First arm pullreq of 4.2... thanks -- PMM The following changes since commit 27608c7c66bd923eb5e5faab80e795408cbe2b51: Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20190814a' into staging (2019-08-16 12:00:18 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190816 for you to fetch changes up to 664b7e3b97d6376f3329986c465b3782458b0f8b: target/arm: Use tcg_gen_extrh_i64_i32 to extract the high word (2019-08-16 14:02:53 +0100) ---------------------------------------------------------------- target-arm queue: * target/arm: generate a custom MIDR for -cpu max * hw/misc/zynq_slcr: refactor to use standard register definition * Set ENET_BD_BDU in I.MX FEC controller * target/arm: Fix routing of singlestep exceptions * refactor a32/t32 decoder handling of PC * minor optimisations/cleanups of some a32/t32 codegen * target/arm/cpu64: Ensure kvm really supports aarch64=off * target/arm/cpu: Ensure we can use the pmu with kvm * target/arm: Minor cleanups preparatory to KVM SVE support ---------------------------------------------------------------- Aaron Hill (1): Set ENET_BD_BDU in I.MX FEC controller Alex Bennée (1): target/arm: generate a custom MIDR for -cpu max Andrew Jones (6): target/arm/cpu64: Ensure kvm really supports aarch64=off target/arm/cpu: Ensure we can use the pmu with kvm target/arm/helper: zcr: Add build bug next to value range assumption target/arm/cpu: Use div-round-up to determine predicate register array size target/arm/kvm64: Fix error returns target/arm/kvm64: Move the get/put of fpsimd registers out Damien Hedde (1): hw/misc/zynq_slcr: use standard register definition Peter Maydell (2): target/arm: Factor out 'generate singlestep exception' function target/arm: Fix routing of singlestep exceptions Richard Henderson (18): target/arm: Pass in pc to thumb_insn_is_16bit target/arm: Introduce pc_curr target/arm: Introduce read_pc target/arm: Introduce add_reg_for_lit target/arm: Remove redundant s->pc & ~1 target/arm: Replace s->pc with s->base.pc_next target/arm: Replace offset with pc in gen_exception_insn target/arm: Replace offset with pc in gen_exception_internal_insn target/arm: Remove offset argument to gen_exception_bkpt_insn target/arm: Use unallocated_encoding for aarch32 target/arm: Remove helper_double_saturate target/arm: Use tcg_gen_extract_i32 for shifter_out_im target/arm: Use tcg_gen_deposit_i32 for PKHBT, PKHTB target/arm: Remove redundant shift tests target/arm: Use ror32 instead of open-coding the operation target/arm: Use tcg_gen_rotri_i32 for gen_swap_half target/arm: Simplify SMMLA, SMMLAR, SMMLS, SMMLSR target/arm: Use tcg_gen_extrh_i64_i32 to extract the high word target/arm/cpu.h | 13 +- target/arm/helper.h | 1 - target/arm/kvm_arm.h | 28 ++ target/arm/translate-a64.h | 4 +- target/arm/translate.h | 39 ++- hw/misc/zynq_slcr.c | 450 ++++++++++++++++---------------- hw/net/imx_fec.c | 4 + target/arm/cpu.c | 30 ++- target/arm/cpu64.c | 31 ++- target/arm/helper.c | 7 + target/arm/kvm.c | 7 + target/arm/kvm64.c | 161 +++++++----- target/arm/op_helper.c | 15 -- target/arm/translate-a64.c | 130 ++++------ target/arm/translate-vfp.inc.c | 45 +--- target/arm/translate.c | 572 +++++++++++++++++------------------------ 16 files changed, 771 insertions(+), 766 deletions(-) From: Alex Bennée <alex.bennee@linaro.org> While most features are now detected by probing the ID_* registers kernels can (and do) use MIDR_EL1 for working out of they have to apply errata. This can trip up warnings in the kernel as it tries to work out if it should apply workarounds to features that don't actually exist in the reported CPU type. Avoid this problem by synthesising our own MIDR value. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190726113950.7499-1-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 ++++++ target/arm/cpu64.c | 19 +++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(V7M_FPCCR, ASPEN, 31, 1) /* * System register ID fields. */ +FIELD(MIDR_EL1, REVISION, 0, 4) +FIELD(MIDR_EL1, PARTNUM, 4, 12) +FIELD(MIDR_EL1, ARCHITECTURE, 16, 4) +FIELD(MIDR_EL1, VARIANT, 20, 4) +FIELD(MIDR_EL1, IMPLEMENTER, 24, 8) + FIELD(ID_ISAR0, SWAP, 0, 4) FIELD(ID_ISAR0, BITCOUNT, 4, 4) FIELD(ID_ISAR0, BITFIELD, 8, 4) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) uint32_t u; aarch64_a57_initfn(obj); + /* + * Reset MIDR so the guest doesn't mistake our 'max' CPU type for a real + * one and try to apply errata workarounds or use impdef features we + * don't provide. + * An IMPLEMENTER field of 0 means "reserved for software use"; + * ARCHITECTURE must be 0xf indicating "v7 or later, check ID registers + * to see which features are present"; + * the VARIANT, PARTNUM and REVISION fields are all implementation + * defined and we choose to define PARTNUM just in case guest + * code needs to distinguish this QEMU CPU from other software + * implementations, though this shouldn't be needed. + */ + t = FIELD_DP64(0, MIDR_EL1, IMPLEMENTER, 0); + t = FIELD_DP64(t, MIDR_EL1, ARCHITECTURE, 0xf); + t = FIELD_DP64(t, MIDR_EL1, PARTNUM, 'Q'); + t = FIELD_DP64(t, MIDR_EL1, VARIANT, 0); + t = FIELD_DP64(t, MIDR_EL1, REVISION, 0); + cpu->midr = t; + t = cpu->isar.id_aa64isar0; t = FIELD_DP64(t, ID_AA64ISAR0, AES, 2); /* AES + PMULL */ t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Replace the zynq_slcr registers enum and macros using the hw/registerfields.h macros. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20190729145654.14644-30-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 450 ++++++++++++++++++++++---------------------- 1 file changed, 225 insertions(+), 225 deletions(-) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "qemu/log.h" #include "qemu/module.h" +#include "hw/registerfields.h" #ifndef ZYNQ_SLCR_ERR_DEBUG #define ZYNQ_SLCR_ERR_DEBUG 0 @@ -XXX,XX +XXX,XX @@ #define XILINX_LOCK_KEY 0x767b #define XILINX_UNLOCK_KEY 0xdf0d -#define R_PSS_RST_CTRL_SOFT_RST 0x1 +REG32(SCL, 0x000) +REG32(LOCK, 0x004) +REG32(UNLOCK, 0x008) +REG32(LOCKSTA, 0x00c) -enum { - SCL = 0x000 / 4, - LOCK, - UNLOCK, - LOCKSTA, +REG32(ARM_PLL_CTRL, 0x100) +REG32(DDR_PLL_CTRL, 0x104) +REG32(IO_PLL_CTRL, 0x108) +REG32(PLL_STATUS, 0x10c) +REG32(ARM_PLL_CFG, 0x110) +REG32(DDR_PLL_CFG, 0x114) +REG32(IO_PLL_CFG, 0x118) - ARM_PLL_CTRL = 0x100 / 4, - DDR_PLL_CTRL, - IO_PLL_CTRL, - PLL_STATUS, - ARM_PLL_CFG, - DDR_PLL_CFG, - IO_PLL_CFG, - - ARM_CLK_CTRL = 0x120 / 4, - DDR_CLK_CTRL, - DCI_CLK_CTRL, - APER_CLK_CTRL, - USB0_CLK_CTRL, - USB1_CLK_CTRL, - GEM0_RCLK_CTRL, - GEM1_RCLK_CTRL, - GEM0_CLK_CTRL, - GEM1_CLK_CTRL, - SMC_CLK_CTRL, - LQSPI_CLK_CTRL, - SDIO_CLK_CTRL, - UART_CLK_CTRL, - SPI_CLK_CTRL, - CAN_CLK_CTRL, - CAN_MIOCLK_CTRL, - DBG_CLK_CTRL, - PCAP_CLK_CTRL, - TOPSW_CLK_CTRL, +REG32(ARM_CLK_CTRL, 0x120) +REG32(DDR_CLK_CTRL, 0x124) +REG32(DCI_CLK_CTRL, 0x128) +REG32(APER_CLK_CTRL, 0x12c) +REG32(USB0_CLK_CTRL, 0x130) +REG32(USB1_CLK_CTRL, 0x134) +REG32(GEM0_RCLK_CTRL, 0x138) +REG32(GEM1_RCLK_CTRL, 0x13c) +REG32(GEM0_CLK_CTRL, 0x140) +REG32(GEM1_CLK_CTRL, 0x144) +REG32(SMC_CLK_CTRL, 0x148) +REG32(LQSPI_CLK_CTRL, 0x14c) +REG32(SDIO_CLK_CTRL, 0x150) +REG32(UART_CLK_CTRL, 0x154) +REG32(SPI_CLK_CTRL, 0x158) +REG32(CAN_CLK_CTRL, 0x15c) +REG32(CAN_MIOCLK_CTRL, 0x160) +REG32(DBG_CLK_CTRL, 0x164) +REG32(PCAP_CLK_CTRL, 0x168) +REG32(TOPSW_CLK_CTRL, 0x16c) #define FPGA_CTRL_REGS(n, start) \ - FPGA ## n ## _CLK_CTRL = (start) / 4, \ - FPGA ## n ## _THR_CTRL, \ - FPGA ## n ## _THR_CNT, \ - FPGA ## n ## _THR_STA, - FPGA_CTRL_REGS(0, 0x170) - FPGA_CTRL_REGS(1, 0x180) - FPGA_CTRL_REGS(2, 0x190) - FPGA_CTRL_REGS(3, 0x1a0) + REG32(FPGA ## n ## _CLK_CTRL, (start)) \ + REG32(FPGA ## n ## _THR_CTRL, (start) + 0x4)\ + REG32(FPGA ## n ## _THR_CNT, (start) + 0x8)\ + REG32(FPGA ## n ## _THR_STA, (start) + 0xc) +FPGA_CTRL_REGS(0, 0x170) +FPGA_CTRL_REGS(1, 0x180) +FPGA_CTRL_REGS(2, 0x190) +FPGA_CTRL_REGS(3, 0x1a0) - BANDGAP_TRIP = 0x1b8 / 4, - PLL_PREDIVISOR = 0x1c0 / 4, - CLK_621_TRUE, +REG32(BANDGAP_TRIP, 0x1b8) +REG32(PLL_PREDIVISOR, 0x1c0) +REG32(CLK_621_TRUE, 0x1c4) - PSS_RST_CTRL = 0x200 / 4, - DDR_RST_CTRL, - TOPSW_RESET_CTRL, - DMAC_RST_CTRL, - USB_RST_CTRL, - GEM_RST_CTRL, - SDIO_RST_CTRL, - SPI_RST_CTRL, - CAN_RST_CTRL, - I2C_RST_CTRL, - UART_RST_CTRL, - GPIO_RST_CTRL, - LQSPI_RST_CTRL, - SMC_RST_CTRL, - OCM_RST_CTRL, - FPGA_RST_CTRL = 0x240 / 4, - A9_CPU_RST_CTRL, +REG32(PSS_RST_CTRL, 0x200) + FIELD(PSS_RST_CTRL, SOFT_RST, 0, 1) +REG32(DDR_RST_CTRL, 0x204) +REG32(TOPSW_RESET_CTRL, 0x208) +REG32(DMAC_RST_CTRL, 0x20c) +REG32(USB_RST_CTRL, 0x210) +REG32(GEM_RST_CTRL, 0x214) +REG32(SDIO_RST_CTRL, 0x218) +REG32(SPI_RST_CTRL, 0x21c) +REG32(CAN_RST_CTRL, 0x220) +REG32(I2C_RST_CTRL, 0x224) +REG32(UART_RST_CTRL, 0x228) +REG32(GPIO_RST_CTRL, 0x22c) +REG32(LQSPI_RST_CTRL, 0x230) +REG32(SMC_RST_CTRL, 0x234) +REG32(OCM_RST_CTRL, 0x238) +REG32(FPGA_RST_CTRL, 0x240) +REG32(A9_CPU_RST_CTRL, 0x244) - RS_AWDT_CTRL = 0x24c / 4, - RST_REASON, +REG32(RS_AWDT_CTRL, 0x24c) +REG32(RST_REASON, 0x250) - REBOOT_STATUS = 0x258 / 4, - BOOT_MODE, +REG32(REBOOT_STATUS, 0x258) +REG32(BOOT_MODE, 0x25c) - APU_CTRL = 0x300 / 4, - WDT_CLK_SEL, +REG32(APU_CTRL, 0x300) +REG32(WDT_CLK_SEL, 0x304) - TZ_DMA_NS = 0x440 / 4, - TZ_DMA_IRQ_NS, - TZ_DMA_PERIPH_NS, +REG32(TZ_DMA_NS, 0x440) +REG32(TZ_DMA_IRQ_NS, 0x444) +REG32(TZ_DMA_PERIPH_NS, 0x448) - PSS_IDCODE = 0x530 / 4, +REG32(PSS_IDCODE, 0x530) - DDR_URGENT = 0x600 / 4, - DDR_CAL_START = 0x60c / 4, - DDR_REF_START = 0x614 / 4, - DDR_CMD_STA, - DDR_URGENT_SEL, - DDR_DFI_STATUS, +REG32(DDR_URGENT, 0x600) +REG32(DDR_CAL_START, 0x60c) +REG32(DDR_REF_START, 0x614) +REG32(DDR_CMD_STA, 0x618) +REG32(DDR_URGENT_SEL, 0x61c) +REG32(DDR_DFI_STATUS, 0x620) - MIO = 0x700 / 4, +REG32(MIO, 0x700) #define MIO_LENGTH 54 - MIO_LOOPBACK = 0x804 / 4, - MIO_MST_TRI0, - MIO_MST_TRI1, +REG32(MIO_LOOPBACK, 0x804) +REG32(MIO_MST_TRI0, 0x808) +REG32(MIO_MST_TRI1, 0x80c) - SD0_WP_CD_SEL = 0x830 / 4, - SD1_WP_CD_SEL, +REG32(SD0_WP_CD_SEL, 0x830) +REG32(SD1_WP_CD_SEL, 0x834) - LVL_SHFTR_EN = 0x900 / 4, - OCM_CFG = 0x910 / 4, +REG32(LVL_SHFTR_EN, 0x900) +REG32(OCM_CFG, 0x910) - CPU_RAM = 0xa00 / 4, +REG32(CPU_RAM, 0xa00) - IOU = 0xa30 / 4, +REG32(IOU, 0xa30) - DMAC_RAM = 0xa50 / 4, +REG32(DMAC_RAM, 0xa50) - AFI0 = 0xa60 / 4, - AFI1 = AFI0 + 3, - AFI2 = AFI1 + 3, - AFI3 = AFI2 + 3, +REG32(AFI0, 0xa60) +REG32(AFI1, 0xa6c) +REG32(AFI2, 0xa78) +REG32(AFI3, 0xa84) #define AFI_LENGTH 3 - OCM = 0xa90 / 4, +REG32(OCM, 0xa90) - DEVCI_RAM = 0xaa0 / 4, +REG32(DEVCI_RAM, 0xaa0) - CSG_RAM = 0xab0 / 4, +REG32(CSG_RAM, 0xab0) - GPIOB_CTRL = 0xb00 / 4, - GPIOB_CFG_CMOS18, - GPIOB_CFG_CMOS25, - GPIOB_CFG_CMOS33, - GPIOB_CFG_HSTL = 0xb14 / 4, - GPIOB_DRVR_BIAS_CTRL, +REG32(GPIOB_CTRL, 0xb00) +REG32(GPIOB_CFG_CMOS18, 0xb04) +REG32(GPIOB_CFG_CMOS25, 0xb08) +REG32(GPIOB_CFG_CMOS33, 0xb0c) +REG32(GPIOB_CFG_HSTL, 0xb14) +REG32(GPIOB_DRVR_BIAS_CTRL, 0xb18) - DDRIOB = 0xb40 / 4, +REG32(DDRIOB, 0xb40) #define DDRIOB_LENGTH 14 -}; #define ZYNQ_SLCR_MMIO_SIZE 0x1000 #define ZYNQ_SLCR_NUM_REGS (ZYNQ_SLCR_MMIO_SIZE / 4) @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset(DeviceState *d) DB_PRINT("RESET\n"); - s->regs[LOCKSTA] = 1; + s->regs[R_LOCKSTA] = 1; /* 0x100 - 0x11C */ - s->regs[ARM_PLL_CTRL] = 0x0001A008; - s->regs[DDR_PLL_CTRL] = 0x0001A008; - s->regs[IO_PLL_CTRL] = 0x0001A008; - s->regs[PLL_STATUS] = 0x0000003F; - s->regs[ARM_PLL_CFG] = 0x00014000; - s->regs[DDR_PLL_CFG] = 0x00014000; - s->regs[IO_PLL_CFG] = 0x00014000; + s->regs[R_ARM_PLL_CTRL] = 0x0001A008; + s->regs[R_DDR_PLL_CTRL] = 0x0001A008; + s->regs[R_IO_PLL_CTRL] = 0x0001A008; + s->regs[R_PLL_STATUS] = 0x0000003F; + s->regs[R_ARM_PLL_CFG] = 0x00014000; + s->regs[R_DDR_PLL_CFG] = 0x00014000; + s->regs[R_IO_PLL_CFG] = 0x00014000; /* 0x120 - 0x16C */ - s->regs[ARM_CLK_CTRL] = 0x1F000400; - s->regs[DDR_CLK_CTRL] = 0x18400003; - s->regs[DCI_CLK_CTRL] = 0x01E03201; - s->regs[APER_CLK_CTRL] = 0x01FFCCCD; - s->regs[USB0_CLK_CTRL] = s->regs[USB1_CLK_CTRL] = 0x00101941; - s->regs[GEM0_RCLK_CTRL] = s->regs[GEM1_RCLK_CTRL] = 0x00000001; - s->regs[GEM0_CLK_CTRL] = s->regs[GEM1_CLK_CTRL] = 0x00003C01; - s->regs[SMC_CLK_CTRL] = 0x00003C01; - s->regs[LQSPI_CLK_CTRL] = 0x00002821; - s->regs[SDIO_CLK_CTRL] = 0x00001E03; - s->regs[UART_CLK_CTRL] = 0x00003F03; - s->regs[SPI_CLK_CTRL] = 0x00003F03; - s->regs[CAN_CLK_CTRL] = 0x00501903; - s->regs[DBG_CLK_CTRL] = 0x00000F03; - s->regs[PCAP_CLK_CTRL] = 0x00000F01; + s->regs[R_ARM_CLK_CTRL] = 0x1F000400; + s->regs[R_DDR_CLK_CTRL] = 0x18400003; + s->regs[R_DCI_CLK_CTRL] = 0x01E03201; + s->regs[R_APER_CLK_CTRL] = 0x01FFCCCD; + s->regs[R_USB0_CLK_CTRL] = s->regs[R_USB1_CLK_CTRL] = 0x00101941; + s->regs[R_GEM0_RCLK_CTRL] = s->regs[R_GEM1_RCLK_CTRL] = 0x00000001; + s->regs[R_GEM0_CLK_CTRL] = s->regs[R_GEM1_CLK_CTRL] = 0x00003C01; + s->regs[R_SMC_CLK_CTRL] = 0x00003C01; + s->regs[R_LQSPI_CLK_CTRL] = 0x00002821; + s->regs[R_SDIO_CLK_CTRL] = 0x00001E03; + s->regs[R_UART_CLK_CTRL] = 0x00003F03; + s->regs[R_SPI_CLK_CTRL] = 0x00003F03; + s->regs[R_CAN_CLK_CTRL] = 0x00501903; + s->regs[R_DBG_CLK_CTRL] = 0x00000F03; + s->regs[R_PCAP_CLK_CTRL] = 0x00000F01; /* 0x170 - 0x1AC */ - s->regs[FPGA0_CLK_CTRL] = s->regs[FPGA1_CLK_CTRL] = s->regs[FPGA2_CLK_CTRL] - = s->regs[FPGA3_CLK_CTRL] = 0x00101800; - s->regs[FPGA0_THR_STA] = s->regs[FPGA1_THR_STA] = s->regs[FPGA2_THR_STA] - = s->regs[FPGA3_THR_STA] = 0x00010000; + s->regs[R_FPGA0_CLK_CTRL] = s->regs[R_FPGA1_CLK_CTRL] + = s->regs[R_FPGA2_CLK_CTRL] + = s->regs[R_FPGA3_CLK_CTRL] = 0x00101800; + s->regs[R_FPGA0_THR_STA] = s->regs[R_FPGA1_THR_STA] + = s->regs[R_FPGA2_THR_STA] + = s->regs[R_FPGA3_THR_STA] = 0x00010000; /* 0x1B0 - 0x1D8 */ - s->regs[BANDGAP_TRIP] = 0x0000001F; - s->regs[PLL_PREDIVISOR] = 0x00000001; - s->regs[CLK_621_TRUE] = 0x00000001; + s->regs[R_BANDGAP_TRIP] = 0x0000001F; + s->regs[R_PLL_PREDIVISOR] = 0x00000001; + s->regs[R_CLK_621_TRUE] = 0x00000001; /* 0x200 - 0x25C */ - s->regs[FPGA_RST_CTRL] = 0x01F33F0F; - s->regs[RST_REASON] = 0x00000040; + s->regs[R_FPGA_RST_CTRL] = 0x01F33F0F; + s->regs[R_RST_REASON] = 0x00000040; - s->regs[BOOT_MODE] = 0x00000001; + s->regs[R_BOOT_MODE] = 0x00000001; /* 0x700 - 0x7D4 */ for (i = 0; i < 54; i++) { - s->regs[MIO + i] = 0x00001601; + s->regs[R_MIO + i] = 0x00001601; } for (i = 2; i <= 8; i++) { - s->regs[MIO + i] = 0x00000601; + s->regs[R_MIO + i] = 0x00000601; } - s->regs[MIO_MST_TRI0] = s->regs[MIO_MST_TRI1] = 0xFFFFFFFF; + s->regs[R_MIO_MST_TRI0] = s->regs[R_MIO_MST_TRI1] = 0xFFFFFFFF; - s->regs[CPU_RAM + 0] = s->regs[CPU_RAM + 1] = s->regs[CPU_RAM + 3] - = s->regs[CPU_RAM + 4] = s->regs[CPU_RAM + 7] - = 0x00010101; - s->regs[CPU_RAM + 2] = s->regs[CPU_RAM + 5] = 0x01010101; - s->regs[CPU_RAM + 6] = 0x00000001; + s->regs[R_CPU_RAM + 0] = s->regs[R_CPU_RAM + 1] = s->regs[R_CPU_RAM + 3] + = s->regs[R_CPU_RAM + 4] = s->regs[R_CPU_RAM + 7] + = 0x00010101; + s->regs[R_CPU_RAM + 2] = s->regs[R_CPU_RAM + 5] = 0x01010101; + s->regs[R_CPU_RAM + 6] = 0x00000001; - s->regs[IOU + 0] = s->regs[IOU + 1] = s->regs[IOU + 2] = s->regs[IOU + 3] - = 0x09090909; - s->regs[IOU + 4] = s->regs[IOU + 5] = 0x00090909; - s->regs[IOU + 6] = 0x00000909; + s->regs[R_IOU + 0] = s->regs[R_IOU + 1] = s->regs[R_IOU + 2] + = s->regs[R_IOU + 3] = 0x09090909; + s->regs[R_IOU + 4] = s->regs[R_IOU + 5] = 0x00090909; + s->regs[R_IOU + 6] = 0x00000909; - s->regs[DMAC_RAM] = 0x00000009; + s->regs[R_DMAC_RAM] = 0x00000009; - s->regs[AFI0 + 0] = s->regs[AFI0 + 1] = 0x09090909; - s->regs[AFI1 + 0] = s->regs[AFI1 + 1] = 0x09090909; - s->regs[AFI2 + 0] = s->regs[AFI2 + 1] = 0x09090909; - s->regs[AFI3 + 0] = s->regs[AFI3 + 1] = 0x09090909; - s->regs[AFI0 + 2] = s->regs[AFI1 + 2] = s->regs[AFI2 + 2] - = s->regs[AFI3 + 2] = 0x00000909; + s->regs[R_AFI0 + 0] = s->regs[R_AFI0 + 1] = 0x09090909; + s->regs[R_AFI1 + 0] = s->regs[R_AFI1 + 1] = 0x09090909; + s->regs[R_AFI2 + 0] = s->regs[R_AFI2 + 1] = 0x09090909; + s->regs[R_AFI3 + 0] = s->regs[R_AFI3 + 1] = 0x09090909; + s->regs[R_AFI0 + 2] = s->regs[R_AFI1 + 2] = s->regs[R_AFI2 + 2] + = s->regs[R_AFI3 + 2] = 0x00000909; - s->regs[OCM + 0] = 0x01010101; - s->regs[OCM + 1] = s->regs[OCM + 2] = 0x09090909; + s->regs[R_OCM + 0] = 0x01010101; + s->regs[R_OCM + 1] = s->regs[R_OCM + 2] = 0x09090909; - s->regs[DEVCI_RAM] = 0x00000909; - s->regs[CSG_RAM] = 0x00000001; + s->regs[R_DEVCI_RAM] = 0x00000909; + s->regs[R_CSG_RAM] = 0x00000001; - s->regs[DDRIOB + 0] = s->regs[DDRIOB + 1] = s->regs[DDRIOB + 2] - = s->regs[DDRIOB + 3] = 0x00000e00; - s->regs[DDRIOB + 4] = s->regs[DDRIOB + 5] = s->regs[DDRIOB + 6] - = 0x00000e00; - s->regs[DDRIOB + 12] = 0x00000021; + s->regs[R_DDRIOB + 0] = s->regs[R_DDRIOB + 1] = s->regs[R_DDRIOB + 2] + = s->regs[R_DDRIOB + 3] = 0x00000e00; + s->regs[R_DDRIOB + 4] = s->regs[R_DDRIOB + 5] = s->regs[R_DDRIOB + 6] + = 0x00000e00; + s->regs[R_DDRIOB + 12] = 0x00000021; } static bool zynq_slcr_check_offset(hwaddr offset, bool rnw) { switch (offset) { - case LOCK: - case UNLOCK: - case DDR_CAL_START: - case DDR_REF_START: + case R_LOCK: + case R_UNLOCK: + case R_DDR_CAL_START: + case R_DDR_REF_START: return !rnw; /* Write only */ - case LOCKSTA: - case FPGA0_THR_STA: - case FPGA1_THR_STA: - case FPGA2_THR_STA: - case FPGA3_THR_STA: - case BOOT_MODE: - case PSS_IDCODE: - case DDR_CMD_STA: - case DDR_DFI_STATUS: - case PLL_STATUS: + case R_LOCKSTA: + case R_FPGA0_THR_STA: + case R_FPGA1_THR_STA: + case R_FPGA2_THR_STA: + case R_FPGA3_THR_STA: + case R_BOOT_MODE: + case R_PSS_IDCODE: + case R_DDR_CMD_STA: + case R_DDR_DFI_STATUS: + case R_PLL_STATUS: return rnw;/* read only */ - case SCL: - case ARM_PLL_CTRL ... IO_PLL_CTRL: - case ARM_PLL_CFG ... IO_PLL_CFG: - case ARM_CLK_CTRL ... TOPSW_CLK_CTRL: - case FPGA0_CLK_CTRL ... FPGA0_THR_CNT: - case FPGA1_CLK_CTRL ... FPGA1_THR_CNT: - case FPGA2_CLK_CTRL ... FPGA2_THR_CNT: - case FPGA3_CLK_CTRL ... FPGA3_THR_CNT: - case BANDGAP_TRIP: - case PLL_PREDIVISOR: - case CLK_621_TRUE: - case PSS_RST_CTRL ... A9_CPU_RST_CTRL: - case RS_AWDT_CTRL: - case RST_REASON: - case REBOOT_STATUS: - case APU_CTRL: - case WDT_CLK_SEL: - case TZ_DMA_NS ... TZ_DMA_PERIPH_NS: - case DDR_URGENT: - case DDR_URGENT_SEL: - case MIO ... MIO + MIO_LENGTH - 1: - case MIO_LOOPBACK ... MIO_MST_TRI1: - case SD0_WP_CD_SEL: - case SD1_WP_CD_SEL: - case LVL_SHFTR_EN: - case OCM_CFG: - case CPU_RAM: - case IOU: - case DMAC_RAM: - case AFI0 ... AFI3 + AFI_LENGTH - 1: - case OCM: - case DEVCI_RAM: - case CSG_RAM: - case GPIOB_CTRL ... GPIOB_CFG_CMOS33: - case GPIOB_CFG_HSTL: - case GPIOB_DRVR_BIAS_CTRL: - case DDRIOB ... DDRIOB + DDRIOB_LENGTH - 1: + case R_SCL: + case R_ARM_PLL_CTRL ... R_IO_PLL_CTRL: + case R_ARM_PLL_CFG ... R_IO_PLL_CFG: + case R_ARM_CLK_CTRL ... R_TOPSW_CLK_CTRL: + case R_FPGA0_CLK_CTRL ... R_FPGA0_THR_CNT: + case R_FPGA1_CLK_CTRL ... R_FPGA1_THR_CNT: + case R_FPGA2_CLK_CTRL ... R_FPGA2_THR_CNT: + case R_FPGA3_CLK_CTRL ... R_FPGA3_THR_CNT: + case R_BANDGAP_TRIP: + case R_PLL_PREDIVISOR: + case R_CLK_621_TRUE: + case R_PSS_RST_CTRL ... R_A9_CPU_RST_CTRL: + case R_RS_AWDT_CTRL: + case R_RST_REASON: + case R_REBOOT_STATUS: + case R_APU_CTRL: + case R_WDT_CLK_SEL: + case R_TZ_DMA_NS ... R_TZ_DMA_PERIPH_NS: + case R_DDR_URGENT: + case R_DDR_URGENT_SEL: + case R_MIO ... R_MIO + MIO_LENGTH - 1: + case R_MIO_LOOPBACK ... R_MIO_MST_TRI1: + case R_SD0_WP_CD_SEL: + case R_SD1_WP_CD_SEL: + case R_LVL_SHFTR_EN: + case R_OCM_CFG: + case R_CPU_RAM: + case R_IOU: + case R_DMAC_RAM: + case R_AFI0 ... R_AFI3 + AFI_LENGTH - 1: + case R_OCM: + case R_DEVCI_RAM: + case R_CSG_RAM: + case R_GPIOB_CTRL ... R_GPIOB_CFG_CMOS33: + case R_GPIOB_CFG_HSTL: + case R_GPIOB_DRVR_BIAS_CTRL: + case R_DDRIOB ... R_DDRIOB + DDRIOB_LENGTH - 1: return true; default: return false; @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_write(void *opaque, hwaddr offset, } switch (offset) { - case SCL: - s->regs[SCL] = val & 0x1; + case R_SCL: + s->regs[R_SCL] = val & 0x1; return; - case LOCK: + case R_LOCK: if ((val & 0xFFFF) == XILINX_LOCK_KEY) { DB_PRINT("XILINX LOCK 0xF8000000 + 0x%x <= 0x%x\n", (int)offset, (unsigned)val & 0xFFFF); - s->regs[LOCKSTA] = 1; + s->regs[R_LOCKSTA] = 1; } else { DB_PRINT("WRONG XILINX LOCK KEY 0xF8000000 + 0x%x <= 0x%x\n", (int)offset, (unsigned)val & 0xFFFF); } return; - case UNLOCK: + case R_UNLOCK: if ((val & 0xFFFF) == XILINX_UNLOCK_KEY) { DB_PRINT("XILINX UNLOCK 0xF8000000 + 0x%x <= 0x%x\n", (int)offset, (unsigned)val & 0xFFFF); - s->regs[LOCKSTA] = 0; + s->regs[R_LOCKSTA] = 0; } else { DB_PRINT("WRONG XILINX UNLOCK KEY 0xF8000000 + 0x%x <= 0x%x\n", (int)offset, (unsigned)val & 0xFFFF); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_write(void *opaque, hwaddr offset, return; } - if (s->regs[LOCKSTA]) { + if (s->regs[R_LOCKSTA]) { qemu_log_mask(LOG_GUEST_ERROR, "SCLR registers are locked. Unlock them first\n"); return; @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_write(void *opaque, hwaddr offset, s->regs[offset] = val; switch (offset) { - case PSS_RST_CTRL: - if (val & R_PSS_RST_CTRL_SOFT_RST) { + case R_PSS_RST_CTRL: + if (FIELD_EX32(val, PSS_RST_CTRL, SOFT_RST)) { qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); } break; -- 2.20.1 From: Aaron Hill <aa1ronham@gmail.com> This commit properly sets the ENET_BD_BDU flag once the emulated FEC controller has finished processing the last descriptor. This is done for both transmit and receive descriptors. This allows the QNX 7.0.0 BSP for the Sabrelite board (which can be found at http://blackberry.qnx.com/en/developers/bsp) to properly control the FEC. Without this patch, the BSP ethernet driver will never re-use FEC descriptors, as the unset ENET_BD_BDU flag will cause it to believe that the descriptors are still in use by the NIC. Note that Linux does not appear to use this field at all, and is unaffected by this patch. Without this patch, QNX will think that the NIC is still processing its transaction descriptors, and won't send any more data over the network. For reference: On page 1192 of the I.MX 6DQ reference manual revision (Rev. 5, 06/2018), which can be found at https://www.nxp.com/products/processors-and-microcontrollers/arm-based-processors-and-mcus/i.mx-applications-processors/i.mx-6-processors/i.mx-6quad-processors-high-performance-3d-graphics-hd-video-arm-cortex-a9-core:i.MX6Q?&tab=Documentation_Tab&linkline=Application-Note the 'BDU' field is described as follows for the 'Enhanced transmit buffer descriptor': 'Last buffer descriptor update done. Indicates that the last BD data has been updated by uDMA. This field is written by the user (=0) and uDMA (=1).' The same description is used for the receive buffer descriptor. Signed-off-by: Aaron Hill <aa1ronham@gmail.com> Message-id: 20190805142417.10433-1-aaron.hill@alertinnovation.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/imx_fec.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -XXX,XX +XXX,XX @@ static void imx_enet_do_tx(IMXFECState *s, uint32_t index) if (bd.option & ENET_BD_TX_INT) { s->regs[ENET_EIR] |= int_txf; } + /* Indicate that we've updated the last buffer descriptor. */ + bd.last_buffer = ENET_BD_BDU; } if (bd.option & ENET_BD_TX_INT) { s->regs[ENET_EIR] |= int_txb; @@ -XXX,XX +XXX,XX @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf, /* Last buffer in frame. */ bd.flags |= flags | ENET_BD_L; FEC_PRINTF("rx frame flags %04x\n", bd.flags); + /* Indicate that we've updated the last buffer descriptor. */ + bd.last_buffer = ENET_BD_BDU; if (bd.option & ENET_BD_RX_INT) { s->regs[ENET_EIR] |= ENET_INT_RXF; } -- 2.20.1 Factor out code to 'generate a singlestep exception', which is currently repeated in four places. To do this we need to also pull the identical copies of the gen-exception() function out of translate-a64.c and translate.c into translate.h. (There is a bug in the code: we're taking the exception to the wrong target EL. This will be simpler to fix if there's only one place to do it.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20190805130952.4415-2-peter.maydell@linaro.org --- target/arm/translate.h | 23 +++++++++++++++++++++++ target/arm/translate-a64.c | 19 ++----------------- target/arm/translate.c | 20 ++------------------ 3 files changed, 27 insertions(+), 35 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ #define TARGET_ARM_TRANSLATE_H #include "exec/translator.h" +#include "internals.h" /* internal defines */ @@ -XXX,XX +XXX,XX @@ static inline void gen_ss_advance(DisasContext *s) } } +static inline void gen_exception(int excp, uint32_t syndrome, + uint32_t target_el) +{ + TCGv_i32 tcg_excp = tcg_const_i32(excp); + TCGv_i32 tcg_syn = tcg_const_i32(syndrome); + TCGv_i32 tcg_el = tcg_const_i32(target_el); + + gen_helper_exception_with_syndrome(cpu_env, tcg_excp, + tcg_syn, tcg_el); + + tcg_temp_free_i32(tcg_el); + tcg_temp_free_i32(tcg_syn); + tcg_temp_free_i32(tcg_excp); +} + +/* Generate an architectural singlestep exception */ +static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) +{ + gen_exception(EXCP_UDEF, syn_swstep(s->ss_same_el, isv, ex), + default_exception_el(s)); +} + /* * Given a VFP floating point constant encoded into an 8 bit immediate in an * instruction, expand it to the actual constant value of the specified diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_exception_internal(int excp) tcg_temp_free_i32(tcg_excp); } -static void gen_exception(int excp, uint32_t syndrome, uint32_t target_el) -{ - TCGv_i32 tcg_excp = tcg_const_i32(excp); - TCGv_i32 tcg_syn = tcg_const_i32(syndrome); - TCGv_i32 tcg_el = tcg_const_i32(target_el); - - gen_helper_exception_with_syndrome(cpu_env, tcg_excp, - tcg_syn, tcg_el); - tcg_temp_free_i32(tcg_el); - tcg_temp_free_i32(tcg_syn); - tcg_temp_free_i32(tcg_excp); -} - static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) { gen_a64_set_pc_im(s->pc - offset); @@ -XXX,XX +XXX,XX @@ static void gen_step_complete_exception(DisasContext *s) * of the exception, and our syndrome information is always correct. */ gen_ss_advance(s); - gen_exception(EXCP_UDEF, syn_swstep(s->ss_same_el, 1, s->is_ldex), - default_exception_el(s)); + gen_swstep_exception(s, 1, s->is_ldex); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) * bits should be zero. */ assert(dc->base.num_insns == 1); - gen_exception(EXCP_UDEF, syn_swstep(dc->ss_same_el, 0, 0), - default_exception_el(dc)); + gen_swstep_exception(dc, 0, 0); dc->base.is_jmp = DISAS_NORETURN; } else { disas_a64_insn(env, dc); 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 void gen_exception_internal(int excp) tcg_temp_free_i32(tcg_excp); } -static void gen_exception(int excp, uint32_t syndrome, uint32_t target_el) -{ - TCGv_i32 tcg_excp = tcg_const_i32(excp); - TCGv_i32 tcg_syn = tcg_const_i32(syndrome); - TCGv_i32 tcg_el = tcg_const_i32(target_el); - - gen_helper_exception_with_syndrome(cpu_env, tcg_excp, - tcg_syn, tcg_el); - - tcg_temp_free_i32(tcg_el); - tcg_temp_free_i32(tcg_syn); - tcg_temp_free_i32(tcg_excp); -} - static void gen_step_complete_exception(DisasContext *s) { /* We just completed step of an insn. Move from Active-not-pending @@ -XXX,XX +XXX,XX @@ static void gen_step_complete_exception(DisasContext *s) * of the exception, and our syndrome information is always correct. */ gen_ss_advance(s); - gen_exception(EXCP_UDEF, syn_swstep(s->ss_same_el, 1, s->is_ldex), - default_exception_el(s)); + gen_swstep_exception(s, 1, s->is_ldex); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static bool arm_pre_translate_insn(DisasContext *dc) * bits should be zero. */ assert(dc->base.num_insns == 1); - gen_exception(EXCP_UDEF, syn_swstep(dc->ss_same_el, 0, 0), - default_exception_el(dc)); + gen_swstep_exception(dc, 0, 0); dc->base.is_jmp = DISAS_NORETURN; return true; } -- 2.20.1 When generating an architectural single-step exception we were routing it to the "default exception level", which is to say the same exception level we execute at except that EL0 exceptions go to EL1. This is incorrect because the debug exception level can be configured by the guest for situations such as single stepping of EL0 and EL1 code by EL2. We have to track the target debug exception level in the TB flags, because it is dependent on CPU state like HCR_EL2.TGE and MDCR_EL2.TDE. (That we were previously calling the arm_debug_target_el() function to determine dc->ss_same_el is itself a bug, though one that would only have manifested as incorrect syndrome information.) Since we are out of TB flag bits unless we want to expand into the cs_base field, we share some bits with the M-profile only HANDLER and STACKCHECK bits, since only A-profile has this singlestep. Fixes: https://bugs.launchpad.net/qemu/+bug/1838913 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20190805130952.4415-3-peter.maydell@linaro.org --- target/arm/cpu.h | 5 +++++ target/arm/translate.h | 15 +++++++++++---- target/arm/helper.c | 6 ++++++ target/arm/translate-a64.c | 2 +- target/arm/translate.c | 4 +++- 5 files changed, 26 insertions(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_ANY, PSTATE_SS, 26, 1) /* Target EL if we take a floating-point-disabled exception */ FIELD(TBFLAG_ANY, FPEXC_EL, 24, 2) FIELD(TBFLAG_ANY, BE_DATA, 23, 1) +/* + * For A-profile only, target EL for debug exceptions. + * Note that this overlaps with the M-profile-only HANDLER and STACKCHECK bits. + */ +FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 21, 2) /* Bit usage when in AArch32 state: */ FIELD(TBFLAG_A32, THUMB, 0, 1) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { uint32_t svc_imm; int aarch64; int current_el; + /* Debug target exception level for single-step exceptions */ + int debug_target_el; GHashTable *cp_regs; uint64_t features; /* CPU features bits */ /* Because unallocated encodings generate different exception syndrome @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { * ie A64 LDX*, LDAX*, A32/T32 LDREX*, LDAEX*. */ bool is_ldex; - /* True if a single-step exception will be taken to the current EL */ - bool ss_same_el; /* True if v8.3-PAuth is active. */ bool pauth_active; /* True with v8.5-BTI and SCTLR_ELx.BT* set. */ @@ -XXX,XX +XXX,XX @@ static inline void gen_exception(int excp, uint32_t syndrome, /* Generate an architectural singlestep exception */ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) { - gen_exception(EXCP_UDEF, syn_swstep(s->ss_same_el, isv, ex), - default_exception_el(s)); + bool same_el = (s->debug_target_el == s->current_el); + + /* + * If singlestep is targeting a lower EL than the current one, + * then s->ss_active must be false and we can never get here. + */ + assert(s->debug_target_el >= s->current_el); + + gen_exception(EXCP_UDEF, syn_swstep(same_el, isv, ex), s->debug_target_el); } /* 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)) { + int target_el = arm_debug_target_el(env); + + flags = FIELD_DP32(flags, TBFLAG_ANY, DEBUG_TARGET_EL, target_el); + } + *pflags = flags; *cs_base = 0; } 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 aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE); dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE_SS); dc->is_ldex = false; - dc->ss_same_el = (arm_debug_target_el(env) == dc->current_el); + dc->debug_target_el = FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL); /* Bound the number of insns to execute to those left on the page. */ bound = -(dc->base.pc_first | TARGET_PAGE_MASK) / 4; 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 void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE); dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE_SS); dc->is_ldex = false; - dc->ss_same_el = false; /* Can't be true since EL_d must be AArch64 */ + if (!arm_feature(env, ARM_FEATURE_M)) { + dc->debug_target_el = FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL); + } dc->page_start = dc->base.pc_first & TARGET_PAGE_MASK; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This function is used in two different contexts, and it will be clearer if the function is given the address to which it applies. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) 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 void disas_arm_insn(DisasContext *s, unsigned int insn) } } -static bool thumb_insn_is_16bit(DisasContext *s, uint32_t insn) +static bool thumb_insn_is_16bit(DisasContext *s, uint32_t pc, uint32_t insn) { - /* Return true if this is a 16 bit instruction. We must be precise - * about this (matching the decode). We assume that s->pc still - * points to the first 16 bits of the insn. + /* + * Return true if this is a 16 bit instruction. We must be precise + * about this (matching the decode). */ if ((insn >> 11) < 0x1d) { /* Definitely a 16-bit instruction */ @@ -XXX,XX +XXX,XX @@ static bool thumb_insn_is_16bit(DisasContext *s, uint32_t insn) return false; } - if ((insn >> 11) == 0x1e && s->pc - s->page_start < TARGET_PAGE_SIZE - 3) { + if ((insn >> 11) == 0x1e && pc - s->page_start < TARGET_PAGE_SIZE - 3) { /* 0b1111_0xxx_xxxx_xxxx : BL/BLX prefix, and the suffix * is not on the next page; we merge this into a 32-bit * insn. @@ -XXX,XX +XXX,XX @@ static bool insn_crosses_page(CPUARMState *env, DisasContext *s) */ uint16_t insn = arm_lduw_code(env, s->pc, s->sctlr_b); - return !thumb_insn_is_16bit(s, insn); + return !thumb_insn_is_16bit(s, s->pc, insn); } static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) @@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } insn = arm_lduw_code(env, dc->pc, dc->sctlr_b); - is_16bit = thumb_insn_is_16bit(dc, insn); + is_16bit = thumb_insn_is_16bit(dc, dc->pc, insn); dc->pc += 2; if (!is_16bit) { uint32_t insn2 = arm_lduw_code(env, dc->pc, dc->sctlr_b); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Add a new field to retain the address of the instruction currently being translated. The 32-bit uses are all within subroutines used by a32 and t32. This will become less obvious when t16 support is merged with a32+t32, and having a clear definition will help. Convert aarch64 as well for consistency. Note that there is one instance of a pre-assert fprintf that used the wrong value for the address of the current instruction. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 2 +- target/arm/translate.h | 2 ++ target/arm/translate-a64.c | 21 +++++++++++---------- target/arm/translate.c | 14 ++++++++------ 4 files changed, 22 insertions(+), 17 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void unallocated_encoding(DisasContext *s); qemu_log_mask(LOG_UNIMP, \ "%s:%d: unsupported instruction encoding 0x%08x " \ "at pc=%016" PRIx64 "\n", \ - __FILE__, __LINE__, insn, s->pc - 4); \ + __FILE__, __LINE__, insn, s->pc_curr); \ unallocated_encoding(s); \ } while (0) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { const ARMISARegisters *isar; target_ulong pc; + /* The address of the current instruction being translated. */ + target_ulong pc_curr; target_ulong page_start; uint32_t insn; /* Nonzero if this instruction has been conditionally skipped. */ 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 inline AArch64DecodeFn *lookup_disas_fn(const AArch64DecodeTable *table, */ static void disas_uncond_b_imm(DisasContext *s, uint32_t insn) { - uint64_t addr = s->pc + sextract32(insn, 0, 26) * 4 - 4; + uint64_t addr = s->pc_curr + sextract32(insn, 0, 26) * 4; if (insn & (1U << 31)) { /* BL Branch with link */ @@ -XXX,XX +XXX,XX @@ static void disas_comp_b_imm(DisasContext *s, uint32_t insn) sf = extract32(insn, 31, 1); op = extract32(insn, 24, 1); /* 0: CBZ; 1: CBNZ */ rt = extract32(insn, 0, 5); - addr = s->pc + sextract32(insn, 5, 19) * 4 - 4; + addr = s->pc_curr + sextract32(insn, 5, 19) * 4; tcg_cmp = read_cpu_reg(s, rt, sf); label_match = gen_new_label(); @@ -XXX,XX +XXX,XX @@ static void disas_test_b_imm(DisasContext *s, uint32_t insn) bit_pos = (extract32(insn, 31, 1) << 5) | extract32(insn, 19, 5); op = extract32(insn, 24, 1); /* 0: TBZ; 1: TBNZ */ - addr = s->pc + sextract32(insn, 5, 14) * 4 - 4; + addr = s->pc_curr + sextract32(insn, 5, 14) * 4; rt = extract32(insn, 0, 5); tcg_cmp = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void disas_cond_b_imm(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - addr = s->pc + sextract32(insn, 5, 19) * 4 - 4; + addr = s->pc_curr + sextract32(insn, 5, 19) * 4; cond = extract32(insn, 0, 4); reset_btype(s); @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, TCGv_i32 tcg_syn, tcg_isread; uint32_t syndrome; - gen_a64_set_pc_im(s->pc - 4); + gen_a64_set_pc_im(s->pc_curr); tmpptr = tcg_const_ptr(ri); syndrome = syn_aa64_sysregtrap(op0, op1, op2, crn, crm, rt, isread); tcg_syn = tcg_const_i32(syndrome); @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) /* The pre HVC helper handles cases when HVC gets trapped * as an undefined insn by runtime configuration. */ - gen_a64_set_pc_im(s->pc - 4); + gen_a64_set_pc_im(s->pc_curr); gen_helper_pre_hvc(cpu_env); gen_ss_advance(s); gen_exception_insn(s, 0, EXCP_HVC, syn_aa64_hvc(imm16), 2); @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) unallocated_encoding(s); break; } - gen_a64_set_pc_im(s->pc - 4); + gen_a64_set_pc_im(s->pc_curr); tmp = tcg_const_i32(syn_aa64_smc(imm16)); gen_helper_pre_smc(cpu_env, tmp); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) tcg_rt = cpu_reg(s, rt); - clean_addr = tcg_const_i64((s->pc - 4) + imm); + clean_addr = tcg_const_i64(s->pc_curr + imm); if (is_vector) { do_fp_ld(s, rt, clean_addr, size); } else { @@ -XXX,XX +XXX,XX @@ static void disas_pc_rel_adr(DisasContext *s, uint32_t insn) offset = sextract64(insn, 5, 19); offset = offset << 2 | extract32(insn, 29, 2); rd = extract32(insn, 0, 5); - base = s->pc - 4; + base = s->pc_curr; if (page) { /* ADRP (page based) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) break; default: fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n", - __func__, insn, fpopcode, s->pc); + __func__, insn, fpopcode, s->pc_curr); g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) { uint32_t insn; + s->pc_curr = s->pc; insn = arm_ldl_code(env, s->pc, s->sctlr_b); s->insn = insn; s->pc += 4; diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_hvc(DisasContext *s, int imm16) * as an undefined insn by runtime configuration (ie before * the insn really executes). */ - gen_set_pc_im(s, s->pc - 4); + gen_set_pc_im(s, s->pc_curr); gen_helper_pre_hvc(cpu_env); /* Otherwise we will treat this as a real exception which * happens after execution of the insn. (The distinction matters @@ -XXX,XX +XXX,XX @@ static inline void gen_smc(DisasContext *s) */ TCGv_i32 tmp; - gen_set_pc_im(s, s->pc - 4); + gen_set_pc_im(s, s->pc_curr); tmp = tcg_const_i32(syn_aa32_smc()); gen_helper_pre_smc(cpu_env, tmp); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static void gen_msr_banked(DisasContext *s, int r, int sysm, int rn) /* Sync state because msr_banked() can raise exceptions */ gen_set_condexec(s); - gen_set_pc_im(s, s->pc - 4); + gen_set_pc_im(s, s->pc_curr); tcg_reg = load_reg(s, rn); tcg_tgtmode = tcg_const_i32(tgtmode); tcg_regno = tcg_const_i32(regno); @@ -XXX,XX +XXX,XX @@ static void gen_mrs_banked(DisasContext *s, int r, int sysm, int rn) /* Sync state because mrs_banked() can raise exceptions */ gen_set_condexec(s); - gen_set_pc_im(s, s->pc - 4); + gen_set_pc_im(s, s->pc_curr); tcg_reg = tcg_temp_new_i32(); tcg_tgtmode = tcg_const_i32(tgtmode); tcg_regno = tcg_const_i32(regno); @@ -XXX,XX +XXX,XX @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) } gen_set_condexec(s); - gen_set_pc_im(s, s->pc - 4); + gen_set_pc_im(s, s->pc_curr); tmpptr = tcg_const_ptr(ri); tcg_syn = tcg_const_i32(syndrome); tcg_isread = tcg_const_i32(isread); @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, tmp = tcg_const_i32(mode); /* get_r13_banked() will raise an exception if called from System mode */ gen_set_condexec(s); - gen_set_pc_im(s, s->pc - 4); + gen_set_pc_im(s, s->pc_curr); gen_helper_get_r13_banked(addr, cpu_env, tmp); tcg_temp_free_i32(tmp); switch (amode) { @@ -XXX,XX +XXX,XX @@ static void arm_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) return; } + dc->pc_curr = dc->pc; insn = arm_ldl_code(env, dc->pc, dc->sctlr_b); dc->insn = insn; dc->pc += 4; @@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) return; } + dc->pc_curr = dc->pc; insn = arm_lduw_code(env, dc->pc, dc->sctlr_b); is_16bit = thumb_insn_is_16bit(dc, dc->pc, insn); dc->pc += 2; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We currently have 3 different ways of computing the architectural value of "PC" as seen in the ARM ARM. The value of s->pc has been incremented past the current insn, but that is all. Thus for a32, PC = s->pc + 4; for t32, PC = s->pc; for t16, PC = s->pc + 2. These differing computations make it impossible at present to unify the various code paths. With the newly introduced s->pc_curr, we can compute the correct value for all cases, using the formula given in the ARM ARM. This changes the behaviour for load_reg() and load_reg_var() when called with reg==15 from a 32-bit Thumb instruction: previously they would have returned the incorrect value of pc_curr + 6, and now they will return the architecturally correct value of PC, which is pc_curr + 4. This will not affect well-behaved guest software, because all of the places we call these functions from T32 code are instructions where using r15 is UNPREDICTABLE. Using the architectural PC value here is more consistent with the T16 and A32 behaviour. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-4-richard.henderson@linaro.org [PMM: added commit message note about UNPREDICTABLE T32 cases] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 59 ++++++++++++++++-------------------------- 1 file changed, 23 insertions(+), 36 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void store_cpu_offset(TCGv_i32 var, int offset) #define store_cpu_field(var, name) \ store_cpu_offset(var, offsetof(CPUARMState, name)) +/* The architectural value of PC. */ +static uint32_t read_pc(DisasContext *s) +{ + return s->pc_curr + (s->thumb ? 4 : 8); +} + /* Set a variable to the value of a CPU register. */ static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) { if (reg == 15) { - uint32_t addr; - /* normally, since we updated PC, we need only to add one insn */ - if (s->thumb) - addr = (long)s->pc + 2; - else - addr = (long)s->pc + 4; - tcg_gen_movi_i32(var, addr); + tcg_gen_movi_i32(var, read_pc(s)); } else { tcg_gen_mov_i32(var, cpu_R[reg]); } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) /* branch link and change to thumb (blx <offset>) */ int32_t offset; - val = (uint32_t)s->pc; tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, val); + tcg_gen_movi_i32(tmp, s->pc); store_reg(s, 14, tmp); /* Sign-extend the 24-bit offset */ offset = (((int32_t)insn) << 8) >> 8; + val = read_pc(s); /* offset * 4 + bit24 * 2 + (thumb bit) */ val += (offset << 2) | ((insn >> 23) & 2) | 1; - /* pipeline offset */ - val += 4; /* protected by ARCH(5); above, near the start of uncond block */ gen_bx_im(s, val); return; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } else { /* store */ if (i == 15) { - /* special case: r15 = PC + 8 */ - val = (long)s->pc + 4; tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, val); + tcg_gen_movi_i32(tmp, read_pc(s)); } else if (user) { tmp = tcg_temp_new_i32(); tmp2 = tcg_const_i32(i); @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) int32_t offset; /* branch (and link) */ - val = (int32_t)s->pc; if (insn & (1 << 24)) { tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, val); + tcg_gen_movi_i32(tmp, s->pc); store_reg(s, 14, tmp); } offset = sextract32(insn << 2, 0, 26); - val += offset + 4; - gen_jmp(s, val); + gen_jmp(s, read_pc(s) + offset); } break; case 0xc: @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(addr); } else if ((insn & (7 << 5)) == 0) { /* Table Branch. */ - if (rn == 15) { - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, s->pc); - } else { - addr = load_reg(s, rn); - } + addr = load_reg(s, rn); tmp = load_reg(s, rm); tcg_gen_add_i32(addr, addr, tmp); if (insn & (1 << 4)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } tcg_temp_free_i32(addr); tcg_gen_shli_i32(tmp, tmp, 1); - tcg_gen_addi_i32(tmp, tmp, s->pc); + tcg_gen_addi_i32(tmp, tmp, read_pc(s)); store_reg(s, 15, tmp); } else { bool is_lasr = false; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tcg_gen_movi_i32(cpu_R[14], s->pc | 1); } - offset += s->pc; + offset += read_pc(s); if (insn & (1 << 12)) { /* b/bl */ gen_jmp(s, offset); @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) offset |= (insn & (1 << 11)) << 8; /* jump to the offset */ - gen_jmp(s, s->pc + offset); + gen_jmp(s, read_pc(s) + offset); } } else { /* @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) if (insn & (1 << 11)) { rd = (insn >> 8) & 7; /* load pc-relative. Bit 1 of PC is ignored. */ - val = s->pc + 2 + ((insn & 0xff) * 4); + val = read_pc(s) + ((insn & 0xff) * 4); val &= ~(uint32_t)2; addr = tcg_temp_new_i32(); tcg_gen_movi_i32(addr, val); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) } else { /* PC. bit 1 is ignored. */ tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, (s->pc + 2) & ~(uint32_t)2); + tcg_gen_movi_i32(tmp, read_pc(s) & ~(uint32_t)2); } val = (insn & 0xff) * 4; tcg_gen_addi_i32(tmp, tmp, val); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, s->condlabel); tcg_temp_free_i32(tmp); offset = ((insn & 0xf8) >> 2) | (insn & 0x200) >> 3; - val = (uint32_t)s->pc + 2; - val += offset; - gen_jmp(s, val); + gen_jmp(s, read_pc(s) + offset); break; case 15: /* IT, nop-hint. */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) arm_skip_unless(s, cond); /* jump to the offset */ - val = (uint32_t)s->pc + 2; + val = read_pc(s); offset = ((int32_t)insn << 24) >> 24; val += offset << 1; gen_jmp(s, val); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) break; } /* unconditional branch */ - val = (uint32_t)s->pc; + val = read_pc(s); offset = ((int32_t)insn << 21) >> 21; - val += (offset << 1) + 2; + val += offset << 1; gen_jmp(s, val); break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) /* 0b1111_0xxx_xxxx_xxxx : BL/BLX prefix */ uint32_t uoffset = ((int32_t)insn << 21) >> 9; - tcg_gen_movi_i32(cpu_R[14], s->pc + 2 + uoffset); + tcg_gen_movi_i32(cpu_R[14], read_pc(s) + uoffset); } break; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Provide a common routine for the places that require ALIGN(PC, 4) as the base address as opposed to plain PC. The two are always the same for A32, but the difference is meaningful for thumb mode. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 38 ++------ target/arm/translate.c | 166 +++++++++++++++------------------ 2 files changed, 82 insertions(+), 122 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) offset = -offset; } - if (s->thumb && a->rn == 15) { - /* This is actually UNPREDICTABLE */ - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, s->pc & ~2); - } else { - addr = load_reg(s, a->rn); - } - tcg_gen_addi_i32(addr, addr, offset); + /* For thumb, use of PC is UNPREDICTABLE. */ + addr = add_reg_for_lit(s, a->rn, offset); tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) offset = -offset; } - if (s->thumb && a->rn == 15) { - /* This is actually UNPREDICTABLE */ - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, s->pc & ~2); - } else { - addr = load_reg(s, a->rn); - } - tcg_gen_addi_i32(addr, addr, offset); + /* For thumb, use of PC is UNPREDICTABLE. */ + addr = add_reg_for_lit(s, a->rn, offset); tmp = tcg_temp_new_i64(); if (a->l) { gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) return true; } - if (s->thumb && a->rn == 15) { - /* This is actually UNPREDICTABLE */ - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, s->pc & ~2); - } else { - addr = load_reg(s, a->rn); - } + /* For thumb, use of PC is UNPREDICTABLE. */ + addr = add_reg_for_lit(s, a->rn, 0); if (a->p) { /* pre-decrement */ tcg_gen_addi_i32(addr, addr, -(a->imm << 2)); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) return true; } - if (s->thumb && a->rn == 15) { - /* This is actually UNPREDICTABLE */ - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, s->pc & ~2); - } else { - addr = load_reg(s, a->rn); - } + /* For thumb, use of PC is UNPREDICTABLE. */ + addr = add_reg_for_lit(s, a->rn, 0); if (a->p) { /* pre-decrement */ tcg_gen_addi_i32(addr, addr, -(a->imm << 2)); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) return tmp; } +/* + * Create a new temp, REG + OFS, except PC is ALIGN(PC, 4). + * This is used for load/store for which use of PC implies (literal), + * or ADD that implies ADR. + */ +static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + + if (reg == 15) { + tcg_gen_movi_i32(tmp, (read_pc(s) & ~3) + ofs); + } else { + tcg_gen_addi_i32(tmp, cpu_R[reg], ofs); + } + return tmp; +} + /* Set a CPU register. The source must be a temporary and will be marked as dead. */ static void store_reg(DisasContext *s, int reg, TCGv_i32 var) @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) */ bool wback = extract32(insn, 21, 1); - if (rn == 15) { - if (insn & (1 << 21)) { - /* UNPREDICTABLE */ - goto illegal_op; - } - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, s->pc & ~3); - } else { - addr = load_reg(s, rn); + if (rn == 15 && (insn & (1 << 21))) { + /* UNPREDICTABLE */ + goto illegal_op; } + + addr = add_reg_for_lit(s, rn, 0); offset = (insn & 0xff) * 4; if ((insn & (1 << 23)) == 0) { offset = -offset; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) store_reg(s, rd, tmp); } else { /* Add/sub 12-bit immediate. */ - if (rn == 15) { - offset = s->pc & ~(uint32_t)3; - if (insn & (1 << 23)) - offset -= imm; - else - offset += imm; - tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, offset); - store_reg(s, rd, tmp); + if (insn & (1 << 23)) { + imm = -imm; + } + tmp = add_reg_for_lit(s, rn, imm); + if (rn == 13 && rd == 13) { + /* ADD SP, SP, imm or SUB SP, SP, imm */ + store_sp_checked(s, tmp); } else { - tmp = load_reg(s, rn); - if (insn & (1 << 23)) - tcg_gen_subi_i32(tmp, tmp, imm); - else - tcg_gen_addi_i32(tmp, tmp, imm); - if (rn == 13 && rd == 13) { - /* ADD SP, SP, imm or SUB SP, SP, imm */ - store_sp_checked(s, tmp); - } else { - store_reg(s, rd, tmp); - } + store_reg(s, rd, tmp); } } } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } } memidx = get_mem_index(s); - if (rn == 15) { - addr = tcg_temp_new_i32(); - /* PC relative. */ - /* s->pc has already been incremented by 4. */ - imm = s->pc & 0xfffffffc; - if (insn & (1 << 23)) - imm += insn & 0xfff; - else - imm -= insn & 0xfff; - tcg_gen_movi_i32(addr, imm); + imm = insn & 0xfff; + if (insn & (1 << 23)) { + /* PC relative or Positive offset. */ + addr = add_reg_for_lit(s, rn, imm); + } else if (rn == 15) { + /* PC relative with negative offset. */ + addr = add_reg_for_lit(s, rn, -imm); } else { addr = load_reg(s, rn); - if (insn & (1 << 23)) { - /* Positive offset. */ - imm = insn & 0xfff; - tcg_gen_addi_i32(addr, addr, imm); - } else { - imm = insn & 0xff; - switch ((insn >> 8) & 0xf) { - case 0x0: /* Shifted Register. */ - shift = (insn >> 4) & 0xf; - if (shift > 3) { - tcg_temp_free_i32(addr); - goto illegal_op; - } - tmp = load_reg(s, rm); - if (shift) - tcg_gen_shli_i32(tmp, tmp, shift); - tcg_gen_add_i32(addr, addr, tmp); - tcg_temp_free_i32(tmp); - break; - case 0xc: /* Negative offset. */ - tcg_gen_addi_i32(addr, addr, -imm); - break; - case 0xe: /* User privilege. */ - tcg_gen_addi_i32(addr, addr, imm); - memidx = get_a32_user_mem_index(s); - break; - case 0x9: /* Post-decrement. */ - imm = -imm; - /* Fall through. */ - case 0xb: /* Post-increment. */ - postinc = 1; - writeback = 1; - break; - case 0xd: /* Pre-decrement. */ - imm = -imm; - /* Fall through. */ - case 0xf: /* Pre-increment. */ - writeback = 1; - break; - default: + imm = insn & 0xff; + switch ((insn >> 8) & 0xf) { + case 0x0: /* Shifted Register. */ + shift = (insn >> 4) & 0xf; + if (shift > 3) { tcg_temp_free_i32(addr); goto illegal_op; } + tmp = load_reg(s, rm); + if (shift) { + tcg_gen_shli_i32(tmp, tmp, shift); + } + tcg_gen_add_i32(addr, addr, tmp); + tcg_temp_free_i32(tmp); + break; + case 0xc: /* Negative offset. */ + tcg_gen_addi_i32(addr, addr, -imm); + break; + case 0xe: /* User privilege. */ + tcg_gen_addi_i32(addr, addr, imm); + memidx = get_a32_user_mem_index(s); + break; + case 0x9: /* Post-decrement. */ + imm = -imm; + /* Fall through. */ + case 0xb: /* Post-increment. */ + postinc = 1; + writeback = 1; + break; + case 0xd: /* Pre-decrement. */ + imm = -imm; + /* Fall through. */ + case 0xf: /* Pre-increment. */ + writeback = 1; + break; + default: + tcg_temp_free_i32(addr); + goto illegal_op; } } @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) if (insn & (1 << 11)) { rd = (insn >> 8) & 7; /* load pc-relative. Bit 1 of PC is ignored. */ - val = read_pc(s) + ((insn & 0xff) * 4); - val &= ~(uint32_t)2; - addr = tcg_temp_new_i32(); - tcg_gen_movi_i32(addr, val); + addr = add_reg_for_lit(s, 15, (insn & 0xff) * 4); tmp = tcg_temp_new_i32(); gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) * - Add PC/SP (immediate) */ rd = (insn >> 8) & 7; - if (insn & (1 << 11)) { - /* SP */ - tmp = load_reg(s, 13); - } else { - /* PC. bit 1 is ignored. */ - tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, read_pc(s) & ~(uint32_t)2); - } val = (insn & 0xff) * 4; - tcg_gen_addi_i32(tmp, tmp, val); + tmp = add_reg_for_lit(s, insn & (1 << 11) ? 13 : 15, val); store_reg(s, rd, tmp); break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The thumb bit has already been removed from s->pc, and is always even. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) 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 void gen_exception_bkpt_insn(DisasContext *s, int offset, uint32_t syn) /* Force a TB lookup after an instruction that changes the CPU state. */ static inline void gen_lookup_tb(DisasContext *s) { - tcg_gen_movi_i32(cpu_R[15], s->pc & ~1); + tcg_gen_movi_i32(cpu_R[15], s->pc); s->base.is_jmp = DISAS_EXIT; } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * self-modifying code correctly and also to take * any pending interrupts immediately. */ - gen_goto_tb(s, 0, s->pc & ~1); + gen_goto_tb(s, 0, s->pc); return; case 7: /* sb */ if ((insn & 0xf) || !dc_isar_feature(aa32_sb, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * for TCG; MB and end the TB instead. */ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); - gen_goto_tb(s, 0, s->pc & ~1); + gen_goto_tb(s, 0, s->pc); return; default: goto illegal_op; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) * and also to take any pending interrupts * immediately. */ - gen_goto_tb(s, 0, s->pc & ~1); + gen_goto_tb(s, 0, s->pc); break; case 7: /* sb */ if ((insn & 0xf) || !dc_isar_feature(aa32_sb, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) * for TCG; MB and end the TB instead. */ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); - gen_goto_tb(s, 0, s->pc & ~1); + gen_goto_tb(s, 0, s->pc); break; default: goto illegal_op; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We must update s->base.pc_next when we return from the translate_insn hook to the main translator loop. By incrementing s->base.pc_next immediately after reading the insn word, "pc_next" contains the address of the next instruction throughout translation. All remaining uses of s->pc are referencing the address of the next insn, so this is now a simple global replacement. Remove the "s->pc" field. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 1 - target/arm/translate-a64.c | 51 +++++++++--------- target/arm/translate.c | 103 ++++++++++++++++++------------------- 3 files changed, 72 insertions(+), 83 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { DisasContextBase base; const ARMISARegisters *isar; - target_ulong pc; /* The address of the current instruction being translated. */ target_ulong pc_curr; target_ulong page_start; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_exception_internal(int excp) static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) { - gen_a64_set_pc_im(s->pc - offset); + gen_a64_set_pc_im(s->base.pc_next - offset); gen_exception_internal(excp); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) static void gen_exception_insn(DisasContext *s, int offset, int excp, uint32_t syndrome, uint32_t target_el) { - gen_a64_set_pc_im(s->pc - offset); + gen_a64_set_pc_im(s->base.pc_next - offset); gen_exception(excp, syndrome, target_el); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void gen_exception_bkpt_insn(DisasContext *s, int offset, { TCGv_i32 tcg_syn; - gen_a64_set_pc_im(s->pc - offset); + gen_a64_set_pc_im(s->base.pc_next - offset); tcg_syn = tcg_const_i32(syndrome); gen_helper_exception_bkpt_insn(cpu_env, tcg_syn); tcg_temp_free_i32(tcg_syn); @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_imm(DisasContext *s, uint32_t insn) if (insn & (1U << 31)) { /* BL Branch with link */ - tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); + tcg_gen_movi_i64(cpu_reg(s, 30), s->base.pc_next); } /* B Branch / BL Branch with link */ @@ -XXX,XX +XXX,XX @@ static void disas_comp_b_imm(DisasContext *s, uint32_t insn) tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ, tcg_cmp, 0, label_match); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); gen_set_label(label_match); gen_goto_tb(s, 1, addr); } @@ -XXX,XX +XXX,XX @@ static void disas_test_b_imm(DisasContext *s, uint32_t insn) tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ, tcg_cmp, 0, label_match); tcg_temp_free_i64(tcg_cmp); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); gen_set_label(label_match); gen_goto_tb(s, 1, addr); } @@ -XXX,XX +XXX,XX @@ static void disas_cond_b_imm(DisasContext *s, uint32_t insn) /* genuinely conditional branches */ TCGLabel *label_match = gen_new_label(); arm_gen_test_cc(cond, label_match); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); gen_set_label(label_match); gen_goto_tb(s, 1, addr); } else { @@ -XXX,XX +XXX,XX @@ static void handle_sync(DisasContext *s, uint32_t insn, * any pending interrupts immediately. */ reset_btype(s); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); return; case 7: /* SB */ @@ -XXX,XX +XXX,XX @@ static void handle_sync(DisasContext *s, uint32_t insn, * MB and end the TB instead. */ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); return; default: @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) gen_a64_set_pc(s, dst); /* BLR also needs to load return address */ if (opc == 1) { - tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); + tcg_gen_movi_i64(cpu_reg(s, 30), s->base.pc_next); } break; @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) gen_a64_set_pc(s, dst); /* BLRAA also needs to load return address */ if (opc == 9) { - tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); + tcg_gen_movi_i64(cpu_reg(s, 30), s->base.pc_next); } break; @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) { uint32_t insn; - s->pc_curr = s->pc; - insn = arm_ldl_code(env, s->pc, s->sctlr_b); + s->pc_curr = s->base.pc_next; + insn = arm_ldl_code(env, s->base.pc_next, s->sctlr_b); s->insn = insn; - s->pc += 4; + s->base.pc_next += 4; s->fp_access_checked = false; @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, int bound, core_mmu_idx; dc->isar = &arm_cpu->isar; - dc->pc = dc->base.pc_first; dc->condjmp = 0; dc->aarch64 = 1; @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *dc = container_of(dcbase, DisasContext, base); - tcg_gen_insn_start(dc->pc, 0, 0); + tcg_gen_insn_start(dc->base.pc_next, 0, 0); dc->insn_start = tcg_last_op(); } @@ -XXX,XX +XXX,XX @@ static bool aarch64_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu, DisasContext *dc = container_of(dcbase, DisasContext, base); if (bp->flags & BP_CPU) { - gen_a64_set_pc_im(dc->pc); + gen_a64_set_pc_im(dc->base.pc_next); gen_helper_check_breakpoints(cpu_env); /* End the TB early; it likely won't be executed */ dc->base.is_jmp = DISAS_TOO_MANY; @@ -XXX,XX +XXX,XX @@ static bool aarch64_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu, to for it to be properly cleared -- thus we increment the PC here so that the logic setting tb->size below does the right thing. */ - dc->pc += 4; + dc->base.pc_next += 4; dc->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) disas_a64_insn(env, dc); } - dc->base.pc_next = dc->pc; translator_loop_temp_check(&dc->base); } @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) */ switch (dc->base.is_jmp) { default: - gen_a64_set_pc_im(dc->pc); + gen_a64_set_pc_im(dc->base.pc_next); /* fall through */ case DISAS_EXIT: case DISAS_JUMP: @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) switch (dc->base.is_jmp) { case DISAS_NEXT: case DISAS_TOO_MANY: - gen_goto_tb(dc, 1, dc->pc); + gen_goto_tb(dc, 1, dc->base.pc_next); break; default: case DISAS_UPDATE: - gen_a64_set_pc_im(dc->pc); + gen_a64_set_pc_im(dc->base.pc_next); /* fall through */ case DISAS_EXIT: tcg_gen_exit_tb(NULL, 0); @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) case DISAS_SWI: break; case DISAS_WFE: - gen_a64_set_pc_im(dc->pc); + gen_a64_set_pc_im(dc->base.pc_next); gen_helper_wfe(cpu_env); break; case DISAS_YIELD: - gen_a64_set_pc_im(dc->pc); + gen_a64_set_pc_im(dc->base.pc_next); gen_helper_yield(cpu_env); break; case DISAS_WFI: @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) */ TCGv_i32 tmp = tcg_const_i32(4); - gen_a64_set_pc_im(dc->pc); + gen_a64_set_pc_im(dc->base.pc_next); gen_helper_wfi(cpu_env, tmp); tcg_temp_free_i32(tmp); /* The helper doesn't necessarily throw an exception, but we @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) } } } - - /* Functions above can change dc->pc, so re-align db->pc_next */ - dc->base.pc_next = dc->pc; } static void aarch64_tr_disas_log(const DisasContextBase *dcbase, diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_blxns(DisasContext *s, int rm) * We do however need to set the PC, because the blxns helper reads it. * The blxns helper may throw an exception. */ - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); gen_helper_v7m_blxns(cpu_env, var); tcg_temp_free_i32(var); s->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static inline void gen_hvc(DisasContext *s, int imm16) * for single stepping.) */ s->svc_imm = imm16; - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->base.is_jmp = DISAS_HVC; } @@ -XXX,XX +XXX,XX @@ static inline void gen_smc(DisasContext *s) tmp = tcg_const_i32(syn_aa32_smc()); gen_helper_pre_smc(cpu_env, tmp); tcg_temp_free_i32(tmp); - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->base.is_jmp = DISAS_SMC; } static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) { gen_set_condexec(s); - gen_set_pc_im(s, s->pc - offset); + gen_set_pc_im(s, s->base.pc_next - offset); gen_exception_internal(excp); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void gen_exception_insn(DisasContext *s, int offset, int excp, int syn, uint32_t target_el) { gen_set_condexec(s); - gen_set_pc_im(s, s->pc - offset); + gen_set_pc_im(s, s->base.pc_next - offset); gen_exception(excp, syn, target_el); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void gen_exception_bkpt_insn(DisasContext *s, int offset, uint32_t syn) TCGv_i32 tcg_syn; gen_set_condexec(s); - gen_set_pc_im(s, s->pc - offset); + gen_set_pc_im(s, s->base.pc_next - offset); tcg_syn = tcg_const_i32(syn); gen_helper_exception_bkpt_insn(cpu_env, tcg_syn); tcg_temp_free_i32(tcg_syn); @@ -XXX,XX +XXX,XX @@ static void gen_exception_bkpt_insn(DisasContext *s, int offset, uint32_t syn) /* Force a TB lookup after an instruction that changes the CPU state. */ static inline void gen_lookup_tb(DisasContext *s) { - tcg_gen_movi_i32(cpu_R[15], s->pc); + tcg_gen_movi_i32(cpu_R[15], s->base.pc_next); s->base.is_jmp = DISAS_EXIT; } @@ -XXX,XX +XXX,XX @@ static inline bool use_goto_tb(DisasContext *s, target_ulong dest) { #ifndef CONFIG_USER_ONLY return (s->base.tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK) || - ((s->pc - 1) & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK); + ((s->base.pc_next - 1) & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK); #else return true; #endif @@ -XXX,XX +XXX,XX @@ static void gen_nop_hint(DisasContext *s, int val) */ case 1: /* yield */ if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->base.is_jmp = DISAS_YIELD; } break; case 3: /* wfi */ - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->base.is_jmp = DISAS_WFI; break; case 2: /* wfe */ if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->base.is_jmp = DISAS_WFE; } break; @@ -XXX,XX +XXX,XX @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) if (isread) { return 1; } - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->base.is_jmp = DISAS_WFI; return 0; default: @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * self-modifying code correctly and also to take * any pending interrupts immediately. */ - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); return; case 7: /* sb */ if ((insn & 0xf) || !dc_isar_feature(aa32_sb, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * for TCG; MB and end the TB instead. */ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); return; default: goto illegal_op; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) int32_t offset; tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, s->pc); + tcg_gen_movi_i32(tmp, s->base.pc_next); store_reg(s, 14, tmp); /* Sign-extend the 24-bit offset */ offset = (((int32_t)insn) << 8) >> 8; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) /* branch link/exchange thumb (blx) */ tmp = load_reg(s, rm); tmp2 = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp2, s->pc); + tcg_gen_movi_i32(tmp2, s->base.pc_next); store_reg(s, 14, tmp2); gen_bx(s, tmp); break; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) /* branch (and link) */ if (insn & (1 << 24)) { tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, s->pc); + tcg_gen_movi_i32(tmp, s->base.pc_next); store_reg(s, 14, tmp); } offset = sextract32(insn << 2, 0, 26); @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) break; case 0xf: /* swi */ - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->svc_imm = extract32(insn, 0, 24); s->base.is_jmp = DISAS_SWI; break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) if (insn & (1 << 14)) { /* Branch and link. */ - tcg_gen_movi_i32(cpu_R[14], s->pc | 1); + tcg_gen_movi_i32(cpu_R[14], s->base.pc_next | 1); } offset += read_pc(s); @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) * and also to take any pending interrupts * immediately. */ - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); break; case 7: /* sb */ if ((insn & 0xf) || !dc_isar_feature(aa32_sb, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) * for TCG; MB and end the TB instead. */ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); - gen_goto_tb(s, 0, s->pc); + gen_goto_tb(s, 0, s->base.pc_next); break; default: goto illegal_op; @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) /* BLX/BX */ tmp = load_reg(s, rm); if (link) { - val = (uint32_t)s->pc | 1; + val = (uint32_t)s->base.pc_next | 1; tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, val); store_reg(s, 14, tmp2); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) if (cond == 0xf) { /* swi */ - gen_set_pc_im(s, s->pc); + gen_set_pc_im(s, s->base.pc_next); s->svc_imm = extract32(insn, 0, 8); s->base.is_jmp = DISAS_SWI; break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) tcg_gen_andi_i32(tmp, tmp, 0xfffffffc); tmp2 = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp2, s->pc | 1); + tcg_gen_movi_i32(tmp2, s->base.pc_next | 1); store_reg(s, 14, tmp2); gen_bx(s, tmp); break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) tcg_gen_addi_i32(tmp, tmp, offset); tmp2 = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp2, s->pc | 1); + tcg_gen_movi_i32(tmp2, s->base.pc_next | 1); store_reg(s, 14, tmp2); gen_bx(s, tmp); } else { @@ -XXX,XX +XXX,XX @@ undef: static bool insn_crosses_page(CPUARMState *env, DisasContext *s) { - /* Return true if the insn at dc->pc might cross a page boundary. + /* Return true if the insn at dc->base.pc_next might cross a page boundary. * (False positives are OK, false negatives are not.) * We know this is a Thumb insn, and our caller ensures we are - * only called if dc->pc is less than 4 bytes from the page + * only called if dc->base.pc_next is less than 4 bytes from the page * boundary, so we cross the page if the first 16 bits indicate * that this is a 32 bit insn. */ - uint16_t insn = arm_lduw_code(env, s->pc, s->sctlr_b); + uint16_t insn = arm_lduw_code(env, s->base.pc_next, s->sctlr_b); - return !thumb_insn_is_16bit(s, s->pc, insn); + return !thumb_insn_is_16bit(s, s->base.pc_next, insn); } static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) uint32_t condexec, core_mmu_idx; dc->isar = &cpu->isar; - dc->pc = dc->base.pc_first; dc->condjmp = 0; dc->aarch64 = 0; @@ -XXX,XX +XXX,XX @@ static void arm_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) { DisasContext *dc = container_of(dcbase, DisasContext, base); - tcg_gen_insn_start(dc->pc, + tcg_gen_insn_start(dc->base.pc_next, (dc->condexec_cond << 4) | (dc->condexec_mask >> 1), 0); dc->insn_start = tcg_last_op(); @@ -XXX,XX +XXX,XX @@ static bool arm_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu, if (bp->flags & BP_CPU) { gen_set_condexec(dc); - gen_set_pc_im(dc, dc->pc); + gen_set_pc_im(dc, dc->base.pc_next); gen_helper_check_breakpoints(cpu_env); /* End the TB early; it's likely not going to be executed */ dc->base.is_jmp = DISAS_TOO_MANY; @@ -XXX,XX +XXX,XX @@ static bool arm_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu, tb->size below does the right thing. */ /* TODO: Advance PC by correct instruction length to * avoid disassembler error messages */ - dc->pc += 2; + dc->base.pc_next += 2; dc->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static bool arm_pre_translate_insn(DisasContext *dc) { #ifdef CONFIG_USER_ONLY /* Intercept jump to the magic kernel page. */ - if (dc->pc >= 0xffff0000) { + if (dc->base.pc_next >= 0xffff0000) { /* We always get here via a jump, so know we are not in a conditional execution block. */ gen_exception_internal(EXCP_KERNEL_TRAP); @@ -XXX,XX +XXX,XX @@ static void arm_post_translate_insn(DisasContext *dc) gen_set_label(dc->condlabel); dc->condjmp = 0; } - dc->base.pc_next = dc->pc; translator_loop_temp_check(&dc->base); } @@ -XXX,XX +XXX,XX @@ static void arm_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) return; } - dc->pc_curr = dc->pc; - insn = arm_ldl_code(env, dc->pc, dc->sctlr_b); + dc->pc_curr = dc->base.pc_next; + insn = arm_ldl_code(env, dc->base.pc_next, dc->sctlr_b); dc->insn = insn; - dc->pc += 4; + dc->base.pc_next += 4; disas_arm_insn(dc, insn); arm_post_translate_insn(dc); @@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) return; } - dc->pc_curr = dc->pc; - insn = arm_lduw_code(env, dc->pc, dc->sctlr_b); - is_16bit = thumb_insn_is_16bit(dc, dc->pc, insn); - dc->pc += 2; + dc->pc_curr = dc->base.pc_next; + insn = arm_lduw_code(env, dc->base.pc_next, dc->sctlr_b); + is_16bit = thumb_insn_is_16bit(dc, dc->base.pc_next, insn); + dc->base.pc_next += 2; if (!is_16bit) { - uint32_t insn2 = arm_lduw_code(env, dc->pc, dc->sctlr_b); + uint32_t insn2 = arm_lduw_code(env, dc->base.pc_next, dc->sctlr_b); insn = insn << 16 | insn2; - dc->pc += 2; + dc->base.pc_next += 2; } dc->insn = insn; @@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) * but isn't very efficient). */ if (dc->base.is_jmp == DISAS_NEXT - && (dc->pc - dc->page_start >= TARGET_PAGE_SIZE - || (dc->pc - dc->page_start >= TARGET_PAGE_SIZE - 3 + && (dc->base.pc_next - dc->page_start >= TARGET_PAGE_SIZE + || (dc->base.pc_next - dc->page_start >= TARGET_PAGE_SIZE - 3 && insn_crosses_page(env, dc)))) { dc->base.is_jmp = DISAS_TOO_MANY; } @@ -XXX,XX +XXX,XX @@ static void arm_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) case DISAS_NEXT: case DISAS_TOO_MANY: case DISAS_UPDATE: - gen_set_pc_im(dc, dc->pc); + gen_set_pc_im(dc, dc->base.pc_next); /* fall through */ default: /* FIXME: Single stepping a WFI insn will not halt the CPU. */ @@ -XXX,XX +XXX,XX @@ static void arm_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) switch(dc->base.is_jmp) { case DISAS_NEXT: case DISAS_TOO_MANY: - gen_goto_tb(dc, 1, dc->pc); + gen_goto_tb(dc, 1, dc->base.pc_next); break; case DISAS_JUMP: gen_goto_ptr(); break; case DISAS_UPDATE: - gen_set_pc_im(dc, dc->pc); + gen_set_pc_im(dc, dc->base.pc_next); /* fall through */ default: /* indicate that the hash table must be used to find the next TB */ @@ -XXX,XX +XXX,XX @@ static void arm_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) gen_set_label(dc->condlabel); gen_set_condexec(dc); if (unlikely(is_singlestepping(dc))) { - gen_set_pc_im(dc, dc->pc); + gen_set_pc_im(dc, dc->base.pc_next); gen_singlestep_exception(dc); } else { - gen_goto_tb(dc, 1, dc->pc); + gen_goto_tb(dc, 1, dc->base.pc_next); } } - - /* Functions above can change dc->pc, so re-align db->pc_next */ - dc->base.pc_next = dc->pc; } static void arm_tr_disas_log(const DisasContextBase *dcbase, CPUState *cpu) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The offset is variable depending on the instruction set, whereas we have stored values for the current pc and the next pc. Passing in the actual value is clearer in intent. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 25 ++++++++++++++----------- target/arm/translate-vfp.inc.c | 6 +++--- target/arm/translate.c | 31 ++++++++++++++++--------------- 3 files changed, 33 insertions(+), 29 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 gen_exception_internal_insn(DisasContext *s, int offset, int excp) s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_insn(DisasContext *s, int offset, int excp, +static void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, uint32_t syndrome, uint32_t target_el) { - gen_a64_set_pc_im(s->base.pc_next - offset); + gen_a64_set_pc_im(pc); gen_exception(excp, syndrome, target_el); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest) void unallocated_encoding(DisasContext *s) { /* Unallocated and reserved encodings are uncategorized */ - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); } @@ -XXX,XX +XXX,XX @@ static inline bool fp_access_check(DisasContext *s) return true; } - gen_exception_insn(s, 4, EXCP_UDEF, syn_fp_access_trap(1, 0xe, false), - s->fp_excp_el); + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); return false; } @@ -XXX,XX +XXX,XX @@ static inline bool fp_access_check(DisasContext *s) bool sve_access_check(DisasContext *s) { if (s->sve_excp_el) { - gen_exception_insn(s, 4, EXCP_UDEF, syn_sve_access_trap(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_sve_access_trap(), s->sve_excp_el); return false; } @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) switch (op2_ll) { case 1: /* SVC */ gen_ss_advance(s); - gen_exception_insn(s, 0, EXCP_SWI, syn_aa64_svc(imm16), - default_exception_el(s)); + gen_exception_insn(s, s->base.pc_next, EXCP_SWI, + syn_aa64_svc(imm16), default_exception_el(s)); break; case 2: /* HVC */ if (s->current_el == 0) { @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) gen_a64_set_pc_im(s->pc_curr); gen_helper_pre_hvc(cpu_env); gen_ss_advance(s); - gen_exception_insn(s, 0, EXCP_HVC, syn_aa64_hvc(imm16), 2); + gen_exception_insn(s, s->base.pc_next, EXCP_HVC, + syn_aa64_hvc(imm16), 2); break; case 3: /* SMC */ if (s->current_el == 0) { @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) gen_helper_pre_smc(cpu_env, tmp); tcg_temp_free_i32(tmp); gen_ss_advance(s); - gen_exception_insn(s, 0, EXCP_SMC, syn_aa64_smc(imm16), 3); + gen_exception_insn(s, s->base.pc_next, EXCP_SMC, + syn_aa64_smc(imm16), 3); break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) if (s->btype != 0 && s->guarded_page && !btype_destination_ok(insn, s->bt, s->btype)) { - gen_exception_insn(s, 4, EXCP_UDEF, syn_btitrap(s->btype), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_btitrap(s->btype), default_exception_el(s)); return; } diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) { if (s->fp_excp_el) { if (arm_dc_feature(s, ARM_FEATURE_M)) { - gen_exception_insn(s, 4, EXCP_NOCP, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, syn_uncategorized(), s->fp_excp_el); } else { - gen_exception_insn(s, 4, EXCP_UDEF, + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); } @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) if (!s->vfp_enabled && !ignore_vfp_enabled) { assert(!arm_dc_feature(s, ARM_FEATURE_M)); - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); return false; } 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 void gen_exception_internal_insn(DisasContext *s, int offset, int excp) s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_insn(DisasContext *s, int offset, int excp, +static void gen_exception_insn(DisasContext *s, uint32_t pc, int excp, int syn, uint32_t target_el) { gen_set_condexec(s); - gen_set_pc_im(s, s->base.pc_next - offset); + gen_set_pc_im(s, pc); gen_exception(excp, syn, target_el); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) return; } - gen_exception_insn(s, s->thumb ? 2 : 4, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); } @@ -XXX,XX +XXX,XX @@ static bool msr_banked_access_decode(DisasContext *s, int r, int sysm, int rn, undef: /* If we get here then some access check did not pass */ - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), exc_target); + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_uncategorized(), exc_target); return false; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) * for attempts to execute invalid vfp/neon encodings with FP disabled. */ if (s->fp_excp_el) { - gen_exception_insn(s, 4, EXCP_UDEF, + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) * for attempts to execute invalid vfp/neon encodings with FP disabled. */ if (s->fp_excp_el) { - gen_exception_insn(s, 4, EXCP_UDEF, + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) } if (s->fp_excp_el) { - gen_exception_insn(s, 4, EXCP_UDEF, + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) off_rm = vfp_reg_offset(0, rm); } if (s->fp_excp_el) { - gen_exception_insn(s, 4, EXCP_UDEF, + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, * For the UNPREDICTABLE cases we choose to UNDEF. */ if (s->current_el == 1 && !s->ns && mode == ARM_CPU_MODE_MON) { - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), 3); + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), 3); return; } @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, } if (undef) { - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); return; } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * UsageFault exception. */ if (arm_dc_feature(s, ARM_FEATURE_M)) { - gen_exception_insn(s, 4, EXCP_INVSTATE, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_INVSTATE, syn_uncategorized(), default_exception_el(s)); return; } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) break; default: illegal_op: - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); break; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } /* All other insns: NOCP */ - gen_exception_insn(s, 4, EXCP_NOCP, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, syn_uncategorized(), default_exception_el(s)); break; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } return; illegal_op: - gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); } @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) return; illegal_op: undef: - gen_exception_insn(s, 2, EXCP_UDEF, syn_uncategorized(), + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), default_exception_el(s)); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The offset is variable depending on the instruction set. Passing in the actual value is clearer in intent. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 8 ++++---- target/arm/translate.c | 8 ++++---- 2 files changed, 8 insertions(+), 8 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 gen_exception_internal(int excp) tcg_temp_free_i32(tcg_excp); } -static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) +static void gen_exception_internal_insn(DisasContext *s, uint64_t pc, int excp) { - gen_a64_set_pc_im(s->base.pc_next - offset); + gen_a64_set_pc_im(pc); gen_exception_internal(excp); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) break; } #endif - gen_exception_internal_insn(s, 0, EXCP_SEMIHOST); + gen_exception_internal_insn(s, s->base.pc_next, EXCP_SEMIHOST); } else { unsupported_encoding(s, insn); } @@ -XXX,XX +XXX,XX @@ static bool aarch64_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu, /* End the TB early; it likely won't be executed */ dc->base.is_jmp = DISAS_TOO_MANY; } else { - gen_exception_internal_insn(dc, 0, EXCP_DEBUG); + gen_exception_internal_insn(dc, dc->base.pc_next, EXCP_DEBUG); /* The address covered by the breakpoint must be included in [tb->pc, tb->pc + tb->size) in order to for it to be properly cleared -- thus we diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_smc(DisasContext *s) s->base.is_jmp = DISAS_SMC; } -static void gen_exception_internal_insn(DisasContext *s, int offset, int excp) +static void gen_exception_internal_insn(DisasContext *s, uint32_t pc, int excp) { gen_set_condexec(s); - gen_set_pc_im(s, s->base.pc_next - offset); + gen_set_pc_im(s, pc); gen_exception_internal(excp); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) s->current_el != 0 && #endif (imm == (s->thumb ? 0x3c : 0xf000))) { - gen_exception_internal_insn(s, 0, EXCP_SEMIHOST); + gen_exception_internal_insn(s, s->base.pc_next, EXCP_SEMIHOST); return; } @@ -XXX,XX +XXX,XX @@ static bool arm_tr_breakpoint_check(DisasContextBase *dcbase, CPUState *cpu, /* End the TB early; it's likely not going to be executed */ dc->base.is_jmp = DISAS_TOO_MANY; } else { - gen_exception_internal_insn(dc, 0, EXCP_DEBUG); + gen_exception_internal_insn(dc, dc->base.pc_next, EXCP_DEBUG); /* The address covered by the breakpoint must be included in [tb->pc, tb->pc + tb->size) in order to for it to be properly cleared -- thus we -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Unlike the other more generic gen_exception{,_internal}_insn interfaces, breakpoints always refer to the current instruction. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 7 +++---- target/arm/translate.c | 8 ++++---- 2 files changed, 7 insertions(+), 8 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 gen_exception_insn(DisasContext *s, uint64_t pc, int excp, s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_bkpt_insn(DisasContext *s, int offset, - uint32_t syndrome) +static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syndrome) { TCGv_i32 tcg_syn; - gen_a64_set_pc_im(s->base.pc_next - offset); + gen_a64_set_pc_im(s->pc_curr); tcg_syn = tcg_const_i32(syndrome); gen_helper_exception_bkpt_insn(cpu_env, tcg_syn); tcg_temp_free_i32(tcg_syn); @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) break; } /* BRK */ - gen_exception_bkpt_insn(s, 4, syn_aa64_bkpt(imm16)); + gen_exception_bkpt_insn(s, syn_aa64_bkpt(imm16)); break; case 2: if (op2_ll != 0) { 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 void gen_exception_insn(DisasContext *s, uint32_t pc, int excp, s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_bkpt_insn(DisasContext *s, int offset, uint32_t syn) +static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syn) { TCGv_i32 tcg_syn; gen_set_condexec(s); - gen_set_pc_im(s, s->base.pc_next - offset); + gen_set_pc_im(s, s->pc_curr); tcg_syn = tcg_const_i32(syn); gen_helper_exception_bkpt_insn(cpu_env, tcg_syn); tcg_temp_free_i32(tcg_syn); @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) case 1: /* bkpt */ ARCH(5); - gen_exception_bkpt_insn(s, 4, syn_aa32_bkpt(imm16, false)); + gen_exception_bkpt_insn(s, syn_aa32_bkpt(imm16, false)); break; case 2: /* Hypervisor call (v7) */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) { int imm8 = extract32(insn, 0, 8); ARCH(5); - gen_exception_bkpt_insn(s, 2, syn_aa32_bkpt(imm8, true)); + gen_exception_bkpt_insn(s, syn_aa32_bkpt(imm8, true)); break; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Promote this function from aarch64 to fully general use. Use it to unify the code sequences for generating illegal opcode exceptions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 2 -- target/arm/translate.h | 2 ++ target/arm/translate-a64.c | 7 ------- target/arm/translate-vfp.inc.c | 3 +-- target/arm/translate.c | 22 ++++++++++++---------- 5 files changed, 15 insertions(+), 21 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_TRANSLATE_A64_H #define TARGET_ARM_TRANSLATE_A64_H -void unallocated_encoding(DisasContext *s); - #define unsupported_encoding(s, insn) \ do { \ qemu_log_mask(LOG_UNIMP, \ diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasCompare { bool value_global; } DisasCompare; +void unallocated_encoding(DisasContext *s); + /* Share the TCG temporaries common between 32 and 64 bit modes. */ extern TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF; extern TCGv_i64 cpu_exclusive_addr; 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 inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest) } } -void unallocated_encoding(DisasContext *s) -{ - /* Unallocated and reserved encodings are uncategorized */ - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); -} - static void init_tmp_a64_array(DisasContext *s) { #ifdef CONFIG_DEBUG_TCG diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) if (!s->vfp_enabled && !ignore_vfp_enabled) { assert(!arm_dc_feature(s, ARM_FEATURE_M)); - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); + unallocated_encoding(s); return false; } 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 void gen_exception_bkpt_insn(DisasContext *s, uint32_t syn) s->base.is_jmp = DISAS_NORETURN; } +void unallocated_encoding(DisasContext *s) +{ + /* Unallocated and reserved encodings are uncategorized */ + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), + default_exception_el(s)); +} + /* Force a TB lookup after an instruction that changes the CPU state. */ static inline void gen_lookup_tb(DisasContext *s) { @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) return; } - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); + unallocated_encoding(s); } static inline void gen_add_data_offset(DisasContext *s, unsigned int insn, @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, } if (undef) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); + unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) break; default: illegal_op: - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); + unallocated_encoding(s); break; } } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } return; illegal_op: - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); + unallocated_encoding(s); } static void disas_thumb_insn(DisasContext *s, uint32_t insn) @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(DisasContext *s, uint32_t insn) return; illegal_op: undef: - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); + unallocated_encoding(s); } static bool insn_crosses_page(CPUARMState *env, DisasContext *s) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Replace x = double_saturate(y) with x = add_saturate(y, y). There is no need for a separate more specialized helper. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190807045335.1361-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 1 - target/arm/op_helper.c | 15 --------------- target/arm/translate.c | 4 ++-- 3 files changed, 2 insertions(+), 18 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(add_saturate, i32, env, i32, i32) DEF_HELPER_3(sub_saturate, i32, env, i32, i32) DEF_HELPER_3(add_usaturate, i32, env, i32, i32) DEF_HELPER_3(sub_usaturate, i32, env, i32, i32) -DEF_HELPER_2(double_saturate, i32, env, s32) DEF_HELPER_FLAGS_2(sdiv, TCG_CALL_NO_RWG_SE, s32, s32, s32) DEF_HELPER_FLAGS_2(udiv, TCG_CALL_NO_RWG_SE, i32, i32, i32) DEF_HELPER_FLAGS_1(rbit, TCG_CALL_NO_RWG_SE, i32, i32) 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(sub_saturate)(CPUARMState *env, uint32_t a, uint32_t b) return res; } -uint32_t HELPER(double_saturate)(CPUARMState *env, int32_t val) -{ - uint32_t res; - if (val >= 0x40000000) { - res = ~SIGNBIT; - env->QF = 1; - } else if (val <= (int32_t)0xc0000000) { - res = SIGNBIT; - env->QF = 1; - } else { - res = val << 1; - } - return res; -} - uint32_t HELPER(add_usaturate)(CPUARMState *env, uint32_t a, uint32_t b) { uint32_t res = a + b; 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 void disas_arm_insn(DisasContext *s, unsigned int insn) tmp = load_reg(s, rm); tmp2 = load_reg(s, rn); if (op1 & 2) - gen_helper_double_saturate(tmp2, cpu_env, tmp2); + gen_helper_add_saturate(tmp2, cpu_env, tmp2, tmp2); if (op1 & 1) gen_helper_sub_saturate(tmp, cpu_env, tmp, tmp2); else @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp = load_reg(s, rn); tmp2 = load_reg(s, rm); if (op & 1) - gen_helper_double_saturate(tmp, cpu_env, tmp); + gen_helper_add_saturate(tmp, cpu_env, tmp, tmp); if (op & 2) gen_helper_sub_saturate(tmp, cpu_env, tmp2, tmp); else -- 2.20.1 From: Andrew Jones <drjones@redhat.com> If -cpu <cpu>,aarch64=off is used then KVM must also be used, and it and the host must support running the vcpu in 32-bit mode. Also, if -cpu <cpu>,aarch64=on is used, then it doesn't matter if kvm is enabled or not. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 14 ++++++++++++++ target/arm/cpu64.c | 12 ++++++------ target/arm/kvm64.c | 9 +++++++++ 3 files changed, 29 insertions(+), 6 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 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf); */ void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu); +/** + * kvm_arm_aarch32_supported: + * @cs: CPUState + * + * Returns: true if the KVM VCPU can enable AArch32 mode + * and false otherwise. + */ +bool kvm_arm_aarch32_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 void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu) cpu->host_cpu_probe_failed = true; } +static inline bool kvm_arm_aarch32_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 aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp) * restriction allows us to avoid fixing up functionality that assumes a * uniform execution state like do_interrupt. */ - if (!kvm_enabled()) { - error_setg(errp, "'aarch64' feature cannot be disabled " - "unless KVM is enabled"); - return; - } - if (value == false) { + if (!kvm_enabled() || !kvm_arm_aarch32_supported(CPU(cpu))) { + error_setg(errp, "'aarch64' feature cannot be disabled " + "unless KVM is enabled and 32-bit EL1 " + "is supported"); + return; + } unset_feature(&cpu->env, ARM_FEATURE_AARCH64); } else { set_feature(&cpu->env, ARM_FEATURE_AARCH64); 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 @@ #include "exec/gdbstub.h" #include "sysemu/sysemu.h" #include "sysemu/kvm.h" +#include "sysemu/kvm_int.h" #include "kvm_arm.h" +#include "hw/boards.h" #include "internals.h" static bool have_guest_debug; @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) return true; } +bool kvm_arm_aarch32_supported(CPUState *cpu) +{ + KVMState *s = KVM_STATE(current_machine->accelerator); + + return kvm_check_extension(s, KVM_CAP_ARM_EL1_32BIT); +} + #define ARM_CPU_ID_MPIDR 3, 0, 0, 0, 5 int kvm_arch_init_vcpu(CPUState *cs) -- 2.20.1 From: Andrew Jones <drjones@redhat.com> We first convert the pmu property from a static property to one with its own accessors. Then we use the set accessor to check if the PMU is supported when using KVM. Indeed a 32-bit KVM host does not support the PMU, so this check will catch an attempt to use it at property-set time. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 14 ++++++++++++++ target/arm/cpu.c | 30 +++++++++++++++++++++++++----- target/arm/kvm.c | 7 +++++++ 3 files changed, 46 insertions(+), 5 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 @@ void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu); */ bool kvm_arm_aarch32_supported(CPUState *cs); +/** + * bool kvm_arm_pmu_supported: + * @cs: CPUState + * + * Returns: true if the KVM VCPU can enable its PMU + * and false otherwise. + */ +bool kvm_arm_pmu_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_aarch32_supported(CPUState *cs) return false; } +static inline bool kvm_arm_pmu_supported(CPUState *cs) +{ + return false; +} + static inline int kvm_arm_get_max_vm_ipa_size(MachineState *ms) { return -ENOENT; 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 Property arm_cpu_has_el3_property = static Property arm_cpu_cfgend_property = DEFINE_PROP_BOOL("cfgend", ARMCPU, cfgend, false); -/* use property name "pmu" to match other archs and virt tools */ -static Property arm_cpu_has_pmu_property = - DEFINE_PROP_BOOL("pmu", ARMCPU, has_pmu, true); - static Property arm_cpu_has_vfp_property = DEFINE_PROP_BOOL("vfp", ARMCPU, has_vfp, true); @@ -XXX,XX +XXX,XX @@ static Property arm_cpu_pmsav7_dregion_property = pmsav7_dregion, qdev_prop_uint32, uint32_t); +static bool arm_get_pmu(Object *obj, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + + return cpu->has_pmu; +} + +static void arm_set_pmu(Object *obj, bool value, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + + if (value) { + if (kvm_enabled() && !kvm_arm_pmu_supported(CPU(cpu))) { + error_setg(errp, "'pmu' feature not supported by KVM on this host"); + return; + } + set_feature(&cpu->env, ARM_FEATURE_PMU); + } else { + unset_feature(&cpu->env, ARM_FEATURE_PMU); + } + cpu->has_pmu = value; +} + static void arm_get_init_svtor(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) } if (arm_feature(&cpu->env, ARM_FEATURE_PMU)) { - qdev_property_add_static(DEVICE(obj), &arm_cpu_has_pmu_property, + cpu->has_pmu = true; + object_property_add_bool(obj, "pmu", arm_get_pmu, arm_set_pmu, &error_abort); } 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 @@ void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu) env->features = arm_host_cpu_features.features; } +bool kvm_arm_pmu_supported(CPUState *cpu) +{ + KVMState *s = KVM_STATE(current_machine->accelerator); + + return kvm_check_extension(s, KVM_CAP_ARM_PMU_V3); +} + int kvm_arm_get_max_vm_ipa_size(MachineState *ms) { KVMState *s = KVM_STATE(ms->accelerator); -- 2.20.1 From: Andrew Jones <drjones@redhat.com> The current implementation of ZCR_ELx matches the architecture, only implementing the lower four bits, with the rest RAZ/WI. This puts a strict limit on ARM_MAX_VQ of 16. Make sure we don't let ARM_MAX_VQ grow without a corresponding update here. Suggested-by: Dave Martin <Dave.Martin@arm.