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 First set of arm patches for 6.2. I have a lot more in my to-review queue still... -- PMM The following changes since commit d42685765653ec155fdf60910662f8830bdb2cef: Open 6.2 development tree (2021-08-25 10:25:12 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210825 for you to fetch changes up to 24b1a6aa43615be22c7ee66bd68ec5675f6a6a9a: docs: Document how to use gdb with unix sockets (2021-08-25 10:48:51 +0100) ---------------------------------------------------------------- target-arm queue: * More MVE emulation work * Implement M-profile trapping on division by zero * kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() * hw/char/pl011: add support for sending break * fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices * hw/dma/pl330: Add memory region to replace default * sbsa-ref: Rename SBSA_GWDT enum value * fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices * docs: Document how to use gdb with unix sockets ---------------------------------------------------------------- Eduardo Habkost (1): sbsa-ref: Rename SBSA_GWDT enum value Guenter Roeck (2): fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices Hamza Mahfooz (1): target/arm: kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() Jan Luebbe (1): hw/char/pl011: add support for sending break Peter Maydell (37): target/arm: Note that we handle VMOVL as a special case of VSHLL target/arm: Print MVE VPR in CPU dumps target/arm: Fix MVE VSLI by 0 and VSRI by <dt> target/arm: Fix signed VADDV target/arm: Fix mask handling for MVE narrowing operations target/arm: Fix 48-bit saturating shifts target/arm: Fix MVE 48-bit SQRSHRL for small right shifts target/arm: Fix calculation of LTP mask when LR is 0 target/arm: Factor out mve_eci_mask() target/arm: Fix VPT advance when ECI is non-zero target/arm: Fix VLDRB/H/W for predicated elements target/arm: Implement MVE VMULL (polynomial) target/arm: Implement MVE incrementing/decrementing dup insns target/arm: Factor out gen_vpst() target/arm: Implement MVE integer vector comparisons target/arm: Implement MVE integer vector-vs-scalar comparisons target/arm: Implement MVE VPSEL target/arm: Implement MVE VMLAS target/arm: Implement MVE shift-by-scalar target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats target/arm: Implement MVE integer min/max across vector target/arm: Implement MVE VABAV target/arm: Implement MVE narrowing moves target/arm: Rename MVEGenDualAccOpFn to MVEGenLongDualAccOpFn target/arm: Implement MVE VMLADAV and VMLSLDAV target/arm: Implement MVE VMLA target/arm: Implement MVE saturating doubling multiply accumulates target/arm: Implement MVE VQABS, VQNEG target/arm: Implement MVE VMAXA, VMINA target/arm: Implement MVE VMOV to/from 2 general-purpose registers target/arm: Implement MVE VPNOT target/arm: Implement MVE VCTP target/arm: Implement MVE scatter-gather insns target/arm: Implement MVE scatter-gather immediate forms target/arm: Implement MVE interleaving loads/stores target/arm: Re-indent sdiv and udiv helpers target/arm: Implement M-profile trapping on division by zero Sebastian Meyer (1): docs: Document how to use gdb with unix sockets Wen, Jianxian (1): hw/dma/pl330: Add memory region to replace default docs/system/gdb.rst | 26 +- include/hw/arm/fsl-imx7.h | 5 + target/arm/cpu.h | 1 + target/arm/helper-mve.h | 283 ++++++++++ target/arm/helper.h | 4 +- target/arm/translate-a32.h | 2 + target/arm/vec_internal.h | 11 + target/arm/mve.decode | 226 +++++++- target/arm/t32.decode | 1 + hw/arm/exynos4210.c | 3 + hw/arm/fsl-imx6ul.c | 12 + hw/arm/fsl-imx7.c | 7 + hw/arm/sbsa-ref.c | 6 +- hw/arm/xilinx_zynq.c | 3 + hw/char/pl011.c | 6 + hw/dma/pl330.c | 26 +- target/arm/cpu.c | 3 + target/arm/helper.c | 34 +- target/arm/kvm.c | 17 +- target/arm/m_helper.c | 4 + target/arm/mve_helper.c | 1254 ++++++++++++++++++++++++++++++++++++++++++-- target/arm/translate-mve.c | 877 ++++++++++++++++++++++++++++++- target/arm/translate-vfp.c | 2 +- target/arm/translate.c | 37 +- target/arm/vec_helper.c | 14 +- 25 files changed, 2746 insertions(+), 118 deletions(-) Although the architecture doesn't define it as an alias, VMOVL (vector move long) is encoded as a VSHLL with a zero shift. Add a comment in the decode file noting that we handle VMOVL as part of VSHLL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w # VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file +# Note that VMOVL is encoded as "VSHLL with a zero shift count"; we +# implement it that way rather than special-casing it in the decode. VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h -- 2.20.1 Include the MVE VPR register value in the CPU dumps produced by arm_cpu_dump_state() if we are printing FPU information. This makes it easier to interpret debug logs when predication is active. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) i, v); } qemu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); + if (cpu_isar_feature(aa32_mve, cpu)) { + qemu_fprintf(f, "VPR: %08x\n", env->v7m.vpr); + } } } -- 2.20.1 In the MVE shift-and-insert insns, we special case VSLI by 0 and VSRI by <dt>. VSRI by <dt> means "don't update the destination", which is what we've implemented. However VSLI by 0 is "set destination to the input", so we don't want to use the same special-casing that we do for VSRI by <dt>. Since the generic logic gives the right answer for a shift by 0, just use that. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_S(vrshli_s, DO_VRSHLS) uint16_t mask; \ uint64_t shiftmask; \ unsigned e; \ - if (shift == 0 || shift == ESIZE * 8) { \ + if (shift == ESIZE * 8) { \ /* \ - * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ - * The generic logic would give the right answer for 0 but \ - * fails for <dt>. \ + * Only VSRI can shift by <dt>; it should mean "don't \ + * update the destination". The generic logic can't handle \ + * this because it would try to shift by an out-of-range \ + * amount, so special case it here. \ */ \ goto done; \ } \ -- 2.20.1 A cut-and-paste error meant we handled signed VADDV like unsigned VADDV; fix the type used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true) return ra; \ } \ -DO_VADDV(vaddvsb, 1, uint8_t) -DO_VADDV(vaddvsh, 2, uint16_t) -DO_VADDV(vaddvsw, 4, uint32_t) +DO_VADDV(vaddvsb, 1, int8_t) +DO_VADDV(vaddvsh, 2, int16_t) +DO_VADDV(vaddvsw, 4, int32_t) DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) -- 2.20.1 In the MVE helpers for the narrowing operations (DO_VSHRN and DO_VSHRN_SAT) we were using the wrong bits of the predicate mask for the 'top' versions of the insn. This is because the loop works over the double-sized input elements and shifts the predicate mask by that many bits each time, but when we write out the half-sized output we must look at the mask bits for whichever half of the element we are writing to. Correct this by shifting the whole mask right by ESIZE bits for the 'top' insns. This allows us also to simplify the saturation bit checking (where we had noticed that we needed to look at a different mask bit for the 'top' insn.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL_ALL(vshllt, true) TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ TYPE r = FN(m[H##LESIZE(le)], shift); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ @@ -XXX,XX +XXX,XX @@ static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, uint16_t mask = mve_element_mask(env); \ bool qc = false; \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ bool sat = false; \ TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ - qc |= sat && (mask & 1 << (TOP * ESIZE)); \ + qc |= sat & mask & 1; \ } \ if (qc) { \ env->vfp.qc[0] = qc; \ -- 2.20.1 In do_sqrshl48_d() and do_uqrshl48_d() we got some of the edge cases wrong and failed to saturate correctly: (1) In do_sqrshl48_d() we used the same code that do_shrshl_bhs() does to obtain the saturated most-negative and most-positive 48-bit signed values for the large-shift-left case. This gives (1 << 47) for saturate-to-most-negative, but we weren't sign-extending this value to the 64-bit output as the pseudocode requires. (2) For left shifts by less than 48, we copied the "8/16 bit" code from do_sqrshl_bhs() and do_uqrshl_bhs(). This doesn't do the right thing because it assumes the C type we're working with is at least twice the number of bits we're saturating to (so that a shift left by bits-1 can't shift anything off the top of the value). This isn't true for bits == 48, so we would incorrectly return 0 rather than the most-positive value for situations like "shift (1 << 44) right by 20". Instead check for saturation by doing the shift and signextend and then testing whether shifting back left again gives the original value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } return src >> -shift; } else if (shift < 48) { - int64_t val = src << shift; - int64_t extval = sextract64(val, 0, 48); - if (!sat || val == extval) { + int64_t extval = sextract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } *sat = 1; - return (1ULL << 47) - (src >= 0); + return src >= 0 ? MAKE_64BIT_MASK(0, 47) : MAKE_64BIT_MASK(47, 17); } /* Operate on 64-bit values, but saturate at 48 bits */ @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, return extval; } } else if (shift < 48) { - uint64_t val = src << shift; - uint64_t extval = extract64(val, 0, 48); - if (!sat || val == extval) { + uint64_t extval = extract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { -- 2.20.1 We got an edge case wrong in the 48-bit SQRSHRL implementation: if the shift is to the right, although it always makes the result smaller than the input value it might not be within the 48-bit range the result is supposed to be if the input had some bits in [63..48] set and the shift didn't bring all of those within the [47..0] range. Handle this similarly to the way we already do for this case in do_uqrshl48_d(): extend the calculated result from 48 bits, and return that if not saturating or if it doesn't change the result; otherwise fall through to return a saturated value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, bool round, uint32_t *sat) { + int64_t val, extval; + if (shift <= -48) { /* Rounding the sign bit always produces 0. */ if (round) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } else if (shift < 0) { if (round) { src >>= -shift - 1; - return (src >> 1) + (src & 1); + val = (src >> 1) + (src & 1); + } else { + val = src >> -shift; + } + extval = sextract64(val, 0, 48); + if (!sat || val == extval) { + return extval; } - return src >> -shift; } else if (shift < 48) { int64_t extval = sextract64(src << shift, 0, 48); if (!sat || src == (extval >> shift)) { -- 2.20.1 In mve_element_mask(), we calculate a mask for tail predication which should have a number of 1 bits based on the value of LR. However, our MAKE_64BIT_MASK() macro has undefined behaviour when passed a zero length. Special case this to give the all-zeroes mask we require. