Probably the last arm pullreq before softfreeze... The following changes since commit 58560ad254fbda71d4daa6622d71683190070ee2: Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-4.2-20191024' into staging (2019-10-24 16:22:58 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20191024 for you to fetch changes up to a01a4a3e85ae8f6fe21adbedc80f7013faabdcf4: hw/arm/highbank: Use AddressSpace when using write_secondary_boot() (2019-10-24 17:16:30 +0100) ---------------------------------------------------------------- target-arm queue: * raspi boards: some cleanup * raspi: implement the bcm2835 system timer device * raspi: implement a dummy thermal sensor * KVM: support providing SVE to the guest * misc devices: switch to ptimer transaction API * cache TB flag state to improve performance of cpu_get_tb_cpu_state * aspeed: Add an AST2600 eval board ---------------------------------------------------------------- Andrew Jones (9): target/arm/monitor: Introduce qmp_query_cpu_model_expansion tests: arm: Introduce cpu feature tests target/arm: Allow SVE to be disabled via a CPU property target/arm/cpu64: max cpu: Introduce sve<N> properties target/arm/kvm64: Add kvm_arch_get/put_sve target/arm/kvm64: max cpu: Enable SVE when available target/arm/kvm: scratch vcpu: Preserve input kvm_vcpu_init features target/arm/cpu64: max cpu: Support sve properties with KVM target/arm/kvm: host cpu: Add support for sve<N> properties Cédric Le Goater (2): hw/gpio: Fix property accessors of the AST2600 GPIO 1.8V model aspeed: Add an AST2600 eval board Peter Maydell (8): hw/net/fsl_etsec/etsec.c: Switch to transaction-based ptimer API hw/timer/xilinx_timer.c: Switch to transaction-based ptimer API hw/dma/xilinx_axidma.c: Switch to transaction-based ptimer API hw/timer/slavio_timer: Remove useless check for NULL t->timer hw/timer/slavio_timer.c: Switch to transaction-based ptimer API hw/timer/grlib_gptimer.c: Switch to transaction-based ptimer API hw/m68k/mcf5206.c: Switch to transaction-based ptimer API hw/watchdog/milkymist-sysctl.c: Switch to transaction-based ptimer API Philippe Mathieu-Daudé (8): hw/misc/bcm2835_thermal: Add a dummy BCM2835 thermal sensor hw/arm/bcm2835_peripherals: Use the thermal sensor block hw/timer/bcm2835: Add the BCM2835 SYS_timer hw/arm/bcm2835_peripherals: Use the SYS_timer hw/arm/bcm2836: Make the SoC code modular hw/arm/bcm2836: Rename cpus[] as cpu[].core hw/arm/raspi: Use AddressSpace when using arm_boot::write_secondary_boot hw/arm/highbank: Use AddressSpace when using write_secondary_boot() Richard Henderson (24): target/arm: Split out rebuild_hflags_common target/arm: Split out rebuild_hflags_a64 target/arm: Split out rebuild_hflags_common_32 target/arm: Split arm_cpu_data_is_big_endian target/arm: Split out rebuild_hflags_m32 target/arm: Reduce tests vs M-profile in cpu_get_tb_cpu_state target/arm: Split out rebuild_hflags_a32 target/arm: Split out rebuild_hflags_aprofile target/arm: Hoist XSCALE_CPAR, VECLEN, VECSTRIDE in cpu_get_tb_cpu_state target/arm: Simplify set of PSTATE_SS in cpu_get_tb_cpu_state target/arm: Hoist computation of TBFLAG_A32.VFPEN target/arm: Add arm_rebuild_hflags target/arm: Split out arm_mmu_idx_el target/arm: Hoist store to cs_base in cpu_get_tb_cpu_state target/arm: Add HELPER(rebuild_hflags_{a32, a64, m32}) target/arm: Rebuild hflags at EL changes target/arm: Rebuild hflags at MSR writes target/arm: Rebuild hflags at CPSR writes target/arm: Rebuild hflags at Xscale SCTLR writes target/arm: Rebuild hflags for M-profile target/arm: Rebuild hflags for M-profile NVIC linux-user/aarch64: Rebuild hflags for TARGET_WORDS_BIGENDIAN linux-user/arm: Rebuild hflags for TARGET_WORDS_BIGENDIAN target/arm: Rely on hflags correct in cpu_get_tb_cpu_state hw/misc/Makefile.objs | 1 + hw/timer/Makefile.objs | 1 + tests/Makefile.include | 5 +- qapi/machine-target.json | 6 +- hw/net/fsl_etsec/etsec.h | 1 - include/hw/arm/aspeed.h | 1 + include/hw/arm/bcm2835_peripherals.h | 5 +- include/hw/arm/bcm2836.h | 4 +- include/hw/arm/raspi_platform.h | 1 + include/hw/misc/bcm2835_thermal.h | 27 ++ include/hw/timer/bcm2835_systmr.h | 33 +++ include/qemu/bitops.h | 1 + target/arm/cpu.h | 105 +++++-- target/arm/helper.h | 4 + target/arm/internals.h | 9 + target/arm/kvm_arm.h | 39 +++ hw/arm/aspeed.c | 23 ++ hw/arm/bcm2835_peripherals.c | 30 +- hw/arm/bcm2836.c | 44 +-- hw/arm/highbank.c | 3 +- hw/arm/raspi.c | 14 +- hw/dma/xilinx_axidma.c | 9 +- hw/gpio/aspeed_gpio.c | 8 +- hw/intc/armv7m_nvic.c | 22 +- hw/m68k/mcf5206.c | 15 +- hw/misc/bcm2835_thermal.c | 135 +++++++++ hw/net/fsl_etsec/etsec.c | 9 +- hw/timer/bcm2835_systmr.c | 163 +++++++++++ hw/timer/grlib_gptimer.c | 28 +- hw/timer/milkymist-sysctl.c | 25 +- hw/timer/slavio_timer.c | 32 ++- hw/timer/xilinx_timer.c | 13 +- linux-user/aarch64/cpu_loop.c | 1 + linux-user/arm/cpu_loop.c | 1 + linux-user/syscall.c | 1 + target/arm/cpu.c | 26 +- target/arm/cpu64.c | 364 +++++++++++++++++++++-- target/arm/helper-a64.c | 3 + target/arm/helper.c | 403 +++++++++++++++++--------- target/arm/kvm.c | 25 +- target/arm/kvm32.c | 6 +- target/arm/kvm64.c | 325 ++++++++++++++++++--- target/arm/m_helper.c | 6 + target/arm/machine.c | 1 + target/arm/monitor.c | 158 ++++++++++ target/arm/op_helper.c | 4 + target/arm/translate-a64.c | 13 +- target/arm/translate.c | 33 ++- tests/arm-cpu-features.c | 540 +++++++++++++++++++++++++++++++++++ docs/arm-cpu-features.rst | 317 ++++++++++++++++++++ hw/timer/trace-events | 5 + 51 files changed, 2725 insertions(+), 323 deletions(-) create mode 100644 include/hw/misc/bcm2835_thermal.h create mode 100644 include/hw/timer/bcm2835_systmr.h create mode 100644 hw/misc/bcm2835_thermal.c create mode 100644 hw/timer/bcm2835_systmr.c create mode 100644 tests/arm-cpu-features.c create mode 100644 docs/arm-cpu-features.rst From: Cédric Le Goater <clg@kaod.org> The property names of AST2600 GPIO 1.8V model are one character bigger than the names of the other ASPEED GPIO model. Increase the string buffer size by one and be more strict on the expected pattern of the property name. This fixes the QOM test of the ast2600-evb machine under : Apple LLVM version 10.0.0 (clang-1000.10.44.4) Target: x86_64-apple-darwin17.7.0 Thread model: posix InstalledDir: /Library/Developer/CommandLineTools/usr/bin Cc: Rashmica Gupta <rashmica.g@gmail.com> Fixes: 36d737ee82b2 ("hw/gpio: Add in AST2600 specific implementation") Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 20191023130455.1347-2-clg@kaod.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/aspeed_gpio.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/hw/gpio/aspeed_gpio.c b/hw/gpio/aspeed_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/aspeed_gpio.c +++ b/hw/gpio/aspeed_gpio.c @@ -XXX,XX +XXX,XX @@ static void aspeed_gpio_get_pin(Object *obj, Visitor *v, const char *name, { int pin = 0xfff; bool level = true; - char group[3]; + char group[4]; AspeedGPIOState *s = ASPEED_GPIO(obj); int set_idx, group_idx = 0; if (sscanf(name, "gpio%2[A-Z]%1d", group, &pin) != 2) { /* 1.8V gpio */ - if (sscanf(name, "gpio%3s%1d", group, &pin) != 2) { + if (sscanf(name, "gpio%3[18A-E]%1d", group, &pin) != 2) { error_setg(errp, "%s: error reading %s", __func__, name); return; } @@ -XXX,XX +XXX,XX @@ static void aspeed_gpio_set_pin(Object *obj, Visitor *v, const char *name, Error *local_err = NULL; bool level; int pin = 0xfff; - char group[3]; + char group[4]; AspeedGPIOState *s = ASPEED_GPIO(obj); int set_idx, group_idx = 0; @@ -XXX,XX +XXX,XX @@ static void aspeed_gpio_set_pin(Object *obj, Visitor *v, const char *name, } if (sscanf(name, "gpio%2[A-Z]%1d", group, &pin) != 2) { /* 1.8V gpio */ - if (sscanf(name, "gpio%3s%1d", group, &pin) != 2) { + if (sscanf(name, "gpio%3[18A-E]%1d", group, &pin) != 2) { error_setg(errp, "%s: error reading %s", __func__, name); return; } -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20191023130455.1347-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed.h | 1 + hw/arm/aspeed.c | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/hw/arm/aspeed.h b/include/hw/arm/aspeed.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed.h +++ b/include/hw/arm/aspeed.h @@ -XXX,XX +XXX,XX @@ typedef struct AspeedBoardConfig { const char *desc; const char *soc_name; uint32_t hw_strap1; + uint32_t hw_strap2; const char *fmc_model; const char *spi_model; uint32_t num_cs; diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ struct AspeedBoardState { /* Witherspoon hardware value: 0xF10AD216 (but use romulus definition) */ #define WITHERSPOON_BMC_HW_STRAP1 ROMULUS_BMC_HW_STRAP1 +/* AST2600 evb hardware value */ +#define AST2600_EVB_HW_STRAP1 0x000000C0 +#define AST2600_EVB_HW_STRAP2 0x00000003 + /* * The max ram region is for firmwares that scan the address space * with load/store to guess how much RAM the SoC has. @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, &error_abort); object_property_set_int(OBJECT(&bmc->soc), cfg->hw_strap1, "hw-strap1", &error_abort); + object_property_set_int(OBJECT(&bmc->soc), cfg->hw_strap2, "hw-strap2", + &error_abort); object_property_set_int(OBJECT(&bmc->soc), cfg->num_cs, "num-cs", &error_abort); object_property_set_int(OBJECT(&bmc->soc), machine->smp.cpus, "num-cpus", @@ -XXX,XX +XXX,XX @@ static void ast2500_evb_i2c_init(AspeedBoardState *bmc) i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "ds1338", 0x32); } +static void ast2600_evb_i2c_init(AspeedBoardState *bmc) +{ + /* Start with some devices on our I2C busses */ + ast2500_evb_i2c_init(bmc); +} + static void romulus_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .num_cs = 2, .i2c_init = witherspoon_bmc_i2c_init, .ram = 512 * MiB, + }, { + .name = MACHINE_TYPE_NAME("ast2600-evb"), + .desc = "Aspeed AST2600 EVB (Cortex A7)", + .soc_name = "ast2600-a0", + .hw_strap1 = AST2600_EVB_HW_STRAP1, + .hw_strap2 = AST2600_EVB_HW_STRAP2, + .fmc_model = "w25q512jv", + .spi_model = "mx66u51235f", + .num_cs = 1, + .i2c_init = ast2600_evb_i2c_init, + .ram = 1 * GiB, }, }; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create a function to compute the values of the TBFLAG_ANY bits that will be cached. For now, the env->hflags variable is not used, and the results are fed back to cpu_get_tb_cpu_state. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 29 ++++++++++++++++++----------- target/arm/helper.c | 26 +++++++++++++++++++------- 2 files changed, 37 insertions(+), 18 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 @@ typedef struct CPUARMState { uint32_t pstate; uint32_t aarch64; /* 1 if CPU is in aarch64 state; inverse of PSTATE.nRW */ + /* Cached TBFLAGS state. See below for which bits are included. */ + uint32_t hflags; + /* Frequently accessed CPSR bits are stored separately for efficiency. This contains all the other bits. Use cpsr_{read,write} to access the whole CPSR. */ @@ -XXX,XX +XXX,XX @@ typedef ARMCPU ArchCPU; #include "exec/cpu-all.h" -/* Bit usage in the TB flags field: bit 31 indicates whether we are +/* + * Bit usage in the TB flags field: bit 31 indicates whether we are * in 32 or 64 bit mode. The meaning of the other bits depends on that. * We put flags which are shared between 32 and 64 bit mode at the top * of the word, and flags which apply to only one mode at the bottom. + * + * Unless otherwise noted, these bits are cached in env->hflags. */ FIELD(TBFLAG_ANY, AARCH64_STATE, 31, 1) FIELD(TBFLAG_ANY, MMUIDX, 28, 3) FIELD(TBFLAG_ANY, SS_ACTIVE, 27, 1) -FIELD(TBFLAG_ANY, PSTATE_SS, 26, 1) +FIELD(TBFLAG_ANY, PSTATE_SS, 26, 1) /* Not cached. */ /* Target EL if we take a floating-point-disabled exception */ FIELD(TBFLAG_ANY, FPEXC_EL, 24, 2) FIELD(TBFLAG_ANY, BE_DATA, 23, 1) @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_ANY, BE_DATA, 23, 1) FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 21, 2) /* Bit usage when in AArch32 state: */ -FIELD(TBFLAG_A32, THUMB, 0, 1) -FIELD(TBFLAG_A32, VECLEN, 1, 3) -FIELD(TBFLAG_A32, VECSTRIDE, 4, 2) +FIELD(TBFLAG_A32, THUMB, 0, 1) /* Not cached. */ +FIELD(TBFLAG_A32, VECLEN, 1, 3) /* Not cached. */ +FIELD(TBFLAG_A32, VECSTRIDE, 4, 2) /* Not cached. */ /* * We store the bottom two bits of the CPAR as TB flags and handle * checks on the other bits at runtime. This shares the same bits as * VECSTRIDE, which is OK as no XScale CPU has VFP. + * Not cached, because VECLEN+VECSTRIDE are not cached. */ FIELD(TBFLAG_A32, XSCALE_CPAR, 4, 2) /* @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A32, XSCALE_CPAR, 4, 2) * the same thing as the current security state of the processor! */ FIELD(TBFLAG_A32, NS, 6, 1) -FIELD(TBFLAG_A32, VFPEN, 7, 1) -FIELD(TBFLAG_A32, CONDEXEC, 8, 8) +FIELD(TBFLAG_A32, VFPEN, 7, 1) /* Not cached. */ +FIELD(TBFLAG_A32, CONDEXEC, 8, 8) /* Not cached. */ FIELD(TBFLAG_A32, SCTLR_B, 16, 1) /* For M profile only, set if FPCCR.LSPACT is set */ -FIELD(TBFLAG_A32, LSPACT, 18, 1) +FIELD(TBFLAG_A32, LSPACT, 18, 1) /* Not cached. */ /* For M profile only, set if we must create a new FP context */ -FIELD(TBFLAG_A32, NEW_FP_CTXT_NEEDED, 19, 1) +FIELD(TBFLAG_A32, NEW_FP_CTXT_NEEDED, 19, 1) /* Not cached. */ /* For M profile only, set if FPCCR.S does not match current security state */ -FIELD(TBFLAG_A32, FPCCR_S_WRONG, 20, 1) +FIELD(TBFLAG_A32, FPCCR_S_WRONG, 20, 1) /* Not cached. */ /* For M profile only, Handler (ie not Thread) mode */ FIELD(TBFLAG_A32, HANDLER, 21, 1) /* For M profile only, whether we should generate stack-limit checks */ @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, SVEEXC_EL, 2, 2) FIELD(TBFLAG_A64, ZCR_LEN, 4, 4) FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1) FIELD(TBFLAG_A64, BT, 9, 1) -FIELD(TBFLAG_A64, BTYPE, 10, 2) +FIELD(TBFLAG_A64, BTYPE, 10, 2) /* Not cached. */ FIELD(TBFLAG_A64, TBID, 12, 2) static inline bool bswap_code(bool sctlr_b) 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 @@ ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) } #endif +static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx, uint32_t flags) +{ + flags = FIELD_DP32(flags, TBFLAG_ANY, FPEXC_EL, fp_el); + flags = FIELD_DP32(flags, TBFLAG_ANY, MMUIDX, + arm_to_core_mmu_idx(mmu_idx)); + + if (arm_cpu_data_is_big_endian(env)) { + flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); + } + if (arm_singlestep_active(env)) { + flags = FIELD_DP32(flags, TBFLAG_ANY, SS_ACTIVE, 1); + } + return flags; +} + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } - flags = FIELD_DP32(flags, TBFLAG_ANY, MMUIDX, arm_to_core_mmu_idx(mmu_idx)); + flags = rebuild_hflags_common(env, fp_el, mmu_idx, flags); /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine * states defined in the ARM ARM for software singlestep: @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * 0 x Inactive (the TB flag for SS is always 0) * 1 0 Active-pending * 1 1 Active-not-pending + * SS_ACTIVE is set in hflags; PSTATE_SS is computed every TB. */ - if (arm_singlestep_active(env)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, SS_ACTIVE, 1); + if (FIELD_EX32(flags, TBFLAG_ANY, SS_ACTIVE)) { if (is_a64(env)) { if (env->pstate & PSTATE_SS) { flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE_SS, 1); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } } - if (arm_cpu_data_is_big_endian(env)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); - } - flags = FIELD_DP32(flags, TBFLAG_ANY, FPEXC_EL, fp_el); if (arm_v7m_is_handler_mode(env)) { flags = FIELD_DP32(flags, TBFLAG_A32, HANDLER, 1); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create a function to compute the values of the TBFLAG_A64 bits that will be cached. For now, the env->hflags variable is not used, and the results are fed back to cpu_get_tb_cpu_state. Note that not all BTI related flags are cached, so we have to test the BTI feature twice -- once for those bits moved out to rebuild_hflags_a64 and once for those bits that remain in cpu_get_tb_cpu_state. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 131 +++++++++++++++++++++++--------------------- 1 file changed, 69 insertions(+), 62 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 @@ static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, return flags; } +static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, + ARMMMUIdx mmu_idx) +{ + ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); + ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); + uint32_t flags = 0; + uint64_t sctlr; + int tbii, tbid; + + flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); + + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + if (regime_el(env, stage1) < 2) { + ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1); + tbid = (p1.tbi << 1) | p0.tbi; + tbii = tbid & ~((p1.tbid << 1) | p0.tbid); + } else { + tbid = p0.tbi; + tbii = tbid & !p0.tbid; + } + + flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); + flags = FIELD_DP32(flags, TBFLAG_A64, TBID, tbid); + + if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { + int sve_el = sve_exception_el(env, el); + uint32_t zcr_len; + + /* + * If SVE is disabled, but FP is enabled, + * then the effective len is 0. + */ + if (sve_el != 0 && fp_el == 0) { + zcr_len = 0; + } else { + zcr_len = sve_zcr_len_for_el(env, el); + } + flags = FIELD_DP32(flags, TBFLAG_A64, SVEEXC_EL, sve_el); + flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len); + } + + sctlr = arm_sctlr(env, el); + + if (cpu_isar_feature(aa64_pauth, env_archcpu(env))) { + /* + * In order to save space in flags, we record only whether + * pauth is "inactive", meaning all insns are implemented as + * a nop, or "active" when some action must be performed. + * The decision of which action to take is left to a helper. + */ + if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) { + flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1); + } + } + + if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { + /* Note that SCTLR_EL[23].BT == SCTLR_BT1. */ + if (sctlr & (el == 0 ? SCTLR_BT0 : SCTLR_BT1)) { + flags = FIELD_DP32(flags, TBFLAG_A64, BT, 1); + } + } + + return rebuild_hflags_common(env, fp_el, mmu_idx, flags); +} + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, uint32_t flags = 0; if (is_a64(env)) { - ARMCPU *cpu = env_archcpu(env); - uint64_t sctlr; - *pc = env->pc; - flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); - - /* Get control bits for tagged addresses. */ - { - ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); - ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); - int tbii, tbid; - - /* FIXME: ARMv8.1-VHE S2 translation regime. */ - if (regime_el(env, stage1) < 2) { - ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1); - tbid = (p1.tbi << 1) | p0.tbi; - tbii = tbid & ~((p1.tbid << 1) | p0.tbid); - } else { - tbid = p0.tbi; - tbii = tbid & !p0.tbid; - } - - flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); - flags = FIELD_DP32(flags, TBFLAG_A64, TBID, tbid); - } - - if (cpu_isar_feature(aa64_sve, cpu)) { - int sve_el = sve_exception_el(env, current_el); - uint32_t zcr_len; - - /* If SVE is disabled, but FP is enabled, - * then the effective len is 0. - */ - if (sve_el != 0 && fp_el == 0) { - zcr_len = 0; - } else { - zcr_len = sve_zcr_len_for_el(env, current_el); - } - flags = FIELD_DP32(flags, TBFLAG_A64, SVEEXC_EL, sve_el); - flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len); - } - - sctlr = arm_sctlr(env, current_el); - - if (cpu_isar_feature(aa64_pauth, cpu)) { - /* - * In order to save space in flags, we record only whether - * pauth is "inactive", meaning all insns are implemented as - * a nop, or "active" when some action must be performed. - * The decision of which action to take is left to a helper. - */ - if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) { - flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1); - } - } - - if (cpu_isar_feature(aa64_bti, cpu)) { - /* Note that SCTLR_EL[23].BT == SCTLR_BT1. */ - if (sctlr & (current_el == 0 ? SCTLR_BT0 : SCTLR_BT1)) { - flags = FIELD_DP32(flags, TBFLAG_A64, BT, 1); - } + flags = rebuild_hflags_a64(env, current_el, fp_el, mmu_idx); + if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { flags = FIELD_DP32(flags, TBFLAG_A64, BTYPE, env->btype); } } else { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A32, XSCALE_CPAR, env->cp15.c15_cpar); } - } - flags = rebuild_hflags_common(env, fp_el, mmu_idx, flags); + flags = rebuild_hflags_common(env, fp_el, mmu_idx, flags); + } /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine * states defined in the ARM ARM for software singlestep: -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create a function to compute the values of the TBFLAG_A32 bits that will be cached, and are used by all profiles. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 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 @@ static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, return flags; } +static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx, uint32_t flags) +{ + flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR_B, arm_sctlr_b(env)); + flags = FIELD_DP32(flags, TBFLAG_A32, NS, !access_secure_reg(env)); + + return rebuild_hflags_common(env, fp_el, mmu_idx, flags); +} + static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, ARMMMUIdx mmu_idx = arm_mmu_idx(env); int current_el = arm_current_el(env); int fp_el = fp_exception_el(env, current_el); - uint32_t flags = 0; + uint32_t flags; if (is_a64(env)) { *pc = env->pc; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } else { *pc = env->regs[15]; + flags = rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); flags = FIELD_DP32(flags, TBFLAG_A32, VECLEN, env->vfp.vec_len); flags = FIELD_DP32(flags, TBFLAG_A32, VECSTRIDE, env->vfp.vec_stride); flags = FIELD_DP32(flags, TBFLAG_A32, CONDEXEC, env->condexec_bits); - flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR_B, arm_sctlr_b(env)); - flags = FIELD_DP32(flags, TBFLAG_A32, NS, !access_secure_reg(env)); if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30) || arm_el_is_aa64(env, 1) || arm_feature(env, ARM_FEATURE_M)) { flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A32, XSCALE_CPAR, env->cp15.c15_cpar); } - - flags = rebuild_hflags_common(env, fp_el, mmu_idx, flags); } /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Set TBFLAG_ANY.BE_DATA in rebuild_hflags_common_32 and rebuild_hflags_a64 instead of rebuild_hflags_common, where we do not need to re-test is_a64() nor re-compute the various inputs. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 49 +++++++++++++++++++++++++++------------------ target/arm/helper.c | 16 +++++++++++---- 2 files changed, 42 insertions(+), 23 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline uint64_t arm_sctlr(CPUARMState *env, int el) } } +static inline bool arm_cpu_data_is_big_endian_a32(CPUARMState *env, + bool sctlr_b) +{ +#ifdef CONFIG_USER_ONLY + /* + * In system mode, BE32 is modelled in line with the + * architecture (as word-invariant big-endianness), where loads + * and stores are done little endian but from addresses which + * are adjusted by XORing with the appropriate constant. So the + * endianness to use for the raw data access is not affected by + * SCTLR.B. + * In user mode, however, we model BE32 as byte-invariant + * big-endianness (because user-only code cannot tell the + * difference), and so we need to use a data access endianness + * that depends on SCTLR.B. + */ + if (sctlr_b) { + return true; + } +#endif + /* In 32bit endianness is determined by looking at CPSR's E bit */ + return env->uncached_cpsr & CPSR_E; +} + +static inline bool arm_cpu_data_is_big_endian_a64(int el, uint64_t sctlr) +{ + return sctlr & (el ? SCTLR_EE : SCTLR_E0E); +} /* Return true if the processor is in big-endian mode. */ static inline bool arm_cpu_data_is_big_endian(CPUARMState *env) { - /* In 32bit endianness is determined by looking at CPSR's E bit */ if (!is_a64(env)) { - return -#ifdef CONFIG_USER_ONLY - /* In system mode, BE32 is modelled in line with the - * architecture (as word-invariant big-endianness), where loads - * and stores are done little endian but from addresses which - * are adjusted by XORing with the appropriate constant. So the - * endianness to use for the raw data access is not affected by - * SCTLR.B. - * In user mode, however, we model BE32 as byte-invariant - * big-endianness (because user-only code cannot tell the - * difference), and so we need to use a data access endianness - * that depends on SCTLR.B. - */ - arm_sctlr_b(env) || -#endif - ((env->uncached_cpsr & CPSR_E) ? 1 : 0); + return arm_cpu_data_is_big_endian_a32(env, arm_sctlr_b(env)); } else { int cur_el = arm_current_el(env); uint64_t sctlr = arm_sctlr(env, cur_el); - - return (sctlr & (cur_el ? SCTLR_EE : SCTLR_E0E)) != 0; + return arm_cpu_data_is_big_endian_a64(cur_el, sctlr); } } 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 uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, flags = FIELD_DP32(flags, TBFLAG_ANY, MMUIDX, arm_to_core_mmu_idx(mmu_idx)); - if (arm_cpu_data_is_big_endian(env)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); - } if (arm_singlestep_active(env)) { flags = FIELD_DP32(flags, TBFLAG_ANY, SS_ACTIVE, 1); } @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx, uint32_t flags) { - flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR_B, arm_sctlr_b(env)); + bool sctlr_b = arm_sctlr_b(env); + + if (sctlr_b) { + flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR_B, 1); + } + if (arm_cpu_data_is_big_endian_a32(env, sctlr_b)) { + flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); + } flags = FIELD_DP32(flags, TBFLAG_A32, NS, !access_secure_reg(env)); return rebuild_hflags_common(env, fp_el, mmu_idx, flags); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, sctlr = arm_sctlr(env, el); + if (arm_cpu_data_is_big_endian_a64(el, sctlr)) { + flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); + } + if (cpu_isar_feature(aa64_pauth, env_archcpu(env))) { /* * In order to save space in flags, we record only whether -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create a function to compute the values of the TBFLAG_A32 bits that will be cached, and are used by M-profile. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 45 ++++++++++++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 15 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 @@ static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, return rebuild_hflags_common(env, fp_el, mmu_idx, flags); } +static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx) +{ + uint32_t flags = 0; + + if (arm_v7m_is_handler_mode(env)) { + flags = FIELD_DP32(flags, TBFLAG_A32, HANDLER, 1); + } + + /* + * v8M always applies stack limit checks unless CCR.STKOFHFNMIGN + * is suppressing them because the requested execution priority + * is less than 0. + */ + if (arm_feature(env, ARM_FEATURE_V8) && + !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) && + (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) { + flags = FIELD_DP32(flags, TBFLAG_A32, STACKCHECK, 1); + } + + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); +} + static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } else { *pc = env->regs[15]; - flags = rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); + + if (arm_feature(env, ARM_FEATURE_M)) { + flags = rebuild_hflags_m32(env, fp_el, mmu_idx); + } else { + flags = rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); + } + flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); flags = FIELD_DP32(flags, TBFLAG_A32, VECLEN, env->vfp.vec_len); flags = FIELD_DP32(flags, TBFLAG_A32, VECSTRIDE, env->vfp.vec_stride); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } - if (arm_v7m_is_handler_mode(env)) { - flags = FIELD_DP32(flags, TBFLAG_A32, HANDLER, 1); - } - - /* v8M always applies stack limit checks unless CCR.STKOFHFNMIGN is - * suppressing them because the requested execution priority is less than 0. - */ - if (arm_feature(env, ARM_FEATURE_V8) && - arm_feature(env, ARM_FEATURE_M) && - !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) && - (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) { - flags = FIELD_DP32(flags, TBFLAG_A32, STACKCHECK, 1); - } - if (arm_feature(env, ARM_FEATURE_M_SECURITY) && FIELD_EX32(env->v7m.fpccr[M_REG_S], V7M_FPCCR, S) != env->v7m.secure) { flags = FIELD_DP32(flags, TBFLAG_A32, FPCCR_S_WRONG, 1); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Hoist the computation of some TBFLAG_A32 bits that only apply to M-profile under a single test for ARM_FEATURE_M. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 49 +++++++++++++++++++++------------------------ 1 file changed, 23 insertions(+), 26 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 cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (arm_feature(env, ARM_FEATURE_M)) { flags = rebuild_hflags_m32(env, fp_el, mmu_idx); + + if (arm_feature(env, ARM_FEATURE_M_SECURITY) && + FIELD_EX32(env->v7m.fpccr[M_REG_S], V7M_FPCCR, S) + != env->v7m.secure) { + flags = FIELD_DP32(flags, TBFLAG_A32, FPCCR_S_WRONG, 1); + } + + if ((env->v7m.fpccr[env->v7m.secure] & R_V7M_FPCCR_ASPEN_MASK) && + (!(env->v7m.control[M_REG_S] & R_V7M_CONTROL_FPCA_MASK) || + (env->v7m.secure && + !(env->v7m.control[M_REG_S] & R_V7M_CONTROL_SFPA_MASK)))) { + /* + * ASPEN is set, but FPCA/SFPA indicate that there is no + * active FP context; we must create a new FP context before + * executing any FP insn. + */ + flags = FIELD_DP32(flags, TBFLAG_A32, NEW_FP_CTXT_NEEDED, 1); + } + + bool is_secure = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK; + if (env->v7m.fpccr[is_secure] & R_V7M_FPCCR_LSPACT_MASK) { + flags = FIELD_DP32(flags, TBFLAG_A32, LSPACT, 1); + } } else { flags = rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); } @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } - if (arm_feature(env, ARM_FEATURE_M_SECURITY) && - FIELD_EX32(env->v7m.fpccr[M_REG_S], V7M_FPCCR, S) != env->v7m.secure) { - flags = FIELD_DP32(flags, TBFLAG_A32, FPCCR_S_WRONG, 1); - } - - if (arm_feature(env, ARM_FEATURE_M) && - (env->v7m.fpccr[env->v7m.secure] & R_V7M_FPCCR_ASPEN_MASK) && - (!(env->v7m.control[M_REG_S] & R_V7M_CONTROL_FPCA_MASK) || - (env->v7m.secure && - !(env->v7m.control[M_REG_S] & R_V7M_CONTROL_SFPA_MASK)))) { - /* - * ASPEN is set, but FPCA/SFPA indicate that there is no active - * FP context; we must create a new FP context before executing - * any FP insn. - */ - flags = FIELD_DP32(flags, TBFLAG_A32, NEW_FP_CTXT_NEEDED, 1); - } - - if (arm_feature(env, ARM_FEATURE_M)) { - bool is_secure = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK; - - if (env->v7m.fpccr[is_secure] & R_V7M_FPCCR_LSPACT_MASK) { - flags = FIELD_DP32(flags, TBFLAG_A32, LSPACT, 1); - } - } - if (!arm_feature(env, ARM_FEATURE_M)) { int target_el = arm_debug_target_el(env); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Currently a trivial wrapper for rebuild_hflags_common_32. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 8 +++++++- 1 file changed, 7 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 @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } +static uint32_t rebuild_hflags_a32(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx) +{ + return rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); +} + static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A32, LSPACT, 1); } } else { - flags = rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); + flags = rebuild_hflags_a32(env, fp_el, mmu_idx); } flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create a function to compute the values of the TBFLAG_ANY bits that will be cached, and are used by A-profile. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 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 @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } +static uint32_t rebuild_hflags_aprofile(CPUARMState *env) +{ + int flags = 0; + + flags = FIELD_DP32(flags, TBFLAG_ANY, DEBUG_TARGET_EL, + arm_debug_target_el(env)); + return flags; +} + static uint32_t rebuild_hflags_a32(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx) { - return rebuild_hflags_common_32(env, fp_el, mmu_idx, 0); + uint32_t flags = rebuild_hflags_aprofile(env); + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, ARMMMUIdx mmu_idx) { + uint32_t flags = rebuild_hflags_aprofile(env); ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); - uint32_t flags = 0; uint64_t sctlr; int tbii, tbid; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } - if (!arm_feature(env, ARM_FEATURE_M)) { - int target_el = arm_debug_target_el(env); - - flags = FIELD_DP32(flags, TBFLAG_ANY, DEBUG_TARGET_EL, target_el); - } - *pflags = flags; *cs_base = 0; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We do not need to compute any of these values for M-profile. Further, XSCALE_CPAR overlaps VECSTRIDE so obviously the two sets must be mutually exclusive. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 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 cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } else { flags = rebuild_hflags_a32(env, fp_el, mmu_idx); + + /* + * Note that XSCALE_CPAR shares bits with VECSTRIDE. + * Note that VECLEN+VECSTRIDE are RES0 for M-profile. + */ + if (arm_feature(env, ARM_FEATURE_XSCALE)) { + flags = FIELD_DP32(flags, TBFLAG_A32, + XSCALE_CPAR, env->cp15.c15_cpar); + } else { + flags = FIELD_DP32(flags, TBFLAG_A32, VECLEN, + env->vfp.vec_len); + flags = FIELD_DP32(flags, TBFLAG_A32, VECSTRIDE, + env->vfp.vec_stride); + } } flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); - flags = FIELD_DP32(flags, TBFLAG_A32, VECLEN, env->vfp.vec_len); - flags = FIELD_DP32(flags, TBFLAG_A32, VECSTRIDE, env->vfp.vec_stride); flags = FIELD_DP32(flags, TBFLAG_A32, CONDEXEC, env->condexec_bits); if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30) || arm_el_is_aa64(env, 1) || arm_feature(env, ARM_FEATURE_M)) { flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); } - /* Note that XSCALE_CPAR shares bits with VECSTRIDE */ - if (arm_feature(env, ARM_FEATURE_XSCALE)) { - flags = FIELD_DP32(flags, TBFLAG_A32, - XSCALE_CPAR, env->cp15.c15_cpar); - } } /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Hoist the variable load for PSTATE into the existing test vs is_a64. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 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 cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, ARMMMUIdx mmu_idx = arm_mmu_idx(env); int current_el = arm_current_el(env); int fp_el = fp_exception_el(env, current_el); - uint32_t flags; + uint32_t flags, pstate_for_ss; if (is_a64(env)) { *pc = env->pc; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { flags = FIELD_DP32(flags, TBFLAG_A64, BTYPE, env->btype); } + pstate_for_ss = env->pstate; } else { *pc = env->regs[15]; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, || arm_el_is_aa64(env, 1) || arm_feature(env, ARM_FEATURE_M)) { flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); } + pstate_for_ss = env->uncached_cpsr; } - /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine + /* + * The SS_ACTIVE and PSTATE_SS bits correspond to the state machine * states defined in the ARM ARM for software singlestep: * SS_ACTIVE PSTATE.SS State * 0 x Inactive (the TB flag for SS is always 0) @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * 1 1 Active-not-pending * SS_ACTIVE is set in hflags; PSTATE_SS is computed every TB. */ - if (FIELD_EX32(flags, TBFLAG_ANY, SS_ACTIVE)) { - if (is_a64(env)) { - if (env->pstate & PSTATE_SS) { - flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE_SS, 1); - } - } else { - if (env->uncached_cpsr & PSTATE_SS) { - flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE_SS, 1); - } - } + if (FIELD_EX32(flags, TBFLAG_ANY, SS_ACTIVE) && + (pstate_for_ss & PSTATE_SS)) { + flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE_SS, 1); } *pflags = flags; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> There are 3 conditions that each enable this flag. M-profile always enables; A-profile with EL1 as AA64 always enables. Both of these conditions can easily be cached. The final condition relies on the FPEXC register which we are not prepared to cache. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- target/arm/helper.c | 14 ++++++++++---- 2 files changed, 11 insertions(+), 5 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 @@ FIELD(TBFLAG_A32, XSCALE_CPAR, 4, 2) * the same thing as the current security state of the processor! */ FIELD(TBFLAG_A32, NS, 6, 1) -FIELD(TBFLAG_A32, VFPEN, 7, 1) /* Not cached. */ +FIELD(TBFLAG_A32, VFPEN, 7, 1) /* Partially cached, minus FPEXC. */ FIELD(TBFLAG_A32, CONDEXEC, 8, 8) /* Not cached. */ FIELD(TBFLAG_A32, SCTLR_B, 16, 1) /* For M profile only, set if FPCCR.LSPACT is set */ 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 uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, { uint32_t flags = 0; + /* v8M always enables the fpu. */ + flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); + if (arm_v7m_is_handler_mode(env)) { flags = FIELD_DP32(flags, TBFLAG_A32, HANDLER, 1); } @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a32(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx) { uint32_t flags = rebuild_hflags_aprofile(env); + + if (arm_el_is_aa64(env, 1)) { + flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); + } return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A32, VECSTRIDE, env->vfp.vec_stride); } + if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30)) { + flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); + } } flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); flags = FIELD_DP32(flags, TBFLAG_A32, CONDEXEC, env->condexec_bits); - if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30) - || arm_el_is_aa64(env, 1) || arm_feature(env, ARM_FEATURE_M)) { - flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); - } pstate_for_ss = env->uncached_cpsr; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This function assumes nothing about the current state of the cpu, and writes the computed value to env->hflags. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 ++++++ target/arm/helper.c | 30 ++++++++++++++++++++++-------- 2 files changed, 28 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 @@ void arm_register_pre_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, void *opaque); +/** + * arm_rebuild_hflags: + * Rebuild the cached TBFLAGS for arbitrary changed processor state. + */ +void arm_rebuild_hflags(CPUARMState *env); + /** * aa32_vfp_dreg: * Return a pointer to the Dn register within env in 32-bit mode. 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 uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, return rebuild_hflags_common(env, fp_el, mmu_idx, flags); } +static uint32_t rebuild_hflags_internal(CPUARMState *env) +{ + int el = arm_current_el(env); + int fp_el = fp_exception_el(env, el); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + + if (is_a64(env)) { + return rebuild_hflags_a64(env, el, fp_el, mmu_idx); + } else if (arm_feature(env, ARM_FEATURE_M)) { + return rebuild_hflags_m32(env, fp_el, mmu_idx); + } else { + return rebuild_hflags_a32(env, fp_el, mmu_idx); + } +} + +void arm_rebuild_hflags(CPUARMState *env) +{ + env->hflags = rebuild_hflags_internal(env); +} + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { - ARMMMUIdx mmu_idx = arm_mmu_idx(env); - int current_el = arm_current_el(env); - int fp_el = fp_exception_el(env, current_el); uint32_t flags, pstate_for_ss; + flags = rebuild_hflags_internal(env); + if (is_a64(env)) { *pc = env->pc; - flags = rebuild_hflags_a64(env, current_el, fp_el, mmu_idx); if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { flags = FIELD_DP32(flags, TBFLAG_A64, BTYPE, env->btype); } @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *pc = env->regs[15]; if (arm_feature(env, ARM_FEATURE_M)) { - flags = rebuild_hflags_m32(env, fp_el, mmu_idx); - if (arm_feature(env, ARM_FEATURE_M_SECURITY) && FIELD_EX32(env->v7m.fpccr[M_REG_S], V7M_FPCCR, S) != env->v7m.secure) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A32, LSPACT, 1); } } else { - flags = rebuild_hflags_a32(env, fp_el, mmu_idx); - /* * Note that XSCALE_CPAR shares bits with VECSTRIDE. * Note that VECLEN+VECSTRIDE are RES0 for M-profile. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Avoid calling arm_current_el() twice. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 9 +++++++++ target/arm/helper.c | 12 +++++++----- 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ void arm_cpu_update_virq(ARMCPU *cpu); */ void arm_cpu_update_vfiq(ARMCPU *cpu); +/** + * arm_mmu_idx_el: + * @env: The cpu environment + * @el: The EL to use. + * + * Return the full ARMMMUIdx for the translation regime for EL. + */ +ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el); + /** * arm_mmu_idx: * @env: The cpu environment 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 @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) } #endif -ARMMMUIdx arm_mmu_idx(CPUARMState *env) +ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el) { - int el; - if (arm_feature(env, ARM_FEATURE_M)) { return arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); } - el = arm_current_el(env); if (el < 2 && arm_is_secure_below_el3(env)) { return ARMMMUIdx_S1SE0 + el; } else { @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_mmu_idx(CPUARMState *env) } } +ARMMMUIdx arm_mmu_idx(CPUARMState *env) +{ + return arm_mmu_idx_el(env, arm_current_el(env)); +} + int cpu_mmu_index(CPUARMState *env, bool ifetch) { return arm_to_core_mmu_idx(arm_mmu_idx(env)); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_internal(CPUARMState *env) { int el = arm_current_el(env); int fp_el = fp_exception_el(env, el); - ARMMMUIdx mmu_idx = arm_mmu_idx(env); + ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, el); if (is_a64(env)) { return rebuild_hflags_a64(env, el, fp_el, mmu_idx); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> By performing this store early, we avoid having to save and restore the register holding the address around any function calls. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, { uint32_t flags, pstate_for_ss; + *cs_base = 0; flags = rebuild_hflags_internal(env); if (is_a64(env)) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } *pflags = flags; - *cs_base = 0; } #ifdef TARGET_AARCH64 -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This functions are given the mode and el state of the cpu and writes the computed value to env->hflags. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 4 ++++ target/arm/helper.c | 24 ++++++++++++++++++++++++ 2 files changed, 28 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_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_2(rebuild_hflags_m32, TCG_CALL_NO_RWG, void, env, int) +DEF_HELPER_FLAGS_2(rebuild_hflags_a32, TCG_CALL_NO_RWG, void, env, int) +DEF_HELPER_FLAGS_2(rebuild_hflags_a64, TCG_CALL_NO_RWG, void, env, int) + DEF_HELPER_1(vfp_get_fpscr, i32, env) DEF_HELPER_2(vfp_set_fpscr, void, env, i32) 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); } +void HELPER(rebuild_hflags_m32)(CPUARMState *env, int el) +{ + 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_a32)(CPUARMState *env, int el) +{ + int fp_el = fp_exception_el(env, el); + ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, el); + + env->hflags = rebuild_hflags_a32(env, fp_el, mmu_idx); +} + +void HELPER(rebuild_hflags_a64)(CPUARMState *env, int el) +{ + int fp_el = fp_exception_el(env, el); + ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, el); + + env->hflags = rebuild_hflags_a64(env, el, fp_el, mmu_idx); +} + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Begin setting, but not relying upon, env->hflags. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/syscall.c | 1 + target/arm/cpu.c | 1 + target/arm/helper-a64.c | 3 +++ target/arm/helper.c | 2 ++ target/arm/machine.c | 1 + target/arm/op_helper.c | 1 + 6 files changed, 9 insertions(+) diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, aarch64_sve_narrow_vq(env, vq); } env->vfp.zcr_el[1] = vq - 1; + arm_rebuild_hflags(env); ret = vq * 16; } return ret; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) hw_breakpoint_update_all(cpu); hw_watchpoint_update_all(cpu); + arm_rebuild_hflags(env); } bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) } else { env->regs[15] = new_pc & ~0x3; } + helper_rebuild_hflags_a32(env, new_el); qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " "AArch32 EL%d PC 0x%" PRIx32 "\n", cur_el, new_el, env->regs[15]); @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) } aarch64_restore_sp(env, new_el); env->pc = new_pc; + helper_rebuild_hflags_a64(env, new_el); qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " "AArch64 EL%d PC 0x%" PRIx64 "\n", cur_el, new_el, env->pc); } + /* * Note that cur_el can never be 0. If new_el is 0, then * el0_a64 is return_to_aa64, else el0_a64 is ignored. 