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 Nuvoton new board models, and some more minor stuff. I also put in the deprecation patches for unicore32 and lm32. thanks -- PMM The following changes since commit a68694cd1f3e5448cca814ff39b871f9ebd71ed5: Merge remote-tracking branch 'remotes/philmd-gitlab/tags/edk2-next-20200914' into staging (2020-09-14 12:18:58 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200914 for you to fetch changes up to dd44ae00fc5342ed99acb68ec3508f76a71d523a: MAINTAINERS: Add maintainer entry for Xilinx ZynqMP CAN controller (2020-09-14 14:27:08 +0100) ---------------------------------------------------------------- target-arm queue: * hw/misc/a9scu: Do not allow invalid CPU count * hw/misc/a9scu: Minor cleanups * hw/timer/armv7m_systick: assert that board code set system_clock_scale * decodetree: Improve identifier matching * target/arm: Clean up neon fp insn size field decode * target/arm: Remove KVM support for 32-bit Arm hosts * hw/arm/mps2: New board models mps2-an386, mps2-an500 * Deprecate Unicore32 port * Deprecate lm32 port * target/arm: Count PMU events when MDCR.SPME is set * hw/arm: versal-virt: Correct the tx/rx GEM clocks * New Nuvoton iBMC board models npcm750-evb, quanta-gsj * xlnx-zynqmp: implement ZynqMP CAN controllers ---------------------------------------------------------------- Aaron Lindsay (1): target/arm: Count PMU events when MDCR.SPME is set Edgar E. Iglesias (1): hw/arm: versal-virt: Correct the tx/rx GEM clocks Havard Skinnemoen (14): hw/misc: Add NPCM7xx System Global Control Registers device model hw/misc: Add NPCM7xx Clock Controller device model hw/timer: Add NPCM7xx Timer device model hw/arm: Add NPCM730 and NPCM750 SoC models hw/arm: Add two NPCM7xx-based machines roms: Add virtual Boot ROM for NPCM7xx SoCs hw/arm: Load -bios image as a boot ROM for npcm7xx hw/nvram: NPCM7xx OTP device model hw/mem: Stubbed out NPCM7xx Memory Controller model hw/ssi: NPCM7xx Flash Interface Unit device model hw/arm: Wire up BMC boot flash for npcm750-evb and quanta-gsj hw/arm/npcm7xx: add board setup stub for CPU and UART clocks docs/system: Add Nuvoton machine documentation tests/acceptance: console boot tests for quanta-gsj Peter Maydell (11): hw/timer/armv7m_systick: assert that board code set system_clock_scale target/arm: Convert Neon 3-same-fp size field to MO_* in decode target/arm: Convert Neon VCVT fp size field to MO_* in decode target/arm: Convert VCMLA, VCADD size field to MO_* in decode target/arm: Remove KVM support for 32-bit Arm hosts target/arm: Remove no-longer-reachable 32-bit KVM code hw/arm/mps2: New board model mps2-an386 hw/arm/mps2: New board model mps2-an500 docs/system/arm/mps2.rst: Make board list consistent Deprecate Unicore32 port Deprecate lm32 port Philippe Mathieu-Daudé (4): hw/misc/a9scu: Do not allow invalid CPU count hw/misc/a9scu: Simplify setting MemoryRegionOps::valid fields hw/misc/a9scu: Simplify setting MemoryRegionOps::impl fields hw/misc/a9scu: Report unimplemented accesses with qemu_log_mask(UNIMP) Richard Henderson (1): decodetree: Improve identifier matching Vikram Garhwal (4): hw/net/can: Introduce Xilinx ZynqMP CAN controller xlnx-zynqmp: Connect Xilinx ZynqMP CAN controllers tests/qtest: Introduce tests for Xilinx ZynqMP CAN controller MAINTAINERS: Add maintainer entry for Xilinx ZynqMP CAN controller docs/system/arm/mps2.rst | 20 +- docs/system/arm/nuvoton.rst | 92 +++ docs/system/deprecated.rst | 32 +- docs/system/target-arm.rst | 1 + configure | 2 +- default-configs/arm-softmmu.mak | 1 + include/hw/arm/npcm7xx.h | 112 +++ include/hw/arm/xlnx-zynqmp.h | 8 + include/hw/mem/npcm7xx_mc.h | 36 + include/hw/misc/npcm7xx_clk.h | 48 ++ include/hw/misc/npcm7xx_gcr.h | 43 ++ include/hw/net/xlnx-zynqmp-can.h | 78 +++ include/hw/nvram/npcm7xx_otp.h | 79 +++ include/hw/ssi/npcm7xx_fiu.h | 73 ++ include/hw/timer/npcm7xx_timer.h | 78 +++ target/arm/kvm-consts.h | 7 - target/arm/kvm_arm.h | 6 - target/arm/neon-dp.decode | 18 +- target/arm/neon-shared.decode | 18 +- tests/decode/succ_ident1.decode | 7 + hw/arm/mps2.c | 97 ++- hw/arm/npcm7xx.c | 532 +++++++++++++++ hw/arm/npcm7xx_boards.c | 197 ++++++ hw/arm/xlnx-versal-virt.c | 2 +- hw/arm/xlnx-zcu102.c | 20 + hw/arm/xlnx-zynqmp.c | 34 + hw/mem/npcm7xx_mc.c | 84 +++ hw/misc/a9scu.c | 59 +- hw/misc/npcm7xx_clk.c | 266 ++++++++ hw/misc/npcm7xx_gcr.c | 269 ++++++++ hw/net/can/xlnx-zynqmp-can.c | 1165 ++++++++++++++++++++++++++++++++ hw/nvram/npcm7xx_otp.c | 440 ++++++++++++ hw/ssi/npcm7xx_fiu.c | 572 ++++++++++++++++ hw/timer/armv7m_systick.c | 8 + hw/timer/npcm7xx_timer.c | 543 +++++++++++++++ target/arm/cpu.c | 101 ++- target/arm/helper.c | 2 +- target/arm/kvm.c | 7 - target/arm/kvm32.c | 595 ---------------- tests/qtest/xlnx-can-test.c | 359 ++++++++++ .gitmodules | 3 + MAINTAINERS | 18 + hw/arm/Kconfig | 9 + hw/arm/meson.build | 1 + hw/mem/meson.build | 1 + hw/misc/meson.build | 4 + hw/misc/trace-events | 8 + hw/net/can/meson.build | 1 + hw/nvram/meson.build | 1 + hw/ssi/meson.build | 1 + hw/ssi/trace-events | 11 + hw/timer/meson.build | 1 + hw/timer/trace-events | 5 + pc-bios/README | 6 + pc-bios/meson.build | 1 + pc-bios/npcm7xx_bootrom.bin | Bin 0 -> 768 bytes roms/Makefile | 7 + roms/vbootrom | 1 + scripts/decodetree.py | 46 +- target/arm/meson.build | 5 +- target/arm/translate-neon.c.inc | 42 +- tests/acceptance/boot_linux_console.py | 83 +++ tests/qtest/meson.build | 1 + 63 files changed, 5584 insertions(+), 783 deletions(-) create mode 100644 docs/system/arm/nuvoton.rst create mode 100644 include/hw/arm/npcm7xx.h create mode 100644 include/hw/mem/npcm7xx_mc.h create mode 100644 include/hw/misc/npcm7xx_clk.h create mode 100644 include/hw/misc/npcm7xx_gcr.h create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 include/hw/nvram/npcm7xx_otp.h create mode 100644 include/hw/ssi/npcm7xx_fiu.h create mode 100644 include/hw/timer/npcm7xx_timer.h create mode 100644 tests/decode/succ_ident1.decode create mode 100644 hw/arm/npcm7xx.c create mode 100644 hw/arm/npcm7xx_boards.c create mode 100644 hw/mem/npcm7xx_mc.c create mode 100644 hw/misc/npcm7xx_clk.c create mode 100644 hw/misc/npcm7xx_gcr.c create mode 100644 hw/net/can/xlnx-zynqmp-can.c create mode 100644 hw/nvram/npcm7xx_otp.c create mode 100644 hw/ssi/npcm7xx_fiu.c create mode 100644 hw/timer/npcm7xx_timer.c delete mode 100644 target/arm/kvm32.c create mode 100644 tests/qtest/xlnx-can-test.c create mode 100644 pc-bios/npcm7xx_bootrom.bin create mode 160000 roms/vbootrom From: Philippe Mathieu-Daudé <f4bug@amsat.org> Per the datasheet (DDI0407 r2p0): "The SCU connects one to four Cortex-A9 processors to the memory system through the AXI interfaces." Change the instance_init() handler to a device_realize() one so we can verify the property is in range, and return an error to the caller if not. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/a9scu.h" #include "hw/qdev-properties.h" #include "migration/vmstate.h" +#include "qapi/error.h" #include "qemu/module.h" +#define A9_SCU_CPU_MAX 4 + static uint64_t a9_scu_read(void *opaque, hwaddr offset, unsigned size) { @@ -XXX,XX +XXX,XX @@ static void a9_scu_reset(DeviceState *dev) s->control = 0; } -static void a9_scu_init(Object *obj) +static void a9_scu_realize(DeviceState *dev, Error **errp) { - A9SCUState *s = A9_SCU(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + A9SCUState *s = A9_SCU(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - memory_region_init_io(&s->iomem, obj, &a9_scu_ops, s, + if (!s->num_cpu || s->num_cpu > A9_SCU_CPU_MAX) { + error_setg(errp, "Illegal CPU count: %u", s->num_cpu); + return; + } + + memory_region_init_io(&s->iomem, OBJECT(s), &a9_scu_ops, s, "a9-scu", 0x100); sysbus_init_mmio(sbd, &s->iomem); } @@ -XXX,XX +XXX,XX @@ static void a9_scu_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, a9_scu_properties); dc->vmsd = &vmstate_a9_scu; dc->reset = a9_scu_reset; + dc->realize = a9_scu_realize; } static const TypeInfo a9_scu_info = { .name = TYPE_A9_SCU, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(A9SCUState), - .instance_init = a9_scu_init, .class_init = a9_scu_class_init, }; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Per the datasheet (DDI0407 r2p0): "All SCU registers are byte accessible" and are 32-bit aligned. Set MemoryRegionOps::valid min/max fields and simplify the write() handler. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-3-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { A9SCUState *s = (A9SCUState *)opaque; - uint32_t mask; + uint32_t mask = MAKE_64BIT_MASK(0, size * 8); uint32_t shift; - switch (size) { - case 1: - mask = 0xff; - break; - case 2: - mask = 0xffff; - break; - case 4: - mask = 0xffffffff; - break; - default: - fprintf(stderr, "Invalid size %u in write to a9 scu register %x\n", - size, (unsigned)offset); - return; - } switch (offset) { case 0x00: /* Control */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, static const MemoryRegionOps a9_scu_ops = { .read = a9_scu_read, .write = a9_scu_write, + .valid = { + .min_access_size = 1, + .max_access_size = 4, + }, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This model implementation is designed for 32-bit accesses. We can simplify setting the MemoryRegionOps::impl min/max fields to 32-bit (memory::access_with_adjusted_size() will take care of the 8/16-bit accesses). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ static uint64_t a9_scu_read(void *opaque, hwaddr offset, return (((1 << s->num_cpu) - 1) << 4) | (s->num_cpu - 1); case 0x08: /* CPU Power Status */ return s->status; - case 0x09: /* CPU status. */ - return s->status >> 8; - case 0x0a: /* CPU status. */ - return s->status >> 16; - case 0x0b: /* CPU status. */ - return s->status >> 24; case 0x0c: /* Invalidate All Registers In Secure State */ return 0; case 0x40: /* Filtering Start Address Register */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { A9SCUState *s = (A9SCUState *)opaque; - uint32_t mask = MAKE_64BIT_MASK(0, size * 8); - uint32_t shift; switch (offset) { case 0x00: /* Control */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, case 0x4: /* Configuration: RO */ break; case 0x08: case 0x09: case 0x0A: case 0x0B: /* Power Control */ - shift = (offset - 0x8) * 8; - s->status &= ~(mask << shift); - s->status |= ((value & mask) << shift); + s->status = value; break; case 0x0c: /* Invalidate All Registers In Secure State */ /* no-op as we do not implement caches */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, static const MemoryRegionOps a9_scu_ops = { .read = a9_scu_read, .write = a9_scu_write, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + }, .valid = { .min_access_size = 1, .max_access_size = 4, -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Report unimplemented register accesses using qemu_log_mask(UNIMP). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-5-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "migration/vmstate.h" #include "qapi/error.h" +#include "qemu/log.h" #include "qemu/module.h" #define A9_SCU_CPU_MAX 4 @@ -XXX,XX +XXX,XX @@ static uint64_t a9_scu_read(void *opaque, hwaddr offset, case 0x54: /* SCU Non-secure Access Control Register */ /* unimplemented, fall through */ default: + qemu_log_mask(LOG_UNIMP, "%s: Unsupported offset 0x%"HWADDR_PRIx"\n", + __func__, offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, case 0x54: /* SCU Non-secure Access Control Register */ /* unimplemented, fall through */ default: + qemu_log_mask(LOG_UNIMP, "%s: Unsupported offset 0x%"HWADDR_PRIx + " value 0x%"PRIx64"\n", + __func__, offset, value); break; } } -- 2.20.1 It is the responsibility of board code for an armv7m system to set system_clock_scale appropriately for the CPU speed of the core. If it forgets to do this, then QEMU will hang if the guest tries to use the systick timer in the "tick at the CPU clock frequency" mode. We forgot that in a couple of our boards (see commits ce4f70e81ed23c93f, e7e5a9595ab1136). Add an assertion in the systick reset method so we don't let any new boards in with the same bug. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200825160847.18091-1-peter.maydell@linaro.org --- hw/timer/armv7m_systick.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/armv7m_systick.c +++ b/hw/timer/armv7m_systick.c @@ -XXX,XX +XXX,XX @@ static void systick_reset(DeviceState *dev) { SysTickState *s = SYSTICK(dev); + /* + * Forgetting to set system_clock_scale is always a board code + * bug. We can't check this earlier because for some boards + * (like stellaris) it is not yet configured at the point where + * the systick device is realized. + */ + assert(system_clock_scale != 0); + s->control = 0; s->reload = 0; s->tick = 0; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Only argument set members have to be C identifiers, everything else gets prefixed during conversion to C. Some places just checked the leading character, and some places matched a leading character plus a C identifier. Convert everything to match full identifiers, including the [&%@&] prefix, and drop the full C identifier requirement. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903192334.1603773-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/decode/succ_ident1.decode | 7 +++++ scripts/decodetree.py | 46 +++++++++++++++++++++------------ 2 files changed, 37 insertions(+), 16 deletions(-) create mode 100644 tests/decode/succ_ident1.decode diff --git a/tests/decode/succ_ident1.decode b/tests/decode/succ_ident1.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/decode/succ_ident1.decode @@ -XXX,XX +XXX,XX @@ +%1f 0:8 +%2f 8:8 +%3f 16:8 + +&3arg a b c +@3arg ........ ........ ........ ........ &3arg a=%1f b=%2f c=%3f +3insn 00000000 ........ ........ ........ @3arg diff --git a/scripts/decodetree.py b/scripts/decodetree.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/decodetree.py +++ b/scripts/decodetree.py @@ -XXX,XX +XXX,XX @@ output_fd = None insntype = 'uint32_t' decode_function = 'decode' -re_ident = '[a-zA-Z][a-zA-Z0-9_]*' +# An identifier for C. +re_C_ident = '[a-zA-Z][a-zA-Z0-9_]*' +# Identifiers for Arguments, Fields, Formats and Patterns. +re_arg_ident = '&[a-zA-Z0-9_]*' +re_fld_ident = '%[a-zA-Z0-9_]*' +re_fmt_ident = '@[a-zA-Z0-9_]*' +re_pat_ident = '[a-zA-Z0-9_]*' def error_with_file(file, lineno, *args): """Print an error message from file:line and args and exit.""" @@ -XXX,XX +XXX,XX @@ class ExcMultiPattern(MultiPattern): def parse_field(lineno, name, toks): """Parse one instruction field from TOKS at LINENO""" global fields - global re_ident global insnwidth # A "simple" field will have only one entry; @@ -XXX,XX +XXX,XX @@ def parse_field(lineno, name, toks): width = 0 func = None for t in toks: - if re.fullmatch('!function=' + re_ident, t): + if re.match('^!function=', t): if func: error(lineno, 'duplicate function') func = t.split('=') @@ -XXX,XX +XXX,XX @@ def parse_field(lineno, name, toks): def parse_arguments(lineno, name, toks): """Parse one argument set from TOKS at LINENO""" global arguments - global re_ident + global re_C_ident global anyextern flds = [] @@ -XXX,XX +XXX,XX @@ def parse_arguments(lineno, name, toks): extern = True anyextern = True continue - if not re.fullmatch(re_ident, t): + if not re.fullmatch(re_C_ident, t): error(lineno, 'invalid argument set token "{0}"'.format(t)) if t in flds: error(lineno, 'duplicate argument "{0}"'.format(t)) @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): global arguments global formats global allpatterns - global re_ident + global re_arg_ident + global re_fld_ident + global re_fmt_ident + global re_C_ident global insnwidth global insnmask global variablewidth @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): fmt = None for t in toks: # '&Foo' gives a format an explcit argument set. - if t[0] == '&': + if re.fullmatch(re_arg_ident, t): tt = t[1:] if arg: error(lineno, 'multiple argument sets') @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): continue # '@Foo' gives a pattern an explicit format. - if t[0] == '@': + if re.fullmatch(re_fmt_ident, t): tt = t[1:] if fmt: error(lineno, 'multiple formats') @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): continue # '%Foo' imports a field. - if t[0] == '%': + if re.fullmatch(re_fld_ident, t): tt = t[1:] flds = add_field_byname(lineno, flds, tt, tt) continue # 'Foo=%Bar' imports a field with a different name. - if re.fullmatch(re_ident + '=%' + re_ident, t): + if re.fullmatch(re_C_ident + '=' + re_fld_ident, t): (fname, iname) = t.split('=%') flds = add_field_byname(lineno, flds, fname, iname) continue # 'Foo=number' sets an argument field to a constant value - if re.fullmatch(re_ident + '=[+-]?[0-9]+', t): + if re.fullmatch(re_C_ident + '=[+-]?[0-9]+', t): (fname, value) = t.split('=') value = int(value) flds = add_field(lineno, flds, fname, ConstField(value)) @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): fixedmask = (fixedmask << shift) | fms undefmask = (undefmask << shift) | ubm # Otherwise, fieldname:fieldwidth - elif re.fullmatch(re_ident + ':s?[0-9]+', t): + elif re.fullmatch(re_C_ident + ':s?[0-9]+', t): (fname, flen) = t.split(':') sign = False if flen[0] == 's': @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): def parse_file(f, parent_pat): """Parse all of the patterns within a file""" + global re_arg_ident + global re_fld_ident + global re_fmt_ident + global re_pat_ident # Read all of the lines of the file. Concatenate lines # ending in backslash; discard empty lines and comments. @@ -XXX,XX +XXX,XX @@ def parse_file(f, parent_pat): continue # Determine the type of object needing to be parsed. - if name[0] == '%': + if re.fullmatch(re_fld_ident, name): parse_field(start_lineno, name[1:], toks) - elif name[0] == '&': + elif re.fullmatch(re_arg_ident, name): parse_arguments(start_lineno, name[1:], toks) - elif name[0] == '@': + elif re.fullmatch(re_fmt_ident, name): parse_generic(start_lineno, None, name[1:], toks) - else: + elif re.fullmatch(re_pat_ident, name): parse_generic(start_lineno, parent_pat, name, toks) + else: + error(lineno, 'invalid token "{0}"'.format(name)) toks = [] if nesting != 0: -- 2.20.1 In the Neon instructions, some instruction formats have a 2-bit size field which corresponds exactly to QEMU's MO_8/16/32/64. However the floating-point insns in the 3-same group have a 1-bit size field which is "0 for 32-bit float and 1 for 16-bit float". Currently we pass these values directly through to trans_ functions, which means that when reading a particular trans_ function you need to know if that insn uses a 2-bit size or a 1-bit size. Move the handling of the 1-bit size to the decodetree file, so that all these insns consistently pass a size to the trans_ function which is an MO_8/16/32/64 value. In this commit we switch over the insns using the 3same_fp and 3same_fp_q0 formats. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200903133209.5141-2-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 15 ++++++++++----- target/arm/translate-neon.c.inc | 16 +++++++++++----- 2 files changed, 21 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 @@ @3same_q0 .... ... . . . size:2 .... .... .... . 0 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 -# For FP insns the high bit of 'size' is used as part of opcode decode -@3same_fp .... ... . . . . size:1 .... .... .... . q:1 . . .... \ - &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp -@3same_fp_q0 .... ... . . . . size:1 .... .... .... . 0 . . .... \ - &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 +# For FP insns the high bit of 'size' is used as part of opcode decode, +# and the 'size' bit is 0 for 32-bit float and 1 for 16-bit float. +# This converts this encoding to the same MO_8/16/32/64 values that the +# integer neon insns use. +%3same_fp_size 20:1 !function=neon_3same_fp_size + +@3same_fp .... ... . . . . . .... .... .... . q:1 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%3same_fp_size +@3same_fp_q0 .... ... . . . . . .... .... .... . 0 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 size=%3same_fp_size VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static inline int rsub_8(DisasContext *s, int x) return 8 - x; } +static inline int neon_3same_fp_size(DisasContext *s, int x) +{ + /* Convert 0==fp32, 1==fp16 into a MO_* value */ + return MO_32 - x; +} + /* Include the generated Neon decoder */ #include "decode-neon-dp.c.inc" #include "decode-neon-ls.c.inc" @@ -XXX,XX +XXX,XX @@ DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) WRAP_FP_GVEC(gen_##INSN##_fp16_3s, FPST_STD_F16, HFUNC) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ - if (a->size != 0) { \ + if (a->size == MO_16) { \ if (!dc_isar_feature(aa32_fp16_arith, s)) { \ return false; \ } \ @@ -XXX,XX +XXX,XX @@ static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) return false; } - if (a->size != 0) { + if (a->size == MO_16) { if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return false; } - if (a->size != 0) { + if (a->size == MO_16) { if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, assert(a->q == 0); /* enforced by decode patterns */ - fpstatus = fpstatus_ptr(a->size != 0 ? FPST_STD_F16 : FPST_STD); + fpstatus = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, #define DO_3S_FP_PAIR(INSN,FUNC) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ - if (a->size != 0) { \ + if (a->size == MO_16) { \ if (!dc_isar_feature(aa32_fp16_arith, s)) { \ return false; \ } \ -- 2.20.1 Convert the insns using the 2reg_vcvt and 2reg_vcvt_f16 formats to pass the size through to the trans function as a MO_* value rather than the '0==f32, 1==f16' used in the fp 3-same encodings. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200903133209.5141-3-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 +-- target/arm/translate-neon.c.inc | 4 ++-- 2 files changed, 3 insertions(+), 4 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 + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 shift=%neon_rshift_i5 @2reg_vcvt_f16 .... ... . . . 11 .... .... .... . q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, return false; } - if (a->size != 0) { + if (a->size == MO_16) { if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, return true; } - fpst = fpstatus_ptr(a->size ? FPST_STD_F16 : FPST_STD); + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, vec_size, vec_size, a->shift, fn); tcg_temp_free_ptr(fpst); return true; -- 2.20.1 The VCMLA and VCADD insns have a size field which is 0 for fp16 and 1 for fp32 (note that this is the reverse of the Neon 3-same encoding!). Convert it to MO_* values in decode for consistency. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200903133209.5141-4-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 18 ++++++++++++------ target/arm/translate-neon.c.inc | 22 ++++++++++++---------- 2 files changed, 24 insertions(+), 16 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ %vd_dp 22:1 12:4 %vd_sp 12:4 22:1 -VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +# For VCMLA/VCADD insns, convert the single-bit size field +# which is 0 for fp16 and 1 for fp32 into a MO_* constant. +# (Note that this is the reverse of the sense of the 1-bit size +# field in the 3same_fp Neon insns.) +%vcadd_size 20:1 !function=plus1 -VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VCMLA 1111 110 rot:2 . 1 . .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size + +VCADD 1111 110 rot:1 1 . 0 . .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size # VUDOT and VSDOT VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ @@ -XXX,XX +XXX,XX @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ - vn=%vn_dp vd=%vd_dp size=0 + vn=%vn_dp vd=%vd_dp size=1 VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0 + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=2 index=0 VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ vm=%vm_dp vn=%vn_dp vd=%vd_dp diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) gen_helper_gvec_3_ptr *fn_gvec_ptr; if (!dc_isar_feature(aa32_vcma, s) - || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { + || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) } opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD); - fn_gvec_ptr = a->size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); + fn_gvec_ptr = (a->size == MO_16) ? + gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas; tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) gen_helper_gvec_3_ptr *fn_gvec_ptr; if (!dc_isar_feature(aa32_vcma, s) - || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { + || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) } opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD); - fn_gvec_ptr = a->size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); + fn_gvec_ptr = (a->size == MO_16) ? + gen_helper_gvec_fcaddh : gen_helper_gvec_fcadds; tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) if (!dc_isar_feature(aa32_vcma, s)) { return false; } - if (a->size == 0 && !dc_isar_feature(aa32_fp16_arith, s)) { + if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) return true; } - fn_gvec_ptr = (a->size ? gen_helper_gvec_fcmlas_idx - : gen_helper_gvec_fcmlah_idx); + fn_gvec_ptr = (a->size == MO_16) ? + gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx; opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD); + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), -- 2.20.1 We deprecated the support for KVM on 32-bit Arm hosts in time for release 5.0, which means that our deprecation policy allows us to drop it in release 5.2. Remove the code. To repeat the rationale from the deprecation note: the Linux kernel dropped support for 32-bit Arm KVM hosts in 5.7. Running 32-bit guests on a 64-bit Arm host remains supported. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200904154156.31943-2-peter.maydell@linaro.org --- docs/system/deprecated.rst | 16 +- configure | 2 +- target/arm/kvm32.c | 595 ------------------------------------- target/arm/meson.build | 5 +- 4 files changed, 10 insertions(+), 608 deletions(-) delete mode 100644 target/arm/kvm32.c diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -XXX,XX +XXX,XX @@ The ``compat`` property used to set backwards compatibility modes for the processor has been deprecated. The ``max-cpu-compat`` property of the ``pseries`` machine type should be used instead. -KVM guest support on 32-bit Arm hosts (since 5.0) -''''''''''''''''''''''''''''''''''''''''''''''''' - -The Linux kernel has dropped support for allowing 32-bit Arm systems -to host KVM guests as of the 5.7 kernel. Accordingly, QEMU is deprecating -its support for this configuration and will remove it in a future version. -Running 32-bit guests on a 64-bit Arm host remains supported. - System emulator devices ----------------------- @@ -XXX,XX +XXX,XX @@ should be used instead of the 1.09.1 version. System emulator CPUS -------------------- +KVM guest support on 32-bit Arm hosts (removed in 5.2) +'''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The Linux kernel has dropped support for allowing 32-bit Arm systems +to host KVM guests as of the 5.7 kernel. Accordingly, QEMU is deprecating +its support for this configuration and will remove it in a future version. +Running 32-bit guests on a 64-bit Arm host remains supported. + RISC-V ISA Specific CPUs (removed in 5.1) ''''''''''''''''''''''''''''''''''''''''' diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ supported_kvm_target() { test "$kvm" = "yes" || return 1 glob "$1" "*-softmmu" || return 1 case "${1%-softmmu}:$cpu" in - arm:arm | aarch64:aarch64 | \ + aarch64:aarch64 | \ i386:i386 | i386:x86_64 | i386:x32 | \ x86_64:i386 | x86_64:x86_64 | x86_64:x32 | \ mips:mips | mipsel:mips | mips64:mips | mips64el:mips | \ diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/target/arm/kvm32.