arm queue; dunno if this will be the last before softfreeze or not, but anyway probably the last large one. New orangepi-pc board model is the big item here. thanks -- PMM The following changes since commit 67d9ef7d541c3d21a25796c51c26da096a433565: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-docs-20200312' into staging (2020-03-12 15:20:52 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200312 for you to fetch changes up to aca53be34ac3e7cac5f39396a51a338860a5a837: target/arm: kvm: Inject events at the last stage of sync (2020-03-12 16:31:10 +0000) ---------------------------------------------------------------- target-arm queue: * Fix various bugs that might result in an assert() due to incorrect hflags for M-profile CPUs * Fix Aspeed SMC Controller user-mode select handling * Report correct (with-tag) address in fault address register when TBI is enabled * cubieboard: make sure SOC object isn't leaked * fsl-imx25: Wire up eSDHC controllers * fsl-imx25: Wire up USB controllers * New board model: orangepi-pc (OrangePi PC) * ARM/KVM: if user doesn't select GIC version and the host kernel can only provide GICv3, use that, rather than defaulting to "fail because GICv2 isn't possible" * kvm: Only do KVM_SET_VCPU_EVENTS at the last stage of sync ---------------------------------------------------------------- Beata Michalska (1): target/arm: kvm: Inject events at the last stage of sync Cédric Le Goater (2): aspeed/smc: Add some tracing aspeed/smc: Fix User mode select/unselect scheme Eric Auger (6): hw/arm/virt: Document 'max' value in gic-version property description hw/arm/virt: Introduce VirtGICType enum type hw/arm/virt: Introduce finalize_gic_version() target/arm/kvm: Let kvm_arm_vgic_probe() return a bitmap hw/arm/virt: kvm: Restructure finalize_gic_version() hw/arm/virt: kvm: allow gicv3 by default if v2 cannot work Guenter Roeck (2): hw/arm/fsl-imx25: Wire up eSDHC controllers hw/arm/fsl-imx25: Wire up USB controllers Igor Mammedov (1): hw/arm/cubieboard: make sure SOC object isn't leaked Niek Linnenbank (13): hw/arm: add Allwinner H3 System-on-Chip hw/arm: add Xunlong Orange Pi PC machine hw/arm/allwinner-h3: add Clock Control Unit hw/arm/allwinner-h3: add USB host controller hw/arm/allwinner-h3: add System Control module hw/arm/allwinner: add CPU Configuration module hw/arm/allwinner: add Security Identifier device hw/arm/allwinner: add SD/MMC host controller hw/arm/allwinner-h3: add EMAC ethernet device hw/arm/allwinner-h3: add Boot ROM support hw/arm/allwinner-h3: add SDRAM controller device hw/arm/allwinner: add RTC device support docs: add Orange Pi PC document Peter Maydell (4): hw/intc/armv7m_nvic: Rebuild hflags on reset target/arm: Update hflags in trans_CPS_v7m() target/arm: Recalculate hflags correctly after writes to CONTROL target/arm: Fix some comment typos Philippe Mathieu-Daudé (5): tests/boot_linux_console: Add a quick test for the OrangePi PC board tests/boot_linux_console: Add initrd test for the Orange Pi PC board tests/boot_linux_console: Add a SD card test for the OrangePi PC board tests/boot_linux_console: Add a SLOW test booting Ubuntu on OrangePi PC tests/boot_linux_console: Test booting NetBSD via U-Boot on OrangePi PC Richard Henderson (2): target/arm: Check addresses for disabled regimes target/arm: Disable clean_data_tbi for system mode Makefile.objs | 1 + hw/arm/Makefile.objs | 1 + hw/misc/Makefile.objs | 5 + hw/net/Makefile.objs | 1 + hw/rtc/Makefile.objs | 1 + hw/sd/Makefile.objs | 1 + hw/usb/hcd-ehci.h | 1 + include/hw/arm/allwinner-a10.h | 4 + include/hw/arm/allwinner-h3.h | 161 ++++++ include/hw/arm/fsl-imx25.h | 18 + include/hw/arm/virt.h | 12 +- include/hw/misc/allwinner-cpucfg.h | 52 ++ include/hw/misc/allwinner-h3-ccu.h | 66 +++ include/hw/misc/allwinner-h3-dramc.h | 106 ++++ include/hw/misc/allwinner-h3-sysctrl.h | 67 +++ include/hw/misc/allwinner-sid.h | 60 +++ include/hw/net/allwinner-sun8i-emac.h | 99 ++++ include/hw/rtc/allwinner-rtc.h | 134 +++++ include/hw/sd/allwinner-sdhost.h | 135 +++++ target/arm/helper.h | 1 + target/arm/kvm_arm.h | 3 + hw/arm/allwinner-a10.c | 19 + hw/arm/allwinner-h3.c | 465 ++++++++++++++++++ hw/arm/cubieboard.c | 18 + hw/arm/fsl-imx25.c | 56 +++ hw/arm/imx25_pdk.c | 16 + hw/arm/orangepi.c | 130 +++++ hw/arm/virt.c | 145 ++++-- hw/intc/armv7m_nvic.c | 6 + hw/misc/allwinner-cpucfg.c | 282 +++++++++++ hw/misc/allwinner-h3-ccu.c | 242 +++++++++ hw/misc/allwinner-h3-dramc.c | 358 ++++++++++++++ hw/misc/allwinner-h3-sysctrl.c | 140 ++++++ hw/misc/allwinner-sid.c | 168 +++++++ hw/net/allwinner-sun8i-emac.c | 871 +++++++++++++++++++++++++++++++++ hw/rtc/allwinner-rtc.c | 411 ++++++++++++++++ hw/sd/allwinner-sdhost.c | 854 ++++++++++++++++++++++++++++++++ hw/ssi/aspeed_smc.c | 56 ++- hw/usb/hcd-ehci-sysbus.c | 17 + target/arm/helper.c | 49 +- target/arm/kvm.c | 14 +- target/arm/kvm32.c | 15 +- target/arm/kvm64.c | 15 +- target/arm/translate-a64.c | 11 + target/arm/translate.c | 14 +- MAINTAINERS | 9 + default-configs/arm-softmmu.mak | 1 + docs/system/arm/orangepi.rst | 253 ++++++++++ docs/system/target-arm.rst | 2 + hw/arm/Kconfig | 12 + hw/misc/trace-events | 19 + hw/net/Kconfig | 3 + hw/net/trace-events | 10 + hw/rtc/trace-events | 4 + hw/sd/trace-events | 7 + hw/ssi/trace-events | 10 + tests/acceptance/boot_linux_console.py | 230 +++++++++ 57 files changed, 5787 insertions(+), 74 deletions(-) create mode 100644 include/hw/arm/allwinner-h3.h create mode 100644 include/hw/misc/allwinner-cpucfg.h create mode 100644 include/hw/misc/allwinner-h3-ccu.h create mode 100644 include/hw/misc/allwinner-h3-dramc.h create mode 100644 include/hw/misc/allwinner-h3-sysctrl.h create mode 100644 include/hw/misc/allwinner-sid.h create mode 100644 include/hw/net/allwinner-sun8i-emac.h create mode 100644 include/hw/rtc/allwinner-rtc.h create mode 100644 include/hw/sd/allwinner-sdhost.h create mode 100644 hw/arm/allwinner-h3.c create mode 100644 hw/arm/orangepi.c create mode 100644 hw/misc/allwinner-cpucfg.c create mode 100644 hw/misc/allwinner-h3-ccu.c create mode 100644 hw/misc/allwinner-h3-dramc.c create mode 100644 hw/misc/allwinner-h3-sysctrl.c create mode 100644 hw/misc/allwinner-sid.c create mode 100644 hw/net/allwinner-sun8i-emac.c create mode 100644 hw/rtc/allwinner-rtc.c create mode 100644 hw/sd/allwinner-sdhost.c create mode 100644 docs/system/arm/orangepi.rst create mode 100644 hw/ssi/trace-events Some of an M-profile CPU's cached hflags state depends on state that's in our NVIC object. We already do an hflags rebuild when the NVIC registers are written, but we also need to do this on NVIC reset, because there's no guarantee that this will happen before the CPU reset. This fixes an assertion due to mismatched hflags which happens if the CPU is reset from inside a HardFault handler. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-2-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->itns[i] = true; } } + + /* + * We updated state that affects the CPU's MMUidx and thus its hflags; + * and we can't guarantee that we run before the CPU reset function. + */ + arm_rebuild_hflags(&s->cpu->env); } static void nvic_systick_trigger(void *opaque, int n, int level) -- 2.20.1 For M-profile CPUs, the FAULTMASK value affects the CPU's MMU index (it changes the NegPri bit). We update the hflags after calls to the v7m_msr helper in trans_MSR_v7m() but forgot to do so in trans_CPS_v7m(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-3-peter.maydell@linaro.org --- target/arm/translate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_CPS(DisasContext *s, arg_CPS *a) static bool trans_CPS_v7m(DisasContext *s, arg_CPS_v7m *a) { - TCGv_i32 tmp, addr; + TCGv_i32 tmp, addr, el; if (!arm_dc_feature(s, ARM_FEATURE_M)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_CPS_v7m(DisasContext *s, arg_CPS_v7m *a) gen_helper_v7m_msr(cpu_env, addr, tmp); tcg_temp_free_i32(addr); } + el = tcg_const_i32(s->current_el); + gen_helper_rebuild_hflags_m32(cpu_env, el); + tcg_temp_free_i32(el); tcg_temp_free_i32(tmp); gen_lookup_tb(s); return true; -- 2.20.1 A write to the CONTROL register can change our current EL (by writing to the nPRIV bit). That means that we can't assume that s->current_el is still valid in trans_MSR_v7m() when we try to rebuild the hflags. Add a new helper rebuild_hflags_m32_newel() which, like the existing rebuild_hflags_a32_newel(), recalculates the current EL from scratch, and use it in trans_MSR_v7m(). This fixes an assertion about an hflags mismatch when the guest changes privilege by writing to CONTROL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-4-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/helper.c | 12 ++++++++++++ target/arm/translate.c | 7 +++---- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(msr_banked, void, env, i32, i32, i32) DEF_HELPER_2(get_user_reg, i32, env, i32) DEF_HELPER_3(set_user_reg, void, env, i32, i32) +DEF_HELPER_FLAGS_1(rebuild_hflags_m32_newel, TCG_CALL_NO_RWG, void, env) DEF_HELPER_FLAGS_2(rebuild_hflags_m32, TCG_CALL_NO_RWG, void, env, int) DEF_HELPER_FLAGS_1(rebuild_hflags_a32_newel, TCG_CALL_NO_RWG, void, env) DEF_HELPER_FLAGS_2(rebuild_hflags_a32, TCG_CALL_NO_RWG, void, env, int) 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 @@ void arm_rebuild_hflags(CPUARMState *env) env->hflags = rebuild_hflags_internal(env); } +/* + * If we have triggered a EL state change we can't rely on the + * translator having passed it to us, we need to recompute. + */ +void HELPER(rebuild_hflags_m32_newel)(CPUARMState *env) +{ + int el = arm_current_el(env); + int fp_el = fp_exception_el(env, el); + ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, el); + env->hflags = rebuild_hflags_m32(env, fp_el, mmu_idx); +} + void HELPER(rebuild_hflags_m32)(CPUARMState *env, int el) { int fp_el = fp_exception_el(env, el); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_MRS_v7m(DisasContext *s, arg_MRS_v7m *a) static bool trans_MSR_v7m(DisasContext *s, arg_MSR_v7m *a) { - TCGv_i32 addr, reg, el; + TCGv_i32 addr, reg; if (!arm_dc_feature(s, ARM_FEATURE_M)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_MSR_v7m(DisasContext *s, arg_MSR_v7m *a) gen_helper_v7m_msr(cpu_env, addr, reg); tcg_temp_free_i32(addr); tcg_temp_free_i32(reg); - el = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_m32(cpu_env, el); - tcg_temp_free_i32(el); + /* If we wrote to CONTROL, the EL might have changed */ + gen_helper_rebuild_hflags_m32_newel(cpu_env); gen_lookup_tb(s); return true; } -- 2.20.1 Fix a couple of comment typos. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-5-peter.maydell@linaro.org --- target/arm/helper.c | 2 +- target/arm/translate.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(rebuild_hflags_m32)(CPUARMState *env, int el) /* * If we have triggered a EL state change we can't rely on the - * translator having passed it too us, we need to recompute. + * translator having passed it to us, we need to recompute. */ void HELPER(rebuild_hflags_a32_newel)(CPUARMState *env) { 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_coproc_insn(DisasContext *s, uint32_t insn) if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { /* - * A write to any coprocessor regiser that ends a TB + * A write to any coprocessor register that ends a TB * must rebuild the hflags for the next TB. */ TCGv_i32 tcg_el = tcg_const_i32(s->current_el); -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200206112645.21275-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- Makefile.objs | 1 + hw/ssi/aspeed_smc.c | 17 +++++++++++++++++ hw/ssi/trace-events | 9 +++++++++ 3 files changed, 27 insertions(+) create mode 100644 hw/ssi/trace-events diff --git a/Makefile.objs b/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -XXX,XX +XXX,XX @@ trace-events-subdirs += hw/scsi trace-events-subdirs += hw/sd trace-events-subdirs += hw/sparc trace-events-subdirs += hw/sparc64 +trace-events-subdirs += hw/ssi trace-events-subdirs += hw/timer trace-events-subdirs += hw/tpm trace-events-subdirs += hw/usb diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "exec/address-spaces.h" #include "qemu/units.h" +#include "trace.h" #include "hw/irq.h" #include "hw/qdev-properties.h" @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_flash_set_segment(AspeedSMCState *s, int cs, s->ctrl->reg_to_segment(s, new, &seg); + trace_aspeed_smc_flash_set_segment(cs, new, seg.addr, seg.addr + seg.size); + /* The start address of CS0 is read-only */ if (cs == 0 && seg.addr != s->ctrl->flash_window_base) { qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_smc_flash_read(void *opaque, hwaddr addr, unsigned size) __func__, aspeed_smc_flash_mode(fl)); } + trace_aspeed_smc_flash_read(fl->id, addr, size, ret, + aspeed_smc_flash_mode(fl)); return ret; } @@ -XXX,XX +XXX,XX @@ static bool aspeed_smc_do_snoop(AspeedSMCFlash *fl, uint64_t data, AspeedSMCState *s = fl->controller; uint8_t addr_width = aspeed_smc_flash_is_4byte(fl) ? 4 : 3; + trace_aspeed_smc_do_snoop(fl->id, s->snoop_index, s->snoop_dummies, + (uint8_t) data & 0xff); + if (s->snoop_index == SNOOP_OFF) { return false; /* Do nothing */ @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_flash_write(void *opaque, hwaddr addr, uint64_t data, AspeedSMCState *s = fl->controller; int i; + trace_aspeed_smc_flash_write(fl->id, addr, size, data, + aspeed_smc_flash_mode(fl)); + if (!aspeed_smc_is_writable(fl)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: flash is not writable at 0x%" HWADDR_PRIx "\n", __func__, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size) (s->ctrl->has_dma && addr == R_DMA_CHECKSUM) || (addr >= R_SEG_ADDR0 && addr < R_SEG_ADDR0 + s->ctrl->max_slaves) || (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->ctrl->max_slaves)) { + + trace_aspeed_smc_read(addr, size, s->regs[addr]); + return s->regs[addr]; } else { qemu_log_mask(LOG_UNIMP, "%s: not implemented: 0x%" HWADDR_PRIx "\n", @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_dma_checksum(AspeedSMCState *s) __func__, s->regs[R_DMA_FLASH_ADDR]); return; } + trace_aspeed_smc_dma_checksum(s->regs[R_DMA_FLASH_ADDR], data); /* * When the DMA is on-going, the DMA registers are updated @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, addr >>= 2; + trace_aspeed_smc_write(addr, size, data); + if (addr == s->r_conf || (addr >= s->r_timings && addr < s->r_timings + s->ctrl->nregs_timings) || diff --git a/hw/ssi/trace-events b/hw/ssi/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/ssi/trace-events @@ -XXX,XX +XXX,XX @@ +# aspeed_smc.c + +aspeed_smc_flash_set_segment(int cs, uint64_t reg, uint64_t start, uint64_t end) "CS%d segreg=0x%"PRIx64" [ 0x%"PRIx64" - 0x%"PRIx64" ]" +aspeed_smc_flash_read(int cs, uint64_t addr, uint32_t size, uint64_t data, int mode) "CS%d @0x%" PRIx64 " size %u: 0x%" PRIx64" mode:%d" +aspeed_smc_do_snoop(int cs, int index, int dummies, int data) "CS%d index:0x%x dummies:%d data:0x%x" +aspeed_smc_flash_write(int cs, uint64_t addr, uint32_t size, uint64_t data, int mode) "CS%d @0x%" PRIx64 " size %u: 0x%" PRIx64" mode:%d" +aspeed_smc_read(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 +aspeed_smc_dma_checksum(uint32_t addr, uint32_t data) "0x%08x: 0x%08x" +aspeed_smc_write(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The Aspeed SMC Controller can operate in different modes : Read, Fast Read, Write and User modes. When the User mode is configured, it selects automatically the SPI slave device until the CE_STOP_ACTIVE bit is set to 1. When any other modes are configured the device is unselected. The HW logic handles the chip select automatically when the flash is accessed through its AHB window. When configuring the CEx Control Register, the User mode logic to select and unselect the slave is incorrect and data corruption can be seen on machines using two chips, witherspoon and romulus. Rework the handler setting the CEx Control Register to fix this issue. Fixes: 7c1c69bca43c ("ast2400: add SMC controllers (FMC and SPI)") Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20200206112645.21275-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/aspeed_smc.c | 39 +++++++++++++++++++++++---------------- hw/ssi/trace-events | 1 + 2 files changed, 24 insertions(+), 16 deletions(-) diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ static inline int aspeed_smc_flash_is_4byte(const AspeedSMCFlash *fl) } } -static inline bool aspeed_smc_is_ce_stop_active(const AspeedSMCFlash *fl) +static void aspeed_smc_flash_do_select(AspeedSMCFlash *fl, bool unselect) { - const AspeedSMCState *s = fl->controller; + AspeedSMCState *s = fl->controller; - return s->regs[s->r_ctrl0 + fl->id] & CTRL_CE_STOP_ACTIVE; + trace_aspeed_smc_flash_select(fl->id, unselect ? "un" : ""); + + qemu_set_irq(s->cs_lines[fl->id], unselect); } static void aspeed_smc_flash_select(AspeedSMCFlash *fl) { - AspeedSMCState *s = fl->controller; - - s->regs[s->r_ctrl0 + fl->id] &= ~CTRL_CE_STOP_ACTIVE; - qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); + aspeed_smc_flash_do_select(fl, false); } static void aspeed_smc_flash_unselect(AspeedSMCFlash *fl) { - AspeedSMCState *s = fl->controller; - - s->regs[s->r_ctrl0 + fl->id] |= CTRL_CE_STOP_ACTIVE; - qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); + aspeed_smc_flash_do_select(fl, true); } static uint32_t aspeed_smc_check_segment_addr(const AspeedSMCFlash *fl, @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps aspeed_smc_flash_ops = { }, }; -static void aspeed_smc_flash_update_cs(AspeedSMCFlash *fl) +static void aspeed_smc_flash_update_ctrl(AspeedSMCFlash *fl, uint32_t value) { AspeedSMCState *s = fl->controller; + bool unselect; - s->snoop_index = aspeed_smc_is_ce_stop_active(fl) ? SNOOP_OFF : SNOOP_START; + /* User mode selects the CS, other modes unselect */ + unselect = (value & CTRL_CMD_MODE_MASK) != CTRL_USERMODE; - qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); + /* A change of CTRL_CE_STOP_ACTIVE from 0 to 1, unselects the CS */ + if (!(s->regs[s->r_ctrl0 + fl->id] & CTRL_CE_STOP_ACTIVE) && + value & CTRL_CE_STOP_ACTIVE) { + unselect = true; + } + + s->regs[s->r_ctrl0 + fl->id] = value; + + s->snoop_index = unselect ? SNOOP_OFF : SNOOP_START; + + aspeed_smc_flash_do_select(fl, unselect); } static void aspeed_smc_reset(DeviceState *d) @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, s->regs[addr] = value; } else if (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs) { int cs = addr - s->r_ctrl0; - s->regs[addr] = value; - aspeed_smc_flash_update_cs(&s->flashes[cs]); + aspeed_smc_flash_update_ctrl(&s->flashes[cs], value); } else if (addr >= R_SEG_ADDR0 && addr < R_SEG_ADDR0 + s->ctrl->max_slaves) { int cs = addr - R_SEG_ADDR0; 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_flash_write(int cs, uint64_t addr, uint32_t size, uint64_t data, int aspeed_smc_read(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 aspeed_smc_dma_checksum(uint32_t addr, uint32_t data) "0x%08x: 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" -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We fail to validate the upper bits of a virtual address on a translation disabled regime, as per AArch64.TranslateAddressS1Off. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200308012946.16303-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 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 @@ bool get_phys_addr(CPUARMState *env, target_ulong address, /* Definitely a real MMU, not an MPU */ if (regime_translation_disabled(env, mmu_idx)) { - /* MMU disabled. */ + /* + * MMU disabled. S1 addresses within aa64 translation regimes are + * still checked for bounds -- see AArch64.TranslateAddressS1Off. + */ + if (mmu_idx != ARMMMUIdx_Stage2) { + int r_el = regime_el(env, mmu_idx); + if (arm_el_is_aa64(env, r_el)) { + int pamax = arm_pamax(env_archcpu(env)); + uint64_t tcr = env->cp15.tcr_el[r_el].raw_tcr; + int addrtop, tbi; + + tbi = aa64_va_parameter_tbi(tcr, mmu_idx); + if (access_type == MMU_INST_FETCH) { + tbi &= ~aa64_va_parameter_tbid(tcr, mmu_idx); + } + tbi = (tbi >> extract64(address, 55, 1)) & 1; + addrtop = (tbi ? 55 : 63); + + if (extract64(address, pamax, addrtop - pamax + 1) != 0) { + fi->type = ARMFault_AddressSize; + fi->level = 0; + fi->stage2 = false; + return 1; + } + + /* + * When TBI is disabled, we've just validated that all of the + * bits above PAMax are zero, so logically we only need to + * clear the top byte for TBI. But it's clearer to follow + * the pseudocode set of addrdesc.paddress. + */ + address = extract64(address, 0, 52); + } + } *phys_ptr = address; *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; *page_size = TARGET_PAGE_SIZE; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We must include the tag in the FAR_ELx register when raising an addressing exception. Which means that we should not clear out the tag during translation. We cannot at present comply with this for user mode, so we retain the clean_data_tbi function for the moment, though it no longer does what it says on the tin for system mode. This function is to be replaced with MTE, so don't worry about the slight misnaming. Buglink: https://bugs.launchpad.net/qemu/+bug/1867072 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200308012946.16303-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) static TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr) { TCGv_i64 clean = new_tmp_a64(s); + /* + * In order to get the correct value in the FAR_ELx register, + * we must present the memory subsystem with the "dirty" address + * including the TBI. In system mode we can make this work via + * the TLB, dropping the TBI during translation. But for user-only + * mode we don't have that option, and must remove the top byte now. + */ +#ifdef CONFIG_USER_ONLY gen_top_byte_ignore(s, clean, addr, s->tbid); +#else + tcg_gen_mov_i64(clean, addr); +#endif return clean; } -- 2.20.1 From: Igor Mammedov <imammedo@redhat.com> SOC object returned by object_new() is leaked in current code. Set SOC parent explicitly to board and then unref to SOC object to make sure that refererence returned by object_new() is taken care of. The SOC object will be kept alive by its parent (machine) and will be automatically freed when MachineState is destroyed. Signed-off-by: Igor Mammedov <imammedo@redhat.com> Reported-by: Andrew Jones <drjones@redhat.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20200303091254.22373-1-imammedo@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/cubieboard.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) } a10 = AW_A10(object_new(TYPE_AW_A10)); + object_property_add_child(OBJECT(machine), "soc", OBJECT(a10), + &error_abort); + object_unref(OBJECT(a10)); object_property_set_int(OBJECT(&a10->emac), 1, "phy-addr", &err); if (err != NULL) { -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Wire up eSDHC controllers in fsl-imx25. For imx25-pdk, connect drives provided on the command line to available eSDHC controllers. This patch enables booting the imx25-pdk emulation from SD card. Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20200310215146.19688-2-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: made commit subject consistent with other patch] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx25.h | 9 +++++++++ hw/arm/fsl-imx25.c | 32 ++++++++++++++++++++++++++++++++ hw/arm/imx25_pdk.c | 16 ++++++++++++++++ 3 files changed, 57 insertions(+) diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx_rngc.h" #include "hw/i2c/imx_i2c.h" #include "hw/gpio/imx_gpio.h" +#include "hw/sd/sdhci.h" #include "exec/memory.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ #define FSL_IMX25_NUM_EPITS 2 #define FSL_IMX25_NUM_I2CS 3 #define FSL_IMX25_NUM_GPIOS 4 +#define FSL_IMX25_NUM_ESDHCS 2 typedef struct FslIMX25State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { IMXRNGCState rngc; IMXI2CState i2c[FSL_IMX25_NUM_I2CS]; IMXGPIOState gpio[FSL_IMX25_NUM_GPIOS]; + SDHCIState esdhc[FSL_IMX25_NUM_ESDHCS]; MemoryRegion rom[2]; MemoryRegion iram; MemoryRegion iram_alias; @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO3_SIZE 0x4000 #define FSL_IMX25_RNGC_ADDR 0x53FB0000 #define FSL_IMX25_RNGC_SIZE 0x4000 +#define FSL_IMX25_ESDHC1_ADDR 0x53FB4000 +#define FSL_IMX25_ESDHC1_SIZE 0x4000 +#define FSL_IMX25_ESDHC2_ADDR 0x53FB8000 +#define FSL_IMX25_ESDHC2_SIZE 0x4000 #define FSL_IMX25_GPIO1_ADDR 0x53FCC000 #define FSL_IMX25_GPIO1_SIZE 0x4000 #define FSL_IMX25_GPIO2_ADDR 0x53FD0000 @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO2_IRQ 51 #define FSL_IMX25_GPIO3_IRQ 16 #define FSL_IMX25_GPIO4_IRQ 23 +#define FSL_IMX25_ESDHC1_IRQ 9 +#define FSL_IMX25_ESDHC2_IRQ 8 #endif /* FSL_IMX25_H */ diff --git a/hw/arm/fsl-imx25.c b/hw/arm/fsl-imx25.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx25.c +++ b/hw/arm/fsl-imx25.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "chardev/char.h" +#define IMX25_ESDHC_CAPABILITIES 0x07e20000 + static void fsl_imx25_init(Object *obj) { FslIMX25State *s = FSL_IMX25(obj); @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_init(Object *obj) sysbus_init_child_obj(obj, "gpio[*]", &s->gpio[i], sizeof(s->gpio[i]), TYPE_IMX_GPIO); } + + for (i = 0; i < FSL_IMX25_NUM_ESDHCS; i++) { + sysbus_init_child_obj(obj, "sdhc[*]", &s->esdhc[i], sizeof(s->esdhc[i]), + TYPE_IMX_USDHC); + } } static void fsl_imx25_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp) gpio_table[i].irq)); } + /* Initialize all SDHC */ + for (i = 0; i < FSL_IMX25_NUM_ESDHCS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } esdhc_table[FSL_IMX25_NUM_ESDHCS] = { + { FSL_IMX25_ESDHC1_ADDR, FSL_IMX25_ESDHC1_IRQ }, + { FSL_IMX25_ESDHC2_ADDR, FSL_IMX25_ESDHC2_IRQ }, + }; + + object_property_set_uint(OBJECT(&s->esdhc[i]), 2, "sd-spec-version", + &err); + object_property_set_uint(OBJECT(&s->esdhc[i]), IMX25_ESDHC_CAPABILITIES, + "capareg", &err); + object_property_set_bool(OBJECT(&s->esdhc[i]), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->esdhc[i]), 0, esdhc_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->esdhc[i]), 0, + qdev_get_gpio_in(DEVICE(&s->avic), + esdhc_table[i].irq)); + } + /* initialize 2 x 16 KB ROM */ memory_region_init_rom(&s->rom[0], NULL, "imx25.rom0", FSL_IMX25_ROM0_SIZE, &err); diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "cpu.h" +#include "hw/qdev-properties.h" #include "hw/arm/fsl-imx25.h" #include "hw/boards.h" #include "qemu/error-report.h" @@ -XXX,XX +XXX,XX @@ static void imx25_pdk_init(MachineState *machine) imx25_pdk_binfo.board_id = 1771, imx25_pdk_binfo.nb_cpus = 1; + for (i = 0; i < FSL_IMX25_NUM_ESDHCS; i++) { + BusState *bus; + DeviceState *carddev; + DriveInfo *di; + BlockBackend *blk; + + di = drive_get_next(IF_SD); + blk = di ? blk_by_legacy_dinfo(di) : NULL; + bus = qdev_get_child_bus(DEVICE(&s->soc.esdhc[i]), "sd-bus"); + carddev = qdev_create(bus, TYPE_SD_CARD); + qdev_prop_set_drive(carddev, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(carddev), true, + "realized", &error_fatal); + } + /* * We test explicitly for qtest here as it is not done (yet?) in * arm_load_kernel(). Without this the "make check" command would -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> i.MX25 supports two USB controllers. Let's wire them up. With this patch, imx25-pdk can boot from both USB ports. Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20200310215146.19688-3-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx25.h | 9 +++++++++ hw/arm/fsl-imx25.c | 24 ++++++++++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -XXX,XX +XXX,XX @@ #include "hw/i2c/imx_i2c.h" #include "hw/gpio/imx_gpio.h" #include "hw/sd/sdhci.h" +#include "hw/usb/chipidea.h" #include "exec/memory.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ #define FSL_IMX25_NUM_I2CS 3 #define FSL_IMX25_NUM_GPIOS 4 #define FSL_IMX25_NUM_ESDHCS 2 +#define FSL_IMX25_NUM_USBS 2 typedef struct FslIMX25State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { IMXI2CState i2c[FSL_IMX25_NUM_I2CS]; IMXGPIOState gpio[FSL_IMX25_NUM_GPIOS]; SDHCIState esdhc[FSL_IMX25_NUM_ESDHCS]; + ChipideaState usb[FSL_IMX25_NUM_USBS]; MemoryRegion rom[2]; MemoryRegion iram; MemoryRegion iram_alias; @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO1_SIZE 0x4000 #define FSL_IMX25_GPIO2_ADDR 0x53FD0000 #define FSL_IMX25_GPIO2_SIZE 0x4000 +#define FSL_IMX25_USB1_ADDR 0x53FF4000 +#define FSL_IMX25_USB1_SIZE 0x0200 +#define FSL_IMX25_USB2_ADDR 0x53FF4400 +#define FSL_IMX25_USB2_SIZE 0x0200 #define FSL_IMX25_AVIC_ADDR 0x68000000 #define FSL_IMX25_AVIC_SIZE 0x4000 #define FSL_IMX25_IRAM_ADDR 0x78000000 @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO4_IRQ 23 #define FSL_IMX25_ESDHC1_IRQ 9 #define FSL_IMX25_ESDHC2_IRQ 8 +#define FSL_IMX25_USB1_IRQ 37 +#define FSL_IMX25_USB2_IRQ 35 #endif /* FSL_IMX25_H */ diff --git a/hw/arm/fsl-imx25.c b/hw/arm/fsl-imx25.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx25.c +++ b/hw/arm/fsl-imx25.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_init(Object *obj) sysbus_init_child_obj(obj, "sdhc[*]", &s->esdhc[i], sizeof(s->esdhc[i]), TYPE_IMX_USDHC); } + + for (i = 0; i < FSL_IMX25_NUM_USBS; i++) { + sysbus_init_child_obj(obj, "usb[*]", &s->usb[i], sizeof(s->usb[i]), + TYPE_CHIPIDEA); + } + } static void fsl_imx25_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp) esdhc_table[i].irq)); } + /* USB */ + for (i = 0; i < FSL_IMX25_NUM_USBS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } usb_table[FSL_IMX25_NUM_USBS] = { + { FSL_IMX25_USB1_ADDR, FSL_IMX25_USB1_IRQ }, + { FSL_IMX25_USB2_ADDR, FSL_IMX25_USB2_IRQ }, + }; + + object_property_set_bool(OBJECT(&s->usb[i]), true, "realized", + &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, usb_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i]), 0, + qdev_get_gpio_in(DEVICE(&s->avic), + usb_table[i].irq)); + } + /* initialize 2 x 16 KB ROM */ memory_region_init_rom(&s->rom[0], NULL, "imx25.rom0", FSL_IMX25_ROM0_SIZE, &err); -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner H3 is a System on Chip containing four ARM Cortex A7 processor cores. Features and specifications include DDR2/DDR3 memory, SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and various I/O modules. This commit adds support for the Allwinner H3 System on Chip. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-2-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 106 +++++++++++ hw/arm/allwinner-h3.c | 327 ++++++++++++++++++++++++++++++++ MAINTAINERS | 7 + default-configs/arm-softmmu.mak | 1 + hw/arm/Kconfig | 8 + 6 files changed, 450 insertions(+) create mode 100644 include/hw/arm/allwinner-h3.h create mode 100644 hw/arm/allwinner-h3.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_DIGIC) += digic.o obj-$(CONFIG_OMAP) += omap1.o omap2.o obj-$(CONFIG_STRONGARM) += strongarm.o obj-$(CONFIG_ALLWINNER_A10) += allwinner-a10.o cubieboard.o +obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3.o obj-$(CONFIG_RASPI) += bcm2835_peripherals.o bcm2836.o raspi.o obj-$(CONFIG_STM32F205_SOC) += stm32f205_soc.o obj-$(CONFIG_STM32F405_SOC) += stm32f405_soc.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System on Chip emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * The Allwinner H3 is a System on Chip containing four ARM Cortex A7 + * processor cores. Features and specifications include DDR2/DDR3 memory, + * SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and + * various I/O modules. + * + * This implementation is based on the following datasheet: + * + * https://linux-sunxi.org/File:Allwinner_H3_Datasheet_V1.2.pdf + * + * The latest datasheet and more info can be found on the Linux Sunxi wiki: + * + * https://linux-sunxi.org/H3 + */ + +#ifndef HW_ARM_ALLWINNER_H3_H +#define HW_ARM_ALLWINNER_H3_H + +#include "qom/object.h" +#include "hw/arm/boot.h" +#include "hw/timer/allwinner-a10-pit.h" +#include "hw/intc/arm_gic.h" +#include "target/arm/cpu.h" + +/** + * Allwinner H3 device list + * + * This enumeration is can be used refer to a particular device in the + * Allwinner H3 SoC. For example, the physical memory base address for + * each device can be found in the AwH3State object in the memmap member + * using the device enum value as index. + * + * @see AwH3State + */ +enum { + AW_H3_SRAM_A1, + AW_H3_SRAM_A2, + AW_H3_SRAM_C, + AW_H3_PIT, + AW_H3_UART0, + AW_H3_UART1, + AW_H3_UART2, + AW_H3_UART3, + AW_H3_GIC_DIST, + AW_H3_GIC_CPU, + AW_H3_GIC_HYP, + AW_H3_GIC_VCPU, + AW_H3_SDRAM +}; + +/** Total number of CPU cores in the H3 SoC */ +#define AW_H3_NUM_CPUS (4) + +/** + * Allwinner H3 object model + * @{ + */ + +/** Object type for the Allwinner H3 SoC */ +#define TYPE_AW_H3 "allwinner-h3" + +/** Convert input object to Allwinner H3 state object */ +#define AW_H3(obj) OBJECT_CHECK(AwH3State, (obj), TYPE_AW_H3) + +/** @} */ + +/** + * Allwinner H3 object + * + * This struct contains the state of all the devices + * which are currently emulated by the H3 SoC code. + */ +typedef struct AwH3State { + /*< private >*/ + DeviceState parent_obj; + /*< public >*/ + + ARMCPU cpus[AW_H3_NUM_CPUS]; + const hwaddr *memmap; + AwA10PITState timer; + GICState gic; + MemoryRegion sram_a1; + MemoryRegion sram_a2; + MemoryRegion sram_c; +} AwH3State; + +#endif /* HW_ARM_ALLWINNER_H3_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System on Chip emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "hw/qdev-core.h" +#include "cpu.h" +#include "hw/sysbus.h" +#include "hw/char/serial.h" +#include "hw/misc/unimp.h" +#include "sysemu/sysemu.h" +#include "hw/arm/allwinner-h3.h" + +/* Memory map */ +const hwaddr allwinner_h3_memmap[] = { + [AW_H3_SRAM_A1] = 0x00000000, + [AW_H3_SRAM_A2] = 0x00044000, + [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_PIT] = 0x01c20c00, + [AW_H3_UART0] = 0x01c28000, + [AW_H3_UART1] = 0x01c28400, + [AW_H3_UART2] = 0x01c28800, + [AW_H3_UART3] = 0x01c28c00, + [AW_H3_GIC_DIST] = 0x01c81000, + [AW_H3_GIC_CPU] = 0x01c82000, + [AW_H3_GIC_HYP] = 0x01c84000, + [AW_H3_GIC_VCPU] = 0x01c86000, + [AW_H3_SDRAM] = 0x40000000 +}; + +/* List of unimplemented devices */ +struct AwH3Unimplemented { + const char *device_name; + hwaddr base; + hwaddr size; +} unimplemented[] = { + { "d-engine", 0x01000000, 4 * MiB }, + { "d-inter", 0x01400000, 128 * KiB }, + { "syscon", 0x01c00000, 4 * KiB }, + { "dma", 0x01c02000, 4 * KiB }, + { "nfdc", 0x01c03000, 4 * KiB }, + { "ts", 0x01c06000, 4 * KiB }, + { "keymem", 0x01c0b000, 4 * KiB }, + { "lcd0", 0x01c0c000, 4 * KiB }, + { "lcd1", 0x01c0d000, 4 * KiB }, + { "ve", 0x01c0e000, 4 * KiB }, + { "mmc0", 0x01c0f000, 4 * KiB }, + { "mmc1", 0x01c10000, 4 * KiB }, + { "mmc2", 0x01c11000, 4 * KiB }, + { "sid", 0x01c14000, 1 * KiB }, + { "crypto", 0x01c15000, 4 * KiB }, + { "msgbox", 0x01c17000, 4 * KiB }, + { "spinlock", 0x01c18000, 4 * KiB }, + { "usb0-otg", 0x01c19000, 4 * KiB }, + { "usb0-phy", 0x01c1a000, 4 * KiB }, + { "usb1-phy", 0x01c1b000, 4 * KiB }, + { "usb2-phy", 0x01c1c000, 4 * KiB }, + { "usb3-phy", 0x01c1d000, 4 * KiB }, + { "smc", 0x01c1e000, 4 * KiB }, + { "ccu", 0x01c20000, 1 * KiB }, + { "pio", 0x01c20800, 1 * KiB }, + { "owa", 0x01c21000, 1 * KiB }, + { "pwm", 0x01c21400, 1 * KiB }, + { "keyadc", 0x01c21800, 1 * KiB }, + { "pcm0", 0x01c22000, 1 * KiB }, + { "pcm1", 0x01c22400, 1 * KiB }, + { "pcm2", 0x01c22800, 1 * KiB }, + { "audio", 0x01c22c00, 2 * KiB }, + { "smta", 0x01c23400, 1 * KiB }, + { "ths", 0x01c25000, 1 * KiB }, + { "uart0", 0x01c28000, 1 * KiB }, + { "uart1", 0x01c28400, 1 * KiB }, + { "uart2", 0x01c28800, 1 * KiB }, + { "uart3", 0x01c28c00, 1 * KiB }, + { "twi0", 0x01c2ac00, 1 * KiB }, + { "twi1", 0x01c2b000, 1 * KiB }, + { "twi2", 0x01c2b400, 1 * KiB }, + { "scr", 0x01c2c400, 1 * KiB }, + { "emac", 0x01c30000, 64 * KiB }, + { "gpu", 0x01c40000, 64 * KiB }, + { "hstmr", 0x01c60000, 4 * KiB }, + { "dramcom", 0x01c62000, 4 * KiB }, + { "dramctl0", 0x01c63000, 4 * KiB }, + { "dramphy0", 0x01c65000, 4 * KiB }, + { "spi0", 0x01c68000, 4 * KiB }, + { "spi1", 0x01c69000, 4 * KiB }, + { "csi", 0x01cb0000, 320 * KiB }, + { "tve", 0x01e00000, 64 * KiB }, + { "hdmi", 0x01ee0000, 128 * KiB }, + { "rtc", 0x01f00000, 1 * KiB }, + { "r_timer", 0x01f00800, 1 * KiB }, + { "r_intc", 0x01f00c00, 1 * KiB }, + { "r_wdog", 0x01f01000, 1 * KiB }, + { "r_prcm", 0x01f01400, 1 * KiB }, + { "r_twd", 0x01f01800, 1 * KiB }, + { "r_cpucfg", 0x01f01c00, 1 * KiB }, + { "r_cir-rx", 0x01f02000, 1 * KiB }, + { "r_twi", 0x01f02400, 1 * KiB }, + { "r_uart", 0x01f02800, 1 * KiB }, + { "r_pio", 0x01f02c00, 1 * KiB }, + { "r_pwm", 0x01f03800, 1 * KiB }, + { "core-dbg", 0x3f500000, 128 * KiB }, + { "tsgen-ro", 0x3f506000, 4 * KiB }, + { "tsgen-ctl", 0x3f507000, 4 * KiB }, + { "ddr-mem", 0x40000000, 2 * GiB }, + { "n-brom", 0xffff0000, 32 * KiB }, + { "s-brom", 0xffff0000, 64 * KiB } +}; + +/* Per Processor Interrupts */ +enum { + AW_H3_GIC_PPI_MAINT = 9, + AW_H3_GIC_PPI_HYPTIMER = 10, + AW_H3_GIC_PPI_VIRTTIMER = 11, + AW_H3_GIC_PPI_SECTIMER = 13, + AW_H3_GIC_PPI_PHYSTIMER = 14 +}; + +/* Shared Processor Interrupts */ +enum { + AW_H3_GIC_SPI_UART0 = 0, + AW_H3_GIC_SPI_UART1 = 1, + AW_H3_GIC_SPI_UART2 = 2, + AW_H3_GIC_SPI_UART3 = 3, + AW_H3_GIC_SPI_TIMER0 = 18, + AW_H3_GIC_SPI_TIMER1 = 19, +}; + +/* Allwinner H3 general constants */ +enum { + AW_H3_GIC_NUM_SPI = 128 +}; + +static void allwinner_h3_init(Object *obj) +{ + AwH3State *s = AW_H3(obj); + + s->memmap = allwinner_h3_memmap; + + for (int i = 0; i < AW_H3_NUM_CPUS; i++) { + object_initialize_child(obj, "cpu[*]", &s->cpus[i], sizeof(s->cpus[i]), + ARM_CPU_TYPE_NAME("cortex-a7"), + &error_abort, NULL); + } + + sysbus_init_child_obj(obj, "gic", &s->gic, sizeof(s->gic), + TYPE_ARM_GIC); + + sysbus_init_child_obj(obj, "timer", &s->timer, sizeof(s->timer), + TYPE_AW_A10_PIT); + object_property_add_alias(obj, "clk0-freq", OBJECT(&s->timer), + "clk0-freq", &error_abort); + object_property_add_alias(obj, "clk1-freq", OBJECT(&s->timer), + "clk1-freq", &error_abort); +} + +static void allwinner_h3_realize(DeviceState *dev, Error **errp) +{ + AwH3State *s = AW_H3(dev); + unsigned i; + + /* CPUs */ + for (i = 0; i < AW_H3_NUM_CPUS; i++) { + + /* Provide Power State Coordination Interface */ + qdev_prop_set_int32(DEVICE(&s->cpus[i]), "psci-conduit", + QEMU_PSCI_CONDUIT_HVC); + + /* Disable secondary CPUs */ + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "start-powered-off", + i > 0); + + /* All exception levels required */ + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "has_el3", true); + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "has_el2", true); + + /* Mark realized */ + qdev_init_nofail(DEVICE(&s->cpus[i])); + } + + /* Generic Interrupt Controller */ + qdev_prop_set_uint32(DEVICE(&s->gic), "num-irq", AW_H3_GIC_NUM_SPI + + GIC_INTERNAL); + qdev_prop_set_uint32(DEVICE(&s->gic), "revision", 2); + qdev_prop_set_uint32(DEVICE(&s->gic), "num-cpu", AW_H3_NUM_CPUS); + qdev_prop_set_bit(DEVICE(&s->gic), "has-security-extensions", false); + qdev_prop_set_bit(DEVICE(&s->gic), "has-virtualization-extensions", true); + qdev_init_nofail(DEVICE(&s->gic)); + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 0, s->memmap[AW_H3_GIC_DIST]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 1, s->memmap[AW_H3_GIC_CPU]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 2, s->memmap[AW_H3_GIC_HYP]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 3, s->memmap[AW_H3_GIC_VCPU]); + + /* + * Wire the outputs from each CPU's generic timer and the GICv3 + * maintenance interrupt signal to the appropriate GIC PPI inputs, + * and the GIC's IRQ/FIQ/VIRQ/VFIQ interrupt outputs to the CPU's inputs. + */ + for (i = 0; i < AW_H3_NUM_CPUS; i++) { + DeviceState *cpudev = DEVICE(&s->cpus[i]); + int ppibase = AW_H3_GIC_NUM_SPI + i * GIC_INTERNAL + GIC_NR_SGIS; + int irq; + /* + * Mapping from the output timer irq lines from the CPU to the + * GIC PPI inputs used for this board. + */ + const int timer_irq[] = { + [GTIMER_PHYS] = AW_H3_GIC_PPI_PHYSTIMER, + [GTIMER_VIRT] = AW_H3_GIC_PPI_VIRTTIMER, + [GTIMER_HYP] = AW_H3_GIC_PPI_HYPTIMER, + [GTIMER_SEC] = AW_H3_GIC_PPI_SECTIMER, + }; + + /* Connect CPU timer outputs to GIC PPI inputs */ + for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { + qdev_connect_gpio_out(cpudev, irq, + qdev_get_gpio_in(DEVICE(&s->gic), + ppibase + timer_irq[irq])); + } + + /* Connect GIC outputs to CPU interrupt inputs */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i, + qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + AW_H3_NUM_CPUS, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (2 * AW_H3_NUM_CPUS), + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (3 * AW_H3_NUM_CPUS), + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + + /* GIC maintenance signal */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (4 * AW_H3_NUM_CPUS), + qdev_get_gpio_in(DEVICE(&s->gic), + ppibase + AW_H3_GIC_PPI_MAINT)); + } + + /* Timer */ + qdev_init_nofail(DEVICE(&s->timer)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->timer), 0, s->memmap[AW_H3_PIT]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TIMER0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), 1, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TIMER1)); + + /* SRAM */ + memory_region_init_ram(&s->sram_a1, OBJECT(dev), "sram A1", + 64 * KiB, &error_abort); + memory_region_init_ram(&s->sram_a2, OBJECT(dev), "sram A2", + 32 * KiB, &error_abort); + memory_region_init_ram(&s->sram_c, OBJECT(dev), "sram C", + 44 * KiB, &error_abort); + memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_A1], + &s->sram_a1); + memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_A2], + &s->sram_a2); + memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_C], + &s->sram_c); + + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART0], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART0), + 115200, serial_hd(0), DEVICE_NATIVE_ENDIAN); + /* UART1 */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART1], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART1), + 115200, serial_hd(1), DEVICE_NATIVE_ENDIAN); + /* UART2 */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART2], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART2), + 115200, serial_hd(2), DEVICE_NATIVE_ENDIAN); + /* UART3 */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART3], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART3), + 115200, serial_hd(3), DEVICE_NATIVE_ENDIAN); + + /* Unimplemented devices */ + for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { + create_unimplemented_device(unimplemented[i].device_name, + unimplemented[i].base, + unimplemented[i].size); + } +} + +static void allwinner_h3_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = allwinner_h3_realize; + /* Reason: uses serial_hd() in realize function */ + dc->user_creatable = false; +} + +static const TypeInfo allwinner_h3_type_info = { + .name = TYPE_AW_H3, + .parent = TYPE_DEVICE, + .instance_size = sizeof(AwH3State), + .instance_init = allwinner_h3_init, + .class_init = allwinner_h3_class_init, +}; + +static void allwinner_h3_register_types(void) +{ + type_register_static(&allwinner_h3_type_info); +} + +type_init(allwinner_h3_register_types) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/*/allwinner* F: include/hw/*/allwinner* F: hw/arm/cubieboard.c +Allwinner-h3 +M: Niek Linnenbank <nieklinnenbank@gmail.com> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/*/allwinner-h3* +F: include/hw/*/allwinner-h3* + ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org 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_FSL_IMX25=y CONFIG_FSL_IMX7=y CONFIG_FSL_IMX6UL=y CONFIG_SEMIHOSTING=y +CONFIG_ALLWINNER_H3=y 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 ALLWINNER_A10 select SERIAL select UNIMP +config ALLWINNER_H3 + bool + select ALLWINNER_A10_PIT + select SERIAL + select ARM_TIMER + select ARM_GIC + select UNIMP + config RASPI bool select FRAMEBUFFER -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Xunlong Orange Pi PC is an Allwinner H3 System on Chip based embedded computer with mainline support in both U-Boot and Linux. The board comes with a Quad Core Cortex A7 @ 1.3GHz, 1GiB RAM, 100Mbit ethernet, USB, SD/MMC, USB, HDMI and various other I/O. This commit add support for the Xunlong Orange Pi PC machine. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: KONRAD Frederic <frederic.konrad@adacore.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Acked-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20200311221854.30370-3-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 2 +- hw/arm/orangepi.c | 92 ++++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 1 + 3 files changed, 94 insertions(+), 1 deletion(-) create mode 100644 hw/arm/orangepi.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_DIGIC) += digic.o obj-$(CONFIG_OMAP) += omap1.o omap2.o obj-$(CONFIG_STRONGARM) += strongarm.o obj-$(CONFIG_ALLWINNER_A10) += allwinner-a10.o cubieboard.o -obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3.o +obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3.o orangepi.o obj-$(CONFIG_RASPI) += bcm2835_peripherals.o bcm2836.o raspi.o obj-$(CONFIG_STM32F205_SOC) += stm32f205_soc.o obj-$(CONFIG_STM32F405_SOC) += stm32f405_soc.o diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ +/* + * Orange Pi emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "cpu.h" +#include "hw/sysbus.