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 take_aarch32_exception(CPUARMState *env, int new_mode, env->regs[14] = env->regs[15] + offset; } env->regs[15] = newpc; + arm_rebuild_hflags(env); } static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) pstate_write(env, PSTATE_DAIF | new_mode); env->aarch64 = 1; aarch64_restore_sp(env, new_el); + helper_rebuild_hflags_a64(env, new_el); env->pc = addr; diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id) if (!kvm_enabled()) { pmu_op_finish(&cpu->env); } + arm_rebuild_hflags(&cpu->env); return 0; } diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(cpsr_write_eret)(CPUARMState *env, uint32_t val) * state. Do the masking now. */ env->regs[15] &= (env->thumb ? ~1 : ~3); + arm_rebuild_hflags(env); qemu_mutex_lock_iothread(); arm_call_el_change_hook(env_archcpu(env)); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 13 +++++++++++-- target/arm/translate.c | 28 +++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 7 deletions(-) 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 handle_sys(DisasContext *s, uint32_t insn, bool isread, if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { /* I/O operations must end the TB here (whether read or write) */ s->base.is_jmp = DISAS_UPDATE; - } else if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { - /* We default to ending the TB on a coprocessor register write, + } + if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { + /* + * A write to any coprocessor regiser that ends a TB + * must rebuild the hflags for the next TB. + */ + TCGv_i32 tcg_el = tcg_const_i32(s->current_el); + gen_helper_rebuild_hflags_a64(cpu_env, tcg_el); + tcg_temp_free_i32(tcg_el); + /* + * We default to ending the TB on a coprocessor register write, * but allow this to be suppressed by the register definition * (usually only necessary to work around guest bugs). */ 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) ri = get_arm_cp_reginfo(s->cp_regs, ENCODE_CP_REG(cpnum, is64, s->ns, crn, crm, opc1, opc2)); if (ri) { + bool need_exit_tb; + /* Check access permissions */ if (!cp_access_ok(s->current_el, ri, isread)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) } } - if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { - /* I/O operations must end the TB here (whether read or write) */ - gen_lookup_tb(s); - } else if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { - /* We default to ending the TB on a coprocessor register write, + /* I/O operations must end the TB here (whether read or write) */ + need_exit_tb = ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && + (ri->type & ARM_CP_IO)); + + if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { + /* + * A write to any coprocessor regiser that ends a TB + * must rebuild the hflags for the next TB. + */ + TCGv_i32 tcg_el = tcg_const_i32(s->current_el); + if (arm_dc_feature(s, ARM_FEATURE_M)) { + gen_helper_rebuild_hflags_m32(cpu_env, tcg_el); + } else { + gen_helper_rebuild_hflags_a32(cpu_env, tcg_el); + } + tcg_temp_free_i32(tcg_el); + /* + * We default to ending the TB on a coprocessor register write, * but allow this to be suppressed by the register definition * (usually only necessary to work around guest bugs). */ + need_exit_tb = true; + } + if (need_exit_tb) { gen_lookup_tb(s); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/op_helper.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(usat16)(CPUARMState *env, uint32_t x, uint32_t shift) void HELPER(setend)(CPUARMState *env) { env->uncached_cpsr ^= CPSR_E; + arm_rebuild_hflags(env); } /* Function checks whether WFx (WFI/WFE) instructions are set up to be trapped. @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(cpsr_read)(CPUARMState *env) void HELPER(cpsr_write)(CPUARMState *env, uint32_t val, uint32_t mask) { cpsr_write(env, val, mask, CPSRWriteByInstr); + /* TODO: Not all cpsr bits are relevant to hflags. */ + arm_rebuild_hflags(env); } /* Write the CPSR for a 32-bit exception return */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, /* ??? Lots of these bits are not implemented. */ /* This may enable/disable the MMU, so do a TLB flush. */ tlb_flush(CPU(cpu)); + + if (ri->type & ARM_CP_SUPPRESS_TB_END) { + /* + * Normally we would always end the TB on an SCTLR write; see the + * comment in ARMCPRegInfo sctlr initialization below for why Xscale + * is special. Setting ARM_CP_SUPPRESS_TB_END also stops the rebuild + * of hflags from the translator, so do it here. + */ + arm_rebuild_hflags(env); + } } static CPAccessResult fpexc32_access(CPUARMState *env, const ARMCPRegInfo *ri, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/m_helper.c | 6 ++++++ target/arm/translate.c | 5 ++++- 2 files changed, 10 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 @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest) switch_v7m_security_state(env, dest & 1); env->thumb = 1; env->regs[15] = dest & ~1; + arm_rebuild_hflags(env); } void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) switch_v7m_security_state(env, 0); env->thumb = 1; env->regs[15] = dest; + arm_rebuild_hflags(env); } static uint32_t *get_v7m_sp_ptr(CPUARMState *env, bool secure, bool threadmode, @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, env->regs[14] = lr; env->regs[15] = addr & 0xfffffffe; env->thumb = addr & 1; + arm_rebuild_hflags(env); } static void v7m_update_fpccr(CPUARMState *env, uint32_t frameptr, @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) /* Otherwise, we have a successful exception exit. */ arm_clear_exclusive(env); + arm_rebuild_hflags(env); qemu_log_mask(CPU_LOG_INT, "...successful exception return\n"); } @@ -XXX,XX +XXX,XX @@ static bool do_v7m_function_return(ARMCPU *cpu) xpsr_write(env, 0, XPSR_IT); env->thumb = newpc & 1; env->regs[15] = newpc & ~1; + arm_rebuild_hflags(env); qemu_log_mask(CPU_LOG_INT, "...function return successful\n"); return true; @@ -XXX,XX +XXX,XX @@ static bool v7m_handle_execute_nsc(ARMCPU *cpu) switch_v7m_security_state(env, true); xpsr_write(env, 0, XPSR_IT); env->regs[15] += 4; + arm_rebuild_hflags(env); return true; gen_invep: 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; + TCGv_i32 addr, reg, el; 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); gen_lookup_tb(s); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/armv7m_nvic.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) 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 MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, } } nvic_irq_update(s); - return MEMTX_OK; + goto exit_ok; case 0x200 ... 0x23f: /* NVIC Set pend */ /* the special logic in armv7m_nvic_set_pending() * is not needed since IRQs are never escalated @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, } } nvic_irq_update(s); - return MEMTX_OK; + goto exit_ok; case 0x300 ... 0x33f: /* NVIC Active */ - return MEMTX_OK; /* R/O */ + goto exit_ok; /* R/O */ case 0x400 ... 0x5ef: /* NVIC Priority */ startvec = (offset - 0x400) + NVIC_FIRST_IRQ; /* vector # */ @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, } } nvic_irq_update(s); - return MEMTX_OK; + goto exit_ok; case 0xd18 ... 0xd1b: /* System Handler Priority (SHPR1) */ if (!arm_feature(&s->cpu->env, ARM_FEATURE_M_MAIN)) { - return MEMTX_OK; + goto exit_ok; } /* fall through */ case 0xd1c ... 0xd23: /* System Handler Priority (SHPR2, SHPR3) */ @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, set_prio(s, hdlidx, sbank, newprio); } nvic_irq_update(s); - return MEMTX_OK; + goto exit_ok; case 0xd28 ... 0xd2b: /* Configurable Fault Status (CFSR) */ if (!arm_feature(&s->cpu->env, ARM_FEATURE_M_MAIN)) { - return MEMTX_OK; + goto exit_ok; } /* All bits are W1C, so construct 32 bit value with 0s in * the parts not written by the access size @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, */ s->cpu->env.v7m.cfsr[M_REG_NS] &= ~(value & R_V7M_CFSR_BFSR_MASK); } - return MEMTX_OK; + goto exit_ok; } if (size == 4) { nvic_writel(s, offset, value, attrs); - return MEMTX_OK; + goto exit_ok; } qemu_log_mask(LOG_GUEST_ERROR, "NVIC: Bad write of size %d at offset 0x%x\n", size, offset); /* This is UNPREDICTABLE; treat as RAZ/WI */ + + exit_ok: + /* Ensure any changes made are reflected in the cached hflags. */ + arm_rebuild_hflags(&s->cpu->env); return MEMTX_OK; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-23-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/cpu_loop.c | 1 + 1 file changed, 1 insertion(+) diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs) for (i = 1; i < 4; ++i) { env->cp15.sctlr_el[i] |= SCTLR_EE; } + arm_rebuild_hflags(env); #endif if (cpu_isar_feature(aa64_pauth, cpu)) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Continue setting, but not relying upon, env->hflags. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-24-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/arm/cpu_loop.c | 1 + 1 file changed, 1 insertion(+) diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/cpu_loop.c +++ b/linux-user/arm/cpu_loop.c @@ -XXX,XX +XXX,XX @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs) } else { env->cp15.sctlr_el[1] |= SCTLR_B; } + arm_rebuild_hflags(env); #endif ts->stack_base = info->start_stack; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This is the payoff. From perf record -g data of ubuntu 18 boot and shutdown: BEFORE: - 23.02% 2.82% qemu-system-aar [.] helper_lookup_tb_ptr - 20.22% helper_lookup_tb_ptr + 10.05% tb_htable_lookup - 9.13% cpu_get_tb_cpu_state 3.20% aa64_va_parameters_both 0.55% fp_exception_el - 11.66% 4.74% qemu-system-aar [.] cpu_get_tb_cpu_state - 6.96% cpu_get_tb_cpu_state 3.63% aa64_va_parameters_both 0.60% fp_exception_el 0.53% sve_exception_el AFTER: - 16.40% 3.40% qemu-system-aar [.] helper_lookup_tb_ptr - 13.03% helper_lookup_tb_ptr + 11.19% tb_htable_lookup 0.55% cpu_get_tb_cpu_state 0.98% 0.71% qemu-system-aar [.] cpu_get_tb_cpu_state 0.87% 0.24% qemu-system-aar [.] rebuild_hflags_a64 Before, helper_lookup_tb_ptr is the second hottest function in the application, consuming almost a quarter of the runtime. Within the entire execution, cpu_get_tb_cpu_state consumes about 12%. After, helper_lookup_tb_ptr has dropped to the fourth hottest function, with consumption dropping to a sixth of the runtime. Within the entire execution, cpu_get_tb_cpu_state has dropped below 1%, and the supporting function to rebuild hflags also consumes about 1%. Assertions are retained for --enable-debug-tcg. Tested-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191023150057.25731-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 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_a64)(CPUARMState *env, int el) void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { - uint32_t flags, pstate_for_ss; + uint32_t flags = env->hflags; + uint32_t pstate_for_ss; *cs_base = 0; - flags = rebuild_hflags_internal(env); +#ifdef CONFIG_DEBUG_TCG + assert(flags == rebuild_hflags_internal(env)); +#endif - if (is_a64(env)) { + if (FIELD_EX32(flags, TBFLAG_ANY, AARCH64_STATE)) { *pc = env->pc; if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { flags = FIELD_DP32(flags, TBFLAG_A64, BTYPE, env->btype); -- 2.20.1 Switch the fsl_etsec code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191017132122.4402-2-peter.maydell@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/fsl_etsec/etsec.h | 1 - hw/net/fsl_etsec/etsec.c | 9 +++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/hw/net/fsl_etsec/etsec.h b/hw/net/fsl_etsec/etsec.h index XXXXXXX..XXXXXXX 100644 --- a/hw/net/fsl_etsec/etsec.h +++ b/hw/net/fsl_etsec/etsec.h @@ -XXX,XX +XXX,XX @@ typedef struct eTSEC { uint16_t phy_control; /* Polling */ - QEMUBH *bh; struct ptimer_state *ptimer; /* Whether we should flush the rx queue when buffer becomes available. */ diff --git a/hw/net/fsl_etsec/etsec.c b/hw/net/fsl_etsec/etsec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/fsl_etsec/etsec.c +++ b/hw/net/fsl_etsec/etsec.c @@ -XXX,XX +XXX,XX @@ #include "etsec.h" #include "registers.h" #include "qemu/log.h" -#include "qemu/main-loop.h" #include "qemu/module.h" /* #define HEX_DUMP */ @@ -XXX,XX +XXX,XX @@ static void write_dmactrl(eTSEC *etsec, if (!(value & DMACTRL_WOP)) { /* Start polling */ + ptimer_transaction_begin(etsec->ptimer); ptimer_stop(etsec->ptimer); ptimer_set_count(etsec->ptimer, 1); ptimer_run(etsec->ptimer, 1); + ptimer_transaction_commit(etsec->ptimer); } } @@ -XXX,XX +XXX,XX @@ static void etsec_realize(DeviceState *dev, Error **errp) object_get_typename(OBJECT(dev)), dev->id, etsec); qemu_format_nic_info_str(qemu_get_queue(etsec->nic), etsec->conf.macaddr.a); - - etsec->bh = qemu_bh_new(etsec_timer_hit, etsec); - etsec->ptimer = ptimer_init_with_bh(etsec->bh, PTIMER_POLICY_DEFAULT); + etsec->ptimer = ptimer_init(etsec_timer_hit, etsec, PTIMER_POLICY_DEFAULT); + ptimer_transaction_begin(etsec->ptimer); ptimer_set_freq(etsec->ptimer, 100); + ptimer_transaction_commit(etsec->ptimer); } static void etsec_instance_init(Object *obj) -- 2.20.1 Switch the xilinx_timer code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191017132122.4402-3-peter.maydell@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/xilinx_timer.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/hw/timer/xilinx_timer.c b/hw/timer/xilinx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/xilinx_timer.c +++ b/hw/timer/xilinx_timer.c @@ -XXX,XX +XXX,XX @@ #include "hw/ptimer.h" #include "hw/qdev-properties.h" #include "qemu/log.h" -#include "qemu/main-loop.h" #include "qemu/module.h" #define D(x) @@ -XXX,XX +XXX,XX @@ struct xlx_timer { - QEMUBH *bh; ptimer_state *ptimer; void *parent; int nr; /* for debug. */ @@ -XXX,XX +XXX,XX @@ timer_read(void *opaque, hwaddr addr, unsigned int size) return r; } +/* Must be called inside ptimer transaction block */ static void timer_enable(struct xlx_timer *xt) { uint64_t count; @@ -XXX,XX +XXX,XX @@ timer_write(void *opaque, hwaddr addr, value &= ~TCSR_TINT; xt->regs[addr] = value & 0x7ff; - if (value & TCSR_ENT) + if (value & TCSR_ENT) { + ptimer_transaction_begin(xt->ptimer); timer_enable(xt); + ptimer_transaction_commit(xt->ptimer); + } break; default: @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_realize(DeviceState *dev, Error **errp) xt->parent = t; xt->nr = i; - xt->bh = qemu_bh_new(timer_hit, xt); - xt->ptimer = ptimer_init_with_bh(xt->bh, PTIMER_POLICY_DEFAULT); + xt->ptimer = ptimer_init(timer_hit, xt, PTIMER_POLICY_DEFAULT); + ptimer_transaction_begin(xt->ptimer); ptimer_set_freq(xt->ptimer, t->freq_hz); + ptimer_transaction_commit(xt->ptimer); } memory_region_init_io(&t->mmio, OBJECT(t), &timer_ops, t, "xlnx.xps-timer", -- 2.20.1 Switch the xilinx_axidma code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191017132122.4402-4-peter.maydell@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xilinx_axidma.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/hw/dma/xilinx_axidma.c b/hw/dma/xilinx_axidma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xilinx_axidma.c +++ b/hw/dma/xilinx_axidma.c @@ -XXX,XX +XXX,XX @@ #include "hw/ptimer.h" #include "hw/qdev-properties.h" #include "qemu/log.h" -#include "qemu/main-loop.h" #include "qemu/module.h" #include "hw/stream.h" @@ -XXX,XX +XXX,XX @@ enum { }; struct Stream { - QEMUBH *bh; ptimer_state *ptimer; qemu_irq irq; @@ -XXX,XX +XXX,XX @@ static void stream_complete(struct Stream *s) unsigned int comp_delay; /* Start the delayed timer. */ + ptimer_transaction_begin(s->ptimer); comp_delay = s->regs[R_DMACR] >> 24; if (comp_delay) { ptimer_stop(s->ptimer); @@ -XXX,XX +XXX,XX @@ static void stream_complete(struct Stream *s) s->regs[R_DMASR] |= DMASR_IOC_IRQ; stream_reload_complete_cnt(s); } + ptimer_transaction_commit(s->ptimer); } static void stream_process_mem2s(struct Stream *s, StreamSlave *tx_data_dev, @@ -XXX,XX +XXX,XX @@ static void xilinx_axidma_realize(DeviceState *dev, Error **errp) struct Stream *st = &s->streams[i]; st->nr = i; - st->bh = qemu_bh_new(timer_hit, st); - st->ptimer = ptimer_init_with_bh(st->bh, PTIMER_POLICY_DEFAULT); + st->ptimer = ptimer_init(timer_hit, st, PTIMER_POLICY_DEFAULT); + ptimer_transaction_begin(st->ptimer); ptimer_set_freq(st->ptimer, s->freqhz); + ptimer_transaction_commit(st->ptimer); } return; -- 2.20.1 In the slavio timer devcie, the ptimer TimerContext::timer is always created by slavio_timer_init(), so there's no need to check it for NULL; remove the single unneeded NULL check. This will be useful to avoid compiler/Coverity errors when a subsequent change adds a use of t->timer before the location we currently do the NULL check. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191021134357.14266-2-peter.maydell@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/slavio_timer.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/hw/timer/slavio_timer.c b/hw/timer/slavio_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/slavio_timer.c +++ b/hw/timer/slavio_timer.c @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, // set limit, reset counter qemu_irq_lower(t->irq); t->limit = val & TIMER_MAX_COUNT32; - if (t->timer) { - if (t->limit == 0) { /* free-run */ - ptimer_set_limit(t->timer, - LIMIT_TO_PERIODS(TIMER_MAX_COUNT32), 1); - } else { - ptimer_set_limit(t->timer, LIMIT_TO_PERIODS(t->limit), 1); - } + if (t->limit == 0) { /* free-run */ + ptimer_set_limit(t->timer, + LIMIT_TO_PERIODS(TIMER_MAX_COUNT32), 1); + } else { + ptimer_set_limit(t->timer, LIMIT_TO_PERIODS(t->limit), 1); } } break; -- 2.20.1 Switch the slavio_timer code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20191021134357.14266-4-peter.maydell@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/slavio_timer.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/hw/timer/slavio_timer.c b/hw/timer/slavio_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/slavio_timer.c +++ b/hw/timer/slavio_timer.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "migration/vmstate.h" #include "trace.h" -#include "qemu/main-loop.h" #include "qemu/module.h" /* @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, saddr = addr >> 2; switch (saddr) { case TIMER_LIMIT: + ptimer_transaction_begin(t->timer); if (slavio_timer_is_user(tc)) { uint64_t count; @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, ptimer_set_limit(t->timer, LIMIT_TO_PERIODS(t->limit), 1); } } + ptimer_transaction_commit(t->timer); break; case TIMER_COUNTER: if (slavio_timer_is_user(tc)) { @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, t->reached = 0; count = ((uint64_t)t->counthigh) << 32 | t->count; trace_slavio_timer_mem_writel_limit(timer_index, count); + ptimer_transaction_begin(t->timer); ptimer_set_count(t->timer, LIMIT_TO_PERIODS(t->limit - count)); + ptimer_transaction_commit(t->timer); } else { trace_slavio_timer_mem_writel_counter_invalid(); } @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, case TIMER_COUNTER_NORST: // set limit without resetting counter t->limit = val & TIMER_MAX_COUNT32; + ptimer_transaction_begin(t->timer); if (t->limit == 0) { /* free-run */ ptimer_set_limit(t->timer, LIMIT_TO_PERIODS(TIMER_MAX_COUNT32), 0); } else { ptimer_set_limit(t->timer, LIMIT_TO_PERIODS(t->limit), 0); } + ptimer_transaction_commit(t->timer); break; case TIMER_STATUS: + ptimer_transaction_begin(t->timer); if (slavio_timer_is_user(tc)) { // start/stop user counter if (val & 1) { @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, } } t->run = val & 1; + ptimer_transaction_commit(t->timer); break; case TIMER_MODE: if (timer_index == 0) { @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, unsigned int processor = 1 << i; CPUTimerState *curr_timer = &s->cputimer[i + 1]; + ptimer_transaction_begin(curr_timer->timer); // check for a change in timer mode for this processor if ((val & processor) != (s->cputimer_mode & processor)) { if (val & processor) { // counter -> user timer @@ -XXX,XX +XXX,XX @@ static void slavio_timer_mem_writel(void *opaque, hwaddr addr, trace_slavio_timer_mem_writel_mode_counter(timer_index); } } + ptimer_transaction_commit(curr_timer->timer); } } else { trace_slavio_timer_mem_writel_mode_invalid(); @@ -XXX,XX +XXX,XX @@ static void slavio_timer_reset(DeviceState *d) curr_timer->count = 0; curr_timer->reached = 0; if (i <= s->num_cpus) { + ptimer_transaction_begin(curr_timer->timer); ptimer_set_limit(curr_timer->timer, LIMIT_TO_PERIODS(TIMER_MAX_COUNT32), 1); ptimer_run(curr_timer->timer, 0); curr_timer->run = 1; + ptimer_transaction_commit(curr_timer->timer); } } s->cputimer_mode = 0; @@ -XXX,XX +XXX,XX @@ static void slavio_timer_init(Object *obj) { SLAVIO_TIMERState *s = SLAVIO_TIMER(obj); SysBusDevice *dev = SYS_BUS_DEVICE(obj); - QEMUBH *bh; unsigned int i; TimerContext *tc; @@ -XXX,XX +XXX,XX @@ static void slavio_timer_init(Object *obj) tc->s = s; tc->timer_index = i; - bh = qemu_bh_new(slavio_timer_irq, tc); - s->cputimer[i].timer = ptimer_init_with_bh(bh, PTIMER_POLICY_DEFAULT); + s->cputimer[i].timer = ptimer_init(slavio_timer_irq, tc, + PTIMER_POLICY_DEFAULT); + ptimer_transaction_begin(s->cputimer[i].timer); ptimer_set_period(s->cputimer[i].timer, TIMER_PERIOD); + ptimer_transaction_commit(s->cputimer[i].timer); size = i == 0 ? SYS_TIMER_SIZE : CPU_TIMER_SIZE; snprintf(timer_name, sizeof(timer_name), "timer-%i", i); -- 2.20.1 Switch the grlib_gptimer code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20191021134357.14266-3-peter.maydell@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/grlib_gptimer.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/hw/timer/grlib_gptimer.c b/hw/timer/grlib_gptimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/grlib_gptimer.c +++ b/hw/timer/grlib_gptimer.c @@ -XXX,XX +XXX,XX @@ #include "hw/irq.h" #include "hw/ptimer.h" #include "hw/qdev-properties.h" -#include "qemu/main-loop.h" #include "qemu/module.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ typedef struct GPTimer GPTimer; typedef struct GPTimerUnit GPTimerUnit; struct GPTimer { - QEMUBH *bh; struct ptimer_state *ptimer; qemu_irq irq; @@ -XXX,XX +XXX,XX @@ struct GPTimerUnit { uint32_t config; }; +static void grlib_gptimer_tx_begin(GPTimer *timer) +{ + ptimer_transaction_begin(timer->ptimer); +} + +static void grlib_gptimer_tx_commit(GPTimer *timer) +{ + ptimer_transaction_commit(timer->ptimer); +} + +/* Must be called within grlib_gptimer_tx_begin/commit block */ static void grlib_gptimer_enable(GPTimer *timer) { assert(timer != NULL); @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_enable(GPTimer *timer) ptimer_run(timer->ptimer, 1); } +/* Must be called within grlib_gptimer_tx_begin/commit block */ static void grlib_gptimer_restart(GPTimer *timer) { assert(timer != NULL); @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_set_scaler(GPTimerUnit *unit, uint32_t scaler) trace_grlib_gptimer_set_scaler(scaler, value); for (i = 0; i < unit->nr_timers; i++) { + ptimer_transaction_begin(unit->timers[i].ptimer); ptimer_set_freq(unit->timers[i].ptimer, value); + ptimer_transaction_commit(unit->timers[i].ptimer); } } @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_write(void *opaque, hwaddr addr, switch (timer_addr) { case COUNTER_OFFSET: trace_grlib_gptimer_writel(id, addr, value); + grlib_gptimer_tx_begin(&unit->timers[id]); unit->timers[id].counter = value; grlib_gptimer_enable(&unit->timers[id]); + grlib_gptimer_tx_commit(&unit->timers[id]); return; case COUNTER_RELOAD_OFFSET: @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_write(void *opaque, hwaddr addr, /* gptimer_restart calls gptimer_enable, so if "enable" and "load" bits are present, we just have to call restart. */ + grlib_gptimer_tx_begin(&unit->timers[id]); if (value & GPTIMER_LOAD) { grlib_gptimer_restart(&unit->timers[id]); } else if (value & GPTIMER_ENABLE) { @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_write(void *opaque, hwaddr addr, value &= ~(GPTIMER_LOAD & GPTIMER_DEBUG_HALT); unit->timers[id].config = value; + grlib_gptimer_tx_commit(&unit->timers[id]); return; default: @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_reset(DeviceState *d) timer->counter = 0; timer->reload = 0; timer->config = 0; + ptimer_transaction_begin(timer->ptimer); ptimer_stop(timer->ptimer); ptimer_set_count(timer->ptimer, 0); ptimer_set_freq(timer->ptimer, unit->freq_hz); + ptimer_transaction_commit(timer->ptimer); } } @@ -XXX,XX +XXX,XX @@ static void grlib_gptimer_realize(DeviceState *dev, Error **errp) GPTimer *timer = &unit->timers[i]; timer->unit = unit; - timer->bh = qemu_bh_new(grlib_gptimer_hit, timer); - timer->ptimer = ptimer_init_with_bh(timer->bh, PTIMER_POLICY_DEFAULT); + timer->ptimer = ptimer_init(grlib_gptimer_hit, timer, + PTIMER_POLICY_DEFAULT); timer->id = i; /* One IRQ line for each timer */ sysbus_init_irq(sbd, &timer->irq); + ptimer_transaction_begin(timer->ptimer); ptimer_set_freq(timer->ptimer, unit->freq_hz); + ptimer_transaction_commit(timer->ptimer); } memory_region_init_io(&unit->iomem, OBJECT(unit), &grlib_gptimer_ops, -- 2.20.1 Switch the mcf5206 code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20191021140600.10725-1-peter.maydell@linaro.org --- hw/m68k/mcf5206.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/hw/m68k/mcf5206.c b/hw/m68k/mcf5206.c index XXXXXXX..XXXXXXX 100644 --- a/hw/m68k/mcf5206.c +++ b/hw/m68k/mcf5206.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/error-report.h" -#include "qemu/main-loop.h" #include "cpu.h" #include "hw/hw.h" #include "hw/irq.h" @@ -XXX,XX +XXX,XX @@ static void m5206_timer_recalibrate(m5206_timer_state *s) int prescale; int mode; + ptimer_transaction_begin(s->timer); ptimer_stop(s->timer); - if ((s->tmr & TMR_RST) == 0) - return; + if ((s->tmr & TMR_RST) == 0) { + goto exit; + } prescale = (s->tmr >> 8) + 1; mode = (s->tmr >> 1) & 3; @@ -XXX,XX +XXX,XX @@ static void m5206_timer_recalibrate(m5206_timer_state *s) ptimer_set_limit(s->timer, s->trr, 0); ptimer_run(s->timer, 0); +exit: + ptimer_transaction_commit(s->timer); } static void m5206_timer_trigger(void *opaque) @@ -XXX,XX +XXX,XX @@ static void m5206_timer_write(m5206_timer_state *s, uint32_t addr, uint32_t val) s->tcr = val; break; case 0xc: + ptimer_transaction_begin(s->timer); ptimer_set_count(s->timer, val); + ptimer_transaction_commit(s->timer); break; case 0x11: s->ter &= ~val; @@ -XXX,XX +XXX,XX @@ static void m5206_timer_write(m5206_timer_state *s, uint32_t addr, uint32_t val) static m5206_timer_state *m5206_timer_init(qemu_irq irq) { m5206_timer_state *s; - QEMUBH *bh; s = g_new0(m5206_timer_state, 1); - bh = qemu_bh_new(m5206_timer_trigger, s); - s->timer = ptimer_init_with_bh(bh, PTIMER_POLICY_DEFAULT); + s->timer = ptimer_init(m5206_timer_trigger, s, PTIMER_POLICY_DEFAULT); s->irq = irq; m5206_timer_reset(s); return s; -- 2.20.1 Switch the milkymist-sysctl code away from bottom-half based ptimers to the new transaction-based ptimer API. This just requires adding begin/commit calls around the various places that modify the ptimer state, and using the new ptimer_init() function to create the timer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20191021141040.11007-1-peter.maydell@linaro.org --- hw/timer/milkymist-sysctl.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/hw/timer/milkymist-sysctl.c b/hw/timer/milkymist-sysctl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/milkymist-sysctl.c +++ b/hw/timer/milkymist-sysctl.c @@ -XXX,XX +XXX,XX @@ #include "hw/ptimer.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -#include "qemu/main-loop.h" #include "qemu/module.h" enum { @@ -XXX,XX +XXX,XX @@ struct MilkymistSysctlState { MemoryRegion regs_region; - QEMUBH *bh0; - QEMUBH *bh1; ptimer_state *ptimer0; ptimer_state *ptimer1; @@ -XXX,XX +XXX,XX @@ static void sysctl_write(void *opaque, hwaddr addr, uint64_t value, s->regs[addr] = value; break; case R_TIMER0_COMPARE: + ptimer_transaction_begin(s->ptimer0); ptimer_set_limit(s->ptimer0, value, 0); s->regs[addr] = value; + ptimer_transaction_commit(s->ptimer0); break; case R_TIMER1_COMPARE: + ptimer_transaction_begin(s->ptimer1); ptimer_set_limit(s->ptimer1, value, 0); s->regs[addr] = value; + ptimer_transaction_commit(s->ptimer1); break; case R_TIMER0_CONTROL: + ptimer_transaction_begin(s->ptimer0); s->regs[addr] = value; if (s->regs[R_TIMER0_CONTROL] & CTRL_ENABLE) { trace_milkymist_sysctl_start_timer0(); @@ -XXX,XX +XXX,XX @@ static void sysctl_write(void *opaque, hwaddr addr, uint64_t value, trace_milkymist_sysctl_stop_timer0(); ptimer_stop(s->ptimer0); } + ptimer_transaction_commit(s->ptimer0); break; case R_TIMER1_CONTROL: + ptimer_transaction_begin(s->ptimer1); s->regs[addr] = value; if (s->regs[R_TIMER1_CONTROL] & CTRL_ENABLE) { trace_milkymist_sysctl_start_timer1(); @@ -XXX,XX +XXX,XX @@ static void sysctl_write(void *opaque, hwaddr addr, uint64_t value, trace_milkymist_sysctl_stop_timer1(); ptimer_stop(s->ptimer1); } + ptimer_transaction_commit(s->ptimer1); break; case R_ICAP: sysctl_icap_write(s, value); @@ -XXX,XX +XXX,XX @@ static void milkymist_sysctl_reset(DeviceState *d) s->regs[i] = 0; } + ptimer_transaction_begin(s->ptimer0); ptimer_stop(s->ptimer0); + ptimer_transaction_commit(s->ptimer0); + ptimer_transaction_begin(s->ptimer1); ptimer_stop(s->ptimer1); + ptimer_transaction_commit(s->ptimer1); /* defaults */ s->regs[R_ICAP] = ICAP_READY; @@ -XXX,XX +XXX,XX @@ static void milkymist_sysctl_realize(DeviceState *dev, Error **errp) { MilkymistSysctlState *s = MILKYMIST_SYSCTL(dev); - s->bh0 = qemu_bh_new(timer0_hit, s); - s->bh1 = qemu_bh_new(timer1_hit, s); - s->ptimer0 = ptimer_init_with_bh(s->bh0, PTIMER_POLICY_DEFAULT); - s->ptimer1 = ptimer_init_with_bh(s->bh1, PTIMER_POLICY_DEFAULT); + s->ptimer0 = ptimer_init(timer0_hit, s, PTIMER_POLICY_DEFAULT); + s->ptimer1 = ptimer_init(timer1_hit, s, PTIMER_POLICY_DEFAULT); + ptimer_transaction_begin(s->ptimer0); ptimer_set_freq(s->ptimer0, s->freq_hz); + ptimer_transaction_commit(s->ptimer0); + ptimer_transaction_begin(s->ptimer1); ptimer_set_freq(s->ptimer1, s->freq_hz); + ptimer_transaction_commit(s->ptimer1); } static const VMStateDescription vmstate_milkymist_sysctl = { -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Add support for the query-cpu-model-expansion QMP command to Arm. We do this selectively, only exposing CPU properties which represent optional CPU features which the user may want to enable/disable. Additionally we restrict the list of queryable cpu models to 'max', 'host', or the current type when KVM is in use. And, finally, we only implement expansion type 'full', as Arm does not yet have a "base" CPU type. More details and example queries are described in a new document (docs/arm-cpu-features.rst). Note, certainly more features may be added to the list of advertised features, e.g. 'vfp' and 'neon'. The only requirement is that we can detect invalid configurations and emit failures at QMP query time. For 'vfp' and 'neon' this will require some refactoring to share a validation function between the QMP query and the CPU realize functions. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Beata Michalska <beata.michalska@linaro.org> Message-id: 20191024121808.9612-2-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qapi/machine-target.json | 6 +- target/arm/monitor.c | 146 ++++++++++++++++++++++++++++++++++++++ docs/arm-cpu-features.rst | 137 +++++++++++++++++++++++++++++++++++ 3 files changed, 286 insertions(+), 3 deletions(-) create mode 100644 docs/arm-cpu-features.rst diff --git a/qapi/machine-target.json b/qapi/machine-target.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/machine-target.json +++ b/qapi/machine-target.json @@ -XXX,XX +XXX,XX @@ ## { 'struct': 'CpuModelExpansionInfo', 'data': { 'model': 'CpuModelInfo' }, - 'if': 'defined(TARGET_S390X) || defined(TARGET_I386)' } + 'if': 'defined(TARGET_S390X) || defined(TARGET_I386) || defined(TARGET_ARM)' } ## # @query-cpu-model-expansion: @@ -XXX,XX +XXX,XX @@ # query-cpu-model-expansion while using these is not advised. # # Some architectures may not support all expansion types. s390x supports -# "full" and "static". +# "full" and "static". Arm only supports "full". # # Returns: a CpuModelExpansionInfo. Returns an error if expanding CPU models is # not supported, if the model cannot be expanded, if the model contains @@ -XXX,XX +XXX,XX @@ 'data': { 'type': 'CpuModelExpansionType', 'model': 'CpuModelInfo' }, 'returns': 'CpuModelExpansionInfo', - 'if': 'defined(TARGET_S390X) || defined(TARGET_I386)' } + 'if': 'defined(TARGET_S390X) || defined(TARGET_I386) || defined(TARGET_ARM)' } ## # @CpuDefinitionInfo: diff --git a/target/arm/monitor.c b/target/arm/monitor.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/monitor.c +++ b/target/arm/monitor.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "hw/boards.h" #include "kvm_arm.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-commands-machine-target.h" #include "qapi/qapi-commands-misc-target.h" +#include "qapi/qmp/qerror.h" +#include "qapi/qmp/qdict.h" +#include "qom/qom-qobject.h" static GICCapability *gic_cap_new(int version) { @@ -XXX,XX +XXX,XX @@ GICCapabilityList *qmp_query_gic_capabilities(Error **errp) return head; } + +/* + * These are cpu model features we want to advertise. The order here + * matters as this is the order in which qmp_query_cpu_model_expansion + * will attempt to set them. If there are dependencies between features, + * then the order that considers those dependencies must be used. + */ +static const char *cpu_model_advertised_features[] = { + "aarch64", "pmu", + NULL +}; + +CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type, + CpuModelInfo *model, + Error **errp) +{ + CpuModelExpansionInfo *expansion_info; + const QDict *qdict_in = NULL; + QDict *qdict_out; + ObjectClass *oc; + Object *obj; + const char *name; + int i; + + if (type != CPU_MODEL_EXPANSION_TYPE_FULL) { + error_setg(errp, "The requested expansion type is not supported"); + return NULL; + } + + if (!kvm_enabled() && !strcmp(model->name, "host")) { + error_setg(errp, "The CPU type '%s' requires KVM", model->name); + return NULL; + } + + oc = cpu_class_by_name(TYPE_ARM_CPU, model->name); + if (!oc) { + error_setg(errp, "The CPU type '%s' is not a recognized ARM CPU type", + model->name); + return NULL; + } + + if (kvm_enabled()) { + const char *cpu_type = current_machine->cpu_type; + int len = strlen(cpu_type) - strlen(ARM_CPU_TYPE_SUFFIX); + bool supported = false; + + if (!strcmp(model->name, "host") || !strcmp(model->name, "max")) { + /* These are kvmarm's recommended cpu types */ + supported = true; + } else if (strlen(model->name) == len && + !strncmp(model->name, cpu_type, len)) { + /* KVM is enabled and we're using this type, so it works. */ + supported = true; + } + if (!supported) { + error_setg(errp, "We cannot guarantee the CPU type '%s' works " + "with KVM on this host", model->name); + return NULL; + } + } + + if (model->props) { + qdict_in = qobject_to(QDict, model->props); + if (!qdict_in) { + error_setg(errp, QERR_INVALID_PARAMETER_TYPE, "props", "dict"); + return NULL; + } + } + + obj = object_new(object_class_get_name(oc)); + + if (qdict_in) { + Visitor *visitor; + Error *err = NULL; + + visitor = qobject_input_visitor_new(model->props); + visit_start_struct(visitor, NULL, NULL, 0, &err); + if (err) { + visit_free(visitor); + object_unref(obj); + error_propagate(errp, err); + return NULL; + } + + i = 0; + while ((name = cpu_model_advertised_features[i++]) != NULL) { + if (qdict_get(qdict_in, name)) { + object_property_set(obj, visitor, name, &err); + if (err) { + break; + } + } + } + + if (!err) { + visit_check_struct(visitor, &err); + } + visit_end_struct(visitor, NULL); + visit_free(visitor); + if (err) { + object_unref(obj); + error_propagate(errp, err); + return NULL; + } + } + + expansion_info = g_new0(CpuModelExpansionInfo, 1); + expansion_info->model = g_malloc0(sizeof(*expansion_info->model)); + expansion_info->model->name = g_strdup(model->name); + + qdict_out = qdict_new(); + + i = 0; + while ((name = cpu_model_advertised_features[i++]) != NULL) { + ObjectProperty *prop = object_property_find(obj, name, NULL); + if (prop) { + Error *err = NULL; + QObject *value; + + assert(prop->get); + value = object_property_get_qobject(obj, name, &err); + assert(!err); + + qdict_put_obj(qdict_out, name, value); + } + } + + if (!qdict_size(qdict_out)) { + qobject_unref(qdict_out); + } else { + expansion_info->model->props = QOBJECT(qdict_out); + expansion_info->model->has_props = true; + } + + object_unref(obj); + + return expansion_info; +} diff --git a/docs/arm-cpu-features.rst b/docs/arm-cpu-features.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/arm-cpu-features.rst @@ -XXX,XX +XXX,XX @@ +================ +ARM CPU Features +================ + +Examples of probing and using ARM CPU features + +Introduction +============ + +CPU features are optional features that a CPU of supporting type may +choose to implement or not. In QEMU, optional CPU features have +corresponding boolean CPU proprieties that, when enabled, indicate +that the feature is implemented, and, conversely, when disabled, +indicate that it is not implemented. An example of an ARM CPU feature +is the Performance Monitoring Unit (PMU). CPU types such as the +Cortex-A15 and the Cortex-A57, which respectively implement ARM +architecture reference manuals ARMv7-A and ARMv8-A, may both optionally +implement PMUs. For example, if a user wants to use a Cortex-A15 without +a PMU, then the `-cpu` parameter should contain `pmu=off` on the QEMU +command line, i.e. `-cpu cortex-a15,pmu=off`. + +As not all CPU types support all optional CPU features, then whether or +not a CPU property exists depends on the CPU type. For example, CPUs +that implement the ARMv8-A architecture reference manual may optionally +support the AArch32 CPU feature, which may be enabled by disabling the +`aarch64` CPU property. A CPU type such as the Cortex-A15, which does +not implement ARMv8-A, will not have the `aarch64` CPU property. + +QEMU's support may be limited for some CPU features, only partially +supporting the feature or only supporting the feature under certain +configurations. For example, the `aarch64` CPU feature, which, when +disabled, enables the optional AArch32 CPU feature, is only supported +when using the KVM accelerator and when running on a host CPU type that +supports the feature. + +CPU Feature Probing +=================== + +Determining which CPU features are available and functional for a given +CPU type is possible with the `query-cpu-model-expansion` QMP command. +Below are some examples where `scripts/qmp/qmp-shell` (see the top comment +block in the script for usage) is used to issue the QMP commands. + +(1) Determine which CPU features are available for the `max` CPU type + (Note, we started QEMU with qemu-system-aarch64, so `max` is + implementing the ARMv8-A reference manual in this case):: + + (QEMU) query-cpu-model-expansion type=full model={"name":"max"} + { "return": { + "model": { "name": "max", "props": { + "pmu": true, "aarch64": true + }}}} + +We see that the `max` CPU type has the `pmu` and `aarch64` CPU features. +We also see that the CPU features are enabled, as they are all `true`. + +(2) Let's try to disable the PMU:: + + (QEMU) query-cpu-model-expansion type=full model={"name":"max","props":{"pmu":false}} + { "return": { + "model": { "name": "max", "props": { + "pmu": false, "aarch64": true + }}}} + +We see it worked, as `pmu` is now `false`. + +(3) Let's try to disable `aarch64`, which enables the AArch32 CPU feature:: + + (QEMU) query-cpu-model-expansion type=full model={"name":"max","props":{"aarch64":false}} + {"error": { + "class": "GenericError", "desc": + "'aarch64' feature cannot be disabled unless KVM is enabled and 32-bit EL1 is supported" + }} + +It looks like this feature is limited to a configuration we do not +currently have. + +(4) Let's try probing CPU features for the Cortex-A15 CPU type:: + + (QEMU) query-cpu-model-expansion type=full model={"name":"cortex-a15"} + {"return": {"model": {"name": "cortex-a15", "props": {"pmu": true}}}} + +Only the `pmu` CPU feature is available. + +A note about CPU feature dependencies +------------------------------------- + +It's possible for features to have dependencies on other features. I.e. +it may be possible to change one feature at a time without error, but +when attempting to change all features at once an error could occur +depending on the order they are processed. It's also possible changing +all at once doesn't generate an error, because a feature's dependencies +are satisfied with other features, but the same feature cannot be changed +independently without error. For these reasons callers should always +attempt to make their desired changes all at once in order to ensure the +collection is valid. + +A note about CPU models and KVM +------------------------------- + +Named CPU models generally do not work with KVM. There are a few cases +that do work, e.g. using the named CPU model `cortex-a57` with KVM on a +seattle host, but mostly if KVM is enabled the `host` CPU type must be +used. This means the guest is provided all the same CPU features as the +host CPU type has. And, for this reason, the `host` CPU type should +enable all CPU features that the host has by default. Indeed it's even +a bit strange to allow disabling CPU features that the host has when using +the `host` CPU type, but in the absence of CPU models it's the best we can +do if we want to launch guests without all the host's CPU features enabled. + +Enabling KVM also affects the `query-cpu-model-expansion` QMP command. The +affect is not only limited to specific features, as pointed out in example +(3) of "CPU Feature Probing", but also to which CPU types may be expanded. +When KVM is enabled, only the `max`, `host`, and current CPU type may be +expanded. This restriction is necessary as it's not possible to know all +CPU types that may work with KVM, but it does impose a small risk of users +experiencing unexpected errors. For example on a seattle, as mentioned +above, the `cortex-a57` CPU type is also valid when KVM is enabled. +Therefore a user could use the `host` CPU type for the current type, but +then attempt to query `cortex-a57`, however that query will fail with our +restrictions. This shouldn't be an issue though as management layers and +users have been preferring the `host` CPU type for use with KVM for quite +some time. Additionally, if the KVM-enabled QEMU instance running on a +seattle host is using the `cortex-a57` CPU type, then querying `cortex-a57` +will work. + +Using CPU Features +================== + +After determining which CPU features are available and supported for a +given CPU type, then they may be selectively enabled or disabled on the +QEMU command line with that CPU type:: + + $ qemu-system-aarch64 -M virt -cpu max,pmu=off + +The example above disables the PMU for the `max` CPU type. + -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Now that Arm CPUs have advertised features lets add tests to ensure we maintain their expected availability with and without KVM. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 20191024121808.9612-3-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/Makefile.include | 5 +- tests/arm-cpu-features.c | 240 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 244 insertions(+), 1 deletion(-) create mode 100644 tests/arm-cpu-features.c diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-qtest-sparc64-$(CONFIG_ISA_TESTDEV) = tests/endianness-test$(EXESUF) check-qtest-sparc64-y += tests/prom-env-test$(EXESUF) check-qtest-sparc64-y += tests/boot-serial-test$(EXESUF) +check-qtest-arm-y += tests/arm-cpu-features$(EXESUF) check-qtest-arm-y += tests/microbit-test$(EXESUF) check-qtest-arm-y += tests/m25p80-test$(EXESUF) check-qtest-arm-y += tests/test-arm-mptimer$(EXESUF) @@ -XXX,XX +XXX,XX @@ check-qtest-arm-y += tests/boot-serial-test$(EXESUF) check-qtest-arm-y += tests/hexloader-test$(EXESUF) check-qtest-arm-$(CONFIG_PFLASH_CFI02) += tests/pflash-cfi02-test$(EXESUF) -check-qtest-aarch64-y = tests/numa-test$(EXESUF) +check-qtest-aarch64-y += tests/arm-cpu-features$(EXESUF) +check-qtest-aarch64-y += tests/numa-test$(EXESUF) check-qtest-aarch64-y += tests/boot-serial-test$(EXESUF) check-qtest-aarch64-y += tests/migration-test$(EXESUF) # TODO: once aarch64 TCG is fixed on ARM 32 bit host, make test unconditional @@ -XXX,XX +XXX,XX @@ tests/test-qapi-util$(EXESUF): tests/test-qapi-util.o $(test-util-obj-y) tests/numa-test$(EXESUF): tests/numa-test.o tests/vmgenid-test$(EXESUF): tests/vmgenid-test.o tests/boot-sector.o tests/acpi-utils.o tests/cdrom-test$(EXESUF): tests/cdrom-test.o tests/boot-sector.o $(libqos-obj-y) +tests/arm-cpu-features$(EXESUF): tests/arm-cpu-features.o tests/migration/stress$(EXESUF): tests/migration/stress.o $(call quiet-command, $(LINKPROG) -static -O3 $(PTHREAD_LIB) -o $@ $< ,"LINK","$(TARGET_DIR)$@") diff --git a/tests/arm-cpu-features.c b/tests/arm-cpu-features.