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * ARM implementation of KVM hooks, 32 bit specific code. - * - * Copyright Christoffer Dall 2009-2010 - * - * 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 <sys/ioctl.h> - -#include <linux/kvm.h> - -#include "qemu-common.h" -#include "cpu.h" -#include "qemu/timer.h" -#include "sysemu/runstate.h" -#include "sysemu/kvm.h" -#include "kvm_arm.h" -#include "internals.h" -#include "qemu/log.h" - -static int read_sys_reg32(int fd, uint32_t *pret, uint64_t id) -{ - struct kvm_one_reg idreg = { .id = id, .addr = (uintptr_t)pret }; - - assert((id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32); - return ioctl(fd, KVM_GET_ONE_REG, &idreg); -} - -bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) -{ - /* Identify the feature bits corresponding to the host CPU, and - * fill out the ARMHostCPUClass fields accordingly. To do this - * we have to create a scratch VM, create a single CPU inside it, - * and then query that CPU for the relevant ID registers. - */ - int err = 0, fdarray[3]; - uint32_t midr, id_pfr0; - uint64_t features = 0; - - /* Old kernels may not know about the PREFERRED_TARGET ioctl: however - * we know these will only support creating one kind of guest CPU, - * which is its preferred CPU type. - */ - static const uint32_t cpus_to_try[] = { - QEMU_KVM_ARM_TARGET_CORTEX_A15, - QEMU_KVM_ARM_TARGET_NONE - }; - /* - * target = -1 informs kvm_arm_create_scratch_host_vcpu() - * to use the preferred target - */ - struct kvm_vcpu_init init = { .target = -1, }; - - if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) { - return false; - } - - ahcf->target = init.target; - - /* This is not strictly blessed by the device tree binding docs yet, - * but in practice the kernel does not care about this string so - * there is no point maintaining an KVM_ARM_TARGET_* -> string table. - */ - ahcf->dtb_compatible = "arm,arm-v7"; - - err |= read_sys_reg32(fdarray[2], &midr, ARM_CP15_REG32(0, 0, 0, 0)); - err |= read_sys_reg32(fdarray[2], &id_pfr0, ARM_CP15_REG32(0, 0, 1, 0)); - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar0, - ARM_CP15_REG32(0, 0, 2, 0)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar1, - ARM_CP15_REG32(0, 0, 2, 1)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar2, - ARM_CP15_REG32(0, 0, 2, 2)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar3, - ARM_CP15_REG32(0, 0, 2, 3)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar4, - ARM_CP15_REG32(0, 0, 2, 4)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar5, - ARM_CP15_REG32(0, 0, 2, 5)); - if (read_sys_reg32(fdarray[2], &ahcf->isar.id_isar6, - ARM_CP15_REG32(0, 0, 2, 7))) { - /* - * Older kernels don't support reading ID_ISAR6. This register was - * only introduced in ARMv8, so we can assume that it is zero on a - * CPU that a kernel this old is running on. - */ - ahcf->isar.id_isar6 = 0; - } - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_dfr0, - ARM_CP15_REG32(0, 0, 1, 2)); - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr0, - KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_VFP | KVM_REG_ARM_VFP_MVFR0); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr1, - KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_VFP | KVM_REG_ARM_VFP_MVFR1); - /* - * FIXME: There is not yet a way to read MVFR2. - * Fortunately there is not yet anything in there that affects migration. - */ - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr0, - ARM_CP15_REG32(0, 0, 1, 4)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr1, - ARM_CP15_REG32(0, 0, 1, 5)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr2, - ARM_CP15_REG32(0, 0, 1, 6)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr3, - ARM_CP15_REG32(0, 0, 1, 7)); - if (read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr4, - ARM_CP15_REG32(0, 0, 2, 6))) { - /* - * Older kernels don't support reading ID_MMFR4 (a new in v8 - * register); assume it's zero. - */ - ahcf->isar.id_mmfr4 = 0; - } - - /* - * There is no way to read DBGDIDR, because currently 32-bit KVM - * doesn't implement debug at all. Leave it at zero. - */ - - kvm_arm_destroy_scratch_host_vcpu(fdarray); - - if (err < 0) { - return false; - } - - /* Now we've retrieved all the register information we can - * set the feature bits based on the ID register fields. - * We can assume any KVM supporting CPU is at least a v7 - * with VFPv3, virtualization extensions, and the generic - * timers; this in turn implies most of the other feature - * bits, but a few must be tested. - */ - features |= 1ULL << ARM_FEATURE_V7VE; - features |= 1ULL << ARM_FEATURE_GENERIC_TIMER; - - if (extract32(id_pfr0, 12, 4) == 1) { - features |= 1ULL << ARM_FEATURE_THUMB2EE; - } - if (extract32(ahcf->isar.mvfr1, 12, 4) == 1) { - features |= 1ULL << ARM_FEATURE_NEON; - } - - ahcf->features = features; - - return true; -} - -bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx) -{ - /* Return true if the regidx is a register we should synchronize - * via the cpreg_tuples array (ie is not a core reg we sync by - * hand in kvm_arch_get/put_registers()) - */ - switch (regidx & KVM_REG_ARM_COPROC_MASK) { - case KVM_REG_ARM_CORE: - case KVM_REG_ARM_VFP: - return false; - default: - return true; - } -} - -typedef struct CPRegStateLevel { - uint64_t regidx; - int level; -} CPRegStateLevel; - -/* All coprocessor registers not listed in the following table are assumed to - * be of the level KVM_PUT_RUNTIME_STATE. If a register should be written less - * often, you must add it to this table with a state of either - * KVM_PUT_RESET_STATE or KVM_PUT_FULL_STATE. - */ -static const CPRegStateLevel non_runtime_cpregs[] = { - { KVM_REG_ARM_TIMER_CNT, KVM_PUT_FULL_STATE }, -}; - -int kvm_arm_cpreg_level(uint64_t regidx) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(non_runtime_cpregs); i++) { - const CPRegStateLevel *l = &non_runtime_cpregs[i]; - if (l->regidx == regidx) { - return l->level; - } - } - - return KVM_PUT_RUNTIME_STATE; -} - -#define ARM_CPU_ID_MPIDR 0, 0, 0, 5 - -int kvm_arch_init_vcpu(CPUState *cs) -{ - int ret; - uint64_t v; - uint32_t mpidr; - struct kvm_one_reg r; - ARMCPU *cpu = ARM_CPU(cs); - - if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE) { - fprintf(stderr, "KVM is not supported for this guest CPU type\n"); - return -EINVAL; - } - - qemu_add_vm_change_state_handler(kvm_arm_vm_state_change, cs); - - /* Determine init features for this CPU */ - memset(cpu->kvm_init_features, 0, sizeof(cpu->kvm_init_features)); - if (cs->start_powered_off) { - cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_POWER_OFF; - } - if (kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PSCI_0_2)) { - cpu->psci_version = 2; - cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2; - } - - /* Do KVM_ARM_VCPU_INIT ioctl */ - ret = kvm_arm_vcpu_init(cs); - if (ret) { - return ret; - } - - /* Query the kernel to make sure it supports 32 VFP - * registers: QEMU's "cortex-a15" CPU is always a - * VFP-D32 core. The simplest way to do this is just - * to attempt to read register d31. - */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP | 31; - r.addr = (uintptr_t)(&v); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret == -ENOENT) { - return -EINVAL; - } - - /* - * When KVM is in use, PSCI is emulated in-kernel and not by qemu. - * Currently KVM has its own idea about MPIDR assignment, so we - * override our defaults with what we get from KVM. - */ - ret = kvm_get_one_reg(cs, ARM_CP15_REG32(ARM_CPU_ID_MPIDR), &mpidr); - if (ret) { - return ret; - } - cpu->mp_affinity = mpidr & ARM32_AFFINITY_MASK; - - /* Check whether userspace can specify guest syndrome value */ - kvm_arm_init_serror_injection(cs); - - return kvm_arm_init_cpreg_list(cpu); -} - -int kvm_arch_destroy_vcpu(CPUState *cs) -{ - return 0; -} - -typedef struct Reg { - uint64_t id; - int offset; -} Reg; - -#define COREREG(KERNELNAME, QEMUFIELD) \ - { \ - KVM_REG_ARM | KVM_REG_SIZE_U32 | \ - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(KERNELNAME), \ - offsetof(CPUARMState, QEMUFIELD) \ - } - -#define VFPSYSREG(R) \ - { \ - KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | \ - KVM_REG_ARM_VFP_##R, \ - offsetof(CPUARMState, vfp.xregs[ARM_VFP_##R]) \ - } - -/* Like COREREG, but handle fields which are in a uint64_t in CPUARMState. */ -#define COREREG64(KERNELNAME, QEMUFIELD) \ - { \ - KVM_REG_ARM | KVM_REG_SIZE_U32 | \ - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(KERNELNAME), \ - offsetoflow32(CPUARMState, QEMUFIELD) \ - } - -static const Reg regs[] = { - /* R0_usr .. R14_usr */ - COREREG(usr_regs.uregs[0], regs[0]), - COREREG(usr_regs.uregs[1], regs[1]), - COREREG(usr_regs.uregs[2], regs[2]), - COREREG(usr_regs.uregs[3], regs[3]), - COREREG(usr_regs.uregs[4], regs[4]), - COREREG(usr_regs.uregs[5], regs[5]), - COREREG(usr_regs.uregs[6], regs[6]), - COREREG(usr_regs.uregs[7], regs[7]), - COREREG(usr_regs.uregs[8], usr_regs[0]), - COREREG(usr_regs.uregs[9], usr_regs[1]), - COREREG(usr_regs.uregs[10], usr_regs[2]), - COREREG(usr_regs.uregs[11], usr_regs[3]), - COREREG(usr_regs.uregs[12], usr_regs[4]), - COREREG(usr_regs.uregs[13], banked_r13[BANK_USRSYS]), - COREREG(usr_regs.uregs[14], banked_r14[BANK_USRSYS]), - /* R13, R14, SPSR for SVC, ABT, UND, IRQ banks */ - COREREG(svc_regs[0], banked_r13[BANK_SVC]), - COREREG(svc_regs[1], banked_r14[BANK_SVC]), - COREREG64(svc_regs[2], banked_spsr[BANK_SVC]), - COREREG(abt_regs[0], banked_r13[BANK_ABT]), - COREREG(abt_regs[1], banked_r14[BANK_ABT]), - COREREG64(abt_regs[2], banked_spsr[BANK_ABT]), - COREREG(und_regs[0], banked_r13[BANK_UND]), - COREREG(und_regs[1], banked_r14[BANK_UND]), - COREREG64(und_regs[2], banked_spsr[BANK_UND]), - COREREG(irq_regs[0], banked_r13[BANK_IRQ]), - COREREG(irq_regs[1], banked_r14[BANK_IRQ]), - COREREG64(irq_regs[2], banked_spsr[BANK_IRQ]), - /* R8_fiq .. R14_fiq and SPSR_fiq */ - COREREG(fiq_regs[0], fiq_regs[0]), - COREREG(fiq_regs[1], fiq_regs[1]), - COREREG(fiq_regs[2], fiq_regs[2]), - COREREG(fiq_regs[3], fiq_regs[3]), - COREREG(fiq_regs[4], fiq_regs[4]), - COREREG(fiq_regs[5], banked_r13[BANK_FIQ]), - COREREG(fiq_regs[6], banked_r14[BANK_FIQ]), - COREREG64(fiq_regs[7], banked_spsr[BANK_FIQ]), - /* R15 */ - COREREG(usr_regs.uregs[15], regs[15]), - /* VFP system registers */ - VFPSYSREG(FPSID), - VFPSYSREG(MVFR1), - VFPSYSREG(MVFR0), - VFPSYSREG(FPEXC), - VFPSYSREG(FPINST), - VFPSYSREG(FPINST2), -}; - -int kvm_arch_put_registers(CPUState *cs, int level) -{ - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - struct kvm_one_reg r; - int mode, bn; - int ret, i; - uint32_t cpsr, fpscr; - - /* Make sure the banked regs are properly set */ - mode = env->uncached_cpsr & CPSR_M; - bn = bank_number(mode); - if (mode == ARM_CPU_MODE_FIQ) { - memcpy(env->fiq_regs, env->regs + 8, 5 * sizeof(uint32_t)); - } else { - memcpy(env->usr_regs, env->regs + 8, 5 * sizeof(uint32_t)); - } - env->banked_r13[bn] = env->regs[13]; - env->banked_spsr[bn] = env->spsr; - env->banked_r14[r14_bank_number(mode)] = env->regs[14]; - - /* Now we can safely copy stuff down to the kernel */ - for (i = 0; i < ARRAY_SIZE(regs); i++) { - r.id = regs[i].id; - r.addr = (uintptr_t)(env) + regs[i].offset; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - } - - /* Special cases which aren't a single CPUARMState field */ - cpsr = cpsr_read(env); - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr); - r.addr = (uintptr_t)(&cpsr); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - - /* VFP registers */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; - for (i = 0; i < 32; i++) { - r.addr = (uintptr_t)aa32_vfp_dreg(env, i); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - r.id++; - } - - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | - KVM_REG_ARM_VFP_FPSCR; - fpscr = vfp_get_fpscr(env); - r.addr = (uintptr_t)&fpscr; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - - write_cpustate_to_list(cpu, true); - - if (!write_list_to_kvmstate(cpu, level)) { - return EINVAL; - } - - /* - * Setting VCPU events should be triggered after syncing the registers - * to avoid overwriting potential changes made by KVM upon calling - * KVM_SET_VCPU_EVENTS ioctl - */ - ret = kvm_put_vcpu_events(cpu); - if (ret) { - return ret; - } - - kvm_arm_sync_mpstate_to_kvm(cpu); - - return ret; -} - -int kvm_arch_get_registers(CPUState *cs) -{ - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - struct kvm_one_reg r; - int mode, bn; - int ret, i; - uint32_t cpsr, fpscr; - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - r.id = regs[i].id; - r.addr = (uintptr_t)(env) + regs[i].offset; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - } - - /* Special cases which aren't a single CPUARMState field */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr); - r.addr = (uintptr_t)(&cpsr); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - cpsr_write(env, cpsr, 0xffffffff, CPSRWriteRaw); - - /* Make sure the current mode regs are properly set */ - mode = env->uncached_cpsr & CPSR_M; - bn = bank_number(mode); - if (mode == ARM_CPU_MODE_FIQ) { - memcpy(env->regs + 8, env->fiq_regs, 5 * sizeof(uint32_t)); - } else { - memcpy(env->regs + 8, env->usr_regs, 5 * sizeof(uint32_t)); - } - env->regs[13] = env->banked_r13[bn]; - env->spsr = env->banked_spsr[bn]; - env->regs[14] = env->banked_r14[r14_bank_number(mode)]; - - /* VFP registers */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; - for (i = 0; i < 32; i++) { - r.addr = (uintptr_t)aa32_vfp_dreg(env, i); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - r.id++; - } - - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | - KVM_REG_ARM_VFP_FPSCR; - r.addr = (uintptr_t)&fpscr; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - vfp_set_fpscr(env, fpscr); - - ret = kvm_get_vcpu_events(cpu); - if (ret) { - return ret; - } - - if (!write_kvmstate_to_list(cpu)) { - return EINVAL; - } - /* Note that it's OK to have registers which aren't in CPUState, - * so we can ignore a failure return here. - */ - write_list_to_cpustate(cpu); - - kvm_arm_sync_mpstate_to_qemu(cpu); - - return 0; -} - -int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) -{ - qemu_log_mask(LOG_UNIMP, "%s: guest debug not yet implemented\n", __func__); - return -EINVAL; -} - -int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) -{ - qemu_log_mask(LOG_UNIMP, "%s: guest debug not yet implemented\n", __func__); - return -EINVAL; -} - -bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit) -{ - qemu_log_mask(LOG_UNIMP, "%s: guest debug not yet implemented\n", __func__); - return false; -} - -int kvm_arch_insert_hw_breakpoint(target_ulong addr, - target_ulong len, int type) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); - return -EINVAL; -} - -int kvm_arch_remove_hw_breakpoint(target_ulong addr, - target_ulong len, int type) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); - return -EINVAL; -} - -void kvm_arch_remove_all_hw_breakpoints(void) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -void kvm_arm_copy_hw_debug_data(struct kvm_guest_debug_arch *ptr) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -bool kvm_arm_hw_debug_active(CPUState *cs) -{ - return false; -} - -void kvm_arm_pmu_set_irq(CPUState *cs, int irq) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -void kvm_arm_pmu_init(CPUState *cs) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -#define ARM_REG_DFSR ARM_CP15_REG32(0, 5, 0, 0) -#define ARM_REG_TTBCR ARM_CP15_REG32(0, 2, 0, 2) -/* - *DFSR: - * TTBCR.EAE == 0 - * FS[4] - DFSR[10] - * FS[3:0] - DFSR[3:0] - * TTBCR.EAE == 1 - * FS, bits [5:0] - */ -#define DFSR_FSC(lpae, v) \ - ((lpae) ? ((v) & 0x3F) : (((v) >> 6) | ((v) & 0x1F))) - -#define DFSC_EXTABT(lpae) ((lpae) ? 0x10 : 0x08) - -bool kvm_arm_verify_ext_dabt_pending(CPUState *cs) -{ - uint32_t dfsr_val; - - if (!kvm_get_one_reg(cs, ARM_REG_DFSR, &dfsr_val)) { - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - uint32_t ttbcr; - int lpae = 0; - - if (!kvm_get_one_reg(cs, ARM_REG_TTBCR, &ttbcr)) { - lpae = arm_feature(env, ARM_FEATURE_LPAE) && (ttbcr & TTBCR_EAE); - } - /* The verification is based on FS filed of the DFSR reg only*/ - return (DFSR_FSC(lpae, dfsr_val) == DFSC_EXTABT(lpae)); - } - return false; -} diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(zlib) arm_ss.add(when: 'CONFIG_TCG', if_true: files('arm-semi.c')) -kvm_ss = ss.source_set() -kvm_ss.add(when: 'TARGET_AARCH64', if_true: files('kvm64.c'), if_false: files('kvm32.c')) -arm_ss.add_all(when: 'CONFIG_KVM', if_true: kvm_ss) -arm_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c'), if_false: files('kvm-stub.c')) +arm_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c', 'kvm64.c'), if_false: files('kvm-stub.c')) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'cpu64.c', -- 2.20.1 Now that 32-bit KVM host support is gone, KVM can never be enabled unless CONFIG_AARCH64 is true, and some code paths are no longer reachable and can be deleted. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200904154156.31943-3-peter.maydell@linaro.org --- target/arm/kvm-consts.h | 7 --- target/arm/kvm_arm.h | 6 --- target/arm/cpu.c | 101 +++++++++++++++++++--------------------- target/arm/kvm.c | 7 --- 4 files changed, 47 insertions(+), 74 deletions(-) diff --git a/target/arm/kvm-consts.h b/target/arm/kvm-consts.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm-consts.h +++ b/target/arm/kvm-consts.h @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_PSCI_RET_DISABLED, PSCI_RET_DISABLED); */ #define QEMU_KVM_ARM_TARGET_NONE UINT_MAX -#ifdef TARGET_AARCH64 MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_AEM_V8, KVM_ARM_TARGET_AEM_V8); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_FOUNDATION_V8, KVM_ARM_TARGET_FOUNDATION_V8); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A57, KVM_ARM_TARGET_CORTEX_A57); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_XGENE_POTENZA, KVM_ARM_TARGET_XGENE_POTENZA); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A53, KVM_ARM_TARGET_CORTEX_A53); -#else -MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A15, KVM_ARM_TARGET_CORTEX_A15); -MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A7, KVM_ARM_TARGET_CORTEX_A7); -#endif #define CP_REG_ARM64 0x6000000000000000ULL #define CP_REG_ARM_COPROC_MASK 0x000000000FFF0000 @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A7, KVM_ARM_TARGET_CORTEX_A7); /* No kernel define but it's useful to QEMU */ #define CP_REG_ARM64_SYSREG_CP (CP_REG_ARM64_SYSREG >> CP_REG_ARM_COPROC_SHIFT) -#ifdef TARGET_AARCH64 MISMATCH_CHECK(CP_REG_ARM64, KVM_REG_ARM64); MISMATCH_CHECK(CP_REG_ARM_COPROC_MASK, KVM_REG_ARM_COPROC_MASK); MISMATCH_CHECK(CP_REG_ARM_COPROC_SHIFT, KVM_REG_ARM_COPROC_SHIFT); @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(CP_REG_ARM64_SYSREG_CRM_MASK, KVM_REG_ARM64_SYSREG_CRM_MASK); MISMATCH_CHECK(CP_REG_ARM64_SYSREG_CRM_SHIFT, KVM_REG_ARM64_SYSREG_CRM_SHIFT); MISMATCH_CHECK(CP_REG_ARM64_SYSREG_OP2_MASK, KVM_REG_ARM64_SYSREG_OP2_MASK); MISMATCH_CHECK(CP_REG_ARM64_SYSREG_OP2_SHIFT, KVM_REG_ARM64_SYSREG_OP2_SHIFT); -#endif #undef MISMATCH_CHECK diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ static inline const char *gic_class_name(void) static inline const char *gicv3_class_name(void) { if (kvm_irqchip_in_kernel()) { -#ifdef TARGET_AARCH64 return "kvm-arm-gicv3"; -#else - error_report("KVM GICv3 acceleration is not supported on this " - "platform"); - exit(1); -#endif } else { if (kvm_enabled()) { error_report("Userspace GICv3 is not supported with KVM"); 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 cortex_a15_initfn(Object *obj) } #ifndef TARGET_AARCH64 -/* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); - * otherwise, a CPU with as many features enabled as our emulation supports. +/* + * -cpu max: a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-aarch64 is defined in cpu64.c; - * this only needs to handle 32 bits. + * this only needs to handle 32 bits, and need not care about KVM. */ static void arm_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - if (kvm_enabled()) { - kvm_arm_set_cpu_features_from_host(cpu); - } else { - cortex_a15_initfn(obj); + cortex_a15_initfn(obj); - /* old-style VFP short-vector support */ - cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); + /* old-style VFP short-vector support */ + cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); #ifdef CONFIG_USER_ONLY - /* We don't set these in system emulation mode for the moment, - * since we don't correctly set (all of) the ID registers to - * advertise them. - */ - set_feature(&cpu->env, ARM_FEATURE_V8); - { - uint32_t t; + /* + * We don't set these in system emulation mode for the moment, + * since we don't correctly set (all of) the ID registers to + * advertise them. + */ + set_feature(&cpu->env, ARM_FEATURE_V8); + { + uint32_t t; - t = cpu->isar.id_isar5; - t = FIELD_DP32(t, ID_ISAR5, AES, 2); - t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); - t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); - t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); - t = FIELD_DP32(t, ID_ISAR5, RDM, 1); - t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); - cpu->isar.id_isar5 = t; + t = cpu->isar.id_isar5; + t = FIELD_DP32(t, ID_ISAR5, AES, 2); + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = t; - t = cpu->isar.id_isar6; - t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); - t = FIELD_DP32(t, ID_ISAR6, DP, 1); - t = FIELD_DP32(t, ID_ISAR6, FHM, 1); - t = FIELD_DP32(t, ID_ISAR6, SB, 1); - t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); - cpu->isar.id_isar6 = t; + t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); + t = FIELD_DP32(t, ID_ISAR6, DP, 1); + t = FIELD_DP32(t, ID_ISAR6, FHM, 1); + t = FIELD_DP32(t, ID_ISAR6, SB, 1); + t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); + cpu->isar.id_isar6 = t; - t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ - t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ - cpu->isar.mvfr1 = t; + t = cpu->isar.mvfr1; + t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ + t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + cpu->isar.mvfr1 = t; - t = cpu->isar.mvfr2; - t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ - t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ - cpu->isar.mvfr2 = t; + t = cpu->isar.mvfr2; + t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ + t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ + cpu->isar.mvfr2 = t; - t = cpu->isar.id_mmfr3; - t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->isar.id_mmfr3 = t; + t = cpu->isar.id_mmfr3; + t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ + cpu->isar.id_mmfr3 = t; - t = cpu->isar.id_mmfr4; - t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ - t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ - t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ - t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ - cpu->isar.id_mmfr4 = t; - } -#endif + t = cpu->isar.id_mmfr4; + t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ + t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ + cpu->isar.id_mmfr4 = t; } +#endif } #endif @@ -XXX,XX +XXX,XX @@ static void arm_host_initfn(Object *obj) static const TypeInfo host_arm_cpu_type_info = { .name = TYPE_ARM_HOST_CPU, -#ifdef TARGET_AARCH64 .parent = TYPE_AARCH64_CPU, -#else - .parent = TYPE_ARM_CPU, -#endif .instance_init = arm_host_initfn, }; diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_process_async_events(CPUState *cs) return 0; } -/* The #ifdef protections are until 32bit headers are imported and can - * be removed once both 32 and 64 bit reach feature parity. - */ void kvm_arch_update_guest_debug(CPUState *cs, struct kvm_guest_debug *dbg) { -#ifdef KVM_GUESTDBG_USE_SW_BP if (kvm_sw_breakpoints_active(cs)) { dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP; } -#endif -#ifdef KVM_GUESTDBG_USE_HW if (kvm_arm_hw_debug_active(cs)) { dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW; kvm_arm_copy_hw_debug_data(&dbg->arch); } -#endif } void kvm_arch_init_irq_routing(KVMState *s) -- 2.20.1 Implement a model of the MPS2 with the AN386 firmware. This is essentially identical to the AN385 firmware, but it has a Cortex-M4 rather than a Cortex-M3. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903202048.15370-2-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 8 +++++--- hw/arm/mps2.c | 34 +++++++++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 8 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ -Arm MPS2 boards (``mps2-an385``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) -================================================================================ +Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) +================================================================================================ These board models all use Arm M-profile CPUs. @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: ``mps2-an385`` Cortex-M3 as documented in ARM Application Note AN385 +``mps2-an386`` + Cortex-M4 as documented in ARM Application Note AN386 ``mps2-an511`` Cortex-M3 'DesignStart' as documented in AN511 ``mps2-an505`` @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: Differences between QEMU and real hardware: -- AN385 remapping of low 16K of memory to either ZBT SSRAM1 or to +- AN385/AN386 remapping of low 16K of memory to either ZBT SSRAM1 or to block RAM is unimplemented (QEMU always maps this to ZBT SSRAM1, as if zbt_boot_ctrl is always zero) - QEMU provides a LAN9118 ethernet rather than LAN9220; the only guest diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ * as seen by the guest depend significantly on the FPGA image. * We model the following FPGA images: * "mps2-an385" -- Cortex-M3 as documented in ARM Application Note AN385 + * "mps2-an386" -- Cortex-M4 as documented in ARM Application Note AN386 * "mps2-an511" -- Cortex-M3 'DesignStart' as documented in AN511 * * Links to the TRM for the board itself and to the various Application @@ -XXX,XX +XXX,XX @@ typedef enum MPS2FPGAType { FPGA_AN385, + FPGA_AN386, FPGA_AN511, } MPS2FPGAType; @@ -XXX,XX +XXX,XX @@ typedef struct MPS2MachineState MPS2MachineState; #define TYPE_MPS2_MACHINE "mps2" #define TYPE_MPS2_AN385_MACHINE MACHINE_TYPE_NAME("mps2-an385") +#define TYPE_MPS2_AN386_MACHINE MACHINE_TYPE_NAME("mps2-an386") #define TYPE_MPS2_AN511_MACHINE MACHINE_TYPE_NAME("mps2-an511") DECLARE_OBJ_CHECKERS(MPS2MachineState, MPS2MachineClass, @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * tradeoffs. For QEMU they're all just RAM, though. We arbitrarily * call the 16MB our "system memory", as it's the largest lump. * - * Common to both boards: - * 0x21000000..0x21ffffff : PSRAM (16MB) - * AN385 only: + * AN385/AN386/AN511: + * 0x21000000 .. 0x21ffffff : PSRAM (16MB) + * AN385/AN386 only: * 0x00000000 .. 0x003fffff : ZBT SSRAM1 * 0x00400000 .. 0x007fffff : mirror of ZBT SSRAM1 * 0x20000000 .. 0x203fffff : ZBT SSRAM 2&3 @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * 0x20000000 .. 0x2001ffff : SRAM * 0x20400000 .. 0x207fffff : ZBT SSRAM 2&3 * - * The AN385 has a feature where the lowest 16K can be mapped + * The AN385/AN386 has a feature where the lowest 16K can be mapped * either to the bottom of the ZBT SSRAM1 or to the block RAM. * This is of no use for QEMU so we don't implement it (as if * zbt_boot_ctrl is always zero). @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: + case FPGA_AN386: make_ram(&mms->ssram1, "mps.ssram1", 0x0, 0x400000); make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", &mms->ssram1, 0x400000); make_ram(&mms->ssram23, "mps.ssram23", 0x20000000, 0x400000); @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) armv7m = DEVICE(&mms->armv7m); switch (mmc->fpga_type) { case FPGA_AN385: + case FPGA_AN386: qdev_prop_set_uint32(armv7m, "num-irq", 32); break; case FPGA_AN511: @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: + case FPGA_AN386: { /* The overflow IRQs for UARTs 0, 1 and 2 are ORed together. * Overflow for UARTs 4 and 5 doesn't trigger any interrupt. @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) */ lan9118_init(&nd_table[0], 0x40200000, qdev_get_gpio_in(armv7m, - mmc->fpga_type == FPGA_AN385 ? 13 : 47)); + mmc->fpga_type == FPGA_AN511 ? 47 : 13)); system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; @@ -XXX,XX +XXX,XX @@ static void mps2_an385_class_init(ObjectClass *oc, void *data) mmc->scc_id = 0x41043850; } +static void mps2_an386_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2MachineClass *mmc = MPS2_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS2 with AN386 FPGA image for Cortex-M4"; + mmc->fpga_type = FPGA_AN386; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); + mmc->scc_id = 0x41043860; +} + static void mps2_an511_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2_an385_info = { .class_init = mps2_an385_class_init, }; +static const TypeInfo mps2_an386_info = { + .name = TYPE_MPS2_AN386_MACHINE, + .parent = TYPE_MPS2_MACHINE, + .class_init = mps2_an386_class_init, +}; + static const TypeInfo mps2_an511_info = { .name = TYPE_MPS2_AN511_MACHINE, .parent = TYPE_MPS2_MACHINE, @@ -XXX,XX +XXX,XX @@ static void mps2_machine_init(void) { type_register_static(&mps2_info); type_register_static(&mps2_an385_info); + type_register_static(&mps2_an386_info); type_register_static(&mps2_an511_info); } -- 2.20.1 Implement a model of the MPS2 with the AN500 firmware. This is similar to the AN385, with the following differences: * Cortex-M7 CPU * PSRAM is at 0x6000_0000 * Ethernet is at 0xa000_0000 * No zbt_boot_ctrl remapping of the low 16K (but QEMU doesn't implement this anyway) * no "block RAM" at 0x01000000 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903202048.15370-3-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 6 ++-- hw/arm/mps2.c | 67 +++++++++++++++++++++++++++++++++------- 2 files changed, 60 insertions(+), 13 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ -Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) -================================================================================================ +Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an500``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) +================================================================================================================ These board models all use Arm M-profile CPUs. @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: Cortex-M3 as documented in ARM Application Note AN385 ``mps2-an386`` Cortex-M4 as documented in ARM Application Note AN386 +``mps2-an500`` + Cortex-M7 as documented in ARM Application Note AN500 ``mps2-an511`` Cortex-M3 'DesignStart' as documented in AN511 ``mps2-an505`` diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ * We model the following FPGA images: * "mps2-an385" -- Cortex-M3 as documented in ARM Application Note AN385 * "mps2-an386" -- Cortex-M4 as documented in ARM Application Note AN386 + * "mps2-an500" -- Cortex-M7 as documented in ARM Application Note AN500 * "mps2-an511" -- Cortex-M3 'DesignStart' as documented in AN511 * * Links to the TRM for the board itself and to the various Application @@ -XXX,XX +XXX,XX @@ typedef enum MPS2FPGAType { FPGA_AN385, FPGA_AN386, + FPGA_AN500, FPGA_AN511, } MPS2FPGAType; @@ -XXX,XX +XXX,XX @@ struct MPS2MachineClass { MachineClass parent; MPS2FPGAType fpga_type; uint32_t scc_id; + bool has_block_ram; + hwaddr ethernet_base; + hwaddr psram_base; }; typedef struct MPS2MachineClass MPS2MachineClass; @@ -XXX,XX +XXX,XX @@ typedef struct MPS2MachineState MPS2MachineState; #define TYPE_MPS2_MACHINE "mps2" #define TYPE_MPS2_AN385_MACHINE MACHINE_TYPE_NAME("mps2-an385") #define TYPE_MPS2_AN386_MACHINE MACHINE_TYPE_NAME("mps2-an386") +#define TYPE_MPS2_AN500_MACHINE MACHINE_TYPE_NAME("mps2-an500") #define TYPE_MPS2_AN511_MACHINE MACHINE_TYPE_NAME("mps2-an511") DECLARE_OBJ_CHECKERS(MPS2MachineState, MPS2MachineClass, @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * * AN385/AN386/AN511: * 0x21000000 .. 