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) */ int masklen = env->regs[14] << env->v7m.ltpsize; assert(masklen <= 16); - mask &= MAKE_64BIT_MASK(0, masklen); + uint16_t ltpmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + mask &= ltpmask; } if ((env->condexec_bits & 0xf) == 0) { -- 2.20.1 In some situations we need a mask telling us which parts of the vector correspond to beats that are not being executed because of ECI, separately from the combined "which bytes are predicated away" mask. Factor this mask calculation out of mve_element_mask() into its own function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 58 ++++++++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "tcg/tcg.h" +static uint16_t mve_eci_mask(CPUARMState *env) +{ + /* + * Return the mask of which elements in the MVE vector correspond + * to beats being executed. The mask has 1 bits for executed lanes + * and 0 bits where ECI says this beat was already executed. + */ + int eci; + + if ((env->condexec_bits & 0xf) != 0) { + return 0xffff; + } + + eci = env->condexec_bits >> 4; + switch (eci) { + case ECI_NONE: + return 0xffff; + case ECI_A0: + return 0xfff0; + case ECI_A0A1: + return 0xff00; + case ECI_A0A1A2: + case ECI_A0A1A2B0: + return 0xf000; + default: + g_assert_not_reached(); + } +} + static uint16_t mve_element_mask(CPUARMState *env) { /* @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) mask &= ltpmask; } - if ((env->condexec_bits & 0xf) == 0) { - /* - * ECI bits indicate which beats are already executed; - * we handle this by effectively predicating them out. - */ - int eci = env->condexec_bits >> 4; - switch (eci) { - case ECI_NONE: - break; - case ECI_A0: - mask &= 0xfff0; - break; - case ECI_A0A1: - mask &= 0xff00; - break; - case ECI_A0A1A2: - case ECI_A0A1A2B0: - mask &= 0xf000; - break; - default: - g_assert_not_reached(); - } - } - + /* + * ECI bits indicate which beats are already executed; + * we handle this by effectively predicating them out. + */ + mask &= mve_eci_mask(env); return mask; } -- 2.20.1 We were not paying attention to the ECI state when advancing the VPT state. Architecturally, VPT state advance happens for every beat (see the pseudocode VPTAdvance()), so on every beat the 4 bits of VPR.P0 corresponding to the current beat are inverted if required, and at the end of beats 1 and 3 the VPR MASK fields are updated. This means that if the ECI state says we should not be executing all 4 beats then we need to skip some of the updating of the VPR that we currently do in mve_advance_vpt(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) /* Advance the VPT and ECI state if necessary */ uint32_t vpr = env->v7m.vpr; unsigned mask01, mask23; + uint16_t inv_mask; + uint16_t eci_mask = mve_eci_mask(env); if ((env->condexec_bits & 0xf) == 0) { env->condexec_bits = (env->condexec_bits == (ECI_A0A1A2B0 << 4)) ? @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) return; } + /* Invert P0 bits if needed, but only for beats we actually executed */ mask01 = FIELD_EX32(vpr, V7M_VPR, MASK01); mask23 = FIELD_EX32(vpr, V7M_VPR, MASK23); - if (mask01 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff; + /* Start by assuming we invert all bits corresponding to executed beats */ + inv_mask = eci_mask; + if (mask01 <= 8) { + /* MASK01 says don't invert low half of P0 */ + inv_mask &= ~0xff; } - if (mask23 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff00; + if (mask23 <= 8) { + /* MASK23 says don't invert high half of P0 */ + inv_mask &= ~0xff00; } - vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + vpr ^= inv_mask; + /* Only update MASK01 if beat 1 executed */ + if (eci_mask & 0xf0) { + vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + } + /* Beat 3 always executes, so update MASK23 */ vpr = FIELD_DP32(vpr, V7M_VPR, MASK23, mask23 << 1); env->v7m.vpr = vpr; } -- 2.20.1 For vector loads, predicated elements are zeroed, instead of retaining their previous values (as happens for most data processing operations). This means we need to distinguish "beat not executed due to ECI" (don't touch destination element) from "beat executed but predicated out" (zero destination element). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) env->v7m.vpr = vpr; } - +/* For loads, predicated lanes are zeroed instead of keeping their old values */ #define DO_VLDR(OP, MSIZE, LDTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) * then take an exception. \ */ \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ - if (mask & (1 << b)) { \ - d[H##ESIZE(e)] = cpu_##LDTYPE##_data_ra(env, addr, GETPC()); \ + if (eci_mask & (1 << b)) { \ + d[H##ESIZE(e)] = (mask & (1 << b)) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ } \ addr += MSIZE; \ } \ -- 2.20.1 Implement the MVE VMULL (polynomial) insn. Unlike Neon, this comes in two flavours: 8x8->16 and a 16x16->32. Also unlike Neon, the inputs are in either the low or the high half of each double-width element. The assembler for this insn indicates the size with "P8" or "P16", encoded into bit 28 as size = 0 or 1. We choose to follow the same encoding as VQDMULL and decode this into a->size as MO_16 or MO_32 indicating the size of the result elements. This then carries through to the helper function names where it then matches up with the existing pmull_h() which does an 8x8->16 operation and a new pmull_w() which does the 16x16->32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++++ target/arm/vec_internal.h | 11 +++++++++++ target/arm/mve.decode | 14 ++++++++++---- target/arm/mve_helper.c | 16 ++++++++++++++++ target/arm/translate-mve.c | 28 ++++++++++++++++++++++++++++ target/arm/vec_helper.c | 14 +++++++++++++- 6 files changed, 83 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmulltub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpth, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullptw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vqdmulhb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_internal.h +++ b/target/arm/vec_internal.h @@ -XXX,XX +XXX,XX @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); +/* + * 8 x 8 -> 16 vector polynomial multiply where the inputs are + * in the low 8 bits of each 16-bit element +*/ +uint64_t pmull_h(uint64_t op1, uint64_t op2); +/* + * 16 x 16 -> 32 vector polynomial multiply where the inputs are + * in the low 16 bits of each 32-bit element + */ +uint64_t pmull_w(uint64_t op1, uint64_t op2); + #endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VHADD_U 111 1 1111 0 . .. ... 0 ... 0 0000 . 1 . 0 ... 0 @2op VHSUB_S 111 0 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op VHSUB_U 111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op -VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op -VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +{ + VMULLP_B 111 . 1110 0 . 11 ... 1 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op + VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op +} +{ + VMULLP_T 111 . 1110 0 . 11 ... 1 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op + VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +} VQDMULH 1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op VQRDMULH 1111 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_L(vmulltub, 1, 1, uint8_t, 2, uint16_t, DO_MUL) DO_2OP_L(vmulltuh, 1, 2, uint16_t, 4, uint32_t, DO_MUL) DO_2OP_L(vmulltuw, 1, 4, uint32_t, 8, uint64_t, DO_MUL) +/* + * Polynomial multiply. We can always do this generating 64 bits + * of the result at a time, so we don't need to use DO_2OP_L. + */ +#define VMULLPH_MASK 0x00ff00ff00ff00ffULL +#define VMULLPW_MASK 0x0000ffff0000ffffULL +#define DO_VMULLPBH(N, M) pmull_h((N) & VMULLPH_MASK, (M) & VMULLPH_MASK) +#define DO_VMULLPTH(N, M) DO_VMULLPBH((N) >> 8, (M) >> 8) +#define DO_VMULLPBW(N, M) pmull_w((N) & VMULLPW_MASK, (M) & VMULLPW_MASK) +#define DO_VMULLPTW(N, M) DO_VMULLPBW((N) >> 16, (M) >> 16) + +DO_2OP(vmullpbh, 8, uint64_t, DO_VMULLPBH) +DO_2OP(vmullpth, 8, uint64_t, DO_VMULLPTH) +DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW) +DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW) + /* * Because the computation type is at least twice as large as required, * these work for both signed and unsigned source types. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT(DisasContext *s, arg_2op *a) return do_2op(s, a, fns[a->size]); } +static bool trans_VMULLP_B(DisasContext *s, arg_2op *a) +{ + /* + * Note that a->size indicates the output size, ie VMULL.P8 + * is the 8x8->16 operation and a->size is MO_16; VMULL.P16 + * is the 16x16->32 operation and a->size is MO_32. + */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpbh, + gen_helper_mve_vmullpbw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + +static bool trans_VMULLP_T(DisasContext *s, arg_2op *a) +{ + /* a->size is as for trans_VMULLP_B */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpth, + gen_helper_mve_vmullptw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + /* * VADC and VSBC: these perform an add-with-carry or subtract-with-carry * of the 32-bit elements in each lane of the input vectors, where the diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t expand_byte_to_half(uint64_t x) | ((x & 0xff000000) << 24); } -static uint64_t pmull_h(uint64_t op1, uint64_t op2) +uint64_t pmull_w(uint64_t op1, uint64_t op2) { uint64_t result = 0; int i; + for (i = 0; i < 16; ++i) { + uint64_t mask = (op1 & 0x0000000100000001ull) * 0xffffffff; + result ^= op2 & mask; + op1 >>= 1; + op2 <<= 1; + } + return result; +} +uint64_t pmull_h(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; for (i = 0; i < 8; ++i) { uint64_t mask = (op1 & 0x0001000100010001ull) * 0xffff; result ^= op2 & mask; -- 2.20.1 Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 12 ++++ target/arm/mve.decode | 25 ++++++++ target/arm/mve_helper.c | 63 +++++++++++++++++++ target/arm/translate-mve.c | 120 +++++++++++++++++++++++++++++++++++++ 4 files changed, 220 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_viduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_vidupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) + +DEF_HELPER_FLAGS_5(mve_viwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + +DEF_HELPER_FLAGS_5(mve_vdwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + DEF_HELPER_FLAGS_3(mve_vclsb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsw, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2scalar qd qn rm size &1imm qd imm cmode op &2shift qd qm shift size +&vidup qd rn size imm +&viwdup qd rn rm size imm @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 1 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=0 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 1 1 0000 @vdup size=1 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 +# Incrementing and decrementing dup + +# VIDUP, VDDUP format immediate: 1 << (immh:imml) +%imm_vidup 7:1 0:1 !function=vidup_imm + +# VIDUP, VDDUP registers: Rm bits [3:1] from insn, bit 0 is 1; +# Rn bits [3:1] from insn, bit 0 is 0 +%vidup_rm 1:3 !function=times_2_plus_1 +%vidup_rn 17:3 !function=times_2 + +@vidup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rn=%vidup_rn &vidup +@viwdup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rm=%vidup_rm rn=%vidup_rn &viwdup +{ + VIDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 111 . @vidup + VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup +} +{ + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup +} + # multiply-add long dual accumulate # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) { return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); } + +#define DO_VIDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIWDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t wrap, \ + uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, wrap, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIDUP_ALL(OP, FN) \ + DO_VIDUP(OP##b, 1, int8_t, FN) \ + DO_VIDUP(OP##h, 2, int16_t, FN) \ + DO_VIDUP(OP##w, 4, int32_t, FN) + +#define DO_VIWDUP_ALL(OP, FN) \ + DO_VIWDUP(OP##b, 1, int8_t, FN) \ + DO_VIWDUP(OP##h, 2, int16_t, FN) \ + DO_VIWDUP(OP##w, 4, int32_t, FN) + +static uint32_t do_add_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + offset += imm; + if (offset == wrap) { + offset = 0; + } + return offset; +} + +static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + if (offset == 0) { + offset = wrap; + } + offset -= imm; + return offset; +} + +DO_VIDUP_ALL(vidup, DO_ADD) +DO_VIWDUP_ALL(viwdup, do_add_wrap) +DO_VIWDUP_ALL(vdwdup, do_sub_wrap) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "translate-a32.h" +static inline int vidup_imm(DisasContext *s, int x) +{ + return 1 << x; +} + /* Include the generated decoder */ #include "decode-mve.c.inc" @@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) mve_update_eci(s); return true; } + +static bool do_vidup(DisasContext *s, arg_vidup *a, MVEGenVIDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn; + + /* + * Vector increment/decrement with wrap and duplicate (VIDUP, VDDUP). + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (a->size == MO_64) { + /* size 0b11 is another encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + fn(rn, cpu_env, qd, rn, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} + +static bool do_viwdup(DisasContext *s, arg_viwdup *a, MVEGenVIWDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn, rm; + + /* + * Vector increment/decrement with wrap and duplicate (VIWDUp, VDWDUP) + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. Rm specifies a point where + * the count wraps back around to 0. The updated offset is written back + * to Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (!fn || a->rm == 13 || a->rm == 15) { + /* + * size 0b11 is another encoding; Rm == 13 is UNPREDICTABLE; + * Rm == 13 is VIWDUP, VDWDUP. + */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + rm = load_reg(s, a->rm); + fn(rn, cpu_env, qd, rn, rm, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +static bool