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 Big fat pullreq this time around, because it has all of RTH's SVE2 emulation patchset in it. -- PMM The following changes since commit 0dab1d36f55c3ed649bb8e4c74b9269ef3a63049: Merge remote-tracking branch 'remotes/stefanha-gitlab/tags/block-pull-request' into staging (2021-05-24 15:48:08 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210525 for you to fetch changes up to f8680aaa6e5bfc6022b75157c23db7d2ea98ab11: target/arm: Enable SVE2 and related extensions (2021-05-25 16:01:44 +0100) ---------------------------------------------------------------- target-arm queue: * Implement SVE2 emulation * Implement integer matrix multiply accumulate * Implement FEAT_TLBIOS * Implement FEAT_TLBRANGE * disas/libvixl: Protect C system header for C++ compiler * Use correct SP in M-profile exception return * AN524, AN547: Correct modelling of internal SRAMs * hw/intc/arm_gicv3_cpuif: Fix EOIR write access check logic * hw/arm/smmuv3: Another range invalidation fix ---------------------------------------------------------------- Eric Auger (1): hw/arm/smmuv3: Another range invalidation fix Peter Maydell (8): hw/intc/arm_gicv3_cpuif: Fix EOIR write access check logic hw/arm/mps2-tz: Don't duplicate modelling of SRAM in AN524 hw/arm/mps2-tz: Make SRAM_ADDR_WIDTH board-specific hw/arm/armsse.c: Correct modelling of SSE-300 internal SRAMs hw/arm/armsse: Convert armsse_realize() to use ERRP_GUARD hw/arm/mps2-tz: Allow board to specify a boot RAM size hw/arm: Model TCMs in the SSE-300, not the AN547 target/arm: Use correct SP in M-profile exception return Philippe Mathieu-Daudé (1): disas/libvixl: Protect C system header for C++ compiler Rebecca Cran (3): target/arm: Add support for FEAT_TLBIRANGE target/arm: Add support for FEAT_TLBIOS target/arm: set ID_AA64ISAR0.TLB to 2 for max AARCH64 CPU type Richard Henderson (84): accel/tcg: Replace g_new() + memcpy() by g_memdup() accel/tcg: Pass length argument to tlb_flush_range_locked() accel/tlb: Rename TLBFlushPageBitsByMMUIdxData -> TLBFlushRangeData accel/tcg: Remove {encode,decode}_pbm_to_runon accel/tcg: Add tlb_flush_range_by_mmuidx() accel/tcg: Add tlb_flush_range_by_mmuidx_all_cpus() accel/tlb: Add tlb_flush_range_by_mmuidx_all_cpus_synced() accel/tcg: Rename tlb_flush_page_bits -> range]_by_mmuidx_async_0 accel/tlb: Rename tlb_flush_[page_bits > range]_by_mmuidx_async_[2 > 1] target/arm: Add ID_AA64ZFR0 fields and isar_feature_aa64_sve2 target/arm: Implement SVE2 Integer Multiply - Unpredicated target/arm: Implement SVE2 integer pairwise add and accumulate long target/arm: Implement SVE2 integer unary operations (predicated) target/arm: Split out saturating/rounding shifts from neon target/arm: Implement SVE2 saturating/rounding bitwise shift left (predicated) target/arm: Implement SVE2 integer halving add/subtract (predicated) target/arm: Implement SVE2 integer pairwise arithmetic target/arm: Implement SVE2 saturating add/subtract (predicated) target/arm: Implement SVE2 integer add/subtract long target/arm: Implement SVE2 integer add/subtract interleaved long target/arm: Implement SVE2 integer add/subtract wide target/arm: Implement SVE2 integer multiply long target/arm: Implement SVE2 PMULLB, PMULLT target/arm: Implement SVE2 bitwise shift left long target/arm: Implement SVE2 bitwise exclusive-or interleaved target/arm: Implement SVE2 bitwise permute target/arm: Implement SVE2 complex integer add target/arm: Implement SVE2 integer absolute difference and accumulate long target/arm: Implement SVE2 integer add/subtract long with carry target/arm: Implement SVE2 bitwise shift right and accumulate target/arm: Implement SVE2 bitwise shift and insert target/arm: Implement SVE2 integer absolute difference and accumulate target/arm: Implement SVE2 saturating extract narrow target/arm: Implement SVE2 SHRN, RSHRN target/arm: Implement SVE2 SQSHRUN, SQRSHRUN target/arm: Implement SVE2 UQSHRN, UQRSHRN target/arm: Implement SVE2 SQSHRN, SQRSHRN target/arm: Implement SVE2 WHILEGT, WHILEGE, WHILEHI, WHILEHS target/arm: Implement SVE2 WHILERW, WHILEWR target/arm: Implement SVE2 bitwise ternary operations target/arm: Implement SVE2 saturating multiply-add long target/arm: Implement SVE2 saturating multiply-add high target/arm: Implement SVE2 integer multiply-add long target/arm: Implement SVE2 complex integer multiply-add target/arm: Implement SVE2 XAR target/arm: Use correct output type for gvec_sdot_*_b target/arm: Pass separate addend to {U, S}DOT helpers target/arm: Pass separate addend to FCMLA helpers target/arm: Split out formats for 2 vectors + 1 index target/arm: Split out formats for 3 vectors + 1 index target/arm: Implement SVE2 integer multiply (indexed) target/arm: Implement SVE2 integer multiply-add (indexed) target/arm: Implement SVE2 saturating multiply-add high (indexed) target/arm: Implement SVE2 saturating multiply-add (indexed) target/arm: Implement SVE2 saturating multiply (indexed) target/arm: Implement SVE2 signed saturating doubling multiply high target/arm: Implement SVE2 saturating multiply high (indexed) target/arm: Implement SVE2 multiply-add long (indexed) target/arm: Implement SVE2 integer multiply long (indexed) target/arm: Implement SVE2 complex integer multiply-add (indexed) target/arm: Implement SVE2 complex integer dot product target/arm: Macroize helper_gvec_{s,u}dot_{b,h} target/arm: Macroize helper_gvec_{s,u}dot_idx_{b,h} target/arm: Implement SVE mixed sign dot product (indexed) target/arm: Implement SVE mixed sign dot product target/arm: Implement SVE2 crypto unary operations target/arm: Implement SVE2 crypto destructive binary operations target/arm: Implement SVE2 crypto constructive binary operations target/arm: Implement SVE2 FCVTNT target/arm: Share table of sve load functions target/arm: Tidy do_ldrq target/arm: Implement SVE2 LD1RO target/arm: Implement 128-bit ZIP, UZP, TRN target/arm: Move endian adjustment macros to vec_internal.h target/arm: Implement aarch64 SUDOT, USDOT target/arm: Split out do_neon_ddda_fpst target/arm: Remove unused fpst from VDOT_scalar target/arm: Fix decode for VDOT (indexed) target/arm: Split out do_neon_ddda target/arm: Split decode of VSDOT and VUDOT target/arm: Implement aarch32 VSUDOT, VUSDOT target/arm: Implement integer matrix multiply accumulate linux-user/aarch64: Enable hwcap bits for sve2 and related extensions target/arm: Enable SVE2 and related extensions Stephen Long (17): target/arm: Implement SVE2 floating-point pairwise target/arm: Implement SVE2 MATCH, NMATCH target/arm: Implement SVE2 ADDHNB, ADDHNT target/arm: Implement SVE2 RADDHNB, RADDHNT target/arm: Implement SVE2 SUBHNB, SUBHNT target/arm: Implement SVE2 RSUBHNB, RSUBHNT target/arm: Implement SVE2 HISTCNT, HISTSEG target/arm: Implement SVE2 scatter store insns target/arm: Implement SVE2 gather load insns target/arm: Implement SVE2 FMMLA target/arm: Implement SVE2 SPLICE, EXT target/arm: Implement SVE2 TBL, TBX target/arm: Implement SVE2 FCVTLT target/arm: Implement SVE2 FCVTXNT, FCVTX target/arm: Implement SVE2 FLOGB target/arm: Implement SVE2 bitwise shift immediate target/arm: Implement SVE2 fp multiply-add long disas/libvixl/vixl/code-buffer.h | 2 +- disas/libvixl/vixl/globals.h | 16 +- disas/libvixl/vixl/invalset.h | 2 +- disas/libvixl/vixl/platform.h | 2 + disas/libvixl/vixl/utils.h | 2 +- include/exec/exec-all.h | 44 + include/hw/arm/armsse.h | 2 + target/arm/cpu.h | 76 + target/arm/helper-sve.h | 722 ++++++++- target/arm/helper.h | 110 +- target/arm/translate-a64.h | 3 + target/arm/vec_internal.h | 167 ++ target/arm/neon-shared.decode | 24 +- target/arm/sve.decode | 574 ++++++- accel/tcg/cputlb.c | 231 ++- hw/arm/armsse.c | 35 +- hw/arm/mps2-tz.c | 39 +- hw/arm/smmuv3.c | 50 +- hw/intc/arm_gicv3_cpuif.c | 48 +- linux-user/elfload.c | 10 + target/arm/cpu.c | 2 + target/arm/cpu64.c | 14 + target/arm/cpu_tcg.c | 1 + target/arm/helper.c | 327 +++- target/arm/kvm64.c | 21 +- target/arm/m_helper.c | 3 +- target/arm/neon_helper.c | 507 +----- target/arm/sve_helper.c | 2110 +++++++++++++++++++++++-- target/arm/translate-a64.c | 111 +- target/arm/translate-neon.c | 231 +-- target/arm/translate-sve.c | 3200 +++++++++++++++++++++++++++++++++++--- target/arm/vec_helper.c | 887 ++++++++--- disas/libvixl/vixl/utils.cc | 2 +- 33 files changed, 8275 insertions(+), 1300 deletions(-) From: Eric Auger <eric.auger@redhat.com> 6d9cd115b9 ("hw/arm/smmuv3: Enforce invalidation on a power of two range") failed to completely fix misalignment issues with range invalidation. For instance invalidations patterns like "invalidate 32 4kB pages starting from 0xff395000 are not correctly handled" due to the fact the previous fix only made sure the number of invalidated pages were a power of 2 but did not properly handle the start address was not aligned with the range. This can be noticed when boothing a fedora 33 with protected virtio-blk-pci. Signed-off-by: Eric Auger <eric.auger@redhat.com> Fixes: 6d9cd115b9 ("hw/arm/smmuv3: Enforce invalidation on a power of two range") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3.c | 50 +++++++++++++++++++++++++------------------------ 1 file changed, 26 insertions(+), 24 deletions(-) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova, static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) { - uint8_t scale = 0, num = 0, ttl = 0; - dma_addr_t addr = CMD_ADDR(cmd); + dma_addr_t end, addr = CMD_ADDR(cmd); uint8_t type = CMD_TYPE(cmd); uint16_t vmid = CMD_VMID(cmd); + uint8_t scale = CMD_SCALE(cmd); + uint8_t num = CMD_NUM(cmd); + uint8_t ttl = CMD_TTL(cmd); bool leaf = CMD_LEAF(cmd); uint8_t tg = CMD_TG(cmd); - uint64_t first_page = 0, last_page; - uint64_t num_pages = 1; + uint64_t num_pages; + uint8_t granule; int asid = -1; - if (tg) { - scale = CMD_SCALE(cmd); - num = CMD_NUM(cmd); - ttl = CMD_TTL(cmd); - num_pages = (num + 1) * BIT_ULL(scale); - } - if (type == SMMU_CMD_TLBI_NH_VA) { asid = CMD_ASID(cmd); } + if (!tg) { + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, 1, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1); + smmu_iotlb_inv_iova(s, asid, addr, tg, 1, ttl); + return; + } + + /* RIL in use */ + + num_pages = (num + 1) * BIT_ULL(scale); + granule = tg * 2 + 10; + /* Split invalidations into ^2 range invalidations */ - last_page = num_pages - 1; - while (num_pages) { - uint8_t granule = tg * 2 + 10; - uint64_t mask, count; + end = addr + (num_pages << granule) - 1; - mask = dma_aligned_pow2_mask(first_page, last_page, 64 - granule); - count = mask + 1; + while (addr != end + 1) { + uint64_t mask = dma_aligned_pow2_mask(addr, end, 64); - trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, count, ttl, leaf); - smmuv3_inv_notifiers_iova(s, asid, addr, tg, count); - smmu_iotlb_inv_iova(s, asid, addr, tg, count, ttl); - - num_pages -= count; - first_page += count; - addr += count * BIT_ULL(granule); + num_pages = (mask + 1) >> granule; + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages); + smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl); + addr += mask + 1; } } -- 2.20.1 In icc_eoir_write() we assume that we can identify the group of the IRQ being completed based purely on which register is being written to and the current CPU state, and that "CPU state matches group indicated by register" is the only necessary access check. This isn't correct: if the CPU is not in Secure state then EOIR1 will only complete Group 1 NS IRQs, but if the CPU is in EL3 it can complete both Group 1 S and Group 1 NS IRQs. (The pseudocode ICC_EOIR1_EL1 makes this clear.) We were also missing the logic to prevent EOIR0 writes completing G0 IRQs when they should not. Rearrange the logic to first identify the group of the current highest priority interrupt and then look at whether we should complete it or ignore the access based on which register was accessed and the state of the CPU. The resulting behavioural change is: * EL3 can now complete G1NS interrupts * G0 interrupt completion is now ignored if the GIC and the CPU have the security extension enabled and the CPU is not secure Reported-by: Chan Kim <ckim@etri.re.kr> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510150016.24910-1-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 48 ++++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 16 deletions(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int irq = value & 0xffffff; int grp; + bool is_eoir0 = ri->crm == 8; - if (icv_access(env, ri->crm == 8 ? HCR_FMO : HCR_IMO)) { + if (icv_access(env, is_eoir0 ? HCR_FMO : HCR_IMO)) { icv_eoir_write(env, ri, value); return; } - trace_gicv3_icc_eoir_write(ri->crm == 8 ? 0 : 1, + trace_gicv3_icc_eoir_write(is_eoir0 ? 0 : 1, gicv3_redist_affid(cs), value); - if (ri->crm == 8) { - /* EOIR0 */ - grp = GICV3_G0; - } else { - /* EOIR1 */ - if (arm_is_secure(env)) { - grp = GICV3_G1; - } else { - grp = GICV3_G1NS; - } - } - if (irq >= cs->gic->num_irq) { /* This handles two cases: * 1. If software writes the ID of a spurious interrupt [ie 1020-1023] @@ -XXX,XX +XXX,XX @@ static void icc_eoir_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } - if (icc_highest_active_group(cs) != grp) { - return; + grp = icc_highest_active_group(cs); + switch (grp) { + case GICV3_G0: + if (!is_eoir0) { + return; + } + if (!(cs->gic->gicd_ctlr & GICD_CTLR_DS) + && arm_feature(env, ARM_FEATURE_EL3) && !arm_is_secure(env)) { + return; + } + break; + case GICV3_G1: + if (is_eoir0) { + return; + } + if (!arm_is_secure(env)) { + return; + } + break; + case GICV3_G1NS: + if (is_eoir0) { + return; + } + if (!arm_is_el3_or_mon(env) && arm_is_secure(env)) { + return; + } + break; + default: + g_assert_not_reached(); } icc_drop_prio(cs, grp); -- 2.20.1 The SRAM at 0x2000_0000 is part of the SSE-200 itself, and we model it that way in hw/arm/armsse.c (along with the associated MPCs). We incorrectly also added an entry to the RAMInfo array for the AN524 in hw/arm/mps2-tz.c, which was pointless because the CPU would never see it. Delete it. The bug had no guest-visible effect because devices in the SSE-200 take priority over those in the board model (armsse.c maps s->board_memory at priority -2). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510190844.17799-2-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static const RAMInfo an524_raminfo[] = { { .size = 512 * KiB, .mpc = 0, .mrindex = 0, - }, { - .name = "sram", - .base = 0x20000000, - .size = 32 * 4 * KiB, - .mpc = -1, - .mrindex = 1, }, { /* We don't model QSPI flash yet; for now expose it as simple ROM */ .name = "QSPI", .base = 0x28000000, .size = 8 * MiB, .mpc = 1, - .mrindex = 2, + .mrindex = 1, .flags = IS_ROM, }, { .name = "DDR", -- 2.20.1 The AN547 sets the SRAM_ADDR_WIDTH for the SSE-300 to 21; since this is not the default value for the SSE-300, model this in mps2-tz.c as a per-board value. Reported-by: Devaraj Ranganna <devaraj.ranganna@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510190844.17799-3-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { int numirq; /* Number of external interrupts */ int uart_overflow_irq; /* number of the combined UART overflow IRQ */ uint32_t init_svtor; /* init-svtor setting for SSE */ + uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */ const RAMInfo *raminfo; const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) OBJECT(system_memory), &error_abort); qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq); qdev_prop_set_uint32(iotkitdev, "init-svtor", mmc->init_svtor); + qdev_prop_set_uint32(iotkitdev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width); qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk); qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk); sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; mps2tz_set_default_ram_info(mmc); @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; mps2tz_set_default_ram_info(mmc); @@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) mmc->numirq = 95; mmc->uart_overflow_irq = 47; mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 15; mmc->raminfo = an524_raminfo; mmc->armsse_type = TYPE_SSE200; mps2tz_set_default_ram_info(mmc); @@ -XXX,XX +XXX,XX @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data) mmc->numirq = 96; mmc->uart_overflow_irq = 48; mmc->init_svtor = 0x00000000; + mmc->sram_addr_width = 21; mmc->raminfo = an547_raminfo; mmc->armsse_type = TYPE_SSE300; mps2tz_set_default_ram_info(mmc); -- 2.20.1 The SSE-300 was not correctly modelling its internal SRAMs: * the SRAM address width default is 18 * the SRAM is mapped at 0x2100_0000, not 0x2000_0000 like the SSE-200 and IoTKit The default address width is no longer guest-visible since our only SSE-300 board sets it explicitly to a non-default value, but following the hardware's default will help for any future boards we need to model. Reported-by: Devaraj Ranganna <devaraj.ranganna@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510190844.17799-4-peter.maydell@linaro.org --- hw/arm/armsse.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ struct ARMSSEInfo { const char *cpu_type; uint32_t sse_version; int sram_banks; + uint32_t sram_bank_base; int num_cpus; uint32_t sys_version; uint32_t iidr; @@ -XXX,XX +XXX,XX @@ static Property sse300_properties[] = { DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), - DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), + DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 18), DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true), DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true), @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_IOTKIT, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"), .sram_banks = 1, + .sram_bank_base = 0x20000000, .num_cpus = 1, .sys_version = 0x41743, .iidr = 0, @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_SSE200, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"), .sram_banks = 4, + .sram_bank_base = 0x20000000, .num_cpus = 2, .sys_version = 0x22041743, .iidr = 0, @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .sse_version = ARMSSE_SSE300, .cpu_type = ARM_CPU_TYPE_NAME("cortex-m55"), .sram_banks = 2, + .sram_bank_base = 0x21000000, .num_cpus = 1, .sys_version = 0x7e00043b, .iidr = 0x74a0043b, @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) /* Map the upstream end of the MPC into the right place... */ sbd_mpc = SYS_BUS_DEVICE(&s->mpc[i]); memory_region_add_subregion(&s->container, - 0x20000000 + i * sram_bank_size, + info->sram_bank_base + i * sram_bank_size, sysbus_mmio_get_region(sbd_mpc, 1)); /* ...and its register interface */ memory_region_add_subregion(&s->container, 0x50083000 + i * 0x1000, -- 2.20.1 Convert armsse_realize() to use ERRP_GUARD(), following the rules in include/qapi/error.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510190844.17799-5-peter.maydell@linaro.org --- hw/arm/armsse.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) const ARMSSEDeviceInfo *devinfo; int i; MemoryRegion *mr; - Error *err = NULL; SysBusDevice *sbd_apb_ppc0; SysBusDevice *sbd_secctl; DeviceState *dev_apb_ppc0; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) DeviceState *dev_splitter; uint32_t addr_width_max; + ERRP_GUARD(); + if (!s->board_memory) { error_setg(errp, "memory property was not set"); return; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) uint32_t sram_bank_size = 1 << s->sram_addr_width; memory_region_init_ram(&s->sram[i], NULL, ramname, - sram_bank_size, &err); + sram_bank_size, errp); g_free(ramname); - if (err) { - error_propagate(errp, err); + if (*errp) { return; } object_property_set_link(OBJECT(&s->mpc[i]), "downstream", -- 2.20.1 Currently we model the ITCM in the AN547's RAMInfo list. This is incorrect because this RAM is really a part of the SSE-300. We can't just delete it from the RAMInfo list, though, because this would make boot_ram_size() assert because it wouldn't be able to find an entry in the list covering guest address 0. Allow a board to specify a boot RAM size manually if it doesn't have any RAM itself at address 0 and is relying on the SSE for that, and set the correct value for the AN547. The other boards can continue to use the "look it up from the RAMInfo list" logic. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510190844.17799-6-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { uint32_t sram_addr_width; /* SRAM_ADDR_WIDTH setting for SSE */ const RAMInfo *raminfo; const char *armsse_type; + uint32_t boot_ram_size; /* size of ram at address 0; 0 == find in raminfo */ }; struct MPS2TZMachineState { @@ -XXX,XX +XXX,XX @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms) const RAMInfo *p; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + /* + * Use a per-board specification (for when the boot RAM is in + * the SSE and so doesn't have a RAMInfo list entry) + */ + if (mmc->boot_ram_size) { + return mmc->boot_ram_size; + } + for (p = mmc->raminfo; p->name; p++) { if (p->base == boot_mem_base(mms)) { return p->size; @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->sram_addr_width = 15; mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); } @@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) mmc->sram_addr_width = 15; mmc->raminfo = an524_raminfo; mmc->armsse_type = TYPE_SSE200; + mmc->boot_ram_size = 0; mps2tz_set_default_ram_info(mmc); object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap); @@ -XXX,XX +XXX,XX @@ static void mps3tz_an547_class_init(ObjectClass *oc, void *data) mmc->sram_addr_width = 21; mmc->raminfo = an547_raminfo; mmc->armsse_type = TYPE_SSE300; + mmc->boot_ram_size = 512 * KiB; mps2tz_set_default_ram_info(mmc); } -- 2.20.1 The SSE-300 has an ITCM at 0x0000_0000 and a DTCM at 0x2000_0000. Currently we model these in the AN547 board, but this is conceptually wrong, because they are a part of the SSE-300 itself. Move the modelling of the TCMs out of mps2-tz.c into sse300.c. This has no guest-visible effects. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210510190844.17799-7-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 2 ++ hw/arm/armsse.c | 19 +++++++++++++++++++ hw/arm/mps2-tz.c | 12 ------------ 3 files changed, 21 insertions(+), 12 deletions(-) diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armsse.h +++ b/include/hw/arm/armsse.h @@ -XXX,XX +XXX,XX @@ struct ARMSSE { MemoryRegion alias2; MemoryRegion alias3[SSE_MAX_CPUS]; MemoryRegion sram[MAX_SRAM_BANKS]; + MemoryRegion itcm; + MemoryRegion dtcm; qemu_irq *exp_irqs[SSE_MAX_CPUS]; qemu_irq ppc0_irq; diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "qemu/module.h" #include "qemu/bitops.h" +#include "qemu/units.h" #include "qapi/error.h" #include "trace.h" #include "hw/sysbus.h" @@ -XXX,XX +XXX,XX @@ struct ARMSSEInfo { bool has_cpuid; bool has_cpu_pwrctrl; bool has_sse_counter; + bool has_tcms; Property *props; const ARMSSEDeviceInfo *devinfo; const bool *irq_is_common; @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = false, .has_cpu_pwrctrl = false, .has_sse_counter = false, + .has_tcms = false, .props = iotkit_properties, .devinfo = iotkit_devices, .irq_is_common = sse200_irq_is_common, @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = true, .has_cpu_pwrctrl = false, .has_sse_counter = false, + .has_tcms = false, .props = sse200_properties, .devinfo = sse200_devices, .irq_is_common = sse200_irq_is_common, @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .has_cpuid = true, .has_cpu_pwrctrl = true, .has_sse_counter = true, + .has_tcms = true, .props = sse300_properties, .devinfo = sse300_devices, .irq_is_common = sse300_irq_is_common, @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) sysbus_mmio_get_region(sbd, 1)); } + if (info->has_tcms) { + /* The SSE-300 has an ITCM at 0x0000_0000 and a DTCM at 0x2000_0000 */ + memory_region_init_ram(&s->itcm, NULL, "sse300-itcm", 512 * KiB, errp); + if (*errp) { + return; + } + memory_region_init_ram(&s->dtcm, NULL, "sse300-dtcm", 512 * KiB, errp); + if (*errp) { + return; + } + memory_region_add_subregion(&s->container, 0x00000000, &s->itcm); + memory_region_add_subregion(&s->container, 0x20000000, &s->dtcm); + } + /* Devices behind APB PPC0: * 0x40000000: timer0 * 0x40001000: timer1 diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static const RAMInfo an524_raminfo[] = { { }; static const RAMInfo an547_raminfo[] = { { - .name = "itcm", - .base = 0x00000000, - .size = 512 * KiB, - .mpc = -1, - .mrindex = 0, - }, { .name = "sram", .base = 0x01000000, .size = 2 * MiB, .mpc = 0, .mrindex = 1, - }, { - .name = "dtcm", - .base = 0x20000000, - .size = 4 * 128 * KiB, - .mpc = -1, - .mrindex = 2, }, { .name = "sram 2", .base = 0x21000000, -- 2.20.1 When an M-profile CPU is restoring registers from the stack on exception return, the stack pointer to use is determined based on bits in the magic exception return type value. We were not getting this logic entirely correct. Whether we use one of the Secure stack pointers or one of the Non-Secure stack pointers depends on the EXCRET.S bit. However, whether we use the MSP or the PSP then depends on the SPSEL bit in either the CONTROL_S or CONTROL_NS register. We were incorrectly selecting MSP vs PSP based on the EXCRET.SPSEL bit. (In the pseudocode this is in the PopStack() function, which calls LookUpSp_with_security_mode() which in turn looks at the relevant CONTROL.SPSEL bit.) The buggy behaviour wasn't noticeable in most cases, because we write EXCRET.SPSEL to the CONTROL.SPSEL bit for the S/NS register selected by EXCRET.ES, so we only do the wrong thing when EXCRET.S and EXCRET.ES are different. This will happen when secure code takes a secure exception, which then tail-chains to a non-secure exception which finally returns to the original secure code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210520130905.2049-1-peter.maydell@linaro.org --- target/arm/m_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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 @@ static void do_v7m_exception_exit(ARMCPU *cpu) * We use this limited C variable scope so we don't accidentally * use 'frame_sp_p' after we do something that makes it invalid. */ + bool spsel = env->v7m.control[return_to_secure] & R_V7M_CONTROL_SPSEL_MASK; uint32_t *frame_sp_p = get_v7m_sp_ptr(env, return_to_secure, !return_to_handler, - return_to_sp_process); + spsel); uint32_t frameptr = *frame_sp_p; bool pop_ok = true; ARMMMUIdx mmu_idx; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Using g_memdup is a bit more compact than g_new + memcpy. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-2-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- accel/tcg/cputlb.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, } else if (encode_pbm_to_runon(&runon, d)) { async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); } else { - TLBFlushPageBitsByMMUIdxData *p - = g_new(TLBFlushPageBitsByMMUIdxData, 1); - /* Otherwise allocate a structure, freed by the worker. */ - *p = d; + TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d)); async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2, RUN_ON_CPU_HOST_PTR(p)); } @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); } else { CPUState *dst_cpu; - TLBFlushPageBitsByMMUIdxData *p; /* Allocate a separate data block for each destination cpu. */ CPU_FOREACH(dst_cpu) { if (dst_cpu != src_cpu) { - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; + TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d)); async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, RUN_ON_CPU_HOST_PTR(p)); @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, /* Allocate a separate data block for each destination cpu. */ CPU_FOREACH(dst_cpu) { if (dst_cpu != src_cpu) { - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; + p = g_memdup(&d, sizeof(d)); async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, RUN_ON_CPU_HOST_PTR(p)); } } - p = g_new(TLBFlushPageBitsByMMUIdxData, 1); - *p = d; + p = g_memdup(&d, sizeof(d)); async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2, RUN_ON_CPU_HOST_PTR(p)); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rename tlb_flush_page_bits_locked() -> tlb_flush_range_locked(), and have callers pass a length argument (currently TARGET_PAGE_SIZE) via the TLBFlushPageBitsByMMUIdxData structure. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-3-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- accel/tcg/cputlb.c | 48 +++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr) tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS); } -static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, - target_ulong page, unsigned bits) +static void tlb_flush_range_locked(CPUArchState *env, int midx, + target_ulong addr, target_ulong len, + unsigned bits) { CPUTLBDesc *d = &env_tlb(env)->d[midx]; CPUTLBDescFast *f = &env_tlb(env)->f[midx]; @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, * If @bits is smaller than the tlb size, there may be multiple entries * within the TLB; otherwise all addresses that match under @mask hit * the same TLB entry. - * * TODO: Perhaps allow bits to be a few bits less than the size. * For now, just flush the entire TLB. + * + * If @len is larger than the tlb size, then it will take longer to + * test all of the entries in the TLB than it will to flush it all. */ - if (mask < f->mask) { + if (mask < f->mask || len > f->mask) { tlb_debug("forcing full flush midx %d (" - TARGET_FMT_lx "/" TARGET_FMT_lx ")\n", - midx, page, mask); + TARGET_FMT_lx "/" TARGET_FMT_lx "+" TARGET_FMT_lx ")\n", + midx, addr, mask, len); tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime()); return; } - /* Check if we need to flush due to large pages. */ - if ((page & d->large_page_mask) == d->large_page_addr) { + /* + * Check if we need to flush due to large pages. + * Because large_page_mask contains all 1's from the msb, + * we only need to test the end of the range. + */ + if (((addr + len - 1) & d->large_page_mask) == d->large_page_addr) { tlb_debug("forcing full flush midx %d (" TARGET_FMT_lx "/" TARGET_FMT_lx ")\n", midx, d->large_page_addr, d->large_page_mask); @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_locked(CPUArchState *env, int midx, return; } - if (tlb_flush_entry_mask_locked(tlb_entry(env, midx, page), page, mask)) { - tlb_n_used_entries_dec(env, midx); + for (target_ulong i = 0; i < len; i += TARGET_PAGE_SIZE) { + target_ulong page = addr + i; + CPUTLBEntry *entry = tlb_entry(env, midx, page); + + if (tlb_flush_entry_mask_locked(entry, page, mask)) { + tlb_n_used_entries_dec(env, midx); + } + tlb_flush_vtlb_page_mask_locked(env, midx, page, mask); } - tlb_flush_vtlb_page_mask_locked(env, midx, page, mask); } typedef struct { target_ulong addr; + target_ulong len; uint16_t idxmap; uint16_t bits; } TLBFlushPageBitsByMMUIdxData; @@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, assert_cpu_is_self(cpu); - tlb_debug("page addr:" TARGET_FMT_lx "/%u mmu_map:0x%x\n", - d.addr, d.bits, d.idxmap); + tlb_debug("range:" TARGET_FMT_lx "/%u+" TARGET_FMT_lx " mmu_map:0x%x\n", + d.addr, d.bits, d.len, d.idxmap); qemu_spin_lock(&env_tlb(env)->c.lock); for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) { if ((d.idxmap >> mmu_idx) & 1) { - tlb_flush_page_bits_locked(env, mmu_idx, d.addr, d.bits); + tlb_flush_range_locked(env, mmu_idx, d.addr, d.len, d.bits); } } qemu_spin_unlock(&env_tlb(env)->c.lock); - tb_flush_jmp_cache(cpu, d.addr); + for (target_ulong i = 0; i < d.len; i += TARGET_PAGE_SIZE) { + tb_flush_jmp_cache(cpu, d.addr + i); + } } static bool encode_pbm_to_runon(run_on_cpu_data *out, @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = TARGET_PAGE_SIZE; d.idxmap = idxmap; d.bits = bits; @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = TARGET_PAGE_SIZE; d.idxmap = idxmap; d.bits = bits; @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; + d.len = TARGET_PAGE_SIZE; d.idxmap = idxmap; d.bits = bits; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the structure to match the rename of tlb_flush_range_locked. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-4-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- accel/tcg/cputlb.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ typedef struct { target_ulong len; uint16_t idxmap; uint16_t bits; -} TLBFlushPageBitsByMMUIdxData; +} TLBFlushRangeData; static void tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, - TLBFlushPageBitsByMMUIdxData d) + TLBFlushRangeData d) { CPUArchState *env = cpu->env_ptr; int mmu_idx; @@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, } static bool encode_pbm_to_runon(run_on_cpu_data *out, - TLBFlushPageBitsByMMUIdxData d) + TLBFlushRangeData d) { /* We need 6 bits to hold to hold @bits up to 63. */ if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) { @@ -XXX,XX +XXX,XX @@ static bool encode_pbm_to_runon(run_on_cpu_data *out, return false; } -static TLBFlushPageBitsByMMUIdxData +static TLBFlushRangeData decode_runon_to_pbm(run_on_cpu_data data) { target_ulong addr_map_bits = (target_ulong) data.target_ptr; - return (TLBFlushPageBitsByMMUIdxData){ + return (TLBFlushRangeData){ .addr = addr_map_bits & TARGET_PAGE_MASK, .idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6, .bits = addr_map_bits & 0x3f @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu, static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, run_on_cpu_data data) { - TLBFlushPageBitsByMMUIdxData *d = data.host_ptr; + TLBFlushRangeData *d = data.host_ptr; tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d); g_free(d); } @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; + TLBFlushRangeData d; run_on_cpu_data runon; /* If all bits are significant, this devolves to tlb_flush_page. */ @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); } else { /* Otherwise allocate a structure, freed by the worker. */ - TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d)); + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2, RUN_ON_CPU_HOST_PTR(p)); } @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; + TLBFlushRangeData d; run_on_cpu_data runon; /* If all bits are significant, this devolves to tlb_flush_page. */ @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, /* Allocate a separate data block for each destination cpu. */ CPU_FOREACH(dst_cpu) { if (dst_cpu != src_cpu) { - TLBFlushPageBitsByMMUIdxData *p = g_memdup(&d, sizeof(d)); + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, RUN_ON_CPU_HOST_PTR(p)); @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, uint16_t idxmap, unsigned bits) { - TLBFlushPageBitsByMMUIdxData d; + TLBFlushRangeData d; run_on_cpu_data runon; /* If all bits are significant, this devolves to tlb_flush_page. */ @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, runon); } else { CPUState *dst_cpu; - TLBFlushPageBitsByMMUIdxData *p; + TLBFlushRangeData *p; /* Allocate a separate data block for each destination cpu. */ CPU_FOREACH(dst_cpu) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We will not be able to fit address + length into a 64-bit packet. Drop this optimization before re-organizing this code. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-10-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> [PMM: Moved patch earlier in the series] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- accel/tcg/cputlb.c | 86 +++++++++++----------------------------------- 1 file changed, 20 insertions(+), 66 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, } } -static bool encode_pbm_to_runon(run_on_cpu_data *out, - TLBFlushRangeData d) -{ - /* We need 6 bits to hold to hold @bits up to 63. */ - if (d.idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) { - *out = RUN_ON_CPU_TARGET_PTR(d.addr | (d.idxmap << 6) | d.bits); - return true; - } - return false; -} - -static TLBFlushRangeData -decode_runon_to_pbm(run_on_cpu_data data) -{ - target_ulong addr_map_bits = (target_ulong) data.target_ptr; - return (TLBFlushRangeData){ - .addr = addr_map_bits & TARGET_PAGE_MASK, - .idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6, - .bits = addr_map_bits & 0x3f - }; -} - -static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu, - run_on_cpu_data runon) -{ - tlb_flush_page_bits_by_mmuidx_async_0(cpu, decode_runon_to_pbm(runon)); -} - static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, run_on_cpu_data data) { @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits) { TLBFlushRangeData d; - run_on_cpu_data runon; /* If all bits are significant, this devolves to tlb_flush_page. */ if (bits >= TARGET_LONG_BITS) { @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, if (qemu_cpu_is_self(cpu)) { tlb_flush_page_bits_by_mmuidx_async_0(cpu, d); - } else if (encode_pbm_to_runon(&runon, d)) { - async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); } else { /* Otherwise allocate a structure, freed by the worker. */ TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, unsigned bits) { TLBFlushRangeData d; - run_on_cpu_data runon; + CPUState *dst_cpu; /* If all bits are significant, this devolves to tlb_flush_page. */ if (bits >= TARGET_LONG_BITS) { @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, d.idxmap = idxmap; d.bits = bits; - if (encode_pbm_to_runon(&runon, d)) { - flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); - } else { - CPUState *dst_cpu; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); - async_run_on_cpu(dst_cpu, - tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); - } + /* Allocate a separate data block for each destination cpu. */ + CPU_FOREACH(dst_cpu) { + if (dst_cpu != src_cpu) { + TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(dst_cpu, + tlb_flush_page_bits_by_mmuidx_async_2, + RUN_ON_CPU_HOST_PTR(p)); } } @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, uint16_t idxmap, unsigned bits) { - TLBFlushRangeData d; - run_on_cpu_data runon; + TLBFlushRangeData d, *p; + CPUState *dst_cpu; /* If all bits are significant, this devolves to tlb_flush_page. */ if (bits >= TARGET_LONG_BITS) { @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, d.idxmap = idxmap; d.bits = bits; - if (encode_pbm_to_runon(&runon, d)) { - flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, runon); - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, - runon); - } else { - CPUState *dst_cpu; - TLBFlushRangeData *p; - - /* Allocate a separate data block for each destination cpu. */ - CPU_FOREACH(dst_cpu) { - if (dst_cpu != src_cpu) { - p = g_memdup(&d, sizeof(d)); - async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); - } + /* Allocate a separate data block for each destination cpu. */ + CPU_FOREACH(dst_cpu) { + if (dst_cpu != src_cpu) { + p = g_memdup(&d, sizeof(d)); + async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, + RUN_ON_CPU_HOST_PTR(p)); } - - p = g_memdup(&d, sizeof(d)); - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2, - RUN_ON_CPU_HOST_PTR(p)); } + + p = g_memdup(&d, sizeof(d)); + async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2, + RUN_ON_CPU_HOST_PTR(p)); } /* update the TLBs so that writes to code in the virtual page 'addr' -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Forward tlb_flush_page_bits_by_mmuidx to tlb_flush_range_by_mmuidx passing TARGET_PAGE_SIZE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-5-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/exec-all.h | 19 +++++++++++++++++++ accel/tcg/cputlb.c | 20 +++++++++++++++----- 2 files changed, 34 insertions(+), 5 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr, void tlb_flush_page_bits_by_mmuidx_all_cpus_synced (CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits); +/** + * tlb_flush_range_by_mmuidx + * @cpu: CPU whose TLB should be flushed + * @addr: virtual address of the start of the range to be flushed + * @len: length of range to be flushed + * @idxmap: bitmap of mmu indexes to flush + * @bits: number of significant bits in address + * + * For each mmuidx in @idxmap, flush all pages within [@addr,@addr+@len), + * comparing only the low @bits worth of each virtual page. + */ +void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits); /** * tlb_set_page_with_attrs: * @cpu: CPU to add this TLB entry for @@ -XXX,XX +XXX,XX @@ tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits) { } +static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits) +{ +} #endif /** * probe_access: diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, g_free(d); } -void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, - uint16_t idxmap, unsigned bits) +void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits) { TLBFlushRangeData d; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx(cpu, addr, idxmap); return; } @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; - d.len = TARGET_PAGE_SIZE; + d.len = len; d.idxmap = idxmap; d.bits = bits; @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, } } +void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, + uint16_t idxmap, unsigned bits) +{ + tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits); +} + void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, target_ulong addr, uint16_t idxmap, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Forward tlb_flush_page_bits_by_mmuidx_all_cpus to tlb_flush_range_by_mmuidx_all_cpus passing TARGET_PAGE_SIZE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-6-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/exec-all.h | 13 +++++++++++++ accel/tcg/cputlb.c | 24 +++++++++++++++++------- 2 files changed, 30 insertions(+), 7 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, target_ulong len, uint16_t idxmap, unsigned bits); + +/* Similarly, with broadcast and syncing. */ +void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr, + target_ulong len, uint16_t idxmap, + unsigned bits); + /** * tlb_set_page_with_attrs: * @cpu: CPU to add this TLB entry for @@ -XXX,XX +XXX,XX @@ static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, unsigned bits) { } +static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits) +{ +} #endif /** * probe_access: diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr, tlb_flush_range_by_mmuidx(cpu, addr, TARGET_PAGE_SIZE, idxmap, bits); } -void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, - target_ulong addr, - uint16_t idxmap, - unsigned bits) +void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu, + target_ulong addr, target_ulong len, + uint16_t idxmap, unsigned bits) { TLBFlushRangeData d; CPUState *dst_cpu; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap); return; } @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; - d.len = TARGET_PAGE_SIZE; + d.len = len; d.idxmap = idxmap; d.bits = bits; @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d); } +void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, + target_ulong addr, + uint16_t idxmap, unsigned bits) +{ + tlb_flush_range_by_mmuidx_all_cpus(src_cpu, addr, TARGET_PAGE_SIZE, + idxmap, bits); +} + void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, target_ulong addr, uint16_t idxmap, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Forward tlb_flush_page_bits_by_mmuidx_all_cpus_synced to tlb_flush_range_by_mmuidx_all_cpus_synced passing TARGET_PAGE_SIZE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-7-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/exec-all.h | 12 ++++++++++++ accel/tcg/cputlb.c | 27 ++++++++++++++++++++------- 2 files changed, 32 insertions(+), 7 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr, target_ulong len, uint16_t idxmap, unsigned bits); +void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits); /** * tlb_set_page_with_attrs: @@ -XXX,XX +XXX,XX @@ static inline void tlb_flush_range_by_mmuidx_all_cpus(CPUState *cpu, unsigned bits) { } +static inline void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, + target_ulong addr, + target_long len, + uint16_t idxmap, + unsigned bits) +{ +} #endif /** * probe_access: diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, idxmap, bits); } -void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, - target_ulong addr, - uint16_t idxmap, - unsigned bits) +void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu, + target_ulong addr, + target_ulong len, + uint16_t idxmap, + unsigned bits) { TLBFlushRangeData d, *p; CPUState *dst_cpu; - /* If all bits are significant, this devolves to tlb_flush_page. */ - if (bits >= TARGET_LONG_BITS) { + /* + * If all bits are significant, and len is small, + * this devolves to tlb_flush_page. + */ + if (bits >= TARGET_LONG_BITS && len <= TARGET_PAGE_SIZE) { tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap); return; } @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, /* This should already be page aligned */ d.addr = addr & TARGET_PAGE_MASK; - d.len = TARGET_PAGE_SIZE; + d.len = len; d.idxmap = idxmap; d.bits = bits; @@ -XXX,XX +XXX,XX @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, RUN_ON_CPU_HOST_PTR(p)); } +void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu, + target_ulong addr, + uint16_t idxmap, + unsigned bits) +{ + tlb_flush_range_by_mmuidx_all_cpus_synced(src_cpu, addr, TARGET_PAGE_SIZE, + idxmap, bits); +} + /* update the TLBs so that writes to code in the virtual page 'addr' can be detected */ void tlb_protect_code(ram_addr_t ram_addr) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rename to match tlb_flush_range_locked. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-8-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- accel/tcg/cputlb.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ typedef struct { uint16_t bits; } TLBFlushRangeData; -static void -tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu, - TLBFlushRangeData d) +static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, + TLBFlushRangeData d) { CPUArchState *env = cpu->env_ptr; int mmu_idx; @@ -XXX,XX +XXX,XX @@ static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, run_on_cpu_data data) { TLBFlushRangeData *d = data.host_ptr; - tlb_flush_page_bits_by_mmuidx_async_0(cpu, *d); + tlb_flush_range_by_mmuidx_async_0(cpu, *d); g_free(d); } @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, d.bits = bits; if (qemu_cpu_is_self(cpu)) { - tlb_flush_page_bits_by_mmuidx_async_0(cpu, d); + tlb_flush_range_by_mmuidx_async_0(cpu, d); } else { /* Otherwise allocate a structure, freed by the worker. */ TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu, } } - tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, d); + tlb_flush_range_by_mmuidx_async_0(src_cpu, d); } void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rename to match tlb_flush_range_locked. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210509151618.2331764-9-f4bug@amsat.org Message-Id: <20210508201640.1045808-1-richard.henderson@linaro.org> [PMD: Split from bigger patch] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- accel/tcg/cputlb.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static void tlb_flush_range_by_mmuidx_async_0(CPUState *cpu, } } -static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu, - run_on_cpu_data data) +static void tlb_flush_range_by_mmuidx_async_1(CPUState *cpu, + run_on_cpu_data data) { TLBFlushRangeData *d = data.host_ptr; tlb_flush_range_by_mmuidx_async_0(cpu, *d); @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx(CPUState *cpu, target_ulong addr, } else { /* Otherwise allocate a structure, freed by the worker. */ TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); - async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2, + async_run_on_cpu(cpu, tlb_flush_range_by_mmuidx_async_1, RUN_ON_CPU_HOST_PTR(p)); } } @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus(CPUState *src_cpu, if (dst_cpu != src_cpu) { TLBFlushRangeData *p = g_memdup(&d, sizeof(d)); async_run_on_cpu(dst_cpu, - tlb_flush_page_bits_by_mmuidx_async_2, + tlb_flush_range_by_mmuidx_async_1, RUN_ON_CPU_HOST_PTR(p)); } } @@ -XXX,XX +XXX,XX @@ void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *src_cpu, CPU_FOREACH(dst_cpu) { if (dst_cpu != src_cpu) { p = g_memdup(&d, sizeof(d)); - async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2, + async_run_on_cpu(dst_cpu, tlb_flush_range_by_mmuidx_async_1, RUN_ON_CPU_HOST_PTR(p)); } } p = g_memdup(&d, sizeof(d)); - async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2, + async_safe_run_on_cpu(src_cpu, tlb_flush_range_by_mmuidx_async_1, RUN_ON_CPU_HOST_PTR(p)); } -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> ARMv8.4 adds the mandatory FEAT_TLBIRANGE. It provides TLBI maintenance instructions that apply to a range of input addresses. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210512182337.18563-2-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 + target/arm/helper.c | 281 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 286 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pauth_arch(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; } +static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; +} + static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMMMUIdxBit_SE3, bits); } +#ifdef TARGET_AARCH64 +static uint64_t tlbi_aa64_range_get_length(CPUARMState *env, + uint64_t value) +{ + unsigned int page_shift; + unsigned int page_size_granule; + uint64_t num; + uint64_t scale; + uint64_t exponent; + uint64_t length; + + num = extract64(value, 39, 4); + scale = extract64(value, 44, 2); + page_size_granule = extract64(value, 46, 2); + + page_shift = page_size_granule * 2 + 12; + + if (page_size_granule == 0) { + qemu_log_mask(LOG_GUEST_ERROR, "Invalid page size granule %d\n", + page_size_granule); + return 0; + } + + exponent = (5 * scale) + 1; + length = (num + 1) << (exponent + page_shift); + + return length; +} + +static uint64_t tlbi_aa64_range_get_base(CPUARMState *env, uint64_t value, + bool two_ranges) +{ + /* TODO: ARMv8.7 FEAT_LPA2 */ + uint64_t pageaddr; + + if (two_ranges) { + pageaddr = sextract64(value, 0, 37) << TARGET_PAGE_BITS; + } else { + pageaddr = extract64(value, 0, 37) << TARGET_PAGE_BITS; + } + + return pageaddr; +} + +static void do_rvae_write(CPUARMState *env, uint64_t value, + int idxmap, bool synced) +{ + ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap); + bool two_ranges = regime_has_2_ranges(one_idx); + uint64_t baseaddr, length; + int bits; + + baseaddr = tlbi_aa64_range_get_base(env, value, two_ranges); + length = tlbi_aa64_range_get_length(env, value); + bits = tlbbits_for_regime(env, one_idx, baseaddr); + + if (synced) { + tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env), + baseaddr, + length, + idxmap, + bits); + } else { + tlb_flush_range_by_mmuidx(env_cpu(env), baseaddr, + length, idxmap, bits); + } +} + +static void tlbi_aa64_rvae1_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL1&0. + * Currently handles all of RVAE1, RVAAE1, RVAALE1 and RVALE1, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, vae1_tlbmask(env), + tlb_force_broadcast(env)); +} + +static void tlbi_aa64_rvae1is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, Inner/Outer Shareable EL1&0. + * Currently handles all of RVAE1IS, RVAE1OS, RVAAE1IS, RVAAE1OS, + * RVAALE1IS, RVAALE1OS, RVALE1IS and RVALE1OS, since we don't support + * flush-for-specific-ASID-only, flush-last-level-only or inner/outer + * shareable specific flushes. + */ + + do_rvae_write(env, value, vae1_tlbmask(env), true); +} + +static int vae2_tlbmask(CPUARMState *env) +{ + return (arm_is_secure_below_el3(env) + ? ARMMMUIdxBit_SE2 : ARMMMUIdxBit_E2); +} + +static void tlbi_aa64_rvae2_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL2. + * Currently handles all of RVAE2 and RVALE2, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, vae2_tlbmask(env), + tlb_force_broadcast(env)); + + +} + +static void tlbi_aa64_rvae2is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, Inner/Outer Shareable, EL2. + * Currently handles all of RVAE2IS, RVAE2OS, RVALE2IS and RVALE2OS, + * since we don't support flush-for-specific-ASID-only, + * flush-last-level-only or inner/outer shareable specific flushes. + */ + + do_rvae_write(env, value, vae2_tlbmask(env), true); + +} + +static void tlbi_aa64_rvae3_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL3. + * Currently handles all of RVAE3 and RVALE3, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, ARMMMUIdxBit_SE3, + tlb_force_broadcast(env)); +} + +static void tlbi_aa64_rvae3is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL3, Inner/Outer Shareable. + * Currently handles all of RVAE3IS, RVAE3OS, RVALE3IS and RVALE3OS, + * since we don't support flush-for-specific-ASID-only, + * flush-last-level-only or inner/outer specific flushes. + */ + + do_rvae_write(env, value, ARMMMUIdxBit_SE3, true); +} +#endif + static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo pauth_reginfo[] = { REGINFO_SENTINEL }; +static const ARMCPRegInfo tlbirange_reginfo[] = { + { .name = "TLBI_RVAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 3, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 7, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 3, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 7, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVAAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 3, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVAALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 7, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RIPAS2E1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2_write }, + { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae2_write }, + { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVALE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVAE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVALE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVAE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3_write }, + { .name = "TLBI_RVALE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3_write }, + REGINFO_SENTINEL +}; + static uint64_t rndr_readfn(CPUARMState *env, const ARMCPRegInfo *ri) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_rndr, cpu)) { define_arm_cp_regs(cpu, rndr_reginfo); } + if (cpu_isar_feature(aa64_tlbirange, cpu)) { + define_arm_cp_regs(cpu, tlbirange_reginfo); + } #ifndef CONFIG_USER_ONLY /* Data Cache clean instructions up to PoP */ if (cpu_isar_feature(aa64_dcpop, cpu)) { -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> ARMv8.4 adds the mandatory FEAT_TLBIOS. It provides TLBI maintenance instructions that extend to the Outer Shareable domain. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210512182337.18563-3-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++++ target/arm/helper.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; } +static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; +} + static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbirange_reginfo[] = { REGINFO_SENTINEL }; +static const ARMCPRegInfo tlbios_reginfo[] = { + { .name = "TLBI_VMALLE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_ASIDE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 2, + .access = PL1_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_ALLE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle2is_write }, + { .name = "TLBI_ALLE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_VMALLS12E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_IPAS2E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 3, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_IPAS2LE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 7, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_ALLE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle3is_write }, + REGINFO_SENTINEL +}; + static uint64_t rndr_readfn(CPUARMState *env, const ARMCPRegInfo *ri) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_tlbirange, cpu)) { define_arm_cp_regs(cpu, tlbirange_reginfo); } + if (cpu_isar_feature(aa64_tlbios, cpu)) { + define_arm_cp_regs(cpu, tlbios_reginfo); + } #ifndef CONFIG_USER_ONLY /* Data Cache clean instructions up to PoP */ if (cpu_isar_feature(aa64_dcpop, cpu)) { -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Indicate support for FEAT_TLBIOS and FEAT_TLBIRANGE by setting ID_AA64ISAR0.TLB to 2 for the max AARCH64 CPU type. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210512182337.18563-4-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); t = FIELD_DP64(t, ID_AA64ISAR0, FHM, 1); t = FIELD_DP64(t, ID_AA64ISAR0, TS, 2); /* v8.5-CondM */ + t = FIELD_DP64(t, ID_AA64ISAR0, TLB, 2); /* FEAT_TLBIRANGE */ t = FIELD_DP64(t, ID_AA64ISAR0, RNDR, 1); cpu->isar.id_aa64isar0 = t; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> When selecting an ARM target on Debian unstable, we get: Compiling C++ object libcommon.fa.p/disas_libvixl_vixl_utils.cc.o FAILED: libcommon.fa.p/disas_libvixl_vixl_utils.cc.o c++ -Ilibcommon.fa.p -I. -I.. [...] -o libcommon.fa.p/disas_libvixl_vixl_utils.cc.o -c ../disas/libvixl/vixl/utils.cc In file included from /home/philmd/qemu/disas/libvixl/vixl/utils.h:30, from ../disas/libvixl/vixl/utils.cc:27: /usr/include/string.h:36:43: error: missing binary operator before token "(" 36 | #if defined __cplusplus && (__GNUC_PREREQ (4, 4) \ | ^ /usr/include/string.h:53:62: error: missing binary operator before token "(" 53 | #if defined __USE_MISC || defined __USE_XOPEN || __GLIBC_USE (ISOC2X) | ^ /usr/include/string.h:165:21: error: missing binary operator before token "(" 165 | || __GLIBC_USE (LIB_EXT2) || __GLIBC_USE (ISOC2X)) | ^ /usr/include/string.h:174:43: error: missing binary operator before token "(" 174 | #if defined __USE_XOPEN2K8 || __GLIBC_USE (LIB_EXT2) || __GLIBC_USE (ISOC2X) | ^ /usr/include/string.h:492:19: error: missing binary operator before token "(" 492 | #if __GNUC_PREREQ (3,4) | ^ Relevant information from the host: $ lsb_release -d Description: Debian GNU/Linux 11 (bullseye) $ gcc --version gcc (Debian 10.2.1-6) 10.2.1 20210110 $ dpkg -S /usr/include/string.h libc6-dev: /usr/include/string.h $ apt-cache show libc6-dev Package: libc6-dev Version: 2.31-11 Partially cherry-pick vixl commit 78973f258039f6e96 [*]: Refactor VIXL to use `extern` block when including C header that do not have a C++ counterpart. which is similar to commit 875df03b221 ('osdep: protect qemu/osdep.h with extern "C"'). [*] https://git.linaro.org/arm/vixl.git/commit/?id=78973f258039f6e96 Buglink: https://bugs.launchpad.net/qemu/+bug/1914870 Suggested-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20210516171023.510778-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- disas/libvixl/vixl/code-buffer.h | 2 +- disas/libvixl/vixl/globals.h | 16 +++++++++------- disas/libvixl/vixl/invalset.h | 2 +- disas/libvixl/vixl/platform.h | 2 ++ disas/libvixl/vixl/utils.h | 2 +- disas/libvixl/vixl/utils.cc | 2 +- 6 files changed, 15 insertions(+), 11 deletions(-) diff --git a/disas/libvixl/vixl/code-buffer.h b/disas/libvixl/vixl/code-buffer.h index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/vixl/code-buffer.h +++ b/disas/libvixl/vixl/code-buffer.h @@ -XXX,XX +XXX,XX @@ #ifndef VIXL_CODE_BUFFER_H #define VIXL_CODE_BUFFER_H -#include <string.h> +#include <cstring> #include "vixl/globals.h" namespace vixl { diff --git a/disas/libvixl/vixl/globals.h b/disas/libvixl/vixl/globals.h index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/vixl/globals.h +++ b/disas/libvixl/vixl/globals.h @@ -XXX,XX +XXX,XX @@ #define __STDC_FORMAT_MACROS #endif -#include <stdint.h> +extern "C" { #include <inttypes.h> - -#include <assert.h> -#include <stdarg.h> -#include <stdio.h> #include <stdint.h> -#include <stdlib.h> -#include <stddef.h> +} + +#include <cassert> +#include <cstdarg> +#include <cstddef> +#include <cstdio> +#include <cstdlib> + #include "vixl/platform.h" diff --git a/disas/libvixl/vixl/invalset.h b/disas/libvixl/vixl/invalset.h index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/vixl/invalset.h +++ b/disas/libvixl/vixl/invalset.h @@ -XXX,XX +XXX,XX @@ #ifndef VIXL_INVALSET_H_ #define VIXL_INVALSET_H_ -#include <string.h> +#include <cstring> #include <algorithm> #include <vector> diff --git a/disas/libvixl/vixl/platform.h b/disas/libvixl/vixl/platform.h index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/vixl/platform.h +++ b/disas/libvixl/vixl/platform.h @@ -XXX,XX +XXX,XX @@ #define PLATFORM_H // Define platform specific functionalities. +extern "C" { #include <signal.h> +} namespace vixl { inline void HostBreakpoint() { raise(SIGINT); } diff --git a/disas/libvixl/vixl/utils.h b/disas/libvixl/vixl/utils.h index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/vixl/utils.h +++ b/disas/libvixl/vixl/utils.h @@ -XXX,XX +XXX,XX @@ #ifndef VIXL_UTILS_H #define VIXL_UTILS_H -#include <string.h> #include <cmath> +#include <cstring> #include "vixl/globals.h" #include "vixl/compiler-intrinsics.h" diff --git a/disas/libvixl/vixl/utils.cc b/disas/libvixl/vixl/utils.cc index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/vixl/utils.cc +++ b/disas/libvixl/vixl/utils.cc @@ -XXX,XX +XXX,XX @@ // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #include "vixl/utils.h" -#include <stdio.h> +#include <cstdio> namespace vixl { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Will be used for SVE2 isa subset enablement. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 16 ++++++++++++++++ target/arm/helper.c | 3 +-- target/arm/kvm64.c | 21 +++++++++++++++------ 3 files changed, 32 insertions(+), 8 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 @@ struct ARMCPU { uint64_t id_aa64mmfr2; uint64_t id_aa64dfr0; uint64_t id_aa64dfr1; + uint64_t id_aa64zfr0; } isar; uint64_t midr; uint32_t revidr; @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4) FIELD(ID_AA64DFR0, TRACEFILT, 40, 4) FIELD(ID_AA64DFR0, MTPMU, 48, 4) +FIELD(ID_AA64ZFR0, SVEVER, 0, 4) +FIELD(ID_AA64ZFR0, AES, 4, 4) +FIELD(ID_AA64ZFR0, BITPERM, 16, 4) +FIELD(ID_AA64ZFR0, BFLOAT16, 20, 4) +FIELD(ID_AA64ZFR0, SHA3, 32, 4) +FIELD(ID_AA64ZFR0, SM4, 40, 4) +FIELD(ID_AA64ZFR0, I8MM, 44, 4) +FIELD(ID_AA64ZFR0, F32MM, 52, 4) +FIELD(ID_AA64ZFR0, F64MM, 56, 4) + FIELD(ID_DFR0, COPDBG, 0, 4) FIELD(ID_DFR0, COPSDBG, 4, 4) FIELD(ID_DFR0, MMAPDBG, 8, 4) @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; } +static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ 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 register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, - /* At present, only SVEver == 0 is defined anyway. */ - .resetvalue = 0 }, + .resetvalue = cpu->isar.id_aa64zfr0 }, { .name = "ID_AA64PFR5_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 5, .access = PL1_R, .type = ARM_CP_CONST, 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 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0; - kvm_arm_destroy_scratch_host_vcpu(fdarray); - - if (err < 0) { - return false; - } - /* Add feature bits that can't appear until after VCPU init. */ if (sve_supported) { t = ahcf->isar.id_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); ahcf->isar.id_aa64pfr0 = t; + + /* + * Before v5.1, KVM did not support SVE and did not expose + * ID_AA64ZFR0_EL1 even as RAZ. After v5.1, KVM still does + * not expose the register to "user" requests like this + * unless the host supports SVE. + */ + err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64zfr0, + ARM64_SYS_REG(3, 0, 0, 4, 4)); + } + + kvm_arm_destroy_scratch_host_vcpu(fdarray); + + if (err < 0) { + return false; } /* -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For MUL, we can rely on generic support. For SMULH and UMULH, create some trivial helpers. For PMUL, back in a21bb78e5817, we organized helper_gvec_pmul_b in preparation for this use. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 ++++ target/arm/sve.decode | 10 ++++ target/arm/translate-sve.c | 50 ++++++++++++++++++++ target/arm/vec_helper.c | 96 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 166 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_smulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_umulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_umulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ ST1_zprz 1110010 .. 00 ..... 100 ... ..... ..... \ @rprr_scatter_store xs=0 esz=3 scale=0 ST1_zprz 1110010 .. 00 ..... 110 ... ..... ..... \ @rprr_scatter_store xs=1 esz=3 scale=0 + +#### SVE2 Support + +### SVE2 Integer Multiply - Unpredicated + +# SVE2 integer multiply vectors (unpredicated) +MUL_zzz 00000100 .. 1 ..... 0110 00 ..... ..... @rd_rn_rm +SMULH_zzz 00000100 .. 1 ..... 0110 10 ..... ..... @rd_rn_rm +UMULH_zzz 00000100 .. 1 ..... 0110 11 ..... ..... @rd_rn_rm +PMUL_zzz 00000100 00 1 ..... 0110 01 ..... ..... @rd_rn_rm_e0 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a) { return do_movz_zpz(s, a->rd, a->rn, a->pg, a->esz, false); } + +/* + * SVE2 Integer Multiply - Unpredicated + */ + +static bool trans_MUL_zzz(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzz(s, tcg_gen_gvec_mul, a->esz, a->rd, a->rn, a->rm); + } + return true; +} + +static bool do_sve2_zzz_ool(DisasContext *s, arg_rrr_esz *a, + gen_helper_gvec_3 *fn) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); + } + return true; +} + +static bool trans_SMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, + gen_helper_gvec_smulh_s, gen_helper_gvec_smulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +static bool trans_UMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_umulh_b, gen_helper_gvec_umulh_h, + gen_helper_gvec_umulh_s, gen_helper_gvec_umulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a) +{ + return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b); +} diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc) clear_tail(vd, oprsz, simd_maxsz(desc)); } #endif + +/* + * NxN -> N highpart multiply + * + * TODO: expose this as a generic vector operation. + */ + +void HELPER(gvec_smulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ((int32_t)n[i] * m[i]) >> 8; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_smulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = ((int32_t)n[i] * m[i]) >> 16; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_smulh_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int32_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = ((int64_t)n[i] * m[i]) >> 32; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_smulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t discard; + + for (i = 0; i < opr_sz / 8; ++i) { + muls64(&discard, &d[i], n[i], m[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ((uint32_t)n[i] * m[i]) >> 8; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint16_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = ((uint32_t)n[i] * m[i]) >> 16; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = ((uint64_t)n[i] * m[i]) >> 32; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_umulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t discard; + + for (i = 0; i < opr_sz / 8; ++i) { + mulu64(&discard, &d[i], n[i], m[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 ++++++++++++ target/arm/sve.decode | 5 +++++ target/arm/sve_helper.c | 44 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 39 +++++++++++++++++++++++++++++++++ 4 files changed, 102 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_umulh_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_umulh_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ MUL_zzz 00000100 .. 1 ..... 0110 00 ..... ..... @rd_rn_rm SMULH_zzz 00000100 .. 1 ..... 0110 10 ..... ..... @rd_rn_rm UMULH_zzz 00000100 .. 1 ..... 0110 11 ..... ..... @rd_rn_rm PMUL_zzz 00000100 00 1 ..... 0110 01 ..... ..... @rd_rn_rm_e0 + +### SVE2 Integer - Predicated + +SADALP_zpzz 01000100 .. 000 100 101 ... ..... ..... @rdm_pg_rn +UADALP_zpzz 01000100 .. 000 101 101 ... ..... ..... @rdm_pg_rn diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_D(sve_asr_zpzz_d, int64_t, DO_ASR) DO_ZPZZ_D(sve_lsr_zpzz_d, uint64_t, DO_LSR) DO_ZPZZ_D(sve_lsl_zpzz_d, uint64_t, DO_LSL) +static inline uint16_t do_sadalp_h(int16_t n, int16_t m) +{ + int8_t n1 = n, n2 = n >> 8; + return m + n1 + n2; +} + +static inline uint32_t do_sadalp_s(int32_t n, int32_t m) +{ + int16_t n1 = n, n2 = n >> 16; + return m + n1 + n2; +} + +static inline uint64_t do_sadalp_d(int64_t n, int64_t m) +{ + int32_t n1 = n, n2 = n >> 32; + return m + n1 + n2; +} + +DO_ZPZZ(sve2_sadalp_zpzz_h, int16_t, H1_2, do_sadalp_h) +DO_ZPZZ(sve2_sadalp_zpzz_s, int32_t, H1_4, do_sadalp_s) +DO_ZPZZ_D(sve2_sadalp_zpzz_d, int64_t, do_sadalp_d) + +static inline uint16_t do_uadalp_h(uint16_t n, uint16_t m) +{ + uint8_t n1 = n, n2 = n >> 8; + return m + n1 + n2; +} + +static inline uint32_t do_uadalp_s(uint32_t n, uint32_t m) +{ + uint16_t n1 = n, n2 = n >> 16; + return m + n1 + n2; +} + +static inline uint64_t do_uadalp_d(uint64_t n, uint64_t m) +{ + uint32_t n1 = n, n2 = n >> 32; + return m + n1 + n2; +} + +DO_ZPZZ(sve2_uadalp_zpzz_h, uint16_t, H1_2, do_uadalp_h) +DO_ZPZZ(sve2_uadalp_zpzz_s, uint32_t, H1_4, do_uadalp_s) +DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d) + #undef DO_ZPZZ #undef DO_ZPZZ_D diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a) { return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b); } + +/* + * SVE2 Integer - Predicated + */ + +static bool do_sve2_zpzz_ool(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4 *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzz_ool(s, a, fn); +} + +static bool trans_SADALP_zpzz(DisasContext *s, arg_rprr_esz *a) +{ + static gen_helper_gvec_4 * const fns[3] = { + gen_helper_sve2_sadalp_zpzz_h, + gen_helper_sve2_sadalp_zpzz_s, + gen_helper_sve2_sadalp_zpzz_d, + }; + if (a->esz == 0) { + return false; + } + return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); +} + +static bool trans_UADALP_zpzz(DisasContext *s, arg_rprr_esz *a) +{ + static gen_helper_gvec_4 * const fns[3] = { + gen_helper_sve2_uadalp_zpzz_h, + gen_helper_sve2_uadalp_zpzz_s, + gen_helper_sve2_uadalp_zpzz_d, + }; + if (a->esz == 0) { + return false; + } + return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 13 +++++++++++ target/arm/sve.decode | 7 ++++++ target/arm/sve_helper.c | 21 +++++++++++++++++ target/arm/translate-sve.c | 47 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 88 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqabs_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqneg_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqneg_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqneg_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqneg_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_splice, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_cmpeq_ppzz_b, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ PMUL_zzz 00000100 00 1 ..... 0110 01 ..... ..... @rd_rn_rm_e0 SADALP_zpzz 01000100 .. 000 100 101 ... ..... ..... @rdm_pg_rn UADALP_zpzz 01000100 .. 000 101 101 ... ..... ..... @rdm_pg_rn + +### SVE2 integer unary operations (predicated) + +URECPE 01000100 .. 000 000 101 ... ..... ..... @rd_pg_rn +URSQRTE 01000100 .. 000 001 101 ... ..... ..... @rd_pg_rn +SQABS 01000100 .. 001 000 101 ... ..... ..... @rd_pg_rn +SQNEG 01000100 .. 001 001 101 ... ..... ..... @rd_pg_rn diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16) DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32) DO_ZPZ_D(sve_rbit_d, uint64_t, revbit64) +#define DO_SQABS(X) \ + ({ __typeof(X) x_ = (X), min_ = 1ull << (sizeof(X) * 8 - 1); \ + x_ >= 0 ? x_ : x_ == min_ ? -min_ - 1 : -x_; }) + +DO_ZPZ(sve2_sqabs_b, int8_t, H1, DO_SQABS) +DO_ZPZ(sve2_sqabs_h, int16_t, H1_2, DO_SQABS) +DO_ZPZ(sve2_sqabs_s, int32_t, H1_4, DO_SQABS) +DO_ZPZ_D(sve2_sqabs_d, int64_t, DO_SQABS) + +#define DO_SQNEG(X) \ + ({ __typeof(X) x_ = (X), min_ = 1ull << (sizeof(X) * 8 - 1); \ + x_ == min_ ? -min_ - 1 : -x_; }) + +DO_ZPZ(sve2_sqneg_b, uint8_t, H1, DO_SQNEG) +DO_ZPZ(sve2_sqneg_h, uint16_t, H1_2, DO_SQNEG) +DO_ZPZ(sve2_sqneg_s, uint32_t, H1_4, DO_SQNEG) +DO_ZPZ_D(sve2_sqneg_d, uint64_t, DO_SQNEG) + +DO_ZPZ(sve2_urecpe_s, uint32_t, H1_4, helper_recpe_u32) +DO_ZPZ(sve2_ursqrte_s, uint32_t, H1_4, helper_rsqrte_u32) + /* Three-operand expander, unpredicated, in which the third operand is "wide". */ #define DO_ZZW(NAME, TYPE, TYPEW, H, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UADALP_zpzz(DisasContext *s, arg_rprr_esz *a) } return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]); } + +/* + * SVE2 integer unary operations (predicated) + */ + +static bool do_sve2_zpz_ool(DisasContext *s, arg_rpr_esz *a, + gen_helper_gvec_3 *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ool(s, a, fn); +} + +static bool trans_URECPE(DisasContext *s, arg_rpr_esz *a) +{ + if (a->esz != 2) { + return false; + } + return do_sve2_zpz_ool(s, a, gen_helper_sve2_urecpe_s); +} + +static bool trans_URSQRTE(DisasContext *s, arg_rpr_esz *a) +{ + if (a->esz != 2) { + return false; + } + return do_sve2_zpz_ool(s, a, gen_helper_sve2_ursqrte_s); +} + +static bool trans_SQABS(DisasContext *s, arg_rpr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqabs_b, gen_helper_sve2_sqabs_h, + gen_helper_sve2_sqabs_s, gen_helper_sve2_sqabs_d, + }; + return do_sve2_zpz_ool(s, a, fns[a->esz]); +} + +static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqneg_b, gen_helper_sve2_sqneg_h, + gen_helper_sve2_sqneg_s, gen_helper_sve2_sqneg_d, + }; + return do_sve2_zpz_ool(s, a, fns[a->esz]); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Split these operations out into a header that can be shared between neon and sve. The "sat" pointer acts both as a boolean for control of saturating behavior and controls the difference in behavior between neon and sve -- QC bit or no QC bit. Widen the shift operand in the new helpers, as the SVE2 insns treat the whole input element as significant. For the neon uses, truncate the shift to int8_t while passing the parameter. Implement right-shift rounding as tmp = src >> (shift - 1); dst = (tmp >> 1) + (tmp & 1); This is the same number of instructions as the current tmp = 1 << (shift - 1); dst = (src + tmp) >> shift; without any possibility of intermediate overflow. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vec_internal.h | 138 +++++++++++ target/arm/neon_helper.c | 507 +++++++------------------------------- 2 files changed, 221 insertions(+), 424 deletions(-) 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 @@ static inline void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) } } +static inline int32_t do_sqrshl_bhs(int32_t src, int32_t shift, int bits, + bool round, uint32_t *sat) +{ + if (shift <= -bits) { + /* Rounding the sign bit always produces 0. */ + if (round) { + return 0; + } + return src >> 31; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < bits) { + int32_t val = src << shift; + if (bits == 32) { + if (!sat || val >> shift == src) { + return val; + } + } else { + int32_t extval = sextract32(val, 0, bits); + if (!sat || val == extval) { + return extval; + } + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return (1u << (bits - 1)) - (src >= 0); +} + +static inline uint32_t do_uqrshl_bhs(uint32_t src, int32_t shift, int bits, + bool round, uint32_t *sat) +{ + if (shift <= -(bits + round)) { + return 0; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < bits) { + uint32_t val = src << shift; + if (bits == 32) { + if (!sat || val >> shift == src) { + return val; + } + } else { + uint32_t extval = extract32(val, 0, bits); + if (!sat || val == extval) { + return extval; + } + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return MAKE_64BIT_MASK(0, bits); +} + +static inline int32_t do_suqrshl_bhs(int32_t src, int32_t shift, int bits, + bool round, uint32_t *sat) +{ + if (sat && src < 0) { + *sat = 1; + return 0; + } + return do_uqrshl_bhs(src, shift, bits, round, sat); +} + +static inline int64_t do_sqrshl_d(int64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (shift <= -64) { + /* Rounding the sign bit always produces 0. */ + if (round) { + return 0; + } + return src >> 63; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < 64) { + int64_t val = src << shift; + if (!sat || val >> shift == src) { + return val; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return src < 0 ? INT64_MIN : INT64_MAX; +} + +static inline uint64_t do_uqrshl_d(uint64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (shift <= -(64 + round)) { + return 0; + } else if (shift < 0) { + if (round) { + src >>= -shift - 1; + return (src >> 1) + (src & 1); + } + return src >> -shift; + } else if (shift < 64) { + uint64_t val = src << shift; + if (!sat || val >> shift == src) { + return val; + } + } else if (!sat || src == 0) { + return 0; + } + + *sat = 1; + return UINT64_MAX; +} + +static inline int64_t do_suqrshl_d(int64_t src, int64_t shift, + bool round, uint32_t *sat) +{ + if (sat && src < 0) { + *sat = 1; + return 0; + } + return do_uqrshl_d(src, shift, round, sat); +} + #endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" #include "fpu/softfloat.h" +#include "vec_internal.h" #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) @@ -XXX,XX +XXX,XX @@ NEON_POP(pmax_s16, neon_s16, 2) NEON_POP(pmax_u16, neon_u16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8 || \ - tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, NULL)) NEON_VOP(shl_u16, neon_u16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> (sizeof(src1) * 8 - 1); \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, NULL)) NEON_VOP(shl_s16, neon_s16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if ((tmp >= (ssize_t)sizeof(src1) * 8) \ - || (tmp <= -(ssize_t)sizeof(src1) * 8)) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, NULL)) NEON_VOP(rshl_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, NULL)) NEON_VOP(rshl_s16, neon_s16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_rshl_s32)(uint32_t valop, uint32_t shiftop) +uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift) { - int32_t dest; - int32_t val = (int32_t)valop; - int8_t shift = (int8_t)shiftop; - if ((shift >= 32) || (shift <= -32)) { - dest = 0; - } else if (shift < 0) { - int64_t big_dest = ((int64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - } - return dest; + return do_sqrshl_bhs(val, (int8_t)shift, 32, true, NULL); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_rshl_s64)(uint64_t valop, uint64_t shiftop) +uint64_t HELPER(neon_rshl_s64)(uint64_t val, uint64_t shift) { - int8_t shift = (int8_t)shiftop; - int64_t val = valop; - if ((shift >= 64) || (shift <= -64)) { - val = 0; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == INT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x4000000000000000LL; - } else { - val++; - val >>= 1; - } - } else { - val <<= shift; - } - return val; + return do_sqrshl_d(val, (int8_t)shift, true, NULL); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8 || \ - tmp < -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> (-tmp - 1); \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, NULL)) NEON_VOP(rshl_u8, neon_u8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, NULL)) NEON_VOP(rshl_u16, neon_u16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shiftop) +uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift) { - uint32_t dest; - int8_t shift = (int8_t)shiftop; - if (shift >= 32 || shift < -32) { - dest = 0; - } else if (shift == -32) { - dest = val >> 31; - } else if (shift < 0) { - uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - } - return dest; + return do_uqrshl_bhs(val, (int8_t)shift, 32, true, NULL); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shiftop) +uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shift) { - int8_t shift = (uint8_t)shiftop; - if (shift >= 64 || shift < -64) { - val = 0; - } else if (shift == -64) { - /* Rounding a 1-bit result just preserves that bit. */ - val >>= 63; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == UINT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x8000000000000000ULL; - } else { - val++; - val >>= 1; - } - } else { - val <<= shift; - } - return val; + return do_uqrshl_d(val, (int8_t)shift, true, NULL); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = 0; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = ~0; \ - } \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) NEON_VOP_ENV(qshl_u8, neon_u8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) NEON_VOP_ENV(qshl_u16, neon_u16, 2) -NEON_VOP_ENV(qshl_u32, neon_u32, 1) #undef NEON_FN -uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shiftop) +uint32_t HELPER(neon_qshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) { - int8_t shift = (int8_t)shiftop; - if (shift >= 64) { - if (val) { - val = ~(uint64_t)0; - SET_QC(); - } - } else if (shift <= -64) { - val = 0; - } else if (shift < 0) { - val >>= -shift; - } else { - uint64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = ~(uint64_t)0; - } - } - return val; + return do_uqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } else { \ - dest = src1; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> 31; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } \ - }} while (0) +uint64_t HELPER(neon_qshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) +{ + return do_uqrshl_d(val, (int8_t)shift, false, env->vfp.qc); +} + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) NEON_VOP_ENV(qshl_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) NEON_VOP_ENV(qshl_s16, neon_s16, 2) -NEON_VOP_ENV(qshl_s32, neon_s32, 1) #undef NEON_FN -uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop) +uint32_t HELPER(neon_qshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) { - int8_t shift = (uint8_t)shiftop; - int64_t val = valop; - if (shift >= 64) { - if (val) { - SET_QC(); - val = (val >> 63) ^ ~SIGNBIT64; - } - } else if (shift <= -64) { - val >>= 63; - } else if (shift < 0) { - val >>= -shift; - } else { - int64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = (tmp >> 63) ^ ~SIGNBIT64; - } - } - return val; + return do_sqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - if (src1 & (1 << (sizeof(src1) * 8 - 1))) { \ - SET_QC(); \ - dest = 0; \ - } else { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = 0; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = src1 >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = ~0; \ - } \ - } \ - }} while (0) -NEON_VOP_ENV(qshlu_s8, neon_u8, 4) -NEON_VOP_ENV(qshlu_s16, neon_u16, 2) +uint64_t HELPER(neon_qshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift) +{ + return do_sqrshl_d(val, (int8_t)shift, false, env->vfp.qc); +} + +#define NEON_FN(dest, src1, src2) \ + (dest = do_suqrshl_bhs(src1, (int8_t)src2, 8, false, env->vfp.qc)) +NEON_VOP_ENV(qshlu_s8, neon_s8, 4) #undef NEON_FN -uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t valop, uint32_t shiftop) +#define NEON_FN(dest, src1, src2) \ + (dest = do_suqrshl_bhs(src1, (int8_t)src2, 16, false, env->vfp.qc)) +NEON_VOP_ENV(qshlu_s16, neon_s16, 2) +#undef NEON_FN + +uint32_t HELPER(neon_qshlu_s32)(CPUARMState *env, uint32_t val, uint32_t shift) { - if ((int32_t)valop < 0) { - SET_QC(); - return 0; - } - return helper_neon_qshl_u32(env, valop, shiftop); + return do_suqrshl_bhs(val, (int8_t)shift, 32, false, env->vfp.qc); } -uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop) +uint64_t HELPER(neon_qshlu_s64)(CPUARMState *env, uint64_t val, uint64_t shift) { - if ((int64_t)valop < 0) { - SET_QC(); - return 0; - } - return helper_neon_qshl_u64(env, valop, shiftop); + return do_suqrshl_d(val, (int8_t)shift, false, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = ~0; \ - } else { \ - dest = 0; \ - } \ - } else if (tmp < -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \ - dest = src1 >> (sizeof(src1) * 8 - 1); \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = ~0; \ - } \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u8, neon_u8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_u16, neon_u16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shiftop) +uint32_t HELPER(neon_qrshl_u32)(CPUARMState *env, uint32_t val, uint32_t shift) { - uint32_t dest; - int8_t shift = (int8_t)shiftop; - if (shift >= 32) { - if (val) { - SET_QC(); - dest = ~0; - } else { - dest = 0; - } - } else if (shift < -32) { - dest = 0; - } else if (shift == -32) { - dest = val >> 31; - } else if (shift < 0) { - uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - if ((dest >> shift) != val) { - SET_QC(); - dest = ~0; - } - } - return dest; + return do_uqrshl_bhs(val, (int8_t)shift, 32, true, env->vfp.qc); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shiftop) +uint64_t HELPER(neon_qrshl_u64)(CPUARMState *env, uint64_t val, uint64_t shift) { - int8_t shift = (int8_t)shiftop; - if (shift >= 64) { - if (val) { - SET_QC(); - val = ~0; - } - } else if (shift < -64) { - val = 0; - } else if (shift == -64) { - val >>= 63; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == UINT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x8000000000000000ULL; - } else { - val++; - val >>= 1; - } - } else { \ - uint64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = ~0; - } - } - return val; + return do_uqrshl_d(val, (int8_t)shift, true, env->vfp.qc); } -#define NEON_FN(dest, src1, src2) do { \ - int8_t tmp; \ - tmp = (int8_t)src2; \ - if (tmp >= (ssize_t)sizeof(src1) * 8) { \ - if (src1) { \ - SET_QC(); \ - dest = (typeof(dest))(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } else { \ - dest = 0; \ - } \ - } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \ - dest = 0; \ - } else if (tmp < 0) { \ - dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \ - } else { \ - dest = src1 << tmp; \ - if ((dest >> tmp) != src1) { \ - SET_QC(); \ - dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \ - if (src1 > 0) { \ - dest--; \ - } \ - } \ - }} while (0) +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 8, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s8, neon_s8, 4) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, (int8_t)src2, 16, true, env->vfp.qc)) NEON_VOP_ENV(qrshl_s16, neon_s16, 2) #undef NEON_FN -/* The addition of the rounding constant may overflow, so we use an - * intermediate 64 bit accumulator. */ -uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t valop, uint32_t shiftop) +uint32_t HELPER(neon_qrshl_s32)(CPUARMState *env, uint32_t val, uint32_t shift) { - int32_t dest; - int32_t val = (int32_t)valop; - int8_t shift = (int8_t)shiftop; - if (shift >= 32) { - if (val) { - SET_QC(); - dest = (val >> 31) ^ ~SIGNBIT; - } else { - dest = 0; - } - } else if (shift <= -32) { - dest = 0; - } else if (shift < 0) { - int64_t big_dest = ((int64_t)val + (1 << (-1 - shift))); - dest = big_dest >> -shift; - } else { - dest = val << shift; - if ((dest >> shift) != val) { - SET_QC(); - dest = (val >> 31) ^ ~SIGNBIT; - } - } - return dest; + return do_sqrshl_bhs(val, (int8_t)shift, 32, true, env->vfp.qc); } -/* Handling addition overflow with 64 bit input values is more - * tricky than with 32 bit values. */ -uint64_t HELPER(neon_qrshl_s64)(CPUARMState *env, uint64_t valop, uint64_t shiftop) +uint64_t HELPER(neon_qrshl_s64)(CPUARMState *env, uint64_t val, uint64_t shift) { - int8_t shift = (uint8_t)shiftop; - int64_t val = valop; - - if (shift >= 64) { - if (val) { - SET_QC(); - val = (val >> 63) ^ ~SIGNBIT64; - } - } else if (shift <= -64) { - val = 0; - } else if (shift < 0) { - val >>= (-shift - 1); - if (val == INT64_MAX) { - /* In this case, it means that the rounding constant is 1, - * and the addition would overflow. Return the actual - * result directly. */ - val = 0x4000000000000000ULL; - } else { - val++; - val >>= 1; - } - } else { - int64_t tmp = val; - val <<= shift; - if ((val >> shift) != tmp) { - SET_QC(); - val = (tmp >> 63) ^ ~SIGNBIT64; - } - } - return val; + return do_sqrshl_d(val, (int8_t)shift, true, env->vfp.qc); } uint32_t HELPER(neon_add_u8)(uint32_t a, uint32_t b) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 54 +++++++++++++++++++++++ target/arm/sve.decode | 17 ++++++++ target/arm/sve_helper.c | 87 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 18 ++++++++ 4 files changed, 176 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ URECPE 01000100 .. 