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/arm/allwinner-h3.h" +#include "sysemu/sysemu.h" + +static struct arm_boot_info orangepi_binfo = { + .nb_cpus = AW_H3_NUM_CPUS, +}; + +static void orangepi_init(MachineState *machine) +{ + AwH3State *h3; + + /* BIOS is not supported by this board */ + if (bios_name) { + error_report("BIOS not supported for this machine"); + exit(1); + } + + /* This board has fixed size RAM */ + if (machine->ram_size != 1 * GiB) { + error_report("This machine can only be used with 1GiB of RAM"); + exit(1); + } + + /* Only allow Cortex-A7 for this board */ + if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a7")) != 0) { + error_report("This board can only be used with cortex-a7 CPU"); + exit(1); + } + + h3 = AW_H3(object_new(TYPE_AW_H3)); + object_property_add_child(OBJECT(machine), "soc", OBJECT(h3), + &error_abort); + object_unref(OBJECT(h3)); + + /* Setup timer properties */ + object_property_set_int(OBJECT(h3), 32768, "clk0-freq", + &error_abort); + object_property_set_int(OBJECT(h3), 24 * 1000 * 1000, "clk1-freq", + &error_abort); + + /* Mark H3 object realized */ + object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); + + /* SDRAM */ + memory_region_add_subregion(get_system_memory(), h3->memmap[AW_H3_SDRAM], + machine->ram); + + orangepi_binfo.loader_start = h3->memmap[AW_H3_SDRAM]; + orangepi_binfo.ram_size = machine->ram_size; + arm_load_kernel(ARM_CPU(first_cpu), machine, &orangepi_binfo); +} + +static void orangepi_machine_init(MachineClass *mc) +{ + mc->desc = "Orange Pi PC"; + mc->init = orangepi_init; + mc->min_cpus = AW_H3_NUM_CPUS; + mc->max_cpus = AW_H3_NUM_CPUS; + mc->default_cpus = AW_H3_NUM_CPUS; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a7"); + mc->default_ram_size = 1 * GiB; + mc->default_ram_id = "orangepi.ram"; +} + +DEFINE_MACHINE("orangepi-pc", orangepi_machine_init) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Maintained F: hw/*/allwinner-h3* F: include/hw/*/allwinner-h3* +F: hw/arm/orangepi.c ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Clock Control Unit is responsible for clock signal generation, configuration and distribution in the Allwinner H3 System on Chip. This commit adds support for the Clock Control Unit which emulates a simple read/write register interface. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-4-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-h3-ccu.h | 66 ++++++++ hw/arm/allwinner-h3.c | 9 +- hw/misc/allwinner-h3-ccu.c | 242 +++++++++++++++++++++++++++++ 5 files changed, 320 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-h3-ccu.h create mode 100644 hw/misc/allwinner-h3-ccu.c 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_MACIO) += macio/ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o common-obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" +#include "hw/misc/allwinner-h3-ccu.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A1, AW_H3_SRAM_A2, AW_H3_SRAM_C, + AW_H3_CCU, AW_H3_PIT, AW_H3_UART0, AW_H3_UART1, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { ARMCPU cpus[AW_H3_NUM_CPUS]; const hwaddr *memmap; AwA10PITState timer; + AwH3ClockCtlState ccu; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-h3-ccu.h b/include/hw/misc/allwinner-h3-ccu.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-h3-ccu.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 Clock Control Unit emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_H3_CCU_H +#define HW_MISC_ALLWINNER_H3_CCU_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by CCU device */ +#define AW_H3_CCU_IOSIZE (0x400) + +/** Total number of known registers */ +#define AW_H3_CCU_REGS_NUM (AW_H3_CCU_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_H3_CCU "allwinner-h3-ccu" +#define AW_H3_CCU(obj) \ + OBJECT_CHECK(AwH3ClockCtlState, (obj), TYPE_AW_H3_CCU) + +/** @} */ + +/** + * Allwinner H3 CCU object instance state. + */ +typedef struct AwH3ClockCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_H3_CCU_REGS_NUM]; + +} AwH3ClockCtlState; + +#endif /* HW_MISC_ALLWINNER_H3_CCU_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A1] = 0x00000000, [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_CCU] = 0x01c20000, [AW_H3_PIT] = 0x01c20c00, [AW_H3_UART0] = 0x01c28000, [AW_H3_UART1] = 0x01c28400, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "usb2-phy", 0x01c1c000, 4 * KiB }, { "usb3-phy", 0x01c1d000, 4 * KiB }, { "smc", 0x01c1e000, 4 * KiB }, - { "ccu", 0x01c20000, 1 * KiB }, { "pio", 0x01c20800, 1 * KiB }, { "owa", 0x01c21000, 1 * KiB }, { "pwm", 0x01c21400, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "clk0-freq", &error_abort); object_property_add_alias(obj, "clk1-freq", OBJECT(&s->timer), "clk1-freq", &error_abort); + + sysbus_init_child_obj(obj, "ccu", &s->ccu, sizeof(s->ccu), + TYPE_AW_H3_CCU); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_C], &s->sram_c); + /* Clock Control Unit */ + qdev_init_nofail(DEVICE(&s->ccu)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_H3_CCU]); + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART0], 2, qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART0), diff --git a/hw/misc/allwinner-h3-ccu.c b/hw/misc/allwinner-h3-ccu.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-h3-ccu.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 Clock Control Unit emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-h3-ccu.h" + +/* CCU register offsets */ +enum { + REG_PLL_CPUX = 0x0000, /* PLL CPUX Control */ + REG_PLL_AUDIO = 0x0008, /* PLL Audio Control */ + REG_PLL_VIDEO = 0x0010, /* PLL Video Control */ + REG_PLL_VE = 0x0018, /* PLL VE Control */ + REG_PLL_DDR = 0x0020, /* PLL DDR Control */ + REG_PLL_PERIPH0 = 0x0028, /* PLL Peripherals 0 Control */ + REG_PLL_GPU = 0x0038, /* PLL GPU Control */ + REG_PLL_PERIPH1 = 0x0044, /* PLL Peripherals 1 Control */ + REG_PLL_DE = 0x0048, /* PLL Display Engine Control */ + REG_CPUX_AXI = 0x0050, /* CPUX/AXI Configuration */ + REG_APB1 = 0x0054, /* ARM Peripheral Bus 1 Config */ + REG_APB2 = 0x0058, /* ARM Peripheral Bus 2 Config */ + REG_DRAM_CFG = 0x00F4, /* DRAM Configuration */ + REG_MBUS = 0x00FC, /* MBUS Reset */ + REG_PLL_TIME0 = 0x0200, /* PLL Stable Time 0 */ + REG_PLL_TIME1 = 0x0204, /* PLL Stable Time 1 */ + REG_PLL_CPUX_BIAS = 0x0220, /* PLL CPUX Bias */ + REG_PLL_AUDIO_BIAS = 0x0224, /* PLL Audio Bias */ + REG_PLL_VIDEO_BIAS = 0x0228, /* PLL Video Bias */ + REG_PLL_VE_BIAS = 0x022C, /* PLL VE Bias */ + REG_PLL_DDR_BIAS = 0x0230, /* PLL DDR Bias */ + REG_PLL_PERIPH0_BIAS = 0x0234, /* PLL Peripherals 0 Bias */ + REG_PLL_GPU_BIAS = 0x023C, /* PLL GPU Bias */ + REG_PLL_PERIPH1_BIAS = 0x0244, /* PLL Peripherals 1 Bias */ + REG_PLL_DE_BIAS = 0x0248, /* PLL Display Engine Bias */ + REG_PLL_CPUX_TUNING = 0x0250, /* PLL CPUX Tuning */ + REG_PLL_DDR_TUNING = 0x0260, /* PLL DDR Tuning */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* CCU register flags */ +enum { + REG_DRAM_CFG_UPDATE = (1 << 16), +}; + +enum { + REG_PLL_ENABLE = (1 << 31), + REG_PLL_LOCK = (1 << 28), +}; + + +/* CCU register reset values */ +enum { + REG_PLL_CPUX_RST = 0x00001000, + REG_PLL_AUDIO_RST = 0x00035514, + REG_PLL_VIDEO_RST = 0x03006207, + REG_PLL_VE_RST = 0x03006207, + REG_PLL_DDR_RST = 0x00001000, + REG_PLL_PERIPH0_RST = 0x00041811, + REG_PLL_GPU_RST = 0x03006207, + REG_PLL_PERIPH1_RST = 0x00041811, + REG_PLL_DE_RST = 0x03006207, + REG_CPUX_AXI_RST = 0x00010000, + REG_APB1_RST = 0x00001010, + REG_APB2_RST = 0x01000000, + REG_DRAM_CFG_RST = 0x00000000, + REG_MBUS_RST = 0x80000000, + REG_PLL_TIME0_RST = 0x000000FF, + REG_PLL_TIME1_RST = 0x000000FF, + REG_PLL_CPUX_BIAS_RST = 0x08100200, + REG_PLL_AUDIO_BIAS_RST = 0x10100000, + REG_PLL_VIDEO_BIAS_RST = 0x10100000, + REG_PLL_VE_BIAS_RST = 0x10100000, + REG_PLL_DDR_BIAS_RST = 0x81104000, + REG_PLL_PERIPH0_BIAS_RST = 0x10100010, + REG_PLL_GPU_BIAS_RST = 0x10100000, + REG_PLL_PERIPH1_BIAS_RST = 0x10100010, + REG_PLL_DE_BIAS_RST = 0x10100000, + REG_PLL_CPUX_TUNING_RST = 0x0A101000, + REG_PLL_DDR_TUNING_RST = 0x14880000, +}; + +static uint64_t allwinner_h3_ccu_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3ClockCtlState *s = AW_H3_CCU(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case 0x308 ... AW_H3_CCU_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_h3_ccu_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3ClockCtlState *s = AW_H3_CCU(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_DRAM_CFG: /* DRAM Configuration */ + val &= ~REG_DRAM_CFG_UPDATE; + break; + case REG_PLL_CPUX: /* PLL CPUX Control */ + case REG_PLL_AUDIO: /* PLL Audio Control */ + case REG_PLL_VIDEO: /* PLL Video Control */ + case REG_PLL_VE: /* PLL VE Control */ + case REG_PLL_DDR: /* PLL DDR Control */ + case REG_PLL_PERIPH0: /* PLL Peripherals 0 Control */ + case REG_PLL_GPU: /* PLL GPU Control */ + case REG_PLL_PERIPH1: /* PLL Peripherals 1 Control */ + case REG_PLL_DE: /* PLL Display Engine Control */ + if (val & REG_PLL_ENABLE) { + val |= REG_PLL_LOCK; + } + break; + case 0x308 ... AW_H3_CCU_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_h3_ccu_ops = { + .read = allwinner_h3_ccu_read, + .write = allwinner_h3_ccu_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_h3_ccu_reset(DeviceState *dev) +{ + AwH3ClockCtlState *s = AW_H3_CCU(dev); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_PLL_CPUX)] = REG_PLL_CPUX_RST; + s->regs[REG_INDEX(REG_PLL_AUDIO)] = REG_PLL_AUDIO_RST; + s->regs[REG_INDEX(REG_PLL_VIDEO)] = REG_PLL_VIDEO_RST; + s->regs[REG_INDEX(REG_PLL_VE)] = REG_PLL_VE_RST; + s->regs[REG_INDEX(REG_PLL_DDR)] = REG_PLL_DDR_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH0)] = REG_PLL_PERIPH0_RST; + s->regs[REG_INDEX(REG_PLL_GPU)] = REG_PLL_GPU_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH1)] = REG_PLL_PERIPH1_RST; + s->regs[REG_INDEX(REG_PLL_DE)] = REG_PLL_DE_RST; + s->regs[REG_INDEX(REG_CPUX_AXI)] = REG_CPUX_AXI_RST; + s->regs[REG_INDEX(REG_APB1)] = REG_APB1_RST; + s->regs[REG_INDEX(REG_APB2)] = REG_APB2_RST; + s->regs[REG_INDEX(REG_DRAM_CFG)] = REG_DRAM_CFG_RST; + s->regs[REG_INDEX(REG_MBUS)] = REG_MBUS_RST; + s->regs[REG_INDEX(REG_PLL_TIME0)] = REG_PLL_TIME0_RST; + s->regs[REG_INDEX(REG_PLL_TIME1)] = REG_PLL_TIME1_RST; + s->regs[REG_INDEX(REG_PLL_CPUX_BIAS)] = REG_PLL_CPUX_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_AUDIO_BIAS)] = REG_PLL_AUDIO_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_VIDEO_BIAS)] = REG_PLL_VIDEO_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_VE_BIAS)] = REG_PLL_VE_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_DDR_BIAS)] = REG_PLL_DDR_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH0_BIAS)] = REG_PLL_PERIPH0_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_GPU_BIAS)] = REG_PLL_GPU_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH1_BIAS)] = REG_PLL_PERIPH1_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_DE_BIAS)] = REG_PLL_DE_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_CPUX_TUNING)] = REG_PLL_CPUX_TUNING_RST; + s->regs[REG_INDEX(REG_PLL_DDR_TUNING)] = REG_PLL_DDR_TUNING_RST; +} + +static void allwinner_h3_ccu_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwH3ClockCtlState *s = AW_H3_CCU(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_h3_ccu_ops, s, + TYPE_AW_H3_CCU, AW_H3_CCU_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_h3_ccu_vmstate = { + .name = "allwinner-h3-ccu", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwH3ClockCtlState, AW_H3_CCU_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_h3_ccu_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_h3_ccu_reset; + dc->vmsd = &allwinner_h3_ccu_vmstate; +} + +static const TypeInfo allwinner_h3_ccu_info = { + .name = TYPE_AW_H3_CCU, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_h3_ccu_init, + .instance_size = sizeof(AwH3ClockCtlState), + .class_init = allwinner_h3_ccu_class_init, +}; + +static void allwinner_h3_ccu_register(void) +{ + type_register_static(&allwinner_h3_ccu_info); +} + +type_init(allwinner_h3_ccu_register) -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner H3 System on Chip contains multiple USB 2.0 bus connections which provide software access using the Enhanced Host Controller Interface (EHCI) and Open Host Controller Interface (OHCI) interfaces. This commit adds support for both interfaces in the Allwinner H3 System on Chip. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Gerd Hoffmann <kraxel@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-5-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-ehci.h | 1 + include/hw/arm/allwinner-h3.h | 8 +++++++ hw/arm/allwinner-h3.c | 44 +++++++++++++++++++++++++++++++++++ hw/usb/hcd-ehci-sysbus.c | 17 ++++++++++++++ hw/arm/Kconfig | 2 ++ 5 files changed, 72 insertions(+) diff --git a/hw/usb/hcd-ehci.h b/hw/usb/hcd-ehci.h index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-ehci.h +++ b/hw/usb/hcd-ehci.h @@ -XXX,XX +XXX,XX @@ typedef struct EHCIPCIState { #define TYPE_SYS_BUS_EHCI "sysbus-ehci-usb" #define TYPE_PLATFORM_EHCI "platform-ehci-usb" #define TYPE_EXYNOS4210_EHCI "exynos4210-ehci-usb" +#define TYPE_AW_H3_EHCI "aw-h3-ehci-usb" #define TYPE_TEGRA2_EHCI "tegra2-ehci-usb" #define TYPE_PPC4xx_EHCI "ppc4xx-ehci-usb" #define TYPE_FUSBH200_EHCI "fusbh200-ehci-usb" diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A1, AW_H3_SRAM_A2, AW_H3_SRAM_C, + AW_H3_EHCI0, + AW_H3_OHCI0, + AW_H3_EHCI1, + AW_H3_OHCI1, + AW_H3_EHCI2, + AW_H3_OHCI2, + AW_H3_EHCI3, + AW_H3_OHCI3, AW_H3_CCU, AW_H3_PIT, AW_H3_UART0, diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/char/serial.h" #include "hw/misc/unimp.h" +#include "hw/usb/hcd-ehci.h" #include "sysemu/sysemu.h" #include "hw/arm/allwinner-h3.h" @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A1] = 0x00000000, [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_EHCI0] = 0x01c1a000, + [AW_H3_OHCI0] = 0x01c1a400, + [AW_H3_EHCI1] = 0x01c1b000, + [AW_H3_OHCI1] = 0x01c1b400, + [AW_H3_EHCI2] = 0x01c1c000, + [AW_H3_OHCI2] = 0x01c1c400, + [AW_H3_EHCI3] = 0x01c1d000, + [AW_H3_OHCI3] = 0x01c1d400, [AW_H3_CCU] = 0x01c20000, [AW_H3_PIT] = 0x01c20c00, [AW_H3_UART0] = 0x01c28000, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART3 = 3, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, + AW_H3_GIC_SPI_EHCI0 = 72, + AW_H3_GIC_SPI_OHCI0 = 73, + AW_H3_GIC_SPI_EHCI1 = 74, + AW_H3_GIC_SPI_OHCI1 = 75, + AW_H3_GIC_SPI_EHCI2 = 76, + AW_H3_GIC_SPI_OHCI2 = 77, + AW_H3_GIC_SPI_EHCI3 = 78, + AW_H3_GIC_SPI_OHCI3 = 79, }; /* Allwinner H3 general constants */ @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->ccu)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_H3_CCU]); + /* Universal Serial Bus */ + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI0)); + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI1], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI1)); + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI2], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI2)); + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI3], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI3)); + + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI0], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI0)); + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI1], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI1)); + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI2], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI2)); + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI3], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI3)); + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART0], 2, qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART0), diff --git a/hw/usb/hcd-ehci-sysbus.c b/hw/usb/hcd-ehci-sysbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-ehci-sysbus.c +++ b/hw/usb/hcd-ehci-sysbus.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo ehci_exynos4210_type_info = { .class_init = ehci_exynos4210_class_init, }; +static void ehci_aw_h3_class_init(ObjectClass *oc, void *data) +{ + SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(oc); + DeviceClass *dc = DEVICE_CLASS(oc); + + sec->capsbase = 0x0; + sec->opregbase = 0x10; + set_bit(DEVICE_CATEGORY_USB, dc->categories); +} + +static const TypeInfo ehci_aw_h3_type_info = { + .name = TYPE_AW_H3_EHCI, + .parent = TYPE_SYS_BUS_EHCI, + .class_init = ehci_aw_h3_class_init, +}; + static void ehci_tegra2_class_init(ObjectClass *oc, void *data) { SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static void ehci_sysbus_register_types(void) type_register_static(&ehci_type_info); type_register_static(&ehci_platform_type_info); type_register_static(&ehci_exynos4210_type_info); + type_register_static(&ehci_aw_h3_type_info); type_register_static(&ehci_tegra2_type_info); type_register_static(&ehci_ppc4xx_type_info); type_register_static(&ehci_fusbh200_type_info); 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 ALLWINNER_H3 select ARM_TIMER select ARM_GIC select UNIMP + select USB_OHCI + select USB_EHCI_SYSBUS config RASPI bool -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner H3 System on Chip has an System Control module that provides system wide generic controls and device information. This commit adds support for the Allwinner H3 System Control module. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-6-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-h3-sysctrl.h | 67 ++++++++++++ hw/arm/allwinner-h3.c | 9 +- hw/misc/allwinner-h3-sysctrl.c | 140 +++++++++++++++++++++++++ 5 files changed, 219 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-h3-sysctrl.h create mode 100644 hw/misc/allwinner-h3-sysctrl.c 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_MACIO) += macio/ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o common-obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" +#include "hw/misc/allwinner-h3-sysctrl.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A1, AW_H3_SRAM_A2, AW_H3_SRAM_C, + AW_H3_SYSCTRL, AW_H3_EHCI0, AW_H3_OHCI0, AW_H3_EHCI1, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { const hwaddr *memmap; AwA10PITState timer; AwH3ClockCtlState ccu; + AwH3SysCtrlState sysctrl; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-h3-sysctrl.h b/include/hw/misc/allwinner-h3-sysctrl.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-h3-sysctrl.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System Control emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_H3_SYSCTRL_H +#define HW_MISC_ALLWINNER_H3_SYSCTRL_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Highest register address used by System Control device */ +#define AW_H3_SYSCTRL_REGS_MAXADDR (0x30) + +/** Total number of known registers */ +#define AW_H3_SYSCTRL_REGS_NUM ((AW_H3_SYSCTRL_REGS_MAXADDR / \ + sizeof(uint32_t)) + 1) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_H3_SYSCTRL "allwinner-h3-sysctrl" +#define AW_H3_SYSCTRL(obj) \ + OBJECT_CHECK(AwH3SysCtrlState, (obj), TYPE_AW_H3_SYSCTRL) + +/** @} */ + +/** + * Allwinner H3 System Control object instance state + */ +typedef struct AwH3SysCtrlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_H3_SYSCTRL_REGS_NUM]; + +} AwH3SysCtrlState; + +#endif /* HW_MISC_ALLWINNER_H3_SYSCTRL_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A1] = 0x00000000, [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_SYSCTRL] = 0x01c00000, [AW_H3_EHCI0] = 0x01c1a000, [AW_H3_OHCI0] = 0x01c1a400, [AW_H3_EHCI1] = 0x01c1b000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { } unimplemented[] = { { "d-engine", 0x01000000, 4 * MiB }, { "d-inter", 0x01400000, 128 * KiB }, - { "syscon", 0x01c00000, 4 * KiB }, { "dma", 0x01c02000, 4 * KiB }, { "nfdc", 0x01c03000, 4 * KiB }, { "ts", 0x01c06000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "ccu", &s->ccu, sizeof(s->ccu), TYPE_AW_H3_CCU); + + sysbus_init_child_obj(obj, "sysctrl", &s->sysctrl, sizeof(s->sysctrl), + TYPE_AW_H3_SYSCTRL); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->ccu)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_H3_CCU]); + /* System Control */ + qdev_init_nofail(DEVICE(&s->sysctrl)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->sysctrl), 0, s->memmap[AW_H3_SYSCTRL]); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/misc/allwinner-h3-sysctrl.c b/hw/misc/allwinner-h3-sysctrl.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-h3-sysctrl.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System Control emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-h3-sysctrl.h" + +/* System Control register offsets */ +enum { + REG_VER = 0x24, /* Version */ + REG_EMAC_PHY_CLK = 0x30, /* EMAC PHY Clock */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* System Control register reset values */ +enum { + REG_VER_RST = 0x0, + REG_EMAC_PHY_CLK_RST = 0x58000, +}; + +static uint64_t allwinner_h3_sysctrl_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3SysCtrlState *s = AW_H3_SYSCTRL(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_SYSCTRL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_h3_sysctrl_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3SysCtrlState *s = AW_H3_SYSCTRL(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_SYSCTRL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_VER: /* Version */ + break; + default: + s->regs[idx] = (uint32_t) val; + break; + } +} + +static const MemoryRegionOps allwinner_h3_sysctrl_ops = { + .read = allwinner_h3_sysctrl_read, + .write = allwinner_h3_sysctrl_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_h3_sysctrl_reset(DeviceState *dev) +{ + AwH3SysCtrlState *s = AW_H3_SYSCTRL(dev); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_VER)] = REG_VER_RST; + s->regs[REG_INDEX(REG_EMAC_PHY_CLK)] = REG_EMAC_PHY_CLK_RST; +} + +static void allwinner_h3_sysctrl_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwH3SysCtrlState *s = AW_H3_SYSCTRL(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_h3_sysctrl_ops, s, + TYPE_AW_H3_SYSCTRL, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_h3_sysctrl_vmstate = { + .name = "allwinner-h3-sysctrl", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwH3SysCtrlState, AW_H3_SYSCTRL_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_h3_sysctrl_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_h3_sysctrl_reset; + dc->vmsd = &allwinner_h3_sysctrl_vmstate; +} + +static const TypeInfo allwinner_h3_sysctrl_info = { + .name = TYPE_AW_H3_SYSCTRL, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_h3_sysctrl_init, + .instance_size = sizeof(AwH3SysCtrlState), + .class_init = allwinner_h3_sysctrl_class_init, +}; + +static void allwinner_h3_sysctrl_register(void) +{ + type_register_static(&allwinner_h3_sysctrl_info); +} + +type_init(allwinner_h3_sysctrl_register) -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Various Allwinner System on Chip designs contain multiple processors that can be configured and reset using the generic CPU Configuration module interface. This commit adds support for the Allwinner CPU configuration interface which emulates the following features: * CPU reset * CPU status Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-7-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-cpucfg.h | 52 ++++++ hw/arm/allwinner-h3.c | 9 +- hw/misc/allwinner-cpucfg.c | 282 +++++++++++++++++++++++++++++ hw/misc/trace-events | 5 + 6 files changed, 351 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-cpucfg.h create mode 100644 hw/misc/allwinner-cpucfg.c 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-$(CONFIG_MACIO) += macio/ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o +obj-$(CONFIG_ALLWINNER_H3) += allwinner-cpucfg.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" +#include "hw/misc/allwinner-cpucfg.h" #include "hw/misc/allwinner-h3-sysctrl.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_CPU, AW_H3_GIC_HYP, AW_H3_GIC_VCPU, + AW_H3_CPUCFG, AW_H3_SDRAM }; @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { const hwaddr *memmap; AwA10PITState timer; AwH3ClockCtlState ccu; + AwCpuCfgState cpucfg; AwH3SysCtrlState sysctrl; GICState gic; MemoryRegion sram_a1; diff --git a/include/hw/misc/allwinner-cpucfg.h b/include/hw/misc/allwinner-cpucfg.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-cpucfg.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner CPU Configuration Module emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_CPUCFG_H +#define HW_MISC_ALLWINNER_CPUCFG_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * Object model + * @{ + */ + +#define TYPE_AW_CPUCFG "allwinner-cpucfg" +#define AW_CPUCFG(obj) \ + OBJECT_CHECK(AwCpuCfgState, (obj), TYPE_AW_CPUCFG) + +/** @} */ + +/** + * Allwinner CPU Configuration Module instance state + */ +typedef struct AwCpuCfgState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + MemoryRegion iomem; + uint32_t gen_ctrl; + uint32_t super_standby; + uint32_t entry_addr; + +} AwCpuCfgState; + +#endif /* HW_MISC_ALLWINNER_CPUCFG_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, [AW_H3_GIC_VCPU] = 0x01c86000, + [AW_H3_CPUCFG] = 0x01f01c00, [AW_H3_SDRAM] = 0x40000000 }; @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "r_wdog", 0x01f01000, 1 * KiB }, { "r_prcm", 0x01f01400, 1 * KiB }, { "r_twd", 0x01f01800, 1 * KiB }, - { "r_cpucfg", 0x01f01c00, 1 * KiB }, { "r_cir-rx", 0x01f02000, 1 * KiB }, { "r_twi", 0x01f02400, 1 * KiB }, { "r_uart", 0x01f02800, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "sysctrl", &s->sysctrl, sizeof(s->sysctrl), TYPE_AW_H3_SYSCTRL); + + sysbus_init_child_obj(obj, "cpucfg", &s->cpucfg, sizeof(s->cpucfg), + TYPE_AW_CPUCFG); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->sysctrl)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->sysctrl), 0, s->memmap[AW_H3_SYSCTRL]); + /* CPU Configuration */ + qdev_init_nofail(DEVICE(&s->cpucfg)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->cpucfg), 0, s->memmap[AW_H3_CPUCFG]); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/misc/allwinner-cpucfg.c b/hw/misc/allwinner-cpucfg.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-cpucfg.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner CPU Configuration Module emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/error-report.h" +#include "qemu/timer.h" +#include "hw/core/cpu.h" +#include "target/arm/arm-powerctl.h" +#include "target/arm/cpu.h" +#include "hw/misc/allwinner-cpucfg.h" +#include "trace.h" + +/* CPUCFG register offsets */ +enum { + REG_CPUS_RST_CTRL = 0x0000, /* CPUs Reset Control */ + REG_CPU0_RST_CTRL = 0x0040, /* CPU#0 Reset Control */ + REG_CPU0_CTRL = 0x0044, /* CPU#0 Control */ + REG_CPU0_STATUS = 0x0048, /* CPU#0 Status */ + REG_CPU1_RST_CTRL = 0x0080, /* CPU#1 Reset Control */ + REG_CPU1_CTRL = 0x0084, /* CPU#1 Control */ + REG_CPU1_STATUS = 0x0088, /* CPU#1 Status */ + REG_CPU2_RST_CTRL = 0x00C0, /* CPU#2 Reset Control */ + REG_CPU2_CTRL = 0x00C4, /* CPU#2 Control */ + REG_CPU2_STATUS = 0x00C8, /* CPU#2 Status */ + REG_CPU3_RST_CTRL = 0x0100, /* CPU#3 Reset Control */ + REG_CPU3_CTRL = 0x0104, /* CPU#3 Control */ + REG_CPU3_STATUS = 0x0108, /* CPU#3 Status */ + REG_CPU_SYS_RST = 0x0140, /* CPU System Reset */ + REG_CLK_GATING = 0x0144, /* CPU Clock Gating */ + REG_GEN_CTRL = 0x0184, /* General Control */ + REG_SUPER_STANDBY = 0x01A0, /* Super Standby Flag */ + REG_ENTRY_ADDR = 0x01A4, /* Reset Entry Address */ + REG_DBG_EXTERN = 0x01E4, /* Debug External */ + REG_CNT64_CTRL = 0x0280, /* 64-bit Counter Control */ + REG_CNT64_LOW = 0x0284, /* 64-bit Counter Low */ + REG_CNT64_HIGH = 0x0288, /* 64-bit Counter High */ +}; + +/* CPUCFG register flags */ +enum { + CPUX_RESET_RELEASED = ((1 << 1) | (1 << 0)), + CPUX_STATUS_SMP = (1 << 0), + CPU_SYS_RESET_RELEASED = (1 << 0), + CLK_GATING_ENABLE = ((1 << 8) | 0xF), +}; + +/* CPUCFG register reset values */ +enum { + REG_CLK_GATING_RST = 0x0000010F, + REG_GEN_CTRL_RST = 0x00000020, + REG_SUPER_STANDBY_RST = 0x0, + REG_CNT64_CTRL_RST = 0x0, +}; + +/* CPUCFG constants */ +enum { + CPU_EXCEPTION_LEVEL_ON_RESET = 3, /* EL3 */ +}; + +static void allwinner_cpucfg_cpu_reset(AwCpuCfgState *s, uint8_t cpu_id) +{ + int ret; + + trace_allwinner_cpucfg_cpu_reset(cpu_id, s->entry_addr); + + ARMCPU *target_cpu = ARM_CPU(arm_get_cpu_by_id(cpu_id)); + if (!target_cpu) { + /* + * Called with a bogus value for cpu_id. Guest error will + * already have been logged, we can simply return here. + */ + return; + } + bool target_aa64 = arm_feature(&target_cpu->env, ARM_FEATURE_AARCH64); + + ret = arm_set_cpu_on(cpu_id, s->entry_addr, 0, + CPU_EXCEPTION_LEVEL_ON_RESET, target_aa64); + if (ret != QEMU_ARM_POWERCTL_RET_SUCCESS) { + error_report("%s: failed to bring up CPU %d: err %d", + __func__, cpu_id, ret); + return; + } +} + +static uint64_t allwinner_cpucfg_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwCpuCfgState *s = AW_CPUCFG(opaque); + uint64_t val = 0; + + switch (offset) { + case REG_CPUS_RST_CTRL: /* CPUs Reset Control */ + case REG_CPU_SYS_RST: /* CPU System Reset */ + val = CPU_SYS_RESET_RELEASED; + break; + case REG_CPU0_RST_CTRL: /* CPU#0 Reset Control */ + case REG_CPU1_RST_CTRL: /* CPU#1 Reset Control */ + case REG_CPU2_RST_CTRL: /* CPU#2 Reset Control */ + case REG_CPU3_RST_CTRL: /* CPU#3 Reset Control */ + val = CPUX_RESET_RELEASED; + break; + case REG_CPU0_CTRL: /* CPU#0 Control */ + case REG_CPU1_CTRL: /* CPU#1 Control */ + case REG_CPU2_CTRL: /* CPU#2 Control */ + case REG_CPU3_CTRL: /* CPU#3 Control */ + val = 0; + break; + case REG_CPU0_STATUS: /* CPU#0 Status */ + case REG_CPU1_STATUS: /* CPU#1 Status */ + case REG_CPU2_STATUS: /* CPU#2 Status */ + case REG_CPU3_STATUS: /* CPU#3 Status */ + val = CPUX_STATUS_SMP; + break; + case REG_CLK_GATING: /* CPU Clock Gating */ + val = CLK_GATING_ENABLE; + break; + case REG_GEN_CTRL: /* General Control */ + val = s->gen_ctrl; + break; + case REG_SUPER_STANDBY: /* Super Standby Flag */ + val = s->super_standby; + break; + case REG_ENTRY_ADDR: /* Reset Entry Address */ + val = s->entry_addr; + break; + case REG_DBG_EXTERN: /* Debug External */ + case REG_CNT64_CTRL: /* 64-bit Counter Control */ + case REG_CNT64_LOW: /* 64-bit Counter Low */ + case REG_CNT64_HIGH: /* 64-bit Counter High */ + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register at 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + trace_allwinner_cpucfg_read(offset, val, size); + + return val; +} + +static void allwinner_cpucfg_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwCpuCfgState *s = AW_CPUCFG(opaque); + + trace_allwinner_cpucfg_write(offset, val, size); + + switch (offset) { + case REG_CPUS_RST_CTRL: /* CPUs Reset Control */ + case REG_CPU_SYS_RST: /* CPU System Reset */ + break; + case REG_CPU0_RST_CTRL: /* CPU#0 Reset Control */ + case REG_CPU1_RST_CTRL: /* CPU#1 Reset Control */ + case REG_CPU2_RST_CTRL: /* CPU#2 Reset Control */ + case REG_CPU3_RST_CTRL: /* CPU#3 Reset Control */ + if (val) { + allwinner_cpucfg_cpu_reset(s, (offset - REG_CPU0_RST_CTRL) >> 6); + } + break; + case REG_CPU0_CTRL: /* CPU#0 Control */ + case REG_CPU1_CTRL: /* CPU#1 Control */ + case REG_CPU2_CTRL: /* CPU#2 Control */ + case REG_CPU3_CTRL: /* CPU#3 Control */ + case REG_CPU0_STATUS: /* CPU#0 Status */ + case REG_CPU1_STATUS: /* CPU#1 Status */ + case REG_CPU2_STATUS: /* CPU#2 Status */ + case REG_CPU3_STATUS: /* CPU#3 Status */ + case REG_CLK_GATING: /* CPU Clock Gating */ + break; + case REG_GEN_CTRL: /* General Control */ + s->gen_ctrl = val; + break; + case REG_SUPER_STANDBY: /* Super Standby Flag */ + s->super_standby = val; + break; + case REG_ENTRY_ADDR: /* Reset Entry Address */ + s->entry_addr = val; + break; + case REG_DBG_EXTERN: /* Debug External */ + case REG_CNT64_CTRL: /* 64-bit Counter Control */ + case REG_CNT64_LOW: /* 64-bit Counter Low */ + case REG_CNT64_HIGH: /* 64-bit Counter High */ + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register at 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } +} + +static const MemoryRegionOps allwinner_cpucfg_ops = { + .read = allwinner_cpucfg_read, + .write = allwinner_cpucfg_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_cpucfg_reset(DeviceState *dev) +{ + AwCpuCfgState *s = AW_CPUCFG(dev); + + /* Set default values for registers */ + s->gen_ctrl = REG_GEN_CTRL_RST; + s->super_standby = REG_SUPER_STANDBY_RST; + s->entry_addr = 0; +} + +static void allwinner_cpucfg_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwCpuCfgState *s = AW_CPUCFG(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_cpucfg_ops, s, + TYPE_AW_CPUCFG, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_cpucfg_vmstate = { + .name = "allwinner-cpucfg", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(gen_ctrl, AwCpuCfgState), + VMSTATE_UINT32(super_standby, AwCpuCfgState), + VMSTATE_UINT32(entry_addr, AwCpuCfgState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_cpucfg_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_cpucfg_reset; + dc->vmsd = &allwinner_cpucfg_vmstate; +} + +static const TypeInfo allwinner_cpucfg_info = { + .name = TYPE_AW_CPUCFG, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_cpucfg_init, + .instance_size = sizeof(AwCpuCfgState), + .class_init = allwinner_cpucfg_class_init, +}; + +static void allwinner_cpucfg_register(void) +{ + type_register_static(&allwinner_cpucfg_info); +} + +type_init(allwinner_cpucfg_register) 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 @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-cpucfg.c +allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_addr 0x%" PRIu32 +allwinner_cpucfg_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_cpucfg_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" ecc_mem_writel_mdr(uint32_t val) "Write memory delay 0x%08x" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Security Identifier device found in various Allwinner System on Chip designs gives applications a per-board unique identifier. This commit adds support for the Allwinner Security Identifier using a 128-bit UUID value as input. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-8-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-sid.h | 60 ++++++++++++ hw/arm/allwinner-h3.c | 11 ++- hw/arm/orangepi.c | 8 ++ hw/misc/allwinner-sid.c | 168 ++++++++++++++++++++++++++++++++ hw/misc/trace-events | 4 + 7 files changed, 254 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-sid.h create mode 100644 hw/misc/allwinner-sid.c 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_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o obj-$(CONFIG_ALLWINNER_H3) += allwinner-cpucfg.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-sid.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o common-obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-h3-ccu.h" #include "hw/misc/allwinner-cpucfg.h" #include "hw/misc/allwinner-h3-sysctrl.h" +#include "hw/misc/allwinner-sid.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A2, AW_H3_SRAM_C, AW_H3_SYSCTRL, + AW_H3_SID, AW_H3_EHCI0, AW_H3_OHCI0, AW_H3_EHCI1, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwH3ClockCtlState ccu; AwCpuCfgState cpucfg; AwH3SysCtrlState sysctrl; + AwSidState sid; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-sid.h b/include/hw/misc/allwinner-sid.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-sid.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Security ID emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_SID_H +#define HW_MISC_ALLWINNER_SID_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "qemu/uuid.h" + +/** + * Object model + * @{ + */ + +#define TYPE_AW_SID "allwinner-sid" +#define AW_SID(obj) \ + OBJECT_CHECK(AwSidState, (obj), TYPE_AW_SID) + +/** @} */ + +/** + * Allwinner Security ID object instance state + */ +typedef struct AwSidState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Control register defines how and what to read */ + uint32_t control; + + /** RdKey register contains the data retrieved by the device */ + uint32_t rdkey; + + /** Stores the emulated device identifier */ + QemuUUID identifier; + +} AwSidState; + +#endif /* HW_MISC_ALLWINNER_SID_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, [AW_H3_SYSCTRL] = 0x01c00000, + [AW_H3_SID] = 0x01c14000, [AW_H3_EHCI0] = 0x01c1a000, [AW_H3_OHCI0] = 0x01c1a400, [AW_H3_EHCI1] = 0x01c1b000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "mmc0", 0x01c0f000, 4 * KiB }, { "mmc1", 0x01c10000, 4 * KiB }, { "mmc2", 0x01c11000, 4 * KiB }, - { "sid", 0x01c14000, 1 * KiB }, { "crypto", 0x01c15000, 4 * KiB }, { "msgbox", 0x01c17000, 4 * KiB }, { "spinlock", 0x01c18000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "cpucfg", &s->cpucfg, sizeof(s->cpucfg), TYPE_AW_CPUCFG); + + sysbus_init_child_obj(obj, "sid", &s->sid, sizeof(s->sid), + TYPE_AW_SID); + object_property_add_alias(obj, "identifier", OBJECT(&s->sid), + "identifier", &error_abort); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->cpucfg)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->cpucfg), 0, s->memmap[AW_H3_CPUCFG]); + /* Security Identifier */ + qdev_init_nofail(DEVICE(&s->sid)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->sid), 0, s->memmap[AW_H3_SID]); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) object_property_set_int(OBJECT(h3), 24 * 1000 * 1000, "clk1-freq", &error_abort); + /* Setup SID properties. Currently using a default fixed SID identifier. */ + if (qemu_uuid_is_null(&h3->sid.identifier)) { + qdev_prop_set_string(DEVICE(h3), "identifier", + "02c00081-1111-2222-3333-000044556677"); + } else if (ldl_be_p(&h3->sid.identifier.data[0]) != 0x02c00081) { + warn_report("Security Identifier value does not include H3 prefix"); + } + /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); diff --git a/hw/misc/allwinner-sid.c b/hw/misc/allwinner-sid.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-sid.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Security ID emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/guest-random.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/misc/allwinner-sid.h" +#include "trace.h" + +/* SID register offsets */ +enum { + REG_PRCTL = 0x40, /* Control */ + REG_RDKEY = 0x60, /* Read Key */ +}; + +/* SID register flags */ +enum { + REG_PRCTL_WRITE = 0x0002, /* Unknown write flag */ + REG_PRCTL_OP_LOCK = 0xAC00, /* Lock operation */ +}; + +static uint64_t allwinner_sid_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwSidState *s = AW_SID(opaque); + uint64_t val = 0; + + switch (offset) { + case REG_PRCTL: /* Control */ + val = s->control; + break; + case REG_RDKEY: /* Read Key */ + val = s->rdkey; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_sid_read(offset, val, size); + + return val; +} + +static void allwinner_sid_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwSidState *s = AW_SID(opaque); + + trace_allwinner_sid_write(offset, val, size); + + switch (offset) { + case REG_PRCTL: /* Control */ + s->control = val; + + if ((s->control & REG_PRCTL_OP_LOCK) && + (s->control & REG_PRCTL_WRITE)) { + uint32_t id = s->control >> 16; + + if (id <= sizeof(QemuUUID) - sizeof(s->rdkey)) { + s->rdkey = ldl_be_p(&s->identifier.data[id]); + } + } + s->control &= ~REG_PRCTL_WRITE; + break; + case REG_RDKEY: /* Read Key */ + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } +} + +static const MemoryRegionOps allwinner_sid_ops = { + .read = allwinner_sid_read, + .write = allwinner_sid_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_sid_reset(DeviceState *dev) +{ + AwSidState *s = AW_SID(dev); + + /* Set default values for registers */ + s->control = 0; + s->rdkey = 0; +} + +static void allwinner_sid_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwSidState *s = AW_SID(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_sid_ops, s, + TYPE_AW_SID, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static Property allwinner_sid_properties[] = { + DEFINE_PROP_UUID_NODEFAULT("identifier", AwSidState, identifier), + DEFINE_PROP_END_OF_LIST() +}; + +static const VMStateDescription allwinner_sid_vmstate = { + .name = "allwinner-sid", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(control, AwSidState), + VMSTATE_UINT32(rdkey, AwSidState), + VMSTATE_UINT8_ARRAY_V(identifier.data, AwSidState, sizeof(QemuUUID), 1), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sid_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_sid_reset; + dc->vmsd = &allwinner_sid_vmstate; + device_class_set_props(dc, allwinner_sid_properties); +} + +static const TypeInfo allwinner_sid_info = { + .name = TYPE_AW_SID, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_sid_init, + .instance_size = sizeof(AwSidState), + .class_init = allwinner_sid_class_init, +}; + +static void allwinner_sid_register(void) +{ + type_register_static(&allwinner_sid_info); +} + +type_init(allwinner_sid_register) 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 @@ allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_ad allwinner_cpucfg_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_cpucfg_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +# allwinner-sid.c +allwinner_sid_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" ecc_mem_writel_mdr(uint32_t val) "Write memory delay 0x%08x" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner System on Chip families sun4i and above contain an integrated storage controller for Secure Digital (SD) and Multi Media Card (MMC) interfaces. This commit adds support for the Allwinner SD/MMC storage controller with the following emulated features: * DMA transfers * Direct FIFO I/O * Short/Long format command responses * Auto-Stop command (CMD12) * Insert & remove card detection The following boards are extended with the SD host controller: * Cubieboard (hw/arm/cubieboard.c) * Orange Pi PC (hw/arm/orangepi.c) Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-9-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/Makefile.objs | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/sd/allwinner-sdhost.h | 135 +++++ hw/arm/allwinner-a10.c | 11 + hw/arm/allwinner-h3.c | 15 +- hw/arm/cubieboard.c | 15 + hw/arm/orangepi.c | 16 + hw/sd/allwinner-sdhost.c | 854 +++++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/sd/trace-events | 7 + 11 files changed, 1059 insertions(+), 1 deletion(-) create mode 100644 include/hw/sd/allwinner-sdhost.h create mode 100644 hw/sd/allwinner-sdhost.c diff --git a/hw/sd/Makefile.objs b/hw/sd/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/Makefile.objs +++ b/hw/sd/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SD) += sd.o core.o sdmmc-internal.o common-obj-$(CONFIG_SDHCI) += sdhci.o common-obj-$(CONFIG_SDHCI_PCI) += sdhci-pci.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-sdhost.o common-obj-$(CONFIG_MILKYMIST) += milkymist-memcard.o common-obj-$(CONFIG_OMAP) += omap_mmc.o common-obj-$(CONFIG_PXA2XX) += pxa2xx_mmci.o diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/allwinner-a10-pic.h" #include "hw/net/allwinner_emac.h" +#include "hw/sd/allwinner-sdhost.h" #include "hw/ide/ahci.h" #include "hw/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" @@ -XXX,XX +XXX,XX @@ typedef struct AwA10State { AwA10PICState intc; AwEmacState emac; AllwinnerAHCIState sata; + AwSdHostState mmc0; MemoryRegion sram_a; EHCISysBusState ehci[AW_A10_NUM_USB]; OHCISysBusState ohci[AW_A10_NUM_USB]; diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-cpucfg.h" #include "hw/misc/allwinner-h3-sysctrl.h" #include "hw/misc/allwinner-sid.h" +#include "hw/sd/allwinner-sdhost.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A2, AW_H3_SRAM_C, AW_H3_SYSCTRL, + AW_H3_MMC0, AW_H3_SID, AW_H3_EHCI0, AW_H3_OHCI0, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwCpuCfgState cpucfg; AwH3SysCtrlState sysctrl; AwSidState sid; + AwSdHostState mmc0; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/sd/allwinner-sdhost.h b/include/hw/sd/allwinner-sdhost.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/sd/allwinner-sdhost.