0x21ffffff : PSRAM (16MB) - * AN385/AN386 only: + * AN385/AN386/AN500: * 0x00000000 .. 0x003fffff : ZBT SSRAM1 * 0x00400000 .. 0x007fffff : mirror of ZBT SSRAM1 * 0x20000000 .. 0x203fffff : ZBT SSRAM 2&3 * 0x20400000 .. 0x207fffff : mirror of ZBT SSRAM 2&3 + * AN385/AN386 only: * 0x01000000 .. 0x01003fff : block RAM (16K) * 0x01004000 .. 0x01007fff : mirror of above * 0x01008000 .. 0x0100bfff : mirror of above @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * 0x00400000 .. 0x007fffff : ZBT SSRAM1 * 0x20000000 .. 0x2001ffff : SRAM * 0x20400000 .. 0x207fffff : ZBT SSRAM 2&3 + * AN500 only: + * 0x60000000 .. 0x60ffffff : PSRAM (16MB) * * The AN385/AN386 has a feature where the lowest 16K can be mapped * either to the bottom of the ZBT SSRAM1 or to the block RAM. * This is of no use for QEMU so we don't implement it (as if * zbt_boot_ctrl is always zero). */ - memory_region_add_subregion(system_memory, 0x21000000, machine->ram); + memory_region_add_subregion(system_memory, mmc->psram_base, machine->ram); - switch (mmc->fpga_type) { - case FPGA_AN385: - case FPGA_AN386: - make_ram(&mms->ssram1, "mps.ssram1", 0x0, 0x400000); - make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", &mms->ssram1, 0x400000); - make_ram(&mms->ssram23, "mps.ssram23", 0x20000000, 0x400000); - make_ram_alias(&mms->ssram23_m, "mps.ssram23_m", - &mms->ssram23, 0x20400000); + if (mmc->has_block_ram) { make_ram(&mms->blockram, "mps.blockram", 0x01000000, 0x4000); make_ram_alias(&mms->blockram_m1, "mps.blockram_m1", &mms->blockram, 0x01004000); @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) &mms->blockram, 0x01008000); make_ram_alias(&mms->blockram_m3, "mps.blockram_m3", &mms->blockram, 0x0100c000); + } + + switch (mmc->fpga_type) { + case FPGA_AN385: + case FPGA_AN386: + case FPGA_AN500: + make_ram(&mms->ssram1, "mps.ssram1", 0x0, 0x400000); + make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", &mms->ssram1, 0x400000); + make_ram(&mms->ssram23, "mps.ssram23", 0x20000000, 0x400000); + make_ram_alias(&mms->ssram23_m, "mps.ssram23_m", + &mms->ssram23, 0x20400000); break; case FPGA_AN511: make_ram(&mms->blockram, "mps.blockram", 0x0, 0x40000); @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: case FPGA_AN386: + case FPGA_AN500: qdev_prop_set_uint32(armv7m, "num-irq", 32); break; case FPGA_AN511: @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: case FPGA_AN386: + case FPGA_AN500: { /* The overflow IRQs for UARTs 0, 1 and 2 are ORed together. * Overflow for UARTs 4 and 5 doesn't trigger any interrupt. @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) /* In hardware this is a LAN9220; the LAN9118 is software compatible * except that it doesn't support the checksum-offload feature. */ - lan9118_init(&nd_table[0], 0x40200000, + lan9118_init(&nd_table[0], mmc->ethernet_base, qdev_get_gpio_in(armv7m, mmc->fpga_type == FPGA_AN511 ? 47 : 13)); @@ -XXX,XX +XXX,XX @@ static void mps2_an385_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN385; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m3"); mmc->scc_id = 0x41043850; + mmc->psram_base = 0x21000000; + mmc->ethernet_base = 0x40200000; + mmc->has_block_ram = true; } static void mps2_an386_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2_an386_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN386; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); mmc->scc_id = 0x41043860; + mmc->psram_base = 0x21000000; + mmc->ethernet_base = 0x40200000; + mmc->has_block_ram = true; +} + +static void mps2_an500_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2MachineClass *mmc = MPS2_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS2 with AN500 FPGA image for Cortex-M7"; + mmc->fpga_type = FPGA_AN500; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m7"); + mmc->scc_id = 0x41045000; + mmc->psram_base = 0x60000000; + mmc->ethernet_base = 0xa0000000; + mmc->has_block_ram = false; } static void mps2_an511_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2_an511_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN511; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m3"); mmc->scc_id = 0x41045110; + mmc->psram_base = 0x21000000; + mmc->ethernet_base = 0x40200000; + mmc->has_block_ram = false; } static const TypeInfo mps2_info = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2_an386_info = { .class_init = mps2_an386_class_init, }; +static const TypeInfo mps2_an500_info = { + .name = TYPE_MPS2_AN500_MACHINE, + .parent = TYPE_MPS2_MACHINE, + .class_init = mps2_an500_class_init, +}; + static const TypeInfo mps2_an511_info = { .name = TYPE_MPS2_AN511_MACHINE, .parent = TYPE_MPS2_MACHINE, @@ -XXX,XX +XXX,XX @@ static void mps2_machine_init(void) type_register_static(&mps2_info); type_register_static(&mps2_an385_info); type_register_static(&mps2_an386_info); + type_register_static(&mps2_an500_info); type_register_static(&mps2_an511_info); } -- 2.20.1 Make the list of MPS2 boards consistent in the phrasing of each entry, use the correct casing of "Arm", and move the mps2-an511 entry so the list is in numeric order. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903202048.15370-4-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ as seen by the guest depend significantly on the FPGA image. QEMU models the following FPGA images: ``mps2-an385`` - Cortex-M3 as documented in ARM Application Note AN385 + Cortex-M3 as documented in Arm Application Note AN385 ``mps2-an386`` - Cortex-M4 as documented in ARM Application Note AN386 + Cortex-M4 as documented in Arm Application Note AN386 ``mps2-an500`` - Cortex-M7 as documented in ARM Application Note AN500 -``mps2-an511`` - Cortex-M3 'DesignStart' as documented in AN511 + Cortex-M7 as documented in Arm Application Note AN500 ``mps2-an505`` - Cortex-M33 as documented in ARM Application Note AN505 + Cortex-M33 as documented in Arm Application Note AN505 +``mps2-an511`` + Cortex-M3 'DesignStart' as documented in Arm Application Note AN511 ``mps2-an521`` - Dual Cortex-M33 as documented in Application Note AN521 + Dual Cortex-M33 as documented in Arm Application Note AN521 Differences between QEMU and real hardware: -- 2.20.1 Deprecate our Unicore32 target support: * the Linux kernel dropped support for unicore32 in commit 05119217a9bd199c for its 5.9 release (with rationale in the cover letter: https://lkml.org/lkml/2020/8/3/232 ) * there is apparently no upstream toolchain that can create unicore32 binaries * the maintainer doesn't seem to have made any contributions to QEMU since the port first landed in 2012 * nobody else seems to have made changes to the unicore code except for generic cleanups either Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: 20200825172719.19422-1-peter.maydell@linaro.org --- docs/system/deprecated.rst | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -XXX,XX +XXX,XX @@ The above, converted to the current supported format:: linux-user mode CPUs -------------------- +``unicore32`` CPUs (since 5.2.0) +'''''''''''''''''''''''''''''''' + +The ``unicore32`` guest CPU support is deprecated and will be removed in +a future version of QEMU. Support for this CPU was removed from the +upstream Linux kernel, and there is no available upstream toolchain +to build binaries for it. + ``tilegx`` CPUs (since 5.1.0) ''''''''''''''''''''''''''''' -- 2.20.1 Deprecate our lm32 target support. Michael Walle (former lm32 maintainer) suggested that we do this in 2019: https://www.mail-archive.com/qemu-devel@nongnu.org/msg605024.html because the only public user of the architecture is the many-years-dead milkymist project. (The Linux port to lm32 was never merged upstream.) In commit 4b4d96c776f552e (March 2020) we marked it as 'orphan' in the MAINTAINERS file, but didn't officially deprecate it. Mark it deprecated now, with the intention of removing it from QEMU in mid-2021 before the 6.1 release. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Acked-by: Michael Walle <michael@walle.cc> Message-id: 20200827113259.25064-1-peter.maydell@linaro.org --- docs/system/deprecated.rst | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -XXX,XX +XXX,XX @@ The above, converted to the current supported format:: linux-user mode CPUs -------------------- +``lm32`` CPUs (since 5.2.0) +''''''''''''''''''''''''''' + +The ``lm32`` guest CPU support is deprecated and will be removed in +a future version of QEMU. The only public user of this architecture +was the milkymist project, which has been dead for years; there was +never an upstream Linux port. + ``unicore32`` CPUs (since 5.2.0) '''''''''''''''''''''''''''''''' -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> This check was backwards when introduced in commit 033614c47de78409ad3fb39bb7bd1483b71c6789: target/arm: Filter cycle counter based on PMCCFILTR_EL0 Cc: qemu-stable@nongnu.org Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) } } else { prohibited = arm_feature(env, ARM_FEATURE_EL3) && - (env->cp15.mdcr_el3 & MDCR_SPME); + !(env->cp15.mdcr_el3 & MDCR_SPME); } if (prohibited && counter == 31) { -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Correct the GEMs tx/rx clocks to use the 125Mhz fixed-clock. This matches the setup with the fixed-link 100Mbit PHY. It also avoids the following warnings from the Linux kernel driver: eth0: unable to generate target frequency: 125000000 Hz Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200909174647.662864-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal-virt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_gem_nodes(VersalVirt *s) s->phandle.ethernet_phy[i]); qemu_fdt_setprop_cells(s->fdt, name, "clocks", s->phandle.clk_25Mhz, s->phandle.clk_25Mhz, - s->phandle.clk_25Mhz, s->phandle.clk_25Mhz); + s->phandle.clk_125Mhz, s->phandle.clk_125Mhz); qemu_fdt_setprop(s->fdt, name, "clock-names", clocknames, sizeof(clocknames)); qemu_fdt_setprop_cells(s->fdt, name, "interrupts", -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Implement a device model for the System Global Control Registers in the NPCM730 and NPCM750 BMC SoCs. This is primarily used to enable SMP boot (the boot ROM spins reading the SCRPAD register) and DDR memory initialization; other registers are best effort for now. The reset values of the MDLR and PWRON registers are determined by the SoC variant (730 vs 750) and board straps respectively. Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-2-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_gcr.h | 43 ++++++ hw/misc/npcm7xx_gcr.c | 269 ++++++++++++++++++++++++++++++++++ MAINTAINERS | 8 + hw/arm/Kconfig | 3 + hw/misc/meson.build | 3 + hw/misc/trace-events | 4 + 6 files changed, 330 insertions(+) create mode 100644 include/hw/misc/npcm7xx_gcr.h create mode 100644 hw/misc/npcm7xx_gcr.c diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx System Global Control Registers. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_GCR_H +#define NPCM7XX_GCR_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_GCR_NR_REGS (0x148 / sizeof(uint32_t)) + +typedef struct NPCM7xxGCRState { + SysBusDevice parent; + + MemoryRegion iomem; + + uint32_t regs[NPCM7XX_GCR_NR_REGS]; + + uint32_t reset_pwron; + uint32_t reset_mdlr; + uint32_t reset_intcr3; +} NPCM7xxGCRState; + +#define TYPE_NPCM7XX_GCR "npcm7xx-gcr" +#define NPCM7XX_GCR(obj) OBJECT_CHECK(NPCM7xxGCRState, (obj), TYPE_NPCM7XX_GCR) + +#endif /* NPCM7XX_GCR_H */ diff --git a/hw/misc/npcm7xx_gcr.c b/hw/misc/npcm7xx_gcr.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/npcm7xx_gcr.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx System Global Control Registers. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "hw/misc/npcm7xx_gcr.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qemu/cutils.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +#include "trace.h" + +#define NPCM7XX_GCR_MIN_DRAM_SIZE (128 * MiB) +#define NPCM7XX_GCR_MAX_DRAM_SIZE (2 * GiB) + +enum NPCM7xxGCRRegisters { + NPCM7XX_GCR_PDID, + NPCM7XX_GCR_PWRON, + NPCM7XX_GCR_MFSEL1 = 0x0c / sizeof(uint32_t), + NPCM7XX_GCR_MFSEL2, + NPCM7XX_GCR_MISCPE, + NPCM7XX_GCR_SPSWC = 0x038 / sizeof(uint32_t), + NPCM7XX_GCR_INTCR, + NPCM7XX_GCR_INTSR, + NPCM7XX_GCR_HIFCR = 0x050 / sizeof(uint32_t), + NPCM7XX_GCR_INTCR2 = 0x060 / sizeof(uint32_t), + NPCM7XX_GCR_MFSEL3, + NPCM7XX_GCR_SRCNT, + NPCM7XX_GCR_RESSR, + NPCM7XX_GCR_RLOCKR1, + NPCM7XX_GCR_FLOCKR1, + NPCM7XX_GCR_DSCNT, + NPCM7XX_GCR_MDLR, + NPCM7XX_GCR_SCRPAD3, + NPCM7XX_GCR_SCRPAD2, + NPCM7XX_GCR_DAVCLVLR = 0x098 / sizeof(uint32_t), + NPCM7XX_GCR_INTCR3, + NPCM7XX_GCR_VSINTR = 0x0ac / sizeof(uint32_t), + NPCM7XX_GCR_MFSEL4, + NPCM7XX_GCR_CPBPNTR = 0x0c4 / sizeof(uint32_t), + NPCM7XX_GCR_CPCTL = 0x0d0 / sizeof(uint32_t), + NPCM7XX_GCR_CP2BST, + NPCM7XX_GCR_B2CPNT, + NPCM7XX_GCR_CPPCTL, + NPCM7XX_GCR_I2CSEGSEL, + NPCM7XX_GCR_I2CSEGCTL, + NPCM7XX_GCR_VSRCR, + NPCM7XX_GCR_MLOCKR, + NPCM7XX_GCR_SCRPAD = 0x013c / sizeof(uint32_t), + NPCM7XX_GCR_USB1PHYCTL, + NPCM7XX_GCR_USB2PHYCTL, + NPCM7XX_GCR_REGS_END, +}; + +static const uint32_t cold_reset_values[NPCM7XX_GCR_NR_REGS] = { + [NPCM7XX_GCR_PDID] = 0x04a92750, /* Poleg A1 */ + [NPCM7XX_GCR_MISCPE] = 0x0000ffff, + [NPCM7XX_GCR_SPSWC] = 0x00000003, + [NPCM7XX_GCR_INTCR] = 0x0000035e, + [NPCM7XX_GCR_HIFCR] = 0x0000004e, + [NPCM7XX_GCR_INTCR2] = (1U << 19), /* DDR initialized */ + [NPCM7XX_GCR_RESSR] = 0x80000000, + [NPCM7XX_GCR_DSCNT] = 0x000000c0, + [NPCM7XX_GCR_DAVCLVLR] = 0x5a00f3cf, + [NPCM7XX_GCR_SCRPAD] = 0x00000008, + [NPCM7XX_GCR_USB1PHYCTL] = 0x034730e4, + [NPCM7XX_GCR_USB2PHYCTL] = 0x034730e4, +}; + +static uint64_t npcm7xx_gcr_read(void *opaque, hwaddr offset, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxGCRState *s = opaque; + + if (reg >= NPCM7XX_GCR_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return 0; + } + + trace_npcm7xx_gcr_read(offset, s->regs[reg]); + + return s->regs[reg]; +} + +static void npcm7xx_gcr_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxGCRState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_gcr_write(offset, value); + + if (reg >= NPCM7XX_GCR_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return; + } + + switch (reg) { + case NPCM7XX_GCR_PDID: + case NPCM7XX_GCR_PWRON: + case NPCM7XX_GCR_INTSR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + return; + + case NPCM7XX_GCR_RESSR: + case NPCM7XX_GCR_CP2BST: + /* Write 1 to clear */ + value = s->regs[reg] & ~value; + break; + + case NPCM7XX_GCR_RLOCKR1: + case NPCM7XX_GCR_MDLR: + /* Write 1 to set */ + value |= s->regs[reg]; + break; + }; + + s->regs[reg] = value; +} + +static const struct MemoryRegionOps npcm7xx_gcr_ops = { + .read = npcm7xx_gcr_read, + .write = npcm7xx_gcr_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_gcr_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxGCRState *s = NPCM7XX_GCR(obj); + + 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; + } +} + +static void npcm7xx_gcr_realize(DeviceState *dev, Error **errp) +{ + ERRP_GUARD(); + NPCM7xxGCRState *s = NPCM7XX_GCR(dev); + uint64_t dram_size; + Object *obj; + + obj = object_property_get_link(OBJECT(dev), "dram-mr", errp); + if (!obj) { + error_prepend(errp, "%s: required dram-mr link not found: ", __func__); + return; + } + dram_size = memory_region_size(MEMORY_REGION(obj)); + if (!is_power_of_2(dram_size) || + dram_size < NPCM7XX_GCR_MIN_DRAM_SIZE || + dram_size > NPCM7XX_GCR_MAX_DRAM_SIZE) { + g_autofree char *sz = size_to_str(dram_size); + g_autofree char *min_sz = size_to_str(NPCM7XX_GCR_MIN_DRAM_SIZE); + g_autofree char *max_sz = size_to_str(NPCM7XX_GCR_MAX_DRAM_SIZE); + error_setg(errp, "%s: unsupported DRAM size %s", __func__, sz); + error_append_hint(errp, + "DRAM size must be a power of two between %s and %s," + " inclusive.\n", min_sz, max_sz); + return; + } + + /* Power-on reset value */ + s->reset_intcr3 = 0x00001002; + + /* + * The GMMAP (Graphics Memory Map) field is used by u-boot to detect the + * DRAM size, and is normally initialized by the boot block as part of DRAM + * training. However, since we don't have a complete emulation of the + * memory controller and try to make it look like it has already been + * initialized, the boot block will skip this initialization, and we need + * to make sure this field is set correctly up front. + * + * WARNING: some versions of u-boot only looks at bits 8 and 9, so 2 GiB of + * DRAM will be interpreted as 128 MiB. + * + * https://github.com/Nuvoton-Israel/u-boot/blob/2aef993bd2aafeb5408dbaad0f3ce099ee40c4aa/board/nuvoton/poleg/poleg.c#L244 + */ + s->reset_intcr3 |= ctz64(dram_size / NPCM7XX_GCR_MIN_DRAM_SIZE) << 8; +} + +static void npcm7xx_gcr_init(Object *obj) +{ + NPCM7xxGCRState *s = NPCM7XX_GCR(obj); + + memory_region_init_io(&s->iomem, obj, &npcm7xx_gcr_ops, s, + TYPE_NPCM7XX_GCR, 4 * KiB); + sysbus_init_mmio(&s->parent, &s->iomem); +} + +static const VMStateDescription vmstate_npcm7xx_gcr = { + .name = "npcm7xx-gcr", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxGCRState, NPCM7XX_GCR_NR_REGS), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_gcr_properties[] = { + DEFINE_PROP_UINT32("disabled-modules", NPCM7xxGCRState, reset_mdlr, 0), + DEFINE_PROP_UINT32("power-on-straps", NPCM7xxGCRState, reset_pwron, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_gcr_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_GCR_REGS_END > NPCM7XX_GCR_NR_REGS); + + dc->desc = "NPCM7xx System Global Control Registers"; + dc->realize = npcm7xx_gcr_realize; + dc->vmsd = &vmstate_npcm7xx_gcr; + rc->phases.enter = npcm7xx_gcr_enter_reset; + + device_class_set_props(dc, npcm7xx_gcr_properties); +} + +static const TypeInfo npcm7xx_gcr_info = { + .name = TYPE_NPCM7XX_GCR, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxGCRState), + .instance_init = npcm7xx_gcr_init, + .class_init = npcm7xx_gcr_class_init, +}; + +static void npcm7xx_gcr_register_type(void) +{ + type_register_static(&npcm7xx_gcr_info); +} +type_init(npcm7xx_gcr_register_type); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Odd Fixes F: hw/arm/musicpal.c F: docs/system/arm/musicpal.rst +Nuvoton NPCM7xx +M: Havard Skinnemoen <hskinnemoen@google.com> +M: Tyrone Ting <kfting@nuvoton.com> +L: qemu-arm@nongnu.org +S: Supported +F: hw/*/npcm7xx* +F: include/hw/*/npcm7xx* + nSeries M: Andrzej Zaborowski <balrogg@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> 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 XLNX_VERSAL select VIRTIO_MMIO select UNIMP +config NPCM7XX + bool + config FSL_IMX25 bool select IMX diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_IMX', if_true: files( )) softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-hpdmc.c', 'milkymist-pfpu.c')) softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( + 'npcm7xx_gcr.c', +)) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files( 'omap_clk.c', 'omap_gpmc.c', diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ mos6522_set_sr_int(void) "set sr_int" mos6522_write(uint64_t addr, uint64_t val) "reg=0x%"PRIx64 " val=0x%"PRIx64 mos6522_read(uint64_t addr, unsigned val) "reg=0x%"PRIx64 " val=0x%x" +# npcm7xx_gcr.c +npcm7xx_gcr_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_gcr_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 + # stm32f4xx_syscfg.c stm32f4xx_syscfg_set_irq(int gpio, int line, int level) "Interupt: GPIO: %d, Line: %d; Level: %d" stm32f4xx_pulse_exti(int irq) "Pulse EXTI: %d" -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Enough functionality to boot the Linux kernel has been implemented. This includes: - Correct power-on reset values so the various clock rates can be accurately calculated. - Clock enables stick around when written. In addition, a best effort attempt to implement SECCNT and CNTR25M was made even though I don't think the kernel needs them. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-3-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_clk.h | 48 ++++++ hw/misc/npcm7xx_clk.c | 266 ++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + hw/misc/trace-events | 4 + 4 files changed, 319 insertions(+) create mode 100644 include/hw/misc/npcm7xx_clk.h create mode 100644 hw/misc/npcm7xx_clk.c diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Clock Control Registers. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_CLK_H +#define NPCM7XX_CLK_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/* + * The reference clock frequency for the timer modules, and the SECCNT and + * CNTR25M registers in this module, is always 25 MHz. + */ +#define NPCM7XX_TIMER_REF_HZ (25000000) + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_CLK_NR_REGS (0x70 / sizeof(uint32_t)) + +typedef struct NPCM7xxCLKState { + SysBusDevice parent; + + MemoryRegion iomem; + + uint32_t regs[NPCM7XX_CLK_NR_REGS]; + + /* Time reference for SECCNT and CNTR25M, initialized by power on reset */ + int64_t ref_ns; +} NPCM7xxCLKState; + +#define TYPE_NPCM7XX_CLK "npcm7xx-clk" +#define NPCM7XX_CLK(obj) OBJECT_CHECK(NPCM7xxCLKState, (obj), TYPE_NPCM7XX_CLK) + +#endif /* NPCM7XX_CLK_H */ diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/npcm7xx_clk.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Clock Control Registers. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "hw/misc/npcm7xx_clk.h" +#include "migration/vmstate.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qemu/units.h" +#include "trace.h" + +#define PLLCON_LOKI BIT(31) +#define PLLCON_LOKS BIT(30) +#define PLLCON_PWDEN BIT(12) + +enum NPCM7xxCLKRegisters { + NPCM7XX_CLK_CLKEN1, + NPCM7XX_CLK_CLKSEL, + NPCM7XX_CLK_CLKDIV1, + NPCM7XX_CLK_PLLCON0, + NPCM7XX_CLK_PLLCON1, + NPCM7XX_CLK_SWRSTR, + NPCM7XX_CLK_IPSRST1 = 0x20 / sizeof(uint32_t), + NPCM7XX_CLK_IPSRST2, + NPCM7XX_CLK_CLKEN2, + NPCM7XX_CLK_CLKDIV2, + NPCM7XX_CLK_CLKEN3, + NPCM7XX_CLK_IPSRST3, + NPCM7XX_CLK_WD0RCR, + NPCM7XX_CLK_WD1RCR, + NPCM7XX_CLK_WD2RCR, + NPCM7XX_CLK_SWRSTC1, + NPCM7XX_CLK_SWRSTC2, + NPCM7XX_CLK_SWRSTC3, + NPCM7XX_CLK_SWRSTC4, + NPCM7XX_CLK_PLLCON2, + NPCM7XX_CLK_CLKDIV3, + NPCM7XX_CLK_CORSTC, + NPCM7XX_CLK_PLLCONG, + NPCM7XX_CLK_AHBCKFI, + NPCM7XX_CLK_SECCNT, + NPCM7XX_CLK_CNTR25M, + NPCM7XX_CLK_REGS_END, +}; + +/* + * These reset values were taken from version 0.91 of the NPCM750R data sheet. + * + * All are loaded on power-up reset. CLKENx and SWRSTR should also be loaded on + * core domain reset, but this reset type is not yet supported by QEMU. + */ +static const uint32_t cold_reset_values[NPCM7XX_CLK_NR_REGS] = { + [NPCM7XX_CLK_CLKEN1] = 0xffffffff, + [NPCM7XX_CLK_CLKSEL] = 0x004aaaaa, + [NPCM7XX_CLK_CLKDIV1] = 0x5413f855, + [NPCM7XX_CLK_PLLCON0] = 0x00222101 | PLLCON_LOKI, + [NPCM7XX_CLK_PLLCON1] = 0x00202101 | PLLCON_LOKI, + [NPCM7XX_CLK_IPSRST1] = 0x00001000, + [NPCM7XX_CLK_IPSRST2] = 0x80000000, + [NPCM7XX_CLK_CLKEN2] = 0xffffffff, + [NPCM7XX_CLK_CLKDIV2] = 0xaa4f8f9f, + [NPCM7XX_CLK_CLKEN3] = 0xffffffff, + [NPCM7XX_CLK_IPSRST3] = 0x03000000, + [NPCM7XX_CLK_WD0RCR] = 0xffffffff, + [NPCM7XX_CLK_WD1RCR] = 0xffffffff, + [NPCM7XX_CLK_WD2RCR] = 0xffffffff, + [NPCM7XX_CLK_SWRSTC1] = 0x00000003, + [NPCM7XX_CLK_PLLCON2] = 0x00c02105 | PLLCON_LOKI, + [NPCM7XX_CLK_CORSTC] = 0x04000003, + [NPCM7XX_CLK_PLLCONG] = 0x01228606 | PLLCON_LOKI, + [NPCM7XX_CLK_AHBCKFI] = 0x000000c8, +}; + +static uint64_t npcm7xx_clk_read(void *opaque, hwaddr offset, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxCLKState *s = opaque; + int64_t now_ns; + uint32_t value = 0; + + if (reg >= NPCM7XX_CLK_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return 0; + } + + switch (reg) { + case NPCM7XX_CLK_SWRSTR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is write-only\n", + __func__, offset); + break; + + case NPCM7XX_CLK_SECCNT: + now_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + value = (now_ns - s->ref_ns) / NANOSECONDS_PER_SECOND; + break; + + case NPCM7XX_CLK_CNTR25M: + now_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + /* + * This register counts 25 MHz cycles, updating every 640 ns. It rolls + * over to zero every second. + * + * The 4 LSBs are always zero: (1e9 / 640) << 4 = 25000000. + */ + value = (((now_ns - s->ref_ns) / 640) << 4) % NPCM7XX_TIMER_REF_HZ; + break; + + default: + value = s->regs[reg]; + break; + }; + + trace_npcm7xx_clk_read(offset, value); + + return value; +} + +static void npcm7xx_clk_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxCLKState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_clk_write(offset, value); + + if (reg >= NPCM7XX_CLK_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return; + } + + switch (reg) { + case NPCM7XX_CLK_SWRSTR: + qemu_log_mask(LOG_UNIMP, "%s: SW reset not implemented: 0x%02x\n", + __func__, value); + value = 0; + break; + + case NPCM7XX_CLK_PLLCON0: + case NPCM7XX_CLK_PLLCON1: + case NPCM7XX_CLK_PLLCON2: + case NPCM7XX_CLK_PLLCONG: + if (value & PLLCON_PWDEN) { + /* Power down -- clear lock and indicate loss of lock */ + value &= ~PLLCON_LOKI; + value |= PLLCON_LOKS; + } else { + /* Normal mode -- assume always locked */ + value |= PLLCON_LOKI; + /* Keep LOKS unchanged unless cleared by writing 1 */ + if (value & PLLCON_LOKS) { + value &= ~PLLCON_LOKS; + } else { + value |= (value & PLLCON_LOKS); + } + } + break; + + case NPCM7XX_CLK_CNTR25M: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + return; + } + + s->regs[reg] = value; +} + +static const struct MemoryRegionOps npcm7xx_clk_ops = { + .read = npcm7xx_clk_read, + .write = npcm7xx_clk_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_clk_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxCLKState *s = NPCM7XX_CLK(obj); + + 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); + return; + } + + /* + * 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(Object *obj) +{ + NPCM7xxCLKState *s = NPCM7XX_CLK(obj); + + memory_region_init_io(&s->iomem, obj, &npcm7xx_clk_ops, s, + TYPE_NPCM7XX_CLK, 4 * KiB); + sysbus_init_mmio(&s->parent, &s->iomem); +} + +static const VMStateDescription vmstate_npcm7xx_clk = { + .name = "npcm7xx-clk", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxCLKState, NPCM7XX_CLK_NR_REGS), + VMSTATE_INT64(ref_ns, NPCM7xxCLKState), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_clk_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_CLK_REGS_END > NPCM7XX_CLK_NR_REGS); + + dc->desc = "NPCM7xx Clock Control Registers"; + dc->vmsd = &vmstate_npcm7xx_clk; + rc->phases.enter = npcm7xx_clk_enter_reset; +} + +static const TypeInfo npcm7xx_clk_info = { + .name = TYPE_NPCM7XX_CLK, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxCLKState), + .instance_init = npcm7xx_clk_init, + .class_init = npcm7xx_clk_class_init, +}; + +static void npcm7xx_clk_register_type(void) +{ + type_register_static(&npcm7xx_clk_info); +} +type_init(npcm7xx_clk_register_type); diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_IMX', if_true: files( softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-hpdmc.c', 'milkymist-pfpu.c')) softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( + 'npcm7xx_clk.c', 'npcm7xx_gcr.c', )) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files( diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ mos6522_set_sr_int(void) "set sr_int" mos6522_write(uint64_t addr, uint64_t val) "reg=0x%"PRIx64 " val=0x%"PRIx64 mos6522_read(uint64_t addr, unsigned val) "reg=0x%"PRIx64 " val=0x%x" +# npcm7xx_clk.c +npcm7xx_clk_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_clk_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 + # npcm7xx_gcr.c npcm7xx_gcr_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 npcm7xx_gcr_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> The NPCM730 and NPCM750 SoCs have three timer modules each holding five timers and some shared registers (e.g. interrupt status). Each timer runs at 25 MHz divided by a prescaler, and counts down from a configurable initial value to zero. When zero is reached, the interrupt flag for the timer is set, and the timer is disabled (one-shot mode) or reloaded from its initial value (periodic mode). This implementation is sufficient to boot a Linux kernel configured for NPCM750. Note that the kernel does not seem to actually turn on the interrupts. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-4-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/timer/npcm7xx_timer.h | 78 +++++ hw/timer/npcm7xx_timer.c | 543 +++++++++++++++++++++++++++++++ hw/timer/meson.build | 1 + hw/timer/trace-events | 5 + 4 files changed, 627 insertions(+) create mode 100644 include/hw/timer/npcm7xx_timer.h create mode 100644 hw/timer/npcm7xx_timer.c diff --git a/include/hw/timer/npcm7xx_timer.h b/include/hw/timer/npcm7xx_timer.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/npcm7xx_timer.