000 000 101 ... ..... ..... @rd_pg_rn URSQRTE 01000100 .. 000 001 101 ... ..... ..... @rd_pg_rn SQABS 01000100 .. 001 000 101 ... ..... ..... @rd_pg_rn SQNEG 01000100 .. 001 001 101 ... ..... ..... @rd_pg_rn + +### SVE2 saturating/rounding bitwise shift left (predicated) + +SRSHL 01000100 .. 000 010 100 ... ..... ..... @rdn_pg_rm +URSHL 01000100 .. 000 011 100 ... ..... ..... @rdn_pg_rm +SRSHL 01000100 .. 000 110 100 ... ..... ..... @rdm_pg_rn # SRSHLR +URSHL 01000100 .. 000 111 100 ... ..... ..... @rdm_pg_rn # URSHLR + +SQSHL 01000100 .. 001 000 100 ... ..... ..... @rdn_pg_rm +UQSHL 01000100 .. 001 001 100 ... ..... ..... @rdn_pg_rm +SQSHL 01000100 .. 001 100 100 ... ..... ..... @rdm_pg_rn # SQSHLR +UQSHL 01000100 .. 001 101 100 ... ..... ..... @rdm_pg_rn # UQSHLR + +SQRSHL 01000100 .. 001 010 100 ... ..... ..... @rdn_pg_rm +UQRSHL 01000100 .. 001 011 100 ... ..... ..... @rdn_pg_rm +SQRSHL 01000100 .. 001 110 100 ... ..... ..... @rdm_pg_rn # SQRSHLR +UQRSHL 01000100 .. 001 111 100 ... ..... ..... @rdm_pg_rn # UQRSHLR diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" #include "tcg/tcg.h" +#include "vec_internal.h" /* Note that vector data is stored in host-endian 64-bit chunks, @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uadalp_zpzz_h, uint16_t, H1_2, do_uadalp_h) DO_ZPZZ(sve2_uadalp_zpzz_s, uint32_t, H1_4, do_uadalp_s) DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d) +#define do_srshl_b(n, m) do_sqrshl_bhs(n, m, 8, true, NULL) +#define do_srshl_h(n, m) do_sqrshl_bhs(n, m, 16, true, NULL) +#define do_srshl_s(n, m) do_sqrshl_bhs(n, m, 32, true, NULL) +#define do_srshl_d(n, m) do_sqrshl_d(n, m, true, NULL) + +DO_ZPZZ(sve2_srshl_zpzz_b, int8_t, H1, do_srshl_b) +DO_ZPZZ(sve2_srshl_zpzz_h, int16_t, H1_2, do_srshl_h) +DO_ZPZZ(sve2_srshl_zpzz_s, int32_t, H1_4, do_srshl_s) +DO_ZPZZ_D(sve2_srshl_zpzz_d, int64_t, do_srshl_d) + +#define do_urshl_b(n, m) do_uqrshl_bhs(n, (int8_t)m, 8, true, NULL) +#define do_urshl_h(n, m) do_uqrshl_bhs(n, (int16_t)m, 16, true, NULL) +#define do_urshl_s(n, m) do_uqrshl_bhs(n, m, 32, true, NULL) +#define do_urshl_d(n, m) do_uqrshl_d(n, m, true, NULL) + +DO_ZPZZ(sve2_urshl_zpzz_b, uint8_t, H1, do_urshl_b) +DO_ZPZZ(sve2_urshl_zpzz_h, uint16_t, H1_2, do_urshl_h) +DO_ZPZZ(sve2_urshl_zpzz_s, uint32_t, H1_4, do_urshl_s) +DO_ZPZZ_D(sve2_urshl_zpzz_d, uint64_t, do_urshl_d) + +/* + * Unlike the NEON and AdvSIMD versions, there is no QC bit to set. + * We pass in a pointer to a dummy saturation field to trigger + * the saturating arithmetic but discard the information about + * whether it has occurred. + */ +#define do_sqshl_b(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 8, false, &discard); }) +#define do_sqshl_h(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 16, false, &discard); }) +#define do_sqshl_s(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 32, false, &discard); }) +#define do_sqshl_d(n, m) \ + ({ uint32_t discard; do_sqrshl_d(n, m, false, &discard); }) + +DO_ZPZZ(sve2_sqshl_zpzz_b, int8_t, H1_2, do_sqshl_b) +DO_ZPZZ(sve2_sqshl_zpzz_h, int16_t, H1_2, do_sqshl_h) +DO_ZPZZ(sve2_sqshl_zpzz_s, int32_t, H1_4, do_sqshl_s) +DO_ZPZZ_D(sve2_sqshl_zpzz_d, int64_t, do_sqshl_d) + +#define do_uqshl_b(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, false, &discard); }) +#define do_uqshl_h(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, false, &discard); }) +#define do_uqshl_s(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, m, 32, false, &discard); }) +#define do_uqshl_d(n, m) \ + ({ uint32_t discard; do_uqrshl_d(n, m, false, &discard); }) + +DO_ZPZZ(sve2_uqshl_zpzz_b, uint8_t, H1_2, do_uqshl_b) +DO_ZPZZ(sve2_uqshl_zpzz_h, uint16_t, H1_2, do_uqshl_h) +DO_ZPZZ(sve2_uqshl_zpzz_s, uint32_t, H1_4, do_uqshl_s) +DO_ZPZZ_D(sve2_uqshl_zpzz_d, uint64_t, do_uqshl_d) + +#define do_sqrshl_b(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 8, true, &discard); }) +#define do_sqrshl_h(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 16, true, &discard); }) +#define do_sqrshl_s(n, m) \ + ({ uint32_t discard; do_sqrshl_bhs(n, m, 32, true, &discard); }) +#define do_sqrshl_d(n, m) \ + ({ uint32_t discard; do_sqrshl_d(n, m, true, &discard); }) + +DO_ZPZZ(sve2_sqrshl_zpzz_b, int8_t, H1_2, do_sqrshl_b) +DO_ZPZZ(sve2_sqrshl_zpzz_h, int16_t, H1_2, do_sqrshl_h) +DO_ZPZZ(sve2_sqrshl_zpzz_s, int32_t, H1_4, do_sqrshl_s) +DO_ZPZZ_D(sve2_sqrshl_zpzz_d, int64_t, do_sqrshl_d) + +#undef do_sqrshl_d + +#define do_uqrshl_b(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int8_t)m, 8, true, &discard); }) +#define do_uqrshl_h(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, (int16_t)m, 16, true, &discard); }) +#define do_uqrshl_s(n, m) \ + ({ uint32_t discard; do_uqrshl_bhs(n, m, 32, true, &discard); }) +#define do_uqrshl_d(n, m) \ + ({ uint32_t discard; do_uqrshl_d(n, m, true, &discard); }) + +DO_ZPZZ(sve2_uqrshl_zpzz_b, uint8_t, H1_2, do_uqrshl_b) +DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h) +DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s) +DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d) + +#undef do_uqrshl_d + #undef DO_ZPZZ #undef DO_ZPZZ_D diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQNEG(DisasContext *s, arg_rpr_esz *a) }; return do_sve2_zpz_ool(s, a, fns[a->esz]); } + +#define DO_SVE2_ZPZZ(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ +{ \ + static gen_helper_gvec_4 * const fns[4] = { \ + gen_helper_sve2_##name##_zpzz_b, gen_helper_sve2_##name##_zpzz_h, \ + gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d, \ + }; \ + return do_sve2_zpzz_ool(s, a, fns[a->esz]); \ +} + +DO_SVE2_ZPZZ(SQSHL, sqshl) +DO_SVE2_ZPZZ(SQRSHL, sqrshl) +DO_SVE2_ZPZZ(SRSHL, srshl) + +DO_SVE2_ZPZZ(UQSHL, uqshl) +DO_SVE2_ZPZZ(UQRSHL, uqrshl) +DO_SVE2_ZPZZ(URSHL, urshl) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 54 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 11 ++++++++ target/arm/sve_helper.c | 39 +++++++++++++++++++++++++++ target/arm/translate-sve.c | 8 ++++++ 4 files changed, 112 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_uqrshl_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_srhadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_urhadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_shsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uhsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQRSHL 01000100 .. 001 010 100 ... ..... ..... @rdn_pg_rm UQRSHL 01000100 .. 001 011 100 ... ..... ..... @rdn_pg_rm SQRSHL 01000100 .. 001 110 100 ... ..... ..... @rdm_pg_rn # SQRSHLR UQRSHL 01000100 .. 001 111 100 ... ..... ..... @rdm_pg_rn # UQRSHLR + +### SVE2 integer halving add/subtract (predicated) + +SHADD 01000100 .. 010 000 100 ... ..... ..... @rdn_pg_rm +UHADD 01000100 .. 010 001 100 ... ..... ..... @rdn_pg_rm +SHSUB 01000100 .. 010 010 100 ... ..... ..... @rdn_pg_rm +UHSUB 01000100 .. 010 011 100 ... ..... ..... @rdn_pg_rm +SRHADD 01000100 .. 010 100 100 ... ..... ..... @rdn_pg_rm +URHADD 01000100 .. 010 101 100 ... ..... ..... @rdn_pg_rm +SHSUB 01000100 .. 010 110 100 ... ..... ..... @rdm_pg_rn # SHSUBR +UHSUB 01000100 .. 010 111 100 ... ..... ..... @rdm_pg_rn # UHSUBR diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d) #undef do_uqrshl_d +#define DO_HADD_BHS(n, m) (((int64_t)n + m) >> 1) +#define DO_HADD_D(n, m) ((n >> 1) + (m >> 1) + (n & m & 1)) + +DO_ZPZZ(sve2_shadd_zpzz_b, int8_t, H1, DO_HADD_BHS) +DO_ZPZZ(sve2_shadd_zpzz_h, int16_t, H1_2, DO_HADD_BHS) +DO_ZPZZ(sve2_shadd_zpzz_s, int32_t, H1_4, DO_HADD_BHS) +DO_ZPZZ_D(sve2_shadd_zpzz_d, int64_t, DO_HADD_D) + +DO_ZPZZ(sve2_uhadd_zpzz_b, uint8_t, H1, DO_HADD_BHS) +DO_ZPZZ(sve2_uhadd_zpzz_h, uint16_t, H1_2, DO_HADD_BHS) +DO_ZPZZ(sve2_uhadd_zpzz_s, uint32_t, H1_4, DO_HADD_BHS) +DO_ZPZZ_D(sve2_uhadd_zpzz_d, uint64_t, DO_HADD_D) + +#define DO_RHADD_BHS(n, m) (((int64_t)n + m + 1) >> 1) +#define DO_RHADD_D(n, m) ((n >> 1) + (m >> 1) + ((n | m) & 1)) + +DO_ZPZZ(sve2_srhadd_zpzz_b, int8_t, H1, DO_RHADD_BHS) +DO_ZPZZ(sve2_srhadd_zpzz_h, int16_t, H1_2, DO_RHADD_BHS) +DO_ZPZZ(sve2_srhadd_zpzz_s, int32_t, H1_4, DO_RHADD_BHS) +DO_ZPZZ_D(sve2_srhadd_zpzz_d, int64_t, DO_RHADD_D) + +DO_ZPZZ(sve2_urhadd_zpzz_b, uint8_t, H1, DO_RHADD_BHS) +DO_ZPZZ(sve2_urhadd_zpzz_h, uint16_t, H1_2, DO_RHADD_BHS) +DO_ZPZZ(sve2_urhadd_zpzz_s, uint32_t, H1_4, DO_RHADD_BHS) +DO_ZPZZ_D(sve2_urhadd_zpzz_d, uint64_t, DO_RHADD_D) + +#define DO_HSUB_BHS(n, m) (((int64_t)n - m) >> 1) +#define DO_HSUB_D(n, m) ((n >> 1) - (m >> 1) - (~n & m & 1)) + +DO_ZPZZ(sve2_shsub_zpzz_b, int8_t, H1, DO_HSUB_BHS) +DO_ZPZZ(sve2_shsub_zpzz_h, int16_t, H1_2, DO_HSUB_BHS) +DO_ZPZZ(sve2_shsub_zpzz_s, int32_t, H1_4, DO_HSUB_BHS) +DO_ZPZZ_D(sve2_shsub_zpzz_d, int64_t, DO_HSUB_D) + +DO_ZPZZ(sve2_uhsub_zpzz_b, uint8_t, H1, DO_HSUB_BHS) +DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS) +DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS) +DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) + #undef DO_ZPZZ #undef DO_ZPZZ_D diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ(SRSHL, srshl) DO_SVE2_ZPZZ(UQSHL, uqshl) DO_SVE2_ZPZZ(UQRSHL, uqrshl) DO_SVE2_ZPZZ(URSHL, urshl) + +DO_SVE2_ZPZZ(SHADD, shadd) +DO_SVE2_ZPZZ(SRHADD, srhadd) +DO_SVE2_ZPZZ(SHSUB, shsub) + +DO_SVE2_ZPZZ(UHADD, uhadd) +DO_SVE2_ZPZZ(URHADD, urhadd) +DO_SVE2_ZPZZ(UHSUB, uhsub) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 45 ++++++++++++++++++++++ target/arm/sve.decode | 8 ++++ target/arm/sve_helper.c | 76 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 6 +++ 4 files changed, 135 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_addp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SRHADD 01000100 .. 010 100 100 ... ..... ..... @rdn_pg_rm URHADD 01000100 .. 010 101 100 ... ..... ..... @rdn_pg_rm SHSUB 01000100 .. 010 110 100 ... ..... ..... @rdm_pg_rn # SHSUBR UHSUB 01000100 .. 010 111 100 ... ..... ..... @rdm_pg_rn # UHSUBR + +### SVE2 integer pairwise arithmetic + +ADDP 01000100 .. 010 001 101 ... ..... ..... @rdn_pg_rm +SMAXP 01000100 .. 010 100 101 ... ..... ..... @rdn_pg_rm +UMAXP 01000100 .. 010 101 101 ... ..... ..... @rdn_pg_rm +SMINP 01000100 .. 010 110 101 ... ..... ..... @rdn_pg_rm +UMINP 01000100 .. 010 111 101 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) #undef DO_ZPZZ #undef DO_ZPZZ_D +/* + * Three operand expander, operating on element pairs. + * If the slot I is even, the elements from from VN {I, I+1}. + * If the slot I is odd, the elements from from VM {I-1, I}. + * Load all of the input elements in each pair before overwriting output. + */ +#define DO_ZPZZ_PAIR(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPE n0 = *(TYPE *)(vn + H(i)); \ + TYPE m0 = *(TYPE *)(vm + H(i)); \ + TYPE n1 = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE m1 = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(n0, n1); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(m0, m1); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +/* Similarly, specialized for 64-bit operands. */ +#define DO_ZPZZ_PAIR_D(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; \ + TYPE *d = vd, *n = vn, *m = vm; \ + uint8_t *pg = vg; \ + for (i = 0; i < opr_sz; i += 2) { \ + TYPE n0 = n[i], n1 = n[i + 1]; \ + TYPE m0 = m[i], m1 = m[i + 1]; \ + if (pg[H1(i)] & 1) { \ + d[i] = OP(n0, n1); \ + } \ + if (pg[H1(i + 1)] & 1) { \ + d[i + 1] = OP(m0, m1); \ + } \ + } \ +} + +DO_ZPZZ_PAIR(sve2_addp_zpzz_b, uint8_t, H1, DO_ADD) +DO_ZPZZ_PAIR(sve2_addp_zpzz_h, uint16_t, H1_2, DO_ADD) +DO_ZPZZ_PAIR(sve2_addp_zpzz_s, uint32_t, H1_4, DO_ADD) +DO_ZPZZ_PAIR_D(sve2_addp_zpzz_d, uint64_t, DO_ADD) + +DO_ZPZZ_PAIR(sve2_umaxp_zpzz_b, uint8_t, H1, DO_MAX) +DO_ZPZZ_PAIR(sve2_umaxp_zpzz_h, uint16_t, H1_2, DO_MAX) +DO_ZPZZ_PAIR(sve2_umaxp_zpzz_s, uint32_t, H1_4, DO_MAX) +DO_ZPZZ_PAIR_D(sve2_umaxp_zpzz_d, uint64_t, DO_MAX) + +DO_ZPZZ_PAIR(sve2_uminp_zpzz_b, uint8_t, H1, DO_MIN) +DO_ZPZZ_PAIR(sve2_uminp_zpzz_h, uint16_t, H1_2, DO_MIN) +DO_ZPZZ_PAIR(sve2_uminp_zpzz_s, uint32_t, H1_4, DO_MIN) +DO_ZPZZ_PAIR_D(sve2_uminp_zpzz_d, uint64_t, DO_MIN) + +DO_ZPZZ_PAIR(sve2_smaxp_zpzz_b, int8_t, H1, DO_MAX) +DO_ZPZZ_PAIR(sve2_smaxp_zpzz_h, int16_t, H1_2, DO_MAX) +DO_ZPZZ_PAIR(sve2_smaxp_zpzz_s, int32_t, H1_4, DO_MAX) +DO_ZPZZ_PAIR_D(sve2_smaxp_zpzz_d, int64_t, DO_MAX) + +DO_ZPZZ_PAIR(sve2_sminp_zpzz_b, int8_t, H1, DO_MIN) +DO_ZPZZ_PAIR(sve2_sminp_zpzz_h, int16_t, H1_2, DO_MIN) +DO_ZPZZ_PAIR(sve2_sminp_zpzz_s, int32_t, H1_4, DO_MIN) +DO_ZPZZ_PAIR_D(sve2_sminp_zpzz_d, int64_t, DO_MIN) + +#undef DO_ZPZZ_PAIR +#undef DO_ZPZZ_PAIR_D + /* Three-operand expander, controlled by a predicate, in which the * third operand is "wide". That is, for D = N op M, the same 64-bit * value of M is used with all of the narrower values of N. diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ(SHSUB, shsub) DO_SVE2_ZPZZ(UHADD, uhadd) DO_SVE2_ZPZZ(URHADD, urhadd) DO_SVE2_ZPZZ(UHSUB, uhsub) + +DO_SVE2_ZPZZ(ADDP, addp) +DO_SVE2_ZPZZ(SMAXP, smaxp) +DO_SVE2_ZPZZ(UMAXP, umaxp) +DO_SVE2_ZPZZ(SMINP, sminp) +DO_SVE2_ZPZZ(UMINP, uminp) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 54 +++++++++++ target/arm/sve.decode | 11 +++ target/arm/sve_helper.c | 194 ++++++++++++++++++++++++++----------- target/arm/translate-sve.c | 7 ++ 4 files changed, 210 insertions(+), 56 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SMAXP 01000100 .. 010 100 101 ... ..... ..... @rdn_pg_rm UMAXP 01000100 .. 010 101 101 ... ..... ..... @rdn_pg_rm SMINP 01000100 .. 010 110 101 ... ..... ..... @rdn_pg_rm UMINP 01000100 .. 010 111 101 ... ..... ..... @rdn_pg_rm + +### SVE2 saturating add/subtract (predicated) + +SQADD_zpzz 01000100 .. 011 000 100 ... ..... ..... @rdn_pg_rm +UQADD_zpzz 01000100 .. 011 001 100 ... ..... ..... @rdn_pg_rm +SQSUB_zpzz 01000100 .. 011 010 100 ... ..... ..... @rdn_pg_rm +UQSUB_zpzz 01000100 .. 011 011 100 ... ..... ..... @rdn_pg_rm +SUQADD 01000100 .. 011 100 100 ... ..... ..... @rdn_pg_rm +USQADD 01000100 .. 011 101 100 ... ..... ..... @rdn_pg_rm +SQSUB_zpzz 01000100 .. 011 110 100 ... ..... ..... @rdm_pg_rn # SQSUBR +UQSUB_zpzz 01000100 .. 011 111 100 ... ..... ..... @rdm_pg_rn # UQSUBR diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS) DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS) DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max) +{ + return val >= max ? max : val <= min ? min : val; +} + +#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX) +#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX) +#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX) + +static inline int64_t do_sqadd_d(int64_t n, int64_t m) +{ + int64_t r = n + m; + if (((r ^ n) & ~(n ^ m)) < 0) { + /* Signed overflow. */ + return r < 0 ? INT64_MAX : INT64_MIN; + } + return r; +} + +DO_ZPZZ(sve2_sqadd_zpzz_b, int8_t, H1, DO_SQADD_B) +DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H) +DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S) +DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d) + +#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX) +#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX) +#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX) + +static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m) +{ + uint64_t r = n + m; + return r < n ? UINT64_MAX : r; +} + +DO_ZPZZ(sve2_uqadd_zpzz_b, uint8_t, H1, DO_UQADD_B) +DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H) +DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S) +DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d) + +#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX) +#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX) +#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX) + +static inline int64_t do_sqsub_d(int64_t n, int64_t m) +{ + int64_t r = n - m; + if (((r ^ n) & (n ^ m)) < 0) { + /* Signed overflow. */ + return r < 0 ? INT64_MAX : INT64_MIN; + } + return r; +} + +DO_ZPZZ(sve2_sqsub_zpzz_b, int8_t, H1, DO_SQSUB_B) +DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H) +DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S) +DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d) + +#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX) +#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX) +#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX) + +static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m) +{ + return n > m ? n - m : 0; +} + +DO_ZPZZ(sve2_uqsub_zpzz_b, uint8_t, H1, DO_UQSUB_B) +DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H) +DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S) +DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d) + +#define DO_SUQADD_B(n, m) \ + do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX) +#define DO_SUQADD_H(n, m) \ + do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX) +#define DO_SUQADD_S(n, m) \ + do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX) + +static inline int64_t do_suqadd_d(int64_t n, uint64_t m) +{ + uint64_t r = n + m; + + if (n < 0) { + /* Note that m - abs(n) cannot underflow. */ + if (r > INT64_MAX) { + /* Result is either very large positive or negative. */ + if (m > -n) { + /* m > abs(n), so r is a very large positive. */ + return INT64_MAX; + } + /* Result is negative. */ + } + } else { + /* Both inputs are positive: check for overflow. */ + if (r < m || r > INT64_MAX) { + return INT64_MAX; + } + } + return r; +} + +DO_ZPZZ(sve2_suqadd_zpzz_b, uint8_t, H1, DO_SUQADD_B) +DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H) +DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S) +DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d) + +#define DO_USQADD_B(n, m) \ + do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX) +#define DO_USQADD_H(n, m) \ + do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX) +#define DO_USQADD_S(n, m) \ + do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX) + +static inline uint64_t do_usqadd_d(uint64_t n, int64_t m) +{ + uint64_t r = n + m; + + if (m < 0) { + return n < -m ? 0 : r; + } + return r < n ? UINT64_MAX : r; +} + +DO_ZPZZ(sve2_usqadd_zpzz_b, uint8_t, H1, DO_USQADD_B) +DO_ZPZZ(sve2_usqadd_zpzz_h, uint16_t, H1_2, DO_USQADD_H) +DO_ZPZZ(sve2_usqadd_zpzz_s, uint32_t, H1_4, DO_USQADD_S) +DO_ZPZZ_D(sve2_usqadd_zpzz_d, uint64_t, do_usqadd_d) + #undef DO_ZPZZ #undef DO_ZPZZ_D @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_b)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int8_t)) { - int r = *(int8_t *)(a + i) + b; - if (r > INT8_MAX) { - r = INT8_MAX; - } else if (r < INT8_MIN) { - r = INT8_MIN; - } - *(int8_t *)(d + i) = r; + *(int8_t *)(d + i) = DO_SQADD_B(b, *(int8_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_h)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int16_t)) { - int r = *(int16_t *)(a + i) + b; - if (r > INT16_MAX) { - r = INT16_MAX; - } else if (r < INT16_MIN) { - r = INT16_MIN; - } - *(int16_t *)(d + i) = r; + *(int16_t *)(d + i) = DO_SQADD_H(b, *(int16_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_s)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int32_t)) { - int64_t r = *(int32_t *)(a + i) + b; - if (r > INT32_MAX) { - r = INT32_MAX; - } else if (r < INT32_MIN) { - r = INT32_MIN; - } - *(int32_t *)(d + i) = r; + *(int32_t *)(d + i) = DO_SQADD_S(b, *(int32_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sqaddi_d)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int64_t)) { - int64_t ai = *(int64_t *)(a + i); - int64_t r = ai + b; - if (((r ^ ai) & ~(ai ^ b)) < 0) { - /* Signed overflow. */ - r = (r < 0 ? INT64_MAX : INT64_MIN); - } - *(int64_t *)(d + i) = r; + *(int64_t *)(d + i) = do_sqadd_d(b, *(int64_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_b)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint8_t)) { - int r = *(uint8_t *)(a + i) + b; - if (r > UINT8_MAX) { - r = UINT8_MAX; - } else if (r < 0) { - r = 0; - } - *(uint8_t *)(d + i) = r; + *(uint8_t *)(d + i) = DO_UQADD_B(b, *(uint8_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_h)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint16_t)) { - int r = *(uint16_t *)(a + i) + b; - if (r > UINT16_MAX) { - r = UINT16_MAX; - } else if (r < 0) { - r = 0; - } - *(uint16_t *)(d + i) = r; + *(uint16_t *)(d + i) = DO_UQADD_H(b, *(uint16_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_s)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint32_t)) { - int64_t r = *(uint32_t *)(a + i) + b; - if (r > UINT32_MAX) { - r = UINT32_MAX; - } else if (r < 0) { - r = 0; - } - *(uint32_t *)(d + i) = r; + *(uint32_t *)(d + i) = DO_UQADD_S(b, *(uint32_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqaddi_d)(void *d, void *a, uint64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint64_t)) { - uint64_t r = *(uint64_t *)(a + i) + b; - if (r < b) { - r = UINT64_MAX; - } - *(uint64_t *)(d + i) = r; + *(uint64_t *)(d + i) = do_uqadd_d(b, *(uint64_t *)(a + i)); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uqsubi_d)(void *d, void *a, uint64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint64_t)) { - uint64_t ai = *(uint64_t *)(a + i); - *(uint64_t *)(d + i) = (ai < b ? 0 : ai - b); + *(uint64_t *)(d + i) = do_uqsub_d(*(uint64_t *)(a + i), b); } } diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ(SMAXP, smaxp) DO_SVE2_ZPZZ(UMAXP, umaxp) DO_SVE2_ZPZZ(SMINP, sminp) DO_SVE2_ZPZZ(UMINP, uminp) + +DO_SVE2_ZPZZ(SQADD_zpzz, sqadd) +DO_SVE2_ZPZZ(UQADD_zpzz, uqadd) +DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub) +DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub) +DO_SVE2_ZPZZ(SUQADD, suqadd) +DO_SVE2_ZPZZ(USQADD, usqadd) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 24 ++++++++++++++++++++ target/arm/sve.decode | 19 ++++++++++++++++ target/arm/sve_helper.c | 43 +++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 46 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 132 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_ssubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uaddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_usubl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SUQADD 01000100 .. 011 100 100 ... ..... ..... @rdn_pg_rm USQADD 01000100 .. 011 101 100 ... ..... ..... @rdn_pg_rm SQSUB_zpzz 01000100 .. 011 110 100 ... ..... ..... @rdm_pg_rn # SQSUBR UQSUB_zpzz 01000100 .. 011 111 100 ... ..... ..... @rdm_pg_rn # UQSUBR + +#### SVE2 Widening Integer Arithmetic + +## SVE2 integer add/subtract long + +SADDLB 01000101 .. 0 ..... 00 0000 ..... ..... @rd_rn_rm +SADDLT 01000101 .. 0 ..... 00 0001 ..... ..... @rd_rn_rm +UADDLB 01000101 .. 0 ..... 00 0010 ..... ..... @rd_rn_rm +UADDLT 01000101 .. 0 ..... 00 0011 ..... ..... @rd_rn_rm + +SSUBLB 01000101 .. 0 ..... 00 0100 ..... ..... @rd_rn_rm +SSUBLT 01000101 .. 0 ..... 00 0101 ..... ..... @rd_rn_rm +USUBLB 01000101 .. 0 ..... 00 0110 ..... ..... @rd_rn_rm +USUBLT 01000101 .. 0 ..... 00 0111 ..... ..... @rd_rn_rm + +SABDLB 01000101 .. 0 ..... 00 1100 ..... ..... @rd_rn_rm +SABDLT 01000101 .. 0 ..... 00 1101 ..... ..... @rd_rn_rm +UABDLB 01000101 .. 0 ..... 00 1110 ..... ..... @rd_rn_rm +UABDLT 01000101 .. 0 ..... 00 1111 ..... ..... @rd_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZW(sve_lsl_zzw_s, uint32_t, uint64_t, H1_4, DO_LSL) #undef DO_ZPZ #undef DO_ZPZ_D +/* + * Three-operand expander, unpredicated, in which the two inputs are + * selected from the top or bottom half of the wide column. + */ +#define DO_ZZZ_TB(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + int sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, mm); \ + } \ +} + +DO_ZZZ_TB(sve2_saddl_h, int16_t, int8_t, H1_2, H1, DO_ADD) +DO_ZZZ_TB(sve2_saddl_s, int32_t, int16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_TB(sve2_saddl_d, int64_t, int32_t, , H1_4, DO_ADD) + +DO_ZZZ_TB(sve2_ssubl_h, int16_t, int8_t, H1_2, H1, DO_SUB) +DO_ZZZ_TB(sve2_ssubl_s, int32_t, int16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_TB(sve2_ssubl_d, int64_t, int32_t, , H1_4, DO_SUB) + +DO_ZZZ_TB(sve2_sabdl_h, int16_t, int8_t, H1_2, H1, DO_ABD) +DO_ZZZ_TB(sve2_sabdl_s, int32_t, int16_t, H1_4, H1_2, DO_ABD) +DO_ZZZ_TB(sve2_sabdl_d, int64_t, int32_t, , H1_4, DO_ABD) + +DO_ZZZ_TB(sve2_uaddl_h, uint16_t, uint8_t, H1_2, H1, DO_ADD) +DO_ZZZ_TB(sve2_uaddl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_TB(sve2_uaddl_d, uint64_t, uint32_t, , H1_4, DO_ADD) + +DO_ZZZ_TB(sve2_usubl_h, uint16_t, uint8_t, H1_2, H1, DO_SUB) +DO_ZZZ_TB(sve2_usubl_s, uint32_t, uint16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_TB(sve2_usubl_d, uint64_t, uint32_t, , H1_4, DO_SUB) + +DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, H1_2, H1, DO_ABD) +DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD) +DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, , H1_4, DO_ABD) + +#undef DO_ZZZ_TB + /* Two-operand reduction expander, controlled by a predicate. * The difference between TYPERED and TYPERET has to do with * sign-extension. E.g. for SMAX, TYPERED must be signed, diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub) DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub) DO_SVE2_ZPZZ(SUQADD, suqadd) DO_SVE2_ZPZZ(USQADD, usqadd) + +/* + * SVE2 Widening Integer Arithmetic + */ + +static bool do_sve2_zzw_ool(DisasContext *s, arg_rrr_esz *a, + gen_helper_gvec_3 *fn, int data) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, data, fn); + } + return true; +} + +#define DO_SVE2_ZZZ_TB(NAME, name, SEL1, SEL2) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ +{ \ + static gen_helper_gvec_3 * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_h, \ + gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ + }; \ + return do_sve2_zzw_ool(s, a, fns[a->esz], (SEL2 << 1) | SEL1); \ +} + +DO_SVE2_ZZZ_TB(SADDLB, saddl, false, false) +DO_SVE2_ZZZ_TB(SSUBLB, ssubl, false, false) +DO_SVE2_ZZZ_TB(SABDLB, sabdl, false, false) + +DO_SVE2_ZZZ_TB(UADDLB, uaddl, false, false) +DO_SVE2_ZZZ_TB(USUBLB, usubl, false, false) +DO_SVE2_ZZZ_TB(UABDLB, uabdl, false, false) + +DO_SVE2_ZZZ_TB(SADDLT, saddl, true, true) +DO_SVE2_ZZZ_TB(SSUBLT, ssubl, true, true) +DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true) + +DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true) +DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true) +DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 6 ++++++ target/arm/translate-sve.c | 4 ++++ 2 files changed, 10 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SABDLB 01000101 .. 0 ..... 00 1100 ..... ..... @rd_rn_rm SABDLT 01000101 .. 0 ..... 00 1101 ..... ..... @rd_rn_rm UABDLB 01000101 .. 0 ..... 00 1110 ..... ..... @rd_rn_rm UABDLT 01000101 .. 0 ..... 00 1111 ..... ..... @rd_rn_rm + +## SVE2 integer add/subtract interleaved long + +SADDLBT 01000101 .. 0 ..... 1000 00 ..... ..... @rd_rn_rm +SSUBLBT 01000101 .. 0 ..... 1000 10 ..... ..... @rd_rn_rm +SSUBLTB 01000101 .. 0 ..... 1000 11 ..... ..... @rd_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_TB(SABDLT, sabdl, true, true) DO_SVE2_ZZZ_TB(UADDLT, uaddl, true, true) DO_SVE2_ZZZ_TB(USUBLT, usubl, true, true) DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true) + +DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true) +DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true) +DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 16 ++++++++++++++++ target/arm/sve.decode | 12 ++++++++++++ target/arm/sve_helper.c | 30 ++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 20 ++++++++++++++++++++ 4 files changed, 78 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_uabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_uabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_uabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_saddw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_ssubw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_ssubw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_uaddw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_uaddw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_usubw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_usubw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UABDLT 01000101 .. 0 ..... 00 1111 ..... ..... @rd_rn_rm SADDLBT 01000101 .. 0 ..... 1000 00 ..... ..... @rd_rn_rm SSUBLBT 01000101 .. 0 ..... 1000 10 ..... ..... @rd_rn_rm SSUBLTB 01000101 .. 0 ..... 1000 11 ..... ..... @rd_rn_rm + +## SVE2 integer add/subtract wide + +SADDWB 01000101 .. 0 ..... 010 000 ..... ..... @rd_rn_rm +SADDWT 01000101 .. 0 ..... 010 001 ..... ..... @rd_rn_rm +UADDWB 01000101 .. 0 ..... 010 010 ..... ..... @rd_rn_rm +UADDWT 01000101 .. 0 ..... 010 011 ..... ..... @rd_rn_rm + +SSUBWB 01000101 .. 0 ..... 010 100 ..... ..... @rd_rn_rm +SSUBWT 01000101 .. 0 ..... 010 101 ..... ..... @rd_rn_rm +USUBWB 01000101 .. 0 ..... 010 110 ..... ..... @rd_rn_rm +USUBWT 01000101 .. 0 ..... 010 111 ..... ..... @rd_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, , H1_4, DO_ABD) #undef DO_ZZZ_TB +#define DO_ZZZ_WTB(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sel2 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, mm); \ + } \ +} + +DO_ZZZ_WTB(sve2_saddw_h, int16_t, int8_t, H1_2, H1, DO_ADD) +DO_ZZZ_WTB(sve2_saddw_s, int32_t, int16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_WTB(sve2_saddw_d, int64_t, int32_t, , H1_4, DO_ADD) + +DO_ZZZ_WTB(sve2_ssubw_h, int16_t, int8_t, H1_2, H1, DO_SUB) +DO_ZZZ_WTB(sve2_ssubw_s, int32_t, int16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_WTB(sve2_ssubw_d, int64_t, int32_t, , H1_4, DO_SUB) + +DO_ZZZ_WTB(sve2_uaddw_h, uint16_t, uint8_t, H1_2, H1, DO_ADD) +DO_ZZZ_WTB(sve2_uaddw_s, uint32_t, uint16_t, H1_4, H1_2, DO_ADD) +DO_ZZZ_WTB(sve2_uaddw_d, uint64_t, uint32_t, , H1_4, DO_ADD) + +DO_ZZZ_WTB(sve2_usubw_h, uint16_t, uint8_t, H1_2, H1, DO_SUB) +DO_ZZZ_WTB(sve2_usubw_s, uint32_t, uint16_t, H1_4, H1_2, DO_SUB) +DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, , H1_4, DO_SUB) + +#undef DO_ZZZ_WTB + /* Two-operand reduction expander, controlled by a predicate. * The difference between TYPERED and TYPERET has to do with * sign-extension. E.g. for SMAX, TYPERED must be signed, diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true) DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true) DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true) DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false) + +#define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ +{ \ + static gen_helper_gvec_3 * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_h, \ + gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ + }; \ + return do_sve2_zzw_ool(s, a, fns[a->esz], SEL2); \ +} + +DO_SVE2_ZZZ_WTB(SADDWB, saddw, false) +DO_SVE2_ZZZ_WTB(SADDWT, saddw, true) +DO_SVE2_ZZZ_WTB(SSUBWB, ssubw, false) +DO_SVE2_ZZZ_WTB(SSUBWT, ssubw, true) + +DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false) +DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true) +DO_SVE2_ZZZ_WTB(USUBWB, usubw, false) +DO_SVE2_ZZZ_WTB(USUBWT, usubw, true) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Exclude PMULL from this category for the moment. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 15 +++++++++++++++ target/arm/sve.decode | 9 +++++++++ target/arm/sve_helper.c | 31 +++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 9 +++++++++ 4 files changed, 64 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG, DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_smull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_umull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SSUBWB 01000101 .. 0 ..... 010 100 ..... ..... @rd_rn_rm SSUBWT 01000101 .. 0 ..... 010 101 ..... ..... @rd_rn_rm USUBWB 01000101 .. 0 ..... 010 110 ..... ..... @rd_rn_rm USUBWT 01000101 .. 0 ..... 010 111 ..... ..... @rd_rn_rm + +## SVE2 integer multiply long + +SQDMULLB_zzz 01000101 .. 0 ..... 011 000 ..... ..... @rd_rn_rm +SQDMULLT_zzz 01000101 .. 0 ..... 011 001 ..... ..... @rd_rn_rm +SMULLB_zzz 01000101 .. 0 ..... 011 100 ..... ..... @rd_rn_rm +SMULLT_zzz 01000101 .. 0 ..... 011 101 ..... ..... @rd_rn_rm +UMULLB_zzz 01000101 .. 0 ..... 011 110 ..... ..... @rd_rn_rm +UMULLT_zzz 01000101 .. 0 ..... 011 111 ..... ..... @rd_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZ_TB(sve2_uabdl_h, uint16_t, uint8_t, H1_2, H1, DO_ABD) DO_ZZZ_TB(sve2_uabdl_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD) DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t, , H1_4, DO_ABD) +DO_ZZZ_TB(sve2_smull_zzz_h, int16_t, int8_t, H1_2, H1, DO_MUL) +DO_ZZZ_TB(sve2_smull_zzz_s, int32_t, int16_t, H1_4, H1_2, DO_MUL) +DO_ZZZ_TB(sve2_smull_zzz_d, int64_t, int32_t, , H1_4, DO_MUL) + +DO_ZZZ_TB(sve2_umull_zzz_h, uint16_t, uint8_t, H1_2, H1, DO_MUL) +DO_ZZZ_TB(sve2_umull_zzz_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL) +DO_ZZZ_TB(sve2_umull_zzz_d, uint64_t, uint32_t, , H1_4, DO_MUL) + +/* Note that the multiply cannot overflow, but the doubling can. */ +static inline int16_t do_sqdmull_h(int16_t n, int16_t m) +{ + int16_t val = n * m; + return DO_SQADD_H(val, val); +} + +static inline int32_t do_sqdmull_s(int32_t n, int32_t m) +{ + int32_t val = n * m; + return DO_SQADD_S(val, val); +} + +static inline int64_t do_sqdmull_d(int64_t n, int64_t m) +{ + int64_t val = n * m; + return do_sqadd_d(val, val); +} + +DO_ZZZ_TB(sve2_sqdmull_zzz_h, int16_t, int8_t, H1_2, H1, do_sqdmull_h) +DO_ZZZ_TB(sve2_sqdmull_zzz_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s) +DO_ZZZ_TB(sve2_sqdmull_zzz_d, int64_t, int32_t, , H1_4, do_sqdmull_d) + #undef DO_ZZZ_TB #define DO_ZZZ_WTB(NAME, TYPEW, TYPEN, HW, HN, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true) DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true) DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false) +DO_SVE2_ZZZ_TB(SQDMULLB_zzz, sqdmull_zzz, false, false) +DO_SVE2_ZZZ_TB(SQDMULLT_zzz, sqdmull_zzz, true, true) + +DO_SVE2_ZZZ_TB(SMULLB_zzz, smull_zzz, false, false) +DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true) + +DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false) +DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true) + #define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ { \ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 ++++++++++ target/arm/helper-sve.h | 1 + target/arm/sve.decode | 2 ++ target/arm/translate-sve.c | 22 ++++++++++++++++++++++ target/arm/vec_helper.c | 24 ++++++++++++++++++++++++ 5 files changed, 59 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; } +static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0; +} + +static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_umull_zzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ USUBWT 01000101 .. 0 ..... 010 111 ..... ..... @rd_rn_rm SQDMULLB_zzz 01000101 .. 0 ..... 011 000 ..... ..... @rd_rn_rm SQDMULLT_zzz 01000101 .. 0 ..... 011 001 ..... ..... @rd_rn_rm +PMULLB 01000101 .. 0 ..... 011 010 ..... ..... @rd_rn_rm +PMULLT 01000101 .. 0 ..... 011 011 ..... ..... @rd_rn_rm SMULLB_zzz 01000101 .. 0 ..... 011 100 ..... ..... @rd_rn_rm SMULLT_zzz 01000101 .. 0 ..... 011 101 ..... ..... @rd_rn_rm UMULLB_zzz 01000101 .. 0 ..... 