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 Hi; here's the first arm pullreq for 9.1. This includes the reset method function signature change, so it has some chance of compile failures due to merge conflicts if some other pullreq added a device reset method and that pullreq got applied before this one. If so, the changes needed to fix those up can be created by running the spatch rune described in the commit message of the "hw, target: Add ResetType argument to hold and exit phase methods" commit. thanks -- PMM The following changes since commit 5da72194df36535d773c8bdc951529ecd5e31707: Merge tag 'pull-tcg-20240424' of https://gitlab.com/rth7680/qemu into staging (2024-04-24 15:51:49 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240425 for you to fetch changes up to 214652da123e3821657a64691ee556281e9f6238: tests/qtest: Add tests for the STM32L4x5 USART (2024-04-25 10:21:59 +0100) ---------------------------------------------------------------- target-arm queue: * Implement FEAT_NMI and NMI support in the GICv3 * hw/dma: avoid apparent overflow in soc_dma_set_request * linux-user/flatload.c: Remove unused bFLT shared-library and ZFLAT code * Add ResetType argument to Resettable hold and exit phase methods * Add RESET_TYPE_SNAPSHOT_LOAD ResetType * Implement STM32L4x5 USART ---------------------------------------------------------------- Anastasia Belova (1): hw/dma: avoid apparent overflow in soc_dma_set_request Arnaud Minier (5): hw/char: Implement STM32L4x5 USART skeleton hw/char/stm32l4x5_usart: Enable serial read and write hw/char/stm32l4x5_usart: Add options for serial parameters setting hw/arm: Add the USART to the stm32l4x5 SoC tests/qtest: Add tests for the STM32L4x5 USART Jinjie Ruan (22): target/arm: Handle HCR_EL2 accesses for bits introduced with FEAT_NMI target/arm: Add PSTATE.ALLINT target/arm: Add support for FEAT_NMI, Non-maskable Interrupt target/arm: Implement ALLINT MSR (immediate) target/arm: Support MSR access to ALLINT target/arm: Add support for Non-maskable Interrupt target/arm: Add support for NMI in arm_phys_excp_target_el() target/arm: Handle IS/FS in ISR_EL1 for NMI, VINMI and VFNMI target/arm: Handle PSTATE.ALLINT on taking an exception hw/intc/arm_gicv3: Add external IRQ lines for NMI hw/arm/virt: Wire NMI and VINMI irq lines from GIC to CPU target/arm: Handle NMI in arm_cpu_do_interrupt_aarch64() hw/intc/arm_gicv3: Add has-nmi property to GICv3 device hw/intc/arm_gicv3_kvm: Not set has-nmi=true for the KVM GICv3 hw/intc/arm_gicv3: Add irq non-maskable property hw/intc/arm_gicv3_redist: Implement GICR_INMIR0 hw/intc/arm_gicv3: Implement GICD_INMIR hw/intc/arm_gicv3: Implement NMI interrupt priority hw/intc/arm_gicv3: Report the NMI interrupt in gicv3_cpuif_update() hw/intc/arm_gicv3: Report the VINMI interrupt target/arm: Add FEAT_NMI to max hw/arm/virt: Enable NMI support in the GIC if the CPU has FEAT_NMI Peter Maydell (9): hw/intc/arm_gicv3: Add NMI handling CPU interface registers hw/intc/arm_gicv3: Handle icv_nmiar1_read() for icc_nmiar1_read() linux-user/flatload.c: Remove unused bFLT shared-library and ZFLAT code hw/misc: Don't special case RESET_TYPE_COLD in npcm7xx_clk, gcr allwinner-i2c, adm1272: Use device_cold_reset() for software-triggered reset scripts/coccinelle: New script to add ResetType to hold and exit phases hw, target: Add ResetType argument to hold and exit phase methods docs/devel/reset: Update to new API for hold and exit phase methods reset: Add RESET_TYPE_SNAPSHOT_LOAD MAINTAINERS | 1 + docs/devel/reset.rst | 25 +- docs/system/arm/b-l475e-iot01a.rst | 2 +- docs/system/arm/emulation.rst | 1 + scripts/coccinelle/reset-type.cocci | 133 ++++++++ hw/intc/gicv3_internal.h | 13 + include/hw/arm/stm32l4x5_soc.h | 7 + include/hw/char/stm32l4x5_usart.h | 67 ++++ include/hw/intc/arm_gic_common.h | 2 + include/hw/intc/arm_gicv3_common.h | 14 + include/hw/resettable.h | 5 +- linux-user/flat.h | 5 +- target/arm/cpu-features.h | 5 + target/arm/cpu-qom.h | 5 +- target/arm/cpu.h | 9 + target/arm/internals.h | 21 ++ target/arm/tcg/helper-a64.h | 1 + target/arm/tcg/a64.decode | 1 + hw/adc/npcm7xx_adc.c | 2 +- hw/arm/pxa2xx_pic.c | 2 +- hw/arm/smmu-common.c | 2 +- hw/arm/smmuv3.c | 4 +- hw/arm/stellaris.c | 10 +- hw/arm/stm32l4x5_soc.c | 83 ++++- hw/arm/virt.c | 29 +- hw/audio/asc.c | 2 +- hw/char/cadence_uart.c | 2 +- hw/char/sifive_uart.c | 2 +- hw/char/stm32l4x5_usart.c | 637 ++++++++++++++++++++++++++++++++++++ hw/core/cpu-common.c | 2 +- hw/core/qdev.c | 4 +- hw/core/reset.c | 17 +- hw/core/resettable.c | 8 +- hw/display/virtio-vga.c | 4 +- hw/dma/soc_dma.c | 4 +- hw/gpio/npcm7xx_gpio.c | 2 +- hw/gpio/pl061.c | 2 +- hw/gpio/stm32l4x5_gpio.c | 2 +- hw/hyperv/vmbus.c | 2 +- hw/i2c/allwinner-i2c.c | 5 +- hw/i2c/npcm7xx_smbus.c | 2 +- hw/input/adb.c | 2 +- hw/input/ps2.c | 12 +- hw/intc/arm_gic_common.c | 2 +- hw/intc/arm_gic_kvm.c | 4 +- hw/intc/arm_gicv3.c | 67 +++- hw/intc/arm_gicv3_common.c | 50 ++- hw/intc/arm_gicv3_cpuif.c | 268 ++++++++++++++- hw/intc/arm_gicv3_dist.c | 36 ++ hw/intc/arm_gicv3_its.c | 4 +- hw/intc/arm_gicv3_its_common.c | 2 +- hw/intc/arm_gicv3_its_kvm.c | 4 +- hw/intc/arm_gicv3_kvm.c | 9 +- hw/intc/arm_gicv3_redist.c | 22 ++ hw/intc/xics.c | 2 +- hw/m68k/q800-glue.c | 2 +- hw/misc/djmemc.c | 2 +- hw/misc/iosb.c | 2 +- hw/misc/mac_via.c | 8 +- hw/misc/macio/cuda.c | 4 +- hw/misc/macio/pmu.c | 4 +- hw/misc/mos6522.c | 2 +- hw/misc/npcm7xx_clk.c | 13 +- hw/misc/npcm7xx_gcr.c | 12 +- hw/misc/npcm7xx_mft.c | 2 +- hw/misc/npcm7xx_pwm.c | 2 +- hw/misc/stm32l4x5_exti.c | 2 +- hw/misc/stm32l4x5_rcc.c | 10 +- hw/misc/stm32l4x5_syscfg.c | 2 +- hw/misc/xlnx-versal-cframe-reg.c | 2 +- hw/misc/xlnx-versal-crl.c | 2 +- hw/misc/xlnx-versal-pmc-iou-slcr.c | 2 +- hw/misc/xlnx-versal-trng.c | 2 +- hw/misc/xlnx-versal-xramc.c | 2 +- hw/misc/xlnx-zynqmp-apu-ctrl.c | 2 +- hw/misc/xlnx-zynqmp-crf.c | 2 +- hw/misc/zynq_slcr.c | 4 +- hw/net/can/xlnx-zynqmp-can.c | 2 +- hw/net/e1000.c | 2 +- hw/net/e1000e.c | 2 +- hw/net/igb.c | 2 +- hw/net/igbvf.c | 2 +- hw/nvram/xlnx-bbram.c | 2 +- hw/nvram/xlnx-versal-efuse-ctrl.c | 2 +- hw/nvram/xlnx-zynqmp-efuse.c | 2 +- hw/pci-bridge/cxl_root_port.c | 4 +- hw/pci-bridge/pcie_root_port.c | 2 +- hw/pci-host/bonito.c | 2 +- hw/pci-host/pnv_phb.c | 4 +- hw/pci-host/pnv_phb3_msi.c | 4 +- hw/pci/pci.c | 4 +- hw/rtc/mc146818rtc.c | 2 +- hw/s390x/css-bridge.c | 2 +- hw/sensor/adm1266.c | 2 +- hw/sensor/adm1272.c | 4 +- hw/sensor/isl_pmbus_vr.c | 10 +- hw/sensor/max31785.c | 2 +- hw/sensor/max34451.c | 2 +- hw/ssi/npcm7xx_fiu.c | 2 +- hw/timer/etraxfs_timer.c | 2 +- hw/timer/npcm7xx_timer.c | 2 +- hw/usb/hcd-dwc2.c | 8 +- hw/usb/xlnx-versal-usb2-ctrl-regs.c | 2 +- hw/virtio/virtio-pci.c | 2 +- linux-user/flatload.c | 293 +---------------- target/arm/cpu.c | 151 ++++++++- target/arm/helper.c | 101 +++++- target/arm/tcg/cpu64.c | 1 + target/arm/tcg/helper-a64.c | 16 +- target/arm/tcg/translate-a64.c | 19 ++ target/avr/cpu.c | 4 +- target/cris/cpu.c | 4 +- target/hexagon/cpu.c | 4 +- target/i386/cpu.c | 4 +- target/loongarch/cpu.c | 4 +- target/m68k/cpu.c | 4 +- target/microblaze/cpu.c | 4 +- target/mips/cpu.c | 4 +- target/openrisc/cpu.c | 4 +- target/ppc/cpu_init.c | 4 +- target/riscv/cpu.c | 4 +- target/rx/cpu.c | 4 +- target/sh4/cpu.c | 4 +- target/sparc/cpu.c | 4 +- target/tricore/cpu.c | 4 +- target/xtensa/cpu.c | 4 +- tests/qtest/stm32l4x5_usart-test.c | 315 ++++++++++++++++++ hw/arm/Kconfig | 1 + hw/char/Kconfig | 3 + hw/char/meson.build | 1 + hw/char/trace-events | 12 + hw/intc/trace-events | 2 + tests/qtest/meson.build | 4 +- 133 files changed, 2239 insertions(+), 537 deletions(-) create mode 100644 scripts/coccinelle/reset-type.cocci create mode 100644 include/hw/char/stm32l4x5_usart.h create mode 100644 hw/char/stm32l4x5_usart.c create mode 100644 tests/qtest/stm32l4x5_usart-test.c From: Jinjie Ruan <ruanjinjie@huawei.com> FEAT_NMI defines another three new bits in HCRX_EL2: TALLINT, HCRX_VINMI and HCRX_VFNMI. When the feature is enabled, allow these bits to be written in HCRX_EL2. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-2-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu-features.h | 5 +++++ target/arm/helper.c | 8 +++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; } +static inline bool isar_feature_aa64_nmi(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, NMI) != 0; +} + static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) { return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; 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 @@ bool el_is_in_host(CPUARMState *env, int el) static void hcrx_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { + ARMCPU *cpu = env_archcpu(env); uint64_t valid_mask = 0; /* FEAT_MOPS adds MSCEn and MCE2 */ - if (cpu_isar_feature(aa64_mops, env_archcpu(env))) { + if (cpu_isar_feature(aa64_mops, cpu)) { valid_mask |= HCRX_MSCEN | HCRX_MCE2; } + /* FEAT_NMI adds TALLINT, VINMI and VFNMI */ + if (cpu_isar_feature(aa64_nmi, cpu)) { + valid_mask |= HCRX_TALLINT | HCRX_VINMI | HCRX_VFNMI; + } + /* Clear RES0 bits. */ env->cp15.hcrx_el2 = value & valid_mask; } -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> When PSTATE.ALLINT is set, an IRQ or FIQ interrupt that is targeted to ELx, with or without superpriority is masked. As Richard suggested, place ALLINT bit in PSTATE in env->pstate. In the pseudocode, AArch64.ExceptionReturn() calls SetPSTATEFromPSR(), which treats PSTATE.ALLINT as one of the bits which are reinstated from SPSR to PSTATE regardless of whether this is an illegal exception return or not. So handle PSTATE.ALLINT the same way as PSTATE.DAIF in the illegal_return exit path of the exception_return helper. With the change, exception entry and return are automatically handled. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-3-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + target/arm/tcg/helper-a64.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define PSTATE_D (1U << 9) #define PSTATE_BTYPE (3U << 10) #define PSTATE_SSBS (1U << 12) +#define PSTATE_ALLINT (1U << 13) #define PSTATE_IL (1U << 20) #define PSTATE_SS (1U << 21) #define PSTATE_PAN (1U << 22) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ illegal_return: */ env->pstate |= PSTATE_IL; env->pc = new_pc; - spsr &= PSTATE_NZCV | PSTATE_DAIF; - spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF); + spsr &= PSTATE_NZCV | PSTATE_DAIF | PSTATE_ALLINT; + spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF | PSTATE_ALLINT); pstate_write(env, spsr); if (!arm_singlestep_active(env)) { env->pstate &= ~PSTATE_SS; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Add support for FEAT_NMI. NMI (FEAT_NMI) is an mandatory feature in ARMv8.8-A and ARM v9.3-A. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-4-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id) if (isar_feature_aa64_mte(id)) { valid |= PSTATE_TCO; } + if (isar_feature_aa64_nmi(id)) { + valid |= PSTATE_ALLINT; + } return valid; } -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Add ALLINT MSR (immediate) to decodetree, in which the CRm is 0b000x. The EL0 check is necessary to ALLINT, and the EL1 check is necessary when imm == 1. So implement it inline for EL2/3, or EL1 with imm==0. Avoid the unconditional write to pc and use raise_exception_ra to unwind. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-5-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-a64.h | 1 + target/arm/tcg/a64.decode | 1 + target/arm/tcg/helper-a64.c | 12 ++++++++++++ target/arm/tcg/translate-a64.c | 19 +++++++++++++++++++ 4 files changed, 33 insertions(+) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_1(rbit64, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_2(msr_i_spsel, void, env, i32) DEF_HELPER_2(msr_i_daifset, void, env, i32) DEF_HELPER_2(msr_i_daifclear, void, env, i32) +DEF_HELPER_1(msr_set_allint_el1, void, env) DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, ptr) DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, ptr) DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ MSR_i_DIT 1101 0101 0000 0 011 0100 .... 010 11111 @msr_i MSR_i_TCO 1101 0101 0000 0 011 0100 .... 100 11111 @msr_i MSR_i_DAIFSET 1101 0101 0000 0 011 0100 .... 110 11111 @msr_i MSR_i_DAIFCLEAR 1101 0101 0000 0 011 0100 .... 111 11111 @msr_i +MSR_i_ALLINT 1101 0101 0000 0 001 0100 000 imm:1 000 11111 MSR_i_SVCR 1101 0101 0000 0 011 0100 0 mask:2 imm:1 011 11111 # MRS, MSR (register), SYS, SYSL. These are all essentially the diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(msr_i_spsel)(CPUARMState *env, uint32_t imm) update_spsel(env, imm); } +void HELPER(msr_set_allint_el1)(CPUARMState *env) +{ + /* ALLINT update to PSTATE. */ + if (arm_hcrx_el2_eff(env) & HCRX_TALLINT) { + raise_exception_ra(env, EXCP_UDEF, + syn_aa64_sysregtrap(0, 1, 0, 4, 1, 0x1f, 0), 2, + GETPC()); + } + + env->pstate |= PSTATE_ALLINT; +} + static void daif_check(CPUARMState *env, uint32_t op, uint32_t imm, uintptr_t ra) { diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_MSR_i_DAIFCLEAR(DisasContext *s, arg_i *a) return true; } +static bool trans_MSR_i_ALLINT(DisasContext *s, arg_i *a) +{ + if (!dc_isar_feature(aa64_nmi, s) || s->current_el == 0) { + return false; + } + + if (a->imm == 0) { + clear_pstate_bits(PSTATE_ALLINT); + } else if (s->current_el > 1) { + set_pstate_bits(PSTATE_ALLINT); + } else { + gen_helper_msr_set_allint_el1(tcg_env); + } + + /* Exit the cpu loop to re-evaluate pending IRQs. */ + s->base.is_jmp = DISAS_UPDATE_EXIT; + return true; +} + static bool trans_MSR_i_SVCR(DisasContext *s, arg_MSR_i_SVCR *a) { if (!dc_isar_feature(aa64_sme, s) || a->mask == 0) { -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Support ALLINT msr access as follow: mrs <xt>, ALLINT // read allint msr ALLINT, <xt> // write allint with imm Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-6-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo rme_mte_reginfo[] = { .opc0 = 1, .opc1 = 6, .crn = 7, .crm = 14, .opc2 = 5, .access = PL3_W, .type = ARM_CP_NOP }, }; + +static void aa64_allint_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + env->pstate = (env->pstate & ~PSTATE_ALLINT) | (value & PSTATE_ALLINT); +} + +static uint64_t aa64_allint_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return env->pstate & PSTATE_ALLINT; +} + +static CPAccessResult aa64_allint_access(CPUARMState *env, + const ARMCPRegInfo *ri, bool isread) +{ + if (!isread && arm_current_el(env) == 1 && + (arm_hcrx_el2_eff(env) & HCRX_TALLINT)) { + return CP_ACCESS_TRAP_EL2; + } + return CP_ACCESS_OK; +} + +static const ARMCPRegInfo nmi_reginfo[] = { + { .name = "ALLINT", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .opc2 = 0, .crn = 4, .crm = 3, + .type = ARM_CP_NO_RAW, + .access = PL1_RW, .accessfn = aa64_allint_access, + .fieldoffset = offsetof(CPUARMState, pstate), + .writefn = aa64_allint_write, .readfn = aa64_allint_read, + .resetfn = arm_cp_reset_ignore }, +}; #endif /* TARGET_AARCH64 */ static void define_pmu_regs(ARMCPU *cpu) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_nv2, cpu)) { define_arm_cp_regs(cpu, nv2_reginfo); } + + if (cpu_isar_feature(aa64_nmi, cpu)) { + define_arm_cp_regs(cpu, nmi_reginfo); + } #endif if (cpu_isar_feature(any_predinv, cpu)) { -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> This only implements the external delivery method via the GICv3. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-7-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu-qom.h | 5 +- target/arm/cpu.h | 6 ++ target/arm/internals.h | 18 +++++ target/arm/cpu.c | 147 ++++++++++++++++++++++++++++++++++++++--- target/arm/helper.c | 33 +++++++-- 5 files changed, 193 insertions(+), 16 deletions(-) diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-qom.h +++ b/target/arm/cpu-qom.h @@ -XXX,XX +XXX,XX @@ DECLARE_CLASS_CHECKERS(AArch64CPUClass, AARCH64_CPU, #define ARM_CPU_TYPE_SUFFIX "-" TYPE_ARM_CPU #define ARM_CPU_TYPE_NAME(name) (name ARM_CPU_TYPE_SUFFIX) -/* Meanings of the ARMCPU object's four inbound GPIO lines */ +/* Meanings of the ARMCPU object's seven inbound GPIO lines */ #define ARM_CPU_IRQ 0 #define ARM_CPU_FIQ 1 #define ARM_CPU_VIRQ 2 #define ARM_CPU_VFIQ 3 +#define ARM_CPU_NMI 4 +#define ARM_CPU_VINMI 5 +#define ARM_CPU_VFNMI 6 /* For M profile, some registers are banked secure vs non-secure; * these are represented as a 2-element array where the first element 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_DIVBYZERO 23 /* v7M DIVBYZERO UsageFault */ #define EXCP_VSERR 24 #define EXCP_GPC 25 /* v9 Granule Protection Check Fault */ +#define EXCP_NMI 26 +#define EXCP_VINMI 27 +#define EXCP_VFNMI 28 /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 @@ -XXX,XX +XXX,XX @@ #define CPU_INTERRUPT_VIRQ CPU_INTERRUPT_TGT_EXT_2 #define CPU_INTERRUPT_VFIQ CPU_INTERRUPT_TGT_EXT_3 #define CPU_INTERRUPT_VSERR CPU_INTERRUPT_TGT_INT_0 +#define CPU_INTERRUPT_NMI CPU_INTERRUPT_TGT_EXT_4 +#define CPU_INTERRUPT_VINMI CPU_INTERRUPT_TGT_EXT_0 +#define CPU_INTERRUPT_VFNMI CPU_INTERRUPT_TGT_INT_1 /* The usual mapping for an AArch64 system register to its AArch32 * counterpart is for the 32 bit world to have access to the lower diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ void arm_cpu_update_virq(ARMCPU *cpu); */ void arm_cpu_update_vfiq(ARMCPU *cpu); +/** + * arm_cpu_update_vinmi: Update CPU_INTERRUPT_VINMI bit in cs->interrupt_request + * + * Update the CPU_INTERRUPT_VINMI bit in cs->interrupt_request, following + * a change to either the input VNMI line from the GIC or the HCRX_EL2.VINMI. + * Must be called with the BQL held. + */ +void arm_cpu_update_vinmi(ARMCPU *cpu); + +/** + * arm_cpu_update_vfnmi: Update CPU_INTERRUPT_VFNMI bit in cs->interrupt_request + * + * Update the CPU_INTERRUPT_VFNMI bit in cs->interrupt_request, following + * a change to the HCRX_EL2.VFNMI. + * Must be called with the BQL held. + */ +void arm_cpu_update_vfnmi(ARMCPU *cpu); + /** * arm_cpu_update_vserr: Update CPU_INTERRUPT_VSERR bit * 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 @@ void arm_restore_state_to_opc(CPUState *cs, } #endif /* CONFIG_TCG */ +/* + * With SCTLR_ELx.NMI == 0, IRQ with Superpriority is masked identically with + * IRQ without Superpriority. Moreover, if the GIC is configured so that + * FEAT_GICv3_NMI is only set if FEAT_NMI is set, then we won't ever see + * CPU_INTERRUPT_*NMI anyway. So we might as well accept NMI here + * unconditionally. + */ static bool arm_cpu_has_work(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ static bool arm_cpu_has_work(CPUState *cs) return (cpu->power_state != PSCI_OFF) && cs->interrupt_request & (CPU_INTERRUPT_FIQ | CPU_INTERRUPT_HARD + | CPU_INTERRUPT_NMI | CPU_INTERRUPT_VINMI | CPU_INTERRUPT_VFNMI | CPU_INTERRUPT_VFIQ | CPU_INTERRUPT_VIRQ | CPU_INTERRUPT_VSERR | CPU_INTERRUPT_EXITTB); } @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, CPUARMState *env = cpu_env(cs); bool pstate_unmasked; bool unmasked = false; + bool allIntMask = false; /* * Don't take exceptions if they target a lower EL. @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, return false; } + if (cpu_isar_feature(aa64_nmi, env_archcpu(env)) && + env->cp15.sctlr_el[target_el] & SCTLR_NMI && cur_el == target_el) { + allIntMask = env->pstate & PSTATE_ALLINT || + ((env->cp15.sctlr_el[target_el] & SCTLR_SPINTMASK) && + (env->pstate & PSTATE_SP)); + } + switch (excp_idx) { + case EXCP_NMI: + pstate_unmasked = !allIntMask; + break; + + case EXCP_VINMI: + if (!(hcr_el2 & HCR_IMO) || (hcr_el2 & HCR_TGE)) { + /* VINMIs are only taken when hypervized. */ + return false; + } + return !allIntMask; + case EXCP_VFNMI: + if (!(hcr_el2 & HCR_FMO) || (hcr_el2 & HCR_TGE)) { + /* VFNMIs are only taken when hypervized. */ + return false; + } + return !allIntMask; case EXCP_FIQ: - pstate_unmasked = !(env->daif & PSTATE_F); + pstate_unmasked = (!(env->daif & PSTATE_F)) && (!allIntMask); break; case EXCP_IRQ: - pstate_unmasked = !(env->daif & PSTATE_I); + pstate_unmasked = (!(env->daif & PSTATE_I)) && (!allIntMask); break; case EXCP_VFIQ: @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, /* VFIQs are only taken when hypervized. */ return false; } - return !(env->daif & PSTATE_F); + return !(env->daif & PSTATE_F) && (!allIntMask); case EXCP_VIRQ: if (!(hcr_el2 & HCR_IMO) || (hcr_el2 & HCR_TGE)) { /* VIRQs are only taken when hypervized. */ return false; } - return !(env->daif & PSTATE_I); + return !(env->daif & PSTATE_I) && (!allIntMask); case EXCP_VSERR: if (!(hcr_el2 & HCR_AMO) || (hcr_el2 & HCR_TGE)) { /* VIRQs are only taken when hypervized. */ @@ -XXX,XX +XXX,XX @@ static bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) /* The prioritization of interrupts is IMPLEMENTATION DEFINED. */ + if (cpu_isar_feature(aa64_nmi, env_archcpu(env)) && + (arm_sctlr(env, cur_el) & SCTLR_NMI)) { + if (interrupt_request & CPU_INTERRUPT_NMI) { + excp_idx = EXCP_NMI; + target_el = arm_phys_excp_target_el(cs, excp_idx, cur_el, secure); + if (arm_excp_unmasked(cs, excp_idx, target_el, + cur_el, secure, hcr_el2)) { + goto found; + } + } + if (interrupt_request & CPU_INTERRUPT_VINMI) { + excp_idx = EXCP_VINMI; + target_el = 1; + if (arm_excp_unmasked(cs, excp_idx, target_el, + cur_el, secure, hcr_el2)) { + goto found; + } + } + if (interrupt_request & CPU_INTERRUPT_VFNMI) { + excp_idx = EXCP_VFNMI; + target_el = 1; + if (arm_excp_unmasked(cs, excp_idx, target_el, + cur_el, secure, hcr_el2)) { + goto found; + } + } + } else { + /* + * NMI disabled: interrupts with superpriority are handled + * as if they didn't have it + */ + if (interrupt_request & CPU_INTERRUPT_NMI) { + interrupt_request |= CPU_INTERRUPT_HARD; + } + if (interrupt_request & CPU_INTERRUPT_VINMI) { + interrupt_request |= CPU_INTERRUPT_VIRQ; + } + if (interrupt_request & CPU_INTERRUPT_VFNMI) { + interrupt_request |= CPU_INTERRUPT_VFIQ; + } + } + if (interrupt_request & CPU_INTERRUPT_FIQ) { excp_idx = EXCP_FIQ; target_el = arm_phys_excp_target_el(cs, excp_idx, cur_el, secure); @@ -XXX,XX +XXX,XX @@ void arm_cpu_update_virq(ARMCPU *cpu) CPUARMState *env = &cpu->env; CPUState *cs = CPU(cpu); - bool new_state = (env->cp15.hcr_el2 & HCR_VI) || + bool new_state = ((arm_hcr_el2_eff(env) & HCR_VI) && + !(arm_hcrx_el2_eff(env) & HCRX_VINMI)) || (env->irq_line_state & CPU_INTERRUPT_VIRQ); if (new_state != ((cs->interrupt_request & CPU_INTERRUPT_VIRQ) != 0)) { @@ -XXX,XX +XXX,XX @@ void arm_cpu_update_vfiq(ARMCPU *cpu) CPUARMState *env = &cpu->env; CPUState *cs = CPU(cpu); - bool new_state = (env->cp15.hcr_el2 & HCR_VF) || + bool new_state = ((arm_hcr_el2_eff(env) & HCR_VF) && + !(arm_hcrx_el2_eff(env) & HCRX_VFNMI)) || (env->irq_line_state & CPU_INTERRUPT_VFIQ); if (new_state != ((cs->interrupt_request & CPU_INTERRUPT_VFIQ) != 0)) { @@ -XXX,XX +XXX,XX @@ void arm_cpu_update_vfiq(ARMCPU *cpu) } } +void arm_cpu_update_vinmi(ARMCPU *cpu) +{ + /* + * Update the interrupt level for VINMI, which is the logical OR of + * the HCRX_EL2.VINMI bit and the input line level from the GIC. + */ + CPUARMState *env = &cpu->env; + CPUState *cs = CPU(cpu); + + bool new_state = ((arm_hcr_el2_eff(env) & HCR_VI) && + (arm_hcrx_el2_eff(env) & HCRX_VINMI)) || + (env->irq_line_state & CPU_INTERRUPT_VINMI); + + if (new_state != ((cs->interrupt_request & CPU_INTERRUPT_VINMI) != 0)) { + if (new_state) { + cpu_interrupt(cs, CPU_INTERRUPT_VINMI); + } else { + cpu_reset_interrupt(cs, CPU_INTERRUPT_VINMI); + } + } +} + +void arm_cpu_update_vfnmi(ARMCPU *cpu) +{ + /* + * Update the interrupt level for VFNMI, which is the HCRX_EL2.VFNMI bit. + */ + CPUARMState *env = &cpu->env; + CPUState *cs = CPU(cpu); + + bool new_state = (arm_hcr_el2_eff(env) & HCR_VF) && + (arm_hcrx_el2_eff(env) & HCRX_VFNMI); + + if (new_state != ((cs->interrupt_request & CPU_INTERRUPT_VFNMI) != 0)) { + if (new_state) { + cpu_interrupt(cs, CPU_INTERRUPT_VFNMI); + } else { + cpu_reset_interrupt(cs, CPU_INTERRUPT_VFNMI); + } + } +} + void arm_cpu_update_vserr(ARMCPU *cpu) { /* @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_irq(void *opaque, int irq, int level) [ARM_CPU_IRQ] = CPU_INTERRUPT_HARD, [ARM_CPU_FIQ] = CPU_INTERRUPT_FIQ, [ARM_CPU_VIRQ] = CPU_INTERRUPT_VIRQ, - [ARM_CPU_VFIQ] = CPU_INTERRUPT_VFIQ + [ARM_CPU_VFIQ] = CPU_INTERRUPT_VFIQ, + [ARM_CPU_NMI] = CPU_INTERRUPT_NMI, + [ARM_CPU_VINMI] = CPU_INTERRUPT_VINMI, }; if (!arm_feature(env, ARM_FEATURE_EL2) && @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_irq(void *opaque, int irq, int level) case ARM_CPU_VFIQ: arm_cpu_update_vfiq(cpu); break; + case ARM_CPU_VINMI: + arm_cpu_update_vinmi(cpu); + break; case ARM_CPU_IRQ: case ARM_CPU_FIQ: + case ARM_CPU_NMI: if (level) { cpu_interrupt(cs, mask[irq]); } else { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) #else /* Our inbound IRQ and FIQ lines */ if (kvm_enabled()) { - /* VIRQ and VFIQ are unused with KVM but we add them to maintain - * the same interface as non-KVM CPUs. + /* + * VIRQ, VFIQ, NMI, VINMI are unused with KVM but we add + * them to maintain the same interface as non-KVM CPUs. */ - qdev_init_gpio_in(DEVICE(cpu), arm_cpu_kvm_set_irq, 4); + qdev_init_gpio_in(DEVICE(cpu), arm_cpu_kvm_set_irq, 6); } else { - qdev_init_gpio_in(DEVICE(cpu), arm_cpu_set_irq, 4); + qdev_init_gpio_in(DEVICE(cpu), arm_cpu_set_irq, 6); } qdev_init_gpio_out(DEVICE(cpu), cpu->gt_timer_outputs, diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void do_hcr_write(CPUARMState *env, uint64_t value, uint64_t valid_mask) * and the state of the input lines from the GIC. (This requires * that we have the BQL, which is done by marking the * reginfo structs as ARM_CP_IO.) - * Note that if a write to HCR pends a VIRQ or VFIQ it is never - * possible for it to be taken immediately, because VIRQ and - * VFIQ are masked unless running at EL0 or EL1, and HCR - * can only be written at EL2. + * Note that if a write to HCR pends a VIRQ or VFIQ or VINMI or + * VFNMI, it is never possible for it to be taken immediately + * because VIRQ, VFIQ, VINMI and VFNMI are masked unless running + * at EL0 or EL1, and HCR can only be written at EL2. */ g_assert(bql_locked()); arm_cpu_update_virq(cpu); arm_cpu_update_vfiq(cpu); arm_cpu_update_vserr(cpu); + if (cpu_isar_feature(aa64_nmi, cpu)) { + arm_cpu_update_vinmi(cpu); + arm_cpu_update_vfnmi(cpu); + } } static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) @@ -XXX,XX +XXX,XX @@ static void hcrx_write(CPUARMState *env, const ARMCPRegInfo *ri, /* Clear RES0 bits. */ env->cp15.hcrx_el2 = value & valid_mask; + + /* + * Updates to VINMI and VFNMI require us to update the status of + * virtual NMI, which are the logical OR of these bits + * and the state of the input lines from the GIC. (This requires + * that we have the BQL, which is done by marking the + * reginfo structs as ARM_CP_IO.) + * Note that if a write to HCRX pends a VINMI or VFNMI it is never + * possible for it to be taken immediately, because VINMI and + * VFNMI are masked unless running at EL0 or EL1, and HCRX + * can only be written at EL2. + */ + if (cpu_isar_feature(aa64_nmi, cpu)) { + g_assert(bql_locked()); + arm_cpu_update_vinmi(cpu); + arm_cpu_update_vfnmi(cpu); + } } static CPAccessResult access_hxen(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_hxen(CPUARMState *env, const ARMCPRegInfo *ri, static const ARMCPRegInfo hcrx_el2_reginfo = { .name = "HCRX_EL2", .state = ARM_CP_STATE_AA64, + .type = ARM_CP_IO, .