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Timer Controller + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_TIMER_H +#define NPCM7XX_TIMER_H + +#include "exec/memory.h" +#include "hw/sysbus.h" +#include "qemu/timer.h" + +/* Each Timer Module (TIM) instance holds five 25 MHz timers. */ +#define NPCM7XX_TIMERS_PER_CTRL (5) + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_TIMER_NR_REGS (0x54 / sizeof(uint32_t)) + +typedef struct NPCM7xxTimerCtrlState NPCM7xxTimerCtrlState; + +/** + * struct NPCM7xxTimer - Individual timer state. + * @irq: GIC interrupt line to fire on expiration (if enabled). + * @qtimer: QEMU timer that notifies us on expiration. + * @expires_ns: Absolute virtual expiration time. + * @remaining_ns: Remaining time until expiration if timer is paused. + * @tcsr: The Timer Control and Status Register. + * @ticr: The Timer Initial Count Register. + */ +typedef struct NPCM7xxTimer { + NPCM7xxTimerCtrlState *ctrl; + + qemu_irq irq; + QEMUTimer qtimer; + int64_t expires_ns; + int64_t remaining_ns; + + uint32_t tcsr; + uint32_t ticr; +} NPCM7xxTimer; + +/** + * struct NPCM7xxTimerCtrlState - Timer Module device state. + * @parent: System bus device. + * @iomem: Memory region through which registers are accessed. + * @tisr: The Timer Interrupt Status Register. + * @wtcr: The Watchdog Timer Control Register. + * @timer: The five individual timers managed by this module. + */ +struct NPCM7xxTimerCtrlState { + SysBusDevice parent; + + MemoryRegion iomem; + + uint32_t tisr; + uint32_t wtcr; + + NPCM7xxTimer timer[NPCM7XX_TIMERS_PER_CTRL]; +}; + +#define TYPE_NPCM7XX_TIMER "npcm7xx-timer" +#define NPCM7XX_TIMER(obj) \ + OBJECT_CHECK(NPCM7xxTimerCtrlState, (obj), TYPE_NPCM7XX_TIMER) + +#endif /* NPCM7XX_TIMER_H */ diff --git a/hw/timer/npcm7xx_timer.c b/hw/timer/npcm7xx_timer.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/npcm7xx_timer.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Timer Controller + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "hw/irq.h" +#include "hw/misc/npcm7xx_clk.h" +#include "hw/timer/npcm7xx_timer.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qemu/units.h" +#include "trace.h" + +/* 32-bit register indices. */ +enum NPCM7xxTimerRegisters { + NPCM7XX_TIMER_TCSR0, + NPCM7XX_TIMER_TCSR1, + NPCM7XX_TIMER_TICR0, + NPCM7XX_TIMER_TICR1, + NPCM7XX_TIMER_TDR0, + NPCM7XX_TIMER_TDR1, + NPCM7XX_TIMER_TISR, + NPCM7XX_TIMER_WTCR, + NPCM7XX_TIMER_TCSR2, + NPCM7XX_TIMER_TCSR3, + NPCM7XX_TIMER_TICR2, + NPCM7XX_TIMER_TICR3, + NPCM7XX_TIMER_TDR2, + NPCM7XX_TIMER_TDR3, + NPCM7XX_TIMER_TCSR4 = 0x0040 / sizeof(uint32_t), + NPCM7XX_TIMER_TICR4 = 0x0048 / sizeof(uint32_t), + NPCM7XX_TIMER_TDR4 = 0x0050 / sizeof(uint32_t), + NPCM7XX_TIMER_REGS_END, +}; + +/* Register field definitions. */ +#define NPCM7XX_TCSR_CEN BIT(30) +#define NPCM7XX_TCSR_IE BIT(29) +#define NPCM7XX_TCSR_PERIODIC BIT(27) +#define NPCM7XX_TCSR_CRST BIT(26) +#define NPCM7XX_TCSR_CACT BIT(25) +#define NPCM7XX_TCSR_RSVD 0x01ffff00 +#define NPCM7XX_TCSR_PRESCALE_START 0 +#define NPCM7XX_TCSR_PRESCALE_LEN 8 + +/* + * Returns the index of timer in the tc->timer array. This can be used to + * locate the registers that belong to this timer. + */ +static int npcm7xx_timer_index(NPCM7xxTimerCtrlState *tc, NPCM7xxTimer *timer) +{ + int index = timer - tc->timer; + + g_assert(index >= 0 && index < NPCM7XX_TIMERS_PER_CTRL); + + return index; +} + +/* Return the value by which to divide the reference clock rate. */ +static uint32_t npcm7xx_tcsr_prescaler(uint32_t tcsr) +{ + return extract32(tcsr, NPCM7XX_TCSR_PRESCALE_START, + NPCM7XX_TCSR_PRESCALE_LEN) + 1; +} + +/* Convert a timer cycle count to a time interval in nanoseconds. */ +static int64_t npcm7xx_timer_count_to_ns(NPCM7xxTimer *t, uint32_t count) +{ + int64_t ns = count; + + ns *= NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ; + ns *= npcm7xx_tcsr_prescaler(t->tcsr); + + return ns; +} + +/* Convert a time interval in nanoseconds to a timer cycle count. */ +static uint32_t npcm7xx_timer_ns_to_count(NPCM7xxTimer *t, int64_t ns) +{ + int64_t count; + + count = ns / (NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ); + count /= npcm7xx_tcsr_prescaler(t->tcsr); + + return count; +} + +/* + * Raise the interrupt line if there's a pending interrupt and interrupts are + * enabled for this timer. If not, lower it. + */ +static void npcm7xx_timer_check_interrupt(NPCM7xxTimer *t) +{ + NPCM7xxTimerCtrlState *tc = t->ctrl; + int index = npcm7xx_timer_index(tc, t); + bool pending = (t->tcsr & NPCM7XX_TCSR_IE) && (tc->tisr & BIT(index)); + + qemu_set_irq(t->irq, pending); + trace_npcm7xx_timer_irq(DEVICE(tc)->canonical_path, index, pending); +} + +/* Start or resume the timer. */ +static void npcm7xx_timer_start(NPCM7xxTimer *t) +{ + int64_t now; + + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + t->expires_ns = now + t->remaining_ns; + timer_mod(&t->qtimer, t->expires_ns); +} + +/* + * Called when the counter reaches zero. Sets the interrupt flag, and either + * restarts or disables the timer. + */ +static void npcm7xx_timer_reached_zero(NPCM7xxTimer *t) +{ + NPCM7xxTimerCtrlState *tc = t->ctrl; + int index = npcm7xx_timer_index(tc, t); + + tc->tisr |= BIT(index); + + if (t->tcsr & NPCM7XX_TCSR_PERIODIC) { + t->remaining_ns = npcm7xx_timer_count_to_ns(t, t->ticr); + if (t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_start(t); + } + } else { + t->tcsr &= ~(NPCM7XX_TCSR_CEN | NPCM7XX_TCSR_CACT); + } + + npcm7xx_timer_check_interrupt(t); +} + +/* Stop counting. Record the time remaining so we can continue later. */ +static void npcm7xx_timer_pause(NPCM7xxTimer *t) +{ + int64_t now; + + timer_del(&t->qtimer); + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + t->remaining_ns = t->expires_ns - now; + if (t->remaining_ns <= 0) { + npcm7xx_timer_reached_zero(t); + } +} + +/* + * Restart the timer from its initial value. If the timer was enabled and stays + * enabled, adjust the QEMU timer according to the new count. If the timer is + * transitioning from disabled to enabled, the caller is expected to start the + * timer later. + */ +static void npcm7xx_timer_restart(NPCM7xxTimer *t, uint32_t old_tcsr) +{ + t->remaining_ns = npcm7xx_timer_count_to_ns(t, t->ticr); + + if (old_tcsr & t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_start(t); + } +} + +/* Register read and write handlers */ + +static uint32_t npcm7xx_timer_read_tdr(NPCM7xxTimer *t) +{ + if (t->tcsr & NPCM7XX_TCSR_CEN) { + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + return npcm7xx_timer_ns_to_count(t, t->expires_ns - now); + } + + return npcm7xx_timer_ns_to_count(t, t->remaining_ns); +} + +static void npcm7xx_timer_write_tcsr(NPCM7xxTimer *t, uint32_t new_tcsr) +{ + uint32_t old_tcsr = t->tcsr; + uint32_t tdr; + + if (new_tcsr & NPCM7XX_TCSR_RSVD) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: reserved bits in 0x%08x ignored\n", + __func__, new_tcsr); + new_tcsr &= ~NPCM7XX_TCSR_RSVD; + } + if (new_tcsr & NPCM7XX_TCSR_CACT) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: read-only bits in 0x%08x ignored\n", + __func__, new_tcsr); + new_tcsr &= ~NPCM7XX_TCSR_CACT; + } + if ((new_tcsr & NPCM7XX_TCSR_CRST) && (new_tcsr & NPCM7XX_TCSR_CEN)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: both CRST and CEN set; ignoring CEN.\n", + __func__); + new_tcsr &= ~NPCM7XX_TCSR_CEN; + } + + /* Calculate the value of TDR before potentially changing the prescaler. */ + tdr = npcm7xx_timer_read_tdr(t); + + t->tcsr = (t->tcsr & NPCM7XX_TCSR_CACT) | new_tcsr; + + if (npcm7xx_tcsr_prescaler(old_tcsr) != npcm7xx_tcsr_prescaler(new_tcsr)) { + /* Recalculate time remaining based on the current TDR value. */ + t->remaining_ns = npcm7xx_timer_count_to_ns(t, tdr); + if (old_tcsr & t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_start(t); + } + } + + if ((old_tcsr ^ new_tcsr) & NPCM7XX_TCSR_IE) { + npcm7xx_timer_check_interrupt(t); + } + if (new_tcsr & NPCM7XX_TCSR_CRST) { + npcm7xx_timer_restart(t, old_tcsr); + t->tcsr &= ~NPCM7XX_TCSR_CRST; + } + if ((old_tcsr ^ new_tcsr) & NPCM7XX_TCSR_CEN) { + if (new_tcsr & NPCM7XX_TCSR_CEN) { + t->tcsr |= NPCM7XX_TCSR_CACT; + npcm7xx_timer_start(t); + } else { + t->tcsr &= ~NPCM7XX_TCSR_CACT; + npcm7xx_timer_pause(t); + } + } +} + +static void npcm7xx_timer_write_ticr(NPCM7xxTimer *t, uint32_t new_ticr) +{ + t->ticr = new_ticr; + + npcm7xx_timer_restart(t, t->tcsr); +} + +static void npcm7xx_timer_write_tisr(NPCM7xxTimerCtrlState *s, uint32_t value) +{ + int i; + + s->tisr &= ~value; + for (i = 0; i < ARRAY_SIZE(s->timer); i++) { + if (value & (1U << i)) { + npcm7xx_timer_check_interrupt(&s->timer[i]); + } + } +} + +static hwaddr npcm7xx_tcsr_index(hwaddr reg) +{ + switch (reg) { + case NPCM7XX_TIMER_TCSR0: + return 0; + case NPCM7XX_TIMER_TCSR1: + return 1; + case NPCM7XX_TIMER_TCSR2: + return 2; + case NPCM7XX_TIMER_TCSR3: + return 3; + case NPCM7XX_TIMER_TCSR4: + return 4; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_ticr_index(hwaddr reg) +{ + switch (reg) { + case NPCM7XX_TIMER_TICR0: + return 0; + case NPCM7XX_TIMER_TICR1: + return 1; + case NPCM7XX_TIMER_TICR2: + return 2; + case NPCM7XX_TIMER_TICR3: + return 3; + case NPCM7XX_TIMER_TICR4: + return 4; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_tdr_index(hwaddr reg) +{ + switch (reg) { + case NPCM7XX_TIMER_TDR0: + return 0; + case NPCM7XX_TIMER_TDR1: + return 1; + case NPCM7XX_TIMER_TDR2: + return 2; + case NPCM7XX_TIMER_TDR3: + return 3; + case NPCM7XX_TIMER_TDR4: + return 4; + default: + g_assert_not_reached(); + } +} + +static uint64_t npcm7xx_timer_read(void *opaque, hwaddr offset, unsigned size) +{ + NPCM7xxTimerCtrlState *s = opaque; + uint64_t value = 0; + hwaddr reg; + + reg = offset / sizeof(uint32_t); + switch (reg) { + case NPCM7XX_TIMER_TCSR0: + case NPCM7XX_TIMER_TCSR1: + case NPCM7XX_TIMER_TCSR2: + case NPCM7XX_TIMER_TCSR3: + case NPCM7XX_TIMER_TCSR4: + value = s->timer[npcm7xx_tcsr_index(reg)].tcsr; + break; + + case NPCM7XX_TIMER_TICR0: + case NPCM7XX_TIMER_TICR1: + case NPCM7XX_TIMER_TICR2: + case NPCM7XX_TIMER_TICR3: + case NPCM7XX_TIMER_TICR4: + value = s->timer[npcm7xx_ticr_index(reg)].ticr; + break; + + case NPCM7XX_TIMER_TDR0: + case NPCM7XX_TIMER_TDR1: + case NPCM7XX_TIMER_TDR2: + case NPCM7XX_TIMER_TDR3: + case NPCM7XX_TIMER_TDR4: + value = npcm7xx_timer_read_tdr(&s->timer[npcm7xx_tdr_index(reg)]); + break; + + case NPCM7XX_TIMER_TISR: + value = s->tisr; + break; + + case NPCM7XX_TIMER_WTCR: + value = s->wtcr; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + break; + } + + trace_npcm7xx_timer_read(DEVICE(s)->canonical_path, offset, value); + + return value; +} + +static void npcm7xx_timer_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxTimerCtrlState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_timer_write(DEVICE(s)->canonical_path, offset, value); + + switch (reg) { + case NPCM7XX_TIMER_TCSR0: + case NPCM7XX_TIMER_TCSR1: + case NPCM7XX_TIMER_TCSR2: + case NPCM7XX_TIMER_TCSR3: + case NPCM7XX_TIMER_TCSR4: + npcm7xx_timer_write_tcsr(&s->timer[npcm7xx_tcsr_index(reg)], value); + return; + + case NPCM7XX_TIMER_TICR0: + case NPCM7XX_TIMER_TICR1: + case NPCM7XX_TIMER_TICR2: + case NPCM7XX_TIMER_TICR3: + case NPCM7XX_TIMER_TICR4: + npcm7xx_timer_write_ticr(&s->timer[npcm7xx_ticr_index(reg)], value); + return; + + case NPCM7XX_TIMER_TDR0: + case NPCM7XX_TIMER_TDR1: + case NPCM7XX_TIMER_TDR2: + case NPCM7XX_TIMER_TDR3: + case NPCM7XX_TIMER_TDR4: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + return; + + case NPCM7XX_TIMER_TISR: + npcm7xx_timer_write_tisr(s, value); + return; + + case NPCM7XX_TIMER_WTCR: + qemu_log_mask(LOG_UNIMP, "%s: WTCR write not implemented: 0x%08x\n", + __func__, value); + return; + } + + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); +} + +static const struct MemoryRegionOps npcm7xx_timer_ops = { + .read = npcm7xx_timer_read, + .write = npcm7xx_timer_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +/* Called when the QEMU timer expires. */ +static void npcm7xx_timer_expired(void *opaque) +{ + NPCM7xxTimer *t = opaque; + + if (t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_reached_zero(t); + } +} + +static void npcm7xx_timer_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(obj); + int i; + + for (i = 0; i < NPCM7XX_TIMERS_PER_CTRL; i++) { + NPCM7xxTimer *t = &s->timer[i]; + + timer_del(&t->qtimer); + t->expires_ns = 0; + t->remaining_ns = 0; + t->tcsr = 0x00000005; + t->ticr = 0x00000000; + } + + s->tisr = 0x00000000; + s->wtcr = 0x00000400; +} + +static void npcm7xx_timer_hold_reset(Object *obj) +{ + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(obj); + int i; + + for (i = 0; i < NPCM7XX_TIMERS_PER_CTRL; i++) { + qemu_irq_lower(s->timer[i].irq); + } +} + +static void npcm7xx_timer_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(dev); + SysBusDevice *sbd = &s->parent; + int i; + + for (i = 0; i < NPCM7XX_TIMERS_PER_CTRL; i++) { + NPCM7xxTimer *t = &s->timer[i]; + t->ctrl = s; + timer_init_ns(&t->qtimer, QEMU_CLOCK_VIRTUAL, npcm7xx_timer_expired, t); + sysbus_init_irq(sbd, &t->irq); + } + + memory_region_init_io(&s->iomem, OBJECT(s), &npcm7xx_timer_ops, s, + TYPE_NPCM7XX_TIMER, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription vmstate_npcm7xx_timer = { + .name = "npcm7xx-timer", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_TIMER(qtimer, NPCM7xxTimer), + VMSTATE_INT64(expires_ns, NPCM7xxTimer), + VMSTATE_INT64(remaining_ns, NPCM7xxTimer), + VMSTATE_UINT32(tcsr, NPCM7xxTimer), + VMSTATE_UINT32(ticr, NPCM7xxTimer), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_npcm7xx_timer_ctrl = { + .name = "npcm7xx-timer-ctrl", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32(tisr, NPCM7xxTimerCtrlState), + VMSTATE_UINT32(wtcr, NPCM7xxTimerCtrlState), + VMSTATE_STRUCT_ARRAY(timer, NPCM7xxTimerCtrlState, + NPCM7XX_TIMERS_PER_CTRL, 0, vmstate_npcm7xx_timer, + NPCM7xxTimer), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_timer_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_TIMER_REGS_END > NPCM7XX_TIMER_NR_REGS); + + dc->desc = "NPCM7xx Timer Controller"; + dc->realize = npcm7xx_timer_realize; + dc->vmsd = &vmstate_npcm7xx_timer_ctrl; + rc->phases.enter = npcm7xx_timer_enter_reset; + rc->phases.hold = npcm7xx_timer_hold_reset; +} + +static const TypeInfo npcm7xx_timer_info = { + .name = TYPE_NPCM7XX_TIMER, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxTimerCtrlState), + .class_init = npcm7xx_timer_class_init, +}; + +static void npcm7xx_timer_register_type(void) +{ + type_register_static(&npcm7xx_timer_info); +} +type_init(npcm7xx_timer_register_type); diff --git a/hw/timer/meson.build b/hw/timer/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_LM32', if_true: files('lm32_timer.c')) softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-sysctl.c')) softmmu_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_gictimer.c')) softmmu_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-timer.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_timer.c')) softmmu_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_timer.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_gptimer.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_synctimer.c')) diff --git a/hw/timer/trace-events b/hw/timer/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -XXX,XX +XXX,XX @@ cmsdk_apb_dualtimer_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK A cmsdk_apb_dualtimer_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB dualtimer write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" cmsdk_apb_dualtimer_reset(void) "CMSDK APB dualtimer: reset" +# npcm7xx_timer.c +npcm7xx_timer_read(const char *id, uint64_t offset, uint64_t value) " %s offset: 0x%04" PRIx64 " value 0x%08" PRIx64 +npcm7xx_timer_write(const char *id, uint64_t offset, uint64_t value) "%s offset: 0x%04" PRIx64 " value 0x%08" PRIx64 +npcm7xx_timer_irq(const char *id, int timer, int state) "%s timer %d state %d" + # nrf51_timer.c nrf51_timer_read(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" nrf51_timer_write(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> The Nuvoton NPCM7xx SoC family are used to implement Baseboard Management Controllers in servers. While the family includes four SoCs, this patch implements limited support for two of them: NPCM730 (targeted for Data Center applications) and NPCM750 (targeted for Enterprise applications). This patch includes little more than the bare minimum needed to boot a Linux kernel built with NPCM7xx support in direct-kernel mode: - Two Cortex-A9 CPU cores with built-in periperhals. - Global Configuration Registers. - Clock Management. - 3 Timer Modules with 5 timers each. - 4 serial ports. The chips themselves have a lot more features, some of which will be added to the model at a later stage. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-5-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 85 ++++++++ hw/arm/npcm7xx.c | 407 +++++++++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 5 + hw/arm/meson.build | 1 + 4 files changed, 498 insertions(+) create mode 100644 include/hw/arm/npcm7xx.h create mode 100644 hw/arm/npcm7xx.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx SoC family. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_H +#define NPCM7XX_H + +#include "hw/boards.h" +#include "hw/cpu/a9mpcore.h" +#include "hw/misc/npcm7xx_clk.h" +#include "hw/misc/npcm7xx_gcr.h" +#include "hw/timer/npcm7xx_timer.h" +#include "target/arm/cpu.h" + +#define NPCM7XX_MAX_NUM_CPUS (2) + +/* The first half of the address space is reserved for DDR4 DRAM. */ +#define NPCM7XX_DRAM_BA (0x00000000) +#define NPCM7XX_DRAM_SZ (2 * GiB) + +/* Magic addresses for setting up direct kernel booting and SMP boot stubs. */ +#define NPCM7XX_LOADER_START (0x00000000) /* Start of SDRAM */ +#define NPCM7XX_SMP_LOADER_START (0xffff0000) /* Boot ROM */ +#define NPCM7XX_SMP_BOOTREG_ADDR (0xf080013c) /* GCR.SCRPAD */ +#define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ + +typedef struct NPCM7xxState { + DeviceState parent; + + ARMCPU cpu[NPCM7XX_MAX_NUM_CPUS]; + A9MPPrivState a9mpcore; + + MemoryRegion sram; + MemoryRegion irom; + MemoryRegion ram3; + MemoryRegion *dram; + + NPCM7xxGCRState gcr; + NPCM7xxCLKState clk; + NPCM7xxTimerCtrlState tim[3]; +} NPCM7xxState; + +#define TYPE_NPCM7XX "npcm7xx" +#define NPCM7XX(obj) OBJECT_CHECK(NPCM7xxState, (obj), TYPE_NPCM7XX) + +#define TYPE_NPCM730 "npcm730" +#define TYPE_NPCM750 "npcm750" + +typedef struct NPCM7xxClass { + DeviceClass parent; + + /* Bitmask of modules that are permanently disabled on this chip. */ + uint32_t disabled_modules; + /* Number of CPU cores enabled in this SoC class (may be 1 or 2). */ + uint32_t num_cpus; +} NPCM7xxClass; + +#define NPCM7XX_CLASS(klass) \ + OBJECT_CLASS_CHECK(NPCM7xxClass, (klass), TYPE_NPCM7XX) +#define NPCM7XX_GET_CLASS(obj) \ + OBJECT_GET_CLASS(NPCM7xxClass, (obj), TYPE_NPCM7XX) + +/** + * npcm7xx_load_kernel - Loads memory with everything needed to boot + * @machine - The machine containing the SoC to be booted. + * @soc - The SoC containing the CPU to be booted. + * + * This will set up the ARM boot info structure for the specific NPCM7xx + * derivative and call arm_load_kernel() to set up loading of the kernel, etc. + * into memory, if requested by the user. + */ +void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc); + +#endif /* NPCM7XX_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx SoC family. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "exec/address-spaces.h" +#include "hw/arm/boot.h" +#include "hw/arm/npcm7xx.h" +#include "hw/char/serial.h" +#include "hw/loader.h" +#include "hw/misc/unimp.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" +#include "qemu/units.h" +#include "sysemu/sysemu.h" + +/* + * This covers the whole MMIO space. We'll use this to catch any MMIO accesses + * that aren't handled by any device. + */ +#define NPCM7XX_MMIO_BA (0x80000000) +#define NPCM7XX_MMIO_SZ (0x7ffd0000) + +/* Core system modules. */ +#define NPCM7XX_L2C_BA (0xf03fc000) +#define NPCM7XX_CPUP_BA (0xf03fe000) +#define NPCM7XX_GCR_BA (0xf0800000) +#define NPCM7XX_CLK_BA (0xf0801000) + +/* Internal AHB SRAM */ +#define NPCM7XX_RAM3_BA (0xc0008000) +#define NPCM7XX_RAM3_SZ (4 * KiB) + +/* Memory blocks at the end of the address space */ +#define NPCM7XX_RAM2_BA (0xfffd0000) +#define NPCM7XX_RAM2_SZ (128 * KiB) +#define NPCM7XX_ROM_BA (0xffff0000) +#define NPCM7XX_ROM_SZ (64 * KiB) + +/* + * Interrupt lines going into the GIC. This does not include internal Cortex-A9 + * interrupts. + */ +enum NPCM7xxInterrupt { + NPCM7XX_UART0_IRQ = 2, + NPCM7XX_UART1_IRQ, + NPCM7XX_UART2_IRQ, + NPCM7XX_UART3_IRQ, + NPCM7XX_TIMER0_IRQ = 32, /* Timer Module 0 */ + NPCM7XX_TIMER1_IRQ, + NPCM7XX_TIMER2_IRQ, + NPCM7XX_TIMER3_IRQ, + NPCM7XX_TIMER4_IRQ, + NPCM7XX_TIMER5_IRQ, /* Timer Module 1 */ + NPCM7XX_TIMER6_IRQ, + NPCM7XX_TIMER7_IRQ, + NPCM7XX_TIMER8_IRQ, + NPCM7XX_TIMER9_IRQ, + NPCM7XX_TIMER10_IRQ, /* Timer Module 2 */ + NPCM7XX_TIMER11_IRQ, + NPCM7XX_TIMER12_IRQ, + NPCM7XX_TIMER13_IRQ, + NPCM7XX_TIMER14_IRQ, +}; + +/* Total number of GIC interrupts, including internal Cortex-A9 interrupts. */ +#define NPCM7XX_NUM_IRQ (160) + +/* Register base address for each Timer Module */ +static const hwaddr npcm7xx_tim_addr[] = { + 0xf0008000, + 0xf0009000, + 0xf000a000, +}; + +/* Register base address for each 16550 UART */ +static const hwaddr npcm7xx_uart_addr[] = { + 0xf0001000, + 0xf0002000, + 0xf0003000, + 0xf0004000, +}; + +static void npcm7xx_write_secondary_boot(ARMCPU *cpu, + const struct arm_boot_info *info) +{ + /* + * The default smpboot stub halts the secondary CPU with a 'wfi' + * instruction, but the arch/arm/mach-npcm/platsmp.c in the Linux kernel + * does not send an IPI to wake it up, so the second CPU fails to boot. So + * we need to provide our own smpboot stub that can not use 'wfi', it has + * to spin the secondary CPU until the first CPU writes to the SCRPAD reg. + */ + uint32_t smpboot[] = { + 0xe59f2018, /* ldr r2, bootreg_addr */ + 0xe3a00000, /* mov r0, #0 */ + 0xe5820000, /* str r0, [r2] */ + 0xe320f002, /* wfe */ + 0xe5921000, /* ldr r1, [r2] */ + 0xe1110001, /* tst r1, r1 */ + 0x0afffffb, /* beq <wfe> */ + 0xe12fff11, /* bx r1 */ + NPCM7XX_SMP_BOOTREG_ADDR, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(smpboot); i++) { + smpboot[i] = tswap32(smpboot[i]); + } + + rom_add_blob_fixed("smpboot", smpboot, sizeof(smpboot), + NPCM7XX_SMP_LOADER_START); +} + +static struct arm_boot_info npcm7xx_binfo = { + .loader_start = NPCM7XX_LOADER_START, + .smp_loader_start = NPCM7XX_SMP_LOADER_START, + .smp_bootreg_addr = NPCM7XX_SMP_BOOTREG_ADDR, + .gic_cpu_if_addr = NPCM7XX_GIC_CPU_IF_ADDR, + .write_secondary_boot = npcm7xx_write_secondary_boot, + .board_id = -1, +}; + +void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc) +{ + NPCM7xxClass *sc = NPCM7XX_GET_CLASS(soc); + + npcm7xx_binfo.ram_size = machine->ram_size; + npcm7xx_binfo.nb_cpus = sc->num_cpus; + + arm_load_kernel(&soc->cpu[0], machine, &npcm7xx_binfo); +} + +static qemu_irq npcm7xx_irq(NPCM7xxState *s, int n) +{ + return qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); +} + +static void npcm7xx_init(Object *obj) +{ + NPCM7xxState *s = NPCM7XX(obj); + int i; + + for (i = 0; i < NPCM7XX_MAX_NUM_CPUS; i++) { + object_initialize_child(obj, "cpu[*]", &s->cpu[i], + ARM_CPU_TYPE_NAME("cortex-a9")); + } + + object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); + object_initialize_child(obj, "gcr", &s->gcr, TYPE_NPCM7XX_GCR); + object_property_add_alias(obj, "power-on-straps", OBJECT(&s->gcr), + "power-on-straps"); + object_initialize_child(obj, "clk", &s->clk, TYPE_NPCM7XX_CLK); + + for (i = 0; i < ARRAY_SIZE(s->tim); i++) { + object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); + } +} + +static void npcm7xx_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxState *s = NPCM7XX(dev); + NPCM7xxClass *nc = NPCM7XX_GET_CLASS(s); + int i; + + if (memory_region_size(s->dram) > NPCM7XX_DRAM_SZ) { + error_setg(errp, "%s: NPCM7xx cannot address more than %" PRIu64 + " MiB of DRAM", __func__, NPCM7XX_DRAM_SZ / MiB); + return; + } + + /* CPUs */ + for (i = 0; i < nc->num_cpus; i++) { + object_property_set_int(OBJECT(&s->cpu[i]), "mp-affinity", + arm_cpu_mp_affinity(i, NPCM7XX_MAX_NUM_CPUS), + &error_abort); + object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar", + NPCM7XX_GIC_CPU_IF_ADDR, &error_abort); + object_property_set_bool(OBJECT(&s->cpu[i]), "reset-hivecs", true, + &error_abort); + + /* Disable security extensions. */ + object_property_set_bool(OBJECT(&s->cpu[i]), "has_el3", false, + &error_abort); + + if (!qdev_realize(DEVICE(&s->cpu[i]), NULL, errp)) { + return; + } + } + + /* A9MPCORE peripherals. Can only fail if we pass bad parameters here. */ + object_property_set_int(OBJECT(&s->a9mpcore), "num-cpu", nc->num_cpus, + &error_abort); + object_property_set_int(OBJECT(&s->a9mpcore), "num-irq", NPCM7XX_NUM_IRQ, + &error_abort); + sysbus_realize(SYS_BUS_DEVICE(&s->a9mpcore), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->a9mpcore), 0, NPCM7XX_CPUP_BA); + + for (i = 0; i < nc->num_cpus; i++) { + sysbus_connect_irq(SYS_BUS_DEVICE(&s->a9mpcore), i, + qdev_get_gpio_in(DEVICE(&s->cpu[i]), ARM_CPU_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->a9mpcore), i + nc->num_cpus, + qdev_get_gpio_in(DEVICE(&s->cpu[i]), ARM_CPU_FIQ)); + } + + /* L2 cache controller */ + sysbus_create_simple("l2x0", NPCM7XX_L2C_BA, NULL); + + /* System Global Control Registers (GCR). Can fail due to user input. */ + object_property_set_int(OBJECT(&s->gcr), "disabled-modules", + nc->disabled_modules, &error_abort); + object_property_add_const_link(OBJECT(&s->gcr), "dram-mr", OBJECT(s->dram)); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gcr), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gcr), 0, NPCM7XX_GCR_BA); + + /* Clock Control Registers (CLK). Cannot fail. */ + sysbus_realize(SYS_BUS_DEVICE(&s->clk), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->clk), 0, NPCM7XX_CLK_BA); + + /* Timer Modules (TIM). Cannot fail. */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); + for (i = 0; i < ARRAY_SIZE(s->tim); i++) { + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->tim[i]); + int first_irq; + int j; + + sysbus_realize(sbd, &error_abort); + sysbus_mmio_map(sbd, 0, npcm7xx_tim_addr[i]); + + first_irq = NPCM7XX_TIMER0_IRQ + i * NPCM7XX_TIMERS_PER_CTRL; + for (j = 0; j < NPCM7XX_TIMERS_PER_CTRL; j++) { + qemu_irq irq = npcm7xx_irq(s, first_irq + j); + sysbus_connect_irq(sbd, j, irq); + } + } + + /* UART0..3 (16550 compatible) */ + for (i = 0; i < ARRAY_SIZE(npcm7xx_uart_addr); i++) { + serial_mm_init(get_system_memory(), npcm7xx_uart_addr[i], 2, + npcm7xx_irq(s, NPCM7XX_UART0_IRQ + i), 115200, + serial_hd(i), DEVICE_LITTLE_ENDIAN); + } + + /* RAM2 (SRAM) */ + memory_region_init_ram(&s->sram, OBJECT(dev), "ram2", + NPCM7XX_RAM2_SZ, &error_abort); + memory_region_add_subregion(get_system_memory(), NPCM7XX_RAM2_BA, &s->sram); + + /* RAM3 (SRAM) */ + memory_region_init_ram(&s->ram3, OBJECT(dev), "ram3", + NPCM7XX_RAM3_SZ, &error_abort); + memory_region_add_subregion(get_system_memory(), NPCM7XX_RAM3_BA, &s->ram3); + + /* Internal ROM */ + memory_region_init_rom(&s->irom, OBJECT(dev), "irom", NPCM7XX_ROM_SZ, + &error_abort); + memory_region_add_subregion(get_system_memory(), NPCM7XX_ROM_BA, &s->irom); + + create_unimplemented_device("npcm7xx.shm", 0xc0001000, 4 * KiB); + create_unimplemented_device("npcm7xx.vdmx", 0xe0800000, 4 * KiB); + create_unimplemented_device("npcm7xx.pcierc", 0xe1000000, 64 * KiB); + create_unimplemented_device("npcm7xx.kcs", 0xf0007000, 4 * KiB); + create_unimplemented_device("npcm7xx.rng", 0xf000b000, 4 * KiB); + create_unimplemented_device("npcm7xx.adc", 0xf000c000, 4 * KiB); + create_unimplemented_device("npcm7xx.gfxi", 0xf000e000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[0]", 0xf0010000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[1]", 0xf0011000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[2]", 0xf0012000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[3]", 0xf0013000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[4]", 0xf0014000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[5]", 0xf0015000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[6]", 0xf0016000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[7]", 0xf0017000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[0]", 0xf0080000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[1]", 0xf0081000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[2]", 0xf0082000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[3]", 0xf0083000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[4]", 0xf0084000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[5]", 0xf0085000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[6]", 0xf0086000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[7]", 0xf0087000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[8]", 0xf0088000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[9]", 0xf0089000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[10]", 0xf008a000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[11]", 0xf008b000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[12]", 0xf008c000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[13]", 0xf008d000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[14]", 0xf008e000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[15]", 