011 110 ..... ..... @rd_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true) DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false) DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true) +static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_gvec_pmull_q, gen_helper_sve2_pmull_h, + NULL, gen_helper_sve2_pmull_d, + }; + if (a->esz == 0 && !dc_isar_feature(aa64_sve2_pmull128, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], sel); +} + +static bool trans_PMULLB(DisasContext *s, arg_rrr_esz *a) +{ + return do_trans_pmull(s, a, false); +} + +static bool trans_PMULLT(DisasContext *s, arg_rrr_esz *a) +{ + return do_trans_pmull(s, a, true); +} + #define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ { \ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) d[i] = pmull_h(nn, mm); } } + +static uint64_t pmull_d(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; + + for (i = 0; i < 32; ++i) { + uint64_t mask = -((op1 >> i) & 1); + result ^= (op2 << i) & mask; + } + return result; +} + +void HELPER(sve2_pmull_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t sel = H4(simd_data(desc)); + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *n = vn, *m = vm; + uint64_t *d = vd; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = pmull_d(n[2 * i + sel], m[2 * i + sel]); + } +} #endif #define DO_CMP0(NAME, TYPE, OP) \ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 8 ++ target/arm/sve.decode | 8 ++ target/arm/sve_helper.c | 22 +++++ target/arm/translate-sve.c | 159 +++++++++++++++++++++++++++++++++++++ 4 files changed, 197 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sshll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sshll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sshll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_ushll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_ushll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_ushll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SMULLB_zzz 01000101 .. 0 ..... 011 100 ..... ..... @rd_rn_rm SMULLT_zzz 01000101 .. 0 ..... 011 101 ..... ..... @rd_rn_rm UMULLB_zzz 01000101 .. 0 ..... 011 110 ..... ..... @rd_rn_rm UMULLT_zzz 01000101 .. 0 ..... 011 111 ..... ..... @rd_rn_rm + +## SVE2 bitwise shift left long + +# Note bit23 == 0 is handled by esz > 0 in do_sve2_shll_tb. +SSHLLB 01000101 .. 0 ..... 1010 00 ..... ..... @rd_rn_tszimm_shl +SSHLLT 01000101 .. 0 ..... 1010 01 ..... ..... @rd_rn_tszimm_shl +USHLLB 01000101 .. 0 ..... 1010 10 ..... ..... @rd_rn_tszimm_shl +USHLLT 01000101 .. 0 ..... 1010 11 ..... ..... @rd_rn_tszimm_shl diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, , H1_4, DO_SUB) #undef DO_ZZZ_WTB +#define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + intptr_t sel = (simd_data(desc) & 1) * sizeof(TYPEN); \ + int shift = simd_data(desc) >> 1; \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel)); \ + *(TYPEW *)(vd + HW(i)) = nn << shift; \ + } \ +} + +DO_ZZI_SHLL(sve2_sshll_h, int16_t, int8_t, H1_2, H1) +DO_ZZI_SHLL(sve2_sshll_s, int32_t, int16_t, H1_4, H1_2) +DO_ZZI_SHLL(sve2_sshll_d, int64_t, int32_t, , H1_4) + +DO_ZZI_SHLL(sve2_ushll_h, uint16_t, uint8_t, H1_2, H1) +DO_ZZI_SHLL(sve2_ushll_s, uint32_t, uint16_t, H1_4, H1_2) +DO_ZZI_SHLL(sve2_ushll_d, uint64_t, uint32_t, , H1_4) + +#undef DO_ZZI_SHLL + /* Two-operand reduction expander, controlled by a predicate. * The difference between TYPERED and TYPERET has to do with * sign-extension. E.g. for SMAX, TYPERED must be signed, diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false) DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true) DO_SVE2_ZZZ_WTB(USUBWB, usubw, false) DO_SVE2_ZZZ_WTB(USUBWT, usubw, true) + +static void gen_sshll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm) +{ + int top = imm & 1; + int shl = imm >> 1; + int halfbits = 4 << vece; + + if (top) { + if (shl == halfbits) { + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(halfbits, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); + } else { + tcg_gen_sari_vec(vece, d, n, halfbits); + tcg_gen_shli_vec(vece, d, d, shl); + } + } else { + tcg_gen_shli_vec(vece, d, n, halfbits); + tcg_gen_sari_vec(vece, d, d, halfbits - shl); + } +} + +static void gen_ushll_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int imm) +{ + int halfbits = 4 << vece; + int top = imm & 1; + int shl = (imm >> 1); + int shift; + uint64_t mask; + + mask = MAKE_64BIT_MASK(0, halfbits); + mask <<= shl; + mask = dup_const(vece, mask); + + shift = shl - top * halfbits; + if (shift < 0) { + tcg_gen_shri_i64(d, n, -shift); + } else { + tcg_gen_shli_i64(d, n, shift); + } + tcg_gen_andi_i64(d, d, mask); +} + +static void gen_ushll16_i64(TCGv_i64 d, TCGv_i64 n, int64_t imm) +{ + gen_ushll_i64(MO_16, d, n, imm); +} + +static void gen_ushll32_i64(TCGv_i64 d, TCGv_i64 n, int64_t imm) +{ + gen_ushll_i64(MO_32, d, n, imm); +} + +static void gen_ushll64_i64(TCGv_i64 d, TCGv_i64 n, int64_t imm) +{ + gen_ushll_i64(MO_64, d, n, imm); +} + +static void gen_ushll_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t imm) +{ + int halfbits = 4 << vece; + int top = imm & 1; + int shl = imm >> 1; + + if (top) { + if (shl == halfbits) { + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(halfbits, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); + } else { + tcg_gen_shri_vec(vece, d, n, halfbits); + tcg_gen_shli_vec(vece, d, d, shl); + } + } else { + if (shl == 0) { + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); + } else { + tcg_gen_shli_vec(vece, d, n, halfbits); + tcg_gen_shri_vec(vece, d, d, halfbits - shl); + } + } +} + +static bool do_sve2_shll_tb(DisasContext *s, arg_rri_esz *a, + bool sel, bool uns) +{ + static const TCGOpcode sshll_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, 0 + }; + static const TCGOpcode ushll_list[] = { + INDEX_op_shli_vec, INDEX_op_shri_vec, 0 + }; + static const GVecGen2i ops[2][3] = { + { { .fniv = gen_sshll_vec, + .opt_opc = sshll_list, + .fno = gen_helper_sve2_sshll_h, + .vece = MO_16 }, + { .fniv = gen_sshll_vec, + .opt_opc = sshll_list, + .fno = gen_helper_sve2_sshll_s, + .vece = MO_32 }, + { .fniv = gen_sshll_vec, + .opt_opc = sshll_list, + .fno = gen_helper_sve2_sshll_d, + .vece = MO_64 } }, + { { .fni8 = gen_ushll16_i64, + .fniv = gen_ushll_vec, + .opt_opc = ushll_list, + .fno = gen_helper_sve2_ushll_h, + .vece = MO_16 }, + { .fni8 = gen_ushll32_i64, + .fniv = gen_ushll_vec, + .opt_opc = ushll_list, + .fno = gen_helper_sve2_ushll_s, + .vece = MO_32 }, + { .fni8 = gen_ushll64_i64, + .fniv = gen_ushll_vec, + .opt_opc = ushll_list, + .fno = gen_helper_sve2_ushll_d, + .vece = MO_64 } }, + }; + + if (a->esz < 0 || a->esz > 2 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2i(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, (a->imm << 1) | sel, + &ops[uns][a->esz]); + } + return true; +} + +static bool trans_SSHLLB(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, false, false); +} + +static bool trans_SSHLLT(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, true, false); +} + +static bool trans_USHLLB(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, false, true); +} + +static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_shll_tb(s, a, true, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 5 +++++ target/arm/sve.decode | 5 +++++ target/arm/sve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-sve.c | 19 +++++++++++++++++++ 4 files changed, 49 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_sshll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_ushll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_ushll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_ushll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_eoril_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_eoril_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_eoril_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_eoril_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SSHLLB 01000101 .. 0 ..... 1010 00 ..... ..... @rd_rn_tszimm_shl SSHLLT 01000101 .. 0 ..... 1010 01 ..... ..... @rd_rn_tszimm_shl USHLLB 01000101 .. 0 ..... 1010 10 ..... ..... @rd_rn_tszimm_shl USHLLT 01000101 .. 0 ..... 1010 11 ..... ..... @rd_rn_tszimm_shl + +## SVE2 bitwise exclusive-or interleaved + +EORBT 01000101 .. 0 ..... 10010 0 ..... ..... @rd_rn_rm +EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, , H1_4, DO_SUB) #undef DO_ZZZ_WTB +#define DO_ZZZ_NTB(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + intptr_t sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPE); \ + intptr_t sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPE); \ + for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + H(i + sel1)); \ + TYPE mm = *(TYPE *)(vm + H(i + sel2)); \ + *(TYPE *)(vd + H(i + sel1)) = OP(nn, mm); \ + } \ +} + +DO_ZZZ_NTB(sve2_eoril_b, uint8_t, H1, DO_EOR) +DO_ZZZ_NTB(sve2_eoril_h, uint16_t, H1_2, DO_EOR) +DO_ZZZ_NTB(sve2_eoril_s, uint32_t, H1_4, DO_EOR) +DO_ZZZ_NTB(sve2_eoril_d, uint64_t, , DO_EOR) + +#undef DO_ZZZ_NTB + #define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true) DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false) DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true) +static bool do_eor_tb(DisasContext *s, arg_rrr_esz *a, bool sel1) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_eoril_b, gen_helper_sve2_eoril_h, + gen_helper_sve2_eoril_s, gen_helper_sve2_eoril_d, + }; + return do_sve2_zzw_ool(s, a, fns[a->esz], (!sel1 << 1) | sel1); +} + +static bool trans_EORBT(DisasContext *s, arg_rrr_esz *a) +{ + return do_eor_tb(s, a, false); +} + +static bool trans_EORTB(DisasContext *s, arg_rrr_esz *a) +{ + return do_eor_tb(s, a, true); +} + static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) { static gen_helper_gvec_3 * const fns[4] = { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++ target/arm/helper-sve.h | 15 ++++++++ target/arm/sve.decode | 6 ++++ target/arm/sve_helper.c | 73 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 36 +++++++++++++++++++ 5 files changed, 135 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; } +static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_eoril_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_eoril_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_eoril_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_eoril_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_bext_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bext_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bext_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bext_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_bdep_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bdep_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bdep_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bdep_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_bgrp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bgrp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bgrp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_bgrp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ USHLLT 01000101 .. 0 ..... 1010 11 ..... ..... @rd_rn_tszimm_shl EORBT 01000101 .. 0 ..... 10010 0 ..... ..... @rd_rn_rm EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm + +## SVE2 bitwise permute + +BEXT 01000101 .. 0 ..... 1011 00 ..... ..... @rd_rn_rm +BDEP 01000101 .. 0 ..... 1011 01 ..... ..... @rd_rn_rm +BGRP 01000101 .. 0 ..... 1011 10 ..... ..... @rd_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZ_NTB(sve2_eoril_d, uint64_t, , DO_EOR) #undef DO_ZZZ_NTB +#define DO_BITPERM(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + TYPE mm = *(TYPE *)(vm + i); \ + *(TYPE *)(vd + i) = OP(nn, mm, sizeof(TYPE) * 8); \ + } \ +} + +static uint64_t bitextract(uint64_t data, uint64_t mask, int n) +{ + uint64_t res = 0; + int db, rb = 0; + + for (db = 0; db < n; ++db) { + if ((mask >> db) & 1) { + res |= ((data >> db) & 1) << rb; + ++rb; + } + } + return res; +} + +DO_BITPERM(sve2_bext_b, uint8_t, bitextract) +DO_BITPERM(sve2_bext_h, uint16_t, bitextract) +DO_BITPERM(sve2_bext_s, uint32_t, bitextract) +DO_BITPERM(sve2_bext_d, uint64_t, bitextract) + +static uint64_t bitdeposit(uint64_t data, uint64_t mask, int n) +{ + uint64_t res = 0; + int rb, db = 0; + + for (rb = 0; rb < n; ++rb) { + if ((mask >> rb) & 1) { + res |= ((data >> db) & 1) << rb; + ++db; + } + } + return res; +} + +DO_BITPERM(sve2_bdep_b, uint8_t, bitdeposit) +DO_BITPERM(sve2_bdep_h, uint16_t, bitdeposit) +DO_BITPERM(sve2_bdep_s, uint32_t, bitdeposit) +DO_BITPERM(sve2_bdep_d, uint64_t, bitdeposit) + +static uint64_t bitgroup(uint64_t data, uint64_t mask, int n) +{ + uint64_t resm = 0, resu = 0; + int db, rbm = 0, rbu = 0; + + for (db = 0; db < n; ++db) { + uint64_t val = (data >> db) & 1; + if ((mask >> db) & 1) { + resm |= val << rbm++; + } else { + resu |= val << rbu++; + } + } + + return resm | (resu << rbm); +} + +DO_BITPERM(sve2_bgrp_b, uint8_t, bitgroup) +DO_BITPERM(sve2_bgrp_h, uint16_t, bitgroup) +DO_BITPERM(sve2_bgrp_s, uint32_t, bitgroup) +DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup) + +#undef DO_BITPERM + #define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a) { return do_sve2_shll_tb(s, a, true, true); } + +static bool trans_BEXT(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, + gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, + }; + if (!dc_isar_feature(aa64_sve2_bitperm, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], 0); +} + +static bool trans_BDEP(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, + gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, + }; + if (!dc_isar_feature(aa64_sve2_bitperm, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], 0); +} + +static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, + gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, + }; + if (!dc_isar_feature(aa64_sve2_bitperm, s)) { + return false; + } + return do_sve2_zzw_ool(s, a, fns[a->esz], 0); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 10 +++++++++ target/arm/sve.decode | 9 ++++++++ target/arm/sve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 31 ++++++++++++++++++++++++++++ 4 files changed, 92 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_bgrp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_bgrp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_bgrp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_bgrp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_cadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_cadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_cadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_cadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqcadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqcadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqcadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqcadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm BEXT 01000101 .. 0 ..... 1011 00 ..... ..... @rd_rn_rm BDEP 01000101 .. 0 ..... 1011 01 ..... ..... @rd_rn_rm BGRP 01000101 .. 0 ..... 1011 10 ..... ..... @rd_rn_rm + +#### SVE2 Accumulate + +## SVE2 complex integer add + +CADD_rot90 01000101 .. 00000 0 11011 0 ..... ..... @rdn_rm +CADD_rot270 01000101 .. 00000 0 11011 1 ..... ..... @rdn_rm +SQCADD_rot90 01000101 .. 00000 1 11011 0 ..... ..... @rdn_rm +SQCADD_rot270 01000101 .. 00000 1 11011 1 ..... ..... @rdn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup) #undef DO_BITPERM +#define DO_CADD(NAME, TYPE, H, ADD_OP, SUB_OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sub_r = simd_data(desc); \ + if (sub_r) { \ + for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \ + TYPE acc_r = *(TYPE *)(vn + H(i)); \ + TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE el2_r = *(TYPE *)(vm + H(i)); \ + TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + acc_r = ADD_OP(acc_r, el2_i); \ + acc_i = SUB_OP(acc_i, el2_r); \ + *(TYPE *)(vd + H(i)) = acc_r; \ + *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i; \ + } \ + } else { \ + for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) { \ + TYPE acc_r = *(TYPE *)(vn + H(i)); \ + TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE el2_r = *(TYPE *)(vm + H(i)); \ + TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + acc_r = SUB_OP(acc_r, el2_i); \ + acc_i = ADD_OP(acc_i, el2_r); \ + *(TYPE *)(vd + H(i)) = acc_r; \ + *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i; \ + } \ + } \ +} + +DO_CADD(sve2_cadd_b, int8_t, H1, DO_ADD, DO_SUB) +DO_CADD(sve2_cadd_h, int16_t, H1_2, DO_ADD, DO_SUB) +DO_CADD(sve2_cadd_s, int32_t, H1_4, DO_ADD, DO_SUB) +DO_CADD(sve2_cadd_d, int64_t, , DO_ADD, DO_SUB) + +DO_CADD(sve2_sqcadd_b, int8_t, H1, DO_SQADD_B, DO_SQSUB_B) +DO_CADD(sve2_sqcadd_h, int16_t, H1_2, DO_SQADD_H, DO_SQSUB_H) +DO_CADD(sve2_sqcadd_s, int32_t, H1_4, DO_SQADD_S, DO_SQSUB_S) +DO_CADD(sve2_sqcadd_d, int64_t, , do_sqadd_d, do_sqsub_d) + +#undef DO_CADD + #define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a) } return do_sve2_zzw_ool(s, a, fns[a->esz], 0); } + +static bool do_cadd(DisasContext *s, arg_rrr_esz *a, bool sq, bool rot) +{ + static gen_helper_gvec_3 * const fns[2][4] = { + { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, + gen_helper_sve2_cadd_s, gen_helper_sve2_cadd_d }, + { gen_helper_sve2_sqcadd_b, gen_helper_sve2_sqcadd_h, + gen_helper_sve2_sqcadd_s, gen_helper_sve2_sqcadd_d }, + }; + return do_sve2_zzw_ool(s, a, fns[sq][a->esz], rot); +} + +static bool trans_CADD_rot90(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, false, false); +} + +static bool trans_CADD_rot270(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, false, true); +} + +static bool trans_SQCADD_rot90(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, true, false); +} + +static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a) +{ + return do_cadd(s, a, true, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 ++++++++++ target/arm/sve.decode | 12 +++++++++ target/arm/sve_helper.c | 23 ++++++++++++++++ target/arm/translate-sve.c | 55 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 104 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_sqcadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqcadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqcadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqcadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sabal_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sabal_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sabal_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uabal_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uabal_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uabal_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rpr_s rd pg rn s &rprr_s rd pg rn rm s &rprr_esz rd pg rn rm esz +&rrrr_esz rd ra rn rm esz &rprrr_esz rd pg rn rm ra esz &rpri_esz rd pg rn imm esz &ptrue rd esz pat s @@ -XXX,XX +XXX,XX @@ @rdn_i8s ........ esz:2 ...... ... imm:s8 rd:5 \ &rri_esz rn=%reg_movprfx +# Four operand, vector element size +@rda_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 \ + &rrrr_esz ra=%reg_movprfx + # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -XXX,XX +XXX,XX @@ CADD_rot90 01000101 .. 00000 0 11011 0 ..... ..... @rdn_rm CADD_rot270 01000101 .. 00000 0 11011 1 ..... ..... @rdn_rm SQCADD_rot90 01000101 .. 00000 1 11011 0 ..... ..... @rdn_rm SQCADD_rot270 01000101 .. 00000 1 11011 1 ..... ..... @rdn_rm + +## SVE2 integer absolute difference and accumulate long + +SABALB 01000101 .. 0 ..... 1100 00 ..... ..... @rda_rn_rm +SABALT 01000101 .. 0 ..... 1100 01 ..... ..... @rda_rn_rm +UABALB 01000101 .. 0 ..... 1100 10 ..... ..... @rda_rn_rm +UABALT 01000101 .. 0 ..... 1100 11 ..... ..... @rda_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZ_NTB(sve2_eoril_d, uint64_t, , DO_EOR) #undef DO_ZZZ_NTB +#define DO_ZZZW_ACC(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + intptr_t sel1 = simd_data(desc) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel1)); \ + TYPEW aa = *(TYPEW *)(va + HW(i)); \ + *(TYPEW *)(vd + HW(i)) = OP(nn, mm) + aa; \ + } \ +} + +DO_ZZZW_ACC(sve2_sabal_h, int16_t, int8_t, H1_2, H1, DO_ABD) +DO_ZZZW_ACC(sve2_sabal_s, int32_t, int16_t, H1_4, H1_2, DO_ABD) +DO_ZZZW_ACC(sve2_sabal_d, int64_t, int32_t, , H1_4, DO_ABD) + +DO_ZZZW_ACC(sve2_uabal_h, uint16_t, uint8_t, H1_2, H1, DO_ABD) +DO_ZZZW_ACC(sve2_uabal_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD) +DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t, , H1_4, DO_ABD) + +#undef DO_ZZZW_ACC + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_ool_zzz(DisasContext *s, gen_helper_gvec_3 *fn, vsz, vsz, data, fn); } +/* Invoke an out-of-line helper on 4 Zregs. */ +static void gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn, + int rd, int rn, int rm, int ra, int data) +{ + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + vsz, vsz, data, fn); +} + /* Invoke an out-of-line helper on 2 Zregs and a predicate. */ static void gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn, int rd, int rn, int pg, int data) @@ -XXX,XX +XXX,XX @@ static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a) { return do_cadd(s, a, true, true); } + +static bool do_sve2_zzzz_ool(DisasContext *s, arg_rrrr_esz *a, + gen_helper_gvec_4 *fn, int data) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data); + } + return true; +} + +static bool do_abal(DisasContext *s, arg_rrrr_esz *a, bool uns, bool sel) +{ + static gen_helper_gvec_4 * const fns[2][4] = { + { NULL, gen_helper_sve2_sabal_h, + gen_helper_sve2_sabal_s, gen_helper_sve2_sabal_d }, + { NULL, gen_helper_sve2_uabal_h, + gen_helper_sve2_uabal_s, gen_helper_sve2_uabal_d }, + }; + return do_sve2_zzzz_ool(s, a, fns[uns][a->esz], sel); +} + +static bool trans_SABALB(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, false, false); +} + +static bool trans_SABALT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, false, true); +} + +static bool trans_UABALB(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, true, false); +} + +static bool trans_UABALT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_abal(s, a, true, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 3 +++ target/arm/sve.decode | 6 ++++++ target/arm/sve_helper.c | 34 ++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 23 +++++++++++++++++++++++ 4 files changed, 66 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uabal_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_uabal_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_adcl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_adcl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SABALB 01000101 .. 0 ..... 1100 00 ..... ..... @rda_rn_rm SABALT 01000101 .. 0 ..... 1100 01 ..... ..... @rda_rn_rm UABALB 01000101 .. 0 ..... 1100 10 ..... ..... @rda_rn_rm UABALT 01000101 .. 0 ..... 1100 11 ..... ..... @rda_rn_rm + +## SVE2 integer add/subtract long with carry + +# ADC and SBC decoded via size in helper dispatch. +ADCLB 01000101 .. 0 ..... 11010 0 ..... ..... @rda_rn_rm +ADCLT 01000101 .. 0 ..... 11010 1 ..... ..... @rda_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t, , H1_4, DO_ABD) #undef DO_ZZZW_ACC +void HELPER(sve2_adcl_s)(void *vd, void *vn, void *vm, void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int sel = H4(extract32(desc, SIMD_DATA_SHIFT, 1)); + uint32_t inv = -extract32(desc, SIMD_DATA_SHIFT + 1, 1); + uint32_t *a = va, *n = vn; + uint64_t *d = vd, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + uint32_t e1 = a[2 * i + H4(0)]; + uint32_t e2 = n[2 * i + sel] ^ inv; + uint64_t c = extract64(m[i], 32, 1); + /* Compute and store the entire 33-bit result at once. */ + d[i] = c + e1 + e2; + } +} + +void HELPER(sve2_adcl_d)(void *vd, void *vn, void *vm, void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int sel = extract32(desc, SIMD_DATA_SHIFT, 1); + uint64_t inv = -(uint64_t)extract32(desc, SIMD_DATA_SHIFT + 1, 1); + uint64_t *d = vd, *a = va, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; i += 2) { + Int128 e1 = int128_make64(a[i]); + Int128 e2 = int128_make64(n[i + sel] ^ inv); + Int128 c = int128_make64(m[i + 1] & 1); + Int128 r = int128_add(int128_add(e1, e2), c); + d[i + 0] = int128_getlo(r); + d[i + 1] = int128_gethi(r); + } +} + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UABALT(DisasContext *s, arg_rrrr_esz *a) { return do_abal(s, a, true, true); } + +static bool do_adcl(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[2] = { + gen_helper_sve2_adcl_s, + gen_helper_sve2_adcl_d, + }; + /* + * Note that in this case the ESZ field encodes both size and sign. + * Split out 'subtract' into bit 1 of the data field for the helper. + */ + return do_sve2_zzzz_ool(s, a, fns[a->esz & 1], (a->esz & 2) | sel); +} + +static bool trans_ADCLB(DisasContext *s, arg_rrrr_esz *a) +{ + return do_adcl(s, a, false); +} + +static bool trans_ADCLT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_adcl(s, a, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 8 ++++++++ target/arm/translate-sve.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UABALT 01000101 .. 0 ..... 1100 11 ..... ..... @rda_rn_rm # ADC and SBC decoded via size in helper dispatch. ADCLB 01000101 .. 0 ..... 11010 0 ..... ..... @rda_rn_rm ADCLT 01000101 .. 0 ..... 11010 1 ..... ..... @rda_rn_rm + +## SVE2 bitwise shift right and accumulate + +# TODO: Use @rda and %reg_movprfx here. +SSRA 01000101 .. 0 ..... 1110 00 ..... ..... @rd_rn_tszimm_shr +USRA 01000101 .. 0 ..... 1110 01 ..... ..... @rd_rn_tszimm_shr +SRSRA 01000101 .. 0 ..... 1110 10 ..... ..... @rd_rn_tszimm_shr +URSRA 01000101 .. 0 ..... 1110 11 ..... ..... @rd_rn_tszimm_shr diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ADCLT(DisasContext *s, arg_rrrr_esz *a) { return do_adcl(s, a, true); } + +static bool do_sve2_fn2i(DisasContext *s, arg_rri_esz *a, GVecGen2iFn *fn) +{ + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + unsigned rd_ofs = vec_full_reg_offset(s, a->rd); + unsigned rn_ofs = vec_full_reg_offset(s, a->rn); + fn(a->esz, rd_ofs, rn_ofs, a->imm, vsz, vsz); + } + return true; +} + +static bool trans_SSRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_ssra); +} + +static bool trans_USRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_usra); +} + +static bool trans_SRSRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_srsra); +} + +static bool trans_URSRA(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_ursra); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 5 +++++ target/arm/translate-sve.c | 10 ++++++++++ 2 files changed, 15 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SSRA 01000101 .. 0 ..... 1110 00 ..... ..... @rd_rn_tszimm_shr USRA 01000101 .. 0 ..... 1110 01 ..... ..... @rd_rn_tszimm_shr SRSRA 01000101 .. 0 ..... 1110 10 ..... ..... @rd_rn_tszimm_shr URSRA 01000101 .. 0 ..... 1110 11 ..... ..... @rd_rn_tszimm_shr + +## SVE2 bitwise shift and insert + +SRI 01000101 .. 0 ..... 11110 0 ..... ..... @rd_rn_tszimm_shr +SLI 01000101 .. 0 ..... 11110 1 ..... ..... @rd_rn_tszimm_shl diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_URSRA(DisasContext *s, arg_rri_esz *a) { return do_sve2_fn2i(s, a, gen_gvec_ursra); } + +static bool trans_SRI(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_sri); +} + +static bool trans_SLI(DisasContext *s, arg_rri_esz *a) +{ + return do_sve2_fn2i(s, a, gen_gvec_sli); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 6 ++++++ target/arm/translate-sve.c | 21 +++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ URSRA 01000101 .. 0 ..... 1110 11 ..... ..... @rd_rn_tszimm_shr SRI 01000101 .. 0 ..... 11110 0 ..... ..... @rd_rn_tszimm_shr SLI 01000101 .. 0 ..... 11110 1 ..... ..... @rd_rn_tszimm_shl + +## SVE2 integer absolute difference and accumulate + +# TODO: Use @rda and %reg_movprfx here. +SABA 01000101 .. 0 ..... 11111 0 ..... ..... @rd_rn_rm +UABA 01000101 .. 0 ..... 11111 1 ..... ..... @rd_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SLI(DisasContext *s, arg_rri_esz *a) { return do_sve2_fn2i(s, a, gen_gvec_sli); } + +static bool do_sve2_fn_zzz(DisasContext *s, arg_rrr_esz *a, GVecGen3Fn *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzz(s, fn, a->esz, a->rd, a->rn, a->rm); + } + return true; +} + +static bool trans_SABA(DisasContext *s, arg_rrr_esz *a) +{ + return do_sve2_fn_zzz(s, a, gen_gvec_saba); +} + +static bool trans_UABA(DisasContext *s, arg_rrr_esz *a) +{ + return do_sve2_fn_zzz(s, a, gen_gvec_uaba); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 24 ++++ target/arm/sve.decode | 12 ++ target/arm/sve_helper.c | 56 +++++++++ target/arm/translate-sve.c | 238 +++++++++++++++++++++++++++++++++++++ 4 files changed, 330 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_uabal_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_adcl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_adcl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqxtnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqxtnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SLI 01000101 .. 0 ..... 11110 1 ..... ..... @rd_rn_tszimm_shl # TODO: Use @rda and %reg_movprfx here. SABA 01000101 .. 0 ..... 11111 0 ..... ..... @rd_rn_rm UABA 01000101 .. 0 ..... 11111 1 ..... ..... @rd_rn_rm + +#### SVE2 Narrowing + +## SVE2 saturating extract narrow + +# Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0. +SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl +SQXTNT 01000101 .. 1 ..... 010 001 ..... ..... @rd_rn_tszimm_shl +UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl +UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl +SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl +SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t, , H1_4, DO_ABD) #undef DO_ZZZW_ACC +#define DO_XTNB(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + nn = OP(nn) & MAKE_64BIT_MASK(0, sizeof(TYPE) * 4); \ + *(TYPE *)(vd + i) = nn; \ + } \ +} + +#define DO_XTNT(NAME, TYPE, TYPEN, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc), odd = H(sizeof(TYPEN)); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + *(TYPEN *)(vd + i + odd) = OP(nn); \ + } \ +} + +#define DO_SQXTN_H(n) do_sat_bhs(n, INT8_MIN, INT8_MAX) +#define DO_SQXTN_S(n) do_sat_bhs(n, INT16_MIN, INT16_MAX) +#define DO_SQXTN_D(n) do_sat_bhs(n, INT32_MIN, INT32_MAX) + +DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H) +DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S) +DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D) + +DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H) +DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S) +DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D) + +#define DO_UQXTN_H(n) do_sat_bhs(n, 0, UINT8_MAX) +#define DO_UQXTN_S(n) do_sat_bhs(n, 0, UINT16_MAX) +#define DO_UQXTN_D(n) do_sat_bhs(n, 0, UINT32_MAX) + +DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H) +DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S) +DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D) + +DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H) +DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S) +DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D) + +DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H) +DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S) +DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D) + +DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H) +DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S) +DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D) + +#undef DO_XTNB +#undef DO_XTNT + void HELPER(sve2_adcl_s)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UABA(DisasContext *s, arg_rrr_esz *a) { return do_sve2_fn_zzz(s, a, gen_gvec_uaba); } + +static bool do_sve2_narrow_extract(DisasContext *s, arg_rri_esz *a, + const GVecGen2 ops[3]) +{ + if (a->esz < 0 || a->esz > MO_32 || a->imm != 0 || + !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, &ops[a->esz]); + } + return true; +} + +static const TCGOpcode sqxtn_list[] = { + INDEX_op_shli_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0 +}; + +static void gen_sqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t mask = (1ull << halfbits) - 1; + int64_t min = -1ull << (halfbits - 1); + int64_t max = -min - 1; + + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, d, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, d, d, t); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_and_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtnb_vec, + .opt_opc = sqxtn_list, + .fno = gen_helper_sve2_sqxtnb_h, + .vece = MO_16 }, + { .fniv = gen_sqxtnb_vec, + .opt_opc = sqxtn_list, + .fno = gen_helper_sve2_sqxtnb_s, + .vece = MO_32 }, + { .fniv = gen_sqxtnb_vec, + .opt_opc = sqxtn_list, + .fno = gen_helper_sve2_sqxtnb_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static void gen_sqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t mask = (1ull << halfbits) - 1; + int64_t min = -1ull << (halfbits - 1); + int64_t max = -min - 1; + + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtnt_vec, + .opt_opc = sqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtnt_h, + .vece = MO_16 }, + { .fniv = gen_sqxtnt_vec, + .opt_opc = sqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtnt_s, + .vece = MO_32 }, + { .fniv = gen_sqxtnt_vec, + .opt_opc = sqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtnt_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static const TCGOpcode uqxtn_list[] = { + INDEX_op_shli_vec, INDEX_op_umin_vec, 0 +}; + +static void gen_uqxtnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_UQXTNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_uqxtnb_vec, + .opt_opc = uqxtn_list, + .fno = gen_helper_sve2_uqxtnb_h, + .vece = MO_16 }, + { .fniv = gen_uqxtnb_vec, + .opt_opc = uqxtn_list, + .fno = gen_helper_sve2_uqxtnb_s, + .vece = MO_32 }, + { .fniv = gen_uqxtnb_vec, + .opt_opc = uqxtn_list, + .fno = gen_helper_sve2_uqxtnb_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static void gen_uqxtnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_UQXTNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_uqxtnt_vec, + .opt_opc = uqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_uqxtnt_h, + .vece = MO_16 }, + { .fniv = gen_uqxtnt_vec, + .opt_opc = uqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_uqxtnt_s, + .vece = MO_32 }, + { .fniv = gen_uqxtnt_vec, + .opt_opc = uqxtn_list, + .load_dest = true, + .fno = gen_helper_sve2_uqxtnt_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static const TCGOpcode sqxtun_list[] = { + INDEX_op_shli_vec, INDEX_op_umin_vec, INDEX_op_smax_vec, 0 +}; + +static void gen_sqxtunb_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, d, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTUNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtunb_vec, + .opt_opc = sqxtun_list, + .fno = gen_helper_sve2_sqxtunb_h, + .vece = MO_16 }, + { .fniv = gen_sqxtunb_vec, + .opt_opc = sqxtun_list, + .fno = gen_helper_sve2_sqxtunb_s, + .vece = MO_32 }, + { .fniv = gen_sqxtunb_vec, + .opt_opc = sqxtun_list, + .fno = gen_helper_sve2_sqxtunb_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} + +static void gen_sqxtunt_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = (1ull << halfbits) - 1; + + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2 ops[3] = { + { .fniv = gen_sqxtunt_vec, + .opt_opc = sqxtun_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtunt_h, + .vece = MO_16 }, + { .fniv = gen_sqxtunt_vec, + .opt_opc = sqxtun_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtunt_s, + .vece = MO_32 }, + { .fniv = gen_sqxtunt_vec, + .opt_opc = sqxtun_list, + .load_dest = true, + .fno = gen_helper_sve2_sqxtunt_d, + .vece = MO_64 }, + }; + return do_sve2_narrow_extract(s, a, ops); +} -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 35 +++++++++++++++++++++++++++++ target/arm/sve.decode | 8 +++++++ target/arm/sve_helper.c | 46 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 25 +++++++++++++++++++++ 4 files changed, 114 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_uqxtnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl + +## SVE2 floating-point pairwise operations + +FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm +FMAXNMP 01100100 .. 010 10 0 100 ... ..... ..... @rdn_pg_rm +FMINNMP 01100100 .. 010 10 1 100 ... ..... ..... @rdn_pg_rm +FMAXP 01100100 .. 010 11 0 100 ... ..... ..... @rdn_pg_rm +FMINP 01100100 .. 010 11 1 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_PAIR_D(sve2_sminp_zpzz_d, int64_t, DO_MIN) #undef DO_ZPZZ_PAIR #undef DO_ZPZZ_PAIR_D +#define DO_ZPZZ_PAIR_FP(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPE n0 = *(TYPE *)(vn + H(i)); \ + TYPE m0 = *(TYPE *)(vm + H(i)); \ + TYPE n1 = *(TYPE *)(vn + H(i + sizeof(TYPE))); \ + TYPE m1 = *(TYPE *)(vm + H(i + sizeof(TYPE))); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(n0, n1, status); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = OP(m0, m1, status); \ + } \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_ZPZZ_PAIR_FP(sve2_faddp_zpzz_h, float16, H1_2, float16_add) +DO_ZPZZ_PAIR_FP(sve2_faddp_zpzz_s, float32, H1_4, float32_add) +DO_ZPZZ_PAIR_FP(sve2_faddp_zpzz_d, float64, , float64_add) + +DO_ZPZZ_PAIR_FP(sve2_fmaxnmp_zpzz_h, float16, H1_2, float16_maxnum) +DO_ZPZZ_PAIR_FP(sve2_fmaxnmp_zpzz_s, float32, H1_4, float32_maxnum) +DO_ZPZZ_PAIR_FP(sve2_fmaxnmp_zpzz_d, float64, , float64_maxnum) + +DO_ZPZZ_PAIR_FP(sve2_fminnmp_zpzz_h, float16, H1_2, float16_minnum) +DO_ZPZZ_PAIR_FP(sve2_fminnmp_zpzz_s, float32, H1_4, float32_minnum) +DO_ZPZZ_PAIR_FP(sve2_fminnmp_zpzz_d, float64, , float64_minnum) + +DO_ZPZZ_PAIR_FP(sve2_fmaxp_zpzz_h, float16, H1_2, float16_max) +DO_ZPZZ_PAIR_FP(sve2_fmaxp_zpzz_s, float32, H1_4, float32_max) +DO_ZPZZ_PAIR_FP(sve2_fmaxp_zpzz_d, float64, , float64_max) + +DO_ZPZZ_PAIR_FP(sve2_fminp_zpzz_h, float16, H1_2, float16_min) +DO_ZPZZ_PAIR_FP(sve2_fminp_zpzz_s, float32, H1_4, float32_min) +DO_ZPZZ_PAIR_FP(sve2_fminp_zpzz_d, float64, , float64_min) + +#undef DO_ZPZZ_PAIR_FP + /* Three-operand expander, controlled by a predicate, in which the * third operand is "wide". That is, for D = N op M, the same 64-bit * value of M is used with all of the narrower values of N. diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a) }; return do_sve2_narrow_extract(s, a, ops); } + +static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpzz_fp(s, a, fn); +} + +#define DO_SVE2_ZPZZ_FP(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_zpzz_h, \ + gen_helper_sve2_##name##_zpzz_s, gen_helper_sve2_##name##_zpzz_d \ + }; \ + return do_sve2_zpzz_fp(s, a, fns[a->esz]); \ +} + +DO_SVE2_ZPZZ_FP(FADDP, faddp) +DO_SVE2_ZPZZ_FP(FMAXNMP, fmaxnmp) +DO_SVE2_ZPZZ_FP(FMINNMP, fminnmp) +DO_SVE2_ZPZZ_FP(FMAXP, fmaxp) +DO_SVE2_ZPZZ_FP(FMINP, fminp) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 16 ++++ target/arm/sve.decode | 8 ++ target/arm/sve_helper.c | 54 ++++++++++++- target/arm/translate-sve.c | 160 +++++++++++++++++++++++++++++++++++++ 4 files changed, 236 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_shrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_shrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_rshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_rshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_rshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl +## SVE2 bitwise shift right narrow + +# Bit 23 == 0 is handled by esz > 0 in the translator. +SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr +SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr +RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr +RSHRNT 01000101 .. 1 ..... 