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 2, .access = PL2_RW, .writefn = hcrx_write, .accessfn = access_hxen, .nv2_redirect_offset = 0xa0, @@ -XXX,XX +XXX,XX @@ void arm_log_exception(CPUState *cs) [EXCP_DIVBYZERO] = "v7M DIVBYZERO UsageFault", [EXCP_VSERR] = "Virtual SERR", [EXCP_GPC] = "Granule Protection Check", + [EXCP_NMI] = "NMI", + [EXCP_VINMI] = "Virtual IRQ NMI", + [EXCP_VFNMI] = "Virtual FIQ NMI", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> According to Arm GIC section 4.6.3 Interrupt superpriority, the interrupt with superpriority is always IRQ, never FIQ, so handle NMI same as IRQ in arm_phys_excp_target_el(). Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-8-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 1 + 1 file changed, 1 insertion(+) 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 arm_phys_excp_target_el(CPUState *cs, uint32_t excp_idx, hcr_el2 = arm_hcr_el2_eff(env); switch (excp_idx) { case EXCP_IRQ: + case EXCP_NMI: scr = ((env->cp15.scr_el3 & SCR_IRQ) == SCR_IRQ); hcr = hcr_el2 & HCR_IMO; break; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Add IS and FS bit in ISR_EL1 and handle the read. With CPU_INTERRUPT_NMI or CPU_INTERRUPT_VINMI, both CPSR_I and ISR_IS must be set. With CPU_INTERRUPT_VFNMI, both CPSR_F and ISR_FS must be set. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-9-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/helper.c | 13 +++++++++++++ 2 files changed, 15 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define CPSR_N (1U << 31) #define CPSR_NZCV (CPSR_N | CPSR_Z | CPSR_C | CPSR_V) #define CPSR_AIF (CPSR_A | CPSR_I | CPSR_F) +#define ISR_FS (1U << 9) +#define ISR_IS (1U << 10) #define CPSR_IT (CPSR_IT_0_1 | CPSR_IT_2_7) #define CACHED_CPSR_BITS (CPSR_T | CPSR_AIF | CPSR_GE | CPSR_IT | CPSR_Q \ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t isr_read(CPUARMState *env, const ARMCPRegInfo *ri) if (cs->interrupt_request & CPU_INTERRUPT_VIRQ) { ret |= CPSR_I; } + if (cs->interrupt_request & CPU_INTERRUPT_VINMI) { + ret |= ISR_IS; + ret |= CPSR_I; + } } else { if (cs->interrupt_request & CPU_INTERRUPT_HARD) { ret |= CPSR_I; } + + if (cs->interrupt_request & CPU_INTERRUPT_NMI) { + ret |= ISR_IS; + ret |= CPSR_I; + } } if (hcr_el2 & HCR_FMO) { if (cs->interrupt_request & CPU_INTERRUPT_VFIQ) { ret |= CPSR_F; } + if (cs->interrupt_request & CPU_INTERRUPT_VFNMI) { + ret |= ISR_FS; + ret |= CPSR_F; + } } else { if (cs->interrupt_request & CPU_INTERRUPT_FIQ) { ret |= CPSR_F; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Set or clear PSTATE.ALLINT on taking an exception to ELx according to the SCTLR_ELx.SPINTMASK bit. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-10-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) } } + if (cpu_isar_feature(aa64_nmi, cpu)) { + if (!(env->cp15.sctlr_el[new_el] & SCTLR_SPINTMASK)) { + new_mode |= PSTATE_ALLINT; + } else { + new_mode &= ~PSTATE_ALLINT; + } + } + pstate_write(env, PSTATE_DAIF | new_mode); env->aarch64 = true; aarch64_restore_sp(env, new_el); -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Augment the GICv3's QOM device interface by adding one new set of sysbus IRQ line, to signal NMI to each CPU. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-11-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/intc/arm_gic_common.h | 2 ++ include/hw/intc/arm_gicv3_common.h | 2 ++ hw/intc/arm_gicv3_common.c | 6 ++++++ 3 files changed, 10 insertions(+) diff --git a/include/hw/intc/arm_gic_common.h b/include/hw/intc/arm_gic_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gic_common.h +++ b/include/hw/intc/arm_gic_common.h @@ -XXX,XX +XXX,XX @@ struct GICState { qemu_irq parent_fiq[GIC_NCPU]; qemu_irq parent_virq[GIC_NCPU]; qemu_irq parent_vfiq[GIC_NCPU]; + qemu_irq parent_nmi[GIC_NCPU]; + qemu_irq parent_vnmi[GIC_NCPU]; qemu_irq maintenance_irq[GIC_NCPU]; /* GICD_CTLR; for a GIC with the security extensions the NS banked version diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { qemu_irq parent_fiq; qemu_irq parent_virq; qemu_irq parent_vfiq; + qemu_irq parent_nmi; + qemu_irq parent_vnmi; /* Redistributor */ uint32_t level; /* Current IRQ level */ diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ void gicv3_init_irqs_and_mmio(GICv3State *s, qemu_irq_handler handler, for (i = 0; i < s->num_cpu; i++) { sysbus_init_irq(sbd, &s->cpu[i].parent_vfiq); } + for (i = 0; i < s->num_cpu; i++) { + sysbus_init_irq(sbd, &s->cpu[i].parent_nmi); + } + for (i = 0; i < s->num_cpu; i++) { + sysbus_init_irq(sbd, &s->cpu[i].parent_vnmi); + } memory_region_init_io(&s->iomem_dist, OBJECT(s), ops, s, "gicv3_dist", 0x10000); -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Wire the new NMI and VINMI interrupt line from the GIC to each CPU if it is not GICv2. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240407081733.3231820-12-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) /* Wire the outputs from each CPU's generic timer and the GICv3 * maintenance interrupt signal to the appropriate GIC PPI inputs, - * and the GIC's IRQ/FIQ/VIRQ/VFIQ interrupt outputs to the CPU's inputs. + * and the GIC's IRQ/FIQ/VIRQ/VFIQ/NMI/VINMI interrupt outputs to the + * CPU's inputs. */ for (i = 0; i < smp_cpus; i++) { DeviceState *cpudev = DEVICE(qemu_get_cpu(i)); @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); sysbus_connect_irq(gicbusdev, i + 3 * smp_cpus, qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + + if (vms->gic_version != VIRT_GIC_VERSION_2) { + sysbus_connect_irq(gicbusdev, i + 4 * smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_NMI)); + sysbus_connect_irq(gicbusdev, i + 5 * smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VINMI)); + } } fdt_add_gic_node(vms); -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> According to Arm GIC section 4.6.3 Interrupt superpriority, the interrupt with superpriority is always IRQ, never FIQ, so the NMI exception trap entry behave like IRQ. And VINMI(vIRQ with Superpriority) can be raised from the GIC or come from the hcrx_el2.HCRX_VINMI bit, VFNMI(vFIQ with Superpriority) come from the hcrx_el2.HCRX_VFNMI bit. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-13-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) break; case EXCP_IRQ: case EXCP_VIRQ: + case EXCP_NMI: + case EXCP_VINMI: addr += 0x80; break; case EXCP_FIQ: case EXCP_VFIQ: + case EXCP_VFNMI: addr += 0x100; break; case EXCP_VSERR: -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Add a property has-nmi to the GICv3 device, and use this to set the NMI bit in the GICD_TYPER register. This isn't visible to guests yet because the property defaults to false and we won't set it in the board code until we've landed all of the changes needed to implement FEAT_GICV3_NMI. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-14-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 1 + include/hw/intc/arm_gicv3_common.h | 1 + hw/intc/arm_gicv3_common.c | 1 + hw/intc/arm_gicv3_dist.c | 2 ++ 4 files changed, 5 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ #define GICD_CTLR_E1NWF (1U << 7) #define GICD_CTLR_RWP (1U << 31) +#define GICD_TYPER_NMI_SHIFT 9 #define GICD_TYPER_LPIS_SHIFT 17 /* 16 bits EventId */ diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3State { uint32_t num_irq; uint32_t revision; bool lpi_enable; + bool nmi_support; bool security_extn; bool force_8bit_prio; bool irq_reset_nonsecure; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static Property arm_gicv3_common_properties[] = { DEFINE_PROP_UINT32("num-irq", GICv3State, num_irq, 32), DEFINE_PROP_UINT32("revision", GICv3State, revision, 3), DEFINE_PROP_BOOL("has-lpi", GICv3State, lpi_enable, 0), + DEFINE_PROP_BOOL("has-nmi", GICv3State, nmi_support, 0), DEFINE_PROP_BOOL("has-security-extensions", GICv3State, security_extn, 0), /* * Compatibility property: force 8 bits of physical priority, even diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, * by GICD_TYPER.IDbits) * MBIS == 0 (message-based SPIs not supported) * SecurityExtn == 1 if security extns supported + * NMI = 1 if Non-maskable interrupt property is supported * CPUNumber == 0 since for us ARE is always 1 * ITLinesNumber == (((max SPI IntID + 1) / 32) - 1) */ @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, bool dvis = s->revision >= 4; *data = (1 << 25) | (1 << 24) | (dvis << 18) | (sec_extn << 10) | + (s->nmi_support << GICD_TYPER_NMI_SHIFT) | (s->lpi_enable << GICD_TYPER_LPIS_SHIFT) | (0xf << 19) | itlinesnumber; return true; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> So far, there is no FEAT_GICv3_NMI support in the in-kernel GIC, so make it an error to try to set has-nmi=true for the KVM GICv3. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Message-id: 20240407081733.3231820-15-ruanjinjie@huawei.com Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) return; } + if (s->nmi_support) { + error_setg(errp, "NMI is not supported with the in-kernel GIC"); + return; + } + gicv3_init_irqs_and_mmio(s, kvm_arm_gicv3_set_irq, NULL); for (i = 0; i < s->num_cpu; i++) { -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> A SPI, PPI or SGI interrupt can have non-maskable property. So maintain non-maskable property in PendingIrq and GICR/GICD. Since add new device state, it also needs to be migrated, so also save NMI info in vmstate_gicv3_cpu and vmstate_gicv3. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Acked-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-16-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/intc/arm_gicv3_common.h | 4 ++++ hw/intc/arm_gicv3_common.c | 38 ++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ typedef struct { int irq; uint8_t prio; int grp; + bool nmi; } PendingIrq; struct GICv3CPUState { @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { uint32_t gicr_ienabler0; uint32_t gicr_ipendr0; uint32_t gicr_iactiver0; + uint32_t gicr_inmir0; uint32_t edge_trigger; /* ICFGR0 and ICFGR1 even bits */ uint32_t gicr_igrpmodr0; uint32_t gicr_nsacr; @@ -XXX,XX +XXX,XX @@ struct GICv3State { GIC_DECLARE_BITMAP(active); /* GICD_ISACTIVER */ GIC_DECLARE_BITMAP(level); /* Current level */ GIC_DECLARE_BITMAP(edge_trigger); /* GICD_ICFGR even bits */ + GIC_DECLARE_BITMAP(nmi); /* GICD_INMIR */ uint8_t gicd_ipriority[GICV3_MAXIRQ]; uint64_t gicd_irouter[GICV3_MAXIRQ]; /* Cached information: pointer to the cpu i/f for the CPUs specified @@ -XXX,XX +XXX,XX @@ GICV3_BITMAP_ACCESSORS(pending) GICV3_BITMAP_ACCESSORS(active) GICV3_BITMAP_ACCESSORS(level) GICV3_BITMAP_ACCESSORS(edge_trigger) +GICV3_BITMAP_ACCESSORS(nmi) #define TYPE_ARM_GICV3_COMMON "arm-gicv3-common" typedef struct ARMGICv3CommonClass ARMGICv3CommonClass; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_gicv3_gicv4 = { } }; +static bool gicv3_cpu_nmi_needed(void *opaque) +{ + GICv3CPUState *cs = opaque; + + return cs->gic->nmi_support; +} + +static const VMStateDescription vmstate_gicv3_cpu_nmi = { + .name = "arm_gicv3_cpu/nmi", + .version_id = 1, + .minimum_version_id = 1, + .needed = gicv3_cpu_nmi_needed, + .fields = (const VMStateField[]) { + VMSTATE_UINT32(gicr_inmir0, GICv3CPUState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_gicv3_cpu = { .name = "arm_gicv3_cpu", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3_cpu = { &vmstate_gicv3_cpu_virt, &vmstate_gicv3_cpu_sre_el1, &vmstate_gicv3_gicv4, + &vmstate_gicv3_cpu_nmi, NULL } }; @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_gicv3_gicd_no_migration_shift_bug = { } }; +static bool gicv3_nmi_needed(void *opaque) +{ + GICv3State *cs = opaque; + + return cs->nmi_support; +} + +const VMStateDescription vmstate_gicv3_gicd_nmi = { + .name = "arm_gicv3/gicd_nmi", + .version_id = 1, + .minimum_version_id = 1, + .needed = gicv3_nmi_needed, + .fields = (const VMStateField[]) { + VMSTATE_UINT32_ARRAY(nmi, GICv3State, GICV3_BMP_SIZE), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_gicv3 = { .name = "arm_gicv3", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3 = { }, .subsections = (const VMStateDescription * const []) { &vmstate_gicv3_gicd_no_migration_shift_bug, + &vmstate_gicv3_gicd_nmi, NULL } }; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Add GICR_INMIR0 register and support access GICR_INMIR0. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-17-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 1 + hw/intc/arm_gicv3_redist.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ #define GICR_ICFGR1 (GICR_SGI_OFFSET + 0x0C04) #define GICR_IGRPMODR0 (GICR_SGI_OFFSET + 0x0D00) #define GICR_NSACR (GICR_SGI_OFFSET + 0x0E00) +#define GICR_INMIR0 (GICR_SGI_OFFSET + 0x0F80) /* VLPI redistributor registers, offsets from VLPI_base */ #define GICR_VPROPBASER (GICR_VLPI_OFFSET + 0x70) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static int gicr_ns_access(GICv3CPUState *cs, int irq) return extract32(cs->gicr_nsacr, irq * 2, 2); } +static void gicr_write_bitmap_reg(GICv3CPUState *cs, MemTxAttrs attrs, + uint32_t *reg, uint32_t val) +{ + /* Helper routine to implement writing to a "set" register */ + val &= mask_group(cs, attrs); + *reg = val; + gicv3_redist_update(cs); +} + static void gicr_write_set_bitmap_reg(GICv3CPUState *cs, MemTxAttrs attrs, uint32_t *reg, uint32_t val) { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_readl(GICv3CPUState *cs, hwaddr offset, *data = value; return MEMTX_OK; } + case GICR_INMIR0: + *data = cs->gic->nmi_support ? + gicr_read_bitmap_reg(cs, attrs, cs->gicr_inmir0) : 0; + return MEMTX_OK; case GICR_ICFGR0: case GICR_ICFGR1: { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, gicv3_redist_update(cs); return MEMTX_OK; } + case GICR_INMIR0: + if (cs->gic->nmi_support) { + gicr_write_bitmap_reg(cs, attrs, &cs->gicr_inmir0, value); + } + return MEMTX_OK; + case GICR_ICFGR0: /* Register is all RAZ/WI or RAO/WI bits */ return MEMTX_OK; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Add GICD_INMIR, GICD_INMIRnE register and support access GICD_INMIR0. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-18-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 2 ++ hw/intc/arm_gicv3_dist.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ #define GICD_SGIR 0x0F00 #define GICD_CPENDSGIR 0x0F10 #define GICD_SPENDSGIR 0x0F20 +#define GICD_INMIR 0x0F80 +#define GICD_INMIRnE 0x3B00 #define GICD_IROUTER 0x6000 #define GICD_IDREGS 0xFFD0 diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static int gicd_ns_access(GICv3State *s, int irq) return extract32(s->gicd_nsacr[irq / 16], (irq % 16) * 2, 2); } +static void gicd_write_bitmap_reg(GICv3State *s, MemTxAttrs attrs, + uint32_t *bmp, maskfn *maskfn, + int offset, uint32_t val) +{ + /* + * Helper routine to implement writing to a "set" register + * (GICD_INMIR, etc). + * Semantics implemented here: + * RAZ/WI for SGIs, PPIs, unimplemented IRQs + * Bits corresponding to Group 0 or Secure Group 1 interrupts RAZ/WI. + * offset should be the offset in bytes of the register from the start + * of its group. + */ + int irq = offset * 8; + + if (irq < GIC_INTERNAL || irq >= s->num_irq) { + return; + } + val &= mask_group_and_nsacr(s, attrs, maskfn, irq); + *gic_bmp_ptr32(bmp, irq) = val; + gicv3_update(s, irq, 32); +} + static void gicd_write_set_bitmap_reg(GICv3State *s, MemTxAttrs attrs, uint32_t *bmp, maskfn *maskfn, @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, /* RAZ/WI since affinity routing is always enabled */ *data = 0; return true; + case GICD_INMIR ... GICD_INMIR + 0x7f: + *data = (!s->nmi_support) ? 0 : + gicd_read_bitmap_reg(s, attrs, s->nmi, NULL, + offset - GICD_INMIR); + return true; case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: { uint64_t r; @@ -XXX,XX +XXX,XX @@ static bool gicd_writel(GICv3State *s, hwaddr offset, case GICD_SPENDSGIR ... GICD_SPENDSGIR + 0xf: /* RAZ/WI since affinity routing is always enabled */ return true; + case GICD_INMIR ... GICD_INMIR + 0x7f: + if (s->nmi_support) { + gicd_write_bitmap_reg(s, attrs, s->nmi, NULL, + offset - GICD_INMIR, value); + } + return true; case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: { uint64_t r; -- 2.34.1 Add the NMIAR CPU interface registers which deal with acknowledging NMI. When introduce NMI interrupt, there are some updates to the semantics for the register ICC_IAR1_EL1 and ICC_HPPIR1_EL1. For ICC_IAR1_EL1 register, it should return 1022 if the intid has non-maskable property. And for ICC_NMIAR1_EL1 register, it should return 1023 if the intid do not have non-maskable property. Howerever, these are not necessary for ICC_HPPIR1_EL1 register. And the APR and RPR has NMI bits which should be handled correctly. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> [PMM: Separate out whether cpuif supports NMI from whether the GIC proper (IRI) supports NMI] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-19-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 5 + include/hw/intc/arm_gicv3_common.h | 7 ++ hw/intc/arm_gicv3_cpuif.c | 147 ++++++++++++++++++++++++++++- hw/intc/trace-events | 1 + 4 files changed, 155 insertions(+), 5 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GICR_VPENDBASER, VALID, 63, 1) #define ICC_CTLR_EL3_A3V (1U << 15) #define ICC_CTLR_EL3_NDS (1U << 17) +#define ICC_AP1R_EL1_NMI (1ULL << 63) +#define ICC_RPR_EL1_NSNMI (1ULL << 62) +#define ICC_RPR_EL1_NMI (1ULL << 63) + #define ICH_VMCR_EL2_VENG0_SHIFT 0 #define ICH_VMCR_EL2_VENG0 (1U << ICH_VMCR_EL2_VENG0_SHIFT) #define ICH_VMCR_EL2_VENG1_SHIFT 1 @@ -XXX,XX +XXX,XX @@ FIELD(VTE, RDBASE, 42, RDBASE_PROCNUM_LENGTH) /* Special interrupt IDs */ #define INTID_SECURE 1020 #define INTID_NONSECURE 1021 +#define INTID_NMI 1022 #define INTID_SPURIOUS 1023 /* Functions internal to the emulated GICv3 */ diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { /* This is temporary working state, to avoid a malloc in gicv3_update() */ bool seenbetter; + + /* + * Whether the CPU interface has NMI support (FEAT_GICv3_NMI). The + * CPU interface may support NMIs even when the GIC proper (what the + * spec calls the IRI; the redistributors and distributor) does not. + */ + bool nmi_support; }; /* diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ #include "hw/irq.h" #include "cpu.h" #include "target/arm/cpregs.h" +#include "target/arm/cpu-features.h" #include "sysemu/tcg.h" #include "sysemu/qtest.h" @@ -XXX,XX +XXX,XX @@ static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) return intid; } +static uint64_t icv_nmiar1_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* todo */ + uint64_t intid = INTID_SPURIOUS; + return intid; +} + static uint32_t icc_fullprio_mask(GICv3CPUState *cs) { /* @@ -XXX,XX +XXX,XX @@ static int icc_highest_active_prio(GICv3CPUState *cs) */ int i; + if (cs->nmi_support) { + /* + * If an NMI is active this takes precedence over anything else + * for priority purposes; the NMI bit is only in the AP1R0 bit. + * We return here the effective priority of the NMI, which is + * either 0x0 or 0x80. Callers will need to check NMI again for + * purposes of either setting the RPR register bits or for + * prioritization of NMI vs non-NMI. + */ + if (cs->icc_apr[GICV3_G1][0] & ICC_AP1R_EL1_NMI) { + return 0; + } + if (cs->icc_apr[GICV3_G1NS][0] & ICC_AP1R_EL1_NMI) { + return (cs->gic->gicd_ctlr & GICD_CTLR_DS) ? 0 : 0x80; + } + } + for (i = 0; i < icc_num_aprs(cs); i++) { uint32_t apr = cs->icc_apr[GICV3_G0][i] | cs->icc_apr[GICV3_G1][i] | cs->icc_apr[GICV3_G1NS][i]; @@ -XXX,XX +XXX,XX @@ static bool icc_hppi_can_preempt(GICv3CPUState *cs) */ int rprio; uint32_t mask; + ARMCPU *cpu = ARM_CPU(cs->cpu); + CPUARMState *env = &cpu->env; if (icc_no_enabled_hppi(cs)) { return false; } - if (cs->hppi.prio >= cs->icc_pmr_el1) { + if (cs->hppi.nmi) { + if (!(cs->gic->gicd_ctlr & GICD_CTLR_DS) && + cs->hppi.grp == GICV3_G1NS) { + if (cs->icc_pmr_el1 < 0x80) { + return false; + } + if (arm_is_secure(env) && cs->icc_pmr_el1 == 0x80) { + return false; + } + } + } else if (cs->hppi.prio >= cs->icc_pmr_el1) { /* Priority mask masks this interrupt */ return false; } @@ -XXX,XX +XXX,XX @@ static bool icc_hppi_can_preempt(GICv3CPUState *cs) return true; } + if (cs->hppi.nmi && (cs->hppi.prio & mask) == (rprio & mask)) { + if (!(cs->icc_apr[cs->hppi.grp][0] & ICC_AP1R_EL1_NMI)) { + return true; + } + } + return false; } @@ -XXX,XX +XXX,XX @@ static void icc_activate_irq(GICv3CPUState *cs, int irq) int aprbit = prio >> (8 - cs->prebits); int regno = aprbit / 32; int regbit = aprbit % 32; + bool nmi = cs->hppi.nmi; - cs->icc_apr[cs->hppi.grp][regno] |= (1 << regbit); + if (nmi) { + cs->icc_apr[cs->hppi.grp][regno] |= ICC_AP1R_EL1_NMI; + } else { + cs->icc_apr[cs->hppi.grp][regno] |= (1 << regbit); + } if (irq < GIC_INTERNAL) { cs->gicr_iactiver0 = deposit32(cs->gicr_iactiver0, irq, 1, 1); @@ -XXX,XX +XXX,XX @@ static uint64_t icc_iar0_read(CPUARMState *env, const ARMCPRegInfo *ri) static uint64_t icc_iar1_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); + int el = arm_current_el(env); uint64_t intid; if (icv_access(env, HCR_IMO)) { @@ -XXX,XX +XXX,XX @@ static uint64_t icc_iar1_read(CPUARMState *env, const ARMCPRegInfo *ri) } if (!gicv3_intid_is_special(intid)) { - icc_activate_irq(cs, intid); + if (cs->hppi.nmi && env->cp15.sctlr_el[el] & SCTLR_NMI) { + intid = INTID_NMI; + } else { + icc_activate_irq(cs, intid); + } } trace_gicv3_icc_iar1_read(gicv3_redist_affid(cs), intid); return intid; } +static uint64_t icc_nmiar1_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + GICv3CPUState *cs = icc_cs_from_env(env); + uint64_t intid; + + if (icv_access(env, HCR_IMO)) { + return icv_nmiar1_read(env, ri); + } + + if (!icc_hppi_can_preempt(cs)) { + intid = INTID_SPURIOUS; + } else { + intid = icc_hppir1_value(cs, env); + } + + if (!gicv3_intid_is_special(intid)) { + if (!cs->hppi.nmi) { + intid = INTID_SPURIOUS; + } else { + icc_activate_irq(cs, intid); + } + } + + trace_gicv3_icc_nmiar1_read(gicv3_redist_affid(cs), intid); + return intid; +} + static void icc_drop_prio(GICv3CPUState *cs, int grp) { /* Drop the priority of the currently active interrupt in @@ -XXX,XX +XXX,XX @@ static void icc_drop_prio(GICv3CPUState *cs, int grp) if (!