return do_ldst_sg_imm(s, a, fns[a->w], MO_64); } +static bool do_vldst_il(DisasContext *s, arg_vldst_il *a, MVEGenLdStIlFn *fn, + int addrinc) +{ + TCGv_i32 rn; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd) || + !fn || (a->rn == 13 && a->w) || a->rn == 15) { + /* Variously UNPREDICTABLE or UNDEF or related-encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + rn = load_reg(s, a->rn); + /* + * We pass the index of Qd, not a pointer, because the helper must + * access multiple Q registers starting at Qd and working up. + */ + fn(cpu_env, tcg_constant_i32(a->qd), rn); + + if (a->w) { + tcg_gen_addi_i32(rn, rn, addrinc); + store_reg(s, a->rn, rn); + } else { + tcg_temp_free_i32(rn); + } + mve_update_and_store_eci(s); + return true; +} + +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +static bool trans_VLD2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld20b), F(vld20h), F(vld20w), NULL, }, + { F(vld21b), F(vld21h), F(vld21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VLD4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld40b), F(vld40h), F(vld40w), NULL, }, + { F(vld41b), F(vld41h), F(vld41w), NULL, }, + { F(vld42b), F(vld42h), F(vld42w), NULL, }, + { F(vld43b), F(vld43h), F(vld43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +static bool trans_VST2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst20b), F(vst20h), F(vst20w), NULL, }, + { F(vst21b), F(vst21h), F(vst21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VST4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst40b), F(vst40h), F(vst40w), NULL, }, + { F(vst41b), F(vst41h), F(vst41w), NULL, }, + { F(vst42b), F(vst42h), F(vst42w), NULL, }, + { F(vst43b), F(vst43h), F(vst43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 We're about to make a code change to the sdiv and udiv helper functions, so first fix their indentation and coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-2-peter.maydell@linaro.org --- target/arm/helper.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) 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(uxtb16)(uint32_t x) int32_t HELPER(sdiv)(int32_t num, int32_t den) { - if (den == 0) - return 0; - if (num == INT_MIN && den == -1) - return INT_MIN; + if (den == 0) { + return 0; + } + if (num == INT_MIN && den == -1) { + return INT_MIN; + } return num / den; } uint32_t HELPER(udiv)(uint32_t num, uint32_t den) { - if (den == 0) - return 0; + if (den == 0) { + return 0; + } return num / den; } -- 2.20.1 Unlike A-profile, for M-profile the UDIV and SDIV insns can be configured to raise an exception on division by zero, using the CCR DIV_0_TRP bit. Implement support for setting this bit by making the helper functions raise the appropriate exception. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-3-peter.maydell@linaro.org --- target/arm/cpu.h | 1 + target/arm/helper.h | 4 ++-- target/arm/helper.c | 19 +++++++++++++++++-- target/arm/m_helper.c | 4 ++++ target/arm/translate.c | 4 ++-- 5 files changed, 26 insertions(+), 6 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 @@ #define EXCP_LAZYFP 20 /* v7M fault during lazy FP stacking */ #define EXCP_LSERR 21 /* v8M LSERR SecureFault */ #define EXCP_UNALIGNED 22 /* v7M UNALIGNED UsageFault */ +#define EXCP_DIVBYZERO 23 /* v7M DIVBYZERO UsageFault */ /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 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(add_saturate, i32, env, i32, i32) DEF_HELPER_3(sub_saturate, i32, env, i32, i32) DEF_HELPER_3(add_usaturate, i32, env, i32, i32) DEF_HELPER_3(sub_usaturate, i32, env, i32, i32) -DEF_HELPER_FLAGS_2(sdiv, TCG_CALL_NO_RWG_SE, s32, s32, s32) -DEF_HELPER_FLAGS_2(udiv, TCG_CALL_NO_RWG_SE, i32, i32, i32) +DEF_HELPER_FLAGS_3(sdiv, TCG_CALL_NO_RWG, s32, env, s32, s32) +DEF_HELPER_FLAGS_3(udiv, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_1(rbit, TCG_CALL_NO_RWG_SE, i32, i32) #define PAS_OP(pfx) \ 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(sxtb16)(uint32_t x) return res; } +static void handle_possible_div0_trap(CPUARMState *env, uintptr_t ra) +{ + /* + * Take a division-by-zero exception if necessary; otherwise return + * to get the usual non-trapping division behaviour (result of 0) + */ + if (arm_feature(env, ARM_FEATURE_M) + && (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_DIV_0_TRP_MASK)) { + raise_exception_ra(env, EXCP_DIVBYZERO, 0, 1, ra); + } +} + uint32_t HELPER(uxtb16)(uint32_t