00 0111 ..... ..... @rd_rn_tszimm_shr + ## SVE2 floating-point pairwise operations FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ when N is negative, add 2**M-1. */ #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M) +static inline uint64_t do_urshr(uint64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else if (sh == 64) { + return x >> 63; + } else { + return 0; + } +} + DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR) DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR) DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR) @@ -XXX,XX +XXX,XX @@ DO_ZPZI(sve_asrd_h, int16_t, H1_2, DO_ASRD) DO_ZPZI(sve_asrd_s, int32_t, H1_4, DO_ASRD) DO_ZPZI_D(sve_asrd_d, int64_t, DO_ASRD) -#undef DO_SHR -#undef DO_SHL #undef DO_ASRD #undef DO_ZPZI #undef DO_ZPZI_D +#define DO_SHRNB(NAME, TYPEW, TYPEN, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + i); \ + *(TYPEW *)(vd + i) = (TYPEN)OP(nn, shift); \ + } \ +} + +#define DO_SHRNT(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, shift); \ + } \ +} + +DO_SHRNB(sve2_shrnb_h, uint16_t, uint8_t, DO_SHR) +DO_SHRNB(sve2_shrnb_s, uint32_t, uint16_t, DO_SHR) +DO_SHRNB(sve2_shrnb_d, uint64_t, uint32_t, DO_SHR) + +DO_SHRNT(sve2_shrnt_h, uint16_t, uint8_t, H1_2, H1, DO_SHR) +DO_SHRNT(sve2_shrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_SHR) +DO_SHRNT(sve2_shrnt_d, uint64_t, uint32_t, , H1_4, DO_SHR) + +DO_SHRNB(sve2_rshrnb_h, uint16_t, uint8_t, do_urshr) +DO_SHRNB(sve2_rshrnb_s, uint32_t, uint16_t, do_urshr) +DO_SHRNB(sve2_rshrnb_d, uint64_t, uint32_t, do_urshr) + +DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr) +DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr) +DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, , H1_4, do_urshr) + +#undef DO_SHRNB +#undef DO_SHRNT + /* Fully general four-operand expander, controlled by a predicate. */ #define DO_ZPZZZ(NAME, TYPE, H, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a) return do_sve2_narrow_extract(s, a, ops); } +static bool do_sve2_shr_narrow(DisasContext *s, arg_rri_esz *a, + const GVecGen2i ops[3]) +{ + if (a->esz < 0 || a->esz > MO_32 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + assert(a->imm > 0 && a->imm <= (8 << a->esz)); + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_2i(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vsz, vsz, a->imm, &ops[a->esz]); + } + return true; +} + +static void gen_shrnb_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr) +{ + int halfbits = 4 << vece; + uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits)); + + tcg_gen_shri_i64(d, n, shr); + tcg_gen_andi_i64(d, d, mask); +} + +static void gen_shrnb16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnb_i64(MO_16, d, n, shr); +} + +static void gen_shrnb32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnb_i64(MO_32, d, n, shr); +} + +static void gen_shrnb64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnb_i64(MO_64, d, n, shr); +} + +static void gen_shrnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + uint64_t mask = MAKE_64BIT_MASK(0, halfbits); + + tcg_gen_shri_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_SHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { INDEX_op_shri_vec, 0 }; + static const GVecGen2i ops[3] = { + { .fni8 = gen_shrnb16_i64, + .fniv = gen_shrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_shrnb_h, + .vece = MO_16 }, + { .fni8 = gen_shrnb32_i64, + .fniv = gen_shrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_shrnb_s, + .vece = MO_32 }, + { .fni8 = gen_shrnb64_i64, + .fniv = gen_shrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_shrnb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_shrnt_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr) +{ + int halfbits = 4 << vece; + uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits)); + + tcg_gen_shli_i64(n, n, halfbits - shr); + tcg_gen_andi_i64(n, n, ~mask); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_or_i64(d, d, n); +} + +static void gen_shrnt16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnt_i64(MO_16, d, n, shr); +} + +static void gen_shrnt32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + gen_shrnt_i64(MO_32, d, n, shr); +} + +static void gen_shrnt64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr) +{ + tcg_gen_shri_i64(n, n, shr); + tcg_gen_deposit_i64(d, d, n, 32, 32); +} + +static void gen_shrnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + uint64_t mask = MAKE_64BIT_MASK(0, halfbits); + + tcg_gen_shli_vec(vece, n, n, halfbits - shr); + tcg_gen_dupi_vec(vece, t, mask); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { INDEX_op_shli_vec, 0 }; + static const GVecGen2i ops[3] = { + { .fni8 = gen_shrnt16_i64, + .fniv = gen_shrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_shrnt_h, + .vece = MO_16 }, + { .fni8 = gen_shrnt32_i64, + .fniv = gen_shrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_shrnt_s, + .vece = MO_32 }, + { .fni8 = gen_shrnt64_i64, + .fniv = gen_shrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_shrnt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_RSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_rshrnb_h }, + { .fno = gen_helper_sve2_rshrnb_s }, + { .fno = gen_helper_sve2_rshrnb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_RSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_rshrnt_h }, + { .fno = gen_helper_sve2_rshrnt_s }, + { .fno = gen_helper_sve2_rshrnt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 16 +++++++ target/arm/sve.decode | 4 ++ target/arm/sve_helper.c | 35 ++++++++++++++ target/arm/translate-sve.c | 98 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 153 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_rshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_rshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_rshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrunb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl ## SVE2 bitwise shift right narrow # Bit 23 == 0 is handled by esz > 0 in the translator. +SQSHRUNB 01000101 .. 1 ..... 00 0000 ..... ..... @rd_rn_tszimm_shr +SQSHRUNT 01000101 .. 1 ..... 00 0001 ..... ..... @rd_rn_tszimm_shr +SQRSHRUNB 01000101 .. 1 ..... 00 0010 ..... ..... @rd_rn_tszimm_shr +SQRSHRUNT 01000101 .. 1 ..... 00 0011 ..... ..... @rd_rn_tszimm_shr SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_urshr(uint64_t x, unsigned sh) } } +static inline int64_t do_srshr(int64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else { + /* Rounding the sign bit always produces 0. */ + return 0; + } +} + DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR) DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR) DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR) @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr) DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr) DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, , H1_4, do_urshr) +#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX) +#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX) +#define DO_SQSHRUN_D(x, sh) \ + do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX) + +DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H) +DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S) +DO_SHRNB(sve2_sqshrunb_d, int64_t, uint32_t, DO_SQSHRUN_D) + +DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H) +DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S) +DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, , H1_4, DO_SQSHRUN_D) + +#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX) +#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX) +#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX) + +DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H) +DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S) +DO_SHRNB(sve2_sqrshrunb_d, int64_t, uint32_t, DO_SQRSHRUN_D) + +DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H) +DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S) +DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRUN_D) + #undef DO_SHRNB #undef DO_SHRNT diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_RSHRNT(DisasContext *s, arg_rri_esz *a) return do_sve2_shr_narrow(s, a, ops); } +static void gen_sqshrunb_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRUNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_sari_vec, INDEX_op_smax_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrunb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrunb_h, + .vece = MO_16 }, + { .fniv = gen_sqshrunb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrunb_s, + .vece = MO_32 }, + { .fniv = gen_sqshrunb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrunb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_sqshrunt_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, 0); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRUNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, + INDEX_op_smax_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrunt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrunt_h, + .vece = MO_16 }, + { .fniv = gen_sqshrunt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrunt_s, + .vece = MO_32 }, + { .fniv = gen_sqshrunt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrunt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRUNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrunb_h }, + { .fno = gen_helper_sve2_sqrshrunb_s }, + { .fno = gen_helper_sve2_sqrshrunb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRUNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrunt_h }, + { .fno = gen_helper_sve2_sqrshrunt_s }, + { .fno = gen_helper_sve2_sqrshrunt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 16 +++++++ target/arm/sve.decode | 4 ++ target/arm/sve_helper.c | 24 ++++++++++ target/arm/translate-sve.c | 93 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 137 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_sqrshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqrshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqrshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqrshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr RSHRNT 01000101 .. 1 ..... 00 0111 ..... ..... @rd_rn_tszimm_shr +UQSHRNB 01000101 .. 1 ..... 00 1100 ..... ..... @rd_rn_tszimm_shr +UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr +UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr +UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr ## SVE2 floating-point pairwise operations diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H) DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S) DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRUN_D) +#define DO_UQSHRN_H(x, sh) MIN(x >> sh, UINT8_MAX) +#define DO_UQSHRN_S(x, sh) MIN(x >> sh, UINT16_MAX) +#define DO_UQSHRN_D(x, sh) MIN(x >> sh, UINT32_MAX) + +DO_SHRNB(sve2_uqshrnb_h, uint16_t, uint8_t, DO_UQSHRN_H) +DO_SHRNB(sve2_uqshrnb_s, uint32_t, uint16_t, DO_UQSHRN_S) +DO_SHRNB(sve2_uqshrnb_d, uint64_t, uint32_t, DO_UQSHRN_D) + +DO_SHRNT(sve2_uqshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_UQSHRN_H) +DO_SHRNT(sve2_uqshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_UQSHRN_S) +DO_SHRNT(sve2_uqshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQSHRN_D) + +#define DO_UQRSHRN_H(x, sh) MIN(do_urshr(x, sh), UINT8_MAX) +#define DO_UQRSHRN_S(x, sh) MIN(do_urshr(x, sh), UINT16_MAX) +#define DO_UQRSHRN_D(x, sh) MIN(do_urshr(x, sh), UINT32_MAX) + +DO_SHRNB(sve2_uqrshrnb_h, uint16_t, uint8_t, DO_UQRSHRN_H) +DO_SHRNB(sve2_uqrshrnb_s, uint32_t, uint16_t, DO_UQRSHRN_S) +DO_SHRNB(sve2_uqrshrnb_d, uint64_t, uint32_t, DO_UQRSHRN_D) + +DO_SHRNT(sve2_uqrshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_UQRSHRN_H) +DO_SHRNT(sve2_uqrshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_UQRSHRN_S) +DO_SHRNT(sve2_uqrshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQRSHRN_D) + #undef DO_SHRNB #undef DO_SHRNT diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQRSHRUNT(DisasContext *s, arg_rri_esz *a) return do_sve2_shr_narrow(s, a, ops); } +static void gen_uqshrnb_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_shri_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_UQSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shri_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_uqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_uqshrnb_h, + .vece = MO_16 }, + { .fniv = gen_uqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_uqshrnb_s, + .vece = MO_32 }, + { .fniv = gen_uqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_uqshrnb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_uqshrnt_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + + tcg_gen_shri_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_umin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_UQSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shli_vec, INDEX_op_shri_vec, INDEX_op_umin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_uqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_uqshrnt_h, + .vece = MO_16 }, + { .fniv = gen_uqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_uqshrnt_s, + .vece = MO_32 }, + { .fniv = gen_uqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_uqshrnt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_UQRSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_uqrshrnb_h }, + { .fno = gen_helper_sve2_uqrshrnb_s }, + { .fno = gen_helper_sve2_uqrshrnb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_uqrshrnt_h }, + { .fno = gen_helper_sve2_uqrshrnt_s }, + { .fno = gen_helper_sve2_uqrshrnt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This completes the section "SVE2 bitwise shift right narrow". Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 16 ++++++ target/arm/sve.decode | 4 ++ target/arm/sve_helper.c | 24 +++++++++ target/arm/translate-sve.c | 105 +++++++++++++++++++++++++++++++++++++ 4 files changed, 149 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_sqrshrunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqrshrunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_sqrshrunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve2_sqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve2_sqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve2_uqshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_uqshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_uqshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr RSHRNT 01000101 .. 1 ..... 00 0111 ..... ..... @rd_rn_tszimm_shr +SQSHRNB 01000101 .. 1 ..... 00 1000 ..... ..... @rd_rn_tszimm_shr +SQSHRNT 01000101 .. 1 ..... 00 1001 ..... ..... @rd_rn_tszimm_shr +SQRSHRNB 01000101 .. 1 ..... 00 1010 ..... ..... @rd_rn_tszimm_shr +SQRSHRNT 01000101 .. 1 ..... 00 1011 ..... ..... @rd_rn_tszimm_shr UQSHRNB 01000101 .. 1 ..... 00 1100 ..... ..... @rd_rn_tszimm_shr UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H) DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S) DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRUN_D) +#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX) +#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX) +#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX) + +DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H) +DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S) +DO_SHRNB(sve2_sqshrnb_d, int64_t, uint32_t, DO_SQSHRN_D) + +DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H) +DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S) +DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, , H1_4, DO_SQSHRN_D) + +#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX) +#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX) +#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX) + +DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H) +DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S) +DO_SHRNB(sve2_sqrshrnb_d, int64_t, uint32_t, DO_SQRSHRN_D) + +DO_SHRNT(sve2_sqrshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRN_H) +DO_SHRNT(sve2_sqrshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRN_S) +DO_SHRNT(sve2_sqrshrnt_d, int64_t, uint32_t, , H1_4, DO_SQRSHRN_D) + #define DO_UQSHRN_H(x, sh) MIN(x >> sh, UINT8_MAX) #define DO_UQSHRN_S(x, sh) MIN(x >> sh, UINT16_MAX) #define DO_UQSHRN_D(x, sh) MIN(x >> sh, UINT32_MAX) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQRSHRUNT(DisasContext *s, arg_rri_esz *a) return do_sve2_shr_narrow(s, a, ops); } +static void gen_sqshrnb_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = MAKE_64BIT_MASK(0, halfbits - 1); + int64_t min = -max - 1; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_and_vec(vece, d, n, t); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_sari_vec, INDEX_op_smax_vec, INDEX_op_smin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrnb_h, + .vece = MO_16 }, + { .fniv = gen_sqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrnb_s, + .vece = MO_32 }, + { .fniv = gen_sqshrnb_vec, + .opt_opc = vec_list, + .fno = gen_helper_sve2_sqshrnb_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static void gen_sqshrnt_vec(unsigned vece, TCGv_vec d, + TCGv_vec n, int64_t shr) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + int halfbits = 4 << vece; + int64_t max = MAKE_64BIT_MASK(0, halfbits - 1); + int64_t min = -max - 1; + + tcg_gen_sari_vec(vece, n, n, shr); + tcg_gen_dupi_vec(vece, t, min); + tcg_gen_smax_vec(vece, n, n, t); + tcg_gen_dupi_vec(vece, t, max); + tcg_gen_smin_vec(vece, n, n, t); + tcg_gen_shli_vec(vece, n, n, halfbits); + tcg_gen_dupi_vec(vece, t, MAKE_64BIT_MASK(0, halfbits)); + tcg_gen_bitsel_vec(vece, d, t, d, n); + tcg_temp_free_vec(t); +} + +static bool trans_SQSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const TCGOpcode vec_list[] = { + INDEX_op_shli_vec, INDEX_op_sari_vec, + INDEX_op_smax_vec, INDEX_op_smin_vec, 0 + }; + static const GVecGen2i ops[3] = { + { .fniv = gen_sqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrnt_h, + .vece = MO_16 }, + { .fniv = gen_sqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrnt_s, + .vece = MO_32 }, + { .fniv = gen_sqshrnt_vec, + .opt_opc = vec_list, + .load_dest = true, + .fno = gen_helper_sve2_sqshrnt_d, + .vece = MO_64 }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRNB(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrnb_h }, + { .fno = gen_helper_sve2_sqrshrnb_s }, + { .fno = gen_helper_sve2_sqrshrnb_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + +static bool trans_SQRSHRNT(DisasContext *s, arg_rri_esz *a) +{ + static const GVecGen2i ops[3] = { + { .fno = gen_helper_sve2_sqrshrnt_h }, + { .fno = gen_helper_sve2_sqrshrnt_s }, + { .fno = gen_helper_sve2_sqrshrnt_d }, + }; + return do_sve2_shr_narrow(s, a, ops); +} + static void gen_uqshrnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rename the existing sve_while (less-than) helper to sve_whilel to make room for a new sve_whileg helper for greater-than. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 3 +- target/arm/sve.decode | 2 +- target/arm/sve_helper.c | 38 +++++++++++++++++++++++++- target/arm/translate-sve.c | 56 ++++++++++++++++++++++++++++---------- 4 files changed, 82 insertions(+), 17 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) -DEF_HELPER_FLAGS_3(sve_while, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit -WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 +WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4 ### SVE Integer Wide Immediate - Unpredicated Group diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } -uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) +uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + intptr_t i, invcount, oprbits; + uint64_t bits; + + if (count == 0) { + return do_zero(d, oprsz); + } + + oprbits = oprsz * 8; + tcg_debug_assert(count <= oprbits); + + bits = esz_mask; + if (oprbits & 63) { + bits &= MAKE_64BIT_MASK(0, oprbits & 63); + } + + invcount = oprbits - count; + for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { + d->p[i] = bits; + bits = esz_mask; + } + + d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); + + while (--i >= 0) { + d->p[i] = 0; + } + + return predtest_ones(d, oprsz, esz_mask); +} + /* Recursive reduction on a function; * C.f. the ARM ARM function ReducePredicated. * diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) unsigned vsz = vec_full_reg_size(s); unsigned desc = 0; TCGCond cond; + uint64_t maxval; + /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */ + bool eq = a->eq == a->lt; + /* The greater-than conditions are all SVE2. */ + if (!a->lt && !dc_isar_feature(aa64_sve2, s)) { + return false; + } if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) */ t0 = tcg_temp_new_i64(); t1 = tcg_temp_new_i64(); - tcg_gen_sub_i64(t0, op1, op0); + + if (a->lt) { + tcg_gen_sub_i64(t0, op1, op0); + if (a->u) { + maxval = a->sf ? UINT64_MAX : UINT32_MAX; + cond = eq ? TCG_COND_LEU : TCG_COND_LTU; + } else { + maxval = a->sf ? INT64_MAX : INT32_MAX; + cond = eq ? TCG_COND_LE : TCG_COND_LT; + } + } else { + tcg_gen_sub_i64(t0, op0, op1); + if (a->u) { + maxval = 0; + cond = eq ? TCG_COND_GEU : TCG_COND_GTU; + } else { + maxval = a->sf ? INT64_MIN : INT32_MIN; + cond = eq ? TCG_COND_GE : TCG_COND_GT; + } + } tmax = tcg_const_i64(vsz >> a->esz); - if (a->eq) { + if (eq) { /* Equality means one more iteration. */ tcg_gen_addi_i64(t0, t0, 1); - /* If op1 is max (un)signed integer (and the only time the addition - * above could overflow), then we produce an all-true predicate by - * setting the count to the vector length. This is because the - * pseudocode is described as an increment + compare loop, and the - * max integer would always compare true. + /* + * For the less-than while, if op1 is maxval (and the only time + * the addition above could overflow), then we produce an all-true + * predicate by setting the count to the vector length. This is + * because the pseudocode is described as an increment + compare + * loop, and the maximum integer would always compare true. + * Similarly, the greater-than while has the same issue with the + * minimum integer due to the decrement + compare loop. */ - tcg_gen_movi_i64(t1, (a->sf - ? (a->u ? UINT64_MAX : INT64_MAX) - : (a->u ? UINT32_MAX : INT32_MAX))); + tcg_gen_movi_i64(t1, maxval); tcg_gen_movcond_i64(TCG_COND_EQ, t0, op1, t1, tmax, t0); } @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) tcg_temp_free_i64(tmax); /* Set the count to zero if the condition is false. */ - cond = (a->u - ? (a->eq ? TCG_COND_LEU : TCG_COND_LTU) - : (a->eq ? TCG_COND_LE : TCG_COND_LT)); tcg_gen_movi_i64(t1, 0); tcg_gen_movcond_i64(cond, t0, op0, op1, t0, t1); tcg_temp_free_i64(t1); @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); - gen_helper_sve_while(t2, ptr, t2, t3); + if (a->lt) { + gen_helper_sve_whilel(t2, ptr, t2, t3); + } else { + gen_helper_sve_whileg(t2, ptr, t2, t3); + } do_pred_flags(t2); tcg_temp_free_ptr(ptr); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 3 ++ target/arm/translate-sve.c | 67 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4 +# SVE2 pointer conflict compare +WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 + ### SVE Integer Wide Immediate - Unpredicated Group # SVE broadcast floating-point immediate (unpredicated) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) return true; } +static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) +{ + TCGv_i64 op0, op1, diff, t1, tmax; + TCGv_i32 t2, t3; + TCGv_ptr ptr; + unsigned vsz = vec_full_reg_size(s); + unsigned desc = 0; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + op0 = read_cpu_reg(s, a->rn, 1); + op1 = read_cpu_reg(s, a->rm, 1); + + tmax = tcg_const_i64(vsz); + diff = tcg_temp_new_i64(); + + if (a->rw) { + /* WHILERW */ + /* diff = abs(op1 - op0), noting that op0/1 are unsigned. */ + t1 = tcg_temp_new_i64(); + tcg_gen_sub_i64(diff, op0, op1); + tcg_gen_sub_i64(t1, op1, op0); + tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1); + tcg_temp_free_i64(t1); + /* Round down to a multiple of ESIZE. */ + tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* If op1 == op0, diff == 0, and the condition is always true. */ + tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff); + } else { + /* WHILEWR */ + tcg_gen_sub_i64(diff, op1, op0); + /* Round down to a multiple of ESIZE. */ + tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* If op0 >= op1, diff <= 0, the condition is always true. */ + tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff); + } + + /* Bound to the maximum. */ + tcg_gen_umin_i64(diff, diff, tmax); + tcg_temp_free_i64(tmax); + + /* Since we're bounded, pass as a 32-bit type. */ + t2 = tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(t2, diff); + tcg_temp_free_i64(diff); + + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + t3 = tcg_const_i32(desc); + + ptr = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); + + gen_helper_sve_whilel(t2, ptr, t2, t3); + do_pred_flags(t2); + + tcg_temp_free_ptr(ptr); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t3); + return true; +} + /* *** SVE Integer Wide Immediate - Unpredicated Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 6 ++ target/arm/sve.decode | 12 +++ target/arm/sve_helper.c | 50 +++++++++ target/arm/translate-sve.c | 213 +++++++++++++++++++++++++++++++++++++ 4 files changed, 281 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_eor3, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_bcax, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_bsl1n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_bsl2n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_nbsl, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @rda_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 \ &rrrr_esz ra=%reg_movprfx +# Four operand with unused vector element size +@rdn_ra_rm_e0 ........ ... rm:5 ... ... ra:5 rd:5 \ + &rrrr_esz esz=0 rn=%reg_movprfx + # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -XXX,XX +XXX,XX @@ ORR_zzz 00000100 01 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 EOR_zzz 00000100 10 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 BIC_zzz 00000100 11 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 +# SVE2 bitwise ternary operations +EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 +BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +BCAX 00000100 01 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 +BSL1N 00000100 01 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +BSL2N 00000100 10 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +NBSL 00000100 11 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 + ### SVE Index Generation Group # SVE index generation (immediate start, immediate increment) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64) #undef DO_ST1_ZPZ_S #undef DO_ST1_ZPZ_D + +void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = n[i] ^ m[i] ^ k[i]; + } +} + +void HELPER(sve2_bcax)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = n[i] ^ (m[i] & ~k[i]); + } +} + +void HELPER(sve2_bsl1n)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = (~n[i] & k[i]) | (m[i] & ~k[i]); + } +} + +void HELPER(sve2_bsl2n)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = (n[i] & k[i]) | (~m[i] & ~k[i]); + } +} + +void HELPER(sve2_nbsl)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn, *m = vm, *k = vk; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ~((n[i] & k[i]) | (m[i] & ~k[i])); + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn_zzz(DisasContext *s, GVecGen3Fn *gvec_fn, vec_full_reg_offset(s, rm), vsz, vsz); } +/* Invoke a vector expander on four Zregs. */ +static void gen_gvec_fn_zzzz(DisasContext *s, GVecGen4Fn *gvec_fn, + int esz, int rd, int rn, int rm, int ra) +{ + unsigned vsz = vec_full_reg_size(s); + gvec_fn(esz, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), vsz, vsz); +} + /* Invoke a vector move on two Zregs. */ static bool do_mov_z(DisasContext *s, int rd, int rn) { @@ -XXX,XX +XXX,XX @@ static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a) return do_zzz_fn(s, a, tcg_gen_gvec_andc); } +static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzzz(s, fn, a->esz, a->rd, a->rn, a->rm, a->ra); + } + return true; +} + +static void gen_eor3_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_xor_i64(d, n, m); + tcg_gen_xor_i64(d, d, k); +} + +static void gen_eor3_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_xor_vec(vece, d, n, m); + tcg_gen_xor_vec(vece, d, d, k); +} + +static void gen_eor3(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_eor3_i64, + .fniv = gen_eor3_vec, + .fno = gen_helper_sve2_eor3, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_EOR3(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_eor3); +} + +static void gen_bcax_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_andc_i64(d, m, k); + tcg_gen_xor_i64(d, d, n); +} + +static void gen_bcax_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_andc_vec(vece, d, m, k); + tcg_gen_xor_vec(vece, d, d, n); +} + +static void gen_bcax(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bcax_i64, + .fniv = gen_bcax_vec, + .fno = gen_helper_sve2_bcax, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_BCAX(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bcax); +} + +static void gen_bsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + /* BSL differs from the generic bitsel in argument ordering. */ + tcg_gen_gvec_bitsel(vece, d, a, n, m, oprsz, maxsz); +} + +static bool trans_BSL(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bsl); +} + +static void gen_bsl1n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_andc_i64(n, k, n); + tcg_gen_andc_i64(m, m, k); + tcg_gen_or_i64(d, n, m); +} + +static void gen_bsl1n_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + if (TCG_TARGET_HAS_bitsel_vec) { + tcg_gen_not_vec(vece, n, n); + tcg_gen_bitsel_vec(vece, d, k, n, m); + } else { + tcg_gen_andc_vec(vece, n, k, n); + tcg_gen_andc_vec(vece, m, m, k); + tcg_gen_or_vec(vece, d, n, m); + } +} + +static void gen_bsl1n(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bsl1n_i64, + .fniv = gen_bsl1n_vec, + .fno = gen_helper_sve2_bsl1n, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_BSL1N(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bsl1n); +} + +static void gen_bsl2n_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + /* + * Z[dn] = (n & k) | (~m & ~k) + * = | ~(m | k) + */ + tcg_gen_and_i64(n, n, k); + if (TCG_TARGET_HAS_orc_i64) { + tcg_gen_or_i64(m, m, k); + tcg_gen_orc_i64(d, n, m); + } else { + tcg_gen_nor_i64(m, m, k); + tcg_gen_or_i64(d, n, m); + } +} + +static void gen_bsl2n_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + if (TCG_TARGET_HAS_bitsel_vec) { + tcg_gen_not_vec(vece, m, m); + tcg_gen_bitsel_vec(vece, d, k, n, m); + } else { + tcg_gen_and_vec(vece, n, n, k); + tcg_gen_or_vec(vece, m, m, k); + tcg_gen_orc_vec(vece, d, n, m); + } +} + +static void gen_bsl2n(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_bsl2n_i64, + .fniv = gen_bsl2n_vec, + .fno = gen_helper_sve2_bsl2n, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_BSL2N(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_bsl2n); +} + +static void gen_nbsl_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 k) +{ + tcg_gen_and_i64(n, n, k); + tcg_gen_andc_i64(m, m, k); + tcg_gen_nor_i64(d, n, m); +} + +static void gen_nbsl_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec k) +{ + tcg_gen_bitsel_vec(vece, d, k, n, m); + tcg_gen_not_vec(vece, d, d); +} + +static void gen_nbsl(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen4 op = { + .fni8 = gen_nbsl_i64, + .fniv = gen_nbsl_vec, + .fno = gen_helper_sve2_nbsl, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &op); +} + +static bool trans_NBSL(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sve2_zzzz_fn(s, a, gen_nbsl); +} + /* *** SVE Integer Arithmetic - Unpredicated Group */ -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-34-richard.henderson@linaro.org Message-Id: <20200415145915.2859-1-steplong@quicinc.com> [rth: Expanded comment for do_match2] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 10 ++++++ target/arm/sve.decode | 5 +++ target/arm/sve_helper.c | 64 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 22 +++++++++++++ 4 files changed, 101 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_b, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_h, TCG_CALL_NO_RWG, + i32, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr +### SVE2 Character Match + +MATCH 01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm +NMATCH 01000101 .. 1 ..... 100 ... ..... 1 .... @pd_pg_rn_rm + ## SVE2 floating-point pairwise operations FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_nbsl)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) d[i] = ~((n[i] & k[i]) | (m[i] & ~k[i])); } } + +/* + * Returns true if m0 or m1 contains the low uint8_t/uint16_t in n. + * See hasless(v,1) from + * https://graphics.stanford.edu/~seander/bithacks.html#ZeroInWord + */ +static inline bool do_match2(uint64_t n, uint64_t m0, uint64_t m1, int esz) +{ + int bits = 8 << esz; + uint64_t ones = dup_const(esz, 1); + uint64_t signs = ones << (bits - 1); + uint64_t cmp0, cmp1; + + cmp1 = dup_const(esz, n); + cmp0 = cmp1 ^ m0; + cmp1 = cmp1 ^ m1; + cmp0 = (cmp0 - ones) & ~cmp0; + cmp1 = (cmp1 - ones) & ~cmp1; + return (cmp0 | cmp1) & signs; +} + +static inline uint32_t do_match(void *vd, void *vn, void *vm, void *vg, + uint32_t desc, int esz, bool nmatch) +{ + uint16_t esz_mask = pred_esz_masks[esz]; + intptr_t opr_sz = simd_oprsz(desc); + uint32_t flags = PREDTEST_INIT; + intptr_t i, j, k; + + for (i = 0; i < opr_sz; i += 16) { + uint64_t m0 = *(uint64_t *)(vm + i); + uint64_t m1 = *(uint64_t *)(vm + i + 8); + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)) & esz_mask; + uint16_t out = 0; + + for (j = 0; j < 16; j += 8) { + uint64_t n = *(uint64_t *)(vn + i + j); + + for (k = 0; k < 8; k += 1 << esz) { + if (pg & (1 << (j + k))) { + bool o = do_match2(n >> (k * 8), m0, m1, esz); + out |= (o ^ nmatch) << (j + k); + } + } + } + *(uint16_t *)(vd + H1_2(i >> 3)) = out; + flags = iter_predtest_fwd(out, pg, flags); + } + return flags; +} + +#define DO_PPZZ_MATCH(NAME, ESZ, INV) \ +uint32_t HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ +{ \ + return do_match(vd, vn, vm, vg, desc, ESZ, INV); \ +} + +DO_PPZZ_MATCH(sve2_match_ppzz_b, MO_8, false) +DO_PPZZ_MATCH(sve2_match_ppzz_h, MO_16, false) + +DO_PPZZ_MATCH(sve2_nmatch_ppzz_b, MO_8, true) +DO_PPZZ_MATCH(sve2_nmatch_ppzz_h, MO_16, true) + +#undef DO_PPZZ_MATCH diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a) return do_sve2_shr_narrow(s, a, ops); } +static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_flags_4 *fn) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_ppzz_flags(s, a, fn); +} + +#define DO_SVE2_PPZZ_MATCH(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ +{ \ + static gen_helper_gvec_flags_4 * const fns[4] = { \ + gen_helper_sve2_##name##_ppzz_b, gen_helper_sve2_##name##_ppzz_h, \ + NULL, NULL \ + }; \ + return do_sve2_ppzz_flags(s, a, fns[a->esz]); \ +} + +DO_SVE2_PPZZ_MATCH(MATCH, match) +DO_SVE2_PPZZ_MATCH(NMATCH, nmatch) + static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 ++++++++++ target/arm/sve.decode | 14 ++++++++++ target/arm/sve_helper.c | 30 +++++++++++++++++++++ target/arm/translate-sve.c | 54 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 112 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_bcax, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_bsl1n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_bsl2n, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_nbsl, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlal_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FMAXNMP 01100100 .. 010 10 0 100 ... ..... ..... @rdn_pg_rm FMINNMP 01100100 .. 010 10 1 100 ... ..... ..... @rdn_pg_rm FMAXP 01100100 .. 010 11 0 100 ... ..... ..... @rdn_pg_rm FMINP 01100100 .. 010 11 1 100 ... ..... ..... @rdn_pg_rm + +#### SVE Integer Multiply-Add (unpredicated) + +## SVE2 saturating multiply-add long + +SQDMLALB_zzzw 01000100 .. 0 ..... 0110 00 ..... ..... @rda_rn_rm +SQDMLALT_zzzw 01000100 .. 0 ..... 0110 01 ..... ..... @rda_rn_rm +SQDMLSLB_zzzw 01000100 .. 0 ..... 0110 10 ..... ..... @rda_rn_rm +SQDMLSLT_zzzw 01000100 .. 0 ..... 0110 11 ..... ..... @rda_rn_rm + +## SVE2 saturating multiply-add interleaved long + +SQDMLALBT 01000100 .. 0 ..... 00001 0 ..... ..... @rda_rn_rm +SQDMLSLBT 01000100 .. 0 ..... 00001 1 ..... ..... @rda_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_adcl_d)(void *vd, void *vn, void *vm, void *va, uint32_t desc) } } +#define DO_SQDMLAL(NAME, TYPEW, TYPEN, HW, HN, DMUL_OP, SUM_OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + int sel1 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + int sel2 = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(TYPEN); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + sel1)); \ + TYPEW mm = *(TYPEN *)(vm + HN(i + sel2)); \ + TYPEW aa = *(TYPEW *)(va + HW(i)); \ + *(TYPEW *)(vd + HW(i)) = SUM_OP(aa, DMUL_OP(nn, mm)); \ + } \ +} + +DO_SQDMLAL(sve2_sqdmlal_zzzw_h, int16_t, int8_t, H1_2, H1, + do_sqdmull_h, DO_SQADD_H) +DO_SQDMLAL(sve2_sqdmlal_zzzw_s, int32_t, int16_t, H1_4, H1_2, + do_sqdmull_s, DO_SQADD_S) +DO_SQDMLAL(sve2_sqdmlal_zzzw_d, int64_t, int32_t, , H1_4, + do_sqdmull_d, do_sqadd_d) + +DO_SQDMLAL(sve2_sqdmlsl_zzzw_h, int16_t, int8_t, H1_2, H1, + do_sqdmull_h, DO_SQSUB_H) +DO_SQDMLAL(sve2_sqdmlsl_zzzw_s, int32_t, int16_t, H1_4, H1_2, + do_sqdmull_s, DO_SQSUB_S) +DO_SQDMLAL(sve2_sqdmlsl_zzzw_d, int64_t, int32_t, , H1_4, + do_sqdmull_d, do_sqsub_d) + +#undef DO_SQDMLAL + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ_FP(FMAXNMP, fmaxnmp) DO_SVE2_ZPZZ_FP(FMINNMP, fminnmp) DO_SVE2_ZPZZ_FP(FMAXP, fmaxp) DO_SVE2_ZPZZ_FP(FMINP, fminp) + +/* + * SVE Integer Multiply-Add (unpredicated) + */ + +static bool do_sqdmlal_zzzw(DisasContext *s, arg_rrrr_esz *a, + bool sel1, bool sel2) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_sqdmlal_zzzw_h, + gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1); +} + +static bool do_sqdmlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, + bool sel1, bool sel2) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_sqdmlsl_zzzw_h, + gen_helper_sve2_sqdmlsl_zzzw_s, gen_helper_sve2_sqdmlsl_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], (sel2 << 1) | sel1); +} + +static bool trans_SQDMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlal_zzzw(s, a, false, false); +} + +static bool trans_SQDMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlal_zzzw(s, a, true, true); +} + +static bool trans_SQDMLALBT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlal_zzzw(s, a, false, true); +} + +static bool trans_SQDMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlsl_zzzw(s, a, false, false); +} + +static bool trans_SQDMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlsl_zzzw(s, a, true, true); +} + +static bool trans_SQDMLSLBT(DisasContext *s, arg_rrrr_esz *a) +{ + return do_sqdmlsl_zzzw(s, a, false, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> SVE2 has two additional sizes of the operation and unlike NEON, there is no saturation flag. Create new entry points for SVE2 that do not set QC. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 17 ++++ target/arm/sve.decode | 5 ++ target/arm/translate-sve.c | 18 +++++ target/arm/vec_helper.c | 161 +++++++++++++++++++++++++++++++++++-- 4 files changed, 195 insertions(+), 6 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_qrdmlah_s32, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQDMLSLT_zzzw 01000100 .. 0 ..... 0110 11 ..... ..... @rda_rn_rm SQDMLALBT 01000100 .. 0 ..... 00001 0 ..... ..... @rda_rn_rm SQDMLSLBT 01000100 .. 0 ..... 00001 1 ..... ..... @rda_rn_rm + +## SVE2 saturating multiply-add high + +SQRDMLAH_zzzz 01000100 .. 0 ..... 01110 0 ..... ..... @rda_rn_rm +SQRDMLSH_zzzz 01000100 .. 0 ..... 