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 1 + 1 file changed, 1 insertion(+) 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 zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, int new_len; /* Bits other than [3:0] are RAZ/WI. */ + QEMU_BUILD_BUG_ON(ARM_MAX_VQ > 16); raw_write(env, ri, value & 0xf); /* -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Unless we're guaranteed to always increase ARM_MAX_VQ by a multiple of four, then we should use DIV_ROUND_UP to ensure we get an appropriate array size. Signed-off-by: Andrew Jones <drjones@redhat.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 @@ typedef struct ARMVectorReg { #ifdef TARGET_AARCH64 /* In AArch32 mode, predicate registers do not exist at all. */ typedef struct ARMPredicateReg { - uint64_t p[2 * ARM_MAX_VQ / 8] QEMU_ALIGNED(16); + uint64_t p[DIV_ROUND_UP(2 * ARM_MAX_VQ, 8)] QEMU_ALIGNED(16); } ARMPredicateReg; /* In AArch32 mode, PAC keys do not exist at all. */ -- 2.20.1 From: Andrew Jones <drjones@redhat.com> A couple return -EINVAL's forgot their '-'s. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 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_put_registers(CPUState *cs, int level) write_cpustate_to_list(cpu, true); if (!write_list_to_kvmstate(cpu, level)) { - return EINVAL; + return -EINVAL; } kvm_arm_sync_mpstate_to_kvm(cpu); @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) } if (!write_kvmstate_to_list(cpu)) { - return EINVAL; + return -EINVAL; } /* Note that it's OK to have registers which aren't in CPUState, * so we can ignore a failure return here. -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Move the getting/putting of the fpsimd registers out of kvm_arch_get/put_registers() into their own helper functions to prepare for alternatively getting/putting SVE registers. No functional change. Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm64.c | 148 +++++++++++++++++++++++++++------------------ 1 file changed, 88 insertions(+), 60 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_arm_cpreg_level(uint64_t regidx) #define AARCH64_SIMD_CTRL_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U32 | \ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) +static int kvm_arch_put_fpsimd(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + struct kvm_one_reg reg; + uint32_t fpr; + int i, ret; + + for (i = 0; i < 32; i++) { + uint64_t *q = aa64_vfp_qreg(env, i); +#ifdef HOST_WORDS_BIGENDIAN + uint64_t fp_val[2] = { q[1], q[0] }; + reg.addr = (uintptr_t)fp_val; +#else + reg.addr = (uintptr_t)q; +#endif + reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); + 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; + } + + return 0; +} + int kvm_arch_put_registers(CPUState *cs, int level) { struct kvm_one_reg reg; - uint32_t fpr; uint64_t val; - int i; - int ret; + int i, ret; unsigned int el; ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) } } - /* Advanced SIMD and FP registers. */ - for (i = 0; i < 32; i++) { - uint64_t *q = aa64_vfp_qreg(env, i); -#ifdef HOST_WORDS_BIGENDIAN - uint64_t fp_val[2] = { q[1], q[0] }; - reg.addr = (uintptr_t)fp_val; -#else - reg.addr = (uintptr_t)q; -#endif - reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); - 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; - } - - fpr = vfp_get_fpcr(env); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg); + ret = kvm_arch_put_fpsimd(cs); if (ret) { return ret; } @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } +static int kvm_arch_get_fpsimd(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + struct kvm_one_reg reg; + uint32_t fpr; + int i, ret; + + for (i = 0; i < 32; i++) { + uint64_t *q = aa64_vfp_qreg(env, i); + reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); + reg.addr = (uintptr_t)q; + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); + if (ret) { + return ret; + } else { +#ifdef HOST_WORDS_BIGENDIAN + uint64_t t; + t = q[0], q[0] = q[1], q[1] = t; +#endif + } + } + + 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); + + return 0; +} + int kvm_arch_get_registers(CPUState *cs) { struct kvm_one_reg reg; uint64_t val; - uint32_t fpr; unsigned int el; - int i; - int ret; + int i, ret; ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) env->spsr = env->banked_spsr[i]; } - /* Advanced SIMD and FP registers */ - for (i = 0; i < 32; i++) { - uint64_t *q = aa64_vfp_qreg(env, i); - reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); - reg.addr = (uintptr_t)q; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); - if (ret) { - return ret; - } else { -#ifdef HOST_WORDS_BIGENDIAN - uint64_t t; - t = q[0], q[0] = q[1], q[1] = t; -#endif - } - } - - reg.addr = (uintptr_t)(&fpr); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg); + ret = kvm_arch_get_fpsimd(cs); if (ret) { return ret; } - vfp_set_fpsr(env, 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) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Extract is a compact combination of shift + and. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) 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 void gen_sar(TCGv_i32 dest, TCGv_i32 t0, TCGv_i32 t1) static void shifter_out_im(TCGv_i32 var, int shift) { - if (shift == 0) { - tcg_gen_andi_i32(cpu_CF, var, 1); - } else { - tcg_gen_shri_i32(cpu_CF, var, shift); - if (shift != 31) { - tcg_gen_andi_i32(cpu_CF, cpu_CF, 1); - } - } + tcg_gen_extract_i32(cpu_CF, var, shift, 1); } /* Shift by immediate. Includes special handling for shift == 0. */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Use deposit as the composit operation to merge the bits from the two inputs. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) 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 void disas_arm_insn(DisasContext *s, unsigned int insn) shift = (insn >> 7) & 0x1f; if (insn & (1 << 6)) { /* pkhtb */ - if (shift == 0) + if (shift == 0) { shift = 31; + } tcg_gen_sari_i32(tmp2, tmp2, shift); - tcg_gen_andi_i32(tmp, tmp, 0xffff0000); - tcg_gen_ext16u_i32(tmp2, tmp2); + tcg_gen_deposit_i32(tmp, tmp, tmp2, 0, 16); } else { /* pkhbt */ - if (shift) - tcg_gen_shli_i32(tmp2, tmp2, shift); - tcg_gen_ext16u_i32(tmp, tmp); - tcg_gen_andi_i32(tmp2, tmp2, 0xffff0000); + tcg_gen_shli_i32(tmp2, tmp2, shift); + tcg_gen_deposit_i32(tmp, tmp2, tmp, 0, 16); } - tcg_gen_or_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); store_reg(s, rd, tmp); } else if ((insn & 0x00200020) == 0x00200000) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) shift = ((insn >> 10) & 0x1c) | ((insn >> 6) & 0x3); if (insn & (1 << 5)) { /* pkhtb */ - if (shift == 0) + if (shift == 0) { shift = 31; + } tcg_gen_sari_i32(tmp2, tmp2, shift); - tcg_gen_andi_i32(tmp, tmp, 0xffff0000); - tcg_gen_ext16u_i32(tmp2, tmp2); + tcg_gen_deposit_i32(tmp, tmp, tmp2, 0, 16); } else { /* pkhbt */ - if (shift) - tcg_gen_shli_i32(tmp2, tmp2, shift); - tcg_gen_ext16u_i32(tmp, tmp); - tcg_gen_andi_i32(tmp2, tmp2, 0xffff0000); + tcg_gen_shli_i32(tmp2, tmp2, shift); + tcg_gen_deposit_i32(tmp, tmp2, tmp, 0, 16); } - tcg_gen_or_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); store_reg(s, rd, tmp); } else { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The immediate shift generator functions already test for, and eliminate, the case of a shift by zero. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) 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 void disas_arm_insn(DisasContext *s, unsigned int insn) shift = (insn >> 10) & 3; /* ??? In many cases it's not necessary to do a rotate, a shift is sufficient. */ - if (shift != 0) - tcg_gen_rotri_i32(tmp, tmp, shift * 8); + tcg_gen_rotri_i32(tmp, tmp, shift * 8); op1 = (insn >> 20) & 7; switch (op1) { case 0: gen_sxtb16(tmp); break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) shift = (insn >> 4) & 3; /* ??? In many cases it's not necessary to do a rotate, a shift is sufficient. */ - if (shift != 0) - tcg_gen_rotri_i32(tmp, tmp, shift * 8); + tcg_gen_rotri_i32(tmp, tmp, shift * 8); op = (insn >> 20) & 7; switch (op) { case 0: gen_sxth(tmp); break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) case 7: goto illegal_op; default: /* Saturate. */ - if (shift) { - if (op & 1) - tcg_gen_sari_i32(tmp, tmp, shift); - else - tcg_gen_shli_i32(tmp, tmp, shift); + if (op & 1) { + tcg_gen_sari_i32(tmp, tmp, shift); + } else { + tcg_gen_shli_i32(tmp, tmp, shift); } tmp2 = tcg_const_i32(imm); if (op & 4) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) goto illegal_op; } tmp = load_reg(s, rm); - if (shift) { - tcg_gen_shli_i32(tmp, tmp, shift); - } + tcg_gen_shli_i32(tmp, tmp, shift); tcg_gen_add_i32(addr, addr, tmp); tcg_temp_free_i32(tmp); break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The helper function is more documentary, and also already handles the case of rotate by zero. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) 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 void disas_arm_insn(DisasContext *s, unsigned int insn) /* CPSR = immediate */ val = insn & 0xff; shift = ((insn >> 8) & 0xf) * 2; - if (shift) - val = (val >> shift) | (val << (32 - shift)); + val = ror32(val, shift); i = ((insn & (1 << 22)) != 0); if (gen_set_psr_im(s, msr_mask(s, (insn >> 16) & 0xf, i), i, val)) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) /* immediate operand */ val = insn & 0xff; shift = ((insn >> 8) & 0xf) * 2; - if (shift) { - val = (val >> shift) | (val << (32 - shift)); - } + val = ror32(val, shift); tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, val); if (logic_cc && shift) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rotate is the more compact and obvious way to swap 16-bit elements of a 32-bit word. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) 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 TCGv_i64 gen_muls_i64_i32(TCGv_i32 a, TCGv_i32 b) /* Swap low and high halfwords. */ static void gen_swap_half(TCGv_i32 var) { - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_shri_i32(tmp, var, 16); - tcg_gen_shli_i32(var, var, 16); - tcg_gen_or_i32(var, var, tmp); - tcg_temp_free_i32(tmp); + tcg_gen_rotri_i32(var, var, 16); } /* Dual 16-bit add. Result placed in t0 and t1 is marked as dead. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> All of the inputs to these instructions are 32-bits. Rather than extend each input to 64-bits and then extract the high 32-bits of the output, use tcg_gen_muls2_i32 and other 32-bit generator functions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 72 +++++++++++++++--------------------------- 1 file changed, 26 insertions(+), 46 deletions(-) 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 void gen_revsh(TCGv_i32 var) tcg_gen_ext16s_i32(var, var); } -/* Return (b << 32) + a. Mark inputs as dead */ -static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv_i32 b) -{ - TCGv_i64 tmp64 = tcg_temp_new_i64(); - - tcg_gen_extu_i32_i64(tmp64, b); - tcg_temp_free_i32(b); - tcg_gen_shli_i64(tmp64, tmp64, 32); - tcg_gen_add_i64(a, tmp64, a); - - tcg_temp_free_i64(tmp64); - return a; -} - -/* Return (b << 32) - a. Mark inputs as dead. */ -static TCGv_i64 gen_subq_msw(TCGv_i64 a, TCGv_i32 b) -{ - TCGv_i64 tmp64 = tcg_temp_new_i64(); - - tcg_gen_extu_i32_i64(tmp64, b); - tcg_temp_free_i32(b); - tcg_gen_shli_i64(tmp64, tmp64, 32); - tcg_gen_sub_i64(a, tmp64, a); - - tcg_temp_free_i64(tmp64); - return a; -} - /* 32x32->64 multiply. Marks inputs as dead. */ static TCGv_i64 gen_mulu_i64_i32(TCGv_i32 a, TCGv_i32 b) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) (SMMUL, SMMLA, SMMLS) */ tmp = load_reg(s, rm); tmp2 = load_reg(s, rs); - tmp64 = gen_muls_i64_i32(tmp, tmp2); + tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2); if (rd != 15) { - tmp = load_reg(s, rd); + tmp3 = load_reg(s, rd); if (insn & (1 << 6)) { - tmp64 = gen_subq_msw(tmp64, tmp); + tcg_gen_sub_i32(tmp, tmp, tmp3); } else { - tmp64 = gen_addq_msw(tmp64, tmp); + tcg_gen_add_i32(tmp, tmp, tmp3); } + tcg_temp_free_i32(tmp3); } if (insn & (1 << 5)) { - tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u); + /* + * Adding 0x80000000 to the 64-bit quantity + * means that we have carry in to the high + * word when the low word has the high bit set. + */ + tcg_gen_shri_i32(tmp2, tmp2, 31); + tcg_gen_add_i32(tmp, tmp, tmp2); } - tcg_gen_shri_i64(tmp64, tmp64, 32); - tmp = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tmp, tmp64); - tcg_temp_free_i64(tmp64); + tcg_temp_free_i32(tmp2); store_reg(s, rn, tmp); break; case 0: @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } break; case 5: case 6: /* 32 * 32 -> 32msb (SMMUL, SMMLA, SMMLS) */ - tmp64 = gen_muls_i64_i32(tmp, tmp2); + tcg_gen_muls2_i32(tmp2, tmp, tmp, tmp2); if (rs != 15) { - tmp = load_reg(s, rs); + tmp3 = load_reg(s, rs); if (insn & (1 << 20)) { - tmp64 = gen_addq_msw(tmp64, tmp); + tcg_gen_add_i32(tmp, tmp, tmp3); } else { - tmp64 = gen_subq_msw(tmp64, tmp); + tcg_gen_sub_i32(tmp, tmp, tmp3); } + tcg_temp_free_i32(tmp3); } if (insn & (1 << 4)) { - tcg_gen_addi_i64(tmp64, tmp64, 0x80000000u); + /* + * Adding 0x80000000 to the 64-bit quantity + * means that we have carry in to the high + * word when the low word has the high bit set. + */ + tcg_gen_shri_i32(tmp2, tmp2, 31); + tcg_gen_add_i32(tmp, tmp, tmp2); } - tcg_gen_shri_i64(tmp64, tmp64, 32); - tmp = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tmp, tmp64); - tcg_temp_free_i64(tmp64); + tcg_temp_free_i32(tmp2); break; case 7: /* Unsigned sum of absolute differences. */ gen_helper_usad8(tmp, tmp, tmp2); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Separate shift + extract low will result in one extra insn for hosts like RISC-V, MIPS, and Sparc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190808202616.13782-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) 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_iwmmxt_insn(DisasContext *s, uint32_t insn) if (insn & ARM_CP_RW_BIT) { /* TMRRC */ iwmmxt_load_reg(cpu_V0, wrd); tcg_gen_extrl_i64_i32(cpu_R[rdlo], cpu_V0); - tcg_gen_shri_i64(cpu_V0, cpu_V0, 32); - tcg_gen_extrl_i64_i32(cpu_R[rdhi], cpu_V0); + tcg_gen_extrh_i64_i32(cpu_R[rdhi], cpu_V0); } else { /* TMCRR */ tcg_gen_concat_i32_i64(cpu_V0, cpu_R[rdlo], cpu_R[rdhi]); iwmmxt_store_reg(cpu_V0, wrd); @@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn) if (insn & ARM_CP_RW_BIT) { /* MRA */ iwmmxt_load_reg(cpu_V0, acc); tcg_gen_extrl_i64_i32(cpu_R[rdlo], cpu_V0); - tcg_gen_shri_i64(cpu_V0, cpu_V0, 32); - tcg_gen_extrl_i64_i32(cpu_R[rdhi], cpu_V0); + tcg_gen_extrh_i64_i32(cpu_R[rdhi], cpu_V0); tcg_gen_andi_i32(cpu_R[rdhi], cpu_R[rdhi], (1 << (40 - 32)) - 1); } else { /* MAR */ tcg_gen_concat_i32_i64(cpu_V0, cpu_R[rdlo], cpu_R[rdhi]); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) gen_helper_neon_narrow_high_u16(tmp, cpu_V0); break; case 2: - tcg_gen_shri_i64(cpu_V0, cpu_V0, 32); - tcg_gen_extrl_i64_i32(tmp, cpu_V0); + tcg_gen_extrh_i64_i32(tmp, cpu_V0); break; default: abort(); } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; case 2: tcg_gen_addi_i64(cpu_V0, cpu_V0, 1u << 31); - tcg_gen_shri_i64(cpu_V0, cpu_V0, 32); - tcg_gen_extrl_i64_i32(tmp, cpu_V0); + tcg_gen_extrh_i64_i32(tmp, cpu_V0); break; default: abort(); } @@ -XXX,XX +XXX,XX @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) tmp = tcg_temp_new_i32(); tcg_gen_extrl_i64_i32(tmp, tmp64); store_reg(s, rt, tmp); - tcg_gen_shri_i64(tmp64, tmp64, 32); tmp = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tmp, tmp64); + tcg_gen_extrh_i64_i32(tmp, tmp64); tcg_temp_free_i64(tmp64); store_reg(s, rt2, tmp); } else { @@ -XXX,XX +XXX,XX @@ static void gen_storeq_reg(DisasContext *s, int rlow, int rhigh, TCGv_i64 val) tcg_gen_extrl_i64_i32(tmp, val); store_reg(s, rlow, tmp); tmp = tcg_temp_new_i32(); - tcg_gen_shri_i64(val, val, 32); - tcg_gen_extrl_i64_i32(tmp, val); + tcg_gen_extrh_i64_i32(tmp, val); store_reg(s, rhigh, tmp); } -- 2.20.1 target-arm queue: the big stuff here is the final part of rth's patches for Cortex-A76 and Neoverse-N1 support; also present are Gavin's NUMA series and a few other things. thanks -- PMM The following changes since commit 554623226f800acf48a2ed568900c1c968ec9a8b: Merge tag 'qemu-sparc-20220508' of https://github.com/mcayland/qemu into staging (2022-05-08 17:03:26 -0500) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220509 for you to fetch changes up to ae9141d4a3265553503bf07d3574b40f84615a34: hw/acpi/aml-build: Use existing CPU topology to build PPTT table (2022-05-09 11:47:55 +0100) ---------------------------------------------------------------- target-arm queue: * MAINTAINERS/.mailmap: update email for Leif Lindholm * hw/arm: add version information to sbsa-ref machine DT * Enable new features for -cpu max: FEAT_Debugv8p2, FEAT_Debugv8p4, FEAT_RAS (minimal version only), FEAT_IESB, FEAT_CSV2, FEAT_CSV2_2, FEAT_CSV3, FEAT_DGH * Emulate Cortex-A76 * Emulate Neoverse-N1 * Fix the virt board default NUMA topology ---------------------------------------------------------------- Gavin Shan (6): qapi/machine.json: Add cluster-id qtest/numa-test: Specify CPU topology in aarch64_numa_cpu() hw/arm/virt: Consider SMP configuration in CPU topology qtest/numa-test: Correct CPU and NUMA association in aarch64_numa_cpu() hw/arm/virt: Fix CPU's default NUMA node ID hw/acpi/aml-build: Use existing CPU topology to build PPTT table Leif Lindholm (2): MAINTAINERS/.mailmap: update email for Leif Lindholm hw/arm: add versioning to sbsa-ref machine DT Richard Henderson (24): target/arm: Handle cpreg registration for missing EL