0xf008f000, 4 * KiB); + create_unimplemented_device("npcm7xx.espi", 0xf009f000, 4 * KiB); + create_unimplemented_device("npcm7xx.peci", 0xf0100000, 4 * KiB); + create_unimplemented_device("npcm7xx.siox[1]", 0xf0101000, 4 * KiB); + create_unimplemented_device("npcm7xx.siox[2]", 0xf0102000, 4 * KiB); + create_unimplemented_device("npcm7xx.pwm[0]", 0xf0103000, 4 * KiB); + create_unimplemented_device("npcm7xx.pwm[1]", 0xf0104000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[0]", 0xf0180000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[1]", 0xf0181000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[2]", 0xf0182000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[3]", 0xf0183000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[4]", 0xf0184000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[5]", 0xf0185000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[6]", 0xf0186000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[7]", 0xf0187000, 4 * KiB); + create_unimplemented_device("npcm7xx.pspi1", 0xf0200000, 4 * KiB); + create_unimplemented_device("npcm7xx.pspi2", 0xf0201000, 4 * KiB); + create_unimplemented_device("npcm7xx.ahbpci", 0xf0400000, 1 * MiB); + create_unimplemented_device("npcm7xx.mcphy", 0xf05f0000, 64 * KiB); + create_unimplemented_device("npcm7xx.gmac1", 0xf0802000, 8 * KiB); + create_unimplemented_device("npcm7xx.gmac2", 0xf0804000, 8 * KiB); + create_unimplemented_device("npcm7xx.ehci", 0xf0806000, 4 * KiB); + create_unimplemented_device("npcm7xx.ohci", 0xf0807000, 4 * KiB); + create_unimplemented_device("npcm7xx.vcd", 0xf0810000, 64 * KiB); + create_unimplemented_device("npcm7xx.ece", 0xf0820000, 8 * KiB); + create_unimplemented_device("npcm7xx.vdma", 0xf0822000, 8 * KiB); + create_unimplemented_device("npcm7xx.emc1", 0xf0825000, 4 * KiB); + create_unimplemented_device("npcm7xx.emc2", 0xf0826000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[0]", 0xf0830000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[1]", 0xf0831000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[2]", 0xf0832000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[3]", 0xf0833000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[4]", 0xf0834000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[5]", 0xf0835000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[6]", 0xf0836000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[7]", 0xf0837000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[8]", 0xf0838000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[9]", 0xf0839000, 4 * KiB); + create_unimplemented_device("npcm7xx.sd", 0xf0840000, 8 * KiB); + create_unimplemented_device("npcm7xx.mmc", 0xf0842000, 8 * KiB); + create_unimplemented_device("npcm7xx.pcimbx", 0xf0848000, 512 * KiB); + create_unimplemented_device("npcm7xx.aes", 0xf0858000, 4 * KiB); + create_unimplemented_device("npcm7xx.des", 0xf0859000, 4 * KiB); + create_unimplemented_device("npcm7xx.sha", 0xf085a000, 4 * KiB); + create_unimplemented_device("npcm7xx.secacc", 0xf085b000, 4 * KiB); + create_unimplemented_device("npcm7xx.spixcs0", 0xf8000000, 16 * MiB); + create_unimplemented_device("npcm7xx.spixcs1", 0xf9000000, 16 * MiB); + create_unimplemented_device("npcm7xx.spix", 0xfb001000, 4 * KiB); +} + +static Property npcm7xx_properties[] = { + DEFINE_PROP_LINK("dram-mr", NPCM7xxState, dram, TYPE_MEMORY_REGION, + MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = npcm7xx_realize; + dc->user_creatable = false; + device_class_set_props(dc, npcm7xx_properties); +} + +static void npcm730_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxClass *nc = NPCM7XX_CLASS(oc); + + /* NPCM730 is optimized for data center use, so no graphics, etc. */ + nc->disabled_modules = 0x00300395; + nc->num_cpus = 2; +} + +static void npcm750_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxClass *nc = NPCM7XX_CLASS(oc); + + /* NPCM750 has 2 cores and a full set of peripherals */ + nc->disabled_modules = 0x00000000; + nc->num_cpus = 2; +} + +static const TypeInfo npcm7xx_soc_types[] = { + { + .name = TYPE_NPCM7XX, + .parent = TYPE_DEVICE, + .instance_size = sizeof(NPCM7xxState), + .instance_init = npcm7xx_init, + .class_size = sizeof(NPCM7xxClass), + .class_init = npcm7xx_class_init, + .abstract = true, + }, { + .name = TYPE_NPCM730, + .parent = TYPE_NPCM7XX, + .class_init = npcm730_class_init, + }, { + .name = TYPE_NPCM750, + .parent = TYPE_NPCM7XX, + .class_init = npcm750_class_init, + }, +}; + +DEFINE_TYPES(npcm7xx_soc_types); 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 XLNX_VERSAL config NPCM7XX bool + select A9MPCORE + select ARM_GIC + select PL310 # cache controller + select SERIAL + select UNIMP config FSL_IMX25 bool diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) +arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) arm_ss.add(when: 'CONFIG_CHEETAH', if_true: files('palm.c')) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This adds two new machines, both supported by OpenBMC: - npcm750-evb: Nuvoton NPCM750 Evaluation Board. - quanta-gsj: A board with a NPCM730 chip. They rely on the NPCM7xx SoC device to do the heavy lifting. They are almost completely identical at the moment, apart from the SoC type, which currently only changes the reset contents of one register (GCR.MDLR), but they might grow apart a bit more as more functionality is added. Both machines can boot the Linux kernel into /bin/sh. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-6-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- default-configs/arm-softmmu.mak | 1 + include/hw/arm/npcm7xx.h | 19 +++++ hw/arm/npcm7xx_boards.c | 145 ++++++++++++++++++++++++++++++++ hw/arm/meson.build | 2 +- 4 files changed, 166 insertions(+), 1 deletion(-) create mode 100644 hw/arm/npcm7xx_boards.c diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_GUMSTIX=y CONFIG_SPITZ=y CONFIG_TOSA=y CONFIG_Z2=y +CONFIG_NPCM7XX=y CONFIG_COLLIE=y CONFIG_ASPEED_SOC=y CONFIG_NETDUINO2=y diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_SMP_BOOTREG_ADDR (0xf080013c) /* GCR.SCRPAD */ #define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ +typedef struct NPCM7xxMachine { + MachineState parent; +} NPCM7xxMachine; + +#define TYPE_NPCM7XX_MACHINE MACHINE_TYPE_NAME("npcm7xx") +#define NPCM7XX_MACHINE(obj) \ + OBJECT_CHECK(NPCM7xxMachine, (obj), TYPE_NPCM7XX_MACHINE) + +typedef struct NPCM7xxMachineClass { + MachineClass parent; + + const char *soc_type; +} NPCM7xxMachineClass; + +#define NPCM7XX_MACHINE_CLASS(klass) \ + OBJECT_CLASS_CHECK(NPCM7xxMachineClass, (klass), TYPE_NPCM7XX_MACHINE) +#define NPCM7XX_MACHINE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(NPCM7xxMachineClass, (obj), TYPE_NPCM7XX_MACHINE) + typedef struct NPCM7xxState { DeviceState parent; diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ +/* + * Machine definitions for boards featuring an NPCM7xx SoC. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "exec/address-spaces.h" +#include "hw/arm/npcm7xx.h" +#include "hw/core/cpu.h" +#include "qapi/error.h" +#include "qemu/units.h" + +#define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 +#define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff + +static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) +{ + memory_region_add_subregion(get_system_memory(), NPCM7XX_DRAM_BA, dram); + + object_property_set_link(OBJECT(soc), "dram-mr", OBJECT(dram), + &error_abort); +} + +static NPCM7xxState *npcm7xx_create_soc(MachineState *machine, + uint32_t hw_straps) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_GET_CLASS(machine); + MachineClass *mc = &nmc->parent; + Object *obj; + + if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { + error_report("This board can only be used with %s", + mc->default_cpu_type); + exit(1); + } + + obj = object_new_with_props(nmc->soc_type, OBJECT(machine), "soc", + &error_abort, NULL); + object_property_set_uint(obj, "power-on-straps", hw_straps, &error_abort); + + return NPCM7XX(obj); +} + +static void npcm750_evb_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, NPCM750_EVB_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_kernel(machine, soc); +} + +static void quanta_gsj_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, QUANTA_GSJ_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_kernel(machine, soc); +} + +static void npcm7xx_set_soc_type(NPCM7xxMachineClass *nmc, const char *type) +{ + NPCM7xxClass *sc = NPCM7XX_CLASS(object_class_by_name(type)); + MachineClass *mc = MACHINE_CLASS(nmc); + + nmc->soc_type = type; + mc->default_cpus = mc->min_cpus = mc->max_cpus = sc->num_cpus; +} + +static void npcm7xx_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->no_floppy = 1; + mc->no_cdrom = 1; + mc->no_parallel = 1; + mc->default_ram_id = "ram"; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a9"); +} + +/* + * Schematics: + * https://github.com/Nuvoton-Israel/nuvoton-info/blob/master/npcm7xx-poleg/evaluation-board/board_deliverables/NPCM750x_EB_ver.A1.1_COMPLETE.pdf + */ +static void npcm750_evb_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM750); + + mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex A9)"; + mc->init = npcm750_evb_init; + mc->default_ram_size = 512 * MiB; +}; + +static void gsj_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM730); + + mc->desc = "Quanta GSJ (Cortex A9)"; + mc->init = quanta_gsj_init; + mc->default_ram_size = 512 * MiB; +}; + +static const TypeInfo npcm7xx_machine_types[] = { + { + .name = TYPE_NPCM7XX_MACHINE, + .parent = TYPE_MACHINE, + .instance_size = sizeof(NPCM7xxMachine), + .class_size = sizeof(NPCM7xxMachineClass), + .class_init = npcm7xx_machine_class_init, + .abstract = true, + }, { + .name = MACHINE_TYPE_NAME("npcm750-evb"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = npcm750_evb_machine_class_init, + }, { + .name = MACHINE_TYPE_NAME("quanta-gsj"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = gsj_machine_class_init, + }, +}; + +DEFINE_TYPES(npcm7xx_machine_types) diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) -arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c')) +arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) arm_ss.add(when: 'CONFIG_CHEETAH', if_true: files('palm.c')) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This is a minimalistic boot ROM written specifically for use with QEMU. It supports loading the second-stage loader from SPI flash into RAM, SMP boot, and not much else. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-7-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- .gitmodules | 3 +++ MAINTAINERS | 2 ++ pc-bios/README | 6 ++++++ pc-bios/meson.build | 1 + pc-bios/npcm7xx_bootrom.bin | Bin 0 -> 768 bytes roms/Makefile | 7 +++++++ roms/vbootrom | 1 + 7 files changed, 20 insertions(+) create mode 100644 pc-bios/npcm7xx_bootrom.bin create mode 160000 roms/vbootrom diff --git a/.gitmodules b/.gitmodules index XXXXXXX..XXXXXXX 100644 --- a/.gitmodules +++ b/.gitmodules @@ -XXX,XX +XXX,XX @@ [submodule "meson"] path = meson url = https://github.com/mesonbuild/meson/ +[submodule "roms/vbootrom"] + path = roms/vbootrom + url = https://github.com/google/vbootrom.git diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Supported F: hw/*/npcm7xx* F: include/hw/*/npcm7xx* +F: pc-bios/npcm7xx_bootrom.bin +F: roms/vbootrom nSeries M: Andrzej Zaborowski <balrogg@gmail.com> diff --git a/pc-bios/README b/pc-bios/README index XXXXXXX..XXXXXXX 100644 --- a/pc-bios/README +++ b/pc-bios/README @@ -XXX,XX +XXX,XX @@ ("Simplified BSD License" or "FreeBSD License", SPDX: BSD-2-Clause). OpenSBI source code also contains code reused from other projects desribed here: https://github.com/riscv/opensbi/blob/master/ThirdPartyNotices.md. + +- npcm7xx_bootrom.bin is a simplified, free (Apache 2.0) boot ROM for Nuvoton + NPCM7xx BMC devices. It currently implements the bare minimum to load, parse, + initialize and run boot images stored in SPI flash, but may grow more + features over time as needed. The source code is available at: + https://github.com/google/vbootrom diff --git a/pc-bios/meson.build b/pc-bios/meson.build index XXXXXXX..XXXXXXX 100644 --- a/pc-bios/meson.build +++ b/pc-bios/meson.build @@ -XXX,XX +XXX,XX @@ blobs = files( 'opensbi-riscv64-generic-fw_dynamic.bin', 'opensbi-riscv32-generic-fw_dynamic.elf', 'opensbi-riscv64-generic-fw_dynamic.elf', + 'npcm7xx_bootrom.bin', ) if install_blobs diff --git a/pc-bios/npcm7xx_bootrom.bin b/pc-bios/npcm7xx_bootrom.bin new file mode 100644 index XXXXXXX..XXXXXXX GIT binary patch literal 768 zcmd5)JxClu6n-<aczPbVhZYusb8wKx;7TklHfmuZdYT9pDRLwd1p_t-DFpWpyA+8( zwKtZg3J4a0aCM3_X(ZL&4g;46VVk5e$K;z;L99|b@aE%v^S$rQ8)h(Vm@cB9IYc+2 z2SHd4^NwTIGE%w>9S05p1#kf90Sj5Z(jG8}+)IZIp~iXK=T&)dL`%d-q*8aR#mq{7 z9`=6;Dr(H0ACe72R5x?!)^86Qj-X%{+!K9iZNA@*wkBAV&iZ(l^I9?!Gz=S2I_*1d zr+tTQDHjvyzKnw(hu00yX`u!Fv<!~XVcX?@kr#<B0(gGU?$W{gSsQa}CF^8Cfzp2X z@P}yDV-bci(K9XL$FU!som2C`c)?Uc&294s^}Wzumap{hg1X^jN|V25M5tQZ=<9lN z%(zKz#t-qCwHKb;HygOCpvCNL_4@1tXV1YGf^XUE_$zr{g8zWh-6gz-teI(eibtxo z?0OZI4%rU0741PgUD`2xq@H|*4=+Rs?%N)Ox5G+q>C;DilBe_YlkeSUVHA-crNk+k jtiF_MudA<CB(}8|fqYwCf3re&=&@_s761P#-ID$TwgmBa literal 0 HcmV?d00001 diff --git a/roms/Makefile b/roms/Makefile index XXXXXXX..XXXXXXX 100644 --- a/roms/Makefile +++ b/roms/Makefile @@ -XXX,XX +XXX,XX @@ find-cross-gcc = $(firstword $(wildcard $(patsubst %ld,%gcc,$(call find-cross-ld # finally strip off path + toolname so we get the prefix find-cross-prefix = $(subst gcc,,$(notdir $(call find-cross-gcc,$(1)))) +arm_cross_prefix := $(call find-cross-prefix,arm) powerpc64_cross_prefix := $(call find-cross-prefix,powerpc64) powerpc_cross_prefix := $(call find-cross-prefix,powerpc) x86_64_cross_prefix := $(call find-cross-prefix,x86_64) @@ -XXX,XX +XXX,XX @@ default help: @echo " skiboot -- update skiboot.lid" @echo " u-boot.e500 -- update u-boot.e500" @echo " u-boot.sam460 -- update u-boot.sam460" + @echo " npcm7xx_bootrom -- update vbootrom for npcm7xx" @echo " efi -- update UEFI (edk2) platform firmware" @echo " opensbi32-generic -- update OpenSBI for 32-bit generic machine" @echo " opensbi64-generic -- update OpenSBI for 64-bit generic machine" @@ -XXX,XX +XXX,XX @@ bios-microvm: $(MAKE) -C qboot cp qboot/bios.bin ../pc-bios/bios-microvm.bin +npcm7xx_bootrom: + $(MAKE) -C vbootrom CROSS_COMPILE=$(arm_cross_prefix) + cp vbootrom/npcm7xx_bootrom.bin ../pc-bios/npcm7xx_bootrom.bin + clean: rm -rf seabios/.config seabios/out seabios/builds $(MAKE) -C sgabios clean @@ -XXX,XX +XXX,XX @@ clean: $(MAKE) -f Makefile.edk2 clean $(MAKE) -C opensbi clean $(MAKE) -C qboot clean + $(MAKE) -C vbootrom clean diff --git a/roms/vbootrom b/roms/vbootrom new file mode 160000 index XXXXXXX..XXXXXXX --- /dev/null +++ b/roms/vbootrom @@ -0,0 +1 @@ +Subproject commit 0c37a43527f0ee2b9584e7fb2fdc805e902635ac -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> If a -bios option is specified on the command line, load the image into the internal ROM memory region, which contains the first instructions run by the CPU after reset. If -bios is not specified, the vbootrom included with qemu is loaded by default. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-8-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "hw/arm/npcm7xx.h" #include "hw/core/cpu.h" +#include "hw/loader.h" #include "qapi/error.h" +#include "qemu-common.h" #include "qemu/units.h" +#include "sysemu/sysemu.h" #define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 #define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff +static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; + +static void npcm7xx_load_bootrom(MachineState *machine, NPCM7xxState *soc) +{ + g_autofree char *filename = NULL; + int ret; + + if (!bios_name) { + bios_name = npcm7xx_default_bootrom; + } + + filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); + if (!filename) { + error_report("Could not find ROM image '%s'", bios_name); + if (!machine->kernel_filename) { + /* We can't boot without a bootrom or a kernel image. */ + exit(1); + } + return; + } + ret = load_image_mr(filename, &soc->irom); + if (ret < 0) { + error_report("Failed to load ROM image '%s'", filename); + exit(1); + } +} + static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) { memory_region_add_subregion(get_system_memory(), NPCM7XX_DRAM_BA, dram); @@ -XXX,XX +XXX,XX @@ static void npcm750_evb_init(MachineState *machine) npcm7xx_connect_dram(soc, machine->ram); qdev_realize(DEVICE(soc), NULL, &error_fatal); + npcm7xx_load_bootrom(machine, soc); npcm7xx_load_kernel(machine, soc); } @@ -XXX,XX +XXX,XX @@ static void quanta_gsj_init(MachineState *machine) npcm7xx_connect_dram(soc, machine->ram); qdev_realize(DEVICE(soc), NULL, &error_fatal); + npcm7xx_load_bootrom(machine, soc); npcm7xx_load_kernel(machine, soc); } -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This supports reading and writing OTP fuses and keys. Only fuse reading has been tested. Protection is not implemented. Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-9-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 3 + include/hw/nvram/npcm7xx_otp.h | 79 ++++++ hw/arm/npcm7xx.c | 29 +++ hw/nvram/npcm7xx_otp.c | 440 +++++++++++++++++++++++++++++++++ hw/nvram/meson.build | 1 + 5 files changed, 552 insertions(+) create mode 100644 include/hw/nvram/npcm7xx_otp.h create mode 100644 hw/nvram/npcm7xx_otp.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/a9mpcore.h" #include "hw/misc/npcm7xx_clk.h" #include "hw/misc/npcm7xx_gcr.h" +#include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxGCRState gcr; NPCM7xxCLKState clk; NPCM7xxTimerCtrlState tim[3]; + NPCM7xxOTPState key_storage; + NPCM7xxOTPState fuse_array; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/include/hw/nvram/npcm7xx_otp.h b/include/hw/nvram/npcm7xx_otp.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/nvram/npcm7xx_otp.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx OTP (Fuse Array) Interface + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_OTP_H +#define NPCM7XX_OTP_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/* Each OTP module holds 8192 bits of one-time programmable storage */ +#define NPCM7XX_OTP_ARRAY_BITS (8192) +#define NPCM7XX_OTP_ARRAY_BYTES (NPCM7XX_OTP_ARRAY_BITS / BITS_PER_BYTE) + +/* Fuse array offsets */ +#define NPCM7XX_FUSE_FUSTRAP (0) +#define NPCM7XX_FUSE_CP_FUSTRAP (12) +#define NPCM7XX_FUSE_DAC_CALIB (16) +#define NPCM7XX_FUSE_ADC_CALIB (24) +#define NPCM7XX_FUSE_DERIVATIVE (64) +#define NPCM7XX_FUSE_TEST_SIG (72) +#define NPCM7XX_FUSE_DIE_LOCATION (74) +#define NPCM7XX_FUSE_GP1 (80) +#define NPCM7XX_FUSE_GP2 (128) + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_OTP_NR_REGS (0x18 / sizeof(uint32_t)) + +/** + * struct NPCM7xxOTPState - Device state for one OTP module. + * @parent: System bus device. + * @mmio: Memory region through which registers are accessed. + * @regs: Register contents. + * @array: OTP storage array. + */ +typedef struct NPCM7xxOTPState { + SysBusDevice parent; + + MemoryRegion mmio; + uint32_t regs[NPCM7XX_OTP_NR_REGS]; + uint8_t array[NPCM7XX_OTP_ARRAY_BYTES]; +} NPCM7xxOTPState; + +#define TYPE_NPCM7XX_OTP "npcm7xx-otp" +#define NPCM7XX_OTP(obj) OBJECT_CHECK(NPCM7xxOTPState, (obj), TYPE_NPCM7XX_OTP) + +#define TYPE_NPCM7XX_KEY_STORAGE "npcm7xx-key-storage" +#define TYPE_NPCM7XX_FUSE_ARRAY "npcm7xx-fuse-array" + +typedef struct NPCM7xxOTPClass NPCM7xxOTPClass; + +/** + * npcm7xx_otp_array_write - ECC encode and write data to OTP array. + * @s: OTP module. + * @data: Data to be encoded and written. + * @offset: Offset of first byte to be written in the OTP array. + * @len: Number of bytes before ECC encoding. + * + * Each nibble of data is encoded into a byte, so the number of bytes written + * to the array will be @len * 2. + */ +extern void npcm7xx_otp_array_write(NPCM7xxOTPState *s, const void *data, + unsigned int offset, unsigned int len); + +#endif /* NPCM7XX_OTP_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_MMIO_BA (0x80000000) #define NPCM7XX_MMIO_SZ (0x7ffd0000) +/* OTP key storage and fuse strap array */ +#define NPCM7XX_OTP1_BA (0xf0189000) +#define NPCM7XX_OTP2_BA (0xf018a000) + /* Core system modules. */ #define NPCM7XX_L2C_BA (0xf03fc000) #define NPCM7XX_CPUP_BA (0xf03fe000) @@ -XXX,XX +XXX,XX @@ void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc) arm_load_kernel(&soc->cpu[0], machine, &npcm7xx_binfo); } +static void npcm7xx_init_fuses(NPCM7xxState *s) +{ + NPCM7xxClass *nc = NPCM7XX_GET_CLASS(s); + uint32_t value; + + /* + * The initial mask of disabled modules indicates the chip derivative (e.g. + * NPCM750 or NPCM730). + */ + value = tswap32(nc->disabled_modules); + npcm7xx_otp_array_write(&s->fuse_array, &value, NPCM7XX_FUSE_DERIVATIVE, + sizeof(value)); +} + static qemu_irq npcm7xx_irq(NPCM7xxState *s, int n) { return qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) object_property_add_alias(obj, "power-on-straps", OBJECT(&s->gcr), "power-on-straps"); object_initialize_child(obj, "clk", &s->clk, TYPE_NPCM7XX_CLK); + object_initialize_child(obj, "otp1", &s->key_storage, + TYPE_NPCM7XX_KEY_STORAGE); + object_initialize_child(obj, "otp2", &s->fuse_array, + TYPE_NPCM7XX_FUSE_ARRAY); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->clk), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->clk), 0, NPCM7XX_CLK_BA); + /* OTP key storage and fuse strap array. Cannot fail. */ + sysbus_realize(SYS_BUS_DEVICE(&s->key_storage), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->key_storage), 0, NPCM7XX_OTP1_BA); + sysbus_realize(SYS_BUS_DEVICE(&s->fuse_array), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->fuse_array), 0, NPCM7XX_OTP2_BA); + npcm7xx_init_fuses(s); + /* Timer Modules (TIM). Cannot fail. */ QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { diff --git a/hw/nvram/npcm7xx_otp.c b/hw/nvram/npcm7xx_otp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/nvram/npcm7xx_otp.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx OTP (Fuse Array) Interface + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "hw/nvram/npcm7xx_otp.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +/* Each module has 4 KiB of register space. Only a fraction of it is used. */ +#define NPCM7XX_OTP_REGS_SIZE (4 * KiB) + +/* 32-bit register indices. */ +typedef enum NPCM7xxOTPRegister { + NPCM7XX_OTP_FST, + NPCM7XX_OTP_FADDR, + NPCM7XX_OTP_FDATA, + NPCM7XX_OTP_FCFG, + /* Offset 0x10 is FKEYIND in OTP1, FUSTRAP in OTP2 */ + NPCM7XX_OTP_FKEYIND = 0x0010 / sizeof(uint32_t), + NPCM7XX_OTP_FUSTRAP = 0x0010 / sizeof(uint32_t), + NPCM7XX_OTP_FCTL, + NPCM7XX_OTP_REGS_END, +} NPCM7xxOTPRegister; + +/* Register field definitions. */ +#define FST_RIEN BIT(2) +#define FST_RDST BIT(1) +#define FST_RDY BIT(0) +#define FST_RO_MASK (FST_RDST | FST_RDY) + +#define FADDR_BYTEADDR(rv) extract32((rv), 0, 10) +#define FADDR_BITPOS(rv) extract32((rv), 10, 3) + +#define FDATA_CLEAR 0x00000001 + +#define FCFG_FDIS BIT(31) +#define FCFG_FCFGLK_MASK 0x00ff0000 + +#define FCTL_PROG_CMD1 0x00000001 +#define FCTL_PROG_CMD2 0xbf79e5d0 +#define FCTL_READ_CMD 0x00000002 + +/** + * struct NPCM7xxOTPClass - OTP module class. + * @parent: System bus device class. + * @mmio_ops: MMIO register operations for this type of module. + * + * The two OTP modules (key-storage and fuse-array) have slightly different + * behavior, so we give them different MMIO register operations. + */ +struct NPCM7xxOTPClass { + SysBusDeviceClass parent; + + const MemoryRegionOps *mmio_ops; +}; + +#define NPCM7XX_OTP_CLASS(klass) \ + OBJECT_CLASS_CHECK(NPCM7xxOTPClass, (klass), TYPE_NPCM7XX_OTP) +#define NPCM7XX_OTP_GET_CLASS(obj) \ + OBJECT_GET_CLASS(NPCM7xxOTPClass, (obj), TYPE_NPCM7XX_OTP) + +static uint8_t ecc_encode_nibble(uint8_t n) +{ + uint8_t result = n; + + result |= (((n >> 0) & 1) ^ ((n >> 1) & 1)) << 4; + result |= (((n >> 2) & 1) ^ ((n >> 3) & 1)) << 5; + result |= (((n >> 0) & 1) ^ ((n >> 2) & 1)) << 6; + result |= (((n >> 1) & 1) ^ ((n >> 3) & 1)) << 7; + + return result; +} + +void npcm7xx_otp_array_write(NPCM7xxOTPState *s, const void *data, + unsigned int offset, unsigned int len) +{ + const uint8_t *src = data; + uint8_t *dst = &s->array[offset]; + + while (len-- > 0) { + uint8_t c = *src++; + + *dst++ = ecc_encode_nibble(extract8(c, 0, 4)); + *dst++ = ecc_encode_nibble(extract8(c, 4, 4)); + } +} + +/* Common register read handler for both OTP classes. */ +static uint64_t npcm7xx_otp_read(NPCM7xxOTPState *s, NPCM7xxOTPRegister reg) +{ + uint32_t value = 0; + + switch (reg) { + case NPCM7XX_OTP_FST: + case NPCM7XX_OTP_FADDR: + case NPCM7XX_OTP_FDATA: + case NPCM7XX_OTP_FCFG: + value = s->regs[reg]; + break; + + case NPCM7XX_OTP_FCTL: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: read from write-only FCTL register\n", + DEVICE(s)->canonical_path); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: read from invalid offset 0x%zx\n", + DEVICE(s)->canonical_path, reg * sizeof(uint32_t)); + break; + } + + return value; +} + +/* Read a byte from the OTP array into the data register. */ +static void npcm7xx_otp_read_array(NPCM7xxOTPState *s) +{ + uint32_t faddr = s->regs[NPCM7XX_OTP_FADDR]; + + s->regs[NPCM7XX_OTP_FDATA] = s->array[FADDR_BYTEADDR(faddr)]; + s->regs[NPCM7XX_OTP_FST] |= FST_RDST | FST_RDY; +} + +/* Program a byte from the data register into the OTP array. */ +static void npcm7xx_otp_program_array(NPCM7xxOTPState *s) +{ + uint32_t faddr = s->regs[NPCM7XX_OTP_FADDR]; + + /* Bits can only go 0->1, never 1->0. */ + s->array[FADDR_BYTEADDR(faddr)] |= (1U << FADDR_BITPOS(faddr)); + s->regs[NPCM7XX_OTP_FST] |= FST_RDST | FST_RDY; +} + +/* Compute the next value of the FCFG register. */ +static uint32_t npcm7xx_otp_compute_fcfg(uint32_t cur_value, uint32_t new_value) +{ + uint32_t lock_mask; + uint32_t value; + + /* + * FCFGLK holds sticky bits 16..23, indicating which bits in FPRGLK (8..15) + * and FRDLK (0..7) that are read-only. + */ + lock_mask = (cur_value & FCFG_FCFGLK_MASK) >> 8; + lock_mask |= lock_mask >> 8; + /* FDIS and FCFGLK bits are sticky (write 1 to set; can't clear). */ + value = cur_value & (FCFG_FDIS | FCFG_FCFGLK_MASK); + /* Preserve read-only bits in FPRGLK and FRDLK */ + value |= cur_value & lock_mask; + /* Set all bits that aren't read-only. */ + value |= new_value & ~lock_mask; + + return value; +} + +/* Common register write handler for both OTP classes. */ +static void npcm7xx_otp_write(NPCM7xxOTPState *s, NPCM7xxOTPRegister reg, + uint32_t value) +{ + switch (reg) { + case NPCM7XX_OTP_FST: + /* RDST is cleared by writing 1 to it. */ + if (value & FST_RDST) { + s->regs[NPCM7XX_OTP_FST] &= ~FST_RDST; + } + /* Preserve read-only and write-one-to-clear bits */ + value &= ~FST_RO_MASK; + value |= s->regs[NPCM7XX_OTP_FST] & FST_RO_MASK; + break; + + case NPCM7XX_OTP_FADDR: + break; + + case NPCM7XX_OTP_FDATA: + /* + * This register is cleared by writing a magic value to it; no other + * values can be written. + */ + if (value == FDATA_CLEAR) { + value = 0; + } else { + value = s->regs[NPCM7XX_OTP_FDATA]; + } + break; + + case NPCM7XX_OTP_FCFG: + value = npcm7xx_otp_compute_fcfg(s->regs[NPCM7XX_OTP_FCFG], value); + break; + + case NPCM7XX_OTP_FCTL: + switch (value) { + case FCTL_READ_CMD: + npcm7xx_otp_read_array(s); + break; + + case FCTL_PROG_CMD1: + /* + * Programming requires writing two separate magic values to this + * register; this is the first one. Just store it so it can be + * verified later when the second magic value is received. + */ + break; + + case FCTL_PROG_CMD2: + /* + * Only initiate programming if we received the first half of the + * command immediately before this one. + */ + if (s->regs[NPCM7XX_OTP_FCTL] == FCTL_PROG_CMD1) { + npcm7xx_otp_program_array(s); + } + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: unrecognized FCNTL value 0x%" PRIx32 "\n", + DEVICE(s)->canonical_path, value); + break; + } + if (value != FCTL_PROG_CMD1) { + value = 0; + } + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: write to invalid offset 0x%zx\n", + DEVICE(s)->canonical_path, reg * sizeof(uint32_t)); + return; + } + + s->regs[reg] = value; +} + +/* Register read handler specific to the fuse array OTP module. */ +static uint64_t npcm7xx_fuse_array_read(void *opaque, hwaddr addr, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + uint32_t value; + + /* + * Only the Fuse Strap register needs special handling; all other registers + * work the same way for both kinds of OTP modules. + */ + if (reg != NPCM7XX_OTP_FUSTRAP) { + value = npcm7xx_otp_read(s, reg); + } else { + /* FUSTRAP is stored as three copies in the OTP array. */ + uint32_t fustrap[3]; + + memcpy(fustrap, &s->array[0], sizeof(fustrap)); + + /* Determine value by a majority vote on each bit. */ + value = (fustrap[0] & fustrap[1]) | (fustrap[0] & fustrap[2]) | + (fustrap[1] & fustrap[2]); + } + + return value; +} + +/* Register write handler specific to the fuse array OTP module. */ +static void npcm7xx_fuse_array_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + + /* + * The Fuse Strap register is read-only. Other registers are handled by + * common code. + */ + if (reg != NPCM7XX_OTP_FUSTRAP) { + npcm7xx_otp_write(s, reg, v); + } +} + +static const MemoryRegionOps npcm7xx_fuse_array_ops = { + .read = npcm7xx_fuse_array_read, + .write = npcm7xx_fuse_array_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +/* Register read handler specific to the key storage OTP module. */ +static uint64_t npcm7xx_key_storage_read(void *opaque, hwaddr addr, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + + /* + * Only the Fuse Key Index register needs special handling; all other + * registers work the same way for both kinds of OTP modules. + */ + if (reg != NPCM7XX_OTP_FKEYIND) { + return npcm7xx_otp_read(s, reg); + } + + qemu_log_mask(LOG_UNIMP, "%s: FKEYIND is not implemented\n", __func__); + + return s->regs[NPCM7XX_OTP_FKEYIND]; +} + +/* Register write handler specific to the key storage OTP module. */ +static void npcm7xx_key_storage_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + + /* + * Only the Fuse Key Index register needs special handling; all other + * registers work the same way for both kinds of OTP modules. + */ + if (reg != NPCM7XX_OTP_FKEYIND) { + npcm7xx_otp_write(s, reg, v); + return; + } + + qemu_log_mask(LOG_UNIMP, "%s: FKEYIND is not implemented\n", __func__); + + s->regs[NPCM7XX_OTP_FKEYIND] = v; +} + +static const MemoryRegionOps npcm7xx_key_storage_ops = { + .read = npcm7xx_key_storage_read, + .write = npcm7xx_key_storage_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_otp_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxOTPState *s = NPCM7XX_OTP(obj); + + memset(s->regs, 0, sizeof(s->regs)); + + s->regs[NPCM7XX_OTP_FST] = 0x00000001; + s->regs[NPCM7XX_OTP_FCFG] = 0x20000000; +} + +static void npcm7xx_otp_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxOTPClass *oc = NPCM7XX_OTP_GET_CLASS(dev); + NPCM7xxOTPState *s = NPCM7XX_OTP(dev); + SysBusDevice *sbd = &s->parent; + + memset(s->array, 0, sizeof(s->array)); + + memory_region_init_io(&s->mmio, OBJECT(s), oc->mmio_ops, s, "regs", + NPCM7XX_OTP_REGS_SIZE); + sysbus_init_mmio(sbd, &s->mmio); +} + +static const VMStateDescription vmstate_npcm7xx_otp = { + .name = "npcm7xx-otp", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxOTPState, NPCM7XX_OTP_NR_REGS), + VMSTATE_UINT8_ARRAY(array, NPCM7xxOTPState, NPCM7XX_OTP_ARRAY_BYTES), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_otp_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_OTP_REGS_END > NPCM7XX_OTP_NR_REGS); + + dc->realize = npcm7xx_otp_realize; + dc->vmsd = &vmstate_npcm7xx_otp; + rc->phases.enter = npcm7xx_otp_enter_reset; +} + +static void npcm7xx_key_storage_class_init(ObjectClass *klass, void *data) +{ + NPCM7xxOTPClass *oc = NPCM7XX_OTP_CLASS(klass); + + oc->mmio_ops = &npcm7xx_key_storage_ops; +} + +static void npcm7xx_fuse_array_class_init(ObjectClass *klass, void *data) +{ + NPCM7xxOTPClass *oc = NPCM7XX_OTP_CLASS(klass); + + oc->mmio_ops = &npcm7xx_fuse_array_ops; +} + +static const TypeInfo npcm7xx_otp_types[] = { + { + .name = TYPE_NPCM7XX_OTP, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxOTPState), + .class_size = sizeof(NPCM7xxOTPClass), + .class_init = npcm7xx_otp_class_init, + .abstract = true, + }, + { + .name = TYPE_NPCM7XX_KEY_STORAGE, + .parent = TYPE_NPCM7XX_OTP, + .class_init = npcm7xx_key_storage_class_init, + }, + { + .name = TYPE_NPCM7XX_FUSE_ARRAY, + .parent = TYPE_NPCM7XX_OTP, + .class_init = npcm7xx_fuse_array_class_init, + }, +}; +DEFINE_TYPES(npcm7xx_otp_types); diff --git a/hw/nvram/meson.build b/hw/nvram/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/meson.build +++ b/hw/nvram/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_DS1225Y', if_true: files('ds1225y.c')) softmmu_ss.add(when: 'CONFIG_NMC93XX_EEPROM', if_true: files('eeprom93xx.c')) softmmu_ss.add(when: 'CONFIG_AT24C', if_true: files('eeprom_at24c.c')) softmmu_ss.add(when: 'CONFIG_MAC_NVRAM', if_true: files('mac_nvram.