01110 1 ..... ..... @rda_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQDMLSLBT(DisasContext *s, arg_rrrr_esz *a) { return do_sqdmlsl_zzzw(s, a, false, true); } + +static bool trans_SQRDMLAH_zzzz(DisasContext *s, arg_rrrr_esz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_sqrdmlah_b, gen_helper_sve2_sqrdmlah_h, + gen_helper_sve2_sqrdmlah_s, gen_helper_sve2_sqrdmlah_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); +} + +static bool trans_SQRDMLSH_zzzz(DisasContext *s, arg_rrrr_esz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_sqrdmlsh_b, gen_helper_sve2_sqrdmlsh_h, + gen_helper_sve2_sqrdmlsh_s, gen_helper_sve2_sqrdmlsh_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); +} diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/helper-proto.h" #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" +#include "qemu/int128.h" #include "vec_internal.h" /* Note that vector data is stored in host-endian 64-bit chunks, @@ -XXX,XX +XXX,XX @@ #define H4(x) (x) #endif +/* Signed saturating rounding doubling multiply-accumulate high half, 8-bit */ +static int8_t do_sqrdmlah_b(int8_t src1, int8_t src2, int8_t src3, + bool neg, bool round) +{ + /* + * Simplify: + * = ((a3 << 8) + ((e1 * e2) << 1) + (round << 7)) >> 8 + * = ((a3 << 7) + (e1 * e2) + (round << 6)) >> 7 + */ + int32_t ret = (int32_t)src1 * src2; + if (neg) { + ret = -ret; + } + ret += ((int32_t)src3 << 7) + (round << 6); + ret >>= 7; + + if (ret != (int8_t)ret) { + ret = (ret < 0 ? INT8_MIN : INT8_MAX); + } + return ret; +} + +void HELPER(sve2_sqrdmlah_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm, *a = va; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], a[i], false, true); + } +} + +void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm, *a = va; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], a[i], true, true); + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ static int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3, bool neg, bool round, uint32_t *sat) { - /* - * Simplify: - * = ((a3 << 16) + ((e1 * e2) << 1) + (1 << 15)) >> 16 - * = ((a3 << 15) + (e1 * e2) + (1 << 14)) >> 15 - */ + /* Simplify similarly to do_sqrdmlah_b above. */ int32_t ret = (int32_t)src1 * src2; if (neg) { ret = -ret; @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_h)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(sve2_sqrdmlah_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], a[i], false, true, &discard); + } +} + +void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], a[i], true, true, &discard); + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */ static int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, bool neg, bool round, uint32_t *sat) { - /* Simplify similarly to int_qrdmlah_s16 above. */ + /* Simplify similarly to do_sqrdmlah_b above. */ int64_t ret = (int64_t)src1 * src2; if (neg) { ret = -ret; @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_s)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(sve2_sqrdmlah_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int32_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = do_sqrdmlah_s(n[i], m[i], a[i], false, true, &discard); + } +} + +void HELPER(sve2_sqrdmlsh_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int32_t *d = vd, *n = vn, *m = vm, *a = va; + uint32_t discard; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = do_sqrdmlah_s(n[i], m[i], a[i], true, true, &discard); + } +} + +/* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */ +static int64_t do_sat128_d(Int128 r) +{ + int64_t ls = int128_getlo(r); + int64_t hs = int128_gethi(r); + + if (unlikely(hs != (ls >> 63))) { + return hs < 0 ? INT64_MIN : INT64_MAX; + } + return ls; +} + +static int64_t do_sqrdmlah_d(int64_t n, int64_t m, int64_t a, + bool neg, bool round) +{ + uint64_t l, h; + Int128 r, t; + + /* As in do_sqrdmlah_b, but with 128-bit arithmetic. */ + muls64(&l, &h, m, n); + r = int128_make128(l, h); + if (neg) { + r = int128_neg(r); + } + if (a) { + t = int128_exts64(a); + t = int128_lshift(t, 63); + r = int128_add(r, t); + } + if (round) { + t = int128_exts64(1ll << 62); + r = int128_add(r, t); + } + r = int128_rshift(r, 63); + + return do_sat128_d(r); +} + +void HELPER(sve2_sqrdmlah_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm, *a = va; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], a[i], false, true); + } +} + +void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm, *a = va; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], a[i], true, true); + } +} + /* Integer 8 and 16-bit dot-product. * * Note that for the loops herein, host endianness does not matter -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 28 ++++++++++++++ target/arm/sve.decode | 11 ++++++ target/arm/sve_helper.c | 18 +++++++++ target/arm/translate-sve.c | 76 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 133 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_sqdmlsl_zzzw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smlal_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlal_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_umlal_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smlsl_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQDMLSLBT 01000100 .. 0 ..... 00001 1 ..... ..... @rda_rn_rm SQRDMLAH_zzzz 01000100 .. 0 ..... 01110 0 ..... ..... @rda_rn_rm SQRDMLSH_zzzz 01000100 .. 0 ..... 01110 1 ..... ..... @rda_rn_rm + +## SVE2 integer multiply-add long + +SMLALB_zzzw 01000100 .. 0 ..... 010 000 ..... ..... @rda_rn_rm +SMLALT_zzzw 01000100 .. 0 ..... 010 001 ..... ..... @rda_rn_rm +UMLALB_zzzw 01000100 .. 0 ..... 010 010 ..... ..... @rda_rn_rm +UMLALT_zzzw 01000100 .. 0 ..... 010 011 ..... ..... @rda_rn_rm +SMLSLB_zzzw 01000100 .. 0 ..... 010 100 ..... ..... @rda_rn_rm +SMLSLT_zzzw 01000100 .. 0 ..... 010 101 ..... ..... @rda_rn_rm +UMLSLB_zzzw 01000100 .. 0 ..... 010 110 ..... ..... @rda_rn_rm +UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZZW_ACC(sve2_uabal_h, uint16_t, uint8_t, H1_2, H1, DO_ABD) DO_ZZZW_ACC(sve2_uabal_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD) DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t, , H1_4, DO_ABD) +DO_ZZZW_ACC(sve2_smlal_zzzw_h, int16_t, int8_t, H1_2, H1, DO_MUL) +DO_ZZZW_ACC(sve2_smlal_zzzw_s, int32_t, int16_t, H1_4, H1_2, DO_MUL) +DO_ZZZW_ACC(sve2_smlal_zzzw_d, int64_t, int32_t, , H1_4, DO_MUL) + +DO_ZZZW_ACC(sve2_umlal_zzzw_h, uint16_t, uint8_t, H1_2, H1, DO_MUL) +DO_ZZZW_ACC(sve2_umlal_zzzw_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL) +DO_ZZZW_ACC(sve2_umlal_zzzw_d, uint64_t, uint32_t, , H1_4, DO_MUL) + +#define DO_NMUL(N, M) -(N * M) + +DO_ZZZW_ACC(sve2_smlsl_zzzw_h, int16_t, int8_t, H1_2, H1, DO_NMUL) +DO_ZZZW_ACC(sve2_smlsl_zzzw_s, int32_t, int16_t, H1_4, H1_2, DO_NMUL) +DO_ZZZW_ACC(sve2_smlsl_zzzw_d, int64_t, int32_t, , H1_4, DO_NMUL) + +DO_ZZZW_ACC(sve2_umlsl_zzzw_h, uint16_t, uint8_t, H1_2, H1, DO_NMUL) +DO_ZZZW_ACC(sve2_umlsl_zzzw_s, uint32_t, uint16_t, H1_4, H1_2, DO_NMUL) +DO_ZZZW_ACC(sve2_umlsl_zzzw_d, uint64_t, uint32_t, , H1_4, DO_NMUL) + #undef DO_ZZZW_ACC #define DO_XTNB(NAME, TYPE, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQRDMLSH_zzzz(DisasContext *s, arg_rrrr_esz *a) }; return do_sve2_zzzz_ool(s, a, fns[a->esz], 0); } + +static bool do_smlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_smlal_zzzw_h, + gen_helper_sve2_smlal_zzzw_s, gen_helper_sve2_smlal_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_SMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlal_zzzw(s, a, false); +} + +static bool trans_SMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlal_zzzw(s, a, true); +} + +static bool do_umlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_umlal_zzzw_h, + gen_helper_sve2_umlal_zzzw_s, gen_helper_sve2_umlal_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_UMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlal_zzzw(s, a, false); +} + +static bool trans_UMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlal_zzzw(s, a, true); +} + +static bool do_smlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_smlsl_zzzw_h, + gen_helper_sve2_smlsl_zzzw_s, gen_helper_sve2_smlsl_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_SMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlsl_zzzw(s, a, false); +} + +static bool trans_SMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_smlsl_zzzw(s, a, true); +} + +static bool do_umlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + static gen_helper_gvec_4 * const fns[] = { + NULL, gen_helper_sve2_umlsl_zzzw_h, + gen_helper_sve2_umlsl_zzzw_s, gen_helper_sve2_umlsl_zzzw_d, + }; + return do_sve2_zzzz_ool(s, a, fns[a->esz], sel); +} + +static bool trans_UMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlsl_zzzw(s, a, false); +} + +static bool trans_UMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) +{ + return do_umlsl_zzzw(s, a, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-38-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 18 +++++++++++++++ target/arm/vec_internal.h | 5 +++++ target/arm/sve.decode | 5 +++++ target/arm/sve_helper.c | 46 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 32 ++++++++++++++++++++++++++ target/arm/vec_helper.c | 15 ++++++------- 6 files changed, 113 insertions(+), 8 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) 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 @@ static inline int64_t do_suqrshl_d(int64_t src, int64_t shift, return do_uqrshl_d(src, shift, round, sat); } +int8_t do_sqrdmlah_b(int8_t, int8_t, int8_t, bool, bool); +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); + #endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SMLSLB_zzzw 01000100 .. 0 ..... 010 100 ..... ..... @rda_rn_rm SMLSLT_zzzw 01000100 .. 0 ..... 010 101 ..... ..... @rda_rn_rm UMLSLB_zzzw 01000100 .. 0 ..... 010 110 ..... ..... @rda_rn_rm UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm + +## SVE2 complex integer multiply-add + +CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx +SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_SQDMLAL(sve2_sqdmlsl_zzzw_d, int64_t, int32_t, , H1_4, #undef DO_SQDMLAL +#define DO_CMLA_FUNC(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(TYPE); \ + int rot = simd_data(desc); \ + int sel_a = rot & 1, sel_b = sel_a ^ 1; \ + bool sub_r = rot == 1 || rot == 2; \ + bool sub_i = rot >= 2; \ + TYPE *d = vd, *n = vn, *m = vm, *a = va; \ + for (i = 0; i < opr_sz; i += 2) { \ + TYPE elt1_a = n[H(i + sel_a)]; \ + TYPE elt2_a = m[H(i + sel_a)]; \ + TYPE elt2_b = m[H(i + sel_b)]; \ + d[H(i)] = OP(elt1_a, elt2_a, a[H(i)], sub_r); \ + d[H(i + 1)] = OP(elt1_a, elt2_b, a[H(i + 1)], sub_i); \ + } \ +} + +#define DO_CMLA(N, M, A, S) (A + (N * M) * (S ? -1 : 1)) + +DO_CMLA_FUNC(sve2_cmla_zzzz_b, uint8_t, H1, DO_CMLA) +DO_CMLA_FUNC(sve2_cmla_zzzz_h, uint16_t, H2, DO_CMLA) +DO_CMLA_FUNC(sve2_cmla_zzzz_s, uint32_t, H4, DO_CMLA) +DO_CMLA_FUNC(sve2_cmla_zzzz_d, uint64_t, , DO_CMLA) + +#define DO_SQRDMLAH_B(N, M, A, S) \ + do_sqrdmlah_b(N, M, A, S, true) +#define DO_SQRDMLAH_H(N, M, A, S) \ + ({ uint32_t discard; do_sqrdmlah_h(N, M, A, S, true, &discard); }) +#define DO_SQRDMLAH_S(N, M, A, S) \ + ({ uint32_t discard; do_sqrdmlah_s(N, M, A, S, true, &discard); }) +#define DO_SQRDMLAH_D(N, M, A, S) \ + do_sqrdmlah_d(N, M, A, S, true) + +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_b, int8_t, H1, DO_SQRDMLAH_B) +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_h, int16_t, H2, DO_SQRDMLAH_H) +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_s, int32_t, H4, DO_SQRDMLAH_S) +DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_d, int64_t, , DO_SQRDMLAH_D) + +#undef DO_CMLA +#undef DO_CMLA_FUNC +#undef DO_SQRDMLAH_B +#undef DO_SQRDMLAH_H +#undef DO_SQRDMLAH_S +#undef DO_SQRDMLAH_D + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a) { return do_umlsl_zzzw(s, a, true); } + +static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_cmla_zzzz_b, gen_helper_sve2_cmla_zzzz_h, + gen_helper_sve2_cmla_zzzz_s, gen_helper_sve2_cmla_zzzz_d, + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot); + } + return true; +} + +static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) +{ + static gen_helper_gvec_4 * const fns[] = { + gen_helper_sve2_sqrdcmlah_zzzz_b, gen_helper_sve2_sqrdcmlah_zzzz_h, + gen_helper_sve2_sqrdcmlah_zzzz_s, gen_helper_sve2_sqrdcmlah_zzzz_d, + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot); + } + return true; +} 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 @@ #endif /* Signed saturating rounding doubling multiply-accumulate high half, 8-bit */ -static int8_t do_sqrdmlah_b(int8_t src1, int8_t src2, int8_t src3, - bool neg, bool round) +int8_t do_sqrdmlah_b(int8_t src1, int8_t src2, int8_t src3, + bool neg, bool round) { /* * Simplify: @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm, } /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ -static int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3, - bool neg, bool round, uint32_t *sat) +int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3, + bool neg, bool round, uint32_t *sat) { /* Simplify similarly to do_sqrdmlah_b above. */ int32_t ret = (int32_t)src1 * src2; @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm, } /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */ -static int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, - bool neg, bool round, uint32_t *sat) +int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, + bool neg, bool round, uint32_t *sat) { /* Simplify similarly to do_sqrdmlah_b above. */ int64_t ret = (int64_t)src1 * src2; @@ -XXX,XX +XXX,XX @@ static int64_t do_sat128_d(Int128 r) return ls; } -static int64_t do_sqrdmlah_d(int64_t n, int64_t m, int64_t a, - bool neg, bool round) +int64_t do_sqrdmlah_d(int64_t n, int64_t m, int64_t a, bool neg, bool round) { uint64_t l, h; Int128 r, t; -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-39-richard.henderson@linaro.org Message-Id: <20200417162231.10374-2-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 8 ++++++++ target/arm/sve.decode | 5 +++++ target/arm/sve_helper.c | 36 ++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 13 +++++++++++++ 4 files changed, 62 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_addhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_addhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr +## SVE2 integer add/subtract narrow high part + +ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm +ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm + ### SVE2 Character Match MATCH 01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_SHRNT(sve2_uqrshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQRSHRN_D) #undef DO_SHRNB #undef DO_SHRNT +#define DO_BINOPNB(NAME, TYPEW, TYPEN, SHIFT, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + i); \ + TYPEW mm = *(TYPEW *)(vm + i); \ + *(TYPEW *)(vd + i) = (TYPEN)OP(nn, mm, SHIFT); \ + } \ +} + +#define DO_BINOPNT(NAME, TYPEW, TYPEN, SHIFT, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + TYPEW mm = *(TYPEW *)(vm + HW(i)); \ + *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, mm, SHIFT); \ + } \ +} + +#define DO_ADDHN(N, M, SH) ((N + M) >> SH) + +DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN) +DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN) +DO_BINOPNB(sve2_addhnb_d, uint64_t, uint32_t, 32, DO_ADDHN) + +DO_BINOPNT(sve2_addhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_ADDHN) +DO_BINOPNT(sve2_addhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_ADDHN) +DO_BINOPNT(sve2_addhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_ADDHN) + +#undef DO_ADDHN + +#undef DO_BINOPNB + /* Fully general four-operand expander, controlled by a predicate. */ #define DO_ZPZZZ(NAME, TYPE, H, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a) return do_sve2_shr_narrow(s, a, ops); } +#define DO_SVE2_ZZZ_NARROW(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ +{ \ + static gen_helper_gvec_3 * const fns[4] = { \ + NULL, gen_helper_sve2_##name##_h, \ + gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \ + }; \ + return do_sve2_zzz_ool(s, a, fns[a->esz]); \ +} + +DO_SVE2_ZZZ_NARROW(ADDHNB, addhnb) +DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt) + static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_flags_4 *fn) { -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-40-richard.henderson@linaro.org Message-Id: <20200417162231.10374-3-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 8 ++++++++ target/arm/sve.decode | 2 ++ target/arm/sve_helper.c | 10 ++++++++++ target/arm/translate-sve.c | 2 ++ 4 files changed, 22 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_addhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_addhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_addhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_raddhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_raddhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm +RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm +RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm ### SVE2 Character Match diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ } #define DO_ADDHN(N, M, SH) ((N + M) >> SH) +#define DO_RADDHN(N, M, SH) ((N + M + ((__typeof(N))1 << (SH - 1))) >> SH) DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN) DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN) @@ -XXX,XX +XXX,XX @@ DO_BINOPNT(sve2_addhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_ADDHN) DO_BINOPNT(sve2_addhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_ADDHN) DO_BINOPNT(sve2_addhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_ADDHN) +DO_BINOPNB(sve2_raddhnb_h, uint16_t, uint8_t, 8, DO_RADDHN) +DO_BINOPNB(sve2_raddhnb_s, uint32_t, uint16_t, 16, DO_RADDHN) +DO_BINOPNB(sve2_raddhnb_d, uint64_t, uint32_t, 32, DO_RADDHN) + +DO_BINOPNT(sve2_raddhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RADDHN) +DO_BINOPNT(sve2_raddhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RADDHN) +DO_BINOPNT(sve2_raddhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RADDHN) + +#undef DO_RADDHN #undef DO_ADDHN #undef DO_BINOPNB diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \ DO_SVE2_ZZZ_NARROW(ADDHNB, addhnb) DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt) +DO_SVE2_ZZZ_NARROW(RADDHNB, raddhnb) +DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt) static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_flags_4 *fn) -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-41-richard.henderson@linaro.org Message-Id: <20200417162231.10374-4-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 8 ++++++++ target/arm/sve.decode | 2 ++ target/arm/sve_helper.c | 10 ++++++++++ target/arm/translate-sve.c | 3 +++ 4 files changed, 23 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_raddhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_raddhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_raddhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_subhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_subhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm +SUBHNB 01000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm +SUBHNT 01000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm ### SVE2 Character Match diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ #define DO_ADDHN(N, M, SH) ((N + M) >> SH) #define DO_RADDHN(N, M, SH) ((N + M + ((__typeof(N))1 << (SH - 1))) >> SH) +#define DO_SUBHN(N, M, SH) ((N - M) >> SH) DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN) DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN) @@ -XXX,XX +XXX,XX @@ DO_BINOPNT(sve2_raddhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RADDHN) DO_BINOPNT(sve2_raddhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RADDHN) DO_BINOPNT(sve2_raddhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RADDHN) +DO_BINOPNB(sve2_subhnb_h, uint16_t, uint8_t, 8, DO_SUBHN) +DO_BINOPNB(sve2_subhnb_s, uint32_t, uint16_t, 16, DO_SUBHN) +DO_BINOPNB(sve2_subhnb_d, uint64_t, uint32_t, 32, DO_SUBHN) + +DO_BINOPNT(sve2_subhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_SUBHN) +DO_BINOPNT(sve2_subhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_SUBHN) +DO_BINOPNT(sve2_subhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_SUBHN) + +#undef DO_SUBHN #undef DO_RADDHN #undef DO_ADDHN diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt) DO_SVE2_ZZZ_NARROW(RADDHNB, raddhnb) DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt) +DO_SVE2_ZZZ_NARROW(SUBHNB, subhnb) +DO_SVE2_ZZZ_NARROW(SUBHNT, subhnt) + static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_flags_4 *fn) { -- 2.20.1 From: Stephen Long <steplong@quicinc.com> This completes the section 'SVE2 integer add/subtract narrow high part' Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-42-richard.henderson@linaro.org Message-Id: <20200417162231.10374-5-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 8 ++++++++ target/arm/sve.decode | 2 ++ target/arm/sve_helper.c | 10 ++++++++++ target/arm/translate-sve.c | 2 ++ 4 files changed, 22 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_subhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_subhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_subhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_rsubhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_rsubhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm SUBHNB 01000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm SUBHNT 01000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm +RSUBHNB 01000101 .. 1 ..... 011 110 ..... ..... @rd_rn_rm +RSUBHNT 01000101 .. 1 ..... 011 111 ..... ..... @rd_rn_rm ### SVE2 Character Match diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ #define DO_ADDHN(N, M, SH) ((N + M) >> SH) #define DO_RADDHN(N, M, SH) ((N + M + ((__typeof(N))1 << (SH - 1))) >> SH) #define DO_SUBHN(N, M, SH) ((N - M) >> SH) +#define DO_RSUBHN(N, M, SH) ((N - M + ((__typeof(N))1 << (SH - 1))) >> SH) DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN) DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN) @@ -XXX,XX +XXX,XX @@ DO_BINOPNT(sve2_subhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_SUBHN) DO_BINOPNT(sve2_subhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_SUBHN) DO_BINOPNT(sve2_subhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_SUBHN) +DO_BINOPNB(sve2_rsubhnb_h, uint16_t, uint8_t, 8, DO_RSUBHN) +DO_BINOPNB(sve2_rsubhnb_s, uint32_t, uint16_t, 16, DO_RSUBHN) +DO_BINOPNB(sve2_rsubhnb_d, uint64_t, uint32_t, 32, DO_RSUBHN) + +DO_BINOPNT(sve2_rsubhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RSUBHN) +DO_BINOPNT(sve2_rsubhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RSUBHN) +DO_BINOPNT(sve2_rsubhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RSUBHN) + +#undef DO_RSUBHN #undef DO_SUBHN #undef DO_RADDHN #undef DO_ADDHN diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt) DO_SVE2_ZZZ_NARROW(SUBHNB, subhnb) DO_SVE2_ZZZ_NARROW(SUBHNT, subhnt) +DO_SVE2_ZZZ_NARROW(RSUBHNB, rsubhnb) +DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt) static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_flags_4 *fn) -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-43-richard.henderson@linaro.org Message-Id: <20200416173109.8856-1-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 7 ++ target/arm/sve.decode | 6 ++ target/arm/sve_helper.c | 131 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 19 ++++++ 4 files changed, 163 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_b, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_h, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_histcnt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_histcnt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_histseg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rprrr_esz rn=%reg_movprfx @rdn_pg_rm_ra ........ esz:2 . ra:5 ... pg:3 rm:5 rd:5 \ &rprrr_esz rn=%reg_movprfx +@rd_pg_rn_rm ........ esz:2 . rm:5 ... pg:3 rn:5 rd:5 &rprr_esz # One register operand, with governing predicate, vector element size @rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz @@ -XXX,XX +XXX,XX @@ RSUBHNT 01000101 .. 1 ..... 011 111 ..... ..... @rd_rn_rm MATCH 01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm NMATCH 01000101 .. 1 ..... 100 ... ..... 1 .... @pd_pg_rn_rm +### SVE2 Histogram Computation + +HISTCNT 01000101 .. 1 ..... 110 ... ..... ..... @rd_pg_rn_rm +HISTSEG 01000101 .. 1 ..... 101 000 ..... ..... @rd_rn_rm + ## SVE2 floating-point pairwise operations FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_PPZZ_MATCH(sve2_nmatch_ppzz_b, MO_8, true) DO_PPZZ_MATCH(sve2_nmatch_ppzz_h, MO_16, true) #undef DO_PPZZ_MATCH + +void HELPER(sve2_histcnt_s)(void *vd, void *vn, void *vm, void *vg, + uint32_t desc) +{ + ARMVectorReg scratch; + intptr_t i, j; + intptr_t opr_sz = simd_oprsz(desc); + uint32_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + if (d == n) { + n = memcpy(&scratch, n, opr_sz); + if (d == m) { + m = n; + } + } else if (d == m) { + m = memcpy(&scratch, m, opr_sz); + } + + for (i = 0; i < opr_sz; i += 4) { + uint64_t count = 0; + uint8_t pred; + + pred = pg[H1(i >> 3)] >> (i & 7); + if (pred & 1) { + uint32_t nn = n[H4(i >> 2)]; + + for (j = 0; j <= i; j += 4) { + pred = pg[H1(j >> 3)] >> (j & 7); + if ((pred & 1) && nn == m[H4(j >> 2)]) { + ++count; + } + } + } + d[H4(i >> 2)] = count; + } +} + +void HELPER(sve2_histcnt_d)(void *vd, void *vn, void *vm, void *vg, + uint32_t desc) +{ + ARMVectorReg scratch; + intptr_t i, j; + intptr_t opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint8_t *pg = vg; + + if (d == n) { + n = memcpy(&scratch, n, opr_sz); + if (d == m) { + m = n; + } + } else if (d == m) { + m = memcpy(&scratch, m, opr_sz); + } + + for (i = 0; i < opr_sz / 8; ++i) { + uint64_t count = 0; + if (pg[H1(i)] & 1) { + uint64_t nn = n[i]; + for (j = 0; j <= i; ++j) { + if ((pg[H1(j)] & 1) && nn == m[j]) { + ++count; + } + } + } + d[i] = count; + } +} + +/* + * Returns the number of bytes in m0 and m1 that match n. + * Unlike do_match2 we don't just need true/false, we need an exact count. + * This requires two extra logical operations. + */ +static inline uint64_t do_histseg_cnt(uint8_t n, uint64_t m0, uint64_t m1) +{ + const uint64_t mask = dup_const(MO_8, 0x7f); + uint64_t cmp0, cmp1; + + cmp1 = dup_const(MO_8, n); + cmp0 = cmp1 ^ m0; + cmp1 = cmp1 ^ m1; + + /* + * 1: clear msb of each byte to avoid carry to next byte (& mask) + * 2: carry in to msb if byte != 0 (+ mask) + * 3: set msb if cmp has msb set (| cmp) + * 4: set ~msb to ignore them (| mask) + * We now have 0xff for byte != 0 or 0x7f for byte == 0. + * 5: invert, resulting in 0x80 if and only if byte == 0. + */ + cmp0 = ~(((cmp0 & mask) + mask) | cmp0 | mask); + cmp1 = ~(((cmp1 & mask) + mask) | cmp1 | mask); + + /* + * Combine the two compares in a way that the bits do + * not overlap, and so preserves the count of set bits. + * If the host has an efficient instruction for ctpop, + * then ctpop(x) + ctpop(y) has the same number of + * operations as ctpop(x | (y >> 1)). If the host does + * not have an efficient ctpop, then we only want to + * use it once. + */ + return ctpop64(cmp0 | (cmp1 >> 1)); +} + +void HELPER(sve2_histseg)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j; + intptr_t opr_sz = simd_oprsz(desc); + + for (i = 0; i < opr_sz; i += 16) { + uint64_t n0 = *(uint64_t *)(vn + i); + uint64_t m0 = *(uint64_t *)(vm + i); + uint64_t n1 = *(uint64_t *)(vn + i + 8); + uint64_t m1 = *(uint64_t *)(vm + i + 8); + uint64_t out0 = 0; + uint64_t out1 = 0; + + for (j = 0; j < 64; j += 8) { + uint64_t cnt0 = do_histseg_cnt(n0 >> j, m0, m1); + uint64_t cnt1 = do_histseg_cnt(n1 >> j, m0, m1); + out0 |= cnt0 << j; + out1 |= cnt1 << j; + } + + *(uint64_t *)(vd + i) = out0; + *(uint64_t *)(vd + i + 8) = out1; + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \ DO_SVE2_PPZZ_MATCH(MATCH, match) DO_SVE2_PPZZ_MATCH(NMATCH, nmatch) +static bool trans_HISTCNT(DisasContext *s, arg_rprr_esz *a) +{ + static gen_helper_gvec_4 * const fns[2] = { + gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d + }; + if (a->esz < 2) { + return false; + } + return do_sve2_zpzz_ool(s, a, fns[a->esz - 2]); +} + +static bool trans_HISTSEG(DisasContext *s, arg_rrr_esz *a) +{ + if (a->esz != 0) { + return false; + } + return do_sve2_zzz_ool(s, a, gen_helper_sve2_histseg); +} + static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In addition, use the same vector generator interface for AdvSIMD. This fixes a bug in which the AdvSIMD insn failed to clear the high bits of the SVE register. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-44-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 4 ++ target/arm/helper.h | 2 + target/arm/translate-a64.h | 3 ++ target/arm/sve.decode | 4 ++ target/arm/sve_helper.c | 39 ++++++++++++++ target/arm/translate-a64.c | 25 ++------- target/arm/translate-sve.c | 104 +++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 12 +++++ 8 files changed, 172 insertions(+), 21 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_histcnt_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_4(sve2_histseg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_xar_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_xar_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_xar_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ bool disas_sve(DisasContext *, uint32_t); void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, int64_t shift, + uint32_t opr_sz, uint32_t max_sz); #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rr_dbm rd rn dbm &rrri rd rn rm imm &rri_esz rd rn imm esz +&rrri_esz rd rn rm imm esz &rrr_esz rd rn rm esz &rpr_esz rd pg rn esz &rpr_s rd pg rn s @@ -XXX,XX +XXX,XX @@ ORR_zzz 00000100 01 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 EOR_zzz 00000100 10 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 BIC_zzz 00000100 11 1 ..... 001 100 ..... ..... @rd_rn_rm_e0 +XAR 00000100 .. 1 ..... 001 101 rm:5 rd:5 &rrri_esz \ + rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr + # SVE2 bitwise ternary operations EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_histseg)(void *vd, void *vn, void *vm, uint32_t desc) *(uint64_t *)(vd + i + 8) = out1; } } + +void HELPER(sve2_xar_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + int shr = simd_data(desc); + int shl = 8 - shr; + uint64_t mask = dup_const(MO_8, 0xff >> shr); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + uint64_t t = n[i] ^ m[i]; + d[i] = ((t >> shr) & mask) | ((t << shl) & ~mask); + } +} + +void HELPER(sve2_xar_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + int shr = simd_data(desc); + int shl = 16 - shr; + uint64_t mask = dup_const(MO_16, 0xffff >> shr); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + uint64_t t = n[i] ^ m[i]; + d[i] = ((t >> shr) & mask) | ((t << shl) & ~mask); + } +} + +void HELPER(sve2_xar_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 4; + int shr = simd_data(desc); + uint32_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ror32(n[i] ^ m[i], shr); + } +} diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) int imm6 = extract32(insn, 10, 6); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; - int pass; if (!dc_isar_feature(aa64_sha3, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) return; } - tcg_op1 = tcg_temp_new_i64(); - tcg_op2 = tcg_temp_new_i64(); - tcg_res[0] = tcg_temp_new_i64(); - tcg_res[1] = tcg_temp_new_i64(); - - for (pass = 0; pass < 2; pass++) { - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - - tcg_gen_xor_i64(tcg_res[pass], tcg_op1, tcg_op2); - tcg_gen_rotri_i64(tcg_res[pass], tcg_res[pass], imm6); - } - write_vec_element(s, tcg_res[0], rd, 0, MO_64); - write_vec_element(s, tcg_res[1], rd, 1, MO_64); - - tcg_temp_free_i64(tcg_op1); - tcg_temp_free_i64(tcg_op2); - tcg_temp_free_i64(tcg_res[0]); - tcg_temp_free_i64(tcg_res[1]); + gen_gvec_xar(MO_64, vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), imm6, 16, + vec_full_reg_size(s)); } /* Crypto three-reg imm2 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_BIC_zzz(DisasContext *s, arg_rrr_esz *a) return do_zzz_fn(s, a, tcg_gen_gvec_andc); } +static void gen_xar8_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + uint64_t mask = dup_const(MO_8, 0xff >> sh); + + tcg_gen_xor_i64(t, n, m); + tcg_gen_shri_i64(d, t, sh); + tcg_gen_shli_i64(t, t, 8 - sh); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_andi_i64(t, t, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_xar16_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + uint64_t mask = dup_const(MO_16, 0xffff >> sh); + + tcg_gen_xor_i64(t, n, m); + tcg_gen_shri_i64(d, t, sh); + tcg_gen_shli_i64(t, t, 16 - sh); + tcg_gen_andi_i64(d, d, mask); + tcg_gen_andi_i64(t, t, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_xar_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, int32_t sh) +{ + tcg_gen_xor_i32(d, n, m); + tcg_gen_rotri_i32(d, d, sh); +} + +static void gen_xar_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, int64_t sh) +{ + tcg_gen_xor_i64(d, n, m); + tcg_gen_rotri_i64(d, d, sh); +} + +static void gen_xar_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, int64_t sh) +{ + tcg_gen_xor_vec(vece, d, n, m); + tcg_gen_rotri_vec(vece, d, d, sh); +} + +void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, int64_t shift, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop[] = { INDEX_op_rotli_vec, 0 }; + static const GVecGen3i ops[4] = { + { .fni8 = gen_xar8_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fni8 = gen_xar16_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_xar_i32, + .fniv = gen_xar_vec, + .fno = gen_helper_sve2_xar_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_xar_i64, + .fniv = gen_xar_vec, + .fno = gen_helper_gvec_xar_d, + .opt_opc = vecop, + .vece = MO_64 } + }; + int esize = 8 << vece; + + /* The SVE2 range is 1 .. esize; the AdvSIMD range is 0 .. esize-1. */ + tcg_debug_assert(shift >= 0); + tcg_debug_assert(shift <= esize); + shift &= esize - 1; + + if (shift == 0) { + /* xar with no rotate devolves to xor. */ + tcg_gen_gvec_xor(vece, rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_3i(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, + shift, &ops[vece]); + } +} + +static bool trans_XAR(DisasContext *s, arg_rrri_esz *a) +{ + if (a->esz < 0 || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + gen_gvec_xar(a->esz, vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), a->imm, vsz, vsz); + } + return true; +} + static bool do_sve2_zzzz_fn(DisasContext *s, arg_rrrr_esz *a, GVecGen4Fn *fn) { if (!dc_isar_feature(aa64_sve2, s)) { diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_umulh_d)(void *vd, void *vn, void *vm, uint32_t desc) } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +void HELPER(gvec_xar_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + int shr = simd_data(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ror64(n[i] ^ m[i], shr); + } + clear_tail(d, opr_sz * 8, simd_maxsz(desc)); +} -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Add decoding logic for SVE2 64-bit/32-bit scatter non-temporal store insns. 64-bit * STNT1B (vector plus scalar) * STNT1H (vector plus scalar) * STNT1W (vector plus scalar) * STNT1D (vector plus scalar) 32-bit * STNT1B (vector plus scalar) * STNT1H (vector plus scalar) * STNT1W (vector plus scalar) Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-45-richard.henderson@linaro.org Message-Id: <20200422141553.8037-1-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 10 ++++++++++ target/arm/translate-sve.c | 8 ++++++++ 2 files changed, 18 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx + +### SVE2 Memory Store Group + +# SVE2 64-bit scatter non-temporal store (vector plus scalar) +STNT1_zprz 1110010 .. 00 ..... 001 ... ..... ..... \ + @rprr_scatter_store xs=2 esz=3 scale=0 + +# SVE2 32-bit scatter non-temporal store (vector plus scalar) +STNT1_zprz 1110010 .. 10 ..... 001 ... ..... ..... \ + @rprr_scatter_store xs=0 esz=2 scale=0 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a) return true; } +static bool trans_STNT1_zprz(DisasContext *s, arg_ST1_zprz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return trans_ST1_zprz(s, a); +} + /* * Prefetches */ -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Add decoding logic for SVE2 64-bit/32-bit gather non-temporal load insns. 64-bit * LDNT1SB * LDNT1B (vector plus scalar) * LDNT1SH * LDNT1H (vector plus scalar) * LDNT1SW * LDNT1W (vector plus scalar) * LDNT1D (vector plus scalar) 32-bit * LDNT1SB * LDNT1B (vector plus scalar) * LDNT1SH * LDNT1H (vector plus scalar) * LDNT1W (vector plus scalar) Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-46-richard.henderson@linaro.org Message-Id: <20200422152343.12493-1-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 11 +++++++++++ target/arm/translate-sve.c | 8 ++++++++ 2 files changed, 19 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx +### SVE2 Memory Gather Load Group + +# SVE2 64-bit gather non-temporal load +# (scalar plus unpacked 32-bit unscaled offsets) +LDNT1_zprz 1100010 msz:2 00 rm:5 1 u:1 0 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=0 esz=3 scale=0 ff=0 + +# SVE2 32-bit gather non-temporal load (scalar plus 32-bit unscaled offsets) +LDNT1_zprz 1000010 msz:2 00 rm:5 10 u:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=0 esz=2 scale=0 ff=0 + ### SVE2 Memory Store Group # SVE2 64-bit scatter non-temporal store (vector plus scalar) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a) return true; } +static bool trans_LDNT1_zprz(DisasContext *s, arg_LD1_zprz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return trans_LD1_zprz(s, a); +} + /* Indexed by [mte][be][xs][msz]. */ static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][2][2][3] = { { /* MTE Inactive */ -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-47-richard.henderson@linaro.org Message-Id: <20200422165503.13511-1-steplong@quicinc.com> [rth: Fix indexing in helpers, expand macro to straight functions.] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 ++++++ target/arm/helper-sve.h | 3 ++ target/arm/sve.decode | 4 +++ target/arm/sve_helper.c | 74 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 34 ++++++++++++++++++ 5 files changed, 125 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; } +static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx +### SVE2 floating point matrix multiply accumulate + +FMMLA 01100100 .. 1 ..... 111001 ..... ..... @rda_rn_rm + ### SVE2 Memory Gather Load Group # SVE2 64-bit gather non-temporal load diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_xar_s)(void *vd, void *vn, void *vm, uint32_t desc) d[i] = ror32(n[i] ^ m[i], shr); } } + +void HELPER(fmmla_s)(void *vd, void *vn, void *vm, void *va, + void *status, uint32_t desc) +{ + intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float32) * 4); + + for (s = 0; s < opr_sz; ++s) { + float32 *n = vn + s * sizeof(float32) * 4; + float32 *m = vm + s * sizeof(float32) * 4; + float32 *a = va + s * sizeof(float32) * 4; + float32 *d = vd + s * sizeof(float32) * 4; + float32 n00 = n[H4(0)], n01 = n[H4(1)]; + float32 n10 = n[H4(2)], n11 = n[H4(3)]; + float32 m00 = m[H4(0)], m01 = m[H4(1)]; + float32 m10 = m[H4(2)], m11 = m[H4(3)]; + float32 p0, p1; + + /* i = 0, j = 0 */ + p0 = float32_mul(n00, m00, status); + p1 = float32_mul(n01, m01, status); + d[H4(0)] = float32_add(a[H4(0)], float32_add(p0, p1, status), status); + + /* i = 0, j = 1 */ + p0 = float32_mul(n00, m10, status); + p1 = float32_mul(n01, m11, status); + d[H4(1)] = float32_add(a[H4(1)], float32_add(p0, p1, status), status); + + /* i = 1, j = 0 */ + p0 = float32_mul(n10, m00, status); + p1 = float32_mul(n11, m01, status); + d[H4(2)] = float32_add(a[H4(2)], float32_add(p0, p1, status), status); + + /* i = 1, j = 1 */ + p0 = float32_mul(n10, m10, status); + p1 = float32_mul(n11, m11, status); + d[H4(3)] = float32_add(a[H4(3)], float32_add(p0, p1, status), status); + } +} + +void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void *va, + void *status, uint32_t desc) +{ + intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float64) * 4); + + for (s = 0; s < opr_sz; ++s) { + float64 *n = vn + s * sizeof(float64) * 4; + float64 *m = vm + s * sizeof(float64) * 4; + float64 *a = va + s * sizeof(float64) * 4; + float64 *d = vd + s * sizeof(float64) * 4; + float64 n00 = n[0], n01 = n[1], n10 = n[2], n11 = n[3]; + float64 m00 = m[0], m01 = m[1], m10 = m[2], m11 = m[3]; + float64 p0, p1; + + /* i = 0, j = 0 */ + p0 = float64_mul(n00, m00, status); + p1 = float64_mul(n01, m01, status); + d[0] = float64_add(a[0], float64_add(p0, p1, status), status); + + /* i = 0, j = 1 */ + p0 = float64_mul(n00, m10, status); + p1 = float64_mul(n01, m11, status); + d[1] = float64_add(a[1], float64_add(p0, p1, status), status); + + /* i = 1, j = 0 */ + p0 = float64_mul(n10, m00, status); + p1 = float64_mul(n11, m01, status); + d[2] = float64_add(a[2], float64_add(p0, p1, status), status); + + /* i = 1, j = 1 */ + p0 = float64_mul(n10, m10, status); + p1 = float64_mul(n11, m11, status); + d[3] = float64_add(a[3], float64_add(p0, p1, status), status); + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZPZZ_FP(FMINP, fminp) * SVE Integer Multiply-Add (unpredicated) */ +static bool trans_FMMLA(DisasContext *s, arg_rrrr_esz *a) +{ + gen_helper_gvec_4_ptr *fn; + + switch (a->esz) { + case MO_32: + if (!dc_isar_feature(aa64_sve_f32mm, s)) { + return false; + } + fn = gen_helper_fmmla_s; + break; + case MO_64: + if (!dc_isar_feature(aa64_sve_f64mm, s)) { + return false; + } + fn = gen_helper_fmmla_d; + break; + default: + return false; + } + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = fpstatus_ptr(FPST_FPCR); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + static bool do_sqdmlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel1, bool sel2) { -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-48-richard.henderson@linaro.org Message-Id: <20200423180347.9403-1-steplong@quicinc.com> [rth: Rename the trans_* functions to *_sve2.] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 11 +++++++++-- target/arm/translate-sve.c | 35 ++++++++++++++++++++++++++++++----- 2 files changed, 39 insertions(+), 7 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ CPY_z_i 00000101 .. 01 .... 00 . ........ ..... @rdn_pg4 imm=%sh8_i8s ### SVE Permute - Extract Group -# SVE extract vector (immediate offset) +# SVE extract vector (destructive) EXT 00000101 001 ..... 000 ... rm:5 rd:5 \ &rrri rn=%reg_movprfx imm=%imm8_16_10 +# SVE2 extract vector (constructive) +EXT_sve2 00000101 011 ..... 000 ... rn:5 rd:5 \ + &rri imm=%imm8_16_10 + ### SVE Permute - Unpredicated Group # SVE broadcast general register @@ -XXX,XX +XXX,XX @@ REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn -# SVE vector splice (predicated) +# SVE vector splice (predicated, destructive) SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm +# SVE2 vector splice (predicated, constructive) +SPLICE_sve2 00000101 .. 101 101 100 ... ..... ..... @rd_pg_rn + ### SVE Select Vectors Group # SVE select vector elements (predicated) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_CPY_z_i(DisasContext *s, arg_CPY_z_i *a) *** SVE Permute Extract Group */ -static bool trans_EXT(DisasContext *s, arg_EXT *a) +static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm) { if (!sve_access_check(s)) { return true; } unsigned vsz = vec_full_reg_size(s); - unsigned n_ofs = a->imm >= vsz ? 