x) { uint32_t res; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) return res; } -int32_t HELPER(sdiv)(int32_t num, int32_t den) +int32_t HELPER(sdiv)(CPUARMState *env, int32_t num, int32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } if (num == INT_MIN && den == -1) { @@ -XXX,XX +XXX,XX @@ int32_t HELPER(sdiv)(int32_t num, int32_t den) return num / den; } -uint32_t HELPER(udiv)(uint32_t num, uint32_t den) +uint32_t HELPER(udiv)(CPUARMState *env, uint32_t num, uint32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } return num / den; @@ -XXX,XX +XXX,XX @@ void arm_log_exception(int idx) [EXCP_LAZYFP] = "v7M exception during lazy FP stacking", [EXCP_LSERR] = "v8M LSERR UsageFault", [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", + [EXCP_DIVBYZERO] = "v7M DIVBYZERO UsageFault", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_UNALIGNED_MASK; break; + case EXCP_DIVBYZERO: + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_DIVBYZERO_MASK; + break; case EXCP_SWI: /* The PC already points to the next instruction. */ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); 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 op_div(DisasContext *s, arg_rrr *a, bool u) t1 = load_reg(s, a->rn); t2 = load_reg(s, a->rm); if (u) { - gen_helper_udiv(t1, t1, t2); + gen_helper_udiv(t1, cpu_env, t1, t2); } else { - gen_helper_sdiv(t1, t1, t2); + gen_helper_sdiv(t1, cpu_env, t1, t2); } tcg_temp_free_i32(t2); store_reg(s, a->rd, t1); -- 2.20.1 From: Hamza Mahfooz <someguy@effective-light.com> As per commit 5626f8c6d468 ("rcu: Add automatically released rcu_read_lock variants"), RCU_READ_LOCK_GUARD() should be used instead of rcu_read_{un}lock(). Signed-off-by: Hamza Mahfooz <someguy@effective-light.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20210727235201.11491-1-someguy@effective-light.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, hwaddr xlat, len, doorbell_gpa; MemoryRegionSection mrs; MemoryRegion *mr; - int ret = 1; if (as == &address_space_memory) { return 0; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, /* MSI doorbell address is translated by an IOMMU */ - rcu_read_lock(); + RCU_READ_LOCK_GUARD(); + mr = address_space_translate(as, address, &xlat, &len, true, MEMTXATTRS_UNSPECIFIED); + if (!mr) { - goto unlock; + return 1; } + mrs = memory_region_find(mr, xlat, 1); + if (!mrs.mr) { - goto unlock; + return 1; } doorbell_gpa = mrs.offset_within_address_space; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, trace_kvm_arm_fixup_msi_route(address, doorbell_gpa); - ret = 0; - -unlock: - rcu_read_unlock(); - return ret; + return 0; } int kvm_arch_add_msi_route_post(struct kvm_irq_routing_entry *route, -- 2.20.1 From: Jan Luebbe <jlu@pengutronix.de> Break events are currently only handled by chardev/char-serial.c, so we just ignore errors, which results in no behaviour change for other chardevs. Signed-off-by: Jan Luebbe <jlu@pengutronix.de> Message-id: 20210806144700.3751979-1-jlu@pengutronix.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/pl011.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties-system.h" #include "migration/vmstate.h" #include "chardev/char-fe.h" +#include "chardev/char-serial.h" #include "qemu/log.h" #include "qemu/module.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, s->read_count = 0; s->read_pos = 0; } + if ((s->lcr ^ value) & 0x1) { + int break_enable = value & 0x1; + qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_BREAK, + &break_enable); + } s->lcr = value; pl011_set_read_trigger(s); break; -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 and ASRC as unimplemented devices to avoid random Linux kernel crashes, such as Unhandled fault: external abort on non-linefetch (0x808) at 0xd1580010 pgd = (ptrval) [d1580010] *pgd=8231b811, *pte=02034653, *ppte=02034453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c095837c>] (_regmap_update_bits+0xe4/0xec) [<c095837c>] (_regmap_update_bits) from [<c09599b4>] (regmap_update_bits_base+0x50/0x74) [<c09599b4>] (regmap_update_bits_base) from [<c0d3e9e4>] (fsl_asrc_runtime_resume+0x1e4/0x21c) [<c0d3e9e4>] (fsl_asrc_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d3ecc4>] (fsl_asrc_probe+0x2a8/0x708) [<c0d3ecc4>] (fsl_asrc_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) or Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810160318.87376-1-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx6ul.