trans_VIDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VDDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + /* VDDUP is just like VIDUP but with a negative immediate */ + a->imm = -a->imm; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VIWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_viwdupb, + gen_helper_mve_viwduph, + gen_helper_mve_viwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} + +static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_vdwdupb, + gen_helper_mve_vdwduph, + gen_helper_mve_vdwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} -- 2.20.1 Factor out the "generate code to update VPR.MASK01/MASK23" part of trans_VPST(); we are going to want to reuse it for the VPT insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } -static bool trans_VPST(DisasContext *s, arg_VPST *a) +static void gen_vpst(DisasContext *s, uint32_t mask) { - TCGv_i32 vpr; - - /* mask == 0 is a "related encoding" */ - if (!dc_isar_feature(aa32_mve, s) || !a->mask) { - return false; - } - if (!mve_eci_check(s) || !vfp_access_check(s)) { - return true; - } /* * Set the VPR mask fields. We take advantage of MASK01 and MASK23 * being adjacent fields in the register. * - * This insn is not predicated, but it is subject to beat-wise + * Updating the masks is not predicated, but it is subject to beat-wise * execution, and the mask is updated on the odd-numbered beats. * So if PSR.ECI says we should skip beat 1, we mustn't update the * 01 mask field. */ - vpr = load_cpu_field(v7m.vpr); + TCGv_i32 vpr = load_cpu_field(v7m.vpr); switch (s->eci) { case ECI_NONE: case ECI_A0: /* Update both 01 and 23 fields */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask | (a->mask << 4)), + tcg_constant_i32(mask | (mask << 4)), R_V7M_VPR_MASK01_SHIFT, R_V7M_VPR_MASK01_LENGTH + R_V7M_VPR_MASK23_LENGTH); break; @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) case ECI_A0A1A2B0: /* Update only the 23 mask field */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask), + tcg_constant_i32(mask), R_V7M_VPR_MASK23_SHIFT, R_V7M_VPR_MASK23_LENGTH); break; default: g_assert_not_reached(); } store_cpu_field(vpr, v7m.vpr); +} + +static bool trans_VPST(DisasContext *s, arg_VPST *a) +{ + /* mask == 0 is a "related encoding" */ + if (!dc_isar_feature(aa32_mve, s) || !a->mask) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + gen_vpst(s, a->mask); mve_update_and_store_eci(s); return true; } -- 2.20.1 Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 ++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++- target/arm/mve_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 47 ++++++++++++++++++++++++++++++++ 4 files changed, 152 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpeqb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpneb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpnew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpcsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmphib, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphih, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphiw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgeb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpltb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpltw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgtb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2shift qd qm shift size &vidup qd rn size imm &viwdup qd rn rm size imm +&vcmp qm qn size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +# Vector comparison; 4-bit Qm but 3-bit Qn +%mask_22_13 22:1 13:3 +@vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar } # Predicate operations -%mask_22_13 22:1 13:3 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 # Logical immediate operations (1 reg and modified-immediate) @@ -XXX,XX +XXX,XX @@ VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd + +# Comparisons. We expand out the conditions which are split across +# encodings T1, T2, T3 and the fc bits. These include VPT, which is +# effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. +VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp +VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) DO_VIDUP_ALL(vidup, DO_ADD) DO_VIWDUP_ALL(viwdup, do_add_wrap) DO_VIWDUP_ALL(vdwdup, do_sub_wrap) + +/* + * Vector comparison. + * P0 bits for non-executed beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed beats (where mask is 0) are 0. + * P0 bits otherwise are updated with the results of the comparisons. + * We must also keep unchanged the MASK fields at the top of v7m.vpr. + */ +#define DO_VCMP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)]); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) + +#define DO_EQ(N, M) ((N) == (M)) +#define DO_NE(N, M) ((N) != (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_GE(N, M) ((N) >= (M)) +#define DO_LT(N, M) ((N) < (M)) +#define DO_GT(N, M) ((N) > (M)) +#define DO_LE(N, M) ((N) <= (M)) + +DO_VCMP_U(vcmpeq, DO_EQ) +DO_VCMP_U(vcmpne, DO_NE) +DO_VCMP_U(vcmpcs, DO_GE) +DO_VCMP_U(vcmphi, DO_GT) +DO_VCMP_S(vcmpge, DO_GE) +DO_VCMP_S(vcmplt, DO_LT) +DO_VCMP_S(vcmpgt, DO_GT) +DO_VCMP_S(vcmple, DO_LE) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); +typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) }; return do_viwdup(s, a, fns[a->size]); } + +static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) +{ + TCGv_ptr qn, qm; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qn, qm); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + +#define DO_VCMP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vcmp(s, a, fns[a->size]); \ + } + +DO_VCMP(VCMPEQ, vcmpeq) +DO_VCMP(VCMPNE, vcmpne) +DO_VCMP(VCMPCS, vcmpcs) +DO_VCMP(VCMPHI, vcmphi) +DO_VCMP(VCMPGE, vcmpge) +DO_VCMP(VCMPLT, vcmplt) +DO_VCMP(VCMPGT, vcmpgt) +DO_VCMP(VCMPLE, vcmple) -- 2.20.1 Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++++--- target/arm/mve_helper.c | 44 +++++++++++++++++++++++++++++++------- target/arm/translate-mve.c | 43 +++++++++++++++++++++++++++++++++++++ 4 files changed, 126 insertions(+), 11 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vidup qd rn size imm &viwdup qd rn rm size imm &vcmp qm qn size mask +&vcmp_scalar qn rm size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 +@vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 # Vector loads and stores @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar rdahi=%rdahi rdalo=%rdalo } -# Predicate operations -VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but @@ -XXX,XX +XXX,XX @@ VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp + +{ + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar +} +VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar +VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar +VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar +VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar +VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar +VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar +VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VIWDUP_ALL(vdwdup, do_sub_wrap) mve_advance_vpt(env); \ } -#define DO_VCMP_S(OP, FN) \ - DO_VCMP(OP##b, 1, int8_t, FN) \ - DO_VCMP(OP##h, 2, int16_t, FN) \ - DO_VCMP(OP##w, 4, int32_t, FN) +#define DO_VCMP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], (TYPE)rm); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } -#define DO_VCMP_U(OP, FN) \ - DO_VCMP(OP##b, 1, uint8_t, FN) \ - DO_VCMP(OP##h, 2, uint16_t, FN) \ - DO_VCMP(OP##w, 4, uint32_t, FN) +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, int8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, int16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, uint8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, uint16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, uint32_t, FN) #define DO_EQ(N, M) ((N) == (M)) #define DO_NE(N, M) ((N) != (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); +typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) return true; } +static bool do_vcmp_scalar(DisasContext *s, arg_vcmp_scalar *a, + MVEGenScalarCmpFn *fn) +{ + TCGv_ptr qn; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || !fn || a->rm == 13) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + if (a->rm == 15) { + /* Encoding Rm=0b1111 means "constant zero" */ + rm = tcg_constant_i32(0); + } else { + rm = load_reg(s, a->rm); + } + fn(cpu_env, qn, rm); + tcg_temp_free_ptr(qn); + tcg_temp_free_i32(rm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + #define DO_VCMP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) NULL, \ }; \ return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + gen_helper_mve_##FN##_scalarb, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalarw, \ + NULL, \ + }; \ + return do_vcmp_scalar(s, a, fns[a->size]); \ } DO_VCMP(VCMPEQ, vcmpeq) -- 2.20.1 Implement the MVE VPSEL insn, which sets each byte of the destination vector Qd to the byte from either Qn or Qm depending on the value of the corresponding bit in VPR.P0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/mve.decode | 7 +++++-- target/arm/mve_helper.c | 19 +++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 28 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp -VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp -VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +{ + VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz + VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp + VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +} VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMP_S(vcmpge, DO_GE) DO_VCMP_S(vcmplt, DO_LT) DO_VCMP_S(vcmpgt, DO_GT) DO_VCMP_S(vcmple, DO_LE) + +void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) +{ + /* + * Qd[n] = VPR.P0[n] ? Qn[n] : Qm[n] + * but note that whether bytes are written to Qd is still subject + * to (all forms of) predication in the usual way. + */ + uint64_t *d = vd, *n = vn, *m = vm; + uint16_t mask = mve_element_mask(env); + uint16_t p0 = FIELD_EX32(env->v7m.vpr, V7M_VPR, P0); + unsigned e; + for (e = 0; e < 16 / 8; e++, mask >>= 8, p0 >>= 8) { + uint64_t r = m[H8(e)]; + mergemask(&r, n[H8(e)], p0); + mergemask(&d[H8(e)], r, mask); + } + mve_advance_vpt(env); +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_LOGIC(VORR, gen_helper_mve_vorr) DO_LOGIC(VORN, gen_helper_mve_vorn) DO_LOGIC(VEOR, gen_helper_mve_veor) +DO_LOGIC(VPSEL, gen_helper_mve_vpsel) + #define DO_2OP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2op *a) \ { \ -- 2.20.1 Implement the MVE VMLAS insn, which multiplies a vector by a vector and adds a scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 1 + 4 files changed, 34 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +# The U bit (28) is don't-care because it does not affect the result +VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +/* "accumulating" version where FN takes d as well as n and m */ +#define DO_2OP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m), mask); \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) DO_2OP_SCALAR(OP##h, 2, int16_t, FN) \ DO_2OP_SCALAR(OP##w, 4, int32_t, FN) +#define DO_2OP_ACC_SCALAR_U(OP, FN) \ + DO_2OP_ACC_SCALAR(OP##b, 1, uint8_t, FN) \ + DO_2OP_ACC_SCALAR(OP##h, 2, uint16_t, FN) \ + DO_2OP_ACC_SCALAR(OP##w, 4, uint32_t, FN) + DO_2OP_SCALAR_U(vadd_scalar, DO_ADD) DO_2OP_SCALAR_U(vsub_scalar, DO_SUB) DO_2OP_SCALAR_U(vmul_scalar, DO_MUL) @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by vector plus scalar */ +#define DO_VMLAS(D, N, M) ((N) * (D) + (M)) + +DO_2OP_ACC_SCALAR_U(vmlas, DO_VMLAS) + /* * Long saturating scalar ops. As with DO_2OP_L, TYPE and H are for the * input (smaller) type and LESIZE, LTYPE, LH for the output (long) type. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 +++++++ target/arm/mve.decode | 23 ++++++++++++++++--- target/arm/mve_helper.c | 2 ++ target/arm/translate-mve.c | 46 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 76 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &viwdup qd rn rm size imm &vcmp qm qn size mask &vcmp_scalar qn rm size mask +&shl_scalar qda rm size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +@shl_scalar .... .... .... size:2 .. .... .... .... rm:4 &shl_scalar qda=%qd + # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 @@ -XXX,XX +XXX,XX @@ VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_no VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar -VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar + +{ + VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + +{ + VSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar @@ -XXX,XX +XXX,XX @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar - VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) +DO_2SHIFT_SAT_U(vqrshli_u, DO_UQRSHL_OP) +DO_2SHIFT_SAT_S(vqrshli_s, DO_SQRSHL_OP) /* Shift-and-insert; we always work with 64 bits at a time */ #define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, + MVEGenTwoOpShiftFn *fn) +{ + TCGv_ptr qda; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qda) || + a->rm == 13 || a->rm == 15 || !fn) { + /* Rm cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qda = mve_qreg_ptr(a->qda); + rm = load_reg(s, a->rm); + fn(cpu_env, qda, qda, rm); + tcg_temp_free_ptr(qda); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +#define DO_2SHIFT_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_shl_scalar *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_2shift_scalar(s, a, fns[a->size]); \ + } + +DO_2SHIFT_SCALAR(VSHL_S_scalar, vshli_s) +DO_2SHIFT_SCALAR(VSHL_U_scalar, vshli_u) +DO_2SHIFT_SCALAR(VRSHL_S_scalar, vrshli_s) +DO_2SHIFT_SCALAR(VRSHL_U_scalar, vrshli_u) +DO_2SHIFT_SCALAR(VQSHL_S_scalar, vqshli_s) +DO_2SHIFT_SCALAR(VQSHL_U_scalar, vqshli_u) +DO_2SHIFT_SCALAR(VQRSHL_S_scalar, vqrshli_s) +DO_2SHIFT_SCALAR(VQRSHL_U_scalar, vqrshli_u) + #define DO_VSHLL(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ { \ -- 2.20.1 All the users of the vmlaldav formats have an 'x bit in bit 12 and an 'a' bit in bit 5; move these to the format rather than specifying them in each insn pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 &vmlaldav rdahi rdalo size qn qm x a -@vmlaldav .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav -@vmlaldav_nosz .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav +VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLSLDAV 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav +VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_nosz +VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz # Scalar operations -- 2.20.1 Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++++ target/arm/mve.decode | 18 +++++++++-- target/arm/mve_helper.c | 66 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 48 +++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp qm qn size mask &vcmp_scalar qn rm size mask &shl_scalar qda rm size +&vmaxv qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +{ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} + +{ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) +/* + * Vector max/min across vector. Unlike VADDV, we must + * read ra as the element size, not its full width. + * We work with int64_t internally for simplicity. + */ +#define DO_VMAXMINV(OP, ESIZE, TYPE, RATYPE, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + int64_t ra = (RATYPE)ra_in; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + ra = FN(ra, m[H##ESIZE(e)]); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define DO_VMAXMINV_U(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, uint8_t, uint8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, uint16_t, uint16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, uint32_t, uint32_t, FN) +#define DO_VMAXMINV_S(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, int8_t, int8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, int16_t, int16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, int32_t, int32_t, FN) + +/* + * Helpers for max and min of absolute values across vector: + * note that we only take the absolute value of 'm', not 'n' + */ +static int64_t do_maxa(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MAX(n, m); +} + +static int64_t do_mina(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MIN(n, m); +} + +DO_VMAXMINV_S(vmaxvs, DO_MAX) +DO_VMAXMINV_U(vmaxvu, DO_MAX) +DO_VMAXMINV_S(vminvs, DO_MIN) +DO_VMAXMINV_U(vminvu, DO_MIN) +/* + * VMAXAV, VMINAV treat the general purpose input as unsigned + * and the vector elements as signed. + */ +DO_VMAXMINV(vmaxavb, 1, int8_t, uint8_t, do_maxa) +DO_VMAXMINV(vmaxavh, 2, int16_t, uint16_t, do_maxa) +DO_VMAXMINV(vmaxavw, 4, int32_t, uint32_t, do_maxa) +DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) +DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) +DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCMP(VCMPGE, vcmpge) DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) + +static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) +{ + /* + * MIN/MAX operations across a vector: compute the min or + * max of the initial value in a general purpose register + * and all the elements in the vector, and store it back + * into the general purpose register. + */ + TCGv_ptr qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VMAXV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV(VMAXV_S, vmaxvs) +DO_VMAXV(VMAXV_U, vmaxvu) +DO_VMAXV(VMAXAV, vmaxav) +DO_VMAXV(VMINV_S, vminvs) +DO_VMAXV(VMINV_U, vminvu) +DO_VMAXV(VMINAV, vminav) -- 2.20.1 Implement the MVE VABAV insn, which computes absolute differences between elements of two vectors and accumulates the result into a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 7 +++++++ target/arm/mve.decode | 6 ++++++ target/arm/mve_helper.c | 26 +++++++++++++++++++++++ target/arm/translate-mve.c | 43 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vabavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp_scalar qn rm size mask &shl_scalar qda rm size &vmaxv qm rda size +&vabav qn qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar rdahi=%rdahi rdalo=%rdalo } +@vabav .... .... .. size:2 .... rda:4 .... .... .... &vabav qn=%qn qm=%qm + +VABAV_S 111 0 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav +VABAV_U 111 1 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav + # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) +#define DO_VABAV(OP, ESIZE, TYPE) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t ra) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm, *n = vn; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + int64_t n0 = n[H##ESIZE(e)]; \ + int64_t m0 = m[H##ESIZE(e)]; \ + uint32_t r = n0 >= m0 ? (n0 - m0) : (m0 - n0); \ + ra += r; \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } + +DO_VABAV(vabavsb, 1, int8_t) +DO_VABAV(vabavsh, 2, int16_t) +DO_VABAV(vabavsw, 4, int32_t) +DO_VABAV(vabavub, 1, uint8_t) +DO_VABAV(vabavuh, 2, uint16_t) +DO_VABAV(vabavuw, 4, uint32_t) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ DO_VMAXV(VMAXAV, vmaxav) DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) + +static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) +{ + /* Absolute difference accumulated across vector */ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qm | a->qn) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + qn = mve_qreg_ptr(a->qn); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + tcg_temp_free_ptr(qn); + mve_update_eci(s); + return true; +} + +#define DO_VABAV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vabav *a) \ + { \ + static MVEGenVABAVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vabav(s, a, fns[a->size]); \ + } + +DO_VABAV(VABAV_S, vabavs) +DO_VABAV(VABAV_U, vabavu) -- 2.20.1 Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++ target/arm/mve.decode | 12 ++++++ target/arm/mve_helper.c | 78 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 22 +++++++++++ 4 files changed, 132 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovunbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovuntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsh, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbuh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntuh, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vand, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vbic, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNB 111 1 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BU 111 1 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNT 111 1 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TU 111 1 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) +#define DO_VMOVN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], \ + m[H##LESIZE(le)], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMOVN(vmovnbb, false, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnbh, false, 2, uint16_t, 4, uint32_t) +DO_VMOVN(vmovntb, true, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnth, true, 2, uint16_t, 4, uint32_t) + +#define DO_VMOVN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + bool qc = false; \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + bool sat = false; \ + TYPE r = FN(m[H##LESIZE(le)], &sat); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VMOVN_SAT_UB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) + +#define DO_VMOVN_SAT_UH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) + +#define DO_VMOVN_SAT_SB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) + +#define DO_VMOVN_SAT_SH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) + +#define DO_VQMOVN_SB(N, SATP) \ + do_sat_bhs((int64_t)(N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQMOVN_UB(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT8_MAX, SATP) +#define DO_VQMOVUN_B(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT8_MAX, SATP) + +#define DO_VQMOVN_SH(N, SATP) \ + do_sat_bhs((int64_t)(N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQMOVN_UH(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT16_MAX, SATP) +#define DO_VQMOVUN_H(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT16_MAX, SATP) + +DO_VMOVN_SAT_SB(vqmovnbsb, vqmovntsb, DO_VQMOVN_SB) +DO_VMOVN_SAT_SH(vqmovnbsh, vqmovntsh, DO_VQMOVN_SH) +DO_VMOVN_SAT_UB(vqmovnbub, vqmovntub, DO_VQMOVN_UB) +DO_VMOVN_SAT_UH(vqmovnbuh, vqmovntuh, DO_VQMOVN_UH) +DO_VMOVN_SAT_SB(vqmovunbb, vqmovuntb, DO_VQMOVUN_B) +DO_VMOVN_SAT_SH(vqmovunbh, vqmovunth, DO_VQMOVUN_H) + uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, uint32_t shift) { diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +/* Narrowing moves: only size 0 and 1 are valid */ +#define DO_VMOVN(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + NULL, \ + NULL, \ + }; \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VMOVN(VMOVNB, vmovnb) +DO_VMOVN(VMOVNT, vmovnt) +DO_VMOVN(VQMOVUNB, vqmovunb) +DO_VMOVN(VQMOVUNT, vqmovunt) +DO_VMOVN(VQMOVN_BS, vqmovnbs) +DO_VMOVN(VQMOVN_TS, vqmovnts) +DO_VMOVN(VQMOVN_BU, vqmovnbu) +DO_VMOVN(VQMOVN_TU, vqmovntu) + static bool trans_VREV16(DisasContext *s, arg_1op *a) { static MVEGenOneOpFn * const fns[] = { -- 2.20.1 The MVEGenDualAccOpFn is a bit misnamed, since it is used for the "long dual accumulate" operations that use a 64-bit accumulator. Rename it to MVEGenLongDualAccOpFn so we can use the former name for the 32-bit accumulator insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenLongDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) } static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, - MVEGenDualAccOpFn *fn) + MVEGenLongDualAccOpFn *fn) { TCGv_ptr qn, qm; TCGv_i64 rda; @@ -XXX,XX +XXX,XX @@ static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavsh, gen_helper_mve_vmlaldavxsh }, { gen_helper_mve_vmlaldavsw, gen_helper_mve_vmlaldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavuh, NULL }, { gen_helper_mve_vmlaldavuw, NULL }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlsldavsh, gen_helper_mve_vmlsldavxsh }, { gen_helper_mve_vmlsldavsw, gen_helper_mve_vmlsldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhsw, gen_helper_mve_vrmlaldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhuw, NULL, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlsldavhsw, gen_helper_mve_vrmlsldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); -- 2.20.1 Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 17 ++++++++++ target/arm/mve.decode | 33 +++++++++++++++++--- target/arm/mve_helper.c | 41 ++++++++++++++++++++++++ target/arm/translate-mve.c | 64 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrmlaldavhuw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhxsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vmladavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vmladavsxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvub, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 %size_16 16:1 !function=plus_1 &vmlaldav rdahi rdalo size qn qm x a +&vmladav rda size qn qm x a @vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav @vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +@vmladav .