*papr) { continue; } + + if (i == 0 && cs->nmi_support && (*papr & ICC_AP1R_EL1_NMI)) { + *papr &= (~ICC_AP1R_EL1_NMI); + break; + } + /* Clear the lowest set bit */ *papr &= *papr - 1; break; @@ -XXX,XX +XXX,XX @@ static int icc_highest_active_group(GICv3CPUState *cs) */ int i; + if (cs->nmi_support) { + if (cs->icc_apr[GICV3_G1][0] & ICC_AP1R_EL1_NMI) { + return GICV3_G1; + } + if (cs->icc_apr[GICV3_G1NS][0] & ICC_AP1R_EL1_NMI) { + return GICV3_G1NS; + } + } + for (i = 0; i < ARRAY_SIZE(cs->icc_apr[0]); i++) { int g0ctz = ctz32(cs->icc_apr[GICV3_G0][i]); int g1ctz = ctz32(cs->icc_apr[GICV3_G1][i]); @@ -XXX,XX +XXX,XX @@ static void icc_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } - cs->icc_apr[grp][regno] = value & 0xFFFFFFFFU; + if (cs->nmi_support) { + cs->icc_apr[grp][regno] = value & (0xFFFFFFFFU | ICC_AP1R_EL1_NMI); + } else { + cs->icc_apr[grp][regno] = value & 0xFFFFFFFFU; + } gicv3_cpuif_update(cs); } @@ -XXX,XX +XXX,XX @@ static void icc_dir_write(CPUARMState *env, const ARMCPRegInfo *ri, static uint64_t icc_rpr_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); - int prio; + uint64_t prio; if (icv_access(env, HCR_FMO | HCR_IMO)) { return icv_rpr_read(env, ri); @@ -XXX,XX +XXX,XX @@ static uint64_t icc_rpr_read(CPUARMState *env, const ARMCPRegInfo *ri) } } + if (cs->nmi_support) { + /* NMI info is reported in the high bits of RPR */ + if (arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env)) { + if (cs->icc_apr[GICV3_G1NS][0] & ICC_AP1R_EL1_NMI) { + prio |= ICC_RPR_EL1_NMI; + } + } else { + if (cs->icc_apr[GICV3_G1NS][0] & ICC_AP1R_EL1_NMI) { + prio |= ICC_RPR_EL1_NSNMI; + } + if (cs->icc_apr[GICV3_G1][0] & ICC_AP1R_EL1_NMI) { + prio |= ICC_RPR_EL1_NMI; + } + } + } + trace_gicv3_icc_rpr_read(gicv3_redist_affid(cs), prio); return prio; } @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo gicv3_cpuif_icc_apxr23_reginfo[] = { }, }; +static const ARMCPRegInfo gicv3_cpuif_gicv3_nmi_reginfo[] = { + { .name = "ICC_NMIAR1_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 9, .opc2 = 5, + .type = ARM_CP_IO | ARM_CP_NO_RAW, + .access = PL1_R, .accessfn = gicv3_irq_access, + .readfn = icc_nmiar1_read, + }, +}; + static uint64_t ich_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); @@ -XXX,XX +XXX,XX @@ void gicv3_init_cpuif(GICv3State *s) */ define_arm_cp_regs(cpu, gicv3_cpuif_reginfo); + /* + * If the CPU implements FEAT_NMI and FEAT_GICv3 it must also + * implement FEAT_GICv3_NMI, which is the CPU interface part + * of NMI support. This is distinct from whether the GIC proper + * (redistributors and distributor) have NMI support. In QEMU + * that is a property of the GIC device in s->nmi_support; + * cs->nmi_support indicates the CPU interface's support. + */ + if (cpu_isar_feature(aa64_nmi, cpu)) { + cs->nmi_support = true; + define_arm_cp_regs(cpu, gicv3_cpuif_gicv3_nmi_reginfo); + } + /* * The CPU implementation specifies the number of supported * bits of physical priority. For backwards compatibility diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_cpuif_set_irqs(uint32_t cpuid, int fiqlevel, int irqlevel) "GICv3 CPU i/f gicv3_icc_generate_sgi(uint32_t cpuid, int irq, int irm, uint32_t aff, uint32_t targetlist) "GICv3 CPU i/f 0x%x generating SGI %d IRM %d target affinity 0x%xxx targetlist 0x%x" gicv3_icc_iar0_read(uint32_t cpu, uint64_t val) "GICv3 ICC_IAR0 read cpu 0x%x value 0x%" PRIx64 gicv3_icc_iar1_read(uint32_t cpu, uint64_t val) "GICv3 ICC_IAR1 read cpu 0x%x value 0x%" PRIx64 +gicv3_icc_nmiar1_read(uint32_t cpu, uint64_t val) "GICv3 ICC_NMIAR1 read cpu 0x%x value 0x%" PRIx64 gicv3_icc_eoir_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICC_EOIR%d write cpu 0x%x value 0x%" PRIx64 gicv3_icc_hppir0_read(uint32_t cpu, uint64_t val) "GICv3 ICC_HPPIR0 read cpu 0x%x value 0x%" PRIx64 gicv3_icc_hppir1_read(uint32_t cpu, uint64_t val) "GICv3 ICC_HPPIR1 read cpu 0x%x value 0x%" PRIx64 -- 2.34.1 Implement icv_nmiar1_read() for icc_nmiar1_read(), so add definition for ICH_LR_EL2.NMI and ICH_AP1R_EL2.NMI bit. If FEAT_GICv3_NMI is supported, ich_ap_write() should consider ICV_AP1R_EL1.NMI bit. In icv_activate_irq() and icv_eoir_write(), the ICV_AP1R_EL1.NMI bit should be set or clear according to the Non-maskable property. And the RPR priority should also update the NMI bit according to the APR priority NMI bit. By the way, add gicv3_icv_nmiar1_read trace event. If the hpp irq is a NMI, the icv iar read should return 1022 and trap for NMI again Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> [PMM: use cs->nmi_support instead of cs->gic->nmi_support] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-20-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 4 ++ hw/intc/arm_gicv3_cpuif.c | 105 +++++++++++++++++++++++++++++++++----- hw/intc/trace-events | 1 + 3 files changed, 98 insertions(+), 12 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GICR_VPENDBASER, VALID, 63, 1) #define ICH_LR_EL2_PRIORITY_SHIFT 48 #define ICH_LR_EL2_PRIORITY_LENGTH 8 #define ICH_LR_EL2_PRIORITY_MASK (0xffULL << ICH_LR_EL2_PRIORITY_SHIFT) +#define ICH_LR_EL2_NMI (1ULL << 59) #define ICH_LR_EL2_GROUP (1ULL << 60) #define ICH_LR_EL2_HW (1ULL << 61) #define ICH_LR_EL2_STATE_SHIFT 62 @@ -XXX,XX +XXX,XX @@ FIELD(GICR_VPENDBASER, VALID, 63, 1) #define ICH_VTR_EL2_PREBITS_SHIFT 26 #define ICH_VTR_EL2_PRIBITS_SHIFT 29 +#define ICV_AP1R_EL1_NMI (1ULL << 63) +#define ICV_RPR_EL1_NMI (1ULL << 63) + /* ITS Registers */ FIELD(GITS_BASER, SIZE, 0, 8) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static int ich_highest_active_virt_prio(GICv3CPUState *cs) int i; int aprmax = ich_num_aprs(cs); + if (cs->ich_apr[GICV3_G1NS][0] & ICV_AP1R_EL1_NMI) { + return 0x0; + } + for (i = 0; i < aprmax; i++) { uint32_t apr = cs->ich_apr[GICV3_G0][i] | cs->ich_apr[GICV3_G1NS][i]; @@ -XXX,XX +XXX,XX @@ static int hppvi_index(GICv3CPUState *cs) * correct behaviour. */ int prio = 0xff; + bool nmi = false; if (!(cs->ich_vmcr_el2 & (ICH_VMCR_EL2_VENG0 | ICH_VMCR_EL2_VENG1))) { /* Both groups disabled, definitely nothing to do */ @@ -XXX,XX +XXX,XX @@ static int hppvi_index(GICv3CPUState *cs) for (i = 0; i < cs->num_list_regs; i++) { uint64_t lr = cs->ich_lr_el2[i]; + bool thisnmi; int thisprio; if (ich_lr_state(lr) != ICH_LR_EL2_STATE_PENDING) { @@ -XXX,XX +XXX,XX @@ static int hppvi_index(GICv3CPUState *cs) } } + thisnmi = lr & ICH_LR_EL2_NMI; thisprio = ich_lr_prio(lr); - if (thisprio < prio) { + if ((thisprio < prio) || ((thisprio == prio) && (thisnmi & (!nmi)))) { prio = thisprio; + nmi = thisnmi; idx = i; } } @@ -XXX,XX +XXX,XX @@ static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) * equivalent of these checks. */ int grp; + bool is_nmi; uint32_t mask, prio, rprio, vpmr; if (!(cs->ich_hcr_el2 & ICH_HCR_EL2_EN)) { @@ -XXX,XX +XXX,XX @@ static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) */ prio = ich_lr_prio(lr); + is_nmi = lr & ICH_LR_EL2_NMI; vpmr = extract64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VPMR_SHIFT, ICH_VMCR_EL2_VPMR_LENGTH); - if (prio >= vpmr) { + if (!is_nmi && prio >= vpmr) { /* Priority mask masks this interrupt */ return false; } @@ -XXX,XX +XXX,XX @@ static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) return true; } + if ((prio & mask) == (rprio & mask) && is_nmi && + !(cs->ich_apr[GICV3_G1NS][0] & ICV_AP1R_EL1_NMI)) { + return true; + } + return false; } @@ -XXX,XX +XXX,XX @@ static void icv_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_icv_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); - cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; + if (cs->nmi_support) { + cs->ich_apr[grp][regno] = value & (0xFFFFFFFFU | ICV_AP1R_EL1_NMI); + } else { + cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; + } gicv3_cpuif_virt_irq_fiq_update(cs); return; @@ -XXX,XX +XXX,XX @@ static void icv_ctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, static uint64_t icv_rpr_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); - int prio = ich_highest_active_virt_prio(cs); + uint64_t prio = ich_highest_active_virt_prio(cs); + + if (cs->ich_apr[GICV3_G1NS][0] & ICV_AP1R_EL1_NMI) { + prio |= ICV_RPR_EL1_NMI; + } trace_gicv3_icv_rpr_read(gicv3_redist_affid(cs), prio); return prio; @@ -XXX,XX +XXX,XX @@ static void icv_activate_irq(GICv3CPUState *cs, int idx, int grp) */ uint32_t mask = icv_gprio_mask(cs, grp); int prio = ich_lr_prio(cs->ich_lr_el2[idx]) & mask; + bool nmi = cs->ich_lr_el2[idx] & ICH_LR_EL2_NMI; int aprbit = prio >> (8 - cs->vprebits); int regno = aprbit / 32; int regbit = aprbit % 32; cs->ich_lr_el2[idx] &= ~ICH_LR_EL2_STATE_PENDING_BIT; cs->ich_lr_el2[idx] |= ICH_LR_EL2_STATE_ACTIVE_BIT; - cs->ich_apr[grp][regno] |= (1 << regbit); + + if (nmi) { + cs->ich_apr[grp][regno] |= ICV_AP1R_EL1_NMI; + } else { + cs->ich_apr[grp][regno] |= (1 << regbit); + } } static void icv_activate_vlpi(GICv3CPUState *cs) @@ -XXX,XX +XXX,XX @@ static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) int grp = ri->crm == 8 ? GICV3_G0 : GICV3_G1NS; int idx = hppvi_index(cs); uint64_t intid = INTID_SPURIOUS; + int el = arm_current_el(env); if (idx == HPPVI_INDEX_VLPI) { if (cs->hppvlpi.grp == grp && icv_hppvlpi_can_preempt(cs)) { @@ -XXX,XX +XXX,XX @@ static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) } else if (idx >= 0) { uint64_t lr = cs->ich_lr_el2[idx]; int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; + bool nmi = env->cp15.sctlr_el[el] & SCTLR_NMI && lr & ICH_LR_EL2_NMI; if (thisgrp == grp && icv_hppi_can_preempt(cs, lr)) { intid = ich_lr_vintid(lr); if (!gicv3_intid_is_special(intid)) { - icv_activate_irq(cs, idx, grp); + if (!nmi) { + icv_activate_irq(cs, idx, grp); + } else { + intid = INTID_NMI; + } } else { /* Interrupt goes from Pending to Invalid */ cs->ich_lr_el2[idx] &= ~ICH_LR_EL2_STATE_PENDING_BIT; @@ -XXX,XX +XXX,XX @@ static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) static uint64_t icv_nmiar1_read(CPUARMState *env, const ARMCPRegInfo *ri) { - /* todo */ + GICv3CPUState *cs = icc_cs_from_env(env); + int idx = hppvi_index(cs); uint64_t intid = INTID_SPURIOUS; + + if (idx >= 0 && idx != HPPVI_INDEX_VLPI) { + uint64_t lr = cs->ich_lr_el2[idx]; + int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; + + if ((thisgrp == GICV3_G1NS) && icv_hppi_can_preempt(cs, lr)) { + intid = ich_lr_vintid(lr); + if (!gicv3_intid_is_special(intid)) { + if (lr & ICH_LR_EL2_NMI) { + icv_activate_irq(cs, idx, GICV3_G1NS); + } else { + intid = INTID_SPURIOUS; + } + } else { + /* Interrupt goes from Pending to Invalid */ + cs->ich_lr_el2[idx] &= ~ICH_LR_EL2_STATE_PENDING_BIT; + /* + * We will now return the (bogus) ID from the list register, + * as per the pseudocode. + */ + } + } + } + + trace_gicv3_icv_nmiar1_read(gicv3_redist_affid(cs), intid); + + gicv3_cpuif_virt_update(cs); + return intid; } @@ -XXX,XX +XXX,XX @@ static void icv_increment_eoicount(GICv3CPUState *cs) ICH_HCR_EL2_EOICOUNT_LENGTH, eoicount + 1); } -static int icv_drop_prio(GICv3CPUState *cs) +static int icv_drop_prio(GICv3CPUState *cs, bool *nmi) { /* Drop the priority of the currently active virtual interrupt * (favouring group 0 if there is a set active bit at @@ -XXX,XX +XXX,XX @@ static int icv_drop_prio(GICv3CPUState *cs) continue; } + if (i == 0 && cs->nmi_support && (*papr1 & ICV_AP1R_EL1_NMI)) { + *papr1 &= (~ICV_AP1R_EL1_NMI); + *nmi = true; + return 0xff; + } + /* We can't just use the bit-twiddling hack icc_drop_prio() does * because we need to return the bit number we cleared so * it can be compared against the list register's priority field. @@ -XXX,XX +XXX,XX @@ static void icv_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, int irq = value & 0xffffff; int grp = ri->crm == 8 ? GICV3_G0 : GICV3_G1NS; int idx, dropprio; + bool nmi = false; trace_gicv3_icv_eoir_write(ri->crm == 8 ? 0 : 1, gicv3_redist_affid(cs), value); @@ -XXX,XX +XXX,XX @@ static void icv_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, * error checks" (because that lets us avoid scanning the AP * registers twice). */ - dropprio = icv_drop_prio(cs); - if (dropprio == 0xff) { + dropprio = icv_drop_prio(cs, &nmi); + if (dropprio == 0xff && !nmi) { /* No active interrupt. It is CONSTRAINED UNPREDICTABLE * whether the list registers are checked in this * situation; we choose not to. @@ -XXX,XX +XXX,XX @@ static void icv_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t lr = cs->ich_lr_el2[idx]; int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; int lr_gprio = ich_lr_prio(lr) & icv_gprio_mask(cs, grp); + bool thisnmi = lr & ICH_LR_EL2_NMI; - if (thisgrp == grp && lr_gprio == dropprio) { + if (thisgrp == grp && (lr_gprio == dropprio || (thisnmi & nmi))) { if (!icv_eoi_split(env, cs) || irq >= GICV3_LPI_INTID_START) { /* * Priority drop and deactivate not split: deactivate irq now. @@ -XXX,XX +XXX,XX @@ static void ich_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_ich_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); - cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; + if (cs->nmi_support) { + cs->ich_apr[grp][regno] = value & (0xFFFFFFFFU | ICV_AP1R_EL1_NMI); + } else { + cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; + } gicv3_cpuif_virt_irq_fiq_update(cs); } @@ -XXX,XX +XXX,XX @@ static void ich_lr_write(CPUARMState *env, const ARMCPRegInfo *ri, 8 - cs->vpribits, 0); } + /* Enforce RES0 bit in NMI field when FEAT_GICv3_NMI is not implemented */ + if (!cs->nmi_support) { + value &= ~ICH_LR_EL2_NMI; + } + cs->ich_lr_el2[regno] = value; gicv3_cpuif_virt_update(cs); } diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_icv_rpr_read(uint32_t cpu, uint64_t val) "GICv3 ICV_RPR read cpu 0x%x valu gicv3_icv_hppir_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_HPPIR%d read cpu 0x%x value 0x%" PRIx64 gicv3_icv_dir_write(uint32_t cpu, uint64_t val) "GICv3 ICV_DIR write cpu 0x%x value 0x%" PRIx64 gicv3_icv_iar_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_IAR%d read cpu 0x%x value 0x%" PRIx64 +gicv3_icv_nmiar1_read(uint32_t cpu, uint64_t val) "GICv3 ICV_NMIAR1 read cpu 0x%x value 0x%" PRIx64 gicv3_icv_eoir_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_EOIR%d write cpu 0x%x value 0x%" PRIx64 gicv3_cpuif_virt_update(uint32_t cpuid, int idx, int hppvlpi, int grp, int prio) "GICv3 CPU i/f 0x%x virt HPPI update LR index %d HPPVLPI %d grp %d prio %d" gicv3_cpuif_virt_set_irqs(uint32_t cpuid, int fiqlevel, int irqlevel) "GICv3 CPU i/f 0x%x virt HPPI update: setting FIQ %d IRQ %d" -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> If GICD_CTLR_DS bit is zero and the NMI is non-secure, the NMI priority is higher than 0x80, otherwise it is higher than 0x0. And save the interrupt non-maskable property in hppi.nmi to deliver NMI exception. Since both GICR and GICD can deliver NMI, it is both necessary to check whether the pending irq is NMI in gicv3_redist_update_noirqset and gicv3_update_noirqset. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-21-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3.c | 67 +++++++++++++++++++++++++++++++++----- hw/intc/arm_gicv3_common.c | 3 ++ hw/intc/arm_gicv3_redist.c | 3 ++ 3 files changed, 64 insertions(+), 9 deletions(-) diff --git a/hw/intc/arm_gicv3.c b/hw/intc/arm_gicv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3.c +++ b/hw/intc/arm_gicv3.c @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gicv3.h" #include "gicv3_internal.h" -static bool irqbetter(GICv3CPUState *cs, int irq, uint8_t prio) +static bool irqbetter(GICv3CPUState *cs, int irq, uint8_t prio, bool nmi) { /* Return true if this IRQ at this priority should take * precedence over the current recorded highest priority @@ -XXX,XX +XXX,XX @@ static bool irqbetter(GICv3CPUState *cs, int irq, uint8_t prio) * is the same as this one (a property which the calling code * relies on). */ - if (prio < cs->hppi.prio) { - return true; + if (prio != cs->hppi.prio) { + return prio < cs->hppi.prio; } + + /* + * The same priority IRQ with non-maskable property should signal to + * the CPU as it have the priority higher than the labelled 0x80 or 0x00. + */ + if (nmi != cs->hppi.nmi) { + return nmi; + } + /* If multiple pending interrupts have the same priority then it is an * IMPDEF choice which of them to signal to the CPU. We choose to * signal the one with the lowest interrupt number. */ - if (prio == cs->hppi.prio && irq <= cs->hppi.irq) { + if (irq <= cs->hppi.irq) { return true; } return false; @@ -XXX,XX +XXX,XX @@ static uint32_t gicr_int_pending(GICv3CPUState *cs) return pend; } +static bool gicv3_get_priority(GICv3CPUState *cs, bool is_redist, int irq, + uint8_t *prio) +{ + uint32_t nmi = 0x0; + + if (is_redist) { + nmi = extract32(cs->gicr_inmir0, irq, 1); + } else { + nmi = *gic_bmp_ptr32(cs->gic->nmi, irq); + nmi = nmi & (1 << (irq & 0x1f)); + } + + if (nmi) { + /* DS = 0 & Non-secure NMI */ + if (!(cs->gic->gicd_ctlr & GICD_CTLR_DS) && + ((is_redist && extract32(cs->gicr_igroupr0, irq, 1)) || + (!is_redist && gicv3_gicd_group_test(cs->gic, irq)))) { + *prio = 0x80; + } else { + *prio = 0x0; + } + + return true; + } + + if (is_redist) { + *prio = cs->gicr_ipriorityr[irq]; + } else { + *prio = cs->gic->gicd_ipriority[irq]; + } + + return false; +} + /* Update the interrupt status after state in a redistributor * or CPU interface has changed, but don't tell the CPU i/f. */ @@ -XXX,XX +XXX,XX @@ static void gicv3_redist_update_noirqset(GICv3CPUState *cs) uint8_t prio; int i; uint32_t pend; + bool nmi = false; /* Find out which redistributor interrupts are eligible to be * signaled to the CPU interface. @@ -XXX,XX +XXX,XX @@ static void gicv3_redist_update_noirqset(GICv3CPUState *cs) if (!(pend & (1 << i))) { continue; } - prio = cs->gicr_ipriorityr[i]; - if (irqbetter(cs, i, prio)) { + nmi = gicv3_get_priority(cs, true, i, &prio); + if (irqbetter(cs, i, prio, nmi)) { cs->hppi.irq = i; cs->hppi.prio = prio; + cs->hppi.nmi = nmi; seenbetter = true; } } @@ -XXX,XX +XXX,XX @@ static void gicv3_redist_update_noirqset(GICv3CPUState *cs) if ((cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) && cs->gic->lpi_enable && (cs->gic->gicd_ctlr & GICD_CTLR_EN_GRP1NS) && (cs->hpplpi.prio != 0xff)) { - if (irqbetter(cs, cs->hpplpi.irq, cs->hpplpi.prio)) { + if (irqbetter(cs, cs->hpplpi.irq, cs->hpplpi.prio, cs->hpplpi.nmi)) { cs->hppi.irq = cs->hpplpi.irq; cs->hppi.prio = cs->hpplpi.prio; + cs->hppi.nmi = cs->hpplpi.nmi; cs->hppi.grp = cs->hpplpi.grp; seenbetter = true; } @@ -XXX,XX +XXX,XX @@ static void gicv3_update_noirqset(GICv3State *s, int start, int len) int i; uint8_t prio; uint32_t pend = 0; + bool nmi = false; assert(start >= GIC_INTERNAL); assert(len > 0); @@ -XXX,XX +XXX,XX @@ static void gicv3_update_noirqset(GICv3State *s, int start, int len) */ continue; } - prio = s->gicd_ipriority[i]; - if (irqbetter(cs, i, prio)) { + nmi = gicv3_get_priority(cs, false, i, &prio); + if (irqbetter(cs, i, prio, nmi)) { cs->hppi.irq = i; cs->hppi.prio = prio; + cs->hppi.nmi = nmi; cs->seenbetter = true; } } @@ -XXX,XX +XXX,XX @@ void gicv3_full_update_noirqset(GICv3State *s) for (i = 0; i < s->num_cpu; i++) { s->cpu[i].hppi.prio = 0xff; + s->cpu[i].hppi.nmi = false; } /* Note that we can guarantee that these functions will not diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_reset_hold(Object *obj) memset(cs->gicr_ipriorityr, 0, sizeof(cs->gicr_ipriorityr)); cs->hppi.prio = 0xff; + cs->hppi.nmi = false; cs->hpplpi.prio = 0xff; + cs->hpplpi.nmi = false; cs->hppvlpi.prio = 0xff; + cs->hppvlpi.nmi = false; /* State in the CPU interface must *not* be reset here, because it * is part of the CPU's reset domain, not the GIC device's. diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static void update_for_one_lpi(GICv3CPUState *cs, int irq, ((prio == hpp->prio) && (irq <= hpp->irq))) { hpp->irq = irq; hpp->prio = prio; + hpp->nmi = false; /* LPIs and vLPIs are always non-secure Grp1 interrupts */ hpp->grp = GICV3_G1NS; } @@ -XXX,XX +XXX,XX @@ static void update_for_all_lpis(GICv3CPUState *cs, uint64_t ptbase, int i, bit; hpp->prio = 0xff; + hpp->nmi = false; for (i = GICV3_LPI_INTID_START / 8; i < pendt_size / 8; i++) { address_space_read(as, ptbase + i, MEMTXATTRS_UNSPECIFIED, &pend, 1); @@ -XXX,XX +XXX,XX @@ static void gicv3_redist_update_vlpi_only(GICv3CPUState *cs) if (!FIELD_EX64(cs->gicr_vpendbaser, GICR_VPENDBASER, VALID)) { cs->hppvlpi.prio = 0xff; + cs->hppvlpi.nmi = false; return; } -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> In CPU Interface, if the IRQ has the non-maskable property, report NMI to the corresponding PE. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-22-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_cpuif.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_update(GICv3CPUState *cs) /* Tell the CPU about its highest priority pending interrupt */ int irqlevel = 0; int fiqlevel = 0; + int nmilevel = 0; ARMCPU *cpu = ARM_CPU(cs->cpu); CPUARMState *env = &cpu->env; @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_update(GICv3CPUState *cs) if (isfiq) { fiqlevel = 1; + } else if (cs->hppi.nmi) { + nmilevel = 1; } else { irqlevel = 1; } @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_update(GICv3CPUState *cs) qemu_set_irq(cs->parent_fiq, fiqlevel); qemu_set_irq(cs->parent_irq, irqlevel); + qemu_set_irq(cs->parent_nmi, nmilevel); } static uint64_t icc_pmr_read(CPUARMState *env, const ARMCPRegInfo *ri) -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> In vCPU Interface, if the vIRQ has the non-maskable property, report vINMI to the corresponding vPE. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-23-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_cpuif.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_virt_irq_fiq_update(GICv3CPUState *cs) int idx; int irqlevel = 0; int fiqlevel = 0; + int nmilevel = 0; idx = hppvi_index(cs); trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx, @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_virt_irq_fiq_update(GICv3CPUState *cs) uint64_t lr = cs->ich_lr_el2[idx]; if (icv_hppi_can_preempt(cs, lr)) { - /* Virtual interrupts are simple: G0 are always FIQ, and G1 IRQ */ + /* + * Virtual interrupts are simple: G0 are always FIQ, and G1 are + * IRQ or NMI which depends on the ICH_LR<n>_EL2.NMI to have + * non-maskable property. + */ if (lr & ICH_LR_EL2_GROUP) { - irqlevel = 1; + if (lr & ICH_LR_EL2_NMI) { + nmilevel = 1; + } else { + irqlevel = 1; + } } else { fiqlevel = 1; } @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_virt_irq_fiq_update(GICv3CPUState *cs) trace_gicv3_cpuif_virt_set_irqs(gicv3_redist_affid(cs), fiqlevel, irqlevel); qemu_set_irq(cs->parent_vfiq, fiqlevel); qemu_set_irq(cs->parent_virq, irqlevel); + qemu_set_irq(cs->parent_vnmi, nmilevel); } static void gicv3_cpuif_virt_update(GICv3CPUState *cs) -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> Enable FEAT_NMI on the 'max' CPU. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240407081733.3231820-24-ruanjinjie@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_MTE (Memory Tagging Extension) - FEAT_MTE2 (Memory Tagging Extension) - FEAT_MTE3 (MTE Asymmetric Fault Handling) +- FEAT_NMI (Non-maskable Interrupt) - FEAT_NV (Nested Virtualization) - FEAT_NV2 (Enhanced nested virtualization support) - FEAT_PACIMP (Pointer authentication - IMPLEMENTATION DEFINED algorithm) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ + t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1); /* FEAT_NMI */ cpu->isar.id_aa64pfr1 = t; t = cpu->isar.id_aa64mmfr0; -- 2.34.1 From: Jinjie Ruan <ruanjinjie@huawei.com> If the CPU implements FEAT_NMI, then turn on the NMI support in the GICv3 too. It's permitted to have a configuration with FEAT_NMI in the CPU (and thus NMI support in the CPU interfaces too) but no NMI support in the distributor and redistributor, but this isn't a very useful setup as it's close to having no NMI support at all. We don't need to gate the enabling of NMI in the GIC behind a machine version property, because none of our current CPUs implement FEAT_NMI, and '-cpu max' is not something we maintain migration compatibility across versions for. So we can always enable the GIC NMI support when the CPU has it. Neither hvf nor KVM support NMI in the GIC yet, so we don't enable it unless we're using TCG. Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240407081733.3231820-25-ruanjinjie@huawei.com [PMM: Update comment and commit message] Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_v2m(VirtMachineState *vms) vms->msi_controller = VIRT_MSI_CTRL_GICV2M; } +/* + * If the CPU has FEAT_NMI, then turn on the NMI support in the GICv3 too. + * It's permitted to have a configuration with NMI in the CPU (and thus the + * GICv3 CPU interface) but not in the distributor/redistributors, but it's + * not very useful. + */ +static bool gicv3_nmi_present(VirtMachineState *vms) +{ + ARMCPU *cpu = ARM_CPU(qemu_get_cpu(0)); + + return tcg_enabled() && cpu_isar_feature(aa64_nmi, cpu) && + (vms->gic_version != VIRT_GIC_VERSION_2); +} + static void create_gic(VirtMachineState *vms, MemoryRegion *mem) { MachineState *ms = MACHINE(vms); @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) vms->virt); } } + + if (gicv3_nmi_present(vms)) { + qdev_prop_set_bit(vms->gic, "has-nmi", true); + } + gicbusdev = SYS_BUS_DEVICE(vms->gic); sysbus_realize_and_unref(gicbusdev, &error_fatal); sysbus_mmio_map(gicbusdev, 0, vms->memmap[VIRT_GIC_DIST].base); -- 2.34.1 From: Anastasia Belova <abelova@astralinux.ru> In soc_dma_set_request() we try to set a bit in a uint64_t, but we do it with "1 << ch->num", which can't set any bits past 31; any use for a channel number of 32 or more would fail due to integer overflow. This doesn't happen in practice for our current use of this code, because the worst case is when we call soc_dma_init() with an argument of 32 for the number of channels, and QEMU builds with -fwrapv so the shift into the sign bit is well-defined. However, it's obviously not the intended behaviour of the code. Add casts to force the shift to be done as 64-bit arithmetic, allowing up to 64 channels. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: afbb5194d4 ("Handle on-chip DMA controllers in one place, convert OMAP DMA to use it.") Signed-off-by: Anastasia Belova <abelova@astralinux.ru> Message-id: 20240409115301.21829-1-abelova@astralinux.ru [PMM: Edit commit message to clarify that this doesn't actually bite us in our current usage of this code.] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/soc_dma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/dma/soc_dma.c b/hw/dma/soc_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/soc_dma.c +++ b/hw/dma/soc_dma.c @@ -XXX,XX +XXX,XX @@ void soc_dma_set_request(struct soc_dma_ch_s *ch, int level) dma->enabled_count += level - ch->enable; if (level) - dma->ch_enable_mask |= 1 << ch->num; + dma->ch_enable_mask |= (uint64_t)1 << ch->num; else - dma->ch_enable_mask &= ~(1 << ch->num); + dma->ch_enable_mask &= ~((uint64_t)1 << ch->num); if (level != ch->enable) { soc_dma_ch_freq_update(dma); -- 2.34.1 Ever since the bFLT format support was added in 2006, there has been a chunk of code in the file guarded by CONFIG_BINFMT_SHARED_FLAT which is supposedly for shared library support. This is not enabled and it's not possible to enable it, because if you do you'll run into the "#error needs checking" in the calc_reloc() function. Similarly, CONFIG_BINFMT_ZFLAT exists but can't be enabled because of an "#error code needs checking" in load_flat_file(). This code is obviously unfinished and has never been used; nobody in the intervening 18 years has complained about this or fixed it, so just delete the dead code. If anybody ever wants the feature they can always pull it out of git, or (perhaps better) write it from scratch based on the current Linux bFLT loader rather than the one of 18 years ago. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240411115313.680433-1-peter.maydell@linaro.org --- linux-user/flat.h | 5 +- linux-user/flatload.c | 293 ++---------------------------------------- 2 files changed, 11 insertions(+), 287 deletions(-) diff --git a/linux-user/flat.h b/linux-user/flat.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/flat.h +++ b/linux-user/flat.h @@ -XXX,XX +XXX,XX @@ #define FLAT_VERSION 0x00000004L -#ifdef CONFIG_BINFMT_SHARED_FLAT -#define MAX_SHARED_LIBS (4) -#else +/* QEMU doesn't support bflt shared libraries */ #define MAX_SHARED_LIBS (1) -#endif /* * To make everything easier to port and manage cross platform diff --git a/linux-user/flatload.c b/linux-user/flatload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/flatload.c +++ b/linux-user/flatload.c @@ -XXX,XX +XXX,XX @@ * JAN/99 -- coded full program relocation (gerg@snapgear.com) */ -/* ??? ZFLAT and shared library support is currently disabled. */ - /****************************************************************************/ #include "qemu/osdep.h" @@ -XXX,XX +XXX,XX @@ struct lib_info { short loaded; /* Has this library been loaded? */ }; -#ifdef CONFIG_BINFMT_SHARED_FLAT -static int load_flat_shared_library(int id, struct lib_info *p); -#endif - struct linux_binprm; /****************************************************************************/ @@ -XXX,XX +XXX,XX @@ static int target_pread(int fd, abi_ulong ptr, abi_ulong len, unlock_user(buf, ptr, len); return ret; } -/****************************************************************************/ - -#ifdef CONFIG_BINFMT_ZFLAT - -#include <linux/zlib.h> - -#define LBUFSIZE 4000 - -/* gzip flag byte */ -#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */ -#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */ -#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ -#define ORIG_NAME 0x08 /* bit 3 set: original file name present */ -#define COMMENT 0x10 /* bit 4 set: file comment present */ -#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ -#define RESERVED 0xC0 /* bit 6,7: reserved */ - -static int decompress_exec( - struct linux_binprm *bprm, - unsigned long offset, - char *dst, - long len, - int fd) -{ - unsigned char *buf; - z_stream strm; - loff_t fpos; - int ret, retval; - - DBG_FLT("decompress_exec(offset=%x,buf=%x,len=%x)\n",(int)offset, (int)dst, (int)len); - - memset(&strm, 0, sizeof(strm)); - strm.workspace = kmalloc(zlib_inflate_workspacesize(), GFP_KERNEL); - if (strm.workspace == NULL) { - DBG_FLT("binfmt_flat: no memory for decompress workspace\n"); - return -ENOMEM; - } - buf = kmalloc(LBUFSIZE, GFP_KERNEL); - if (buf == NULL) { - DBG_FLT("binfmt_flat: no memory for read buffer\n"); - retval = -ENOMEM; - goto out_free; - } - - /* Read in first chunk of data and parse gzip header. */ - fpos = offset; - ret = bprm->file->f_op->read(bprm->file, buf, LBUFSIZE, &fpos); - - strm.next_in = buf; - strm.avail_in = ret; - strm.total_in = 0; - - retval = -ENOEXEC; - - /* Check minimum size -- gzip header */ - if (ret < 10) { - DBG_FLT("binfmt_flat: file too small?\n"); - goto out_free_buf; - } - - /* Check gzip magic number */ - if ((buf[0] != 037) || ((buf[1] != 0213) && (buf[1] != 0236))) { - DBG_FLT("binfmt_flat: unknown compression magic?\n"); - goto out_free_buf; - } - - /* Check gzip method */ - if (buf[2] != 8) { - DBG_FLT("binfmt_flat: unknown compression method?\n"); - goto out_free_buf; - } - /* Check gzip flags */ - if ((buf[3] & ENCRYPTED) || (buf[3] & CONTINUATION) || - (buf[3] & RESERVED)) { - DBG_FLT("binfmt_flat: unknown flags?\n"); - goto out_free_buf; - } - - ret = 10; - if (buf[3] & EXTRA_FIELD) { - ret += 2 + buf[10] + (buf[11] << 8); - if (unlikely(LBUFSIZE == ret)) { - DBG_FLT("binfmt_flat: buffer overflow (EXTRA)?\n"); - goto out_free_buf; - } - } - if (buf[3] & ORIG_NAME) { - for (; ret < LBUFSIZE && (buf[ret] != 0); ret++) - ; - if (unlikely(LBUFSIZE == ret)) { - DBG_FLT("binfmt_flat: buffer overflow (ORIG_NAME)?\n"); - goto out_free_buf; - } - } - if (buf[3] & COMMENT) { - for (; ret < LBUFSIZE && (buf[ret] != 0); ret++) - ; - if (unlikely(LBUFSIZE == ret)) { - DBG_FLT("binfmt_flat: buffer overflow (COMMENT)?\n"); - goto out_free_buf; - } - } - - strm.next_in += ret; - strm.avail_in -= ret; - - strm.next_out = dst; - strm.avail_out = len; - strm.total_out = 0; - - if (zlib_inflateInit2(&strm, -MAX_WBITS) != Z_OK) { - DBG_FLT("binfmt_flat: zlib init failed?\n"); - goto out_free_buf; - } - - while ((ret = zlib_inflate(&strm, Z_NO_FLUSH)) == Z_OK) { - ret = bprm->file->f_op->read(bprm->file, buf, LBUFSIZE, &fpos); - if (ret <= 0) - break; - if (is_error(ret)) { - break; - } - len -= ret; - - strm.next_in = buf; - strm.avail_in = ret; - strm.total_in = 0; - } - - if (ret < 0) { - DBG_FLT("binfmt_flat: decompression failed (%d), %s\n", - ret, strm.msg); - goto out_zlib; - } - - retval = 0; -out_zlib: - zlib_inflateEnd(&strm); -out_free_buf: - kfree(buf); -out_free: - kfree(strm.workspace); -out: - return retval; -} - -#endif /* CONFIG_BINFMT_ZFLAT */ /****************************************************************************/ @@ -XXX,XX +XXX,XX @@ calc_reloc(abi_ulong r, struct lib_info *p, int curid, int internalp) abi_ulong text_len; abi_ulong start_code; -#ifdef CONFIG_BINFMT_SHARED_FLAT -#error needs checking - if (r == 0) - id = curid; /* Relocs of 0 are always self referring */ - else { - id = (r >> 24) & 0xff; /* Find ID for this reloc */ - r &= 0x00ffffff; /* Trim ID off here */ - } - if (id >= MAX_SHARED_LIBS) { - fprintf(stderr, "BINFMT_FLAT: reference 0x%x to shared library %d\n", - (unsigned) r, id); - goto failed; - } - if (curid != id) { - if (internalp) { - fprintf(stderr, "BINFMT_FLAT: reloc address 0x%x not " - "in same module (%d != %d)\n", - (unsigned) r, curid, id); - goto failed; - } else if (!p[id].loaded && is_error(load_flat_shared_library(id, p))) { - fprintf(stderr, "BINFMT_FLAT: failed to load library %d\n", id); - goto failed; - } - /* Check versioning information (i.e. time stamps) */ - if (p[id].build_date && p[curid].build_date - && p[curid].build_date < p[id].build_date) { - fprintf(stderr, "BINFMT_FLAT: library %d is younger than %d\n", - id, curid); - goto failed; - } - } -#else id = 0; -#endif start_brk = p[id].start_brk; start_data = p[id].start_data; @@ -XXX,XX +XXX,XX @@ static int load_flat_file(struct linux_binprm * bprm, if (rev == OLD_FLAT_VERSION && flat_old_ram_flag(flags)) flags = FLAT_FLAG_RAM; -#ifndef CONFIG_BINFMT_ZFLAT if (flags & (FLAT_FLAG_GZIP|FLAT_FLAG_GZDATA)) { - fprintf(stderr, "Support for ZFLAT executables is not enabled\n"); + fprintf(stderr, "ZFLAT executables are not supported\n"); return -ENOEXEC; } -#endif /* * calculate the extra space we need to map in @@ -XXX,XX +XXX,XX @@ static int load_flat_file(struct linux_binprm * bprm, (int)(data_len + bss_len + stack_len), (int)datapos); fpos = ntohl(hdr->data_start); -#ifdef CONFIG_BINFMT_ZFLAT - if (flags & FLAT_FLAG_GZDATA) { - result = decompress_exec(bprm, fpos, (char *) datapos, - data_len + (relocs * sizeof(abi_ulong))) - } else -#endif - { - result = target_pread(bprm->src.fd, datapos, - data_len + (relocs * sizeof(abi_ulong)), - fpos); - } + result = target_pread(bprm->src.fd, datapos, + data_len + (relocs * sizeof(abi_ulong)), + fpos); if (result < 0) { fprintf(stderr, "Unable to read data+bss\n"); return result; @@ -XXX,XX +XXX,XX @@ static int load_flat_file(struct linux_binprm * bprm, datapos = realdatastart + indx_len; reloc = (textpos + ntohl(hdr->reloc_start) + indx_len); -#ifdef CONFIG_BINFMT_ZFLAT -#error code needs checking - /* - * load it all in and treat it like a RAM load from now on - */ - if (flags & FLAT_FLAG_GZIP) { - result = decompress_exec(bprm, sizeof (struct flat_hdr), - (((char *) textpos) + sizeof (struct flat_hdr)), - (text_len + data_len + (relocs * sizeof(unsigned long)) - - sizeof (struct flat_hdr)), - 0); - memmove((void *) datapos, (void *) realdatastart, - data_len + (relocs * sizeof(unsigned long))); - } else if (flags & FLAT_FLAG_GZDATA) { - fpos = 0; - result = bprm->file->f_op->read(bprm->file, - (char *) textpos, text_len, &fpos); - if (!is_error(result)) { - result = decompress_exec(bprm, text_len, (char *) datapos, - data_len + (relocs * sizeof(unsigned long)), 0); - } - } - else -#endif - { - result = target_pread(bprm->src.fd, textpos, - text_len, 0); - if (result >= 0) { - result = target_pread(bprm->src.fd, datapos, - data_len + (relocs * sizeof(abi_ulong)), - ntohl(hdr->data_start)); - } + result = target_pread(bprm->src.fd, textpos, + text_len, 0); + if (result >= 0) { + result = target_pread(bprm->src.fd, datapos, + data_len + (relocs * sizeof(abi_ulong)), + ntohl(hdr->data_start)); } if (result < 0) { fprintf(stderr, "Unable to read code+data+bss\n"); @@ -XXX,XX +XXX,XX @@ static int load_flat_file(struct linux_binprm * bprm, /****************************************************************************/ -#ifdef CONFIG_BINFMT_SHARED_FLAT - -/* - * Load a shared library into memory. The library gets its own data - * segment (including bss) but not argv/argc/environ. - */ - -static int load_flat_shared_library(int id, struct lib_info *libs) -{ - struct linux_binprm bprm; - int res; - char buf[16]; - - /* Create the file name */ - sprintf(buf, "/lib/lib%d.so", id); - - /* Open the file up */ - bprm.filename = buf; - bprm.file = open_exec(bprm.filename); - res = PTR_ERR(bprm.file); - if (IS_ERR(bprm.file)) - return res; - - res = prepare_binprm(&bprm); - - if (!is_error(res)) { - res = load_flat_file(&bprm, libs, id, NULL); - } - if (bprm.file) { - allow_write_access(bprm.file); - fput(bprm.file); - bprm.file = NULL; - } - return(res); -} - -#endif /* CONFIG_BINFMT_SHARED_FLAT */ - int load_flt_binary(struct linux_binprm *bprm, struct image_info *info) { struct lib_info libinfo[MAX_SHARED_LIBS]; @@ -XXX,XX +XXX,XX @@ int load_flt_binary(struct linux_binprm *bprm, struct image_info *info) */ start_addr = libinfo[0].entry; -#ifdef CONFIG_BINFMT_SHARED_FLAT -#error here - for (i = MAX_SHARED_LIBS-1; i>0; i--) { - if (libinfo[i].loaded) { - /* Push previous first to call address */ - --sp; - if (put_user_ual(start_addr, sp)) - return -EFAULT; - start_addr = libinfo[i].entry; - } - } -#endif - /* Stash our initial stack pointer into the mm structure */ info->start_code = libinfo[0].start_code; info->end_code = libinfo[0].start_code + libinfo[0].text_len; -- 2.34.1 The npcm7xx_clk and npcm7xx_gcr device reset methods look at the ResetType argument and only handle RESET_TYPE_COLD, producing a warning if another reset type is passed. This is different from how every other three-phase-reset method we have works, and makes it difficult to add new reset types. A better pattern is "assume that any reset type you don't know about should be handled like RESET_TYPE_COLD"; switch these devices to do that. Then adding a new reset type will only need to touch those devices where its behaviour really needs to be different from the standard cold reset. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20240412160809.1260625-2-peter.maydell@linaro.org --- hw/misc/npcm7xx_clk.c | 13 +++---------- hw/misc/npcm7xx_gcr.c | 12 ++++-------- 2 files changed, 7 insertions(+), 18 deletions(-) diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_clk.c +++ b/hw/misc/npcm7xx_clk.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_clk_enter_reset(Object *obj, ResetType type) QEMU_BUILD_BUG_ON(sizeof(s->regs) != sizeof(cold_reset_values)); - switch (type) { - case RESET_TYPE_COLD: - memcpy(s->regs, cold_reset_values, sizeof(cold_reset_values)); - s->ref_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - npcm7xx_clk_update_all_clocks(s); - return; - } - + memcpy(s->regs, cold_reset_values, sizeof(cold_reset_values)); + s->ref_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + npcm7xx_clk_update_all_clocks(s); /* * A small number of registers need to be reset on a core domain reset, * but no such reset type exists yet. */ - qemu_log_mask(LOG_UNIMP, "%s: reset type %d not implemented.", - __func__, type); } static void npcm7xx_clk_init_clock_hierarchy(NPCM7xxCLKState *s) diff --git a/hw/misc/npcm7xx_gcr.c b/hw/misc/npcm7xx_gcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_gcr.c +++ b/hw/misc/npcm7xx_gcr.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_gcr_enter_reset(Object *obj, ResetType type) QEMU_BUILD_BUG_ON(sizeof(s->regs) != sizeof(cold_reset_values)); - switch (type) { - case RESET_TYPE_COLD: - memcpy(s->regs, cold_reset_values, sizeof(s->regs)); - s->regs[NPCM7XX_GCR_PWRON] = s->reset_pwron; - s->regs[NPCM7XX_GCR_MDLR] = s->reset_mdlr; - s->regs[NPCM7XX_GCR_INTCR3] = s->reset_intcr3; - break; - } + memcpy(s->regs, cold_reset_values, sizeof(s->regs)); + s->regs[NPCM7XX_GCR_PWRON] = s->reset_pwron; + s->regs[NPCM7XX_GCR_MDLR] = s->reset_mdlr; + s->regs[NPCM7XX_GCR_INTCR3] = s->reset_intcr3; } static void npcm7xx_gcr_realize(DeviceState *dev, Error **errp) -- 2.34.1 Rather than directly calling the device's implementation of its 'hold' reset phase, call device_cold_reset(). This means we don't have to adjust this callsite when we add another argument to the function signature for the hold and exit reset methods. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20240412160809.1260625-3-peter.maydell@linaro.org --- hw/i2c/allwinner-i2c.c | 3 +-- hw/sensor/adm1272.c | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/allwinner-i2c.c +++ b/hw/i2c/allwinner-i2c.c @@ -XXX,XX +XXX,XX @@ static void allwinner_i2c_write(void *opaque, hwaddr offset, break; case TWI_SRST_REG: if (((value & TWI_SRST_MASK) == 0) && (s->srst & TWI_SRST_MASK)) { - /* Perform reset */ - allwinner_i2c_reset_hold(OBJECT(s)); + device_cold_reset(DEVICE(s)); } s->srst = value & TWI_SRST_MASK; break; diff --git a/hw/sensor/adm1272.c b/hw/sensor/adm1272.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sensor/adm1272.c +++ b/hw/sensor/adm1272.c @@ -XXX,XX +XXX,XX @@ static int adm1272_write_data(PMBusDevice *pmdev, const uint8_t *buf, break; case ADM1272_MFR_POWER_CYCLE: - adm1272_exit_reset((Object *)s); + device_cold_reset(DEVICE(s)); break; case ADM1272_HYSTERESIS_LOW: -- 2.34.1 We pass a ResetType argument to the Resettable class enter phase method, but we don't pass it to hold and exit, even though the callsites have it readily available. This means that if a device cared about the ResetType it would need to record it in the enter phase method to use later on. We should pass the type to all three of the phase methods to avoid having to do that. This coccinelle script adds the ResetType argument to the hold and exit phases of the Resettable interface. The first part of the script (rules holdfn_assigned, holdfn_defined, exitfn_assigned, exitfn_defined) update implementations of the interface within device models, both to change the signature of their method implementations and to pass on the reset type when they invoke reset on some other device. The second part of the script is various special cases: * method callsites in resettable_phase_hold(), resettable_phase_exit() and device_phases_reset() * updating the typedefs for the methods * isl_pmbus_vr.c has some code where one device's reset method directly calls the implementation of a different device's method Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20240412160809.1260625-4-peter.maydell@linaro.org --- scripts/coccinelle/reset-type.cocci | 133 ++++++++++++++++++++++++++++ 1 file changed, 133 insertions(+) create mode 100644 scripts/coccinelle/reset-type.cocci diff --git a/scripts/coccinelle/reset-type.cocci b/scripts/coccinelle/reset-type.cocci new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/scripts/coccinelle/reset-type.cocci @@ -XXX,XX +XXX,XX @@ +// Convert device code using three-phase reset to add a ResetType +// argument to implementations of ResettableHoldPhase and +// ResettableEnterPhase methods. +// +// Copyright Linaro Ltd 2024 +// SPDX-License-Identifier: GPL-2.0-or-later +// +// for dir in include hw target; do \ +// spatch --macro-file scripts/cocci-macro-file.h \ +// --sp-file scripts/coccinelle/reset-type.cocci \ +// --keep-comments --smpl-spacing --in-place --include-headers \ +// --dir $dir; done +// +// This coccinelle script aims to produce a complete change that needs +// no human interaction, so as well as the generic "update device +// implementations of the hold and exit phase methods" it includes +// the special-case transformations needed for the core code and for +// one device model that does something a bit nonstandard. Those +// special cases are at the end of the file. + +// Look for where we use a function as a ResettableHoldPhase method, +// either by directly assigning it to phases.hold or by calling +// resettable_class_set_parent_phases, and remember the function name. +@ holdfn_assigned @ +identifier enterfn, holdfn, exitfn; +identifier rc; +expression e; +@@ +ResettableClass *rc; +... +( + rc->phases.hold = holdfn; +| + resettable_class_set_parent_phases(rc, enterfn, holdfn, exitfn, e); +) + +// Look for the definition of the function we found in holdfn_assigned, +// and add the new argument. If the function calls a hold function +// itself (probably chaining to the parent class reset) then add the +// new argument there too. +@ holdfn_defined @ +identifier holdfn_assigned.holdfn; +typedef Object; +identifier obj; +expression parent; +@@ +-holdfn(Object *obj) ++holdfn(Object *obj, ResetType type) +{ + <... +- parent.hold(obj) ++ parent.hold(obj, type) + ...> +} + +// Similarly for ResettableExitPhase. +@ exitfn_assigned @ +identifier enterfn, holdfn, exitfn; +identifier rc; +expression e; +@@ +ResettableClass *rc; +... +( + rc->phases.exit = exitfn; +| + resettable_class_set_parent_phases(rc, enterfn, holdfn, exitfn, e); +) +@ exitfn_defined @ +identifier exitfn_assigned.exitfn; +typedef Object; +identifier obj; +expression parent; +@@ +-exitfn(Object *obj) ++exitfn(Object *obj, ResetType type) +{ + <... +- parent.exit(obj) ++ parent.exit(obj, type) + ...> +} + +// SPECIAL CASES ONLY BELOW HERE +// We use a python scripted constraint on the position of the match +// to ensure that they only match in a particular function. See +// https://public-inbox.org/git/alpine.DEB.2.21.1808240652370.2344@hadrien/ +// which recommends this as the way to do "match only in this function". + +// Special case: isl_pmbus_vr.c has some reset methods calling others directly +@ isl_pmbus_vr @ +identifier obj; +@@ +- isl_pmbus_vr_exit_reset(obj); ++ isl_pmbus_vr_exit_reset(obj, type); + +// Special case: device_phases_reset() needs to pass RESET_TYPE_COLD +@ device_phases_reset_hold @ +expression obj; +identifier rc; +identifier phase; +position p : script:python() { p[0].current_element == "device_phases_reset" }; +@@ +- rc->phases.phase(obj)@p ++ rc->phases.phase(obj, RESET_TYPE_COLD) + +// Special case: in resettable_phase_hold() and resettable_phase_exit() +// we need to pass through the ResetType argument to the method being called +@ resettable_phase_hold @ +expression obj; +identifier rc; +position p : script:python() { p[0].current_element == "resettable_phase_hold" }; +@@ +- rc->phases.hold(obj)@p ++ rc->phases.hold(obj, type) +@ resettable_phase_exit @ +expression obj; +identifier rc; +position p : script:python() { p[0].current_element == "resettable_phase_exit" }; +@@ +- rc->phases.exit(obj)@p ++ rc->phases.exit(obj, type) +// Special case: the typedefs for the methods need to declare the new argument +@ phase_typedef_hold @ +identifier obj; +@@ +- typedef void (*ResettableHoldPhase)(Object *obj); ++ typedef void (*ResettableHoldPhase)(Object *obj, ResetType type); +@ phase_typedef_exit @ +identifier obj; +@@ +- typedef void (*ResettableExitPhase)(Object *obj); ++ typedef void (*ResettableExitPhase)(Object *obj, ResetType type); -- 2.34.1 We pass a ResetType argument to the Resettable class enter phase method, but we don't pass it to hold and exit, even though the callsites have it readily available. This means that if a device cared about the ResetType it would need to record it in the enter phase method to use later on. Pass the type to all three of the phase methods to avoid having to do that. Commit created with for dir in hw target include; do \ spatch --macro-file scripts/cocci-macro-file.h \ --sp-file scripts/coccinelle/reset-type.cocci \ --keep-comments --smpl-spacing --in-place \ --include-headers --dir $dir; done and no manual edits. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20240412160809.1260625-5-peter.maydell@linaro.org --- include/hw/resettable.h | 4 ++-- hw/adc/npcm7xx_adc.c | 2 +- hw/arm/pxa2xx_pic.c | 2 +- hw/arm/smmu-common.c | 2 +- hw/arm/smmuv3.c | 4 ++-- hw/arm/stellaris.c | 10 +++++----- hw/audio/asc.c | 2 +- hw/char/cadence_uart.c | 2 +- hw/char/sifive_uart.c | 2 +- hw/core/cpu-common.c | 2 +- hw/core/qdev.c | 4 ++-- hw/core/reset.c | 2 +- hw/core/resettable.c | 4 ++-- hw/display/virtio-vga.c | 4 ++-- hw/gpio/npcm7xx_gpio.c | 2 +- hw/gpio/pl061.c | 2 +- hw/gpio/stm32l4x5_gpio.c | 2 +- hw/hyperv/vmbus.c | 2 +- hw/i2c/allwinner-i2c.c | 2 +- hw/i2c/npcm7xx_smbus.c | 2 +- hw/input/adb.c | 2 +- hw/input/ps2.c | 12 ++++++------ hw/intc/arm_gic_common.c | 2 +- hw/intc/arm_gic_kvm.c | 4 ++-- hw/intc/arm_gicv3_common.c | 2 +- hw/intc/arm_gicv3_its.c | 4 ++-- hw/intc/arm_gicv3_its_common.c | 2 +- hw/intc/arm_gicv3_its_kvm.c | 4 ++-- hw/intc/arm_gicv3_kvm.c | 4 ++-- hw/intc/xics.c | 2 +- hw/m68k/q800-glue.c | 2 +- hw/misc/djmemc.c | 2 +- hw/misc/iosb.c | 2 +- hw/misc/mac_via.c | 8 ++++---- hw/misc/macio/cuda.c | 4 ++-- hw/misc/macio/pmu.c | 4 ++-- hw/misc/mos6522.c | 2 +- hw/misc/npcm7xx_mft.c | 2 +- hw/misc/npcm7xx_pwm.c | 2 +- hw/misc/stm32l4x5_exti.c | 2 +- hw/misc/stm32l4x5_rcc.c | 10 +++++----- hw/misc/stm32l4x5_syscfg.c | 2 +- hw/misc/xlnx-versal-cframe-reg.c | 2 +- hw/misc/xlnx-versal-crl.c | 2 +- hw/misc/xlnx-versal-pmc-iou-slcr.c | 2 +- hw/misc/xlnx-versal-trng.c | 2 +- hw/misc/xlnx-versal-xramc.c | 2 +- hw/misc/xlnx-zynqmp-apu-ctrl.c | 2 +- hw/misc/xlnx-zynqmp-crf.c | 2 +- hw/misc/zynq_slcr.c | 4 ++-- hw/net/can/xlnx-zynqmp-can.c | 2 +- hw/net/e1000.c | 2 +- hw/net/e1000e.c | 2 +- hw/net/igb.c | 2 +- hw/net/igbvf.c | 2 +- hw/nvram/xlnx-bbram.c | 2 +- hw/nvram/xlnx-versal-efuse-ctrl.c | 2 +- hw/nvram/xlnx-zynqmp-efuse.c | 2 +- hw/pci-bridge/cxl_root_port.c | 4 ++-- hw/pci-bridge/pcie_root_port.c | 2 +- hw/pci-host/bonito.c | 2 +- hw/pci-host/pnv_phb.c | 4 ++-- hw/pci-host/pnv_phb3_msi.c | 4 ++-- hw/pci/pci.c | 4 ++-- hw/rtc/mc146818rtc.c | 2 +- hw/s390x/css-bridge.c | 2 +- hw/sensor/adm1266.c | 2 +- hw/sensor/adm1272.c | 2 +- hw/sensor/isl_pmbus_vr.c | 10 +++++----- hw/sensor/max31785.c | 2 +- hw/sensor/max34451.c | 2 +- hw/ssi/npcm7xx_fiu.c | 2 +- hw/timer/etraxfs_timer.c | 2 +- hw/timer/npcm7xx_timer.c | 2 +- hw/usb/hcd-dwc2.c | 8 ++++---- hw/usb/xlnx-versal-usb2-ctrl-regs.c | 2 +- hw/virtio/virtio-pci.c | 2 +- target/arm/cpu.c | 4 ++-- target/avr/cpu.c | 4 ++-- target/cris/cpu.c | 4 ++-- target/hexagon/cpu.c | 4 ++-- target/i386/cpu.c | 4 ++-- target/loongarch/cpu.c | 4 ++-- target/m68k/cpu.c | 4 ++-- target/microblaze/cpu.c | 4 ++-- target/mips/cpu.c | 4 ++-- target/openrisc/cpu.c | 4 ++-- target/ppc/cpu_init.c | 4 ++-- target/riscv/cpu.c | 4 ++-- target/rx/cpu.c | 4 ++-- target/sh4/cpu.c | 4 ++-- target/sparc/cpu.c | 4 ++-- target/tricore/cpu.c | 4 ++-- target/xtensa/cpu.c | 4 ++-- 94 files changed, 150 insertions(+), 150 deletions(-) diff --git a/include/hw/resettable.h b/include/hw/resettable.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/resettable.h +++ b/include/hw/resettable.h @@ -XXX,XX +XXX,XX @@ typedef enum ResetType { * the callback. */ typedef void (*ResettableEnterPhase)(Object *obj, ResetType type); -typedef void (*ResettableHoldPhase)(Object *obj); -typedef void (*ResettableExitPhase)(Object *obj); +typedef void (*ResettableHoldPhase)(Object *obj, ResetType type); +typedef void (*ResettableExitPhase)(Object *obj, ResetType type); typedef ResettableState * (*ResettableGetState)(Object *obj); typedef void (*ResettableTrFunction)(Object *obj); typedef ResettableTrFunction (*ResettableGetTrFunction)(Object *obj); diff --git a/hw/adc/npcm7xx_adc.c b/hw/adc/npcm7xx_adc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/adc/npcm7xx_adc.c +++ b/hw/adc/npcm7xx_adc.