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner (sun4i and above) SD Host Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_SD_ALLWINNER_SDHOST_H +#define HW_SD_ALLWINNER_SDHOST_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/sd/sd.h" + +/** + * Object model types + * @{ + */ + +/** Generic Allwinner SD Host Controller (abstract) */ +#define TYPE_AW_SDHOST "allwinner-sdhost" + +/** Allwinner sun4i family (A10, A12) */ +#define TYPE_AW_SDHOST_SUN4I TYPE_AW_SDHOST "-sun4i" + +/** Allwinner sun5i family and newer (A13, H2+, H3, etc) */ +#define TYPE_AW_SDHOST_SUN5I TYPE_AW_SDHOST "-sun5i" + +/** @} */ + +/** + * Object model macros + * @{ + */ + +#define AW_SDHOST(obj) \ + OBJECT_CHECK(AwSdHostState, (obj), TYPE_AW_SDHOST) +#define AW_SDHOST_CLASS(klass) \ + OBJECT_CLASS_CHECK(AwSdHostClass, (klass), TYPE_AW_SDHOST) +#define AW_SDHOST_GET_CLASS(obj) \ + OBJECT_GET_CLASS(AwSdHostClass, (obj), TYPE_AW_SDHOST) + +/** @} */ + +/** + * Allwinner SD Host Controller object instance state. + */ +typedef struct AwSdHostState { + /*< private >*/ + SysBusDevice busdev; + /*< public >*/ + + /** Secure Digital (SD) bus, which connects to SD card (if present) */ + SDBus sdbus; + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Interrupt output signal to notify CPU */ + qemu_irq irq; + + /** Number of bytes left in current DMA transfer */ + uint32_t transfer_cnt; + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t global_ctl; /**< Global Control */ + uint32_t clock_ctl; /**< Clock Control */ + uint32_t timeout; /**< Timeout */ + uint32_t bus_width; /**< Bus Width */ + uint32_t block_size; /**< Block Size */ + uint32_t byte_count; /**< Byte Count */ + + uint32_t command; /**< Command */ + uint32_t command_arg; /**< Command Argument */ + uint32_t response[4]; /**< Command Response */ + + uint32_t irq_mask; /**< Interrupt Mask */ + uint32_t irq_status; /**< Raw Interrupt Status */ + uint32_t status; /**< Status */ + + uint32_t fifo_wlevel; /**< FIFO Water Level */ + uint32_t fifo_func_sel; /**< FIFO Function Select */ + uint32_t debug_enable; /**< Debug Enable */ + uint32_t auto12_arg; /**< Auto Command 12 Argument */ + uint32_t newtiming_set; /**< SD New Timing Set */ + uint32_t newtiming_debug; /**< SD New Timing Debug */ + uint32_t hardware_rst; /**< Hardware Reset */ + uint32_t dmac; /**< Internal DMA Controller Control */ + uint32_t desc_base; /**< Descriptor List Base Address */ + uint32_t dmac_status; /**< Internal DMA Controller Status */ + uint32_t dmac_irq; /**< Internal DMA Controller IRQ Enable */ + uint32_t card_threshold; /**< Card Threshold Control */ + uint32_t startbit_detect; /**< eMMC DDR Start Bit Detection Control */ + uint32_t response_crc; /**< Response CRC */ + uint32_t data_crc[8]; /**< Data CRC */ + uint32_t status_crc; /**< Status CRC */ + + /** @} */ + +} AwSdHostState; + +/** + * Allwinner SD Host Controller class-level struct. + * + * This struct is filled by each sunxi device specific code + * such that the generic code can use this struct to support + * all devices. + */ +typedef struct AwSdHostClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ + + /** Maximum buffer size in bytes per DMA descriptor */ + size_t max_desc_size; + +} AwSdHostClass; + +#endif /* HW_SD_ALLWINNER_SDHOST_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_PIC_REG_BASE 0x01c20400 #define AW_A10_PIT_REG_BASE 0x01c20c00 #define AW_A10_UART0_REG_BASE 0x01c28000 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) sizeof(s->ohci[i]), TYPE_SYSBUS_OHCI); } } + + sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), + TYPE_AW_SDHOST_SUN4I); } static void aw_a10_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(dev, 64 + i)); } } + + /* SD/MMC */ + qdev_init_nofail(DEVICE(&s->mmc0)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mmc0), 0, AW_A10_MMC0_BASE); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc0), 0, qdev_get_gpio_in(dev, 32)); + object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), + "sd-bus", &error_abort); } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, [AW_H3_SYSCTRL] = 0x01c00000, + [AW_H3_MMC0] = 0x01c0f000, [AW_H3_SID] = 0x01c14000, [AW_H3_EHCI0] = 0x01c1a000, [AW_H3_OHCI0] = 0x01c1a400, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "lcd0", 0x01c0c000, 4 * KiB }, { "lcd1", 0x01c0d000, 4 * KiB }, { "ve", 0x01c0e000, 4 * KiB }, - { "mmc0", 0x01c0f000, 4 * KiB }, { "mmc1", 0x01c10000, 4 * KiB }, { "mmc2", 0x01c11000, 4 * KiB }, { "crypto", 0x01c15000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART3 = 3, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, + AW_H3_GIC_SPI_MMC0 = 60, AW_H3_GIC_SPI_EHCI0 = 72, AW_H3_GIC_SPI_OHCI0 = 73, AW_H3_GIC_SPI_EHCI1 = 74, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) TYPE_AW_SID); object_property_add_alias(obj, "identifier", OBJECT(&s->sid), "identifier", &error_abort); + + sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), + TYPE_AW_SDHOST_SUN5I); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->sid)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->sid), 0, s->memmap[AW_H3_SID]); + /* SD/MMC */ + qdev_init_nofail(DEVICE(&s->mmc0)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mmc0), 0, s->memmap[AW_H3_MMC0]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc0), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_MMC0)); + + object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), + "sd-bus", &error_abort); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "hw/sysbus.h" #include "hw/boards.h" +#include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" static struct arm_boot_info cubieboard_binfo = { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) { AwA10State *a10; Error *err = NULL; + DriveInfo *di; + BlockBackend *blk; + BusState *bus; + DeviceState *carddev; /* BIOS is not supported by this board */ if (bios_name) { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) exit(1); } + /* Retrieve SD bus */ + di = drive_get_next(IF_SD); + blk = di ? blk_by_legacy_dinfo(di) : NULL; + bus = qdev_get_child_bus(DEVICE(a10), "sd-bus"); + + /* Plug in SD card */ + carddev = qdev_create(bus, TYPE_SD_CARD); + qdev_prop_set_drive(carddev, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(carddev), true, "realized", &error_fatal); + memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE, machine->ram); diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info orangepi_binfo = { static void orangepi_init(MachineState *machine) { AwH3State *h3; + DriveInfo *di; + BlockBackend *blk; + BusState *bus; + DeviceState *carddev; /* BIOS is not supported by this board */ if (bios_name) { @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); + /* Retrieve SD bus */ + di = drive_get_next(IF_SD); + blk = di ? blk_by_legacy_dinfo(di) : NULL; + bus = qdev_get_child_bus(DEVICE(h3), "sd-bus"); + + /* Plug in SD card */ + carddev = qdev_create(bus, TYPE_SD_CARD); + qdev_prop_set_drive(carddev, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(carddev), true, "realized", &error_fatal); + /* SDRAM */ memory_region_add_subregion(get_system_memory(), h3->memmap[AW_H3_SDRAM], machine->ram); @@ -XXX,XX +XXX,XX @@ static void orangepi_machine_init(MachineClass *mc) { mc->desc = "Orange Pi PC"; mc->init = orangepi_init; + mc->block_default_type = IF_SD; + mc->units_per_default_bus = 1; mc->min_cpus = AW_H3_NUM_CPUS; mc->max_cpus = AW_H3_NUM_CPUS; mc->default_cpus = AW_H3_NUM_CPUS; diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/sd/allwinner-sdhost.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner (sun4i and above) SD Host Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "sysemu/blockdev.h" +#include "hw/irq.h" +#include "hw/sd/allwinner-sdhost.h" +#include "migration/vmstate.h" +#include "trace.h" + +#define TYPE_AW_SDHOST_BUS "allwinner-sdhost-bus" +#define AW_SDHOST_BUS(obj) \ + OBJECT_CHECK(SDBus, (obj), TYPE_AW_SDHOST_BUS) + +/* SD Host register offsets */ +enum { + REG_SD_GCTL = 0x00, /* Global Control */ + REG_SD_CKCR = 0x04, /* Clock Control */ + REG_SD_TMOR = 0x08, /* Timeout */ + REG_SD_BWDR = 0x0C, /* Bus Width */ + REG_SD_BKSR = 0x10, /* Block Size */ + REG_SD_BYCR = 0x14, /* Byte Count */ + REG_SD_CMDR = 0x18, /* Command */ + REG_SD_CAGR = 0x1C, /* Command Argument */ + REG_SD_RESP0 = 0x20, /* Response Zero */ + REG_SD_RESP1 = 0x24, /* Response One */ + REG_SD_RESP2 = 0x28, /* Response Two */ + REG_SD_RESP3 = 0x2C, /* Response Three */ + REG_SD_IMKR = 0x30, /* Interrupt Mask */ + REG_SD_MISR = 0x34, /* Masked Interrupt Status */ + REG_SD_RISR = 0x38, /* Raw Interrupt Status */ + REG_SD_STAR = 0x3C, /* Status */ + REG_SD_FWLR = 0x40, /* FIFO Water Level */ + REG_SD_FUNS = 0x44, /* FIFO Function Select */ + REG_SD_DBGC = 0x50, /* Debug Enable */ + REG_SD_A12A = 0x58, /* Auto command 12 argument */ + REG_SD_NTSR = 0x5C, /* SD NewTiming Set */ + REG_SD_SDBG = 0x60, /* SD newTiming Set Debug */ + REG_SD_HWRST = 0x78, /* Hardware Reset Register */ + REG_SD_DMAC = 0x80, /* Internal DMA Controller Control */ + REG_SD_DLBA = 0x84, /* Descriptor List Base Address */ + REG_SD_IDST = 0x88, /* Internal DMA Controller Status */ + REG_SD_IDIE = 0x8C, /* Internal DMA Controller IRQ Enable */ + REG_SD_THLDC = 0x100, /* Card Threshold Control */ + REG_SD_DSBD = 0x10C, /* eMMC DDR Start Bit Detection Control */ + REG_SD_RES_CRC = 0x110, /* Response CRC from card/eMMC */ + REG_SD_DATA7_CRC = 0x114, /* CRC Data 7 from card/eMMC */ + REG_SD_DATA6_CRC = 0x118, /* CRC Data 6 from card/eMMC */ + REG_SD_DATA5_CRC = 0x11C, /* CRC Data 5 from card/eMMC */ + REG_SD_DATA4_CRC = 0x120, /* CRC Data 4 from card/eMMC */ + REG_SD_DATA3_CRC = 0x124, /* CRC Data 3 from card/eMMC */ + REG_SD_DATA2_CRC = 0x128, /* CRC Data 2 from card/eMMC */ + REG_SD_DATA1_CRC = 0x12C, /* CRC Data 1 from card/eMMC */ + REG_SD_DATA0_CRC = 0x130, /* CRC Data 0 from card/eMMC */ + REG_SD_CRC_STA = 0x134, /* CRC status from card/eMMC during write */ + REG_SD_FIFO = 0x200, /* Read/Write FIFO */ +}; + +/* SD Host register flags */ +enum { + SD_GCTL_FIFO_AC_MOD = (1 << 31), + SD_GCTL_DDR_MOD_SEL = (1 << 10), + SD_GCTL_CD_DBC_ENB = (1 << 8), + SD_GCTL_DMA_ENB = (1 << 5), + SD_GCTL_INT_ENB = (1 << 4), + SD_GCTL_DMA_RST = (1 << 2), + SD_GCTL_FIFO_RST = (1 << 1), + SD_GCTL_SOFT_RST = (1 << 0), +}; + +enum { + SD_CMDR_LOAD = (1 << 31), + SD_CMDR_CLKCHANGE = (1 << 21), + SD_CMDR_WRITE = (1 << 10), + SD_CMDR_AUTOSTOP = (1 << 12), + SD_CMDR_DATA = (1 << 9), + SD_CMDR_RESPONSE_LONG = (1 << 7), + SD_CMDR_RESPONSE = (1 << 6), + SD_CMDR_CMDID_MASK = (0x3f), +}; + +enum { + SD_RISR_CARD_REMOVE = (1 << 31), + SD_RISR_CARD_INSERT = (1 << 30), + SD_RISR_SDIO_INTR = (1 << 16), + SD_RISR_AUTOCMD_DONE = (1 << 14), + SD_RISR_DATA_COMPLETE = (1 << 3), + SD_RISR_CMD_COMPLETE = (1 << 2), + SD_RISR_NO_RESPONSE = (1 << 1), +}; + +enum { + SD_STAR_CARD_PRESENT = (1 << 8), +}; + +enum { + SD_IDST_INT_SUMMARY = (1 << 8), + SD_IDST_RECEIVE_IRQ = (1 << 1), + SD_IDST_TRANSMIT_IRQ = (1 << 0), + SD_IDST_IRQ_MASK = (1 << 1) | (1 << 0) | (1 << 8), + SD_IDST_WR_MASK = (0x3ff), +}; + +/* SD Host register reset values */ +enum { + REG_SD_GCTL_RST = 0x00000300, + REG_SD_CKCR_RST = 0x0, + REG_SD_TMOR_RST = 0xFFFFFF40, + REG_SD_BWDR_RST = 0x0, + REG_SD_BKSR_RST = 0x00000200, + REG_SD_BYCR_RST = 0x00000200, + REG_SD_CMDR_RST = 0x0, + REG_SD_CAGR_RST = 0x0, + REG_SD_RESP_RST = 0x0, + REG_SD_IMKR_RST = 0x0, + REG_SD_MISR_RST = 0x0, + REG_SD_RISR_RST = 0x0, + REG_SD_STAR_RST = 0x00000100, + REG_SD_FWLR_RST = 0x000F0000, + REG_SD_FUNS_RST = 0x0, + REG_SD_DBGC_RST = 0x0, + REG_SD_A12A_RST = 0x0000FFFF, + REG_SD_NTSR_RST = 0x00000001, + REG_SD_SDBG_RST = 0x0, + REG_SD_HWRST_RST = 0x00000001, + REG_SD_DMAC_RST = 0x0, + REG_SD_DLBA_RST = 0x0, + REG_SD_IDST_RST = 0x0, + REG_SD_IDIE_RST = 0x0, + REG_SD_THLDC_RST = 0x0, + REG_SD_DSBD_RST = 0x0, + REG_SD_RES_CRC_RST = 0x0, + REG_SD_DATA_CRC_RST = 0x0, + REG_SD_CRC_STA_RST = 0x0, + REG_SD_FIFO_RST = 0x0, +}; + +/* Data transfer descriptor for DMA */ +typedef struct TransferDescriptor { + uint32_t status; /* Status flags */ + uint32_t size; /* Data buffer size */ + uint32_t addr; /* Data buffer address */ + uint32_t next; /* Physical address of next descriptor */ +} TransferDescriptor; + +/* Data transfer descriptor flags */ +enum { + DESC_STATUS_HOLD = (1 << 31), /* Set when descriptor is in use by DMA */ + DESC_STATUS_ERROR = (1 << 30), /* Set when DMA transfer error occurred */ + DESC_STATUS_CHAIN = (1 << 4), /* Indicates chained descriptor. */ + DESC_STATUS_FIRST = (1 << 3), /* Set on the first descriptor */ + DESC_STATUS_LAST = (1 << 2), /* Set on the last descriptor */ + DESC_STATUS_NOIRQ = (1 << 1), /* Skip raising interrupt after transfer */ + DESC_SIZE_MASK = (0xfffffffc) +}; + +static void allwinner_sdhost_update_irq(AwSdHostState *s) +{ + uint32_t irq; + + if (s->global_ctl & SD_GCTL_INT_ENB) { + irq = s->irq_status & s->irq_mask; + } else { + irq = 0; + } + + trace_allwinner_sdhost_update_irq(irq); + qemu_set_irq(s->irq, irq); +} + +static void allwinner_sdhost_update_transfer_cnt(AwSdHostState *s, + uint32_t bytes) +{ + if (s->transfer_cnt > bytes) { + s->transfer_cnt -= bytes; + } else { + s->transfer_cnt = 0; + } + + if (!s->transfer_cnt) { + s->irq_status |= SD_RISR_DATA_COMPLETE; + } +} + +static void allwinner_sdhost_set_inserted(DeviceState *dev, bool inserted) +{ + AwSdHostState *s = AW_SDHOST(dev); + + trace_allwinner_sdhost_set_inserted(inserted); + + if (inserted) { + s->irq_status |= SD_RISR_CARD_INSERT; + s->irq_status &= ~SD_RISR_CARD_REMOVE; + s->status |= SD_STAR_CARD_PRESENT; + } else { + s->irq_status &= ~SD_RISR_CARD_INSERT; + s->irq_status |= SD_RISR_CARD_REMOVE; + s->status &= ~SD_STAR_CARD_PRESENT; + } + + allwinner_sdhost_update_irq(s); +} + +static void allwinner_sdhost_send_command(AwSdHostState *s) +{ + SDRequest request; + uint8_t resp[16]; + int rlen; + + /* Auto clear load flag */ + s->command &= ~SD_CMDR_LOAD; + + /* Clock change does not actually interact with the SD bus */ + if (!(s->command & SD_CMDR_CLKCHANGE)) { + + /* Prepare request */ + request.cmd = s->command & SD_CMDR_CMDID_MASK; + request.arg = s->command_arg; + + /* Send request to SD bus */ + rlen = sdbus_do_command(&s->sdbus, &request, resp); + if (rlen < 0) { + goto error; + } + + /* If the command has a response, store it in the response registers */ + if ((s->command & SD_CMDR_RESPONSE)) { + if (rlen == 4 && !(s->command & SD_CMDR_RESPONSE_LONG)) { + s->response[0] = ldl_be_p(&resp[0]); + s->response[1] = s->response[2] = s->response[3] = 0; + + } else if (rlen == 16 && (s->command & SD_CMDR_RESPONSE_LONG)) { + s->response[0] = ldl_be_p(&resp[12]); + s->response[1] = ldl_be_p(&resp[8]); + s->response[2] = ldl_be_p(&resp[4]); + s->response[3] = ldl_be_p(&resp[0]); + } else { + goto error; + } + } + } + + /* Set interrupt status bits */ + s->irq_status |= SD_RISR_CMD_COMPLETE; + return; + +error: + s->irq_status |= SD_RISR_NO_RESPONSE; +} + +static void allwinner_sdhost_auto_stop(AwSdHostState *s) +{ + /* + * The stop command (CMD12) ensures the SD bus + * returns to the transfer state. + */ + if ((s->command & SD_CMDR_AUTOSTOP) && (s->transfer_cnt == 0)) { + /* First save current command registers */ + uint32_t saved_cmd = s->command; + uint32_t saved_arg = s->command_arg; + + /* Prepare stop command (CMD12) */ + s->command &= ~SD_CMDR_CMDID_MASK; + s->command |= 12; /* CMD12 */ + s->command_arg = 0; + + /* Put the command on SD bus */ + allwinner_sdhost_send_command(s); + + /* Restore command values */ + s->command = saved_cmd; + s->command_arg = saved_arg; + + /* Set IRQ status bit for automatic stop done */ + s->irq_status |= SD_RISR_AUTOCMD_DONE; + } +} + +static uint32_t allwinner_sdhost_process_desc(AwSdHostState *s, + hwaddr desc_addr, + TransferDescriptor *desc, + bool is_write, uint32_t max_bytes) +{ + AwSdHostClass *klass = AW_SDHOST_GET_CLASS(s); + uint32_t num_done = 0; + uint32_t num_bytes = max_bytes; + uint8_t buf[1024]; + + /* Read descriptor */ + cpu_physical_memory_read(desc_addr, desc, sizeof(*desc)); + if (desc->size == 0) { + desc->size = klass->max_desc_size; + } else if (desc->size > klass->max_desc_size) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: DMA descriptor buffer size " + " is out-of-bounds: %" PRIu32 " > %zu", + __func__, desc->size, klass->max_desc_size); + desc->size = klass->max_desc_size; + } + if (desc->size < num_bytes) { + num_bytes = desc->size; + } + + trace_allwinner_sdhost_process_desc(desc_addr, desc->size, + is_write, max_bytes); + + while (num_done < num_bytes) { + /* Try to completely fill the local buffer */ + uint32_t buf_bytes = num_bytes - num_done; + if (buf_bytes > sizeof(buf)) { + buf_bytes = sizeof(buf); + } + + /* Write to SD bus */ + if (is_write) { + cpu_physical_memory_read((desc->addr & DESC_SIZE_MASK) + num_done, + buf, buf_bytes); + + for (uint32_t i = 0; i < buf_bytes; i++) { + sdbus_write_data(&s->sdbus, buf[i]); + } + + /* Read from SD bus */ + } else { + for (uint32_t i = 0; i < buf_bytes; i++) { + buf[i] = sdbus_read_data(&s->sdbus); + } + cpu_physical_memory_write((desc->addr & DESC_SIZE_MASK) + num_done, + buf, buf_bytes); + } + num_done += buf_bytes; + } + + /* Clear hold flag and flush descriptor */ + desc->status &= ~DESC_STATUS_HOLD; + cpu_physical_memory_write(desc_addr, desc, sizeof(*desc)); + + return num_done; +} + +static void allwinner_sdhost_dma(AwSdHostState *s) +{ + TransferDescriptor desc; + hwaddr desc_addr = s->desc_base; + bool is_write = (s->command & SD_CMDR_WRITE); + uint32_t bytes_done = 0; + + /* Check if DMA can be performed */ + if (s->byte_count == 0 || s->block_size == 0 || + !(s->global_ctl & SD_GCTL_DMA_ENB)) { + return; + } + + /* + * For read operations, data must be available on the SD bus + * If not, it is an error and we should not act at all + */ + if (!is_write && !sdbus_data_ready(&s->sdbus)) { + return; + } + + /* Process the DMA descriptors until all data is copied */ + while (s->byte_count > 0) { + bytes_done = allwinner_sdhost_process_desc(s, desc_addr, &desc, + is_write, s->byte_count); + allwinner_sdhost_update_transfer_cnt(s, bytes_done); + + if (bytes_done <= s->byte_count) { + s->byte_count -= bytes_done; + } else { + s->byte_count = 0; + } + + if (desc.status & DESC_STATUS_LAST) { + break; + } else { + desc_addr = desc.next; + } + } + + /* Raise IRQ to signal DMA is completed */ + s->irq_status |= SD_RISR_DATA_COMPLETE | SD_RISR_SDIO_INTR; + + /* Update DMAC bits */ + s->dmac_status |= SD_IDST_INT_SUMMARY; + + if (is_write) { + s->dmac_status |= SD_IDST_TRANSMIT_IRQ; + } else { + s->dmac_status |= SD_IDST_RECEIVE_IRQ; + } +} + +static uint64_t allwinner_sdhost_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwSdHostState *s = AW_SDHOST(opaque); + uint32_t res = 0; + + switch (offset) { + case REG_SD_GCTL: /* Global Control */ + res = s->global_ctl; + break; + case REG_SD_CKCR: /* Clock Control */ + res = s->clock_ctl; + break; + case REG_SD_TMOR: /* Timeout */ + res = s->timeout; + break; + case REG_SD_BWDR: /* Bus Width */ + res = s->bus_width; + break; + case REG_SD_BKSR: /* Block Size */ + res = s->block_size; + break; + case REG_SD_BYCR: /* Byte Count */ + res = s->byte_count; + break; + case REG_SD_CMDR: /* Command */ + res = s->command; + break; + case REG_SD_CAGR: /* Command Argument */ + res = s->command_arg; + break; + case REG_SD_RESP0: /* Response Zero */ + res = s->response[0]; + break; + case REG_SD_RESP1: /* Response One */ + res = s->response[1]; + break; + case REG_SD_RESP2: /* Response Two */ + res = s->response[2]; + break; + case REG_SD_RESP3: /* Response Three */ + res = s->response[3]; + break; + case REG_SD_IMKR: /* Interrupt Mask */ + res = s->irq_mask; + break; + case REG_SD_MISR: /* Masked Interrupt Status */ + res = s->irq_status & s->irq_mask; + break; + case REG_SD_RISR: /* Raw Interrupt Status */ + res = s->irq_status; + break; + case REG_SD_STAR: /* Status */ + res = s->status; + break; + case REG_SD_FWLR: /* FIFO Water Level */ + res = s->fifo_wlevel; + break; + case REG_SD_FUNS: /* FIFO Function Select */ + res = s->fifo_func_sel; + break; + case REG_SD_DBGC: /* Debug Enable */ + res = s->debug_enable; + break; + case REG_SD_A12A: /* Auto command 12 argument */ + res = s->auto12_arg; + break; + case REG_SD_NTSR: /* SD NewTiming Set */ + res = s->newtiming_set; + break; + case REG_SD_SDBG: /* SD newTiming Set Debug */ + res = s->newtiming_debug; + break; + case REG_SD_HWRST: /* Hardware Reset Register */ + res = s->hardware_rst; + break; + case REG_SD_DMAC: /* Internal DMA Controller Control */ + res = s->dmac; + break; + case REG_SD_DLBA: /* Descriptor List Base Address */ + res = s->desc_base; + break; + case REG_SD_IDST: /* Internal DMA Controller Status */ + res = s->dmac_status; + break; + case REG_SD_IDIE: /* Internal DMA Controller Interrupt Enable */ + res = s->dmac_irq; + break; + case REG_SD_THLDC: /* Card Threshold Control */ + res = s->card_threshold; + break; + case REG_SD_DSBD: /* eMMC DDR Start Bit Detection Control */ + res = s->startbit_detect; + break; + case REG_SD_RES_CRC: /* Response CRC from card/eMMC */ + res = s->response_crc; + break; + case REG_SD_DATA7_CRC: /* CRC Data 7 from card/eMMC */ + case REG_SD_DATA6_CRC: /* CRC Data 6 from card/eMMC */ + case REG_SD_DATA5_CRC: /* CRC Data 5 from card/eMMC */ + case REG_SD_DATA4_CRC: /* CRC Data 4 from card/eMMC */ + case REG_SD_DATA3_CRC: /* CRC Data 3 from card/eMMC */ + case REG_SD_DATA2_CRC: /* CRC Data 2 from card/eMMC */ + case REG_SD_DATA1_CRC: /* CRC Data 1 from card/eMMC */ + case REG_SD_DATA0_CRC: /* CRC Data 0 from card/eMMC */ + res = s->data_crc[((offset - REG_SD_DATA7_CRC) / sizeof(uint32_t))]; + break; + case REG_SD_CRC_STA: /* CRC status from card/eMMC in write operation */ + res = s->status_crc; + break; + case REG_SD_FIFO: /* Read/Write FIFO */ + if (sdbus_data_ready(&s->sdbus)) { + res = sdbus_read_data(&s->sdbus); + res |= sdbus_read_data(&s->sdbus) << 8; + res |= sdbus_read_data(&s->sdbus) << 16; + res |= sdbus_read_data(&s->sdbus) << 24; + allwinner_sdhost_update_transfer_cnt(s, sizeof(uint32_t)); + allwinner_sdhost_auto_stop(s); + allwinner_sdhost_update_irq(s); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no data ready on SD bus\n", + __func__); + } + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" + HWADDR_PRIx"\n", __func__, offset); + res = 0; + break; + } + + trace_allwinner_sdhost_read(offset, res, size); + return res; +} + +static void allwinner_sdhost_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AwSdHostState *s = AW_SDHOST(opaque); + + trace_allwinner_sdhost_write(offset, value, size); + + switch (offset) { + case REG_SD_GCTL: /* Global Control */ + s->global_ctl = value; + s->global_ctl &= ~(SD_GCTL_DMA_RST | SD_GCTL_FIFO_RST | + SD_GCTL_SOFT_RST); + allwinner_sdhost_update_irq(s); + break; + case REG_SD_CKCR: /* Clock Control */ + s->clock_ctl = value; + break; + case REG_SD_TMOR: /* Timeout */ + s->timeout = value; + break; + case REG_SD_BWDR: /* Bus Width */ + s->bus_width = value; + break; + case REG_SD_BKSR: /* Block Size */ + s->block_size = value; + break; + case REG_SD_BYCR: /* Byte Count */ + s->byte_count = value; + s->transfer_cnt = value; + break; + case REG_SD_CMDR: /* Command */ + s->command = value; + if (value & SD_CMDR_LOAD) { + allwinner_sdhost_send_command(s); + allwinner_sdhost_dma(s); + allwinner_sdhost_auto_stop(s); + } + allwinner_sdhost_update_irq(s); + break; + case REG_SD_CAGR: /* Command Argument */ + s->command_arg = value; + break; + case REG_SD_RESP0: /* Response Zero */ + s->response[0] = value; + break; + case REG_SD_RESP1: /* Response One */ + s->response[1] = value; + break; + case REG_SD_RESP2: /* Response Two */ + s->response[2] = value; + break; + case REG_SD_RESP3: /* Response Three */ + s->response[3] = value; + break; + case REG_SD_IMKR: /* Interrupt Mask */ + s->irq_mask = value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_MISR: /* Masked Interrupt Status */ + case REG_SD_RISR: /* Raw Interrupt Status */ + s->irq_status &= ~value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_STAR: /* Status */ + s->status &= ~value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_FWLR: /* FIFO Water Level */ + s->fifo_wlevel = value; + break; + case REG_SD_FUNS: /* FIFO Function Select */ + s->fifo_func_sel = value; + break; + case REG_SD_DBGC: /* Debug Enable */ + s->debug_enable = value; + break; + case REG_SD_A12A: /* Auto command 12 argument */ + s->auto12_arg = value; + break; + case REG_SD_NTSR: /* SD NewTiming Set */ + s->newtiming_set = value; + break; + case REG_SD_SDBG: /* SD newTiming Set Debug */ + s->newtiming_debug = value; + break; + case REG_SD_HWRST: /* Hardware Reset Register */ + s->hardware_rst = value; + break; + case REG_SD_DMAC: /* Internal DMA Controller Control */ + s->dmac = value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_DLBA: /* Descriptor List Base Address */ + s->desc_base = value; + break; + case REG_SD_IDST: /* Internal DMA Controller Status */ + s->dmac_status &= (~SD_IDST_WR_MASK) | (~value & SD_IDST_WR_MASK); + allwinner_sdhost_update_irq(s); + break; + case REG_SD_IDIE: /* Internal DMA Controller Interrupt Enable */ + s->dmac_irq = value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_THLDC: /* Card Threshold Control */ + s->card_threshold = value; + break; + case REG_SD_DSBD: /* eMMC DDR Start Bit Detection Control */ + s->startbit_detect = value; + break; + case REG_SD_FIFO: /* Read/Write FIFO */ + sdbus_write_data(&s->sdbus, value & 0xff); + sdbus_write_data(&s->sdbus, (value >> 8) & 0xff); + sdbus_write_data(&s->sdbus, (value >> 16) & 0xff); + sdbus_write_data(&s->sdbus, (value >> 24) & 0xff); + allwinner_sdhost_update_transfer_cnt(s, sizeof(uint32_t)); + allwinner_sdhost_auto_stop(s); + allwinner_sdhost_update_irq(s); + break; + case REG_SD_RES_CRC: /* Response CRC from card/eMMC */ + case REG_SD_DATA7_CRC: /* CRC Data 7 from card/eMMC */ + case REG_SD_DATA6_CRC: /* CRC Data 6 from card/eMMC */ + case REG_SD_DATA5_CRC: /* CRC Data 5 from card/eMMC */ + case REG_SD_DATA4_CRC: /* CRC Data 4 from card/eMMC */ + case REG_SD_DATA3_CRC: /* CRC Data 3 from card/eMMC */ + case REG_SD_DATA2_CRC: /* CRC Data 2 from card/eMMC */ + case REG_SD_DATA1_CRC: /* CRC Data 1 from card/eMMC */ + case REG_SD_DATA0_CRC: /* CRC Data 0 from card/eMMC */ + case REG_SD_CRC_STA: /* CRC status from card/eMMC in write operation */ + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" + HWADDR_PRIx"\n", __func__, offset); + break; + } +} + +static const MemoryRegionOps allwinner_sdhost_ops = { + .read = allwinner_sdhost_read, + .write = allwinner_sdhost_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const VMStateDescription vmstate_allwinner_sdhost = { + .name = "allwinner-sdhost", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(global_ctl, AwSdHostState), + VMSTATE_UINT32(clock_ctl, AwSdHostState), + VMSTATE_UINT32(timeout, AwSdHostState), + VMSTATE_UINT32(bus_width, AwSdHostState), + VMSTATE_UINT32(block_size, AwSdHostState), + VMSTATE_UINT32(byte_count, AwSdHostState), + VMSTATE_UINT32(transfer_cnt, AwSdHostState), + VMSTATE_UINT32(command, AwSdHostState), + VMSTATE_UINT32(command_arg, AwSdHostState), + VMSTATE_UINT32_ARRAY(response, AwSdHostState, 4), + VMSTATE_UINT32(irq_mask, AwSdHostState), + VMSTATE_UINT32(irq_status, AwSdHostState), + VMSTATE_UINT32(status, AwSdHostState), + VMSTATE_UINT32(fifo_wlevel, AwSdHostState), + VMSTATE_UINT32(fifo_func_sel, AwSdHostState), + VMSTATE_UINT32(debug_enable, AwSdHostState), + VMSTATE_UINT32(auto12_arg, AwSdHostState), + VMSTATE_UINT32(newtiming_set, AwSdHostState), + VMSTATE_UINT32(newtiming_debug, AwSdHostState), + VMSTATE_UINT32(hardware_rst, AwSdHostState), + VMSTATE_UINT32(dmac, AwSdHostState), + VMSTATE_UINT32(desc_base, AwSdHostState), + VMSTATE_UINT32(dmac_status, AwSdHostState), + VMSTATE_UINT32(dmac_irq, AwSdHostState), + VMSTATE_UINT32(card_threshold, AwSdHostState), + VMSTATE_UINT32(startbit_detect, AwSdHostState), + VMSTATE_UINT32(response_crc, AwSdHostState), + VMSTATE_UINT32_ARRAY(data_crc, AwSdHostState, 8), + VMSTATE_UINT32(status_crc, AwSdHostState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sdhost_init(Object *obj) +{ + AwSdHostState *s = AW_SDHOST(obj); + + qbus_create_inplace(&s->sdbus, sizeof(s->sdbus), + TYPE_AW_SDHOST_BUS, DEVICE(s), "sd-bus"); + + memory_region_init_io(&s->iomem, obj, &allwinner_sdhost_ops, s, + TYPE_AW_SDHOST, 4 * KiB); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(s), &s->irq); +} + +static void allwinner_sdhost_reset(DeviceState *dev) +{ + AwSdHostState *s = AW_SDHOST(dev); + + s->global_ctl = REG_SD_GCTL_RST; + s->clock_ctl = REG_SD_CKCR_RST; + s->timeout = REG_SD_TMOR_RST; + s->bus_width = REG_SD_BWDR_RST; + s->block_size = REG_SD_BKSR_RST; + s->byte_count = REG_SD_BYCR_RST; + s->transfer_cnt = 0; + + s->command = REG_SD_CMDR_RST; + s->command_arg = REG_SD_CAGR_RST; + + for (int i = 0; i < ARRAY_SIZE(s->response); i++) { + s->response[i] = REG_SD_RESP_RST; + } + + s->irq_mask = REG_SD_IMKR_RST; + s->irq_status = REG_SD_RISR_RST; + s->status = REG_SD_STAR_RST; + + s->fifo_wlevel = REG_SD_FWLR_RST; + s->fifo_func_sel = REG_SD_FUNS_RST; + s->debug_enable = REG_SD_DBGC_RST; + s->auto12_arg = REG_SD_A12A_RST; + s->newtiming_set = REG_SD_NTSR_RST; + s->newtiming_debug = REG_SD_SDBG_RST; + s->hardware_rst = REG_SD_HWRST_RST; + s->dmac = REG_SD_DMAC_RST; + s->desc_base = REG_SD_DLBA_RST; + s->dmac_status = REG_SD_IDST_RST; + s->dmac_irq = REG_SD_IDIE_RST; + s->card_threshold = REG_SD_THLDC_RST; + s->startbit_detect = REG_SD_DSBD_RST; + s->response_crc = REG_SD_RES_CRC_RST; + + for (int i = 0; i < ARRAY_SIZE(s->data_crc); i++) { + s->data_crc[i] = REG_SD_DATA_CRC_RST; + } + + s->status_crc = REG_SD_CRC_STA_RST; +} + +static void allwinner_sdhost_bus_class_init(ObjectClass *klass, void *data) +{ + SDBusClass *sbc = SD_BUS_CLASS(klass); + + sbc->set_inserted = allwinner_sdhost_set_inserted; +} + +static void allwinner_sdhost_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_sdhost_reset; + dc->vmsd = &vmstate_allwinner_sdhost; +} + +static void allwinner_sdhost_sun4i_class_init(ObjectClass *klass, void *data) +{ + AwSdHostClass *sc = AW_SDHOST_CLASS(klass); + sc->max_desc_size = 8 * KiB; +} + +static void allwinner_sdhost_sun5i_class_init(ObjectClass *klass, void *data) +{ + AwSdHostClass *sc = AW_SDHOST_CLASS(klass); + sc->max_desc_size = 64 * KiB; +} + +static TypeInfo allwinner_sdhost_info = { + .name = TYPE_AW_SDHOST, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_sdhost_init, + .instance_size = sizeof(AwSdHostState), + .class_init = allwinner_sdhost_class_init, + .class_size = sizeof(AwSdHostClass), + .abstract = true, +}; + +static const TypeInfo allwinner_sdhost_sun4i_info = { + .name = TYPE_AW_SDHOST_SUN4I, + .parent = TYPE_AW_SDHOST, + .class_init = allwinner_sdhost_sun4i_class_init, +}; + +static const TypeInfo allwinner_sdhost_sun5i_info = { + .name = TYPE_AW_SDHOST_SUN5I, + .parent = TYPE_AW_SDHOST, + .class_init = allwinner_sdhost_sun5i_class_init, +}; + +static const TypeInfo allwinner_sdhost_bus_info = { + .name = TYPE_AW_SDHOST_BUS, + .parent = TYPE_SD_BUS, + .instance_size = sizeof(SDBus), + .class_init = allwinner_sdhost_bus_class_init, +}; + +static void allwinner_sdhost_register_types(void) +{ + type_register_static(&allwinner_sdhost_info); + type_register_static(&allwinner_sdhost_sun4i_info); + type_register_static(&allwinner_sdhost_sun5i_info); + type_register_static(&allwinner_sdhost_bus_info); +} + +type_init(allwinner_sdhost_register_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 ALLWINNER_H3 select UNIMP select USB_OHCI select USB_EHCI_SYSBUS + select SD config RASPI bool diff --git a/hw/sd/trace-events b/hw/sd/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/trace-events +++ b/hw/sd/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-sdhost.c +allwinner_sdhost_set_inserted(bool inserted) "inserted %u" +allwinner_sdhost_process_desc(uint64_t desc_addr, uint32_t desc_size, bool is_write, uint32_t max_bytes) "desc_addr 0x%" PRIx64 " desc_size %" PRIu32 " is_write %u max_bytes %" PRIu32 +allwinner_sdhost_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_sdhost_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_sdhost_update_irq(uint32_t irq) "IRQ bits 0x%" PRIx32 + # bcm2835_sdhost.c bcm2835_sdhost_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" bcm2835_sdhost_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner Sun8i System on Chip family includes an Ethernet MAC (EMAC) which provides 10M/100M/1000M Ethernet connectivity. This commit adds support for the Allwinner EMAC from the Sun8i family (H2+, H3, A33, etc), including emulation for the following functionality: * DMA transfers * MII interface * Transmit CRC calculation Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-10-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/net/allwinner-sun8i-emac.h | 99 +++ hw/arm/allwinner-h3.c | 16 +- hw/arm/orangepi.c | 3 + hw/net/allwinner-sun8i-emac.c | 871 ++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/net/Kconfig | 3 + hw/net/trace-events | 10 + 9 files changed, 1006 insertions(+), 1 deletion(-) create mode 100644 include/hw/net/allwinner-sun8i-emac.h create mode 100644 hw/net/allwinner-sun8i-emac.c diff --git a/hw/net/Makefile.objs b/hw/net/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Makefile.objs +++ b/hw/net/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_XGMAC) += xgmac.o common-obj-$(CONFIG_MIPSNET) += mipsnet.o common-obj-$(CONFIG_XILINX_AXI) += xilinx_axienet.o common-obj-$(CONFIG_ALLWINNER_EMAC) += allwinner_emac.o +common-obj-$(CONFIG_ALLWINNER_SUN8I_EMAC) += allwinner-sun8i-emac.o common-obj-$(CONFIG_IMX_FEC) += imx_fec.o common-obj-$(CONFIG_CADENCE) += cadence_gem.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-h3-sysctrl.h" #include "hw/misc/allwinner-sid.h" #include "hw/sd/allwinner-sdhost.h" +#include "hw/net/allwinner-sun8i-emac.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_UART1, AW_H3_UART2, AW_H3_UART3, + AW_H3_EMAC, AW_H3_GIC_DIST, AW_H3_GIC_CPU, AW_H3_GIC_HYP, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; + AwSun8iEmacState emac; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/net/allwinner-sun8i-emac.h b/include/hw/net/allwinner-sun8i-emac.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/allwinner-sun8i-emac.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Sun8i Ethernet MAC emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_NET_ALLWINNER_SUN8I_EMAC_H +#define HW_NET_ALLWINNER_SUN8I_EMAC_H + +#include "qom/object.h" +#include "net/net.h" +#include "hw/sysbus.h" + +/** + * Object model + * @{ + */ + +#define TYPE_AW_SUN8I_EMAC "allwinner-sun8i-emac" +#define AW_SUN8I_EMAC(obj) \ + OBJECT_CHECK(AwSun8iEmacState, (obj), TYPE_AW_SUN8I_EMAC) + +/** @} */ + +/** + * Allwinner Sun8i EMAC object instance state + */ +typedef struct AwSun8iEmacState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Interrupt output signal to notify CPU */ + qemu_irq irq; + + /** Generic Network Interface Controller (NIC) for networking API */ + NICState *nic; + + /** Generic Network Interface Controller (NIC) configuration */ + NICConf conf; + + /** + * @name Media Independent Interface (MII) + * @{ + */ + + uint8_t mii_phy_addr; /**< PHY address */ + uint32_t mii_cr; /**< Control */ + uint32_t mii_st; /**< Status */ + uint32_t mii_adv; /**< Advertised Abilities */ + + /** @} */ + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t basic_ctl0; /**< Basic Control 0 */ + uint32_t basic_ctl1; /**< Basic Control 1 */ + uint32_t int_en; /**< Interrupt Enable */ + uint32_t int_sta; /**< Interrupt Status */ + uint32_t frm_flt; /**< Receive Frame Filter */ + + uint32_t rx_ctl0; /**< Receive Control 0 */ + uint32_t rx_ctl1; /**< Receive Control 1 */ + uint32_t rx_desc_head; /**< Receive Descriptor List Address */ + uint32_t rx_desc_curr; /**< Current Receive Descriptor Address */ + + uint32_t tx_ctl0; /**< Transmit Control 0 */ + uint32_t tx_ctl1; /**< Transmit Control 1 */ + uint32_t tx_desc_head; /**< Transmit Descriptor List Address */ + uint32_t tx_desc_curr; /**< Current Transmit Descriptor Address */ + uint32_t tx_flowctl; /**< Transmit Flow Control */ + + uint32_t mii_cmd; /**< Management Interface Command */ + uint32_t mii_data; /**< Management Interface Data */ + + /** @} */ + +} AwSun8iEmacState; + +#endif /* HW_NET_ALLWINNER_SUN8I_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_UART1] = 0x01c28400, [AW_H3_UART2] = 0x01c28800, [AW_H3_UART3] = 0x01c28c00, + [AW_H3_EMAC] = 0x01c30000, [AW_H3_GIC_DIST] = 0x01c81000, [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "twi1", 0x01c2b000, 1 * KiB }, { "twi2", 0x01c2b400, 1 * KiB }, { "scr", 0x01c2c400, 1 * KiB }, - { "emac", 0x01c30000, 64 * KiB }, { "gpu", 0x01c40000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, { "dramcom", 0x01c62000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_OHCI2 = 77, AW_H3_GIC_SPI_EHCI3 = 78, AW_H3_GIC_SPI_OHCI3 = 79, + AW_H3_GIC_SPI_EMAC = 82 }; /* Allwinner H3 general constants */ @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), TYPE_AW_SDHOST_SUN5I); + + sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), + TYPE_AW_SUN8I_EMAC); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), "sd-bus", &error_abort); + /* EMAC */ + if (nd_table[0].used) { + qemu_check_nic_model(&nd_table[0], TYPE_AW_SUN8I_EMAC); + qdev_set_nic_properties(DEVICE(&s->emac), &nd_table[0]); + } + qdev_init_nofail(DEVICE(&s->emac)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->emac), 0, s->memmap[AW_H3_EMAC]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->emac), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_EMAC)); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) warn_report("Security Identifier value does not include H3 prefix"); } + /* Setup EMAC properties */ + object_property_set_int(OBJECT(&h3->emac), 1, "phy-addr", &error_abort); + /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); diff --git a/hw/net/allwinner-sun8i-emac.c b/hw/net/allwinner-sun8i-emac.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/allwinner-sun8i-emac.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Sun8i Ethernet MAC emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "net/net.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "qemu/log.h" +#include "trace.h" +#include "net/checksum.h" +#include "qemu/module.h" +#include "exec/cpu-common.h" +#include "hw/net/allwinner-sun8i-emac.h" + +/* EMAC register offsets */ +enum { + REG_BASIC_CTL_0 = 0x0000, /* Basic Control 0 */ + REG_BASIC_CTL_1 = 0x0004, /* Basic Control 1 */ + REG_INT_STA = 0x0008, /* Interrupt Status */ + REG_INT_EN = 0x000C, /* Interrupt Enable */ + REG_TX_CTL_0 = 0x0010, /* Transmit Control 0 */ + REG_TX_CTL_1 = 0x0014, /* Transmit Control 1 */ + REG_TX_FLOW_CTL = 0x001C, /* Transmit Flow Control */ + REG_TX_DMA_DESC_LIST = 0x0020, /* Transmit Descriptor List Address */ + REG_RX_CTL_0 = 0x0024, /* Receive Control 0 */ + REG_RX_CTL_1 = 0x0028, /* Receive Control 1 */ + REG_RX_DMA_DESC_LIST = 0x0034, /* Receive Descriptor List Address */ + REG_FRM_FLT = 0x0038, /* Receive Frame Filter */ + REG_RX_HASH_0 = 0x0040, /* Receive Hash Table 0 */ + REG_RX_HASH_1 = 0x0044, /* Receive Hash Table 1 */ + REG_MII_CMD = 0x0048, /* Management Interface Command */ + REG_MII_DATA = 0x004C, /* Management Interface Data */ + REG_ADDR_HIGH = 0x0050, /* MAC Address High */ + REG_ADDR_LOW = 0x0054, /* MAC Address Low */ + REG_TX_DMA_STA = 0x00B0, /* Transmit DMA Status */ + REG_TX_CUR_DESC = 0x00B4, /* Transmit Current Descriptor */ + REG_TX_CUR_BUF = 0x00B8, /* Transmit Current Buffer */ + REG_RX_DMA_STA = 0x00C0, /* Receive DMA Status */ + REG_RX_CUR_DESC = 0x00C4, /* Receive Current Descriptor */ + REG_RX_CUR_BUF = 0x00C8, /* Receive Current Buffer */ + REG_RGMII_STA = 0x00D0, /* RGMII Status */ +}; + +/* EMAC register flags */ +enum { + BASIC_CTL0_100Mbps = (0b11 << 2), + BASIC_CTL0_FD = (1 << 0), + BASIC_CTL1_SOFTRST = (1 << 0), +}; + +enum { + INT_STA_RGMII_LINK = (1 << 16), + INT_STA_RX_EARLY = (1 << 13), + INT_STA_RX_OVERFLOW = (1 << 12), + INT_STA_RX_TIMEOUT = (1 << 11), + INT_STA_RX_DMA_STOP = (1 << 10), + INT_STA_RX_BUF_UA = (1 << 9), + INT_STA_RX = (1 << 8), + INT_STA_TX_EARLY = (1 << 5), + INT_STA_TX_UNDERFLOW = (1 << 4), + INT_STA_TX_TIMEOUT = (1 << 3), + INT_STA_TX_BUF_UA = (1 << 2), + INT_STA_TX_DMA_STOP = (1 << 1), + INT_STA_TX = (1 << 0), +}; + +enum { + INT_EN_RX_EARLY = (1 << 13), + INT_EN_RX_OVERFLOW = (1 << 12), + INT_EN_RX_TIMEOUT = (1 << 11), + INT_EN_RX_DMA_STOP = (1 << 10), + INT_EN_RX_BUF_UA = (1 << 9), + INT_EN_RX = (1 << 8), + INT_EN_TX_EARLY = (1 << 5), + INT_EN_TX_UNDERFLOW = (1 << 4), + INT_EN_TX_TIMEOUT = (1 << 3), + INT_EN_TX_BUF_UA = (1 << 2), + INT_EN_TX_DMA_STOP = (1 << 1), + INT_EN_TX = (1 << 0), +}; + +enum { + TX_CTL0_TX_EN = (1 << 31), + TX_CTL1_TX_DMA_START = (1 << 31), + TX_CTL1_TX_DMA_EN = (1 << 30), + TX_CTL1_TX_FLUSH = (1 << 0), +}; + +enum { + RX_CTL0_RX_EN = (1 << 31), + RX_CTL0_STRIP_FCS = (1 << 28), + RX_CTL0_CRC_IPV4 = (1 << 27), +}; + +enum { + RX_CTL1_RX_DMA_START = (1 << 31), + RX_CTL1_RX_DMA_EN = (1 << 30), + RX_CTL1_RX_MD = (1 << 1), +}; + +enum { + RX_FRM_FLT_DIS_ADDR = (1 << 31), +}; + +enum { + MII_CMD_PHY_ADDR_SHIFT = (12), + MII_CMD_PHY_ADDR_MASK = (0xf000), + MII_CMD_PHY_REG_SHIFT = (4), + MII_CMD_PHY_REG_MASK = (0xf0), + MII_CMD_PHY_RW = (1 << 1), + MII_CMD_PHY_BUSY = (1 << 0), +}; + +enum { + TX_DMA_STA_STOP = (0b000), + TX_DMA_STA_RUN_FETCH = (0b001), + TX_DMA_STA_WAIT_STA = (0b010), +}; + +enum { + RX_DMA_STA_STOP = (0b000), + RX_DMA_STA_RUN_FETCH = (0b001), + RX_DMA_STA_WAIT_FRM = (0b011), +}; + +/* EMAC register reset values */ +enum { + REG_BASIC_CTL_1_RST = 0x08000000, +}; + +/* EMAC constants */ +enum { + AW_SUN8I_EMAC_MIN_PKT_SZ = 64 +}; + +/* Transmit/receive frame descriptor */ +typedef struct FrameDescriptor { + uint32_t status; + uint32_t status2; + uint32_t addr; + uint32_t next; +} FrameDescriptor; + +/* Frame descriptor flags */ +enum { + DESC_STATUS_CTL = (1 << 31), + DESC_STATUS2_BUF_SIZE_MASK = (0x7ff), +}; + +/* Transmit frame descriptor flags */ +enum { + TX_DESC_STATUS_LENGTH_ERR = (1 << 14), + TX_DESC_STATUS2_FIRST_DESC = (1 << 29), + TX_DESC_STATUS2_LAST_DESC = (1 << 30), + TX_DESC_STATUS2_CHECKSUM_MASK = (0x3 << 27), +}; + +/* Receive frame descriptor flags */ +enum { + RX_DESC_STATUS_FIRST_DESC = (1 << 9), + RX_DESC_STATUS_LAST_DESC = (1 << 8), + RX_DESC_STATUS_FRM_LEN_MASK = (0x3fff0000), + RX_DESC_STATUS_FRM_LEN_SHIFT = (16), + RX_DESC_STATUS_NO_BUF = (1 << 14), + RX_DESC_STATUS_HEADER_ERR = (1 << 7), + RX_DESC_STATUS_LENGTH_ERR = (1 << 4), + RX_DESC_STATUS_CRC_ERR = (1 << 1), + RX_DESC_STATUS_PAYLOAD_ERR = (1 << 0), + RX_DESC_STATUS2_RX_INT_CTL = (1 << 31), +}; + +/* MII register offsets */ +enum { + MII_REG_CR = (0x0), /* Control */ + MII_REG_ST = (0x1), /* Status */ + MII_REG_ID_HIGH = (0x2), /* Identifier High */ + MII_REG_ID_LOW = (0x3), /* Identifier Low */ + MII_REG_ADV = (0x4), /* Advertised abilities */ + MII_REG_LPA = (0x5), /* Link partner abilities */ +}; + +/* MII register flags */ +enum { + MII_REG_CR_RESET = (1 << 15), + MII_REG_CR_POWERDOWN = (1 << 11), + MII_REG_CR_10Mbit = (0), + MII_REG_CR_100Mbit = (1 << 13), + MII_REG_CR_1000Mbit = (1 << 6), + MII_REG_CR_AUTO_NEG = (1 << 12), + MII_REG_CR_AUTO_NEG_RESTART = (1 << 9), + MII_REG_CR_FULLDUPLEX = (1 << 8), +}; + +enum { + MII_REG_ST_100BASE_T4 = (1 << 15), + MII_REG_ST_100BASE_X_FD = (1 << 14), + MII_REG_ST_100BASE_X_HD = (1 << 13), + MII_REG_ST_10_FD = (1 << 12), + MII_REG_ST_10_HD = (1 << 11), + MII_REG_ST_100BASE_T2_FD = (1 << 10), + MII_REG_ST_100BASE_T2_HD = (1 << 9), + MII_REG_ST_AUTONEG_COMPLETE = (1 << 5), + MII_REG_ST_AUTONEG_AVAIL = (1 << 3), + MII_REG_ST_LINK_UP = (1 << 2), +}; + +enum { + MII_REG_LPA_10_HD = (1 << 5), + MII_REG_LPA_10_FD = (1 << 6), + MII_REG_LPA_100_HD = (1 << 7), + MII_REG_LPA_100_FD = (1 << 8), + MII_REG_LPA_PAUSE = (1 << 10), + MII_REG_LPA_ASYMPAUSE = (1 << 11), +}; + +/* MII constants */ +enum { + MII_PHY_ID_HIGH = 0x0044, + MII_PHY_ID_LOW = 0x1400, +}; + +static void allwinner_sun8i_emac_mii_set_link(AwSun8iEmacState *s, + bool link_active) +{ + if (link_active) { + s->mii_st |= MII_REG_ST_LINK_UP; + } else { + s->mii_st &= ~MII_REG_ST_LINK_UP; + } +} + +static void allwinner_sun8i_emac_mii_reset(AwSun8iEmacState *s, + bool link_active) +{ + s->mii_cr = MII_REG_CR_100Mbit | MII_REG_CR_AUTO_NEG | + MII_REG_CR_FULLDUPLEX; + s->mii_st = MII_REG_ST_100BASE_T4 | MII_REG_ST_100BASE_X_FD | + MII_REG_ST_100BASE_X_HD | MII_REG_ST_10_FD | MII_REG_ST_10_HD | + MII_REG_ST_100BASE_T2_FD | MII_REG_ST_100BASE_T2_HD | + MII_REG_ST_AUTONEG_COMPLETE | MII_REG_ST_AUTONEG_AVAIL; + s->mii_adv = 0; + + allwinner_sun8i_emac_mii_set_link(s, link_active); +} + +static void allwinner_sun8i_emac_mii_cmd(AwSun8iEmacState *s) +{ + uint8_t addr, reg; + + addr = (s->mii_cmd & MII_CMD_PHY_ADDR_MASK) >> MII_CMD_PHY_ADDR_SHIFT; + reg = (s->mii_cmd & MII_CMD_PHY_REG_MASK) >> MII_CMD_PHY_REG_SHIFT; + + if (addr != s->mii_phy_addr) { + return; + } + + /* Read or write a PHY register? */ + if (s->mii_cmd & MII_CMD_PHY_RW) { + trace_allwinner_sun8i_emac_mii_write_reg(reg, s->mii_data); + + switch (reg) { + case MII_REG_CR: + if (s->mii_data & MII_REG_CR_RESET) { + allwinner_sun8i_emac_mii_reset(s, s->mii_st & + MII_REG_ST_LINK_UP); + } else { + s->mii_cr = s->mii_data & ~(MII_REG_CR_RESET | + MII_REG_CR_AUTO_NEG_RESTART); + } + break; + case MII_REG_ADV: + s->mii_adv = s->mii_data; + break; + case MII_REG_ID_HIGH: + case MII_REG_ID_LOW: + case MII_REG_LPA: + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: write access to " + "unknown MII register 0x%x\n", reg); + break; + } + } else { + switch (reg) { + case MII_REG_CR: + s->mii_data = s->mii_cr; + break; + case MII_REG_ST: + s->mii_data = s->mii_st; + break; + case MII_REG_ID_HIGH: + s->mii_data = MII_PHY_ID_HIGH; + break; + case MII_REG_ID_LOW: + s->mii_data = MII_PHY_ID_LOW; + break; + case MII_REG_ADV: + s->mii_data = s->mii_adv; + break; + case MII_REG_LPA: + s->mii_data = MII_REG_LPA_10_HD | MII_REG_LPA_10_FD | + MII_REG_LPA_100_HD | MII_REG_LPA_100_FD | + MII_REG_LPA_PAUSE | MII_REG_LPA_ASYMPAUSE; + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: read access to " + "unknown MII register 0x%x\n", reg); + s->mii_data = 0; + break; + } + + trace_allwinner_sun8i_emac_mii_read_reg(reg, s->mii_data); + } +} + +static void allwinner_sun8i_emac_update_irq(AwSun8iEmacState *s) +{ + qemu_set_irq(s->irq, (s->int_sta & s->int_en) != 0); +} + +static uint32_t allwinner_sun8i_emac_next_desc(FrameDescriptor *desc, + size_t min_size) +{ + uint32_t paddr = desc->next; + + cpu_physical_memory_read(paddr, desc, sizeof(*desc)); + + if ((desc->status & DESC_STATUS_CTL) && + (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_size) { + return paddr; + } else { + return 0; + } +} + +static uint32_t allwinner_sun8i_emac_get_desc(FrameDescriptor *desc, + uint32_t start_addr, + size_t min_size) +{ + uint32_t desc_addr = start_addr; + + /* Note that the list is a cycle. Last entry points back to the head. */ + while (desc_addr != 0) { + cpu_physical_memory_read(desc_addr, desc, sizeof(*desc)); + + if ((desc->status & DESC_STATUS_CTL) && + (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_size) { + return desc_addr; + } else if (desc->next == start_addr) { + break; + } else { + desc_addr = desc->next; + } + } + + return 0; +} + +static uint32_t allwinner_sun8i_emac_rx_desc(AwSun8iEmacState *s, + FrameDescriptor *desc, + size_t min_size) +{ + return allwinner_sun8i_emac_get_desc(desc, s->rx_desc_curr, min_size); +} + +static uint32_t allwinner_sun8i_emac_tx_desc(AwSun8iEmacState *s, + FrameDescriptor *desc, + size_t min_size) +{ + return allwinner_sun8i_emac_get_desc(desc, s->tx_desc_head, min_size); +} + +static void allwinner_sun8i_emac_flush_desc(FrameDescriptor *desc, + uint32_t phys_addr) +{ + cpu_physical_memory_write(phys_addr, desc, sizeof(*desc)); +} + +static int allwinner_sun8i_emac_can_receive(NetClientState *nc) +{ + AwSun8iEmacState *s = qemu_get_nic_opaque(nc); + FrameDescriptor desc; + + return (s->rx_ctl0 & RX_CTL0_RX_EN) && + (allwinner_sun8i_emac_rx_desc(s, &desc, 0) != 0); +} + +static ssize_t allwinner_sun8i_emac_receive(NetClientState *nc, + const uint8_t *buf, + size_t size) +{ + AwSun8iEmacState *s = qemu_get_nic_opaque(nc); + FrameDescriptor desc; + size_t bytes_left = size; + size_t desc_bytes = 0; + size_t pad_fcs_size = 4; + size_t padding = 0; + + if (!