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=%size_16 &vmladav +@vmladav_nosz .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=0 &vmladav -VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +{ + VMLADAV_S 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} +{ + VMLADAV_U 1111 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} + +{ + VMLSDAV 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 1 @vmladav + VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +} + +{ + VMLSDAV 1111 1110 1111 ... 0 ... . 1110 . 0 . 0 ... 1 @vmladav_nosz + VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz +} + +VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz +VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } -VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz - # Scalar operations VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavxsh, 2, int16_t, true, +=, -=) DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) +/* + * Multiply add dual accumulate ops + */ +#define DO_DAV(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t a) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *n = vn, *m = vm; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + if (e & 1) { \ + a ODDACC \ + n[H##ESIZE(e - 1 * XCHG)] * m[H##ESIZE(e)]; \ + } else { \ + a EVENACC \ + n[H##ESIZE(e + 1 * XCHG)] * m[H##ESIZE(e)]; \ + } \ + } \ + } \ + mve_advance_vpt(env); \ + return a; \ + } + +#define DO_DAV_S(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, int8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, int16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, int32_t, XCHG, EVENACC, ODDACC) + +#define DO_DAV_U(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, uint8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, uint16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, uint32_t, XCHG, EVENACC, ODDACC) + +DO_DAV_S(vmladavs, false, +=, +=) +DO_DAV_U(vmladavu, false, +=, +=) +DO_DAV_S(vmlsdav, false, +=, -=) +DO_DAV_S(vmladavsx, true, +=, +=) +DO_DAV_S(vmlsdavx, true, +=, -=) + /* * Rounding multiply add long dual accumulate high. In the pseudocode * this is implemented with a 72-bit internal accumulator value of which diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TC typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } +static bool do_dual_acc(DisasContext *s, arg_vmladav *a, MVEGenDualAccOpFn *fn) +{ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qn) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + + /* + * This insn is subject to beat-wise execution. Partial execution + * of an A=0 (no-accumulate) insn which does not execute the first + * beat must start with the current rda value, not 0. + */ + if (a->a || mve_skip_first_beat(s)) { + rda = load_reg(s, a->rda); + } else { + rda = tcg_const_i32(0); + } + + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + + mve_update_eci(s); + return true; +} + +#define DO_DUAL_ACC(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmladav *a) \ + { \ + static MVEGenDualAccOpFn * const fns[4][2] = { \ + { gen_helper_mve_##FN##b, gen_helper_mve_##FN##xb }, \ + { gen_helper_mve_##FN##h, gen_helper_mve_##FN##xh }, \ + { gen_helper_mve_##FN##w, gen_helper_mve_##FN##xw }, \ + { NULL, NULL }, \ + }; \ + return do_dual_acc(s, a, fns[a->size][a->x]); \ + } + +DO_DUAL_ACC(VMLADAV_S, vmladavs) +DO_DUAL_ACC(VMLSDAV, vmlsdav) + +static bool trans_VMLADAV_U(DisasContext *s, arg_vmladav *a) +{ + static MVEGenDualAccOpFn * const fns[4][2] = { + { gen_helper_mve_vmladavub, NULL }, + { gen_helper_mve_vmladavuh, NULL }, + { gen_helper_mve_vmladavuw, NULL }, + { NULL, NULL }, + }; + return do_dual_acc(s, a, fns[a->size][a->x]); +} + static void gen_vpst(DisasContext *s, uint32_t mask) { /* -- 2.20.1 Implement the MVE VMLA insn, which multiplies a vector by a scalar and accumulates into another vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 1 + target/arm/mve_helper.c | 5 +++++ target/arm/translate-mve.c | 1 + 4 files changed, 11 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlab, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlah, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlaw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar # The U bit (28) is don't-care because it does not affect the result +VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar # Vector add across vector diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by scalar plus vector */ +#define DO_VMLA(D, N, M) ((N) * (M) + (D)) + +DO_2OP_ACC_SCALAR_U(vmla, DO_VMLA) + /* Vector by vector plus scalar */ #define DO_VMLAS(D, N, M) ((N) * (D) + (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) -- 2.20.1 Implement the MVE saturating doubling multiply accumulate insns VQDMLAH, VQRDMLAH, VQDMLASH and VQRDMLASH. These perform a multiply, double, add the accumulator shifted by the element size, possibly round, saturate to twice the element size, then take the high half of the result. The *MLAH insns do vector * scalar + vector, and the *MLASH insns do vector * vector + scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 16 +++++++ target/arm/mve.decode | 5 ++ target/arm/mve_helper.c | 95 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 4 ++ 4 files changed, 120 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar +VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar +VQDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 110 .... @2scalar +VQDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 110 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +#define DO_2OP_SAT_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m, &sat), \ + mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +static int8_t do_vqdmlah_b(int8_t a, int8_t b, int8_t c, int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 8) + (round << 7); + return do_sat_bhw(r, INT16_MIN, INT16_MAX, sat) >> 8; +} + +static int16_t do_vqdmlah_h(int16_t a, int16_t b, int16_t c, + int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 16) + (round << 15); + return do_sat_bhw(r, INT32_MIN, INT32_MAX, sat) >> 16; +} + +static int32_t do_vqdmlah_w(int32_t a, int32_t b, int32_t c, + int round, bool *sat) +{ + /* + * Architecturally we should do the entire add, double, round + * and then check for saturation. We do three saturating adds, + * but we need to be careful about the order. If the first + * m1 + m2 saturates then it's impossible for the *2+rc to + * bring it back into the non-saturated range. However, if + * m1 + m2 is negative then it's possible that doing the doubling + * would take the intermediate result below INT64_MAX and the + * addition of the rounding constant then brings it back in range. + * So we add half the rounding constant and half the "c << esize" + * before doubling rather than adding the rounding constant after + * the doubling. + */ + int64_t m1 = (int64_t)a * b; + int64_t m2 = (int64_t)c << 31; + int64_t r; + if (sadd64_overflow(m1, m2, &r) || + sadd64_overflow(r, (round << 30), &r) || + sadd64_overflow(r, r, &r)) { + *sat = true; + return r < 0 ? INT32_MAX : INT32_MIN; + } + return r >> 32; +} + +/* + * The *MLAH insns are vector * scalar + vector; + * the *MLASH insns are vector * vector + scalar + */ +#define DO_VQDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 0, S) +#define DO_VQDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 0, S) +#define DO_VQDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 0, S) +#define DO_VQRDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 1, S) +#define DO_VQRDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 1, S) +#define DO_VQRDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 1, S) + +#define DO_VQDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 0, S) +#define DO_VQDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 0, S) +#define DO_VQDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 0, S) +#define DO_VQRDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 1, S) +#define DO_VQRDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 1, S) +#define DO_VQRDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 1, S) + +DO_2OP_SAT_ACC_SCALAR(vqdmlahb, 1, int8_t, DO_VQDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlahh, 2, int16_t, DO_VQDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlahw, 4, int32_t, DO_VQDMLAH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahb, 1, int8_t, DO_VQRDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahh, 2, int16_t, DO_VQRDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahw, 4, int32_t, DO_VQRDMLAH_W) + +DO_2OP_SAT_ACC_SCALAR(vqdmlashb, 1, int8_t, DO_VQDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlashh, 2, int16_t, DO_VQDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlashw, 4, int32_t, DO_VQDMLASH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashb, 1, int8_t, DO_VQRDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashh, 2, int16_t, DO_VQRDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashw, 4, int32_t, DO_VQRDMLASH_W) + /* Vector by scalar plus vector */ #define DO_VMLA(D, N, M) ((N) * (M) + (D)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) +DO_2OP_SCALAR(VQDMLAH, vqdmlah) +DO_2OP_SCALAR(VQRDMLAH, vqrdmlah) +DO_2OP_SCALAR(VQDMLASH, vqdmlash) +DO_2OP_SCALAR(VQRDMLASH, vqrdmlash) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE 1-operand saturating operations VQABS and VQNEG. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 50 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VABS_fp 1111 1111 1 . 11 .. 01 ... 0 0111 01 . 0 ... 0 @1op VNEG 1111 1111 1 . 11 .. 01 ... 0 0011 11 . 0 ... 0 @1op VNEG_fp 1111 1111 1 . 11 .. 01 ... 0 0111 11 . 0 ... 0 @1op +VQABS 1111 1111 1 . 11 .. 00 ... 0 0111 01 . 0 ... 0 @1op +VQNEG 1111 1111 1 . 11 .. 00 ... 0 0111 11 . 0 ... 0 @1op + &vdup qd rt size # Qd is in the fields usually named Qn @vdup .... .... . . .. ... . rt:4 .... . . . . .... qd=%qn &vdup diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) } mve_advance_vpt(env); } + +#define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], FN(m[H##ESIZE(e)], &sat), mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VQABS_B(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQABS_H(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQABS_W(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT32_MIN, INT32_MAX, SATP) + +#define DO_VQNEG_B(N, SATP) do_sat_bhs(-(int64_t)N, INT8_MIN, INT8_MAX, SATP) +#define DO_VQNEG_H(N, SATP) do_sat_bhs(-(int64_t)N, INT16_MIN, INT16_MAX, SATP) +#define DO_VQNEG_W(N, SATP) do_sat_bhs(-(int64_t)N, INT32_MIN, INT32_MAX, SATP) + +DO_1OP_SAT(vqabsb, 1, int8_t, DO_VQABS_B) +DO_1OP_SAT(vqabsh, 2, int16_t, DO_VQABS_H) +DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) + +DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) +DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) +DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLZ, vclz) DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +DO_1OP(VQABS, vqabs) +DO_1OP(VQNEG, vqneg) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMAXA and VMINA insns, which take the absolute value of the signed elements in the input vector and then accumulate the unsigned max or min into the destination vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 4 ++++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 40 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMAXA 111 0 1110 0 . 11 .. 11 ... 0 1110 1 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VMINA 111 0 1110 0 . 11 .. 11 ... 