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_adc_enter_reset(Object *obj, ResetType type) npcm7xx_adc_reset(s); } -static void npcm7xx_adc_hold_reset(Object *obj) +static void npcm7xx_adc_hold_reset(Object *obj, ResetType type) { NPCM7xxADCState *s = NPCM7XX_ADC(obj); diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ static int pxa2xx_pic_post_load(void *opaque, int version_id) return 0; } -static void pxa2xx_pic_reset_hold(Object *obj) +static void pxa2xx_pic_reset_hold(Object *obj, ResetType type) { PXA2xxPICState *s = PXA2XX_PIC(obj); diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ static void smmu_base_realize(DeviceState *dev, Error **errp) } } -static void smmu_base_reset_hold(Object *obj) +static void smmu_base_reset_hold(Object *obj, ResetType type) { SMMUState *s = ARM_SMMU(obj); diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static void smmu_init_irq(SMMUv3State *s, SysBusDevice *dev) } } -static void smmu_reset_hold(Object *obj) +static void smmu_reset_hold(Object *obj, ResetType type) { SMMUv3State *s = ARM_SMMUV3(obj); SMMUv3Class *c = ARM_SMMUV3_GET_CLASS(s); if (c->parent_phases.hold) { - c->parent_phases.hold(obj); + c->parent_phases.hold(obj, type); } smmuv3_init_regs(s); diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_sys_reset_enter(Object *obj, ResetType type) s->dcgc[0] = 1; } -static void stellaris_sys_reset_hold(Object *obj) +static void stellaris_sys_reset_hold(Object *obj, ResetType type) { ssys_state *s = STELLARIS_SYS(obj); @@ -XXX,XX +XXX,XX @@ static void stellaris_sys_reset_hold(Object *obj) ssys_calculate_system_clock(s, true); } -static void stellaris_sys_reset_exit(Object *obj) +static void stellaris_sys_reset_exit(Object *obj, ResetType type) { } @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_reset_enter(Object *obj, ResetType type) i2c_end_transfer(s->bus); } -static void stellaris_i2c_reset_hold(Object *obj) +static void stellaris_i2c_reset_hold(Object *obj, ResetType type) { stellaris_i2c_state *s = STELLARIS_I2C(obj); @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_reset_hold(Object *obj) s->mcr = 0; } -static void stellaris_i2c_reset_exit(Object *obj) +static void stellaris_i2c_reset_exit(Object *obj, ResetType type) { stellaris_i2c_state *s = STELLARIS_I2C(obj); @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_trigger(void *opaque, int irq, int level) } } -static void stellaris_adc_reset_hold(Object *obj) +static void stellaris_adc_reset_hold(Object *obj, ResetType type) { StellarisADCState *s = STELLARIS_ADC(obj); int n; diff --git a/hw/audio/asc.c b/hw/audio/asc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/audio/asc.c +++ b/hw/audio/asc.c @@ -XXX,XX +XXX,XX @@ static void asc_fifo_init(ASCFIFOState *fs, int index) g_free(name); } -static void asc_reset_hold(Object *obj) +static void asc_reset_hold(Object *obj, ResetType type) { ASCState *s = ASC(obj); diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ static void cadence_uart_reset_init(Object *obj, ResetType type) s->r[R_TTRIG] = 0x00000020; } -static void cadence_uart_reset_hold(Object *obj) +static void cadence_uart_reset_hold(Object *obj, ResetType type) { CadenceUARTState *s = CADENCE_UART(obj); diff --git a/hw/char/sifive_uart.c b/hw/char/sifive_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/sifive_uart.c +++ b/hw/char/sifive_uart.c @@ -XXX,XX +XXX,XX @@ static void sifive_uart_reset_enter(Object *obj, ResetType type) s->rx_fifo_len = 0; } -static void sifive_uart_reset_hold(Object *obj) +static void sifive_uart_reset_hold(Object *obj, ResetType type) { SiFiveUARTState *s = SIFIVE_UART(obj); qemu_irq_lower(s->irq); diff --git a/hw/core/cpu-common.c b/hw/core/cpu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/cpu-common.c +++ b/hw/core/cpu-common.c @@ -XXX,XX +XXX,XX @@ void cpu_reset(CPUState *cpu) trace_cpu_reset(cpu->cpu_index); } -static void cpu_common_reset_hold(Object *obj) +static void cpu_common_reset_hold(Object *obj, ResetType type) { CPUState *cpu = CPU(obj); CPUClass *cc = CPU_GET_CLASS(cpu); diff --git a/hw/core/qdev.c b/hw/core/qdev.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -XXX,XX +XXX,XX @@ static void device_phases_reset(DeviceState *dev) rc->phases.enter(OBJECT(dev), RESET_TYPE_COLD); } if (rc->phases.hold) { - rc->phases.hold(OBJECT(dev)); + rc->phases.hold(OBJECT(dev), RESET_TYPE_COLD); } if (rc->phases.exit) { - rc->phases.exit(OBJECT(dev)); + rc->phases.exit(OBJECT(dev), RESET_TYPE_COLD); } } diff --git a/hw/core/reset.c b/hw/core/reset.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/reset.c +++ b/hw/core/reset.c @@ -XXX,XX +XXX,XX @@ static ResettableState *legacy_reset_get_state(Object *obj) return &lr->reset_state; } -static void legacy_reset_hold(Object *obj) +static void legacy_reset_hold(Object *obj, ResetType type) { LegacyReset *lr = LEGACY_RESET(obj); diff --git a/hw/core/resettable.c b/hw/core/resettable.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/resettable.c +++ b/hw/core/resettable.c @@ -XXX,XX +XXX,XX @@ static void resettable_phase_hold(Object *obj, void *opaque, ResetType type) trace_resettable_transitional_function(obj, obj_typename); tr_func(obj); } else if (rc->phases.hold) { - rc->phases.hold(obj); + rc->phases.hold(obj, type); } } trace_resettable_phase_hold_end(obj, obj_typename, s->count); @@ -XXX,XX +XXX,XX @@ static void resettable_phase_exit(Object *obj, void *opaque, ResetType type) if (--s->count == 0) { trace_resettable_phase_exit_exec(obj, obj_typename, !!rc->phases.exit); if (rc->phases.exit && !resettable_get_tr_func(rc, obj)) { - rc->phases.exit(obj); + rc->phases.exit(obj, type); } } s->exit_phase_in_progress = false; diff --git a/hw/display/virtio-vga.c b/hw/display/virtio-vga.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/virtio-vga.c +++ b/hw/display/virtio-vga.c @@ -XXX,XX +XXX,XX @@ static void virtio_vga_base_realize(VirtIOPCIProxy *vpci_dev, Error **errp) } } -static void virtio_vga_base_reset_hold(Object *obj) +static void virtio_vga_base_reset_hold(Object *obj, ResetType type) { VirtIOVGABaseClass *klass = VIRTIO_VGA_BASE_GET_CLASS(obj); VirtIOVGABase *vvga = VIRTIO_VGA_BASE(obj); /* reset virtio-gpu */ if (klass->parent_phases.hold) { - klass->parent_phases.hold(obj); + klass->parent_phases.hold(obj, type); } /* reset vga */ diff --git a/hw/gpio/npcm7xx_gpio.c b/hw/gpio/npcm7xx_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/npcm7xx_gpio.c +++ b/hw/gpio/npcm7xx_gpio.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_gpio_enter_reset(Object *obj, ResetType type) s->regs[NPCM7XX_GPIO_ODSC] = s->reset_odsc; } -static void npcm7xx_gpio_hold_reset(Object *obj) +static void npcm7xx_gpio_hold_reset(Object *obj, ResetType type) { NPCM7xxGPIOState *s = NPCM7XX_GPIO(obj); diff --git a/hw/gpio/pl061.c b/hw/gpio/pl061.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/pl061.c +++ b/hw/gpio/pl061.c @@ -XXX,XX +XXX,XX @@ static void pl061_enter_reset(Object *obj, ResetType type) s->amsel = 0; } -static void pl061_hold_reset(Object *obj) +static void pl061_hold_reset(Object *obj, ResetType type) { PL061State *s = PL061(obj); int i, level; diff --git a/hw/gpio/stm32l4x5_gpio.c b/hw/gpio/stm32l4x5_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/stm32l4x5_gpio.c +++ b/hw/gpio/stm32l4x5_gpio.c @@ -XXX,XX +XXX,XX @@ static bool is_push_pull(Stm32l4x5GpioState *s, unsigned pin) return extract32(s->otyper, pin, 1) == 0; } -static void stm32l4x5_gpio_reset_hold(Object *obj) +static void stm32l4x5_gpio_reset_hold(Object *obj, ResetType type) { Stm32l4x5GpioState *s = STM32L4X5_GPIO(obj); diff --git a/hw/hyperv/vmbus.c b/hw/hyperv/vmbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/hyperv/vmbus.c +++ b/hw/hyperv/vmbus.c @@ -XXX,XX +XXX,XX @@ static void vmbus_unrealize(BusState *bus) qemu_mutex_destroy(&vmbus->rx_queue_lock); } -static void vmbus_reset_hold(Object *obj) +static void vmbus_reset_hold(Object *obj, ResetType type) { vmbus_deinit(VMBUS(obj)); } diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/allwinner-i2c.c +++ b/hw/i2c/allwinner-i2c.c @@ -XXX,XX +XXX,XX @@ static inline bool allwinner_i2c_interrupt_is_enabled(AWI2CState *s) return s->cntr & TWI_CNTR_INT_EN; } -static void allwinner_i2c_reset_hold(Object *obj) +static void allwinner_i2c_reset_hold(Object *obj, ResetType type) { AWI2CState *s = AW_I2C(obj); diff --git a/hw/i2c/npcm7xx_smbus.c b/hw/i2c/npcm7xx_smbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/npcm7xx_smbus.c +++ b/hw/i2c/npcm7xx_smbus.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_smbus_enter_reset(Object *obj, ResetType type) s->rx_cur = 0; } -static void npcm7xx_smbus_hold_reset(Object *obj) +static void npcm7xx_smbus_hold_reset(Object *obj, ResetType type) { NPCM7xxSMBusState *s = NPCM7XX_SMBUS(obj); diff --git a/hw/input/adb.c b/hw/input/adb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/adb.c +++ b/hw/input/adb.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_adb_bus = { } }; -static void adb_bus_reset_hold(Object *obj) +static void adb_bus_reset_hold(Object *obj, ResetType type) { ADBBusState *adb_bus = ADB_BUS(obj); diff --git a/hw/input/ps2.c b/hw/input/ps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/ps2.c +++ b/hw/input/ps2.c @@ -XXX,XX +XXX,XX @@ void ps2_write_mouse(PS2MouseState *s, int val) } } -static void ps2_reset_hold(Object *obj) +static void ps2_reset_hold(Object *obj, ResetType type) { PS2State *s = PS2_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void ps2_reset_hold(Object *obj) ps2_reset_queue(s); } -static void ps2_reset_exit(Object *obj) +static void ps2_reset_exit(Object *obj, ResetType type) { PS2State *s = PS2_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void ps2_common_post_load(PS2State *s) q->cwptr = ccount ? (q->rptr + ccount) & (PS2_BUFFER_SIZE - 1) : -1; } -static void ps2_kbd_reset_hold(Object *obj) +static void ps2_kbd_reset_hold(Object *obj, ResetType type) { PS2DeviceClass *ps2dc = PS2_DEVICE_GET_CLASS(obj); PS2KbdState *s = PS2_KBD_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void ps2_kbd_reset_hold(Object *obj) trace_ps2_kbd_reset(s); if (ps2dc->parent_phases.hold) { - ps2dc->parent_phases.hold(obj); + ps2dc->parent_phases.hold(obj, type); } s->scan_enabled = 1; @@ -XXX,XX +XXX,XX @@ static void ps2_kbd_reset_hold(Object *obj) s->modifiers = 0; } -static void ps2_mouse_reset_hold(Object *obj) +static void ps2_mouse_reset_hold(Object *obj, ResetType type) { PS2DeviceClass *ps2dc = PS2_DEVICE_GET_CLASS(obj); PS2MouseState *s = PS2_MOUSE_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void ps2_mouse_reset_hold(Object *obj) trace_ps2_mouse_reset(s); if (ps2dc->parent_phases.hold) { - ps2dc->parent_phases.hold(obj); + ps2dc->parent_phases.hold(obj, type); } s->mouse_status = 0; diff --git a/hw/intc/arm_gic_common.c b/hw/intc/arm_gic_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic_common.c +++ b/hw/intc/arm_gic_common.c @@ -XXX,XX +XXX,XX @@ static inline void arm_gic_common_reset_irq_state(GICState *s, int cidx, } } -static void arm_gic_common_reset_hold(Object *obj) +static void arm_gic_common_reset_hold(Object *obj, ResetType type) { GICState *s = ARM_GIC_COMMON(obj); int i, j; diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic_kvm.c +++ b/hw/intc/arm_gic_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gic_get(GICState *s) } } -static void kvm_arm_gic_reset_hold(Object *obj) +static void kvm_arm_gic_reset_hold(Object *obj, ResetType type) { GICState *s = ARM_GIC_COMMON(obj); KVMARMGICClass *kgc = KVM_ARM_GIC_GET_CLASS(s); if (kgc->parent_phases.hold) { - kgc->parent_phases.hold(obj); + kgc->parent_phases.hold(obj, type); } if (kvm_arm_gic_can_save_restore(s)) { diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_finalize(Object *obj) g_free(s->redist_region_count); } -static void arm_gicv3_common_reset_hold(Object *obj) +static void arm_gicv3_common_reset_hold(Object *obj, ResetType type) { GICv3State *s = ARM_GICV3_COMMON(obj); int i; diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static void gicv3_arm_its_realize(DeviceState *dev, Error **errp) } } -static void gicv3_its_reset_hold(Object *obj) +static void gicv3_its_reset_hold(Object *obj, ResetType type) { GICv3ITSState *s = ARM_GICV3_ITS_COMMON(obj); GICv3ITSClass *c = ARM_GICV3_ITS_GET_CLASS(s); if (c->parent_phases.hold) { - c->parent_phases.hold(obj); + c->parent_phases.hold(obj, type); } /* Quiescent bit reset to 1 */ diff --git a/hw/intc/arm_gicv3_its_common.c b/hw/intc/arm_gicv3_its_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its_common.c +++ b/hw/intc/arm_gicv3_its_common.c @@ -XXX,XX +XXX,XX @@ void gicv3_its_init_mmio(GICv3ITSState *s, const MemoryRegionOps *ops, msi_nonbroken = true; } -static void gicv3_its_common_reset_hold(Object *obj) +static void gicv3_its_common_reset_hold(Object *obj, ResetType type) { GICv3ITSState *s = ARM_GICV3_ITS_COMMON(obj); diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its_kvm.c +++ b/hw/intc/arm_gicv3_its_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_its_post_load(GICv3ITSState *s) GITS_CTLR, &s->ctlr, true, &error_abort); } -static void kvm_arm_its_reset_hold(Object *obj) +static void kvm_arm_its_reset_hold(Object *obj, ResetType type) { GICv3ITSState *s = ARM_GICV3_ITS_COMMON(obj); KVMARMITSClass *c = KVM_ARM_ITS_GET_CLASS(s); int i; if (c->parent_phases.hold) { - c->parent_phases.hold(obj); + c->parent_phases.hold(obj, type); } if (kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS]; } -static void kvm_arm_gicv3_reset_hold(Object *obj) +static void kvm_arm_gicv3_reset_hold(Object *obj, ResetType type) { GICv3State *s = ARM_GICV3_COMMON(obj); KVMARMGICv3Class *kgc = KVM_ARM_GICV3_GET_CLASS(s); @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_reset_hold(Object *obj) DPRINTF("Reset\n"); if (kgc->parent_phases.hold) { - kgc->parent_phases.hold(obj); + kgc->parent_phases.hold(obj, type); } if (s->migration_blocker) { diff --git a/hw/intc/xics.c b/hw/intc/xics.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/xics.c +++ b/hw/intc/xics.c @@ -XXX,XX +XXX,XX @@ static void ics_reset_irq(ICSIRQState *irq) irq->saved_priority = 0xff; } -static void ics_reset_hold(Object *obj) +static void ics_reset_hold(Object *obj, ResetType type) { ICSState *ics = ICS(obj); g_autofree uint8_t *flags = g_malloc(ics->nr_irqs); diff --git a/hw/m68k/q800-glue.c b/hw/m68k/q800-glue.c index XXXXXXX..XXXXXXX 100644 --- a/hw/m68k/q800-glue.c +++ b/hw/m68k/q800-glue.c @@ -XXX,XX +XXX,XX @@ static void glue_nmi_release(void *opaque) GLUE_set_irq(s, GLUE_IRQ_IN_NMI, 0); } -static void glue_reset_hold(Object *obj) +static void glue_reset_hold(Object *obj, ResetType type) { GLUEState *s = GLUE(obj); diff --git a/hw/misc/djmemc.c b/hw/misc/djmemc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/djmemc.c +++ b/hw/misc/djmemc.c @@ -XXX,XX +XXX,XX @@ static void djmemc_init(Object *obj) sysbus_init_mmio(sbd, &s->mem_regs); } -static void djmemc_reset_hold(Object *obj) +static void djmemc_reset_hold(Object *obj, ResetType type) { DJMEMCState *s = DJMEMC(obj); diff --git a/hw/misc/iosb.c b/hw/misc/iosb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iosb.c +++ b/hw/misc/iosb.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps iosb_mmio_ops = { .endianness = DEVICE_BIG_ENDIAN, }; -static void iosb_reset_hold(Object *obj) +static void iosb_reset_hold(Object *obj, ResetType type) { IOSBState *s = IOSB(obj); diff --git a/hw/misc/mac_via.c b/hw/misc/mac_via.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mac_via.c +++ b/hw/misc/mac_via.c @@ -XXX,XX +XXX,XX @@ static int via1_post_load(void *opaque, int version_id) } /* VIA 1 */ -static void mos6522_q800_via1_reset_hold(Object *obj) +static void mos6522_q800_via1_reset_hold(Object *obj, ResetType type) { MOS6522Q800VIA1State *v1s = MOS6522_Q800_VIA1(obj); MOS6522State *ms = MOS6522(v1s); @@ -XXX,XX +XXX,XX @@ static void mos6522_q800_via1_reset_hold(Object *obj) ADBBusState *adb_bus = &v1s->adb_bus; if (mdc->parent_phases.hold) { - mdc->parent_phases.hold(obj); + mdc->parent_phases.hold(obj, type); } ms->timers[0].frequency = VIA_TIMER_FREQ; @@ -XXX,XX +XXX,XX @@ static void mos6522_q800_via2_portB_write(MOS6522State *s) } } -static void mos6522_q800_via2_reset_hold(Object *obj) +static void mos6522_q800_via2_reset_hold(Object *obj, ResetType type) { MOS6522State *ms = MOS6522(obj); MOS6522DeviceClass *mdc = MOS6522_GET_CLASS(ms); if (mdc->parent_phases.hold) { - mdc->parent_phases.hold(obj); + mdc->parent_phases.hold(obj, type); } ms->timers[0].frequency = VIA_TIMER_FREQ; diff --git a/hw/misc/macio/cuda.c b/hw/misc/macio/cuda.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/macio/cuda.c +++ b/hw/misc/macio/cuda.c @@ -XXX,XX +XXX,XX @@ static void mos6522_cuda_portB_write(MOS6522State *s) cuda_update(cs); } -static void mos6522_cuda_reset_hold(Object *obj) +static void mos6522_cuda_reset_hold(Object *obj, ResetType type) { MOS6522State *ms = MOS6522(obj); MOS6522DeviceClass *mdc = MOS6522_GET_CLASS(ms); if (mdc->parent_phases.hold) { - mdc->parent_phases.hold(obj); + mdc->parent_phases.hold(obj, type); } ms->timers[0].frequency = CUDA_TIMER_FREQ; diff --git a/hw/misc/macio/pmu.c b/hw/misc/macio/pmu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/macio/pmu.c +++ b/hw/misc/macio/pmu.c @@ -XXX,XX +XXX,XX @@ static void mos6522_pmu_portB_write(MOS6522State *s) pmu_update(ps); } -static void mos6522_pmu_reset_hold(Object *obj) +static void mos6522_pmu_reset_hold(Object *obj, ResetType type) { MOS6522State *ms = MOS6522(obj); MOS6522PMUState *mps = container_of(ms, MOS6522PMUState, parent_obj); @@ -XXX,XX +XXX,XX @@ static void mos6522_pmu_reset_hold(Object *obj) MOS6522DeviceClass *mdc = MOS6522_GET_CLASS(ms); if (mdc->parent_phases.hold) { - mdc->parent_phases.hold(obj); + mdc->parent_phases.hold(obj, type); } ms->timers[0].frequency = VIA_TIMER_FREQ; diff --git a/hw/misc/mos6522.c b/hw/misc/mos6522.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mos6522.c +++ b/hw/misc/mos6522.c @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_mos6522 = { } }; -static void mos6522_reset_hold(Object *obj) +static void mos6522_reset_hold(Object *obj, ResetType type) { MOS6522State *s = MOS6522(obj); diff --git a/hw/misc/npcm7xx_mft.c b/hw/misc/npcm7xx_mft.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_mft.c +++ b/hw/misc/npcm7xx_mft.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_mft_enter_reset(Object *obj, ResetType type) npcm7xx_mft_reset(s); } -static void npcm7xx_mft_hold_reset(Object *obj) +static void npcm7xx_mft_hold_reset(Object *obj, ResetType type) { NPCM7xxMFTState *s = NPCM7XX_MFT(obj); diff --git a/hw/misc/npcm7xx_pwm.c b/hw/misc/npcm7xx_pwm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_pwm.c +++ b/hw/misc/npcm7xx_pwm.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_pwm_enter_reset(Object *obj, ResetType type) s->piir = 0x00000000; } -static void npcm7xx_pwm_hold_reset(Object *obj) +static void npcm7xx_pwm_hold_reset(Object *obj, ResetType type) { NPCM7xxPWMState *s = NPCM7XX_PWM(obj); int i; diff --git a/hw/misc/stm32l4x5_exti.c b/hw/misc/stm32l4x5_exti.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_exti.c +++ b/hw/misc/stm32l4x5_exti.c @@ -XXX,XX +XXX,XX @@ static unsigned configurable_mask(unsigned bank) return valid_mask(bank) & ~exti_romask[bank]; } -static void stm32l4x5_exti_reset_hold(Object *obj) +static void stm32l4x5_exti_reset_hold(Object *obj, ResetType type) { Stm32l4x5ExtiState *s = STM32L4X5_EXTI(obj); diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_rcc.c +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ static void clock_mux_reset_enter(Object *obj, ResetType type) set_clock_mux_init_info(s, s->id); } -static void clock_mux_reset_hold(Object *obj) +static void clock_mux_reset_hold(Object *obj, ResetType type) { RccClockMuxState *s = RCC_CLOCK_MUX(obj); clock_mux_update(s, true); } -static void clock_mux_reset_exit(Object *obj) +static void clock_mux_reset_exit(Object *obj, ResetType type) { RccClockMuxState *s = RCC_CLOCK_MUX(obj); clock_mux_update(s, false); @@ -XXX,XX +XXX,XX @@ static void pll_reset_enter(Object *obj, ResetType type) set_pll_init_info(s, s->id); } -static void pll_reset_hold(Object *obj) +static void pll_reset_hold(Object *obj, ResetType type) { RccPllState *s = RCC_PLL(obj); pll_update(s, true); } -static void pll_reset_exit(Object *obj) +static void pll_reset_exit(Object *obj, ResetType type) { RccPllState *s = RCC_PLL(obj); pll_update(s, false); @@ -XXX,XX +XXX,XX @@ static void rcc_update_csr(Stm32l4x5RccState *s) rcc_update_irq(s); } -static void stm32l4x5_rcc_reset_hold(Object *obj) +static void stm32l4x5_rcc_reset_hold(Object *obj, ResetType type) { Stm32l4x5RccState *s = STM32L4X5_RCC(obj); s->cr = 0x00000063; diff --git a/hw/misc/stm32l4x5_syscfg.c b/hw/misc/stm32l4x5_syscfg.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_syscfg.c +++ b/hw/misc/stm32l4x5_syscfg.c @@ -XXX,XX +XXX,XX @@ #define NUM_LINES_PER_EXTICR_REG 4 -static void stm32l4x5_syscfg_hold_reset(Object *obj) +static void stm32l4x5_syscfg_hold_reset(Object *obj, ResetType type) { Stm32l4x5SyscfgState *s = STM32L4X5_SYSCFG(obj); diff --git a/hw/misc/xlnx-versal-cframe-reg.c b/hw/misc/xlnx-versal-cframe-reg.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-versal-cframe-reg.c +++ b/hw/misc/xlnx-versal-cframe-reg.c @@ -XXX,XX +XXX,XX @@ static void cframe_reg_reset_enter(Object *obj, ResetType type) } } -static void cframe_reg_reset_hold(Object *obj) +static void cframe_reg_reset_hold(Object *obj, ResetType type) { XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(obj); diff --git a/hw/misc/xlnx-versal-crl.c b/hw/misc/xlnx-versal-crl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-versal-crl.c +++ b/hw/misc/xlnx-versal-crl.c @@ -XXX,XX +XXX,XX @@ static void crl_reset_enter(Object *obj, ResetType type) } } -static void crl_reset_hold(Object *obj) +static void crl_reset_hold(Object *obj, ResetType type) { XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); diff --git a/hw/misc/xlnx-versal-pmc-iou-slcr.c b/hw/misc/xlnx-versal-pmc-iou-slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-versal-pmc-iou-slcr.c +++ b/hw/misc/xlnx-versal-pmc-iou-slcr.c @@ -XXX,XX +XXX,XX @@ static void xlnx_versal_pmc_iou_slcr_reset_init(Object *obj, ResetType type) } } -static void xlnx_versal_pmc_iou_slcr_reset_hold(Object *obj) +static void xlnx_versal_pmc_iou_slcr_reset_hold(Object *obj, ResetType type) { XlnxVersalPmcIouSlcr *s = XILINX_VERSAL_PMC_IOU_SLCR(obj); diff --git a/hw/misc/xlnx-versal-trng.c b/hw/misc/xlnx-versal-trng.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-versal-trng.c +++ b/hw/misc/xlnx-versal-trng.c @@ -XXX,XX +XXX,XX @@ static void trng_unrealize(DeviceState *dev) s->prng = NULL; } -static void trng_reset_hold(Object *obj) +static void trng_reset_hold(Object *obj, ResetType type) { trng_reset(XLNX_VERSAL_TRNG(obj)); } diff --git a/hw/misc/xlnx-versal-xramc.c b/hw/misc/xlnx-versal-xramc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-versal-xramc.c +++ b/hw/misc/xlnx-versal-xramc.c @@ -XXX,XX +XXX,XX @@ static void xram_ctrl_reset_enter(Object *obj, ResetType type) ARRAY_FIELD_DP32(s->regs, XRAM_IMP, SIZE, s->cfg.encoded_size); } -static void xram_ctrl_reset_hold(Object *obj) +static void xram_ctrl_reset_hold(Object *obj, ResetType type) { XlnxXramCtrl *s = XLNX_XRAM_CTRL(obj); diff --git a/hw/misc/xlnx-zynqmp-apu-ctrl.c b/hw/misc/xlnx-zynqmp-apu-ctrl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-zynqmp-apu-ctrl.c +++ b/hw/misc/xlnx-zynqmp-apu-ctrl.c @@ -XXX,XX +XXX,XX @@ static void zynqmp_apu_reset_enter(Object *obj, ResetType type) s->cpu_in_wfi = 0; } -static void zynqmp_apu_reset_hold(Object *obj) +static void zynqmp_apu_reset_hold(Object *obj, ResetType type) { XlnxZynqMPAPUCtrl *s = XLNX_ZYNQMP_APU_CTRL(obj); diff --git a/hw/misc/xlnx-zynqmp-crf.c b/hw/misc/xlnx-zynqmp-crf.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/xlnx-zynqmp-crf.c +++ b/hw/misc/xlnx-zynqmp-crf.c @@ -XXX,XX +XXX,XX @@ static void crf_reset_enter(Object *obj, ResetType type) } } -static void crf_reset_hold(Object *obj) +static void crf_reset_hold(Object *obj, ResetType type) { XlnxZynqMPCRF *s = XLNX_ZYNQMP_CRF(obj); ir_update_irq(s); diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset_init(Object *obj, ResetType type) s->regs[R_DDRIOB + 12] = 0x00000021; } -static void zynq_slcr_reset_hold(Object *obj) +static void zynq_slcr_reset_hold(Object *obj, ResetType type) { ZynqSLCRState *s = ZYNQ_SLCR(obj); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset_hold(Object *obj) zynq_slcr_propagate_clocks(s); } -static void zynq_slcr_reset_exit(Object *obj) +static void zynq_slcr_reset_exit(Object *obj, ResetType type) { ZynqSLCRState *s = ZYNQ_SLCR(obj); diff --git a/hw/net/can/xlnx-zynqmp-can.c b/hw/net/can/xlnx-zynqmp-can.