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) */ create_unimplemented_device("sdma", FSL_IMX6UL_SDMA_ADDR, 0x4000); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX6UL_SAI1_ADDR, 0x4000); + create_unimplemented_device("sai2", FSL_IMX6UL_SAI2_ADDR, 0x4000); + create_unimplemented_device("sai3", FSL_IMX6UL_SAI3_ADDR, 0x4000); + /* * PWM */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) create_unimplemented_device("pwm3", FSL_IMX6UL_PWM3_ADDR, 0x4000); create_unimplemented_device("pwm4", FSL_IMX6UL_PWM4_ADDR, 0x4000); + /* + * Audio ASRC (asynchronous sample rate converter) + */ + create_unimplemented_device("asrc", FSL_IMX6UL_ASRC_ADDR, 0x4000); + /* * CAN */ -- 2.20.1 From: "Wen, Jianxian" <Jianxian.Wen@verisilicon.com> Add property memory region which can connect with IOMMU region to support SMMU translate. Signed-off-by: Jianxian Wen <jianxian.wen@verisilicon.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 4C23C17B8E87E74E906A25A3254A03F4FA1FEC31@SHASXM03.verisilicon.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/exynos4210.c | 3 +++ hw/arm/xilinx_zynq.c | 3 +++ hw/dma/pl330.c | 26 ++++++++++++++++++++++---- 3 files changed, 28 insertions(+), 4 deletions(-) diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static DeviceState *pl330_create(uint32_t base, qemu_or_irq *orgate, int i; dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(get_system_memory()), + &error_fatal); qdev_prop_set_uint8(dev, "num_events", nevents); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", nreq); diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[39-IRQ_OFFSET]); dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(address_space_mem), + &error_fatal); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", 4); qdev_prop_set_uint8(dev, "num_events", 16); diff --git a/hw/dma/pl330.c b/hw/dma/pl330.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/pl330.c +++ b/hw/dma/pl330.c @@ -XXX,XX +XXX,XX @@ struct PL330State { uint8_t num_faulting; uint8_t periph_busy[PL330_PERIPH_NUM]; + /* Memory region that DMA operation access */ + MemoryRegion *mem_mr; + AddressSpace *mem_as; }; #define TYPE_PL330 "pl330" @@ -XXX,XX +XXX,XX @@ static inline const PL330InsnDesc *pl330_fetch_insn(PL330Chan *ch) uint8_t opcode; int i; - dma_memory_read(&address_space_memory, ch->pc, &opcode, 1); + dma_memory_read(ch->parent->mem_as, ch->pc, &opcode, 1); for (i = 0; insn_desc[i].size; i++) { if ((opcode & insn_desc[i].opmask) == insn_desc[i].opcode) { return &insn_desc[i]; @@ -XXX,XX +XXX,XX @@ static inline void pl330_exec_insn(PL330Chan *ch, const PL330InsnDesc *insn) uint8_t buf[PL330_INSN_MAXSIZE]; assert(insn->size <= PL330_INSN_MAXSIZE); - dma_memory_read(&address_space_memory, ch->pc, buf, insn->size); + dma_memory_read(ch->parent->mem_as, ch->pc, buf, insn->size); insn->exec(ch, buf[0], &buf[1], insn->size - 1); } @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) if (q != NULL && q->len <= pl330_fifo_num_free(&s->fifo)) { int len = q->len - (q->addr & (q->len - 1)); - dma_memory_read(&address_space_memory, q->addr, buf, len); + dma_memory_read(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) fifo_res = pl330_fifo_get(&s->fifo, buf, len, q->tag); } if (fifo_res == PL330_FIFO_OK || q->z) { - dma_memory_write(&address_space_memory, q->addr, buf, len); + dma_memory_write(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static void pl330_realize(DeviceState *dev, Error **errp) "dma", PL330_IOMEM_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + if (!s->mem_mr) { + error_setg(errp, "'memory' link is not set"); + return; + } else if (s->mem_mr == get_system_memory()) { + /* Avoid creating new AS for system memory. */ + s->mem_as = &address_space_memory; + } else { + s->mem_as = g_new0(AddressSpace, 1); + address_space_init(s->mem_as, s->mem_mr, + memory_region_name(s->mem_mr)); + } + s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pl330_exec_cycle_timer, s); s->cfg[0] = (s->mgr_ns_at_rst ? 0x4 : 0) | @@ -XXX,XX +XXX,XX @@ static Property pl330_properties[] = { DEFINE_PROP_UINT8("rd_q_dep", PL330State, rd_q_dep, 16), DEFINE_PROP_UINT16("data_buffer_dep", PL330State, data_buffer_dep, 256), + DEFINE_PROP_LINK("memory", PL330State, mem_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Eduardo Habkost <ehabkost@redhat.com> The SBSA_GWDT enum value conflicts with the SBSA_GWDT() QOM type checking helper, preventing us from using a OBJECT_DEFINE* or DEFINE_INSTANCE_CHECKER macro for the SBSA_GWDT() wrapper. If I understand the SBSA 6.0 specification correctly, the signal being connected to IRQ 16 is the WS0 output signal from the Generic Watchdog. Rename the enum value to SBSA_GWDT_WS0 to be more explicit and avoid the name conflict. Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20210806023119.431680-1-ehabkost@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ enum { SBSA_GIC_DIST, SBSA_GIC_REDIST, SBSA_SECURE_EC, - SBSA_GWDT, + SBSA_GWDT_WS0, SBSA_GWDT_REFRESH, SBSA_GWDT_CONTROL, SBSA_SMMU, @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_AHCI] = 10, [SBSA_EHCI] = 11, [SBSA_SMMU] = 12, /* ... to 15 */ - [SBSA_GWDT] = 16, + [SBSA_GWDT_WS0] = 16, }; static const char * const valid_cpus[] = { @@ -XXX,XX +XXX,XX @@ static void create_wdt(const SBSAMachineState *sms) hwaddr cbase = sbsa_ref_memmap[SBSA_GWDT_CONTROL].base; DeviceState *dev = qdev_new(TYPE_WDT_SBSA); SysBusDevice *s = SYS_BUS_DEVICE(dev); - int irq = sbsa_ref_irqmap[SBSA_GWDT]; + int irq = sbsa_ref_irqmap[SBSA_GWDT_WS0]; sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, rbase); -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 as unimplemented devices to avoid Linux kernel crashes such as the following. Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0-rc5 #1 ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810175607.538090-1-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 5 +++++ hw/arm/fsl-imx7.c | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_UART6_ADDR = 0x30A80000, FSL_IMX7_UART7_ADDR = 0x30A90000, + FSL_IMX7_SAI1_ADDR = 0x308A0000, + FSL_IMX7_SAI2_ADDR = 0x308B0000, + FSL_IMX7_SAI3_ADDR = 0x308C0000, + FSL_IMX7_SAIn_SIZE = 0x10000, + FSL_IMX7_ENET1_ADDR = 0x30BE0000, FSL_IMX7_ENET2_ADDR = 0x30BF0000, diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("can1", FSL_IMX7_CAN1_ADDR, FSL_IMX7_CANn_SIZE); create_unimplemented_device("can2", FSL_IMX7_CAN2_ADDR, FSL_IMX7_CANn_SIZE); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX7_SAI1_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI2_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI3_ADDR, FSL_IMX7_SAIn_SIZE); + /* * OCOTP */ -- 2.20.1 From: Sebastian Meyer <meyer@absint.com> With gdb 9.0 and better it is possible to connect to a gdbstub over unix sockets, which is better than a TCP socket connection in some situations. The QEMU command line to set this up is non-obvious; document it. Signed-off-by: Sebastian Meyer <meyer@absint.com> Message-id: 162867284829.27377.4784930719350564918-0@git.sr.ht [PMM: Tweaked commit message; adjusted wording in a couple of places; fixed rST formatting issue; moved section up out of the 'advanced debugging options' subsection] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/gdb.rst | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/docs/system/gdb.rst b/docs/system/gdb.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/gdb.rst +++ b/docs/system/gdb.rst @@ -XXX,XX +XXX,XX @@ The ``-s`` option will make QEMU listen for an incoming connection from gdb on TCP port 1234, and ``-S`` will make QEMU not start the guest until you tell it to from gdb. (If you want to specify which TCP port to use or to use something other than TCP for the gdbstub -connection, use the ``-gdb dev`` option instead of ``-s``.) +connection, use the ``-gdb dev`` option instead of ``-s``. See +`Using unix sockets`_ for an example.) .. parsed-literal:: @@ -XXX,XX +XXX,XX @@ not just those in the cluster you are currently working on:: (gdb) set schedule-multiple on +Using unix sockets +================== + +An alternate method for connecting gdb to the QEMU gdbstub is to use +a unix socket (if supported by your operating system). This is useful when +running several tests in parallel, or if you do not have a known free TCP +port (e.g. when running automated tests). + +First create a chardev with the appropriate options, then +instruct the gdbserver to use that device: + +.. parsed-literal:: + + |qemu_system| -chardev socket,path=/tmp/gdb-socket,server=on,wait=off,id=gdb0 -gdb chardev:gdb0 -S ... + +Start gdb as before, but this time connect using the path to +the socket:: + + (gdb) target remote /tmp/gdb-socket + +Note that to use a unix socket for the connection you will need +gdb version 9.0 or newer. + Advanced debugging options ========================== -- 2.20.1