(s->rx_ctl0 & RX_CTL0_RX_EN)) { + return -1; + } + + s->rx_desc_curr = allwinner_sun8i_emac_rx_desc(s, &desc, + AW_SUN8I_EMAC_MIN_PKT_SZ); + if (!s->rx_desc_curr) { + s->int_sta |= INT_STA_RX_BUF_UA; + } + + /* Keep filling RX descriptors until the whole frame is written */ + while (s->rx_desc_curr && bytes_left > 0) { + desc.status &= ~DESC_STATUS_CTL; + desc.status &= ~RX_DESC_STATUS_FRM_LEN_MASK; + + if (bytes_left == size) { + desc.status |= RX_DESC_STATUS_FIRST_DESC; + } + + if ((desc.status2 & DESC_STATUS2_BUF_SIZE_MASK) < + (bytes_left + pad_fcs_size)) { + desc_bytes = desc.status2 & DESC_STATUS2_BUF_SIZE_MASK; + desc.status |= desc_bytes << RX_DESC_STATUS_FRM_LEN_SHIFT; + } else { + padding = pad_fcs_size; + if (bytes_left < AW_SUN8I_EMAC_MIN_PKT_SZ) { + padding += (AW_SUN8I_EMAC_MIN_PKT_SZ - bytes_left); + } + + desc_bytes = (bytes_left); + desc.status |= RX_DESC_STATUS_LAST_DESC; + desc.status |= (bytes_left + padding) + << RX_DESC_STATUS_FRM_LEN_SHIFT; + } + + cpu_physical_memory_write(desc.addr, buf, desc_bytes); + allwinner_sun8i_emac_flush_desc(&desc, s->rx_desc_curr); + trace_allwinner_sun8i_emac_receive(s->rx_desc_curr, desc.addr, + desc_bytes); + + /* Check if frame needs to raise the receive interrupt */ + if (!(desc.status2 & RX_DESC_STATUS2_RX_INT_CTL)) { + s->int_sta |= INT_STA_RX; + } + + /* Increment variables */ + buf += desc_bytes; + bytes_left -= desc_bytes; + + /* Move to the next descriptor */ + s->rx_desc_curr = allwinner_sun8i_emac_next_desc(&desc, 64); + if (!s->rx_desc_curr) { + /* Not enough buffer space available */ + s->int_sta |= INT_STA_RX_BUF_UA; + s->rx_desc_curr = s->rx_desc_head; + break; + } + } + + /* Report receive DMA is finished */ + s->rx_ctl1 &= ~RX_CTL1_RX_DMA_START; + allwinner_sun8i_emac_update_irq(s); + + return size; +} + +static void allwinner_sun8i_emac_transmit(AwSun8iEmacState *s) +{ + NetClientState *nc = qemu_get_queue(s->nic); + FrameDescriptor desc; + size_t bytes = 0; + size_t packet_bytes = 0; + size_t transmitted = 0; + static uint8_t packet_buf[2048]; + + s->tx_desc_curr = allwinner_sun8i_emac_tx_desc(s, &desc, 0); + + /* Read all transmit descriptors */ + while (s->tx_desc_curr != 0) { + + /* Read from physical memory into packet buffer */ + bytes = desc.status2 & DESC_STATUS2_BUF_SIZE_MASK; + if (bytes + packet_bytes > sizeof(packet_buf)) { + desc.status |= TX_DESC_STATUS_LENGTH_ERR; + break; + } + cpu_physical_memory_read(desc.addr, packet_buf + packet_bytes, bytes); + packet_bytes += bytes; + desc.status &= ~DESC_STATUS_CTL; + allwinner_sun8i_emac_flush_desc(&desc, s->tx_desc_curr); + + /* After the last descriptor, send the packet */ + if (desc.status2 & TX_DESC_STATUS2_LAST_DESC) { + if (desc.status2 & TX_DESC_STATUS2_CHECKSUM_MASK) { + net_checksum_calculate(packet_buf, packet_bytes); + } + + qemu_send_packet(nc, packet_buf, packet_bytes); + trace_allwinner_sun8i_emac_transmit(s->tx_desc_curr, desc.addr, + bytes); + + packet_bytes = 0; + transmitted++; + } + s->tx_desc_curr = allwinner_sun8i_emac_next_desc(&desc, 0); + } + + /* Raise transmit completed interrupt */ + if (transmitted > 0) { + s->int_sta |= INT_STA_TX; + s->tx_ctl1 &= ~TX_CTL1_TX_DMA_START; + allwinner_sun8i_emac_update_irq(s); + } +} + +static void allwinner_sun8i_emac_reset(DeviceState *dev) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(dev); + NetClientState *nc = qemu_get_queue(s->nic); + + trace_allwinner_sun8i_emac_reset(); + + s->mii_cmd = 0; + s->mii_data = 0; + s->basic_ctl0 = 0; + s->basic_ctl1 = REG_BASIC_CTL_1_RST; + s->int_en = 0; + s->int_sta = 0; + s->frm_flt = 0; + s->rx_ctl0 = 0; + s->rx_ctl1 = RX_CTL1_RX_MD; + s->rx_desc_head = 0; + s->rx_desc_curr = 0; + s->tx_ctl0 = 0; + s->tx_ctl1 = 0; + s->tx_desc_head = 0; + s->tx_desc_curr = 0; + s->tx_flowctl = 0; + + allwinner_sun8i_emac_mii_reset(s, !nc->link_down); +} + +static uint64_t allwinner_sun8i_emac_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(opaque); + uint64_t value = 0; + FrameDescriptor desc; + + switch (offset) { + case REG_BASIC_CTL_0: /* Basic Control 0 */ + value = s->basic_ctl0; + break; + case REG_BASIC_CTL_1: /* Basic Control 1 */ + value = s->basic_ctl1; + break; + case REG_INT_STA: /* Interrupt Status */ + value = s->int_sta; + break; + case REG_INT_EN: /* Interupt Enable */ + value = s->int_en; + break; + case REG_TX_CTL_0: /* Transmit Control 0 */ + value = s->tx_ctl0; + break; + case REG_TX_CTL_1: /* Transmit Control 1 */ + value = s->tx_ctl1; + break; + case REG_TX_FLOW_CTL: /* Transmit Flow Control */ + value = s->tx_flowctl; + break; + case REG_TX_DMA_DESC_LIST: /* Transmit Descriptor List Address */ + value = s->tx_desc_head; + break; + case REG_RX_CTL_0: /* Receive Control 0 */ + value = s->rx_ctl0; + break; + case REG_RX_CTL_1: /* Receive Control 1 */ + value = s->rx_ctl1; + break; + case REG_RX_DMA_DESC_LIST: /* Receive Descriptor List Address */ + value = s->rx_desc_head; + break; + case REG_FRM_FLT: /* Receive Frame Filter */ + value = s->frm_flt; + break; + case REG_RX_HASH_0: /* Receive Hash Table 0 */ + case REG_RX_HASH_1: /* Receive Hash Table 1 */ + break; + case REG_MII_CMD: /* Management Interface Command */ + value = s->mii_cmd; + break; + case REG_MII_DATA: /* Management Interface Data */ + value = s->mii_data; + break; + case REG_ADDR_HIGH: /* MAC Address High */ + value = *(((uint32_t *) (s->conf.macaddr.a)) + 1); + break; + case REG_ADDR_LOW: /* MAC Address Low */ + value = *(uint32_t *) (s->conf.macaddr.a); + break; + case REG_TX_DMA_STA: /* Transmit DMA Status */ + break; + case REG_TX_CUR_DESC: /* Transmit Current Descriptor */ + value = s->tx_desc_curr; + break; + case REG_TX_CUR_BUF: /* Transmit Current Buffer */ + if (s->tx_desc_curr != 0) { + cpu_physical_memory_read(s->tx_desc_curr, &desc, sizeof(desc)); + value = desc.addr; + } else { + value = 0; + } + break; + case REG_RX_DMA_STA: /* Receive DMA Status */ + break; + case REG_RX_CUR_DESC: /* Receive Current Descriptor */ + value = s->rx_desc_curr; + break; + case REG_RX_CUR_BUF: /* Receive Current Buffer */ + if (s->rx_desc_curr != 0) { + cpu_physical_memory_read(s->rx_desc_curr, &desc, sizeof(desc)); + value = desc.addr; + } else { + value = 0; + } + break; + case REG_RGMII_STA: /* RGMII Status */ + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: read access to unknown " + "EMAC register 0x" TARGET_FMT_plx "\n", + offset); + } + + trace_allwinner_sun8i_emac_read(offset, value); + return value; +} + +static void allwinner_sun8i_emac_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(opaque); + NetClientState *nc = qemu_get_queue(s->nic); + + trace_allwinner_sun8i_emac_write(offset, value); + + switch (offset) { + case REG_BASIC_CTL_0: /* Basic Control 0 */ + s->basic_ctl0 = value; + break; + case REG_BASIC_CTL_1: /* Basic Control 1 */ + if (value & BASIC_CTL1_SOFTRST) { + allwinner_sun8i_emac_reset(DEVICE(s)); + value &= ~BASIC_CTL1_SOFTRST; + } + s->basic_ctl1 = value; + if (allwinner_sun8i_emac_can_receive(nc)) { + qemu_flush_queued_packets(nc); + } + break; + case REG_INT_STA: /* Interrupt Status */ + s->int_sta &= ~value; + allwinner_sun8i_emac_update_irq(s); + break; + case REG_INT_EN: /* Interrupt Enable */ + s->int_en = value; + allwinner_sun8i_emac_update_irq(s); + break; + case REG_TX_CTL_0: /* Transmit Control 0 */ + s->tx_ctl0 = value; + break; + case REG_TX_CTL_1: /* Transmit Control 1 */ + s->tx_ctl1 = value; + if (value & TX_CTL1_TX_DMA_EN) { + allwinner_sun8i_emac_transmit(s); + } + break; + case REG_TX_FLOW_CTL: /* Transmit Flow Control */ + s->tx_flowctl = value; + break; + case REG_TX_DMA_DESC_LIST: /* Transmit Descriptor List Address */ + s->tx_desc_head = value; + s->tx_desc_curr = value; + break; + case REG_RX_CTL_0: /* Receive Control 0 */ + s->rx_ctl0 = value; + break; + case REG_RX_CTL_1: /* Receive Control 1 */ + s->rx_ctl1 = value | RX_CTL1_RX_MD; + if ((value & RX_CTL1_RX_DMA_EN) && + allwinner_sun8i_emac_can_receive(nc)) { + qemu_flush_queued_packets(nc); + } + break; + case REG_RX_DMA_DESC_LIST: /* Receive Descriptor List Address */ + s->rx_desc_head = value; + s->rx_desc_curr = value; + break; + case REG_FRM_FLT: /* Receive Frame Filter */ + s->frm_flt = value; + break; + case REG_RX_HASH_0: /* Receive Hash Table 0 */ + case REG_RX_HASH_1: /* Receive Hash Table 1 */ + break; + case REG_MII_CMD: /* Management Interface Command */ + s->mii_cmd = value & ~MII_CMD_PHY_BUSY; + allwinner_sun8i_emac_mii_cmd(s); + break; + case REG_MII_DATA: /* Management Interface Data */ + s->mii_data = value; + break; + case REG_ADDR_HIGH: /* MAC Address High */ + s->conf.macaddr.a[4] = (value & 0xff); + s->conf.macaddr.a[5] = (value & 0xff00) >> 8; + break; + case REG_ADDR_LOW: /* MAC Address Low */ + s->conf.macaddr.a[0] = (value & 0xff); + s->conf.macaddr.a[1] = (value & 0xff00) >> 8; + s->conf.macaddr.a[2] = (value & 0xff0000) >> 16; + s->conf.macaddr.a[3] = (value & 0xff000000) >> 24; + break; + case REG_TX_DMA_STA: /* Transmit DMA Status */ + case REG_TX_CUR_DESC: /* Transmit Current Descriptor */ + case REG_TX_CUR_BUF: /* Transmit Current Buffer */ + case REG_RX_DMA_STA: /* Receive DMA Status */ + case REG_RX_CUR_DESC: /* Receive Current Descriptor */ + case REG_RX_CUR_BUF: /* Receive Current Buffer */ + case REG_RGMII_STA: /* RGMII Status */ + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: write access to unknown " + "EMAC register 0x" TARGET_FMT_plx "\n", + offset); + } +} + +static void allwinner_sun8i_emac_set_link(NetClientState *nc) +{ + AwSun8iEmacState *s = qemu_get_nic_opaque(nc); + + trace_allwinner_sun8i_emac_set_link(!nc->link_down); + allwinner_sun8i_emac_mii_set_link(s, !nc->link_down); +} + +static const MemoryRegionOps allwinner_sun8i_emac_mem_ops = { + .read = allwinner_sun8i_emac_read, + .write = allwinner_sun8i_emac_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static NetClientInfo net_allwinner_sun8i_emac_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = allwinner_sun8i_emac_can_receive, + .receive = allwinner_sun8i_emac_receive, + .link_status_changed = allwinner_sun8i_emac_set_link, +}; + +static void allwinner_sun8i_emac_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwSun8iEmacState *s = AW_SUN8I_EMAC(obj); + + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_sun8i_emac_mem_ops, + s, TYPE_AW_SUN8I_EMAC, 64 * KiB); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(sbd, &s->irq); +} + +static void allwinner_sun8i_emac_realize(DeviceState *dev, Error **errp) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(dev); + + qemu_macaddr_default_if_unset(&s->conf.macaddr); + s->nic = qemu_new_nic(&net_allwinner_sun8i_emac_info, &s->conf, + object_get_typename(OBJECT(dev)), dev->id, s); + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static Property allwinner_sun8i_emac_properties[] = { + DEFINE_NIC_PROPERTIES(AwSun8iEmacState, conf), + DEFINE_PROP_UINT8("phy-addr", AwSun8iEmacState, mii_phy_addr, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static int allwinner_sun8i_emac_post_load(void *opaque, int version_id) +{ + AwSun8iEmacState *s = opaque; + + allwinner_sun8i_emac_set_link(qemu_get_queue(s->nic)); + + return 0; +} + +static const VMStateDescription vmstate_aw_emac = { + .name = "allwinner-sun8i-emac", + .version_id = 1, + .minimum_version_id = 1, + .post_load = allwinner_sun8i_emac_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT8(mii_phy_addr, AwSun8iEmacState), + VMSTATE_UINT32(mii_cmd, AwSun8iEmacState), + VMSTATE_UINT32(mii_data, AwSun8iEmacState), + VMSTATE_UINT32(mii_cr, AwSun8iEmacState), + VMSTATE_UINT32(mii_st, AwSun8iEmacState), + VMSTATE_UINT32(mii_adv, AwSun8iEmacState), + VMSTATE_UINT32(basic_ctl0, AwSun8iEmacState), + VMSTATE_UINT32(basic_ctl1, AwSun8iEmacState), + VMSTATE_UINT32(int_en, AwSun8iEmacState), + VMSTATE_UINT32(int_sta, AwSun8iEmacState), + VMSTATE_UINT32(frm_flt, AwSun8iEmacState), + VMSTATE_UINT32(rx_ctl0, AwSun8iEmacState), + VMSTATE_UINT32(rx_ctl1, AwSun8iEmacState), + VMSTATE_UINT32(rx_desc_head, AwSun8iEmacState), + VMSTATE_UINT32(rx_desc_curr, AwSun8iEmacState), + VMSTATE_UINT32(tx_ctl0, AwSun8iEmacState), + VMSTATE_UINT32(tx_ctl1, AwSun8iEmacState), + VMSTATE_UINT32(tx_desc_head, AwSun8iEmacState), + VMSTATE_UINT32(tx_desc_curr, AwSun8iEmacState), + VMSTATE_UINT32(tx_flowctl, AwSun8iEmacState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sun8i_emac_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = allwinner_sun8i_emac_realize; + dc->reset = allwinner_sun8i_emac_reset; + dc->vmsd = &vmstate_aw_emac; + device_class_set_props(dc, allwinner_sun8i_emac_properties); +} + +static const TypeInfo allwinner_sun8i_emac_info = { + .name = TYPE_AW_SUN8I_EMAC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AwSun8iEmacState), + .instance_init = allwinner_sun8i_emac_init, + .class_init = allwinner_sun8i_emac_class_init, +}; + +static void allwinner_sun8i_emac_register_types(void) +{ + type_register_static(&allwinner_sun8i_emac_info); +} + +type_init(allwinner_sun8i_emac_register_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 ALLWINNER_A10 config ALLWINNER_H3 bool select ALLWINNER_A10_PIT + select ALLWINNER_SUN8I_EMAC select SERIAL select ARM_TIMER select ARM_GIC diff --git a/hw/net/Kconfig b/hw/net/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Kconfig +++ b/hw/net/Kconfig @@ -XXX,XX +XXX,XX @@ config MIPSNET config ALLWINNER_EMAC bool +config ALLWINNER_SUN8I_EMAC + bool + config IMX_FEC bool diff --git a/hw/net/trace-events b/hw/net/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-sun8i-emac.c +allwinner_sun8i_emac_mii_write_reg(uint32_t reg, uint32_t value) "MII write: reg=0x%" PRIx32 " value=0x%" PRIx32 +allwinner_sun8i_emac_mii_read_reg(uint32_t reg, uint32_t value) "MII read: reg=0x%" PRIx32 " value=0x%" PRIx32 +allwinner_sun8i_emac_receive(uint32_t desc, uint32_t paddr, uint32_t bytes) "RX packet: desc=0x%" PRIx32 " paddr=0x%" PRIx32 " bytes=%" PRIu32 +allwinner_sun8i_emac_transmit(uint32_t desc, uint32_t paddr, uint32_t bytes) "TX packet: desc=0x%" PRIx32 " paddr=0x%" PRIx32 " bytes=%" PRIu32 +allwinner_sun8i_emac_reset(void) "HW reset" +allwinner_sun8i_emac_set_link(bool active) "Set link: active=%u" +allwinner_sun8i_emac_read(uint64_t offset, uint64_t val) "MMIO read: offset=0x%" PRIx64 " value=0x%" PRIx64 +allwinner_sun8i_emac_write(uint64_t offset, uint64_t val) "MMIO write: offset=0x%" PRIx64 " value=0x%" PRIx64 + # etraxfs_eth.c mdio_phy_read(int regnum, uint16_t value) "read phy_reg:%d value:0x%04x" mdio_phy_write(int regnum, uint16_t value) "write phy_reg:%d value:0x%04x" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> A real Allwinner H3 SoC contains a Boot ROM which is the first code that runs right after the SoC is powered on. The Boot ROM is responsible for loading user code (e.g. a bootloader) from any of the supported external devices and writing the downloaded code to internal SRAM. After loading the SoC begins executing the code written to SRAM. This commits adds emulation of the Boot ROM firmware setup functionality by loading user code from SD card in the A1 SRAM. While the A1 SRAM is 64KiB, we limit the size to 32KiB because the real H3 Boot ROM also rejects sizes larger than 32KiB. For reference, this behaviour is documented by the Linux Sunxi project wiki at: https://linux-sunxi.org/BROM#U-Boot_SPL_limitations Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-11-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-h3.h | 21 +++++++++++++++++++++ hw/arm/allwinner-h3.c | 17 +++++++++++++++++ hw/arm/orangepi.c | 5 +++++ 3 files changed, 43 insertions(+) diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" #include "target/arm/cpu.h" +#include "sysemu/block-backend.h" /** * Allwinner H3 device list @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { MemoryRegion sram_c; } AwH3State; +/** + * Emulate Boot ROM firmware setup functionality. + * + * A real Allwinner H3 SoC contains a Boot ROM + * which is the first code that runs right after + * the SoC is powered on. The Boot ROM is responsible + * for loading user code (e.g. a bootloader) from any + * of the supported external devices and writing the + * downloaded code to internal SRAM. After loading the SoC + * begins executing the code written to SRAM. + * + * This function emulates the Boot ROM by copying 32 KiB + * of data from the given block device and writes it to + * the start of the first internal SRAM memory. + * + * @s: Allwinner H3 state object pointer + * @blk: Block backend device object pointer + */ +void allwinner_h3_bootrom_setup(AwH3State *s, BlockBackend *blk); + #endif /* HW_ARM_ALLWINNER_H3_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/serial.h" #include "hw/misc/unimp.h" #include "hw/usb/hcd-ehci.h" +#include "hw/loader.h" #include "sysemu/sysemu.h" #include "hw/arm/allwinner-h3.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_NUM_SPI = 128 }; +void allwinner_h3_bootrom_setup(AwH3State *s, BlockBackend *blk) +{ + const int64_t rom_size = 32 * KiB; + g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); + + if (blk_pread(blk, 8 * KiB, buffer, rom_size) < 0) { + error_setg(&error_fatal, "%s: failed to read BlockBackend data", + __func__); + return; + } + + rom_add_blob("allwinner-h3.bootrom", buffer, rom_size, + rom_size, s->memmap[AW_H3_SRAM_A1], + NULL, NULL, NULL, NULL, false); +} + static void allwinner_h3_init(Object *obj) { AwH3State *s = AW_H3(obj); diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), h3->memmap[AW_H3_SDRAM], machine->ram); + /* Load target kernel or start using BootROM */ + if (!machine->kernel_filename && blk_is_available(blk)) { + /* Use Boot ROM to copy data from SD card to SRAM */ + allwinner_h3_bootrom_setup(h3, blk); + } orangepi_binfo.loader_start = h3->memmap[AW_H3_SDRAM]; orangepi_binfo.ram_size = machine->ram_size; arm_load_kernel(ARM_CPU(first_cpu), machine, &orangepi_binfo); -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> In the Allwinner H3 SoC the SDRAM controller is responsible for interfacing with the external Synchronous Dynamic Random Access Memory (SDRAM). Types of memory that the SDRAM controller supports are DDR2/DDR3 and capacities of up to 2GiB. This commit adds emulation support of the Allwinner H3 SDRAM controller. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-12-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 5 + include/hw/misc/allwinner-h3-dramc.h | 106 ++++++++ hw/arm/allwinner-h3.c | 19 +- hw/arm/orangepi.c | 6 + hw/misc/allwinner-h3-dramc.c | 358 +++++++++++++++++++++++++++ hw/misc/trace-events | 10 + 7 files changed, 502 insertions(+), 3 deletions(-) create mode 100644 include/hw/misc/allwinner-h3-dramc.h create mode 100644 hw/misc/allwinner-h3-dramc.c 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_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o obj-$(CONFIG_ALLWINNER_H3) += allwinner-cpucfg.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-dramc.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-sid.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" #include "hw/misc/allwinner-cpucfg.h" +#include "hw/misc/allwinner-h3-dramc.h" #include "hw/misc/allwinner-h3-sysctrl.h" #include "hw/misc/allwinner-sid.h" #include "hw/sd/allwinner-sdhost.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_UART2, AW_H3_UART3, AW_H3_EMAC, + AW_H3_DRAMCOM, + AW_H3_DRAMCTL, + AW_H3_DRAMPHY, AW_H3_GIC_DIST, AW_H3_GIC_CPU, AW_H3_GIC_HYP, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwA10PITState timer; AwH3ClockCtlState ccu; AwCpuCfgState cpucfg; + AwH3DramCtlState dramc; AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; diff --git a/include/hw/misc/allwinner-h3-dramc.h b/include/hw/misc/allwinner-h3-dramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-h3-dramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 SDRAM Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_H3_DRAMC_H +#define HW_MISC_ALLWINNER_H3_DRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "exec/hwaddr.h" + +/** + * Constants + * @{ + */ + +/** Highest register address used by DRAMCOM module */ +#define AW_H3_DRAMCOM_REGS_MAXADDR (0x804) + +/** Total number of known DRAMCOM registers */ +#define AW_H3_DRAMCOM_REGS_NUM (AW_H3_DRAMCOM_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** Highest register address used by DRAMCTL module */ +#define AW_H3_DRAMCTL_REGS_MAXADDR (0x88c) + +/** Total number of known DRAMCTL registers */ +#define AW_H3_DRAMCTL_REGS_NUM (AW_H3_DRAMCTL_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** Highest register address used by DRAMPHY module */ +#define AW_H3_DRAMPHY_REGS_MAXADDR (0x4) + +/** Total number of known DRAMPHY registers */ +#define AW_H3_DRAMPHY_REGS_NUM (AW_H3_DRAMPHY_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** @} */ + +/** + * Object model + * @{ + */ + +#define TYPE_AW_H3_DRAMC "allwinner-h3-dramc" +#define AW_H3_DRAMC(obj) \ + OBJECT_CHECK(AwH3DramCtlState, (obj), TYPE_AW_H3_DRAMC) + +/** @} */ + +/** + * Allwinner H3 SDRAM Controller object instance state. + */ +typedef struct AwH3DramCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Physical base address for start of RAM */ + hwaddr ram_addr; + + /** Total RAM size in megabytes */ + uint32_t ram_size; + + /** + * @name Memory Regions + * @{ + */ + + MemoryRegion row_mirror; /**< Simulates rows for RAM size detection */ + MemoryRegion row_mirror_alias; /**< Alias of the row which is mirrored */ + MemoryRegion dramcom_iomem; /**< DRAMCOM module I/O registers */ + MemoryRegion dramctl_iomem; /**< DRAMCTL module I/O registers */ + MemoryRegion dramphy_iomem; /**< DRAMPHY module I/O registers */ + + /** @} */ + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t dramcom[AW_H3_DRAMCOM_REGS_NUM]; /**< Array of DRAMCOM registers */ + uint32_t dramctl[AW_H3_DRAMCTL_REGS_NUM]; /**< Array of DRAMCTL registers */ + uint32_t dramphy[AW_H3_DRAMPHY_REGS_NUM] ;/**< Array of DRAMPHY registers */ + + /** @} */ + +} AwH3DramCtlState; + +#endif /* HW_MISC_ALLWINNER_H3_DRAMC_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_UART2] = 0x01c28800, [AW_H3_UART3] = 0x01c28c00, [AW_H3_EMAC] = 0x01c30000, + [AW_H3_DRAMCOM] = 0x01c62000, + [AW_H3_DRAMCTL] = 0x01c63000, + [AW_H3_DRAMPHY] = 0x01c65000, [AW_H3_GIC_DIST] = 0x01c81000, [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "scr", 0x01c2c400, 1 * KiB }, { "gpu", 0x01c40000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, - { "dramcom", 0x01c62000, 4 * KiB }, - { "dramctl0", 0x01c63000, 4 * KiB }, - { "dramphy0", 0x01c65000, 4 * KiB }, { "spi0", 0x01c68000, 4 * KiB }, { "spi1", 0x01c69000, 4 * KiB }, { "csi", 0x01cb0000, 320 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), TYPE_AW_SUN8I_EMAC); + + sysbus_init_child_obj(obj, "dramc", &s->dramc, sizeof(s->dramc), + TYPE_AW_H3_DRAMC); + object_property_add_alias(obj, "ram-addr", OBJECT(&s->dramc), + "ram-addr", &error_abort); + object_property_add_alias(obj, "ram-size", OBJECT(&s->dramc), + "ram-size", &error_abort); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART3), 115200, serial_hd(3), DEVICE_NATIVE_ENDIAN); + /* DRAMC */ + qdev_init_nofail(DEVICE(&s->dramc)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 0, s->memmap[AW_H3_DRAMCOM]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 1, s->memmap[AW_H3_DRAMCTL]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 2, s->memmap[AW_H3_DRAMPHY]); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) /* Setup EMAC properties */ object_property_set_int(OBJECT(&h3->emac), 1, "phy-addr", &error_abort); + /* DRAMC */ + object_property_set_uint(OBJECT(h3), h3->memmap[AW_H3_SDRAM], + "ram-addr", &error_abort); + object_property_set_int(OBJECT(h3), machine->ram_size / MiB, "ram-size", + &error_abort); + /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); diff --git a/hw/misc/allwinner-h3-dramc.c b/hw/misc/allwinner-h3-dramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-h3-dramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 SDRAM Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu/error-report.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "exec/address-spaces.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" +#include "hw/misc/allwinner-h3-dramc.h" +#include "trace.h" + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* DRAMCOM register offsets */ +enum { + REG_DRAMCOM_CR = 0x0000, /* Control Register */ +}; + +/* DRAMCTL register offsets */ +enum { + REG_DRAMCTL_PIR = 0x0000, /* PHY Initialization Register */ + REG_DRAMCTL_PGSR = 0x0010, /* PHY General Status Register */ + REG_DRAMCTL_STATR = 0x0018, /* Status Register */ +}; + +/* DRAMCTL register flags */ +enum { + REG_DRAMCTL_PGSR_INITDONE = (1 << 0), +}; + +enum { + REG_DRAMCTL_STATR_ACTIVE = (1 << 0), +}; + +static void allwinner_h3_dramc_map_rows(AwH3DramCtlState *s, uint8_t row_bits, + uint8_t bank_bits, uint16_t page_size) +{ + /* + * This function simulates row addressing behavior when bootloader + * software attempts to detect the amount of available SDRAM. In U-Boot + * the controller is configured with the widest row addressing available. + * Then a pattern is written to RAM at an offset on the row boundary size. + * If the value read back equals the value read back from the + * start of RAM, the bootloader knows the amount of row bits. + * + * This function inserts a mirrored memory region when the configured row + * bits are not matching the actual emulated memory, to simulate the + * same behavior on hardware as expected by the bootloader. + */ + uint8_t row_bits_actual = 0; + + /* Calculate the actual row bits using the ram_size property */ + for (uint8_t i = 8; i < 12; i++) { + if (1 << i == s->ram_size) { + row_bits_actual = i + 3; + break; + } + } + + if (s->ram_size == (1 << (row_bits - 3))) { + /* When row bits is the expected value, remove the mirror */ + memory_region_set_enabled(&s->row_mirror_alias, false); + trace_allwinner_h3_dramc_rowmirror_disable(); + + } else if (row_bits_actual) { + /* Row bits not matching ram_size, install the rows mirror */ + hwaddr row_mirror = s->ram_addr + ((1 << (row_bits_actual + + bank_bits)) * page_size); + + memory_region_set_enabled(&s->row_mirror_alias, true); + memory_region_set_address(&s->row_mirror_alias, row_mirror); + + trace_allwinner_h3_dramc_rowmirror_enable(row_mirror); + } +} + +static uint64_t allwinner_h3_dramcom_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_DRAMCOM_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_h3_dramcom_read(offset, s->dramcom[idx], size); + + return s->dramcom[idx]; +} + +static void allwinner_h3_dramcom_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_h3_dramcom_write(offset, val, size); + + if (idx >= AW_H3_DRAMCOM_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_DRAMCOM_CR: /* Control Register */ + allwinner_h3_dramc_map_rows(s, ((val >> 4) & 0xf) + 1, + ((val >> 2) & 0x1) + 2, + 1 << (((val >> 8) & 0xf) + 3)); + break; + default: + break; + }; + + s->dramcom[idx] = (uint32_t) val; +} + +static uint64_t allwinner_h3_dramctl_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_DRAMCTL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_h3_dramctl_read(offset, s->dramctl[idx], size); + + return s->dramctl[idx]; +} + +static void allwinner_h3_dramctl_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_h3_dramctl_write(offset, val, size); + + if (idx >= AW_H3_DRAMCTL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_DRAMCTL_PIR: /* PHY Initialization Register */ + s->dramctl[REG_INDEX(REG_DRAMCTL_PGSR)] |= REG_DRAMCTL_PGSR_INITDONE; + s->dramctl[REG_INDEX(REG_DRAMCTL_STATR)] |= REG_DRAMCTL_STATR_ACTIVE; + break; + default: + break; + } + + s->dramctl[idx] = (uint32_t) val; +} + +static uint64_t allwinner_h3_dramphy_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_DRAMPHY_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_h3_dramphy_read(offset, s->dramphy[idx], size); + + return s->dramphy[idx]; +} + +static void allwinner_h3_dramphy_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_h3_dramphy_write(offset, val, size); + + if (idx >= AW_H3_DRAMPHY_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + s->dramphy[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_h3_dramcom_ops = { + .read = allwinner_h3_dramcom_read, + .write = allwinner_h3_dramcom_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const MemoryRegionOps allwinner_h3_dramctl_ops = { + .read = allwinner_h3_dramctl_read, + .write = allwinner_h3_dramctl_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const MemoryRegionOps allwinner_h3_dramphy_ops = { + .read = allwinner_h3_dramphy_read, + .write = allwinner_h3_dramphy_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_h3_dramc_reset(DeviceState *dev) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(dev); + + /* Set default values for registers */ + memset(&s->dramcom, 0, sizeof(s->dramcom)); + memset(&s->dramctl, 0, sizeof(s->dramctl)); + memset(&s->dramphy, 0, sizeof(s->dramphy)); +} + +static void allwinner_h3_dramc_realize(DeviceState *dev, Error **errp) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(dev); + + /* Only power of 2 RAM sizes from 256MiB up to 2048MiB are supported */ + for (uint8_t i = 8; i < 13; i++) { + if (1 << i == s->ram_size) { + break; + } else if (i == 12) { + error_report("%s: ram-size %u MiB is not supported", + __func__, s->ram_size); + exit(1); + } + } + + /* Setup row mirror mappings */ + memory_region_init_ram(&s->row_mirror, OBJECT(s), + "allwinner-h3-dramc.row-mirror", + 4 * KiB, &error_abort); + memory_region_add_subregion_overlap(get_system_memory(), s->ram_addr, + &s->row_mirror, 10); + + memory_region_init_alias(&s->row_mirror_alias, OBJECT(s), + "allwinner-h3-dramc.row-mirror-alias", + &s->row_mirror, 0, 4 * KiB); + memory_region_add_subregion_overlap(get_system_memory(), + s->ram_addr + 1 * MiB, + &s->row_mirror_alias, 10); + memory_region_set_enabled(&s->row_mirror_alias, false); +} + +static void allwinner_h3_dramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwH3DramCtlState *s = AW_H3_DRAMC(obj); + + /* DRAMCOM registers */ + memory_region_init_io(&s->dramcom_iomem, OBJECT(s), + &allwinner_h3_dramcom_ops, s, + TYPE_AW_H3_DRAMC, 4 * KiB); + sysbus_init_mmio(sbd, &s->dramcom_iomem); + + /* DRAMCTL registers */ + memory_region_init_io(&s->dramctl_iomem, OBJECT(s), + &allwinner_h3_dramctl_ops, s, + TYPE_AW_H3_DRAMC, 4 * KiB); + sysbus_init_mmio(sbd, &s->dramctl_iomem); + + /* DRAMPHY registers */ + memory_region_init_io(&s->dramphy_iomem, OBJECT(s), + &allwinner_h3_dramphy_ops, s, + TYPE_AW_H3_DRAMC, 4 * KiB); + sysbus_init_mmio(sbd, &s->dramphy_iomem); +} + +static Property allwinner_h3_dramc_properties[] = { + DEFINE_PROP_UINT64("ram-addr", AwH3DramCtlState, ram_addr, 0x0), + DEFINE_PROP_UINT32("ram-size", AwH3DramCtlState, ram_size, 256 * MiB), + DEFINE_PROP_END_OF_LIST() +}; + +static const VMStateDescription allwinner_h3_dramc_vmstate = { + .name = "allwinner-h3-dramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(dramcom, AwH3DramCtlState, AW_H3_DRAMCOM_REGS_NUM), + VMSTATE_UINT32_ARRAY(dramctl, AwH3DramCtlState, AW_H3_DRAMCTL_REGS_NUM), + VMSTATE_UINT32_ARRAY(dramphy, AwH3DramCtlState, AW_H3_DRAMPHY_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_h3_dramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_h3_dramc_reset; + dc->vmsd = &allwinner_h3_dramc_vmstate; + dc->realize = allwinner_h3_dramc_realize; + device_class_set_props(dc, allwinner_h3_dramc_properties); +} + +static const TypeInfo allwinner_h3_dramc_info = { + .name = TYPE_AW_H3_DRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_h3_dramc_init, + .instance_size = sizeof(AwH3DramCtlState), + .class_init = allwinner_h3_dramc_class_init, +}; + +static void allwinner_h3_dramc_register(void) +{ + type_register_static(&allwinner_h3_dramc_info); +} + +type_init(allwinner_h3_dramc_register) 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 @@ allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_ad allwinner_cpucfg_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_cpucfg_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +# allwinner-h3-dramc.c +allwinner_h3_dramc_rowmirror_disable(void) "Disable row mirror" +allwinner_h3_dramc_rowmirror_enable(uint64_t addr) "Enable row mirror: addr 0x%" PRIx64 +allwinner_h3_dramcom_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramcom_write(uint64_t offset, uint64_t data, unsigned size) "Write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramctl_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramctl_write(uint64_t offset, uint64_t data, unsigned size) "Write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramphy_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramphy_write(uint64_t offset, uint64_t data, unsigned size) "write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # allwinner-sid.c allwinner_sid_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Allwinner System-on-Chips usually contain a Real Time Clock (RTC) for non-volatile system date and time keeping. This commit adds a generic Allwinner RTC device that supports the RTC devices found in Allwinner SoC family sun4i (A10), sun7i (A20) and sun6i and newer (A31, H2+, H3, etc). The following RTC functionality and features are implemented: * Year-Month-Day read/write * Hour-Minute-Second read/write * General Purpose storage The following boards are extended with the RTC device: * Cubieboard (hw/arm/cubieboard.c) * Orange Pi PC (hw/arm/orangepi.c) Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-13-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/rtc/Makefile.objs | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/rtc/allwinner-rtc.h | 134 +++++++++++ hw/arm/allwinner-a10.c | 8 + hw/arm/allwinner-h3.c | 9 +- hw/rtc/allwinner-rtc.c | 411 +++++++++++++++++++++++++++++++++ hw/rtc/trace-events | 4 + 8 files changed, 571 insertions(+), 1 deletion(-) create mode 100644 include/hw/rtc/allwinner-rtc.h create mode 100644 hw/rtc/allwinner-rtc.c diff --git a/hw/rtc/Makefile.objs b/hw/rtc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/Makefile.objs +++ b/hw/rtc/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_MC146818RTC) += mc146818rtc.o common-obj-$(CONFIG_SUN4V_RTC) += sun4v-rtc.o common-obj-$(CONFIG_ASPEED_SOC) += aspeed_rtc.o common-obj-$(CONFIG_GOLDFISH_RTC) += goldfish_rtc.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-rtc.o diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/ide/ahci.h" #include "hw/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" +#include "hw/rtc/allwinner-rtc.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ typedef struct AwA10State { AwEmacState emac; AllwinnerAHCIState sata; AwSdHostState mmc0; + AwRtcState rtc; MemoryRegion sram_a; EHCISysBusState ehci[AW_A10_NUM_USB]; OHCISysBusState ohci[AW_A10_NUM_USB]; diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-sid.h" #include "hw/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" +#include "hw/rtc/allwinner-rtc.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_CPU, AW_H3_GIC_HYP, AW_H3_GIC_VCPU, + AW_H3_RTC, AW_H3_CPUCFG, AW_H3_SDRAM }; @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwSidState sid; AwSdHostState mmc0; AwSun8iEmacState emac; + AwRtcState rtc; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/rtc/allwinner-rtc.h b/include/hw/rtc/allwinner-rtc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/rtc/allwinner-rtc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Real Time Clock emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_RTC_H +#define HW_MISC_ALLWINNER_RTC_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * Constants + * @{ + */ + +/** Highest register address used by RTC device */ +#define AW_RTC_REGS_MAXADDR (0x200) + +/** Total number of known registers */ +#define AW_RTC_REGS_NUM (AW_RTC_REGS_MAXADDR / sizeof(uint32_t)) + +/** @} */ + +/** + * Object model types + * @{ + */ + +/** Generic Allwinner RTC device (abstract) */ +#define TYPE_AW_RTC "allwinner-rtc" + +/** Allwinner RTC sun4i family (A10, A12) */ +#define TYPE_AW_RTC_SUN4I TYPE_AW_RTC "-sun4i" + +/** Allwinner RTC sun6i family and newer (A31, H2+, H3, etc) */ +#define TYPE_AW_RTC_SUN6I TYPE_AW_RTC "-sun6i" + +/** Allwinner RTC sun7i family (A20) */ +#define TYPE_AW_RTC_SUN7I TYPE_AW_RTC "-sun7i" + +/** @} */ + +/** + * Object model macros + * @{ + */ + +#define AW_RTC(obj) \ + OBJECT_CHECK(AwRtcState, (obj), TYPE_AW_RTC) +#define AW_RTC_CLASS(klass) \ + OBJECT_CLASS_CHECK(AwRtcClass, (klass), TYPE_AW_RTC) +#define AW_RTC_GET_CLASS(obj) \ + OBJECT_GET_CLASS(AwRtcClass, (obj), TYPE_AW_RTC) + +/** @} */ + +/** + * Allwinner RTC per-object instance state. + */ +typedef struct AwRtcState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** + * Actual year represented by the device when year counter is zero + * + * Can be overridden by the user using the corresponding 'base-year' + * property. The base year used by the target OS driver can vary, for + * example the Linux driver for sun6i uses 1970 while NetBSD uses 2000. + */ + int base_year; + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_RTC_REGS_NUM]; + +} AwRtcState; + +/** + * Allwinner RTC class-level struct. + * + * This struct is filled by each sunxi device specific code + * such that the generic code can use this struct to support + * all devices. + */ +typedef struct AwRtcClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ + + /** Defines device specific register map */ + const uint8_t *regmap; + + /** Size of the regmap in bytes */ + size_t regmap_size; + + /** + * Read device specific register + * + * @offset: register offset to read + * @return true if register read successful, false otherwise + */ + bool (*read)(AwRtcState *s, uint32_t offset); + + /** + * Write device specific register + * + * @offset: register offset to write + * @data: value to set in register + * @return true if register write successful, false otherwise + */ + bool (*write)(AwRtcState *s, uint32_t offset, uint32_t data); + +} AwRtcClass; + +#endif /* HW_MISC_ALLWINNER_RTC_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #define AW_A10_EHCI_BASE 0x01c14000 #define AW_A10_OHCI_BASE 0x01c14400 #define AW_A10_SATA_BASE 0x01c18000 +#define AW_A10_RTC_BASE 0x01c20d00 static void aw_a10_init(Object *obj) { @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), TYPE_AW_SDHOST_SUN4I); + + sysbus_init_child_obj(obj, "rtc", &s->rtc, sizeof(s->rtc), + TYPE_AW_RTC_SUN4I); } static void aw_a10_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc0), 0, qdev_get_gpio_in(dev, 32)); object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), "sd-bus", &error_abort); + + /* RTC */ + qdev_init_nofail(DEVICE(&s->rtc)); + sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->rtc), 0, AW_A10_RTC_BASE, 10); } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, [AW_H3_GIC_VCPU] = 0x01c86000, + [AW_H3_RTC] = 0x01f00000, [AW_H3_CPUCFG] = 0x01f01c00, [AW_H3_SDRAM] = 0x40000000 }; @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "csi", 0x01cb0000, 320 * KiB }, { "tve", 0x01e00000, 64 * KiB }, { "hdmi", 0x01ee0000, 128 * KiB }, - { "rtc", 0x01f00000, 1 * KiB }, { "r_timer", 0x01f00800, 1 * KiB }, { "r_intc", 0x01f00c00, 1 * KiB }, { "r_wdog", 0x01f01000, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "ram-addr", &error_abort); object_property_add_alias(obj, "ram-size", OBJECT(&s->dramc), "ram-size", &error_abort); + + sysbus_init_child_obj(obj, "rtc", &s->rtc, sizeof(s->rtc), + TYPE_AW_RTC_SUN6I); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 1, s->memmap[AW_H3_DRAMCTL]); sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 2, s->memmap[AW_H3_DRAMPHY]); + /* RTC */ + qdev_init_nofail(DEVICE(&s->rtc)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->rtc), 0, s->memmap[AW_H3_RTC]); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/rtc/allwinner-rtc.c b/hw/rtc/allwinner-rtc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/rtc/allwinner-rtc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Real Time Clock emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@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. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu-common.h" +#include "hw/qdev-properties.h" +#include "hw/rtc/allwinner-rtc.h" +#include "trace.h" + +/* RTC registers */ +enum { + REG_LOSC = 1, /* Low Oscillator Control */ + REG_YYMMDD, /* RTC Year-Month-Day */ + REG_HHMMSS, /* RTC Hour-Minute-Second */ + REG_ALARM1_WKHHMMSS, /* Alarm1 Week Hour-Minute-Second */ + REG_ALARM1_EN, /* Alarm1 Enable */ + REG_ALARM1_IRQ_EN, /* Alarm1 IRQ Enable */ + REG_ALARM1_IRQ_STA, /* Alarm1 IRQ Status */ + REG_GP0, /* General Purpose Register 0 */ + REG_GP1, /* General Purpose Register 1 */ + REG_GP2, /* General Purpose Register 2 */ + REG_GP3, /* General Purpose Register 3 */ + + /* sun4i registers */ + REG_ALARM1_DDHHMMSS, /* Alarm1 Day Hour-Minute-Second */ + REG_CPUCFG, /* CPU Configuration Register */ + + /* sun6i registers */ + REG_LOSC_AUTOSTA, /* LOSC Auto Switch Status */ + REG_INT_OSC_PRE, /* Internal OSC Clock Prescaler */ + REG_ALARM0_COUNTER, /* Alarm0 Counter */ + REG_ALARM0_CUR_VLU, /* Alarm0 Counter Current Value */ + REG_ALARM0_ENABLE, /* Alarm0 Enable */ + REG_ALARM0_IRQ_EN, /* Alarm0 IRQ Enable */ + REG_ALARM0_IRQ_STA, /* Alarm0 IRQ Status */ + REG_ALARM_CONFIG, /* Alarm Config */ + REG_LOSC_OUT_GATING, /* LOSC Output Gating Register */ + REG_GP4, /* General Purpose Register 4 */ + REG_GP5, /* General Purpose Register 5 */ + REG_GP6, /* General Purpose Register 6 */ + REG_GP7, /* General Purpose Register 7 */ + REG_RTC_DBG, /* RTC Debug Register */ + REG_GPL_HOLD_OUT, /* GPL Hold Output Register */ + REG_VDD_RTC, /* VDD RTC Regulate Register */ + REG_IC_CHARA, /* IC Characteristics Register */ +}; + +/* RTC register flags */ +enum { + REG_LOSC_YMD = (1 << 7), + REG_LOSC_HMS = (1 << 8), +}; + +/* RTC sun4i register map (offset to name) */ +const uint8_t allwinner_rtc_sun4i_regmap[] = { + [0x0000] = REG_LOSC, + [0x0004] = REG_YYMMDD, + [0x0008] = REG_HHMMSS, + [0x000C] = REG_ALARM1_DDHHMMSS, + [0x0010] = REG_ALARM1_WKHHMMSS, + [0x0014] = REG_ALARM1_EN, + [0x0018] = REG_ALARM1_IRQ_EN, + [0x001C] = REG_ALARM1_IRQ_STA, + [0x0020] = REG_GP0, + [0x0024] = REG_GP1, + [0x0028] = REG_GP2, + [0x002C] = REG_GP3, + [0x003C] = REG_CPUCFG, +}; + +/* RTC sun6i register map (offset to name) */ +const uint8_t allwinner_rtc_sun6i_regmap[] = { + [0x0000] = REG_LOSC, + [0x0004] = REG_LOSC_AUTOSTA, + [0x0008] = REG_INT_OSC_PRE, + [0x0010] = REG_YYMMDD, + [0x0014] = REG_HHMMSS, + [0x0020] = REG_ALARM0_COUNTER, + [0x0024] = REG_ALARM0_CUR_VLU, + [0x0028] = REG_ALARM0_ENABLE, + [0x002C] = REG_ALARM0_IRQ_EN, + [0x0030] = REG_ALARM0_IRQ_STA, + [0x0040] = REG_ALARM1_WKHHMMSS, + [0x0044] = REG_ALARM1_EN, + [0x0048] = REG_ALARM1_IRQ_EN, + [0x004C] = REG_ALARM1_IRQ_STA, + [0x0050] = REG_ALARM_CONFIG, + [0x0060] = REG_LOSC_OUT_GATING, + [0x0100] = REG_GP0, + [0x0104] = REG_GP1, + [0x0108] = REG_GP2, + [0x010C] = REG_GP3, + [0x0110] = REG_GP4, + [0x0114] = REG_GP5, + [0x0118] = REG_GP6, + [0x011C] = REG_GP7, + [0x0170] = REG_RTC_DBG, + [0x0180] = REG_GPL_HOLD_OUT, + [0x0190] = REG_VDD_RTC, + [0x01F0] = REG_IC_CHARA, +}; + +static bool allwinner_rtc_sun4i_read(AwRtcState *s, uint32_t offset) +{ + /* no sun4i specific registers currently implemented */ + return false; +} + +static bool allwinner_rtc_sun4i_write(AwRtcState *s, uint32_t offset, + uint32_t data) +{ + /* no sun4i specific registers currently implemented */ + return false; +} + +static bool allwinner_rtc_sun6i_read(AwRtcState *s, uint32_t offset) +{ + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + + switch (c->regmap[offset]) { + case REG_GP4: /* General Purpose Register 4 */ + case REG_GP5: /* General Purpose Register 5 */ + case REG_GP6: /* General Purpose Register 6 */ + case REG_GP7: /* General Purpose Register 7 */ + return true; + default: + break; + } + return false; +} + +static bool allwinner_rtc_sun6i_write(AwRtcState *s, uint32_t offset, + uint32_t data) +{ + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + + switch (c->regmap[offset]) { + case REG_GP4: /* General Purpose Register 4 */ + case REG_GP5: /* General Purpose Register 5 */ + case REG_GP6: /* General Purpose Register 6 */ + case REG_GP7: /* General Purpose Register 7 */ + return true; + default: + break; + } + return false; +} + +static uint64_t allwinner_rtc_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwRtcState *s = AW_RTC(opaque); + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + uint64_t val = 0; + + if (offset >= c->regmap_size) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + if (!c->regmap[offset]) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid register 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + switch (c->regmap[offset]) { + case REG_LOSC: /* Low Oscillator Control */ + val = s->regs[REG_LOSC]; + s->regs[REG_LOSC] &= ~(REG_LOSC_YMD | REG_LOSC_HMS); + break; + case REG_YYMMDD: /* RTC Year-Month-Day */ + case REG_HHMMSS: /* RTC Hour-Minute-Second */ + case REG_GP0: /* General Purpose Register 0 */ + case REG_GP1: /* General Purpose Register 1 */ + case REG_GP2: /* General Purpose Register 2 */ + case REG_GP3: /* General Purpose Register 3 */ + val = s->regs[c->regmap[offset]]; + break; + default: + if (!c->read(s, offset)) { + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register 0x%04x\n", + __func__, (uint32_t)offset); + } + val = s->regs[c->regmap[offset]]; + break; + } + + trace_allwinner_rtc_read(offset, val); + return val; +} + +static void allwinner_rtc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwRtcState *s = AW_RTC(opaque); + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + + if (offset >= c->regmap_size) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + if (!c->regmap[offset]) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid register 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + trace_allwinner_rtc_write(offset, val); + + switch (c->regmap[offset]) { + case REG_YYMMDD: /* RTC Year-Month-Day */ + s->regs[REG_YYMMDD] = val; + s->regs[REG_LOSC] |= REG_LOSC_YMD; + break; + case REG_HHMMSS: /* RTC Hour-Minute-Second */ + s->regs[REG_HHMMSS] = val; + s->regs[REG_LOSC] |= REG_LOSC_HMS; + break; + case REG_GP0: /* General Purpose Register 0 */ + case REG_GP1: /* General Purpose Register 1 */ + case REG_GP2: /* General Purpose Register 2 */ + case REG_GP3: /* General Purpose Register 3 */ + s->regs[c->regmap[offset]] = val; + break; + default: + if (!c->write(s, offset, val)) { + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register 0x%04x\n", + __func__, (uint32_t)offset); + } + break; + } +} + +static const MemoryRegionOps allwinner_rtc_ops = { + .read = allwinner_rtc_read, + .write = allwinner_rtc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_rtc_reset(DeviceState *dev) +{ + AwRtcState *s = AW_RTC(dev); + struct tm now; + + /* Clear registers */ + memset(s->regs, 0, sizeof(s->regs)); + + /* Get current datetime */ + qemu_get_timedate(&now, 0); + + /* Set RTC with current datetime */ + if (s->base_year > 1900) { + s->regs[REG_YYMMDD] = ((now.tm_year + 1900 - s->base_year) << 16) | + ((now.tm_mon + 1) << 8) | + now.tm_mday; + s->regs[REG_HHMMSS] = (((now.tm_wday + 6) % 7) << 29) | + (now.tm_hour << 16) | + (now.tm_min << 8) | + now.tm_sec; + } +} + +static void allwinner_rtc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwRtcState *s = AW_RTC(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_rtc_ops, s, + TYPE_AW_RTC, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_rtc_vmstate = { + .name = "allwinner-rtc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwRtcState, AW_RTC_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static Property allwinner_rtc_properties[] = { + DEFINE_PROP_INT32("base-year", AwRtcState, base_year, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void allwinner_rtc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_rtc_reset; + dc->vmsd = &allwinner_rtc_vmstate; + device_class_set_props(dc, allwinner_rtc_properties); +} + +static void allwinner_rtc_sun4i_init(Object *obj) +{ + AwRtcState *s = AW_RTC(obj); + s->base_year = 2010; +} + +static void allwinner_rtc_sun4i_class_init(ObjectClass *klass, void *data) +{ + AwRtcClass *arc = AW_RTC_CLASS(klass); + + arc->regmap = allwinner_rtc_sun4i_regmap; + arc->regmap_size = sizeof(allwinner_rtc_sun4i_regmap); + arc->read = allwinner_rtc_sun4i_read; + arc->write = allwinner_rtc_sun4i_write; +} + +static void allwinner_rtc_sun6i_init(Object *obj) +{ + AwRtcState *s = AW_RTC(obj); + s->base_year = 1970; +} + +static void allwinner_rtc_sun6i_class_init(ObjectClass *klass, void *data) +{ + AwRtcClass *arc = AW_RTC_CLASS(klass); + + arc->regmap = allwinner_rtc_sun6i_regmap; + arc->regmap_size = sizeof(allwinner_rtc_sun6i_regmap); + arc->read = allwinner_rtc_sun6i_read; + arc->write = allwinner_rtc_sun6i_write; +} + +static void allwinner_rtc_sun7i_init(Object *obj) +{ + AwRtcState *s = AW_RTC(obj); + s->base_year = 1970; +} + +static void allwinner_rtc_sun7i_class_init(ObjectClass *klass, void *data) +{ + AwRtcClass *arc = AW_RTC_CLASS(klass); + allwinner_rtc_sun4i_class_init(klass, arc); +} + +static const TypeInfo allwinner_rtc_info = { + .name = TYPE_AW_RTC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_rtc_init, + .instance_size = sizeof(AwRtcState), + .class_init = allwinner_rtc_class_init, + .class_size = sizeof(AwRtcClass), + .abstract = true, +}; + +static const TypeInfo allwinner_rtc_sun4i_info = { + .name = TYPE_AW_RTC_SUN4I, + .parent = TYPE_AW_RTC, + .class_init = allwinner_rtc_sun4i_class_init, + .instance_init = allwinner_rtc_sun4i_init, +}; + +static const TypeInfo allwinner_rtc_sun6i_info = { + .name = TYPE_AW_RTC_SUN6I, + .parent = TYPE_AW_RTC, + .class_init = allwinner_rtc_sun6i_class_init, + .instance_init = allwinner_rtc_sun6i_init, +}; + +static const TypeInfo allwinner_rtc_sun7i_info = { + .name = TYPE_AW_RTC_SUN7I, + .parent = TYPE_AW_RTC, + .class_init = allwinner_rtc_sun7i_class_init, + .instance_init = allwinner_rtc_sun7i_init, +}; + +static void allwinner_rtc_register(void) +{ + type_register_static(&allwinner_rtc_info); + type_register_static(&allwinner_rtc_sun4i_info); + type_register_static(&allwinner_rtc_sun6i_info); + type_register_static(&allwinner_rtc_sun7i_info); +} + +type_init(allwinner_rtc_register) diff --git a/hw/rtc/trace-events b/hw/rtc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/trace-events +++ b/hw/rtc/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-rtc.c +allwinner_rtc_read(uint64_t addr, uint64_t value) "addr 0x%" PRIx64 " value 0x%" PRIx64 +allwinner_rtc_write(uint64_t addr, uint64_t value) "addr 0x%" PRIx64 " value 0x%" PRIx64 + # sun4v-rtc.c sun4v_rtc_read(uint64_t addr, uint64_t value) "read: addr 0x%" PRIx64 " value 0x%" PRIx64 sun4v_rtc_write(uint64_t addr, uint64_t value) "write: addr 0x%" PRIx64 " value 0x%" PRIx64 -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots a Linux kernel on a OrangePi PC board and verify the serial output is working. The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ If ARM is a target being built, "make check-acceptance" will automatically include this test by the use of the "arch:arm" tags. Alternatively, this test can be run using: $ make check-venv $ ./tests/venv/bin/avocado --show=console,app run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py JOB ID : 2e4d15eceb13c33672af406f08171e6e9de1414a JOB LOG : ~/job-results/job-2019-12-17T05.46-2e4d15e/job.log (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_orangepi: console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d console: CPU: div instructions available: patching division code console: CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: OF: fdt: Machine model: Xunlong Orange Pi PC console: Memory policy: Data cache writealloc console: OF: reserved mem: failed to allocate memory for node 'cma@4a000000' console: cma: Failed to reserve 128 MiB console: psci: probing for conduit method from DT. console: psci: PSCIv0.2 detected in firmware. console: psci: Using standard PSCI v0.2 function IDs console: psci: Trusted OS migration not required console: random: get_random_bytes called from start_kernel+0x8d/0x3c2 with crng_init=0 console: percpu: Embedded 18 pages/cpu @(ptrval) s41228 r8192 d24308 u73728 console: Built 1 zonelists, mobility grouping on. Total pages: 32480 console: Kernel command line: printk.time=0 console=ttyS0,115200 PASS (8.59 s) JOB TIME : 8.81 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-14-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 25 +++++++++++++++++++++++++ 1 file changed, 25 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(Test): exec_command_and_wait_for_pattern(self, 'reboot', 'reboot: Restarting system') + def test_arm_orangepi(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') + deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-4.20.7-sunxi') + dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + dtb_path = self.extract_from_deb(deb_path, dtb_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200n8 ' + 'earlycon=uart,mmio32,0x1c28000') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-append', kernel_command_line) + self.vm.launch() + console_pattern = 'Kernel command line: %s' % kernel_command_line + self.wait_for_console_pattern(console_pattern) + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots a Linux kernel on a OrangePi PC board and verify the serial output is working. The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ The cpio image used comes from the linux-build-test project: https://github.com/groeck/linux-build-test If ARM is a target being built, "make check-acceptance" will automatically include this test by the use of the "arch:arm" tags. Alternatively, this test can be run using: $ avocado --show=console run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d console: CPU: div instructions available: patching division code console: CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: OF: fdt: Machine model: Xunlong Orange Pi PC [...] console: Trying to unpack rootfs image as initramfs... console: Freeing initrd memory: 3256K console: Freeing unused kernel memory: 1024K console: Run /init as init process console: mount: mounting devtmpfs on /dev failed: Device or resource busy console: Starting logging: OK console: Initializing random number generator... random: dd: uninitialized urandom read (512 bytes read) console: done. console: Starting network: OK console: Found console ttyS0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: Boot successful. console: cat /proc/cpuinfo console: / # cat /proc/cpuinfo console: processor : 0 console: model name : ARMv7 Processor rev 5 (v7l) console: BogoMIPS : 125.00 console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm console: CPU implementer : 0x41 console: CPU architecture: 7 console: CPU variant : 0x0 console: CPU part : 0xc07 console: CPU revision : 5 [...] console: processor : 3 console: model name : ARMv7 Processor rev 5 (v7l) console: BogoMIPS : 125.00 console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm console: CPU implementer : 0x41 console: CPU architecture: 7 console: CPU variant : 0x0 console: CPU part : 0xc07 console: CPU revision : 5 console: Hardware : Allwinner sun8i Family console: Revision : 0000 console: Serial : 0000000000000000 console: cat /proc/iomem console: / # cat /proc/iomem console: 01000000-010fffff : clock@1000000 console: 01c00000-01c00fff : system-control@1c00000 console: 01c02000-01c02fff : dma-controller@1c02000 [...] console: reboot console: / # reboot console: / # Found console ttyS0 console: Stopping network: OK console: hrtimer: interrupt took 21852064 ns console: Saving random seed... random: dd: uninitialized urandom read (512 bytes read) console: done. console: Stopping logging: OK console: umount: devtmpfs busy - remounted read-only console: umount: can't unmount /: Invalid argument console: The system is going down NOW! console: Sent SIGTERM to all processes console: Sent SIGKILL to all processes console: Requesting system reboot console: reboot: Restarting system PASS (48.32 s) JOB TIME : 49.16 s Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-15-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 40 ++++++++++++++++++++++++++ 1 file changed, 40 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(Test): console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) + def test_arm_orangepi_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') + deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-4.20.7-sunxi') + dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + dtb_path = self.extract_from_deb(deb_path, dtb_path) + initrd_url = ('https://github.com/groeck/linux-build-test/raw/' + '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' + 'arm/rootfs-armv7a.cpio.gz') + initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c' + initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + initrd_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.gzip_uncompress(initrd_path_gz, initrd_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'panic=-1 noreboot') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-initrd', initrd_path, + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + self.wait_for_console_pattern('Boot successful.') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', + 'system-control@1c00000') + exec_command_and_wait_for_pattern(self, 'reboot', + 'reboot: Restarting system') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ The SD image is from the kernelci.org project: https://kernelci.org/faq/#the-code If ARM is a target being built, "make check-acceptance" will automatically include this test by the use of the "arch:arm" tags. Alternatively, this test can be run using: $ avocado --show=console run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d [...] console: sunxi-wdt 1c20ca0.watchdog: Watchdog enabled (timeout=16 sec, nowayout=0) console: sunxi-mmc 1c0f000.mmc: Linked as a consumer to regulator.2 console: sunxi-mmc 1c0f000.mmc: Got CD GPIO console: ledtrig-cpu: registered to indicate activity on CPUs console: hidraw: raw HID events driver (C) Jiri Kosina console: usbcore: registered new interface driver usbhid console: usbhid: USB HID core driver console: Initializing XFRM netlink socket console: sunxi-mmc 1c0f000.mmc: initialized, max. request size: 16384 KB console: NET: Registered protocol family 10 console: mmc0: host does not support reading read-only switch, assuming write-enable console: mmc0: Problem switching card into high-speed mode! console: mmc0: new SD card at address 4567 console: mmcblk0: mmc0:4567 QEMU! 60.0 MiB [...] console: EXT4-fs (mmcblk0): mounting ext2 file system using the ext4 subsystem console: EXT4-fs (mmcblk0): mounted filesystem without journal. Opts: (null) console: VFS: Mounted root (ext2 filesystem) on device 179:0. console: Run /sbin/init as init process console: EXT4-fs (mmcblk0): re-mounted. Opts: block_validity,barrier,user_xattr,acl console: Starting syslogd: OK console: Starting klogd: OK console: Populating /dev using udev: udevd[203]: starting version 3.2.7 console: /bin/sh: can't access tty; job control turned off console: cat /proc/partitions console: / # cat /proc/partitions console: major minor #blocks name console: 1 0 4096 ram0 console: 1 1 4096 ram1 console: 1 2 4096 ram2 console: 1 3 4096 ram3 console: 179 0 61440 mmcblk0 console: reboot console: / # reboot console: umount: devtmpfs busy - remounted read-only console: EXT4-fs (mmcblk0): re-mounted. Opts: (null) console: The system is going down NOW! console: Sent SIGTERM to all processes console: Sent SIGKILL to all processes console: Requesting system reboot console: reboot: Restarting system JOB TIME : 68.64 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-16-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] [NL: extend test with ethernet device checks] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 47 ++++++++++++++++++++++++++ 1 file changed, 47 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(Test): exec_command_and_wait_for_pattern(self, 'reboot', 'reboot: Restarting system') + def test_arm_orangepi_sd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') + deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-4.20.7-sunxi') + dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + dtb_path = self.extract_from_deb(deb_path, dtb_path) + rootfs_url = ('http://storage.kernelci.org/images/rootfs/buildroot/' + 'kci-2019.02/armel/base/rootfs.ext2.xz') + rootfs_hash = '692510cb625efda31640d1de0a8d60e26040f061' + rootfs_path_xz = self.fetch_asset(rootfs_url, asset_hash=rootfs_hash) + rootfs_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.lzma_uncompress(rootfs_path_xz, rootfs_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'root=/dev/mmcblk0 rootwait rw ' + 'panic=-1 noreboot') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-drive', 'file=' + rootfs_path + ',if=sd,format=raw', + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + shell_ready = "/bin/sh: can't access tty; job control turned off" + self.wait_for_console_pattern(shell_ready) + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/partitions', + 'mmcblk0') + exec_command_and_wait_for_pattern(self, 'ifconfig eth0 up', + 'eth0: Link is Up') + exec_command_and_wait_for_pattern(self, 'udhcpc eth0', + 'udhcpc: lease of 10.0.2.15 obtained') + exec_command_and_wait_for_pattern(self, 'ping -c 3 10.0.2.2', + '3 packets transmitted, 3 packets received, 0% packet loss') + exec_command_and_wait_for_pattern(self, 'reboot', + 'reboot: Restarting system') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots Ubuntu Bionic on a OrangePi PC board. As it requires 1GB of storage, and is slow, this test is disabled on automatic CI testing. It is useful for workstation testing. Currently Avocado timeouts too quickly, so we can't run userland commands. The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ The Ubuntu image is downloaded from: https://dl.armbian.com/orangepipc/Bionic_current This test can be run using: $ AVOCADO_ALLOW_LARGE_STORAGE=yes \ avocado --show=app,console run -t machine:orangepi-pc \ tests/acceptance/boot_linux_console.py console: U-Boot SPL 2019.04-armbian (Nov 18 2019 - 23:08:35 +0100) console: DRAM: 1024 MiB console: Failed to set core voltage! Can't set CPU frequency console: Trying to boot from MMC1 console: U-Boot 2019.04-armbian (Nov 18 2019 - 23:08:35 +0100) Allwinner Technology console: CPU: Allwinner H3 (SUN8I 0000) console: Model: Xunlong Orange Pi PC console: DRAM: 1 GiB console: MMC: mmc@1c0f000: 0 [...] console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 5.3.9-sunxi (root@builder) (gcc version 8.3.0 (GNU Toolchain for the A-profile Architecture 8.3-2019.03 (arm-rel-8.36))) #19.11.3 SMP Mon Nov 18 18:49:43 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d console: CPU: div instructions available: patching division code console: CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: OF: fdt: Machine model: Xunlong Orange Pi PC [...] console: EXT4-fs (mmcblk0p1): mounted filesystem with writeback data mode. Opts: (null) console: done. console: Begin: Running /scripts/local-bottom ... done. console: Begin: Running /scripts/init-bottom ... done. console: systemd[1]: systemd 237 running in system mode. (...) console: systemd[1]: Detected architecture arm. console: Welcome to Ubuntu 18.04.3 LTS! console: systemd[1]: Set hostname to <orangepipc>. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-17-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] [NL: changed test to boot from SD card via BootROM, added check for 7z] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 48 ++++++++++++++++++++++++++ 1 file changed, 48 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 @@ from avocado_qemu import exec_command_and_wait_for_pattern from avocado_qemu import wait_for_console_pattern from avocado.utils import process from avocado.utils import archive +from avocado.utils.path import find_command, CmdNotFoundError +P7ZIP_AVAILABLE = True +try: + find_command('7z') +except CmdNotFoundError: + P7ZIP_AVAILABLE = False class BootLinuxConsole(Test): """ @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): exec_command_and_wait_for_pattern(self, 'reboot', 'reboot: Restarting system') + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + @skipUnless(P7ZIP_AVAILABLE, '7z not installed') + def test_arm_orangepi_bionic(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + + # This test download a 196MB compressed image and expand it to 932MB... + image_url = ('https://dl.armbian.com/orangepipc/archive/' + 'Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.7z') + image_hash = '196a8ffb72b0123d92cea4a070894813d305c71e' + image_path_7z = self.fetch_asset(image_url, asset_hash=image_hash) + image_name = 'Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.img' + image_path = os.path.join(self.workdir, image_name) + process.run("7z e -o%s %s" % (self.workdir, image_path_7z)) + + self.vm.set_console() + self.vm.add_args('-drive', 'file=' + image_path + ',if=sd,format=raw', + '-nic', 'user', + '-no-reboot') + self.vm.launch() + + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'loglevel=7 ' + 'nosmp ' + 'systemd.default_timeout_start_sec=9000 ' + 'systemd.mask=armbian-zram-config.service ' + 'systemd.mask=armbian-ramlog.service') + + self.wait_for_console_pattern('U-Boot SPL') + self.wait_for_console_pattern('Autoboot in ') + exec_command_and_wait_for_pattern(self, ' ', '=>') + exec_command_and_wait_for_pattern(self, "setenv extraargs '" + + kernel_command_line + "'", '=>') + exec_command_and_wait_for_pattern(self, 'boot', 'Starting kernel ...'); + + self.wait_for_console_pattern('systemd[1]: Set hostname ' + + 'to <orangepipc>') + self.wait_for_console_pattern('Starting Load Kernel Modules...') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots U-Boot then NetBSD (stored on a SD card) on a OrangePi PC board. As it requires ~1.3GB of storage, it is disabled by default. U-Boot is built by the Debian project [1], and the SD card image is provided by the NetBSD organization [2]. Once the compressed SD card image is downloaded (304MB) and extracted, this test is fast: $ AVOCADO_ALLOW_LARGE_STORAGE=yes \ avocado --show=app,console run -t machine:orangepi-pc \ tests/acceptance/boot_linux_console.py console: U-Boot SPL 2020.01+dfsg-1 (Jan 08 2020 - 08:19:44 +0000) console: DRAM: 1024 MiB console: U-Boot 2020.01+dfsg-1 (Jan 08 2020 - 08:19:44 +0000) Allwinner Technology console: CPU: Allwinner H3 (SUN8I 0000) console: scanning bus usb@1c1b000 for devices... 1 USB Device(s) found console: scanning bus usb@1c1d000 for devices... 1 USB Device(s) found console: scanning usb for storage devices... 0 Storage Device(s) found console: Hit any key to stop autoboot: 0 console: => setenv bootargs root=ld0a console: => setenv kernel netbsd-GENERIC.ub console: => setenv fdtfile dtb/sun8i-h3-orangepi-pc.dtb console: => boot console: ## Booting kernel from Legacy Image at 42000000 ... console: Image Name: NetBSD/earmv7hf 9.0_RC1 console: Image Type: ARM Linux Kernel Image (no loading done) (uncompressed) console: XIP Kernel Image (no loading done) console: Loading Device Tree to 49ff6000, end 49fffe01 ... OK console: Starting kernel ... console: [ 1.0000000] NetBSD/evbarm (fdt) booting ... console: [ 1.0000000] NetBSD 9.0 (GENERIC) #0: Fri Feb 14 00:06:28 UTC 2020 console: [ 1.0000000] mkrepro@mkrepro.NetBSD.org:/usr/src/sys/arch/evbarm/compile/GENERIC console: [ 1.0000000] total memory = 1024 MB console: [ 1.0000000] avail memory = 1003 MB console: [ 1.0000000] armfdt0 (root) console: [ 1.0000000] simplebus0 at armfdt0: Xunlong Orange Pi PC console: [ 1.0000000] cpu0 at cpus0: Cortex-A7 r0p5 (Cortex V7A core) console: [ 1.0000000] cpu0: DC enabled IC enabled WB enabled LABT branch prediction enabled console: [ 1.0000000] cpu0: 32KB/64B 2-way L1 VIPT Instruction cache console: [ 1.0000000] cpu0: 32KB/64B 2-way write-back-locking-C L1 PIPT Data cache console: [ 1.0000000] cpu0: 2304KB/64B 16-way write-through L2 PIPT Unified cache console: [ 1.0000000] vfp0 at cpu0: NEON MPE (VFP 3.0+), rounding, NaN propagation, denormals ... console: [ 2.3812082] sdmmc0: SD card status: 4-bit, C0 console: [ 2.3812082] ld0 at sdmmc0: <0xaa:0x5859:QEMU!:0x01:0xdeadbeef:0x062> console: [ 2.4012856] ld0: 1226 MB, 622 cyl, 64 head, 63 sec, 512 bytes/sect x 2511872 sectors console: [ 2.5321222] ld0: 4-bit width, High-Speed/SDR25, 50.000 MHz console: [ 3.1068718] WARNING: 4 errors while detecting hardware; check system log. console: [ 3.1179868] boot device: ld0 console: [ 3.1470623] root on ld0a dumps on ld0b console: [ 3.2464436] root file system type: ffs console: [ 3.2897123] kern.module.path=/stand/evbarm/9.0/modules console: Mon Feb 17 20:33:35 UTC 2020 console: Starting root file system check: PASS (35.96 s) RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 JOB TIME : 36.09 s Note, this test only took ~65 seconds to run on Travis-CI, see: [3]. This test is based on a description from Niek Linnenbank from [4]. [1] https://wiki.debian.org/InstallingDebianOn/Allwinner#Creating_a_bootable_SD_Card_with_u-boot [2] https://wiki.netbsd.org/ports/evbarm/allwinner/ [3] https://travis-ci.org/philmd/qemu/jobs/638823612#L3778 [4] https://www.mail-archive.com/qemu-devel@nongnu.org/msg669347.html Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-18-nieklinnenbank@gmail.com [NL: changed test to use NetBSD 9.0 final release and -global allwinner-rtc.base-year] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 70 ++++++++++++++++++++++++++ 1 file changed, 70 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 @@ import shutil from avocado import skipUnless from avocado_qemu import Test from avocado_qemu import exec_command_and_wait_for_pattern +from avocado_qemu import interrupt_interactive_console_until_pattern from avocado_qemu import wait_for_console_pattern from avocado.utils import process from avocado.utils import archive @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): 'to <orangepipc>') self.wait_for_console_pattern('Starting Load Kernel Modules...') + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_orangepi_uboot_netbsd9(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + # This test download a 304MB compressed image and expand it to 1.3GB... + deb_url = ('http://snapshot.debian.org/archive/debian/' + '20200108T145233Z/pool/main/u/u-boot/' + 'u-boot-sunxi_2020.01%2Bdfsg-1_armhf.deb') + deb_hash = 'f67f404a80753ca3d1258f13e38f2b060e13db99' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + # We use the common OrangePi PC 'plus' build of U-Boot for our secondary + # program loader (SPL). We will then set the path to the more specific + # OrangePi "PC" device tree blob with 'setenv fdtfile' in U-Boot prompt, + # before to boot NetBSD. + uboot_path = '/usr/lib/u-boot/orangepi_plus/u-boot-sunxi-with-spl.bin' + uboot_path = self.extract_from_deb(deb_path, uboot_path) + image_url = ('https://cdn.netbsd.org/pub/NetBSD/NetBSD-9.0/' + 'evbarm-earmv7hf/binary/gzimg/armv7.img.gz') + image_hash = '2babb29d36d8360adcb39c09e31060945259917a' + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash) + image_path = os.path.join(self.workdir, 'armv7.img') + image_drive_args = 'if=sd,format=raw,snapshot=on,file=' + image_path + archive.gzip_uncompress(image_path_gz, image_path) + + # dd if=u-boot-sunxi-with-spl.bin of=armv7.img bs=1K seek=8 conv=notrunc + with open(uboot_path, 'rb') as f_in: + with open(image_path, 'r+b') as f_out: + f_out.seek(8 * 1024) + shutil.copyfileobj(f_in, f_out) + + # Extend image, to avoid that NetBSD thinks the partition + # inside the image is larger than device size itself + f_out.seek(0, 2) + f_out.seek(64 * 1024 * 1024, 1) + f_out.write(bytearray([0x00])) + + self.vm.set_console() + self.vm.add_args('-nic', 'user', + '-drive', image_drive_args, + '-global', 'allwinner-rtc.base-year=2000', + '-no-reboot') + self.vm.launch() + wait_for_console_pattern(self, 'U-Boot 2020.01+dfsg-1') + interrupt_interactive_console_until_pattern(self, + 'Hit any key to stop autoboot:', + 'switch to partitions #0, OK') + + exec_command_and_wait_for_pattern(self, '', '=>') + cmd = 'setenv bootargs root=ld0a' + exec_command_and_wait_for_pattern(self, cmd, '=>') + cmd = 'setenv kernel netbsd-GENERIC.ub' + exec_command_and_wait_for_pattern(self, cmd, '=>') + cmd = 'setenv fdtfile dtb/sun8i-h3-orangepi-pc.dtb' + exec_command_and_wait_for_pattern(self, cmd, '=>') + cmd = ("setenv bootcmd 'fatload mmc 0:1 ${kernel_addr_r} ${kernel}; " + "fatload mmc 0:1 ${fdt_addr_r} ${fdtfile}; " + "fdt addr ${fdt_addr_r}; " + "bootm ${kernel_addr_r} - ${fdt_addr_r}'") + exec_command_and_wait_for_pattern(self, cmd, '=>') + + exec_command_and_wait_for_pattern(self, 'boot', + 'Booting kernel from Legacy Image') + wait_for_console_pattern(self, 'Starting kernel ...') + wait_for_console_pattern(self, 'NetBSD 9.0 (GENERIC)') + # Wait for user-space + wait_for_console_pattern(self, 'Starting root file system check') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Xunlong Orange Pi PC machine is a functional ARM machine based on the Allwinner H3 System-on-Chip. It supports mainline Linux, U-Boot, NetBSD and is covered by acceptance tests. This commit adds a documentation text file with a description of the machine and instructions for the user. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-19-nieklinnenbank@gmail.com [PMM: moved file into docs/system/arm to match the reorg of the arm target part of the docs; tweaked heading to match other boards] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + docs/system/arm/orangepi.rst | 253 +++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 2 + 3 files changed, 256 insertions(+) create mode 100644 docs/system/arm/orangepi.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Maintained F: hw/*/allwinner-h3* F: include/hw/*/allwinner-h3* F: hw/arm/orangepi.c +F: docs/system/orangepi.rst ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> diff --git a/docs/system/arm/orangepi.rst b/docs/system/arm/orangepi.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/orangepi.rst @@ -XXX,XX +XXX,XX @@ +Orange Pi PC (``orangepi-pc``) +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The Xunlong Orange Pi PC is an Allwinner H3 System on Chip +based embedded computer with mainline support in both U-Boot +and Linux. The board comes with a Quad Core Cortex-A7 @ 1.3GHz, +1GiB RAM, 100Mbit ethernet, USB, SD/MMC, USB, HDMI and +various other I/O. + +Supported devices +""""""""""""""""" + +The Orange Pi PC machine supports the following devices: + + * SMP (Quad Core Cortex-A7) + * Generic Interrupt Controller configuration + * SRAM mappings + * SDRAM controller + * Real Time Clock + * Timer device (re-used from Allwinner A10) + * UART + * SD/MMC storage controller + * EMAC ethernet + * USB 2.0 interfaces + * Clock Control Unit + * System Control module + * Security Identifier device + +Limitations +""""""""""" + +Currently, Orange Pi PC does *not* support the following features: + +- Graphical output via HDMI, GPU and/or the Display Engine +- Audio output +- Hardware Watchdog + +Also see the 'unimplemented' array in the Allwinner H3 SoC module +for a complete list of unimplemented I/O devices: ``./hw/arm/allwinner-h3.c`` + +Boot options +"""""""""""" + +The Orange Pi PC machine can start using the standard -kernel functionality +for loading a Linux kernel or ELF executable. Additionally, the Orange Pi PC +machine can also emulate the BootROM which is present on an actual Allwinner H3 +based SoC, which loads the bootloader from a SD card, specified via the -sd argument +to qemu-system-arm. + +Machine-specific options +"""""""""""""""""""""""" + +The following machine-specific options are supported: + +- allwinner-rtc.base-year=YYYY + + The Allwinner RTC device is automatically created by the Orange Pi PC machine + and uses a default base year value which can be overridden using the 'base-year' property. + The base year is the actual represented year when the RTC year value is zero. + This option can be used in case the target operating system driver uses a different + base year value. The minimum value for the base year is 1900. + +- allwinner-sid.identifier=abcd1122-a000-b000-c000-12345678ffff + + The Security Identifier value can be read by the guest. + For example, U-Boot uses it to determine a unique MAC address. + +The above machine-specific options can be specified in qemu-system-arm +via the '-global' argument, for example: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -sd mycard.img \ + -global allwinner-rtc.base-year=2000 + +Running mainline Linux +"""""""""""""""""""""" + +Mainline Linux kernels from 4.19 up to latest master are known to work. +To build a Linux mainline kernel that can be booted by the Orange Pi PC machine, +simply configure the kernel using the sunxi_defconfig configuration: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make mrproper + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make sunxi_defconfig + +To be able to use USB storage, you need to manually enable the corresponding +configuration item. Start the kconfig configuration tool: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make menuconfig + +Navigate to the following item, enable it and save your configuration: + + Device Drivers > USB support > USB Mass Storage support + +Build the Linux kernel with: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make + +To boot the newly build linux kernel in QEMU with the Orange Pi PC machine, use: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -kernel /path/to/linux/arch/arm/boot/zImage \ + -append 'console=ttyS0,115200' \ + -dtb /path/to/linux/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dtb + +Orange Pi PC images +""""""""""""""""""" + +Note that the mainline kernel does not have a root filesystem. You may provide it +with an official Orange Pi PC image from the official website: + + http://www.orangepi.org/downloadresources/ + +Another possibility is to run an Armbian image for Orange Pi PC which +can be downloaded from: + + https://www.armbian.com/orange-pi-pc/ + +Alternatively, you can also choose to build you own image with buildroot +using the orangepi_pc_defconfig. Also see https://buildroot.org for more information. + +You can choose to attach the selected image either as an SD card or as USB mass storage. +For example, to boot using the Orange Pi PC Debian image on SD card, simply add the -sd +argument and provide the proper root= kernel parameter: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -kernel /path/to/linux/arch/arm/boot/zImage \ + -append 'console=ttyS0,115200 root=/dev/mmcblk0p2' \ + -dtb /path/to/linux/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dtb \ + -sd OrangePi_pc_debian_stretch_server_linux5.3.5_v1.0.img + +To attach the image as an USB mass storage device to the machine, +simply append to the command: + +.. code-block:: bash + + -drive if=none,id=stick,file=myimage.img \ + -device usb-storage,bus=usb-bus.0,drive=stick + +Instead of providing a custom Linux kernel via the -kernel command you may also +choose to let the Orange Pi PC machine load the bootloader from SD card, just like +a real board would do using the BootROM. Simply pass the selected image via the -sd +argument and remove the -kernel, -append, -dbt and -initrd arguments: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -sd Armbian_19.11.3_Orangepipc_buster_current_5.3.9.img + +Note that both the official Orange Pi PC images and Armbian images start +a lot of userland programs via systemd. Depending on the host hardware and OS, +they may be slow to emulate, especially due to emulating the 4 cores. +To help reduce the performance slow down due to emulating the 4 cores, you can +give the following kernel parameters via U-Boot (or via -append): + +.. code-block:: bash + + => setenv extraargs 'systemd.default_timeout_start_sec=9000 loglevel=7 nosmp console=ttyS0,115200' + +Running U-Boot +"""""""""""""" + +U-Boot mainline can be build and configured using the orangepi_pc_defconfig +using similar commands as describe above for Linux. Note that it is recommended +for development/testing to select the following configuration setting in U-Boot: + + Device Tree Control > Provider for DTB for DT Control > Embedded DTB + +To start U-Boot using the Orange Pi PC machine, provide the +u-boot binary to the -kernel argument: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -kernel /path/to/uboot/u-boot -sd disk.img + +Use the following U-boot commands to load and boot a Linux kernel from SD card: + +.. code-block:: bash + + => setenv bootargs console=ttyS0,115200 + => ext2load mmc 0 0x42000000 zImage + => ext2load mmc 0 0x43000000 sun8i-h3-orangepi-pc.dtb + => bootz 0x42000000 - 0x43000000 + +Running NetBSD +"""""""""""""" + +The NetBSD operating system also includes support for Allwinner H3 based boards, +including the Orange Pi PC. NetBSD 9.0 is known to work best for the Orange Pi PC +board and provides a fully working system with serial console, networking and storage. +For the Orange Pi PC machine, get the 'evbarm-earmv7hf' based image from: + + https://cdn.netbsd.org/pub/NetBSD/NetBSD-9.0/evbarm-earmv7hf/binary/gzimg/armv7.img.gz + +The image requires manually installing U-Boot in the image. Build U-Boot with +the orangepi_pc_defconfig configuration as described in the previous section. +Next, unzip the NetBSD image and write the U-Boot binary including SPL using: + +.. code-block:: bash + + $ gunzip armv7.img.gz + $ dd if=/path/to/u-boot-sunxi-with-spl.bin of=armv7.img bs=1024 seek=8 conv=notrunc + +Finally, before starting the machine the SD image must be extended such +that the NetBSD kernel will not conclude the NetBSD partition is larger than +the emulated SD card: + +.. code-block:: bash + + $ dd if=/dev/zero bs=1M count=64 >> armv7.img + +Start the machine using the following command: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -sd armv7.img -global allwinner-rtc.base-year=2000 + +At the U-Boot stage, interrupt the automatic boot process by pressing a key +and set the following environment variables before booting: + +.. code-block:: bash + + => setenv bootargs root=ld0a + => setenv kernel netbsd-GENERIC.ub + => setenv fdtfile dtb/sun8i-h3-orangepi-pc.dtb + => setenv bootcmd 'fatload mmc 0:1 ${kernel_addr_r} ${kernel}; fatload mmc 0:1 ${fdt_addr_r} ${fdtfile}; fdt addr ${fdt_addr_r}; bootm ${kernel_addr_r} - ${fdt_addr_r}' + +Optionally you may save the environment variables to SD card with 'saveenv'. +To continue booting simply give the 'boot' command and NetBSD boots. + +Orange Pi PC acceptance tests +""""""""""""""""""""""""""""" + +The Orange Pi PC machine has several acceptance tests included. +To run the whole set of tests, build QEMU from source and simply +provide the following command: + +.. code-block:: bash + + $ AVOCADO_ALLOW_LARGE_STORAGE=yes avocado --show=app,console run \ + -t machine:orangepi-pc tests/acceptance/boot_linux_console.py 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 ``qemu-system-aarch64 --machine help``. .. toctree:: + :maxdepth: 1 arm/integratorcp arm/versatile @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/stellaris arm/musicpal arm/sx1 + arm/orangepi Arm CPU features ================ -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Mention 'max' value in the gic-version property description. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-2-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) virt_set_gic_version, NULL); object_property_set_description(obj, "gic-version", "Set GIC version. " - "Valid values are 2, 3 and host", NULL); + "Valid values are 2, 3, host and max", + NULL); vms->highmem_ecam = !vmc->no_highmem_ecam; -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> We plan to introduce yet another value for the gic version (nosel). As we already use exotic values such as 0 and -1, let's introduce a dedicated enum type and let vms->gic_version take this type. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-3-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/virt.h | 11 +++++++++-- hw/arm/virt.c | 30 +++++++++++++++--------------- 2 files changed, 24 insertions(+), 17 deletions(-) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef enum VirtIOMMUType { VIRT_IOMMU_VIRTIO, } VirtIOMMUType; +typedef enum VirtGICType { + VIRT_GIC_VERSION_MAX, + VIRT_GIC_VERSION_HOST, + VIRT_GIC_VERSION_2, + VIRT_GIC_VERSION_3, +} VirtGICType; + typedef struct MemMapEntry { hwaddr base; hwaddr size; @@ -XXX,XX +XXX,XX @@ typedef struct { bool highmem_ecam; bool its; bool virt; - int32_t gic_version; + VirtGICType gic_version; VirtIOMMUType iommu; uint16_t virtio_iommu_bdf; struct arm_boot_info bootinfo; @@ -XXX,XX +XXX,XX @@ static inline int virt_gicv3_redist_region_count(VirtMachineState *vms) uint32_t redist0_capacity = vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; - assert(vms->gic_version == 3); + assert(vms->gic_version == VIRT_GIC_VERSION_3); return vms->smp_cpus > redist0_capacity ? 2 : 1; } diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_timer_nodes(const VirtMachineState *vms) irqflags = GIC_FDT_IRQ_FLAGS_EDGE_LO_HI; } - if (vms->gic_version == 2) { + if (vms->gic_version == VIRT_GIC_VERSION_2) { irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START, GIC_FDT_IRQ_PPI_CPU_WIDTH, (1 << vms->smp_cpus) - 1); @@ -XXX,XX +XXX,XX @@ static void fdt_add_gic_node(VirtMachineState *vms) qemu_fdt_setprop_cell(vms->fdt, nodename, "#address-cells", 0x2); qemu_fdt_setprop_cell(vms->fdt, nodename, "#size-cells", 0x2); qemu_fdt_setprop(vms->fdt, nodename, "ranges", NULL, 0); - if (vms->gic_version == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { int nb_redist_regions = virt_gicv3_redist_region_count(vms); qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", @@ -XXX,XX +XXX,XX @@ static void fdt_add_pmu_nodes(const VirtMachineState *vms) } } - if (vms->gic_version == 2) { + if (vms->gic_version == VIRT_GIC_VERSION_2) { irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START, GIC_FDT_IRQ_PPI_CPU_WIDTH, (1 << vms->smp_cpus) - 1); @@ -XXX,XX +XXX,XX @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx) * purposes are to make TCG consistent (with 64-bit KVM hosts) * and to improve SGI efficiency. */ - if (vms->gic_version == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { clustersz = GICV3_TARGETLIST_BITS; } else { clustersz = GIC_TARGETLIST_BITS; @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) /* We can probe only here because during property set * KVM is not available yet */ - if (vms->gic_version <= 0) { - /* "host" or "max" */ + if (vms->gic_version == VIRT_GIC_VERSION_HOST || + vms->gic_version == VIRT_GIC_VERSION_MAX) { if (!kvm_enabled()) { - if (vms->gic_version == 0) { + if (vms->gic_version == VIRT_GIC_VERSION_HOST) { error_report("gic-version=host requires KVM"); exit(1); } else { /* "max": currently means 3 for TCG */ - vms->gic_version = 3; + vms->gic_version = VIRT_GIC_VERSION_3; } } else { vms->gic_version = kvm_arm_vgic_probe(); @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) /* The maximum number of CPUs depends on the GIC version, or on how * many redistributors we can fit into the memory map. */ - if (vms->gic_version == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { virt_max_cpus = vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; virt_max_cpus += @@ -XXX,XX +XXX,XX @@ static void virt_set_its(Object *obj, bool value, Error **errp) static char *virt_get_gic_version(Object *obj, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); - const char *val = vms->gic_version == 3 ? "3" : "2"; + const char *val = vms->gic_version == VIRT_GIC_VERSION_3 ? "3" : "2"; return g_strdup(val); } @@ -XXX,XX +XXX,XX @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp) VirtMachineState *vms = VIRT_MACHINE(obj); if (!strcmp(value, "3")) { - vms->gic_version = 3; + vms->gic_version = VIRT_GIC_VERSION_3; } else if (!strcmp(value, "2")) { - vms->gic_version = 2; + vms->gic_version = VIRT_GIC_VERSION_2; } else if (!strcmp(value, "host")) { - vms->gic_version = 0; /* Will probe later */ + vms->gic_version = VIRT_GIC_VERSION_HOST; /* Will probe later */ } else if (!strcmp(value, "max")) { - vms->gic_version = -1; /* Will probe later */ + vms->gic_version = VIRT_GIC_VERSION_MAX; /* Will probe later */ } else { error_setg(errp, "Invalid gic-version value"); error_append_hint(errp, "Valid values are 3, 2, host, max.\n"); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) "physical address space above 32 bits", NULL); /* Default GIC type is v2 */ - vms->gic_version = 2; + vms->gic_version = VIRT_GIC_VERSION_2; object_property_add_str(obj, "gic-version", virt_get_gic_version, virt_set_gic_version, NULL); object_property_set_description(obj, "gic-version", -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Let's move the code which freezes which gic-version to be applied in a dedicated function. We also now set by default the VIRT_GIC_VERSION_NO_SET. This eventually turns into the legacy v2 choice in the finalize() function. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-4-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/virt.h | 1 + hw/arm/virt.c | 54 ++++++++++++++++++++++++++----------------- 2 files changed, 34 insertions(+), 21 deletions(-) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef enum VirtGICType { VIRT_GIC_VERSION_HOST, VIRT_GIC_VERSION_2, VIRT_GIC_VERSION_3, + VIRT_GIC_VERSION_NOSEL, } VirtGICType; typedef struct MemMapEntry { diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_memmap(VirtMachineState *vms) } } +/* + * finalize_gic_version - Determines the final gic_version + * according to the gic-version property + * + * Default GIC type is v2 + */ +static void finalize_gic_version(VirtMachineState *vms) +{ + if (vms->gic_version == VIRT_GIC_VERSION_HOST || + vms->gic_version == VIRT_GIC_VERSION_MAX) { + if (!kvm_enabled()) { + if (vms->gic_version == VIRT_GIC_VERSION_HOST) { + error_report("gic-version=host requires KVM"); + exit(1); + } else { + /* "max": currently means 3 for TCG */ + vms->gic_version = VIRT_GIC_VERSION_3; + } + } else { + vms->gic_version = kvm_arm_vgic_probe(); + if (!vms->gic_version) { + error_report( + "Unable to determine GIC version supported by host"); + exit(1); + } + } + } else if (vms->gic_version == VIRT_GIC_VERSION_NOSEL) { + vms->gic_version = VIRT_GIC_VERSION_2; + } +} + static void machvirt_init(MachineState *machine) { VirtMachineState *vms = VIRT_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) /* We can probe only here because during property set * KVM is not available yet */ - if (vms->gic_version == VIRT_GIC_VERSION_HOST || - vms->gic_version == VIRT_GIC_VERSION_MAX) { - if (!kvm_enabled()) { - if (vms->gic_version == VIRT_GIC_VERSION_HOST) { - error_report("gic-version=host requires KVM"); - exit(1); - } else { - /* "max": currently means 3 for TCG */ - vms->gic_version = VIRT_GIC_VERSION_3; - } - } else { - vms->gic_version = kvm_arm_vgic_probe(); - if (!vms->gic_version) { - error_report( - "Unable to determine GIC version supported by host"); - exit(1); - } - } - } + finalize_gic_version(vms); if (!cpu_type_valid(machine->cpu_type)) { error_report("mach-virt: CPU type %s not supported", machine->cpu_type); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) "Set on/off to enable/disable using " "physical address space above 32 bits", NULL); - /* Default GIC type is v2 */ - vms->gic_version = VIRT_GIC_VERSION_2; + vms->gic_version = VIRT_GIC_VERSION_NOSEL; object_property_add_str(obj, "gic-version", virt_get_gic_version, virt_set_gic_version, NULL); object_property_set_description(obj, "gic-version", -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Convert kvm_arm_vgic_probe() so that it returns a bitmap of supported in-kernel emulation VGIC versions instead of the max version: at the moment values can be v2 and v3. This allows to expose the case where the host GICv3 also supports GICv2 emulation. This will be useful to choose the default version in KVM accelerated mode. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200311131618.7187-5-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 3 +++ hw/arm/virt.c | 11 +++++++++-- target/arm/kvm.c | 14 ++++++++------ 3 files changed, 20 insertions(+), 8 deletions(-) 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 @@ #include "exec/memory.h" #include "qemu/error-report.h" +#define KVM_ARM_VGIC_V2 (1 << 0) +#define KVM_ARM_VGIC_V3 (1 << 1) + /** * kvm_arm_vcpu_init: * @cs: CPUState diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) vms->gic_version = VIRT_GIC_VERSION_3; } } else { - vms->gic_version = kvm_arm_vgic_probe(); - if (!vms->gic_version) { + int probe_bitmap = kvm_arm_vgic_probe(); + + if (!probe_bitmap) { error_report( "Unable to determine GIC version supported by host"); exit(1); + } else { + if (probe_bitmap & KVM_ARM_VGIC_V3) { + vms->gic_version = VIRT_GIC_VERSION_3; + } else { + vms->gic_version = VIRT_GIC_VERSION_2; + } } } } else if (vms->gic_version == VIRT_GIC_VERSION_NOSEL) { 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_irqchip_create(KVMState *s) int kvm_arm_vgic_probe(void) { + int val = 0; + if (kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_V3, true) == 0) { - return 3; - } else if (kvm_create_device(kvm_state, - KVM_DEV_TYPE_ARM_VGIC_V2, true) == 0) { - return 2; - } else { - return 0; + val |= KVM_ARM_VGIC_V3; } + if (kvm_create_device(kvm_state, + KVM_DEV_TYPE_ARM_VGIC_V2, true) == 0) { + val |= KVM_ARM_VGIC_V2; + } + return val; } int kvm_arm_set_irq(int cpu, int irqtype, int irq, int level) -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Restructure the finalize_gic_version with switch cases and clearly separate the following cases: - KVM mode / in-kernel irqchip - KVM mode / userspace irqchip - TCG mode In KVM mode / in-kernel irqchip , we explictly check whether the chosen version is supported by the host. If the end-user explicitly sets v2/v3 and this is not supported by the host, then the user gets an explicit error message. Note that for old kernels where the CREATE_DEVICE ioctl doesn't exist then we will now fail if the user specifically asked for gicv2, where previously we (probably) would have succeeded. In KVM mode / userspace irqchip we immediatly output an error in case the end-user explicitly selected v3. Also we warn the end-user about the unexpected usage of gic-version=host in that case as only userspace GICv2 is supported. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-6-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 88 +++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 67 insertions(+), 21 deletions(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_memmap(VirtMachineState *vms) */ static void finalize_gic_version(VirtMachineState *vms) { - if (vms->gic_version == VIRT_GIC_VERSION_HOST || - vms->gic_version == VIRT_GIC_VERSION_MAX) { - if (!kvm_enabled()) { - if (vms->gic_version == VIRT_GIC_VERSION_HOST) { - error_report("gic-version=host requires KVM"); - exit(1); - } else { - /* "max": currently means 3 for TCG */ - vms->gic_version = VIRT_GIC_VERSION_3; - } - } else { - int probe_bitmap = kvm_arm_vgic_probe(); + if (kvm_enabled()) { + int probe_bitmap; - if (!probe_bitmap) { + if (!kvm_irqchip_in_kernel()) { + switch (vms->gic_version) { + case VIRT_GIC_VERSION_HOST: + warn_report( + "gic-version=host not relevant with kernel-irqchip=off " + "as only userspace GICv2 is supported. Using v2 ..."); + return; + case VIRT_GIC_VERSION_MAX: + case VIRT_GIC_VERSION_NOSEL: + vms->gic_version = VIRT_GIC_VERSION_2; + return; + case VIRT_GIC_VERSION_2: + return; + case VIRT_GIC_VERSION_3: error_report( - "Unable to determine GIC version supported by host"); + "gic-version=3 is not supported with kernel-irqchip=off"); exit(1); - } else { - if (probe_bitmap & KVM_ARM_VGIC_V3) { - vms->gic_version = VIRT_GIC_VERSION_3; - } else { - vms->gic_version = VIRT_GIC_VERSION_2; - } } } - } else if (vms->gic_version == VIRT_GIC_VERSION_NOSEL) { + + probe_bitmap = kvm_arm_vgic_probe(); + if (!probe_bitmap) { + error_report("Unable to determine GIC version supported by host"); + exit(1); + } + + switch (vms->gic_version) { + case VIRT_GIC_VERSION_HOST: + case VIRT_GIC_VERSION_MAX: + if (probe_bitmap & KVM_ARM_VGIC_V3) { + vms->gic_version = VIRT_GIC_VERSION_3; + } else { + vms->gic_version = VIRT_GIC_VERSION_2; + } + return; + case VIRT_GIC_VERSION_NOSEL: + vms->gic_version = VIRT_GIC_VERSION_2; + break; + case VIRT_GIC_VERSION_2: + case VIRT_GIC_VERSION_3: + break; + } + + /* Check chosen version is effectively supported by the host */ + if (vms->gic_version == VIRT_GIC_VERSION_2 && + !(probe_bitmap & KVM_ARM_VGIC_V2)) { + error_report("host does not support in-kernel GICv2 emulation"); + exit(1); + } else if (vms->gic_version == VIRT_GIC_VERSION_3 && + !(probe_bitmap & KVM_ARM_VGIC_V3)) { + error_report("host does not support in-kernel GICv3 emulation"); + exit(1); + } + return; + } + + /* TCG mode */ + switch (vms->gic_version) { + case VIRT_GIC_VERSION_NOSEL: vms->gic_version = VIRT_GIC_VERSION_2; + break; + case VIRT_GIC_VERSION_MAX: + vms->gic_version = VIRT_GIC_VERSION_3; + break; + case VIRT_GIC_VERSION_HOST: + error_report("gic-version=host requires KVM"); + exit(1); + case VIRT_GIC_VERSION_2: + case VIRT_GIC_VERSION_3: + break; } } -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> At the moment if the end-user does not specify the gic-version along with KVM acceleration, v2 is set by default. However most of the systems now have GICv3 and sometimes they do not support GICv2 compatibility. This patch keeps the default v2 selection in all cases except in the KVM accelerated mode when either - the host does not support GICv2 in-kernel emulation or - number of VCPUS exceeds 8. Those cases did not work anyway so we do not break any compatibility. Now we get v3 selected in such a case. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-7-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_memmap(VirtMachineState *vms) */ static void finalize_gic_version(VirtMachineState *vms) { + unsigned int max_cpus = MACHINE(vms)->smp.max_cpus; + if (kvm_enabled()) { int probe_bitmap; @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) } return; case VIRT_GIC_VERSION_NOSEL: - vms->gic_version = VIRT_GIC_VERSION_2; + if ((probe_bitmap & KVM_ARM_VGIC_V2) && max_cpus <= GIC_NCPU) { + vms->gic_version = VIRT_GIC_VERSION_2; + } else if (probe_bitmap & KVM_ARM_VGIC_V3) { + /* + * in case the host does not support v2 in-kernel emulation or + * the end-user requested more than 8 VCPUs we now default + * to v3. In any case defaulting to v2 would be broken. + */ + vms->gic_version = VIRT_GIC_VERSION_3; + } else if (max_cpus > GIC_NCPU) { + error_report("host only supports in-kernel GICv2 emulation " + "but more than 8 vcpus are requested"); + exit(1); + } break; case VIRT_GIC_VERSION_2: case VIRT_GIC_VERSION_3: -- 2.20.1 From: Beata Michalska <beata.michalska@linaro.org> KVM_SET_VCPU_EVENTS might actually lead to vcpu registers being modified. As such this should be the last step of sync to avoid potential overwriting of whatever changes KVM might have done. Signed-off-by: Beata Michalska <beata.michalska@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200312003401.29017-2-beata.michalska@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm32.c | 15 ++++++++++----- target/arm/kvm64.c | 15 ++++++++++----- 2 files changed, 20 insertions(+), 10 deletions(-) diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } - ret = kvm_put_vcpu_events(cpu); - 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; diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } - ret = kvm_put_vcpu_events(cpu); - 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; -- 2.20.1 Just my fp16 work, plus some small stuff for the sbsa-ref board; but my rule of thumb is to send a pullreq once I get over about 30 patches... -- PMM The following changes since commit 2f4c51c0f384d7888a04b4815861e6d5fd244d75: Merge remote-tracking branch 'remotes/kraxel/tags/usb-20200831-pull-request' into staging (2020-08-31 19:39:13 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200901 for you to fetch changes up to 3f462bf0f6ea6382dd1502d4eb1fcd33c8e774f5: hw/arm/sbsa-ref : Add embedded controller in secure memory (2020-09-01 14:01:34 +0100) ---------------------------------------------------------------- target-arm queue: * Implement fp16 support for AArch32 VFP and Neon * hw/arm/sbsa-ref: add "reg" property to DT cpu nodes * hw/arm/sbsa-ref : Add embedded controller in secure memory ---------------------------------------------------------------- Graeme Gregory (2): hw/misc/sbsa_ec : Add an embedded controller for sbsa-ref hw/arm/sbsa-ref : Add embedded controller in secure memory Leif Lindholm (1): hw/arm/sbsa-ref: add "reg" property to DT cpu nodes Peter Maydell (44): target/arm: Remove local definitions of float constants target/arm: Use correct ID register check for aa32_fp16_arith target/arm: Implement VFP fp16 for VFP_BINOP operations target/arm: Implement VFP fp16 VMLA, VMLS, VNMLS, VNMLA, VNMUL target/arm: Macroify trans functions for VFMA, VFMS, VFNMA, VFNMS target/arm: Implement VFP fp16 for fused-multiply-add target/arm: Macroify uses of do_vfp_2op_sp() and do_vfp_2op_dp() target/arm: Implement VFP fp16 for VABS, VNEG, VSQRT target/arm: Implement VFP fp16 for VMOV immediate target/arm: Implement VFP fp16 VCMP target/arm: Implement VFP fp16 VLDR and VSTR target/arm: Implement VFP fp16 VCVT between float and integer target/arm: Make VFP_CONV_FIX macros take separate float type and float size target/arm: Use macros instead of open-coding fp16 conversion helpers target/arm: Implement VFP fp16 VCVT between float and fixed-point target/arm: Implement VFP vp16 VCVT-with-specified-rounding-mode target/arm: Implement VFP fp16 VSEL target/arm: Implement VFP fp16 VRINT* target/arm: Implement new VFP fp16 insn VINS target/arm: Implement new VFP fp16 insn VMOVX target/arm: Implement VFP fp16 VMOV between gp and halfprec registers target/arm: Implement FP16 for Neon VADD, VSUB, VABD, VMUL target/arm: Implement fp16 for Neon VRECPE, VRSQRTE using gvec target/arm: Implement fp16 for Neon VABS, VNEG of floats target/arm: Implement fp16 for VCEQ, VCGE, VCGT comparisons target/arm: Implement fp16 for VACGE, VACGT target/arm: Implement fp16 for Neon VMAX, VMIN target/arm: Implement fp16 for Neon VMAXNM, VMINNM target/arm: Implement fp16 for Neon VMLA, VMLS operations target/arm: Implement fp16 for Neon VFMA, VMFS target/arm: Implement fp16 for Neon fp compare-vs-0 target/arm: Implement fp16 for Neon VRECPS target/arm: Implement fp16 for Neon VRSQRTS target/arm: Implement fp16 for Neon pairwise fp ops target/arm: Implement fp16 for Neon float-integer VCVT target/arm: Convert Neon VCVT fixed-point to gvec target/arm: Implement fp16 for Neon VCVT fixed-point target/arm: Implement fp16 for Neon VCVT with rounding modes target/arm: Implement fp16 for Neon VRINT-with-specified-rounding-mode target/arm: Implement fp16 for Neon VRINTX target/arm/vec_helper: Handle oprsz less than 16 bytes in indexed operations target/arm/vec_helper: Add gvec fp indexed multiply-and-add operations target/arm: Implement fp16 for Neon VMUL, VMLA, VMLS target/arm: Enable FP16 in '-cpu max' target/arm/cpu.h | 7 +- target/arm/helper.h | 133 ++++++- target/arm/neon-dp.decode | 8 +- target/arm/vfp-uncond.decode | 27 +- target/arm/vfp.decode | 34 +- hw/arm/sbsa-ref.c | 43 ++- hw/misc/sbsa_ec.c | 98 +++++ target/arm/cpu.c | 3 +- target/arm/cpu64.c | 10 +- target/arm/helper-a64.c | 11 - target/arm/translate-sve.c | 4 - target/arm/vec_helper.c | 431 ++++++++++++++++++++- target/arm/vfp_helper.c | 244 +++++------- hw/misc/meson.build | 2 + target/arm/translate-neon.c.inc | 755 +++++++++++++------------------------ target/arm/translate-vfp.c.inc | 810 ++++++++++++++++++++++++++++++++++++---- 16 files changed, 1819 insertions(+), 801 deletions(-) create mode 100644 hw/misc/sbsa_ec.c In several places the target/arm code defines local float constants for 2, 3 and 1.5, which are also provided by include/fpu/softfloat.h. Remove the unnecessary local duplicate versions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-2-peter.maydell@linaro.org --- target/arm/helper-a64.c | 11 ----------- target/arm/translate-sve.c | 4 ---- target/arm/vfp_helper.c | 4 ---- 3 files changed, 19 deletions(-) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) * versions, these do a fully fused multiply-add or * multiply-add-and-halve. */ -#define float16_two make_float16(0x4000) -#define float16_three make_float16(0x4200) -#define float16_one_point_five make_float16(0x3e00) - -#define float32_two make_float32(0x40000000) -#define float32_three make_float32(0x40400000) -#define float32_one_point_five make_float32(0x3fc00000) - -#define float64_two make_float64(0x4000000000000000ULL) -#define float64_three make_float64(0x4008000000000000ULL) -#define float64_one_point_five make_float64(0x3FF8000000000000ULL) uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp) { diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME##_zpzi(DisasContext *s, arg_rpri_esz *a) \ return true; \ } -#define float16_two make_float16(0x4000) -#define float32_two make_float32(0x40000000) -#define float64_two make_float64(0x4000000000000000ULL) - DO_FP_IMM(FADD, fadds, half, one) DO_FP_IMM(FSUB, fsubs, half, one) DO_FP_IMM(FMUL, fmuls, half, two) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) return r; } -#define float32_two make_float32(0x40000000) -#define float32_three make_float32(0x40400000) -#define float32_one_point_five make_float32(0x3fc00000) - float32 HELPER(recps_f32)(CPUARMState *env, float32 a, float32 b) { float_status *s = &env->vfp.standard_fp_status; -- 2.20.1 The aa32_fp16_arith feature check function currently looks at the AArch64 ID_AA64PFR0 register. This is (as the comment notes) not correct. The bogus check was put in mostly to allow testing of the fp16 variants of the VCMLA instructions and it was something of a mistake that we allowed them to exist in master. Switch the feature check function to testing VMFR1.FPHP, which is what it ought to be. This will remove emulation of the VCMLA and VCADD insns from AArch32 code running on an AArch64 '-cpu max' using system emulation. (They were never enabled for aarch32 linux-user and system-emulation.) Since we weren't advertising their existence via the AArch32 ID register, well-behaved guests wouldn't have been using them anyway. Once we have implemented all the AArch32 support for the FP16 extension we will advertise it in the MVFR1 ID register field, which will reenable these insns along with all the others. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-3-peter.maydell@linaro.org --- target/arm/cpu.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) { - /* - * This is a placeholder for use by VCMA until the rest of - * the ARMv8.2-FP16 extension is implemented for aa32 mode. - * At which point we can properly set and check MVFR1.FPHP. - */ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3; } static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) -- 2.20.1 Implmeent VFP fp16 support for simple binary-operator VFP insns VADD, VSUB, VMUL, VDIV, VMINNM and VMAXNM: * make the VFP_BINOP() macro generate float16 helpers as well as float32 and float64 * implement a do_vfp_3op_hp() function similar to the existing do_vfp_3op_sp() * add decode for the half-precision insn patterns Note that the VFP_BINOP macro use creates a couple of unused helper functions vfp_maxh and vfp_minh, but they're small so it's not worth splitting the BINOP operations into "needs halfprec" and "no halfprec" groups. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-4-peter.maydell@linaro.org --- target/arm/helper.h | 8 ++++ target/arm/vfp-uncond.decode | 3 ++ target/arm/vfp.decode | 4 ++ target/arm/vfp_helper.c | 5 ++ target/arm/translate-vfp.c.inc | 86 ++++++++++++++++++++++++++++++++++ 5 files changed, 106 insertions(+) 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_5(probe_access, TCG_CALL_NO_WG, void, env, tl, i32, i32, i32) DEF_HELPER_1(vfp_get_fpscr, i32, env) DEF_HELPER_2(vfp_set_fpscr, void, env, i32) +DEF_HELPER_3(vfp_addh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_adds, f32, f32, f32, ptr) DEF_HELPER_3(vfp_addd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_subh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_subs, f32, f32, f32, ptr) DEF_HELPER_3(vfp_subd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_mulh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_muls, f32, f32, f32, ptr) DEF_HELPER_3(vfp_muld, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_divh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_divs, f32, f32, f32, ptr) DEF_HELPER_3(vfp_divd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_maxh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_maxs, f32, f32, f32, ptr) DEF_HELPER_3(vfp_maxd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_minh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_mins, f32, f32, f32, ptr) DEF_HELPER_3(vfp_mind, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_maxnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_maxnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) DEF_HELPER_1(vfp_negs, f32, f32) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VSEL 1111 1110 0. cc:2 .... .... 1010 .0.0 .... \ VSEL 1111 1110 0. cc:2 .... .... 1011 .0.0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1 +VMAXNM_hp 1111 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s +VMINNM_hp 1111 1110 1.00 .... .... 1001 .1.0 .... @vfp_dnm_s + VMAXNM_sp 1111 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @vfp_dnm_s diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d +VMUL_hp ---- 1110 0.10 .... .... 1001 .0.0 .... @vfp_dnm_s VMUL_sp ---- 1110 0.10 .... .... 1010 .0.0 .... @vfp_dnm_s VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... @vfp_dnm_d VNMUL_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d +VADD_hp ---- 1110 0.11 .... .... 1001 .0.0 .... @vfp_dnm_s VADD_sp ---- 1110 0.11 .... .... 1010 .0.0 .... @vfp_dnm_s VADD_dp ---- 1110 0.11 .... .... 1011 .0.0 .... @vfp_dnm_d +VSUB_hp ---- 1110 0.11 .... .... 1001 .1.0 .... @vfp_dnm_s VSUB_sp ---- 1110 0.11 .... .... 1010 .1.0 .... @vfp_dnm_s VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... @vfp_dnm_d +VDIV_hp ---- 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val) #define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p)) #define VFP_BINOP(name) \ +dh_ctype_f16 VFP_HELPER(name, h)(dh_ctype_f16 a, dh_ctype_f16 b, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return float16_ ## name(a, b, fpst); \ +} \ float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \ { \ float_status *fpst = fpstp; \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, return true; } +static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, + int vd, int vn, int vm, bool reads_vd) +{ + /* + * Do a half-precision operation. Functionally this is + * the same as do_vfp_3op_sp(), except: + * - it uses the FPST_FPCR_F16 + * - it doesn't need the VFP vector handling (fp16 is a + * v8 feature, and in v8 VFP vectors don't exist) + * - it does the aa32_fp16_arith feature test + */ + TCGv_i32 f0, f1, fd; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + f0 = tcg_temp_new_i32(); + f1 = tcg_temp_new_i32(); + fd = tcg_temp_new_i32(); + fpst = fpstatus_ptr(FPST_FPCR_F16); + + neon_load_reg32(f0, vn); + neon_load_reg32(f1, vm); + + if (reads_vd) { + neon_load_reg32(fd, vd); + } + fn(fd, f0, f1, fpst); + neon_store_reg32(fd, vd); + + tcg_temp_free_i32(f0); + tcg_temp_free_i32(f1); + tcg_temp_free_i32(fd); + tcg_temp_free_ptr(fpst); + + return true; +} + static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, int vd, int vn, int vm, bool reads_vd) { @@ -XXX,XX +XXX,XX @@ static bool trans_VNMLA_dp(DisasContext *s, arg_VNMLA_dp *a) return do_vfp_3op_dp(s, gen_VNMLA_dp, a->vd, a->vn, a->vm, true); } +static bool trans_VMUL_hp(DisasContext *s, arg_VMUL_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_mulh, a->vd, a->vn, a->vm, false); +} + static bool trans_VMUL_sp(DisasContext *s, arg_VMUL_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_muls, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VNMUL_dp(DisasContext *s, arg_VNMUL_dp *a) return do_vfp_3op_dp(s, gen_VNMUL_dp, a->vd, a->vn, a->vm, false); } +static bool trans_VADD_hp(DisasContext *s, arg_VADD_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_addh, a->vd, a->vn, a->vm, false); +} + static bool trans_VADD_sp(DisasContext *s, arg_VADD_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_adds, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VADD_dp(DisasContext *s, arg_VADD_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_addd, a->vd, a->vn, a->vm, false); } +static bool trans_VSUB_hp(DisasContext *s, arg_VSUB_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_subh, a->vd, a->vn, a->vm, false); +} + static bool trans_VSUB_sp(DisasContext *s, arg_VSUB_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_subs, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VSUB_dp(DisasContext *s, arg_VSUB_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_subd, a->vd, a->vn, a->vm, false); } +static bool trans_VDIV_hp(DisasContext *s, arg_VDIV_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_divh, a->vd, a->vn, a->vm, false); +} + static bool trans_VDIV_sp(DisasContext *s, arg_VDIV_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_divs, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VDIV_dp(DisasContext *s, arg_VDIV_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_divd, a->vd, a->vn, a->vm, false); } +static bool trans_VMINNM_hp(DisasContext *s, arg_VMINNM_sp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_hp(s, gen_helper_vfp_minnumh, + a->vd, a->vn, a->vm, false); +} + +static bool trans_VMAXNM_hp(DisasContext *s, arg_VMAXNM_sp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_hp(s, gen_helper_vfp_maxnumh, + a->vd, a->vn, a->vm, false); +} + static bool trans_VMINNM_sp(DisasContext *s, arg_VMINNM_sp *a) { if (!dc_isar_feature(aa32_vminmaxnm, s)) { -- 2.20.1 Implement fp16 versions of the VFP VMLA, VMLS, VNMLS, VNMLA, VNMUL instructions. (These are all the remaining ones which we implement via do_vfp_3op_[hsd]p().) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-5-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/vfp.decode | 5 ++ target/arm/vfp_helper.c | 5 ++ target/arm/translate-vfp.c.inc | 84 ++++++++++++++++++++++++++++++++++ 4 files changed, 95 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) +DEF_HELPER_1(vfp_negh, f16, f16) DEF_HELPER_1(vfp_negs, f32, f32) DEF_HELPER_1(vfp_negd, f64, f64) DEF_HELPER_1(vfp_abss, f32, f32) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VLDM_VSTM_dp ---- 1101 0.1 l:1 rn:4 .... 1011 imm:8 \ vd=%vd_dp p=1 u=0 w=1 # 3-register VFP data-processing; bits [23,21:20,6] identify the operation. +VMLA_hp ---- 1110 0.00 .... .... 1001 .0.0 .... @vfp_dnm_s VMLA_sp ---- 1110 0.00 .... .... 1010 .0.0 .... @vfp_dnm_s VMLA_dp ---- 1110 0.00 .... .... 1011 .0.0 .... @vfp_dnm_d +VMLS_hp ---- 1110 0.00 .... .... 1001 .1.0 .... @vfp_dnm_s VMLS_sp ---- 1110 0.00 .... .... 1010 .1.0 .... @vfp_dnm_s VMLS_dp ---- 1110 0.00 .... .... 1011 .1.0 .... @vfp_dnm_d +VNMLS_hp ---- 1110 0.01 .... .... 1001 .0.0 .... @vfp_dnm_s VNMLS_sp ---- 1110 0.01 .... .... 1010 .0.0 .... @vfp_dnm_s VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d +VNMLA_hp ---- 1110 0.01 .... .... 1001 .1.0 .... @vfp_dnm_s VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d @@ -XXX,XX +XXX,XX @@ VMUL_hp ---- 1110 0.10 .... .... 1001 .0.0 .... @vfp_dnm_s VMUL_sp ---- 1110 0.10 .... .... 1010 .0.0 .... @vfp_dnm_s VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... @vfp_dnm_d +VNMUL_hp ---- 1110 0.10 .... .... 1001 .1.0 .... @vfp_dnm_s VNMUL_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ VFP_BINOP(minnum) VFP_BINOP(maxnum) #undef VFP_BINOP +dh_ctype_f16 VFP_HELPER(neg, h)(dh_ctype_f16 a) +{ + return float16_chs(a); +} + float32 VFP_HELPER(neg, s)(float32 a) { return float32_chs(a); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) return true; } +static void gen_VMLA_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* Note that order of inputs to the add matters for NaNs */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VMLA_hp(DisasContext *s, arg_VMLA_sp *a) +{ + return do_vfp_3op_hp(s, gen_VMLA_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VMLA_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* Note that order of inputs to the add matters for NaNs */ @@ -XXX,XX +XXX,XX @@ static bool trans_VMLA_dp(DisasContext *s, arg_VMLA_dp *a) return do_vfp_3op_dp(s, gen_VMLA_dp, a->vd, a->vn, a->vm, true); } +static void gen_VMLS_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* + * VMLS: vd = vd + -(vn * vm) + * Note that order of inputs to the add matters for NaNs. + */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_negh(tmp, tmp); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VMLS_hp(DisasContext *s, arg_VMLS_sp *a) +{ + return do_vfp_3op_hp(s, gen_VMLS_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* @@ -XXX,XX +XXX,XX @@ static bool trans_VMLS_dp(DisasContext *s, arg_VMLS_dp *a) return do_vfp_3op_dp(s, gen_VMLS_dp, a->vd, a->vn, a->vm, true); } +static void gen_VNMLS_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* + * VNMLS: -fd + (fn * fm) + * Note that it isn't valid to replace (-A + B) with (B - A) or similar + * plausible looking simplifications because this will give wrong results + * for NaNs. + */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_negh(vd, vd); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VNMLS_hp(DisasContext *s, arg_VNMLS_sp *a) +{ + return do_vfp_3op_hp(s, gen_VNMLS_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VNMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* @@ -XXX,XX +XXX,XX @@ static bool trans_VNMLS_dp(DisasContext *s, arg_VNMLS_dp *a) return do_vfp_3op_dp(s, gen_VNMLS_dp, a->vd, a->vn, a->vm, true); } +static void gen_VNMLA_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* VNMLA: -fd + -(fn * fm) */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_negh(tmp, tmp); + gen_helper_vfp_negh(vd, vd); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VNMLA_hp(DisasContext *s, arg_VNMLA_sp *a) +{ + return do_vfp_3op_hp(s, gen_VNMLA_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VNMLA_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* VNMLA: -fd + -(fn * fm) */ @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_dp(DisasContext *s, arg_VMUL_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_muld, a->vd, a->vn, a->vm, false); } +static void gen_VNMUL_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* VNMUL: -(fn * fm) */ + gen_helper_vfp_mulh(vd, vn, vm, fpst); + gen_helper_vfp_negh(vd, vd); +} + +static bool trans_VNMUL_hp(DisasContext *s, arg_VNMUL_sp *a) +{ + return do_vfp_3op_hp(s, gen_VNMUL_hp, a->vd, a->vn, a->vm, false); +} + static void gen_VNMUL_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* VNMUL: -(fn * fm) */ -- 2.20.1 Macroify creation of the trans functions for single and double precision VFMA, VFMS, VFNMA, VFNMS. The repetition was OK for two sizes, but we're about to add halfprec and it will get a bit more than seems reasonable. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-6-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 50 +++++++++------------------------- 1 file changed, 13 insertions(+), 37 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) return true; } -static bool trans_VFMA_sp(DisasContext *s, arg_VFMA_sp *a) -{ - return do_vfm_sp(s, a, false, false); -} - -static bool trans_VFMS_sp(DisasContext *s, arg_VFMS_sp *a) -{ - return do_vfm_sp(s, a, true, false); -} - -static bool trans_VFNMA_sp(DisasContext *s, arg_VFNMA_sp *a) -{ - return do_vfm_sp(s, a, false, true); -} - -static bool trans_VFNMS_sp(DisasContext *s, arg_VFNMS_sp *a) -{ - return do_vfm_sp(s, a, true, true); -} - static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) { /* @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) return true; } -static bool trans_VFMA_dp(DisasContext *s, arg_VFMA_dp *a) -{ - return do_vfm_dp(s, a, false, false); -} +#define MAKE_ONE_VFM_TRANS_FN(INSN, PREC, NEGN, NEGD) \ + static bool trans_##INSN##_##PREC(DisasContext *s, \ + arg_##INSN##_##PREC *a) \ + { \ + return do_vfm_##PREC(s, a, NEGN, NEGD); \ + } -static bool trans_VFMS_dp(DisasContext *s, arg_VFMS_dp *a) -{ - return do_vfm_dp(s, a, true, false); -} +#define MAKE_VFM_TRANS_FNS(PREC) \ + MAKE_ONE_VFM_TRANS_FN(VFMA, PREC, false, false) \ + MAKE_ONE_VFM_TRANS_FN(VFMS, PREC, true, false) \ + MAKE_ONE_VFM_TRANS_FN(VFNMA, PREC, false, true) \ + MAKE_ONE_VFM_TRANS_FN(VFNMS, PREC, true, true) -static bool trans_VFNMA_dp(DisasContext *s, arg_VFNMA_dp *a) -{ - return do_vfm_dp(s, a, false, true); -} - -static bool trans_VFNMS_dp(DisasContext *s, arg_VFNMS_dp *a) -{ - return do_vfm_dp(s, a, true, true); -} +MAKE_VFM_TRANS_FNS(sp) +MAKE_VFM_TRANS_FNS(dp) static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) { -- 2.20.1 Implement VFP fp16 support for fused multiply-add insns VFNMA, VFNMS, VFMA, VFMS. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-7-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/vfp.decode | 5 +++ target/arm/vfp_helper.c | 7 ++++ target/arm/translate-vfp.c.inc | 64 ++++++++++++++++++++++++++++++++++ 4 files changed, 77 insertions(+) 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(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, ptr, i32) DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) +DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr) DEF_HELPER_3(recps_f32, f32, env, f32, f32) DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VDIV_hp ---- 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d +VFMA_hp ---- 1110 1.10 .... .... 1001 .0. 0 .... @vfp_dnm_s +VFMS_hp ---- 1110 1.10 .... .... 1001 .1. 0 .... @vfp_dnm_s +VFNMA_hp ---- 1110 1.01 .... .... 1001 .0. 0 .... @vfp_dnm_s +VFNMS_hp ---- 1110 1.01 .... .... 1001 .1. 0 .... @vfp_dnm_s + VFMA_sp ---- 1110 1.10 .... .... 1010 .0. 0 .... @vfp_dnm_s VFMS_sp ---- 1110 1.10 .... .... 1010 .1. 0 .... @vfp_dnm_s VFNMA_sp ---- 1110 1.01 .... .... 1010 .0. 0 .... @vfp_dnm_s diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_u32)(uint32_t a) } /* VFPv4 fused multiply-accumulate */ +dh_ctype_f16 VFP_HELPER(muladd, h)(dh_ctype_f16 a, dh_ctype_f16 b, + dh_ctype_f16 c, void *fpstp) +{ + float_status *fpst = fpstp; + return float16_muladd(a, b, c, 0, fpst); +} + float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp) { float_status *fpst = fpstp; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMAXNM_dp(DisasContext *s, arg_VMAXNM_dp *a) a->vd, a->vn, a->vm, false); } +static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) +{ + /* + * VFNMA : fd = muladd(-fd, fn, fm) + * VFNMS : fd = muladd(-fd, -fn, fm) + * VFMA : fd = muladd( fd, fn, fm) + * VFMS : fd = muladd( fd, -fn, fm) + * + * These are fused multiply-add, and must be done as one floating + * point operation with no rounding between the multiplication and + * addition steps. NB that doing the negations here as separate + * steps is correct : an input NaN should come out with its sign + * bit flipped if it is a negated-input. + */ + TCGv_ptr fpst; + TCGv_i32 vn, vm, vd; + + /* + * Present in VFPv4 only, and only with the FP16 extension. + * Note that we can't rely on the SIMDFMAC check alone, because + * in a Neon-no-VFP core that ID register field will be non-zero. + */ + if (!dc_isar_feature(aa32_fp16_arith, s) || + !dc_isar_feature(aa32_simdfmac, s) || + !dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vn = tcg_temp_new_i32(); + vm = tcg_temp_new_i32(); + vd = tcg_temp_new_i32(); + + neon_load_reg32(vn, a->vn); + neon_load_reg32(vm, a->vm); + if (neg_n) { + /* VFNMS, VFMS */ + gen_helper_vfp_negh(vn, vn); + } + neon_load_reg32(vd, a->vd); + if (neg_d) { + /* VFNMA, VFNMS */ + gen_helper_vfp_negh(vd, vd); + } + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); + neon_store_reg32(vd, a->vd); + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(vn); + tcg_temp_free_i32(vm); + tcg_temp_free_i32(vd); + + return true; +} + static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) { /* @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) MAKE_ONE_VFM_TRANS_FN(VFNMA, PREC, false, true) \ MAKE_ONE_VFM_TRANS_FN(VFNMS, PREC, true, true) +MAKE_VFM_TRANS_FNS(hp) MAKE_VFM_TRANS_FNS(sp) MAKE_VFM_TRANS_FNS(dp) -- 2.20.1 Macroify the uses of do_vfp_2op_sp() and do_vfp_2op_dp(); this will make it easier to add the halfprec support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-8-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 49 ++++++++++------------------------ 1 file changed, 14 insertions(+), 35 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) return true; } -static bool trans_VMOV_reg_sp(DisasContext *s, arg_VMOV_reg_sp *a) -{ - return do_vfp_2op_sp(s, tcg_gen_mov_i32, a->vd, a->vm); -} +#define DO_VFP_2OP(INSN, PREC, FN) \ + static bool trans_##INSN##_##PREC(DisasContext *s, \ + arg_##INSN##_##PREC *a) \ + { \ + return do_vfp_2op_##PREC(s, FN, a->vd, a->vm); \ + } -static bool trans_VMOV_reg_dp(DisasContext *s, arg_VMOV_reg_dp *a) -{ - return do_vfp_2op_dp(s, tcg_gen_mov_i64, a->vd, a->vm); -} +DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32) +DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64) -static bool trans_VABS_sp(DisasContext *s, arg_VABS_sp *a) -{ - return do_vfp_2op_sp(s, gen_helper_vfp_abss, a->vd, a->vm); -} +DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss) +DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd) -static bool trans_VABS_dp(DisasContext *s, arg_VABS_dp *a) -{ - return do_vfp_2op_dp(s, gen_helper_vfp_absd, a->vd, a->vm); -} - -static bool trans_VNEG_sp(DisasContext *s, arg_VNEG_sp *a) -{ - return do_vfp_2op_sp(s, gen_helper_vfp_negs, a->vd, a->vm); -} - -static bool trans_VNEG_dp(DisasContext *s, arg_VNEG_dp *a) -{ - return do_vfp_2op_dp(s, gen_helper_vfp_negd, a->vd, a->vm); -} +DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs) +DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd) static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) { gen_helper_vfp_sqrts(vd, vm, cpu_env); } -static bool trans_VSQRT_sp(DisasContext *s, arg_VSQRT_sp *a) -{ - return do_vfp_2op_sp(s, gen_VSQRT_sp, a->vd, a->vm); -} - static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) { gen_helper_vfp_sqrtd(vd, vm, cpu_env); } -static bool trans_VSQRT_dp(DisasContext *s, arg_VSQRT_dp *a) -{ - return do_vfp_2op_dp(s, gen_VSQRT_dp, a->vd, a->vm); -} +DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) +DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) { -- 2.20.1 Implement VFP fp16 for VABS, VNEG and VSQRT. This is all the fp16 insns that use the DO_VFP_2OP macro, because there is no fp16 version of VMOV_reg. Notes: * the gen_helper_vfp_negh already exists as we needed to create it for the fp16 multiply-add insns * as usual we need to use the f16 version of the fp_status; this is only relevant for VSQRT Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-9-peter.maydell@linaro.org --- target/arm/helper.h | 2 ++ target/arm/vfp.decode | 3 +++ target/arm/vfp_helper.c | 10 +++++++++ target/arm/translate-vfp.c.inc | 40 ++++++++++++++++++++++++++++++++++ 4 files changed, 55 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) DEF_HELPER_1(vfp_negh, f16, f16) DEF_HELPER_1(vfp_negs, f32, f32) DEF_HELPER_1(vfp_negd, f64, f64) +DEF_HELPER_1(vfp_absh, f16, f16) DEF_HELPER_1(vfp_abss, f32, f32) DEF_HELPER_1(vfp_absd, f64, f64) +DEF_HELPER_2(vfp_sqrth, f16, f16, env) DEF_HELPER_2(vfp_sqrts, f32, f32, env) DEF_HELPER_2(vfp_sqrtd, f64, f64, env) DEF_HELPER_3(vfp_cmps, void, f32, f32, env) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ VMOV_reg_sp ---- 1110 1.11 0000 .... 1010 01.0 .... @vfp_dm_ss VMOV_reg_dp ---- 1110 1.11 0000 .... 1011 01.0 .... @vfp_dm_dd +VABS_hp ---- 1110 1.11 0000 .... 1001 11.0 .... @vfp_dm_ss VABS_sp ---- 1110 1.11 0000 .... 1010 11.0 .... @vfp_dm_ss VABS_dp ---- 1110 1.11 0000 .... 1011 11.0 .... @vfp_dm_dd +VNEG_hp ---- 1110 1.11 0001 .... 1001 01.0 .... @vfp_dm_ss VNEG_sp ---- 1110 1.11 0001 .... 1010 01.0 .... @vfp_dm_ss VNEG_dp ---- 1110 1.11 0001 .... 1011 01.0 .... @vfp_dm_dd +VSQRT_hp ---- 1110 1.11 0001 .... 1001 11.0 .... @vfp_dm_ss VSQRT_sp ---- 1110 1.11 0001 .... 1010 11.0 .... @vfp_dm_ss VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... @vfp_dm_dd diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ float64 VFP_HELPER(neg, d)(float64 a) return float64_chs(a); } +dh_ctype_f16 VFP_HELPER(abs, h)(dh_ctype_f16 a) +{ + return float16_abs(a); +} + float32 VFP_HELPER(abs, s)(float32 a) { return float32_abs(a); @@ -XXX,XX +XXX,XX @@ float64 VFP_HELPER(abs, d)(float64 a) return float64_abs(a); } +dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, CPUARMState *env) +{ + return float16_sqrt(a, &env->vfp.fp_status_f16); +} + float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env) { return float32_sqrt(a, &env->vfp.fp_status); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) return true; } +static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) +{ + /* + * Do a half-precision operation. Functionally this is + * the same as do_vfp_2op_sp(), except: + * - it doesn't need the VFP vector handling (fp16 is a + * v8 feature, and in v8 VFP vectors don't exist) + * - it does the aa32_fp16_arith feature test + */ + TCGv_i32 f0; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + f0 = tcg_temp_new_i32(); + neon_load_reg32(f0, vm); + fn(f0, f0); + neon_store_reg32(f0, vd); + tcg_temp_free_i32(f0); + + return true; +} + static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) { uint32_t delta_m = 0; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32) DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64) +DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh) DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss) DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd) +DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh) DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs) DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd) +static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) +{ + gen_helper_vfp_sqrth(vd, vm, cpu_env); +} + static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) { gen_helper_vfp_sqrts(vd, vm, cpu_env); @@ -XXX,XX +XXX,XX @@ static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) gen_helper_vfp_sqrtd(vd, vm, cpu_env); } +DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp) DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) -- 2.20.1 Implement VFP fp16 support for the VMOV immediate insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-10-peter.maydell@linaro.org --- target/arm/vfp.decode | 2 ++ target/arm/translate-vfp.c.inc | 22 ++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VFMS_dp ---- 1110 1.10 .... .... 1011 .1.0 .... @vfp_dnm_d VFNMA_dp ---- 1110 1.01 .... .... 1011 .0.0 .... @vfp_dnm_d VFNMS_dp ---- 1110 1.01 .... .... 1011 .1.0 .... @vfp_dnm_d +VMOV_imm_hp ---- 1110 1.11 .... .... 1001 0000 .... \ + vd=%vd_sp imm=%vmov_imm VMOV_imm_sp ---- 1110 1.11 .... .... 1010 0000 .... \ vd=%vd_sp imm=%vmov_imm VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ MAKE_VFM_TRANS_FNS(hp) MAKE_VFM_TRANS_FNS(sp) MAKE_VFM_TRANS_FNS(dp) +static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) +{ + TCGv_i32 fd; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm)); + neon_store_reg32(fd, a->vd); + tcg_temp_free_i32(fd); + return true; +} + static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) { uint32_t delta_d = 0; -- 2.20.1 Implement fp16 version of VCMP. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-11-peter.maydell@linaro.org --- target/arm/helper.h | 2 ++ target/arm/vfp.decode | 2 ++ target/arm/vfp_helper.c | 15 +++++++------ target/arm/translate-vfp.c.inc | 39 ++++++++++++++++++++++++++++++++++ 4 files changed, 51 insertions(+), 7 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_1(vfp_absd, f64, f64) DEF_HELPER_2(vfp_sqrth, f16, f16, env) DEF_HELPER_2(vfp_sqrts, f32, f32, env) DEF_HELPER_2(vfp_sqrtd, f64, f64, env) +DEF_HELPER_3(vfp_cmph, void, f16, f16, env) DEF_HELPER_3(vfp_cmps, void, f32, f32, env) DEF_HELPER_3(vfp_cmpd, void, f64, f64, env) +DEF_HELPER_3(vfp_cmpeh, void, f16, f16, env) DEF_HELPER_3(vfp_cmpes, void, f32, f32, env) DEF_HELPER_3(vfp_cmped, void, f64, f64, env) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VSQRT_hp ---- 1110 1.11 0001 .... 1001 11.0 .... @vfp_dm_ss VSQRT_sp ---- 1110 1.11 0001 .... 1010 11.0 .... @vfp_dm_ss VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... @vfp_dm_dd +VCMP_hp ---- 1110 1.11 010 z:1 .... 1001 e:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCMP_sp ---- 1110 1.11 010 z:1 .... 1010 e:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCMP_dp ---- 1110 1.11 010 z:1 .... 1011 e:1 1.0 .... \ diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static void softfloat_to_vfp_compare(CPUARMState *env, FloatRelation cmp) } /* XXX: check quiet/signaling case */ -#define DO_VFP_cmp(p, type) \ -void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \ +#define DO_VFP_cmp(P, FLOATTYPE, ARGTYPE, FPST) \ +void VFP_HELPER(cmp, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \ { \ softfloat_to_vfp_compare(env, \ - type ## _compare_quiet(a, b, &env->vfp.fp_status)); \ + FLOATTYPE ## _compare_quiet(a, b, &env->vfp.FPST)); \ } \ -void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \ +void VFP_HELPER(cmpe, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \ { \ softfloat_to_vfp_compare(env, \ - type ## _compare(a, b, &env->vfp.fp_status)); \ + FLOATTYPE ## _compare(a, b, &env->vfp.FPST)); \ } -DO_VFP_cmp(s, float32) -DO_VFP_cmp(d, float64) +DO_VFP_cmp(h, float16, dh_ctype_f16, fp_status_f16) +DO_VFP_cmp(s, float32, float32, fp_status) +DO_VFP_cmp(d, float64, float64, fp_status) #undef DO_VFP_cmp /* Integer to float and float to integer conversions */ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp) DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) +static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) +{ + TCGv_i32 vd, vm; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + /* Vm/M bits must be zero for the Z variant */ + if (a->z && a->vm != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vd = tcg_temp_new_i32(); + vm = tcg_temp_new_i32(); + + neon_load_reg32(vd, a->vd); + if (a->z) { + tcg_gen_movi_i32(vm, 0); + } else { + neon_load_reg32(vm, a->vm); + } + + if (a->e) { + gen_helper_vfp_cmpeh(vd, vm, cpu_env); + } else { + gen_helper_vfp_cmph(vd, vm, cpu_env); + } + + tcg_temp_free_i32(vd); + tcg_temp_free_i32(vm); + + return true; +} + static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) { TCGv_i32 vd, vm; -- 2.20.1 Implement the fp16 versions of the VFP VLDR/VSTR (immediate). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-12-peter.maydell@linaro.org --- target/arm/vfp.decode | 3 +-- target/arm/translate-vfp.c.inc | 35 ++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 2 deletions(-) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VMOV_single ---- 1110 000 l:1 .... rt:4 1010 . 001 0000 vn=%vn_sp VMOV_64_sp ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 .... vm=%vm_sp VMOV_64_dp ---- 1100 010 op:1 rt2:4 rt:4 1011 00.1 .... vm=%vm_dp -# Note that the half-precision variants of VLDR and VSTR are -# not part of this decodetree at all because they have bits [9:8] == 0b01 +VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8 vd=%vd_sp VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8 vd=%vd_sp VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8 vd=%vd_dp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) return true; } +static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) +{ + uint32_t offset; + TCGv_i32 addr, tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* imm8 field is offset/2 for fp16, unlike fp32 and fp64 */ + offset = a->imm << 1; + if (!a->u) { + offset = -offset; + } + + /* For thumb, use of PC is UNPREDICTABLE. */ + addr = add_reg_for_lit(s, a->rn, offset); + tmp = tcg_temp_new_i32(); + if (a->l) { + gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + neon_store_reg32(tmp, a->vd); + } else { + neon_load_reg32(tmp, a->vd); + gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(addr); + + return true; +} + static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) { uint32_t offset; -- 2.20.1 Implement the fp16 versions of the VFP VCVT instruction forms which convert between floating point and integer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-13-peter.maydell@linaro.org --- target/arm/vfp.decode | 4 +++ target/arm/translate-vfp.c.inc | 65 ++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VCVT_sp ---- 1110 1.11 0111 .... 1010 11.0 .... @vfp_dm_ds VCVT_dp ---- 1110 1.11 0111 .... 1011 11.0 .... @vfp_dm_sd # VCVT from integer to floating point: Vm always single; Vd depends on size +VCVT_int_hp ---- 1110 1.11 1000 .... 1001 s:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCVT_int_sp ---- 1110 1.11 1000 .... 1010 s:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCVT_int_dp ---- 1110 1.11 1000 .... 1011 s:1 1.0 .... \ @@ -XXX,XX +XXX,XX @@ VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \ vd=%vd_dp imm=%vm_sp opc=%vcvt_fix_op # VCVT float to integer (VCVT and VCVTR): Vd always single; Vd depends on size +VCVT_hp_int ---- 1110 1.11 110 s:1 .... 1001 rz:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCVT_sp_int ---- 1110 1.11 110 s:1 .... 1010 rz:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCVT_dp_int ---- 1110 1.11 110 s:1 .... 