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ +/* + * Arm CPU feature test cases + * + * Copyright (c) 2019 Red Hat Inc. + * Authors: + * Andrew Jones <drjones@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "libqtest.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qjson.h" + +#define MACHINE "-machine virt,gic-version=max " +#define QUERY_HEAD "{ 'execute': 'query-cpu-model-expansion', " \ + "'arguments': { 'type': 'full', " +#define QUERY_TAIL "}}" + +static QDict *do_query_no_props(QTestState *qts, const char *cpu_type) +{ + return qtest_qmp(qts, QUERY_HEAD "'model': { 'name': %s }" + QUERY_TAIL, cpu_type); +} + +static QDict *do_query(QTestState *qts, const char *cpu_type, + const char *fmt, ...) +{ + QDict *resp; + + if (fmt) { + QDict *args; + va_list ap; + + va_start(ap, fmt); + args = qdict_from_vjsonf_nofail(fmt, ap); + va_end(ap); + + resp = qtest_qmp(qts, QUERY_HEAD "'model': { 'name': %s, " + "'props': %p }" + QUERY_TAIL, cpu_type, args); + } else { + resp = do_query_no_props(qts, cpu_type); + } + + return resp; +} + +static const char *resp_get_error(QDict *resp) +{ + QDict *qdict; + + g_assert(resp); + + qdict = qdict_get_qdict(resp, "error"); + if (qdict) { + return qdict_get_str(qdict, "desc"); + } + return NULL; +} + +#define assert_error(qts, cpu_type, expected_error, fmt, ...) \ +({ \ + QDict *_resp; \ + const char *_error; \ + \ + _resp = do_query(qts, cpu_type, fmt, ##__VA_ARGS__); \ + g_assert(_resp); \ + _error = resp_get_error(_resp); \ + g_assert(_error); \ + g_assert(g_str_equal(_error, expected_error)); \ + qobject_unref(_resp); \ +}) + +static bool resp_has_props(QDict *resp) +{ + QDict *qdict; + + g_assert(resp); + + if (!qdict_haskey(resp, "return")) { + return false; + } + qdict = qdict_get_qdict(resp, "return"); + + if (!qdict_haskey(qdict, "model")) { + return false; + } + qdict = qdict_get_qdict(qdict, "model"); + + return qdict_haskey(qdict, "props"); +} + +static QDict *resp_get_props(QDict *resp) +{ + QDict *qdict; + + g_assert(resp); + g_assert(resp_has_props(resp)); + + qdict = qdict_get_qdict(resp, "return"); + qdict = qdict_get_qdict(qdict, "model"); + qdict = qdict_get_qdict(qdict, "props"); + return qdict; +} + +#define assert_has_feature(qts, cpu_type, feature) \ +({ \ + QDict *_resp = do_query_no_props(qts, cpu_type); \ + g_assert(_resp); \ + g_assert(resp_has_props(_resp)); \ + g_assert(qdict_get(resp_get_props(_resp), feature)); \ + qobject_unref(_resp); \ +}) + +#define assert_has_not_feature(qts, cpu_type, feature) \ +({ \ + QDict *_resp = do_query_no_props(qts, cpu_type); \ + g_assert(_resp); \ + g_assert(!resp_has_props(_resp) || \ + !qdict_get(resp_get_props(_resp), feature)); \ + qobject_unref(_resp); \ +}) + +static void assert_type_full(QTestState *qts) +{ + const char *error; + QDict *resp; + + resp = qtest_qmp(qts, "{ 'execute': 'query-cpu-model-expansion', " + "'arguments': { 'type': 'static', " + "'model': { 'name': 'foo' }}}"); + g_assert(resp); + error = resp_get_error(resp); + g_assert(error); + g_assert(g_str_equal(error, + "The requested expansion type is not supported")); + qobject_unref(resp); +} + +static void assert_bad_props(QTestState *qts, const char *cpu_type) +{ + const char *error; + QDict *resp; + + resp = qtest_qmp(qts, "{ 'execute': 'query-cpu-model-expansion', " + "'arguments': { 'type': 'full', " + "'model': { 'name': %s, " + "'props': false }}}", + cpu_type); + g_assert(resp); + error = resp_get_error(resp); + g_assert(error); + g_assert(g_str_equal(error, + "Invalid parameter type for 'props', expected: dict")); + qobject_unref(resp); +} + +static void test_query_cpu_model_expansion(const void *data) +{ + QTestState *qts; + + qts = qtest_init(MACHINE "-cpu max"); + + /* Test common query-cpu-model-expansion input validation */ + assert_type_full(qts); + assert_bad_props(qts, "max"); + assert_error(qts, "foo", "The CPU type 'foo' is not a recognized " + "ARM CPU type", NULL); + assert_error(qts, "max", "Parameter 'not-a-prop' is unexpected", + "{ 'not-a-prop': false }"); + assert_error(qts, "host", "The CPU type 'host' requires KVM", NULL); + + /* Test expected feature presence/absence for some cpu types */ + assert_has_feature(qts, "max", "pmu"); + assert_has_feature(qts, "cortex-a15", "pmu"); + assert_has_not_feature(qts, "cortex-a15", "aarch64"); + + if (g_str_equal(qtest_get_arch(), "aarch64")) { + assert_has_feature(qts, "max", "aarch64"); + assert_has_feature(qts, "cortex-a57", "pmu"); + assert_has_feature(qts, "cortex-a57", "aarch64"); + + /* Test that features that depend on KVM generate errors without. */ + assert_error(qts, "max", + "'aarch64' feature cannot be disabled " + "unless KVM is enabled and 32-bit EL1 " + "is supported", + "{ 'aarch64': false }"); + } + + qtest_quit(qts); +} + +static void test_query_cpu_model_expansion_kvm(const void *data) +{ + QTestState *qts; + + qts = qtest_init(MACHINE "-accel kvm -cpu host"); + + if (g_str_equal(qtest_get_arch(), "aarch64")) { + assert_has_feature(qts, "host", "aarch64"); + assert_has_feature(qts, "host", "pmu"); + + assert_error(qts, "cortex-a15", + "We cannot guarantee the CPU type 'cortex-a15' works " + "with KVM on this host", NULL); + } else { + assert_has_not_feature(qts, "host", "aarch64"); + assert_has_not_feature(qts, "host", "pmu"); + } + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + bool kvm_available = false; + + if (!access("/dev/kvm", R_OK | W_OK)) { +#if defined(HOST_AARCH64) + kvm_available = g_str_equal(qtest_get_arch(), "aarch64"); +#elif defined(HOST_ARM) + kvm_available = g_str_equal(qtest_get_arch(), "arm"); +#endif + } + + g_test_init(&argc, &argv, NULL); + + qtest_add_data_func("/arm/query-cpu-model-expansion", + NULL, test_query_cpu_model_expansion); + + if (kvm_available) { + qtest_add_data_func("/arm/kvm/query-cpu-model-expansion", + NULL, test_query_cpu_model_expansion_kvm); + } + + return g_test_run(); +} -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Since 97a28b0eeac14 ("target/arm: Allow VFP and Neon to be disabled via a CPU property") we can disable the 'max' cpu model's VFP and neon features, but there's no way to disable SVE. Add the 'sve=on|off' property to give it that flexibility. We also rename cpu_max_get/set_sve_vq to cpu_max_get/set_sve_max_vq in order for them to follow the typical *_get/set_<property-name> pattern. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Reviewed-by: Beata Michalska <beata.michalska@linaro.org> Message-id: 20191024121808.9612-4-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 3 ++- target/arm/cpu64.c | 52 ++++++++++++++++++++++++++++++++++------ target/arm/monitor.c | 2 +- tests/arm-cpu-features.c | 1 + 4 files changed, 49 insertions(+), 9 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) env->cp15.cpacr_el1 = deposit64(env->cp15.cpacr_el1, 16, 2, 3); env->cp15.cptr_el[3] |= CPTR_EZ; /* with maximum vector length */ - env->vfp.zcr_el[1] = cpu->sve_max_vq - 1; + env->vfp.zcr_el[1] = cpu_isar_feature(aa64_sve, cpu) ? + cpu->sve_max_vq - 1 : 0; env->vfp.zcr_el[2] = env->vfp.zcr_el[1]; env->vfp.zcr_el[3] = env->vfp.zcr_el[1]; /* 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_a72_initfn(Object *obj) define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); } -static void cpu_max_get_sve_vq(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) +static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) { ARMCPU *cpu = ARM_CPU(obj); - visit_type_uint32(v, name, &cpu->sve_max_vq, errp); + uint32_t value; + + /* All vector lengths are disabled when SVE is off. */ + if (!cpu_isar_feature(aa64_sve, cpu)) { + value = 0; + } else { + value = cpu->sve_max_vq; + } + visit_type_uint32(v, name, &value, errp); } -static void cpu_max_set_sve_vq(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) +static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) { ARMCPU *cpu = ARM_CPU(obj); Error *err = NULL; @@ -XXX,XX +XXX,XX @@ static void cpu_max_set_sve_vq(Object *obj, Visitor *v, const char *name, error_propagate(errp, err); } +static void cpu_arm_get_sve(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + bool value = cpu_isar_feature(aa64_sve, cpu); + + visit_type_bool(v, name, &value, errp); +} + +static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + Error *err = NULL; + bool value; + uint64_t t; + + visit_type_bool(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + t = cpu->isar.id_aa64pfr0; + t = FIELD_DP64(t, ID_AA64PFR0, SVE, value); + cpu->isar.id_aa64pfr0 = t; +} + /* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); * otherwise, a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu.c; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) #endif cpu->sve_max_vq = ARM_MAX_VQ; - object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_vq, - cpu_max_set_sve_vq, NULL, NULL, &error_fatal); + object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, + cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); + object_property_add(obj, "sve", "bool", cpu_arm_get_sve, + cpu_arm_set_sve, NULL, NULL, &error_fatal); } } diff --git a/target/arm/monitor.c b/target/arm/monitor.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/monitor.c +++ b/target/arm/monitor.c @@ -XXX,XX +XXX,XX @@ GICCapabilityList *qmp_query_gic_capabilities(Error **errp) * then the order that considers those dependencies must be used. */ static const char *cpu_model_advertised_features[] = { - "aarch64", "pmu", + "aarch64", "pmu", "sve", NULL }; diff --git a/tests/arm-cpu-features.c b/tests/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/arm-cpu-features.c +++ b/tests/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data) if (g_str_equal(qtest_get_arch(), "aarch64")) { assert_has_feature(qts, "max", "aarch64"); + assert_has_feature(qts, "max", "sve"); assert_has_feature(qts, "cortex-a57", "pmu"); assert_has_feature(qts, "cortex-a57", "aarch64"); -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Introduce cpu properties to give fine control over SVE vector lengths. We introduce a property for each valid length up to the current maximum supported, which is 2048-bits. The properties are named, e.g. sve128, sve256, sve384, sve512, ..., where the number is the number of bits. See the updates to docs/arm-cpu-features.rst for a description of the semantics and for example uses. Note, as sve-max-vq is still present and we'd like to be able to support qmp_query_cpu_model_expansion with guests launched with e.g. -cpu max,sve-max-vq=8 on their command lines, then we do allow sve-max-vq and sve<N> properties to be provided at the same time, but this is not recommended, and is why sve-max-vq is not mentioned in the document. If sve-max-vq is provided then it enables all lengths smaller than and including the max and disables all lengths larger. It also has the side-effect that no larger lengths may be enabled and that the max itself cannot be disabled. Smaller non-power-of-two lengths may, however, be disabled, e.g. -cpu max,sve-max-vq=4,sve384=off provides a guest the vector lengths 128, 256, and 512 bits. This patch has been co-authored with Richard Henderson, who reworked the target/arm/cpu64.c changes in order to push all the validation and auto-enabling/disabling steps into the finalizer, resulting in a nice LOC reduction. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Reviewed-by: Beata Michalska <beata.michalska@linaro.org> Message-id: 20191024121808.9612-5-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/qemu/bitops.h | 1 + target/arm/cpu.h | 19 ++++ target/arm/cpu.c | 19 ++++ target/arm/cpu64.c | 192 ++++++++++++++++++++++++++++++++++++- target/arm/helper.c | 10 +- target/arm/monitor.c | 12 +++ tests/arm-cpu-features.c | 194 ++++++++++++++++++++++++++++++++++++++ docs/arm-cpu-features.rst | 168 +++++++++++++++++++++++++++++++-- 8 files changed, 606 insertions(+), 9 deletions(-) diff --git a/include/qemu/bitops.h b/include/qemu/bitops.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/bitops.h +++ b/include/qemu/bitops.h @@ -XXX,XX +XXX,XX @@ #define BITS_PER_LONG (sizeof (unsigned long) * BITS_PER_BYTE) #define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) #define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) 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 @@ typedef struct { #ifdef TARGET_AARCH64 # define ARM_MAX_VQ 16 +void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp); +uint32_t arm_cpu_vq_map_next_smaller(ARMCPU *cpu, uint32_t vq); #else # define ARM_MAX_VQ 1 +static inline void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) { } +static inline uint32_t arm_cpu_vq_map_next_smaller(ARMCPU *cpu, uint32_t vq) +{ return 0; } #endif typedef struct ARMVectorReg { @@ -XXX,XX +XXX,XX @@ struct ARMCPU { /* Used to set the maximum vector length the cpu will support. */ uint32_t sve_max_vq; + + /* + * In sve_vq_map each set bit is a supported vector length of + * (bit-number + 1) * 16 bytes, i.e. each bit number + 1 is the vector + * length in quadwords. + * + * While processing properties during initialization, corresponding + * sve_vq_init bits are set for bits in sve_vq_map that have been + * set by properties. + */ + DECLARE_BITMAP(sve_vq_map, ARM_MAX_VQ); + DECLARE_BITMAP(sve_vq_init, ARM_MAX_VQ); }; void arm_cpu_post_init(Object *obj); @@ -XXX,XX +XXX,XX @@ static inline int arm_feature(CPUARMState *env, int feature) return (env->features & (1ULL << feature)) != 0; } +void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp); + #if !defined(CONFIG_USER_ONLY) /* Return true if exception levels below EL3 are in secure state, * or would be following an exception return to that level. diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) #endif } +void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp) +{ + Error *local_err = NULL; + + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + arm_cpu_sve_finalize(cpu, &local_err); + if (local_err != NULL) { + error_propagate(errp, local_err); + return; + } + } +} + static void arm_cpu_realizefn(DeviceState *dev, Error **errp) { CPUState *cs = CPU(dev); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) return; } + arm_cpu_finalize_features(cpu, &local_err); + if (local_err != NULL) { + error_propagate(errp, local_err); + return; + } + if (arm_feature(env, ARM_FEATURE_AARCH64) && cpu->has_vfp != cpu->has_neon) { /* 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_a72_initfn(Object *obj) define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); } +void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) +{ + /* + * If any vector lengths are explicitly enabled with sve<N> properties, + * then all other lengths are implicitly disabled. If sve-max-vq is + * specified then it is the same as explicitly enabling all lengths + * up to and including the specified maximum, which means all larger + * lengths will be implicitly disabled. If no sve<N> properties + * are enabled and sve-max-vq is not specified, then all lengths not + * explicitly disabled will be enabled. Additionally, all power-of-two + * vector lengths less than the maximum enabled length will be + * automatically enabled and all vector lengths larger than the largest + * disabled power-of-two vector length will be automatically disabled. + * Errors are generated if the user provided input that interferes with + * any of the above. Finally, if SVE is not disabled, then at least one + * vector length must be enabled. + */ + DECLARE_BITMAP(tmp, ARM_MAX_VQ); + uint32_t vq, max_vq = 0; + + /* + * Process explicit sve<N> properties. + * From the properties, sve_vq_map<N> implies sve_vq_init<N>. + * Check first for any sve<N> enabled. + */ + if (!bitmap_empty(cpu->sve_vq_map, ARM_MAX_VQ)) { + max_vq = find_last_bit(cpu->sve_vq_map, ARM_MAX_VQ) + 1; + + if (cpu->sve_max_vq && max_vq > cpu->sve_max_vq) { + error_setg(errp, "cannot enable sve%d", max_vq * 128); + error_append_hint(errp, "sve%d is larger than the maximum vector " + "length, sve-max-vq=%d (%d bits)\n", + max_vq * 128, cpu->sve_max_vq, + cpu->sve_max_vq * 128); + return; + } + + /* Propagate enabled bits down through required powers-of-two. */ + for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { + if (!test_bit(vq - 1, cpu->sve_vq_init)) { + set_bit(vq - 1, cpu->sve_vq_map); + } + } + } else if (cpu->sve_max_vq == 0) { + /* + * No explicit bits enabled, and no implicit bits from sve-max-vq. + */ + if (!cpu_isar_feature(aa64_sve, cpu)) { + /* SVE is disabled and so are all vector lengths. Good. */ + return; + } + + /* Disabling a power-of-two disables all larger lengths. */ + if (test_bit(0, cpu->sve_vq_init)) { + error_setg(errp, "cannot disable sve128"); + error_append_hint(errp, "Disabling sve128 results in all vector " + "lengths being disabled.\n"); + error_append_hint(errp, "With SVE enabled, at least one vector " + "length must be enabled.\n"); + return; + } + for (vq = 2; vq <= ARM_MAX_VQ; vq <<= 1) { + if (test_bit(vq - 1, cpu->sve_vq_init)) { + break; + } + } + max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ; + + bitmap_complement(cpu->sve_vq_map, cpu->sve_vq_init, max_vq); + max_vq = find_last_bit(cpu->sve_vq_map, max_vq) + 1; + } + + /* + * Process the sve-max-vq property. + * Note that we know from the above that no bit above + * sve-max-vq is currently set. + */ + if (cpu->sve_max_vq != 0) { + max_vq = cpu->sve_max_vq; + + if (!test_bit(max_vq - 1, cpu->sve_vq_map) && + test_bit(max_vq - 1, cpu->sve_vq_init)) { + error_setg(errp, "cannot disable sve%d", max_vq * 128); + error_append_hint(errp, "The maximum vector length must be " + "enabled, sve-max-vq=%d (%d bits)\n", + max_vq, max_vq * 128); + return; + } + + /* Set all bits not explicitly set within sve-max-vq. */ + bitmap_complement(tmp, cpu->sve_vq_init, max_vq); + bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq); + } + + /* + * We should know what max-vq is now. Also, as we're done + * manipulating sve-vq-map, we ensure any bits above max-vq + * are clear, just in case anybody looks. + */ + assert(max_vq != 0); + bitmap_clear(cpu->sve_vq_map, max_vq, ARM_MAX_VQ - max_vq); + + /* Ensure all required powers-of-two are enabled. */ + for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { + if (!test_bit(vq - 1, cpu->sve_vq_map)) { + error_setg(errp, "cannot disable sve%d", vq * 128); + error_append_hint(errp, "sve%d is required as it " + "is a power-of-two length smaller than " + "the maximum, sve%d\n", + vq * 128, max_vq * 128); + return; + } + } + + /* + * Now that we validated all our vector lengths, the only question + * left to answer is if we even want SVE at all. + */ + if (!cpu_isar_feature(aa64_sve, cpu)) { + error_setg(errp, "cannot enable sve%d", max_vq * 128); + error_append_hint(errp, "SVE must be enabled to enable vector " + "lengths.\n"); + error_append_hint(errp, "Add sve=on to the CPU property list.\n"); + return; + } + + /* From now on sve_max_vq is the actual maximum supported length. */ + cpu->sve_max_vq = max_vq; +} + +uint32_t arm_cpu_vq_map_next_smaller(ARMCPU *cpu, uint32_t vq) +{ + uint32_t bitnum; + + /* + * We allow vq == ARM_MAX_VQ + 1 to be input because the caller may want + * to find the maximum vq enabled, which may be ARM_MAX_VQ, but this + * function always returns the next smaller than the input. + */ + assert(vq && vq <= ARM_MAX_VQ + 1); + + bitnum = find_last_bit(cpu->sve_vq_map, vq - 1); + return bitnum == vq - 1 ? 0 : bitnum + 1; +} + static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, error_propagate(errp, err); } +static void cpu_arm_get_sve_vq(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + uint32_t vq = atoi(&name[3]) / 128; + bool value; + + /* All vector lengths are disabled when SVE is off. */ + if (!cpu_isar_feature(aa64_sve, cpu)) { + value = false; + } else { + value = test_bit(vq - 1, cpu->sve_vq_map); + } + visit_type_bool(v, name, &value, errp); +} + +static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + uint32_t vq = atoi(&name[3]) / 128; + Error *err = NULL; + bool value; + + visit_type_bool(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + if (value) { + set_bit(vq - 1, cpu->sve_vq_map); + } else { + clear_bit(vq - 1, cpu->sve_vq_map); + } + set_bit(vq - 1, cpu->sve_vq_init); +} + static void cpu_arm_get_sve(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name, static void aarch64_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); + uint32_t vq; if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->dcz_blocksize = 7; /* 512 bytes */ #endif - cpu->sve_max_vq = ARM_MAX_VQ; object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); object_property_add(obj, "sve", "bool", cpu_arm_get_sve, cpu_arm_set_sve, NULL, NULL, &error_fatal); + + for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { + char name[8]; + sprintf(name, "sve%d", vq * 128); + object_property_add(obj, name, "bool", cpu_arm_get_sve_vq, + cpu_arm_set_sve_vq, NULL, NULL, &error_fatal); + } } } 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 @@ int sve_exception_el(CPUARMState *env, int el) return 0; } +static uint32_t sve_zcr_get_valid_len(ARMCPU *cpu, uint32_t start_len) +{ + uint32_t start_vq = (start_len & 0xf) + 1; + + return arm_cpu_vq_map_next_smaller(cpu, start_vq + 1) - 1; +} + /* * Given that SVE is enabled, return the vector length for EL. */ @@ -XXX,XX +XXX,XX @@ uint32_t sve_zcr_len_for_el(CPUARMState *env, int el) if (arm_feature(env, ARM_FEATURE_EL3)) { zcr_len = MIN(zcr_len, 0xf & (uint32_t)env->vfp.zcr_el[3]); } - return zcr_len; + + return sve_zcr_get_valid_len(cpu, zcr_len); } static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, diff --git a/target/arm/monitor.c b/target/arm/monitor.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/monitor.c +++ b/target/arm/monitor.c @@ -XXX,XX +XXX,XX @@ GICCapabilityList *qmp_query_gic_capabilities(Error **errp) return head; } +QEMU_BUILD_BUG_ON(ARM_MAX_VQ > 16); + /* * These are cpu model features we want to advertise. The order here * matters as this is the order in which qmp_query_cpu_model_expansion @@ -XXX,XX +XXX,XX @@ GICCapabilityList *qmp_query_gic_capabilities(Error **errp) */ static const char *cpu_model_advertised_features[] = { "aarch64", "pmu", "sve", + "sve128", "sve256", "sve384", "sve512", + "sve640", "sve768", "sve896", "sve1024", "sve1152", "sve1280", + "sve1408", "sve1536", "sve1664", "sve1792", "sve1920", "sve2048", NULL }; @@ -XXX,XX +XXX,XX @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type, if (!err) { visit_check_struct(visitor, &err); } + if (!err) { + arm_cpu_finalize_features(ARM_CPU(obj), &err); + } visit_end_struct(visitor, NULL); visit_free(visitor); if (err) { @@ -XXX,XX +XXX,XX @@ CpuModelExpansionInfo *qmp_query_cpu_model_expansion(CpuModelExpansionType type, error_propagate(errp, err); return NULL; } + } else { + Error *err = NULL; + arm_cpu_finalize_features(ARM_CPU(obj), &err); + assert(err == NULL); } expansion_info = g_new0(CpuModelExpansionInfo, 1); diff --git a/tests/arm-cpu-features.c b/tests/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/arm-cpu-features.c +++ b/tests/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ * See the COPYING file in the top-level directory. */ #include "qemu/osdep.h" +#include "qemu/bitops.h" #include "libqtest.h" #include "qapi/qmp/qdict.h" #include "qapi/qmp/qjson.h" +/* + * We expect the SVE max-vq to be 16. Also it must be <= 64 + * for our test code, otherwise 'vls' can't just be a uint64_t. + */ +#define SVE_MAX_VQ 16 + #define MACHINE "-machine virt,gic-version=max " #define QUERY_HEAD "{ 'execute': 'query-cpu-model-expansion', " \ "'arguments': { 'type': 'full', " @@ -XXX,XX +XXX,XX @@ static void assert_bad_props(QTestState *qts, const char *cpu_type) qobject_unref(resp); } +static uint64_t resp_get_sve_vls(QDict *resp) +{ + QDict *props; + const QDictEntry *e; + uint64_t vls = 0; + int n = 0; + + g_assert(resp); + g_assert(resp_has_props(resp)); + + props = resp_get_props(resp); + + for (e = qdict_first(props); e; e = qdict_next(props, e)) { + if (strlen(e->key) > 3 && !strncmp(e->key, "sve", 3) && + g_ascii_isdigit(e->key[3])) { + char *endptr; + int bits; + + bits = g_ascii_strtoll(&e->key[3], &endptr, 10); + if (!bits || *endptr != '\0') { + continue; + } + + if (qdict_get_bool(props, e->key)) { + vls |= BIT_ULL((bits / 128) - 1); + } + ++n; + } + } + + g_assert(n == SVE_MAX_VQ); + + return vls; +} + +#define assert_sve_vls(qts, cpu_type, expected_vls, fmt, ...) \ +({ \ + QDict *_resp = do_query(qts, cpu_type, fmt, ##__VA_ARGS__); \ + g_assert(_resp); \ + g_assert(resp_has_props(_resp)); \ + g_assert(resp_get_sve_vls(_resp) == expected_vls); \ + qobject_unref(_resp); \ +}) + +static void sve_tests_default(QTestState *qts, const char *cpu_type) +{ + /* + * With no sve-max-vq or sve<N> properties on the command line + * the default is to have all vector lengths enabled. This also + * tests that 'sve' is 'on' by default. + */ + assert_sve_vls(qts, cpu_type, BIT_ULL(SVE_MAX_VQ) - 1, NULL); + + /* With SVE off, all vector lengths should also be off. */ + assert_sve_vls(qts, cpu_type, 0, "{ 'sve': false }"); + + /* With SVE on, we must have at least one vector length enabled. */ + assert_error(qts, cpu_type, "cannot disable sve128", "{ 'sve128': false }"); + + /* Basic enable/disable tests. */ + assert_sve_vls(qts, cpu_type, 0x7, "{ 'sve384': true }"); + assert_sve_vls(qts, cpu_type, ((BIT_ULL(SVE_MAX_VQ) - 1) & ~BIT_ULL(2)), + "{ 'sve384': false }"); + + /* + * --------------------------------------------------------------------- + * power-of-two(vq) all-power- can can + * of-two(< vq) enable disable + * --------------------------------------------------------------------- + * vq < max_vq no MUST* yes yes + * vq < max_vq yes MUST* yes no + * --------------------------------------------------------------------- + * vq == max_vq n/a MUST* yes** yes** + * --------------------------------------------------------------------- + * vq > max_vq n/a no no yes + * vq > max_vq n/a yes yes yes + * --------------------------------------------------------------------- + * + * [*] "MUST" means this requirement must already be satisfied, + * otherwise 'max_vq' couldn't itself be enabled. + * + * [**] Not testable with the QMP interface, only with the command line. + */ + + /* max_vq := 8 */ + assert_sve_vls(qts, cpu_type, 0x8b, "{ 'sve1024': true }"); + + /* max_vq := 8, vq < max_vq, !power-of-two(vq) */ + assert_sve_vls(qts, cpu_type, 0x8f, + "{ 'sve1024': true, 'sve384': true }"); + assert_sve_vls(qts, cpu_type, 0x8b, + "{ 'sve1024': true, 'sve384': false }"); + + /* max_vq := 8, vq < max_vq, power-of-two(vq) */ + assert_sve_vls(qts, cpu_type, 0x8b, + "{ 'sve1024': true, 'sve256': true }"); + assert_error(qts, cpu_type, "cannot disable sve256", + "{ 'sve1024': true, 'sve256': false }"); + + /* max_vq := 3, vq > max_vq, !all-power-of-two(< vq) */ + assert_error(qts, cpu_type, "cannot disable sve512", + "{ 'sve384': true, 'sve512': false, 'sve640': true }"); + + /* + * We can disable power-of-two vector lengths when all larger lengths + * are also disabled. We only need to disable the power-of-two length, + * as all non-enabled larger lengths will then be auto-disabled. + */ + assert_sve_vls(qts, cpu_type, 0x7, "{ 'sve512': false }"); + + /* max_vq := 3, vq > max_vq, all-power-of-two(< vq) */ + assert_sve_vls(qts, cpu_type, 0x1f, + "{ 'sve384': true, 'sve512': true, 'sve640': true }"); + assert_sve_vls(qts, cpu_type, 0xf, + "{ 'sve384': true, 'sve512': true, 'sve640': false }"); +} + +static void sve_tests_sve_max_vq_8(const void *data) +{ + QTestState *qts; + + qts = qtest_init(MACHINE "-cpu max,sve-max-vq=8"); + + assert_sve_vls(qts, "max", BIT_ULL(8) - 1, NULL); + + /* + * Disabling the max-vq set by sve-max-vq is not allowed, but + * of course enabling it is OK. + */ + assert_error(qts, "max", "cannot disable sve1024", "{ 'sve1024': false }"); + assert_sve_vls(qts, "max", 0xff, "{ 'sve1024': true }"); + + /* + * Enabling anything larger than max-vq set by sve-max-vq is not + * allowed, but of course disabling everything larger is OK. + */ + assert_error(qts, "max", "cannot enable sve1152", "{ 'sve1152': true }"); + assert_sve_vls(qts, "max", 0xff, "{ 'sve1152': false }"); + + /* + * We can enable/disable non power-of-two lengths smaller than the + * max-vq set by sve-max-vq, but, while we can enable power-of-two + * lengths, we can't disable them. + */ + assert_sve_vls(qts, "max", 0xff, "{ 'sve384': true }"); + assert_sve_vls(qts, "max", 0xfb, "{ 'sve384': false }"); + assert_sve_vls(qts, "max", 0xff, "{ 'sve256': true }"); + assert_error(qts, "max", "cannot disable sve256", "{ 'sve256': false }"); + + qtest_quit(qts); +} + +static void sve_tests_sve_off(const void *data) +{ + QTestState *qts; + + qts = qtest_init(MACHINE "-cpu max,sve=off"); + + /* SVE is off, so the map should be empty. */ + assert_sve_vls(qts, "max", 0, NULL); + + /* The map stays empty even if we turn lengths off. */ + assert_sve_vls(qts, "max", 0, "{ 'sve128': false }"); + + /* It's an error to enable lengths when SVE is off. */ + assert_error(qts, "max", "cannot enable sve128", "{ 'sve128': true }"); + + /* With SVE re-enabled we should get all vector lengths enabled. */ + assert_sve_vls(qts, "max", BIT_ULL(SVE_MAX_VQ) - 1, "{ 'sve': true }"); + + /* Or enable SVE with just specific vector lengths. */ + assert_sve_vls(qts, "max", 0x3, + "{ 'sve': true, 'sve128': true, 'sve256': true }"); + + qtest_quit(qts); +} + static void test_query_cpu_model_expansion(const void *data) { QTestState *qts; @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data) if (g_str_equal(qtest_get_arch(), "aarch64")) { assert_has_feature(qts, "max", "aarch64"); assert_has_feature(qts, "max", "sve"); + assert_has_feature(qts, "max", "sve128"); assert_has_feature(qts, "cortex-a57", "pmu"); assert_has_feature(qts, "cortex-a57", "aarch64"); + sve_tests_default(qts, "max"); + /* Test that features that depend on KVM generate errors without. */ assert_error(qts, "max", "'aarch64' feature cannot be disabled " @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) qtest_add_data_func("/arm/query-cpu-model-expansion", NULL, test_query_cpu_model_expansion); + if (g_str_equal(qtest_get_arch(), "aarch64")) { + qtest_add_data_func("/arm/max/query-cpu-model-expansion/sve-max-vq-8", + NULL, sve_tests_sve_max_vq_8); + qtest_add_data_func("/arm/max/query-cpu-model-expansion/sve-off", + NULL, sve_tests_sve_off); + } + if (kvm_available) { qtest_add_data_func("/arm/kvm/query-cpu-model-expansion", NULL, test_query_cpu_model_expansion_kvm); diff --git a/docs/arm-cpu-features.rst b/docs/arm-cpu-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/arm-cpu-features.rst +++ b/docs/arm-cpu-features.rst @@ -XXX,XX +XXX,XX @@ block in the script for usage) is used to issue the QMP commands. (QEMU) query-cpu-model-expansion type=full model={"name":"max"} { "return": { "model": { "name": "max", "props": { - "pmu": true, "aarch64": true + "sve1664": true, "pmu": true, "sve1792": true, "sve1920": true, + "sve128": true, "aarch64": true, "sve1024": true, "sve": true, + "sve640": true, "sve768": true, "sve1408": true, "sve256": true, + "sve1152": true, "sve512": true, "sve384": true, "sve1536": true, + "sve896": true, "sve1280": true, "sve2048": true }}}} -We see that the `max` CPU type has the `pmu` and `aarch64` CPU features. -We also see that the CPU features are enabled, as they are all `true`. +We see that the `max` CPU type has the `pmu`, `aarch64`, `sve`, and many +`sve<N>` CPU features. We also see that all the CPU features are +enabled, as they are all `true`. (The `sve<N>` CPU features are all +optional SVE vector lengths (see "SVE CPU Properties"). While with TCG +all SVE vector lengths can be supported, when KVM is in use it's more +likely that only a few lengths will be supported, if SVE is supported at +all.) (2) Let's try to disable the PMU:: (QEMU) query-cpu-model-expansion type=full model={"name":"max","props":{"pmu":false}} { "return": { "model": { "name": "max", "props": { - "pmu": false, "aarch64": true + "sve1664": true, "pmu": false, "sve1792": true, "sve1920": true, + "sve128": true, "aarch64": true, "sve1024": true, "sve": true, + "sve640": true, "sve768": true, "sve1408": true, "sve256": true, + "sve1152": true, "sve512": true, "sve384": true, "sve1536": true, + "sve896": true, "sve1280": true, "sve2048": true }}}} We see it worked, as `pmu` is now `false`. @@ -XXX,XX +XXX,XX @@ We see it worked, as `pmu` is now `false`. It looks like this feature is limited to a configuration we do not currently have. -(4) Let's try probing CPU features for the Cortex-A15 CPU type:: +(4) Let's disable `sve` and see what happens to all the optional SVE + vector lengths:: + + (QEMU) query-cpu-model-expansion type=full model={"name":"max","props":{"sve":false}} + { "return": { + "model": { "name": "max", "props": { + "sve1664": false, "pmu": true, "sve1792": false, "sve1920": false, + "sve128": false, "aarch64": true, "sve1024": false, "sve": false, + "sve640": false, "sve768": false, "sve1408": false, "sve256": false, + "sve1152": false, "sve512": false, "sve384": false, "sve1536": false, + "sve896": false, "sve1280": false, "sve2048": false + }}}} + +As expected they are now all `false`. + +(5) Let's try probing CPU features for the Cortex-A15 CPU type:: (QEMU) query-cpu-model-expansion type=full model={"name":"cortex-a15"} {"return": {"model": {"name": "cortex-a15", "props": {"pmu": true}}}} @@ -XXX,XX +XXX,XX @@ After determining which CPU features are available and supported for a given CPU type, then they may be selectively enabled or disabled on the QEMU command line with that CPU type:: - $ qemu-system-aarch64 -M virt -cpu max,pmu=off + $ qemu-system-aarch64 -M virt -cpu max,pmu=off,sve=on,sve128=on,sve256=on -The example above disables the PMU for the `max` CPU type. +The example above disables the PMU and enables the first two SVE vector +lengths for the `max` CPU type. Note, the `sve=on` isn't actually +necessary, because, as we observed above with our probe of the `max` CPU +type, `sve` is already on by default. Also, based on our probe of +defaults, it would seem we need to disable many SVE vector lengths, rather +than only enabling the two we want. This isn't the case, because, as +disabling many SVE vector lengths would be quite verbose, the `sve<N>` CPU +properties have special semantics (see "SVE CPU Property Parsing +Semantics"). + +SVE CPU Properties +================== + +There are two types of SVE CPU properties: `sve` and `sve<N>`. The first +is used to enable or disable the entire SVE feature, just as the `pmu` +CPU property completely enables or disables the PMU. The second type +is used to enable or disable specific vector lengths, where `N` is the +number of bits of the length. The `sve<N>` CPU properties have special +dependencies and constraints, see "SVE CPU Property Dependencies and +Constraints" below. Additionally, as we want all supported vector lengths +to be enabled by default, then, in order to avoid overly verbose command +lines (command lines full of `sve<N>=off`, for all `N` not wanted), we +provide the parsing semantics listed in "SVE CPU Property Parsing +Semantics". + +SVE CPU Property Dependencies and Constraints +--------------------------------------------- + + 1) At least one vector length must be enabled when `sve` is enabled. + + 2) If a vector length `N` is enabled, then all power-of-two vector + lengths smaller than `N` must also be enabled. E.g. if `sve512` + is enabled, then the 128-bit and 256-bit vector lengths must also + be enabled. + +SVE CPU Property Parsing Semantics +---------------------------------- + + 1) If SVE is disabled (`sve=off`), then which SVE vector lengths + are enabled or disabled is irrelevant to the guest, as the entire + SVE feature is disabled and that disables all vector lengths for + the guest. However QEMU will still track any `sve<N>` CPU + properties provided by the user. If later an `sve=on` is provided, + then the guest will get only the enabled lengths. If no `sve=on` + is provided and there are explicitly enabled vector lengths, then + an error is generated. + + 2) If SVE is enabled (`sve=on`), but no `sve<N>` CPU properties are + provided, then all supported vector lengths are enabled, including + the non-power-of-two lengths. + + 3) If SVE is enabled, then an error is generated when attempting to + disable the last enabled vector length (see constraint (1) of "SVE + CPU Property Dependencies and Constraints"). + + 4) If one or more vector lengths have been explicitly enabled and at + at least one of the dependency lengths of the maximum enabled length + has been explicitly disabled, then an error is generated (see + constraint (2) of "SVE CPU Property Dependencies and Constraints"). + + 5) If one or more `sve<N>` CPU properties are set `off`, but no `sve<N>`, + CPU properties are set `on`, then the specified vector lengths are + disabled but the default for any unspecified lengths remains enabled. + Disabling a power-of-two vector length also disables all vector + lengths larger than the power-of-two length (see constraint (2) of + "SVE CPU Property Dependencies and Constraints"). + + 6) If one or more `sve<N>` CPU properties are set to `on`, then they + are enabled and all unspecified lengths default to disabled, except + for the required lengths per constraint (2) of "SVE CPU Property + Dependencies and Constraints", which will even be auto-enabled if + they were not explicitly enabled. + + 7) If SVE was disabled (`sve=off`), allowing all vector lengths to be + explicitly disabled (i.e. avoiding the error specified in (3) of + "SVE CPU Property Parsing Semantics"), then if later an `sve=on` is + provided an error will be generated. To avoid this error, one must + enable at least one vector length prior to enabling SVE. + +SVE CPU Property Examples +------------------------- + + 1) Disable SVE:: + + $ qemu-system-aarch64 -M virt -cpu max,sve=off + + 2) Implicitly enable all vector lengths for the `max` CPU type:: + + $ qemu-system-aarch64 -M virt -cpu max + + 3) Only enable the 128-bit vector length:: + + $ qemu-system-aarch64 -M virt -cpu max,sve128=on + + 4) Disable the 512-bit vector length and all larger vector lengths, + since 512 is a power-of-two. This results in all the smaller, + uninitialized lengths (128, 256, and 384) defaulting to enabled:: + + $ qemu-system-aarch64 -M virt -cpu max,sve512=off + + 5) Enable the 128-bit, 256-bit, and 512-bit vector lengths:: + + $ qemu-system-aarch64 -M virt -cpu max,sve128=on,sve256=on,sve512=on + + 6) The same as (5), but since the 128-bit and 256-bit vector + lengths are required for the 512-bit vector length to be enabled, + then allow them to be auto-enabled:: + + $ qemu-system-aarch64 -M virt -cpu max,sve512=on + + 7) Do the same as (6), but by first disabling SVE and then re-enabling it:: + + $ qemu-system-aarch64 -M virt -cpu max,sve=off,sve512=on,sve=on + + 8) Force errors regarding the last vector length:: + + $ qemu-system-aarch64 -M virt -cpu max,sve128=off + $ qemu-system-aarch64 -M virt -cpu max,sve=off,sve128=off,sve=on + +SVE CPU Property Recommendations +-------------------------------- + +The examples in "SVE CPU Property Examples" exhibit many ways to select +vector lengths which developers may find useful in order to avoid overly +verbose command lines. However, the recommended way to select vector +lengths is to explicitly enable each desired length. Therefore only +example's (1), (3), and (5) exhibit recommended uses of the properties. -- 2.20.1 From: Andrew Jones <drjones@redhat.com> These are the SVE equivalents to kvm_arch_get/put_fpsimd. Note, the swabbing is different than it is for fpsmid because the vector format is a little-endian stream of words. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Message-id: 20191024121808.9612-6-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm64.c | 185 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 156 insertions(+), 29 deletions(-) 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_destroy_vcpu(CPUState *cs) bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx) { /* Return true if the regidx is a register we should synchronize - * via the cpreg_tuples array (ie is not a core reg we sync by - * hand in kvm_arch_get/put_registers()) + * via the cpreg_tuples array (ie is not a core or sve reg that + * we sync by hand in kvm_arch_get/put_registers()) */ switch (regidx & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: + case KVM_REG_ARM64_SVE: return false; default: return true; @@ -XXX,XX +XXX,XX @@ int kvm_arm_cpreg_level(uint64_t regidx) static int kvm_arch_put_fpsimd(CPUState *cs) { - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; + CPUARMState *env = &ARM_CPU(cs)->env; struct kvm_one_reg reg; - uint32_t fpr; int i, ret; for (i = 0; i < 32; i++) { @@ -XXX,XX +XXX,XX @@ static int kvm_arch_put_fpsimd(CPUState *cs) } } - reg.addr = (uintptr_t)(&fpr); - fpr = vfp_get_fpsr(env); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); - if (ret) { - return ret; + return 0; +} + +/* + * SVE registers are encoded in KVM's memory in an endianness-invariant format. + * The byte at offset i from the start of the in-memory representation contains + * the bits [(7 + 8 * i) : (8 * i)] of the register value. As this means the + * lowest offsets are stored in the lowest memory addresses, then that nearly + * matches QEMU's representation, which is to use an array of host-endian + * uint64_t's, where the lower offsets are at the lower indices. To complete + * the translation we just need to byte swap the uint64_t's on big-endian hosts. + */ +static uint64_t *sve_bswap64(uint64_t *dst, uint64_t *src, int nr) +{ +#ifdef HOST_WORDS_BIGENDIAN + int i; + + for (i = 0; i < nr; ++i) { + dst[i] = bswap64(src[i]); } - reg.addr = (uintptr_t)(&fpr); - fpr = vfp_get_fpcr(env); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); + return dst; +#else + return src; +#endif +} + +/* + * KVM SVE registers come in slices where ZREGs have a slice size of 2048 bits + * and PREGS and the FFR have a slice size of 256 bits. However we simply hard + * code the slice index to zero for now as it's unlikely we'll need more than + * one slice for quite some time. + */ +static int kvm_arch_put_sve(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + uint64_t tmp[ARM_MAX_VQ * 2]; + uint64_t *r; + struct kvm_one_reg reg; + int n, ret; + + for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) { + r = sve_bswap64(tmp, &env->vfp.zregs[n].d[0], cpu->sve_max_vq * 2); + reg.addr = (uintptr_t)r; + reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); + if (ret) { + return ret; + } + } + + for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) { + r = sve_bswap64(tmp, r = &env->vfp.pregs[n].p[0], + DIV_ROUND_UP(cpu->sve_max_vq * 2, 8)); + reg.addr = (uintptr_t)r; + reg.id = KVM_REG_ARM64_SVE_PREG(n, 0); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); + if (ret) { + return ret; + } + } + + r = sve_bswap64(tmp, &env->vfp.pregs[FFR_PRED_NUM].p[0], + DIV_ROUND_UP(cpu->sve_max_vq * 2, 8)); + reg.addr = (uintptr_t)r; + reg.id = KVM_REG_ARM64_SVE_FFR(0); ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); if (ret) { return ret; @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) { struct kvm_one_reg reg; uint64_t val; + uint32_t fpr; int i, ret; unsigned int el; @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) } } - ret = kvm_arch_put_fpsimd(cs); + if (cpu_isar_feature(aa64_sve, cpu)) { + ret = kvm_arch_put_sve(cs); + } else { + ret = kvm_arch_put_fpsimd(cs); + } + if (ret) { + return ret; + } + + reg.addr = (uintptr_t)(&fpr); + fpr = vfp_get_fpsr(env); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); + if (ret) { + return ret; + } + + reg.addr = (uintptr_t)(&fpr); + fpr = vfp_get_fpcr(env); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); if (ret) { return ret; } @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) static int kvm_arch_get_fpsimd(CPUState *cs) { - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; + CPUARMState *env = &ARM_CPU(cs)->env; struct kvm_one_reg reg; - uint32_t fpr; int i, ret; for (i = 0; i < 32; i++) { @@ -XXX,XX +XXX,XX @@ static int kvm_arch_get_fpsimd(CPUState *cs) } } - reg.addr = (uintptr_t)(&fpr); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); - if (ret) { - return ret; - } - vfp_set_fpsr(env, fpr); + return 0; +} - reg.addr = (uintptr_t)(&fpr); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); +/* + * KVM SVE registers come in slices where ZREGs have a slice size of 2048 bits + * and PREGS and the FFR have a slice size of 256 bits. However we simply hard + * code the slice index to zero for now as it's unlikely we'll need more than + * one slice for quite some time. + */ +static int kvm_arch_get_sve(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + struct kvm_one_reg reg; + uint64_t *r; + int n, ret; + + for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) { + r = &env->vfp.zregs[n].d[0]; + reg.addr = (uintptr_t)r; + reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); + if (ret) { + return ret; + } + sve_bswap64(r, r, cpu->sve_max_vq * 2); + } + + for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) { + r = &env->vfp.pregs[n].p[0]; + reg.addr = (uintptr_t)r; + reg.id = KVM_REG_ARM64_SVE_PREG(n, 0); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); + if (ret) { + return ret; + } + sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8)); + } + + r = &env->vfp.pregs[FFR_PRED_NUM].p[0]; + reg.addr = (uintptr_t)r; + reg.id = KVM_REG_ARM64_SVE_FFR(0); ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); if (ret) { return ret; } - vfp_set_fpcr(env, fpr); + sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8)); return 0; } @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) struct kvm_one_reg reg; uint64_t val; unsigned int el; + uint32_t fpr; int i, ret; ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) env->spsr = env->banked_spsr[i]; } - ret = kvm_arch_get_fpsimd(cs); + if (cpu_isar_feature(aa64_sve, cpu)) { + ret = kvm_arch_get_sve(cs); + } else { + ret = kvm_arch_get_fpsimd(cs); + } if (ret) { return ret; } + reg.addr = (uintptr_t)(&fpr); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); + if (ret) { + return ret; + } + vfp_set_fpsr(env, fpr); + + reg.addr = (uintptr_t)(&fpr); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); + if (ret) { + return ret; + } + vfp_set_fpcr(env, fpr); + ret = kvm_get_vcpu_events(cpu); if (ret) { return ret; -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Enable SVE in the KVM guest when the 'max' cpu type is configured and KVM supports it. KVM SVE requires use of the new finalize vcpu ioctl, so we add that now too. For starters SVE can only be turned on or off, getting all vector lengths the host CPU supports when on. We'll add the other SVE CPU properties in later patches. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Reviewed-by: Beata Michalska <beata.michalska@linaro.org> Message-id: 20191024121808.9612-7-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 27 +++++++++++++++++++++++++++ target/arm/cpu64.c | 17 ++++++++++++++--- target/arm/kvm.c | 5 +++++ target/arm/kvm64.c | 20 +++++++++++++++++++- tests/arm-cpu-features.c | 4 ++++ 5 files changed, 69 insertions(+), 4 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 @@ */ int kvm_arm_vcpu_init(CPUState *cs); +/** + * kvm_arm_vcpu_finalize + * @cs: CPUState + * @feature: int + * + * Finalizes the configuration of the specified VCPU feature by + * invoking the KVM_ARM_VCPU_FINALIZE ioctl. Features requiring + * this are documented in the "KVM_ARM_VCPU_FINALIZE" section of + * KVM's API documentation. + * + * Returns: 0 if success else < 0 error code + */ +int kvm_arm_vcpu_finalize(CPUState *cs, int feature); + /** * kvm_arm_register_device: * @mr: memory region for this device @@ -XXX,XX +XXX,XX @@ bool kvm_arm_aarch32_supported(CPUState *cs); */ bool kvm_arm_pmu_supported(CPUState *cs); +/** + * bool kvm_arm_sve_supported: + * @cs: CPUState + * + * Returns true if the KVM VCPU can enable SVE and false otherwise. + */ +bool kvm_arm_sve_supported(CPUState *cs); + /** * kvm_arm_get_max_vm_ipa_size - Returns the number of bits in the * IPA address space supported by KVM @@ -XXX,XX +XXX,XX @@ static inline bool kvm_arm_pmu_supported(CPUState *cs) return false; } +static inline bool kvm_arm_sve_supported(CPUState *cs) +{ + return false; +} + static inline int kvm_arm_get_max_vm_ipa_size(MachineState *ms) { return -ENOENT; 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 cpu_arm_set_sve(Object *obj, Visitor *v, const char *name, return; } + if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) { + error_setg(errp, "'sve' feature not supported by KVM on this host"); + return; + } + t = cpu->isar.id_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, SVE, value); cpu->isar.id_aa64pfr0 = t; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); uint32_t vq; + uint64_t t; if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); + if (kvm_arm_sve_supported(CPU(cpu))) { + t = cpu->isar.id_aa64pfr0; + t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); + cpu->isar.id_aa64pfr0 = t; + } } else { - uint64_t t; uint32_t u; aarch64_a57_initfn(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); - object_property_add(obj, "sve", "bool", cpu_arm_get_sve, - cpu_arm_set_sve, NULL, NULL, &error_fatal); for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { char name[8]; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu_arm_set_sve_vq, NULL, NULL, &error_fatal); } } + + object_property_add(obj, "sve", "bool", cpu_arm_get_sve, + cpu_arm_set_sve, NULL, NULL, &error_fatal); } struct ARMCPUInfo { 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_arm_vcpu_init(CPUState *cs) return kvm_vcpu_ioctl(cs, KVM_ARM_VCPU_INIT, &init); } +int kvm_arm_vcpu_finalize(CPUState *cs, int feature) +{ + return kvm_vcpu_ioctl(cs, KVM_ARM_VCPU_FINALIZE, &feature); +} + void kvm_arm_init_serror_injection(CPUState *cs) { cap_has_inject_serror_esr = kvm_check_extension(cs->kvm_state, 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_aarch32_supported(CPUState *cpu) return kvm_check_extension(s, KVM_CAP_ARM_EL1_32BIT); } +bool kvm_arm_sve_supported(CPUState *cpu) +{ + KVMState *s = KVM_STATE(current_machine->accelerator); + + return kvm_check_extension(s, KVM_CAP_ARM_SVE); +} + #define ARM_CPU_ID_MPIDR 3, 0, 0, 0, 5 int kvm_arch_init_vcpu(CPUState *cs) @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_EL1_32BIT; } if (!kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PMU_V3)) { - cpu->has_pmu = false; + cpu->has_pmu = false; } if (cpu->has_pmu) { cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PMU_V3; } else { unset_feature(&env->features, ARM_FEATURE_PMU); } + if (cpu_isar_feature(aa64_sve, cpu)) { + assert(kvm_arm_sve_supported(cs)); + cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_SVE; + } /* Do KVM_ARM_VCPU_INIT ioctl */ ret = kvm_arm_vcpu_init(cs); @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) return ret; } + if (cpu_isar_feature(aa64_sve, cpu)) { + ret = kvm_arm_vcpu_finalize(cs, KVM_ARM_VCPU_SVE); + if (ret) { + return ret; + } + } + /* * When KVM is in use, PSCI is emulated in-kernel and not by qemu. * Currently KVM has its own idea about MPIDR assignment, so we diff --git a/tests/arm-cpu-features.c b/tests/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/arm-cpu-features.c +++ b/tests/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) assert_has_feature(qts, "host", "aarch64"); assert_has_feature(qts, "host", "pmu"); + assert_has_feature(qts, "max", "sve"); + assert_error(qts, "cortex-a15", "We cannot guarantee the CPU type 'cortex-a15' works " "with KVM on this host", NULL); } else { assert_has_not_feature(qts, "host", "aarch64"); assert_has_not_feature(qts, "host", "pmu"); + + assert_has_not_feature(qts, "max", "sve"); } qtest_quit(qts); -- 2.20.1 From: Andrew Jones <drjones@redhat.com> kvm_arm_create_scratch_host_vcpu() takes a struct kvm_vcpu_init parameter. Rather than just using it as an output parameter to pass back the preferred target, use it also as an input parameter, allowing a caller to pass a selected target if they wish and to also pass cpu features. If the caller doesn't want to select a target they can pass -1 for the target which indicates they want to use the preferred target and have it passed back like before. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Reviewed-by: Beata Michalska <beata.michalska@linaro.org> Message-id: 20191024121808.9612-8-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm.c | 20 +++++++++++++++----- target/arm/kvm32.c | 6 +++++- target/arm/kvm64.c | 6 +++++- 3 files changed, 25 insertions(+), 7 deletions(-) diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, int *fdarray, struct kvm_vcpu_init *init) { - int ret, kvmfd = -1, vmfd = -1, cpufd = -1; + int ret = 0, kvmfd = -1, vmfd = -1, cpufd = -1; kvmfd = qemu_open("/dev/kvm", O_RDWR); if (kvmfd < 0) { @@ -XXX,XX +XXX,XX @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, goto finish; } - ret = ioctl(vmfd, KVM_ARM_PREFERRED_TARGET, init); + if (init->target == -1) { + struct kvm_vcpu_init preferred; + + ret = ioctl(vmfd, KVM_ARM_PREFERRED_TARGET, &preferred); + if (!ret) { + init->target = preferred.target; + } + } if (ret >= 0) { ret = ioctl(cpufd, KVM_ARM_VCPU_INIT, init); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, * creating one kind of guest CPU which is its preferred * CPU type. */ + struct kvm_vcpu_init try; + while (*cpus_to_try != QEMU_KVM_ARM_TARGET_NONE) { - init->target = *cpus_to_try++; - memset(init->features, 0, sizeof(init->features)); - ret = ioctl(cpufd, KVM_ARM_VCPU_INIT, init); + try.target = *cpus_to_try++; + memcpy(try.features, init->features, sizeof(init->features)); + ret = ioctl(cpufd, KVM_ARM_VCPU_INIT, &try); if (ret >= 0) { break; } @@ -XXX,XX +XXX,XX @@ bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, if (ret < 0) { goto err; } + init->target = try.target; } else { /* Treat a NULL cpus_to_try argument the same as an empty * list, which means we will fail the call since this must 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 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) QEMU_KVM_ARM_TARGET_CORTEX_A15, QEMU_KVM_ARM_TARGET_NONE }; - struct kvm_vcpu_init init; + /* + * target = -1 informs kvm_arm_create_scratch_host_vcpu() + * to use the preferred target + */ + struct kvm_vcpu_init init = { .target = -1, }; if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) { return false; 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) KVM_ARM_TARGET_CORTEX_A57, QEMU_KVM_ARM_TARGET_NONE }; - struct kvm_vcpu_init init; + /* + * target = -1 informs kvm_arm_create_scratch_host_vcpu() + * to use the preferred target + */ + struct kvm_vcpu_init init = { .target = -1, }; if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) { return false; -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Extend the SVE vq map initialization and validation with KVM's supported vector lengths when KVM is enabled. In order to determine and select supported lengths we add two new KVM functions for getting and setting the KVM_REG_ARM64_SVE_VLS pseudo-register. This patch has been co-authored with Richard Henderson, who reworked the target/arm/cpu64.c changes in order to push all the validation and auto-enabling/disabling steps into the finalizer, resulting in a nice LOC reduction. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Message-id: 20191024121808.9612-9-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 12 +++ target/arm/cpu64.c | 176 ++++++++++++++++++++++++++++---------- target/arm/kvm64.c | 100 +++++++++++++++++++++- tests/arm-cpu-features.c | 106 ++++++++++++++++++++++- docs/arm-cpu-features.rst | 45 +++++++--- 5 files changed, 381 insertions(+), 58 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 @@ typedef struct ARMHostCPUFeatures { */ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf); +/** + * kvm_arm_sve_get_vls: + * @cs: CPUState + * @map: bitmap to fill in + * + * Get all the SVE vector lengths supported by the KVM host, setting + * the bits corresponding to their length in quadwords minus one + * (vq - 1) in @map up to ARM_MAX_VQ. + */ +void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map); + /** * kvm_arm_set_cpu_features_from_host: * @cpu: ARMCPU to set the features for @@ -XXX,XX +XXX,XX @@ static inline int kvm_arm_vgic_probe(void) static inline void kvm_arm_pmu_set_irq(CPUState *cs, int irq) {} static inline void kvm_arm_pmu_init(CPUState *cs) {} +static inline void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map) {} #endif static inline const char *gic_class_name(void) 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 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) * any of the above. Finally, if SVE is not disabled, then at least one * vector length must be enabled. */ + DECLARE_BITMAP(kvm_supported, ARM_MAX_VQ); DECLARE_BITMAP(tmp, ARM_MAX_VQ); uint32_t vq, max_vq = 0; + /* Collect the set of vector lengths supported by KVM. */ + bitmap_zero(kvm_supported, ARM_MAX_VQ); + if (kvm_enabled() && kvm_arm_sve_supported(CPU(cpu))) { + kvm_arm_sve_get_vls(CPU(cpu), kvm_supported); + } else if (kvm_enabled()) { + assert(!cpu_isar_feature(aa64_sve, cpu)); + } + /* * Process explicit sve<N> properties. * From the properties, sve_vq_map<N> implies sve_vq_init<N>. @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) return; } - /* Propagate enabled bits down through required powers-of-two. */ - for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { - if (!test_bit(vq - 1, cpu->sve_vq_init)) { - set_bit(vq - 1, cpu->sve_vq_map); + if (kvm_enabled()) { + /* + * For KVM we have to automatically enable all supported unitialized + * lengths, even when the smaller lengths are not all powers-of-two. + */ + bitmap_andnot(tmp, kvm_supported, cpu->sve_vq_init, max_vq); + bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq); + } else { + /* Propagate enabled bits down through required powers-of-two. */ + for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { + if (!test_bit(vq - 1, cpu->sve_vq_init)) { + set_bit(vq - 1, cpu->sve_vq_map); + } } } } else if (cpu->sve_max_vq == 0) { @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) return; } - /* Disabling a power-of-two disables all larger lengths. */ - if (test_bit(0, cpu->sve_vq_init)) { - error_setg(errp, "cannot disable sve128"); - error_append_hint(errp, "Disabling sve128 results in all vector " - "lengths being disabled.\n"); - error_append_hint(errp, "With SVE enabled, at least one vector " - "length must be enabled.\n"); - return; - } - for (vq = 2; vq <= ARM_MAX_VQ; vq <<= 1) { - if (test_bit(vq - 1, cpu->sve_vq_init)) { - break; + if (kvm_enabled()) { + /* Disabling a supported length disables all larger lengths. */ + for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { + if (test_bit(vq - 1, cpu->sve_vq_init) && + test_bit(vq - 1, kvm_supported)) { + break; + } } + max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ; + bitmap_andnot(cpu->sve_vq_map, kvm_supported, + cpu->sve_vq_init, max_vq); + if (max_vq == 0 || bitmap_empty(cpu->sve_vq_map, max_vq)) { + error_setg(errp, "cannot disable sve%d", vq * 128); + error_append_hint(errp, "Disabling sve%d results in all " + "vector lengths being disabled.\n", + vq * 128); + error_append_hint(errp, "With SVE enabled, at least one " + "vector length must be enabled.\n"); + return; + } + } else { + /* Disabling a power-of-two disables all larger lengths. */ + if (test_bit(0, cpu->sve_vq_init)) { + error_setg(errp, "cannot disable sve128"); + error_append_hint(errp, "Disabling sve128 results in all " + "vector lengths being disabled.\n"); + error_append_hint(errp, "With SVE enabled, at least one " + "vector length must be enabled.\n"); + return; + } + for (vq = 2; vq <= ARM_MAX_VQ; vq <<= 1) { + if (test_bit(vq - 1, cpu->sve_vq_init)) { + break; + } + } + max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ; + bitmap_complement(cpu->sve_vq_map, cpu->sve_vq_init, max_vq); } - max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ; - bitmap_complement(cpu->sve_vq_map, cpu->sve_vq_init, max_vq); max_vq = find_last_bit(cpu->sve_vq_map, max_vq) + 1; } @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) assert(max_vq != 0); bitmap_clear(cpu->sve_vq_map, max_vq, ARM_MAX_VQ - max_vq); - /* Ensure all required powers-of-two are enabled. */ - for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { - if (!test_bit(vq - 1, cpu->sve_vq_map)) { - error_setg(errp, "cannot disable sve%d", vq * 128); - error_append_hint(errp, "sve%d is required as it " - "is a power-of-two length smaller than " - "the maximum, sve%d\n", - vq * 128, max_vq * 128); + if (kvm_enabled()) { + /* Ensure the set of lengths matches what KVM supports. */ + bitmap_xor(tmp, cpu->sve_vq_map, kvm_supported, max_vq); + if (!bitmap_empty(tmp, max_vq)) { + vq = find_last_bit(tmp, max_vq) + 1; + if (test_bit(vq - 1, cpu->sve_vq_map)) { + if (cpu->sve_max_vq) { + error_setg(errp, "cannot set sve-max-vq=%d", + cpu->sve_max_vq); + error_append_hint(errp, "This KVM host does not support " + "the vector length %d-bits.\n", + vq * 128); + error_append_hint(errp, "It may not be possible to use " + "sve-max-vq with this KVM host. Try " + "using only sve<N> properties.\n"); + } else { + error_setg(errp, "cannot enable sve%d", vq * 128); + error_append_hint(errp, "This KVM host does not support " + "the vector length %d-bits.\n", + vq * 128); + } + } else { + error_setg(errp, "cannot disable sve%d", vq * 128); + error_append_hint(errp, "The KVM host requires all " + "supported vector lengths smaller " + "than %d bits to also be enabled.\n", + max_vq * 128); + } return; } + } else { + /* Ensure all required powers-of-two are enabled. */ + for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) { + if (!test_bit(vq - 1, cpu->sve_vq_map)) { + error_setg(errp, "cannot disable sve%d", vq * 128); + error_append_hint(errp, "sve%d is required as it " + "is a power-of-two length smaller than " + "the maximum, sve%d\n", + vq * 128, max_vq * 128); + return; + } + } } /* @@ -XXX,XX +XXX,XX @@ static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, { ARMCPU *cpu = ARM_CPU(obj); Error *err = NULL; + uint32_t max_vq; - visit_type_uint32(v, name, &cpu->sve_max_vq, &err); - - if (!err && (cpu->sve_max_vq == 0 || cpu->sve_max_vq > ARM_MAX_VQ)) { - error_setg(&err, "unsupported SVE vector length"); - error_append_hint(&err, "Valid sve-max-vq in range [1-%d]\n", - ARM_MAX_VQ); + visit_type_uint32(v, name, &max_vq, &err); + if (err) { + error_propagate(errp, err); + return; } - error_propagate(errp, err); + + if (kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) { + error_setg(errp, "cannot set sve-max-vq"); + error_append_hint(errp, "SVE not supported by KVM on this host\n"); + return; + } + + if (max_vq == 0 || max_vq > ARM_MAX_VQ) { + error_setg(errp, "unsupported SVE vector length"); + error_append_hint(errp, "Valid sve-max-vq in range [1-%d]\n", + ARM_MAX_VQ); + return; + } + + cpu->sve_max_vq = max_vq; } static void cpu_arm_get_sve_vq(Object *obj, Visitor *v, const char *name, @@ -XXX,XX +XXX,XX @@ static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name, return; } + if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) { + error_setg(errp, "cannot enable %s", name); + error_append_hint(errp, "SVE not supported by KVM on this host\n"); + return; + } + if (value) { set_bit(vq - 1, cpu->sve_vq_map); } else { @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ cpu->dcz_blocksize = 7; /* 512 bytes */ #endif - - object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, - cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); - - for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { - char name[8]; - sprintf(name, "sve%d", vq * 128); - object_property_add(obj, name, "bool", cpu_arm_get_sve_vq, - cpu_arm_set_sve_vq, NULL, NULL, &error_fatal); - } } object_property_add(obj, "sve", "bool", cpu_arm_get_sve, cpu_arm_set_sve, NULL, NULL, &error_fatal); + object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, + cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); + + for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { + char name[8]; + sprintf(name, "sve%d", vq * 128); + object_property_add(obj, name, "bool", cpu_arm_get_sve_vq, + cpu_arm_set_sve_vq, NULL, NULL, &error_fatal); + } } struct ARMCPUInfo { 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_sve_supported(CPUState *cpu) return kvm_check_extension(s, KVM_CAP_ARM_SVE); } +QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1); + +void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map) +{ + /* Only call this function if kvm_arm_sve_supported() returns true. */ + static uint64_t vls[KVM_ARM64_SVE_VLS_WORDS]; + static bool probed; + uint32_t vq = 0; + int i, j; + + bitmap_clear(map, 0, ARM_MAX_VQ); + + /* + * KVM ensures all host CPUs support the same set of vector lengths. + * So we only need to create the scratch VCPUs once and then cache + * the results. + */ + if (!probed) { + struct kvm_vcpu_init init = { + .target = -1, + .features[0] = (1 << KVM_ARM_VCPU_SVE), + }; + struct kvm_one_reg reg = { + .id = KVM_REG_ARM64_SVE_VLS, + .addr = (uint64_t)&vls[0], + }; + int fdarray[3], ret; + + probed = true; + + if (!kvm_arm_create_scratch_host_vcpu(NULL, fdarray, &init)) { + error_report("failed to create scratch VCPU with SVE enabled"); + abort(); + } + ret = ioctl(fdarray[2], KVM_GET_ONE_REG, &reg); + kvm_arm_destroy_scratch_host_vcpu(fdarray); + if (ret) { + error_report("failed to get KVM_REG_ARM64_SVE_VLS: %s", + strerror(errno)); + abort(); + } + + for (i = KVM_ARM64_SVE_VLS_WORDS - 1; i >= 0; --i) { + if (vls[i]) { + vq = 64 - clz64(vls[i]) + i * 64; + break; + } + } + if (vq > ARM_MAX_VQ) { + warn_report("KVM supports vector lengths larger than " + "QEMU can enable"); + } + } + + for (i = 0; i < KVM_ARM64_SVE_VLS_WORDS; ++i) { + if (!vls[i]) { + continue; + } + for (j = 1; j <= 64; ++j) { + vq = j + i * 64; + if (vq > ARM_MAX_VQ) { + return; + } + if (vls[i] & (1UL << (j - 1))) { + set_bit(vq - 1, map); + } + } + } +} + +static int kvm_arm_sve_set_vls(CPUState *cs) +{ + uint64_t vls[KVM_ARM64_SVE_VLS_WORDS] = {0}; + struct kvm_one_reg reg = { + .id = KVM_REG_ARM64_SVE_VLS, + .addr = (uint64_t)&vls[0], + }; + ARMCPU *cpu = ARM_CPU(cs); + uint32_t vq; + int i, j; + + assert(cpu->sve_max_vq <= KVM_ARM64_SVE_VQ_MAX); + + for (vq = 1; vq <= cpu->sve_max_vq; ++vq) { + if (test_bit(vq - 1, cpu->sve_vq_map)) { + i = (vq - 1) / 64; + j = (vq - 1) % 64; + vls[i] |= 1UL << j; + } + } + + return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); +} + #define ARM_CPU_ID_MPIDR 3, 0, 0, 0, 5 int kvm_arch_init_vcpu(CPUState *cs) @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE || !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) { - fprintf(stderr, "KVM is not supported for this guest CPU type\n"); + error_report("KVM is not supported for this guest CPU type"); return -EINVAL; } @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) } if (cpu_isar_feature(aa64_sve, cpu)) { + ret = kvm_arm_sve_set_vls(cs); + if (ret) { + return ret; + } ret = kvm_arm_vcpu_finalize(cs, KVM_ARM_VCPU_SVE); if (ret) { return ret; diff --git a/tests/arm-cpu-features.c b/tests/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/arm-cpu-features.c +++ b/tests/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static QDict *resp_get_props(QDict *resp) return qdict; } +static bool resp_get_feature(QDict *resp, const char *feature) +{ + QDict *props; + + g_assert(resp); + g_assert(resp_has_props(resp)); + props = resp_get_props(resp); + g_assert(qdict_get(props, feature)); + return qdict_get_bool(props, feature); +} + #define assert_has_feature(qts, cpu_type, feature) \ ({ \ QDict *_resp = do_query_no_props(qts, cpu_type); \ @@ -XXX,XX +XXX,XX @@ static void sve_tests_sve_off(const void *data) qtest_quit(qts); } +static void sve_tests_sve_off_kvm(const void *data) +{ + QTestState *qts; + + qts = qtest_init(MACHINE "-accel kvm -cpu max,sve=off"); + + /* + * We don't know if this host supports SVE so we don't + * attempt to test enabling anything. We only test that + * everything is disabled (as it should be with sve=off) + * and that using sve<N>=off to explicitly disable vector + * lengths is OK too. + */ + assert_sve_vls(qts, "max", 0, NULL); + assert_sve_vls(qts, "max", 0, "{ 'sve128': false }"); + + qtest_quit(qts); +} + static void test_query_cpu_model_expansion(const void *data) { QTestState *qts; @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) qts = qtest_init(MACHINE "-accel kvm -cpu host"); if (g_str_equal(qtest_get_arch(), "aarch64")) { + bool kvm_supports_sve; + char max_name[8], name[8]; + uint32_t max_vq, vq; + uint64_t vls; + QDict *resp; + char *error; + assert_has_feature(qts, "host", "aarch64"); assert_has_feature(qts, "host", "pmu"); - assert_has_feature(qts, "max", "sve"); - assert_error(qts, "cortex-a15", "We cannot guarantee the CPU type 'cortex-a15' works " "with KVM on this host", NULL); + + assert_has_feature(qts, "max", "sve"); + resp = do_query_no_props(qts, "max"); + kvm_supports_sve = resp_get_feature(resp, "sve"); + vls = resp_get_sve_vls(resp); + qobject_unref(resp); + + if (kvm_supports_sve) { + g_assert(vls != 0); + max_vq = 64 - __builtin_clzll(vls); + sprintf(max_name, "sve%d", max_vq * 128); + + /* Enabling a supported length is of course fine. */ + assert_sve_vls(qts, "max", vls, "{ %s: true }", max_name); + + /* Get the next supported length smaller than max-vq. */ + vq = 64 - __builtin_clzll(vls & ~BIT_ULL(max_vq - 1)); + if (vq) { + /* + * We have at least one length smaller than max-vq, + * so we can disable max-vq. + */ + assert_sve_vls(qts, "max", (vls & ~BIT_ULL(max_vq - 1)), + "{ %s: false }", max_name); + + /* + * Smaller, supported vector lengths cannot be disabled + * unless all larger, supported vector lengths are also + * disabled. + */ + sprintf(name, "sve%d", vq * 128); + error = g_strdup_printf("cannot disable %s", name); + assert_error(qts, "max", error, + "{ %s: true, %s: false }", + max_name, name); + g_free(error); + } + + /* + * The smallest, supported vector length is required, because + * we need at least one vector length enabled. + */ + vq = __builtin_ffsll(vls); + sprintf(name, "sve%d", vq * 128); + error = g_strdup_printf("cannot disable %s", name); + assert_error(qts, "max", error, "{ %s: false }", name); + g_free(error); + + /* Get an unsupported length. */ + for (vq = 1; vq <= max_vq; ++vq) { + if (!(vls & BIT_ULL(vq - 1))) { + break; + } + } + if (vq <= SVE_MAX_VQ) { + sprintf(name, "sve%d", vq * 128); + error = g_strdup_printf("cannot enable %s", name); + assert_error(qts, "max", error, "{ %s: true }", name); + g_free(error); + } + } else { + g_assert(vls == 0); + } } else { assert_has_not_feature(qts, "host", "aarch64"); assert_has_not_feature(qts, "host", "pmu"); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) if (kvm_available) { qtest_add_data_func("/arm/kvm/query-cpu-model-expansion", NULL, test_query_cpu_model_expansion_kvm); + if (g_str_equal(qtest_get_arch(), "aarch64")) { + qtest_add_data_func("/arm/kvm/query-cpu-model-expansion/sve-off", + NULL, sve_tests_sve_off_kvm); + } } return g_test_run(); diff --git a/docs/arm-cpu-features.rst b/docs/arm-cpu-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/arm-cpu-features.rst +++ b/docs/arm-cpu-features.rst @@ -XXX,XX +XXX,XX @@ SVE CPU Property Dependencies and Constraints 1) At least one vector length must be enabled when `sve` is enabled. - 2) If a vector length `N` is enabled, then all power-of-two vector - lengths smaller than `N` must also be enabled. E.g. if `sve512` - is enabled, then the 128-bit and 256-bit vector lengths must also - be enabled. + 2) If a vector length `N` is enabled, then, when KVM is enabled, all + smaller, host supported vector lengths must also be enabled. If + KVM is not enabled, then only all the smaller, power-of-two vector + lengths must be enabled. E.g. with KVM if the host supports all + vector lengths up to 512-bits (128, 256, 384, 512), then if `sve512` + is enabled, the 128-bit vector length, 256-bit vector length, and + 384-bit vector length must also be enabled. Without KVM, the 384-bit + vector length would not be required. + + 3) If KVM is enabled then only vector lengths that the host CPU type + support may be enabled. If SVE is not supported by the host, then + no `sve*` properties may be enabled. SVE CPU Property Parsing Semantics ---------------------------------- @@ -XXX,XX +XXX,XX @@ SVE CPU Property Parsing Semantics an error is generated. 2) If SVE is enabled (`sve=on`), but no `sve<N>` CPU properties are - provided, then all supported vector lengths are enabled, including - the non-power-of-two lengths. + provided, then all supported vector lengths are enabled, which when + KVM is not in use means including the non-power-of-two lengths, and, + when KVM is in use, it means all vector lengths supported by the host + processor. 3) If SVE is enabled, then an error is generated when attempting to disable the last enabled vector length (see constraint (1) of "SVE @@ -XXX,XX +XXX,XX @@ SVE CPU Property Parsing Semantics has been explicitly disabled, then an error is generated (see constraint (2) of "SVE CPU Property Dependencies and Constraints"). - 5) If one or more `sve<N>` CPU properties are set `off`, but no `sve<N>`, + 5) When KVM is enabled, if the host does not support SVE, then an error + is generated when attempting to enable any `sve*` properties (see + constraint (3) of "SVE CPU Property Dependencies and Constraints"). + + 6) When KVM is enabled, if the host does support SVE, then an error is + generated when attempting to enable any vector lengths not supported + by the host (see constraint (3) of "SVE CPU Property Dependencies and + Constraints"). + + 7) If one or more `sve<N>` CPU properties are set `off`, but no `sve<N>`, CPU properties are set `on`, then the specified vector lengths are disabled but the default for any unspecified lengths remains enabled. - Disabling a power-of-two vector length also disables all vector - lengths larger than the power-of-two length (see constraint (2) of - "SVE CPU Property Dependencies and Constraints"). + When KVM is not enabled, disabling a power-of-two vector length also + disables all vector lengths larger than the power-of-two length. + When KVM is enabled, then disabling any supported vector length also + disables all larger vector lengths (see constraint (2) of "SVE CPU + Property Dependencies and Constraints"). - 6) If one or more `sve<N>` CPU properties are set to `on`, then they + 8) If one or more `sve<N>` CPU properties are set to `on`, then they are enabled and all unspecified lengths default to disabled, except for the required lengths per constraint (2) of "SVE CPU Property Dependencies and Constraints", which will even be auto-enabled if they were not explicitly enabled. - 7) If SVE was disabled (`sve=off`), allowing all vector lengths to be + 9) If SVE was disabled (`sve=off`), allowing all vector lengths to be explicitly disabled (i.e. avoiding the error specified in (3) of "SVE CPU Property Parsing Semantics"), then if later an `sve=on` is provided an error will be generated. To avoid this error, one must -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Allow cpu 'host' to enable SVE when it's available, unless the user chooses to disable it with the added 'sve=off' cpu property. Also give the user the ability to select vector lengths with the sve<N> properties. We don't adopt 'max' cpu's other sve property, sve-max-vq, because that property is difficult to use with KVM. That property assumes all vector lengths in the range from 1 up to and including the specified maximum length are supported, but there may be optional lengths not supported by the host in that range. With KVM one must be more specific when enabling vector lengths. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com> Message-id: 20191024121808.9612-10-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/cpu.c | 3 +++ target/arm/cpu64.c | 33 +++++++++++++++++---------------- target/arm/kvm64.c | 14 +++++++++++++- tests/arm-cpu-features.c | 23 +++++++++++------------ docs/arm-cpu-features.rst | 19 ++++++++++++------- 6 files changed, 58 insertions(+), 36 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 @@ int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq); void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el, bool el0_a64); +void aarch64_add_sve_properties(Object *obj); #else static inline void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) { } static inline void aarch64_sve_change_el(CPUARMState *env, int o, int n, bool a) { } +static inline void aarch64_add_sve_properties(Object *obj) { } #endif #if !defined(CONFIG_TCG) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_host_initfn(Object *obj) ARMCPU *cpu = ARM_CPU(obj); kvm_arm_set_cpu_features_from_host(cpu); + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + aarch64_add_sve_properties(obj); + } arm_cpu_post_init(obj); } 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 cpu_arm_set_sve(Object *obj, Visitor *v, const char *name, cpu->isar.id_aa64pfr0 = t; } +void aarch64_add_sve_properties(Object *obj) +{ + uint32_t vq; + + object_property_add(obj, "sve", "bool", cpu_arm_get_sve, + cpu_arm_set_sve, NULL, NULL, &error_fatal); + + for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { + char name[8]; + sprintf(name, "sve%d", vq * 128); + object_property_add(obj, name, "bool", cpu_arm_get_sve_vq, + cpu_arm_set_sve_vq, NULL, NULL, &error_fatal); + } +} + /* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); * otherwise, a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu.c; @@ -XXX,XX +XXX,XX @@ static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name, static void aarch64_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - uint32_t vq; - uint64_t t; if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); - if (kvm_arm_sve_supported(CPU(cpu))) { - t = cpu->isar.id_aa64pfr0; - t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); - cpu->isar.id_aa64pfr0 = t; - } } else { + uint64_t t; uint32_t u; aarch64_a57_initfn(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) #endif } - object_property_add(obj, "sve", "bool", cpu_arm_get_sve, - cpu_arm_set_sve, NULL, NULL, &error_fatal); + aarch64_add_sve_properties(obj); object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); - - for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { - char name[8]; - sprintf(name, "sve%d", vq * 128); - object_property_add(obj, name, "bool", cpu_arm_get_sve_vq, - cpu_arm_set_sve_vq, NULL, NULL, &error_fatal); - } } struct ARMCPUInfo { 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) * and then query that CPU for the relevant ID registers. */ int fdarray[3]; + bool sve_supported; uint64_t features = 0; + uint64_t t; int err; /* Old kernels may not know about the PREFERRED_TARGET ioctl: however @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) ARM64_SYS_REG(3, 0, 0, 3, 2)); } + 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; } - /* We can assume any KVM supporting CPU is at least a v8 + /* 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; + } + + /* + * We can assume any KVM supporting CPU is at least a v8 * with VFPv4+Neon; this in turn implies most of the other * feature bits. */ diff --git a/tests/arm-cpu-features.c b/tests/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/arm-cpu-features.c +++ b/tests/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void sve_tests_sve_off_kvm(const void *data) { QTestState *qts; - qts = qtest_init(MACHINE "-accel kvm -cpu max,sve=off"); + qts = qtest_init(MACHINE "-accel kvm -cpu host,sve=off"); /* * We don't know if this host supports SVE so we don't @@ -XXX,XX +XXX,XX @@ static void sve_tests_sve_off_kvm(const void *data) * and that using sve<N>=off to explicitly disable vector * lengths is OK too. */ - assert_sve_vls(qts, "max", 0, NULL); - assert_sve_vls(qts, "max", 0, "{ 'sve128': false }"); + assert_sve_vls(qts, "host", 0, NULL); + assert_sve_vls(qts, "host", 0, "{ 'sve128': false }"); qtest_quit(qts); } @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) "We cannot guarantee the CPU type 'cortex-a15' works " "with KVM on this host", NULL); - assert_has_feature(qts, "max", "sve"); - resp = do_query_no_props(qts, "max"); + assert_has_feature(qts, "host", "sve"); + resp = do_query_no_props(qts, "host"); kvm_supports_sve = resp_get_feature(resp, "sve"); vls = resp_get_sve_vls(resp); qobject_unref(resp); @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) sprintf(max_name, "sve%d", max_vq * 128); /* Enabling a supported length is of course fine. */ - assert_sve_vls(qts, "max", vls, "{ %s: true }", max_name); + assert_sve_vls(qts, "host", vls, "{ %s: true }", max_name); /* Get the next supported length smaller than max-vq. */ vq = 64 - __builtin_clzll(vls & ~BIT_ULL(max_vq - 1)); @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) * We have at least one length smaller than max-vq, * so we can disable max-vq. */ - assert_sve_vls(qts, "max", (vls & ~BIT_ULL(max_vq - 1)), + assert_sve_vls(qts, "host", (vls & ~BIT_ULL(max_vq - 1)), "{ %s: false }", max_name); /* @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) */ sprintf(name, "sve%d", vq * 128); error = g_strdup_printf("cannot disable %s", name); - assert_error(qts, "max", error, + assert_error(qts, "host", error, "{ %s: true, %s: false }", max_name, name); g_free(error); @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) vq = __builtin_ffsll(vls); sprintf(name, "sve%d", vq * 128); error = g_strdup_printf("cannot disable %s", name); - assert_error(qts, "max", error, "{ %s: false }", name); + assert_error(qts, "host", error, "{ %s: false }", name); g_free(error); /* Get an unsupported length. */ @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) if (vq <= SVE_MAX_VQ) { sprintf(name, "sve%d", vq * 128); error = g_strdup_printf("cannot enable %s", name); - assert_error(qts, "max", error, "{ %s: true }", name); + assert_error(qts, "host", error, "{ %s: true }", name); g_free(error); } } else { @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) } else { assert_has_not_feature(qts, "host", "aarch64"); assert_has_not_feature(qts, "host", "pmu"); - - assert_has_not_feature(qts, "max", "sve"); + assert_has_not_feature(qts, "host", "sve"); } qtest_quit(qts); diff --git a/docs/arm-cpu-features.rst b/docs/arm-cpu-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/arm-cpu-features.rst +++ b/docs/arm-cpu-features.rst @@ -XXX,XX +XXX,XX @@ SVE CPU Property Examples $ qemu-system-aarch64 -M virt -cpu max - 3) Only enable the 128-bit vector length:: + 3) When KVM is enabled, implicitly enable all host CPU supported vector + lengths with the `host` CPU type:: + + $ qemu-system-aarch64 -M virt,accel=kvm -cpu host + + 4) Only enable the 128-bit vector length:: $ qemu-system-aarch64 -M virt -cpu max,sve128=on - 4) Disable the 512-bit vector length and all larger vector lengths, + 5) Disable the 512-bit vector length and all larger vector lengths, since 512 is a power-of-two. This results in all the smaller, uninitialized lengths (128, 256, and 384) defaulting to enabled:: $ qemu-system-aarch64 -M virt -cpu max,sve512=off - 5) Enable the 128-bit, 256-bit, and 512-bit vector lengths:: + 6) Enable the 128-bit, 256-bit, and 512-bit vector lengths:: $ qemu-system-aarch64 -M virt -cpu max,sve128=on,sve256=on,sve512=on - 6) The same as (5), but since the 128-bit and 256-bit vector + 7) The same as (6), but since the 128-bit and 256-bit vector lengths are required for the 512-bit vector length to be enabled, then allow them to be auto-enabled:: $ qemu-system-aarch64 -M virt -cpu max,sve512=on - 7) Do the same as (6), but by first disabling SVE and then re-enabling it:: + 8) Do the same as (7), but by first disabling SVE and then re-enabling it:: $ qemu-system-aarch64 -M virt -cpu max,sve=off,sve512=on,sve=on - 8) Force errors regarding the last vector length:: + 9) Force errors regarding the last vector length:: $ qemu-system-aarch64 -M virt -cpu max,sve128=off $ qemu-system-aarch64 -M virt -cpu max,sve=off,sve128=off,sve=on @@ -XXX,XX +XXX,XX @@ The examples in "SVE CPU Property Examples" exhibit many ways to select vector lengths which developers may find useful in order to avoid overly verbose command lines. However, the recommended way to select vector lengths is to explicitly enable each desired length. Therefore only -example's (1), (3), and (5) exhibit recommended uses of the properties. +example's (1), (4), and (6) exhibit recommended uses of the properties. -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> We will soon implement the SYS_timer. This timer is used by Linux in the thermal subsystem, so once available, the subsystem will be enabled and poll the temperature sensors. We need to provide the minimum required to keep Linux booting. Add a dummy thermal sensor returning ~25°C based on: https://github.com/raspberrypi/linux/blob/rpi-5.3.y/drivers/thermal/broadcom/bcm2835_thermal.c Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191019234715.25750-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/misc/bcm2835_thermal.h | 27 ++++++ hw/misc/bcm2835_thermal.c | 135 ++++++++++++++++++++++++++++++ 3 files changed, 163 insertions(+) create mode 100644 include/hw/misc/bcm2835_thermal.h create mode 100644 hw/misc/bcm2835_thermal.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-$(CONFIG_OMAP) += omap_tap.o common-obj-$(CONFIG_RASPI) += bcm2835_mbox.o common-obj-$(CONFIG_RASPI) += bcm2835_property.o common-obj-$(CONFIG_RASPI) += bcm2835_rng.o +common-obj-$(CONFIG_RASPI) += bcm2835_thermal.o common-obj-$(CONFIG_SLAVIO) += slavio_misc.o common-obj-$(CONFIG_ZYNQ) += zynq_slcr.o common-obj-$(CONFIG_ZYNQ) += zynq-xadc.o diff --git a/include/hw/misc/bcm2835_thermal.h b/include/hw/misc/bcm2835_thermal.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/bcm2835_thermal.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 dummy thermal sensor + * + * Copyright (C) 2019 Philippe Mathieu-Daudé <f4bug@amsat.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_MISC_BCM2835_THERMAL_H +#define HW_MISC_BCM2835_THERMAL_H + +#include "hw/sysbus.h" + +#define TYPE_BCM2835_THERMAL "bcm2835-thermal" + +#define BCM2835_THERMAL(obj) \ + OBJECT_CHECK(Bcm2835ThermalState, (obj), TYPE_BCM2835_THERMAL) + +typedef struct { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + MemoryRegion iomem; + uint32_t ctl; +} Bcm2835ThermalState; + +#endif diff --git a/hw/misc/bcm2835_thermal.c b/hw/misc/bcm2835_thermal.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/bcm2835_thermal.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 dummy thermal sensor + * + * Copyright (C) 2019 Philippe Mathieu-Daudé <f4bug@amsat.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qapi/error.h" +#include "hw/misc/bcm2835_thermal.h" +#include "hw/registerfields.h" +#include "migration/vmstate.h" + +REG32(CTL, 0) +FIELD(CTL, POWER_DOWN, 0, 1) +FIELD(CTL, RESET, 1, 1) +FIELD(CTL, BANDGAP_CTRL, 2, 3) +FIELD(CTL, INTERRUPT_ENABLE, 5, 1) +FIELD(CTL, DIRECT, 6, 1) +FIELD(CTL, INTERRUPT_CLEAR, 7, 1) +FIELD(CTL, HOLD, 8, 10) +FIELD(CTL, RESET_DELAY, 18, 8) +FIELD(CTL, REGULATOR_ENABLE, 26, 1) + +REG32(STAT, 4) +FIELD(STAT, DATA, 0, 10) +FIELD(STAT, VALID, 10, 1) +FIELD(STAT, INTERRUPT, 11, 1) + +#define THERMAL_OFFSET_C 412 +#define THERMAL_COEFF (-0.538f) + +static uint16_t bcm2835_thermal_temp2adc(int temp_C) +{ + return (temp_C - THERMAL_OFFSET_C) / THERMAL_COEFF; +} + +static uint64_t bcm2835_thermal_read(void *opaque, hwaddr addr, unsigned size) +{ + Bcm2835ThermalState *s = BCM2835_THERMAL(opaque); + uint32_t val = 0; + + switch (addr) { + case A_CTL: + val = s->ctl; + break; + case A_STAT: + /* Temperature is constantly 25°C. */ + val = FIELD_DP32(bcm2835_thermal_temp2adc(25), STAT, VALID, true); + break; + default: + /* MemoryRegionOps are aligned, so this can not happen. */ + g_assert_not_reached(); + } + return val; +} + +static void bcm2835_thermal_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + Bcm2835ThermalState *s = BCM2835_THERMAL(opaque); + + switch (addr) { + case A_CTL: + s->ctl = value; + break; + case A_STAT: + qemu_log_mask(LOG_GUEST_ERROR, "%s: write 0x%" PRIx64 + " to 0x%" HWADDR_PRIx "\n", + __func__, value, addr); + break; + default: + /* MemoryRegionOps are aligned, so this can not happen. */ + g_assert_not_reached(); + } +} + +static const MemoryRegionOps bcm2835_thermal_ops = { + .read = bcm2835_thermal_read, + .write = bcm2835_thermal_write, + .impl.max_access_size = 4, + .valid.min_access_size = 4, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static void bcm2835_thermal_reset(DeviceState *dev) +{ + Bcm2835ThermalState *s = BCM2835_THERMAL(dev); + + s->ctl = 0; +} + +static void bcm2835_thermal_realize(DeviceState *dev, Error **errp) +{ + Bcm2835ThermalState *s = BCM2835_THERMAL(dev); + + memory_region_init_io(&s->iomem, OBJECT(s), &bcm2835_thermal_ops, + s, TYPE_BCM2835_THERMAL, 8); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); +} + +static const VMStateDescription bcm2835_thermal_vmstate = { + .name = "bcm2835_thermal", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(ctl, Bcm2835ThermalState), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_thermal_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = bcm2835_thermal_realize; + dc->reset = bcm2835_thermal_reset; + dc->vmsd = &bcm2835_thermal_vmstate; +} + +static const TypeInfo bcm2835_thermal_info = { + .name = TYPE_BCM2835_THERMAL, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(Bcm2835ThermalState), + .class_init = bcm2835_thermal_class_init, +}; + +static void bcm2835_thermal_register_types(void) +{ + type_register_static(&bcm2835_thermal_info); +} + +type_init(bcm2835_thermal_register_types) -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Map the thermal sensor in the BCM2835 block. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20191019234715.25750-3-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 2 ++ include/hw/arm/raspi_platform.h | 1 + hw/arm/bcm2835_peripherals.c | 13 +++++++++++++ 3 files changed, 16 insertions(+) diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/bcm2835_property.h" #include "hw/misc/bcm2835_rng.h" #include "hw/misc/bcm2835_mbox.h" +#include "hw/misc/bcm2835_thermal.h" #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { SDHCIState sdhci; BCM2835SDHostState sdhost; BCM2835GpioState gpio; + Bcm2835ThermalState thermal; UnimplementedDeviceState i2s; UnimplementedDeviceState spi[1]; UnimplementedDeviceState i2c[3]; diff --git a/include/hw/arm/raspi_platform.h b/include/hw/arm/raspi_platform.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/raspi_platform.h +++ b/include/hw/arm/raspi_platform.h @@ -XXX,XX +XXX,XX @@ #define SPI0_OFFSET 0x204000 #define BSC0_OFFSET 0x205000 /* BSC0 I2C/TWI */ #define OTP_OFFSET 0x20f000 +#define THERMAL_OFFSET 0x212000 #define BSC_SL_OFFSET 0x214000 /* SPI slave */ #define AUX_OFFSET 0x215000 /* AUX: UART1/SPI1/SPI2 */ #define EMMC1_OFFSET 0x300000 diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) object_property_add_const_link(OBJECT(&s->dma), "dma-mr", OBJECT(&s->gpu_bus_mr), &error_abort); + /* Thermal */ + sysbus_init_child_obj(obj, "thermal", &s->thermal, sizeof(s->thermal), + TYPE_BCM2835_THERMAL); + /* GPIO */ sysbus_init_child_obj(obj, "gpio", &s->gpio, sizeof(s->gpio), TYPE_BCM2835_GPIO); @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) INTERRUPT_DMA0 + n)); } + /* THERMAL */ + object_property_set_bool(OBJECT(&s->thermal), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + memory_region_add_subregion(&s->peri_mr, THERMAL_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->thermal), 0)); + /* GPIO */ object_property_set_bool(OBJECT(&s->gpio), true, "realized", &err); if (err) { -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add the 64-bit free running timer. Do not model the COMPARE register (no IRQ generated). This timer is used by Linux kernel and recently U-Boot: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/clocksource/bcm2835_timer.c?h=v3.7 https://github.com/u-boot/u-boot/blob/v2019.07/include/configs/rpi.h#L19 Datasheet used: https://www.raspberrypi.org/app/uploads/2012/02/BCM2835-ARM-Peripherals.pdf Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191019234715.25750-4-f4bug@amsat.org [PMM: squashed in switch to using memset in reset] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/Makefile.objs | 1 + include/hw/timer/bcm2835_systmr.h | 33 ++++++ hw/timer/bcm2835_systmr.c | 163 ++++++++++++++++++++++++++++++ hw/timer/trace-events | 5 + 4 files changed, 202 insertions(+) create mode 100644 include/hw/timer/bcm2835_systmr.h create mode 100644 hw/timer/bcm2835_systmr.c diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/Makefile.objs +++ b/hw/timer/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SUN4V_RTC) += sun4v-rtc.o common-obj-$(CONFIG_CMSDK_APB_TIMER) += cmsdk-apb-timer.o common-obj-$(CONFIG_CMSDK_APB_DUALTIMER) += cmsdk-apb-dualtimer.o common-obj-$(CONFIG_MSF2) += mss-timer.o +common-obj-$(CONFIG_RASPI) += bcm2835_systmr.o diff --git a/include/hw/timer/bcm2835_systmr.h b/include/hw/timer/bcm2835_systmr.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/bcm2835_systmr.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 SYS timer emulation + * + * Copyright (c) 2019 Philippe Mathieu-Daudé <f4bug@amsat.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef BCM2835_SYSTIMER_H +#define BCM2835_SYSTIMER_H + +#include "hw/sysbus.h" +#include "hw/irq.h" + +#define TYPE_BCM2835_SYSTIMER "bcm2835-sys-timer" +#define BCM2835_SYSTIMER(obj) \ + OBJECT_CHECK(BCM2835SystemTimerState, (obj), TYPE_BCM2835_SYSTIMER) + +typedef struct { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + qemu_irq irq; + + struct { + uint32_t status; + uint32_t compare[4]; + } reg; +} BCM2835SystemTimerState; + +#endif diff --git a/hw/timer/bcm2835_systmr.c b/hw/timer/bcm2835_systmr.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/bcm2835_systmr.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 SYS timer emulation + * + * Copyright (C) 2019 Philippe Mathieu-Daudé <f4bug@amsat.org> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * Datasheet: BCM2835 ARM Peripherals (C6357-M-1398) + * https://www.raspberrypi.org/app/uploads/2012/02/BCM2835-ARM-Peripherals.pdf + * + * Only the free running 64-bit counter is implemented. + * The 4 COMPARE registers and the interruption are not implemented. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/timer.h" +#include "hw/timer/bcm2835_systmr.h" +#include "hw/registerfields.h" +#include "migration/vmstate.h" +#include "trace.h" + +REG32(CTRL_STATUS, 0x00) +REG32(COUNTER_LOW, 0x04) +REG32(COUNTER_HIGH, 0x08) +REG32(COMPARE0, 0x0c) +REG32(COMPARE1, 0x10) +REG32(COMPARE2, 0x14) +REG32(COMPARE3, 0x18) + +static void bcm2835_systmr_update_irq(BCM2835SystemTimerState *s) +{ + bool enable = !!s->reg.status; + + trace_bcm2835_systmr_irq(enable); + qemu_set_irq(s->irq, enable); +} + +static void bcm2835_systmr_update_compare(BCM2835SystemTimerState *s, + unsigned timer_index) +{ + /* TODO fow now, since neither Linux nor U-boot use these timers. */ + qemu_log_mask(LOG_UNIMP, "COMPARE register %u not implemented\n", + timer_index); +} + +static uint64_t bcm2835_systmr_read(void *opaque, hwaddr offset, + unsigned size) +{ + BCM2835SystemTimerState *s = BCM2835_SYSTIMER(opaque); + uint64_t r = 0; + + switch (offset) { + case A_CTRL_STATUS: + r = s->reg.status; + break; + case A_COMPARE0 ... A_COMPARE3: + r = s->reg.compare[(offset - A_COMPARE0) >> 2]; + break; + case A_COUNTER_LOW: + case A_COUNTER_HIGH: + /* Free running counter at 1MHz */ + r = qemu_clock_get_us(QEMU_CLOCK_VIRTUAL); + r >>= 8 * (offset - A_COUNTER_LOW); + r &= UINT32_MAX; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: bad offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + break; + } + trace_bcm2835_systmr_read(offset, r); + + return r; +} + +static void bcm2835_systmr_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + BCM2835SystemTimerState *s = BCM2835_SYSTIMER(opaque); + + trace_bcm2835_systmr_write(offset, value); + switch (offset) { + case A_CTRL_STATUS: + s->reg.status &= ~value; /* Ack */ + bcm2835_systmr_update_irq(s); + break; + case A_COMPARE0 ... A_COMPARE3: + s->reg.compare[(offset - A_COMPARE0) >> 2] = value; + bcm2835_systmr_update_compare(s, (offset - A_COMPARE0) >> 2); + break; + case A_COUNTER_LOW: + case A_COUNTER_HIGH: + qemu_log_mask(LOG_GUEST_ERROR, "%s: read-only ofs 0x%" HWADDR_PRIx "\n", + __func__, offset); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: bad offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + break; + } +} + +static const MemoryRegionOps bcm2835_systmr_ops = { + .read = bcm2835_systmr_read, + .write = bcm2835_systmr_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void bcm2835_systmr_reset(DeviceState *dev) +{ + BCM2835SystemTimerState *s = BCM2835_SYSTIMER(dev); + + memset(&s->reg, 0, sizeof(s->reg)); +} + +static void bcm2835_systmr_realize(DeviceState *dev, Error **errp) +{ + BCM2835SystemTimerState *s = BCM2835_SYSTIMER(dev); + + memory_region_init_io(&s->iomem, OBJECT(dev), &bcm2835_systmr_ops, + s, "bcm2835-sys-timer", 0x20); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); +} + +static const VMStateDescription bcm2835_systmr_vmstate = { + .name = "bcm2835_sys_timer", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(reg.status, BCM2835SystemTimerState), + VMSTATE_UINT32_ARRAY(reg.compare, BCM2835SystemTimerState, 4), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_systmr_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = bcm2835_systmr_realize; + dc->reset = bcm2835_systmr_reset; + dc->vmsd = &bcm2835_systmr_vmstate; +} + +static const TypeInfo bcm2835_systmr_info = { + .name = TYPE_BCM2835_SYSTIMER, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835SystemTimerState), + .class_init = bcm2835_systmr_class_init, +}; + +static void bcm2835_systmr_register_types(void) +{ + type_register_static(&bcm2835_systmr_info); +} + +type_init(bcm2835_systmr_register_types); diff --git a/hw/timer/trace-events b/hw/timer/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -XXX,XX +XXX,XX @@ pl031_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" pl031_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" pl031_alarm_raised(void) "alarm raised" pl031_set_alarm(uint32_t ticks) "alarm set for %u ticks" + +# bcm2835_systmr.c +bcm2835_systmr_irq(bool enable) "timer irq state %u" +bcm2835_systmr_read(uint64_t offset, uint64_t data) "timer read: offset 0x%" PRIx64 " data 0x%" PRIx64 +bcm2835_systmr_write(uint64_t offset, uint64_t data) "timer write: offset 0x%" PRIx64 " data 0x%" PRIx64 -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Connect the recently added SYS_timer. Now U-Boot does not hang anymore polling a free running counter stuck at 0. This timer is also used by the Linux kernel thermal subsystem. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20191019234715.25750-5-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 3 ++- hw/arm/bcm2835_peripherals.c | 17 ++++++++++++++++- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" +#include "hw/timer/bcm2835_systmr.h" #include "hw/misc/unimp.h" #define TYPE_BCM2835_PERIPHERALS "bcm2835-peripherals" @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { MemoryRegion ram_alias[4]; qemu_irq irq, fiq; - UnimplementedDeviceState systmr; + BCM2835SystemTimerState systmr; UnimplementedDeviceState armtmr; UnimplementedDeviceState cprman; UnimplementedDeviceState a2w; diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) /* Interrupt Controller */ sysbus_init_child_obj(obj, "ic", &s->ic, sizeof(s->ic), TYPE_BCM2835_IC); + /* SYS Timer */ + sysbus_init_child_obj(obj, "systimer", &s->systmr, sizeof(s->systmr), + TYPE_BCM2835_SYSTIMER); + /* UART0 */ sysbus_init_child_obj(obj, "uart0", &s->uart0, sizeof(s->uart0), TYPE_PL011); @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->ic), 0)); sysbus_pass_irq(SYS_BUS_DEVICE(s), SYS_BUS_DEVICE(&s->ic)); + /* Sys Timer */ + object_property_set_bool(OBJECT(&s->systmr), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + memory_region_add_subregion(&s->peri_mr, ST_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systmr), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->systmr), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_ARM_IRQ, + INTERRUPT_ARM_TIMER)); + /* UART0 */ qdev_prop_set_chr(DEVICE(&s->uart0), "chardev", serial_hd(0)); object_property_set_bool(OBJECT(&s->uart0), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) } create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); - create_unimp(s, &s->systmr, "bcm2835-systimer", ST_OFFSET, 0x20); create_unimp(s, &s->cprman, "bcm2835-cprman", CPRMAN_OFFSET, 0x1000); create_unimp(s, &s->a2w, "bcm2835-a2w", A2W_OFFSET, 0x1000); create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This file creates the BCM2836/BCM2837 blocks. The biggest differences with the BCM2838 we are going to add, are the base addresses of the interrupt controller and the peripherals. Add these addresses in the BCM283XInfo structure to make this block more modular. Remove the MCORE_OFFSET offset as it is not useful and rather confusing. Reviewed-by: Esteban Bosse <estebanbosse@gmail.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191019234715.25750-6-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bcm2836.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/raspi_platform.h" #include "hw/sysbus.h" -/* Peripheral base address seen by the CPU */ -#define BCM2836_PERI_BASE 0x3F000000 - -/* "QA7" (Pi2) interrupt controller and mailboxes etc. */ -#define BCM2836_CONTROL_BASE 0x40000000 - struct BCM283XInfo { const char *name; const char *cpu_type; + hwaddr peri_base; /* Peripheral base address seen by the CPU */ + hwaddr ctrl_base; /* Interrupt controller and mailboxes etc. */ int clusterid; }; @@ -XXX,XX +XXX,XX @@ static const BCM283XInfo bcm283x_socs[] = { { .name = TYPE_BCM2836, .cpu_type = ARM_CPU_TYPE_NAME("cortex-a7"), + .peri_base = 0x3f000000, + .ctrl_base = 0x40000000, .clusterid = 0xf, }, #ifdef TARGET_AARCH64 { .name = TYPE_BCM2837, .cpu_type = ARM_CPU_TYPE_NAME("cortex-a53"), + .peri_base = 0x3f000000, + .ctrl_base = 0x40000000, .clusterid = 0x0, }, #endif @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->peripherals), 0, - BCM2836_PERI_BASE, 1); + info->peri_base, 1); /* bcm2836 interrupt controller (and mailboxes, etc.) */ object_property_set_bool(OBJECT(&s->control), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->control), 0, BCM2836_CONTROL_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->control), 0, info->ctrl_base); sysbus_connect_irq(SYS_BUS_DEVICE(&s->peripherals), 0, qdev_get_gpio_in_named(DEVICE(&s->control), "gpu-irq", 0)); @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) /* set periphbase/CBAR value for CPU-local registers */ object_property_set_int(OBJECT(&s->cpus[n]), - BCM2836_PERI_BASE + MSYNC_OFFSET, + info->peri_base, "reset-cbar", &err); if (err) { error_propagate(errp, err); -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> As we are going to add more core-specific fields, add a 'cpu' structure and move the ARMCPU field there as 'core'. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191019234715.25750-7-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2836.h | 4 +++- hw/arm/bcm2836.c | 26 ++++++++++++++------------ 2 files changed, 17 insertions(+), 13 deletions(-) diff --git a/include/hw/arm/bcm2836.h b/include/hw/arm/bcm2836.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2836.h +++ b/include/hw/arm/bcm2836.h @@ -XXX,XX +XXX,XX @@ typedef struct BCM283XState { char *cpu_type; uint32_t enabled_cpus; - ARMCPU cpus[BCM283X_NCPUS]; + struct { + ARMCPU core; + } cpu[BCM283X_NCPUS]; BCM2836ControlState control; BCM2835PeripheralState peripherals; } BCM283XState; diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -XXX,XX +XXX,XX @@ static void bcm2836_init(Object *obj) int n; for (n = 0; n < BCM283X_NCPUS; n++) { - object_initialize_child(obj, "cpu[*]", &s->cpus[n], sizeof(s->cpus[n]), - info->cpu_type, &error_abort, NULL); + object_initialize_child(obj, "cpu[*]", &s->cpu[n].core, + sizeof(s->cpu[n].core), info->cpu_type, + &error_abort, NULL); } sysbus_init_child_obj(obj, "control", &s->control, sizeof(s->control), @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) for (n = 0; n < BCM283X_NCPUS; n++) { /* TODO: this should be converted to a property of ARM_CPU */ - s->cpus[n].mp_affinity = (info->clusterid << 8) | n; + s->cpu[n].core.mp_affinity = (info->clusterid << 8) | n; /* set periphbase/CBAR value for CPU-local registers */ - object_property_set_int(OBJECT(&s->cpus[n]), + object_property_set_int(OBJECT(&s->cpu[n].core), info->peri_base, "reset-cbar", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) } /* start powered off if not enabled */ - object_property_set_bool(OBJECT(&s->cpus[n]), n >= s->enabled_cpus, + object_property_set_bool(OBJECT(&s->cpu[n].core), n >= s->enabled_cpus, "start-powered-off", &err); if (err) { error_propagate(errp, err); return; } - object_property_set_bool(OBJECT(&s->cpus[n]), true, "realized", &err); + object_property_set_bool(OBJECT(&s->cpu[n].core), true, + "realized", &err); if (err) { error_propagate(errp, err); return; @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) /* Connect irq/fiq outputs from the interrupt controller. */ qdev_connect_gpio_out_named(DEVICE(&s->control), "irq", n, - qdev_get_gpio_in(DEVICE(&s->cpus[n]), ARM_CPU_IRQ)); + qdev_get_gpio_in(DEVICE(&s->cpu[n].core), ARM_CPU_IRQ)); qdev_connect_gpio_out_named(DEVICE(&s->control), "fiq", n, - qdev_get_gpio_in(DEVICE(&s->cpus[n]), ARM_CPU_FIQ)); + qdev_get_gpio_in(DEVICE(&s->cpu[n].core), ARM_CPU_FIQ)); /* Connect timers from the CPU to the interrupt controller */ - qdev_connect_gpio_out(DEVICE(&s->cpus[n]), GTIMER_PHYS, + qdev_connect_gpio_out(DEVICE(&s->cpu[n].core), GTIMER_PHYS, qdev_get_gpio_in_named(DEVICE(&s->control), "cntpnsirq", n)); - qdev_connect_gpio_out(DEVICE(&s->cpus[n]), GTIMER_VIRT, + qdev_connect_gpio_out(DEVICE(&s->cpu[n].core), GTIMER_VIRT, qdev_get_gpio_in_named(DEVICE(&s->control), "cntvirq", n)); - qdev_connect_gpio_out(DEVICE(&s->cpus[n]), GTIMER_HYP, + qdev_connect_gpio_out(DEVICE(&s->cpu[n].core), GTIMER_HYP, qdev_get_gpio_in_named(DEVICE(&s->control), "cnthpirq", n)); - qdev_connect_gpio_out(DEVICE(&s->cpus[n]), GTIMER_SEC, + qdev_connect_gpio_out(DEVICE(&s->cpu[n].core), GTIMER_SEC, qdev_get_gpio_in_named(DEVICE(&s->control), "cntpsirq", n)); } } -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> write_secondary_boot() is used in SMP configurations where the CPU address space might not be the main System Bus. The rom_add_blob_fixed_as() function allow us to specify an address space. Use it to write each boot blob in the corresponding CPU address space. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191019234715.25750-11-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/raspi.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -XXX,XX +XXX,XX @@ static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info) QEMU_BUILD_BUG_ON((BOARDSETUP_ADDR & 0xf) != 0 || (BOARDSETUP_ADDR >> 4) >= 0x100); - rom_add_blob_fixed("raspi_smpboot", smpboot, sizeof(smpboot), - info->smp_loader_start); + rom_add_blob_fixed_as("raspi_smpboot", smpboot, sizeof(smpboot), + info->smp_loader_start, + arm_boot_address_space(cpu, info)); } static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info) { + AddressSpace *as = arm_boot_address_space(cpu, info); /* Unlike the AArch32 version we don't need to call the board setup hook. * The mechanism for doing the spin-table is also entirely different. * We must have four 64-bit fields at absolute addresses @@ -XXX,XX +XXX,XX @@ static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info) 0, 0, 0, 0 }; - rom_add_blob_fixed("raspi_smpboot", smpboot, sizeof(smpboot), - info->smp_loader_start); - rom_add_blob_fixed("raspi_spintables", spintables, sizeof(spintables), - SPINTABLE_ADDR); + rom_add_blob_fixed_as("raspi_smpboot", smpboot, sizeof(smpboot), + info->smp_loader_start, as); + rom_add_blob_fixed_as("raspi_spintables", spintables, sizeof(spintables), + SPINTABLE_ADDR, as); } static void write_board_setup(ARMCPU *cpu, const struct arm_boot_info *info) -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> write_secondary_boot() is used in SMP configurations where the CPU address space might not be the main System Bus. The rom_add_blob_fixed_as() function allow us to specify an address space. Use it to write each boot blob in the corresponding CPU address space. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20191019234715.25750-15-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/highbank.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/highbank.c +++ b/hw/arm/highbank.c @@ -XXX,XX +XXX,XX @@ static void hb_write_secondary(ARMCPU *cpu, const struct arm_boot_info *info) for (n = 0; n < ARRAY_SIZE(smpboot); n++) { smpboot[n] = tswap32(smpboot[n]); } - rom_add_blob_fixed("smpboot", smpboot, sizeof(smpboot), SMP_BOOT_ADDR); + rom_add_blob_fixed_as("smpboot", smpboot, sizeof(smpboot), SMP_BOOT_ADDR, + arm_boot_address_space(cpu, info)); } static void hb_reset_secondary(ARMCPU *cpu, const struct arm_boot_info *info) -- 2.20.1 As promised, more Arm patches. The big thing in here is the MPS2-AN521 board model. thanks -- PMM The following changes since commit cfe6c547690b06fbce54a6d0f7b05dd7f18e36ea: Merge remote-tracking branch 'remotes/xanclic/tags/pull-block-2019-01-31' into staging (2019-01-31 19:26:09 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190201 for you to fetch changes up to 7743b70ffe7a8ce168adce2cf50ad156b1fefb8c: tests/microbit-test: Add tests for nRF51 NVMC (2019-02-01 15:32:17 +0000) ---------------------------------------------------------------- target-arm queue: * New machine mps2-an521 -- this is a model of the AN521 FPGA image for the MPS2 devboard * Fix various places where we failed to UNDEF invalid A64 instructions * Don't UNDEF a valid FCMLA on 32-bit inputs * Fix some bugs in the newly-added PAuth implementation * microbit: Implement NVMC non-volatile memory controller ---------------------------------------------------------------- Aaron Lindsay OS (2): target/arm: Send interrupts on PMU counter overflow target/arm: Add a timer to predict PMU counter overflow Julia Suvorova (1): arm: Clarify the logic of set_pc() Peter Maydell (33): armv7m: Don't assume the NVIC's CPU is CPU 0 armv7m: Make cpu object a child of the armv7m container armv7m: Pass through start-powered-off CPU property hw/arm/iotkit: Rename IoTKit to ARMSSE hw/arm/iotkit: Refactor into abstract base class and subclass hw/arm/iotkit: Rename 'iotkit' local variables and functions hw/arm/iotkit: Rename files to hw/arm/armsse.[ch] hw/misc/iotkit-secctl: Support 4 internal MPCs hw/arm/armsse: Make number of SRAM banks parameterised hw/arm/armsse: Make SRAM bank size configurable hw/arm/armsse: Support dual-CPU configuration hw/arm/armsse: Give each CPU its own view of memory hw/arm/armsse: Put each CPU in its own cluster object iotkit-sysinfo: Make SYS_VERSION and SYS_CONFIG configurable hw/arm/armsse: Add unimplemented-device stubs for MHUs hw/arm/armsse: Add unimplemented-device stubs for PPUs hw/arm/armsse: Add unimplemented-device stub for cache control registers hw/arm/armsse: Add unimplemented-device stub for CPU local control registers hw/misc/armsse-cpuid: Implement SSE-200 CPU_IDENTITY register block hw/arm/armsse: Add CPU_IDENTITY block to SSE-200 hw/arm/armsse: Add SSE-200 model hw/arm/mps2-tz: Add IRQ infrastructure to support SSE-200 hw/arm/mps2-tz: Add mps2-an521 model target/arm/translate-a64: Don't underdecode system instructions target/arm/translate-a64: Don't underdecode PRFM target/arm/translate-a64: Don't underdecode SIMD ld/st multiple target/arm/translate-a64: Don't underdecode SIMD ld/st single target/arm/translate-a64: Don't underdecode add/sub extended register target/arm/translate-a64: Don't underdecode FP insns target/arm/translate-a64: Don't underdecode SDOT and UDOT exec.c: Don't reallocate IOMMUNotifiers that are in use target/arm/translate-a64: Fix FCMLA decoding error target/arm/translate-a64: Fix mishandling of size in FCMLA decode Remi Denis-Courmont (2): target/arm: fix AArch64 virtual address space size target/arm: fix decoding of B{,L}RA{A,B} Richard Henderson (5): target/arm: Enable API, APK bits in SCR, HCR target/arm: Always enable pac keys for user-only aarch64-linux-user: Update HWCAP bits from linux 5.0-rc1 aarch64-linux-user: Enable HWCAP bits for PAuth linux-user: Initialize aarch64 pac keys Steffen Görtz (3): hw/nvram/nrf51_nvm: Add nRF51 non-volatile memories arm: Instantiate NRF51 special NVM's and NVMC tests/microbit-test: Add tests for nRF51 NVMC kumar sourav (1): hw/arm/nrf51_soc: set object owner in memory_region_init_ram hw/arm/Makefile.objs | 2 +- hw/misc/Makefile.objs | 1 + hw/nvram/Makefile.objs | 1 + include/hw/arm/{iotkit.h => armsse.h} | 113 ++- include/hw/arm/armv7m.h | 1 + include/hw/arm/nrf51_soc.h | 2 + include/hw/misc/armsse-cpuid.h | 41 ++ include/hw/misc/iotkit-secctl.h | 6 +- include/hw/misc/iotkit-sysinfo.h | 6 + include/hw/nvram/nrf51_nvm.h | 64 ++ include/qom/cpu.h | 16 +- linux-user/aarch64/target_syscall.h | 2 + target/arm/cpu.h | 12 +- exec.c | 10 +- hw/arm/armsse.c | 1241 +++++++++++++++++++++++++++++++++ hw/arm/armv7m.c | 23 +- hw/arm/boot.c | 4 - hw/arm/iotkit.c | 759 -------------------- hw/arm/mps2-tz.c | 121 +++- hw/arm/nrf51_soc.c | 44 +- hw/intc/armv7m_nvic.c | 3 +- hw/misc/armsse-cpuid.c | 134 ++++ hw/misc/iotkit-secctl.c | 5 +- hw/misc/iotkit-sysinfo.c | 15 +- hw/nvram/nrf51_nvm.c | 388 +++++++++++ linux-user/aarch64/cpu_loop.c | 31 +- linux-user/elfload.c | 10 + target/arm/arm-powerctl.c | 3 - target/arm/cpu.c | 41 +- target/arm/cpu64.c | 75 -- target/arm/helper.c | 139 +++- target/arm/translate-a64.c | 59 +- tests/microbit-test.c | 108 +++ MAINTAINERS | 6 +- default-configs/arm-softmmu.mak | 3 +- hw/misc/trace-events | 4 + 36 files changed, 2552 insertions(+), 941 deletions(-) rename include/hw/arm/{iotkit.h => armsse.h} (53%) create mode 100644 include/hw/misc/armsse-cpuid.h create mode 100644 include/hw/nvram/nrf51_nvm.h create mode 100644 hw/arm/armsse.c delete mode 100644 hw/arm/iotkit.c create mode 100644 hw/misc/armsse-cpuid.c create mode 100644 hw/nvram/nrf51_nvm.c From: kumar sourav <sourav.jb1988@gmail.com> set object owner in memory_region_init_ram() instead of NULL. Signed-off-by: kumar sourav <sourav.jb1988@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190125155630.17430-1-sourav.jb1988@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/nrf51_soc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) } memory_region_add_subregion(&s->container, NRF51_FLASH_BASE, &s->flash); - memory_region_init_ram(&s->sram, NULL, "nrf51.sram", s->sram_size, &err); + memory_region_init_ram(&s->sram, OBJECT(s), "nrf51.sram", s->sram_size, + &err); if (err) { error_propagate(errp, err); return; -- 2.20.1 Currently the ARMv7M NVIC object's realize method assumes that the CPU the NVIC is attached to is CPU 0, because it thinks there can only ever be one CPU in the system. To allow a dual-Cortex-M33 setup we need to remove this assumption; instead the armv7m wrapper object tells the NVIC its CPU, in the same way that it already tells the CPU what the NVIC is. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-2-peter.maydell@linaro.org --- hw/arm/armv7m.c | 6 ++++-- hw/intc/armv7m_nvic.c | 3 +-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) } } - /* Tell the CPU where the NVIC is; it will fail realize if it doesn't - * have one. + /* + * Tell the CPU where the NVIC is; it will fail realize if it doesn't + * have one. Similarly, tell the NVIC where its CPU is. */ s->cpu->env.nvic = &s->nvic; + s->nvic.cpu = s->cpu; object_property_set_bool(OBJECT(s->cpu), true, "realized", &err); if (err != NULL) { 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_realize(DeviceState *dev, Error **errp) Error *err = NULL; int regionlen; - s->cpu = ARM_CPU(qemu_get_cpu(0)); - + /* The armv7m container object will have set our CPU pointer */ if (!s->cpu || !arm_feature(&s->cpu->env, ARM_FEATURE_M)) { error_setg(errp, "The NVIC can only be used with a Cortex-M CPU"); return; -- 2.20.1 Rather than just creating the CPUs with object_new, make them child objects of the armv7m container. This will allow the cluster code to find the CPUs if an armv7m object is made a child of a cluster object. object_new_with_props() will do the parenting for us. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-3-peter.maydell@linaro.org --- hw/arm/armv7m.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1); - s->cpu = ARM_CPU(object_new(s->cpu_type)); + s->cpu = ARM_CPU(object_new_with_props(s->cpu_type, OBJECT(s), "cpu", + &err, NULL)); + if (err != NULL) { + error_propagate(errp, err); + return; + } object_property_set_link(OBJECT(s->cpu), OBJECT(&s->container), "memory", &error_abort); -- 2.20.1 Expose "start-powered-off" as a property of the ARMv7M container, which we just pass through to the CPU object in the same way that we do for "init-svtor" and "idau". (We want this for the SSE-200, which powers up only the first CPU at reset and leaves the second powered down.) As with the other CPU properties here, we can't just use alias properties, because the CPU QOM object is not created until armv7m realize time. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-4-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 1 + hw/arm/armv7m.c | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMv7MState { Object *idau; uint32_t init_svtor; bool enable_bitband; + bool start_powered_off; } ARMv7MState; #endif diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) return; } } + if (object_property_find(OBJECT(s->cpu), "start-powered-off", NULL)) { + object_property_set_bool(OBJECT(s->cpu), s->start_powered_off, + "start-powered-off", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + } /* * Tell the CPU where the NVIC is; it will fail realize if it doesn't @@ -XXX,XX +XXX,XX @@ static Property armv7m_properties[] = { DEFINE_PROP_LINK("idau", ARMv7MState, idau, TYPE_IDAU_INTERFACE, Object *), DEFINE_PROP_UINT32("init-svtor", ARMv7MState, init_svtor, 0), DEFINE_PROP_BOOL("enable-bitband", ARMv7MState, enable_bitband, false), + DEFINE_PROP_BOOL("start-powered-off", ARMv7MState, start_powered_off, + false), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 The Arm IoTKit was effectively the forerunner of a series of subsystems for embedded SoCs, named the SSE-050, SSE-100 and SSE-200: https://developer.arm.com/products/system-design/subsystems These are generally quite similar, though later iterations have extra devices that earlier ones do not. We want to add a model of the SSE-200, which means refactoring the IoTKit code into an abstract base class and subclasses (using the same design that the bcm283x SoC and Aspeed SoC family implementations do). As a first step, rename the IoTKit struct and QOM macros to ARMSSE, which is what we're going to name the base class. We temporarily retain TYPE_IOTKIT to avoid changing the code that instantiates a TYPE_IOTKIT device here and then changing it back again when it is re-introduced as a subclass. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-5-peter.maydell@linaro.org --- include/hw/arm/iotkit.h | 22 ++++++++++----- hw/arm/iotkit.c | 59 +++++++++++++++++++++-------------------- hw/arm/mps2-tz.c | 2 +- 3 files changed, 47 insertions(+), 36 deletions(-) diff --git a/include/hw/arm/iotkit.h b/include/hw/arm/iotkit.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/iotkit.h +++ b/include/hw/arm/iotkit.h @@ -XXX,XX +XXX,XX @@ /* - * ARM IoT Kit + * ARM SSE (Subsystems for Embedded): IoTKit * * Copyright (c) 2018 Linaro Limited * Written by Peter Maydell @@ -XXX,XX +XXX,XX @@ * (at your option) any later version. */ -/* This is a model of the Arm IoT Kit which is documented in +/* + * This is a model of the Arm "Subsystems for Embedded" family of + * hardware, which include the IoT Kit and the SSE-050, SSE-100 and + * SSE-200. Currently we model only the Arm IoT Kit which is documented in * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html * It contains: * a Cortex-M33 @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/core/split-irq.h" -#define TYPE_IOTKIT "iotkit" -#define IOTKIT(obj) OBJECT_CHECK(IoTKit, (obj), TYPE_IOTKIT) +#define TYPE_ARMSSE "iotkit" +#define ARMSSE(obj) OBJECT_CHECK(ARMSSE, (obj), TYPE_ARMSSE) + +/* + * For the moment TYPE_IOTKIT is a synonym for TYPE_ARMSSE (and the + * latter's underlying name is left as "iotkit"); in a later + * commit it will become a subclass of TYPE_ARMSSE. + */ +#define TYPE_IOTKIT TYPE_ARMSSE /* We have an IRQ splitter and an OR gate input for each external PPC * and the 2 internal PPCs @@ -XXX,XX +XXX,XX @@ #define NUM_EXTERNAL_PPCS (IOTS_NUM_AHB_EXP_PPC + IOTS_NUM_APB_EXP_PPC) #define NUM_PPCS (NUM_EXTERNAL_PPCS + 2) -typedef struct IoTKit { +typedef struct ARMSSE { /*< private >*/ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ typedef struct IoTKit { MemoryRegion *board_memory; uint32_t exp_numirq; uint32_t mainclk_frq; -} IoTKit; +} ARMSSE; #endif diff --git a/hw/arm/iotkit.c b/hw/arm/iotkit.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/iotkit.c +++ b/hw/arm/iotkit.c @@ -XXX,XX +XXX,XX @@ /* - * Arm IoT Kit + * Arm SSE (Subsystems for Embedded): IoTKit * * Copyright (c) 2018 Linaro Limited * Written by Peter Maydell @@ -XXX,XX +XXX,XX @@ /* Create an alias region of @size bytes starting at @base * which mirrors the memory starting at @orig. */ -static void make_alias(IoTKit *s, MemoryRegion *mr, const char *name, +static void make_alias(ARMSSE *s, MemoryRegion *mr, const char *name, hwaddr base, hwaddr size, hwaddr orig) { memory_region_init_alias(mr, NULL, name, &s->container, orig, size); @@ -XXX,XX +XXX,XX @@ static void irq_status_forwarder(void *opaque, int n, int level) static void nsccfg_handler(void *opaque, int n, int level) { - IoTKit *s = IOTKIT(opaque); + ARMSSE *s = ARMSSE(opaque); s->nsccfg = level; } -static void iotkit_forward_ppc(IoTKit *s, const char *ppcname, int ppcnum) +static void iotkit_forward_ppc(ARMSSE *s, const char *ppcname, int ppcnum) { /* Each of the 4 AHB and 4 APB PPCs that might be present in a - * system using the IoTKit has a collection of control lines which + * system using the ARMSSE has a collection of control lines which * are provided by the security controller and which we want to - * expose as control lines on the IoTKit device itself, so the - * code using the IoTKit can wire them up to the PPCs. + * expose as control lines on the ARMSSE device itself, so the + * code using the ARMSSE can wire them up to the PPCs. */ SplitIRQ *splitter = &s->ppc_irq_splitter[ppcnum]; DeviceState *iotkitdev = DEVICE(s); @@ -XXX,XX +XXX,XX @@ static void iotkit_forward_ppc(IoTKit *s, const char *ppcname, int ppcnum) g_free(name); } -static void iotkit_forward_sec_resp_cfg(IoTKit *s) +static void iotkit_forward_sec_resp_cfg(ARMSSE *s) { /* Forward the 3rd output from the splitter device as a * named GPIO output of the iotkit object. @@ -XXX,XX +XXX,XX @@ static void iotkit_forward_sec_resp_cfg(IoTKit *s) static void iotkit_init(Object *obj) { - IoTKit *s = IOTKIT(obj); + ARMSSE *s = ARMSSE(obj); int i; memory_region_init(&s->container, obj, "iotkit-container", UINT64_MAX); @@ -XXX,XX +XXX,XX @@ static void iotkit_init(Object *obj) static void iotkit_exp_irq(void *opaque, int n, int level) { - IoTKit *s = IOTKIT(opaque); + ARMSSE *s = ARMSSE(opaque); qemu_set_irq(s->exp_irqs[n], level); } static void iotkit_mpcexp_status(void *opaque, int n, int level) { - IoTKit *s = IOTKIT(opaque); + ARMSSE *s = ARMSSE(opaque); qemu_set_irq(s->mpcexp_status_in[n], level); } static void iotkit_realize(DeviceState *dev, Error **errp) { - IoTKit *s = IOTKIT(dev); + ARMSSE *s = ARMSSE(dev); int i; MemoryRegion *mr; Error *err = NULL; @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) * devices exist in both address spaces but with hard-wired security * permissions that will cause the CPU to fault for non-secure accesses. * - * The IoTKit has an IDAU (Implementation Defined Access Unit), + * The ARMSSE has an IDAU (Implementation Defined Access Unit), * which specifies hard-wired security permissions for different - * areas of the physical address space. For the IoTKit IDAU, the + * areas of the physical address space. For the ARMSSE IDAU, the * top 4 bits of the physical address are the IDAU region ID, and * if bit 28 (ie the lowest bit of the ID) is 0 then this is an NS * region, otherwise it is an S region. @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) * 0x20000000..0x2007ffff 32KB FPGA block RAM * 0x30000000..0x3fffffff alias of 0x20000000..0x2fffffff * 0x40000000..0x4000ffff base peripheral region 1 - * 0x40010000..0x4001ffff CPU peripherals (none for IoTKit) + * 0x40010000..0x4001ffff CPU peripherals (none for ARMSSE) * 0x40020000..0x4002ffff system control element peripherals * 0x40080000..0x400fffff base peripheral region 2 * 0x50000000..0x5fffffff alias of 0x40000000..0x4fffffff @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) qdev_connect_gpio_out_named(dev_secctl, "nsc_cfg", 0, s->nsc_cfg_in); /* The sec_resp_cfg output from the security controller must be split into - * multiple lines, one for each of the PPCs within the IoTKit and one - * that will be an output from the IoTKit to the system. + * multiple lines, one for each of the PPCs within the ARMSSE and one + * that will be an output from the ARMSSE to the system. */ object_property_set_int(OBJECT(&s->sec_resp_splitter), 3, "num-lines", &err); @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) /* 0x40010000 .. 0x4001ffff: private CPU region: unused in IoTKit */ - /* 0x40020000 .. 0x4002ffff : IoTKit system control peripheral region */ + /* 0x40020000 .. 0x4002ffff : ARMSSE system control peripheral region */ /* Devices behind APB PPC1: * 0x4002f000: S32K timer */ @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(DEVICE(&s->nmi_orgate), 0)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->s32kwatchdog), 0, 0x5002e000); - /* 0x40080000 .. 0x4008ffff : IoTKit second Base peripheral region */ + /* 0x40080000 .. 0x4008ffff : ARMSSE second Base peripheral region */ qdev_prop_set_uint32(DEVICE(&s->nswatchdog), "wdogclk-frq", s->mainclk_frq); object_property_set_bool(OBJECT(&s->nswatchdog), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) * Expose our container region to the board model; this corresponds * to the AHB Slave Expansion ports which allow bus master devices * (eg DMA controllers) in the board model to make transactions into - * devices in the IoTKit. + * devices in the ARMSSE. */ sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->container); @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) static void iotkit_idau_check(IDAUInterface *ii, uint32_t address, int *iregion, bool *exempt, bool *ns, bool *nsc) { - /* For IoTKit systems the IDAU responses are simple logical functions + /* + * For ARMSSE systems the IDAU responses are simple logical functions * of the address bits. The NSC attribute is guest-adjustable via the * NSCCFG register in the security controller. */ - IoTKit *s = IOTKIT(ii); + ARMSSE *s = ARMSSE(ii); int region = extract32(address, 28, 4); *ns = !(region & 1); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription iotkit_vmstate = { .version_id = 1, .minimum_version_id = 1, .fields = (VMStateField[]) { - VMSTATE_UINT32(nsccfg, IoTKit), + VMSTATE_UINT32(nsccfg, ARMSSE), VMSTATE_END_OF_LIST() } }; static Property iotkit_properties[] = { - DEFINE_PROP_LINK("memory", IoTKit, board_memory, TYPE_MEMORY_REGION, + DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, MemoryRegion *), - DEFINE_PROP_UINT32("EXP_NUMIRQ", IoTKit, exp_numirq, 64), - DEFINE_PROP_UINT32("MAINCLK", IoTKit, mainclk_frq, 0), + DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), + DEFINE_PROP_UINT32("MAINCLK", ARMSSE, mainclk_frq, 0), DEFINE_PROP_END_OF_LIST() }; static void iotkit_reset(DeviceState *dev) { - IoTKit *s = IOTKIT(dev); + ARMSSE *s = ARMSSE(dev); s->nsccfg = 0; } @@ -XXX,XX +XXX,XX @@ static void iotkit_class_init(ObjectClass *klass, void *data) } static const TypeInfo iotkit_info = { - .name = TYPE_IOTKIT, + .name = TYPE_ARMSSE, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(IoTKit), + .instance_size = sizeof(ARMSSE), .instance_init = iotkit_init, .class_init = iotkit_class_init, .interfaces = (InterfaceInfo[]) { 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 @@ typedef struct { typedef struct { MachineState parent; - IoTKit iotkit; + ARMSSE iotkit; MemoryRegion psram; MemoryRegion ssram[3]; MemoryRegion ssram1_m; -- 2.20.1 The Arm SSE-200 Subsystem for Embedded is a revised and extended version of the older IoTKit SoC. Prepare for adding a model of it by refactoring the IoTKit code into an abstract base class which contains the functionality, driven by a class data block specific to each subclass. (This is the same approach used by the existing bcm283x SoC family implementation.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-6-peter.maydell@linaro.org --- include/hw/arm/iotkit.h | 22 +++++++++++++++++----- hw/arm/iotkit.c | 34 +++++++++++++++++++++++++++++----- 2 files changed, 46 insertions(+), 10 deletions(-) diff --git a/include/hw/arm/iotkit.h b/include/hw/arm/iotkit.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/iotkit.h +++ b/include/hw/arm/iotkit.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/core/split-irq.h" -#define TYPE_ARMSSE "iotkit" +#define TYPE_ARMSSE "arm-sse" #define ARMSSE(obj) OBJECT_CHECK(ARMSSE, (obj), TYPE_ARMSSE) /* - * For the moment TYPE_IOTKIT is a synonym for TYPE_ARMSSE (and the - * latter's underlying name is left as "iotkit"); in a later - * commit it will become a subclass of TYPE_ARMSSE. + * These type names are for specific IoTKit subsystems; other than + * instantiating them, code using these devices should always handle + * them via the ARMSSE base class, so they have no IOTKIT() etc macros. */ -#define TYPE_IOTKIT TYPE_ARMSSE +#define TYPE_IOTKIT "iotkit" /* We have an IRQ splitter and an OR gate input for each external PPC * and the 2 internal PPCs @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { uint32_t mainclk_frq; } ARMSSE; +typedef struct ARMSSEInfo ARMSSEInfo; + +typedef struct ARMSSEClass { + DeviceClass parent_class; + const ARMSSEInfo *info; +} ARMSSEClass; + +#define ARMSSE_CLASS(klass) \ + OBJECT_CLASS_CHECK(ARMSSEClass, (klass), TYPE_ARMSSE) +#define ARMSSE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(ARMSSEClass, (obj), TYPE_ARMSSE) + #endif diff --git a/hw/arm/iotkit.c b/hw/arm/iotkit.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/iotkit.c +++ b/hw/arm/iotkit.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/iotkit.h" #include "hw/arm/arm.h" +struct ARMSSEInfo { + const char *name; +}; + +static const ARMSSEInfo armsse_variants[] = { + { + .name = TYPE_IOTKIT, + }, +}; + /* Clock frequency in HZ of the 32KHz "slow clock" */ #define S32KCLK (32 * 1000) @@ -XXX,XX +XXX,XX @@ static void iotkit_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(klass); + ARMSSEClass *asc = ARMSSE_CLASS(klass); dc->realize = iotkit_realize; dc->vmsd = &iotkit_vmstate; dc->props = iotkit_properties; dc->reset = iotkit_reset; iic->check = iotkit_idau_check; + asc->info = data; } -static const TypeInfo iotkit_info = { +static const TypeInfo armsse_info = { .name = TYPE_ARMSSE, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(ARMSSE), .instance_init = iotkit_init, - .class_init = iotkit_class_init, + .abstract = true, .interfaces = (InterfaceInfo[]) { { TYPE_IDAU_INTERFACE }, { } } }; -static void iotkit_register_types(void) +static void armsse_register_types(void) { - type_register_static(&iotkit_info); + int i; + + type_register_static(&armsse_info); + + for (i = 0; i < ARRAY_SIZE(armsse_variants); i++) { + TypeInfo ti = { + .name = armsse_variants[i].name, + .parent = TYPE_ARMSSE, + .class_init = iotkit_class_init, + .class_data = (void *)&armsse_variants[i], + }; + type_register(&ti); + } } -type_init(iotkit_register_types); +type_init(armsse_register_types); -- 2.20.1 Rename various internal uses of 'iotkit' in hw/arm/iotkit.c to 'armsse', for consistency. The remaining occurences are: * related to the devices TYPE_IOTKIT_SYSCTL, TYPE_IOTKIT_SYSINFO, etc, which this refactor is not touching * references that apply specifically to the IoTKit (like the lack of a private CPU region) * the vmstate, which keeps its old "iotkit" name for migration compatibility reasons Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-7-peter.maydell@linaro.org --- hw/arm/iotkit.c | 68 ++++++++++++++++++++++++------------------------- 1 file changed, 34 insertions(+), 34 deletions(-) diff --git a/hw/arm/iotkit.c b/hw/arm/iotkit.