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_otp.c')) softmmu_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_nvm.c')) specific_ss.add(when: 'CONFIG_PSERIES', if_true: files('spapr_nvram.c')) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This just implements the bare minimum to cause the boot block to skip memory initialization. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-10-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 2 + include/hw/mem/npcm7xx_mc.h | 36 ++++++++++++++++ hw/arm/npcm7xx.c | 6 +++ hw/mem/npcm7xx_mc.c | 84 +++++++++++++++++++++++++++++++++++++ hw/mem/meson.build | 1 + 5 files changed, 129 insertions(+) create mode 100644 include/hw/mem/npcm7xx_mc.h create mode 100644 hw/mem/npcm7xx_mc.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/cpu/a9mpcore.h" +#include "hw/mem/npcm7xx_mc.h" #include "hw/misc/npcm7xx_clk.h" #include "hw/misc/npcm7xx_gcr.h" #include "hw/nvram/npcm7xx_otp.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxTimerCtrlState tim[3]; NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; + NPCM7xxMCState mc; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/include/hw/mem/npcm7xx_mc.h b/include/hw/mem/npcm7xx_mc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/mem/npcm7xx_mc.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Memory Controller stub + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_MC_H +#define NPCM7XX_MC_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/** + * struct NPCM7xxMCState - Device state for the memory controller. + * @parent: System bus device. + * @mmio: Memory region through which registers are accessed. + */ +typedef struct NPCM7xxMCState { + SysBusDevice parent; + + MemoryRegion mmio; +} NPCM7xxMCState; + +#define TYPE_NPCM7XX_MC "npcm7xx-mc" +#define NPCM7XX_MC(obj) OBJECT_CHECK(NPCM7xxMCState, (obj), TYPE_NPCM7XX_MC) + +#endif /* NPCM7XX_MC_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_CPUP_BA (0xf03fe000) #define NPCM7XX_GCR_BA (0xf0800000) #define NPCM7XX_CLK_BA (0xf0801000) +#define NPCM7XX_MC_BA (0xf0824000) /* Internal AHB SRAM */ #define NPCM7XX_RAM3_BA (0xc0008000) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) TYPE_NPCM7XX_KEY_STORAGE); object_initialize_child(obj, "otp2", &s->fuse_array, TYPE_NPCM7XX_FUSE_ARRAY); + object_initialize_child(obj, "mc", &s->mc, TYPE_NPCM7XX_MC); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->fuse_array), 0, NPCM7XX_OTP2_BA); npcm7xx_init_fuses(s); + /* Fake Memory Controller (MC). Cannot fail. */ + sysbus_realize(SYS_BUS_DEVICE(&s->mc), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mc), 0, NPCM7XX_MC_BA); + /* Timer Modules (TIM). Cannot fail. */ QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { diff --git a/hw/mem/npcm7xx_mc.c b/hw/mem/npcm7xx_mc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/mem/npcm7xx_mc.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Memory Controller stub + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "hw/mem/npcm7xx_mc.h" +#include "qapi/error.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +#define NPCM7XX_MC_REGS_SIZE (4 * KiB) + +static uint64_t npcm7xx_mc_read(void *opaque, hwaddr addr, unsigned int size) +{ + /* + * If bits 8..11 @ offset 0 are not zero, the boot block thinks the memory + * controller has already been initialized and will skip DDR training. + */ + if (addr == 0) { + return 0x100; + } + + qemu_log_mask(LOG_UNIMP, "%s: mostly unimplemented\n", __func__); + + return 0; +} + +static void npcm7xx_mc_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + qemu_log_mask(LOG_UNIMP, "%s: mostly unimplemented\n", __func__); +} + +static const MemoryRegionOps npcm7xx_mc_ops = { + .read = npcm7xx_mc_read, + .write = npcm7xx_mc_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_mc_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxMCState *s = NPCM7XX_MC(dev); + + memory_region_init_io(&s->mmio, OBJECT(s), &npcm7xx_mc_ops, s, "regs", + NPCM7XX_MC_REGS_SIZE); + sysbus_init_mmio(&s->parent, &s->mmio); +} + +static void npcm7xx_mc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx Memory Controller stub"; + dc->realize = npcm7xx_mc_realize; +} + +static const TypeInfo npcm7xx_mc_types[] = { + { + .name = TYPE_NPCM7XX_MC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxMCState), + .class_init = npcm7xx_mc_class_init, + }, +}; +DEFINE_TYPES(npcm7xx_mc_types); diff --git a/hw/mem/meson.build b/hw/mem/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/mem/meson.build +++ b/hw/mem/meson.build @@ -XXX,XX +XXX,XX @@ mem_ss = ss.source_set() mem_ss.add(files('memory-device.c')) mem_ss.add(when: 'CONFIG_DIMM', if_true: files('pc-dimm.c')) +mem_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_mc.c')) mem_ss.add(when: 'CONFIG_NVDIMM', if_true: files('nvdimm.c')) softmmu_ss.add_all(when: 'CONFIG_MEM_DEVICE', if_true: mem_ss) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This implements a device model for the NPCM7xx SPI flash controller. Direct reads and writes, and user-mode transactions have been tested in various modes. Protection features are not implemented yet. All the FIU instances are available in the SoC's address space, regardless of whether or not they're connected to actual flash chips. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-11-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 2 + include/hw/ssi/npcm7xx_fiu.h | 73 +++++ hw/arm/npcm7xx.c | 58 ++++ hw/ssi/npcm7xx_fiu.c | 572 +++++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/ssi/meson.build | 1 + hw/ssi/trace-events | 11 + 7 files changed, 718 insertions(+) create mode 100644 include/hw/ssi/npcm7xx_fiu.h create mode 100644 hw/ssi/npcm7xx_fiu.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/npcm7xx_gcr.h" #include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" +#include "hw/ssi/npcm7xx_fiu.h" #include "target/arm/cpu.h" #define NPCM7XX_MAX_NUM_CPUS (2) @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; NPCM7xxMCState mc; + NPCM7xxFIUState fiu[2]; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/include/hw/ssi/npcm7xx_fiu.h b/include/hw/ssi/npcm7xx_fiu.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/ssi/npcm7xx_fiu.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Flash Interface Unit (FIU) + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ +#ifndef NPCM7XX_FIU_H +#define NPCM7XX_FIU_H + +#include "hw/ssi/ssi.h" +#include "hw/sysbus.h" + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_FIU_NR_REGS (0x7c / sizeof(uint32_t)) + +typedef struct NPCM7xxFIUState NPCM7xxFIUState; + +/** + * struct NPCM7xxFIUFlash - Per-chipselect flash controller state. + * @direct_access: Memory region for direct flash access. + * @fiu: Pointer to flash controller shared state. + */ +typedef struct NPCM7xxFIUFlash { + MemoryRegion direct_access; + NPCM7xxFIUState *fiu; +} NPCM7xxFIUFlash; + +/** + * NPCM7xxFIUState - Device state for one Flash Interface Unit. + * @parent: System bus device. + * @mmio: Memory region for register access. + * @cs_count: Number of flash chips that may be connected to this module. + * @active_cs: Currently active chip select, or -1 if no chip is selected. + * @cs_lines: GPIO lines that may be wired to flash chips. + * @flash: Array of @cs_count per-flash-chip state objects. + * @spi: The SPI bus mastered by this controller. + * @regs: Register contents. + * + * Each FIU has a shared bank of registers, and controls up to four chip + * selects. Each chip select has a dedicated memory region which may be used to + * read and write the flash connected to that chip select as if it were memory. + */ +struct NPCM7xxFIUState { + SysBusDevice parent; + + MemoryRegion mmio; + + int32_t cs_count; + int32_t active_cs; + qemu_irq *cs_lines; + NPCM7xxFIUFlash *flash; + + SSIBus *spi; + + uint32_t regs[NPCM7XX_FIU_NR_REGS]; +}; + +#define TYPE_NPCM7XX_FIU "npcm7xx-fiu" +#define NPCM7XX_FIU(obj) OBJECT_CHECK(NPCM7xxFIUState, (obj), TYPE_NPCM7XX_FIU) + +#endif /* NPCM7XX_FIU_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ static const hwaddr npcm7xx_uart_addr[] = { 0xf0004000, }; +/* Direct memory-mapped access to SPI0 CS0-1. */ +static const hwaddr npcm7xx_fiu0_flash_addr[] = { + 0x80000000, /* CS0 */ + 0x88000000, /* CS1 */ +}; + +/* Direct memory-mapped access to SPI3 CS0-3. */ +static const hwaddr npcm7xx_fiu3_flash_addr[] = { + 0xa0000000, /* CS0 */ + 0xa8000000, /* CS1 */ + 0xb0000000, /* CS2 */ + 0xb8000000, /* CS3 */ +}; + +static const struct { + const char *name; + hwaddr regs_addr; + int cs_count; + const hwaddr *flash_addr; +} npcm7xx_fiu[] = { + { + .name = "fiu0", + .regs_addr = 0xfb000000, + .cs_count = ARRAY_SIZE(npcm7xx_fiu0_flash_addr), + .flash_addr = npcm7xx_fiu0_flash_addr, + }, { + .name = "fiu3", + .regs_addr = 0xc0000000, + .cs_count = ARRAY_SIZE(npcm7xx_fiu3_flash_addr), + .flash_addr = npcm7xx_fiu3_flash_addr, + }, +}; + static void npcm7xx_write_secondary_boot(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); } + + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_fiu) != ARRAY_SIZE(s->fiu)); + for (i = 0; i < ARRAY_SIZE(s->fiu); i++) { + object_initialize_child(obj, npcm7xx_fiu[i].name, &s->fiu[i], + TYPE_NPCM7XX_FIU); + } } static void npcm7xx_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) serial_hd(i), DEVICE_LITTLE_ENDIAN); } + /* + * Flash Interface Unit (FIU). Can fail if incorrect number of chip selects + * specified, but this is a programming error. + */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_fiu) != ARRAY_SIZE(s->fiu)); + for (i = 0; i < ARRAY_SIZE(s->fiu); i++) { + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->fiu[i]); + int j; + + object_property_set_int(OBJECT(sbd), "cs-count", + npcm7xx_fiu[i].cs_count, &error_abort); + sysbus_realize(sbd, &error_abort); + + sysbus_mmio_map(sbd, 0, npcm7xx_fiu[i].regs_addr); + for (j = 0; j < npcm7xx_fiu[i].cs_count; j++) { + sysbus_mmio_map(sbd, j + 1, npcm7xx_fiu[i].flash_addr[j]); + } + } + /* RAM2 (SRAM) */ memory_region_init_ram(&s->sram, OBJECT(dev), "ram2", NPCM7XX_RAM2_SZ, &error_abort); diff --git a/hw/ssi/npcm7xx_fiu.c b/hw/ssi/npcm7xx_fiu.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/ssi/npcm7xx_fiu.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Flash Interface Unit (FIU) + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" + +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "hw/ssi/npcm7xx_fiu.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +#include "trace.h" + +/* Up to 128 MiB of flash may be accessed directly as memory. */ +#define NPCM7XX_FIU_FLASH_WINDOW_SIZE (128 * MiB) + +/* Each module has 4 KiB of register space. Only a fraction of it is used. */ +#define NPCM7XX_FIU_CTRL_REGS_SIZE (4 * KiB) + +/* 32-bit FIU register indices. */ +enum NPCM7xxFIURegister { + NPCM7XX_FIU_DRD_CFG, + NPCM7XX_FIU_DWR_CFG, + NPCM7XX_FIU_UMA_CFG, + NPCM7XX_FIU_UMA_CTS, + NPCM7XX_FIU_UMA_CMD, + NPCM7XX_FIU_UMA_ADDR, + NPCM7XX_FIU_PRT_CFG, + NPCM7XX_FIU_UMA_DW0 = 0x0020 / sizeof(uint32_t), + NPCM7XX_FIU_UMA_DW1, + NPCM7XX_FIU_UMA_DW2, + NPCM7XX_FIU_UMA_DW3, + NPCM7XX_FIU_UMA_DR0, + NPCM7XX_FIU_UMA_DR1, + NPCM7XX_FIU_UMA_DR2, + NPCM7XX_FIU_UMA_DR3, + NPCM7XX_FIU_PRT_CMD0, + NPCM7XX_FIU_PRT_CMD1, + NPCM7XX_FIU_PRT_CMD2, + NPCM7XX_FIU_PRT_CMD3, + NPCM7XX_FIU_PRT_CMD4, + NPCM7XX_FIU_PRT_CMD5, + NPCM7XX_FIU_PRT_CMD6, + NPCM7XX_FIU_PRT_CMD7, + NPCM7XX_FIU_PRT_CMD8, + NPCM7XX_FIU_PRT_CMD9, + NPCM7XX_FIU_CFG = 0x78 / sizeof(uint32_t), + NPCM7XX_FIU_REGS_END, +}; + +/* FIU_{DRD,DWR,UMA,PTR}_CFG cannot be written when this bit is set. */ +#define NPCM7XX_FIU_CFG_LCK BIT(31) + +/* Direct Read configuration register fields. */ +#define FIU_DRD_CFG_ADDSIZ(rv) extract32(rv, 16, 2) +#define FIU_ADDSIZ_3BYTES 0 +#define FIU_ADDSIZ_4BYTES 1 +#define FIU_DRD_CFG_DBW(rv) extract32(rv, 12, 2) +#define FIU_DRD_CFG_ACCTYPE(rv) extract32(rv, 8, 2) +#define FIU_DRD_CFG_RDCMD(rv) extract32(rv, 0, 8) + +/* Direct Write configuration register fields. */ +#define FIU_DWR_CFG_ADDSIZ(rv) extract32(rv, 16, 2) +#define FIU_DWR_CFG_WRCMD(rv) extract32(rv, 0, 8) + +/* User-Mode Access register fields. */ + +/* Command Mode Lock and the bits protected by it. */ +#define FIU_UMA_CFG_CMMLCK BIT(30) +#define FIU_UMA_CFG_CMMLCK_MASK 0x00000403 + +#define FIU_UMA_CFG_RDATSIZ(rv) extract32(rv, 24, 5) +#define FIU_UMA_CFG_DBSIZ(rv) extract32(rv, 21, 3) +#define FIU_UMA_CFG_WDATSIZ(rv) extract32(rv, 16, 5) +#define FIU_UMA_CFG_ADDSIZ(rv) extract32(rv, 11, 3) +#define FIU_UMA_CFG_CMDSIZ(rv) extract32(rv, 10, 1) +#define FIU_UMA_CFG_DBPCK(rv) extract32(rv, 6, 2) + +#define FIU_UMA_CTS_RDYIE BIT(25) +#define FIU_UMA_CTS_RDYST BIT(24) +#define FIU_UMA_CTS_SW_CS BIT(16) +#define FIU_UMA_CTS_DEV_NUM(rv) extract32(rv, 8, 2) +#define FIU_UMA_CTS_EXEC_DONE BIT(0) + +/* + * Returns the index of flash in the fiu->flash array. This corresponds to the + * chip select ID of the flash. + */ +static int npcm7xx_fiu_cs_index(NPCM7xxFIUState *fiu, NPCM7xxFIUFlash *flash) +{ + int index = flash - fiu->flash; + + g_assert(index >= 0 && index < fiu->cs_count); + + return index; +} + +/* Assert the chip select specified in the UMA Control/Status Register. */ +static void npcm7xx_fiu_select(NPCM7xxFIUState *s, int cs_id) +{ + trace_npcm7xx_fiu_select(DEVICE(s)->canonical_path, cs_id); + + if (cs_id < s->cs_count) { + qemu_irq_lower(s->cs_lines[cs_id]); + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: UMA to CS%d; this module has only %d chip selects", + DEVICE(s)->canonical_path, cs_id, s->cs_count); + cs_id = -1; + } + + s->active_cs = cs_id; +} + +/* Deassert the currently active chip select. */ +static void npcm7xx_fiu_deselect(NPCM7xxFIUState *s) +{ + if (s->active_cs < 0) { + return; + } + + trace_npcm7xx_fiu_deselect(DEVICE(s)->canonical_path, s->active_cs); + + qemu_irq_raise(s->cs_lines[s->active_cs]); + s->active_cs = -1; +} + +/* Direct flash memory read handler. */ +static uint64_t npcm7xx_fiu_flash_read(void *opaque, hwaddr addr, + unsigned int size) +{ + NPCM7xxFIUFlash *f = opaque; + NPCM7xxFIUState *fiu = f->fiu; + uint64_t value = 0; + uint32_t drd_cfg; + int dummy_cycles; + int i; + + if (fiu->active_cs != -1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: direct flash read with CS%d already active", + DEVICE(fiu)->canonical_path, fiu->active_cs); + } + + npcm7xx_fiu_select(fiu, npcm7xx_fiu_cs_index(fiu, f)); + + drd_cfg = fiu->regs[NPCM7XX_FIU_DRD_CFG]; + ssi_transfer(fiu->spi, FIU_DRD_CFG_RDCMD(drd_cfg)); + + switch (FIU_DRD_CFG_ADDSIZ(drd_cfg)) { + case FIU_ADDSIZ_4BYTES: + ssi_transfer(fiu->spi, extract32(addr, 24, 8)); + /* fall through */ + case FIU_ADDSIZ_3BYTES: + ssi_transfer(fiu->spi, extract32(addr, 16, 8)); + ssi_transfer(fiu->spi, extract32(addr, 8, 8)); + ssi_transfer(fiu->spi, extract32(addr, 0, 8)); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: bad address size %d\n", + DEVICE(fiu)->canonical_path, FIU_DRD_CFG_ADDSIZ(drd_cfg)); + break; + } + + /* Flash chip model expects one transfer per dummy bit, not byte */ + dummy_cycles = + (FIU_DRD_CFG_DBW(drd_cfg) * 8) >> FIU_DRD_CFG_ACCTYPE(drd_cfg); + for (i = 0; i < dummy_cycles; i++) { + ssi_transfer(fiu->spi, 0); + } + + for (i = 0; i < size; i++) { + value = deposit64(value, 8 * i, 8, ssi_transfer(fiu->spi, 0)); + } + + trace_npcm7xx_fiu_flash_read(DEVICE(fiu)->canonical_path, fiu->active_cs, + addr, size, value); + + npcm7xx_fiu_deselect(fiu); + + return value; +} + +/* Direct flash memory write handler. */ +static void npcm7xx_fiu_flash_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + NPCM7xxFIUFlash *f = opaque; + NPCM7xxFIUState *fiu = f->fiu; + uint32_t dwr_cfg; + int cs_id; + int i; + + if (fiu->active_cs != -1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: direct flash write with CS%d already active", + DEVICE(fiu)->canonical_path, fiu->active_cs); + } + + cs_id = npcm7xx_fiu_cs_index(fiu, f); + trace_npcm7xx_fiu_flash_write(DEVICE(fiu)->canonical_path, cs_id, addr, + size, v); + npcm7xx_fiu_select(fiu, cs_id); + + dwr_cfg = fiu->regs[NPCM7XX_FIU_DWR_CFG]; + ssi_transfer(fiu->spi, FIU_DWR_CFG_WRCMD(dwr_cfg)); + + switch (FIU_DWR_CFG_ADDSIZ(dwr_cfg)) { + case FIU_ADDSIZ_4BYTES: + ssi_transfer(fiu->spi, extract32(addr, 24, 8)); + /* fall through */ + case FIU_ADDSIZ_3BYTES: + ssi_transfer(fiu->spi, extract32(addr, 16, 8)); + ssi_transfer(fiu->spi, extract32(addr, 8, 8)); + ssi_transfer(fiu->spi, extract32(addr, 0, 8)); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: bad address size %d\n", + DEVICE(fiu)->canonical_path, FIU_DWR_CFG_ADDSIZ(dwr_cfg)); + break; + } + + for (i = 0; i < size; i++) { + ssi_transfer(fiu->spi, extract64(v, i * 8, 8)); + } + + npcm7xx_fiu_deselect(fiu); +} + +static const MemoryRegionOps npcm7xx_fiu_flash_ops = { + .read = npcm7xx_fiu_flash_read, + .write = npcm7xx_fiu_flash_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 8, + .unaligned = true, + }, +}; + +/* Control register read handler. */ +static uint64_t npcm7xx_fiu_ctrl_read(void *opaque, hwaddr addr, + unsigned int size) +{ + hwaddr reg = addr / sizeof(uint32_t); + NPCM7xxFIUState *s = opaque; + uint32_t value; + + if (reg < NPCM7XX_FIU_NR_REGS) { + value = s->regs[reg]; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: read from invalid offset 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + value = 0; + } + + trace_npcm7xx_fiu_ctrl_read(DEVICE(s)->canonical_path, addr, value); + + return value; +} + +/* Send the specified number of address bytes from the UMA address register. */ +static void send_address(SSIBus *spi, unsigned int addsiz, uint32_t addr) +{ + switch (addsiz) { + case 4: + ssi_transfer(spi, extract32(addr, 24, 8)); + /* fall through */ + case 3: + ssi_transfer(spi, extract32(addr, 16, 8)); + /* fall through */ + case 2: + ssi_transfer(spi, extract32(addr, 8, 8)); + /* fall through */ + case 1: + ssi_transfer(spi, extract32(addr, 0, 8)); + /* fall through */ + case 0: + break; + } +} + +/* Send the number of dummy bits specified in the UMA config register. */ +static void send_dummy_bits(SSIBus *spi, uint32_t uma_cfg, uint32_t uma_cmd) +{ + unsigned int bits_per_clock = 1U << FIU_UMA_CFG_DBPCK(uma_cfg); + unsigned int i; + + for (i = 0; i < FIU_UMA_CFG_DBSIZ(uma_cfg); i++) { + /* Use bytes 0 and 1 first, then keep repeating byte 2 */ + unsigned int field = (i < 2) ? ((i + 1) * 8) : 24; + unsigned int j; + + for (j = 0; j < 8; j += bits_per_clock) { + ssi_transfer(spi, extract32(uma_cmd, field + j, bits_per_clock)); + } + } +} + +/* Perform a User-Mode Access transaction. */ +static void npcm7xx_fiu_uma_transaction(NPCM7xxFIUState *s) +{ + uint32_t uma_cts = s->regs[NPCM7XX_FIU_UMA_CTS]; + uint32_t uma_cfg; + unsigned int i; + + /* SW_CS means the CS is already forced low, so don't touch it. */ + if (uma_cts & FIU_UMA_CTS_SW_CS) { + int cs_id = FIU_UMA_CTS_DEV_NUM(s->regs[NPCM7XX_FIU_UMA_CTS]); + npcm7xx_fiu_select(s, cs_id); + } + + /* Send command, if present. */ + uma_cfg = s->regs[NPCM7XX_FIU_UMA_CFG]; + if (FIU_UMA_CFG_CMDSIZ(uma_cfg) > 0) { + ssi_transfer(s->spi, extract32(s->regs[NPCM7XX_FIU_UMA_CMD], 0, 8)); + } + + /* Send address, if present. */ + send_address(s->spi, FIU_UMA_CFG_ADDSIZ(uma_cfg), + s->regs[NPCM7XX_FIU_UMA_ADDR]); + + /* Write data, if present. */ + for (i = 0; i < FIU_UMA_CFG_WDATSIZ(uma_cfg); i++) { + unsigned int reg = + (i < 16) ? (NPCM7XX_FIU_UMA_DW0 + i / 4) : NPCM7XX_FIU_UMA_DW3; + unsigned int field = (i % 4) * 8; + + ssi_transfer(s->spi, extract32(s->regs[reg], field, 8)); + } + + /* Send dummy bits, if present. */ + send_dummy_bits(s->spi, uma_cfg, s->regs[NPCM7XX_FIU_UMA_CMD]); + + /* Read data, if present. */ + for (i = 0; i < FIU_UMA_CFG_RDATSIZ(uma_cfg); i++) { + unsigned int reg = NPCM7XX_FIU_UMA_DR0 + i / 4; + unsigned int field = (i % 4) * 8; + uint8_t c; + + c = ssi_transfer(s->spi, 0); + if (reg <= NPCM7XX_FIU_UMA_DR3) { + s->regs[reg] = deposit32(s->regs[reg], field, 8, c); + } + } + + /* Again, don't touch CS if the user is forcing it low. */ + if (uma_cts & FIU_UMA_CTS_SW_CS) { + npcm7xx_fiu_deselect(s); + } + + /* RDYST means a command has completed since it was cleared. */ + s->regs[NPCM7XX_FIU_UMA_CTS] |= FIU_UMA_CTS_RDYST; + /* EXEC_DONE means Execute Command / Not Done, so clear it here. */ + s->regs[NPCM7XX_FIU_UMA_CTS] &= ~FIU_UMA_CTS_EXEC_DONE; +} + +/* Control register write handler. */ +static void npcm7xx_fiu_ctrl_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + hwaddr reg = addr / sizeof(uint32_t); + NPCM7xxFIUState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_fiu_ctrl_write(DEVICE(s)->canonical_path, addr, value); + + switch (reg) { + case NPCM7XX_FIU_UMA_CFG: + if (s->regs[reg] & FIU_UMA_CFG_CMMLCK) { + value &= ~FIU_UMA_CFG_CMMLCK_MASK; + value |= (s->regs[reg] & FIU_UMA_CFG_CMMLCK_MASK); + } + /* fall through */ + case NPCM7XX_FIU_DRD_CFG: + case NPCM7XX_FIU_DWR_CFG: + if (s->regs[reg] & NPCM7XX_FIU_CFG_LCK) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to locked register @ 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + return; + } + s->regs[reg] = value; + break; + + case NPCM7XX_FIU_UMA_CTS: + if (value & FIU_UMA_CTS_RDYST) { + value &= ~FIU_UMA_CTS_RDYST; + } else { + value |= s->regs[reg] & FIU_UMA_CTS_RDYST; + } + if ((s->regs[reg] ^ value) & FIU_UMA_CTS_SW_CS) { + if (value & FIU_UMA_CTS_SW_CS) { + /* + * Don't drop CS if there's a transfer in progress, or we're + * about to start one. + */ + if (!((value | s->regs[reg]) & FIU_UMA_CTS_EXEC_DONE)) { + npcm7xx_fiu_deselect(s); + } + } else { + int cs_id = FIU_UMA_CTS_DEV_NUM(s->regs[NPCM7XX_FIU_UMA_CTS]); + npcm7xx_fiu_select(s, cs_id); + } + } + s->regs[reg] = value | (s->regs[reg] & FIU_UMA_CTS_EXEC_DONE); + if (value & FIU_UMA_CTS_EXEC_DONE) { + npcm7xx_fiu_uma_transaction(s); + } + break; + + case NPCM7XX_FIU_UMA_DR0 ... NPCM7XX_FIU_UMA_DR3: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to read-only register @ 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + return; + + case NPCM7XX_FIU_PRT_CFG: + case NPCM7XX_FIU_PRT_CMD0 ... NPCM7XX_FIU_PRT_CMD9: + qemu_log_mask(LOG_UNIMP, "%s: PRT is not implemented\n", __func__); + break; + + case NPCM7XX_FIU_UMA_CMD: + case NPCM7XX_FIU_UMA_ADDR: + case NPCM7XX_FIU_UMA_DW0 ... NPCM7XX_FIU_UMA_DW3: + case NPCM7XX_FIU_CFG: + s->regs[reg] = value; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to invalid offset 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + return; + } +} + +static const MemoryRegionOps npcm7xx_fiu_ctrl_ops = { + .read = npcm7xx_fiu_ctrl_read, + .write = npcm7xx_fiu_ctrl_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_fiu_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxFIUState *s = NPCM7XX_FIU(obj); + + trace_npcm7xx_fiu_enter_reset(DEVICE(obj)->canonical_path, type); + + memset(s->regs, 0, sizeof(s->regs)); + + s->regs[NPCM7XX_FIU_DRD_CFG] = 0x0300100b; + s->regs[NPCM7XX_FIU_DWR_CFG] = 0x03000002; + s->regs[NPCM7XX_FIU_UMA_CFG] = 0x00000400; + s->regs[NPCM7XX_FIU_UMA_CTS] = 0x00010000; + s->regs[NPCM7XX_FIU_UMA_CMD] = 0x0000000b; + s->regs[NPCM7XX_FIU_PRT_CFG] = 0x00000400; + s->regs[NPCM7XX_FIU_CFG] = 0x0000000b; +} + +static void npcm7xx_fiu_hold_reset(Object *obj) +{ + NPCM7xxFIUState *s = NPCM7XX_FIU(obj); + int i; + + trace_npcm7xx_fiu_hold_reset(DEVICE(obj)->canonical_path); + + for (i = 0; i < s->cs_count; i++) { + qemu_irq_raise(s->cs_lines[i]); + } +} + +static void npcm7xx_fiu_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxFIUState *s = NPCM7XX_FIU(dev); + SysBusDevice *sbd = &s->parent; + int i; + + if (s->cs_count <= 0) { + error_setg(errp, "%s: %d chip selects specified, need at least one", + dev->canonical_path, s->cs_count); + return; + } + + s->spi = ssi_create_bus(dev, "spi"); + s->cs_lines = g_new0(qemu_irq, s->cs_count); + qdev_init_gpio_out_named(DEVICE(s), s->cs_lines, "cs", s->cs_count); + s->flash = g_new0(NPCM7xxFIUFlash, s->cs_count); + + /* + * Register the control registers region first. It may be followed by one + * or more direct flash access regions. + */ + memory_region_init_io(&s->mmio, OBJECT(s), &npcm7xx_fiu_ctrl_ops, s, "ctrl", + NPCM7XX_FIU_CTRL_REGS_SIZE); + sysbus_init_mmio(sbd, &s->mmio); + + for (i = 0; i < s->cs_count; i++) { + NPCM7xxFIUFlash *flash = &s->flash[i]; + flash->fiu = s; + memory_region_init_io(&flash->direct_access, OBJECT(s), + &npcm7xx_fiu_flash_ops, &s->flash[i], "flash", + NPCM7XX_FIU_FLASH_WINDOW_SIZE); + sysbus_init_mmio(sbd, &flash->direct_access); + } +} + +static const VMStateDescription vmstate_npcm7xx_fiu = { + .name = "npcm7xx-fiu", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_INT32(active_cs, NPCM7xxFIUState), + VMSTATE_UINT32_ARRAY(regs, NPCM7xxFIUState, NPCM7XX_FIU_NR_REGS), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_fiu_properties[] = { + DEFINE_PROP_INT32("cs-count", NPCM7xxFIUState, cs_count, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_fiu_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_FIU_REGS_END > NPCM7XX_FIU_NR_REGS); + + dc->desc = "NPCM7xx Flash Interface Unit"; + dc->realize = npcm7xx_fiu_realize; + dc->vmsd = &vmstate_npcm7xx_fiu; + rc->phases.enter = npcm7xx_fiu_enter_reset; + rc->phases.hold = npcm7xx_fiu_hold_reset; + device_class_set_props(dc, npcm7xx_fiu_properties); +} + +static const TypeInfo npcm7xx_fiu_types[] = { + { + .name = TYPE_NPCM7XX_FIU, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxFIUState), + .class_init = npcm7xx_fiu_class_init, + }, +}; +DEFINE_TYPES(npcm7xx_fiu_types); 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 NPCM7XX select ARM_GIC select PL310 # cache controller select SERIAL + select SSI select UNIMP config FSL_IMX25 diff --git a/hw/ssi/meson.build b/hw/ssi/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/meson.build +++ b/hw/ssi/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_ASPEED_SOC', if_true: files('aspeed_smc.c')) softmmu_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-spi.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_fiu.c')) softmmu_ss.add(when: 'CONFIG_PL022', if_true: files('pl022.c')) softmmu_ss.add(when: 'CONFIG_SSI', if_true: files('ssi.