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/xlnx-zynqmp-can.c +++ b/hw/net/can/xlnx-zynqmp-can.c @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_can_reset_init(Object *obj, ResetType type) ptimer_transaction_commit(s->can_timer); } -static void xlnx_zynqmp_can_reset_hold(Object *obj) +static void xlnx_zynqmp_can_reset_hold(Object *obj, ResetType type) { XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); unsigned int i; diff --git a/hw/net/e1000.c b/hw/net/e1000.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/e1000.c +++ b/hw/net/e1000.c @@ -XXX,XX +XXX,XX @@ static bool e1000_vet_init_need(void *opaque) return chkflag(VET); } -static void e1000_reset_hold(Object *obj) +static void e1000_reset_hold(Object *obj, ResetType type) { E1000State *d = E1000(obj); E1000BaseClass *edc = E1000_GET_CLASS(d); diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/e1000e.c +++ b/hw/net/e1000e.c @@ -XXX,XX +XXX,XX @@ static void e1000e_pci_uninit(PCIDevice *pci_dev) msi_uninit(pci_dev); } -static void e1000e_qdev_reset_hold(Object *obj) +static void e1000e_qdev_reset_hold(Object *obj, ResetType type) { E1000EState *s = E1000E(obj); diff --git a/hw/net/igb.c b/hw/net/igb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/igb.c +++ b/hw/net/igb.c @@ -XXX,XX +XXX,XX @@ static void igb_pci_uninit(PCIDevice *pci_dev) msi_uninit(pci_dev); } -static void igb_qdev_reset_hold(Object *obj) +static void igb_qdev_reset_hold(Object *obj, ResetType type) { IGBState *s = IGB(obj); diff --git a/hw/net/igbvf.c b/hw/net/igbvf.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/igbvf.c +++ b/hw/net/igbvf.c @@ -XXX,XX +XXX,XX @@ static void igbvf_pci_realize(PCIDevice *dev, Error **errp) pcie_ari_init(dev, 0x150); } -static void igbvf_qdev_reset_hold(Object *obj) +static void igbvf_qdev_reset_hold(Object *obj, ResetType type) { PCIDevice *vf = PCI_DEVICE(obj); diff --git a/hw/nvram/xlnx-bbram.c b/hw/nvram/xlnx-bbram.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-bbram.c +++ b/hw/nvram/xlnx-bbram.c @@ -XXX,XX +XXX,XX @@ static RegisterAccessInfo bbram_ctrl_regs_info[] = { } }; -static void bbram_ctrl_reset_hold(Object *obj) +static void bbram_ctrl_reset_hold(Object *obj, ResetType type) { XlnxBBRam *s = XLNX_BBRAM(obj); unsigned int i; diff --git a/hw/nvram/xlnx-versal-efuse-ctrl.c b/hw/nvram/xlnx-versal-efuse-ctrl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-versal-efuse-ctrl.c +++ b/hw/nvram/xlnx-versal-efuse-ctrl.c @@ -XXX,XX +XXX,XX @@ static void efuse_ctrl_register_reset(RegisterInfo *reg) register_reset(reg); } -static void efuse_ctrl_reset_hold(Object *obj) +static void efuse_ctrl_reset_hold(Object *obj, ResetType type) { XlnxVersalEFuseCtrl *s = XLNX_VERSAL_EFUSE_CTRL(obj); unsigned int i; diff --git a/hw/nvram/xlnx-zynqmp-efuse.c b/hw/nvram/xlnx-zynqmp-efuse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/xlnx-zynqmp-efuse.c +++ b/hw/nvram/xlnx-zynqmp-efuse.c @@ -XXX,XX +XXX,XX @@ static void zynqmp_efuse_register_reset(RegisterInfo *reg) register_reset(reg); } -static void zynqmp_efuse_reset_hold(Object *obj) +static void zynqmp_efuse_reset_hold(Object *obj, ResetType type) { XlnxZynqMPEFuse *s = XLNX_ZYNQMP_EFUSE(obj); unsigned int i; diff --git a/hw/pci-bridge/cxl_root_port.c b/hw/pci-bridge/cxl_root_port.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-bridge/cxl_root_port.c +++ b/hw/pci-bridge/cxl_root_port.c @@ -XXX,XX +XXX,XX @@ static void cxl_rp_realize(DeviceState *dev, Error **errp) component_bar); } -static void cxl_rp_reset_hold(Object *obj) +static void cxl_rp_reset_hold(Object *obj, ResetType type) { PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(obj); CXLRootPort *crp = CXL_ROOT_PORT(obj); if (rpc->parent_phases.hold) { - rpc->parent_phases.hold(obj); + rpc->parent_phases.hold(obj, type); } latch_registers(crp); diff --git a/hw/pci-bridge/pcie_root_port.c b/hw/pci-bridge/pcie_root_port.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-bridge/pcie_root_port.c +++ b/hw/pci-bridge/pcie_root_port.c @@ -XXX,XX +XXX,XX @@ static void rp_write_config(PCIDevice *d, uint32_t address, pcie_aer_root_write_config(d, address, val, len, root_cmd); } -static void rp_reset_hold(Object *obj) +static void rp_reset_hold(Object *obj, ResetType type) { PCIDevice *d = PCI_DEVICE(obj); DeviceState *qdev = DEVICE(obj); diff --git a/hw/pci-host/bonito.c b/hw/pci-host/bonito.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/bonito.c +++ b/hw/pci-host/bonito.c @@ -XXX,XX +XXX,XX @@ static int pci_bonito_map_irq(PCIDevice *pci_dev, int irq_num) } } -static void bonito_reset_hold(Object *obj) +static void bonito_reset_hold(Object *obj, ResetType type) { PCIBonitoState *s = PCI_BONITO(obj); uint32_t val = 0; diff --git a/hw/pci-host/pnv_phb.c b/hw/pci-host/pnv_phb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/pnv_phb.c +++ b/hw/pci-host/pnv_phb.c @@ -XXX,XX +XXX,XX @@ static void pnv_phb_class_init(ObjectClass *klass, void *data) dc->user_creatable = true; } -static void pnv_phb_root_port_reset_hold(Object *obj) +static void pnv_phb_root_port_reset_hold(Object *obj, ResetType type) { PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(obj); PnvPHBRootPort *phb_rp = PNV_PHB_ROOT_PORT(obj); @@ -XXX,XX +XXX,XX @@ static void pnv_phb_root_port_reset_hold(Object *obj) uint8_t *conf = d->config; if (rpc->parent_phases.hold) { - rpc->parent_phases.hold(obj); + rpc->parent_phases.hold(obj, type); } if (phb_rp->version == 3) { diff --git a/hw/pci-host/pnv_phb3_msi.c b/hw/pci-host/pnv_phb3_msi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/pnv_phb3_msi.c +++ b/hw/pci-host/pnv_phb3_msi.c @@ -XXX,XX +XXX,XX @@ static void phb3_msi_resend(ICSState *ics) } } -static void phb3_msi_reset_hold(Object *obj) +static void phb3_msi_reset_hold(Object *obj, ResetType type) { Phb3MsiState *msi = PHB3_MSI(obj); ICSStateClass *icsc = ICS_GET_CLASS(obj); if (icsc->parent_phases.hold) { - icsc->parent_phases.hold(obj); + icsc->parent_phases.hold(obj, type); } memset(msi->rba, 0, sizeof(msi->rba)); diff --git a/hw/pci/pci.c b/hw/pci/pci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -XXX,XX +XXX,XX @@ bool pci_available = true; static char *pcibus_get_dev_path(DeviceState *dev); static char *pcibus_get_fw_dev_path(DeviceState *dev); -static void pcibus_reset_hold(Object *obj); +static void pcibus_reset_hold(Object *obj, ResetType type); static bool pcie_has_upstream_port(PCIDevice *dev); static Property pci_props[] = { @@ -XXX,XX +XXX,XX @@ void pci_device_reset(PCIDevice *dev) * Called via bus_cold_reset on RST# assert, after the devices * have been reset device_cold_reset-ed already. */ -static void pcibus_reset_hold(Object *obj) +static void pcibus_reset_hold(Object *obj, ResetType type) { PCIBus *bus = PCI_BUS(obj); int i; diff --git a/hw/rtc/mc146818rtc.c b/hw/rtc/mc146818rtc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/mc146818rtc.c +++ b/hw/rtc/mc146818rtc.c @@ -XXX,XX +XXX,XX @@ static void rtc_reset_enter(Object *obj, ResetType type) } } -static void rtc_reset_hold(Object *obj) +static void rtc_reset_hold(Object *obj, ResetType type) { MC146818RtcState *s = MC146818_RTC(obj); diff --git a/hw/s390x/css-bridge.c b/hw/s390x/css-bridge.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/css-bridge.c +++ b/hw/s390x/css-bridge.c @@ -XXX,XX +XXX,XX @@ static void ccw_device_unplug(HotplugHandler *hotplug_dev, qdev_unrealize(dev); } -static void virtual_css_bus_reset_hold(Object *obj) +static void virtual_css_bus_reset_hold(Object *obj, ResetType type) { /* This should actually be modelled via the generic css */ css_reset(); diff --git a/hw/sensor/adm1266.c b/hw/sensor/adm1266.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sensor/adm1266.c +++ b/hw/sensor/adm1266.c @@ -XXX,XX +XXX,XX @@ static const uint8_t adm1266_ic_device_id[] = {0x03, 0x41, 0x12, 0x66}; static const uint8_t adm1266_ic_device_rev[] = {0x08, 0x01, 0x08, 0x07, 0x0, 0x0, 0x07, 0x41, 0x30}; -static void adm1266_exit_reset(Object *obj) +static void adm1266_exit_reset(Object *obj, ResetType type) { ADM1266State *s = ADM1266(obj); PMBusDevice *pmdev = PMBUS_DEVICE(obj); diff --git a/hw/sensor/adm1272.c b/hw/sensor/adm1272.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sensor/adm1272.c +++ b/hw/sensor/adm1272.c @@ -XXX,XX +XXX,XX @@ static uint32_t adm1272_direct_to_watts(uint16_t value) return pmbus_direct_mode2data(c, value); } -static void adm1272_exit_reset(Object *obj) +static void adm1272_exit_reset(Object *obj, ResetType type) { ADM1272State *s = ADM1272(obj); PMBusDevice *pmdev = PMBUS_DEVICE(obj); diff --git a/hw/sensor/isl_pmbus_vr.c b/hw/sensor/isl_pmbus_vr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sensor/isl_pmbus_vr.c +++ b/hw/sensor/isl_pmbus_vr.c @@ -XXX,XX +XXX,XX @@ static void isl_pmbus_vr_set(Object *obj, Visitor *v, const char *name, pmbus_check_limits(pmdev); } -static void isl_pmbus_vr_exit_reset(Object *obj) +static void isl_pmbus_vr_exit_reset(Object *obj, ResetType type) { PMBusDevice *pmdev = PMBUS_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void isl_pmbus_vr_exit_reset(Object *obj) } /* The raa228000 uses different direct mode coefficients from most isl devices */ -static void raa228000_exit_reset(Object *obj) +static void raa228000_exit_reset(Object *obj, ResetType type) { PMBusDevice *pmdev = PMBUS_DEVICE(obj); - isl_pmbus_vr_exit_reset(obj); + isl_pmbus_vr_exit_reset(obj, type); pmdev->pages[0].read_iout = 0; pmdev->pages[0].read_pout = 0; @@ -XXX,XX +XXX,XX @@ static void raa228000_exit_reset(Object *obj) pmdev->pages[0].read_temperature_3 = 0; } -static void isl69259_exit_reset(Object *obj) +static void isl69259_exit_reset(Object *obj, ResetType type) { ISLState *s = ISL69260(obj); static const uint8_t ic_device_id[] = {0x04, 0x00, 0x81, 0xD2, 0x49, 0x3c}; g_assert(sizeof(ic_device_id) <= sizeof(s->ic_device_id)); - isl_pmbus_vr_exit_reset(obj); + isl_pmbus_vr_exit_reset(obj, type); s->ic_device_id_len = sizeof(ic_device_id); memcpy(s->ic_device_id, ic_device_id, sizeof(ic_device_id)); diff --git a/hw/sensor/max31785.c b/hw/sensor/max31785.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sensor/max31785.c +++ b/hw/sensor/max31785.c @@ -XXX,XX +XXX,XX @@ static int max31785_write_data(PMBusDevice *pmdev, const uint8_t *buf, return 0; } -static void max31785_exit_reset(Object *obj) +static void max31785_exit_reset(Object *obj, ResetType type) { PMBusDevice *pmdev = PMBUS_DEVICE(obj); MAX31785State *s = MAX31785(obj); diff --git a/hw/sensor/max34451.c b/hw/sensor/max34451.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sensor/max34451.c +++ b/hw/sensor/max34451.c @@ -XXX,XX +XXX,XX @@ static inline void *memset_word(void *s, uint16_t c, size_t n) return s; } -static void max34451_exit_reset(Object *obj) +static void max34451_exit_reset(Object *obj, ResetType type) { PMBusDevice *pmdev = PMBUS_DEVICE(obj); MAX34451State *s = MAX34451(obj); diff --git a/hw/ssi/npcm7xx_fiu.c b/hw/ssi/npcm7xx_fiu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/npcm7xx_fiu.c +++ b/hw/ssi/npcm7xx_fiu.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_fiu_enter_reset(Object *obj, ResetType type) s->regs[NPCM7XX_FIU_CFG] = 0x0000000b; } -static void npcm7xx_fiu_hold_reset(Object *obj) +static void npcm7xx_fiu_hold_reset(Object *obj, ResetType type) { NPCM7xxFIUState *s = NPCM7XX_FIU(obj); int i; diff --git a/hw/timer/etraxfs_timer.c b/hw/timer/etraxfs_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/etraxfs_timer.c +++ b/hw/timer/etraxfs_timer.c @@ -XXX,XX +XXX,XX @@ static void etraxfs_timer_reset_enter(Object *obj, ResetType type) t->rw_intr_mask = 0; } -static void etraxfs_timer_reset_hold(Object *obj) +static void etraxfs_timer_reset_hold(Object *obj, ResetType type) { ETRAXTimerState *t = ETRAX_TIMER(obj); diff --git a/hw/timer/npcm7xx_timer.c b/hw/timer/npcm7xx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/npcm7xx_timer.c +++ b/hw/timer/npcm7xx_timer.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_watchdog_timer_expired(void *opaque) } } -static void npcm7xx_timer_hold_reset(Object *obj) +static void npcm7xx_timer_hold_reset(Object *obj, ResetType type) { NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(obj); int i; diff --git a/hw/usb/hcd-dwc2.c b/hw/usb/hcd-dwc2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-dwc2.c +++ b/hw/usb/hcd-dwc2.c @@ -XXX,XX +XXX,XX @@ static void dwc2_reset_enter(Object *obj, ResetType type) } } -static void dwc2_reset_hold(Object *obj) +static void dwc2_reset_hold(Object *obj, ResetType type) { DWC2Class *c = DWC2_USB_GET_CLASS(obj); DWC2State *s = DWC2_USB(obj); @@ -XXX,XX +XXX,XX @@ static void dwc2_reset_hold(Object *obj) trace_usb_dwc2_reset_hold(); if (c->parent_phases.hold) { - c->parent_phases.hold(obj); + c->parent_phases.hold(obj, type); } dwc2_update_irq(s); } -static void dwc2_reset_exit(Object *obj) +static void dwc2_reset_exit(Object *obj, ResetType type) { DWC2Class *c = DWC2_USB_GET_CLASS(obj); DWC2State *s = DWC2_USB(obj); @@ -XXX,XX +XXX,XX @@ static void dwc2_reset_exit(Object *obj) trace_usb_dwc2_reset_exit(); if (c->parent_phases.exit) { - c->parent_phases.exit(obj); + c->parent_phases.exit(obj, type); } s->hprt0 = HPRT0_PWR; diff --git a/hw/usb/xlnx-versal-usb2-ctrl-regs.c b/hw/usb/xlnx-versal-usb2-ctrl-regs.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/xlnx-versal-usb2-ctrl-regs.c +++ b/hw/usb/xlnx-versal-usb2-ctrl-regs.c @@ -XXX,XX +XXX,XX @@ static void usb2_ctrl_regs_reset_init(Object *obj, ResetType type) } } -static void usb2_ctrl_regs_reset_hold(Object *obj) +static void usb2_ctrl_regs_reset_hold(Object *obj, ResetType type) { VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(obj); diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -XXX,XX +XXX,XX @@ static void virtio_pci_reset(DeviceState *qdev) } } -static void virtio_pci_bus_reset_hold(Object *obj) +static void virtio_pci_bus_reset_hold(Object *obj, ResetType type) { PCIDevice *dev = PCI_DEVICE(obj); DeviceState *qdev = DEVICE(obj); 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 cp_reg_check_reset(gpointer key, gpointer value, gpointer opaque) assert(oldvalue == newvalue); } -static void arm_cpu_reset_hold(Object *obj) +static void arm_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj) CPUARMState *env = &cpu->env; if (acc->parent_phases.hold) { - acc->parent_phases.hold(obj); + acc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUARMState, end_reset_fields)); diff --git a/target/avr/cpu.c b/target/avr/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/avr/cpu.c +++ b/target/avr/cpu.c @@ -XXX,XX +XXX,XX @@ static void avr_restore_state_to_opc(CPUState *cs, cpu_env(cs)->pc_w = data[0]; } -static void avr_cpu_reset_hold(Object *obj) +static void avr_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); AVRCPU *cpu = AVR_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void avr_cpu_reset_hold(Object *obj) CPUAVRState *env = &cpu->env; if (mcc->parent_phases.hold) { - mcc->parent_phases.hold(obj); + mcc->parent_phases.hold(obj, type); } env->pc_w = 0; diff --git a/target/cris/cpu.c b/target/cris/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/cris/cpu.c +++ b/target/cris/cpu.c @@ -XXX,XX +XXX,XX @@ static int cris_cpu_mmu_index(CPUState *cs, bool ifetch) return !!(cpu_env(cs)->pregs[PR_CCS] & U_FLAG); } -static void cris_cpu_reset_hold(Object *obj) +static void cris_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); CRISCPUClass *ccc = CRIS_CPU_GET_CLASS(obj); @@ -XXX,XX +XXX,XX @@ static void cris_cpu_reset_hold(Object *obj) uint32_t vr; if (ccc->parent_phases.hold) { - ccc->parent_phases.hold(obj); + ccc->parent_phases.hold(obj, type); } vr = env->pregs[PR_VR]; diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -XXX,XX +XXX,XX @@ static void hexagon_restore_state_to_opc(CPUState *cs, cpu_env(cs)->gpr[HEX_REG_PC] = data[0]; } -static void hexagon_cpu_reset_hold(Object *obj) +static void hexagon_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); HexagonCPUClass *mcc = HEXAGON_CPU_GET_CLASS(obj); CPUHexagonState *env = cpu_env(cs); if (mcc->parent_phases.hold) { - mcc->parent_phases.hold(obj); + mcc->parent_phases.hold(obj, type); } set_default_nan_mode(1, &env->fp_status); diff --git a/target/i386/cpu.c b/target/i386/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -XXX,XX +XXX,XX @@ static void x86_cpu_set_sgxlepubkeyhash(CPUX86State *env) #endif } -static void x86_cpu_reset_hold(Object *obj) +static void x86_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); X86CPU *cpu = X86_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void x86_cpu_reset_hold(Object *obj) int i; if (xcc->parent_phases.hold) { - xcc->parent_phases.hold(obj); + xcc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUX86State, end_reset_fields)); diff --git a/target/loongarch/cpu.c b/target/loongarch/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/cpu.c +++ b/target/loongarch/cpu.c @@ -XXX,XX +XXX,XX @@ static void loongarch_max_initfn(Object *obj) loongarch_la464_initfn(obj); } -static void loongarch_cpu_reset_hold(Object *obj) +static void loongarch_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); LoongArchCPUClass *lacc = LOONGARCH_CPU_GET_CLASS(obj); CPULoongArchState *env = cpu_env(cs); if (lacc->parent_phases.hold) { - lacc->parent_phases.hold(obj); + lacc->parent_phases.hold(obj, type); } env->fcsr0_mask = FCSR0_M1 | FCSR0_M2 | FCSR0_M3; diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static void m68k_unset_feature(CPUM68KState *env, int feature) env->features &= ~BIT_ULL(feature); } -static void m68k_cpu_reset_hold(Object *obj) +static void m68k_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); M68kCPUClass *mcc = M68K_CPU_GET_CLASS(obj); @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj) int i; if (mcc->parent_phases.hold) { - mcc->parent_phases.hold(obj); + mcc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUM68KState, end_reset_fields)); diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -XXX,XX +XXX,XX @@ static void microblaze_cpu_set_irq(void *opaque, int irq, int level) } #endif -static void mb_cpu_reset_hold(Object *obj) +static void mb_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); MicroBlazeCPU *cpu = MICROBLAZE_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void mb_cpu_reset_hold(Object *obj) CPUMBState *env = &cpu->env; if (mcc->parent_phases.hold) { - mcc->parent_phases.hold(obj); + mcc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUMBState, end_reset_fields)); diff --git a/target/mips/cpu.c b/target/mips/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/cpu.c +++ b/target/mips/cpu.c @@ -XXX,XX +XXX,XX @@ static int mips_cpu_mmu_index(CPUState *cs, bool ifunc) #include "cpu-defs.c.inc" -static void mips_cpu_reset_hold(Object *obj) +static void mips_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); MIPSCPU *cpu = MIPS_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void mips_cpu_reset_hold(Object *obj) CPUMIPSState *env = &cpu->env; if (mcc->parent_phases.hold) { - mcc->parent_phases.hold(obj); + mcc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUMIPSState, end_reset_fields)); diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -XXX,XX +XXX,XX @@ static void openrisc_disas_set_info(CPUState *cpu, disassemble_info *info) info->print_insn = print_insn_or1k; } -static void openrisc_cpu_reset_hold(Object *obj) +static void openrisc_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); OpenRISCCPU *cpu = OPENRISC_CPU(cs); OpenRISCCPUClass *occ = OPENRISC_CPU_GET_CLASS(obj); if (occ->parent_phases.hold) { - occ->parent_phases.hold(obj); + occ->parent_phases.hold(obj, type); } memset(&cpu->env, 0, offsetof(CPUOpenRISCState, end_reset_fields)); diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static int ppc_cpu_mmu_index(CPUState *cs, bool ifetch) return ppc_env_mmu_index(cpu_env(cs), ifetch); } -static void ppc_cpu_reset_hold(Object *obj) +static void ppc_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); PowerPCCPU *cpu = POWERPC_CPU(cs); @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj) int i; if (pcc->parent_phases.hold) { - pcc->parent_phases.hold(obj); + pcc->parent_phases.hold(obj, type); } msr = (target_ulong)0; diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static int riscv_cpu_mmu_index(CPUState *cs, bool ifetch) return riscv_env_mmu_index(cpu_env(cs), ifetch); } -static void riscv_cpu_reset_hold(Object *obj) +static void riscv_cpu_reset_hold(Object *obj, ResetType type) { #ifndef CONFIG_USER_ONLY uint8_t iprio; @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj) CPURISCVState *env = &cpu->env; if (mcc->parent_phases.hold) { - mcc->parent_phases.hold(obj); + mcc->parent_phases.hold(obj, type); } #ifndef CONFIG_USER_ONLY env->misa_mxl = mcc->misa_mxl_max; diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ static int riscv_cpu_mmu_index(CPUState *cs, bool ifunc) return 0; } -static void rx_cpu_reset_hold(Object *obj) +static void rx_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); RXCPUClass *rcc = RX_CPU_GET_CLASS(obj); @@ -XXX,XX +XXX,XX @@ static void rx_cpu_reset_hold(Object *obj) uint32_t *resetvec; if (rcc->parent_phases.hold) { - rcc->parent_phases.hold(obj); + rcc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPURXState, end_reset_fields)); diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static int sh4_cpu_mmu_index(CPUState *cs, bool ifetch) } } -static void superh_cpu_reset_hold(Object *obj) +static void superh_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); SuperHCPUClass *scc = SUPERH_CPU_GET_CLASS(obj); CPUSH4State *env = cpu_env(cs); if (scc->parent_phases.hold) { - scc->parent_phases.hold(obj); + scc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUSH4State, end_reset_fields)); diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ //#define DEBUG_FEATURES -static void sparc_cpu_reset_hold(Object *obj) +static void sparc_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); SPARCCPUClass *scc = SPARC_CPU_GET_CLASS(obj); CPUSPARCState *env = cpu_env(cs); if (scc->parent_phases.hold) { - scc->parent_phases.hold(obj); + scc->parent_phases.hold(obj, type); } memset(env, 0, offsetof(CPUSPARCState, end_reset_fields)); diff --git a/target/tricore/cpu.c b/target/tricore/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/cpu.c +++ b/target/tricore/cpu.c @@ -XXX,XX +XXX,XX @@ static void tricore_restore_state_to_opc(CPUState *cs, cpu_env(cs)->PC = data[0]; } -static void tricore_cpu_reset_hold(Object *obj) +static void tricore_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); TriCoreCPUClass *tcc = TRICORE_CPU_GET_CLASS(obj); if (tcc->parent_phases.hold) { - tcc->parent_phases.hold(obj); + tcc->parent_phases.hold(obj, type); } cpu_state_reset(cpu_env(cs)); diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ bool xtensa_abi_call0(void) } #endif -static void xtensa_cpu_reset_hold(Object *obj) +static void xtensa_cpu_reset_hold(Object *obj, ResetType type) { CPUState *cs = CPU(obj); XtensaCPUClass *xcc = XTENSA_CPU_GET_CLASS(obj); @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_reset_hold(Object *obj) XTENSA_OPTION_DFP_COPROCESSOR); if (xcc->parent_phases.hold) { - xcc->parent_phases.hold(obj); + xcc->parent_phases.hold(obj, type); } env->pc = env->config->exception_vector[EXC_RESET0 + env->static_vectors]; -- 2.34.1 Update the reset documentation's example code to match the new API for the hold and exit phase method APIs where they take a ResetType argument. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20240412160809.1260625-6-peter.maydell@linaro.org --- docs/devel/reset.rst | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/devel/reset.rst b/docs/devel/reset.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/reset.rst +++ b/docs/devel/reset.rst @@ -XXX,XX +XXX,XX @@ in reset. mydev->var = 0; } - static void mydev_reset_hold(Object *obj) + static void mydev_reset_hold(Object *obj, ResetType type) { MyDevClass *myclass = MYDEV_GET_CLASS(obj); MyDevState *mydev = MYDEV(obj); /* call parent class hold phase */ if (myclass->parent_phases.hold) { - myclass->parent_phases.hold(obj); + myclass->parent_phases.hold(obj, type); } /* set an IO */ qemu_set_irq(mydev->irq, 1); } - static void mydev_reset_exit(Object *obj) + static void mydev_reset_exit(Object *obj, ResetType type) { MyDevClass *myclass = MYDEV_GET_CLASS(obj); MyDevState *mydev = MYDEV(obj); /* call parent class exit phase */ if (myclass->parent_phases.exit) { - myclass->parent_phases.exit(obj); + myclass->parent_phases.exit(obj, type); } /* clear an IO */ qemu_set_irq(mydev->irq, 0); -- 2.34.1 Some devices and machines need to handle the reset before a vmsave snapshot is loaded differently -- the main user is the handling of RNG seed information, which does not want to put a new RNG seed into a ROM blob when we are doing a snapshot load. Currently this kind of reset handling is supported only for: * TYPE_MACHINE reset methods, which take a ShutdownCause argument * reset functions registered with qemu_register_reset_nosnapshotload To allow a three-phase-reset device to also distinguish "snapshot load" reset from the normal kind, add a new ResetType RESET_TYPE_SNAPSHOT_LOAD. All our existing reset methods ignore the reset type, so we don't need to update any device code. Add the enum type, and make qemu_devices_reset() use the right reset type for the ShutdownCause it is passed. This allows us to get rid of the device_reset_reason global we were using to implement qemu_register_reset_nosnapshotload(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20240412160809.1260625-7-peter.maydell@linaro.org --- docs/devel/reset.rst | 17 ++++++++++++++--- include/hw/resettable.h | 1 + hw/core/reset.c | 15 ++++----------- hw/core/resettable.c | 4 ---- 4 files changed, 19 insertions(+), 18 deletions(-) diff --git a/docs/devel/reset.rst b/docs/devel/reset.