1011 rz:1 1.0 .... \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) return true; } +static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) +{ + TCGv_i32 vm; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vm = tcg_temp_new_i32(); + neon_load_reg32(vm, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + if (a->s) { + /* i32 -> f16 */ + gen_helper_vfp_sitoh(vm, vm, fpst); + } else { + /* u32 -> f16 */ + gen_helper_vfp_uitoh(vm, vm, fpst); + } + neon_store_reg32(vm, a->vd); + tcg_temp_free_i32(vm); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) { TCGv_i32 vm; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) return true; } +static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) +{ + TCGv_i32 vm; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = fpstatus_ptr(FPST_FPCR_F16); + vm = tcg_temp_new_i32(); + neon_load_reg32(vm, a->vm); + + if (a->s) { + if (a->rz) { + gen_helper_vfp_tosizh(vm, vm, fpst); + } else { + gen_helper_vfp_tosih(vm, vm, fpst); + } + } else { + if (a->rz) { + gen_helper_vfp_touizh(vm, vm, fpst); + } else { + gen_helper_vfp_touih(vm, vm, fpst); + } + } + neon_store_reg32(vm, a->vd); + tcg_temp_free_i32(vm); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) { TCGv_i32 vm; -- 2.20.1 Currently the VFP_CONV_FIX macros take a single fsz argument for the size of the float type, which is used both to select the name of the functions to call (eg float32_is_any_nan()) and also for the type to use for the float inputs and outputs (eg float32). Separate these into fsz and ftype arguments, so that we can use them for fp16, which uses 'float16' in the function names but is still passing inputs and outputs in a 32-bit sized type. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-14-peter.maydell@linaro.org --- target/arm/vfp_helper.c | 46 ++++++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) } /* VFP3 fixed point conversion. */ -#define VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ -float##fsz HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \ +#define VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ +ftype HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \ void *fpstp) \ { return itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); } -#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, ROUND, suff) \ -uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \ +#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, ROUND, suff) \ +uint##isz##_t HELPER(vfp_to##name##p##suff)(ftype x, uint32_t shift, \ void *fpst) \ { \ if (unlikely(float##fsz##_is_any_nan(x))) { \ @@ -XXX,XX +XXX,XX @@ uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \ return float##fsz##_to_##itype##_scalbn(x, ROUND, shift, fpst); \ } -#define VFP_CONV_FIX(name, p, fsz, isz, itype) \ -VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ +#define VFP_CONV_FIX(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \ float_round_to_zero, _round_to_zero) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \ get_float_rounding_mode(fpst), ) -#define VFP_CONV_FIX_A64(name, p, fsz, isz, itype) \ -VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ +#define VFP_CONV_FIX_A64(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \ get_float_rounding_mode(fpst), ) -VFP_CONV_FIX(sh, d, 64, 64, int16) -VFP_CONV_FIX(sl, d, 64, 64, int32) -VFP_CONV_FIX_A64(sq, d, 64, 64, int64) -VFP_CONV_FIX(uh, d, 64, 64, uint16) -VFP_CONV_FIX(ul, d, 64, 64, uint32) -VFP_CONV_FIX_A64(uq, d, 64, 64, uint64) -VFP_CONV_FIX(sh, s, 32, 32, int16) -VFP_CONV_FIX(sl, s, 32, 32, int32) -VFP_CONV_FIX_A64(sq, s, 32, 64, int64) -VFP_CONV_FIX(uh, s, 32, 32, uint16) -VFP_CONV_FIX(ul, s, 32, 32, uint32) -VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) +VFP_CONV_FIX(sh, d, 64, float64, 64, int16) +VFP_CONV_FIX(sl, d, 64, float64, 64, int32) +VFP_CONV_FIX_A64(sq, d, 64, float64, 64, int64) +VFP_CONV_FIX(uh, d, 64, float64, 64, uint16) +VFP_CONV_FIX(ul, d, 64, float64, 64, uint32) +VFP_CONV_FIX_A64(uq, d, 64, float64, 64, uint64) +VFP_CONV_FIX(sh, s, 32, float32, 32, int16) +VFP_CONV_FIX(sl, s, 32, float32, 32, int32) +VFP_CONV_FIX_A64(sq, s, 32, float32, 64, int64) +VFP_CONV_FIX(uh, s, 32, float32, 32, uint16) +VFP_CONV_FIX(ul, s, 32, float32, 32, uint32) +VFP_CONV_FIX_A64(uq, s, 32, float32, 64, uint64) #undef VFP_CONV_FIX #undef VFP_CONV_FIX_FLOAT -- 2.20.1 Now the VFP_CONV_FIX macros can handle fp16's distinction between the width of the operation and the width of the type used to pass operands, use the macros rather than the open-coded functions. This creates an extra six helper functions, all of which we are going to need for the AArch32 VFP fp16 instructions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-15-peter.maydell@linaro.org --- target/arm/helper.h | 6 +++ target/arm/vfp_helper.c | 86 +++-------------------------------------- 2 files changed, 12 insertions(+), 80 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_2(vfp_tosizh, s32, f16, ptr) DEF_HELPER_2(vfp_tosizs, s32, f32, ptr) DEF_HELPER_2(vfp_tosizd, s32, f64, ptr) +DEF_HELPER_3(vfp_toshh_round_to_zero, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_toslh_round_to_zero, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_touhh_round_to_zero, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_toulh_round_to_zero, i32, f16, i32, ptr) DEF_HELPER_3(vfp_toshs_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_tosls_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_touhs_round_to_zero, i32, f32, i32, ptr) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_sqtod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_uhtod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr) +DEF_HELPER_3(vfp_shtoh, f16, i32, i32, ptr) +DEF_HELPER_3(vfp_uhtoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ VFP_CONV_FIX_A64(sq, s, 32, float32, 64, int64) VFP_CONV_FIX(uh, s, 32, float32, 32, uint16) VFP_CONV_FIX(ul, s, 32, float32, 32, uint32) VFP_CONV_FIX_A64(uq, s, 32, float32, 64, uint64) +VFP_CONV_FIX(sh, h, 16, dh_ctype_f16, 32, int16) +VFP_CONV_FIX(sl, h, 16, dh_ctype_f16, 32, int32) +VFP_CONV_FIX_A64(sq, h, 16, dh_ctype_f16, 64, int64) +VFP_CONV_FIX(uh, h, 16, dh_ctype_f16, 32, uint16) +VFP_CONV_FIX(ul, h, 16, dh_ctype_f16, 32, uint32) +VFP_CONV_FIX_A64(uq, h, 16, dh_ctype_f16, 64, uint64) #undef VFP_CONV_FIX #undef VFP_CONV_FIX_FLOAT #undef VFP_CONV_FLOAT_FIX_ROUND #undef VFP_CONV_FIX_A64 -uint32_t HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst) -{ - return int32_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) -{ - return uint32_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) -{ - return int64_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) -{ - return uint64_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_toshh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int16_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint32_t HELPER(vfp_touhh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_uint16_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint32_t HELPER(vfp_toslh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int32_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint32_t HELPER(vfp_toulh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_uint32_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint64_t HELPER(vfp_tosqh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int64_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint64_t HELPER(vfp_touqh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_uint64_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - /* Set the current fp rounding mode and return the old one. * The argument is a softfloat float_round_ value. */ -- 2.20.1 Implement the fp16 versions of the VFP VCVT instruction forms which convert between floating point and fixed-point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-16-peter.maydell@linaro.org --- target/arm/vfp.decode | 2 ++ target/arm/translate-vfp.c.inc | 59 ++++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VJCVT ---- 1110 1.11 1001 .... 1011 11.0 .... @vfp_dm_sd # We assemble bits 18 (op), 16 (u) and 7 (sx) into a single opc field # for the convenience of the trans_VCVT_fix functions. %vcvt_fix_op 18:1 16:1 7:1 +VCVT_fix_hp ---- 1110 1.11 1.1. .... 1001 .1.0 .... \ + vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op VCVT_fix_sp ---- 1110 1.11 1.1. .... 1010 .1.0 .... \ vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) return true; } +static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) +{ + TCGv_i32 vd, shift; + TCGv_ptr fpst; + int frac_bits; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); + + vd = tcg_temp_new_i32(); + neon_load_reg32(vd, a->vd); + + fpst = fpstatus_ptr(FPST_FPCR_F16); + shift = tcg_const_i32(frac_bits); + + /* Switch on op:U:sx bits */ + switch (a->opc) { + case 0: + gen_helper_vfp_shtoh(vd, vd, shift, fpst); + break; + case 1: + gen_helper_vfp_sltoh(vd, vd, shift, fpst); + break; + case 2: + gen_helper_vfp_uhtoh(vd, vd, shift, fpst); + break; + case 3: + gen_helper_vfp_ultoh(vd, vd, shift, fpst); + break; + case 4: + gen_helper_vfp_toshh_round_to_zero(vd, vd, shift, fpst); + break; + case 5: + gen_helper_vfp_toslh_round_to_zero(vd, vd, shift, fpst); + break; + case 6: + gen_helper_vfp_touhh_round_to_zero(vd, vd, shift, fpst); + break; + case 7: + gen_helper_vfp_toulh_round_to_zero(vd, vd, shift, fpst); + break; + default: + g_assert_not_reached(); + } + + neon_store_reg32(vd, a->vd); + tcg_temp_free_i32(vd); + tcg_temp_free_i32(shift); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) { TCGv_i32 vd, shift; -- 2.20.1 Implement the fp16 versions of the VFP VCVT instruction forms which convert between floating point and integer with a specified rounding mode. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-17-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 6 ++++-- target/arm/translate-vfp.c.inc | 32 ++++++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 10 deletions(-) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VRINT 1111 1110 1.11 10 rm:2 .... 1011 01.0 .... \ vm=%vm_dp vd=%vd_dp dp=1 # VCVT float to int with specified rounding mode; Vd is always single-precision +VCVT 1111 1110 1.11 11 rm:2 .... 1001 op:1 1.0 .... \ + vm=%vm_sp vd=%vd_sp sz=1 VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ - vm=%vm_sp vd=%vd_sp dp=0 + vm=%vm_sp vd=%vd_sp sz=2 VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ - vm=%vm_dp vd=%vd_sp dp=1 + vm=%vm_dp vd=%vd_sp sz=3 diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) static bool trans_VCVT(DisasContext *s, arg_VCVT *a) { uint32_t rd, rm; - bool dp = a->dp; + int sz = a->sz; TCGv_ptr fpst; TCGv_i32 tcg_rmode, tcg_shift; int rounding = fp_decode_rm[a->rm]; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + + if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { + if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + if (sz == 1) { + fpst = fpstatus_ptr(FPST_FPCR_F16); + } else { + fpst = fpstatus_ptr(FPST_FPCR); + } tcg_shift = tcg_const_i32(0); tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - if (dp) { + if (sz == 3) { TCGv_i64 tcg_double, tcg_res; TCGv_i32 tcg_tmp; tcg_double = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) tcg_single = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); neon_load_reg32(tcg_single, rm); - if (is_signed) { - gen_helper_vfp_tosls(tcg_res, tcg_single, tcg_shift, fpst); + if (sz == 1) { + if (is_signed) { + gen_helper_vfp_toslh(tcg_res, tcg_single, tcg_shift, fpst); + } else { + gen_helper_vfp_toulh(tcg_res, tcg_single, tcg_shift, fpst); + } } else { - gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); + if (is_signed) { + gen_helper_vfp_tosls(tcg_res, tcg_single, tcg_shift, fpst); + } else { + gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); + } } neon_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_res); -- 2.20.1 Implement the fp16 versions of the VFP VSEL instruction. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-18-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 6 ++++-- target/arm/translate-vfp.c.inc | 16 ++++++++++++---- 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ @vfp_dnm_s ................................ vm=%vm_sp vn=%vn_sp vd=%vd_sp @vfp_dnm_d ................................ vm=%vm_dp vn=%vn_dp vd=%vd_dp +VSEL 1111 1110 0. cc:2 .... .... 1001 .0.0 .... \ + vm=%vm_sp vn=%vn_sp vd=%vd_sp sz=1 VSEL 1111 1110 0. cc:2 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp dp=0 + vm=%vm_sp vn=%vn_sp vd=%vd_sp sz=2 VSEL 1111 1110 0. cc:2 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1 + vm=%vm_dp vn=%vn_dp vd=%vd_dp sz=3 VMAXNM_hp 1111 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s VMINNM_hp 1111 1110 1.00 .... .... 1001 .1.0 .... @vfp_dnm_s diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool vfp_access_check(DisasContext *s) static bool trans_VSEL(DisasContext *s, arg_VSEL *a) { uint32_t rd, rn, rm; - bool dp = a->dp; + int sz = a->sz; if (!dc_isar_feature(aa32_vsel, s)) { return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + + if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && + if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vn | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) return true; } - if (dp) { + if (sz == 3) { TCGv_i64 frn, frm, dest; TCGv_i64 tmp, zero, zf, nf, vf; @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i32(tmp); break; } + /* For fp16 the top half is always zeroes */ + if (sz == 1) { + tcg_gen_andi_i32(dest, dest, 0xffff); + } neon_store_reg32(dest, rd); tcg_temp_free_i32(frn); tcg_temp_free_i32(frm); -- 2.20.1 Implement the fp16 version of the VFP VRINT* insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-19-peter.maydell@linaro.org --- target/arm/helper.h | 2 + target/arm/vfp-uncond.decode | 6 ++- target/arm/vfp.decode | 3 ++ target/arm/vfp_helper.c | 21 ++++++++ target/arm/translate-vfp.c.inc | 98 +++++++++++++++++++++++++++++++--- 5 files changed, 122 insertions(+), 8 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(shr_cc, i32, env, i32, i32) DEF_HELPER_3(sar_cc, i32, env, i32, i32) DEF_HELPER_3(ror_cc, i32, env, i32, i32) +DEF_HELPER_FLAGS_2(rinth_exact, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(rints_exact, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_2(rinth, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, ptr) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @vfp_dnm_s VMAXNM_dp 1111 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d VMINNM_dp 1111 1110 1.00 .... .... 1011 .1.0 .... @vfp_dnm_d +VRINT 1111 1110 1.11 10 rm:2 .... 1001 01.0 .... \ + vm=%vm_sp vd=%vd_sp sz=1 VRINT 1111 1110 1.11 10 rm:2 .... 1010 01.0 .... \ - vm=%vm_sp vd=%vd_sp dp=0 + vm=%vm_sp vd=%vd_sp sz=2 VRINT 1111 1110 1.11 10 rm:2 .... 1011 01.0 .... \ - vm=%vm_dp vd=%vd_dp dp=1 + vm=%vm_dp vd=%vd_dp sz=3 # VCVT float to int with specified rounding mode; Vd is always single-precision VCVT 1111 1110 1.11 11 rm:2 .... 1001 op:1 1.0 .... \ diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VCVT_f16_f32 ---- 1110 1.11 0011 .... 1010 t:1 1.0 .... \ VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \ vd=%vd_sp vm=%vm_dp +VRINTR_hp ---- 1110 1.11 0110 .... 1001 01.0 .... @vfp_dm_ss VRINTR_sp ---- 1110 1.11 0110 .... 1010 01.0 .... @vfp_dm_ss VRINTR_dp ---- 1110 1.11 0110 .... 1011 01.0 .... @vfp_dm_dd +VRINTZ_hp ---- 1110 1.11 0110 .... 1001 11.0 .... @vfp_dm_ss VRINTZ_sp ---- 1110 1.11 0110 .... 1010 11.0 .... @vfp_dm_ss VRINTZ_dp ---- 1110 1.11 0110 .... 1011 11.0 .... @vfp_dm_dd +VRINTX_hp ---- 1110 1.11 0111 .... 1001 01.0 .... @vfp_dm_ss VRINTX_sp ---- 1110 1.11 0111 .... 1010 01.0 .... @vfp_dm_ss VRINTX_dp ---- 1110 1.11 0111 .... 1011 01.0 .... @vfp_dm_dd diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp) } /* ARMv8 round to integral */ +dh_ctype_f16 HELPER(rinth_exact)(dh_ctype_f16 x, void *fp_status) +{ + return float16_round_to_int(x, fp_status); +} + float32 HELPER(rints_exact)(float32 x, void *fp_status) { return float32_round_to_int(x, fp_status); @@ -XXX,XX +XXX,XX @@ float64 HELPER(rintd_exact)(float64 x, void *fp_status) return float64_round_to_int(x, fp_status); } +dh_ctype_f16 HELPER(rinth)(dh_ctype_f16 x, void *fp_status) +{ + int old_flags = get_float_exception_flags(fp_status), new_flags; + float16 ret; + + ret = float16_round_to_int(x, fp_status); + + /* Suppress any inexact exceptions the conversion produced */ + if (!(old_flags & float_flag_inexact)) { + new_flags = get_float_exception_flags(fp_status); + set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status); + } + + return ret; +} + float32 HELPER(rints)(float32 x, void *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static const uint8_t fp_decode_rm[] = { static bool trans_VRINT(DisasContext *s, arg_VRINT *a) { uint32_t rd, rm; - bool dp = a->dp; + int sz = a->sz; TCGv_ptr fpst; TCGv_i32 tcg_rmode; int rounding = fp_decode_rm[a->rm]; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + + if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && + if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + if (sz == 1) { + fpst = fpstatus_ptr(FPST_FPCR_F16); + } else { + fpst = fpstatus_ptr(FPST_FPCR); + } tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - if (dp) { + if (sz == 3) { TCGv_i64 tcg_op; TCGv_i64 tcg_res; tcg_op = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) tcg_op = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); neon_load_reg32(tcg_op, rm); - gen_helper_rints(tcg_res, tcg_op, fpst); + if (sz == 1) { + gen_helper_rinth(tcg_res, tcg_op, fpst); + } else { + gen_helper_rints(tcg_res, tcg_op, fpst); + } neon_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_op); tcg_temp_free_i32(tcg_res); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) return true; } +static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_rinth(tmp, tmp, fpst); + neon_store_reg32(tmp, a->vd); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) { TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) return true; } +static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + TCGv_i32 tcg_rmode; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + tcg_rmode = tcg_const_i32(float_round_to_zero); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); + gen_helper_rinth(tmp, tmp, fpst); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); + neon_store_reg32(tmp, a->vd); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tcg_rmode); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) { TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) return true; } +static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_rinth_exact(tmp, tmp, fpst); + neon_store_reg32(tmp, a->vd); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a) { TCGv_ptr fpst; -- 2.20.1 The fp16 extension includes a new instruction VINS, which copies the lower 16 bits of a 32-bit source VFP register into the upper 16 bits of the destination. Implement it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-20-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 3 +++ target/arm/translate-vfp.c.inc | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ vm=%vm_sp vd=%vd_sp sz=2 VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ vm=%vm_dp vd=%vd_sp sz=3 + +VINS 1111 1110 1.11 0000 .... 1010 11 . 0 .... \ + vd=%vd_sp vm=%vm_sp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_NOCP(DisasContext *s, arg_NOCP *a) return false; } + +static bool trans_VINS(DisasContext *s, arg_VINS *a) +{ + TCGv_i32 rd, rm; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Insert low half of Vm into high half of Vd */ + rm = tcg_temp_new_i32(); + rd = tcg_temp_new_i32(); + neon_load_reg32(rm, a->vm); + neon_load_reg32(rd, a->vd); + tcg_gen_deposit_i32(rd, rd, rm, 16, 16); + neon_store_reg32(rd, a->vd); + tcg_temp_free_i32(rm); + tcg_temp_free_i32(rd); + return true; +} -- 2.20.1 The fp16 extension includes a new instruction VMOVX, which copies the upper 16 bits of a 32-bit source VFP register into the lower 16 bits of the destination and zeroes the high half of the destination. Implement it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-21-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 3 +++ target/arm/translate-vfp.c.inc | 25 +++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ vm=%vm_dp vd=%vd_sp sz=3 +VMOVX 1111 1110 1.11 0000 .... 1010 01 . 0 .... \ + vd=%vd_sp vm=%vm_sp + VINS 1111 1110 1.11 0000 .... 1010 11 . 0 .... \ vd=%vd_sp vm=%vm_sp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VINS(DisasContext *s, arg_VINS *a) tcg_temp_free_i32(rd); return true; } + +static bool trans_VMOVX(DisasContext *s, arg_VINS *a) +{ + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Set Vd to high half of Vm */ + rm = tcg_temp_new_i32(); + neon_load_reg32(rm, a->vm); + tcg_gen_shri_i32(rm, rm, 16); + neon_store_reg32(rm, a->vd); + tcg_temp_free_i32(rm); + return true; +} -- 2.20.1 Implement the VFP fp16 variant of VMOV that transfers a 16-bit value between a general purpose register and a VFP register. Note that Rt == 15 is UNPREDICTABLE; since this insn is v8 and later only we have no need to replicate the old "updates CPSR.NZCV" behaviour that the singleprec version of this insn does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-22-peter.maydell@linaro.org --- target/arm/vfp.decode | 1 + target/arm/translate-vfp.c.inc | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VDUP ---- 1110 1 b:1 q:1 0 .... rt:4 1011 . 0 e:1 1 0000 \ vn=%vn_dp VMSR_VMRS ---- 1110 111 l:1 reg:4 rt:4 1010 0001 0000 +VMOV_half ---- 1110 000 l:1 .... rt:4 1001 . 001 0000 vn=%vn_sp VMOV_single ---- 1110 000 l:1 .... rt:4 1010 . 001 0000 vn=%vn_sp VMOV_64_sp ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 .... vm=%vm_sp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) return true; } +static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) +{ + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (a->rt == 15) { + /* UNPREDICTABLE; we choose to UNDEF */ + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + if (a->l) { + /* VFP to general purpose register */ + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vn); + tcg_gen_andi_i32(tmp, tmp, 0xffff); + store_reg(s, a->rt, tmp); + } else { + /* general purpose register to VFP */ + tmp = load_reg(s, a->rt); + tcg_gen_andi_i32(tmp, tmp, 0xffff); + neon_store_reg32(tmp, a->vn); + tcg_temp_free_i32(tmp); + } + + return true; +} + static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) { TCGv_i32 tmp; -- 2.20.1 Implement FP16 support for the Neon insns which use the DO_3S_FP_GVEC macro: VADD, VSUB, VABD, VMUL. For VABD this requires us to implement a new gvec_fabd_h helper using the machinery we have already for the other helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-24-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/vec_helper.c | 6 ++++++ target/arm/translate-neon.c.inc | 36 +++++++++++++++++---------------- 3 files changed, 26 insertions(+), 17 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_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static float64 float64_ftsmul(float64 op1, uint64_t op2, float_status *stat) return result; } +static float16 float16_abd(float16 op1, float16 op2, float_status *stat) +{ + return float16_abs(float16_sub(op1, op2, stat)); +} + static float32 float32_abd(float32 op1, float32 op2, float_status *stat) { return float32_abs(float32_sub(op1, op2, stat)); @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_ftsmul_h, float16_ftsmul, float16) DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32) DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) +DO_3OP(gvec_fabd_h, float16_abd, float16) DO_3OP(gvec_fabd_s, float32_abd, float32) #ifdef TARGET_AARCH64 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_3same_fp(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn, return true; } -/* - * For all the functions using this macro, size == 1 means fp16, - * which is an architecture extension we don't implement yet. - */ -#define DO_3S_FP_GVEC(INSN,FUNC) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ +#define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \ + static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ { \ - TCGv_ptr fpst = fpstatus_ptr(FPST_STD); \ + TCGv_ptr fpst = fpstatus_ptr(FPST); \ tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpst, \ oprsz, maxsz, 0, FUNC); \ tcg_temp_free_ptr(fpst); \ - } \ + } + +#define DO_3S_FP_GVEC(INSN,SFUNC,HFUNC) \ + WRAP_FP_GVEC(gen_##INSN##_fp32_3s, FPST_STD, SFUNC) \ + 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) { \ - /* TODO fp16 support */ \ - return false; \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + return do_3same(s, a, gen_##INSN##_fp16_3s); \ } \ - return do_3same(s, a, gen_##INSN##_3s); \ + return do_3same(s, a, gen_##INSN##_fp32_3s); \ } -DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s) -DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s) -DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s) -DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s) +DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s, gen_helper_gvec_fadd_h) +DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_h) +DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_h) +DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) /* * For all the functions using this macro, size == 1 means fp16, -- 2.20.1 We already have gvec helpers for floating point VRECPE and VRQSRTE, so convert the Neon decoder to use them and add the fp16 support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-25-peter.maydell@linaro.org --- target/arm/translate-neon.c.inc | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) 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_2misc_fp(DisasContext *s, arg_2misc *a, return do_2misc_fp(s, a, FUNC); \ } -DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32) -DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32) DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos) DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos) DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs) DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) +#define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \ + static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ + uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static gen_helper_gvec_2_ptr * const fns[4] = { \ + NULL, HFUNC, SFUNC, NULL, \ + }; \ + TCGv_ptr fpst; \ + fpst = fpstatus_ptr(vece == MO_16 ? FPST_STD_F16 : FPST_STD); \ + tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, oprsz, maxsz, 0, \ + fns[vece]); \ + tcg_temp_free_ptr(fpst); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + if (a->size == MO_16) { \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + } else if (a->size != MO_32) { \ + return false; \ + } \ + return do_2misc_vec(s, a, gen_##INSN); \ + } + +DO_2MISC_FP_VEC(VRECPE_F, gen_helper_gvec_frecpe_h, gen_helper_gvec_frecpe_s) +DO_2MISC_FP_VEC(VRSQRTE_F, gen_helper_gvec_frsqrte_h, gen_helper_gvec_frsqrte_s) + static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) { -- 2.20.1 Rewrite Neon VABS/VNEG of floats to use gvec logical AND and XOR, so that we can implement the fp16 version of the insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-26-peter.maydell@linaro.org --- target/arm/translate-neon.c.inc | 34 +++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) 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_VCNT(DisasContext *s, arg_2misc *a) return do_2misc(s, a, gen_helper_neon_cnt_u8); } +static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_andi(vece, rd_ofs, rm_ofs, + vece == MO_16 ? 0x7fff : 0x7fffffff, + oprsz, maxsz); +} + static bool trans_VABS_F(DisasContext *s, arg_2misc *a) { - if (a->size != 2) { + if (a->size == MO_16) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + } else if (a->size != MO_32) { return false; } - /* TODO: FP16 : size == 1 */ - return do_2misc(s, a, gen_helper_vfp_abss); + return do_2misc_vec(s, a, gen_VABS_F); +} + +static void gen_VNEG_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_xori(vece, rd_ofs, rm_ofs, + vece == MO_16 ? 0x8000 : 0x80000000, + oprsz, maxsz); } static bool trans_VNEG_F(DisasContext *s, arg_2misc *a) { - if (a->size != 2) { + if (a->size == MO_16) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + } else if (a->size != MO_32) { return false; } - /* TODO: FP16 : size == 1 */ - return do_2misc(s, a, gen_helper_vfp_negs); + return do_2misc_vec(s, a, gen_VNEG_F); } static bool trans_VRECPE(DisasContext *s, arg_2misc *a) -- 2.20.1 Convert the Neon floating-point vector comparison ops VCEQ, VCGE and VCGT over to using a gvec helper and use this to implement the fp16 case. (We put the float16_ceq() etc functions above the DO_2OP() macro definition because later when we convert the compare-against-zero instructions we'll want their definitions to be visible at that point in the source file.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-27-peter.maydell@linaro.org --- target/arm/helper.h | 9 +++++++ target/arm/vec_helper.c | 44 +++++++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 6 ++--- 3 files changed, 56 insertions(+), 3 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_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, 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 @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +/* + * Floating point comparisons producing an integer result (all 1s or all 0s). + * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do. + * Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires. + */ +static uint16_t float16_ceq(float16 op1, float16 op2, float_status *stat) +{ + return -float16_eq_quiet(op1, op2, stat); +} + +static uint32_t float32_ceq(float32 op1, float32 op2, float_status *stat) +{ + return -float32_eq_quiet(op1, op2, stat); +} + +static uint16_t float16_cge(float16 op1, float16 op2, float_status *stat) +{ + return -float16_le(op2, op1, stat); +} + +static uint32_t float32_cge(float32 op1, float32 op2, float_status *stat) +{ + return -float32_le(op2, op1, stat); +} + +static uint16_t float16_cgt(float16 op1, float16 op2, float_status *stat) +{ + return -float16_lt(op2, op1, stat); +} + +static uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat) +{ + return -float32_lt(op2, op1, stat); +} + #define DO_2OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) DO_3OP(gvec_fabd_h, float16_abd, float16) DO_3OP(gvec_fabd_s, float32_abd, float32) +DO_3OP(gvec_fceq_h, float16_ceq, float16) +DO_3OP(gvec_fceq_s, float32_ceq, float32) + +DO_3OP(gvec_fcge_h, float16_cge, float16) +DO_3OP(gvec_fcge_s, float32_cge, float32) + +DO_3OP(gvec_fcgt_h, float16_cgt, float16) +DO_3OP(gvec_fcgt_s, float32_cgt, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) 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 @@ DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s, gen_helper_gvec_fadd_h) DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_h) DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_h) DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) +DO_3S_FP_GVEC(VCEQ, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_h) +DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h) +DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) /* * For all the functions using this macro, size == 1 means fp16, @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) return do_3same_fp(s, a, FUNC, READS_VD); \ } -DO_3S_FP(VCEQ, gen_helper_neon_ceq_f32, false) -DO_3S_FP(VCGE, gen_helper_neon_cge_f32, false) -DO_3S_FP(VCGT, gen_helper_neon_cgt_f32, false) DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false) DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false) DO_3S_FP(VMAX, gen_helper_vfp_maxs, false) -- 2.20.1 Convert the neon floating-point vector absolute comparison ops VACGE and VACGT over to using a gvec hepler and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-28-peter.maydell@linaro.org --- target/arm/helper.h | 6 ++++++ target/arm/vec_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 4 ++-- 3 files changed, 34 insertions(+), 2 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_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat) return -float32_lt(op2, op1, stat); } +static uint16_t float16_acge(float16 op1, float16 op2, float_status *stat) +{ + return -float16_le(float16_abs(op2), float16_abs(op1), stat); +} + +static uint32_t float32_acge(float32 op1, float32 op2, float_status *stat) +{ + return -float32_le(float32_abs(op2), float32_abs(op1), stat); +} + +static uint16_t float16_acgt(float16 op1, float16 op2, float_status *stat) +{ + return -float16_lt(float16_abs(op2), float16_abs(op1), stat); +} + +static uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat) +{ + return -float32_lt(float32_abs(op2), float32_abs(op1), stat); +} + #define DO_2OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_fcge_s, float32_cge, float32) DO_3OP(gvec_fcgt_h, float16_cgt, float16) DO_3OP(gvec_fcgt_s, float32_cgt, float32) +DO_3OP(gvec_facge_h, float16_acge, float16) +DO_3OP(gvec_facge_s, float32_acge, float32) + +DO_3OP(gvec_facgt_h, float16_acgt, float16) +DO_3OP(gvec_facgt_s, float32_acgt, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) 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 @@ DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) DO_3S_FP_GVEC(VCEQ, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_h) DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h) DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) +DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) +DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) /* * For all the functions using this macro, size == 1 means fp16, @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) return do_3same_fp(s, a, FUNC, READS_VD); \ } -DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false) -DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false) DO_3S_FP(VMAX, gen_helper_vfp_maxs, false) DO_3S_FP(VMIN, gen_helper_vfp_mins, false) -- 2.20.1 Convert the Neon float-point VMAX and VMIN insns over to using a gvec helper, and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-29-peter.maydell@linaro.org --- target/arm/helper.h | 6 ++++++ target/arm/vec_helper.c | 6 ++++++ target/arm/translate-neon.c.inc | 5 ++--- 3 files changed, 14 insertions(+), 3 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_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, 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 @@ DO_3OP(gvec_facge_s, float32_acge, float32) DO_3OP(gvec_facgt_h, float16_acgt, float16) DO_3OP(gvec_facgt_s, float32_acgt, float32) +DO_3OP(gvec_fmax_h, float16_max, float16) +DO_3OP(gvec_fmax_s, float32_max, float32) + +DO_3OP(gvec_fmin_h, float16_min, float16) +DO_3OP(gvec_fmin_s, float32_min, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) 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 @@ DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h) DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) +DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) +DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) /* * For all the functions using this macro, size == 1 means fp16, @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) return do_3same_fp(s, a, FUNC, READS_VD); \ } -DO_3S_FP(VMAX, gen_helper_vfp_maxs, false) -DO_3S_FP(VMIN, gen_helper_vfp_mins, false) - static void gen_VMLA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpstatus) { -- 2.20.1 Convert the Neon floating point VMAXNM and VMINNM insns to using a gvec helper and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-30-peter.maydell@linaro.org --- target/arm/helper.h | 6 ++++++ target/arm/vec_helper.c | 6 ++++++ target/arm/translate-neon.c.inc | 23 +++++++++++++++-------- 3 files changed, 27 insertions(+), 8 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_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, 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 @@ DO_3OP(gvec_fmax_s, float32_max, float32) DO_3OP(gvec_fmin_h, float16_min, float16) DO_3OP(gvec_fmin_s, float32_min, float32) +DO_3OP(gvec_fmaxnum_h, float16_maxnum, float16) +DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32) + +DO_3OP(gvec_fminnum_h, float16_minnum, float16) +DO_3OP(gvec_fminnum_s, float32_minnum, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) 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 void gen_VMLS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, DO_3S_FP(VMLA, gen_VMLA_fp_3s, true) DO_3S_FP(VMLS, gen_VMLS_fp_3s, true) +WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) +WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) +WRAP_FP_GVEC(gen_VMINNM_fp32_3s, FPST_STD, gen_helper_gvec_fminnum_s) +WRAP_FP_GVEC(gen_VMINNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fminnum_h) + static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) { @@ -XXX,XX +XXX,XX @@ static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) } if (a->size != 0) { - /* TODO fp16 support */ - return false; + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + return do_3same(s, a, gen_VMAXNM_fp16_3s); } - - return do_3same_fp(s, a, gen_helper_vfp_maxnums, false); + return do_3same(s, a, gen_VMAXNM_fp32_3s); } static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) } if (a->size != 0) { - /* TODO fp16 support */ - return false; + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + return do_3same(s, a, gen_VMINNM_fp16_3s); } - - return do_3same_fp(s, a, gen_helper_vfp_minnums, false); + return do_3same(s, a, gen_VMINNM_fp32_3s); } WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32) -- 2.20.1 Convert the Neon floating-point VMLA and VMLS insns over to using a gvec helper, and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-31-peter.maydell@linaro.org --- target/arm/helper.h | 6 +++++ target/arm/vec_helper.c | 42 +++++++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 33 ++------------------------ 3 files changed, 50 insertions(+), 31 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_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i3 DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, 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 @@ DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64) #endif #undef DO_3OP +/* Non-fused multiply-add (unlike float16_muladd etc, which are fused) */ +static float16 float16_muladd_nf(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_add(dest, float16_mul(op1, op2, stat), stat); +} + +static float32 float32_muladd_nf(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_add(dest, float32_mul(op1, op2, stat), stat); +} + +static float16 float16_mulsub_nf(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_sub(dest, float16_mul(op1, op2, stat), stat); +} + +static float32 float32_mulsub_nf(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_sub(dest, float32_mul(op1, op2, stat), stat); +} + +#define DO_MULADD(NAME, FUNC, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(d[i], n[i], m[i], stat); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_MULADD(gvec_fmla_h, float16_muladd_nf, float16) +DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32) + +DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16) +DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) + /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. */ 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 @@ DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) - -/* - * For all the functions using this macro, size == 1 means fp16, - * which is an architecture extension we don't implement yet. - */ -#define DO_3S_FP(INSN,FUNC,READS_VD) \ - static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ - { \ - if (a->size != 0) { \ - /* TODO fp16 support */ \ - return false; \ - } \ - return do_3same_fp(s, a, FUNC, READS_VD); \ - } - -static void gen_VMLA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, - TCGv_ptr fpstatus) -{ - gen_helper_vfp_muls(vn, vn, vm, fpstatus); - gen_helper_vfp_adds(vd, vd, vn, fpstatus); -} - -static void gen_VMLS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, - TCGv_ptr fpstatus) -{ - gen_helper_vfp_muls(vn, vn, vm, fpstatus); - gen_helper_vfp_subs(vd, vd, vn, fpstatus); -} - -DO_3S_FP(VMLA, gen_VMLA_fp_3s, true) -DO_3S_FP(VMLS, gen_VMLS_fp_3s, true) +DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) +DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) -- 2.20.1 Convert the neon floating-point vector operations VFMA and VFMS to use a gvec helper, and use this to implement the fp16 case. This is the last use of do_3same_fp() so we can now delete that function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-32-peter.maydell@linaro.org --- target/arm/helper.h | 6 +++ target/arm/vec_helper.c | 33 +++++++++++- target/arm/translate-neon.c.inc | 92 +-------------------------------- 3 files changed, 40 insertions(+), 91 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_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static float32 float32_mulsub_nf(float32 dest, float32 op1, float32 op2, return float32_sub(dest, float32_mul(op1, op2, stat), stat); } -#define DO_MULADD(NAME, FUNC, TYPE) \ +/* Fused versions; these have the semantics Neon VFMA/VFMS want */ +static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_muladd(op1, op2, dest, 0, stat); +} + +static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_muladd(op1, op2, dest, 0, stat); +} + +static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_muladd(float16_chs(op1), op2, dest, 0, stat); +} + +static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_muladd(float32_chs(op1), op2, dest, 0, stat); +} + +#define DO_MULADD(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ intptr_t i, oprsz = simd_oprsz(desc); \ @@ -XXX,XX +XXX,XX @@ DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32) DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16) DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) +DO_MULADD(gvec_vfma_h, float16_muladd_f, float16) +DO_MULADD(gvec_vfma_s, float32_muladd_f, float32) + +DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16) +DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) + /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. */ 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 @@ DO_3SAME_PAIR(VPADD, padd_u) DO_3SAME_VQDMULH(VQDMULH, qdmulh) DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) -static bool do_3same_fp(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn, - bool reads_vd) -{ - /* - * FP operations handled elementwise 32 bits at a time. - * If reads_vd is true then the old value of Vd will be - * loaded before calling the callback function. This is - * used for multiply-accumulate type operations. - */ - TCGv_i32 tmp, tmp2; - 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->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - tmp = neon_load_reg(a->vn, pass); - tmp2 = neon_load_reg(a->vm, pass); - if (reads_vd) { - TCGv_i32 tmp_rd = neon_load_reg(a->vd, pass); - fn(tmp_rd, tmp, tmp2, fpstatus); - neon_store_reg(a->vd, pass, tmp_rd); - tcg_temp_free_i32(tmp); - } else { - fn(tmp, tmp, tmp2, fpstatus); - neon_store_reg(a->vd, pass, tmp); - } - tcg_temp_free_i32(tmp2); - } - tcg_temp_free_ptr(fpstatus); - return true; -} - #define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ uint32_t rn_ofs, uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) +DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) +DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -XXX,XX +XXX,XX @@ static bool trans_VRSQRTS_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VRSQRTS_fp_3s); } -static void gen_VFMA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, - TCGv_ptr fpstatus) -{ - gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus); -} - -static bool trans_VFMA_fp_3s(DisasContext *s, arg_3same *a) -{ - if (!dc_isar_feature(aa32_simdfmac, s)) { - return false; - } - - if (a->size != 0) { - /* TODO fp16 support */ - return false; - } - - return do_3same_fp(s, a, gen_VFMA_fp_3s, true); -} - -static void gen_VFMS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, - TCGv_ptr fpstatus) -{ - gen_helper_vfp_negs(vn, vn); - gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus); -} - -static bool trans_VFMS_fp_3s(DisasContext *s, arg_3same *a) -{ - if (!dc_isar_feature(aa32_simdfmac, s)) { - return false; - } - - if (a->size != 0) { - /* TODO fp16 support */ - return false; - } - - return do_3same_fp(s, a, gen_VFMS_fp_3s, true); -} - static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) { /* FP operations handled pairwise 32 bits at a time */ -- 2.20.1 Convert the neon floating-point vector compare-vs-0 insns VCEQ0, VCGT0, VCLE0, VCGE0 and VCLT0 to use a gvec helper, and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-33-peter.maydell@linaro.org --- target/arm/helper.h | 15 +++++++++++++++ target/arm/vec_helper.c | 25 +++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 33 +++++---------------------------- 3 files changed, 45 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_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) 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 @@ DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) +#define WRAP_CMP0_FWD(FN, CMPOP, TYPE) \ + static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \ + { \ + return TYPE##_##CMPOP(op, TYPE##_zero, stat); \ + } + +#define WRAP_CMP0_REV(FN, CMPOP, TYPE) \ + static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \ + { \ + return TYPE##_##CMPOP(TYPE##_zero, op, stat); \ + } + +#define DO_2OP_CMP0(FN, CMPOP, DIRN) \ + WRAP_CMP0_##DIRN(FN, CMPOP, float16) \ + WRAP_CMP0_##DIRN(FN, CMPOP, float32) \ + DO_2OP(gvec_f##FN##0_h, float16_##FN##0, float16) \ + DO_2OP(gvec_f##FN##0_s, float32_##FN##0, float32) + +DO_2OP_CMP0(cgt, cgt, FWD) +DO_2OP_CMP0(cge, cge, FWD) +DO_2OP_CMP0(ceq, ceq, FWD) +DO_2OP_CMP0(clt, cgt, REV) +DO_2OP_CMP0(cle, cge, REV) + #undef DO_2OP +#undef DO_2OP_CMP0 /* Floating-point trigonometric starting value. * See the ARM ARM pseudocode function FPTrigSMul. 