target/arm: Drop EL3 no EL2 fallbacks target/arm: Merge zcr reginfo target/arm: Adjust definition of CONTEXTIDR_EL2 target/arm: Move cortex impdef sysregs to cpu_tcg.c target/arm: Update qemu-system-arm -cpu max to cortex-a57 target/arm: Set ID_DFR0.PerfMon for qemu-system-arm -cpu max target/arm: Split out aa32_max_features target/arm: Annotate arm_max_initfn with FEAT identifiers target/arm: Use field names for manipulating EL2 and EL3 modes target/arm: Enable FEAT_Debugv8p2 for -cpu max target/arm: Enable FEAT_Debugv8p4 for -cpu max target/arm: Add minimal RAS registers target/arm: Enable SCR and HCR bits for RAS target/arm: Implement virtual SError exceptions target/arm: Implement ESB instruction target/arm: Enable FEAT_RAS for -cpu max target/arm: Enable FEAT_IESB for -cpu max target/arm: Enable FEAT_CSV2 for -cpu max target/arm: Enable FEAT_CSV2_2 for -cpu max target/arm: Enable FEAT_CSV3 for -cpu max target/arm: Enable FEAT_DGH for -cpu max target/arm: Define cortex-a76 target/arm: Define neoverse-n1 docs/system/arm/emulation.rst | 10 + docs/system/arm/virt.rst | 2 + qapi/machine.json | 6 +- target/arm/cpregs.h | 11 + target/arm/cpu.h | 23 ++ target/arm/helper.h | 1 + target/arm/internals.h | 16 ++ target/arm/syndrome.h | 5 + target/arm/a32.decode | 16 +- target/arm/t32.decode | 18 +- hw/acpi/aml-build.c | 111 ++++---- hw/arm/sbsa-ref.c | 16 ++ hw/arm/virt.c | 21 +- hw/core/machine-hmp-cmds.c | 4 + hw/core/machine.c | 16 ++ target/arm/cpu.c | 66 ++++- target/arm/cpu64.c | 353 ++++++++++++++----------- target/arm/cpu_tcg.c | 227 +++++++++++----- target/arm/helper.c | 600 +++++++++++++++++++++++++----------------- target/arm/op_helper.c | 43 +++ target/arm/translate-a64.c | 18 ++ target/arm/translate.c | 23 ++ tests/qtest/numa-test.c | 19 +- .mailmap | 3 +- MAINTAINERS | 2 +- 25 files changed, 1068 insertions(+), 562 deletions(-) From: Leif Lindholm <quic_llindhol@quicinc.com> NUVIA was acquired by Qualcomm in March 2021, but kept functioning on separate infrastructure for a transitional period. We've now switched over to contributing as Qualcomm Innovation Center (quicinc), so update my email address to reflect this. Signed-off-by: Leif Lindholm <quic_llindhol@quicinc.com> Message-id: 20220505113740.75565-1-quic_llindhol@quicinc.com Cc: Leif Lindholm <leif@nuviainc.com> Cc: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> [Fixed commit message typo] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- .mailmap | 3 ++- MAINTAINERS | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/.mailmap b/.mailmap index XXXXXXX..XXXXXXX 100644 --- a/.mailmap +++ b/.mailmap @@ -XXX,XX +XXX,XX @@ Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com> Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com> Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn> James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> -Leif Lindholm <leif@nuviainc.com> <leif.lindholm@linaro.org> +Leif Lindholm <quic_llindhol@quicinc.com> <leif.lindholm@linaro.org> +Leif Lindholm <quic_llindhol@quicinc.com> <leif@nuviainc.com> Radoslaw Biernacki <rad@semihalf.com> <radoslaw.biernacki@linaro.org> Paul Burton <paulburton@kernel.org> <paul.burton@mips.com> Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com> diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/ssi/imx_spi.h SBSA-REF M: Radoslaw Biernacki <rad@semihalf.com> M: Peter Maydell <peter.maydell@linaro.org> -R: Leif Lindholm <leif@nuviainc.com> +R: Leif Lindholm <quic_llindhol@quicinc.com> L: qemu-arm@nongnu.org S: Maintained F: hw/arm/sbsa-ref.c -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> More gracefully handle cpregs when EL2 and/or EL3 are missing. If the reg is entirely inaccessible, do not register it at all. If the reg is for EL2, and EL3 is present but EL2 is not, either discard, squash to res0, const, or keep unchanged. Per rule RJFFP, mark the 4 aarch32 hypervisor access registers with ARM_CP_EL3_NO_EL2_KEEP, and mark all of the EL2 address translation and tlb invalidation "regs" ARM_CP_EL3_NO_EL2_UNDEF. Mark the 2 virtualization processor id regs ARM_CP_EL3_NO_EL2_C_NZ. This will simplify cpreg registration for conditional arm features. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpregs.h | 11 +++ target/arm/helper.c | 178 ++++++++++++++++++++++++++++++-------------- 2 files changed, 133 insertions(+), 56 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -XXX,XX +XXX,XX @@ enum { ARM_CP_SVE = 1 << 14, /* Flag: Do not expose in gdb sysreg xml. */ ARM_CP_NO_GDB = 1 << 15, + /* + * Flags: If EL3 but not EL2... + * - UNDEF: discard the cpreg, + * - KEEP: retain the cpreg as is, + * - C_NZ: set const on the cpreg, but retain resetvalue, + * - else: set const on the cpreg, zero resetvalue, aka RES0. + * See rule RJFFP in section D1.1.3 of DDI0487H.a. + */ + ARM_CP_EL3_NO_EL2_UNDEF = 1 << 16, + ARM_CP_EL3_NO_EL2_KEEP = 1 << 17, + ARM_CP_EL3_NO_EL2_C_NZ = 1 << 18, }; /* 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 v8_cp_reginfo[] = { .access = PL1_RW, .readfn = spsel_read, .writefn = spsel_write }, { .name = "FPEXC32_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 3, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_ALIAS | ARM_CP_FPU, + .access = PL2_RW, + .type = ARM_CP_ALIAS | ARM_CP_FPU | ARM_CP_EL3_NO_EL2_KEEP, .fieldoffset = offsetof(CPUARMState, vfp.xregs[ARM_VFP_FPEXC]) }, { .name = "DACR32_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 3, .crm = 0, .opc2 = 0, - .access = PL2_RW, .resetvalue = 0, + .access = PL2_RW, .resetvalue = 0, .type = ARM_CP_EL3_NO_EL2_KEEP, .writefn = dacr_write, .raw_writefn = raw_write, .fieldoffset = offsetof(CPUARMState, cp15.dacr32_el2) }, { .name = "IFSR32_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 0, .opc2 = 1, - .access = PL2_RW, .resetvalue = 0, + .access = PL2_RW, .resetvalue = 0, .type = ARM_CP_EL3_NO_EL2_KEEP, .fieldoffset = offsetof(CPUARMState, cp15.ifsr32_el2) }, { .name = "SPSR_IRQ", .state = ARM_CP_STATE_AA64, .type = ARM_CP_ALIAS, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = { .writefn = tlbimva_hyp_is_write }, { .name = "TLBI_ALLE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL2_W, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_alle2_write }, { .name = "TLBI_VAE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2_write }, { .name = "TLBI_VALE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2_write }, { .name = "TLBI_ALLE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_alle2is_write }, { .name = "TLBI_VAE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, { .name = "TLBI_VALE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, #ifndef CONFIG_USER_ONLY /* Unlike the other EL2-related AT operations, these must @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = { { .name = "AT_S1E2R", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 7, .crm = 8, .opc2 = 0, .access = PL2_W, .accessfn = at_s1e2_access, - .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC, .writefn = ats_write64 }, + .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = ats_write64 }, { .name = "AT_S1E2W", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 7, .crm = 8, .opc2 = 1, .access = PL2_W, .accessfn = at_s1e2_access, - .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC, .writefn = ats_write64 }, + .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = ats_write64 }, /* The AArch32 ATS1H* operations are CONSTRAINED UNPREDICTABLE * if EL2 is not implemented; we choose to UNDEF. Behaviour at EL3 * with SCR.NS == 0 outside Monitor mode is UNPREDICTABLE; we choose @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_cp_reginfo[] = { { .name = "DBGVCR32_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 2, .opc1 = 4, .crn = 0, .crm = 7, .opc2 = 0, .access = PL2_RW, .accessfn = access_tda, - .type = ARM_CP_NOP }, + .type = ARM_CP_NOP | ARM_CP_EL3_NO_EL2_KEEP }, /* Dummy MDCCINT_EL1, since we don't implement the Debug Communications * Channel but Linux may try to access this register. The 32-bit * alias is DBGDCCINT. @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbirange_reginfo[] = { .access = PL2_W, .type = ARM_CP_NOP }, { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbirange_reginfo[] = { .access = PL2_W, .type = ARM_CP_NOP }, { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2_write }, { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2_write }, { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbios_reginfo[] = { .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_ALLE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_alle2is_write }, { .name = "TLBI_VAE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, { .name = "TLBI_ALLE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 4, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbios_reginfo[] = { .writefn = tlbi_aa64_alle1is_write }, { .name = "TLBI_VALE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, { .name = "TLBI_VMALLS12E1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 6, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "VPIDR", .state = ARM_CP_STATE_AA32, .cp = 15, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 0, .access = PL2_RW, .accessfn = access_el3_aa32ns, - .resetvalue = cpu->midr, .type = ARM_CP_ALIAS, + .resetvalue = cpu->midr, + .type = ARM_CP_ALIAS | ARM_CP_EL3_NO_EL2_C_NZ, .fieldoffset = offsetoflow32(CPUARMState, cp15.vpidr_el2) }, { .name = "VPIDR_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 0, .access = PL2_RW, .resetvalue = cpu->midr, + .type = ARM_CP_EL3_NO_EL2_C_NZ, .fieldoffset = offsetof(CPUARMState, cp15.vpidr_el2) }, { .name = "VMPIDR", .state = ARM_CP_STATE_AA32, .cp = 15, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 5, .access = PL2_RW, .accessfn = access_el3_aa32ns, - .resetvalue = vmpidr_def, .type = ARM_CP_ALIAS, + .resetvalue = vmpidr_def, + .type = ARM_CP_ALIAS | ARM_CP_EL3_NO_EL2_C_NZ, .fieldoffset = offsetoflow32(CPUARMState, cp15.vmpidr_el2) }, { .name = "VMPIDR_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 5, - .access = PL2_RW, - .resetvalue = vmpidr_def, + .access = PL2_RW, .resetvalue = vmpidr_def, + .type = ARM_CP_EL3_NO_EL2_C_NZ, .fieldoffset = offsetof(CPUARMState, cp15.vmpidr_el2) }, }; define_arm_cp_regs(cpu, vpidr_regs); @@ -XXX,XX +XXX,XX @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, int crm, int opc1, int opc2, const char *name) { + CPUARMState *env = &cpu->env; uint32_t key; ARMCPRegInfo *r2; bool is64 = r->type & ARM_CP_64BIT; bool ns = secstate & ARM_CP_SECSTATE_NS; int cp = r->cp; - bool isbanked; size_t name_len; + bool make_const; switch (state) { case ARM_CP_STATE_AA32: @@ -XXX,XX +XXX,XX @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, } } + /* + * Eliminate registers that are not present because the EL is missing. + * Doing this here makes it easier to put all registers for a given + * feature into the same ARMCPRegInfo array and define them all at once. + */ + make_const = false; + if (arm_feature(env, ARM_FEATURE_EL3)) { + /* + * An EL2 register without EL2 but with EL3 is (usually) RES0. + * See rule RJFFP in section D1.1.3 of DDI0487H.a. + */ + int min_el = ctz32(r->access) / 2; + if (min_el == 2 && !arm_feature(env, ARM_FEATURE_EL2)) { + if (r->type & ARM_CP_EL3_NO_EL2_UNDEF) { + return; + } + make_const = !(r->type & ARM_CP_EL3_NO_EL2_KEEP); + } + } else { + CPAccessRights max_el = (arm_feature(env, ARM_FEATURE_EL2) + ? PL2_RW : PL1_RW); + if ((r->access & max_el) == 0) { + return; + } + } + /* Combine cpreg and name into one allocation. */ name_len = strlen(name) + 1; r2 = g_malloc(sizeof(*r2) + name_len); @@ -XXX,XX +XXX,XX @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, r2->opaque = opaque; } - isbanked = r->bank_fieldoffsets[0] && r->bank_fieldoffsets[1]; - if (isbanked) { + if (make_const) { + /* This should not have been a very special register to begin. */ + int old_special = r2->type & ARM_CP_SPECIAL_MASK; + assert(old_special == 0 || old_special == ARM_CP_NOP); /* - * Register is banked (using both entries in array). - * Overwriting fieldoffset as the array is only used to define - * banked registers but later only fieldoffset is used. + * Set the special function to CONST, retaining the other flags. + * This is important for e.g. ARM_CP_SVE so that we still + * take the SVE trap if CPTR_EL3.EZ == 0. */ - r2->fieldoffset = r->bank_fieldoffsets[ns]; - } + r2->type = (r2->type & ~ARM_CP_SPECIAL_MASK) | ARM_CP_CONST; + /* + * Usually, these registers become RES0, but there are a few + * special cases like VPIDR_EL2 which have a constant non-zero + * value with writes ignored. + */ + if (!(r->type & ARM_CP_EL3_NO_EL2_C_NZ)) { + r2->resetvalue = 0; + } + /* + * ARM_CP_CONST has precedence, so removing the callbacks and + * offsets are not strictly necessary, but it is potentially + * less confusing to debug later. + */ + r2->readfn = NULL; + r2->writefn = NULL; + r2->raw_readfn = NULL; + r2->raw_writefn = NULL; + r2->resetfn = NULL; + r2->fieldoffset = 0; + r2->bank_fieldoffsets[0] = 0; + r2->bank_fieldoffsets[1] = 0; + } else { + bool isbanked = r->bank_fieldoffsets[0] && r->bank_fieldoffsets[1]; - if (state == ARM_CP_STATE_AA32) { if (isbanked) { /* - * If the register is banked then we don't need to migrate or - * reset the 32-bit instance in certain cases: - * - * 1) If the register has both 32-bit and 64-bit instances then we - * can count on the 64-bit instance taking care of the - * non-secure bank. - * 2) If ARMv8 is enabled then we can count on a 64-bit version - * taking care of the secure bank. This requires that separate - * 32 and 64-bit definitions are provided. + * Register is banked (using both entries in array). + * Overwriting fieldoffset as the array is only used to define + * banked registers but later only fieldoffset is used. */ - if ((r->state == ARM_CP_STATE_BOTH && ns) || - (arm_feature(&cpu->env, ARM_FEATURE_V8) && !ns)) { + r2->fieldoffset = r->bank_fieldoffsets[ns]; + } + if (state == ARM_CP_STATE_AA32) { + if (isbanked) { + /* + * If the register is banked then we don't need to migrate or + * reset the 32-bit instance in certain cases: + * + * 1) If the register has both 32-bit and 64-bit instances + * then we can count on the 64-bit instance taking care + * of the non-secure bank. + * 2) If ARMv8 is enabled then we can count on a 64-bit + * version taking care of the secure bank. This requires + * that separate 32 and 64-bit definitions are provided. + */ + if ((r->state == ARM_CP_STATE_BOTH && ns) || + (arm_feature(env, ARM_FEATURE_V8) && !ns)) { + r2->type |= ARM_CP_ALIAS; + } + } else if ((secstate != r->secure) && !ns) { + /* + * The register is not banked so we only want to allow + * migration of the non-secure instance. + */ r2->type |= ARM_CP_ALIAS; } - } else if ((secstate != r->secure) && !ns) { - /* - * The register is not banked so we only want to allow migration - * of the non-secure instance. - */ - r2->type |= ARM_CP_ALIAS; - } - if (HOST_BIG_ENDIAN && - r->state == ARM_CP_STATE_BOTH && r2->fieldoffset) { - r2->fieldoffset += sizeof(uint32_t); + if (HOST_BIG_ENDIAN && + r->state == ARM_CP_STATE_BOTH && r2->fieldoffset) { + r2->fieldoffset += sizeof(uint32_t); + } } } @@ -XXX,XX +XXX,XX @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, * multiple times. Special registers (ie NOP/WFI) are * never migratable and not even raw-accessible. */ - if (r->type & ARM_CP_SPECIAL_MASK) { + if (r2->type & ARM_CP_SPECIAL_MASK) { r2->type |= ARM_CP_NO_RAW; } if (((r->crm == CP_ANY) && crm != 0) || -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Drop el3_no_el2_cp_reginfo, el3_no_el2_v8_cp_reginfo, and the local vpidr_regs definition, and rely on the squashing to ARM_CP_CONST while registering for v8. This is a behavior change for v7 cpus with Security Extensions and without Virtualization Extensions, in that the virtualization cpregs are now correctly not present. This would be a migration compatibility break, except that we have an existing bug in which migration of 32-bit cpus with Security Extensions enabled does not work. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 158 ++++---------------------------------------- 1 file changed, 13 insertions(+), 145 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 v8_cp_reginfo[] = { .fieldoffset = offsetoflow32(CPUARMState, cp15.mdcr_el3) }, }; -/* Used to describe the behaviour of EL2 regs when EL2 does not exist. */ -static const ARMCPRegInfo el3_no_el2_cp_reginfo[] = { - { .name = "VBAR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 0, - .access = PL2_RW, - .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore }, - { .name = "HCR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, - .access = PL2_RW, - .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "HACR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 7, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ESR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 2, .opc2 = 0, - .access = PL2_RW, - .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPTR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 2, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "MAIR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 10, .crm = 2, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "HMAIR1", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 4, .crn = 10, .crm = 2, .opc2 = 1, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "AMAIR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 10, .crm = 3, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "HAMAIR1", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 4, .crn = 10, .crm = 3, .opc2 = 1, - .access = PL2_RW, .type = ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "AFSR0_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 1, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "AFSR1_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 1, .opc2 = 1, - .access = PL2_RW, .type = ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "TCR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 2, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "VTCR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 1, .opc2 = 2, - .access = PL2_RW, .accessfn = access_el3_aa32ns, - .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "VTTBR", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 6, .crm = 2, - .access = PL2_RW, .accessfn = access_el3_aa32ns, - .