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/iotkit.c +++ b/hw/arm/iotkit.c @@ -XXX,XX +XXX,XX @@ static void nsccfg_handler(void *opaque, int n, int level) s->nsccfg = level; } -static void iotkit_forward_ppc(ARMSSE *s, const char *ppcname, int ppcnum) +static void armsse_forward_ppc(ARMSSE *s, const char *ppcname, int ppcnum) { /* Each of the 4 AHB and 4 APB PPCs that might be present in a * system using the ARMSSE has a collection of control lines which @@ -XXX,XX +XXX,XX @@ static void iotkit_forward_ppc(ARMSSE *s, const char *ppcname, int ppcnum) * code using the ARMSSE can wire them up to the PPCs. */ SplitIRQ *splitter = &s->ppc_irq_splitter[ppcnum]; - DeviceState *iotkitdev = DEVICE(s); + DeviceState *armssedev = DEVICE(s); DeviceState *dev_secctl = DEVICE(&s->secctl); DeviceState *dev_splitter = DEVICE(splitter); char *name; name = g_strdup_printf("%s_nonsec", ppcname); - qdev_pass_gpios(dev_secctl, iotkitdev, name); + qdev_pass_gpios(dev_secctl, armssedev, name); g_free(name); name = g_strdup_printf("%s_ap", ppcname); - qdev_pass_gpios(dev_secctl, iotkitdev, name); + qdev_pass_gpios(dev_secctl, armssedev, name); g_free(name); name = g_strdup_printf("%s_irq_enable", ppcname); - qdev_pass_gpios(dev_secctl, iotkitdev, name); + qdev_pass_gpios(dev_secctl, armssedev, name); g_free(name); name = g_strdup_printf("%s_irq_clear", ppcname); - qdev_pass_gpios(dev_secctl, iotkitdev, name); + qdev_pass_gpios(dev_secctl, armssedev, name); g_free(name); /* irq_status is a little more tricky, because we need to @@ -XXX,XX +XXX,XX @@ static void iotkit_forward_ppc(ARMSSE *s, const char *ppcname, int ppcnum) qdev_connect_gpio_out(dev_splitter, 1, qdev_get_gpio_in(DEVICE(&s->ppc_irq_orgate), ppcnum)); s->irq_status_in[ppcnum] = qdev_get_gpio_in(dev_splitter, 0); - qdev_init_gpio_in_named_with_opaque(iotkitdev, irq_status_forwarder, + qdev_init_gpio_in_named_with_opaque(armssedev, irq_status_forwarder, s->irq_status_in[ppcnum], name, 1); g_free(name); } -static void iotkit_forward_sec_resp_cfg(ARMSSE *s) +static void armsse_forward_sec_resp_cfg(ARMSSE *s) { /* Forward the 3rd output from the splitter device as a - * named GPIO output of the iotkit object. + * named GPIO output of the armsse object. */ DeviceState *dev = DEVICE(s); DeviceState *dev_splitter = DEVICE(&s->sec_resp_splitter); @@ -XXX,XX +XXX,XX @@ static void iotkit_forward_sec_resp_cfg(ARMSSE *s) qdev_connect_gpio_out(dev_splitter, 2, s->sec_resp_cfg_in); } -static void iotkit_init(Object *obj) +static void armsse_init(Object *obj) { ARMSSE *s = ARMSSE(obj); int i; - memory_region_init(&s->container, obj, "iotkit-container", UINT64_MAX); + memory_region_init(&s->container, obj, "armsse-container", UINT64_MAX); sysbus_init_child_obj(obj, "armv7m", &s->armv7m, sizeof(s->armv7m), TYPE_ARMV7M); @@ -XXX,XX +XXX,XX @@ static void iotkit_init(Object *obj) sizeof(s->nswatchdog), TYPE_CMSDK_APB_WATCHDOG); sysbus_init_child_obj(obj, "swatchdog", &s->swatchdog, sizeof(s->swatchdog), TYPE_CMSDK_APB_WATCHDOG); - sysbus_init_child_obj(obj, "iotkit-sysctl", &s->sysctl, + sysbus_init_child_obj(obj, "armsse-sysctl", &s->sysctl, sizeof(s->sysctl), TYPE_IOTKIT_SYSCTL); - sysbus_init_child_obj(obj, "iotkit-sysinfo", &s->sysinfo, + sysbus_init_child_obj(obj, "armsse-sysinfo", &s->sysinfo, sizeof(s->sysinfo), TYPE_IOTKIT_SYSINFO); object_initialize_child(obj, "nmi-orgate", &s->nmi_orgate, sizeof(s->nmi_orgate), TYPE_OR_IRQ, @@ -XXX,XX +XXX,XX @@ static void iotkit_init(Object *obj) } } -static void iotkit_exp_irq(void *opaque, int n, int level) +static void armsse_exp_irq(void *opaque, int n, int level) { ARMSSE *s = ARMSSE(opaque); qemu_set_irq(s->exp_irqs[n], level); } -static void iotkit_mpcexp_status(void *opaque, int n, int level) +static void armsse_mpcexp_status(void *opaque, int n, int level) { ARMSSE *s = ARMSSE(opaque); qemu_set_irq(s->mpcexp_status_in[n], level); } -static void iotkit_realize(DeviceState *dev, Error **errp) +static void armsse_realize(DeviceState *dev, Error **errp) { ARMSSE *s = ARMSSE(dev); int i; @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) for (i = 0; i < s->exp_numirq; i++) { s->exp_irqs[i] = qdev_get_gpio_in(DEVICE(&s->armv7m), i + 32); } - qdev_init_gpio_in_named(dev, iotkit_exp_irq, "EXP_IRQ", s->exp_numirq); + qdev_init_gpio_in_named(dev, armsse_exp_irq, "EXP_IRQ", s->exp_numirq); /* Set up the big aliases first */ make_alias(s, &s->alias1, "alias 1", 0x10000000, 0x10000000, 0x00000000); @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(dev_splitter, 0)); /* This RAM lives behind the Memory Protection Controller */ - memory_region_init_ram(&s->sram0, NULL, "iotkit.sram0", 0x00008000, &err); + memory_region_init_ram(&s->sram0, NULL, "armsse.sram0", 0x00008000, &err); if (err) { error_propagate(errp, err); return; @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) for (i = 0; i < IOTS_NUM_AHB_EXP_PPC; i++) { char *ppcname = g_strdup_printf("ahb_ppcexp%d", i); - iotkit_forward_ppc(s, ppcname, i); + armsse_forward_ppc(s, ppcname, i); g_free(ppcname); } for (i = 0; i < IOTS_NUM_APB_EXP_PPC; i++) { char *ppcname = g_strdup_printf("apb_ppcexp%d", i); - iotkit_forward_ppc(s, ppcname, i + IOTS_NUM_AHB_EXP_PPC); + armsse_forward_ppc(s, ppcname, i + IOTS_NUM_AHB_EXP_PPC); g_free(ppcname); } @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) /* Create GPIO inputs which will pass the line state for our * mpcexp_irq inputs to the correct splitter devices. */ - qdev_init_gpio_in_named(dev, iotkit_mpcexp_status, "mpcexp_status", + qdev_init_gpio_in_named(dev, armsse_mpcexp_status, "mpcexp_status", IOTS_NUM_EXP_MPC); - iotkit_forward_sec_resp_cfg(s); + armsse_forward_sec_resp_cfg(s); /* Forward the MSC related signals */ qdev_pass_gpios(dev_secctl, dev, "mscexp_status"); @@ -XXX,XX +XXX,XX @@ static void iotkit_realize(DeviceState *dev, Error **errp) system_clock_scale = NANOSECONDS_PER_SECOND / s->mainclk_frq; } -static void iotkit_idau_check(IDAUInterface *ii, uint32_t address, +static void armsse_idau_check(IDAUInterface *ii, uint32_t address, int *iregion, bool *exempt, bool *ns, bool *nsc) { /* @@ -XXX,XX +XXX,XX @@ static void iotkit_idau_check(IDAUInterface *ii, uint32_t address, *iregion = region; } -static const VMStateDescription iotkit_vmstate = { +static const VMStateDescription armsse_vmstate = { .name = "iotkit", .version_id = 1, .minimum_version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription iotkit_vmstate = { } }; -static Property iotkit_properties[] = { +static Property armsse_properties[] = { DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), @@ -XXX,XX +XXX,XX @@ static Property iotkit_properties[] = { DEFINE_PROP_END_OF_LIST() }; -static void iotkit_reset(DeviceState *dev) +static void armsse_reset(DeviceState *dev) { ARMSSE *s = ARMSSE(dev); s->nsccfg = 0; } -static void iotkit_class_init(ObjectClass *klass, void *data) +static void armsse_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(klass); ARMSSEClass *asc = ARMSSE_CLASS(klass); - dc->realize = iotkit_realize; - dc->vmsd = &iotkit_vmstate; - dc->props = iotkit_properties; - dc->reset = iotkit_reset; - iic->check = iotkit_idau_check; + dc->realize = armsse_realize; + dc->vmsd = &armsse_vmstate; + dc->props = armsse_properties; + dc->reset = armsse_reset; + iic->check = armsse_idau_check; asc->info = data; } @@ -XXX,XX +XXX,XX @@ static const TypeInfo armsse_info = { .name = TYPE_ARMSSE, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(ARMSSE), - .instance_init = iotkit_init, + .instance_init = armsse_init, .abstract = true, .interfaces = (InterfaceInfo[]) { { TYPE_IDAU_INTERFACE }, @@ -XXX,XX +XXX,XX @@ static void armsse_register_types(void) TypeInfo ti = { .name = armsse_variants[i].name, .parent = TYPE_ARMSSE, - .class_init = iotkit_class_init, + .class_init = armsse_class_init, .class_data = (void *)&armsse_variants[i], }; type_register(&ti); -- 2.20.1 Rename the files that used to be iotkit.[ch] to armsse.[ch] to reflect the fact they new cover multiple Arm subsystems for embedded. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-8-peter.maydell@linaro.org --- hw/arm/Makefile.objs | 2 +- include/hw/arm/{iotkit.h => armsse.h} | 4 ++-- hw/arm/{iotkit.c => armsse.c} | 2 +- hw/arm/mps2-tz.c | 2 +- MAINTAINERS | 4 ++-- default-configs/arm-softmmu.mak | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) rename include/hw/arm/{iotkit.h => armsse.h} (99%) rename hw/arm/{iotkit.c => armsse.c} (99%) 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_ASPEED_SOC) += aspeed_soc.o aspeed.o obj-$(CONFIG_MPS2) += mps2.o obj-$(CONFIG_MPS2) += mps2-tz.o obj-$(CONFIG_MSF2) += msf2-soc.o msf2-som.o -obj-$(CONFIG_IOTKIT) += iotkit.o +obj-$(CONFIG_ARMSSE) += armsse.o obj-$(CONFIG_FSL_IMX7) += fsl-imx7.o mcimx7d-sabre.o obj-$(CONFIG_ARM_SMMUV3) += smmu-common.o smmuv3.o obj-$(CONFIG_FSL_IMX6UL) += fsl-imx6ul.o mcimx6ul-evk.o diff --git a/include/hw/arm/iotkit.h b/include/hw/arm/armsse.h similarity index 99% rename from include/hw/arm/iotkit.h rename to include/hw/arm/armsse.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/iotkit.h +++ b/include/hw/arm/armsse.h @@ -XXX,XX +XXX,XX @@ * + named GPIO outputs mscexp_ns[0..15] */ -#ifndef IOTKIT_H -#define IOTKIT_H +#ifndef ARMSSE_H +#define ARMSSE_H #include "hw/sysbus.h" #include "hw/arm/armv7m.h" diff --git a/hw/arm/iotkit.c b/hw/arm/armsse.c similarity index 99% rename from hw/arm/iotkit.c rename to hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/iotkit.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include "hw/sysbus.h" #include "hw/registerfields.h" -#include "hw/arm/iotkit.h" +#include "hw/arm/armsse.h" #include "hw/arm/arm.h" struct ARMSSEInfo { 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 @@ #include "hw/misc/mps2-fpgaio.h" #include "hw/misc/tz-mpc.h" #include "hw/misc/tz-msc.h" -#include "hw/arm/iotkit.h" +#include "hw/arm/armsse.h" #include "hw/dma/pl080.h" #include "hw/ssi/pl022.h" #include "hw/devices.h" diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/arm/mps2.c F: hw/arm/mps2-tz.c F: hw/misc/mps2-*.c F: include/hw/misc/mps2-*.h -F: hw/arm/iotkit.c -F: include/hw/arm/iotkit.h +F: hw/arm/armsse.c +F: include/hw/arm/armsse.h F: hw/misc/iotkit-secctl.c F: include/hw/misc/iotkit-secctl.h F: hw/misc/iotkit-sysctl.c diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_MPS2_SCC=y CONFIG_TZ_MPC=y CONFIG_TZ_MSC=y CONFIG_TZ_PPC=y -CONFIG_IOTKIT=y +CONFIG_ARMSSE=y CONFIG_IOTKIT_SECCTL=y CONFIG_IOTKIT_SYSCTL=y CONFIG_IOTKIT_SYSINFO=y -- 2.20.1 The SSE-200 has 4 banks of SRAM, each with its own internal Memory Protection Controller. The interrupt status for these extra MPCs appears in the same security controller SECMPCINTSTATUS register as the MPC for the IoTKit's single SRAM bank. Enhance the iotkit-secctl device to allow 4 MPCs. (If the particular IoTKit/SSE variant in use does not have all 4 MPCs then the unused inputs will simply result in the SECMPCINTSTATUS bits being zero as required.) The hardcoded constant "1"s in armsse.c indicate the actual number of SRAM MPCs the IoTKit has, and will be replaced in the following commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-9-peter.maydell@linaro.org --- include/hw/misc/iotkit-secctl.h | 6 +++--- hw/arm/armsse.c | 6 +++--- hw/misc/iotkit-secctl.c | 5 +++-- 3 files changed, 9 insertions(+), 8 deletions(-) diff --git a/include/hw/misc/iotkit-secctl.h b/include/hw/misc/iotkit-secctl.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-secctl.h +++ b/include/hw/misc/iotkit-secctl.h @@ -XXX,XX +XXX,XX @@ * + named GPIO outputs ahb_ppcexp{0,1,2,3}_irq_enable * + named GPIO outputs ahb_ppcexp{0,1,2,3}_irq_clear * + named GPIO inputs ahb_ppcexp{0,1,2,3}_irq_status - * Controlling the MPC in the IoTKit: - * + named GPIO input mpc_status + * Controlling the (up to) 4 MPCs in the IoTKit/SSE: + * + named GPIO inputs mpc_status[0..3] * Controlling each of the 16 expansion MPCs which a system using the IoTKit * might provide: * + named GPIO inputs mpcexp_status[0..15] @@ -XXX,XX +XXX,XX @@ #define IOTS_NUM_APB_EXP_PPC 4 #define IOTS_NUM_AHB_EXP_PPC 4 #define IOTS_NUM_EXP_MPC 16 -#define IOTS_NUM_MPC 1 +#define IOTS_NUM_MPC 4 #define IOTS_NUM_EXP_MSC 16 typedef struct IoTKitSecCtl IoTKitSecCtl; 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_init(Object *obj) sizeof(s->mpc_irq_orgate), TYPE_OR_IRQ, &error_abort, NULL); - for (i = 0; i < ARRAY_SIZE(s->mpc_irq_splitter); i++) { + for (i = 0; i < IOTS_NUM_EXP_MPC + 1; i++) { char *name = g_strdup_printf("mpc-irq-splitter-%d", i); SplitIRQ *splitter = &s->mpc_irq_splitter[i]; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) /* We must OR together lines from the MPC splitters to go to the NVIC */ object_property_set_int(OBJECT(&s->mpc_irq_orgate), - IOTS_NUM_EXP_MPC + IOTS_NUM_MPC, "num-lines", &err); + IOTS_NUM_EXP_MPC + 1, "num-lines", &err); if (err) { error_propagate(errp, err); return; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) } /* Wire up the splitters for the MPC IRQs */ - for (i = 0; i < IOTS_NUM_EXP_MPC + IOTS_NUM_MPC; i++) { + for (i = 0; i < IOTS_NUM_EXP_MPC + 1; i++) { SplitIRQ *splitter = &s->mpc_irq_splitter[i]; DeviceState *dev_splitter = DEVICE(splitter); diff --git a/hw/misc/iotkit-secctl.c b/hw/misc/iotkit-secctl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iotkit-secctl.c +++ b/hw/misc/iotkit-secctl.c @@ -XXX,XX +XXX,XX @@ static void iotkit_secctl_mpc_status(void *opaque, int n, int level) { IoTKitSecCtl *s = IOTKIT_SECCTL(opaque); - s->mpcintstatus = deposit32(s->mpcintstatus, 0, 1, !!level); + s->mpcintstatus = deposit32(s->mpcintstatus, n, 1, !!level); } static void iotkit_secctl_mpcexp_status(void *opaque, int n, int level) @@ -XXX,XX +XXX,XX @@ static void iotkit_secctl_init(Object *obj) qdev_init_gpio_out_named(dev, &s->sec_resp_cfg, "sec_resp_cfg", 1); qdev_init_gpio_out_named(dev, &s->nsc_cfg_irq, "nsc_cfg", 1); - qdev_init_gpio_in_named(dev, iotkit_secctl_mpc_status, "mpc_status", 1); + qdev_init_gpio_in_named(dev, iotkit_secctl_mpc_status, "mpc_status", + IOTS_NUM_MPC); qdev_init_gpio_in_named(dev, iotkit_secctl_mpcexp_status, "mpcexp_status", IOTS_NUM_EXP_MPC); -- 2.20.1 The SSE-200 has four banks of SRAM, each with its own Memory Protection Controller, where the IoTKit has only one. Make the number of SRAM banks a field in ARMSSEInfo. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-10-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 9 +++-- hw/arm/armsse.c | 78 ++++++++++++++++++++++++++--------------- 2 files changed, 56 insertions(+), 31 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 @@ #define NUM_EXTERNAL_PPCS (IOTS_NUM_AHB_EXP_PPC + IOTS_NUM_APB_EXP_PPC) #define NUM_PPCS (NUM_EXTERNAL_PPCS + 2) +#define MAX_SRAM_BANKS 4 +#if MAX_SRAM_BANKS > IOTS_NUM_MPC +#error Too many SRAM banks +#endif + typedef struct ARMSSE { /*< private >*/ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { IoTKitSecCtl secctl; TZPPC apb_ppc0; TZPPC apb_ppc1; - TZMPC mpc; + TZMPC mpc[IOTS_NUM_MPC]; CMSDKAPBTIMER timer0; CMSDKAPBTIMER timer1; CMSDKAPBTIMER s32ktimer; @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { MemoryRegion alias1; MemoryRegion alias2; MemoryRegion alias3; - MemoryRegion sram0; + MemoryRegion sram[MAX_SRAM_BANKS]; qemu_irq *exp_irqs; 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 @@ struct ARMSSEInfo { const char *name; + int sram_banks; }; static const ARMSSEInfo armsse_variants[] = { { .name = TYPE_IOTKIT, + .sram_banks = 1, }, }; @@ -XXX,XX +XXX,XX @@ static void armsse_forward_sec_resp_cfg(ARMSSE *s) static void armsse_init(Object *obj) { ARMSSE *s = ARMSSE(obj); + ARMSSEClass *asc = ARMSSE_GET_CLASS(obj); + const ARMSSEInfo *info = asc->info; int i; + assert(info->sram_banks <= MAX_SRAM_BANKS); + memory_region_init(&s->container, obj, "armsse-container", UINT64_MAX); sysbus_init_child_obj(obj, "armv7m", &s->armv7m, sizeof(s->armv7m), @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) TYPE_TZ_PPC); sysbus_init_child_obj(obj, "apb-ppc1", &s->apb_ppc1, sizeof(s->apb_ppc1), TYPE_TZ_PPC); - sysbus_init_child_obj(obj, "mpc", &s->mpc, sizeof(s->mpc), TYPE_TZ_MPC); + for (i = 0; i < info->sram_banks; i++) { + char *name = g_strdup_printf("mpc%d", i); + sysbus_init_child_obj(obj, name, &s->mpc[i], + sizeof(s->mpc[i]), TYPE_TZ_MPC); + g_free(name); + } object_initialize_child(obj, "mpc-irq-orgate", &s->mpc_irq_orgate, sizeof(s->mpc_irq_orgate), TYPE_OR_IRQ, &error_abort, NULL); - for (i = 0; i < IOTS_NUM_EXP_MPC + 1; i++) { + for (i = 0; i < IOTS_NUM_EXP_MPC + info->sram_banks; i++) { char *name = g_strdup_printf("mpc-irq-splitter-%d", i); SplitIRQ *splitter = &s->mpc_irq_splitter[i]; @@ -XXX,XX +XXX,XX @@ static void armsse_mpcexp_status(void *opaque, int n, int level) static void armsse_realize(DeviceState *dev, Error **errp) { ARMSSE *s = ARMSSE(dev); + ARMSSEClass *asc = ARMSSE_GET_CLASS(dev); + const ARMSSEInfo *info = asc->info; int i; MemoryRegion *mr; Error *err = NULL; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) qdev_connect_gpio_out_named(dev_secctl, "sec_resp_cfg", 0, qdev_get_gpio_in(dev_splitter, 0)); - /* This RAM lives behind the Memory Protection Controller */ - memory_region_init_ram(&s->sram0, NULL, "armsse.sram0", 0x00008000, &err); - if (err) { - error_propagate(errp, err); - return; + /* Each SRAM bank lives behind its own Memory Protection Controller */ + for (i = 0; i < info->sram_banks; i++) { + char *ramname = g_strdup_printf("armsse.sram%d", i); + SysBusDevice *sbd_mpc; + + memory_region_init_ram(&s->sram[i], NULL, ramname, 0x00008000, &err); + g_free(ramname); + if (err) { + error_propagate(errp, err); + return; + } + object_property_set_link(OBJECT(&s->mpc[i]), OBJECT(&s->sram[i]), + "downstream", &err); + if (err) { + error_propagate(errp, err); + return; + } + object_property_set_bool(OBJECT(&s->mpc[i]), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + /* 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 * 0x8000, + sysbus_mmio_get_region(sbd_mpc, 1)); + /* ...and its register interface */ + memory_region_add_subregion(&s->container, 0x50083000 + i * 0x1000, + sysbus_mmio_get_region(sbd_mpc, 0)); } - object_property_set_link(OBJECT(&s->mpc), OBJECT(&s->sram0), - "downstream", &err); - if (err) { - error_propagate(errp, err); - return; - } - object_property_set_bool(OBJECT(&s->mpc), true, "realized", &err); - if (err) { - error_propagate(errp, err); - return; - } - /* Map the upstream end of the MPC into the right place... */ - memory_region_add_subregion(&s->container, 0x20000000, - sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->mpc), - 1)); - /* ...and its register interface */ - memory_region_add_subregion(&s->container, 0x50083000, - sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->mpc), - 0)); /* We must OR together lines from the MPC splitters to go to the NVIC */ object_property_set_int(OBJECT(&s->mpc_irq_orgate), - IOTS_NUM_EXP_MPC + 1, "num-lines", &err); + IOTS_NUM_EXP_MPC + info->sram_banks, + "num-lines", &err); if (err) { error_propagate(errp, err); return; @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) } /* Wire up the splitters for the MPC IRQs */ - for (i = 0; i < IOTS_NUM_EXP_MPC + 1; i++) { + for (i = 0; i < IOTS_NUM_EXP_MPC + info->sram_banks; i++) { SplitIRQ *splitter = &s->mpc_irq_splitter[i]; DeviceState *dev_splitter = DEVICE(splitter); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) "mpcexp_status", i)); } else { /* Splitter input is from our own MPC */ - qdev_connect_gpio_out_named(DEVICE(&s->mpc), "irq", 0, + qdev_connect_gpio_out_named(DEVICE(&s->mpc[i - IOTS_NUM_EXP_MPC]), + "irq", 0, qdev_get_gpio_in(dev_splitter, 0)); qdev_connect_gpio_out(dev_splitter, 0, qdev_get_gpio_in_named(dev_secctl, -- 2.20.1 For the IoTKit the SRAM bank size is always 32K (15 bits); for the SSE-200 this is a configurable parameter, which defaults to 32K but can be changed when it is built into a particular SoC. For instance the Musca-B1 board sets it to 128K (17 bits). Make the bank size a QOM property. We follow the SSE-200 hardware in naming the parameter SRAM_ADDR_WIDTH, which specifies the number of address bits of a single SRAM bank. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-11-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 1 + hw/arm/armsse.c | 18 ++++++++++++++++-- 2 files changed, 17 insertions(+), 2 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 @@ typedef struct ARMSSE { MemoryRegion *board_memory; uint32_t exp_numirq; uint32_t mainclk_frq; + uint32_t sram_addr_width; } ARMSSE; typedef struct ARMSSEInfo ARMSSEInfo; 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) DeviceState *dev_apb_ppc1; DeviceState *dev_secctl; DeviceState *dev_splitter; + uint32_t addr_width_max; if (!s->board_memory) { error_setg(errp, "memory property was not set"); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } + /* max SRAM_ADDR_WIDTH: 24 - log2(SRAM_NUM_BANK) */ + assert(is_power_of_2(info->sram_banks)); + addr_width_max = 24 - ctz32(info->sram_banks); + if (s->sram_addr_width < 1 || s->sram_addr_width > addr_width_max) { + error_setg(errp, "SRAM_ADDR_WIDTH must be between 1 and %d", + addr_width_max); + return; + } + /* Handling of which devices should be available only to secure * code is usually done differently for M profile than for A profile. * Instead of putting some devices only into the secure address space, @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) for (i = 0; i < info->sram_banks; i++) { char *ramname = g_strdup_printf("armsse.sram%d", i); SysBusDevice *sbd_mpc; + uint32_t sram_bank_size = 1 << s->sram_addr_width; - memory_region_init_ram(&s->sram[i], NULL, ramname, 0x00008000, &err); + memory_region_init_ram(&s->sram[i], NULL, ramname, + sram_bank_size, &err); g_free(ramname); if (err) { error_propagate(errp, err); @@ -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 * 0x8000, + memory_region_add_subregion(&s->container, + 0x20000000 + i * sram_bank_size, sysbus_mmio_get_region(sbd_mpc, 1)); /* ...and its register interface */ memory_region_add_subregion(&s->container, 0x50083000 + i * 0x1000, @@ -XXX,XX +XXX,XX @@ static Property armsse_properties[] = { MemoryRegion *), DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), DEFINE_PROP_UINT32("MAINCLK", ARMSSE, mainclk_frq, 0), + DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), DEFINE_PROP_END_OF_LIST() }; -- 2.20.1 The SSE-200 has two Cortex-M33 CPUs. These see the same view of memory, with the exception of the "private CPU region" which has per-CPU devices. Internal device interrupts for SSE-200 devices are mostly wired up to both CPUs, with the exception of a few per-CPU devices. External GPIO inputs on the SSE-200 device are provided for the second CPU's interrupts above 32, as is already the case for the first CPU. Refactor the code to support creation of multiple CPUs. For the moment we leave all CPUs with the same view of memory: this will not work in the multiple-CPU case, but we will fix this in the following commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-12-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 21 +++- hw/arm/armsse.c | 206 ++++++++++++++++++++++++++++++++-------- 2 files changed, 180 insertions(+), 47 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 @@ * + QOM property "memory" is a MemoryRegion containing the devices provided * by the board model. * + QOM property "MAINCLK" is the frequency of the main system clock - * + QOM property "EXP_NUMIRQ" sets the number of expansion interrupts - * + Named GPIO inputs "EXP_IRQ" 0..n are the expansion interrupts, which - * are wired to the NVIC lines 32 .. n+32 + * + QOM property "EXP_NUMIRQ" sets the number of expansion interrupts. + * (In hardware, the SSE-200 permits the number of expansion interrupts + * for the two CPUs to be configured separately, but we restrict it to + * being the same for both, to avoid having to have separate Property + * lists for different variants. This restriction can be relaxed later + * if necessary.) + * + Named GPIO inputs "EXP_IRQ" 0..n are the expansion interrupts for CPU 0, + * which are wired to its NVIC lines 32 .. n+32 + * + Named GPIO inputs "EXP_CPU1_IRQ" 0..n are the expansion interrupts for + * CPU 1, which are wired to its NVIC lines 32 .. n+32 * + sysbus MMIO region 0 is the "AHB Slave Expansion" which allows * bus master devices in the board model to make transactions into * all the devices and memory areas in the IoTKit @@ -XXX,XX +XXX,XX @@ #error Too many SRAM banks #endif +#define SSE_MAX_CPUS 2 + typedef struct ARMSSE { /*< private >*/ SysBusDevice parent_obj; /*< public >*/ - ARMv7MState armv7m; + ARMv7MState armv7m[SSE_MAX_CPUS]; IoTKitSecCtl secctl; TZPPC apb_ppc0; TZPPC apb_ppc1; @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { qemu_or_irq mpc_irq_orgate; qemu_or_irq nmi_orgate; + SplitIRQ cpu_irq_splitter[32]; + CMSDKAPBDualTimer dualtimer; CMSDKAPBWatchdog s32kwatchdog; @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { MemoryRegion alias3; MemoryRegion sram[MAX_SRAM_BANKS]; - qemu_irq *exp_irqs; + qemu_irq *exp_irqs[SSE_MAX_CPUS]; qemu_irq ppc0_irq; qemu_irq ppc1_irq; qemu_irq sec_resp_cfg; 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 *name; int sram_banks; + int num_cpus; }; static const ARMSSEInfo armsse_variants[] = { { .name = TYPE_IOTKIT, .sram_banks = 1, + .num_cpus = 1, }, }; /* Clock frequency in HZ of the 32KHz "slow clock" */ #define S32KCLK (32 * 1000) +/* Is internal IRQ n shared between CPUs in a multi-core SSE ? */ +static bool irq_is_common[32] = { + [0 ... 5] = true, + /* 6, 7: per-CPU MHU interrupts */ + [8 ... 12] = true, + /* 13: per-CPU icache interrupt */ + /* 14: reserved */ + [15 ... 20] = true, + /* 21: reserved */ + [22 ... 26] = true, + /* 27: reserved */ + /* 28, 29: per-CPU CTI interrupts */ + /* 30, 31: reserved */ +}; + /* Create an alias region of @size bytes starting at @base * which mirrors the memory starting at @orig. */ @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) int i; assert(info->sram_banks <= MAX_SRAM_BANKS); + assert(info->num_cpus <= SSE_MAX_CPUS); memory_region_init(&s->container, obj, "armsse-container", UINT64_MAX); - sysbus_init_child_obj(obj, "armv7m", &s->armv7m, sizeof(s->armv7m), - TYPE_ARMV7M); - qdev_prop_set_string(DEVICE(&s->armv7m), "cpu-type", - ARM_CPU_TYPE_NAME("cortex-m33")); + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("armv7m%d", i); + sysbus_init_child_obj(obj, name, &s->armv7m[i], sizeof(s->armv7m), + TYPE_ARMV7M); + qdev_prop_set_string(DEVICE(&s->armv7m[i]), "cpu-type", + ARM_CPU_TYPE_NAME("cortex-m33")); + g_free(name); + } sysbus_init_child_obj(obj, "secctl", &s->secctl, sizeof(s->secctl), TYPE_IOTKIT_SECCTL); @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) TYPE_SPLIT_IRQ, &error_abort, NULL); g_free(name); } + if (info->num_cpus > 1) { + for (i = 0; i < ARRAY_SIZE(s->cpu_irq_splitter); i++) { + if (irq_is_common[i]) { + char *name = g_strdup_printf("cpu-irq-splitter%d", i); + SplitIRQ *splitter = &s->cpu_irq_splitter[i]; + + object_initialize_child(obj, name, splitter, sizeof(*splitter), + TYPE_SPLIT_IRQ, &error_abort, NULL); + g_free(name); + } + } + } } static void armsse_exp_irq(void *opaque, int n, int level) { - ARMSSE *s = ARMSSE(opaque); + qemu_irq *irqarray = opaque; - qemu_set_irq(s->exp_irqs[n], level); + qemu_set_irq(irqarray[n], level); } static void armsse_mpcexp_status(void *opaque, int n, int level) @@ -XXX,XX +XXX,XX @@ static void armsse_mpcexp_status(void *opaque, int n, int level) qemu_set_irq(s->mpcexp_status_in[n], level); } +static qemu_irq armsse_get_common_irq_in(ARMSSE *s, int irqno) +{ + /* + * Return a qemu_irq which can be used to signal IRQ n to + * all CPUs in the SSE. + */ + ARMSSEClass *asc = ARMSSE_GET_CLASS(s); + const ARMSSEInfo *info = asc->info; + + assert(irq_is_common[irqno]); + + if (info->num_cpus == 1) { + /* Only one CPU -- just connect directly to it */ + return qdev_get_gpio_in(DEVICE(&s->armv7m[0]), irqno); + } else { + /* Connect to the splitter which feeds all CPUs */ + return qdev_get_gpio_in(DEVICE(&s->cpu_irq_splitter[irqno]), 0); + } +} + static void armsse_realize(DeviceState *dev, Error **errp) { ARMSSE *s = ARMSSE(dev); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1); - qdev_prop_set_uint32(DEVICE(&s->armv7m), "num-irq", s->exp_numirq + 32); - /* In real hardware the initial Secure VTOR is set from the INITSVTOR0 - * register in the IoT Kit System Control Register block, and the - * initial value of that is in turn specifiable by the FPGA that - * instantiates the IoT Kit. In QEMU we don't implement this wrinkle, - * and simply set the CPU's init-svtor to the IoT Kit default value. - */ - qdev_prop_set_uint32(DEVICE(&s->armv7m), "init-svtor", 0x10000000); - object_property_set_link(OBJECT(&s->armv7m), OBJECT(&s->container), - "memory", &err); - if (err) { - error_propagate(errp, err); - return; - } - object_property_set_link(OBJECT(&s->armv7m), OBJECT(s), "idau", &err); - if (err) { - error_propagate(errp, err); - return; - } - object_property_set_bool(OBJECT(&s->armv7m), true, "realized", &err); - if (err) { - error_propagate(errp, err); - return; + for (i = 0; i < info->num_cpus; i++) { + DeviceState *cpudev = DEVICE(&s->armv7m[i]); + Object *cpuobj = OBJECT(&s->armv7m[i]); + int j; + char *gpioname; + + qdev_prop_set_uint32(cpudev, "num-irq", s->exp_numirq + 32); + /* + * In real hardware the initial Secure VTOR is set from the INITSVTOR0 + * register in the IoT Kit System Control Register block, and the + * initial value of that is in turn specifiable by the FPGA that + * instantiates the IoT Kit. In QEMU we don't implement this wrinkle, + * and simply set the CPU's init-svtor to the IoT Kit default value. + * In SSE-200 the situation is similar, except that the default value + * is a reset-time signal input. Typically a board using the SSE-200 + * will have a system control processor whose boot firmware initializes + * the INITSVTOR* registers before powering up the CPUs in any case, + * so the hardware's default value doesn't matter. QEMU doesn't emulate + * the control processor, so instead we behave in the way that the + * firmware does. All boards currently known about have firmware that + * sets the INITSVTOR0 and INITSVTOR1 registers to 0x10000000, like the + * IoTKit default. We can make this more configurable if necessary. + */ + qdev_prop_set_uint32(cpudev, "init-svtor", 0x10000000); + /* + * Start all CPUs except CPU0 powered down. In real hardware it is + * a configurable property of the SSE-200 which CPUs start powered up + * (via the CPUWAIT0_RST and CPUWAIT1_RST parameters), but since all + * the boards we care about start CPU0 and leave CPU1 powered off, + * we hard-code that for now. We can add QOM properties for this + * later if necessary. + */ + if (i > 0) { + object_property_set_bool(cpuobj, true, "start-powered-off", &err); + if (err) { + error_propagate(errp, err); + return; + } + } + object_property_set_link(cpuobj, OBJECT(&s->container), "memory", &err); + if (err) { + error_propagate(errp, err); + return; + } + object_property_set_link(cpuobj, OBJECT(s), "idau", &err); + if (err) { + error_propagate(errp, err); + return; + } + object_property_set_bool(cpuobj, true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + /* Connect EXP_IRQ/EXP_CPUn_IRQ GPIOs to the NVIC's lines 32 and up */ + s->exp_irqs[i] = g_new(qemu_irq, s->exp_numirq); + for (j = 0; j < s->exp_numirq; j++) { + s->exp_irqs[i][j] = qdev_get_gpio_in(cpudev, i + 32); + } + if (i == 0) { + gpioname = g_strdup("EXP_IRQ"); + } else { + gpioname = g_strdup_printf("EXP_CPU%d_IRQ", i); + } + qdev_init_gpio_in_named_with_opaque(dev, armsse_exp_irq, + s->exp_irqs[i], + gpioname, s->exp_numirq); + g_free(gpioname); } - /* Connect our EXP_IRQ GPIOs to the NVIC's lines 32 and up. */ - s->exp_irqs = g_new(qemu_irq, s->exp_numirq); - for (i = 0; i < s->exp_numirq; i++) { - s->exp_irqs[i] = qdev_get_gpio_in(DEVICE(&s->armv7m), i + 32); + /* Wire up the splitters that connect common IRQs to all CPUs */ + if (info->num_cpus > 1) { + for (i = 0; i < ARRAY_SIZE(s->cpu_irq_splitter); i++) { + if (irq_is_common[i]) { + Object *splitter = OBJECT(&s->cpu_irq_splitter[i]); + DeviceState *devs = DEVICE(splitter); + int cpunum; + + object_property_set_int(splitter, info->num_cpus, + "num-lines", &err); + if (err) { + error_propagate(errp, err); + return; + } + object_property_set_bool(splitter, true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + for (cpunum = 0; cpunum < info->num_cpus; cpunum++) { + DeviceState *cpudev = DEVICE(&s->armv7m[cpunum]); + + qdev_connect_gpio_out(devs, cpunum, + qdev_get_gpio_in(cpudev, i)); + } + } + } } - qdev_init_gpio_in_named(dev, armsse_exp_irq, "EXP_IRQ", s->exp_numirq); /* Set up the big aliases first */ make_alias(s, &s->alias1, "alias 1", 0x10000000, 0x10000000, 0x00000000); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } qdev_connect_gpio_out(DEVICE(&s->mpc_irq_orgate), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 9)); + armsse_get_common_irq_in(s, 9)); /* Devices behind APB PPC0: * 0x40000000: timer0 @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer0), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 3)); + armsse_get_common_irq_in(s, 3)); mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->timer0), 0); object_property_set_link(OBJECT(&s->apb_ppc0), OBJECT(mr), "port[0]", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer1), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 4)); + armsse_get_common_irq_in(s, 4)); mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->timer1), 0); object_property_set_link(OBJECT(&s->apb_ppc0), OBJECT(mr), "port[1]", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } sysbus_connect_irq(SYS_BUS_DEVICE(&s->dualtimer), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 5)); + armsse_get_common_irq_in(s, 5)); mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->dualtimer), 0); object_property_set_link(OBJECT(&s->apb_ppc0), OBJECT(mr), "port[2]", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } qdev_connect_gpio_out(DEVICE(&s->ppc_irq_orgate), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 10)); + armsse_get_common_irq_in(s, 10)); /* 0x40010000 .. 0x4001ffff: private CPU region: unused in IoTKit */ @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } sysbus_connect_irq(SYS_BUS_DEVICE(&s->s32ktimer), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 2)); + armsse_get_common_irq_in(s, 2)); mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->s32ktimer), 0); object_property_set_link(OBJECT(&s->apb_ppc1), OBJECT(mr), "port[0]", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } sysbus_connect_irq(SYS_BUS_DEVICE(&s->nswatchdog), 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 1)); + armsse_get_common_irq_in(s, 1)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->nswatchdog), 0, 0x40081000); qdev_prop_set_uint32(DEVICE(&s->swatchdog), "wdogclk-frq", s->mainclk_frq); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) qdev_pass_gpios(dev_secctl, dev, "mscexp_clear"); qdev_pass_gpios(dev_secctl, dev, "mscexp_ns"); qdev_connect_gpio_out_named(dev_secctl, "msc_irq", 0, - qdev_get_gpio_in(DEVICE(&s->armv7m), 11)); + armsse_get_common_irq_in(s, 11)); /* * Expose our container region to the board model; this corresponds -- 2.20.1 Give each CPU its own container memory region. This is necessary for two reasons: * some devices are instantiated one per CPU and the CPU sees only its own device * since a memory region can only be put into one container, we must give each armv7m object a different MemoryRegion as its 'memory' property, or a dual-CPU configuration will assert on realize when the second armv7m object tries to put the MR into a container when it is already in the first armv7m object's container Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-13-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 10 ++++++++++ hw/arm/armsse.c | 22 ++++++++++++++++++++-- 2 files changed, 30 insertions(+), 2 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 @@ typedef struct ARMSSE { IoTKitSysCtl sysctl; IoTKitSysCtl sysinfo; + /* + * 'container' holds all devices seen by all CPUs. + * 'cpu_container[i]' is the view that CPU i has: this has the + * per-CPU devices of that CPU, plus as the background 'container' + * (or an alias of it, since we can only use it directly once). + * container_alias[i] is the alias of 'container' used by CPU i+1; + * CPU 0 can use 'container' directly. + */ MemoryRegion container; + MemoryRegion container_alias[SSE_MAX_CPUS - 1]; + MemoryRegion cpu_container[SSE_MAX_CPUS]; MemoryRegion alias1; MemoryRegion alias2; MemoryRegion alias3; 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_init(Object *obj) qdev_prop_set_string(DEVICE(&s->armv7m[i]), "cpu-type", ARM_CPU_TYPE_NAME("cortex-m33")); g_free(name); + name = g_strdup_printf("arm-sse-cpu-container%d", i); + memory_region_init(&s->cpu_container[i], obj, name, UINT64_MAX); + g_free(name); + if (i > 0) { + name = g_strdup_printf("arm-sse-container-alias%d", i); + memory_region_init_alias(&s->container_alias[i - 1], obj, + name, &s->container, 0, UINT64_MAX); + g_free(name); + } } sysbus_init_child_obj(obj, "secctl", &s->secctl, sizeof(s->secctl), @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) * 0x50000000..0x5fffffff alias of 0x40000000..0x4fffffff */ - memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1); + memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -2); for (i = 0; i < info->num_cpus; i++) { DeviceState *cpudev = DEVICE(&s->armv7m[i]); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } } - object_property_set_link(cpuobj, OBJECT(&s->container), "memory", &err); + + if (i > 0) { + memory_region_add_subregion_overlap(&s->cpu_container[i], 0, + &s->container_alias[i - 1], -1); + } else { + memory_region_add_subregion_overlap(&s->cpu_container[i], 0, + &s->container, -1); + } + object_property_set_link(cpuobj, OBJECT(&s->cpu_container[i]), + "memory", &err); if (err) { error_propagate(errp, err); return; -- 2.20.1 Create a cluster object to hold each CPU in the SSE. They are logically distinct and may be configured differently (for instance one may not have an FPU where the other does). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-14-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 2 ++ hw/arm/armsse.c | 31 ++++++++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 3 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 @@ #include "hw/misc/iotkit-sysinfo.h" #include "hw/or-irq.h" #include "hw/core/split-irq.h" +#include "hw/cpu/cluster.h" #define TYPE_ARMSSE "arm-sse" #define ARMSSE(obj) OBJECT_CHECK(ARMSSE, (obj), TYPE_ARMSSE) @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { /*< public >*/ ARMv7MState armv7m[SSE_MAX_CPUS]; + CPUClusterState cluster[SSE_MAX_CPUS]; IoTKitSecCtl secctl; TZPPC apb_ppc0; TZPPC apb_ppc1; 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_init(Object *obj) memory_region_init(&s->container, obj, "armsse-container", UINT64_MAX); for (i = 0; i < info->num_cpus; i++) { - char *name = g_strdup_printf("armv7m%d", i); - sysbus_init_child_obj(obj, name, &s->armv7m[i], sizeof(s->armv7m), - TYPE_ARMV7M); + /* + * We put each CPU in its own cluster as they are logically + * distinct and may be configured differently. + */ + char *name; + + name = g_strdup_printf("cluster%d", i); + object_initialize_child(obj, name, &s->cluster[i], + sizeof(s->cluster[i]), TYPE_CPU_CLUSTER, + &error_abort, NULL); + qdev_prop_set_uint32(DEVICE(&s->cluster[i]), "cluster-id", i); + g_free(name); + + name = g_strdup_printf("armv7m%d", i); + sysbus_init_child_obj(OBJECT(&s->cluster[i]), name, + &s->armv7m[i], sizeof(s->armv7m), TYPE_ARMV7M); qdev_prop_set_string(DEVICE(&s->armv7m[i]), "cpu-type", ARM_CPU_TYPE_NAME("cortex-m33")); g_free(name); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } + /* + * The cluster must be realized after the armv7m container, as + * the container's CPU object is only created on realize, and the + * CPU must exist and have been parented into the cluster before + * the cluster is realized. + */ + object_property_set_bool(OBJECT(&s->cluster[i]), + true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } /* Connect EXP_IRQ/EXP_CPUn_IRQ GPIOs to the NVIC's lines 32 and up */ s->exp_irqs[i] = g_new(qemu_irq, s->exp_numirq); -- 2.20.1 The SYS_VERSION and SYS_CONFIG register values differ between the IoTKit and SSE-200. Make them configurable via QOM properties rather than hard-coded, and set them appropriately in the ARMSSE code that instantiates the IOTKIT_SYSINFO device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-15-peter.maydell@linaro.org --- include/hw/misc/iotkit-sysinfo.h | 6 ++++ hw/arm/armsse.c | 51 ++++++++++++++++++++++++++++++++ hw/misc/iotkit-sysinfo.c | 15 ++++++++-- 3 files changed, 70 insertions(+), 2 deletions(-) diff --git a/include/hw/misc/iotkit-sysinfo.h b/include/hw/misc/iotkit-sysinfo.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-sysinfo.h +++ b/include/hw/misc/iotkit-sysinfo.h @@ -XXX,XX +XXX,XX @@ * Arm IoTKit and documented in * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html * QEMU interface: + * + QOM property "SYS_VERSION": value to use for SYS_VERSION register + * + QOM property "SYS_CONFIG": value to use for SYS_CONFIG register * + sysbus MMIO region 0: the system information register bank */ @@ -XXX,XX +XXX,XX @@ typedef struct IoTKitSysInfo { /*< public >*/ MemoryRegion iomem; + + /* Properties */ + uint32_t sys_version; + uint32_t sys_config; } IoTKitSysInfo; #endif 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 "hw/arm/armsse.h" #include "hw/arm/arm.h" +/* Format of the System Information block SYS_CONFIG register */ +typedef enum SysConfigFormat { + IoTKitFormat, + SSE200Format, +} SysConfigFormat; + struct ARMSSEInfo { const char *name; int sram_banks; int num_cpus; + uint32_t sys_version; + SysConfigFormat sys_config_format; }; static const ARMSSEInfo armsse_variants[] = { @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .name = TYPE_IOTKIT, .sram_banks = 1, .num_cpus = 1, + .sys_version = 0x41743, + .sys_config_format = IoTKitFormat, }, }; +static uint32_t armsse_sys_config_value(ARMSSE *s, const ARMSSEInfo *info) +{ + /* Return the SYS_CONFIG value for this SSE */ + uint32_t sys_config; + + switch (info->sys_config_format) { + case IoTKitFormat: + sys_config = 0; + sys_config = deposit32(sys_config, 0, 4, info->sram_banks); + sys_config = deposit32(sys_config, 4, 4, s->sram_addr_width - 12); + break; + case SSE200Format: + sys_config = 0; + sys_config = deposit32(sys_config, 0, 4, info->sram_banks); + sys_config = deposit32(sys_config, 4, 5, s->sram_addr_width); + sys_config = deposit32(sys_config, 24, 4, 2); + if (info->num_cpus > 1) { + sys_config = deposit32(sys_config, 10, 1, 1); + sys_config = deposit32(sys_config, 20, 4, info->sram_banks - 1); + sys_config = deposit32(sys_config, 28, 4, 2); + } + break; + default: + g_assert_not_reached(); + } + return sys_config; +} + /* Clock frequency in HZ of the 32KHz "slow clock" */ #define S32KCLK (32 * 1000) @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in_named(dev_apb_ppc1, "cfg_sec_resp", 0)); + object_property_set_int(OBJECT(&s->sysinfo), info->sys_version, + "SYS_VERSION", &err); + if (err) { + error_propagate(errp, err); + return; + } + object_property_set_int(OBJECT(&s->sysinfo), + armsse_sys_config_value(s, info), + "SYS_CONFIG", &err); + if (err) { + error_propagate(errp, err); + return; + } object_property_set_bool(OBJECT(&s->sysinfo), true, "realized", &err); if (err) { error_propagate(errp, err); diff --git a/hw/misc/iotkit-sysinfo.c b/hw/misc/iotkit-sysinfo.