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_SPI', if_true: files('stm32f2xx_spi.c')) diff --git a/hw/ssi/trace-events b/hw/ssi/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/trace-events +++ b/hw/ssi/trace-events @@ -XXX,XX +XXX,XX @@ aspeed_smc_dma_checksum(uint32_t addr, uint32_t data) "0x%08x: 0x%08x" aspeed_smc_dma_rw(const char *dir, uint32_t flash_addr, uint32_t dram_addr, uint32_t size) "%s flash:@0x%08x dram:@0x%08x size:0x%08x" aspeed_smc_write(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 aspeed_smc_flash_select(int cs, const char *prefix) "CS%d %sselect" + +# npcm7xx_fiu.c + +npcm7xx_fiu_enter_reset(const char *id, int reset_type) "%s reset type: %d" +npcm7xx_fiu_hold_reset(const char *id) "%s" +npcm7xx_fiu_select(const char *id, int cs) "%s select CS%d" +npcm7xx_fiu_deselect(const char *id, int cs) "%s deselect CS%d" +npcm7xx_fiu_ctrl_read(const char *id, uint64_t addr, uint32_t data) "%s offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_fiu_ctrl_write(const char *id, uint64_t addr, uint32_t data) "%s offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_fiu_flash_read(const char *id, int cs, uint64_t addr, unsigned int size, uint64_t value) "%s[%d] offset: 0x%08" PRIx64 " size: %u value: 0x%" PRIx64 +npcm7xx_fiu_flash_write(const char *id, int cs, uint64_t addr, unsigned int size, uint64_t value) "%s[%d] offset: 0x%08" PRIx64 " size: %u value: 0x%" PRIx64 -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This allows these NPCM7xx-based boards to boot from a flash image, e.g. one built with OpenBMC. For example like this: IMAGE=${OPENBMC}/build/tmp/deploy/images/gsj/image-bmc qemu-system-arm -machine quanta-gsj -nographic \ -drive file=${IMAGE},if=mtd,bus=0,unit=0,format=raw,snapshot=on Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200911052101.2602693-12-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/npcm7xx.h" #include "hw/core/cpu.h" #include "hw/loader.h" +#include "hw/qdev-properties.h" #include "qapi/error.h" #include "qemu-common.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ static void npcm7xx_load_bootrom(MachineState *machine, NPCM7xxState *soc) } } +static void npcm7xx_connect_flash(NPCM7xxFIUState *fiu, int cs_no, + const char *flash_type, DriveInfo *dinfo) +{ + DeviceState *flash; + qemu_irq flash_cs; + + flash = qdev_new(flash_type); + if (dinfo) { + qdev_prop_set_drive(flash, "drive", blk_by_legacy_dinfo(dinfo)); + } + qdev_realize_and_unref(flash, BUS(fiu->spi), &error_fatal); + + flash_cs = qdev_get_gpio_in_named(flash, SSI_GPIO_CS, 0); + qdev_connect_gpio_out_named(DEVICE(fiu), "cs", cs_no, flash_cs); +} + static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) { memory_region_add_subregion(get_system_memory(), NPCM7XX_DRAM_BA, dram); @@ -XXX,XX +XXX,XX @@ static void npcm750_evb_init(MachineState *machine) qdev_realize(DEVICE(soc), NULL, &error_fatal); npcm7xx_load_bootrom(machine, soc); + npcm7xx_connect_flash(&soc->fiu[0], 0, "w25q256", drive_get(IF_MTD, 0, 0)); npcm7xx_load_kernel(machine, soc); } @@ -XXX,XX +XXX,XX @@ static void quanta_gsj_init(MachineState *machine) qdev_realize(DEVICE(soc), NULL, &error_fatal); npcm7xx_load_bootrom(machine, soc); + npcm7xx_connect_flash(&soc->fiu[0], 0, "mx25l25635e", + drive_get(IF_MTD, 0, 0)); npcm7xx_load_kernel(machine, soc); } -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> When booting directly into a kernel, bypassing the boot loader, the CPU and UART clocks are not set up correctly. This makes the system appear very slow, and causes the initrd boot test to fail when optimization is off. The UART clock must run at 24 MHz. The default 25 MHz reference clock cannot achieve this, so switch to PLL2/2 @ 480 MHz, which works perfectly with the default /20 divider. The CPU clock should run at 800 MHz, so switch it to PLL1/2. PLL1 runs at 800 MHz by default, so we need to double the feedback divider as well to make it run at 1600 MHz (so PLL1/2 runs at 800 MHz). We don't bother checking for PLL lock because we know our emulated PLLs lock instantly. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-13-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 1 + hw/arm/npcm7xx.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_SMP_LOADER_START (0xffff0000) /* Boot ROM */ #define NPCM7XX_SMP_BOOTREG_ADDR (0xf080013c) /* GCR.SCRPAD */ #define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ +#define NPCM7XX_BOARD_SETUP_ADDR (0xffff1000) /* Boot ROM */ typedef struct NPCM7xxMachine { MachineState parent; diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_ROM_BA (0xffff0000) #define NPCM7XX_ROM_SZ (64 * KiB) +/* Clock configuration values to be fixed up when bypassing bootloader */ + +/* Run PLL1 at 1600 MHz */ +#define NPCM7XX_PLLCON1_FIXUP_VAL (0x00402101) +/* Run the CPU from PLL1 and UART from PLL2 */ +#define NPCM7XX_CLKSEL_FIXUP_VAL (0x004aaba9) + /* * Interrupt lines going into the GIC. This does not include internal Cortex-A9 * interrupts. @@ -XXX,XX +XXX,XX @@ static const struct { }, }; +static void npcm7xx_write_board_setup(ARMCPU *cpu, + const struct arm_boot_info *info) +{ + uint32_t board_setup[] = { + 0xe59f0010, /* ldr r0, clk_base_addr */ + 0xe59f1010, /* ldr r1, pllcon1_value */ + 0xe5801010, /* str r1, [r0, #16] */ + 0xe59f100c, /* ldr r1, clksel_value */ + 0xe5801004, /* str r1, [r0, #4] */ + 0xe12fff1e, /* bx lr */ + NPCM7XX_CLK_BA, + NPCM7XX_PLLCON1_FIXUP_VAL, + NPCM7XX_CLKSEL_FIXUP_VAL, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(board_setup); i++) { + board_setup[i] = tswap32(board_setup[i]); + } + rom_add_blob_fixed("board-setup", board_setup, sizeof(board_setup), + info->board_setup_addr); +} + static void npcm7xx_write_secondary_boot(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info npcm7xx_binfo = { .gic_cpu_if_addr = NPCM7XX_GIC_CPU_IF_ADDR, .write_secondary_boot = npcm7xx_write_secondary_boot, .board_id = -1, + .board_setup_addr = NPCM7XX_BOARD_SETUP_ADDR, + .write_board_setup = npcm7xx_write_board_setup, }; void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-14-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 92 +++++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 1 + 2 files changed, 93 insertions(+) create mode 100644 docs/system/arm/nuvoton.rst diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ +Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) +===================================================== + +The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are +designed to be used as Baseboard Management Controllers (BMCs) in various +servers. They all feature one or two ARM Cortex A9 CPU cores, as well as an +assortment of peripherals targeted for either Enterprise or Data Center / +Hyperscale applications. The former is a superset of the latter, so NPCM750 has +all the peripherals of NPCM730 and more. + +.. _Nuvoton iBMC: https://www.nuvoton.com/products/cloud-computing/ibmc/ + +The NPCM750 SoC has two Cortex A9 cores and is targeted for the Enterprise +segment. The following machines are based on this chip : + +- ``npcm750-evb`` Nuvoton NPCM750 Evaluation board + +The NPCM730 SoC has two Cortex A9 cores and is targeted for Data Center and +Hyperscale applications. The following machines are based on this chip : + +- ``quanta-gsj`` Quanta GSJ server BMC + +There are also two more SoCs, NPCM710 and NPCM705, which are single-core +variants of NPCM750 and NPCM730, respectively. These are currently not +supported by QEMU. + +Supported devices +----------------- + + * SMP (Dual Core Cortex-A9) + * Cortex-A9MPCore built-in peripherals: SCU, GIC, Global Timer, Private Timer + and Watchdog. + * SRAM, ROM and DRAM mappings + * System Global Control Registers (GCR) + * Clock and reset controller (CLK) + * Timer controller (TIM) + * Serial ports (16550-based) + * DDR4 memory controller (dummy interface indicating memory training is done) + * OTP controllers (no protection features) + * Flash Interface Unit (FIU; no protection features) + +Missing devices +--------------- + + * GPIO controller + * LPC/eSPI host-to-BMC interface, including + + * Keyboard and mouse controller interface (KBCI) + * Keyboard Controller Style (KCS) channels + * BIOS POST code FIFO + * System Wake-up Control (SWC) + * Shared memory (SHM) + * eSPI slave interface + + * Ethernet controllers (GMAC and EMC) + * USB host (USBH) + * USB device (USBD) + * SMBus controller (SMBF) + * Peripheral SPI controller (PSPI) + * Analog to Digital Converter (ADC) + * SD/MMC host + * Random Number Generator (RNG) + * PECI interface + * Pulse Width Modulation (PWM) + * Tachometer + * PCI and PCIe root complex and bridges + * VDM and MCTP support + * Serial I/O expansion + * LPC/eSPI host + * Coprocessor + * Graphics + * Video capture + * Encoding compression engine + * Security features + +Boot options +------------ + +The Nuvoton machines can boot from an OpenBMC firmware image, or directly into +a kernel using the ``-kernel`` option. OpenBMC images for `quanta-gsj` and +possibly others can be downloaded from the OpenPOWER jenkins : + + https://openpower.xyz/ + +The firmware image should be attached as an MTD drive. Example : + +.. code-block:: bash + + $ qemu-system-arm -machine quanta-gsj -nographic \ + -drive file=image-bmc,if=mtd,bus=0,unit=0,format=raw + +The default root password for test images is usually ``0penBmc``. 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/musicpal arm/gumstix arm/nseries + arm/nuvoton arm/orangepi arm/palm arm/xscale -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This adds two acceptance tests for the quanta-gsj machine. One test downloads a lightly patched openbmc flash image from github and verifies that it boots all the way to the login prompt. The other test downloads a kernel, initrd and dtb built from the same openbmc source and verifies that the kernel detects all CPUs and boots to the point where it can't find the root filesystem (because we have no flash image in this case). Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-15-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 83 ++++++++++++++++++++++++++ 1 file changed, 83 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): 'sda') # cubieboard's reboot is not functioning; omit reboot test. + def test_arm_quanta_gsj(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:quanta-gsj + """ + # 25 MiB compressed, 32 MiB uncompressed. + image_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/obmc-phosphor-image-gsj.static.mtd.gz') + image_hash = '14895e634923345cb5c8776037ff7876df96f6b1' + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash) + image_name = 'obmc.mtd' + image_path = os.path.join(self.workdir, image_name) + archive.gzip_uncompress(image_path_gz, image_path) + + self.vm.set_console() + drive_args = 'file=' + image_path + ',if=mtd,bus=0,unit=0' + self.vm.add_args('-drive', drive_args) + self.vm.launch() + + # Disable drivers and services that stall for a long time during boot, + # to avoid running past the 90-second timeout. These may be removed + # as the corresponding device support is added. + kernel_command_line = self.KERNEL_COMMON_COMMAND_LINE + ( + 'console=${console} ' + 'mem=${mem} ' + 'initcall_blacklist=npcm_i2c_bus_driver_init ' + 'systemd.mask=systemd-random-seed.service ' + 'systemd.mask=dropbearkey.service ' + ) + + self.wait_for_console_pattern('> BootBlock by Nuvoton') + self.wait_for_console_pattern('>Device: Poleg BMC NPCM730') + self.wait_for_console_pattern('>Skip DDR init.') + self.wait_for_console_pattern('U-Boot ') + interrupt_interactive_console_until_pattern( + self, 'Hit any key to stop autoboot:', 'U-Boot>') + exec_command_and_wait_for_pattern( + self, "setenv bootargs ${bootargs} " + kernel_command_line, + 'U-Boot>') + exec_command_and_wait_for_pattern( + self, 'run romboot', 'Booting Kernel from flash') + self.wait_for_console_pattern('Booting Linux on physical CPU 0x0') + self.wait_for_console_pattern('CPU1: thread -1, cpu 1, socket 0') + self.wait_for_console_pattern('OpenBMC Project Reference Distro') + self.wait_for_console_pattern('gsj login:') + + def test_arm_quanta_gsj_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:quanta-gsj + """ + initrd_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/obmc-phosphor-initramfs-gsj.cpio.xz') + initrd_hash = '98fefe5d7e56727b1eb17d5c00311b1b5c945300' + initrd_path = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + kernel_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/uImage-gsj.bin') + kernel_hash = 'fa67b2f141d56d39b3c54305c0e8a899c99eb2c7' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + dtb_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/nuvoton-npcm730-gsj.dtb') + dtb_hash = '18315f7006d7b688d8312d5c727eecd819aa36a4' + dtb_path = self.fetch_asset(dtb_url, asset_hash=dtb_hash) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200n8 ' + 'earlycon=uart8250,mmio32,0xf0001000') + self.vm.add_args('-kernel', kernel_path, + '-initrd', initrd_path, + '-dtb', dtb_path, + '-append', kernel_command_line) + self.vm.launch() + + self.wait_for_console_pattern('Booting Linux on physical CPU 0x0') + self.wait_for_console_pattern('CPU1: thread -1, cpu 1, socket 0') + self.wait_for_console_pattern( + 'Give root password for system maintenance') + def test_arm_orangepi(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The Xilinx ZynqMP CAN controller is developed based on SocketCAN, QEMU CAN bus implementation. Bus connection and socketCAN connection for each CAN module can be set through command lines. Example for using single CAN: -object can-bus,id=canbus0 \ -machine xlnx-zcu102.canbus0=canbus0 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 Example for connecting both CAN to same virtual CAN on host machine: -object can-bus,id=canbus0 -object can-bus,id=canbus1 \ -machine xlnx-zcu102.canbus0=canbus0 \ -machine xlnx-zcu102.canbus1=canbus1 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 \ -object can-host-socketcan,id=socketcan1,if=vcan0,canbus=canbus1 To create virtual CAN on the host machine, please check the QEMU CAN docs: https://github.com/qemu/qemu/blob/master/docs/can.txt Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1597278668-339715-2-git-send-email-fnu.vikram@xilinx.com [PMM: updated to meson build system] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/xlnx-zynqmp-can.h | 78 ++ hw/net/can/xlnx-zynqmp-can.c | 1165 ++++++++++++++++++++++++++++++ hw/net/can/meson.build | 1 + 3 files changed, 1244 insertions(+) create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 hw/net/can/xlnx-zynqmp-can.c diff --git a/include/hw/net/xlnx-zynqmp-can.h b/include/hw/net/xlnx-zynqmp-can.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/xlnx-zynqmp-can.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef XLNX_ZYNQMP_CAN_H +#define XLNX_ZYNQMP_CAN_H + +#include "hw/register.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/fifo32.h" +#include "hw/ptimer.h" +#include "hw/qdev-clock.h" + +#define TYPE_XLNX_ZYNQMP_CAN "xlnx.zynqmp-can" + +#define XLNX_ZYNQMP_CAN(obj) \ + OBJECT_CHECK(XlnxZynqMPCANState, (obj), TYPE_XLNX_ZYNQMP_CAN) + +#define MAX_CAN_CTRLS 2 +#define XLNX_ZYNQMP_CAN_R_MAX (0x84 / 4) +#define MAILBOX_CAPACITY 64 +#define CAN_TIMER_MAX 0XFFFFUL +#define CAN_DEFAULT_CLOCK (24 * 1000 * 1000) + +/* Each CAN_FRAME will have 4 * 32bit size. */ +#define CAN_FRAME_SIZE 4 +#define RXFIFO_SIZE (MAILBOX_CAPACITY * CAN_FRAME_SIZE) + +typedef struct XlnxZynqMPCANState { + SysBusDevice parent_obj; + MemoryRegion iomem; + + qemu_irq irq; + + CanBusClientState bus_client; + CanBusState *canbus; + + struct { + uint32_t ext_clk_freq; + } cfg; + + RegisterInfo reg_info[XLNX_ZYNQMP_CAN_R_MAX]; + uint32_t regs[XLNX_ZYNQMP_CAN_R_MAX]; + + Fifo32 rx_fifo; + Fifo32 tx_fifo; + Fifo32 txhpb_fifo; + + ptimer_state *can_timer; +} XlnxZynqMPCANState; + +#endif diff --git a/hw/net/can/xlnx-zynqmp-can.c b/hw/net/can/xlnx-zynqmp-can.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/xlnx-zynqmp-can.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * This implementation is based on the following datasheet: + * https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/irq.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/cutils.h" +#include "sysemu/sysemu.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/event_notifier.h" +#include "qom/object_interfaces.h" +#include "hw/net/xlnx-zynqmp-can.h" + +#ifndef XLNX_ZYNQMP_CAN_ERR_DEBUG +#define XLNX_ZYNQMP_CAN_ERR_DEBUG 0 +#endif + +#define DB_PRINT(dev, ...) do { \ + if (XLNX_ZYNQMP_CAN_ERR_DEBUG) { \ + g_autofree char *path = object_get_canonical_path(OBJECT(dev)); \ + qemu_log("%s: %s", path, ## __VA_ARGS__); \ + } \ +} while (0) + +#define MAX_DLC 8 +#undef ERROR + +REG32(SOFTWARE_RESET_REGISTER, 0x0) + FIELD(SOFTWARE_RESET_REGISTER, CEN, 1, 1) + FIELD(SOFTWARE_RESET_REGISTER, SRST, 0, 1) +REG32(MODE_SELECT_REGISTER, 0x4) + FIELD(MODE_SELECT_REGISTER, SNOOP, 2, 1) + FIELD(MODE_SELECT_REGISTER, LBACK, 1, 1) + FIELD(MODE_SELECT_REGISTER, SLEEP, 0, 1) +REG32(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, 0x8) + FIELD(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, BRP, 0, 8) +REG32(ARBITRATION_PHASE_BIT_TIMING_REGISTER, 0xc) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, SJW, 7, 2) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS2, 4, 3) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS1, 0, 4) +REG32(ERROR_COUNTER_REGISTER, 0x10) + FIELD(ERROR_COUNTER_REGISTER, REC, 8, 8) + FIELD(ERROR_COUNTER_REGISTER, TEC, 0, 8) +REG32(ERROR_STATUS_REGISTER, 0x14) + FIELD(ERROR_STATUS_REGISTER, ACKER, 4, 1) + FIELD(ERROR_STATUS_REGISTER, BERR, 3, 1) + FIELD(ERROR_STATUS_REGISTER, STER, 2, 1) + FIELD(ERROR_STATUS_REGISTER, FMER, 1, 1) + FIELD(ERROR_STATUS_REGISTER, CRCER, 0, 1) +REG32(STATUS_REGISTER, 0x18) + FIELD(STATUS_REGISTER, SNOOP, 12, 1) + FIELD(STATUS_REGISTER, ACFBSY, 11, 1) + FIELD(STATUS_REGISTER, TXFLL, 10, 1) + FIELD(STATUS_REGISTER, TXBFLL, 9, 1) + FIELD(STATUS_REGISTER, ESTAT, 7, 2) + FIELD(STATUS_REGISTER, ERRWRN, 6, 1) + FIELD(STATUS_REGISTER, BBSY, 5, 1) + FIELD(STATUS_REGISTER, BIDLE, 4, 1) + FIELD(STATUS_REGISTER, NORMAL, 3, 1) + FIELD(STATUS_REGISTER, SLEEP, 2, 1) + FIELD(STATUS_REGISTER, LBACK, 1, 1) + FIELD(STATUS_REGISTER, CONFIG, 0, 1) +REG32(INTERRUPT_STATUS_REGISTER, 0x1c) + FIELD(INTERRUPT_STATUS_REGISTER, TXFEMP, 14, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFWMEMP, 13, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFWMFLL, 12, 1) + FIELD(INTERRUPT_STATUS_REGISTER, WKUP, 11, 1) + FIELD(INTERRUPT_STATUS_REGISTER, SLP, 10, 1) + FIELD(INTERRUPT_STATUS_REGISTER, BSOFF, 9, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ERROR, 8, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXNEMP, 7, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOFLW, 6, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXUFLW, 5, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOK, 4, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXBFLL, 3, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFLL, 2, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXOK, 1, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ARBLST, 0, 1) +REG32(INTERRUPT_ENABLE_REGISTER, 0x20) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFEMP, 14, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFWMEMP, 13, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFWMFLL, 12, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EWKUP, 11, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ESLP, 10, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EBSOFF, 9, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EERROR, 8, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXNEMP, 7, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOFLW, 6, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXUFLW, 5, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOK, 4, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXBFLL, 3, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFLL, 2, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXOK, 1, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EARBLST, 0, 1) +REG32(INTERRUPT_CLEAR_REGISTER, 0x24) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFEMP, 14, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFWMEMP, 13, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFWMFLL, 12, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CWKUP, 11, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CSLP, 10, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CBSOFF, 9, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CERROR, 8, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXNEMP, 7, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOFLW, 6, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXUFLW, 5, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOK, 4, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXBFLL, 3, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFLL, 2, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXOK, 1, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CARBLST, 0, 1) +REG32(TIMESTAMP_REGISTER, 0x28) + FIELD(TIMESTAMP_REGISTER, CTS, 0, 1) +REG32(WIR, 0x2c) + FIELD(WIR, EW, 8, 8) + FIELD(WIR, FW, 0, 8) +REG32(TXFIFO_ID, 0x30) + FIELD(TXFIFO_ID, IDH, 21, 11) + FIELD(TXFIFO_ID, SRRRTR, 20, 1) + FIELD(TXFIFO_ID, IDE, 19, 1) + FIELD(TXFIFO_ID, IDL, 1, 18) + FIELD(TXFIFO_ID, RTR, 0, 1) +REG32(TXFIFO_DLC, 0x34) + FIELD(TXFIFO_DLC, DLC, 28, 4) +REG32(TXFIFO_DATA1, 0x38) + FIELD(TXFIFO_DATA1, DB0, 24, 8) + FIELD(TXFIFO_DATA1, DB1, 16, 8) + FIELD(TXFIFO_DATA1, DB2, 8, 8) + FIELD(TXFIFO_DATA1, DB3, 0, 8) +REG32(TXFIFO_DATA2, 0x3c) + FIELD(TXFIFO_DATA2, DB4, 24, 8) + FIELD(TXFIFO_DATA2, DB5, 16, 8) + FIELD(TXFIFO_DATA2, DB6, 8, 8) + FIELD(TXFIFO_DATA2, DB7, 0, 8) +REG32(TXHPB_ID, 0x40) + FIELD(TXHPB_ID, IDH, 21, 11) + FIELD(TXHPB_ID, SRRRTR, 20, 1) + FIELD(TXHPB_ID, IDE, 19, 1) + FIELD(TXHPB_ID, IDL, 1, 18) + FIELD(TXHPB_ID, RTR, 0, 1) +REG32(TXHPB_DLC, 0x44) + FIELD(TXHPB_DLC, DLC, 28, 4) +REG32(TXHPB_DATA1, 0x48) + FIELD(TXHPB_DATA1, DB0, 24, 8) + FIELD(TXHPB_DATA1, DB1, 16, 8) + FIELD(TXHPB_DATA1, DB2, 8, 8) + FIELD(TXHPB_DATA1, DB3, 0, 8) +REG32(TXHPB_DATA2, 0x4c) + FIELD(TXHPB_DATA2, DB4, 24, 8) + FIELD(TXHPB_DATA2, DB5, 16, 8) + FIELD(TXHPB_DATA2, DB6, 8, 8) + FIELD(TXHPB_DATA2, DB7, 0, 8) +REG32(RXFIFO_ID, 0x50) + FIELD(RXFIFO_ID, IDH, 21, 11) + FIELD(RXFIFO_ID, SRRRTR, 20, 1) + FIELD(RXFIFO_ID, IDE, 19, 1) + FIELD(RXFIFO_ID, IDL, 1, 18) + FIELD(RXFIFO_ID, RTR, 0, 1) +REG32(RXFIFO_DLC, 0x54) + FIELD(RXFIFO_DLC, DLC, 28, 4) + FIELD(RXFIFO_DLC, RXT, 0, 16) +REG32(RXFIFO_DATA1, 0x58) + FIELD(RXFIFO_DATA1, DB0, 24, 8) + FIELD(RXFIFO_DATA1, DB1, 16, 8) + FIELD(RXFIFO_DATA1, DB2, 8, 8) + FIELD(RXFIFO_DATA1, DB3, 0, 8) +REG32(RXFIFO_DATA2, 0x5c) + FIELD(RXFIFO_DATA2, DB4, 24, 8) + FIELD(RXFIFO_DATA2, DB5, 16, 8) + FIELD(RXFIFO_DATA2, DB6, 8, 8) + FIELD(RXFIFO_DATA2, DB7, 0, 8) +REG32(AFR, 0x60) + FIELD(AFR, UAF4, 3, 1) + FIELD(AFR, UAF3, 2, 1) + FIELD(AFR, UAF2, 1, 1) + FIELD(AFR, UAF1, 0, 1) +REG32(AFMR1, 0x64) + FIELD(AFMR1, AMIDH, 21, 11) + FIELD(AFMR1, AMSRR, 20, 1) + FIELD(AFMR1, AMIDE, 19, 1) + FIELD(AFMR1, AMIDL, 1, 18) + FIELD(AFMR1, AMRTR, 0, 1) +REG32(AFIR1, 0x68) + FIELD(AFIR1, AIIDH, 21, 11) + FIELD(AFIR1, AISRR, 20, 1) + FIELD(AFIR1, AIIDE, 19, 1) + FIELD(AFIR1, AIIDL, 1, 18) + FIELD(AFIR1, AIRTR, 0, 1) +REG32(AFMR2, 0x6c) + FIELD(AFMR2, AMIDH, 21, 11) + FIELD(AFMR2, AMSRR, 20, 1) + FIELD(AFMR2, AMIDE, 19, 1) + FIELD(AFMR2, AMIDL, 1, 18) + FIELD(AFMR2, AMRTR, 0, 1) +REG32(AFIR2, 0x70) + FIELD(AFIR2, AIIDH, 21, 11) + FIELD(AFIR2, AISRR, 20, 1) + FIELD(AFIR2, AIIDE, 19, 1) + FIELD(AFIR2, AIIDL, 1, 18) + FIELD(AFIR2, AIRTR, 0, 1) +REG32(AFMR3, 0x74) + FIELD(AFMR3, AMIDH, 21, 11) + FIELD(AFMR3, AMSRR, 20, 1) + FIELD(AFMR3, AMIDE, 19, 1) + FIELD(AFMR3, AMIDL, 1, 18) + FIELD(AFMR3, AMRTR, 0, 1) +REG32(AFIR3, 0x78) + FIELD(AFIR3, AIIDH, 21, 11) + FIELD(AFIR3, AISRR, 20, 1) + FIELD(AFIR3, AIIDE, 19, 1) + FIELD(AFIR3, AIIDL, 1, 18) + FIELD(AFIR3, AIRTR, 0, 1) +REG32(AFMR4, 0x7c) + FIELD(AFMR4, AMIDH, 21, 11) + FIELD(AFMR4, AMSRR, 20, 1) + FIELD(AFMR4, AMIDE, 19, 1) + FIELD(AFMR4, AMIDL, 1, 18) + FIELD(AFMR4, AMRTR, 0, 1) +REG32(AFIR4, 0x80) + FIELD(AFIR4, AIIDH, 21, 11) + FIELD(AFIR4, AISRR, 20, 1) + FIELD(AFIR4, AIIDE, 19, 1) + FIELD(AFIR4, AIIDL, 1, 18) + FIELD(AFIR4, AIRTR, 0, 1) + +static void can_update_irq(XlnxZynqMPCANState *s) +{ + uint32_t irq; + + /* Watermark register interrupts. */ + if ((fifo32_num_free(&s->tx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, EW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFWMEMP, 1); + } + + if ((fifo32_num_used(&s->rx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, FW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL, 1); + } + + /* RX Interrupts. */ + if (fifo32_num_used(&s->rx_fifo) >= CAN_FRAME_SIZE) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXNEMP, 1); + } + + /* TX interrupts. */ + if (fifo32_is_empty(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFEMP, 1); + } + + if (fifo32_is_full(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFLL, 1); + } + + if (fifo32_is_full(&s->txhpb_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXBFLL, 1); + } + + irq = s->regs[R_INTERRUPT_STATUS_REGISTER]; + irq &= s->regs[R_INTERRUPT_ENABLE_REGISTER]; + + qemu_set_irq(s->irq, irq); +} + +static void can_ier_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + can_update_irq(s); +} + +static uint64_t can_icr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + s->regs[R_INTERRUPT_STATUS_REGISTER] &= ~val; + can_update_irq(s); + + return 0; +} + +static void can_config_reset(XlnxZynqMPCANState *s) +{ + /* Reset all the configuration registers. */ + register_reset(&s->reg_info[R_SOFTWARE_RESET_REGISTER]); + register_reset(&s->reg_info[R_MODE_SELECT_REGISTER]); + register_reset( + &s->reg_info[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]); + register_reset(&s->reg_info[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]); + register_reset(&s->reg_info[R_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_ENABLE_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_CLEAR_REGISTER]); + register_reset(&s->reg_info[R_WIR]); +} + +static void can_config_mode(XlnxZynqMPCANState *s) +{ + register_reset(&s->reg_info[R_ERROR_COUNTER_REGISTER]); + register_reset(&s->reg_info[R_ERROR_STATUS_REGISTER]); + + /* Put XlnxZynqMPCAN in configuration mode. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, BSOFF, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ERROR, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ARBLST, 0); + + can_update_irq(s); +} + +static void update_status_register_mode_bits(XlnxZynqMPCANState *s) +{ + bool sleep_status = ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP); + bool sleep_mode = ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP); + /* Wake up interrupt bit. */ + bool wakeup_irq_val = sleep_status && (sleep_mode == 0); + /* Sleep interrupt bit. */ + bool sleep_irq_val = sleep_mode && (sleep_status == 0); + + /* Clear previous core mode status bits. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 0); + + /* set current mode bit and generate irqs accordingly. */ + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, LBACK)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 1); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, + sleep_irq_val); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 1); + } else { + /* + * If all bits are zero then XlnxZynqMPCAN is set in normal mode. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 1); + /* Set wakeup interrupt bit. */ + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, + wakeup_irq_val); + } + + can_update_irq(s); +} + +static void can_exit_sleep_mode(XlnxZynqMPCANState *s) +{ + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, 0); + update_status_register_mode_bits(s); +} + +static void generate_frame(qemu_can_frame *frame, uint32_t *data) +{ + frame->can_id = data[0]; + frame->can_dlc = FIELD_EX32(data[1], TXFIFO_DLC, DLC); + + frame->data[0] = FIELD_EX32(data[2], TXFIFO_DATA1, DB3); + frame->data[1] = FIELD_EX32(data[2], TXFIFO_DATA1, DB2); + frame->data[2] = FIELD_EX32(data[2], TXFIFO_DATA1, DB1); + frame->data[3] = FIELD_EX32(data[2], TXFIFO_DATA1, DB0); + + frame->data[4] = FIELD_EX32(data[3], TXFIFO_DATA2, DB7); + frame->data[5] = FIELD_EX32(data[3], TXFIFO_DATA2, DB6); + frame->data[6] = FIELD_EX32(data[3], TXFIFO_DATA2, DB5); + frame->data[7] = FIELD_EX32(data[3], TXFIFO_DATA2, DB4); +} + +static bool tx_ready_check(XlnxZynqMPCANState *s) +{ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " data while controller is in reset mode.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in configuration mode. Reset" + " the core so operations can start fresh.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in SNOOP MODE.\n", + path); + return false; + } + + return true; +} + +static void transfer_fifo(XlnxZynqMPCANState *s, Fifo32 *fifo) +{ + qemu_can_frame frame; + uint32_t data[CAN_FRAME_SIZE]; + int i; + bool can_tx = tx_ready_check(s); + + if (can_tx) { + while (!fifo32_is_empty(fifo)) { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + data[i] = fifo32_pop(fifo); + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * Controller is in loopback. In Loopback mode, the CAN core + * transmits a recessive bitstream on to the XlnxZynqMPCAN Bus. + * Any message transmitted is looped back to the RX line and + * acknowledged. The XlnxZynqMPCAN core receives any message + * that it transmits. + */ + if (fifo32_is_full(&s->rx_fifo)) { + DB_PRINT(s, "Loopback: RX FIFO is full." + " TX FIFO will be flushed.