1 1110 1 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) + +/* + * VMAXA, VMINA: vd is unsigned; vm is signed, and we take its + * absolute value; we then do an unsigned comparison. + */ +#define DO_VMAXMINA(OP, ESIZE, STYPE, UTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + UTYPE *d = vd; \ + STYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + UTYPE r = DO_ABS(m[H##ESIZE(e)]); \ + r = FN(d[H##ESIZE(e)], r); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMAXMINA(vmaxab, 1, int8_t, uint8_t, DO_MAX) +DO_VMAXMINA(vmaxah, 2, int16_t, uint16_t, DO_MAX) +DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) +DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) +DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) +DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) DO_1OP(VQABS, vqabs) DO_1OP(VQNEG, vqneg) +DO_1OP(VMAXA, vmaxa) +DO_1OP(VMINA, vmina) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMOV forms that move data between 2 general-purpose registers and 2 32-bit lanes in a vector register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-a32.h | 1 + target/arm/mve.decode | 4 ++ target/arm/translate-mve.c | 85 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-vfp.c | 2 +- 4 files changed, 91 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); static inline TCGv_i32 load_cpu_offset(int offset) { diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# Moves between 2 32-bit vector lanes and 2 general purpose registers +VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd +VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd + # Vector 2-op VAND 1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz VBIC 1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) DO_VABAV(VABAV_S, vabavs) DO_VABAV(VABAV_U, vabavu) + +static bool trans_VMOV_to_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two 32-bit vector lanes to two general-purpose registers. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15 || + a->rt == a->rt2) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg index to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd, a->idx, MO_32); + store_reg(s, a->rt, tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd + 1, a->idx, MO_32); + store_reg(s, a->rt2, tmp); + } + + mve_update_and_store_eci(s); + return true; +} + +static bool trans_VMOV_from_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two general-purpose registers to two 32-bit vector lanes. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg idx to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = load_reg(s, a->rt); + write_neon_element32(tmp, vd, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = load_reg(s, a->rt2); + write_neon_element32(tmp, vd + 1, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + + mve_update_and_store_eci(s); + return true; +} diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return true; } -static bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) { /* * In a CPU with MVE, the VMOV (vector lane to general-purpose register) -- 2.20.1 Implement the MVE VPNOT insn, which inverts the bits in VPR.P0 (subject to both predication and to beatwise execution). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 1 + target/arm/mve.decode | 1 + target/arm/mve_helper.c | 17 +++++++++++++++++ target/arm/translate-mve.c | 19 +++++++++++++++++++ 4 files changed, 38 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) mve_advance_vpt(env); } +void HELPER(mve_vpnot)(CPUARMState *env) +{ + /* + * P0 bits for unexecuted beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed bits (where mask is 0) are 0. + * P0 bits otherwise are inverted. + * (This is the same logic as VCMP.) + * This insn is itself subject to predication and to beat-wise execution, + * and after it executes VPT state advances in the usual way. + */ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t beatpred = ~env->v7m.vpr & mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (beatpred & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) return true; } +static bool trans_VPNOT(DisasContext *s, arg_VPNOT *a) +{ + /* + * Invert the predicate in VPR.P0. We have call out to + * a helper because this insn itself is beatwise and can + * be predicated. + */ + if (!dc_isar_feature(aa32_mve, s)) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + gen_helper_mve_vpnot(cpu_env); + mve_update_eci(s); + return true; +} + static bool trans_VADDV(DisasContext *s, arg_VADDV *a) { /* VADDV: vector add across vector */ -- 2.20.1 Implement the MVE VCTP insn, which sets the VPR.P0 predicate bits so as to predicate any element at index Rn or greater is predicated. As with VPNOT, this insn itself is predicable and subject to beatwise execution. The calculation of the mask is the same as is used to determine ltpmask in mve_element_mask(), but we precalculate masklen in generated code to avoid having to have 4 helpers specialized by size. We put the decode line in with the low-overhead-loop insns in t32.decode because it's logically part of that collection of insn patterns, even though it is an MVE only insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/translate-a32.h | 1 + target/arm/t32.decode | 1 + target/arm/mve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-mve.c | 2 +- target/arm/translate.c | 33 +++++++++++++++++++++++++++++++++ 6 files changed, 58 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) +DEF_HELPER_FLAGS_2(mve_vctp, TCG_CALL_NO_WG, void, env, i32) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ long neon_element_offset(int reg, int element, MemOp memop); void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); +void mve_update_eci(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ BL 1111 0. .......... 11.1 ............ @branch24 # This is DLSTP DLS 1111 0 0000 0 size:2 rn:4 1110 0000 0000 0001 } + VCTP 1111 0 0000 0 size:2 rn:4 1110 1000 0000 0001 ] } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpnot)(CPUARMState *env) mve_advance_vpt(env); } +/* + * VCTP: P0 unexecuted bits unchanged, predicated bits zeroed, + * otherwise set according to value of Rn. The calculation of + * newmask here works in the same way as the calculation of the + * ltpmask in mve_element_mask(), but we have pre-calculated + * the masklen in the generated code. + */ +void HELPER(mve_vctp)(CPUARMState *env, uint32_t masklen) +{ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t newmask; + + assert(masklen <= 16); + newmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + newmask &= mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (newmask & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ bool mve_eci_check(DisasContext *s) } } -static void mve_update_eci(DisasContext *s) +void mve_update_eci(DisasContext *s) { /* * The helper function will always update the CPUState field, diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_LCTP(DisasContext *s, arg_LCTP *a) return true; } +static bool trans_VCTP(DisasContext *s, arg_VCTP *a) +{ + /* + * M-profile Create Vector Tail Predicate. This insn is itself + * predicated and is subject to beatwise execution. + */ + TCGv_i32 rn_shifted, masklen; + + if (!dc_isar_feature(aa32_mve, s) || a->rn == 13 || a->rn == 15) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * We pre-calculate the mask length here to avoid having + * to have multiple helpers specialized for size. + * We pass the helper "rn <= (1 << (4 - size)) ? (rn << size) : 16". + */ + rn_shifted = tcg_temp_new_i32(); + masklen = load_reg(s, a->rn); + tcg_gen_shli_i32(rn_shifted, masklen, a->size); + tcg_gen_movcond_i32(TCG_COND_LEU, masklen, + masklen, tcg_constant_i32(1 << (4 - a->size)), + rn_shifted, tcg_constant_i32(16)); + gen_helper_mve_vctp(cpu_env, masklen); + tcg_temp_free_i32(masklen); + tcg_temp_free_i32(rn_shifted); + mve_update_eci(s); + return true; +} static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half) { -- 2.20.1 Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++ target/arm/mve.decode | 12 ++++ target/arm/mve_helper.c | 129 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 97 ++++++++++++++++++++++++++++ 4 files changed, 270 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrb_h, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrb_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &shl_scalar qda rm size &vmaxv qm rda size &vabav qn qm rda size +&vldst_sg qd qm rn size msize os + +# scatter-gather memory size is in bits 6:4 +%sg_msize 6:1 4:1 @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @vldst_wn ... u:1 ... . . . . l:1 . rn:3 qd:3 . ... .. imm:7 &vldr_vstr +@vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ + qd=%qd qm=%qm msize=%sg_msize + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# gather loads/scatter stores +VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR +/* + * Gather loads/scatter stores. Here each element of Qm specifies + * an offset to use from the base register Rm. In the _os_ versions + * that offset is scaled by the element size. + * For loads, predicated lanes are zeroed instead of retaining + * their previous values. + */ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + OFFTYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + d[H##ESIZE(e)] = (mask & 1) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +/* We know here TYPE is unsigned so always the same as the offset type */ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + TYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + if (mask & 1) { \ + cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +/* + * 64-bit accesses are slightly different: they are done as two 32-bit + * accesses, controlled by the predicate mask for the relevant beat, + * and with a single 32-bit offset in the first of the two Qm elements. + * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + */ +#define DO_VLDR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSTR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + if (mask & 1) { \ + cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +#define ADDR_ADD(BASE, OFFSET) ((BASE) + (OFFSET)) +#define ADDR_ADD_OSH(BASE, OFFSET) ((BASE) + ((OFFSET) << 1)) +#define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) +#define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) + +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) + +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) + +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) + +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) + +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) #include "decode-mve.c.inc" typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) +static bool do_ldst_sg(DisasContext *s, arg_vldst_sg *a, MVEGenLdStSGFn fn) +{ + TCGv_i32 addr; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn || a->rn == 15) { + /* Rn case is UNPREDICTABLE */ + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + addr = load_reg(s, a->rn); + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, addr); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + tcg_temp_free_i32(addr); + mve_update_eci(s); + return true; +} + +/* + * The naming scheme here is "vldrb_sg_sh == in-memory byte loads + * signextended to halfword elements in register". _os_ indicates that + * the offsets in Qm should be scaled by the element size. + */ +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +/* VLDRB/VSTRB (ie msize 1) with OS=1 is UNPREDICTABLE; we UNDEF */ +static bool trans_VLDR_S_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { NULL, F(vldrb_sg_sh), F(vldrb_sg_sw), NULL }, + { NULL, NULL, F(vldrh_sg_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, NULL, F(vldrh_sg_os_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VLDR_U_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vldrb_sg_ub), F(vldrb_sg_uh), F(vldrb_sg_uw), NULL }, + { NULL, F(vldrh_sg_uh), F(vldrh_sg_uw), NULL }, + { NULL, NULL, F(vldrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vldrh_sg_os_uh), F(vldrh_sg_os_uw), NULL }, + { NULL, NULL, F(vldrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_os_ud) } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vstrb_sg_ub), F(vstrb_sg_uh), F(vstrb_sg_uw), NULL }, + { NULL, F(vstrh_sg_uh), F(vstrh_sg_uw), NULL }, + { NULL, NULL, F(vstrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vstrh_sg_os_uh), F(vstrh_sg_os_uw), NULL }, + { NULL, NULL, F(vstrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_os_ud) } + } + }; + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++ target/arm/mve.decode | 10 +++++ target/arm/mve_helper.c | 91 ++++++++++++++++++++++++-------------- target/arm/translate-mve.c | 72 ++++++++++++++++++++++++++++++ 4 files changed, 146 insertions(+), 32 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vmaxv qm rda size &vabav qn qm rda size &vldst_sg qd qm rn size msize os +&vldst_sg_imm qd qm a w imm # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ qd=%qd qm=%qm msize=%sg_msize +# Qm is in the fields usually labeled Qn +@vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ + qd=%qd qm=%qn + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg +VLDRW_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm +VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * For loads, predicated lanes are zeroed instead of retaining * their previous values. */ -#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H##ESIZE(e)]); \ d[H##ESIZE(e)] = (mask & 1) ? \ cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } /* We know here TYPE is unsigned so always the same as the offset type */ -#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ TYPE *d = vd; \ TYPE *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ if (mask & 1) { \ cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ } \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * accesses, controlled by the predicate mask for the relevant beat, * and with a single 32-bit offset in the first of the two Qm elements. * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + * Address writeback happens on the odd beats and updates the address + * stored in the even-beat element. */ -#define DO_VLDR64_SG(OP, ADDRFN) \ +#define DO_VLDR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } -#define DO_VSTR64_SG(OP, ADDRFN) \ +#define DO_VSTR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ uint32_t *d = vd; \ uint32_t *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ if (mask & 1) { \ cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ } \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) -DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) -DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) -DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) -DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) + +DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* * The mergemask(D, R, M) macro performs the operation "*D = R" but diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) #undef F +static bool do_ldst_sg_imm(DisasContext *s, arg_vldst_sg_imm *a, + MVEGenLdStSGFn *fn, unsigned msize) +{ + uint32_t offset; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + offset = a->imm << msize; + if (!a->a) { + offset = -offset; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(offset)); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +static bool trans_VLDRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrw_sg_uw, + gen_helper_mve_vldrw_sg_wb_uw, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VLDRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrd_sg_ud, + gen_helper_mve_vldrd_sg_wb_ud, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + +static bool trans_VSTRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrw_sg_uw, + gen_helper_mve_vstrw_sg_wb_uw, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrd_sg_ud, + gen_helper_mve_vstrd_sg_wb_ud, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE interleaving load/store functions VLD2, VLD4, VST2 and VST4. VLD2 loads 16 bytes of data from memory and writes to 2 consecutive Qregs; VLD4 loads 16 bytes of data from memory and writes to 4 consecutive Qregs. The 'pattern' field in the encoding determines the offset into memory which is accessed and also which elements in the Qregs are written to. (The intention is that a sequence of four consecutive VLD4 with different pattern values performs a complete de-interleaving load of 64 bytes into all elements of the 4 Qregs.) VST2 and VST4 do the same, but for stores. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 48 ++++++ target/arm/mve.decode | 11 ++ target/arm/mve_helper.c | 342 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 94 ++++++++++ 4 files changed, 495 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vld20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43w, TCG_CALL_NO_WG, void, env, i32, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vabav qn qm rda size &vldst_sg qd qm rn size msize os &vldst_sg_imm qd qm a w imm +&vldst_il qd rn size pat w # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ qd=%qd qm=%qn +# Deinterleaving load/interleaving store +@vldst_il .... .... .. w:1 . rn:4 .... ... size:2 pat:2 ..... &vldst_il \ + qd=%qd + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm +# deinterleaving loads/interleaving stores +VLD2 1111 1100 1 .. 1 .... ... 1 111 .. .. 00000 @vldst_il +VLD4 1111 1100 1 .. 1 .... ... 1 111 .. .. 00001 @vldst_il +VST2 1111 1100 1 .. 0 .... ... 1 111 .. .. 00000 @vldst_il +VST4 1111 1100 1 .. 0 .... ... 1 111 .. .. 00001 @vldst_il + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) +/* + * Deinterleaving loads/interleaving stores. + * + * For these helpers we are passed the index of the first Qreg + * (VLD2/VST2 will also access Qn+1, VLD4/VST4 access Qn .. Qn+3) + * and the value of the base address register Rn. + * The helpers are specialized for pattern and element size, so + * for instance vld42h is VLD4 with pattern 2, element size MO_16. + * + * These insns are beatwise but not predicated, so we must honour ECI, + * but need not look at mve_element_mask(). + * + * The pseudocode implements these insns with multiple memory accesses + * of the element size, but rules R_VVVG and R_FXDM permit us to make + * one 32-bit memory access per beat. + */ +#define DO_VLD4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H1(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H2(off[beat])] = data; \ + data >>= 16; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + qd[H2(off[beat])] = data; \ + } \ + } + +#define DO_VLD4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H4(off[beat] >> 2)] = data; \ + } \ + } + +DO_VLD4B(vld40b, 0, 1, 10, 11) +DO_VLD4B(vld41b, 2, 3, 12, 13) +DO_VLD4B(vld42b, 4, 5, 14, 15) +DO_VLD4B(vld43b, 6, 7, 8, 9) + +DO_VLD4H(vld40h, 0, 5) +DO_VLD4H(vld41h, 1, 6) +DO_VLD4H(vld42h, 2, 7) +DO_VLD4H(vld43h, 3, 4) + +DO_VLD4W(vld40w, 0, 1, 10, 11) +DO_VLD4W(vld41w, 2, 3, 12, 13) +DO_VLD4W(vld42w, 4, 5, 14, 15) +DO_VLD4W(vld43w, 6, 7, 8, 9) + +#define DO_VLD2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + qd[H1(off[beat] + (e >> 1))] = data; \ + } \ + } \ + } + +#define DO_VLD2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 2; e++, data >>= 16) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H2(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + qd[H4(off[beat] >> 3)] = data; \ + } \ + } + +DO_VLD2B(vld20b, 0, 2, 12, 14) +DO_VLD2B(vld21b, 4, 6, 8, 10) + +DO_VLD2H(vld20h, 0, 1, 6, 7) +DO_VLD2H(vld21h, 2, 3, 4, 5) + +DO_VLD2W(vld20w, 0, 4, 24, 28) +DO_VLD2W(vld21w, 8, 12, 16, 20) + +#define DO_VST4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 8) | qd[H1(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H2(off[beat])]; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + data |= qd[H2(off[beat])] << 16; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H4(off[beat] >> 2)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST4B(vst40b, 0, 1, 10, 11) +DO_VST4B(vst41b, 2, 3, 12, 13) +DO_VST4B(vst42b, 4, 5, 14, 15) +DO_VST4B(vst43b, 6, 7, 8, 9) + +DO_VST4H(vst40h, 0, 5) +DO_VST4H(vst41h, 1, 6) +DO_VST4H(vst42h, 2, 7) +DO_VST4H(vst43h, 3, 4) + +DO_VST4W(vst40w, 0, 1, 10, 11) +DO_VST4W(vst41w, 2, 3, 12, 13) +DO_VST4W(vst42w, 4, 5, 14, 15) +DO_VST4W(vst43w, 6, 7, 8, 9) + +#define DO_VST2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + data = (data << 8) | qd[H1(off[beat] + (e >> 1))]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 1; e >= 0; e--) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 16) | qd[H2(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + data = qd[H4(off[beat] >> 3)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST2B(vst20b, 0, 2, 12, 14) +DO_VST2B(vst21b, 4, 6, 8, 10) + +DO_VST2H(vst20h, 0, 1, 6, 7) +DO_VST2H(vst21h, 2, 3, 4, 5) + +DO_VST2W(vst20w, 0, 4, 24, 28) +DO_VST2W(vst21w, 8, 12, 16, 20) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStIlFn(TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) return do_ldst_sg_imm(s, a, fns[a->w], MO_64); } +static bool do_vldst_il(DisasContext *s, arg_vldst_il *a, MVEGenLdStIlFn *fn, + int addrinc) +{ + TCGv_i32 rn; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd) || + !fn || (a->rn == 13 && a->w) || a->rn == 15) { + /* Variously UNPREDICTABLE or UNDEF or related-encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + rn = load_reg(s, a->rn); + /* + * We pass the index of Qd, not a pointer, because the helper must + * access multiple Q registers starting at Qd and working up. + */ + fn(cpu_env, tcg_constant_i32(a->qd), rn); + + if (a->w) { + tcg_gen_addi_i32(rn, rn, addrinc); + store_reg(s, a->rn, rn); + } else { + tcg_temp_free_i32(rn); + } + mve_update_and_store_eci(s); + return true; +} + +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +static bool trans_VLD2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld20b), F(vld20h), F(vld20w), NULL, }, + { F(vld21b), F(vld21h), F(vld21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VLD4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld40b), F(vld40h), F(vld40w), NULL, }, + { F(vld41b), F(vld41h), F(vld41w), NULL, }, + { F(vld42b), F(vld42h), F(vld42w), NULL, }, + { F(vld43b), F(vld43h), F(vld43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +static bool trans_VST2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst20b), F(vst20h), F(vst20w), NULL, }, + { F(vst21b), F(vst21h), F(vst21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VST4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst40b), F(vst40h), F(vst40w), NULL, }, + { F(vst41b), F(vst41h), F(vst41w), NULL, }, + { F(vst42b), F(vst42h), F(vst42w), NULL, }, + { F(vst43b), F(vst43h), F(vst43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 We're about to make a code change to the sdiv and udiv helper functions, so first fix their indentation and coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-2-peter.maydell@linaro.org --- target/arm/helper.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) int32_t HELPER(sdiv)(int32_t num, int32_t den) { - if (den == 0) - return 0; - if (num == INT_MIN && den == -1) - return INT_MIN; + if (den == 0) { + return 0; + } + if (num == INT_MIN && den == -1) { + return INT_MIN; + } return num / den; } uint32_t HELPER(udiv)(uint32_t num, uint32_t den) { - if (den == 0) - return 0; + if (den == 0) { + return 0; + } return num / den; } -- 2.20.1 Unlike A-profile, for M-profile the UDIV and SDIV insns can be configured to raise an exception on division by zero, using the CCR DIV_0_TRP bit. Implement support for setting this bit by making the helper functions raise the appropriate exception. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-3-peter.maydell@linaro.org --- target/arm/cpu.h | 1 + target/arm/helper.h | 4 ++-- target/arm/helper.c | 19 +++++++++++++++++-- target/arm/m_helper.c | 4 ++++ target/arm/translate.c | 4 ++-- 5 files changed, 26 insertions(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ #define EXCP_LAZYFP 20 /* v7M fault during lazy FP stacking */ #define EXCP_LSERR 21 /* v8M LSERR SecureFault */ #define EXCP_UNALIGNED 22 /* v7M UNALIGNED UsageFault */ +#define EXCP_DIVBYZERO 23 /* v7M DIVBYZERO UsageFault */ /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(add_saturate, i32, env, i32, i32) DEF_HELPER_3(sub_saturate, i32, env, i32, i32) DEF_HELPER_3(add_usaturate, i32, env, i32, i32) DEF_HELPER_3(sub_usaturate, i32, env, i32, i32) -DEF_HELPER_FLAGS_2(sdiv, TCG_CALL_NO_RWG_SE, s32, s32, s32) -DEF_HELPER_FLAGS_2(udiv, TCG_CALL_NO_RWG_SE, i32, i32, i32) +DEF_HELPER_FLAGS_3(sdiv, TCG_CALL_NO_RWG, s32, env, s32, s32) +DEF_HELPER_FLAGS_3(udiv, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_1(rbit, TCG_CALL_NO_RWG_SE, i32, i32) #define PAS_OP(pfx) \ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sxtb16)(uint32_t x) return res; } +static void handle_possible_div0_trap(CPUARMState *env, uintptr_t ra) +{ + /* + * Take a division-by-zero exception if necessary; otherwise return + * to get the usual non-trapping division behaviour (result of 0) + */ + if (arm_feature(env, ARM_FEATURE_M) + && (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_DIV_0_TRP_MASK)) { + raise_exception_ra(env, EXCP_DIVBYZERO, 0, 1, ra); + } +} + uint32_t HELPER(uxtb16)(uint32_t x) { uint32_t res; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) return res; } -int32_t HELPER(sdiv)(int32_t num, int32_t den) +int32_t HELPER(sdiv)(CPUARMState *env, int32_t num, int32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } if (num == INT_MIN && den == -1) { @@ -XXX,XX +XXX,XX @@ int32_t HELPER(sdiv)(int32_t num, int32_t den) return num / den; } -uint32_t HELPER(udiv)(uint32_t num, uint32_t den) +uint32_t HELPER(udiv)(CPUARMState *env, uint32_t num, uint32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } return num / den; @@ -XXX,XX +XXX,XX @@ void arm_log_exception(int idx) [EXCP_LAZYFP] = "v7M exception during lazy FP stacking", [EXCP_LSERR] = "v8M LSERR UsageFault", [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", + [EXCP_DIVBYZERO] = "v7M DIVBYZERO UsageFault", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_UNALIGNED_MASK; break; + case EXCP_DIVBYZERO: + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_DIVBYZERO_MASK; + break; case EXCP_SWI: /* The PC already points to the next instruction. */ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool op_div(DisasContext *s, arg_rrr *a, bool u) t1 = load_reg(s, a->rn); t2 = load_reg(s, a->rm); if (u) { - gen_helper_udiv(t1, t1, t2); + gen_helper_udiv(t1, cpu_env, t1, t2); } else { - gen_helper_sdiv(t1, t1, t2); + gen_helper_sdiv(t1, cpu_env, t1, t2); } tcg_temp_free_i32(t2); store_reg(s, a->rd, t1); -- 2.20.1 From: Hamza Mahfooz <someguy@effective-light.com> As per commit 5626f8c6d468 ("rcu: Add automatically released rcu_read_lock variants"), RCU_READ_LOCK_GUARD() should be used instead of rcu_read_{un}lock(). Signed-off-by: Hamza Mahfooz <someguy@effective-light.