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iotkit-sysinfo.c +++ b/hw/misc/iotkit-sysinfo.c @@ -XXX,XX +XXX,XX @@ static const int sysinfo_id[] = { static uint64_t iotkit_sysinfo_read(void *opaque, hwaddr offset, unsigned size) { + IoTKitSysInfo *s = IOTKIT_SYSINFO(opaque); uint64_t r; switch (offset) { case A_SYS_VERSION: - r = 0x41743; + r = s->sys_version; break; case A_SYS_CONFIG: - r = 0x31; + r = s->sys_config; break; case A_PID4 ... A_CID3: r = sysinfo_id[(offset - A_PID4) / 4]; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps iotkit_sysinfo_ops = { .valid.max_access_size = 4, }; +static Property iotkit_sysinfo_props[] = { + DEFINE_PROP_UINT32("SYS_VERSION", IoTKitSysInfo, sys_version, 0), + DEFINE_PROP_UINT32("SYS_CONFIG", IoTKitSysInfo, sys_config, 0), + DEFINE_PROP_END_OF_LIST() +}; + static void iotkit_sysinfo_init(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void iotkit_sysinfo_init(Object *obj) static void iotkit_sysinfo_class_init(ObjectClass *klass, void *data) { + DeviceClass *dc = DEVICE_CLASS(klass); + /* * This device has no guest-modifiable state and so it * does not need a reset function or VMState. */ + + dc->props = iotkit_sysinfo_props; } static const TypeInfo iotkit_sysinfo_info = { -- 2.20.1 The SSE-200 has two Message Handling Units (MHUs), which sit behind the APB PPC0. Wire up some unimplemented-device stubs for these, since we don't yet implement a real model of this device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-16-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 3 +++ hw/arm/armsse.c | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) 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 @@ #include "hw/watchdog/cmsdk-apb-watchdog.h" #include "hw/misc/iotkit-sysctl.h" #include "hw/misc/iotkit-sysinfo.h" +#include "hw/misc/unimp.h" #include "hw/or-irq.h" #include "hw/core/split-irq.h" #include "hw/cpu/cluster.h" @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { IoTKitSysCtl sysctl; IoTKitSysCtl sysinfo; + UnimplementedDeviceState mhu[2]; + /* * 'container' holds all devices seen by all CPUs. * 'cpu_container[i]' is the view that CPU i has: this has the 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 { int num_cpus; uint32_t sys_version; SysConfigFormat sys_config_format; + bool has_mhus; }; static const ARMSSEInfo armsse_variants[] = { @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .num_cpus = 1, .sys_version = 0x41743, .sys_config_format = IoTKitFormat, + .has_mhus = false, }, }; @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) sizeof(s->sysctl), TYPE_IOTKIT_SYSCTL); sysbus_init_child_obj(obj, "armsse-sysinfo", &s->sysinfo, sizeof(s->sysinfo), TYPE_IOTKIT_SYSINFO); + if (info->has_mhus) { + sysbus_init_child_obj(obj, "mhu0", &s->mhu[0], sizeof(s->mhu[0]), + TYPE_UNIMPLEMENTED_DEVICE); + sysbus_init_child_obj(obj, "mhu1", &s->mhu[1], sizeof(s->mhu[1]), + TYPE_UNIMPLEMENTED_DEVICE); + } object_initialize_child(obj, "nmi-orgate", &s->nmi_orgate, sizeof(s->nmi_orgate), TYPE_OR_IRQ, &error_abort, NULL); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) * 0x40000000: timer0 * 0x40001000: timer1 * 0x40002000: dual timer + * 0x40003000: MHU0 (SSE-200 only) + * 0x40004000: MHU1 (SSE-200 only) * We must configure and realize each downstream device and connect * it to the appropriate PPC port; then we can realize the PPC and * map its upstream ends to the right place in the container. @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) return; } + if (info->has_mhus) { + for (i = 0; i < ARRAY_SIZE(s->mhu); i++) { + char *name = g_strdup_printf("MHU%d", i); + char *port = g_strdup_printf("port[%d]", i + 3); + + qdev_prop_set_string(DEVICE(&s->mhu[i]), "name", name); + qdev_prop_set_uint64(DEVICE(&s->mhu[i]), "size", 0x1000); + object_property_set_bool(OBJECT(&s->mhu[i]), true, + "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->mhu[i]), 0); + object_property_set_link(OBJECT(&s->apb_ppc0), OBJECT(mr), + port, &err); + if (err) { + error_propagate(errp, err); + return; + } + g_free(name); + g_free(port); + } + } + object_property_set_bool(OBJECT(&s->apb_ppc0), true, "realized", &err); if (err) { error_propagate(errp, err); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(&s->container, 0x40001000, mr); mr = sysbus_mmio_get_region(sbd_apb_ppc0, 2); memory_region_add_subregion(&s->container, 0x40002000, mr); + if (info->has_mhus) { + mr = sysbus_mmio_get_region(sbd_apb_ppc0, 3); + memory_region_add_subregion(&s->container, 0x40003000, mr); + mr = sysbus_mmio_get_region(sbd_apb_ppc0, 4); + memory_region_add_subregion(&s->container, 0x40004000, mr); + } for (i = 0; i < IOTS_APB_PPC0_NUM_PORTS; i++) { qdev_connect_gpio_out_named(dev_secctl, "apb_ppc0_nonsec", i, qdev_get_gpio_in_named(dev_apb_ppc0, -- 2.20.1 Add unimplemented-device stubs for the various Power Policy Unit devices that the SSE-200 has. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-17-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 11 ++++++++ hw/arm/armsse.c | 58 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) 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 @@ #define SSE_MAX_CPUS 2 +/* These define what each PPU in the ppu[] index is for */ +#define CPU0CORE_PPU 0 +#define CPU1CORE_PPU 1 +#define DBG_PPU 2 +#define RAM0_PPU 3 +#define RAM1_PPU 4 +#define RAM2_PPU 5 +#define RAM3_PPU 6 +#define NUM_PPUS 7 + typedef struct ARMSSE { /*< private >*/ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { IoTKitSysCtl sysinfo; UnimplementedDeviceState mhu[2]; + UnimplementedDeviceState ppu[NUM_PPUS]; /* * 'container' holds all devices seen by all CPUs. 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 { uint32_t sys_version; SysConfigFormat sys_config_format; bool has_mhus; + bool has_ppus; }; static const ARMSSEInfo armsse_variants[] = { @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .sys_version = 0x41743, .sys_config_format = IoTKitFormat, .has_mhus = false, + .has_ppus = false, }, }; @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) sysbus_init_child_obj(obj, "mhu1", &s->mhu[1], sizeof(s->mhu[1]), TYPE_UNIMPLEMENTED_DEVICE); } + if (info->has_ppus) { + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("CPU%dCORE_PPU", i); + int ppuidx = CPU0CORE_PPU + i; + + sysbus_init_child_obj(obj, name, &s->ppu[ppuidx], + sizeof(s->ppu[ppuidx]), + TYPE_UNIMPLEMENTED_DEVICE); + g_free(name); + } + sysbus_init_child_obj(obj, "DBG_PPU", &s->ppu[DBG_PPU], + sizeof(s->ppu[DBG_PPU]), + TYPE_UNIMPLEMENTED_DEVICE); + for (i = 0; i < info->sram_banks; i++) { + char *name = g_strdup_printf("RAM%d_PPU", i); + int ppuidx = RAM0_PPU + i; + + sysbus_init_child_obj(obj, name, &s->ppu[ppuidx], + sizeof(s->ppu[ppuidx]), + TYPE_UNIMPLEMENTED_DEVICE); + g_free(name); + } + } object_initialize_child(obj, "nmi-orgate", &s->nmi_orgate, sizeof(s->nmi_orgate), TYPE_OR_IRQ, &error_abort, NULL); @@ -XXX,XX +XXX,XX @@ static qemu_irq armsse_get_common_irq_in(ARMSSE *s, int irqno) } } +static void map_ppu(ARMSSE *s, int ppuidx, const char *name, hwaddr addr) +{ + /* Map a PPU unimplemented device stub */ + DeviceState *dev = DEVICE(&s->ppu[ppuidx]); + + qdev_prop_set_string(dev, "name", name); + qdev_prop_set_uint64(dev, "size", 0x1000); + qdev_init_nofail(dev); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ppu[ppuidx]), 0, addr); +} + static void armsse_realize(DeviceState *dev, Error **errp) { ARMSSE *s = ARMSSE(dev); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->sysctl), 0, 0x50021000); + if (info->has_ppus) { + /* CPUnCORE_PPU for each CPU */ + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("CPU%dCORE_PPU", i); + + map_ppu(s, CPU0CORE_PPU + i, name, 0x50023000 + i * 0x2000); + /* + * We don't support CPU debug so don't create the + * CPU0DEBUG_PPU at 0x50024000 and 0x50026000. + */ + g_free(name); + } + map_ppu(s, DBG_PPU, "DBG_PPU", 0x50029000); + + for (i = 0; i < info->sram_banks; i++) { + char *name = g_strdup_printf("RAM%d_PPU", i); + + map_ppu(s, RAM0_PPU + i, name, 0x5002a000 + i * 0x1000); + g_free(name); + } + } + /* This OR gate wires together outputs from the secure watchdogs to NMI */ object_property_set_int(OBJECT(&s->nmi_orgate), 2, "num-lines", &err); if (err) { -- 2.20.1 The SSE-200 gives each CPU a register bank to use to control its L1 instruction cache. Put in an unimplemented-device stub for this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-18-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 1 + hw/arm/armsse.c | 39 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) 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 @@ typedef struct ARMSSE { UnimplementedDeviceState mhu[2]; UnimplementedDeviceState ppu[NUM_PPUS]; + UnimplementedDeviceState cachectrl[SSE_MAX_CPUS]; /* * 'container' holds all devices seen by all CPUs. 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 { SysConfigFormat sys_config_format; bool has_mhus; bool has_ppus; + bool has_cachectrl; }; static const ARMSSEInfo armsse_variants[] = { @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .sys_config_format = IoTKitFormat, .has_mhus = false, .has_ppus = false, + .has_cachectrl = false, }, }; @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) g_free(name); } } + if (info->has_cachectrl) { + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("cachectrl%d", i); + + sysbus_init_child_obj(obj, name, &s->cachectrl[i], + sizeof(s->cachectrl[i]), + TYPE_UNIMPLEMENTED_DEVICE); + g_free(name); + } + } object_initialize_child(obj, "nmi-orgate", &s->nmi_orgate, sizeof(s->nmi_orgate), TYPE_OR_IRQ, &error_abort, NULL); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) qdev_connect_gpio_out(DEVICE(&s->ppc_irq_orgate), 0, armsse_get_common_irq_in(s, 10)); - /* 0x40010000 .. 0x4001ffff: private CPU region: unused in IoTKit */ + /* + * 0x40010000 .. 0x4001ffff (and the 0x5001000... secure-only alias): + * private per-CPU region (all these devices are SSE-200 only): + * 0x50010000: L1 icache control registers + * 0x50011000: CPUSECCTRL (CPU local security control registers) + * 0x4001f000 and 0x5001f000: CPU_IDENTITY register block + */ + if (info->has_cachectrl) { + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("cachectrl%d", i); + MemoryRegion *mr; + + qdev_prop_set_string(DEVICE(&s->cachectrl[i]), "name", name); + g_free(name); + qdev_prop_set_uint64(DEVICE(&s->cachectrl[i]), "size", 0x1000); + object_property_set_bool(OBJECT(&s->cachectrl[i]), true, + "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->cachectrl[i]), 0); + memory_region_add_subregion(&s->cpu_container[i], 0x50010000, mr); + } + } /* 0x40020000 .. 0x4002ffff : ARMSSE system control peripheral region */ /* Devices behind APB PPC1: -- 2.20.1 The SSE-200 has a "CPU local security control" register bank; add an unimplemented-device stub for it. (The register bank has only one interesting register, which allows the guest to lock down changes to various CPU registers so they cannot be modified further. We don't support that in our Cortex-M33 model anyway.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-19-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 1 + hw/arm/armsse.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) 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 @@ typedef struct ARMSSE { UnimplementedDeviceState mhu[2]; UnimplementedDeviceState ppu[NUM_PPUS]; UnimplementedDeviceState cachectrl[SSE_MAX_CPUS]; + UnimplementedDeviceState cpusecctrl[SSE_MAX_CPUS]; /* * 'container' holds all devices seen by all CPUs. 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 { bool has_mhus; bool has_ppus; bool has_cachectrl; + bool has_cpusecctrl; }; static const ARMSSEInfo armsse_variants[] = { @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .has_mhus = false, .has_ppus = false, .has_cachectrl = false, + .has_cpusecctrl = false, }, }; @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) g_free(name); } } + if (info->has_cpusecctrl) { + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("cpusecctrl%d", i); + + sysbus_init_child_obj(obj, name, &s->cpusecctrl[i], + sizeof(s->cpusecctrl[i]), + TYPE_UNIMPLEMENTED_DEVICE); + g_free(name); + } + } object_initialize_child(obj, "nmi-orgate", &s->nmi_orgate, sizeof(s->nmi_orgate), TYPE_OR_IRQ, &error_abort, NULL); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(&s->cpu_container[i], 0x50010000, mr); } } + if (info->has_cpusecctrl) { + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("CPUSECCTRL%d", i); + MemoryRegion *mr; + + qdev_prop_set_string(DEVICE(&s->cpusecctrl[i]), "name", name); + g_free(name); + qdev_prop_set_uint64(DEVICE(&s->cpusecctrl[i]), "size", 0x1000); + object_property_set_bool(OBJECT(&s->cpusecctrl[i]), true, + "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->cpusecctrl[i]), 0); + memory_region_add_subregion(&s->cpu_container[i], 0x50011000, mr); + } + } /* 0x40020000 .. 0x4002ffff : ARMSSE system control peripheral region */ /* Devices behind APB PPC1: -- 2.20.1 The SSE-200 has a CPU_IDENTITY register block, which is a set of read-only registers. As well as the usual PID/CID registers, there is a single CPUID register which indicates whether the CPU is CPU 0 or CPU 1. Implement a model of this register block. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-20-peter.maydell@linaro.org --- hw/misc/Makefile.objs | 1 + include/hw/misc/armsse-cpuid.h | 41 ++++++++++ hw/misc/armsse-cpuid.c | 134 ++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + default-configs/arm-softmmu.mak | 1 + hw/misc/trace-events | 4 + 6 files changed, 183 insertions(+) create mode 100644 include/hw/misc/armsse-cpuid.h create mode 100644 hw/misc/armsse-cpuid.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 @@ obj-$(CONFIG_TZ_PPC) += tz-ppc.o obj-$(CONFIG_IOTKIT_SECCTL) += iotkit-secctl.o obj-$(CONFIG_IOTKIT_SYSCTL) += iotkit-sysctl.o obj-$(CONFIG_IOTKIT_SYSINFO) += iotkit-sysinfo.o +obj-$(CONFIG_ARMSSE_CPUID) += armsse-cpuid.o obj-$(CONFIG_PVPANIC) += pvpanic.o obj-$(CONFIG_AUX) += auxbus.o diff --git a/include/hw/misc/armsse-cpuid.h b/include/hw/misc/armsse-cpuid.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/armsse-cpuid.h @@ -XXX,XX +XXX,XX @@ +/* + * ARM SSE-200 CPU_IDENTITY register block + * + * Copyright (c) 2019 Linaro Limited + * Written by Peter Maydell + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +/* + * This is a model of the "CPU_IDENTITY" register block which is part of the + * Arm SSE-200 and documented in + * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * + * QEMU interface: + * + QOM property "CPUID": the value to use for the CPUID register + * + sysbus MMIO region 0: the system information register bank + */ + +#ifndef HW_MISC_ARMSSE_CPUID_H +#define HW_MISC_ARMSSE_CPUID_H + +#include "hw/sysbus.h" + +#define TYPE_ARMSSE_CPUID "armsse-cpuid" +#define ARMSSE_CPUID(obj) OBJECT_CHECK(ARMSSECPUID, (obj), TYPE_ARMSSE_CPUID) + +typedef struct ARMSSECPUID { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + + /* Properties */ + uint32_t cpuid; +} ARMSSECPUID; + +#endif diff --git a/hw/misc/armsse-cpuid.c b/hw/misc/armsse-cpuid.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/armsse-cpuid.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM SSE-200 CPU_IDENTITY register block + * + * Copyright (c) 2019 Linaro Limited + * Written by Peter Maydell + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +/* + * This is a model of the "CPU_IDENTITY" register block which is part of the + * Arm SSE-200 and documented in + * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * + * It consists of one read-only CPUID register (set by QOM property), plus the + * usual ID registers. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "trace.h" +#include "qapi/error.h" +#include "sysemu/sysemu.h" +#include "hw/sysbus.h" +#include "hw/registerfields.h" +#include "hw/misc/armsse-cpuid.h" + +REG32(CPUID, 0x0) +REG32(PID4, 0xfd0) +REG32(PID5, 0xfd4) +REG32(PID6, 0xfd8) +REG32(PID7, 0xfdc) +REG32(PID0, 0xfe0) +REG32(PID1, 0xfe4) +REG32(PID2, 0xfe8) +REG32(PID3, 0xfec) +REG32(CID0, 0xff0) +REG32(CID1, 0xff4) +REG32(CID2, 0xff8) +REG32(CID3, 0xffc) + +/* PID/CID values */ +static const int sysinfo_id[] = { + 0x04, 0x00, 0x00, 0x00, /* PID4..PID7 */ + 0x58, 0xb8, 0x0b, 0x00, /* PID0..PID3 */ + 0x0d, 0xf0, 0x05, 0xb1, /* CID0..CID3 */ +}; + +static uint64_t armsse_cpuid_read(void *opaque, hwaddr offset, + unsigned size) +{ + ARMSSECPUID *s = ARMSSE_CPUID(opaque); + uint64_t r; + + switch (offset) { + case A_CPUID: + r = s->cpuid; + break; + case A_PID4 ... A_CID3: + r = sysinfo_id[(offset - A_PID4) / 4]; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "SSE CPU_IDENTITY read: bad offset 0x%x\n", (int)offset); + r = 0; + break; + } + trace_armsse_cpuid_read(offset, r, size); + return r; +} + +static void armsse_cpuid_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + trace_armsse_cpuid_write(offset, value, size); + + qemu_log_mask(LOG_GUEST_ERROR, + "SSE CPU_IDENTITY: write to RO offset 0x%x\n", (int)offset); +} + +static const MemoryRegionOps armsse_cpuid_ops = { + .read = armsse_cpuid_read, + .write = armsse_cpuid_write, + .endianness = DEVICE_LITTLE_ENDIAN, + /* byte/halfword accesses are just zero-padded on reads and writes */ + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .valid.min_access_size = 1, + .valid.max_access_size = 4, +}; + +static Property armsse_cpuid_props[] = { + DEFINE_PROP_UINT32("CPUID", ARMSSECPUID, cpuid, 0), + DEFINE_PROP_END_OF_LIST() +}; + +static void armsse_cpuid_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + ARMSSECPUID *s = ARMSSE_CPUID(obj); + + memory_region_init_io(&s->iomem, obj, &armsse_cpuid_ops, + s, "armsse-cpuid", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); +} + +static void armsse_cpuid_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + /* + * This device has no guest-modifiable state and so it + * does not need a reset function or VMState. + */ + + dc->props = armsse_cpuid_props; +} + +static const TypeInfo armsse_cpuid_info = { + .name = TYPE_ARMSSE_CPUID, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ARMSSECPUID), + .instance_init = armsse_cpuid_init, + .class_init = armsse_cpuid_class_init, +}; + +static void armsse_cpuid_register_types(void) +{ + type_register_static(&armsse_cpuid_info); +} + +type_init(armsse_cpuid_register_types); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/misc/iotkit-sysctl.c F: include/hw/misc/iotkit-sysctl.h F: hw/misc/iotkit-sysinfo.c F: include/hw/misc/iotkit-sysinfo.h +F: hw/misc/armsse-cpuid.c +F: include/hw/misc/armsse-cpuid.h Musicpal M: Jan Kiszka <jan.kiszka@web.de> 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_ARMSSE=y CONFIG_IOTKIT_SECCTL=y CONFIG_IOTKIT_SYSCTL=y CONFIG_IOTKIT_SYSINFO=y +CONFIG_ARMSSE_CPUID=y CONFIG_VERSATILE=y CONFIG_VERSATILE_PCI=y 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 @@ iotkit_sysinfo_write(uint64_t offset, uint64_t data, unsigned size) "IoTKit SysI iotkit_sysctl_read(uint64_t offset, uint64_t data, unsigned size) "IoTKit SysCtl read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" iotkit_sysctl_write(uint64_t offset, uint64_t data, unsigned size) "IoTKit SysCtl write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" iotkit_sysctl_reset(void) "IoTKit SysCtl: reset" + +# hw/misc/armsse-cpuid.c +armsse_cpuid_read(uint64_t offset, uint64_t data, unsigned size) "SSE-200 CPU_IDENTITY read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" +armsse_cpuid_write(uint64_t offset, uint64_t data, unsigned size) "SSE-200 CPU_IDENTITY write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" -- 2.20.1 Instantiate a copy of the CPU_IDENTITY register block for each CPU in an SSE-200. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-21-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 3 +++ hw/arm/armsse.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) 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 @@ #include "hw/watchdog/cmsdk-apb-watchdog.h" #include "hw/misc/iotkit-sysctl.h" #include "hw/misc/iotkit-sysinfo.h" +#include "hw/misc/armsse-cpuid.h" #include "hw/misc/unimp.h" #include "hw/or-irq.h" #include "hw/core/split-irq.h" @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { UnimplementedDeviceState cachectrl[SSE_MAX_CPUS]; UnimplementedDeviceState cpusecctrl[SSE_MAX_CPUS]; + ARMSSECPUID cpuid[SSE_MAX_CPUS]; + /* * 'container' holds all devices seen by all CPUs. * 'cpu_container[i]' is the view that CPU i has: this has the 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 { bool has_ppus; bool has_cachectrl; bool has_cpusecctrl; + bool has_cpuid; }; static const ARMSSEInfo armsse_variants[] = { @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { .has_ppus = false, .has_cachectrl = false, .has_cpusecctrl = false, + .has_cpuid = false, }, }; @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) g_free(name); } } + if (info->has_cpuid) { + for (i = 0; i < info->num_cpus; i++) { + char *name = g_strdup_printf("cpuid%d", i); + + sysbus_init_child_obj(obj, name, &s->cpuid[i], + sizeof(s->cpuid[i]), + TYPE_ARMSSE_CPUID); + g_free(name); + } + } object_initialize_child(obj, "nmi-orgate", &s->nmi_orgate, sizeof(s->nmi_orgate), TYPE_OR_IRQ, &error_abort, NULL); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(&s->cpu_container[i], 0x50011000, mr); } } + if (info->has_cpuid) { + for (i = 0; i < info->num_cpus; i++) { + MemoryRegion *mr; + + qdev_prop_set_uint32(DEVICE(&s->cpuid[i]), "CPUID", i); + object_property_set_bool(OBJECT(&s->cpuid[i]), true, + "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->cpuid[i]), 0); + memory_region_add_subregion(&s->cpu_container[i], 0x4001F000, mr); + } + } /* 0x40020000 .. 0x4002ffff : ARMSSE system control peripheral region */ /* Devices behind APB PPC1: -- 2.20.1 Add a model of the SSE-200, now we have put in all the code that lets us make it different from the IoTKit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-22-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 19 ++++++++++++++++--- hw/arm/armsse.c | 12 ++++++++++++ 2 files changed, 28 insertions(+), 3 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 @@ /* - * ARM SSE (Subsystems for Embedded): IoTKit + * ARM SSE (Subsystems for Embedded): IoTKit, SSE-200 * * Copyright (c) 2018 Linaro Limited * Written by Peter Maydell @@ -XXX,XX +XXX,XX @@ /* * This is a model of the Arm "Subsystems for Embedded" family of * hardware, which include the IoT Kit and the SSE-050, SSE-100 and - * SSE-200. Currently we model only the Arm IoT Kit which is documented in + * SSE-200. Currently we model: + * - the Arm IoT Kit which is documented in * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html - * It contains: + * - the SSE-200 which is documented in + * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * + * The IoTKit contains: * a Cortex-M33 * the IDAU * some timers and watchdogs @@ -XXX,XX +XXX,XX @@ * a security controller * a bus fabric which arranges that some parts of the address * space are secure and non-secure aliases of each other + * The SSE-200 additionally contains: + * a second Cortex-M33 + * two Message Handling Units (MHUs) + * an optional CryptoCell (which we do not model) + * more SRAM banks with associated MPCs + * multiple Power Policy Units (PPUs) + * a control interface for an icache for each CPU + * per-CPU identity and control register blocks * * QEMU interface: * + QOM property "memory" is a MemoryRegion containing the devices provided @@ -XXX,XX +XXX,XX @@ * them via the ARMSSE base class, so they have no IOTKIT() etc macros. */ #define TYPE_IOTKIT "iotkit" +#define TYPE_SSE200 "sse-200" /* We have an IRQ splitter and an OR gate input for each external PPC * and the 2 internal PPCs 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 const ARMSSEInfo armsse_variants[] = { .has_cpusecctrl = false, .has_cpuid = false, }, + { + .name = TYPE_SSE200, + .sram_banks = 4, + .num_cpus = 2, + .sys_version = 0x22041743, + .sys_config_format = SSE200Format, + .has_mhus = true, + .has_ppus = true, + .has_cachectrl = true, + .has_cpusecctrl = true, + .has_cpuid = true, + }, }; static uint32_t armsse_sys_config_value(ARMSSE *s, const ARMSSEInfo *info) -- 2.20.1 In preparation for adding support for the AN521 MPS2 image, we need to handle wiring up the MPS2 device interrupt lines to both CPUs in the SSE-200, rather than just the one that the IoTKit has. Abstract out a "connect to the IoTKit interrupt line" function and make it connect to a splitter which feeds both sets of inputs for the SSE-200 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-23-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 79 ++++++++++++++++++++++++++++++++++++------------ 1 file changed, 59 insertions(+), 20 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 @@ #include "net/net.h" #include "hw/core/split-irq.h" +#define MPS2TZ_NUMIRQ 92 + typedef enum MPS2TZFPGAType { FPGA_AN505, + FPGA_AN521, } MPS2TZFPGAType; typedef struct { @@ -XXX,XX +XXX,XX @@ typedef struct { SplitIRQ sec_resp_splitter; qemu_or_irq uart_irq_orgate; DeviceState *lan9118; + SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ]; } MPS2TZMachineState; #define TYPE_MPS2TZ_MACHINE "mps2tz" @@ -XXX,XX +XXX,XX @@ static void make_ram_alias(MemoryRegion *mr, const char *name, memory_region_add_subregion(get_system_memory(), base, mr); } +static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) +{ + /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + + assert(irqno < MPS2TZ_NUMIRQ); + + switch (mmc->fpga_type) { + case FPGA_AN505: + return qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "EXP_IRQ", irqno); + case FPGA_AN521: + return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); + default: + g_assert_not_reached(); + } +} + /* Most of the devices in the AN505 FPGA image sit behind * Peripheral Protection Controllers. These data structures * define the layout of which devices sit behind which PPCs. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, int txirqno = i * 2 + 1; int combirqno = i + 10; SysBusDevice *s; - DeviceState *iotkitdev = DEVICE(&mms->iotkit); DeviceState *orgate_dev = DEVICE(&mms->uart_irq_orgate); sysbus_init_child_obj(OBJECT(mms), name, uart, sizeof(mms->uart[0]), @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", SYSCLK_FRQ); object_property_set_bool(OBJECT(uart), true, "realized", &error_fatal); s = SYS_BUS_DEVICE(uart); - sysbus_connect_irq(s, 0, qdev_get_gpio_in_named(iotkitdev, - "EXP_IRQ", txirqno)); - sysbus_connect_irq(s, 1, qdev_get_gpio_in_named(iotkitdev, - "EXP_IRQ", rxirqno)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, txirqno)); + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, rxirqno)); sysbus_connect_irq(s, 2, qdev_get_gpio_in(orgate_dev, i * 2)); sysbus_connect_irq(s, 3, qdev_get_gpio_in(orgate_dev, i * 2 + 1)); - sysbus_connect_irq(s, 4, qdev_get_gpio_in_named(iotkitdev, - "EXP_IRQ", combirqno)); + sysbus_connect_irq(s, 4, get_sse_irq_in(mms, combirqno)); return sysbus_mmio_get_region(SYS_BUS_DEVICE(uart), 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size) { SysBusDevice *s; - DeviceState *iotkitdev = DEVICE(&mms->iotkit); NICInfo *nd = &nd_table[0]; /* In hardware this is a LAN9220; the LAN9118 is software compatible @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, qdev_init_nofail(mms->lan9118); s = SYS_BUS_DEVICE(mms->lan9118); - sysbus_connect_irq(s, 0, qdev_get_gpio_in_named(iotkitdev, "EXP_IRQ", 16)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 16)); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(dma); /* Wire up DMACINTR, DMACINTERR, DMACINTTC */ - sysbus_connect_irq(s, 0, qdev_get_gpio_in_named(iotkitdev, - "EXP_IRQ", 58 + i * 3)); - sysbus_connect_irq(s, 1, qdev_get_gpio_in_named(iotkitdev, - "EXP_IRQ", 56 + i * 3)); - sysbus_connect_irq(s, 2, qdev_get_gpio_in_named(iotkitdev, - "EXP_IRQ", 57 + i * 3)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 58 + i * 3)); + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, 56 + i * 3)); + sysbus_connect_irq(s, 2, get_sse_irq_in(mms, 57 + i * 3)); g_free(mscname); return sysbus_mmio_get_region(s, 0); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, */ PL022State *spi = opaque; int i = spi - &mms->spi[0]; - DeviceState *iotkitdev = DEVICE(&mms->iotkit); SysBusDevice *s; sysbus_init_child_obj(OBJECT(mms), name, spi, sizeof(mms->spi[0]), TYPE_PL022); object_property_set_bool(OBJECT(spi), true, "realized", &error_fatal); s = SYS_BUS_DEVICE(spi); - sysbus_connect_irq(s, 0, - qdev_get_gpio_in_named(iotkitdev, "EXP_IRQ", 51 + i)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 51 + i)); return sysbus_mmio_get_region(s, 0); } static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); MachineClass *mc = MACHINE_GET_CLASS(machine); MemoryRegion *system_memory = get_system_memory(); DeviceState *iotkitdev; @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) iotkitdev = DEVICE(&mms->iotkit); object_property_set_link(OBJECT(&mms->iotkit), OBJECT(system_memory), "memory", &error_abort); - qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", 92); + qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", MPS2TZ_NUMIRQ); qdev_prop_set_uint32(iotkitdev, "MAINCLK", SYSCLK_FRQ); object_property_set_bool(OBJECT(&mms->iotkit), true, "realized", &error_fatal); + /* + * The AN521 needs us to create splitters to feed the IRQ inputs + * for each CPU in the SSE-200 from each device in the board. + */ + if (mmc->fpga_type == FPGA_AN521) { + for (i = 0; i < MPS2TZ_NUMIRQ; i++) { + char *name = g_strdup_printf("mps2-irq-splitter%d", i); + SplitIRQ *splitter = &mms->cpu_irq_splitter[i]; + + object_initialize_child(OBJECT(machine), name, + splitter, sizeof(*splitter), + TYPE_SPLIT_IRQ, &error_fatal, NULL); + g_free(name); + + object_property_set_int(OBJECT(splitter), 2, "num-lines", + &error_fatal); + object_property_set_bool(OBJECT(splitter), true, "realized", + &error_fatal); + qdev_connect_gpio_out(DEVICE(splitter), 0, + qdev_get_gpio_in_named(DEVICE(&mms->iotkit), + "EXP_IRQ", i)); + qdev_connect_gpio_out(DEVICE(splitter), 1, + qdev_get_gpio_in_named(DEVICE(&mms->iotkit), + "EXP_CPU1_IRQ", i)); + } + } + /* The sec_resp_cfg output from the IoTKit must be split into multiple * lines, one for each of the PPCs we create here, plus one per MSC. */ @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) object_property_set_bool(OBJECT(&mms->uart_irq_orgate), true, "realized", &error_fatal); qdev_connect_gpio_out(DEVICE(&mms->uart_irq_orgate), 0, - qdev_get_gpio_in_named(iotkitdev, "EXP_IRQ", 15)); + get_sse_irq_in(mms, 15)); /* Most of the devices in the FPGA are behind Peripheral Protection * Controllers. The required order for initializing things is: -- 2.20.1 Add a model of the MPS2 FPGA image described in Application Note AN521. This is identical to the AN505 image, except that it uses the SSE-200 rather than the IoTKit and so has two Cortex-M33 CPUs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190121185118.18550-24-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 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 @@ * as seen by the guest depend significantly on the FPGA image. * This source file covers the following FPGA images, for TrustZone cores: * "mps2-an505" -- Cortex-M33 as documented in ARM Application Note AN505 + * "mps2-an521" -- Dual Cortex-M33 as documented in Application Note AN521 * * Links to the TRM for the board itself and to the various Application * Notes which document the FPGA images can be found here: @@ -XXX,XX +XXX,XX @@ * http://infocenter.arm.com/help/topic/com.arm.doc.100112_0200_06_en/versatile_express_cortex_m_prototyping_systems_v2m_mps2_and_v2m_mps2plus_technical_reference_100112_0200_06_en.pdf * Application Note AN505: * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * Application Note AN521: + * http://infocenter.arm.com/help/topic/com.arm.doc.dai0521c/index.html * * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide * (ARM ECM0601256) for the details of some of the device layout: * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * Similarly, the AN521 uses the SSE-200, and the SSE-200 TRM defines + * most of the device layout: + * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * */ #include "qemu/osdep.h" @@ -XXX,XX +XXX,XX @@ typedef struct { MachineClass parent; MPS2TZFPGAType fpga_type; uint32_t scc_id; + const char *armsse_type; } MPS2TZMachineClass; typedef struct { @@ -XXX,XX +XXX,XX @@ typedef struct { #define TYPE_MPS2TZ_MACHINE "mps2tz" #define TYPE_MPS2TZ_AN505_MACHINE MACHINE_TYPE_NAME("mps2-an505") +#define TYPE_MPS2TZ_AN521_MACHINE MACHINE_TYPE_NAME("mps2-an521") #define MPS2TZ_MACHINE(obj) \ OBJECT_CHECK(MPS2TZMachineState, obj, TYPE_MPS2TZ_MACHINE) @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) } sysbus_init_child_obj(OBJECT(machine), "iotkit", &mms->iotkit, - sizeof(mms->iotkit), TYPE_IOTKIT); + sizeof(mms->iotkit), mmc->armsse_type); iotkitdev = DEVICE(&mms->iotkit); object_property_set_link(OBJECT(&mms->iotkit), OBJECT(system_memory), "memory", &error_abort); @@ -XXX,XX +XXX,XX @@ static void mps2tz_class_init(ObjectClass *oc, void *data) IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(oc); mc->init = mps2tz_common_init; - mc->max_cpus = 1; iic->check = mps2_tz_idau_check; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_CLASS(oc); mc->desc = "ARM MPS2 with AN505 FPGA image for Cortex-M33"; + mc->default_cpus = 1; + mc->min_cpus = mc->default_cpus; + mc->max_cpus = mc->default_cpus; mmc->fpga_type = FPGA_AN505; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045050; + mmc->armsse_type = TYPE_IOTKIT; +} + +static void mps2tz_an521_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS2 with AN521 FPGA image for dual Cortex-M33"; + mc->default_cpus = 2; + mc->min_cpus = mc->default_cpus; + mc->max_cpus = mc->default_cpus; + mmc->fpga_type = FPGA_AN521; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); + mmc->scc_id = 0x41045210; + mmc->armsse_type = TYPE_SSE200; } static const TypeInfo mps2tz_info = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2tz_an505_info = { .class_init = mps2tz_an505_class_init, }; +static const TypeInfo mps2tz_an521_info = { + .name = TYPE_MPS2TZ_AN521_MACHINE, + .parent = TYPE_MPS2TZ_MACHINE, + .class_init = mps2tz_an521_class_init, +}; + static void mps2tz_machine_init(void) { type_register_static(&mps2tz_info); type_register_static(&mps2tz_an505_info); + type_register_static(&mps2tz_an521_info); } type_init(mps2tz_machine_init); -- 2.20.1 The "system instructions" and "system register move" subcategories of "branches, exception generating and system instructions" for A64 only apply if bits [23:22] are zero; other values are currently unallocated. Correctly UNDEF these unallocated encodings. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-2-peter.maydell@linaro.org --- target/arm/translate-a64.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) 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_b_exc_sys(DisasContext *s, uint32_t insn) break; case 0x6a: /* Exception generation / System */ if (insn & (1 << 24)) { - disas_system(s, insn); + if (extract32(insn, 22, 2) == 0) { + disas_system(s, insn); + } else { + unallocated_encoding(s); + } } else { disas_exc(s, insn); } -- 2.20.1 The PRFM prefetch insn in the load/store with imm9 encodings requires idx field 0b00; we were underdecoding this by only checking !is_unpriv (which is equivalent to idx != 2). Correctly UNDEF the unallocated encodings where idx == 0b01 and 0b11 as well as 0b10. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-3-peter.maydell@linaro.org --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_ldst_reg_imm9(DisasContext *s, uint32_t insn, } else { if (size == 3 && opc == 2) { /* PRFM - prefetch */ - if (is_unpriv) { + if (idx != 0) { unallocated_encoding(s); return; } -- 2.20.1 In the AdvSIMD load/store multiple structures encodings, the non-post-indexed case should have zeroes in [20:16] (which is the Rm field for the post-indexed case). Correctly UNDEF the currently unallocated encodings which have non-zeroes in those bits. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-4-peter.maydell@linaro.org --- target/arm/translate-a64.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) 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_ldst_multiple_struct(DisasContext *s, uint32_t insn) { int rt = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); + int rm = extract32(insn, 16, 5); int size = extract32(insn, 10, 2); int opcode = extract32(insn, 12, 4); bool is_store = !extract32(insn, 22, 1); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) return; } + if (!is_postidx && rm != 0) { + unallocated_encoding(s); + return; + } + /* From the shared decode logic */ switch (opcode) { case 0x0: @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) } if (is_postidx) { - int rm = extract32(insn, 16, 5); if (rm == 31) { tcg_gen_mov_i64(tcg_rn, tcg_addr); } else { -- 2.20.1 In the AdvSIMD load/store single structure encodings, the non-post-indexed case should have zeroes in [20:16] (which is the Rm field for the post-indexed case). Bit 31 must also be zero (a check we got right in ldst_multiple but not here). Correctly UNDEF these unallocated encodings. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-5-peter.maydell@linaro.org --- target/arm/translate-a64.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) 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_ldst_single_struct(DisasContext *s, uint32_t insn) { int rt = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); + int rm = extract32(insn, 16, 5); int size = extract32(insn, 10, 2); int S = extract32(insn, 12, 1); int opc = extract32(insn, 13, 3); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) int ebytes, xs; TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; + if (extract32(insn, 31, 1)) { + unallocated_encoding(s); + return; + } + if (!is_postidx && rm != 0) { + unallocated_encoding(s); + return; + } + switch (scale) { case 3: if (!is_load || S) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } if (is_postidx) { - int rm = extract32(insn, 16, 5); if (rm == 31) { tcg_gen_mov_i64(tcg_rn, tcg_addr); } else { -- 2.20.1 In the "add/subtract (extended register)" encoding group, the "opt" field in bits [23:22] must be zero. Correctly UNDEF the unallocated encodings where this field is not zero. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-6-peter.maydell@linaro.org --- target/arm/translate-a64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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_add_sub_ext_reg(DisasContext *s, uint32_t insn) int imm3 = extract32(insn, 10, 3); int option = extract32(insn, 13, 3); int rm = extract32(insn, 16, 5); + int opt = extract32(insn, 22, 2); bool setflags = extract32(insn, 29, 1); bool sub_op = extract32(insn, 30, 1); bool sf = extract32(insn, 31, 1); @@ -XXX,XX +XXX,XX @@ static void disas_add_sub_ext_reg(DisasContext *s, uint32_t insn) TCGv_i64 tcg_rd; TCGv_i64 tcg_result; - if (imm3 > 4) { + if (imm3 > 4 || opt != 0) { unallocated_encoding(s); return; } -- 2.20.1 In the encoding groups * floating-point data-processing (1 source) * floating-point data-processing (2 source) * floating-point data-processing (3 source) * floating-point immediate * floating-point compare * floating-ponit conditional compare * floating-point conditional select bit 31 is M and bit 29 is S (and bit 30 is 0, already checked at this point in the decode). None of these groups allocate any encoding for M=1 or S=1. We checked this in disas_fp_compare(), disas_fp_ccomp() and disas_fp_csel(), but missed it in disas_fp_1src(), disas_fp_2src(), disas_fp_3src() and disas_fp_imm(). We also missed that in the fp immediate encoding the imm5 field must be all zeroes. Correctly UNDEF the unallocated encodings here. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-7-peter.maydell@linaro.org --- target/arm/translate-a64.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) 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 handle_fp_fcvt(DisasContext *s, int opcode, */ static void disas_fp_1src(DisasContext *s, uint32_t insn) { + int mos = extract32(insn, 29, 3); int type = extract32(insn, 22, 2); int opcode = extract32(insn, 15, 6); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); + if (mos) { + unallocated_encoding(s); + return; + } + switch (opcode) { case 0x4: case 0x5: case 0x7: { @@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_half(DisasContext *s, int opcode, */ static void disas_fp_2src(DisasContext *s, uint32_t insn) { + int mos = extract32(insn, 29, 3); int type = extract32(insn, 22, 2); int rd = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); int rm = extract32(insn, 16, 5); int opcode = extract32(insn, 12, 4); - if (opcode > 8) { + if (opcode > 8 || mos) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void handle_fp_3src_half(DisasContext *s, bool o0, bool o1, */ static void disas_fp_3src(DisasContext *s, uint32_t insn) { + int mos = extract32(insn, 29, 3); int type = extract32(insn, 22, 2); int rd = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) bool o0 = extract32(insn, 15, 1); bool o1 = extract32(insn, 21, 1); + if (mos) { + unallocated_encoding(s); + return; + } + switch (type) { case 0: if (!fp_access_check(s)) { @@ -XXX,XX +XXX,XX @@ uint64_t vfp_expand_imm(int size, uint8_t imm8) static void disas_fp_imm(DisasContext *s, uint32_t insn) { int rd = extract32(insn, 0, 5); + int imm5 = extract32(insn, 5, 5); int imm8 = extract32(insn, 13, 8); int type = extract32(insn, 22, 2); + int mos = extract32(insn, 29, 3); uint64_t imm; TCGv_i64 tcg_res; TCGMemOp sz; + if (mos || imm5) { + unallocated_encoding(s); + return; + } + switch (type) { case 0: sz = MO_32; -- 2.20.1 In the AdvSIMD scalar x indexed element and vector x indexed element encoding group, the SDOT and UDOT instructions are vector only, and their opcode is unallocated in the scalar group. Correctly UNDEF this unallocated encoding. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190125182626.9221-8-peter.maydell@linaro.org --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_simd_indexed(DisasContext *s, uint32_t insn) break; case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ - if (size != MO_32 || !dc_isar_feature(aa64_dp, s)) { + if (is_scalar || size != MO_32 || !dc_isar_feature(aa64_dp, s)) { unallocated_encoding(s); return; } -- 2.20.1 The tcg_register_iommu_notifier() code has a GArray of TCGIOMMUNotifier structs which it has registered by passing memory_region_register_iommu_notifier() a pointer to the embedded IOMMUNotifier field. Unfortunately, if we need to enlarge the array via g_array_set_size() this can cause a realloc(), which invalidates the pointer that memory_region_register_iommu_notifier() put into the MemoryRegion's iommu_notify list. This can result in segfaults. Switch the GArray to holding pointers to the TCGIOMMUNotifier structs, so that we can individually allocate and free them. Cc: qemu-stable@nongnu.org Fixes: 1f871c5e6b0f30644a60a ("exec.c: Handle IOMMUs in address_space_translate_for_iotlb()") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128174241.5860-1-peter.maydell@linaro.org --- exec.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static void tcg_register_iommu_notifier(CPUState *cpu, int i; for (i = 0; i < cpu->iommu_notifiers->len; i++) { - notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i); if (notifier->mr == mr && notifier->iommu_idx == iommu_idx) { break; } @@ -XXX,XX +XXX,XX @@ static void tcg_register_iommu_notifier(CPUState *cpu, if (i == cpu->iommu_notifiers->len) { /* Not found, add a new entry at the end of the array */ cpu->iommu_notifiers = g_array_set_size(cpu->iommu_notifiers, i + 1); - notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + notifier = g_new0(TCGIOMMUNotifier, 1); + g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i) = notifier; notifier->mr = mr; notifier->iommu_idx = iommu_idx; @@ -XXX,XX +XXX,XX @@ static void tcg_iommu_free_notifier_list(CPUState *cpu) TCGIOMMUNotifier *notifier; for (i = 0; i < cpu->iommu_notifiers->len; i++) { - notifier = &g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier, i); + notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i); memory_region_unregister_iommu_notifier(notifier->mr, &notifier->n); + g_free(notifier); } g_array_free(cpu->iommu_notifiers, true); } @@ -XXX,XX +XXX,XX @@ void cpu_exec_realizefn(CPUState *cpu, Error **errp) vmstate_register(NULL, cpu->cpu_index, cc->vmsd, cpu); } - cpu->iommu_notifiers = g_array_new(false, true, sizeof(TCGIOMMUNotifier)); + cpu->iommu_notifiers = g_array_new(false, true, sizeof(TCGIOMMUNotifier *)); #endif } -- 2.20.1 The FCMLA (by element) instruction exists in the "vector x indexed element" encoding group, but not in the "scalar x indexed element" group. Correctly UNDEF the unallocated encodings. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190129140411.682-2-peter.maydell@linaro.org --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_simd_indexed(DisasContext *s, uint32_t insn) case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ case 0x17: /* FCMLA #270 */ - if (!dc_isar_feature(aa64_fcma, s)) { + if (is_scalar || !dc_isar_feature(aa64_fcma, s)) { unallocated_encoding(s); return; } -- 2.20.1 In disas_simd_indexed(), for the case of "complex fp", each indexable element is a complex pair, so the total size is twice that indicated in the 'size' field in the encoding. We were trying to do this "double the size" operation with a left shift by 1, but this is incorrect because the 'size' field is a MO_8/MO_16/MO_32/MO_64 value, and doubling the size should be done by a simple increment. This meant we were mishandling FCMLA (by element) of values where the real and imaginary parts are 32-bit floats, and would incorrectly UNDEF this encoding. (No other insns take this code path, and for 16-bit floats it happens that 1 << 1 and 1 + 1 are both the same). Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190129140411.682-3-peter.maydell@linaro.org --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_simd_indexed(DisasContext *s, uint32_t insn) case 2: /* complex fp */ /* Each indexable element is a complex pair. */ - size <<= 1; + size += 1; switch (size) { case MO_32: if (h && !is_q) { -- 2.20.1 From: Aaron Lindsay OS <aaron@os.amperecomputing.com> Whenever we notice that a counter overflow has occurred, send an interrupt. This is made more reliable with the addition of a timer in a follow-on commit. Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190124162401.5111-2-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 61 +++++++++++++++++++++++++++++++++++++-------- 1 file changed, 51 insertions(+), 10 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 @@ static const ARMCPRegInfo v6_cp_reginfo[] = { /* Definitions for the PMU registers */ #define PMCRN_MASK 0xf800 #define PMCRN_SHIFT 11 +#define PMCRLC 0x40 #define PMCRDP 0x10 #define PMCRD 0x8 #define PMCRC 0x4 @@ -XXX,XX +XXX,XX @@ static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) return enabled && !prohibited && !filtered; } +static void pmu_update_irq(CPUARMState *env) +{ + ARMCPU *cpu = arm_env_get_cpu(env); + qemu_set_irq(cpu->pmu_interrupt, (env->cp15.c9_pmcr & PMCRE) && + (env->cp15.c9_pminten & env->cp15.c9_pmovsr)); +} + /* * Ensure c15_ccnt is the guest-visible count so that operations such as * enabling/disabling the counter or filtering, modifying the count itself, @@ -XXX,XX +XXX,XX @@ void pmccntr_op_start(CPUARMState *env) eff_cycles /= 64; } - env->cp15.c15_ccnt = eff_cycles - env->cp15.c15_ccnt_delta; + uint64_t new_pmccntr = eff_cycles - env->cp15.c15_ccnt_delta; + + uint64_t overflow_mask = env->cp15.c9_pmcr & PMCRLC ? \ + 1ull << 63 : 1ull << 31; + if (env->cp15.c15_ccnt & ~new_pmccntr & overflow_mask) { + env->cp15.c9_pmovsr |= (1 << 31); + pmu_update_irq(env); + } + + env->cp15.c15_ccnt = new_pmccntr; } env->cp15.c15_ccnt_delta = cycles; } @@ -XXX,XX +XXX,XX @@ static void pmevcntr_op_start(CPUARMState *env, uint8_t counter) } if (pmu_counter_enabled(env, counter)) { - env->cp15.c14_pmevcntr[counter] = - count - env->cp15.c14_pmevcntr_delta[counter]; + uint32_t new_pmevcntr = count - env->cp15.c14_pmevcntr_delta[counter]; + + if (env->cp15.c14_pmevcntr[counter] & ~new_pmevcntr & INT32_MIN) { + env->cp15.c9_pmovsr |= (1 << counter); + pmu_update_irq(env); + } + env->cp15.c14_pmevcntr[counter] = new_pmevcntr; } env->cp15.c14_pmevcntr_delta[counter] = count; } @@ -XXX,XX +XXX,XX @@ static void pmswinc_write(CPUARMState *env, const ARMCPRegInfo *ri, /* counter is SW_INCR */ (env->cp15.c14_pmevtyper[i] & PMXEVTYPER_EVTCOUNT) == 0x0) { pmevcntr_op_start(env, i); - env->cp15.c14_pmevcntr[i]++; + + /* + * Detect if this write causes an overflow since we can't predict + * PMSWINC overflows like we can for other events + */ + uint32_t new_pmswinc = env->cp15.c14_pmevcntr[i] + 1; + + if (env->cp15.c14_pmevcntr[i] & ~new_pmswinc & INT32_MIN) { + env->cp15.c9_pmovsr |= (1 << i); + pmu_update_irq(env); + } + + env->cp15.c14_pmevcntr[i] = new_pmswinc; + pmevcntr_op_finish(env, i); } } @@ -XXX,XX +XXX,XX @@ static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri, { value &= pmu_counter_mask(env); env->cp15.c9_pmovsr &= ~value; + pmu_update_irq(env); } static void pmovsset_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void pmovsset_write(CPUARMState *env, const ARMCPRegInfo *ri, { value &= pmu_counter_mask(env); env->cp15.c9_pmovsr |= value; + pmu_update_irq(env); } static void pmevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void pmintenset_write(CPUARMState *env, const ARMCPRegInfo *ri, /* We have no event counters so only the C bit can be changed */ value &= pmu_counter_mask(env); env->cp15.c9_pminten |= value; + pmu_update_irq(env); } static void pmintenclr_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void pmintenclr_write(CPUARMState *env, const ARMCPRegInfo *ri, { value &= pmu_counter_mask(env); env->cp15.c9_pminten &= ~value; + pmu_update_irq(env); } static void vbar_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcnten), .writefn = pmcntenclr_write }, { .name = "PMOVSR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 3, - .access = PL0_RW, + .access = PL0_RW, .type = ARM_CP_IO, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmovsr), .accessfn = pmreg_access, .writefn = pmovsr_write, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { { .name = "PMOVSCLR_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 3, .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), .writefn = pmovsr_write, .raw_writefn = raw_write }, { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4, - .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW, + .access = PL0_W, .accessfn = pmreg_access_swinc, + .type = ARM_CP_NO_RAW | ARM_CP_IO, .writefn = pmswinc_write }, { .name = "PMSWINC_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 4, - .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW, + .access = PL0_W, .accessfn = pmreg_access_swinc, + .type = ARM_CP_NO_RAW | ARM_CP_IO, .writefn = pmswinc_write }, { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5, .access = PL0_RW, .type = ARM_CP_ALIAS, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo pmovsset_cp_reginfo[] = { /* PMOVSSET is not implemented in v7 before v7ve */ { .name = "PMOVSSET", .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 3, .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmovsr), .writefn = pmovsset_write, .raw_writefn = raw_write }, { .name = "PMOVSSET_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 14, .opc2 = 3, .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), .writefn = pmovsset_write, .raw_writefn = raw_write }, -- 2.20.1 From: Aaron Lindsay OS <aaron@os.amperecomputing.com> Make PMU overflow interrupts more accurate by using a timer to predict when they will overflow rather than waiting for an event to occur which allows us to otherwise check them. Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190124162401.5111-3-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 +++++++ target/arm/cpu.c | 12 ++++++++ target/arm/helper.c | 72 +++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 92 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { /* Timers used by the generic (architected) timer */ QEMUTimer *gt_timer[NUM_GTIMERS]; + /* + * Timer used by the PMU. Its state is restored after migration by + * pmu_op_finish() - it does not need other handling during migration + */ + QEMUTimer *pmu_timer; /* GPIO outputs for generic timer */ qemu_irq gt_timer_outputs[NUM_GTIMERS]; /* GPIO output for GICv3 maintenance interrupt signal */ @@ -XXX,XX +XXX,XX @@ void pmccntr_op_finish(CPUARMState *env); void pmu_op_start(CPUARMState *env); void pmu_op_finish(CPUARMState *env); +/* + * Called when a PMU counter is due to overflow + */ +void arm_pmu_timer_cb(void *opaque); + /** * Functions to register as EL change hooks for PMU mode filtering */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) QLIST_REMOVE(hook, node); g_free(hook); } +#ifndef CONFIG_USER_ONLY + if (cpu->pmu_timer) { + timer_del(cpu->pmu_timer); + timer_deinit(cpu->pmu_timer); + timer_free(cpu->pmu_timer); + } +#endif } static void arm_cpu_realizefn(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) arm_register_pre_el_change_hook(cpu, &pmu_pre_el_change, 0); arm_register_el_change_hook(cpu, &pmu_post_el_change, 0); } + +#ifndef CONFIG_USER_ONLY + cpu->pmu_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, arm_pmu_timer_cb, + cpu); +#endif } else { cpu->id_aa64dfr0 &= ~0xf00; cpu->pmceid0 = 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 @@ typedef struct pm_event { * counters hold a difference from the return value from this function */ uint64_t (*get_count)(CPUARMState *); + /* + * Return how many nanoseconds it will take (at a minimum) for count events + * to occur. A negative value indicates the counter will never overflow, or + * that the counter has otherwise arranged for the overflow bit to be set + * and the PMU interrupt to be raised on overflow. + */ + int64_t (*ns_per_count)(uint64_t); } pm_event; static bool event_always_supported(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ static uint64_t swinc_get_count(CPUARMState *env) return 0; } +static int64_t swinc_ns_per(uint64_t ignored) +{ + return -1; +} + /* * Return the underlying cycle count for the PMU cycle counters. If we're in * usermode, simply return 0. @@ -XXX,XX +XXX,XX @@ static uint64_t cycles_get_count(CPUARMState *env) } #ifndef CONFIG_USER_ONLY +static int64_t cycles_ns_per(uint64_t cycles) +{ + return (ARM_CPU_FREQ / NANOSECONDS_PER_SECOND) * cycles; +} + static bool instructions_supported(CPUARMState *env) { return use_icount == 1 /* Precise instruction counting */; @@ -XXX,XX +XXX,XX @@ static uint64_t instructions_get_count(CPUARMState *env) { return (uint64_t)cpu_get_icount_raw(); } + +static int64_t instructions_ns_per(uint64_t icount) +{ + return cpu_icount_to_ns((int64_t)icount); +} #endif static const pm_event pm_events[] = { { .number = 0x000, /* SW_INCR */ .supported = event_always_supported, .get_count = swinc_get_count, + .ns_per_count = swinc_ns_per, }, #ifndef CONFIG_USER_ONLY { .number = 0x008, /* INST_RETIRED, Instruction architecturally executed */ .supported = instructions_supported, .get_count = instructions_get_count, + .ns_per_count = instructions_ns_per, }, { .number = 0x011, /* CPU_CYCLES, Cycle */ .supported = event_always_supported, .get_count = cycles_get_count, + .ns_per_count = cycles_ns_per, } #endif }; @@ -XXX,XX +XXX,XX @@ void pmccntr_op_start(CPUARMState *env) void pmccntr_op_finish(CPUARMState *env) { if (pmu_counter_enabled(env, 31)) { - uint64_t prev_cycles = env->cp15.c15_ccnt_delta; +#ifndef CONFIG_USER_ONLY + /* Calculate when the counter will next overflow */ + uint64_t remaining_cycles = -env->cp15.c15_ccnt; + if (!(env->cp15.c9_pmcr & PMCRLC)) { + remaining_cycles = (uint32_t)remaining_cycles; + } + int64_t overflow_in = cycles_ns_per(remaining_cycles); + if (overflow_in > 0) { + int64_t overflow_at = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + + overflow_in; + ARMCPU *cpu = arm_env_get_cpu(env); + timer_mod_anticipate_ns(cpu->pmu_timer, overflow_at); + } +#endif + + uint64_t prev_cycles = env->cp15.c15_ccnt_delta; if (env->cp15.c9_pmcr & PMCRD) { /* Increment once every 64 processor clock cycles */ prev_cycles /= 64; } - env->cp15.c15_ccnt_delta = prev_cycles - env->cp15.c15_ccnt; } } @@ -XXX,XX +XXX,XX @@ static void pmevcntr_op_start(CPUARMState *env, uint8_t counter) static void pmevcntr_op_finish(CPUARMState *env, uint8_t counter) { if (pmu_counter_enabled(env, counter)) { +#ifndef CONFIG_USER_ONLY + uint16_t event = env->cp15.c14_pmevtyper[counter] & PMXEVTYPER_EVTCOUNT; + uint16_t event_idx = supported_event_map[event]; + uint64_t delta = UINT32_MAX - + (uint32_t)env->cp15.c14_pmevcntr[counter] + 1; + int64_t overflow_in = pm_events[event_idx].ns_per_count(delta); + + if (overflow_in > 0) { + int64_t overflow_at = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + + overflow_in; + ARMCPU *cpu = arm_env_get_cpu(env); + timer_mod_anticipate_ns(cpu->pmu_timer, overflow_at); + } +#endif + env->cp15.c14_pmevcntr_delta[counter] -= env->cp15.c14_pmevcntr[counter]; } @@ -XXX,XX +XXX,XX @@ void pmu_post_el_change(ARMCPU *cpu, void *ignored) pmu_op_finish(&cpu->env); } +void arm_pmu_timer_cb(void *opaque) +{ + ARMCPU *cpu = opaque; + + /* + * Update all the counter values based on the current underlying counts, + * triggering interrupts to be raised, if necessary. pmu_op_finish() also + * has the effect of setting the cpu->pmu_timer to the next earliest time a + * counter may expire. + */ + pmu_op_start(&cpu->env); + pmu_op_finish(&cpu->env); +} + static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These bits become writable with the ARMv8.3-PAuth extension. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190129143511.12311-1-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 | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) if (cpu_isar_feature(aa64_lor, cpu)) { valid_mask |= SCR_TLOR; } + if (cpu_isar_feature(aa64_pauth, cpu)) { + valid_mask |= SCR_API | SCR_APK; + } /* Clear all-context RES0 bits. */ value &= valid_mask; @@ -XXX,XX +XXX,XX @@ static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) if (cpu_isar_feature(aa64_lor, cpu)) { valid_mask |= HCR_TLOR; } + if (cpu_isar_feature(aa64_pauth, cpu)) { + valid_mask |= HCR_API | HCR_APK; + } /* Clear RES0 bits. */ value &= valid_mask; -- 2.20.1 From: Julia Suvorova <jusual@mail.ru> Until now, the set_pc logic was unclear, which raised questions about whether it should be used directly, applying a value to PC or adding additional checks, for example, set the Thumb bit in Arm cpu. Let's set the set_pc logic for “Configure the PC, as was done in the ELF file” and implement synchronize_with_tb hook for preserving PC to cpu_tb_exec. Signed-off-by: Julia Suvorova <jusual@mail.ru> Acked-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190129121817.7109-1-jusual@mail.ru Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/qom/cpu.h | 16 ++++++++++++++-- hw/arm/boot.c | 4 ---- target/arm/arm-powerctl.c | 3 --- target/arm/cpu.c | 26 +++++++++++++++++++++++++- target/arm/cpu64.c | 15 --------------- 5 files changed, 39 insertions(+), 25 deletions(-) diff --git a/include/qom/cpu.h b/include/qom/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -XXX,XX +XXX,XX @@ struct TranslationBlock; * @get_arch_id: Callback for getting architecture-dependent CPU ID. * @get_paging_enabled: Callback for inquiring whether paging is enabled. * @get_memory_mapping: Callback for obtaining the memory mappings. - * @set_pc: Callback for setting the Program Counter register. + * @set_pc: Callback for setting the Program Counter register. This + * should have the semantics used by the target architecture when + * setting the PC from a source such as an ELF file entry point; + * for example on Arm it will also set the Thumb mode bit based + * on the least significant bit of the new PC value. + * If the target behaviour here is anything other than "set + * the PC register to the value passed in" then the target must + * also implement the synchronize_from_tb hook. * @synchronize_from_tb: Callback for synchronizing state from a TCG - * #TranslationBlock. + * #TranslationBlock. This is called when we abandon execution + * of a TB before starting it, and must set all parts of the CPU + * state which the previous TB in the chain may not have updated. + * This always includes at least the program counter; some targets + * will need to do more. If this hook is not implemented then the + * default is to call @set_pc(tb->pc). * @handle_mmu_fault: Callback for handling an MMU fault. * @get_phys_page_debug: Callback for obtaining a physical address. * @get_phys_page_attrs_debug: Callback for obtaining a physical address and the diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) g_assert_not_reached(); } - if (!env->aarch64) { - env->thumb = info->entry & 1; - entry &= 0xfffffffe; - } cpu_set_pc(cs, entry); } else { /* If we are booting Linux then we need to check whether we are diff --git a/target/arm/arm-powerctl.c b/target/arm/arm-powerctl.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arm-powerctl.c +++ b/target/arm/arm-powerctl.c @@ -XXX,XX +XXX,XX @@ static void arm_set_cpu_on_async_work(CPUState *target_cpu_state, if (info->target_aa64) { target_cpu->env.xregs[0] = info->context_id; - target_cpu->env.thumb = false; } else { target_cpu->env.regs[0] = info->context_id; - target_cpu->env.thumb = info->entry & 1; - info->entry &= 0xfffffffe; } /* Start the new CPU at the requested address */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_pc(CPUState *cs, vaddr value) { ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; - cpu->env.regs[15] = value; + if (is_a64(env)) { + env->pc = value; + env->thumb = 0; + } else { + env->regs[15] = value & ~1; + env->thumb = value & 1; + } +} + +static void arm_cpu_synchronize_from_tb(CPUState *cs, TranslationBlock *tb) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + + /* + * It's OK to look at env for the current mode here, because it's + * never possible for an AArch64 TB to chain to an AArch32 TB. + */ + if (is_a64(env)) { + env->pc = tb->pc; + } else { + env->regs[15] = tb->pc; + } } static bool arm_cpu_has_work(CPUState *cs) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) cc->cpu_exec_interrupt = arm_cpu_exec_interrupt; cc->dump_state = arm_cpu_dump_state; cc->set_pc = arm_cpu_set_pc; + cc->synchronize_from_tb = arm_cpu_synchronize_from_tb; cc->gdb_read_register = arm_cpu_gdb_read_register; cc->gdb_write_register = arm_cpu_gdb_write_register; #ifdef CONFIG_USER_ONLY 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_cpu_finalizefn(Object *obj) { } -static void aarch64_cpu_set_pc(CPUState *cs, vaddr value) -{ - ARMCPU *cpu = ARM_CPU(cs); - /* It's OK to look at env for the current mode here, because it's - * never possible for an AArch64 TB to chain to an AArch32 TB. - * (Otherwise we would need to use synchronize_from_tb instead.) - */ - if (is_a64(&cpu->env)) { - cpu->env.pc = value; - } else { - cpu->env.regs[15] = value; - } -} - static gchar *aarch64_gdb_arch_name(CPUState *cs) { return g_strdup("aarch64"); @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_class_init(ObjectClass *oc, void *data) CPUClass *cc = CPU_CLASS(oc); cc->cpu_exec_interrupt = arm_cpu_exec_interrupt; - cc->set_pc = aarch64_cpu_set_pc; cc->gdb_read_register = aarch64_cpu_gdb_read_register; cc->gdb_write_register = aarch64_cpu_gdb_write_register; cc->gdb_num_core_regs = 34; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Drop the pac properties. This approach cannot work as written because the properties are applied before arm_cpu_reset, which zeros SCTLR_EL1 (amongst everything else). We can re-introduce the properties if they turn out to be useful. But since linux 5.0 enables all of the keys, they may not be. Fixes: 1ae9cfbd470 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 3 +++ target/arm/cpu64.c | 60 ---------------------------------------------- 2 files changed, 3 insertions(+), 60 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) env->pstate = PSTATE_MODE_EL0t; /* Userspace expects access to DC ZVA, CTL_EL0 and the cache ops */ env->cp15.sctlr_el[1] |= SCTLR_UCT | SCTLR_UCI | SCTLR_DZE; + /* Enable all PAC keys. */ + env->cp15.sctlr_el[1] |= (SCTLR_EnIA | SCTLR_EnIB | + SCTLR_EnDA | SCTLR_EnDB); /* Enable all PAC instructions */ env->cp15.hcr_el2 |= HCR_API; env->cp15.scr_el3 |= SCR_API; 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 cpu_max_set_sve_vq(Object *obj, Visitor *v, const char *name, error_propagate(errp, err); } -#ifdef CONFIG_USER_ONLY -static void cpu_max_get_packey(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - const uint64_t *bit = opaque; - bool enabled = (cpu->env.cp15.sctlr_el[1] & *bit) != 0; - - visit_type_bool(v, name, &enabled, errp); -} - -static void cpu_max_set_packey(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - Error *err = NULL; - const uint64_t *bit = opaque; - bool enabled; - - visit_type_bool(v, name, &enabled, errp); - - if (!err) { - if (enabled) { - cpu->env.cp15.sctlr_el[1] |= *bit; - } else { - cpu->env.cp15.sctlr_el[1] &= ~*bit; - } - } - error_propagate(errp, err); -} -#endif - /* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); * otherwise, a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu.c; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) */ cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ cpu->dcz_blocksize = 7; /* 512 bytes */ - - /* - * Note that Linux will enable enable all of the keys at once. - * But doing it this way will allow experimentation beyond that. - */ - { - static const uint64_t apia_bit = SCTLR_EnIA; - static const uint64_t apib_bit = SCTLR_EnIB; - static const uint64_t apda_bit = SCTLR_EnDA; - static const uint64_t apdb_bit = SCTLR_EnDB; - - object_property_add(obj, "apia", "bool", cpu_max_get_packey, - cpu_max_set_packey, NULL, - (void *)&apia_bit, &error_fatal); - object_property_add(obj, "apib", "bool", cpu_max_get_packey, - cpu_max_set_packey, NULL, - (void *)&apib_bit, &error_fatal); - object_property_add(obj, "apda", "bool", cpu_max_get_packey, - cpu_max_set_packey, NULL, - (void *)&apda_bit, &error_fatal); - object_property_add(obj, "apdb", "bool", cpu_max_get_packey, - cpu_max_set_packey, NULL, - (void *)&apdb_bit, &error_fatal); - - /* Enable all PAC keys by default. */ - cpu->env.cp15.sctlr_el[1] |= SCTLR_EnIA | SCTLR_EnIB; - cpu->env.cp15.sctlr_el[1] |= SCTLR_EnDA | SCTLR_EnDB; - } #endif cpu->sve_max_vq = ARM_MAX_VQ; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP_A64_ASIMDDP = 1 << 20, ARM_HWCAP_A64_SHA512 = 1 << 21, ARM_HWCAP_A64_SVE = 1 << 22, + ARM_HWCAP_A64_ASIMDFHM = 1 << 23, + ARM_HWCAP_A64_DIT = 1 << 24, + ARM_HWCAP_A64_USCAT = 1 << 25, + ARM_HWCAP_A64_ILRCPC = 1 << 26, + ARM_HWCAP_A64_FLAGM = 1 << 27, + ARM_HWCAP_A64_SSBS = 1 << 28, + ARM_HWCAP_A64_SB = 1 << 29, + ARM_HWCAP_A64_PACA = 1 << 30, + ARM_HWCAP_A64_PACG = 1UL << 31, }; #define ELF_HWCAP get_elf_hwcap() -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 1 + 1 file changed, 1 insertion(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); GET_FEATURE_ID(aa64_sve, ARM_HWCAP_A64_SVE); + GET_FEATURE_ID(aa64_pauth, ARM_HWCAP_A64_PACA | ARM_HWCAP_A64_PACG); #undef GET_FEATURE_ID -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Initialize the keys to a non-zero value on process start. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_syscall.h | 2 ++ linux-user/aarch64/cpu_loop.c | 31 +++++++++++++++++++++++++++-- 2 files changed, 31 insertions(+), 2 deletions(-) diff --git a/linux-user/aarch64/target_syscall.h b/linux-user/aarch64/target_syscall.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_syscall.h +++ b/linux-user/aarch64/target_syscall.h @@ -XXX,XX +XXX,XX @@ struct target_pt_regs { #define TARGET_PR_SVE_SET_VL 50 #define TARGET_PR_SVE_GET_VL 51 +void arm_init_pauth_key(ARMPACKey *key); + #endif /* AARCH64_TARGET_SYSCALL_H */ diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ void cpu_loop(CPUARMState *env) } } +static uint64_t arm_rand64(void) +{ + int shift = 64 - clz64(RAND_MAX); + int i, n = 64 / shift + (64 % shift != 0); + uint64_t ret = 0; + + for (i = 0; i < n; i++) { + ret = (ret << shift) | rand(); + } + return ret; +} + +void arm_init_pauth_key(ARMPACKey *key) +{ + key->lo = arm_rand64(); + key->hi = arm_rand64(); +} + void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs) { - CPUState *cpu = ENV_GET_CPU(env); - TaskState *ts = cpu->opaque; + ARMCPU *cpu = arm_env_get_cpu(env); + CPUState *cs = CPU(cpu); + TaskState *ts = cs->opaque; struct image_info *info = ts->info; int i; @@ -XXX,XX +XXX,XX @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs) } #endif + if (cpu_isar_feature(aa64_pauth, cpu)) { + arm_init_pauth_key(&env->apia_key); + arm_init_pauth_key(&env->apib_key); + arm_init_pauth_key(&env->apda_key); + arm_init_pauth_key(&env->apdb_key); + arm_init_pauth_key(&env->apga_key); + } + ts->stack_base = info->start_stack; ts->heap_base = info->brk; /* This will be filled in on the first SYS_HEAPINFO call. */ -- 2.20.1 From: Remi Denis-Courmont <remi.denis.courmont@huawei.com> Since QEMU does not support the ARMv8.2-LVA, Large Virtual Address, extension (yet), the VA address space is 48-bits plus a sign bit. User mode can only handle the positive half of the address space, so that makes a limit of 48 bits. (With LVA, it would be 53 and 52 bits respectively.) The incorrectly large address space conflicts with PAuth instructions, which use bits 48-54 and 56-63 for the pointer authentication code. This also conflicts with (as yet unsupported by QEMU) data tagging and with the ARMv8.5-MTE extension. Signed-off-by: Remi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 @@ bool write_cpustate_to_list(ARMCPU *cpu); #if defined(TARGET_AARCH64) # define TARGET_PHYS_ADDR_SPACE_BITS 48 -# define TARGET_VIRT_ADDR_SPACE_BITS 64 +# define TARGET_VIRT_ADDR_SPACE_BITS 48 #else # define TARGET_PHYS_ADDR_SPACE_BITS 40 # define TARGET_VIRT_ADDR_SPACE_BITS 32 -- 2.20.1 From: Remi Denis-Courmont <remi.denis.courmont@huawei.com> A flawed test lead to the instructions always being treated as unallocated encodings. Fixes: https://bugs.launchpad.net/bugs/1813460 Signed-off-by: Remi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_uncond_b_reg(DisasContext *s, uint32_t insn) if (!dc_isar_feature(aa64_pauth, s)) { goto do_unallocated; } - if (op3 != 2 || op3 != 3) { + if ((op3 & ~1) != 2) { goto do_unallocated; } if (s->pauth_active) { -- 2.20.1 From: Steffen Görtz <contrib@steffen-goertz.de> The nRF51 contains three regions of non-volatile memory (NVM): - CODE (R/W): contains code - FICR (R): Factory information like code size, chip id etc. - UICR (R/W): Changeable configuration data. Lock bits, Code protection configuration, Bootloader address, Nordic SoftRadio configuration, Firmware configuration. Read and write access to the memories is managed by the Non-volatile memory controller. Memory schema: [ CPU ] -+- [ NVM, either FICR, UICR or CODE ] | | \- [ NVMC ] Signed-off-by: Steffen Görtz <contrib@steffen-goertz.de> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Tested-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190201023357.22596-2-stefanha@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/nvram/Makefile.objs | 1 + include/hw/nvram/nrf51_nvm.h | 64 ++++++ hw/nvram/nrf51_nvm.c | 388 +++++++++++++++++++++++++++++++++++ 3 files changed, 453 insertions(+) create mode 100644 include/hw/nvram/nrf51_nvm.h create mode 100644 hw/nvram/nrf51_nvm.c diff --git a/hw/nvram/Makefile.objs b/hw/nvram/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/Makefile.objs +++ b/hw/nvram/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += fw_cfg.o common-obj-y += chrp_nvram.o common-obj-$(CONFIG_MAC_NVRAM) += mac_nvram.o obj-$(CONFIG_PSERIES) += spapr_nvram.o +obj-$(CONFIG_NRF51_SOC) += nrf51_nvm.o diff --git a/include/hw/nvram/nrf51_nvm.h b/include/hw/nvram/nrf51_nvm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/nvram/nrf51_nvm.h @@ -XXX,XX +XXX,XX @@ +/* + * Nordic Semiconductor nRF51 non-volatile memory + * + * It provides an interface to erase regions in flash memory. + * Furthermore it provides the user and factory information registers. + * + * QEMU interface: + * + sysbus MMIO regions 0: NVMC peripheral registers + * + sysbus MMIO regions 1: FICR peripheral registers + * + sysbus MMIO regions 2: UICR peripheral registers + * + flash-size property: flash size in bytes. + * + * Accuracy of the peripheral model: + * + Code regions (MPU configuration) are disregarded. + * + * Copyright 2018 Steffen Görtz <contrib@steffen-goertz.de> + * + * This code is licensed under the GPL version 2 or later. See + * the COPYING file in the top-level directory. + * + */ +#ifndef NRF51_NVM_H +#define NRF51_NVM_H + +#include "hw/sysbus.h" +#define TYPE_NRF51_NVM "nrf51_soc.nvm" +#define NRF51_NVM(obj) OBJECT_CHECK(NRF51NVMState, (obj), TYPE_NRF51_NVM) + +#define NRF51_UICR_FIXTURE_SIZE 64 + +#define NRF51_NVMC_SIZE 0x1000 + +#define NRF51_NVMC_READY 0x400 +#define NRF51_NVMC_READY_READY 0x01 +#define NRF51_NVMC_CONFIG 0x504 +#define NRF51_NVMC_CONFIG_MASK 0x03 +#define NRF51_NVMC_CONFIG_WEN 0x01 +#define NRF51_NVMC_CONFIG_EEN 0x02 +#define NRF51_NVMC_ERASEPCR1 0x508 +#define NRF51_NVMC_ERASEPCR0 0x510 +#define NRF51_NVMC_ERASEALL 0x50C +#define NRF51_NVMC_ERASEUICR 0x514 +#define NRF51_NVMC_ERASE 0x01 + +#define NRF51_UICR_SIZE 0x100 + +typedef struct NRF51NVMState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + MemoryRegion ficr; + MemoryRegion uicr; + MemoryRegion flash; + + uint32_t uicr_content[NRF51_UICR_FIXTURE_SIZE]; + uint32_t flash_size; + uint8_t *storage; + + uint32_t config; + +} NRF51NVMState; + + +#endif diff --git a/hw/nvram/nrf51_nvm.c b/hw/nvram/nrf51_nvm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/nvram/nrf51_nvm.c @@ -XXX,XX +XXX,XX @@ +/* + * Nordic Semiconductor nRF51 non-volatile memory + * + * It provides an interface to erase regions in flash memory. + * Furthermore it provides the user and factory information registers. + * + * Reference Manual: http://infocenter.nordicsemi.com/pdf/nRF51_RM_v3.0.pdf + * + * See nRF51 reference manual and product sheet sections: + * + Non-Volatile Memory Controller (NVMC) + * + Factory Information Configuration Registers (FICR) + * + User Information Configuration Registers (UICR) + * + * Copyright 2018 Steffen Görtz <contrib@steffen-goertz.de> + * + * This code is licensed under the GPL version 2 or later. See + * the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/log.h" +#include "exec/address-spaces.h" +#include "hw/arm/nrf51.h" +#include "hw/nvram/nrf51_nvm.h" + +/* + * FICR Registers Assignments + * CODEPAGESIZE 0x010 + * CODESIZE 0x014 + * CLENR0 0x028 + * PPFC 0x02C + * NUMRAMBLOCK 0x034 + * SIZERAMBLOCKS 0x038 + * SIZERAMBLOCK[0] 0x038 + * SIZERAMBLOCK[1] 0x03C + * SIZERAMBLOCK[2] 0x040 + * SIZERAMBLOCK[3] 0x044 + * CONFIGID 0x05C + * DEVICEID[0] 0x060 + * DEVICEID[1] 0x064 + * ER[0] 0x080 + * ER[1] 0x084 + * ER[2] 0x088 + * ER[3] 0x08C + * IR[0] 0x090 + * IR[1] 0x094 + * IR[2] 0x098 + * IR[3] 0x09C + * DEVICEADDRTYPE 0x0A0 + * DEVICEADDR[0] 0x0A4 + * DEVICEADDR[1] 0x0A8 + * OVERRIDEEN 0x0AC + * NRF_1MBIT[0] 0x0B0 + * NRF_1MBIT[1] 0x0B4 + * NRF_1MBIT[2] 0x0B8 + * NRF_1MBIT[3] 0x0BC + * NRF_1MBIT[4] 0x0C0 + * BLE_1MBIT[0] 0x0EC + * BLE_1MBIT[1] 0x0F0 + * BLE_1MBIT[2] 0x0F4 + * BLE_1MBIT[3] 0x0F8 + * BLE_1MBIT[4] 0x0FC + */ +static const uint32_t ficr_content[64] = { + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000400, + 0x00000100, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000002, 0x00002000, + 0x00002000, 0x00002000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000003, + 0x12345678, 0x9ABCDEF1, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF +}; + +static uint64_t ficr_read(void *opaque, hwaddr offset, unsigned int size) +{ + assert(offset < sizeof(ficr_content)); + return ficr_content[offset / 4]; +} + +static void ficr_write(void *opaque, hwaddr offset, uint64_t value, + unsigned int size) +{ + /* Intentionally do nothing */ +} + +static const MemoryRegionOps ficr_ops = { + .read = ficr_read, + .write = ficr_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN +}; + +/* + * UICR Registers Assignments + * CLENR0 0x000 + * RBPCONF 0x004 + * XTALFREQ 0x008 + * FWID 0x010 + * BOOTLOADERADDR 0x014 + * NRFFW[0] 0x014 + * NRFFW[1] 0x018 + * NRFFW[2] 0x01C + * NRFFW[3] 0x020 + * NRFFW[4] 0x024 + * NRFFW[5] 0x028 + * NRFFW[6] 0x02C + * NRFFW[7] 0x030 + * NRFFW[8] 0x034 + * NRFFW[9] 0x038 + * NRFFW[10] 0x03C + * NRFFW[11] 0x040 + * NRFFW[12] 0x044 + * NRFFW[13] 0x048 + * NRFFW[14] 0x04C + * NRFHW[0] 0x050 + * NRFHW[1] 0x054 + * NRFHW[2] 0x058 + * NRFHW[3] 0x05C + * NRFHW[4] 0x060 + * NRFHW[5] 0x064 + * NRFHW[6] 0x068 + * NRFHW[7] 0x06C + * NRFHW[8] 0x070 + * NRFHW[9] 0x074 + * NRFHW[10] 0x078 + * NRFHW[11] 0x07C + * CUSTOMER[0] 0x080 + * CUSTOMER[1] 0x084 + * CUSTOMER[2] 0x088 + * CUSTOMER[3] 0x08C + * CUSTOMER[4] 0x090 + * CUSTOMER[5] 0x094 + * CUSTOMER[6] 0x098 + * CUSTOMER[7] 0x09C + * CUSTOMER[8] 0x0A0 + * CUSTOMER[9] 0x0A4 + * CUSTOMER[10] 0x0A8 + * CUSTOMER[11] 0x0AC + * CUSTOMER[12] 0x0B0 + * CUSTOMER[13] 0x0B4 + * CUSTOMER[14] 0x0B8 + * CUSTOMER[15] 0x0BC + * CUSTOMER[16] 0x0C0 + * CUSTOMER[17] 0x0C4 + * CUSTOMER[18] 0x0C8 + * CUSTOMER[19] 0x0CC + * CUSTOMER[20] 0x0D0 + * CUSTOMER[21] 0x0D4 + * CUSTOMER[22] 0x0D8 + * CUSTOMER[23] 0x0DC + * CUSTOMER[24] 0x0E0 + * CUSTOMER[25] 0x0E4 + * CUSTOMER[26] 0x0E8 + * CUSTOMER[27] 0x0EC + * CUSTOMER[28] 0x0F0 + * CUSTOMER[29] 0x0F4 + * CUSTOMER[30] 0x0F8 + * CUSTOMER[31] 0x0FC + */ + +static uint64_t uicr_read(void *opaque, hwaddr offset, unsigned int size) +{ + NRF51NVMState *s = NRF51_NVM(opaque); + + assert(offset < sizeof(s->uicr_content)); + return s->uicr_content[offset / 4]; +} + +static void uicr_write(void *opaque, hwaddr offset, uint64_t value, + unsigned int size) +{ + NRF51NVMState *s = NRF51_NVM(opaque); + + assert(offset < sizeof(s->uicr_content)); + s->uicr_content[offset / 4] = value; +} + +static const MemoryRegionOps uicr_ops = { + .read = uicr_read, + .write = uicr_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN +}; + + +static uint64_t io_read(void *opaque, hwaddr offset, unsigned int size) +{ + NRF51NVMState *s = NRF51_NVM(opaque); + uint64_t r = 0; + + switch (offset) { + case NRF51_NVMC_READY: + r = NRF51_NVMC_READY_READY; + break; + case NRF51_NVMC_CONFIG: + r = s->config; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: bad read offset 0x%" HWADDR_PRIx "\n", __func__, offset); + break; + } + + return r; +} + +static void io_write(void *opaque, hwaddr offset, uint64_t value, + unsigned int size) +{ + NRF51NVMState *s = NRF51_NVM(opaque); + + switch (offset) { + case NRF51_NVMC_CONFIG: + s->config = value & NRF51_NVMC_CONFIG_MASK; + break; + case NRF51_NVMC_ERASEPCR0: + case NRF51_NVMC_ERASEPCR1: + if (s->config & NRF51_NVMC_CONFIG_EEN) { + /* Mask in-page sub address */ + value &= ~(NRF51_PAGE_SIZE - 1); + if (value <= (s->flash_size - NRF51_PAGE_SIZE)) { + memset(s->storage + value, 0xFF, NRF51_PAGE_SIZE); + memory_region_flush_rom_device(&s->flash, value, + NRF51_PAGE_SIZE); + } + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Flash erase at 0x%" HWADDR_PRIx" while flash not erasable.\n", + __func__, offset); + } + break; + case NRF51_NVMC_ERASEALL: + if (value == NRF51_NVMC_ERASE) { + if (s->config & NRF51_NVMC_CONFIG_EEN) { + memset(s->storage, 0xFF, s->flash_size); + memory_region_flush_rom_device(&s->flash, 0, s->flash_size); + memset(s->uicr_content, 0xFF, sizeof(s->uicr_content)); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Flash not erasable.\n", + __func__); + } + } + break; + case NRF51_NVMC_ERASEUICR: + if (value == NRF51_NVMC_ERASE) { + memset(s->uicr_content, 0xFF, sizeof(s->uicr_content)); + } + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: bad write offset 0x%" HWADDR_PRIx "\n", __func__, offset); + } +} + +static const MemoryRegionOps io_ops = { + .read = io_read, + .write = io_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + + +static void flash_write(void *opaque, hwaddr offset, uint64_t value, + unsigned int size) +{ + NRF51NVMState *s = NRF51_NVM(opaque); + + if (s->config & NRF51_NVMC_CONFIG_WEN) { + uint32_t oldval; + + assert(offset + size <= s->flash_size); + + /* NOR Flash only allows bits to be flipped from 1's to 0's on write */ + oldval = ldl_le_p(s->storage + offset); + oldval &= value; + stl_le_p(s->storage + offset, oldval); + + memory_region_flush_rom_device(&s->flash, offset, size); + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Flash write 0x%" HWADDR_PRIx" while flash not writable.\n", + __func__, offset); + } +} + + + +static const MemoryRegionOps flash_ops = { + .write = flash_write, + .valid.min_access_size = 4, + .valid.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void nrf51_nvm_init(Object *obj) +{ + NRF51NVMState *s = NRF51_NVM(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->mmio, obj, &io_ops, s, "nrf51_soc.nvmc", + NRF51_NVMC_SIZE); + sysbus_init_mmio(sbd, &s->mmio); + + memory_region_init_io(&s->ficr, obj, &ficr_ops, s, "nrf51_soc.ficr", + sizeof(ficr_content)); + sysbus_init_mmio(sbd, &s->ficr); + + memory_region_init_io(&s->uicr, obj, &uicr_ops, s, "nrf51_soc.uicr", + sizeof(s->uicr_content)); + sysbus_init_mmio(sbd, &s->uicr); +} + +static void nrf51_nvm_realize(DeviceState *dev, Error **errp) +{ + NRF51NVMState *s = NRF51_NVM(dev); + Error *err = NULL; + + memory_region_init_rom_device(&s->flash, OBJECT(dev), &flash_ops, s, + "nrf51_soc.flash", s->flash_size, &err); + if (err) { + error_propagate(errp, err); + return; + } + + s->storage = memory_region_get_ram_ptr(&s->flash); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->flash); +} + +static void nrf51_nvm_reset(DeviceState *dev) +{ + NRF51NVMState *s = NRF51_NVM(dev); + + s->config = 0x00; + memset(s->uicr_content, 0xFF, sizeof(s->uicr_content)); +} + +static Property nrf51_nvm_properties[] = { + DEFINE_PROP_UINT32("flash-size", NRF51NVMState, flash_size, 0x40000), + DEFINE_PROP_END_OF_LIST(), +}; + +static const VMStateDescription vmstate_nvm = { + .name = "nrf51_soc.nvm", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(uicr_content, NRF51NVMState, + NRF51_UICR_FIXTURE_SIZE), + VMSTATE_UINT32(config, NRF51NVMState), + VMSTATE_END_OF_LIST() + } +}; + +static void nrf51_nvm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->props = nrf51_nvm_properties; + dc->vmsd = &vmstate_nvm; + dc->realize = nrf51_nvm_realize; + dc->reset = nrf51_nvm_reset; +} + +static const TypeInfo nrf51_nvm_info = { + .name = TYPE_NRF51_NVM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NRF51NVMState), + .instance_init = nrf51_nvm_init, + .class_init = nrf51_nvm_class_init +}; + +static void nrf51_nvm_register_types(void) +{ + type_register_static(&nrf51_nvm_info); +} + +type_init(nrf51_nvm_register_types) -- 2.20.1 From: Steffen Görtz <contrib@steffen-goertz.de> Instantiates UICR, FICR, FLASH and NVMC in nRF51 SOC. Signed-off-by: Steffen Görtz <contrib@steffen-goertz.de> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190201023357.22596-3-stefanha@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/nrf51_soc.h | 2 ++ hw/arm/nrf51_soc.c | 41 +++++++++++++++++++++++++++----------- 2 files changed, 31 insertions(+), 12 deletions(-) diff --git a/include/hw/arm/nrf51_soc.h b/include/hw/arm/nrf51_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/nrf51_soc.h +++ b/include/hw/arm/nrf51_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/char/nrf51_uart.h" #include "hw/misc/nrf51_rng.h" #include "hw/gpio/nrf51_gpio.h" +#include "hw/nvram/nrf51_nvm.h" #include "hw/timer/nrf51_timer.h" #define TYPE_NRF51_SOC "nrf51-soc" @@ -XXX,XX +XXX,XX @@ typedef struct NRF51State { NRF51UARTState uart; NRF51RNGState rng; + NRF51NVMState nvm; NRF51GPIOState gpio; NRF51TimerState timer[NRF51_NUM_TIMERS]; diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -XXX,XX +XXX,XX @@ * are supported in the future, add a sub-class of NRF51SoC for * the specific variants */ -#define NRF51822_FLASH_SIZE (256 * NRF51_PAGE_SIZE) -#define NRF51822_SRAM_SIZE (16 * NRF51_PAGE_SIZE) +#define NRF51822_FLASH_PAGES 256 +#define NRF51822_SRAM_PAGES 16 +#define NRF51822_FLASH_SIZE (NRF51822_FLASH_PAGES * NRF51_PAGE_SIZE) +#define NRF51822_SRAM_SIZE (NRF51822_SRAM_PAGES * NRF51_PAGE_SIZE) #define BASE_TO_IRQ(base) ((base >> 12) & 0x1F) @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1); - memory_region_init_rom(&s->flash, OBJECT(s), "nrf51.flash", s->flash_size, - &err); - if (err) { - error_propagate(errp, err); - return; - } - memory_region_add_subregion(&s->container, NRF51_FLASH_BASE, &s->flash); - memory_region_init_ram(&s->sram, OBJECT(s), "nrf51.sram", s->sram_size, &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) qdev_get_gpio_in(DEVICE(&s->cpu), BASE_TO_IRQ(NRF51_RNG_BASE))); + /* UICR, FICR, NVMC, FLASH */ + object_property_set_uint(OBJECT(&s->nvm), s->flash_size, "flash-size", + &err); + if (err) { + error_propagate(errp, err); + return; + } + + object_property_set_bool(OBJECT(&s->nvm), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->nvm), 0); + memory_region_add_subregion_overlap(&s->container, NRF51_NVMC_BASE, mr, 0); + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->nvm), 1); + memory_region_add_subregion_overlap(&s->container, NRF51_FICR_BASE, mr, 0); + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->nvm), 2); + memory_region_add_subregion_overlap(&s->container, NRF51_UICR_BASE, mr, 0); + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->nvm), 3); + memory_region_add_subregion_overlap(&s->container, NRF51_FLASH_BASE, mr, 0); + /* GPIO */ object_property_set_bool(OBJECT(&s->gpio), true, "realized", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("nrf51_soc.io", NRF51_IOMEM_BASE, NRF51_IOMEM_SIZE); - create_unimplemented_device("nrf51_soc.ficr", NRF51_FICR_BASE, - NRF51_FICR_SIZE); create_unimplemented_device("nrf51_soc.private", NRF51_PRIVATE_BASE, NRF51_PRIVATE_SIZE); } @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_init(Object *obj) sysbus_init_child_obj(obj, "rng", &s->rng, sizeof(s->rng), TYPE_NRF51_RNG); + sysbus_init_child_obj(obj, "nvm", &s->nvm, sizeof(s->nvm), TYPE_NRF51_NVM); + sysbus_init_child_obj(obj, "gpio", &s->gpio, sizeof(s->gpio), TYPE_NRF51_GPIO); -- 2.20.1 From: Steffen Görtz <contrib@steffen-goertz.de> Signed-off-by: Steffen Görtz <contrib@steffen-goertz.de> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190201023357.22596-4-stefanha@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/microbit-test.c | 108 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 108 insertions(+) diff --git a/tests/microbit-test.c b/tests/microbit-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/microbit-test.c +++ b/tests/microbit-test.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/nrf51.h" #include "hw/char/nrf51_uart.h" #include "hw/gpio/nrf51_gpio.h" +#include "hw/nvram/nrf51_nvm.h" #include "hw/timer/nrf51_timer.h" #include "hw/i2c/microbit_i2c.h" @@ -XXX,XX +XXX,XX @@ static void test_microbit_i2c(void) qtest_quit(qts); } +#define FLASH_SIZE (256 * NRF51_PAGE_SIZE) + +static void fill_and_erase(QTestState *qts, hwaddr base, hwaddr size, + uint32_t address_reg) +{ + hwaddr i; + + /* Erase Page */ + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x02); + qtest_writel(qts, NRF51_NVMC_BASE + address_reg, base); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + /* Check memory */ + for (i = 0; i < size / 4; i++) { + g_assert_cmpuint(qtest_readl(qts, base + i * 4), ==, 0xFFFFFFFF); + } + + /* Fill memory */ + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x01); + for (i = 0; i < size / 4; i++) { + qtest_writel(qts, base + i * 4, i); + g_assert_cmpuint(qtest_readl(qts, base + i * 4), ==, i); + } + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); +} + +static void test_nrf51_nvmc(void) +{ + uint32_t value; + hwaddr i; + QTestState *qts = qtest_init("-M microbit"); + + /* Test always ready */ + value = qtest_readl(qts, NRF51_NVMC_BASE + NRF51_NVMC_READY); + g_assert_cmpuint(value & 0x01, ==, 0x01); + + /* Test write-read config register */ + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x03); + g_assert_cmpuint(qtest_readl(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG), + ==, 0x03); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + g_assert_cmpuint(qtest_readl(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG), + ==, 0x00); + + /* Test PCR0 */ + fill_and_erase(qts, NRF51_FLASH_BASE, NRF51_PAGE_SIZE, + NRF51_NVMC_ERASEPCR0); + fill_and_erase(qts, NRF51_FLASH_BASE + NRF51_PAGE_SIZE, + NRF51_PAGE_SIZE, NRF51_NVMC_ERASEPCR0); + + /* Test PCR1 */ + fill_and_erase(qts, NRF51_FLASH_BASE, NRF51_PAGE_SIZE, + NRF51_NVMC_ERASEPCR1); + fill_and_erase(qts, NRF51_FLASH_BASE + NRF51_PAGE_SIZE, + NRF51_PAGE_SIZE, NRF51_NVMC_ERASEPCR1); + + /* Erase all */ + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x02); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_ERASEALL, 0x01); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x01); + for (i = 0; i < FLASH_SIZE / 4; i++) { + qtest_writel(qts, NRF51_FLASH_BASE + i * 4, i); + g_assert_cmpuint(qtest_readl(qts, NRF51_FLASH_BASE + i * 4), ==, i); + } + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x02); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_ERASEALL, 0x01); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + for (i = 0; i < FLASH_SIZE / 4; i++) { + g_assert_cmpuint(qtest_readl(qts, NRF51_FLASH_BASE + i * 4), + ==, 0xFFFFFFFF); + } + + /* Erase UICR */ + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x02); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_ERASEUICR, 0x01); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + for (i = 0; i < NRF51_UICR_SIZE / 4; i++) { + g_assert_cmpuint(qtest_readl(qts, NRF51_UICR_BASE + i * 4), + ==, 0xFFFFFFFF); + } + + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x01); + for (i = 0; i < NRF51_UICR_SIZE / 4; i++) { + qtest_writel(qts, NRF51_UICR_BASE + i * 4, i); + g_assert_cmpuint(qtest_readl(qts, NRF51_UICR_BASE + i * 4), ==, i); + } + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x02); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_ERASEUICR, 0x01); + qtest_writel(qts, NRF51_NVMC_BASE + NRF51_NVMC_CONFIG, 0x00); + + for (i = 0; i < NRF51_UICR_SIZE / 4; i++) { + g_assert_cmpuint(qtest_readl(qts, NRF51_UICR_BASE + i * 4), + ==, 0xFFFFFFFF); + } + + qtest_quit(qts); +} + static void test_nrf51_gpio(void) { size_t i; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) qtest_add_func("/microbit/nrf51/uart", test_nrf51_uart); qtest_add_func("/microbit/nrf51/gpio", test_nrf51_gpio); + qtest_add_func("/microbit/nrf51/nvmc", test_nrf51_nvmc); qtest_add_func("/microbit/nrf51/timer", test_nrf51_timer); qtest_add_func("/microbit/microbit/i2c", test_microbit_i2c); -- 2.20.1