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/reset.rst +++ b/docs/devel/reset.rst @@ -XXX,XX +XXX,XX @@ instantly reset an object, without keeping it in reset state, just call ``resettable_reset()``. These functions take two parameters: a pointer to the object to reset and a reset type. -Several types of reset will be supported. For now only cold reset is defined; -others may be added later. The Resettable interface handles reset types with an -enum: +The Resettable interface handles reset types with an enum ``ResetType``: ``RESET_TYPE_COLD`` Cold reset is supported by every resettable object. In QEMU, it means we reset @@ -XXX,XX +XXX,XX @@ enum: from what is a real hardware cold reset. It differs from other resets (like warm or bus resets) which may keep certain parts untouched. +``RESET_TYPE_SNAPSHOT_LOAD`` + This is called for a reset which is being done to put the system into a + clean state prior to loading a snapshot. (This corresponds to a reset + with ``SHUTDOWN_CAUSE_SNAPSHOT_LOAD``.) Almost all devices should treat + this the same as ``RESET_TYPE_COLD``. The main exception is devices which + have some non-deterministic state they want to reinitialize to a different + value on each cold reset, such as RNG seed information, and which they + must not reinitialize on a snapshot-load reset. + +Devices which implement reset methods must treat any unknown ``ResetType`` +as equivalent to ``RESET_TYPE_COLD``; this will reduce the amount of +existing code we need to change if we add more types in future. + Calling ``resettable_reset()`` is equivalent to calling ``resettable_assert_reset()`` then ``resettable_release_reset()``. It is possible to interleave multiple calls to these three functions. There may diff --git a/include/hw/resettable.h b/include/hw/resettable.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/resettable.h +++ b/include/hw/resettable.h @@ -XXX,XX +XXX,XX @@ typedef struct ResettableState ResettableState; */ typedef enum ResetType { RESET_TYPE_COLD, + RESET_TYPE_SNAPSHOT_LOAD, } ResetType; /* diff --git a/hw/core/reset.c b/hw/core/reset.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/reset.c +++ b/hw/core/reset.c @@ -XXX,XX +XXX,XX @@ static ResettableContainer *get_root_reset_container(void) return root_reset_container; } -/* - * Reason why the currently in-progress qemu_devices_reset() was called. - * If we made at least SHUTDOWN_CAUSE_SNAPSHOT_LOAD have a corresponding - * ResetType we could perhaps avoid the need for this global. - */ -static ShutdownCause device_reset_reason; - /* * This is an Object which implements Resettable simply to call the * callback function in the hold phase. @@ -XXX,XX +XXX,XX @@ static void legacy_reset_hold(Object *obj, ResetType type) { LegacyReset *lr = LEGACY_RESET(obj); - if (device_reset_reason == SHUTDOWN_CAUSE_SNAPSHOT_LOAD && - lr->skip_on_snapshot_load) { + if (type == RESET_TYPE_SNAPSHOT_LOAD && lr->skip_on_snapshot_load) { return; } lr->func(lr->opaque); @@ -XXX,XX +XXX,XX @@ void qemu_unregister_resettable(Object *obj) void qemu_devices_reset(ShutdownCause reason) { - device_reset_reason = reason; + ResetType type = (reason == SHUTDOWN_CAUSE_SNAPSHOT_LOAD) ? + RESET_TYPE_SNAPSHOT_LOAD : RESET_TYPE_COLD; /* Reset the simulation */ - resettable_reset(OBJECT(get_root_reset_container()), RESET_TYPE_COLD); + resettable_reset(OBJECT(get_root_reset_container()), type); } diff --git a/hw/core/resettable.c b/hw/core/resettable.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/resettable.c +++ b/hw/core/resettable.c @@ -XXX,XX +XXX,XX @@ void resettable_reset(Object *obj, ResetType type) void resettable_assert_reset(Object *obj, ResetType type) { - /* TODO: change this assert when adding support for other reset types */ - assert(type == RESET_TYPE_COLD); trace_resettable_reset_assert_begin(obj, type); assert(!enter_phase_in_progress); @@ -XXX,XX +XXX,XX @@ void resettable_assert_reset(Object *obj, ResetType type) void resettable_release_reset(Object *obj, ResetType type) { - /* TODO: change this assert when adding support for other reset types */ - assert(type == RESET_TYPE_COLD); trace_resettable_reset_release_begin(obj, type); assert(!enter_phase_in_progress); -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Add the basic infrastructure (register read/write, type...) to implement the STM32L4x5 USART. Also create different types for the USART, UART and LPUART of the STM32L4x5 to deduplicate code and enable the implementation of different behaviors depending on the type. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240329174402.60382-2-arnaud.minier@telecom-paris.fr [PMM: update to new reset hold method signature; fixed a few checkpatch nits] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + include/hw/char/stm32l4x5_usart.h | 66 +++++ hw/char/stm32l4x5_usart.c | 396 ++++++++++++++++++++++++++++++ hw/char/Kconfig | 3 + hw/char/meson.build | 1 + hw/char/trace-events | 4 + 6 files changed, 471 insertions(+) create mode 100644 include/hw/char/stm32l4x5_usart.h create mode 100644 hw/char/stm32l4x5_usart.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Inès Varhol <ines.varhol@telecom-paris.fr> L: qemu-arm@nongnu.org S: Maintained F: hw/arm/stm32l4x5_soc.c +F: hw/char/stm32l4x5_usart.c F: hw/misc/stm32l4x5_exti.c F: hw/misc/stm32l4x5_syscfg.c F: hw/misc/stm32l4x5_rcc.c diff --git a/include/hw/char/stm32l4x5_usart.h b/include/hw/char/stm32l4x5_usart.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/char/stm32l4x5_usart.h @@ -XXX,XX +XXX,XX @@ +/* + * STM32L4X5 USART (Universal Synchronous Asynchronous Receiver Transmitter) + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * The STM32L4X5 USART is heavily inspired by the stm32f2xx_usart + * by Alistair Francis. + * The reference used is the STMicroElectronics RM0351 Reference manual + * for STM32L4x5 and STM32L4x6 advanced Arm ® -based 32-bit MCUs. + */ + +#ifndef HW_STM32L4X5_USART_H +#define HW_STM32L4X5_USART_H + +#include "hw/sysbus.h" +#include "chardev/char-fe.h" +#include "qom/object.h" + +#define TYPE_STM32L4X5_USART_BASE "stm32l4x5-usart-base" +#define TYPE_STM32L4X5_USART "stm32l4x5-usart" +#define TYPE_STM32L4X5_UART "stm32l4x5-uart" +#define TYPE_STM32L4X5_LPUART "stm32l4x5-lpuart" +OBJECT_DECLARE_TYPE(Stm32l4x5UsartBaseState, Stm32l4x5UsartBaseClass, + STM32L4X5_USART_BASE) + +typedef enum { + STM32L4x5_USART, + STM32L4x5_UART, + STM32L4x5_LPUART, +} Stm32l4x5UsartType; + +struct Stm32l4x5UsartBaseState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t cr1; + uint32_t cr2; + uint32_t cr3; + uint32_t brr; + uint32_t gtpr; + uint32_t rtor; + /* rqr is write-only */ + uint32_t isr; + /* icr is a clear register */ + uint32_t rdr; + uint32_t tdr; + + Clock *clk; + CharBackend chr; + qemu_irq irq; +}; + +struct Stm32l4x5UsartBaseClass { + SysBusDeviceClass parent_class; + + Stm32l4x5UsartType type; +}; + +#endif /* HW_STM32L4X5_USART_H */ diff --git a/hw/char/stm32l4x5_usart.c b/hw/char/stm32l4x5_usart.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/char/stm32l4x5_usart.c @@ -XXX,XX +XXX,XX @@ +/* + * STM32L4X5 USART (Universal Synchronous Asynchronous Receiver Transmitter) + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * The STM32L4X5 USART is heavily inspired by the stm32f2xx_usart + * by Alistair Francis. + * The reference used is the STMicroElectronics RM0351 Reference manual + * for STM32L4x5 and STM32L4x6 advanced Arm ® -based 32-bit MCUs. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qapi/error.h" +#include "chardev/char-fe.h" +#include "chardev/char-serial.h" +#include "migration/vmstate.h" +#include "hw/char/stm32l4x5_usart.h" +#include "hw/clock.h" +#include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "hw/registerfields.h" +#include "trace.h" + + +REG32(CR1, 0x00) + FIELD(CR1, M1, 28, 1) /* Word length (part 2, see M0) */ + FIELD(CR1, EOBIE, 27, 1) /* End of Block interrupt enable */ + FIELD(CR1, RTOIE, 26, 1) /* Receiver timeout interrupt enable */ + FIELD(CR1, DEAT, 21, 5) /* Driver Enable assertion time */ + FIELD(CR1, DEDT, 16, 5) /* Driver Enable de-assertion time */ + FIELD(CR1, OVER8, 15, 1) /* Oversampling mode */ + FIELD(CR1, CMIE, 14, 1) /* Character match interrupt enable */ + FIELD(CR1, MME, 13, 1) /* Mute mode enable */ + FIELD(CR1, M0, 12, 1) /* Word length (part 1, see M1) */ + FIELD(CR1, WAKE, 11, 1) /* Receiver wakeup method */ + FIELD(CR1, PCE, 10, 1) /* Parity control enable */ + FIELD(CR1, PS, 9, 1) /* Parity selection */ + FIELD(CR1, PEIE, 8, 1) /* PE interrupt enable */ + FIELD(CR1, TXEIE, 7, 1) /* TXE interrupt enable */ + FIELD(CR1, TCIE, 6, 1) /* Transmission complete interrupt enable */ + FIELD(CR1, RXNEIE, 5, 1) /* RXNE interrupt enable */ + FIELD(CR1, IDLEIE, 4, 1) /* IDLE interrupt enable */ + FIELD(CR1, TE, 3, 1) /* Transmitter enable */ + FIELD(CR1, RE, 2, 1) /* Receiver enable */ + FIELD(CR1, UESM, 1, 1) /* USART enable in Stop mode */ + FIELD(CR1, UE, 0, 1) /* USART enable */ +REG32(CR2, 0x04) + FIELD(CR2, ADD_1, 28, 4) /* ADD[7:4] */ + FIELD(CR2, ADD_0, 24, 1) /* ADD[3:0] */ + FIELD(CR2, RTOEN, 23, 1) /* Receiver timeout enable */ + FIELD(CR2, ABRMOD, 21, 2) /* Auto baud rate mode */ + FIELD(CR2, ABREN, 20, 1) /* Auto baud rate enable */ + FIELD(CR2, MSBFIRST, 19, 1) /* Most significant bit first */ + FIELD(CR2, DATAINV, 18, 1) /* Binary data inversion */ + FIELD(CR2, TXINV, 17, 1) /* TX pin active level inversion */ + FIELD(CR2, RXINV, 16, 1) /* RX pin active level inversion */ + FIELD(CR2, SWAP, 15, 1) /* Swap RX/TX pins */ + FIELD(CR2, LINEN, 14, 1) /* LIN mode enable */ + FIELD(CR2, STOP, 12, 2) /* STOP bits */ + FIELD(CR2, CLKEN, 11, 1) /* Clock enable */ + FIELD(CR2, CPOL, 10, 1) /* Clock polarity */ + FIELD(CR2, CPHA, 9, 1) /* Clock phase */ + FIELD(CR2, LBCL, 8, 1) /* Last bit clock pulse */ + FIELD(CR2, LBDIE, 6, 1) /* LIN break detection interrupt enable */ + FIELD(CR2, LBDL, 5, 1) /* LIN break detection length */ + FIELD(CR2, ADDM7, 4, 1) /* 7-bit / 4-bit Address Detection */ + +REG32(CR3, 0x08) + /* TCBGTIE only on STM32L496xx/4A6xx devices */ + FIELD(CR3, UCESM, 23, 1) /* USART Clock Enable in Stop Mode */ + FIELD(CR3, WUFIE, 22, 1) /* Wakeup from Stop mode interrupt enable */ + FIELD(CR3, WUS, 20, 2) /* Wakeup from Stop mode interrupt flag selection */ + FIELD(CR3, SCARCNT, 17, 3) /* Smartcard auto-retry count */ + FIELD(CR3, DEP, 15, 1) /* Driver enable polarity selection */ + FIELD(CR3, DEM, 14, 1) /* Driver enable mode */ + FIELD(CR3, DDRE, 13, 1) /* DMA Disable on Reception Error */ + FIELD(CR3, OVRDIS, 12, 1) /* Overrun Disable */ + FIELD(CR3, ONEBIT, 11, 1) /* One sample bit method enable */ + FIELD(CR3, CTSIE, 10, 1) /* CTS interrupt enable */ + FIELD(CR3, CTSE, 9, 1) /* CTS enable */ + FIELD(CR3, RTSE, 8, 1) /* RTS enable */ + FIELD(CR3, DMAT, 7, 1) /* DMA enable transmitter */ + FIELD(CR3, DMAR, 6, 1) /* DMA enable receiver */ + FIELD(CR3, SCEN, 5, 1) /* Smartcard mode enable */ + FIELD(CR3, NACK, 4, 1) /* Smartcard NACK enable */ + FIELD(CR3, HDSEL, 3, 1) /* Half-duplex selection */ + FIELD(CR3, IRLP, 2, 1) /* IrDA low-power */ + FIELD(CR3, IREN, 1, 1) /* IrDA mode enable */ + FIELD(CR3, EIE, 0, 1) /* Error interrupt enable */ +REG32(BRR, 0x0C) + FIELD(BRR, BRR, 0, 16) +REG32(GTPR, 0x10) + FIELD(GTPR, GT, 8, 8) /* Guard time value */ + FIELD(GTPR, PSC, 0, 8) /* Prescaler value */ +REG32(RTOR, 0x14) + FIELD(RTOR, BLEN, 24, 8) /* Block Length */ + FIELD(RTOR, RTO, 0, 24) /* Receiver timeout value */ +REG32(RQR, 0x18) + FIELD(RQR, TXFRQ, 4, 1) /* Transmit data flush request */ + FIELD(RQR, RXFRQ, 3, 1) /* Receive data flush request */ + FIELD(RQR, MMRQ, 2, 1) /* Mute mode request */ + FIELD(RQR, SBKRQ, 1, 1) /* Send break request */ + FIELD(RQR, ABBRRQ, 0, 1) /* Auto baud rate request */ +REG32(ISR, 0x1C) + /* TCBGT only for STM32L475xx/476xx/486xx devices */ + FIELD(ISR, REACK, 22, 1) /* Receive enable acknowledge flag */ + FIELD(ISR, TEACK, 21, 1) /* Transmit enable acknowledge flag */ + FIELD(ISR, WUF, 20, 1) /* Wakeup from Stop mode flag */ + FIELD(ISR, RWU, 19, 1) /* Receiver wakeup from Mute mode */ + FIELD(ISR, SBKF, 18, 1) /* Send break flag */ + FIELD(ISR, CMF, 17, 1) /* Character match flag */ + FIELD(ISR, BUSY, 16, 1) /* Busy flag */ + FIELD(ISR, ABRF, 15, 1) /* Auto Baud rate flag */ + FIELD(ISR, ABRE, 14, 1) /* Auto Baud rate error */ + FIELD(ISR, EOBF, 12, 1) /* End of block flag */ + FIELD(ISR, RTOF, 11, 1) /* Receiver timeout */ + FIELD(ISR, CTS, 10, 1) /* CTS flag */ + FIELD(ISR, CTSIF, 9, 1) /* CTS interrupt flag */ + FIELD(ISR, LBDF, 8, 1) /* LIN break detection flag */ + FIELD(ISR, TXE, 7, 1) /* Transmit data register empty */ + FIELD(ISR, TC, 6, 1) /* Transmission complete */ + FIELD(ISR, RXNE, 5, 1) /* Read data register not empty */ + FIELD(ISR, IDLE, 4, 1) /* Idle line detected */ + FIELD(ISR, ORE, 3, 1) /* Overrun error */ + FIELD(ISR, NF, 2, 1) /* START bit Noise detection flag */ + FIELD(ISR, FE, 1, 1) /* Framing Error */ + FIELD(ISR, PE, 0, 1) /* Parity Error */ +REG32(ICR, 0x20) + FIELD(ICR, WUCF, 20, 1) /* Wakeup from Stop mode clear flag */ + FIELD(ICR, CMCF, 17, 1) /* Character match clear flag */ + FIELD(ICR, EOBCF, 12, 1) /* End of block clear flag */ + FIELD(ICR, RTOCF, 11, 1) /* Receiver timeout clear flag */ + FIELD(ICR, CTSCF, 9, 1) /* CTS clear flag */ + FIELD(ICR, LBDCF, 8, 1) /* LIN break detection clear flag */ + /* TCBGTCF only on STM32L496xx/4A6xx devices */ + FIELD(ICR, TCCF, 6, 1) /* Transmission complete clear flag */ + FIELD(ICR, IDLECF, 4, 1) /* Idle line detected clear flag */ + FIELD(ICR, ORECF, 3, 1) /* Overrun error clear flag */ + FIELD(ICR, NCF, 2, 1) /* Noise detected clear flag */ + FIELD(ICR, FECF, 1, 1) /* Framing error clear flag */ + FIELD(ICR, PECF, 0, 1) /* Parity error clear flag */ +REG32(RDR, 0x24) + FIELD(RDR, RDR, 0, 9) +REG32(TDR, 0x28) + FIELD(TDR, TDR, 0, 9) + +static void stm32l4x5_usart_base_reset_hold(Object *obj, ResetType type) +{ + Stm32l4x5UsartBaseState *s = STM32L4X5_USART_BASE(obj); + + s->cr1 = 0x00000000; + s->cr2 = 0x00000000; + s->cr3 = 0x00000000; + s->brr = 0x00000000; + s->gtpr = 0x00000000; + s->rtor = 0x00000000; + s->isr = 0x020000C0; + s->rdr = 0x00000000; + s->tdr = 0x00000000; +} + +static uint64_t stm32l4x5_usart_base_read(void *opaque, hwaddr addr, + unsigned int size) +{ + Stm32l4x5UsartBaseState *s = opaque; + uint64_t retvalue = 0; + + switch (addr) { + case A_CR1: + retvalue = s->cr1; + break; + case A_CR2: + retvalue = s->cr2; + break; + case A_CR3: + retvalue = s->cr3; + break; + case A_BRR: + retvalue = FIELD_EX32(s->brr, BRR, BRR); + break; + case A_GTPR: + retvalue = s->gtpr; + break; + case A_RTOR: + retvalue = s->rtor; + break; + case A_RQR: + /* RQR is a write only register */ + retvalue = 0x00000000; + break; + case A_ISR: + retvalue = s->isr; + break; + case A_ICR: + /* ICR is a clear register */ + retvalue = 0x00000000; + break; + case A_RDR: + retvalue = FIELD_EX32(s->rdr, RDR, RDR); + /* Reset RXNE flag */ + s->isr &= ~R_ISR_RXNE_MASK; + break; + case A_TDR: + retvalue = FIELD_EX32(s->tdr, TDR, TDR); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + break; + } + + trace_stm32l4x5_usart_read(addr, retvalue); + + return retvalue; +} + +static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) +{ + Stm32l4x5UsartBaseState *s = opaque; + const uint32_t value = val64; + + trace_stm32l4x5_usart_write(addr, value); + + switch (addr) { + case A_CR1: + s->cr1 = value; + return; + case A_CR2: + s->cr2 = value; + return; + case A_CR3: + s->cr3 = value; + return; + case A_BRR: + s->brr = value; + return; + case A_GTPR: + s->gtpr = value; + return; + case A_RTOR: + s->rtor = value; + return; + case A_RQR: + return; + case A_ISR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: ISR is read only !\n", __func__); + return; + case A_ICR: + /* Clear the status flags */ + s->isr &= ~value; + return; + case A_RDR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: RDR is read only !\n", __func__); + return; + case A_TDR: + s->tdr = value; + return; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + } +} + +static const MemoryRegionOps stm32l4x5_usart_base_ops = { + .read = stm32l4x5_usart_base_read, + .write = stm32l4x5_usart_base_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .max_access_size = 4, + .min_access_size = 4, + .unaligned = false + }, + .impl = { + .max_access_size = 4, + .min_access_size = 4, + .unaligned = false + }, +}; + +static Property stm32l4x5_usart_base_properties[] = { + DEFINE_PROP_CHR("chardev", Stm32l4x5UsartBaseState, chr), + DEFINE_PROP_END_OF_LIST(), +}; + +static void stm32l4x5_usart_base_init(Object *obj) +{ + Stm32l4x5UsartBaseState *s = STM32L4X5_USART_BASE(obj); + + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); + + memory_region_init_io(&s->mmio, obj, &stm32l4x5_usart_base_ops, s, + TYPE_STM32L4X5_USART_BASE, 0x400); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); + + s->clk = qdev_init_clock_in(DEVICE(s), "clk", NULL, s, 0); +} + +static const VMStateDescription vmstate_stm32l4x5_usart_base = { + .name = TYPE_STM32L4X5_USART_BASE, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(cr1, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(cr2, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(cr3, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(brr, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(gtpr, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(rtor, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(isr, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(rdr, Stm32l4x5UsartBaseState), + VMSTATE_UINT32(tdr, Stm32l4x5UsartBaseState), + VMSTATE_CLOCK(clk, Stm32l4x5UsartBaseState), + VMSTATE_END_OF_LIST() + } +}; + + +static void stm32l4x5_usart_base_realize(DeviceState *dev, Error **errp) +{ + ERRP_GUARD(); + Stm32l4x5UsartBaseState *s = STM32L4X5_USART_BASE(dev); + if (!clock_has_source(s->clk)) { + error_setg(errp, "USART clock must be wired up by SoC code"); + return; + } +} + +static void stm32l4x5_usart_base_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.hold = stm32l4x5_usart_base_reset_hold; + device_class_set_props(dc, stm32l4x5_usart_base_properties); + dc->realize = stm32l4x5_usart_base_realize; + dc->vmsd = &vmstate_stm32l4x5_usart_base; +} + +static void stm32l4x5_usart_class_init(ObjectClass *oc, void *data) +{ + Stm32l4x5UsartBaseClass *subc = STM32L4X5_USART_BASE_CLASS(oc); + + subc->type = STM32L4x5_USART; +} + +static void stm32l4x5_uart_class_init(ObjectClass *oc, void *data) +{ + Stm32l4x5UsartBaseClass *subc = STM32L4X5_USART_BASE_CLASS(oc); + + subc->type = STM32L4x5_UART; +} + +static void stm32l4x5_lpuart_class_init(ObjectClass *oc, void *data) +{ + Stm32l4x5UsartBaseClass *subc = STM32L4X5_USART_BASE_CLASS(oc); + + subc->type = STM32L4x5_LPUART; +} + +static const TypeInfo stm32l4x5_usart_types[] = { + { + .name = TYPE_STM32L4X5_USART_BASE, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(Stm32l4x5UsartBaseState), + .instance_init = stm32l4x5_usart_base_init, + .class_init = stm32l4x5_usart_base_class_init, + .abstract = true, + }, { + .name = TYPE_STM32L4X5_USART, + .parent = TYPE_STM32L4X5_USART_BASE, + .class_init = stm32l4x5_usart_class_init, + }, { + .name = TYPE_STM32L4X5_UART, + .parent = TYPE_STM32L4X5_USART_BASE, + .class_init = stm32l4x5_uart_class_init, + }, { + .name = TYPE_STM32L4X5_LPUART, + .parent = TYPE_STM32L4X5_USART_BASE, + .class_init = stm32l4x5_lpuart_class_init, + } +}; + +DEFINE_TYPES(stm32l4x5_usart_types) diff --git a/hw/char/Kconfig b/hw/char/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/char/Kconfig +++ b/hw/char/Kconfig @@ -XXX,XX +XXX,XX @@ config VIRTIO_SERIAL config STM32F2XX_USART bool +config STM32L4X5_USART + bool + config CMSDK_APB_UART bool diff --git a/hw/char/meson.build b/hw/char/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/char/meson.build +++ b/hw/char/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_RENESAS_SCI', if_true: files('renesas_sci.c')) system_ss.add(when: 'CONFIG_SIFIVE_UART', if_true: files('sifive_uart.c')) system_ss.add(when: 'CONFIG_SH_SCI', if_true: files('sh_serial.c')) system_ss.add(when: 'CONFIG_STM32F2XX_USART', if_true: files('stm32f2xx_usart.c')) +system_ss.add(when: 'CONFIG_STM32L4X5_USART', if_true: files('stm32l4x5_usart.c')) system_ss.add(when: 'CONFIG_MCHP_PFSOC_MMUART', if_true: files('mchp_pfsoc_mmuart.c')) system_ss.add(when: 'CONFIG_HTIF', if_true: files('riscv_htif.c')) system_ss.add(when: 'CONFIG_GOLDFISH_TTY', if_true: files('goldfish_tty.c')) diff --git a/hw/char/trace-events b/hw/char/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -XXX,XX +XXX,XX @@ cadence_uart_baudrate(unsigned baudrate) "baudrate %u" sh_serial_read(char *id, unsigned size, uint64_t offs, uint64_t val) " %s size %d offs 0x%02" PRIx64 " -> 0x%02" PRIx64 sh_serial_write(char *id, unsigned size, uint64_t offs, uint64_t val) "%s size %d offs 0x%02" PRIx64 " <- 0x%02" PRIx64 +# stm32l4x5_usart.c +stm32l4x5_usart_read(uint64_t addr, uint32_t data) "USART: Read <0x%" PRIx64 "> -> 0x%" PRIx32 "" +stm32l4x5_usart_write(uint64_t addr, uint32_t data) "USART: Write <0x%" PRIx64 "> <- 0x%" PRIx32 "" + # xen_console.c xen_console_connect(unsigned int idx, unsigned int ring_ref, unsigned int port, unsigned int limit) "idx %u ring_ref %u port %u limit %u" xen_console_disconnect(unsigned int idx) "idx %u" -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Implement the ability to read and write characters to the usart using the serial port. The character transmission is based on the cmsdk-apb-uart implementation. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240329174402.60382-3-arnaud.minier@telecom-paris.fr [PMM: fixed a few checkpatch nits] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/char/stm32l4x5_usart.h | 1 + hw/char/stm32l4x5_usart.c | 143 ++++++++++++++++++++++++++++++ hw/char/trace-events | 7 ++ 3 files changed, 151 insertions(+) diff --git a/include/hw/char/stm32l4x5_usart.h b/include/hw/char/stm32l4x5_usart.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/stm32l4x5_usart.h +++ b/include/hw/char/stm32l4x5_usart.h @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5UsartBaseState { Clock *clk; CharBackend chr; qemu_irq irq; + guint watch_tag; }; struct Stm32l4x5UsartBaseClass { diff --git a/hw/char/stm32l4x5_usart.c b/hw/char/stm32l4x5_usart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/stm32l4x5_usart.c +++ b/hw/char/stm32l4x5_usart.c @@ -XXX,XX +XXX,XX @@ REG32(RDR, 0x24) REG32(TDR, 0x28) FIELD(TDR, TDR, 0, 9) +static void stm32l4x5_update_irq(Stm32l4x5UsartBaseState *s) +{ + if (((s->isr & R_ISR_WUF_MASK) && (s->cr3 & R_CR3_WUFIE_MASK)) || + ((s->isr & R_ISR_CMF_MASK) && (s->cr1 & R_CR1_CMIE_MASK)) || + ((s->isr & R_ISR_ABRF_MASK) && (s->cr1 & R_CR1_RXNEIE_MASK)) || + ((s->isr & R_ISR_EOBF_MASK) && (s->cr1 & R_CR1_EOBIE_MASK)) || + ((s->isr & R_ISR_RTOF_MASK) && (s->cr1 & R_CR1_RTOIE_MASK)) || + ((s->isr & R_ISR_CTSIF_MASK) && (s->cr3 & R_CR3_CTSIE_MASK)) || + ((s->isr & R_ISR_LBDF_MASK) && (s->cr2 & R_CR2_LBDIE_MASK)) || + ((s->isr & R_ISR_TXE_MASK) && (s->cr1 & R_CR1_TXEIE_MASK)) || + ((s->isr & R_ISR_TC_MASK) && (s->cr1 & R_CR1_TCIE_MASK)) || + ((s->isr & R_ISR_RXNE_MASK) && (s->cr1 & R_CR1_RXNEIE_MASK)) || + ((s->isr & R_ISR_IDLE_MASK) && (s->cr1 & R_CR1_IDLEIE_MASK)) || + ((s->isr & R_ISR_ORE_MASK) && + ((s->cr1 & R_CR1_RXNEIE_MASK) || (s->cr3 & R_CR3_EIE_MASK))) || + /* TODO: Handle NF ? */ + ((s->isr & R_ISR_FE_MASK) && (s->cr3 & R_CR3_EIE_MASK)) || + ((s->isr & R_ISR_PE_MASK) && (s->cr1 & R_CR1_PEIE_MASK))) { + qemu_irq_raise(s->irq); + trace_stm32l4x5_usart_irq_raised(s->isr); + } else { + qemu_irq_lower(s->irq); + trace_stm32l4x5_usart_irq_lowered(); + } +} + +static int stm32l4x5_usart_base_can_receive(void *opaque) +{ + Stm32l4x5UsartBaseState *s = opaque; + + if (!(s->isr & R_ISR_RXNE_MASK)) { + return 1; + } + + return 0; +} + +static void stm32l4x5_usart_base_receive(void *opaque, const uint8_t *buf, + int size) +{ + Stm32l4x5UsartBaseState *s = opaque; + + if (!((s->cr1 & R_CR1_UE_MASK) && (s->cr1 & R_CR1_RE_MASK))) { + trace_stm32l4x5_usart_receiver_not_enabled( + FIELD_EX32(s->cr1, CR1, UE), FIELD_EX32(s->cr1, CR1, RE)); + return; + } + + /* Check if overrun detection is enabled and if there is an overrun */ + if (!(s->cr3 & R_CR3_OVRDIS_MASK) && (s->isr & R_ISR_RXNE_MASK)) { + /* + * A character has been received while + * the previous has not been read = Overrun. + */ + s->isr |= R_ISR_ORE_MASK; + trace_stm32l4x5_usart_overrun_detected(s->rdr, *buf); + } else { + /* No overrun */ + s->rdr = *buf; + s->isr |= R_ISR_RXNE_MASK; + trace_stm32l4x5_usart_rx(s->rdr); + } + + stm32l4x5_update_irq(s); +} + +/* + * Try to send tx data, and arrange to be called back later if + * we can't (ie the char backend is busy/blocking). + */ +static gboolean usart_transmit(void *do_not_use, GIOCondition cond, + void *opaque) +{ + Stm32l4x5UsartBaseState *s = STM32L4X5_USART_BASE(opaque); + int ret; + /* TODO: Handle 9 bits transmission */ + uint8_t ch = s->tdr; + + s->watch_tag = 0; + + if (!