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 @@ DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) DO_2MISC_FP_VEC(VRECPE_F, gen_helper_gvec_frecpe_h, gen_helper_gvec_frecpe_s) DO_2MISC_FP_VEC(VRSQRTE_F, gen_helper_gvec_frsqrte_h, gen_helper_gvec_frsqrte_s) +DO_2MISC_FP_VEC(VCGT0_F, gen_helper_gvec_fcgt0_h, gen_helper_gvec_fcgt0_s) +DO_2MISC_FP_VEC(VCGE0_F, gen_helper_gvec_fcge0_h, gen_helper_gvec_fcge0_s) +DO_2MISC_FP_VEC(VCEQ0_F, gen_helper_gvec_fceq0_h, gen_helper_gvec_fceq0_s) +DO_2MISC_FP_VEC(VCLT0_F, gen_helper_gvec_fclt0_h, gen_helper_gvec_fclt0_s) +DO_2MISC_FP_VEC(VCLE0_F, gen_helper_gvec_fcle0_h, gen_helper_gvec_fcle0_s) static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX(DisasContext *s, arg_2misc *a) return do_2misc_fp(s, a, gen_helper_rints_exact); } -#define WRAP_FP_CMP0_FWD(WRAPNAME, FUNC) \ - static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ - { \ - TCGv_i32 zero = tcg_const_i32(0); \ - FUNC(d, m, zero, fpst); \ - tcg_temp_free_i32(zero); \ - } -#define WRAP_FP_CMP0_REV(WRAPNAME, FUNC) \ - static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ - { \ - TCGv_i32 zero = tcg_const_i32(0); \ - FUNC(d, zero, m, fpst); \ - tcg_temp_free_i32(zero); \ - } - -#define DO_FP_CMP0(INSN, FUNC, REV) \ - WRAP_FP_CMP0_##REV(gen_##INSN, FUNC) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_2misc_fp(s, a, gen_##INSN); \ - } - -DO_FP_CMP0(VCGT0_F, gen_helper_neon_cgt_f32, FWD) -DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD) -DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD) -DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV) -DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV) - static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode) { /* -- 2.20.1 Convert the Neon VRECPS insn to using a gvec helper, and use this to implement the fp16 case. The phrasing of the new float32_recps_nf() is slightly different from the old recps_f32() so that it parallels the f16 version; for f16 we can't assume that flush-to-zero is always enabled. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-34-peter.maydell@linaro.org --- target/arm/helper.h | 4 +++- target/arm/vec_helper.c | 31 +++++++++++++++++++++++++++++++ target/arm/vfp_helper.c | 13 ------------- target/arm/translate-neon.c.inc | 21 +-------------------- 4 files changed, 35 insertions(+), 34 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr) -DEF_HELPER_3(recps_f32, f32, env, f32, f32) DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32) DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i3 DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static float32 float32_abd(float32 op1, float32 op2, float_status *stat) return float32_abs(float32_sub(op1, op2, stat)); } +/* + * Reciprocal step. These are the AArch32 version which uses a + * non-fused multiply-and-subtract. + */ +static float16 float16_recps_nf(float16 op1, float16 op2, float_status *stat) +{ + op1 = float16_squash_input_denormal(op1, stat); + op2 = float16_squash_input_denormal(op2, stat); + + if ((float16_is_infinity(op1) && float16_is_zero(op2)) || + (float16_is_infinity(op2) && float16_is_zero(op1))) { + return float16_two; + } + return float16_sub(float16_two, float16_mul(op1, op2, stat), stat); +} + +static float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat) +{ + op1 = float32_squash_input_denormal(op1, stat); + op2 = float32_squash_input_denormal(op2, stat); + + if ((float32_is_infinity(op1) && float32_is_zero(op2)) || + (float32_is_infinity(op2) && float32_is_zero(op1))) { + return float32_two; + } + return float32_sub(float32_two, float32_mul(op1, op2, stat), stat); +} + #define DO_3OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32) DO_3OP(gvec_fminnum_h, float16_minnum, float16) DO_3OP(gvec_fminnum_s, float32_minnum, float32) +DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16) +DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) return r; } -float32 HELPER(recps_f32)(CPUARMState *env, float32 a, float32 b) -{ - float_status *s = &env->vfp.standard_fp_status; - if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) || - (float32_is_infinity(b) && float32_is_zero_or_denormal(a))) { - if (!(float32_is_zero(a) || float32_is_zero(b))) { - float_raise(float_flag_input_denormal, s); - } - return float32_two; - } - return float32_sub(float32_two, float32_mul(a, b, s), s); -} - float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b) { float_status *s = &env->vfp.standard_fp_status; 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 @@ DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) +DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_3s); } -WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32) - -static void gen_VRECPS_fp_3s(unsigned vece, uint32_t rd_ofs, - uint32_t rn_ofs, uint32_t rm_ofs, - uint32_t oprsz, uint32_t maxsz) -{ - static const GVecGen3 ops = { .fni4 = gen_VRECPS_tramp }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops); -} - -static bool trans_VRECPS_fp_3s(DisasContext *s, arg_3same *a) -{ - if (a->size != 0) { - /* TODO fp16 support */ - return false; - } - - return do_3same(s, a, gen_VRECPS_fp_3s); -} - WRAP_ENV_FN(gen_VRSQRTS_tramp, gen_helper_rsqrts_f32) static void gen_VRSQRTS_fp_3s(unsigned vece, uint32_t rd_ofs, -- 2.20.1 Convert the Neon VRSQRTS insn to using a gvec helper, and use this to implement the fp16 case. As with VRECPS, we adjust the phrasing of the new implementation slightly so that the fp32 version parallels the fp16 one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-35-peter.maydell@linaro.org --- target/arm/helper.h | 4 +++- target/arm/vec_helper.c | 30 ++++++++++++++++++++++++++++++ target/arm/vfp_helper.c | 15 --------------- target/arm/translate-neon.c.inc | 21 +-------------------- 4 files changed, 34 insertions(+), 36 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr) -DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32) DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, ptr) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i3 DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat) return float32_sub(float32_two, float32_mul(op1, op2, stat), stat); } +/* Reciprocal square-root step. AArch32 non-fused semantics. */ +static float16 float16_rsqrts_nf(float16 op1, float16 op2, float_status *stat) +{ + op1 = float16_squash_input_denormal(op1, stat); + op2 = float16_squash_input_denormal(op2, stat); + + if ((float16_is_infinity(op1) && float16_is_zero(op2)) || + (float16_is_infinity(op2) && float16_is_zero(op1))) { + return float16_one_point_five; + } + op1 = float16_sub(float16_three, float16_mul(op1, op2, stat), stat); + return float16_div(op1, float16_two, stat); +} + +static float32 float32_rsqrts_nf(float32 op1, float32 op2, float_status *stat) +{ + op1 = float32_squash_input_denormal(op1, stat); + op2 = float32_squash_input_denormal(op2, stat); + + if ((float32_is_infinity(op1) && float32_is_zero(op2)) || + (float32_is_infinity(op2) && float32_is_zero(op1))) { + return float32_one_point_five; + } + op1 = float32_sub(float32_three, float32_mul(op1, op2, stat), stat); + return float32_div(op1, float32_two, stat); +} + #define DO_3OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_fminnum_s, float32_minnum, float32) DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16) DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32) +DO_3OP(gvec_rsqrts_nf_h, float16_rsqrts_nf, float16) +DO_3OP(gvec_rsqrts_nf_s, float32_rsqrts_nf, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) return r; } -float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b) -{ - float_status *s = &env->vfp.standard_fp_status; - float32 product; - if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) || - (float32_is_infinity(b) && float32_is_zero_or_denormal(a))) { - if (!(float32_is_zero(a) || float32_is_zero(b))) { - float_raise(float_flag_input_denormal, s); - } - return float32_one_point_five; - } - product = float32_mul(a, b, s); - return float32_div(float32_sub(float32_three, product, s), float32_two, s); -} - /* NEON helpers. */ /* Constants 256 and 512 are used in some helpers; we avoid relying on 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 @@ DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) +DO_3S_FP_GVEC(VRSQRTS, gen_helper_gvec_rsqrts_nf_s, gen_helper_gvec_rsqrts_nf_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_3s); } -WRAP_ENV_FN(gen_VRSQRTS_tramp, gen_helper_rsqrts_f32) - -static void gen_VRSQRTS_fp_3s(unsigned vece, uint32_t rd_ofs, - uint32_t rn_ofs, uint32_t rm_ofs, - uint32_t oprsz, uint32_t maxsz) -{ - static const GVecGen3 ops = { .fni4 = gen_VRSQRTS_tramp }; - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops); -} - -static bool trans_VRSQRTS_fp_3s(DisasContext *s, arg_3same *a) -{ - if (a->size != 0) { - /* TODO fp16 support */ - return false; - } - - return do_3same(s, a, gen_VRSQRTS_fp_3s); -} - static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) { /* FP operations handled pairwise 32 bits at a time */ -- 2.20.1 Convert the Neon pairwise fp ops to use a single gvic-style helper to do the full operation instead of one helper call for each 32-bit part. This allows us to use the same framework to implement the fp16. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-36-peter.maydell@linaro.org --- target/arm/helper.h | 7 +++++ target/arm/vec_helper.c | 45 +++++++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 42 ++++++++++++------------------ 3 files changed, 68 insertions(+), 26 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_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 @@ DO_ABA(gvec_uaba_s, uint32_t) DO_ABA(gvec_uaba_d, uint64_t) #undef DO_ABA + +#define DO_NEON_PAIRWISE(NAME, OP) \ + void HELPER(NAME##s)(void *vd, void *vn, void *vm, \ + void *stat, uint32_t oprsz) \ + { \ + float_status *fpst = stat; \ + float32 *d = vd; \ + float32 *n = vn; \ + float32 *m = vm; \ + float32 r0, r1; \ + \ + /* Read all inputs before writing outputs in case vm == vd */ \ + r0 = float32_##OP(n[H4(0)], n[H4(1)], fpst); \ + r1 = float32_##OP(m[H4(0)], m[H4(1)], fpst); \ + \ + d[H4(0)] = r0; \ + d[H4(1)] = r1; \ + } \ + \ + void HELPER(NAME##h)(void *vd, void *vn, void *vm, \ + void *stat, uint32_t oprsz) \ + { \ + float_status *fpst = stat; \ + float16 *d = vd; \ + float16 *n = vn; \ + float16 *m = vm; \ + float16 r0, r1, r2, r3; \ + \ + /* Read all inputs before writing outputs in case vm == vd */ \ + r0 = float16_##OP(n[H2(0)], n[H2(1)], fpst); \ + r1 = float16_##OP(n[H2(2)], n[H2(3)], fpst); \ + r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ + r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ + \ + d[H4(0)] = r0; \ + d[H4(1)] = r1; \ + d[H4(2)] = r2; \ + d[H4(3)] = r3; \ + } + +DO_NEON_PAIRWISE(neon_padd, add) +DO_NEON_PAIRWISE(neon_pmax, max) +DO_NEON_PAIRWISE(neon_pmin, min) + +#undef DO_NEON_PAIRWISE 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_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_3s); } -static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) +static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, + gen_helper_gvec_3_ptr *fn) { - /* FP operations handled pairwise 32 bits at a time */ - TCGv_i32 tmp, tmp2, tmp3; + /* FP pairwise operations */ TCGv_ptr fpstatus; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) assert(a->q == 0); /* enforced by decode patterns */ - /* - * Note that we have to be careful not to clobber the source operands - * in the "vm == vd" case by storing the result of the first pass too - * early. Since Q is 0 there are always just two passes, so instead - * of a complicated loop over each pass we just unroll. - */ - fpstatus = fpstatus_ptr(FPST_STD); - tmp = neon_load_reg(a->vn, 0); - tmp2 = neon_load_reg(a->vn, 1); - fn(tmp, tmp, tmp2, fpstatus); - tcg_temp_free_i32(tmp2); - tmp3 = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); - fn(tmp3, tmp3, tmp2, fpstatus); - tcg_temp_free_i32(tmp2); + fpstatus = fpstatus_ptr(a->size != 0 ? 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), + fpstatus, 8, 8, 0, fn); tcg_temp_free_ptr(fpstatus); - neon_store_reg(a->vd, 0, tmp); - neon_store_reg(a->vd, 1, tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ if (a->size != 0) { \ - /* TODO fp16 support */ \ - return false; \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + return do_3same_fp_pair(s, a, FUNC##h); \ } \ - return do_3same_fp_pair(s, a, FUNC); \ + return do_3same_fp_pair(s, a, FUNC##s); \ } -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) +DO_3S_FP_PAIR(VPADD, gen_helper_neon_padd) +DO_3S_FP_PAIR(VPMAX, gen_helper_neon_pmax) +DO_3S_FP_PAIR(VPMIN, gen_helper_neon_pmin) static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) { -- 2.20.1 Convert the Neon float-integer VCVT insns to gvec, and use this to implement fp16 support for them. Note that unlike the VFP int<->fp16 VCVT insns we converted earlier and which convert to/from a 32-bit integer, these Neon insns convert to/from 16-bit integers. So we can use the existing vfp conversion helpers for the f32<->u32/i32 case but need to provide our own for f16<->u16/i16. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-37-peter.maydell@linaro.org --- target/arm/helper.h | 9 +++++++++ target/arm/vec_helper.c | 29 +++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 15 ++++----------- 3 files changed, 42 insertions(+), 11 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_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat) return -float32_lt(float32_abs(op2), float32_abs(op1), stat); } +static int16_t vfp_tosszh(float16 x, void *fpstp) +{ + float_status *fpst = fpstp; + if (float16_is_any_nan(x)) { + float_raise(float_flag_invalid, fpst); + return 0; + } + return float16_to_int16_round_to_zero(x, fpst); +} + +static uint16_t vfp_touszh(float16 x, void *fpstp) +{ + float_status *fpst = fpstp; + if (float16_is_any_nan(x)) { + float_raise(float_flag_invalid, fpst); + return 0; + } + return float16_to_uint16_round_to_zero(x, fpst); +} + #define DO_2OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) +DO_2OP(gvec_sitos, helper_vfp_sitos, int32_t) +DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t) +DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32) +DO_2OP(gvec_touizs, helper_vfp_touizs, float32) +DO_2OP(gvec_sstoh, int16_to_float16, int16_t) +DO_2OP(gvec_ustoh, uint16_to_float16, uint16_t) +DO_2OP(gvec_tosszh, vfp_tosszh, float16) +DO_2OP(gvec_touszh, vfp_touszh, float16) + #define WRAP_CMP0_FWD(FN, CMPOP, TYPE) \ static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \ { \ 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_2misc_fp(DisasContext *s, arg_2misc *a, return true; } -#define DO_2MISC_FP(INSN, FUNC) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_2misc_fp(s, a, FUNC); \ - } - -DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos) -DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos) -DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs) -DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) - #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_2MISC_FP_VEC(VCGE0_F, gen_helper_gvec_fcge0_h, gen_helper_gvec_fcge0_s) DO_2MISC_FP_VEC(VCEQ0_F, gen_helper_gvec_fceq0_h, gen_helper_gvec_fceq0_s) DO_2MISC_FP_VEC(VCLT0_F, gen_helper_gvec_fclt0_h, gen_helper_gvec_fclt0_s) DO_2MISC_FP_VEC(VCLE0_F, gen_helper_gvec_fcle0_h, gen_helper_gvec_fcle0_s) +DO_2MISC_FP_VEC(VCVT_FS, gen_helper_gvec_sstoh, gen_helper_gvec_sitos) +DO_2MISC_FP_VEC(VCVT_FU, gen_helper_gvec_ustoh, gen_helper_gvec_uitos) +DO_2MISC_FP_VEC(VCVT_SF, gen_helper_gvec_tosszh, gen_helper_gvec_tosizs) +DO_2MISC_FP_VEC(VCVT_UF, gen_helper_gvec_touszh, gen_helper_gvec_touizs) static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { -- 2.20.1 Convert the Neon VCVT float<->fixed-point insns to a gvec style, in preparation for adding fp16 support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-38-peter.maydell@linaro.org --- target/arm/helper.h | 5 +++++ target/arm/vec_helper.c | 20 +++++++++++++++++++ target/arm/translate-neon.c.inc | 35 +++++++++++++++++---------------- 3 files changed, 43 insertions(+), 17 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(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 @@ DO_NEON_PAIRWISE(neon_pmax, max) DO_NEON_PAIRWISE(neon_pmin, min) #undef DO_NEON_PAIRWISE + +#define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ + void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + { \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + float_status *fpst = stat; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], shift, fpst); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ + } + +DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t) + +#undef DO_VCVT_FIXED 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_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) } static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, - NeonGenTwoSingleOpFn *fn) + gen_helper_gvec_2_ptr *fn) { /* FP operations in 2-reg-and-shift group */ - TCGv_i32 tmp, shiftv; - TCGv_ptr fpstatus; - int pass; + 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); + TCGv_ptr fpst; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; } + if (a->size != 0) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + 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)) { @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, return true; } - fpstatus = fpstatus_ptr(FPST_STD); - 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); + fpst = fpstatus_ptr(a->size ? 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; } @@ -XXX,XX +XXX,XX @@ static bool do_fp_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) +DO_FP_2SH(VCVT_SF, gen_helper_gvec_vcvt_sf) +DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf) +DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs) +DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu) static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) { -- 2.20.1 Implement fp16 for the Neon VCVT insns which convert between float and fixed-point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-39-peter.maydell@linaro.org --- target/arm/helper.h | 5 +++++ target/arm/neon-dp.decode | 8 +++++++- target/arm/vec_helper.c | 4 ++++ target/arm/translate-neon.c.inc | 5 +++++ 4 files changed, 21 insertions(+), 1 deletion(-) 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(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, 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 @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp # 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_vcvt_f16 .... ... . . . 11 .... .... .... . q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s @@ -XXX,XX +XXX,XX @@ 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_SH_2sh 1111 001 0 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16 +VCVT_UH_2sh 1111 001 1 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16 +VCVT_HS_2sh 1111 001 0 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16 +VCVT_HU_2sh 1111 001 1 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16 + 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 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 @@ DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED 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 @@ DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf) DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs) DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu) +DO_FP_2SH(VCVT_SH, gen_helper_gvec_vcvt_sh) +DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) +DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) +DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) + static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) { /* -- 2.20.1 Convert the Neon VCVT with-specified-rounding-mode instructions to gvec, and use this to implement fp16 support for them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-40-peter.maydell@linaro.org --- target/arm/helper.h | 5 ++ target/arm/vec_helper.c | 23 +++++++ target/arm/translate-neon.c.inc | 105 ++++++++++++-------------------- 3 files changed, 66 insertions(+), 67 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(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 @@ DO_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t) DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED + +#define DO_VCVT_RMODE(NAME, FUNC, TYPE) \ + void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + { \ + float_status *fpst = stat; \ + intptr_t i, oprsz = simd_oprsz(desc); \ + uint32_t rmode = simd_data(desc); \ + uint32_t prev_rmode = get_float_rounding_mode(fpst); \ + TYPE *d = vd, *n = vn; \ + set_float_rounding_mode(rmode, fpst); \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], 0, fpst); \ + } \ + set_float_rounding_mode(prev_rmode, fpst); \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ + } + +DO_VCVT_RMODE(gvec_vcvt_rm_ss, helper_vfp_tosls, uint32_t) +DO_VCVT_RMODE(gvec_vcvt_rm_us, helper_vfp_touls, uint32_t) +DO_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t) +DO_VCVT_RMODE(gvec_vcvt_rm_uh, helper_vfp_touhh, uint16_t) + +#undef DO_VCVT_RMODE 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 @@ DO_VRINT(VRINTZ, FPROUNDING_ZERO) DO_VRINT(VRINTM, FPROUNDING_NEGINF) DO_VRINT(VRINTP, FPROUNDING_POSINF) -static bool do_vcvt(DisasContext *s, arg_2misc *a, int rmode, bool is_signed) -{ - /* - * Handle a VCVT* operation by iterating 32 bits at a time, - * with a specified rounding mode in operation. - */ - int pass; - TCGv_ptr fpst; - TCGv_i32 tcg_rmode, tcg_shift; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !arm_dc_feature(s, ARM_FEATURE_V8)) { - return false; +#define DO_VEC_RMODE(INSN, RMODE, OP) \ + static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ + uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static gen_helper_gvec_2_ptr * const fns[4] = { \ + NULL, \ + gen_helper_gvec_##OP##h, \ + gen_helper_gvec_##OP##s, \ + NULL, \ + }; \ + TCGv_ptr fpst; \ + fpst = fpstatus_ptr(vece == 1 ? FPST_STD_F16 : FPST_STD); \ + tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, oprsz, maxsz, \ + arm_rmode_to_sf(RMODE), fns[vece]); \ + tcg_temp_free_ptr(fpst); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + if (!arm_dc_feature(s, ARM_FEATURE_V8)) { \ + return false; \ + } \ + if (a->size == MO_16) { \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + } else if (a->size != MO_32) { \ + return false; \ + } \ + return do_2misc_vec(s, a, gen_##INSN); \ } - /* 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->size != 2) { - /* TODO: FP16 will be the size == 1 case */ - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - fpst = fpstatus_ptr(FPST_STD); - tcg_shift = tcg_const_i32(0); - tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); - if (is_signed) { - gen_helper_vfp_tosls(tmp, tmp, tcg_shift, fpst); - } else { - gen_helper_vfp_touls(tmp, tmp, tcg_shift, fpst); - } - neon_store_reg(a->vd, pass, tmp); - } - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - tcg_temp_free_i32(tcg_rmode); - tcg_temp_free_i32(tcg_shift); - tcg_temp_free_ptr(fpst); - - return true; -} - -#define DO_VCVT(INSN, RMODE, SIGNED) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_vcvt(s, a, RMODE, SIGNED); \ - } - -DO_VCVT(VCVTAU, FPROUNDING_TIEAWAY, false) -DO_VCVT(VCVTAS, FPROUNDING_TIEAWAY, true) -DO_VCVT(VCVTNU, FPROUNDING_TIEEVEN, false) -DO_VCVT(VCVTNS, FPROUNDING_TIEEVEN, true) -DO_VCVT(VCVTPU, FPROUNDING_POSINF, false) -DO_VCVT(VCVTPS, FPROUNDING_POSINF, true) -DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false) -DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true) +DO_VEC_RMODE(VCVTAU, FPROUNDING_TIEAWAY, vcvt_rm_u) +DO_VEC_RMODE(VCVTAS, FPROUNDING_TIEAWAY, vcvt_rm_s) +DO_VEC_RMODE(VCVTNU, FPROUNDING_TIEEVEN, vcvt_rm_u) +DO_VEC_RMODE(VCVTNS, FPROUNDING_TIEEVEN, vcvt_rm_s) +DO_VEC_RMODE(VCVTPU, FPROUNDING_POSINF, vcvt_rm_u) +DO_VEC_RMODE(VCVTPS, FPROUNDING_POSINF, vcvt_rm_s) +DO_VEC_RMODE(VCVTMU, FPROUNDING_NEGINF, vcvt_rm_u) +DO_VEC_RMODE(VCVTMS, FPROUNDING_NEGINF, vcvt_rm_s) static bool trans_VSWP(DisasContext *s, arg_2misc *a) { -- 2.20.1 Convert the Neon VRINT-with-specified-rounding-mode insns to gvec, and use this to implement the fp16 versions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-41-peter.maydell@linaro.org --- target/arm/helper.h | 4 +- target/arm/vec_helper.c | 21 +++++++++++ target/arm/vfp_helper.c | 17 --------- target/arm/translate-neon.c.inc | 67 +++------------------------------ 4 files changed, 30 insertions(+), 79 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr) DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr) DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) -DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f32, TCG_CALL_NO_RWG, f32, f16, ptr, i32) DEF_HELPER_FLAGS_3(vfp_fcvt_f32_to_f16, TCG_CALL_NO_RWG, f16, f32, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 @@ DO_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t) DO_VCVT_RMODE(gvec_vcvt_rm_uh, helper_vfp_touhh, uint16_t) #undef DO_VCVT_RMODE + +#define DO_VRINT_RMODE(NAME, FUNC, TYPE) \ + void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + { \ + float_status *fpst = stat; \ + intptr_t i, oprsz = simd_oprsz(desc); \ + uint32_t rmode = simd_data(desc); \ + uint32_t prev_rmode = get_float_rounding_mode(fpst); \ + TYPE *d = vd, *n = vn; \ + set_float_rounding_mode(rmode, fpst); \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], fpst); \ + } \ + set_float_rounding_mode(prev_rmode, fpst); \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ + } + +DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t) +DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t) + +#undef DO_VRINT_RMODE diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp) return prev_rmode; } -/* Set the current fp rounding mode in the standard fp status and return - * the old one. This is for NEON instructions that need to change the - * rounding mode but wish to use the standard FPSCR values for everything - * else. Always set the rounding mode back to the correct value after - * modifying it. - * The argument is a softfloat float_round_ value. - */ -uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env) -{ - float_status *fp_status = &env->vfp.standard_fp_status; - - uint32_t prev_rmode = get_float_rounding_mode(fp_status); - set_float_rounding_mode(rmode, fp_status); - - return prev_rmode; -} - /* Half precision conversions. */ float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) { 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_VRINTX(DisasContext *s, arg_2misc *a) return do_2misc_fp(s, a, gen_helper_rints_exact); } -static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode) -{ - /* - * Handle a VRINT* operation by iterating 32 bits at a time, - * with a specified rounding mode in operation. - */ - int pass; - TCGv_ptr fpst; - TCGv_i32 tcg_rmode; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !arm_dc_feature(s, ARM_FEATURE_V8)) { - 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->size != 2) { - /* TODO: FP16 will be the size == 1 case */ - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - fpst = fpstatus_ptr(FPST_STD); - tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); - gen_helper_rints(tmp, tmp, fpst); - neon_store_reg(a->vd, pass, tmp); - } - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - tcg_temp_free_i32(tcg_rmode); - tcg_temp_free_ptr(fpst); - - return true; -} - -#define DO_VRINT(INSN, RMODE) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_vrint(s, a, RMODE); \ - } - -DO_VRINT(VRINTN, FPROUNDING_TIEEVEN) -DO_VRINT(VRINTA, FPROUNDING_TIEAWAY) -DO_VRINT(VRINTZ, FPROUNDING_ZERO) -DO_VRINT(VRINTM, FPROUNDING_NEGINF) -DO_VRINT(VRINTP, FPROUNDING_POSINF) - #define DO_VEC_RMODE(INSN, RMODE, OP) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_VEC_RMODE(VCVTPS, FPROUNDING_POSINF, vcvt_rm_s) DO_VEC_RMODE(VCVTMU, FPROUNDING_NEGINF, vcvt_rm_u) DO_VEC_RMODE(VCVTMS, FPROUNDING_NEGINF, vcvt_rm_s) +DO_VEC_RMODE(VRINTN, FPROUNDING_TIEEVEN, vrint_rm_) +DO_VEC_RMODE(VRINTA, FPROUNDING_TIEAWAY, vrint_rm_) +DO_VEC_RMODE(VRINTZ, FPROUNDING_ZERO, vrint_rm_) +DO_VEC_RMODE(VRINTM, FPROUNDING_NEGINF, vrint_rm_) +DO_VEC_RMODE(VRINTP, FPROUNDING_POSINF, vrint_rm_) + static bool trans_VSWP(DisasContext *s, arg_2misc *a) { TCGv_i64 rm, rd; -- 2.20.1 Convert the Neon VRINTX insn to use gvec, and use this to implement fp16 support for it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-42-peter.maydell@linaro.org --- target/arm/helper.h | 3 +++ target/arm/vec_helper.c | 3 +++ target/arm/translate-neon.c.inc | 45 +++------------------------------ 3 files changed, 9 insertions(+), 42 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(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 @@ DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) +DO_2OP(gvec_vrintx_h, float16_round_to_int, float16) +DO_2OP(gvec_vrintx_s, float32_round_to_int, float32) + DO_2OP(gvec_sitos, helper_vfp_sitos, int32_t) DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t) DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32) 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_VQNEG(DisasContext *s, arg_2misc *a) return do_2misc(s, a, fn[a->size]); } -static bool do_2misc_fp(DisasContext *s, arg_2misc *a, - NeonGenOneSingleOpFn *fn) -{ - int pass; - TCGv_ptr fpst; - - /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ - 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->size != 2) { - /* TODO: FP16 will be the size == 1 case */ - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - fpst = fpstatus_ptr(FPST_STD); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); - fn(tmp, tmp, fpst); - neon_store_reg(a->vd, pass, tmp); - } - tcg_temp_free_ptr(fpst); - - return true; -} - #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_2MISC_FP_VEC(VCVT_FU, gen_helper_gvec_ustoh, gen_helper_gvec_uitos) DO_2MISC_FP_VEC(VCVT_SF, gen_helper_gvec_tosszh, gen_helper_gvec_tosizs) DO_2MISC_FP_VEC(VCVT_UF, gen_helper_gvec_touszh, gen_helper_gvec_touizs) +DO_2MISC_FP_VEC(VRINTX_impl, gen_helper_gvec_vrintx_h, gen_helper_gvec_vrintx_s) + static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) { return false; } - return do_2misc_fp(s, a, gen_helper_rints_exact); + return trans_VRINTX_impl(s, a); } #define DO_VEC_RMODE(INSN, RMODE, OP) \ -- 2.20.1 In the gvec helper functions for indexed operations, for AArch32 Neon the oprsz (total size of the vector) can be less than 16 bytes if the operation is on a D reg. Since the inner loop in these helpers always goes from 0 to segment, we must clamp it based on oprsz to avoid processing a full 16 byte segment when asked to handle an 8 byte wide vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-43-peter.maydell@linaro.org --- target/arm/vec_helper.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) 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 @@ DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) #define DO_MUL_IDX(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ intptr_t idx = simd_data(desc); \ TYPE *d = vd, *n = vn, *m = vm; \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ @@ -XXX,XX +XXX,XX @@ DO_MUL_IDX(gvec_mul_idx_d, uint64_t, ) #define DO_MLA_IDX(NAME, TYPE, OP, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ intptr_t idx = simd_data(desc); \ TYPE *d = vd, *n = vn, *m = vm, *a = va; \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ @@ -XXX,XX +XXX,XX @@ DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, ) #define DO_FMUL_IDX(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ intptr_t idx = simd_data(desc); \ TYPE *d = vd, *n = vn, *m = vm; \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ @@ -XXX,XX +XXX,XX @@ DO_FMUL_IDX(gvec_fmul_idx_d, float64, ) void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ void *stat, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ TYPE op1_neg = extract32(desc, SIMD_DATA_SHIFT, 1); \ intptr_t idx = desc >> (SIMD_DATA_SHIFT + 1); \ TYPE *d = vd, *n = vn, *m = vm, *a = va; \ -- 2.20.1 Add gvec helpers for doing Neon-style indexed non-fused fp multiply-and-accumulate operations. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200828183354.27913-44-peter.maydell@linaro.org --- target/arm/helper.h | 10 ++++++++++ target/arm/vec_helper.c | 27 ++++++++++++++++++++++----- 2 files changed, 32 insertions(+), 5 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_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, 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 @@ DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, ) #undef DO_MLA_IDX -#define DO_FMUL_IDX(NAME, TYPE, H) \ +#define DO_FMUL_IDX(NAME, ADD, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ intptr_t i, j, oprsz = simd_oprsz(desc); \ @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ TYPE mm = m[H(i + idx)]; \ for (j = 0; j < segment; j++) { \ - d[i + j] = TYPE##_mul(n[i + j], mm, stat); \ + d[i + j] = TYPE##_##ADD(d[i + j], \ + TYPE##_mul(n[i + j], mm, stat), stat); \ } \ } \ clear_tail(d, oprsz, simd_maxsz(desc)); \ } -DO_FMUL_IDX(gvec_fmul_idx_h, float16, H2) -DO_FMUL_IDX(gvec_fmul_idx_s, float32, H4) -DO_FMUL_IDX(gvec_fmul_idx_d, float64, ) +#define float16_nop(N, M, S) (M) +#define float32_nop(N, M, S) (M) +#define float64_nop(N, M, S) (M) +DO_FMUL_IDX(gvec_fmul_idx_h, nop, float16, H2) +DO_FMUL_IDX(gvec_fmul_idx_s, nop, float32, H4) +DO_FMUL_IDX(gvec_fmul_idx_d, nop, float64, ) + +/* + * Non-fused multiply-accumulate operations, for Neon. NB that unlike + * the fused ops below they assume accumulate both from and into Vd. + */ +DO_FMUL_IDX(gvec_fmla_nf_idx_h, add, float16, H2) +DO_FMUL_IDX(gvec_fmla_nf_idx_s, add, float32, H4) +DO_FMUL_IDX(gvec_fmls_nf_idx_h, sub, float16, H2) +DO_FMUL_IDX(gvec_fmls_nf_idx_s, sub, float32, H4) + +#undef float16_nop +#undef float32_nop +#undef float64_nop #undef DO_FMUL_IDX #define DO_FMLA_IDX(NAME, TYPE, H) \ -- 2.20.1 Convert the Neon floating-point VMUL, VMLA and VMLS to use gvec, and use this to implement fp16 support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-45-peter.maydell@linaro.org --- target/arm/translate-neon.c.inc | 114 ++++++++++++++++---------------- 1 file changed, 57 insertions(+), 57 deletions(-) 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_VMLS_2sc(DisasContext *s, arg_2scalar *a) return do_2scalar(s, a, opfn[a->size], accfn[a->size]); } -/* - * Rather than have a float-specific version of do_2scalar just for - * three insns, we wrap a NeonGenTwoSingleOpFn to turn it into - * a NeonGenTwoOpFn. - */ -#define WRAP_FP_FN(WRAPNAME, FUNC) \ - static void WRAPNAME(TCGv_i32 rd, TCGv_i32 rn, TCGv_i32 rm) \ - { \ - TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD); \ - FUNC(rd, rn, rm, fpstatus); \ - tcg_temp_free_ptr(fpstatus); \ +static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, + gen_helper_gvec_3_ptr *fn) +{ + /* Two registers and a scalar, using gvec */ + int vec_size = a->q ? 16 : 8; + int rd_ofs = neon_reg_offset(a->vd, 0); + int rn_ofs = neon_reg_offset(a->vn, 0); + int rm_ofs; + int idx; + TCGv_ptr fpstatus; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; } -WRAP_FP_FN(gen_VMUL_F_mul, gen_helper_vfp_muls) -WRAP_FP_FN(gen_VMUL_F_add, gen_helper_vfp_adds) -WRAP_FP_FN(gen_VMUL_F_sub, gen_helper_vfp_subs) + /* 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; + } -static bool trans_VMUL_F_2sc(DisasContext *s, arg_2scalar *a) -{ - static NeonGenTwoOpFn * const opfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_mul, - NULL, - }; + if (!fn) { + /* Bad size (including size == 3, which is a different insn group) */ + return false; + } - return do_2scalar(s, a, opfn[a->size], NULL); + if (a->q && ((a->vd | a->vn) & 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* a->vm is M:Vm, which encodes both register and index */ + idx = extract32(a->vm, a->size + 2, 2); + a->vm = extract32(a->vm, 0, a->size + 2); + rm_ofs = neon_reg_offset(a->vm, 0); + + fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus, + vec_size, vec_size, idx, fn); + tcg_temp_free_ptr(fpstatus); + return true; } -static bool trans_VMLA_F_2sc(DisasContext *s, arg_2scalar *a) -{ - static NeonGenTwoOpFn * const opfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_mul, - NULL, - }; - static NeonGenTwoOpFn * const accfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_add, - NULL, - }; +#define DO_VMUL_F_2sc(NAME, FUNC) \ + static bool trans_##NAME##_F_2sc(DisasContext *s, arg_2scalar *a) \ + { \ + static gen_helper_gvec_3_ptr * const opfn[] = { \ + NULL, \ + gen_helper_##FUNC##_h, \ + gen_helper_##FUNC##_s, \ + NULL, \ + }; \ + if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + return do_2scalar_fp_vec(s, a, opfn[a->size]); \ + } - return do_2scalar(s, a, opfn[a->size], accfn[a->size]); -} - -static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a) -{ - static NeonGenTwoOpFn * const opfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_mul, - NULL, - }; - static NeonGenTwoOpFn * const accfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_sub, - NULL, - }; - - return do_2scalar(s, a, opfn[a->size], accfn[a->size]); -} +DO_VMUL_F_2sc(VMUL, gvec_fmul_idx) +DO_VMUL_F_2sc(VMLA, gvec_fmla_nf_idx) +DO_VMUL_F_2sc(VMLS, gvec_fmls_nf_idx) WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16) WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32) -- 2.20.1 Set the MVFR1 ID register FPHP and SIMDHP fields to indicate that our "-cpu max" has v8.2-FP16. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-46-peter.maydell@linaro.org --- target/arm/cpu.c | 3 ++- target/arm/cpu64.c | 10 ++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) cpu->isar.id_isar6 = t; t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 2); /* v8.0 FP support */ + 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; diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ cpu->isar.id_dfr0 = u; - /* - * FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet, - * so do not set MVFR1.FPHP. Strictly speaking this is not legal, - * but it is also not legal to enable SVE without support for FP16, - * and enabling SVE in system mode is more useful in the short term. - */ + u = cpu->isar.mvfr1; + u = FIELD_DP32(u, MVFR1, FPHP, 3); /* v8.2-FP16 */ + u = FIELD_DP32(u, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + cpu->isar.mvfr1 = u; #ifdef CONFIG_USER_ONLY /* For usermode -cpu max we can use a larger and more efficient DCZ -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> The sbsa-ref platform uses a minimal device tree to pass amount of memory as well as number of cpus to the firmware. However, when dumping that minimal dtb (with -M sbsa-virt,dumpdtb=<file>), the resulting blob generates a warning when decompiled by dtc due to lack of reg property. Add a simple reg property per cpu, representing a 64-bit MPIDR_EL1. This also ends up being cleaner than having the firmware calculating its own IDs for generating APCI. Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200827124335.30586-1-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_EHCI] = 11, }; +static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) +{ + uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; + return arm_cpu_mp_affinity(idx, clustersz); +} + /* * Firmware on this machine only uses ACPI table to load OS, these limited * device tree nodes are just to let firmware know the info which varies from @@ -XXX,XX +XXX,XX @@ static void create_fdt(SBSAMachineState *sms) g_free(matrix); } + /* + * From Documentation/devicetree/bindings/arm/cpus.yaml + * On ARM v8 64-bit systems this property is required + * and matches the MPIDR_EL1 register affinity bits. + * + * * If cpus node's #address-cells property is set to 2 + * + * The first reg cell bits [7:0] must be set to + * bits [39:32] of MPIDR_EL1. + * + * The second reg cell bits [23:0] must be set to + * bits [23:0] of MPIDR_EL1. + */ qemu_fdt_add_subnode(sms->fdt, "/cpus"); + qemu_fdt_setprop_cell(sms->fdt, "/cpus", "#address-cells", 2); + qemu_fdt_setprop_cell(sms->fdt, "/cpus", "#size-cells", 0x0); for (cpu = sms->smp_cpus - 1; cpu >= 0; cpu--) { char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu); ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); CPUState *cs = CPU(armcpu); + uint64_t mpidr = sbsa_ref_cpu_mp_affinity(sms, cpu); qemu_fdt_add_subnode(sms->fdt, nodename); + qemu_fdt_setprop_u64(sms->fdt, nodename, "reg", mpidr); if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) { qemu_fdt_setprop_cell(sms->fdt, nodename, "numa-node-id", @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) arm_load_kernel(ARM_CPU(first_cpu), machine, &sms->bootinfo); } -static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) -{ - uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; - return arm_cpu_mp_affinity(idx, clustersz); -} - static const CPUArchIdList *sbsa_ref_possible_cpu_arch_ids(MachineState *ms) { unsigned int max_cpus = ms->smp.max_cpus; -- 2.20.1 From: Graeme Gregory <graeme@nuviainc.com> A difference between sbsa platform and the virt platform is PSCI is handled by ARM-TF in the sbsa platform. This means that the PSCI code there needs to communicate some of the platform power changes down to the qemu code for things like shutdown/reset control. Space has been left to extend the EC if we find other use cases in future where ARM-TF and qemu need to communicate. Signed-off-by: Graeme Gregory <graeme@nuviainc.com> Reviewed-by: Leif Lindholm <leif@nuviainc.com> Tested-by: Leif Lindholm <leif@nuviainc.com> Message-id: 20200826141952.136164-2-graeme@nuviainc.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 98 +++++++++++++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 2 + 2 files changed, 100 insertions(+) create mode 100644 hw/misc/sbsa_ec.c diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM SBSA Reference Platform Embedded Controller + * + * A device to allow PSCI running in the secure side of sbsa-ref machine + * to communicate platform power states to qemu. + * + * Copyright (c) 2020 Nuvia Inc + * Written by Graeme Gregory <graeme@nuviainc.com> + * + * SPDX-License-Identifer: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/log.h" +#include "hw/sysbus.h" +#include "sysemu/runstate.h" + +typedef struct { + SysBusDevice parent_obj; + MemoryRegion iomem; +} SECUREECState; + +#define TYPE_SBSA_EC "sbsa-ec" +#define SECURE_EC(obj) OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_EC) + +enum sbsa_ec_powerstates { + SBSA_EC_CMD_POWEROFF = 0x01, + SBSA_EC_CMD_REBOOT = 0x02, +}; + +static uint64_t sbsa_ec_read(void *opaque, hwaddr offset, unsigned size) +{ + /* No use for this currently */ + qemu_log_mask(LOG_GUEST_ERROR, "sbsa-ec: no readable registers"); + return 0; +} + +static void sbsa_ec_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + if (offset == 0) { /* PSCI machine power command register */ + switch (value) { + case SBSA_EC_CMD_POWEROFF: + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + break; + case SBSA_EC_CMD_REBOOT: + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "sbsa-ec: unknown power command"); + } + } else { + qemu_log_mask(LOG_GUEST_ERROR, "sbsa-ec: unknown EC register"); + } +} + +static const MemoryRegionOps sbsa_ec_ops = { + .read = sbsa_ec_read, + .write = sbsa_ec_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 4, + .valid.max_access_size = 4, +}; + +static void sbsa_ec_init(Object *obj) +{ + SECUREECState *s = SECURE_EC(obj); + SysBusDevice *dev = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->iomem, obj, &sbsa_ec_ops, s, "sbsa-ec", + 0x1000); + sysbus_init_mmio(dev, &s->iomem); +} + +static void sbsa_ec_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + /* No vmstate or reset required: device has no internal state */ + dc->user_creatable = false; +} + +static const TypeInfo sbsa_ec_info = { + .name = TYPE_SBSA_EC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(SECUREECState), + .instance_init = sbsa_ec_init, + .class_init = sbsa_ec_class_init, +}; + +static void sbsa_ec_register_type(void) +{ + type_register_static(&sbsa_ec_info); +} + +type_init(sbsa_ec_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 @@ specific_ss.add(when: 'CONFIG_MAC_VIA', if_true: files('mac_via.c')) specific_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_cmgcr.c', 'mips_cpc.c')) specific_ss.add(when: 'CONFIG_MIPS_ITU', if_true: files('mips_itu.c')) + +specific_ss.add(when: 'CONFIG_SBSA_REF', if_true: files('sbsa_ec.c')) -- 2.20.1 From: Graeme Gregory <graeme@nuviainc.com> Add the previously created sbsa-ec device to the sbsa-ref machine in secure memory so the PSCI implementation in ARM-TF can access it, but not expose it to non secure firmware or OS except by via ARM-TF. Signed-off-by: Graeme Gregory <graeme@nuviainc.com> Reviewed-by: Leif Lindholm <leif@nuviainc.com> Tested-by: Leif Lindholm <leif@nuviainc.com> Message-id: 20200826141952.136164-3-graeme@nuviainc.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ enum { SBSA_CPUPERIPHS, SBSA_GIC_DIST, SBSA_GIC_REDIST, + SBSA_SECURE_EC, SBSA_SMMU, SBSA_UART, SBSA_RTC, @@ -XXX,XX +XXX,XX @@ static const MemMapEntry sbsa_ref_memmap[] = { [SBSA_CPUPERIPHS] = { 0x40000000, 0x00040000 }, [SBSA_GIC_DIST] = { 0x40060000, 0x00010000 }, [SBSA_GIC_REDIST] = { 0x40080000, 0x04000000 }, + [SBSA_SECURE_EC] = { 0x50000000, 0x00001000 }, [SBSA_UART] = { 0x60000000, 0x00001000 }, [SBSA_RTC] = { 0x60010000, 0x00001000 }, [SBSA_GPIO] = { 0x60020000, 0x00001000 }, @@ -XXX,XX +XXX,XX @@ static void *sbsa_ref_dtb(const struct arm_boot_info *binfo, int *fdt_size) return board->fdt; } +static void create_secure_ec(MemoryRegion *mem) +{ + hwaddr base = sbsa_ref_memmap[SBSA_SECURE_EC].base; + DeviceState *dev = qdev_new("sbsa-ec"); + SysBusDevice *s = SYS_BUS_DEVICE(dev); + + memory_region_add_subregion(mem, base, + sysbus_mmio_get_region(s, 0)); +} + static void sbsa_ref_init(MachineState *machine) { unsigned int smp_cpus = machine->smp.cpus; @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) create_pcie(sms); + create_secure_ec(secure_sysmem); + sms->bootinfo.ram_size = machine->ram_size; sms->bootinfo.nb_cpus = smp_cpus; sms->bootinfo.board_id = -1; -- 2.20.1