0 : a->imm; + unsigned n_ofs = imm >= vsz ? 0 : imm; unsigned n_siz = vsz - n_ofs; - unsigned d = vec_full_reg_offset(s, a->rd); - unsigned n = vec_full_reg_offset(s, a->rn); - unsigned m = vec_full_reg_offset(s, a->rm); + unsigned d = vec_full_reg_offset(s, rd); + unsigned n = vec_full_reg_offset(s, rn); + unsigned m = vec_full_reg_offset(s, rm); /* Use host vector move insns if we have appropriate sizes * and no unfortunate overlap. @@ -XXX,XX +XXX,XX @@ static bool trans_EXT(DisasContext *s, arg_EXT *a) return true; } +static bool trans_EXT(DisasContext *s, arg_EXT *a) +{ + return do_EXT(s, a->rd, a->rn, a->rm, a->imm); +} + +static bool trans_EXT_sve2(DisasContext *s, arg_rri *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_EXT(s, a->rd, a->rn, (a->rn + 1) % 32, a->imm); +} + /* *** SVE Permute - Unpredicated Group */ @@ -XXX,XX +XXX,XX @@ static bool trans_SPLICE(DisasContext *s, arg_rprr_esz *a) return true; } +static bool trans_SPLICE_sve2(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzp(s, gen_helper_sve_splice, + a->rd, a->rn, (a->rn + 1) % 32, a->pg, a->esz); + } + return true; +} + /* *** SVE Integer Compare - Vectors Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The signed dot product routines produce a signed result. Since we use -fwrapv, there is no functional change. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-49-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vec_helper.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm, void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd; + int32_t *d = vd; int8_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 4; ++i) { @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc) void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd; + int64_t *d = vd; int16_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 8; ++i) { @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; intptr_t index = simd_data(desc); - uint32_t *d = vd; + int32_t *d = vd; int8_t *n = vn; int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; intptr_t index = simd_data(desc); - uint64_t *d = vd; + int64_t *d = vd; int16_t *n = vn; int16_t *m_indexed = (int16_t *)vm + index * 4; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For SVE, we potentially have a 4th argument coming from the movprfx instruction. Currently we do not optimize movprfx, so the problem is not visible. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-50-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 20 +++--- target/arm/sve.decode | 7 ++- target/arm/translate-a64.c | 15 ++++- target/arm/translate-neon.c | 10 +-- target/arm/translate-sve.c | 13 ++-- target/arm/vec_helper.c | 120 ++++++++++++++++++++---------------- 6 files changed, 109 insertions(+), 76 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s # SVE integer dot product (unpredicated) -DOT_zzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 ra=%reg_movprfx +DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \ + ra=%reg_movprfx # SVE integer dot product (indexed) -DOT_zzx 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ +DOT_zzxw 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ sz=0 ra=%reg_movprfx -DOT_zzx 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ +DOT_zzxw 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ sz=1 ra=%reg_movprfx # SVE floating-point complex add (predicated) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn, tcg_temp_free_ptr(qc_ptr); } +/* Expand a 4-operand operation using an out-of-line helper. */ +static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn, + int rm, int ra, int data, gen_helper_gvec_4 *fn) +{ + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); +} + /* Set ZF and NF based on a 64 bit result. This is alas fiddlier * than the 32 bit equivalent. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) return; case 0x2: /* SDOT / UDOT */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (16 * u + opcode) { case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ - gen_gvec_op3_ool(s, is_q, rd, rn, rm, index, + gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b); return; diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) static bool trans_VDOT(DisasContext *s, arg_VDOT *a) { int opr_sz; - gen_helper_gvec_3 *fn_gvec; + gen_helper_gvec_4 *fn_gvec; if (!dc_isar_feature(aa32_dp, s)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a) opr_sz = (1 + a->q) * 8; fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; - tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), + tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), + vfp_reg_offset(1, a->vd), opr_sz, opr_sz, 0, fn_gvec); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) { - gen_helper_gvec_3 *fn_gvec; + gen_helper_gvec_4 *fn_gvec; int opr_sz; TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; opr_sz = (1 + a->q) * 8; fpst = fpstatus_ptr(FPST_STD); - tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), + tcg_gen_gvec_4_ool(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->rm), + vfp_reg_offset(1, a->vd), opr_sz, opr_sz, a->index, fn_gvec); tcg_temp_free_ptr(fpst); return true; diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin) #undef DO_ZZI -static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a) +static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) { - static gen_helper_gvec_3 * const fns[2][2] = { + static gen_helper_gvec_4 * const fns[2][2] = { { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } }; if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, 0); + gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0); } return true; } -static bool trans_DOT_zzx(DisasContext *s, arg_DOT_zzx *a) +static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a) { - static gen_helper_gvec_3 * const fns[2][2] = { + static gen_helper_gvec_4 * const fns[2][2] = { { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h }, { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h } }; if (sve_access_check(s)) { - gen_gvec_ool_zzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, a->index); + gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, + a->ra, a->index); } return true; } diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm, * All elements are treated equally, no matter where they are. */ -void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - int32_t *d = vd; + int32_t *d = vd, *a = va; int8_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 4; ++i) { - d[i] += n[i * 4 + 0] * m[i * 4 + 0] - + n[i * 4 + 1] * m[i * 4 + 1] - + n[i * 4 + 2] * m[i * 4 + 2] - + n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + n[i * 4 + 0] * m[i * 4 + 0] + + n[i * 4 + 1] * m[i * 4 + 1] + + n[i * 4 + 2] * m[i * 4 + 2] + + n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd; + uint32_t *d = vd, *a = va; uint8_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 4; ++i) { - d[i] += n[i * 4 + 0] * m[i * 4 + 0] - + n[i * 4 + 1] * m[i * 4 + 1] - + n[i * 4 + 2] * m[i * 4 + 2] - + n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + n[i * 4 + 0] * m[i * 4 + 0] + + n[i * 4 + 1] * m[i * 4 + 1] + + n[i * 4 + 2] * m[i * 4 + 2] + + n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - int64_t *d = vd; + int64_t *d = vd, *a = va; int16_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 8; ++i) { - d[i] += (int64_t)n[i * 4 + 0] * m[i * 4 + 0] - + (int64_t)n[i * 4 + 1] * m[i * 4 + 1] - + (int64_t)n[i * 4 + 2] * m[i * 4 + 2] - + (int64_t)n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + (int64_t)n[i * 4 + 0] * m[i * 4 + 0] + + (int64_t)n[i * 4 + 1] * m[i * 4 + 1] + + (int64_t)n[i * 4 + 2] * m[i * 4 + 2] + + (int64_t)n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd; + uint64_t *d = vd, *a = va; uint16_t *n = vn, *m = vm; for (i = 0; i < opr_sz / 8; ++i) { - d[i] += (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] - + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] - + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] - + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]; + d[i] = (a[i] + + (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] + + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] + + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] + + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; intptr_t index = simd_data(desc); - int32_t *d = vd; + int32_t *d = vd, *a = va; int8_t *n = vn; int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) int8_t m3 = m_indexed[i * 4 + 3]; do { - d[i] += n[i * 4 + 0] * m0 - + n[i * 4 + 1] * m1 - + n[i * 4 + 2] * m2 - + n[i * 4 + 3] * m3; + d[i] = (a[i] + + n[i * 4 + 0] * m0 + + n[i * 4 + 1] * m1 + + n[i * 4 + 2] * m2 + + n[i * 4 + 3] * m3); } while (++i < segend); segend = i + 4; } while (i < opr_sz_4); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; intptr_t index = simd_data(desc); - uint32_t *d = vd; + uint32_t *d = vd, *a = va; uint8_t *n = vn; uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) uint8_t m3 = m_indexed[i * 4 + 3]; do { - d[i] += n[i * 4 + 0] * m0 - + n[i * 4 + 1] * m1 - + n[i * 4 + 2] * m2 - + n[i * 4 + 3] * m3; + d[i] = (a[i] + + n[i * 4 + 0] * m0 + + n[i * 4 + 1] * m1 + + n[i * 4 + 2] * m2 + + n[i * 4 + 3] * m3); } while (++i < segend); segend = i + 4; } while (i < opr_sz_4); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; intptr_t index = simd_data(desc); - int64_t *d = vd; + int64_t *d = vd, *a = va; int16_t *n = vn; int16_t *m_indexed = (int16_t *)vm + index * 4; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) * Process the entire segment all at once, writing back the results * only after we've consumed all of the inputs. */ - for (i = 0; i < opr_sz_8 ; i += 2) { - uint64_t d0, d1; + for (i = 0; i < opr_sz_8; i += 2) { + int64_t d0, d1; - d0 = n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; + d0 = a[i + 0]; + d0 += n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1]; d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2]; d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3]; - d1 = n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; + + d1 = a[i + 1]; + d1 += n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1]; d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2]; d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3]; - d[i + 0] += d0; - d[i + 1] += d1; + d[i + 0] = d0; + d[i + 1] = d1; } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; intptr_t index = simd_data(desc); - uint64_t *d = vd; + uint64_t *d = vd, *a = va; uint16_t *n = vn; uint16_t *m_indexed = (uint16_t *)vm + index * 4; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) * Process the entire segment all at once, writing back the results * only after we've consumed all of the inputs. */ - for (i = 0; i < opr_sz_8 ; i += 2) { + for (i = 0; i < opr_sz_8; i += 2) { uint64_t d0, d1; - d0 = n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; + d0 = a[i + 0]; + d0 += n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1]; d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2]; d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3]; - d1 = n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; + + d1 = a[i + 1]; + d1 += n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1]; d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2]; d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3]; - d[i + 0] += d0; - d[i + 1] += d1; + d[i + 0] = d0; + d[i + 1] = d1; } - clear_tail(d, opr_sz, simd_maxsz(desc)); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For SVE, we potentially have a 4th argument coming from the movprfx instruction. Currently we do not optimize movprfx, so the problem is not visible. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-51-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 20 +++++++-------- target/arm/translate-a64.c | 28 +++++++++++++++++---- target/arm/translate-neon.c | 10 +++++--- target/arm/translate-sve.c | 5 ++-- target/arm/vec_helper.c | 50 +++++++++++++++---------------------- 5 files changed, 62 insertions(+), 51 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlah, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlah_idx, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlas, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn, is_q ? 16 : 8, vec_full_reg_size(s), data, fn); } +/* + * Expand a 4-operand + fpstatus pointer + simd data value operation using + * an out-of-line helper. + */ +static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn, + int rm, int ra, bool is_fp16, int data, + gen_helper_gvec_4_ptr *fn) +{ + TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), fpst, + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); + tcg_temp_free_ptr(fpst); +} + /* Set ZF and NF based on a 64 bit result. This is alas fiddlier * than the 32 bit equivalent. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) rot = extract32(opcode, 0, 2); switch (size) { case 1: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, true, rot, + gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, true, rot, gen_helper_gvec_fcmlah); break; case 2: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot, + gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot, gen_helper_gvec_fcmlas); break; case 3: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot, + gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot, gen_helper_gvec_fcmlad); break; default: @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) { int rot = extract32(insn, 13, 2); int data = (index << 2) | rot; - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), fpst, + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, rd), fpst, is_q ? 16 : 8, vec_full_reg_size(s), data, size == MO_64 ? gen_helper_gvec_fcmlas_idx diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) { int opr_sz; TCGv_ptr fpst; - gen_helper_gvec_3_ptr *fn_gvec_ptr; + gen_helper_gvec_4_ptr *fn_gvec_ptr; if (!dc_isar_feature(aa32_vcma, s) || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); fn_gvec_ptr = (a->size == MO_16) ? gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas; - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), + vfp_reg_offset(1, a->vd), fpst, opr_sz, opr_sz, a->rot, fn_gvec_ptr); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VFML(DisasContext *s, arg_VFML *a) static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) { - gen_helper_gvec_3_ptr *fn_gvec_ptr; + gen_helper_gvec_4_ptr *fn_gvec_ptr; int opr_sz; TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx; opr_sz = (1 + a->q) * 8; fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), + vfp_reg_offset(1, a->vd), fpst, opr_sz, opr_sz, (a->index << 2) | a->rot, fn_gvec_ptr); tcg_temp_free_ptr(fpst); diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a) static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a) { - static gen_helper_gvec_3_ptr * const fns[2] = { + static gen_helper_gvec_4_ptr * const fns[2] = { gen_helper_gvec_fcmlah_idx, gen_helper_gvec_fcmlas_idx, }; @@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a) if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), status, vsz, vsz, a->index * 4 + a->rot, fns[a->esz - 1]); diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float16 *d = vd; - float16 *n = vn; - float16 *m = vm; + float16 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, float16 e4 = e2; float16 e3 = m[H2(i + 1 - flip)] ^ neg_imag; - d[H2(i)] = float16_muladd(e2, e1, d[H2(i)], 0, fpst); - d[H2(i + 1)] = float16_muladd(e4, e3, d[H2(i + 1)], 0, fpst); + d[H2(i)] = float16_muladd(e2, e1, a[H2(i)], 0, fpst); + d[H2(i + 1)] = float16_muladd(e4, e3, a[H2(i + 1)], 0, fpst); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float16 *d = vd; - float16 *n = vn; - float16 *m = vm; + float16 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, float16 e2 = n[H2(j + flip)]; float16 e4 = e2; - d[H2(j)] = float16_muladd(e2, e1, d[H2(j)], 0, fpst); - d[H2(j + 1)] = float16_muladd(e4, e3, d[H2(j + 1)], 0, fpst); + d[H2(j)] = float16_muladd(e2, e1, a[H2(j)], 0, fpst); + d[H2(j + 1)] = float16_muladd(e4, e3, a[H2(j + 1)], 0, fpst); } } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float32 *d = vd; - float32 *n = vn; - float32 *m = vm; + float32 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, float32 e4 = e2; float32 e3 = m[H4(i + 1 - flip)] ^ neg_imag; - d[H4(i)] = float32_muladd(e2, e1, d[H4(i)], 0, fpst); - d[H4(i + 1)] = float32_muladd(e4, e3, d[H4(i + 1)], 0, fpst); + d[H4(i)] = float32_muladd(e2, e1, a[H4(i)], 0, fpst); + d[H4(i + 1)] = float32_muladd(e4, e3, a[H4(i + 1)], 0, fpst); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float32 *d = vd; - float32 *n = vn; - float32 *m = vm; + float32 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, float32 e2 = n[H4(j + flip)]; float32 e4 = e2; - d[H4(j)] = float32_muladd(e2, e1, d[H4(j)], 0, fpst); - d[H4(j + 1)] = float32_muladd(e4, e3, d[H4(j + 1)], 0, fpst); + d[H4(j)] = float32_muladd(e2, e1, a[H4(j)], 0, fpst); + d[H4(j + 1)] = float32_muladd(e4, e3, a[H4(j + 1)], 0, fpst); } } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, +void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, void *va, void *vfpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); - float64 *d = vd; - float64 *n = vn; - float64 *m = vm; + float64 *d = vd, *n = vn, *m = vm, *a = va; float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint64_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, float64 e4 = e2; float64 e3 = m[i + 1 - flip] ^ neg_imag; - d[i] = float64_muladd(e2, e1, d[i], 0, fpst); - d[i + 1] = float64_muladd(e4, e3, d[i + 1], 0, fpst); + d[i] = float64_muladd(e2, e1, a[i], 0, fpst); + d[i + 1] = float64_muladd(e4, e3, a[i + 1], 0, fpst); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Currently only used by FMUL, but will shortly be used more. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-52-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rri_esz rd rn imm esz &rrri_esz rd rn rm imm esz &rrr_esz rd rn rm esz +&rrx_esz rd rn rm index esz &rpr_esz rd pg rn esz &rpr_s rd pg rn s &rprr_s rd pg rn rm s @@ -XXX,XX +XXX,XX @@ @rpri_scatter_store ....... msz:2 .. imm:5 ... pg:3 rn:5 rd:5 \ &rpri_scatter_store +# Two registers and a scalar by N-bit index +@rrx_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \ + &rrx_esz index=%index3_22_19 +@rrx_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 &rrx_esz +@rrx_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 &rrx_esz + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ FMLA_zzxz 01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \ ### SVE FP Multiply Indexed Group # SVE floating-point multiply (indexed) -FMUL_zzx 01100100 0.1 .. rm:3 001000 rn:5 rd:5 \ - index=%index3_22_19 esz=1 -FMUL_zzx 01100100 101 index:2 rm:3 001000 rn:5 rd:5 esz=2 -FMUL_zzx 01100100 111 index:1 rm:4 001000 rn:5 rd:5 esz=3 +FMUL_zzx 01100100 0. 1 ..... 001000 ..... ..... @rrx_3 esz=1 +FMUL_zzx 01100100 10 1 ..... 001000 ..... ..... @rrx_2 esz=2 +FMUL_zzx 01100100 11 1 ..... 001000 ..... ..... @rrx_1 esz=3 ### SVE FP Fast Reduction Group -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Used by FMLA and DOT, but will shortly be used more. Split FMLA from FMLS to avoid an extra sub field; similarly for SDOT from UDOT. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-53-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 29 +++++++++++++++++++---------- target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++---------- 2 files changed, 47 insertions(+), 20 deletions(-) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rprr_s rd pg rn rm s &rprr_esz rd pg rn rm esz &rrrr_esz rd ra rn rm esz +&rrxr_esz rd rn rm ra index esz &rprrr_esz rd pg rn rm ra esz &rpri_esz rd pg rn imm esz &ptrue rd esz pat s @@ -XXX,XX +XXX,XX @@ @rrx_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 &rrx_esz @rrx_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 &rrx_esz +# Three registers and a scalar by N-bit index +@rrxr_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx index=%index3_22_19 +@rrxr_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx +@rrxr_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \ ra=%reg_movprfx # SVE integer dot product (indexed) -DOT_zzxw 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ - sz=0 ra=%reg_movprfx -DOT_zzxw 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ - sz=1 ra=%reg_movprfx +SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 +SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 +UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 # SVE floating-point complex add (predicated) FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ @@ -XXX,XX +XXX,XX @@ FCMLA_zzxz 01100100 11 1 index:1 rm:4 0001 rot:2 rn:5 rd:5 \ ### SVE FP Multiply-Add Indexed Group # SVE floating-point multiply-add (indexed) -FMLA_zzxz 01100100 0.1 .. rm:3 00000 sub:1 rn:5 rd:5 \ - ra=%reg_movprfx index=%index3_22_19 esz=1 -FMLA_zzxz 01100100 101 index:2 rm:3 00000 sub:1 rn:5 rd:5 \ - ra=%reg_movprfx esz=2 -FMLA_zzxz 01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \ - ra=%reg_movprfx esz=3 +FMLA_zzxz 01100100 0. 1 ..... 000000 ..... ..... @rrxr_3 esz=1 +FMLA_zzxz 01100100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 +FMLA_zzxz 01100100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 +FMLS_zzxz 01100100 0. 1 ..... 000001 ..... ..... @rrxr_3 esz=1 +FMLS_zzxz 01100100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 +FMLS_zzxz 01100100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 ### SVE FP Multiply Indexed Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) return true; } -static bool trans_DOT_zzxw(DisasContext *s, arg_DOT_zzxw *a) +static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a, + gen_helper_gvec_4 *fn) { - static gen_helper_gvec_4 * const fns[2][2] = { - { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h }, - { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h } - }; - + if (fn == NULL) { + return false; + } if (sve_access_check(s)) { - gen_gvec_ool_zzzz(s, fns[a->u][a->sz], a->rd, a->rn, a->rm, - a->ra, a->index); + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->index); } return true; } +#define DO_RRXR(NAME, FUNC) \ + static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ + { return do_zzxz_ool(s, a, FUNC); } + +DO_RRXR(trans_SDOT_zzxw_s, gen_helper_gvec_sdot_idx_b) +DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h) +DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b) +DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h) + +#undef DO_RRXR /* *** SVE Floating Point Multiply-Add Indexed Group */ -static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) +static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub) { static gen_helper_gvec_4_ptr * const fns[3] = { gen_helper_gvec_fmla_idx_h, @@ -XXX,XX +XXX,XX @@ static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) vec_full_reg_offset(s, a->rn), vec_full_reg_offset(s, a->rm), vec_full_reg_offset(s, a->ra), - status, vsz, vsz, (a->index << 1) | a->sub, + status, vsz, vsz, (a->index << 1) | sub, fns[a->esz - 1]); tcg_temp_free_ptr(status); } return true; } +static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a) +{ + return do_FMLA_zzxz(s, a, false); +} + +static bool trans_FMLS_zzxz(DisasContext *s, arg_FMLA_zzxz *a) +{ + return do_FMLA_zzxz(s, a, true); +} + /* *** SVE Floating Point Multiply Indexed Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-54-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 7 +++++++ target/arm/translate-sve.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \ ra=%reg_movprfx +#### SVE Multiply - Indexed + # SVE integer dot product (indexed) SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 +# SVE2 integer multiply (indexed) +MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 +MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 +MUL_zzx_d 01000100 11 1 ..... 111110 ..... ..... @rrx_1 esz=3 + # SVE floating-point complex add (predicated) FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ rn=%reg_movprfx diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzzz(DisasContext *s, arg_DOT_zzzz *a) return true; } +/* + * SVE Multiply - Indexed + */ + static bool do_zzxz_ool(DisasContext *s, arg_rrxr_esz *a, gen_helper_gvec_4 *fn) { @@ -XXX,XX +XXX,XX @@ DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h) #undef DO_RRXR +static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data, + gen_helper_gvec_3 *fn) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vsz, vsz, data, fn); + } + return true; +} + +#define DO_SVE2_RRX(NAME, FUNC) \ + static bool NAME(DisasContext *s, arg_rrx_esz *a) \ + { return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, a->index, FUNC); } + +DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h) +DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s) +DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d) + +#undef DO_SVE2_RRX + /* *** SVE Floating Point Multiply-Add Indexed Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-55-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 8 ++++++++ target/arm/translate-sve.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 +# SVE2 integer multiply-add (indexed) +MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1 +MLA_zzxz_s 01000100 10 1 ..... 000010 ..... ..... @rrxr_2 esz=2 +MLA_zzxz_d 01000100 11 1 ..... 000010 ..... ..... @rrxr_1 esz=3 +MLS_zzxz_h 01000100 0. 1 ..... 000011 ..... ..... @rrxr_3 esz=1 +MLS_zzxz_s 01000100 10 1 ..... 000011 ..... ..... @rrxr_2 esz=2 +MLS_zzxz_d 01000100 11 1 ..... 000011 ..... ..... @rrxr_1 esz=3 + # SVE2 integer multiply (indexed) MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d) #undef DO_SVE2_RRX +static bool do_sve2_zzzz_data(DisasContext *s, int rd, int rn, int rm, int ra, + int data, gen_helper_gvec_4 *fn) +{ + if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + vec_full_reg_offset(s, ra), + vsz, vsz, data, fn); + } + return true; +} + +#define DO_SVE2_RRXR(NAME, FUNC) \ + static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ + { return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, a->index, FUNC); } + +DO_SVE2_RRXR(trans_MLA_zzxz_h, gen_helper_gvec_mla_idx_h) +DO_SVE2_RRXR(trans_MLA_zzxz_s, gen_helper_gvec_mla_idx_s) +DO_SVE2_RRXR(trans_MLA_zzxz_d, gen_helper_gvec_mla_idx_d) + +DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h) +DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s) +DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d) + +#undef DO_SVE2_RRXR + /* *** SVE Floating Point Multiply-Add Indexed Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-56-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 ++++++++++++++ target/arm/sve.decode | 8 ++++++++ target/arm/sve_helper.c | 36 ++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 8 ++++++++ 4 files changed, 66 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ MLS_zzxz_h 01000100 0. 1 ..... 000011 ..... ..... @rrxr_3 esz=1 MLS_zzxz_s 01000100 10 1 ..... 000011 ..... ..... @rrxr_2 esz=2 MLS_zzxz_d 01000100 11 1 ..... 000011 ..... ..... @rrxr_1 esz=3 +# SVE2 saturating multiply-add high (indexed) +SQRDMLAH_zzxz_h 01000100 0. 1 ..... 000100 ..... ..... @rrxr_3 esz=1 +SQRDMLAH_zzxz_s 01000100 10 1 ..... 000100 ..... ..... @rrxr_2 esz=2 +SQRDMLAH_zzxz_d 01000100 11 1 ..... 000100 ..... ..... @rrxr_1 esz=3 +SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... ..... @rrxr_3 esz=1 +SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2 +SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3 + # SVE2 integer multiply (indexed) MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_d, int64_t, , DO_SQRDMLAH_D) #undef DO_SQRDMLAH_S #undef DO_SQRDMLAH_D +#define DO_ZZXZ(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, idx = simd_data(desc); \ + TYPE *d = vd, *a = va, *n = vn, *m = (TYPE *)vm + H(idx); \ + for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ + TYPE mm = m[i]; \ + for (j = 0; j < segment; j++) { \ + d[i + j] = OP(n[i + j], mm, a[i + j]); \ + } \ + } \ +} + +#define DO_SQRDMLAH_H(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_h(N, M, A, false, true, &discard); }) +#define DO_SQRDMLAH_S(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_s(N, M, A, false, true, &discard); }) +#define DO_SQRDMLAH_D(N, M, A) do_sqrdmlah_d(N, M, A, false, true) + +DO_ZZXZ(sve2_sqrdmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H) +DO_ZZXZ(sve2_sqrdmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S) +DO_ZZXZ(sve2_sqrdmlah_idx_d, int64_t, , DO_SQRDMLAH_D) + +#define DO_SQRDMLSH_H(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_h(N, M, A, true, true, &discard); }) +#define DO_SQRDMLSH_S(N, M, A) \ + ({ uint32_t discard; do_sqrdmlah_s(N, M, A, true, true, &discard); }) +#define DO_SQRDMLSH_D(N, M, A) do_sqrdmlah_d(N, M, A, true, true) + +DO_ZZXZ(sve2_sqrdmlsh_idx_h, int16_t, H2, DO_SQRDMLSH_H) +DO_ZZXZ(sve2_sqrdmlsh_idx_s, int32_t, H4, DO_SQRDMLSH_S) +DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t, , DO_SQRDMLSH_D) + +#undef DO_ZZXZ + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h) DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s) DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d) +DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h) +DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s) +DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d) + +DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h) +DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s) +DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d) + #undef DO_SVE2_RRXR /* -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-57-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 9 +++++++++ target/arm/sve.decode | 18 ++++++++++++++++++ target/arm/sve_helper.c | 30 ++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 19 +++++++++++++++++++ 4 files changed, 76 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlal_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ %size_23 23:2 %dtype_23_13 23:2 13:2 %index3_22_19 22:1 19:2 +%index3_19_11 19:2 11:1 +%index2_20_11 20:1 11:1 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=tszimm_esz @@ -XXX,XX +XXX,XX @@ @rrxr_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 \ &rrxr_esz ra=%reg_movprfx +# Three registers and a scalar by N-bit index, alternate +@rrxr_3a ........ .. ... rm:3 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx index=%index3_19_11 +@rrxr_2a ........ .. .. rm:4 ...... rn:5 rd:5 \ + &rrxr_esz ra=%reg_movprfx index=%index2_20_11 + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... ..... @rrxr_3 esz=1 SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3 +# SVE2 saturating multiply-add (indexed) +SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2 +SQDMLALB_zzxw_d 01000100 11 1 ..... 0010.0 ..... ..... @rrxr_2a esz=3 +SQDMLALT_zzxw_s 01000100 10 1 ..... 0010.1 ..... ..... @rrxr_3a esz=2 +SQDMLALT_zzxw_d 01000100 11 1 ..... 0010.1 ..... ..... @rrxr_2a esz=3 +SQDMLSLB_zzxw_s 01000100 10 1 ..... 0011.0 ..... ..... @rrxr_3a esz=2 +SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... ..... @rrxr_2a esz=3 +SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2 +SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3 + # SVE2 integer multiply (indexed) MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t, , DO_SQRDMLSH_D) #undef DO_ZZXZ +#define DO_ZZXW(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3) * sizeof(TYPEN); \ + for (i = 0; i < oprsz; i += 16) { \ + TYPEW mm = *(TYPEN *)(vm + HN(i + idx)); \ + for (j = 0; j < 16; j += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel)); \ + TYPEW aa = *(TYPEW *)(va + HW(i + j)); \ + *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm, aa); \ + } \ + } \ +} + +#define DO_SQDMLAL_S(N, M, A) DO_SQADD_S(A, do_sqdmull_s(N, M)) +#define DO_SQDMLAL_D(N, M, A) do_sqadd_d(A, do_sqdmull_d(N, M)) + +DO_ZZXW(sve2_sqdmlal_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLAL_S) +DO_ZZXW(sve2_sqdmlal_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLAL_D) + +#define DO_SQDMLSL_S(N, M, A) DO_SQSUB_S(A, do_sqdmull_s(N, M)) +#define DO_SQDMLSL_D(N, M, A) do_sqsub_d(A, do_sqdmull_d(N, M)) + +DO_ZZXW(sve2_sqdmlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLSL_S) +DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLSL_D) + +#undef DO_ZZXW + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d) #undef DO_SVE2_RRXR +#define DO_SVE2_RRXR_TB(NAME, FUNC, TOP) \ + static bool NAME(DisasContext *s, arg_rrxr_esz *a) \ + { \ + return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->rd, \ + (a->index << 1) | TOP, FUNC); \ + } + +DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, false) +DO_SVE2_RRXR_TB(trans_SQDMLALB_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, false) +DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_s, gen_helper_sve2_sqdmlal_idx_s, true) +DO_SVE2_RRXR_TB(trans_SQDMLALT_zzxw_d, gen_helper_sve2_sqdmlal_idx_d, true) + +DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, false) +DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false) +DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true) +DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true) + +#undef DO_SVE2_RRXR_TB + /* *** SVE Floating Point Multiply-Add Indexed Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-58-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 5 +++++ target/arm/sve.decode | 12 ++++++++++++ target/arm/sve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-sve.c | 14 ++++++++++++++ 4 files changed, 51 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @rrx_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 &rrx_esz @rrx_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 &rrx_esz +# Two registers and a scalar by N-bit index, alternate +@rrx_3a ........ .. . .. rm:3 ...... rn:5 rd:5 \ + &rrx_esz index=%index3_19_11 +@rrx_2a ........ .. . . rm:4 ...... rn:5 rd:5 \ + &rrx_esz index=%index2_20_11 + # Three registers and a scalar by N-bit index @rrxr_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \ &rrxr_esz ra=%reg_movprfx index=%index3_22_19 @@ -XXX,XX +XXX,XX @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... ..... @rrxr_2a esz=3 SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2 SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3 +# SVE2 saturating multiply (indexed) +SQDMULLB_zzx_s 01000100 10 1 ..... 1110.0 ..... ..... @rrx_3a esz=2 +SQDMULLB_zzx_d 01000100 11 1 ..... 1110.0 ..... ..... @rrx_2a esz=3 +SQDMULLT_zzx_s 01000100 10 1 ..... 1110.1 ..... ..... @rrx_3a esz=2 +SQDMULLT_zzx_d 01000100 11 1 ..... 1110.1 ..... ..... @rrx_2a esz=3 + # SVE2 integer multiply (indexed) MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLSL_D) #undef DO_ZZXW +#define DO_ZZX(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3) * sizeof(TYPEN); \ + for (i = 0; i < oprsz; i += 16) { \ + TYPEW mm = *(TYPEN *)(vm + HN(i + idx)); \ + for (j = 0; j < 16; j += sizeof(TYPEW)) { \ + TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel)); \ + *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm); \ + } \ + } \ +} + +DO_ZZX(sve2_sqdmull_idx_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s) +DO_ZZX(sve2_sqdmull_idx_d, int64_t, int32_t, , H1_4, do_sqdmull_d) + +#undef DO_ZZX + #define DO_BITPERM(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d) #undef DO_SVE2_RRX +#define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \ + static bool NAME(DisasContext *s, arg_rrx_esz *a) \ + { \ + return do_sve2_zzz_data(s, a->rd, a->rn, a->rm, \ + (a->index << 1) | TOP, FUNC); \ + } + +DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_s, gen_helper_sve2_sqdmull_idx_s, false) +DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_d, gen_helper_sve2_sqdmull_idx_d, false) +DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_s, gen_helper_sve2_sqdmull_idx_s, true) +DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_d, gen_helper_sve2_sqdmull_idx_d, true) + +#undef DO_SVE2_RRX_TB + static bool do_sve2_zzzz_data(DisasContext *s, int rd, int rn, int rm, int ra, int data, gen_helper_gvec_4 *fn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-59-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 +++++ target/arm/sve.decode | 4 ++ target/arm/translate-sve.c | 18 ++++++++ target/arm/vec_helper.c | 84 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 116 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_sqrdmulh_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(neon_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) #ifdef TARGET_AARCH64 diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SMULH_zzz 00000100 .. 1 ..... 0110 10 ..... ..... @rd_rn_rm UMULH_zzz 00000100 .. 1 ..... 0110 11 ..... ..... @rd_rn_rm PMUL_zzz 00000100 00 1 ..... 0110 01 ..... ..... @rd_rn_rm_e0 +# SVE2 signed saturating doubling multiply high (unpredicated) +SQDMULH_zzz 00000100 .. 1 ..... 0111 00 ..... ..... @rd_rn_rm +SQRDMULH_zzz 00000100 .. 1 ..... 0111 01 ..... ..... @rd_rn_rm + ### SVE2 Integer - Predicated SADALP_zpzz 01000100 .. 000 100 101 ... ..... ..... @rdm_pg_rn diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a) return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b); } +static bool trans_SQDMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, + gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + +static bool trans_SQRDMULH_zzz(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h, + gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d, + }; + return do_sve2_zzz_ool(s, a, fns[a->esz]); +} + /* * SVE2 Integer - Predicated */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm, } } +void HELPER(sve2_sqdmulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], 0, false, false); + } +} + +void HELPER(sve2_sqrdmulh_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + d[i] = do_sqrdmlah_b(n[i], m[i], 0, false, true); + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3, bool neg, bool round, uint32_t *sat) @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm, } } +void HELPER(sve2_sqdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, false, &discard); + } +} + +void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + uint32_t discard; + + for (i = 0; i < opr_sz / 2; ++i) { + d[i] = do_sqrdmlah_h(n[i], m[i], 0, false, true, &discard); + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */ int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, bool neg, bool round, uint32_t *sat) @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_s)(void *vd, void *vn, void *vm, } } +void HELPER(sve2_sqdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int32_t *d = vd, *n = vn, *m = vm; + uint32_t discard; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, false, &discard); + } +} + +void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int32_t *d = vd, *n = vn, *m = vm; + uint32_t discard; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = do_sqrdmlah_s(n[i], m[i], 0, false, true, &discard); + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */ static int64_t do_sat128_d(Int128 r) { @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmlsh_d)(void *vd, void *vn, void *vm, } } +void HELPER(sve2_sqdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, false); + } +} + +void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = do_sqrdmlah_d(n[i], m[i], 0, false, true); + } +} + /* Integer 8 and 16-bit dot-product. * * Note that for the loops herein, host endianness does not matter -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-60-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 14 ++++++ target/arm/sve.decode | 8 ++++ target/arm/translate-sve.c | 8 ++++ target/arm/vec_helper.c | 88 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 118 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) #ifdef TARGET_AARCH64 diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQDMULLB_zzx_d 01000100 11 1 ..... 1110.0 ..... ..... @rrx_2a esz=3 SQDMULLT_zzx_s 01000100 10 1 ..... 1110.1 ..... ..... @rrx_3a esz=2 SQDMULLT_zzx_d 01000100 11 1 ..... 1110.1 ..... ..... @rrx_2a esz=3 +# SVE2 saturating multiply high (indexed) +SQDMULH_zzx_h 01000100 0. 1 ..... 111100 ..... ..... @rrx_3 esz=1 +SQDMULH_zzx_s 01000100 10 1 ..... 111100 ..... ..... @rrx_2 esz=2 +SQDMULH_zzx_d 01000100 11 1 ..... 111100 ..... ..... @rrx_1 esz=3 +SQRDMULH_zzx_h 01000100 0. 1 ..... 111101 ..... ..... @rrx_3 esz=1 +SQRDMULH_zzx_s 01000100 10 1 ..... 111101 ..... ..... @rrx_2 esz=2 +SQRDMULH_zzx_d 01000100 11 1 ..... 