\n"); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, + RXOFLW, 1); + } else { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + fifo32_push(&s->rx_fifo, data[i]); + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, + RXOK, 1); + } + } else { + /* Normal mode Tx. */ + generate_frame(&frame, data); + + can_bus_client_send(&s->bus_client, &frame, 1); + } + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 1); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, TXBFLL, 0); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) { + can_exit_sleep_mode(s); + } + } else { + DB_PRINT(s, "Not enabled for data transfer.\n"); + } + + can_update_irq(s); +} + +static uint64_t can_srr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + ARRAY_FIELD_DP32(s->regs, SOFTWARE_RESET_REGISTER, CEN, + FIELD_EX32(val, SOFTWARE_RESET_REGISTER, CEN)); + + if (FIELD_EX32(val, SOFTWARE_RESET_REGISTER, SRST)) { + DB_PRINT(s, "Resetting controller.\n"); + + /* First, core will do software reset then will enter in config mode. */ + can_config_reset(s); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + can_config_mode(s); + } else { + /* + * Leave config mode. Now XlnxZynqMPCAN core will enter normal, + * sleep, snoop or loopback mode depending upon LBACK, SLEEP, SNOOP + * register states. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 0); + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + + /* XlnxZynqMPCAN is out of config mode. It will send pending data. */ + transfer_fifo(s, &s->txhpb_fifo); + transfer_fifo(s, &s->tx_fifo); + } + + update_status_register_mode_bits(s); + + return s->regs[R_SOFTWARE_RESET_REGISTER]; +} + +static uint64_t can_msr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + uint8_t multi_mode; + + /* + * Multiple mode set check. This is done to make sure user doesn't set + * multiple modes. + */ + multi_mode = FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP); + + if (multi_mode > 1) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to config" + " several modes simultaneously. One mode will be selected" + " according to their priority: LBACK > SLEEP > SNOOP.\n", + path); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + /* We are in configuration mode, any mode can be selected. */ + s->regs[R_MODE_SELECT_REGISTER] = val; + } else { + bool sleep_mode_bit = FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP); + + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, sleep_mode_bit); + + if (FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " LBACK mode without setting CEN bit as 0.\n", + path); + } else if (FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " SNOOP mode without setting CEN bit as 0.\n", + path); + } + + update_status_register_mode_bits(s); + } + + return s->regs[R_MODE_SELECT_REGISTER]; +} + +static uint64_t can_brpr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + val = s->regs[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]; + } + + return val; +} + +static uint64_t can_btr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + val = s->regs[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]; + } + + return val; +} + +static uint64_t can_tcr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + if (FIELD_EX32(val, TIMESTAMP_REGISTER, CTS)) { + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + } + + return 0; +} + +static void update_rx_fifo(XlnxZynqMPCANState *s, const qemu_can_frame *frame) +{ + bool filter_pass = false; + uint16_t timestamp = 0; + + /* If no filter is enabled. Message will be stored in FIFO. */ + if (!((ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)))) { + filter_pass = true; + } + + /* + * Messages that pass any of the acceptance filters will be stored in + * the RX FIFO. + */ + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) { + uint32_t id_masked = s->regs[R_AFMR1] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR1] & s->regs[R_AFIR1]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) { + uint32_t id_masked = s->regs[R_AFMR2] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR2] & s->regs[R_AFIR2]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) { + uint32_t id_masked = s->regs[R_AFMR3] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR3] & s->regs[R_AFIR3]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + uint32_t id_masked = s->regs[R_AFMR4] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR4] & s->regs[R_AFIR4]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + /* Store the message in fifo if it passed through any of the filters. */ + if (filter_pass && frame->can_dlc <= MAX_DLC) { + + if (fifo32_is_full(&s->rx_fifo)) { + DB_PRINT(s, "RX FIFO is full.\n"); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 1); + } else { + timestamp = CAN_TIMER_MAX - ptimer_get_count(s->can_timer); + + fifo32_push(&s->rx_fifo, frame->can_id); + + fifo32_push(&s->rx_fifo, deposit32(0, R_RXFIFO_DLC_DLC_SHIFT, + R_RXFIFO_DLC_DLC_LENGTH, + frame->can_dlc) | + deposit32(0, R_RXFIFO_DLC_RXT_SHIFT, + R_RXFIFO_DLC_RXT_LENGTH, + timestamp)); + + /* First 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA1_DB3_SHIFT, + R_TXFIFO_DATA1_DB3_LENGTH, + frame->data[0]) | + deposit32(0, R_TXFIFO_DATA1_DB2_SHIFT, + R_TXFIFO_DATA1_DB2_LENGTH, + frame->data[1]) | + deposit32(0, R_TXFIFO_DATA1_DB1_SHIFT, + R_TXFIFO_DATA1_DB1_LENGTH, + frame->data[2]) | + deposit32(0, R_TXFIFO_DATA1_DB0_SHIFT, + R_TXFIFO_DATA1_DB0_LENGTH, + frame->data[3])); + /* Last 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA2_DB7_SHIFT, + R_TXFIFO_DATA2_DB7_LENGTH, + frame->data[4]) | + deposit32(0, R_TXFIFO_DATA2_DB6_SHIFT, + R_TXFIFO_DATA2_DB6_LENGTH, + frame->data[5]) | + deposit32(0, R_TXFIFO_DATA2_DB5_SHIFT, + R_TXFIFO_DATA2_DB5_LENGTH, + frame->data[6]) | + deposit32(0, R_TXFIFO_DATA2_DB4_SHIFT, + R_TXFIFO_DATA2_DB4_LENGTH, + frame->data[7])); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + } + + can_update_irq(s); + } else { + DB_PRINT(s, "Message didn't pass through any filter or dlc" + " is not in range.\n"); + } +} + +static uint64_t can_rxfifo_pre_read(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t r = 0; + + if (!fifo32_is_empty(&s->rx_fifo)) { + r = fifo32_pop(&s->rx_fifo); + } else { + DB_PRINT(s, "No message in RXFIFO.\n"); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXUFLW, 1); + } + + can_update_irq(s); + return r; +} + +static void can_filter_enable_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF2) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF3) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 1); + } else { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 0); + } +} + +static uint64_t can_filter_mask_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t val = val64; + uint32_t filter_number = (reg_idx - R_AFMR1) / 2; + + /* modify an acceptance filter, the corresponding UAF bit should be '0.' */ + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " mask is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static uint64_t can_filter_id_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t val = val64; + uint32_t filter_number = (reg_idx - R_AFIR1) / 2; + + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " id is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static void can_tx_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + bool is_txhpb = reg->access->addr > A_TXFIFO_DATA2; + + bool initiate_transfer = (reg->access->addr == A_TXFIFO_DATA2) || + (reg->access->addr == A_TXHPB_DATA2); + + Fifo32 *f = is_txhpb ? &s->txhpb_fifo : &s->tx_fifo; + + DB_PRINT(s, "TX FIFO write.\n"); + + if (!fifo32_is_full(f)) { + fifo32_push(f, val); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: TX FIFO is full.\n", path); + } + + /* Initiate the message send if TX register is written. */ + if (initiate_transfer && + ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + transfer_fifo(s, f); + } + + can_update_irq(s); +} + +static const RegisterAccessInfo can_regs_info[] = { + { .name = "SOFTWARE_RESET_REGISTER", + .addr = A_SOFTWARE_RESET_REGISTER, + .rsvd = 0xfffffffc, + .pre_write = can_srr_pre_write, + },{ .name = "MODE_SELECT_REGISTER", + .addr = A_MODE_SELECT_REGISTER, + .rsvd = 0xfffffff8, + .pre_write = can_msr_pre_write, + },{ .name = "ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER", + .addr = A_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, + .rsvd = 0xffffff00, + .pre_write = can_brpr_pre_write, + },{ .name = "ARBITRATION_PHASE_BIT_TIMING_REGISTER", + .addr = A_ARBITRATION_PHASE_BIT_TIMING_REGISTER, + .rsvd = 0xfffffe00, + .pre_write = can_btr_pre_write, + },{ .name = "ERROR_COUNTER_REGISTER", + .addr = A_ERROR_COUNTER_REGISTER, + .rsvd = 0xffff0000, + .ro = 0xffffffff, + },{ .name = "ERROR_STATUS_REGISTER", + .addr = A_ERROR_STATUS_REGISTER, + .rsvd = 0xffffffe0, + .w1c = 0x1f, + },{ .name = "STATUS_REGISTER", .addr = A_STATUS_REGISTER, + .reset = 0x1, + .rsvd = 0xffffe000, + .ro = 0x1fff, + },{ .name = "INTERRUPT_STATUS_REGISTER", + .addr = A_INTERRUPT_STATUS_REGISTER, + .reset = 0x6000, + .rsvd = 0xffff8000, + .ro = 0x7fff, + },{ .name = "INTERRUPT_ENABLE_REGISTER", + .addr = A_INTERRUPT_ENABLE_REGISTER, + .rsvd = 0xffff8000, + .post_write = can_ier_post_write, + },{ .name = "INTERRUPT_CLEAR_REGISTER", + .addr = A_INTERRUPT_CLEAR_REGISTER, + .rsvd = 0xffff8000, + .pre_write = can_icr_pre_write, + },{ .name = "TIMESTAMP_REGISTER", + .addr = A_TIMESTAMP_REGISTER, + .rsvd = 0xfffffffe, + .pre_write = can_tcr_pre_write, + },{ .name = "WIR", .addr = A_WIR, + .reset = 0x3f3f, + .rsvd = 0xffff0000, + },{ .name = "TXFIFO_ID", .addr = A_TXFIFO_ID, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DLC", .addr = A_TXFIFO_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA1", .addr = A_TXFIFO_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA2", .addr = A_TXFIFO_DATA2, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_ID", .addr = A_TXHPB_ID, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DLC", .addr = A_TXHPB_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA1", .addr = A_TXHPB_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA2", .addr = A_TXHPB_DATA2, + .post_write = can_tx_post_write, + },{ .name = "RXFIFO_ID", .addr = A_RXFIFO_ID, + .ro = 0xffffffff, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DLC", .addr = A_RXFIFO_DLC, + .rsvd = 0xfff0000, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA1", .addr = A_RXFIFO_DATA1, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA2", .addr = A_RXFIFO_DATA2, + .post_read = can_rxfifo_pre_read, + },{ .name = "AFR", .addr = A_AFR, + .rsvd = 0xfffffff0, + .post_write = can_filter_enable_post_write, + },{ .name = "AFMR1", .addr = A_AFMR1, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR1", .addr = A_AFIR1, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR2", .addr = A_AFMR2, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR2", .addr = A_AFIR2, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR3", .addr = A_AFMR3, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR3", .addr = A_AFIR3, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR4", .addr = A_AFMR4, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR4", .addr = A_AFIR4, + .pre_write = can_filter_id_pre_write, + } +}; + +static void xlnx_zynqmp_can_ptimer_cb(void *opaque) +{ + /* No action required on the timer rollover. */ +} + +static const MemoryRegionOps can_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void xlnx_zynqmp_can_reset_init(Object *obj, ResetType type) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = R_RXFIFO_ID; i < ARRAY_SIZE(s->reg_info); ++i) { + register_reset(&s->reg_info[i]); + } + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_reset_hold(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = 0; i < R_RXFIFO_ID; ++i) { + register_reset(&s->reg_info[i]); + } + + /* + * Reset FIFOs when CAN model is reset. This will clear the fifo writes + * done by post_write which gets called from register_reset function, + * post_write handle will not be able to trigger tx because CAN will be + * disabled when software_reset_register is cleared first. + */ + fifo32_reset(&s->rx_fifo); + fifo32_reset(&s->tx_fifo); + fifo32_reset(&s->txhpb_fifo); +} + +static bool xlnx_zynqmp_can_can_receive(CanBusClientState *client) +{ + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + DB_PRINT(s, "Controller is in reset.\n"); + return false; + } else if ((ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) == 0) { + DB_PRINT(s, "Controller is disabled. Incoming messages" + " will be discarded.\n"); + return false; + } else { + return true; + } +} + +static ssize_t xlnx_zynqmp_can_receive(CanBusClientState *client, + const qemu_can_frame *buf, size_t buf_size) { + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + const qemu_can_frame *frame = buf; + + DB_PRINT(s, "Incoming data.\n"); + + if (buf_size <= 0) { + DB_PRINT(s, "Junk data received.\n"); + return 0; + } + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * XlnxZynqMPCAN will not participate in normal bus communication + * and will not receive any messages transmitted by other CAN nodes. + */ + DB_PRINT(s, "Controller is in loopback mode. It will not" + " receive data.\n"); + + } else if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + /* Snoop Mode: Just keep the data. no response back. */ + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP))) { + /* + * XlnxZynqMPCAN is in sleep mode. Any data on bus will bring it to wake + * up state. + */ + can_exit_sleep_mode(s); + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) == 0) { + update_rx_fifo(s, frame); + } else { + DB_PRINT(s, "Cannot receive data as controller is not configured" + " correctly.\n"); + } + + return 1; +} + +static CanBusClientInfo can_xilinx_bus_client_info = { + .can_receive = xlnx_zynqmp_can_can_receive, + .receive = xlnx_zynqmp_can_receive, +}; + +static int xlnx_zynqmp_can_connect_to_bus(XlnxZynqMPCANState *s, + CanBusState *bus) +{ + s->bus_client.info = &can_xilinx_bus_client_info; + + if (can_bus_insert_client(bus, &s->bus_client) < 0) { + return -1; + } + return 0; +} + +static void xlnx_zynqmp_can_realize(DeviceState *dev, Error **errp) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(dev); + + if (s->canbus) { + if (xlnx_zynqmp_can_connect_to_bus(s, s->canbus) < 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + error_setg(errp, "%s: xlnx_zynqmp_can_connect_to_bus" + " failed.", path); + return; + } + + } else { + /* If no bus is set. */ + DB_PRINT(s, "Canbus property is not set.\n"); + } + + /* Create RX FIFO, TXFIFO, TXHPB storage. */ + fifo32_create(&s->rx_fifo, RXFIFO_SIZE); + fifo32_create(&s->tx_fifo, RXFIFO_SIZE); + fifo32_create(&s->txhpb_fifo, CAN_FRAME_SIZE); + + /* Allocate a new timer. */ + s->can_timer = ptimer_init(xlnx_zynqmp_can_ptimer_cb, s, + PTIMER_POLICY_DEFAULT); + + ptimer_transaction_begin(s->can_timer); + + ptimer_set_freq(s->can_timer, s->cfg.ext_clk_freq); + ptimer_set_limit(s->can_timer, CAN_TIMER_MAX, 1); + ptimer_run(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_init(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_XLNX_ZYNQMP_CAN, + XLNX_ZYNQMP_CAN_R_MAX * 4); + reg_array = register_init_block32(DEVICE(obj), can_regs_info, + ARRAY_SIZE(can_regs_info), + s->reg_info, s->regs, + &can_ops, + XLNX_ZYNQMP_CAN_ERR_DEBUG, + XLNX_ZYNQMP_CAN_R_MAX * 4); + + memory_region_add_subregion(&s->iomem, 0x00, &reg_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); +} + +static const VMStateDescription vmstate_can = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_FIFO32(rx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(tx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(txhpb_fifo, XlnxZynqMPCANState), + VMSTATE_UINT32_ARRAY(regs, XlnxZynqMPCANState, XLNX_ZYNQMP_CAN_R_MAX), + VMSTATE_PTIMER(can_timer, XlnxZynqMPCANState), + VMSTATE_END_OF_LIST(), + } +}; + +static Property xlnx_zynqmp_can_properties[] = { + DEFINE_PROP_UINT32("ext_clk_freq", XlnxZynqMPCANState, cfg.ext_clk_freq, + CAN_DEFAULT_CLOCK), + DEFINE_PROP_LINK("canbus", XlnxZynqMPCANState, canbus, TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xlnx_zynqmp_can_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = xlnx_zynqmp_can_reset_init; + rc->phases.hold = xlnx_zynqmp_can_reset_hold; + dc->realize = xlnx_zynqmp_can_realize; + device_class_set_props(dc, xlnx_zynqmp_can_properties); + dc->vmsd = &vmstate_can; +} + +static const TypeInfo can_info = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxZynqMPCANState), + .class_init = xlnx_zynqmp_can_class_init, + .instance_init = xlnx_zynqmp_can_init, +}; + +static void can_register_types(void) +{ + type_register_static(&can_info); +} + +type_init(can_register_types) diff --git a/hw/net/can/meson.build b/hw/net/can/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/meson.build +++ b/hw/net/can/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_CAN_SJA1000', if_true: files('can_sja1000.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_kvaser_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_pcm3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_mioe3680_pci.c')) +softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP', if_true: files('xlnx-zynqmp-can.c')) -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Connect CAN0 and CAN1 on the ZynqMP. Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1597278668-339715-3-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 8 ++++++++ hw/arm/xlnx-zcu102.c | 20 ++++++++++++++++++++ hw/arm/xlnx-zynqmp.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/net/cadence_gem.h" #include "hw/char/cadence_uart.h" +#include "hw/net/xlnx-zynqmp-can.h" #include "hw/ide/ahci.h" #include "hw/sd/sdhci.h" #include "hw/ssi/xilinx_spips.h" @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/cluster.h" #include "target/arm/cpu.h" #include "qom/object.h" +#include "net/can_emu.h" #define TYPE_XLNX_ZYNQMP "xlnx,zynqmp" typedef struct XlnxZynqMPState XlnxZynqMPState; @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(XlnxZynqMPState, XLNX_ZYNQMP, #define XLNX_ZYNQMP_NUM_RPU_CPUS 2 #define XLNX_ZYNQMP_NUM_GEMS 4 #define XLNX_ZYNQMP_NUM_UARTS 2 +#define XLNX_ZYNQMP_NUM_CAN 2 +#define XLNX_ZYNQMP_CAN_REF_CLK (24 * 1000 * 1000) #define XLNX_ZYNQMP_NUM_SDHCI 2 #define XLNX_ZYNQMP_NUM_SPIS 2 #define XLNX_ZYNQMP_NUM_GDMA_CH 8 @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { CadenceGEMState gem[XLNX_ZYNQMP_NUM_GEMS]; CadenceUARTState uart[XLNX_ZYNQMP_NUM_UARTS]; + XlnxZynqMPCANState can[XLNX_ZYNQMP_NUM_CAN]; SysbusAHCIState sata; SDHCIState sdhci[XLNX_ZYNQMP_NUM_SDHCI]; XilinxSPIPS spi[XLNX_ZYNQMP_NUM_SPIS]; @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { bool virt; /* Has the RPU subsystem? */ bool has_rpu; + + /* CAN bus. */ + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; }; #endif diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/qtest.h" #include "sysemu/device_tree.h" #include "qom/object.h" +#include "net/can_emu.h" struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ struct XlnxZCU102 { bool secure; bool virt; + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; + struct arm_boot_info binfo; }; typedef struct XlnxZCU102 XlnxZCU102; @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) object_property_set_bool(OBJECT(&s->soc), "virtualization", s->virt, &error_fatal); + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + gchar *bus_name = g_strdup_printf("canbus%d", i); + + object_property_set_link(OBJECT(&s->soc), bus_name, + OBJECT(s->canbus[i]), &error_fatal); + g_free(bus_name); + } + qdev_realize(DEVICE(&s->soc), NULL, &error_fatal); /* Create and plug in the SD cards */ @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_machine_instance_init(Object *obj) "Set on/off to enable/disable emulating a " "guest CPU which implements the ARM " "Virtualization Extensions"); + object_property_add_link(obj, "xlnx-zcu102.canbus0", TYPE_CAN_BUS, + (Object **)&s->canbus[0], + object_property_allow_set_link, + 0); + + object_property_add_link(obj, "xlnx-zcu102.canbus1", TYPE_CAN_BUS, + (Object **)&s->canbus[1], + object_property_allow_set_link, + 0); } static void xlnx_zcu102_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ static const int uart_intr[XLNX_ZYNQMP_NUM_UARTS] = { 21, 22, }; +static const uint64_t can_addr[XLNX_ZYNQMP_NUM_CAN] = { + 0xFF060000, 0xFF070000, +}; + +static const int can_intr[XLNX_ZYNQMP_NUM_CAN] = { + 23, 24, +}; + static const uint64_t sdhci_addr[XLNX_ZYNQMP_NUM_SDHCI] = { 0xFF160000, 0xFF170000, }; @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_init(Object *obj) TYPE_CADENCE_UART); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_initialize_child(obj, "can[*]", &s->can[i], + TYPE_XLNX_ZYNQMP_CAN); + } + object_initialize_child(obj, "sata", &s->sata, TYPE_SYSBUS_AHCI); for (i = 0; i < XLNX_ZYNQMP_NUM_SDHCI; i++) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) gic_spi[uart_intr[i]]); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_property_set_int(OBJECT(&s->can[i]), "ext_clk_freq", + XLNX_ZYNQMP_CAN_REF_CLK, &error_abort); + + object_property_set_link(OBJECT(&s->can[i]), "canbus", + OBJECT(s->canbus[i]), &error_fatal); + + sysbus_realize(SYS_BUS_DEVICE(&s->can[i]), &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->can[i]), 0, can_addr[i]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->can[i]), 0, + gic_spi[can_intr[i]]); + } + object_property_set_int(OBJECT(&s->sata), "num-ports", SATA_NUM_PORTS, &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->sata), errp)) { @@ -XXX,XX +XXX,XX @@ static Property xlnx_zynqmp_props[] = { DEFINE_PROP_BOOL("has_rpu", XlnxZynqMPState, has_rpu, false), DEFINE_PROP_LINK("ddr-ram", XlnxZynqMPState, ddr_ram, TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_LINK("canbus0", XlnxZynqMPState, canbus[0], TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_LINK("canbus1", XlnxZynqMPState, canbus[1], TYPE_CAN_BUS, + CanBusState *), DEFINE_PROP_END_OF_LIST() }; -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The QTests perform five tests on the Xilinx ZynqMP CAN controller: Tests the CAN controller in loopback, sleep and snoop mode. Tests filtering of incoming CAN messages. Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1597278668-339715-4-git-send-email-fnu.vikram@xilinx.com [PMM: updated to meson build system] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/xlnx-can-test.c | 359 ++++++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 360 insertions(+) create mode 100644 tests/qtest/xlnx-can-test.c diff --git a/tests/qtest/xlnx-can-test.c b/tests/qtest/xlnx-can-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/xlnx-can-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "libqos/libqtest.h" + +/* Base address. */ +#define CAN0_BASE_ADDR 0xFF060000 +#define CAN1_BASE_ADDR 0xFF070000 + +/* Register addresses. */ +#define R_SRR_OFFSET 0x00 +#define R_MSR_OFFSET 0x04 +#define R_SR_OFFSET 0x18 +#define R_ISR_OFFSET 0x1C +#define R_ICR_OFFSET 0x24 +#define R_TXID_OFFSET 0x30 +#define R_TXDLC_OFFSET 0x34 +#define R_TXDATA1_OFFSET 0x38 +#define R_TXDATA2_OFFSET 0x3C +#define R_RXID_OFFSET 0x50 +#define R_RXDLC_OFFSET 0x54 +#define R_RXDATA1_OFFSET 0x58 +#define R_RXDATA2_OFFSET 0x5C +#define R_AFR 0x60 +#define R_AFMR1 0x64 +#define R_AFIR1 0x68 +#define R_AFMR2 0x6C +#define R_AFIR2 0x70 +#define R_AFMR3 0x74 +#define R_AFIR3 0x78 +#define R_AFMR4 0x7C +#define R_AFIR4 0x80 + +/* CAN modes. */ +#define CONFIG_MODE 0x00 +#define NORMAL_MODE 0x00 +#define LOOPBACK_MODE 0x02 +#define SNOOP_MODE 0x04 +#define SLEEP_MODE 0x01 +#define ENABLE_CAN (1 << 1) +#define STATUS_NORMAL_MODE (1 << 3) +#define STATUS_LOOPBACK_MODE (1 << 1) +#define STATUS_SNOOP_MODE (1 << 12) +#define STATUS_SLEEP_MODE (1 << 2) +#define ISR_TXOK (1 << 1) +#define ISR_RXOK (1 << 4) + +static void match_rx_tx_data(uint32_t *buf_tx, uint32_t *buf_rx, + uint8_t can_timestamp) +{ + uint16_t size = 0; + uint8_t len = 4; + + while (size < len) { + if (R_RXID_OFFSET + 4 * size == R_RXDLC_OFFSET) { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size] + can_timestamp); + } else { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size]); + } + + size++; + } +} + +static void read_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_rx) +{ + uint32_t int_status; + + /* Read the interrupt on CAN rx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_RXOK; + + g_assert_cmpint(int_status, ==, ISR_RXOK); + + /* Read the RX register data for CAN. */ + buf_rx[0] = qtest_readl(qts, can_base_addr + R_RXID_OFFSET); + buf_rx[1] = qtest_readl(qts, can_base_addr + R_RXDLC_OFFSET); + buf_rx[2] = qtest_readl(qts, can_base_addr + R_RXDATA1_OFFSET); + buf_rx[3] = qtest_readl(qts, can_base_addr + R_RXDATA2_OFFSET); + + /* Clear the RX interrupt. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_ICR_OFFSET, ISR_RXOK); +} + +static void send_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_tx) +{ + uint32_t int_status; + + /* Write the TX register data for CAN. */ + qtest_writel(qts, can_base_addr + R_TXID_OFFSET, buf_tx[0]); + qtest_writel(qts, can_base_addr + R_TXDLC_OFFSET, buf_tx[1]); + qtest_writel(qts, can_base_addr + R_TXDATA1_OFFSET, buf_tx[2]); + qtest_writel(qts, can_base_addr + R_TXDATA2_OFFSET, buf_tx[3]); + + /* Read the interrupt on CAN for tx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_TXOK; + + g_assert_cmpint(int_status, ==, ISR_TXOK); + + /* Clear the interrupt for tx. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_ICR_OFFSET, ISR_TXOK); +} + +/* + * This test will be transferring data from CAN0 and CAN1 through canbus. CAN0 + * initiate the data transfer to can-bus, CAN1 receives the data. Test compares + * the data sent from CAN0 with received on CAN1. + */ +static void test_can_bus(void) +{ + uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* + * This test is performing loopback mode on CAN0 and CAN1. Data sent from TX of + * each CAN0 and CAN1 are compared with RX register data for respective CAN. + */ +static void test_can_loopback(void) +{ + uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 in loopback mode. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN0 is set in loopback mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + read_data(qts, CAN0_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + /* Configure the CAN1 in loopback mode. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN1 is set in loopback mode. */ + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + qtest_quit(qts); +} + +/* + * Enable filters for CAN1. This will filter incoming messages with ID. In this + * test message will pass through filter 2. + */ +static void test_can_filter(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + /* Set filter for CAN1 for incoming messages. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0x0); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR1, 0xF7); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR1, 0x121F); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR2, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR2, 0x14); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR3, 0x1234); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR3, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR4, 0xFFF); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR4, 0x1234); + + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0xF); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing sleep mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_sleepmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SLEEP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SLEEP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SLEEP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + /* + * Once CAN1 sends data on can-bus. CAN0 should exit sleep mode. + * Check the CAN0 status now. It should exit the sleep mode and receive the + * incoming data. + */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing Snoop mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_snoopmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SNOOP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SNOOP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SNOOP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + + qtest_add_func("/net/can/can_bus", test_can_bus); + qtest_add_func("/net/can/can_loopback", test_can_loopback); + qtest_add_func("/net/can/can_filter", test_can_filter); + qtest_add_func("/net/can/can_test_snoopmode", test_can_snoopmode); + qtest_add_func("/net/can/can_test_sleepmode", test_can_sleepmode); + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ (config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-swtpm-test'] : []) + \ ['numa-test', 'boot-serial-test', + 'xlnx-can-test', 'migration-test'] qtests_s390x = \ -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1597278668-339715-5-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/net/opencores_eth.c Devices ------- +Xilinx CAN +M: Vikram Garhwal <fnu.vikram@xilinx.com> +M: Francisco Iglesias <francisco.iglesias@xilinx.com> +S: Maintained +F: hw/net/can/xlnx-* +F: include/hw/net/xlnx-* +F: tests/qtest/xlnx-can-test* + EDU M: Jiri Slaby <jslaby@suse.cz> S: Maintained -- 2.20.1