(s->cr1 & R_CR1_TE_MASK) || (s->isr & R_ISR_TXE_MASK)) { + return G_SOURCE_REMOVE; + } + + ret = qemu_chr_fe_write(&s->chr, &ch, 1); + if (ret <= 0) { + s->watch_tag = qemu_chr_fe_add_watch(&s->chr, G_IO_OUT | G_IO_HUP, + usart_transmit, s); + if (!s->watch_tag) { + /* + * Most common reason to be here is "no chardev backend": + * just insta-drain the buffer, so the serial output + * goes into a void, rather than blocking the guest. + */ + goto buffer_drained; + } + /* Transmit pending */ + trace_stm32l4x5_usart_tx_pending(); + return G_SOURCE_REMOVE; + } + +buffer_drained: + /* Character successfully sent */ + trace_stm32l4x5_usart_tx(ch); + s->isr |= R_ISR_TC_MASK | R_ISR_TXE_MASK; + stm32l4x5_update_irq(s); + return G_SOURCE_REMOVE; +} + +static void usart_cancel_transmit(Stm32l4x5UsartBaseState *s) +{ + if (s->watch_tag) { + g_source_remove(s->watch_tag); + s->watch_tag = 0; + } +} + static void stm32l4x5_usart_base_reset_hold(Object *obj, ResetType type) { Stm32l4x5UsartBaseState *s = STM32L4X5_USART_BASE(obj); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_reset_hold(Object *obj, ResetType type) s->isr = 0x020000C0; s->rdr = 0x00000000; s->tdr = 0x00000000; + + usart_cancel_transmit(s); + stm32l4x5_update_irq(s); +} + +static void usart_update_rqr(Stm32l4x5UsartBaseState *s, uint32_t value) +{ + /* TXFRQ */ + /* Reset RXNE flag */ + if (value & R_RQR_RXFRQ_MASK) { + s->isr &= ~R_ISR_RXNE_MASK; + } + /* MMRQ */ + /* SBKRQ */ + /* ABRRQ */ + stm32l4x5_update_irq(s); } static uint64_t stm32l4x5_usart_base_read(void *opaque, hwaddr addr, @@ -XXX,XX +XXX,XX @@ static uint64_t stm32l4x5_usart_base_read(void *opaque, hwaddr addr, retvalue = FIELD_EX32(s->rdr, RDR, RDR); /* Reset RXNE flag */ s->isr &= ~R_ISR_RXNE_MASK; + stm32l4x5_update_irq(s); break; case A_TDR: retvalue = FIELD_EX32(s->tdr, TDR, TDR); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr, switch (addr) { case A_CR1: s->cr1 = value; + stm32l4x5_update_irq(s); return; case A_CR2: s->cr2 = value; @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr, s->rtor = value; return; case A_RQR: + usart_update_rqr(s, value); return; case A_ISR: qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr, case A_ICR: /* Clear the status flags */ s->isr &= ~value; + stm32l4x5_update_irq(s); return; case A_RDR: qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr, return; case A_TDR: s->tdr = value; + s->isr &= ~R_ISR_TXE_MASK; + usart_transmit(NULL, G_IO_OUT, s); return; default: qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_realize(DeviceState *dev, Error **errp) error_setg(errp, "USART clock must be wired up by SoC code"); return; } + + qemu_chr_fe_set_handlers(&s->chr, stm32l4x5_usart_base_can_receive, + stm32l4x5_usart_base_receive, NULL, NULL, + s, NULL, true); } static void stm32l4x5_usart_base_class_init(ObjectClass *klass, void *data) diff --git a/hw/char/trace-events b/hw/char/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -XXX,XX +XXX,XX @@ sh_serial_write(char *id, unsigned size, uint64_t offs, uint64_t val) "%s size % # stm32l4x5_usart.c stm32l4x5_usart_read(uint64_t addr, uint32_t data) "USART: Read <0x%" PRIx64 "> -> 0x%" PRIx32 "" stm32l4x5_usart_write(uint64_t addr, uint32_t data) "USART: Write <0x%" PRIx64 "> <- 0x%" PRIx32 "" +stm32l4x5_usart_rx(uint8_t c) "USART: got character 0x%x from backend" +stm32l4x5_usart_tx(uint8_t c) "USART: character 0x%x sent to backend" +stm32l4x5_usart_tx_pending(void) "USART: character send to backend pending" +stm32l4x5_usart_irq_raised(uint32_t reg) "USART: IRQ raised: 0x%08"PRIx32 +stm32l4x5_usart_irq_lowered(void) "USART: IRQ lowered" +stm32l4x5_usart_overrun_detected(uint8_t current, uint8_t received) "USART: Overrun detected, RDR='0x%x', received 0x%x" +stm32l4x5_usart_receiver_not_enabled(uint8_t ue_bit, uint8_t re_bit) "USART: Receiver not enabled, UE=0x%x, RE=0x%x" # xen_console.c xen_console_connect(unsigned int idx, unsigned int ring_ref, unsigned int port, unsigned int limit) "idx %u ring_ref %u port %u limit %u" -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Add a function to change the settings of the serial connection. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240329174402.60382-4-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/stm32l4x5_usart.c | 98 +++++++++++++++++++++++++++++++++++++++ hw/char/trace-events | 1 + 2 files changed, 99 insertions(+) diff --git a/hw/char/stm32l4x5_usart.c b/hw/char/stm32l4x5_usart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/stm32l4x5_usart.c +++ b/hw/char/stm32l4x5_usart.c @@ -XXX,XX +XXX,XX @@ static void usart_cancel_transmit(Stm32l4x5UsartBaseState *s) } } +static void stm32l4x5_update_params(Stm32l4x5UsartBaseState *s) +{ + int speed, parity, data_bits, stop_bits; + uint32_t value, usart_div; + QEMUSerialSetParams ssp; + + /* Select the parity type */ + if (s->cr1 & R_CR1_PCE_MASK) { + if (s->cr1 & R_CR1_PS_MASK) { + parity = 'O'; + } else { + parity = 'E'; + } + } else { + parity = 'N'; + } + + /* Select the number of stop bits */ + switch (FIELD_EX32(s->cr2, CR2, STOP)) { + case 0: + stop_bits = 1; + break; + case 2: + stop_bits = 2; + break; + default: + qemu_log_mask(LOG_UNIMP, + "UNIMPLEMENTED: fractionnal stop bits; CR2[13:12] = %u", + FIELD_EX32(s->cr2, CR2, STOP)); + return; + } + + /* Select the length of the word */ + switch ((FIELD_EX32(s->cr1, CR1, M1) << 1) | FIELD_EX32(s->cr1, CR1, M0)) { + case 0: + data_bits = 8; + break; + case 1: + data_bits = 9; + break; + case 2: + data_bits = 7; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "UNDEFINED: invalid word length, CR1.M = 0b11"); + return; + } + + /* Select the baud rate */ + value = FIELD_EX32(s->brr, BRR, BRR); + if (value < 16) { + qemu_log_mask(LOG_GUEST_ERROR, + "UNDEFINED: BRR less than 16: %u", value); + return; + } + + if (FIELD_EX32(s->cr1, CR1, OVER8) == 0) { + /* + * Oversampling by 16 + * BRR = USARTDIV + */ + usart_div = value; + } else { + /* + * Oversampling by 8 + * - BRR[2:0] = USARTDIV[3:0] shifted 1 bit to the right. + * - BRR[3] must be kept cleared. + * - BRR[15:4] = USARTDIV[15:4] + * - The frequency is multiplied by 2 + */ + usart_div = ((value & 0xFFF0) | ((value & 0x0007) << 1)) / 2; + } + + speed = clock_get_hz(s->clk) / usart_div; + + ssp.speed = speed; + ssp.parity = parity; + ssp.data_bits = data_bits; + ssp.stop_bits = stop_bits; + + qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_PARAMS, &ssp); + + trace_stm32l4x5_usart_update_params(speed, parity, data_bits, stop_bits); +} + static void stm32l4x5_usart_base_reset_hold(Object *obj, ResetType type) { Stm32l4x5UsartBaseState *s = STM32L4X5_USART_BASE(obj); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_write(void *opaque, hwaddr addr, switch (addr) { case A_CR1: s->cr1 = value; + stm32l4x5_update_params(s); stm32l4x5_update_irq(s); return; case A_CR2: s->cr2 = value; + stm32l4x5_update_params(s); return; case A_CR3: s->cr3 = value; return; case A_BRR: s->brr = value; + stm32l4x5_update_params(s); return; case A_GTPR: s->gtpr = value; @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_usart_base_init(Object *obj) s->clk = qdev_init_clock_in(DEVICE(s), "clk", NULL, s, 0); } +static int stm32l4x5_usart_base_post_load(void *opaque, int version_id) +{ + Stm32l4x5UsartBaseState *s = (Stm32l4x5UsartBaseState *)opaque; + + stm32l4x5_update_params(s); + return 0; +} + static const VMStateDescription vmstate_stm32l4x5_usart_base = { .name = TYPE_STM32L4X5_USART_BASE, .version_id = 1, .minimum_version_id = 1, + .post_load = stm32l4x5_usart_base_post_load, .fields = (VMStateField[]) { VMSTATE_UINT32(cr1, Stm32l4x5UsartBaseState), VMSTATE_UINT32(cr2, Stm32l4x5UsartBaseState), diff --git a/hw/char/trace-events b/hw/char/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -XXX,XX +XXX,XX @@ stm32l4x5_usart_irq_raised(uint32_t reg) "USART: IRQ raised: 0x%08"PRIx32 stm32l4x5_usart_irq_lowered(void) "USART: IRQ lowered" stm32l4x5_usart_overrun_detected(uint8_t current, uint8_t received) "USART: Overrun detected, RDR='0x%x', received 0x%x" stm32l4x5_usart_receiver_not_enabled(uint8_t ue_bit, uint8_t re_bit) "USART: Receiver not enabled, UE=0x%x, RE=0x%x" +stm32l4x5_usart_update_params(int speed, uint8_t parity, int data, int stop) "USART: speed: %d, parity: %c, data bits: %d, stop bits: %d" # xen_console.c xen_console_connect(unsigned int idx, unsigned int ring_ref, unsigned int port, unsigned int limit) "idx %u ring_ref %u port %u limit %u" -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Add the USART to the SoC and connect it to the other implemented devices. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240329174402.60382-5-arnaud.minier@telecom-paris.fr [PMM: fixed a few checkpatch nits] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/b-l475e-iot01a.rst | 2 +- include/hw/arm/stm32l4x5_soc.h | 7 +++ hw/arm/stm32l4x5_soc.c | 83 +++++++++++++++++++++++++++--- hw/arm/Kconfig | 1 + 4 files changed, 86 insertions(+), 7 deletions(-) diff --git a/docs/system/arm/b-l475e-iot01a.rst b/docs/system/arm/b-l475e-iot01a.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/b-l475e-iot01a.rst +++ b/docs/system/arm/b-l475e-iot01a.rst @@ -XXX,XX +XXX,XX @@ Currently B-L475E-IOT01A machine's only supports the following devices: - STM32L4x5 SYSCFG (System configuration controller) - STM32L4x5 RCC (Reset and clock control) - STM32L4x5 GPIOs (General-purpose I/Os) +- STM32L4x5 USARTs, UARTs and LPUART (Serial ports) Missing devices """"""""""""""" The B-L475E-IOT01A does *not* support the following devices: -- Serial ports (UART) - Analog to Digital Converter (ADC) - SPI controller - Timer controller (TIMER) diff --git a/include/hw/arm/stm32l4x5_soc.h b/include/hw/arm/stm32l4x5_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32l4x5_soc.h +++ b/include/hw/arm/stm32l4x5_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/stm32l4x5_exti.h" #include "hw/misc/stm32l4x5_rcc.h" #include "hw/gpio/stm32l4x5_gpio.h" +#include "hw/char/stm32l4x5_usart.h" #include "qom/object.h" #define TYPE_STM32L4X5_SOC "stm32l4x5-soc" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_TYPE(Stm32l4x5SocState, Stm32l4x5SocClass, STM32L4X5_SOC) #define NUM_EXTI_OR_GATES 4 +#define STM_NUM_USARTS 3 +#define STM_NUM_UARTS 2 + struct Stm32l4x5SocState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5SocState { Stm32l4x5SyscfgState syscfg; Stm32l4x5RccState rcc; Stm32l4x5GpioState gpio[NUM_GPIOS]; + Stm32l4x5UsartBaseState usart[STM_NUM_USARTS]; + Stm32l4x5UsartBaseState uart[STM_NUM_UARTS]; + Stm32l4x5UsartBaseState lpuart; MemoryRegion sram1; MemoryRegion sram2; diff --git a/hw/arm/stm32l4x5_soc.c b/hw/arm/stm32l4x5_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32l4x5_soc.c +++ b/hw/arm/stm32l4x5_soc.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "hw/or-irq.h" #include "hw/arm/stm32l4x5_soc.h" +#include "hw/char/stm32l4x5_usart.h" #include "hw/gpio/stm32l4x5_gpio.h" #include "hw/qdev-clock.h" #include "hw/misc/unimp.h" @@ -XXX,XX +XXX,XX @@ static const struct { { 0x48001C00, 0x0000000F, 0x00000000, 0x00000000 }, }; +static const hwaddr usart_addr[] = { + 0x40013800, /* "USART1", 0x400 */ + 0x40004400, /* "USART2", 0x400 */ + 0x40004800, /* "USART3", 0x400 */ +}; +static const hwaddr uart_addr[] = { + 0x40004C00, /* "UART4" , 0x400 */ + 0x40005000 /* "UART5" , 0x400 */ +}; + +#define LPUART_BASE_ADDRESS 0x40008000 + +static const int usart_irq[] = { 37, 38, 39 }; +static const int uart_irq[] = { 52, 53 }; +#define LPUART_IRQ 70 + static void stm32l4x5_soc_initfn(Object *obj) { Stm32l4x5SocState *s = STM32L4X5_SOC(obj); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_initfn(Object *obj) g_autofree char *name = g_strdup_printf("gpio%c", 'a' + i); object_initialize_child(obj, name, &s->gpio[i], TYPE_STM32L4X5_GPIO); } + + for (int i = 0; i < STM_NUM_USARTS; i++) { + object_initialize_child(obj, "usart[*]", &s->usart[i], + TYPE_STM32L4X5_USART); + } + + for (int i = 0; i < STM_NUM_UARTS; i++) { + object_initialize_child(obj, "uart[*]", &s->uart[i], + TYPE_STM32L4X5_UART); + } + object_initialize_child(obj, "lpuart1", &s->lpuart, + TYPE_STM32L4X5_LPUART); } static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) sysbus_mmio_map(busdev, 0, RCC_BASE_ADDRESS); sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, RCC_IRQ)); + /* USART devices */ + for (int i = 0; i < STM_NUM_USARTS; i++) { + g_autofree char *name = g_strdup_printf("usart%d-out", i + 1); + dev = DEVICE(&(s->usart[i])); + qdev_prop_set_chr(dev, "chardev", serial_hd(i)); + qdev_connect_clock_in(dev, "clk", + qdev_get_clock_out(DEVICE(&(s->rcc)), name)); + busdev = SYS_BUS_DEVICE(dev); + if (!sysbus_realize(busdev, errp)) { + return; + } + sysbus_mmio_map(busdev, 0, usart_addr[i]); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, usart_irq[i])); + } + + /* + * TODO: Connect the USARTs, UARTs and LPUART to the EXTI once the EXTI + * can handle other gpio-in than the gpios. (e.g. Direct Lines for the + * usarts) + */ + + /* UART devices */ + for (int i = 0; i < STM_NUM_UARTS; i++) { + g_autofree char *name = g_strdup_printf("uart%d-out", STM_NUM_USARTS + i + 1); + dev = DEVICE(&(s->uart[i])); + qdev_prop_set_chr(dev, "chardev", serial_hd(STM_NUM_USARTS + i)); + qdev_connect_clock_in(dev, "clk", + qdev_get_clock_out(DEVICE(&(s->rcc)), name)); + busdev = SYS_BUS_DEVICE(dev); + if (!sysbus_realize(busdev, errp)) { + return; + } + sysbus_mmio_map(busdev, 0, uart_addr[i]); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, uart_irq[i])); + } + + /* LPUART device*/ + dev = DEVICE(&(s->lpuart)); + qdev_prop_set_chr(dev, "chardev", serial_hd(STM_NUM_USARTS + STM_NUM_UARTS)); + qdev_connect_clock_in(dev, "clk", + qdev_get_clock_out(DEVICE(&(s->rcc)), "lpuart1-out")); + busdev = SYS_BUS_DEVICE(dev); + if (!sysbus_realize(busdev, errp)) { + return; + } + sysbus_mmio_map(busdev, 0, LPUART_BASE_ADDRESS); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, LPUART_IRQ)); + /* APB1 BUS */ create_unimplemented_device("TIM2", 0x40000000, 0x400); create_unimplemented_device("TIM3", 0x40000400, 0x400); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("SPI2", 0x40003800, 0x400); create_unimplemented_device("SPI3", 0x40003C00, 0x400); /* RESERVED: 0x40004000, 0x400 */ - create_unimplemented_device("USART2", 0x40004400, 0x400); - create_unimplemented_device("USART3", 0x40004800, 0x400); - create_unimplemented_device("UART4", 0x40004C00, 0x400); - create_unimplemented_device("UART5", 0x40005000, 0x400); create_unimplemented_device("I2C1", 0x40005400, 0x400); create_unimplemented_device("I2C2", 0x40005800, 0x400); create_unimplemented_device("I2C3", 0x40005C00, 0x400); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("DAC1", 0x40007400, 0x400); create_unimplemented_device("OPAMP", 0x40007800, 0x400); create_unimplemented_device("LPTIM1", 0x40007C00, 0x400); - create_unimplemented_device("LPUART1", 0x40008000, 0x400); /* RESERVED: 0x40008400, 0x400 */ create_unimplemented_device("SWPMI1", 0x40008800, 0x400); /* RESERVED: 0x40008C00, 0x800 */ @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("TIM1", 0x40012C00, 0x400); create_unimplemented_device("SPI1", 0x40013000, 0x400); create_unimplemented_device("TIM8", 0x40013400, 0x400); - create_unimplemented_device("USART1", 0x40013800, 0x400); /* RESERVED: 0x40013C00, 0x400 */ create_unimplemented_device("TIM15", 0x40014000, 0x400); create_unimplemented_device("TIM16", 0x40014400, 0x400); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config STM32L4X5_SOC select STM32L4X5_SYSCFG select STM32L4X5_RCC select STM32L4X5_GPIO + select STM32L4X5_USART config XLNX_ZYNQMP_ARM bool -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Test: - read/write from/to the usart registers - send/receive a character/string over the serial port Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240329174402.60382-6-arnaud.minier@telecom-paris.fr [PMM: fix checkpatch nits, remove commented out code] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/stm32l4x5_usart-test.c | 315 +++++++++++++++++++++++++++++ tests/qtest/meson.build | 4 +- 2 files changed, 318 insertions(+), 1 deletion(-) create mode 100644 tests/qtest/stm32l4x5_usart-test.c diff --git a/tests/qtest/stm32l4x5_usart-test.c b/tests/qtest/stm32l4x5_usart-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/stm32l4x5_usart-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTest testcase for STML4X5_USART + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "libqtest.h" +#include "hw/misc/stm32l4x5_rcc_internals.h" +#include "hw/registerfields.h" + +#define RCC_BASE_ADDR 0x40021000 +/* Use USART 1 ADDR, assume the others work the same */ +#define USART1_BASE_ADDR 0x40013800 + +/* See stm32l4x5_usart for definitions */ +REG32(CR1, 0x00) + FIELD(CR1, M1, 28, 1) + FIELD(CR1, OVER8, 15, 1) + FIELD(CR1, M0, 12, 1) + FIELD(CR1, PCE, 10, 1) + FIELD(CR1, TXEIE, 7, 1) + FIELD(CR1, RXNEIE, 5, 1) + FIELD(CR1, TE, 3, 1) + FIELD(CR1, RE, 2, 1) + FIELD(CR1, UE, 0, 1) +REG32(CR2, 0x04) +REG32(CR3, 0x08) + FIELD(CR3, OVRDIS, 12, 1) +REG32(BRR, 0x0C) +REG32(GTPR, 0x10) +REG32(RTOR, 0x14) +REG32(RQR, 0x18) +REG32(ISR, 0x1C) + FIELD(ISR, TXE, 7, 1) + FIELD(ISR, RXNE, 5, 1) + FIELD(ISR, ORE, 3, 1) +REG32(ICR, 0x20) +REG32(RDR, 0x24) +REG32(TDR, 0x28) + +#define NVIC_ISPR1 0XE000E204 +#define NVIC_ICPR1 0xE000E284 +#define USART1_IRQ 37 + +static bool check_nvic_pending(QTestState *qts, unsigned int n) +{ + /* No USART interrupts are less than 32 */ + assert(n > 32); + n -= 32; + return qtest_readl(qts, NVIC_ISPR1) & (1 << n); +} + +static bool clear_nvic_pending(QTestState *qts, unsigned int n) +{ + /* No USART interrupts are less than 32 */ + assert(n > 32); + n -= 32; + qtest_writel(qts, NVIC_ICPR1, (1 << n)); + return true; +} + +/* + * Wait indefinitely for the flag to be updated. + * If this is run on a slow CI runner, + * the meson harness will timeout after 10 minutes for us. + */ +static bool usart_wait_for_flag(QTestState *qts, uint32_t event_addr, + uint32_t flag) +{ + while (true) { + if ((qtest_readl(qts, event_addr) & flag)) { + return true; + } + g_usleep(1000); + } + + return false; +} + +static void usart_receive_string(QTestState *qts, int sock_fd, const char *in, + char *out) +{ + int i, in_len = strlen(in); + + g_assert_true(send(sock_fd, in, in_len, 0) == in_len); + for (i = 0; i < in_len; i++) { + g_assert_true(usart_wait_for_flag(qts, + USART1_BASE_ADDR + A_ISR, R_ISR_RXNE_MASK)); + out[i] = qtest_readl(qts, USART1_BASE_ADDR + A_RDR); + } + out[i] = '\0'; +} + +static void usart_send_string(QTestState *qts, const char *in) +{ + int i, in_len = strlen(in); + + for (i = 0; i < in_len; i++) { + qtest_writel(qts, USART1_BASE_ADDR + A_TDR, in[i]); + g_assert_true(usart_wait_for_flag(qts, + USART1_BASE_ADDR + A_ISR, R_ISR_TXE_MASK)); + } +} + +/* Init the RCC clocks to run at 80 MHz */ +static void init_clocks(QTestState *qts) +{ + uint32_t value; + + /* MSIRANGE can be set only when MSI is OFF or READY */ + qtest_writel(qts, (RCC_BASE_ADDR + A_CR), R_CR_MSION_MASK); + + /* Clocking from MSI, in case MSI was not the default source */ + qtest_writel(qts, (RCC_BASE_ADDR + A_CFGR), 0); + + /* + * Update PLL and set MSI as the source clock. + * PLLM = 1 --> 000 + * PLLN = 40 --> 40 + * PPLLR = 2 --> 00 + * PLLDIV = unused, PLLP = unused (SAI3), PLLQ = unused (48M1) + * SRC = MSI --> 01 + */ + qtest_writel(qts, (RCC_BASE_ADDR + A_PLLCFGR), R_PLLCFGR_PLLREN_MASK | + (40 << R_PLLCFGR_PLLN_SHIFT) | + (0b01 << R_PLLCFGR_PLLSRC_SHIFT)); + + /* PLL activation */ + + value = qtest_readl(qts, (RCC_BASE_ADDR + A_CR)); + qtest_writel(qts, (RCC_BASE_ADDR + A_CR), value | R_CR_PLLON_MASK); + + /* RCC_CFGR is OK by defaut */ + qtest_writel(qts, (RCC_BASE_ADDR + A_CFGR), 0); + + /* CCIPR : no periph clock by default */ + qtest_writel(qts, (RCC_BASE_ADDR + A_CCIPR), 0); + + /* Switches on the PLL clock source */ + value = qtest_readl(qts, (RCC_BASE_ADDR + A_CFGR)); + qtest_writel(qts, (RCC_BASE_ADDR + A_CFGR), (value & ~R_CFGR_SW_MASK) | + (0b11 << R_CFGR_SW_SHIFT)); + + /* Enable SYSCFG clock enabled */ + qtest_writel(qts, (RCC_BASE_ADDR + A_APB2ENR), R_APB2ENR_SYSCFGEN_MASK); + + /* Enable the IO port B clock (See p.252) */ + qtest_writel(qts, (RCC_BASE_ADDR + A_AHB2ENR), R_AHB2ENR_GPIOBEN_MASK); + + /* Enable the clock for USART1 (cf p.259) */ + /* We rewrite SYSCFGEN to not disable it */ + qtest_writel(qts, (RCC_BASE_ADDR + A_APB2ENR), + R_APB2ENR_SYSCFGEN_MASK | R_APB2ENR_USART1EN_MASK); + + /* TODO: Enable usart via gpio */ + + /* Set PCLK as the clock for USART1(cf p.272) i.e. reset both bits */ + qtest_writel(qts, (RCC_BASE_ADDR + A_CCIPR), 0); + + /* Reset USART1 (see p.249) */ + qtest_writel(qts, (RCC_BASE_ADDR + A_APB2RSTR), 1 << 14); + qtest_writel(qts, (RCC_BASE_ADDR + A_APB2RSTR), 0); +} + +static void init_uart(QTestState *qts) +{ + uint32_t cr1; + + init_clocks(qts); + + /* + * For 115200 bauds, see p.1349. + * The clock has a frequency of 80Mhz, + * for 115200, we have to put a divider of 695 = 0x2B7. + */ + qtest_writel(qts, (USART1_BASE_ADDR + A_BRR), 0x2B7); + + /* + * Set the oversampling by 16, + * disable the parity control and + * set the word length to 8. (cf p.1377) + */ + cr1 = qtest_readl(qts, (USART1_BASE_ADDR + A_CR1)); + cr1 &= ~(R_CR1_M1_MASK | R_CR1_M0_MASK | R_CR1_OVER8_MASK | R_CR1_PCE_MASK); + qtest_writel(qts, (USART1_BASE_ADDR + A_CR1), cr1); + + /* Enable the transmitter, the receiver and the USART. */ + qtest_writel(qts, (USART1_BASE_ADDR + A_CR1), + R_CR1_UE_MASK | R_CR1_RE_MASK | R_CR1_TE_MASK); +} + +static void test_write_read(void) +{ + QTestState *qts = qtest_init("-M b-l475e-iot01a"); + + /* Test that we can write and retrieve a value from the device */ + qtest_writel(qts, USART1_BASE_ADDR + A_TDR, 0xFFFFFFFF); + const uint32_t tdr = qtest_readl(qts, USART1_BASE_ADDR + A_TDR); + g_assert_cmpuint(tdr, ==, 0x000001FF); +} + +static void test_receive_char(void) +{ + int sock_fd; + uint32_t cr1; + QTestState *qts = qtest_init_with_serial("-M b-l475e-iot01a", &sock_fd); + + init_uart(qts); + + /* Try without initializing IRQ */ + g_assert_true(send(sock_fd, "a", 1, 0) == 1); + usart_wait_for_flag(qts, USART1_BASE_ADDR + A_ISR, R_ISR_RXNE_MASK); + g_assert_cmphex(qtest_readl(qts, USART1_BASE_ADDR + A_RDR), ==, 'a'); + g_assert_false(check_nvic_pending(qts, USART1_IRQ)); + + /* Now with the IRQ */ + cr1 = qtest_readl(qts, (USART1_BASE_ADDR + A_CR1)); + cr1 |= R_CR1_RXNEIE_MASK; + qtest_writel(qts, USART1_BASE_ADDR + A_CR1, cr1); + g_assert_true(send(sock_fd, "b", 1, 0) == 1); + usart_wait_for_flag(qts, USART1_BASE_ADDR + A_ISR, R_ISR_RXNE_MASK); + g_assert_cmphex(qtest_readl(qts, USART1_BASE_ADDR + A_RDR), ==, 'b'); + g_assert_true(check_nvic_pending(qts, USART1_IRQ)); + clear_nvic_pending(qts, USART1_IRQ); + + close(sock_fd); + + qtest_quit(qts); +} + +static void test_send_char(void) +{ + int sock_fd; + char s[1]; + uint32_t cr1; + QTestState *qts = qtest_init_with_serial("-M b-l475e-iot01a", &sock_fd); + + init_uart(qts); + + /* Try without initializing IRQ */ + qtest_writel(qts, USART1_BASE_ADDR + A_TDR, 'c'); + g_assert_true(recv(sock_fd, s, 1, 0) == 1); + g_assert_cmphex(s[0], ==, 'c'); + g_assert_false(check_nvic_pending(qts, USART1_IRQ)); + + /* Now with the IRQ */ + cr1 = qtest_readl(qts, (USART1_BASE_ADDR + A_CR1)); + cr1 |= R_CR1_TXEIE_MASK; + qtest_writel(qts, USART1_BASE_ADDR + A_CR1, cr1); + qtest_writel(qts, USART1_BASE_ADDR + A_TDR, 'd'); + g_assert_true(recv(sock_fd, s, 1, 0) == 1); + g_assert_cmphex(s[0], ==, 'd'); + g_assert_true(check_nvic_pending(qts, USART1_IRQ)); + clear_nvic_pending(qts, USART1_IRQ); + + close(sock_fd); + + qtest_quit(qts); +} + +static void test_receive_str(void) +{ + int sock_fd; + char s[10]; + QTestState *qts = qtest_init_with_serial("-M b-l475e-iot01a", &sock_fd); + + init_uart(qts); + + usart_receive_string(qts, sock_fd, "hello", s); + g_assert_true(memcmp(s, "hello", 5) == 0); + + close(sock_fd); + + qtest_quit(qts); +} + +static void test_send_str(void) +{ + int sock_fd; + char s[10]; + QTestState *qts = qtest_init_with_serial("-M b-l475e-iot01a", &sock_fd); + + init_uart(qts); + + usart_send_string(qts, "world"); + g_assert_true(recv(sock_fd, s, 10, 0) == 5); + g_assert_true(memcmp(s, "world", 5) == 0); + + close(sock_fd); + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + int ret; + + g_test_init(&argc, &argv, NULL); + g_test_set_nonfatal_assertions(); + + qtest_add_func("stm32l4x5/usart/write_read", test_write_read); + qtest_add_func("stm32l4x5/usart/receive_char", test_receive_char); + qtest_add_func("stm32l4x5/usart/send_char", test_send_char); + qtest_add_func("stm32l4x5/usart/receive_str", test_receive_str); + qtest_add_func("stm32l4x5/usart/send_str", test_send_str); + ret = g_test_run(); + + return ret; +} + diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ slow_qtests = { 'npcm7xx_pwm-test': 300, 'npcm7xx_watchdog_timer-test': 120, 'qom-test' : 900, + 'stm32l4x5_usart-test' : 600, 'test-hmp' : 240, 'pxe-test': 610, 'prom-env-test': 360, @@ -XXX,XX +XXX,XX @@ qtests_stm32l4x5 = \ ['stm32l4x5_exti-test', 'stm32l4x5_syscfg-test', 'stm32l4x5_rcc-test', - 'stm32l4x5_gpio-test'] + 'stm32l4x5_gpio-test', + 'stm32l4x5_usart-test'] qtests_arm = \ (config_all_devices.has_key('CONFIG_MPS2') ? ['sse-timer-test'] : []) + \ -- 2.34.1