111101 ..... ..... @rrx_1 esz=3 + # SVE2 integer multiply (indexed) MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1 MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h) DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s) DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d) +DO_SVE2_RRX(trans_SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h) +DO_SVE2_RRX(trans_SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s) +DO_SVE2_RRX(trans_SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d) + +DO_SVE2_RRX(trans_SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h) +DO_SVE2_RRX(trans_SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s) +DO_SVE2_RRX(trans_SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d) + #undef DO_SVE2_RRX #define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm, uint32_t desc) } } +void HELPER(sve2_sqdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 2; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < 16 / 2; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, &discard); + } + } +} + +void HELPER(sve2_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 2; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < 16 / 2; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, &discard); + } + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */ int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3, bool neg, bool round, uint32_t *sat) @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm, uint32_t desc) } } +void HELPER(sve2_sqdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 4; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < 16 / 4; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, &discard); + } + } +} + +void HELPER(sve2_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + uint32_t discard; + + for (i = 0; i < opr_sz / 4; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < 16 / 4; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, &discard); + } + } +} + /* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */ static int64_t do_sat128_d(Int128 r) { @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm, uint32_t desc) } } +void HELPER(sve2_sqdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx; + + for (i = 0; i < opr_sz / 8; i += 16 / 8) { + int64_t mm = m[i]; + for (j = 0; j < 16 / 8; ++j) { + d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, false); + } + } +} + +void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx; + + for (i = 0; i < opr_sz / 8; i += 16 / 8) { + int64_t mm = m[i]; + for (j = 0; j < 16 / 8; ++j) { + d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, true); + } + } +} + /* Integer 8 and 16-bit dot-product. * * Note that for the loops herein, host endianness does not matter -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-61-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 17 +++++++++++++++++ target/arm/sve.decode | 18 ++++++++++++++++++ target/arm/sve_helper.c | 16 ++++++++++++++++ target/arm/translate-sve.c | 20 ++++++++++++++++++++ 4 files changed, 71 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_smlal_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlal_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_smlsl_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlal_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_umlsl_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... ..... @rrxr_2a esz=3 SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2 SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3 +# SVE2 multiply-add long (indexed) +SMLALB_zzxw_s 01000100 10 1 ..... 1000.0 ..... ..... @rrxr_3a esz=2 +SMLALB_zzxw_d 01000100 11 1 ..... 1000.0 ..... ..... @rrxr_2a esz=3 +SMLALT_zzxw_s 01000100 10 1 ..... 1000.1 ..... ..... @rrxr_3a esz=2 +SMLALT_zzxw_d 01000100 11 1 ..... 1000.1 ..... ..... @rrxr_2a esz=3 +UMLALB_zzxw_s 01000100 10 1 ..... 1001.0 ..... ..... @rrxr_3a esz=2 +UMLALB_zzxw_d 01000100 11 1 ..... 1001.0 ..... ..... @rrxr_2a esz=3 +UMLALT_zzxw_s 01000100 10 1 ..... 1001.1 ..... ..... @rrxr_3a esz=2 +UMLALT_zzxw_d 01000100 11 1 ..... 1001.1 ..... ..... @rrxr_2a esz=3 +SMLSLB_zzxw_s 01000100 10 1 ..... 1010.0 ..... ..... @rrxr_3a esz=2 +SMLSLB_zzxw_d 01000100 11 1 ..... 1010.0 ..... ..... @rrxr_2a esz=3 +SMLSLT_zzxw_s 01000100 10 1 ..... 1010.1 ..... ..... @rrxr_3a esz=2 +SMLSLT_zzxw_d 01000100 11 1 ..... 1010.1 ..... ..... @rrxr_2a esz=3 +UMLSLB_zzxw_s 01000100 10 1 ..... 1011.0 ..... ..... @rrxr_3a esz=2 +UMLSLB_zzxw_d 01000100 11 1 ..... 1011.0 ..... ..... @rrxr_2a esz=3 +UMLSLT_zzxw_s 01000100 10 1 ..... 1011.1 ..... ..... @rrxr_3a esz=2 +UMLSLT_zzxw_d 01000100 11 1 ..... 1011.1 ..... ..... @rrxr_2a esz=3 + # SVE2 saturating multiply (indexed) SQDMULLB_zzx_s 01000100 10 1 ..... 1110.0 ..... ..... @rrx_3a esz=2 SQDMULLB_zzx_d 01000100 11 1 ..... 1110.0 ..... ..... @rrx_2a esz=3 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ } \ } +#define DO_MLA(N, M, A) (A + N * M) + +DO_ZZXW(sve2_smlal_idx_s, int32_t, int16_t, H1_4, H1_2, DO_MLA) +DO_ZZXW(sve2_smlal_idx_d, int64_t, int32_t, , H1_4, DO_MLA) +DO_ZZXW(sve2_umlal_idx_s, uint32_t, uint16_t, H1_4, H1_2, DO_MLA) +DO_ZZXW(sve2_umlal_idx_d, uint64_t, uint32_t, , H1_4, DO_MLA) + +#define DO_MLS(N, M, A) (A - N * M) + +DO_ZZXW(sve2_smlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_MLS) +DO_ZZXW(sve2_smlsl_idx_d, int64_t, int32_t, , H1_4, DO_MLS) +DO_ZZXW(sve2_umlsl_idx_s, uint32_t, uint16_t, H1_4, H1_2, DO_MLS) +DO_ZZXW(sve2_umlsl_idx_d, uint64_t, uint32_t, , H1_4, DO_MLS) + #define DO_SQDMLAL_S(N, M, A) DO_SQADD_S(A, do_sqdmull_s(N, M)) #define DO_SQDMLAL_D(N, M, A) do_sqadd_d(A, do_sqdmull_d(N, M)) @@ -XXX,XX +XXX,XX @@ DO_ZZXW(sve2_sqdmlal_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLAL_D) DO_ZZXW(sve2_sqdmlsl_idx_s, int32_t, int16_t, H1_4, H1_2, DO_SQDMLSL_S) DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t, , H1_4, DO_SQDMLSL_D) +#undef DO_MLA +#undef DO_MLS #undef DO_ZZXW #define DO_ZZX(NAME, TYPEW, TYPEN, HW, HN, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR_TB(trans_SQDMLSLB_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, false) DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_s, gen_helper_sve2_sqdmlsl_idx_s, true) DO_SVE2_RRXR_TB(trans_SQDMLSLT_zzxw_d, gen_helper_sve2_sqdmlsl_idx_d, true) +DO_SVE2_RRXR_TB(trans_SMLALB_zzxw_s, gen_helper_sve2_smlal_idx_s, false) +DO_SVE2_RRXR_TB(trans_SMLALB_zzxw_d, gen_helper_sve2_smlal_idx_d, false) +DO_SVE2_RRXR_TB(trans_SMLALT_zzxw_s, gen_helper_sve2_smlal_idx_s, true) +DO_SVE2_RRXR_TB(trans_SMLALT_zzxw_d, gen_helper_sve2_smlal_idx_d, true) + +DO_SVE2_RRXR_TB(trans_UMLALB_zzxw_s, gen_helper_sve2_umlal_idx_s, false) +DO_SVE2_RRXR_TB(trans_UMLALB_zzxw_d, gen_helper_sve2_umlal_idx_d, false) +DO_SVE2_RRXR_TB(trans_UMLALT_zzxw_s, gen_helper_sve2_umlal_idx_s, true) +DO_SVE2_RRXR_TB(trans_UMLALT_zzxw_d, gen_helper_sve2_umlal_idx_d, true) + +DO_SVE2_RRXR_TB(trans_SMLSLB_zzxw_s, gen_helper_sve2_smlsl_idx_s, false) +DO_SVE2_RRXR_TB(trans_SMLSLB_zzxw_d, gen_helper_sve2_smlsl_idx_d, false) +DO_SVE2_RRXR_TB(trans_SMLSLT_zzxw_s, gen_helper_sve2_smlsl_idx_s, true) +DO_SVE2_RRXR_TB(trans_SMLSLT_zzxw_d, gen_helper_sve2_smlsl_idx_d, true) + +DO_SVE2_RRXR_TB(trans_UMLSLB_zzxw_s, gen_helper_sve2_umlsl_idx_s, false) +DO_SVE2_RRXR_TB(trans_UMLSLB_zzxw_d, gen_helper_sve2_umlsl_idx_d, false) +DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_s, gen_helper_sve2_umlsl_idx_s, true) +DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_d, gen_helper_sve2_umlsl_idx_d, true) + #undef DO_SVE2_RRXR_TB /* -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-62-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 5 +++++ target/arm/sve.decode | 10 ++++++++++ target/arm/sve_helper.c | 6 ++++++ target/arm/translate-sve.c | 10 ++++++++++ 4 files changed, 31 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_umlsl_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_umlsl_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_smull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_smull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_umull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMLSLB_zzxw_d 01000100 11 1 ..... 1011.0 ..... ..... @rrxr_2a esz=3 UMLSLT_zzxw_s 01000100 10 1 ..... 1011.1 ..... ..... @rrxr_3a esz=2 UMLSLT_zzxw_d 01000100 11 1 ..... 1011.1 ..... ..... @rrxr_2a esz=3 +# SVE2 integer multiply long (indexed) +SMULLB_zzx_s 01000100 10 1 ..... 1100.0 ..... ..... @rrx_3a esz=2 +SMULLB_zzx_d 01000100 11 1 ..... 1100.0 ..... ..... @rrx_2a esz=3 +SMULLT_zzx_s 01000100 10 1 ..... 1100.1 ..... ..... @rrx_3a esz=2 +SMULLT_zzx_d 01000100 11 1 ..... 1100.1 ..... ..... @rrx_2a esz=3 +UMULLB_zzx_s 01000100 10 1 ..... 1101.0 ..... ..... @rrx_3a esz=2 +UMULLB_zzx_d 01000100 11 1 ..... 1101.0 ..... ..... @rrx_2a esz=3 +UMULLT_zzx_s 01000100 10 1 ..... 1101.1 ..... ..... @rrx_3a esz=2 +UMULLT_zzx_d 01000100 11 1 ..... 1101.1 ..... ..... @rrx_2a esz=3 + # SVE2 saturating multiply (indexed) SQDMULLB_zzx_s 01000100 10 1 ..... 1110.0 ..... ..... @rrx_3a esz=2 SQDMULLB_zzx_d 01000100 11 1 ..... 1110.0 ..... ..... @rrx_2a esz=3 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ DO_ZZX(sve2_sqdmull_idx_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s) DO_ZZX(sve2_sqdmull_idx_d, int64_t, int32_t, , H1_4, do_sqdmull_d) +DO_ZZX(sve2_smull_idx_s, int32_t, int16_t, H1_4, H1_2, DO_MUL) +DO_ZZX(sve2_smull_idx_d, int64_t, int32_t, , H1_4, DO_MUL) + +DO_ZZX(sve2_umull_idx_s, uint32_t, uint16_t, H1_4, H1_2, DO_MUL) +DO_ZZX(sve2_umull_idx_d, uint64_t, uint32_t, , H1_4, DO_MUL) + #undef DO_ZZX #define DO_BITPERM(NAME, TYPE, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_d, gen_helper_sve2_sqdmull_idx_d, false) DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_s, gen_helper_sve2_sqdmull_idx_s, true) DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_d, gen_helper_sve2_sqdmull_idx_d, true) +DO_SVE2_RRX_TB(trans_SMULLB_zzx_s, gen_helper_sve2_smull_idx_s, false) +DO_SVE2_RRX_TB(trans_SMULLB_zzx_d, gen_helper_sve2_smull_idx_d, false) +DO_SVE2_RRX_TB(trans_SMULLT_zzx_s, gen_helper_sve2_smull_idx_s, true) +DO_SVE2_RRX_TB(trans_SMULLT_zzx_d, gen_helper_sve2_smull_idx_d, true) + +DO_SVE2_RRX_TB(trans_UMULLB_zzx_s, gen_helper_sve2_umull_idx_s, false) +DO_SVE2_RRX_TB(trans_UMULLB_zzx_d, gen_helper_sve2_umull_idx_d, false) +DO_SVE2_RRX_TB(trans_UMULLT_zzx_s, gen_helper_sve2_umull_idx_s, true) +DO_SVE2_RRX_TB(trans_UMULLT_zzx_d, gen_helper_sve2_umull_idx_d, true) + #undef DO_SVE2_RRX_TB static bool do_sve2_zzzz_data(DisasContext *s, int rd, int rn, int rm, int ra, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-63-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 9 +++++++++ target/arm/sve.decode | 12 ++++++++++++ target/arm/sve_helper.c | 28 ++++++++++++++++++++++++++++ target/arm/translate-sve.c | 15 +++++++++++++++ 4 files changed, 64 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_smull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_smull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_umull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_umull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cmla_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cmla_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... ..... @rrxr_2a esz=3 SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2 SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3 +# SVE2 complex integer multiply-add (indexed) +CMLA_zzxz_h 01000100 10 1 index:2 rm:3 0110 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx +CMLA_zzxz_s 01000100 11 1 index:1 rm:4 0110 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx + +# SVE2 complex saturating integer multiply-add (indexed) +SQRDCMLAH_zzxz_h 01000100 10 1 index:2 rm:3 0111 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx +SQRDCMLAH_zzxz_s 01000100 11 1 index:1 rm:4 0111 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx + # SVE2 multiply-add long (indexed) SMLALB_zzxw_s 01000100 10 1 ..... 1000.0 ..... ..... @rrxr_3a esz=2 SMLALB_zzxw_d 01000100 11 1 ..... 1000.0 ..... ..... @rrxr_2a esz=3 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_h, int16_t, H2, DO_SQRDMLAH_H) DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_s, int32_t, H4, DO_SQRDMLAH_S) DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_d, int64_t, , DO_SQRDMLAH_D) +#define DO_CMLA_IDX_FUNC(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + int rot = extract32(desc, SIMD_DATA_SHIFT, 2); \ + int idx = extract32(desc, SIMD_DATA_SHIFT + 2, 2) * 2; \ + int sel_a = rot & 1, sel_b = sel_a ^ 1; \ + bool sub_r = rot == 1 || rot == 2; \ + bool sub_i = rot >= 2; \ + TYPE *d = vd, *n = vn, *m = vm, *a = va; \ + for (i = 0; i < oprsz / sizeof(TYPE); i += 16 / sizeof(TYPE)) { \ + TYPE elt2_a = m[H(i + idx + sel_a)]; \ + TYPE elt2_b = m[H(i + idx + sel_b)]; \ + for (j = 0; j < 16 / sizeof(TYPE); j += 2) { \ + TYPE elt1_a = n[H(i + j + sel_a)]; \ + d[H2(i + j)] = OP(elt1_a, elt2_a, a[H(i + j)], sub_r); \ + d[H2(i + j + 1)] = OP(elt1_a, elt2_b, a[H(i + j + 1)], sub_i); \ + } \ + } \ +} + +DO_CMLA_IDX_FUNC(sve2_cmla_idx_h, int16_t, H2, DO_CMLA) +DO_CMLA_IDX_FUNC(sve2_cmla_idx_s, int32_t, H4, DO_CMLA) + +DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H) +DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S) + #undef DO_CMLA #undef DO_CMLA_FUNC +#undef DO_CMLA_IDX_FUNC #undef DO_SQRDMLAH_B #undef DO_SQRDMLAH_H #undef DO_SQRDMLAH_S diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_d, gen_helper_sve2_umlsl_idx_d, true) #undef DO_SVE2_RRXR_TB +#define DO_SVE2_RRXR_ROT(NAME, FUNC) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra, \ + (a->index << 2) | a->rot, FUNC); \ + } + +DO_SVE2_RRXR_ROT(CMLA_zzxz_h, gen_helper_sve2_cmla_idx_h) +DO_SVE2_RRXR_ROT(CMLA_zzxz_s, gen_helper_sve2_cmla_idx_s) + +DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_h, gen_helper_sve2_sqrdcmlah_idx_h) +DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_s, gen_helper_sve2_sqrdcmlah_idx_s) + +#undef DO_SVE2_RRXR_ROT + /* *** SVE Floating Point Multiply-Add Indexed Group */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-64-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 10 ++++ target/arm/sve.decode | 9 ++++ target/arm/sve_helper.c | 99 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 17 +++++++ 4 files changed, 135 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cdot_zzzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cdot_zzzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_cdot_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_cdot_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s DOT_zzzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 \ ra=%reg_movprfx +# SVE2 complex dot product (vectors) +CDOT_zzzz 01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5 ra=%reg_movprfx + #### SVE Multiply - Indexed # SVE integer dot product (indexed) @@ -XXX,XX +XXX,XX @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... ..... @rrxr_2a esz=3 SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2 SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3 +# SVE2 complex integer dot product (indexed) +CDOT_zzxw_s 01000100 10 1 index:2 rm:3 0100 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx +CDOT_zzxw_d 01000100 11 1 index:1 rm:4 0100 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx + # SVE2 complex integer multiply-add (indexed) CMLA_zzxz_h 01000100 10 1 index:2 rm:3 0110 rot:2 rn:5 rd:5 \ ra=%reg_movprfx diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S) #undef DO_SQRDMLAH_S #undef DO_SQRDMLAH_D +/* Note N and M are 4 elements bundled into one unit. */ +static int32_t do_cdot_s(uint32_t n, uint32_t m, int32_t a, + int sel_a, int sel_b, int sub_i) +{ + for (int i = 0; i <= 1; i++) { + int32_t elt1_r = (int8_t)(n >> (16 * i)); + int32_t elt1_i = (int8_t)(n >> (16 * i + 8)); + int32_t elt2_a = (int8_t)(m >> (16 * i + 8 * sel_a)); + int32_t elt2_b = (int8_t)(m >> (16 * i + 8 * sel_b)); + + a += elt1_r * elt2_a + elt1_i * elt2_b * sub_i; + } + return a; +} + +static int64_t do_cdot_d(uint64_t n, uint64_t m, int64_t a, + int sel_a, int sel_b, int sub_i) +{ + for (int i = 0; i <= 1; i++) { + int64_t elt1_r = (int16_t)(n >> (32 * i + 0)); + int64_t elt1_i = (int16_t)(n >> (32 * i + 16)); + int64_t elt2_a = (int16_t)(m >> (32 * i + 16 * sel_a)); + int64_t elt2_b = (int16_t)(m >> (32 * i + 16 * sel_b)); + + a += elt1_r * elt2_a + elt1_i * elt2_b * sub_i; + } + return a; +} + +void HELPER(sve2_cdot_zzzz_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int rot = simd_data(desc); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint32_t *d = vd, *n = vn, *m = vm, *a = va; + + for (int e = 0; e < opr_sz / 4; e++) { + d[e] = do_cdot_s(n[e], m[e], a[e], sel_a, sel_b, sub_i); + } +} + +void HELPER(sve2_cdot_zzzz_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int rot = simd_data(desc); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint64_t *d = vd, *n = vn, *m = vm, *a = va; + + for (int e = 0; e < opr_sz / 8; e++) { + d[e] = do_cdot_d(n[e], m[e], a[e], sel_a, sel_b, sub_i); + } +} + +void HELPER(sve2_cdot_idx_s)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int rot = extract32(desc, SIMD_DATA_SHIFT, 2); + int idx = H4(extract32(desc, SIMD_DATA_SHIFT + 2, 2)); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint32_t *d = vd, *n = vn, *m = vm, *a = va; + + for (int seg = 0; seg < opr_sz / 4; seg += 4) { + uint32_t seg_m = m[seg + idx]; + for (int e = 0; e < 4; e++) { + d[seg + e] = do_cdot_s(n[seg + e], seg_m, a[seg + e], + sel_a, sel_b, sub_i); + } + } +} + +void HELPER(sve2_cdot_idx_d)(void *vd, void *vn, void *vm, + void *va, uint32_t desc) +{ + int seg, opr_sz = simd_oprsz(desc); + int rot = extract32(desc, SIMD_DATA_SHIFT, 2); + int idx = extract32(desc, SIMD_DATA_SHIFT + 2, 2); + int sel_a = rot & 1; + int sel_b = sel_a ^ 1; + int sub_i = (rot == 0 || rot == 3 ? -1 : 1); + uint64_t *d = vd, *n = vn, *m = vm, *a = va; + + for (seg = 0; seg < opr_sz / 8; seg += 2) { + uint64_t seg_m = m[seg + idx]; + for (int e = 0; e < 2; e++) { + d[seg + e] = do_cdot_d(n[seg + e], seg_m, a[seg + e], + sel_a, sel_b, sub_i); + } + } +} + #define DO_ZZXZ(NAME, TYPE, H, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ { \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_RRXR_ROT(CMLA_zzxz_s, gen_helper_sve2_cmla_idx_s) DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_h, gen_helper_sve2_sqrdcmlah_idx_h) DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_s, gen_helper_sve2_sqrdcmlah_idx_s) +DO_SVE2_RRXR_ROT(CDOT_zzxw_s, gen_helper_sve2_cdot_idx_s) +DO_SVE2_RRXR_ROT(CDOT_zzxw_d, gen_helper_sve2_cdot_idx_d) + #undef DO_SVE2_RRXR_ROT /* @@ -XXX,XX +XXX,XX @@ static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a) return true; } +static bool trans_CDOT_zzzz(DisasContext *s, arg_CMLA_zzzz *a) +{ + if (!dc_isar_feature(aa64_sve2, s) || a->esz < MO_32) { + return false; + } + if (sve_access_check(s)) { + gen_helper_gvec_4 *fn = (a->esz == MO_32 + ? gen_helper_sve2_cdot_zzzz_s + : gen_helper_sve2_cdot_zzzz_d); + gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, a->rot); + } + return true; +} + static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) { static gen_helper_gvec_4 * const fns[] = { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We're about to add more variations on this theme. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-65-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vec_helper.c | 82 ++++++++++------------------------------- 1 file changed, 20 insertions(+), 62 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc) /* Integer 8 and 16-bit dot-product. * * Note that for the loops herein, host endianness does not matter - * with respect to the ordering of data within the 64-bit lanes. + * with respect to the ordering of data within the quad-width lanes. * All elements are treated equally, no matter where they are. */ -void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) -{ - intptr_t i, opr_sz = simd_oprsz(desc); - int32_t *d = vd, *a = va; - int8_t *n = vn, *m = vm; - - for (i = 0; i < opr_sz / 4; ++i) { - d[i] = (a[i] + - n[i * 4 + 0] * m[i * 4 + 0] + - n[i * 4 + 1] * m[i * 4 + 1] + - n[i * 4 + 2] * m[i * 4 + 2] + - n[i * 4 + 3] * m[i * 4 + 3]); - } - clear_tail(d, opr_sz, simd_maxsz(desc)); +#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m = vm; \ + for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \ + d[i] = (a[i] + \ + (TYPED)n[i * 4 + 0] * m[i * 4 + 0] + \ + (TYPED)n[i * 4 + 1] * m[i * 4 + 1] + \ + (TYPED)n[i * 4 + 2] * m[i * 4 + 2] + \ + (TYPED)n[i * 4 + 3] * m[i * 4 + 3]); \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ } -void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) -{ - intptr_t i, opr_sz = simd_oprsz(desc); - uint32_t *d = vd, *a = va; - uint8_t *n = vn, *m = vm; - - for (i = 0; i < opr_sz / 4; ++i) { - d[i] = (a[i] + - n[i * 4 + 0] * m[i * 4 + 0] + - n[i * 4 + 1] * m[i * 4 + 1] + - n[i * 4 + 2] * m[i * 4 + 2] + - n[i * 4 + 3] * m[i * 4 + 3]); - } - clear_tail(d, opr_sz, simd_maxsz(desc)); -} - -void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) -{ - intptr_t i, opr_sz = simd_oprsz(desc); - int64_t *d = vd, *a = va; - int16_t *n = vn, *m = vm; - - for (i = 0; i < opr_sz / 8; ++i) { - d[i] = (a[i] + - (int64_t)n[i * 4 + 0] * m[i * 4 + 0] + - (int64_t)n[i * 4 + 1] * m[i * 4 + 1] + - (int64_t)n[i * 4 + 2] * m[i * 4 + 2] + - (int64_t)n[i * 4 + 3] * m[i * 4 + 3]); - } - clear_tail(d, opr_sz, simd_maxsz(desc)); -} - -void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) -{ - intptr_t i, opr_sz = simd_oprsz(desc); - uint64_t *d = vd, *a = va; - uint16_t *n = vn, *m = vm; - - for (i = 0; i < opr_sz / 8; ++i) { - d[i] = (a[i] + - (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] + - (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] + - (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] + - (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]); - } - clear_tail(d, opr_sz, simd_maxsz(desc)); -} +DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t) +DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t) +DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t) +DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t) void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, void *va, uint32_t desc) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We're about to add more variations on this theme. Accept the inner loop for the _h variants, rather than keep it unrolled. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-66-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vec_helper.c | 160 ++++++++-------------------------------- 1 file changed, 29 insertions(+), 131 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t) DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t) DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t) -void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, - void *va, uint32_t desc) -{ - intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; - intptr_t index = simd_data(desc); - int32_t *d = vd, *a = va; - int8_t *n = vn; - int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; - - /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. - * Otherwise opr_sz is a multiple of 16. - */ - segend = MIN(4, opr_sz_4); - i = 0; - do { - int8_t m0 = m_indexed[i * 4 + 0]; - int8_t m1 = m_indexed[i * 4 + 1]; - int8_t m2 = m_indexed[i * 4 + 2]; - int8_t m3 = m_indexed[i * 4 + 3]; - - do { - d[i] = (a[i] + - n[i * 4 + 0] * m0 + - n[i * 4 + 1] * m1 + - n[i * 4 + 2] * m2 + - n[i * 4 + 3] * m3); - } while (++i < segend); - segend = i + 4; - } while (i < opr_sz_4); - - clear_tail(d, opr_sz, simd_maxsz(desc)); +#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i = 0, opr_sz = simd_oprsz(desc); \ + intptr_t opr_sz_n = opr_sz / sizeof(TYPED); \ + intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n); \ + intptr_t index = simd_data(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 4; \ + do { \ + TYPED m0 = m_indexed[i * 4 + 0]; \ + TYPED m1 = m_indexed[i * 4 + 1]; \ + TYPED m2 = m_indexed[i * 4 + 2]; \ + TYPED m3 = m_indexed[i * 4 + 3]; \ + do { \ + d[i] = (a[i] + \ + n[i * 4 + 0] * m0 + \ + n[i * 4 + 1] * m1 + \ + n[i * 4 + 2] * m2 + \ + n[i * 4 + 3] * m3); \ + } while (++i < segend); \ + segend = i + 4; \ + } while (i < opr_sz_n); \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ } -void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, - void *va, uint32_t desc) -{ - intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; - intptr_t index = simd_data(desc); - uint32_t *d = vd, *a = va; - uint8_t *n = vn; - uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4; - - /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. - * Otherwise opr_sz is a multiple of 16. - */ - segend = MIN(4, opr_sz_4); - i = 0; - do { - uint8_t m0 = m_indexed[i * 4 + 0]; - uint8_t m1 = m_indexed[i * 4 + 1]; - uint8_t m2 = m_indexed[i * 4 + 2]; - uint8_t m3 = m_indexed[i * 4 + 3]; - - do { - d[i] = (a[i] + - n[i * 4 + 0] * m0 + - n[i * 4 + 1] * m1 + - n[i * 4 + 2] * m2 + - n[i * 4 + 3] * m3); - } while (++i < segend); - segend = i + 4; - } while (i < opr_sz_4); - - clear_tail(d, opr_sz, simd_maxsz(desc)); -} - -void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, - void *va, uint32_t desc) -{ - intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; - intptr_t index = simd_data(desc); - int64_t *d = vd, *a = va; - int16_t *n = vn; - int16_t *m_indexed = (int16_t *)vm + index * 4; - - /* This is supported by SVE only, so opr_sz is always a multiple of 16. - * Process the entire segment all at once, writing back the results - * only after we've consumed all of the inputs. - */ - for (i = 0; i < opr_sz_8; i += 2) { - int64_t d0, d1; - - d0 = a[i + 0]; - d0 += n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; - d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1]; - d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2]; - d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3]; - - d1 = a[i + 1]; - d1 += n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; - d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1]; - d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2]; - d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3]; - - d[i + 0] = d0; - d[i + 1] = d1; - } - clear_tail(d, opr_sz, simd_maxsz(desc)); -} - -void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, - void *va, uint32_t desc) -{ - intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; - intptr_t index = simd_data(desc); - uint64_t *d = vd, *a = va; - uint16_t *n = vn; - uint16_t *m_indexed = (uint16_t *)vm + index * 4; - - /* This is supported by SVE only, so opr_sz is always a multiple of 16. - * Process the entire segment all at once, writing back the results - * only after we've consumed all of the inputs. - */ - for (i = 0; i < opr_sz_8; i += 2) { - uint64_t d0, d1; - - d0 = a[i + 0]; - d0 += n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; - d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1]; - d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2]; - d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3]; - - d1 = a[i + 1]; - d1 += n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; - d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1]; - d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2]; - d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3]; - - d[i + 0] = d0; - d[i + 1] = d1; - } - clear_tail(d, opr_sz, simd_maxsz(desc)); -} +DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4) +DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4) +DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, ) +DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, ) void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, void *vfpst, uint32_t desc) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-67-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++++ target/arm/helper.h | 4 ++++ target/arm/sve.decode | 4 ++++ target/arm/translate-sve.c | 16 ++++++++++++++++ target/arm/vec_helper.c | 2 ++ 5 files changed, 31 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; } +static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; +} + static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SQRDMLSH_zzxz_h 01000100 0. 1 ..... 000101 ..... ..... @rrxr_3 esz=1 SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3 +# SVE mixed sign dot product (indexed) +USDOT_zzxw_s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 +SUDOT_zzxw_s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 + # SVE2 saturating multiply-add (indexed) SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2 SQDMLALB_zzxw_d 01000100 11 1 ..... 0010.0 ..... ..... @rrxr_2a esz=3 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_RRXR(trans_SDOT_zzxw_d, gen_helper_gvec_sdot_idx_h) DO_RRXR(trans_UDOT_zzxw_s, gen_helper_gvec_udot_idx_b) DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h) +static bool trans_SUDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + return do_zzxz_ool(s, a, gen_helper_gvec_sudot_idx_b); +} + +static bool trans_USDOT_zzxw_s(DisasContext *s, arg_rrxr_esz *a) +{ + if (!dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + return do_zzxz_ool(s, a, gen_helper_gvec_usdot_idx_b); +} + #undef DO_RRXR static bool do_sve2_zzz_data(DisasContext *s, int rd, int rn, int rm, int data, diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4) DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4) +DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4) +DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4) DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, ) DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, ) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-68-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 1 + target/arm/sve.decode | 4 ++++ target/arm/translate-sve.c | 16 ++++++++++++++++ target/arm/vec_helper.c | 1 + 4 files changed, 22 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx +## SVE mixed sign dot product + +USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm + ### SVE2 floating point matrix multiply accumulate FMMLA 01100100 .. 1 ..... 111001 ..... ..... @rda_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a) } return true; } + +static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) +{ + if (a->esz != 2 || !dc_isar_feature(aa64_sve_i8mm, s)) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + vsz, vsz, 0, gen_helper_gvec_usdot_b); + } + return true; +} diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t) DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t) +DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t) DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t) DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-69-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 6 ++++++ target/arm/translate-sve.c | 11 +++++++++++ 2 files changed, 17 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ STNT1_zprz 1110010 .. 00 ..... 001 ... ..... ..... \ # SVE2 32-bit scatter non-temporal store (vector plus scalar) STNT1_zprz 1110010 .. 10 ..... 001 ... ..... ..... \ @rprr_scatter_store xs=0 esz=2 scale=0 + +### SVE2 Crypto Extensions + +# SVE2 crypto unary operations +# AESMC and AESIMC +AESMC 01000101 00 10000011100 decrypt:1 00000 rd:5 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_USDOT_zzzz(DisasContext *s, arg_USDOT_zzzz *a) } return true; } + +static bool trans_AESMC(DisasContext *s, arg_AESMC *a) +{ + if (!dc_isar_feature(aa64_sve2_aes, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zz(s, gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt); + } + return true; +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-70-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++++ target/arm/sve.decode | 7 +++++++ target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; } +static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; +} + static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @pd_pn_pm ........ esz:2 .. rm:4 ....... rn:4 . rd:4 &rrr_esz @rdn_rm ........ esz:2 ...... ...... rm:5 rd:5 \ &rrr_esz rn=%reg_movprfx +@rdn_rm_e0 ........ .. ...... ...... rm:5 rd:5 \ + &rrr_esz rn=%reg_movprfx esz=0 @rdn_sh_i8u ........ esz:2 ...... ...... ..... rd:5 \ &rri_esz rn=%reg_movprfx imm=%sh8_i8u @rdn_i8u ........ esz:2 ...... ... imm:8 rd:5 \ @@ -XXX,XX +XXX,XX @@ STNT1_zprz 1110010 .. 10 ..... 001 ... ..... ..... \ # SVE2 crypto unary operations # AESMC and AESIMC AESMC 01000101 00 10000011100 decrypt:1 00000 rd:5 + +# SVE2 crypto destructive binary operations +AESE 01000101 00 10001 0 11100 0 ..... ..... @rdn_rm_e0 +AESD 01000101 00 10001 0 11100 1 ..... ..... @rdn_rm_e0 +SM4E 01000101 00 10001 1 11100 0 ..... ..... @rdn_rm_e0 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_AESMC(DisasContext *s, arg_AESMC *a) } return true; } + +static bool do_aese(DisasContext *s, arg_rrr_esz *a, bool decrypt) +{ + if (!dc_isar_feature(aa64_sve2_aes, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, gen_helper_crypto_aese, + a->rd, a->rn, a->rm, decrypt); + } + return true; +} + +static bool trans_AESE(DisasContext *s, arg_rrr_esz *a) +{ + return do_aese(s, a, false); +} + +static bool trans_AESD(DisasContext *s, arg_rrr_esz *a) +{ + return do_aese(s, a, true); +} + +static bool do_sm4(DisasContext *s, arg_rrr_esz *a, gen_helper_gvec_3 *fn) +{ + if (!dc_isar_feature(aa64_sve2_sm4, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, 0); + } + return true; +} + +static bool trans_SM4E(DisasContext *s, arg_rrr_esz *a) +{ + return do_sm4(s, a, gen_helper_crypto_sm4e); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-71-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++++ target/arm/sve.decode | 4 ++++ target/arm/translate-sve.c | 16 ++++++++++++++++ 3 files changed, 25 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; } +static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; +} + static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ AESMC 01000101 00 10000011100 decrypt:1 00000 rd:5 AESE 01000101 00 10001 0 11100 0 ..... ..... @rdn_rm_e0 AESD 01000101 00 10001 0 11100 1 ..... ..... @rdn_rm_e0 SM4E 01000101 00 10001 1 11100 0 ..... ..... @rdn_rm_e0 + +# SVE2 crypto constructive binary operations +SM4EKEY 01000101 00 1 ..... 11110 0 ..... ..... @rd_rn_rm_e0 +RAX1 01000101 00 1 ..... 11110 1 ..... ..... @rd_rn_rm_e0 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_SM4E(DisasContext *s, arg_rrr_esz *a) { return do_sm4(s, a, gen_helper_crypto_sm4e); } + +static bool trans_SM4EKEY(DisasContext *s, arg_rrr_esz *a) +{ + return do_sm4(s, a, gen_helper_crypto_sm4ekey); +} + +static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2_sha3, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_fn_zzz(s, gen_gvec_rax1, MO_64, a->rd, a->rn, a->rm); + } + return true; +} -- 2.20.1 From: Stephen Long <steplong@quicinc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-72-richard.henderson@linaro.org Message-Id: <20200428144352.9275-1-steplong@quicinc.com> [rth: rearrange the macros a little and rebase] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 10 +++++ target/arm/sve.decode | 5 +++ target/arm/sve_helper.c | 90 ++++++++++++++++++++++++++++++-------- target/arm/translate-sve.c | 33 ++++++++++++++ 4 files changed, 119 insertions(+), 19 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2_tbx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_tbx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_tbx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2_tbx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm # SVE unpack vector elements UNPK 00000101 esz:2 1100 u:1 h:1 001110 rn:5 rd:5 +# SVE2 Table Lookup (three sources) + +TBL_sve2 00000101 .. 1 ..... 001010 ..... ..... @rd_rn_rm +TBX 00000101 .. 1 ..... 001011 ..... ..... @rd_rn_rm + ### SVE Permute - Predicates Group # SVE permute predicate elements diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc) } } -#define DO_TBL(NAME, TYPE, H) \ -void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ -{ \ - intptr_t i, opr_sz = simd_oprsz(desc); \ - uintptr_t elem = opr_sz / sizeof(TYPE); \ - TYPE *d = vd, *n = vn, *m = vm; \ - ARMVectorReg tmp; \ - if (unlikely(vd == vn)) { \ - n = memcpy(&tmp, vn, opr_sz); \ - } \ - for (i = 0; i < elem; i++) { \ - TYPE j = m[H(i)]; \ - d[H(i)] = j < elem ? n[H(j)] : 0; \ - } \ +typedef void tb_impl_fn(void *, void *, void *, void *, uintptr_t, bool); + +static inline void do_tbl1(void *vd, void *vn, void *vm, uint32_t desc, + bool is_tbx, tb_impl_fn *fn) +{ + ARMVectorReg scratch; + uintptr_t oprsz = simd_oprsz(desc); + + if (unlikely(vd == vn)) { + vn = memcpy(&scratch, vn, oprsz); + } + + fn(vd, vn, NULL, vm, oprsz, is_tbx); } -DO_TBL(sve_tbl_b, uint8_t, H1) -DO_TBL(sve_tbl_h, uint16_t, H2) -DO_TBL(sve_tbl_s, uint32_t, H4) -DO_TBL(sve_tbl_d, uint64_t, ) +static inline void do_tbl2(void *vd, void *vn0, void *vn1, void *vm, + uint32_t desc, bool is_tbx, tb_impl_fn *fn) +{ + ARMVectorReg scratch; + uintptr_t oprsz = simd_oprsz(desc); -#undef TBL + if (unlikely(vd == vn0)) { + vn0 = memcpy(&scratch, vn0, oprsz); + if (vd == vn1) { + vn1 = vn0; + } + } else if (unlikely(vd == vn1)) { + vn1 = memcpy(&scratch, vn1, oprsz); + } + + fn(vd, vn0, vn1, vm, oprsz, is_tbx); +} + +#define DO_TB(SUFF, TYPE, H) \ +static inline void do_tb_##SUFF(void *vd, void *vt0, void *vt1, \ + void *vm, uintptr_t oprsz, bool is_tbx) \ +{ \ + TYPE *d = vd, *tbl0 = vt0, *tbl1 = vt1, *indexes = vm; \ + uintptr_t i, nelem = oprsz / sizeof(TYPE); \ + for (i = 0; i < nelem; ++i) { \ + TYPE index = indexes[H1(i)], val = 0; \ + if (index < nelem) { \ + val = tbl0[H(index)]; \ + } else { \ + index -= nelem; \ + if (tbl1 && index < nelem) { \ + val = tbl1[H(index)]; \ + } else if (is_tbx) { \ + continue; \ + } \ + } \ + d[H(i)] = val; \ + } \ +} \ +void HELPER(sve_tbl_##SUFF)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + do_tbl1(vd, vn, vm, desc, false, do_tb_##SUFF); \ +} \ +void HELPER(sve2_tbl_##SUFF)(void *vd, void *vn0, void *vn1, \ + void *vm, uint32_t desc) \ +{ \ + do_tbl2(vd, vn0, vn1, vm, desc, false, do_tb_##SUFF); \ +} \ +void HELPER(sve2_tbx_##SUFF)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + do_tbl1(vd, vn, vm, desc, true, do_tb_##SUFF); \ +} + +DO_TB(b, uint8_t, H1) +DO_TB(h, uint16_t, H2) +DO_TB(s, uint32_t, H4) +DO_TB(d, uint64_t, ) + +#undef DO_TB #define DO_UNPK(NAME, TYPED, TYPES, HD, HS) \ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_TBL(DisasContext *s, arg_rrr_esz *a) return true; } +static bool trans_TBL_sve2(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_4 * const fns[4] = { + gen_helper_sve2_tbl_b, gen_helper_sve2_tbl_h, + gen_helper_sve2_tbl_s, gen_helper_sve2_tbl_d + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, + (a->rn + 1) % 32, a->rm, 0); + } + return true; +} + +static bool trans_TBX(DisasContext *s, arg_rrr_esz *a) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, + gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d + }; + + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + if (sve_access_check(s)) { + gen_gvec_ool_zzz(s, fns[a->esz], a->rd, a->rn, a->rm, 0); + } + return true; +} + static bool trans_UNPK(DisasContext *s, arg_UNPK *a) { static gen_helper_gvec_2 * const fns[4][2] = { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Stephen Long <steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210525010358.152808-73-richard.henderson@linaro.org Message-Id: <20200428174332.17162-2-steplong@quicinc.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 5 +++++ target/arm/sve.decode | 4 ++++ target/arm/sve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-sve.c | 16 ++++++++++++++++ 4 files changed, 45 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_cdot_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_cdot_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_fcvtnt_sh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_fcvtnt_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ SM4E 01000101 00 10001 1 11100 0 ..... ..... @rdn_rm_e0 # SVE2 crypto constructive binary operations SM4EKEY 01000101 00 1 ..... 11110 0 ..... ..... @rd_rn_rm_e0 RAX1 01000101 00 1 ..... 11110 1 ..... ..... @rd_rn_rm_e0 + +### SVE2 floating-point convert precision odd elements +FCVTNT_sh 01100100 10 0010 00 101 ... ..... ..... @rd_pg_rn_e0 +FCVTNT_ds 01100100 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0 diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void *va, d[3] = float64_add(a[3], float64_add(p0, p1, status), status); } } + +#define DO_FCVTNT(NAME, TYPEW, TYPEN, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc); \ + uint64_t *g = vg; \ + do { \ + uint64_t pg = g[(i - 1) >> 6]; \ + do { \ + i -= sizeof(TYPEW); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPEW nn = *(TYPEW *)(vn + HW(i)); \ + *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, status); \ + } \ + } while (i & 63); \ + } while (i != 0); \ +} + +DO_FCVTNT(sve2_fcvtnt_sh, uint32_t, uint16_t, H1_4, H1_2, sve_f32_to_f16) +DO_FCVTNT(sve2_fcvtnt_ds, uint64_t, uint32_t, , H1_4, float64_to_float32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a) } return true; } + +static bool trans_FCVTNT_sh(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_sh); +} + +static bool trans_FCVTNT_ds(DisasContext *s, arg_rpr_esz *a) +{ + if (!dc_isar_feature(aa64_sve2, s)) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve2_fcvtnt_ds); +} -- 2.20.1