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20210727235201.11491-1-someguy@effective-light.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, hwaddr xlat, len, doorbell_gpa; MemoryRegionSection mrs; MemoryRegion *mr; - int ret = 1; if (as == &address_space_memory) { return 0; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, /* MSI doorbell address is translated by an IOMMU */ - rcu_read_lock(); + RCU_READ_LOCK_GUARD(); + mr = address_space_translate(as, address, &xlat, &len, true, MEMTXATTRS_UNSPECIFIED); + if (!mr) { - goto unlock; + return 1; } + mrs = memory_region_find(mr, xlat, 1); + if (!mrs.mr) { - goto unlock; + return 1; } doorbell_gpa = mrs.offset_within_address_space; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, trace_kvm_arm_fixup_msi_route(address, doorbell_gpa); - ret = 0; - -unlock: - rcu_read_unlock(); - return ret; + return 0; } int kvm_arch_add_msi_route_post(struct kvm_irq_routing_entry *route, -- 2.20.1 From: Jan Luebbe <jlu@pengutronix.de> Break events are currently only handled by chardev/char-serial.c, so we just ignore errors, which results in no behaviour change for other chardevs. Signed-off-by: Jan Luebbe <jlu@pengutronix.de> Message-id: 20210806144700.3751979-1-jlu@pengutronix.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/pl011.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties-system.h" #include "migration/vmstate.h" #include "chardev/char-fe.h" +#include "chardev/char-serial.h" #include "qemu/log.h" #include "qemu/module.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, s->read_count = 0; s->read_pos = 0; } + if ((s->lcr ^ value) & 0x1) { + int break_enable = value & 0x1; + qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_BREAK, + &break_enable); + } s->lcr = value; pl011_set_read_trigger(s); break; -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 and ASRC as unimplemented devices to avoid random Linux kernel crashes, such as Unhandled fault: external abort on non-linefetch (0x808) at 0xd1580010 pgd = (ptrval) [d1580010] *pgd=8231b811, *pte=02034653, *ppte=02034453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c095837c>] (_regmap_update_bits+0xe4/0xec) [<c095837c>] (_regmap_update_bits) from [<c09599b4>] (regmap_update_bits_base+0x50/0x74) [<c09599b4>] (regmap_update_bits_base) from [<c0d3e9e4>] (fsl_asrc_runtime_resume+0x1e4/0x21c) [<c0d3e9e4>] (fsl_asrc_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d3ecc4>] (fsl_asrc_probe+0x2a8/0x708) [<c0d3ecc4>] (fsl_asrc_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) or Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810160318.87376-1-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx6ul.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) */ create_unimplemented_device("sdma", FSL_IMX6UL_SDMA_ADDR, 0x4000); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX6UL_SAI1_ADDR, 0x4000); + create_unimplemented_device("sai2", FSL_IMX6UL_SAI2_ADDR, 0x4000); + create_unimplemented_device("sai3", FSL_IMX6UL_SAI3_ADDR, 0x4000); + /* * PWM */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) create_unimplemented_device("pwm3", FSL_IMX6UL_PWM3_ADDR, 0x4000); create_unimplemented_device("pwm4", FSL_IMX6UL_PWM4_ADDR, 0x4000); + /* + * Audio ASRC (asynchronous sample rate converter) + */ + create_unimplemented_device("asrc", FSL_IMX6UL_ASRC_ADDR, 0x4000); + /* * CAN */ -- 2.20.1 From: "Wen, Jianxian" <Jianxian.Wen@verisilicon.com> Add property memory region which can connect with IOMMU region to support SMMU translate. Signed-off-by: Jianxian Wen <jianxian.wen@verisilicon.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 4C23C17B8E87E74E906A25A3254A03F4FA1FEC31@SHASXM03.verisilicon.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/exynos4210.c | 3 +++ hw/arm/xilinx_zynq.c | 3 +++ hw/dma/pl330.c | 26 ++++++++++++++++++++++---- 3 files changed, 28 insertions(+), 4 deletions(-) diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static DeviceState *pl330_create(uint32_t base, qemu_or_irq *orgate, int i; dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(get_system_memory()), + &error_fatal); qdev_prop_set_uint8(dev, "num_events", nevents); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", nreq); diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[39-IRQ_OFFSET]); dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(address_space_mem), + &error_fatal); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", 4); qdev_prop_set_uint8(dev, "num_events", 16); diff --git a/hw/dma/pl330.c b/hw/dma/pl330.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/pl330.c +++ b/hw/dma/pl330.c @@ -XXX,XX +XXX,XX @@ struct PL330State { uint8_t num_faulting; uint8_t periph_busy[PL330_PERIPH_NUM]; + /* Memory region that DMA operation access */ + MemoryRegion *mem_mr; + AddressSpace *mem_as; }; #define TYPE_PL330 "pl330" @@ -XXX,XX +XXX,XX @@ static inline const PL330InsnDesc *pl330_fetch_insn(PL330Chan *ch) uint8_t opcode; int i; - dma_memory_read(&address_space_memory, ch->pc, &opcode, 1); + dma_memory_read(ch->parent->mem_as, ch->pc, &opcode, 1); for (i = 0; insn_desc[i].size; i++) { if ((opcode & insn_desc[i].opmask) == insn_desc[i].opcode) { return &insn_desc[i]; @@ -XXX,XX +XXX,XX @@ static inline void pl330_exec_insn(PL330Chan *ch, const PL330InsnDesc *insn) uint8_t buf[PL330_INSN_MAXSIZE]; assert(insn->size <= PL330_INSN_MAXSIZE); - dma_memory_read(&address_space_memory, ch->pc, buf, insn->size); + dma_memory_read(ch->parent->mem_as, ch->pc, buf, insn->size); insn->exec(ch, buf[0], &buf[1], insn->size - 1); } @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) if (q != NULL && q->len <= pl330_fifo_num_free(&s->fifo)) { int len = q->len - (q->addr & (q->len - 1)); - dma_memory_read(&address_space_memory, q->addr, buf, len); + dma_memory_read(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) fifo_res = pl330_fifo_get(&s->fifo, buf, len, q->tag); } if (fifo_res == PL330_FIFO_OK || q->z) { - dma_memory_write(&address_space_memory, q->addr, buf, len); + dma_memory_write(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static void pl330_realize(DeviceState *dev, Error **errp) "dma", PL330_IOMEM_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + if (!s->mem_mr) { + error_setg(errp, "'memory' link is not set"); + return; + } else if (s->mem_mr == get_system_memory()) { + /* Avoid creating new AS for system memory. */ + s->mem_as = &address_space_memory; + } else { + s->mem_as = g_new0(AddressSpace, 1); + address_space_init(s->mem_as, s->mem_mr, + memory_region_name(s->mem_mr)); + } + s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pl330_exec_cycle_timer, s); s->cfg[0] = (s->mgr_ns_at_rst ? 0x4 : 0) | @@ -XXX,XX +XXX,XX @@ static Property pl330_properties[] = { DEFINE_PROP_UINT8("rd_q_dep", PL330State, rd_q_dep, 16), DEFINE_PROP_UINT16("data_buffer_dep", PL330State, data_buffer_dep, 256), + DEFINE_PROP_LINK("memory", PL330State, mem_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Eduardo Habkost <ehabkost@redhat.com> The SBSA_GWDT enum value conflicts with the SBSA_GWDT() QOM type checking helper, preventing us from using a OBJECT_DEFINE* or DEFINE_INSTANCE_CHECKER macro for the SBSA_GWDT() wrapper. If I understand the SBSA 6.0 specification correctly, the signal being connected to IRQ 16 is the WS0 output signal from the Generic Watchdog. Rename the enum value to SBSA_GWDT_WS0 to be more explicit and avoid the name conflict. Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20210806023119.431680-1-ehabkost@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ enum { SBSA_GIC_DIST, SBSA_GIC_REDIST, SBSA_SECURE_EC, - SBSA_GWDT, + SBSA_GWDT_WS0, SBSA_GWDT_REFRESH, SBSA_GWDT_CONTROL, SBSA_SMMU, @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_AHCI] = 10, [SBSA_EHCI] = 11, [SBSA_SMMU] = 12, /* ... to 15 */ - [SBSA_GWDT] = 16, + [SBSA_GWDT_WS0] = 16, }; static const char * const valid_cpus[] = { @@ -XXX,XX +XXX,XX @@ static void create_wdt(const SBSAMachineState *sms) hwaddr cbase = sbsa_ref_memmap[SBSA_GWDT_CONTROL].base; DeviceState *dev = qdev_new(TYPE_WDT_SBSA); SysBusDevice *s = SYS_BUS_DEVICE(dev); - int irq = sbsa_ref_irqmap[SBSA_GWDT]; + int irq = sbsa_ref_irqmap[SBSA_GWDT_WS0]; sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, rbase); -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 as unimplemented devices to avoid Linux kernel crashes such as the following. Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0-rc5 #1 ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810175607.538090-1-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 5 +++++ hw/arm/fsl-imx7.c | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_UART6_ADDR = 0x30A80000, FSL_IMX7_UART7_ADDR = 0x30A90000, + FSL_IMX7_SAI1_ADDR = 0x308A0000, + FSL_IMX7_SAI2_ADDR = 0x308B0000, + FSL_IMX7_SAI3_ADDR = 0x308C0000, + FSL_IMX7_SAIn_SIZE = 0x10000, + FSL_IMX7_ENET1_ADDR = 0x30BE0000, FSL_IMX7_ENET2_ADDR = 0x30BF0000, diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("can1", FSL_IMX7_CAN1_ADDR, FSL_IMX7_CANn_SIZE); create_unimplemented_device("can2", FSL_IMX7_CAN2_ADDR, FSL_IMX7_CANn_SIZE); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX7_SAI1_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI2_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI3_ADDR, FSL_IMX7_SAIn_SIZE); + /* * OCOTP */ -- 2.20.1 From: Sebastian Meyer <meyer@absint.com> With gdb 9.0 and better it is possible to connect to a gdbstub over unix sockets, which is better than a TCP socket connection in some situations. The QEMU command line to set this up is non-obvious; document it. Signed-off-by: Sebastian Meyer <meyer@absint.com> Message-id: 162867284829.27377.4784930719350564918-0@git.sr.ht [PMM: Tweaked commit message; adjusted wording in a couple of places; fixed rST formatting issue; moved section up out of the 'advanced debugging options' subsection] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/gdb.rst | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/docs/system/gdb.rst b/docs/system/gdb.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/gdb.rst +++ b/docs/system/gdb.rst @@ -XXX,XX +XXX,XX @@ The ``-s`` option will make QEMU listen for an incoming connection from gdb on TCP port 1234, and ``-S`` will make QEMU not start the guest until you tell it to from gdb. (If you want to specify which TCP port to use or to use something other than TCP for the gdbstub -connection, use the ``-gdb dev`` option instead of ``-s``.) +connection, use the ``-gdb dev`` option instead of ``-s``. See +`Using unix sockets`_ for an example.) .. parsed-literal:: @@ -XXX,XX +XXX,XX @@ not just those in the cluster you are currently working on:: (gdb) set schedule-multiple on +Using unix sockets +================== + +An alternate method for connecting gdb to the QEMU gdbstub is to use +a unix socket (if supported by your operating system). This is useful when +running several tests in parallel, or if you do not have a known free TCP +port (e.g. when running automated tests). + +First create a chardev with the appropriate options, then +instruct the gdbserver to use that device: + +.. parsed-literal:: + + |qemu_system| -chardev socket,path=/tmp/gdb-socket,server=on,wait=off,id=gdb0 -gdb chardev:gdb0 -S ... + +Start gdb as before, but this time connect using the path to +the socket:: + + (gdb) target remote /tmp/gdb-socket + +Note that to use a unix socket for the connection you will need +gdb version 9.0 or newer. + Advanced debugging options ========================== -- 2.20.1