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "VTTBR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 1, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "SCTLR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 0, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "TPIDR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 13, .crm = 0, .opc2 = 2, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "TTBR0_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "HTTBR", .cp = 15, .opc1 = 4, .crm = 2, - .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "CNTHCTL_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 1, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CNTVOFF_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 0, .opc2 = 3, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CNTVOFF", .cp = 15, .opc1 = 4, .crm = 14, - .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "CNTHP_CVAL_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 2, .opc2 = 2, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CNTHP_CVAL", .cp = 15, .opc1 = 6, .crm = 14, - .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_CONST, - .resetvalue = 0 }, - { .name = "CNTHP_TVAL_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 2, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CNTHP_CTL_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 14, .crm = 2, .opc2 = 1, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 1, - .access = PL2_RW, .accessfn = access_tda, - .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "HPFAR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 4, - .access = PL2_RW, .accessfn = access_el3_aa32ns, - .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "HSTR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 3, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "FAR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "HIFAR", .state = ARM_CP_STATE_AA32, - .type = ARM_CP_CONST, - .cp = 15, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 2, - .access = PL2_RW, .resetvalue = 0 }, -}; - -/* Ditto, but for registers which exist in ARMv8 but not v7 */ -static const ARMCPRegInfo el3_no_el2_v8_cp_reginfo[] = { - { .name = "HCR2", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 4, - .access = PL2_RW, - .type = ARM_CP_CONST, .resetvalue = 0 }, -}; - static void do_hcr_write(CPUARMState *env, uint64_t value, uint64_t valid_mask) { ARMCPU *cpu = env_archcpu(env); @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, v8_idregs); define_arm_cp_regs(cpu, v8_cp_reginfo); } - if (arm_feature(env, ARM_FEATURE_EL2)) { + + /* + * Register the base EL2 cpregs. + * Pre v8, these registers are implemented only as part of the + * Virtualization Extensions (EL2 present). Beginning with v8, + * if EL2 is missing but EL3 is enabled, mostly these become + * RES0 from EL3, with some specific exceptions. + */ + if (arm_feature(env, ARM_FEATURE_EL2) + || (arm_feature(env, ARM_FEATURE_EL3) + && arm_feature(env, ARM_FEATURE_V8))) { uint64_t vmpidr_def = mpidr_read_val(env); ARMCPRegInfo vpidr_regs[] = { { .name = "VPIDR", .state = ARM_CP_STATE_AA32, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) }; define_one_arm_cp_reg(cpu, &rvbar); } - } else { - /* If EL2 is missing but higher ELs are enabled, we need to - * register the no_el2 reginfos. - */ - if (arm_feature(env, ARM_FEATURE_EL3)) { - /* When EL3 exists but not EL2, VPIDR and VMPIDR take the value - * of MIDR_EL1 and MPIDR_EL1. - */ - ARMCPRegInfo vpidr_regs[] = { - { .name = "VPIDR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 0, - .access = PL2_RW, .accessfn = access_el3_aa32ns, - .type = ARM_CP_CONST, .resetvalue = cpu->midr, - .fieldoffset = offsetof(CPUARMState, cp15.vpidr_el2) }, - { .name = "VMPIDR_EL2", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 4, .crn = 0, .crm = 0, .opc2 = 5, - .access = PL2_RW, .accessfn = access_el3_aa32ns, - .type = ARM_CP_NO_RAW, - .writefn = arm_cp_write_ignore, .readfn = mpidr_read }, - }; - define_arm_cp_regs(cpu, vpidr_regs); - define_arm_cp_regs(cpu, el3_no_el2_cp_reginfo); - if (arm_feature(env, ARM_FEATURE_V8)) { - define_arm_cp_regs(cpu, el3_no_el2_v8_cp_reginfo); - } - } } + + /* Register the base EL3 cpregs. */ if (arm_feature(env, ARM_FEATURE_EL3)) { define_arm_cp_regs(cpu, el3_cp_reginfo); ARMCPRegInfo el3_regs[] = { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Drop zcr_no_el2_reginfo and merge the 3 registers into one array, now that ZCR_EL2 can be squashed to RES0 and ZCR_EL3 dropped while registering. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 55 ++++++++++++++------------------------------- 1 file changed, 17 insertions(+), 38 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 void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, } } -static const ARMCPRegInfo zcr_el1_reginfo = { - .name = "ZCR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_SVE, - .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[1]), - .writefn = zcr_write, .raw_writefn = raw_write -}; - -static const ARMCPRegInfo zcr_el2_reginfo = { - .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_SVE, - .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[2]), - .writefn = zcr_write, .raw_writefn = raw_write -}; - -static const ARMCPRegInfo zcr_no_el2_reginfo = { - .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_SVE, - .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore -}; - -static const ARMCPRegInfo zcr_el3_reginfo = { - .name = "ZCR_EL3", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL3_RW, .type = ARM_CP_SVE, - .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[3]), - .writefn = zcr_write, .raw_writefn = raw_write +static const ARMCPRegInfo zcr_reginfo[] = { + { .name = "ZCR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_SVE, + .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[1]), + .writefn = zcr_write, .raw_writefn = raw_write }, + { .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL2_RW, .type = ARM_CP_SVE, + .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[2]), + .writefn = zcr_write, .raw_writefn = raw_write }, + { .name = "ZCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 2, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_SVE, + .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[3]), + .writefn = zcr_write, .raw_writefn = raw_write }, }; void hw_watchpoint_update(ARMCPU *cpu, int n) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) } if (cpu_isar_feature(aa64_sve, cpu)) { - define_one_arm_cp_reg(cpu, &zcr_el1_reginfo); - if (arm_feature(env, ARM_FEATURE_EL2)) { - define_one_arm_cp_reg(cpu, &zcr_el2_reginfo); - } else { - define_one_arm_cp_reg(cpu, &zcr_no_el2_reginfo); - } - if (arm_feature(env, ARM_FEATURE_EL3)) { - define_one_arm_cp_reg(cpu, &zcr_el3_reginfo); - } + define_arm_cp_regs(cpu, zcr_reginfo); } #ifdef TARGET_AARCH64 -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This register is present for either VHE or Debugv8p2. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 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 jazelle_regs[] = { .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, }; +static const ARMCPRegInfo contextidr_el2 = { + .name = "CONTEXTIDR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 13, .crm = 0, .opc2 = 1, + .access = PL2_RW, + .fieldoffset = offsetof(CPUARMState, cp15.contextidr_el[2]) +}; + static const ARMCPRegInfo vhe_reginfo[] = { - { .name = "CONTEXTIDR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 13, .crm = 0, .opc2 = 1, - .access = PL2_RW, - .fieldoffset = offsetof(CPUARMState, cp15.contextidr_el[2]) }, { .name = "TTBR1_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 2, .crm = 0, .opc2 = 1, .access = PL2_RW, .writefn = vmsa_tcr_ttbr_el2_write, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, &ssbs_reginfo); } + if (cpu_isar_feature(aa64_vh, cpu) || + cpu_isar_feature(aa64_debugv8p2, cpu)) { + define_one_arm_cp_reg(cpu, &contextidr_el2); + } if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) { define_arm_cp_regs(cpu, vhe_reginfo); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Previously we were defining some of these in user-only mode, but none of them are accessible from user-only, therefore define them only in system mode. This will shortly be used from cpu_tcg.c also. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 6 ++++ target/arm/cpu64.c | 64 +++--------------------------------------- target/arm/cpu_tcg.c | 59 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 69 insertions(+), 60 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 @@ int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg); int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg); #endif +#ifdef CONFIG_USER_ONLY +static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } +#else +void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu); +#endif + #endif 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 @@ #include "hvf_arm.h" #include "qapi/visitor.h" #include "hw/qdev-properties.h" -#include "cpregs.h" +#include "internals.h" -#ifndef CONFIG_USER_ONLY -static uint64_t a57_a53_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) -{ - ARMCPU *cpu = env_archcpu(env); - - /* Number of cores is in [25:24]; otherwise we RAZ */ - return (cpu->core_count - 1) << 24; -} -#endif - -static const ARMCPRegInfo cortex_a72_a57_a53_cp_reginfo[] = { -#ifndef CONFIG_USER_ONLY - { .name = "L2CTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 2, - .access = PL1_RW, .readfn = a57_a53_l2ctlr_read, - .writefn = arm_cp_write_ignore }, - { .name = "L2CTLR", - .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 2, - .access = PL1_RW, .readfn = a57_a53_l2ctlr_read, - .writefn = arm_cp_write_ignore }, -#endif - { .name = "L2ECTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 3, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "L2ECTLR", - .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 3, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "L2ACTLR", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR", - .cp = 15, .opc1 = 0, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUECTLR", - .cp = 15, .opc1 = 1, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "CPUMERRSR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUMERRSR", - .cp = 15, .opc1 = 2, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "L2MERRSR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 3, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "L2MERRSR", - .cp = 15, .opc1 = 3, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, -}; - static void aarch64_a57_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->gic_num_lrs = 4; cpu->gic_vpribits = 5; cpu->gic_vprebits = 5; - define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); + define_cortex_a72_a57_a53_cp_reginfo(cpu); } static void aarch64_a53_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->gic_num_lrs = 4; cpu->gic_vpribits = 5; cpu->gic_vprebits = 5; - define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); + define_cortex_a72_a57_a53_cp_reginfo(cpu); } static void aarch64_a72_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->gic_num_lrs = 4; cpu->gic_vpribits = 5; cpu->gic_vprebits = 5; - define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); + define_cortex_a72_a57_a53_cp_reginfo(cpu); } void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ #endif #include "cpregs.h" +#ifndef CONFIG_USER_ONLY +static uint64_t l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + ARMCPU *cpu = env_archcpu(env); + + /* Number of cores is in [25:24]; otherwise we RAZ */ + return (cpu->core_count - 1) << 24; +} + +static const ARMCPRegInfo cortex_a72_a57_a53_cp_reginfo[] = { + { .name = "L2CTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 2, + .access = PL1_RW, .readfn = l2ctlr_read, + .writefn = arm_cp_write_ignore }, + { .name = "L2CTLR", + .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 2, + .access = PL1_RW, .readfn = l2ctlr_read, + .writefn = arm_cp_write_ignore }, + { .name = "L2ECTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "L2ECTLR", + .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "L2ACTLR", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 0, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUACTLR", + .cp = 15, .opc1 = 0, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, + { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 1, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUECTLR", + .cp = 15, .opc1 = 1, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, + { .name = "CPUMERRSR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 2, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUMERRSR", + .cp = 15, .opc1 = 2, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, + { .name = "L2MERRSR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "L2MERRSR", + .cp = 15, .opc1 = 3, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, +}; + +void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) +{ + define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); +} +#endif /* !CONFIG_USER_ONLY */ + /* CPU models. These are not needed for the AArch64 linux-user build. */ #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Instead of starting with cortex-a15 and adding v8 features to a v7 cpu, begin with a v8 cpu stripped of its aarch64 features. This fixes the long-standing to-do where we only enabled v8 features for user-only. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu_tcg.c | 151 ++++++++++++++++++++++++++----------------- 1 file changed, 92 insertions(+), 59 deletions(-) diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ static void arm_v7m_class_init(ObjectClass *oc, void *data) static void arm_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); + uint32_t t; - cortex_a15_initfn(obj); + /* aarch64_a57_initfn, advertising none of the aarch64 features */ + cpu->dtb_compatible = "arm,cortex-a57"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + cpu->midr = 0x411fd070; + cpu->revidr = 0x00000000; + cpu->reset_fpsid = 0x41034070; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; + cpu->ctr = 0x8444c004; + cpu->reset_sctlr = 0x00c50838; + cpu->isar.id_pfr0 = 0x00000131; + cpu->isar.id_pfr1 = 0x00011011; + cpu->isar.id_dfr0 = 0x03010066; + cpu->id_afr0 = 0x00000000; + cpu->isar.id_mmfr0 = 0x10101105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02102211; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_isar6 = 0; + cpu->isar.dbgdidr = 0x3516d000; + cpu->clidr = 0x0a200023; + cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */ + cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */ + cpu->ccsidr[2] = 0x70ffe07a; /* 2048KB L2 cache */ + define_cortex_a72_a57_a53_cp_reginfo(cpu); - /* old-style VFP short-vector support */ - cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); + /* Add additional features supported by QEMU */ + t = cpu->isar.id_isar5; + t = FIELD_DP32(t, ID_ISAR5, AES, 2); + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = t; + + t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); + t = FIELD_DP32(t, ID_ISAR6, DP, 1); + t = FIELD_DP32(t, ID_ISAR6, FHM, 1); + t = FIELD_DP32(t, ID_ISAR6, SB, 1); + t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); + t = FIELD_DP32(t, ID_ISAR6, BF16, 1); + t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); + cpu->isar.id_isar6 = t; + + t = cpu->isar.mvfr1; + t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ + t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + cpu->isar.mvfr1 = t; + + t = cpu->isar.mvfr2; + t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ + t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ + cpu->isar.mvfr2 = t; + + t = cpu->isar.id_mmfr3; + t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ + cpu->isar.id_mmfr3 = t; + + t = cpu->isar.id_mmfr4; + t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ + t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ + cpu->isar.id_mmfr4 = t; + + t = cpu->isar.id_pfr0; + t = FIELD_DP32(t, ID_PFR0, DIT, 1); + cpu->isar.id_pfr0 = t; + + t = cpu->isar.id_pfr2; + t = FIELD_DP32(t, ID_PFR2, SSBS, 1); + cpu->isar.id_pfr2 = t; #ifdef CONFIG_USER_ONLY /* - * We don't set these in system emulation mode for the moment, - * since we don't correctly set (all of) the ID registers to - * advertise them. + * Break with true ARMv8 and add back old-style VFP short-vector support. + * Only do this for user-mode, where -cpu max is the default, so that + * older v6 and v7 programs are more likely to work without adjustment. */ - set_feature(&cpu->env, ARM_FEATURE_V8); - { - uint32_t t; - - t = cpu->isar.id_isar5; - t = FIELD_DP32(t, ID_ISAR5, AES, 2); - t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); - t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); - t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); - t = FIELD_DP32(t, ID_ISAR5, RDM, 1); - t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); - cpu->isar.id_isar5 = t; - - t = cpu->isar.id_isar6; - t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); - t = FIELD_DP32(t, ID_ISAR6, DP, 1); - t = FIELD_DP32(t, ID_ISAR6, FHM, 1); - t = FIELD_DP32(t, ID_ISAR6, SB, 1); - t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); - t = FIELD_DP32(t, ID_ISAR6, BF16, 1); - t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); - cpu->isar.id_isar6 = t; - - t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ - t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ - cpu->isar.mvfr1 = t; - - t = cpu->isar.mvfr2; - t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ - t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ - cpu->isar.mvfr2 = t; - - t = cpu->isar.id_mmfr3; - t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->isar.id_mmfr3 = t; - - t = cpu->isar.id_mmfr4; - t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ - t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ - t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ - t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ - cpu->isar.id_mmfr4 = t; - - t = cpu->isar.id_pfr0; - t = FIELD_DP32(t, ID_PFR0, DIT, 1); - cpu->isar.id_pfr0 = t; - - t = cpu->isar.id_pfr2; - t = FIELD_DP32(t, ID_PFR2, SSBS, 1); - cpu->isar.id_pfr2 = t; - } -#endif /* CONFIG_USER_ONLY */ + cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); +#endif } #endif /* !TARGET_AARCH64 */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We set this for qemu-system-aarch64, but failed to do so for the strictly 32-bit emulation. Fixes: 3bec78447a9 ("target/arm: Provide ARMv8.4-PMU in '-cpu max'") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu_tcg.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) t = FIELD_DP32(t, ID_PFR2, SSBS, 1); cpu->isar.id_pfr2 = t; + t = cpu->isar.id_dfr0; + t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ + cpu->isar.id_dfr0 = t; + #ifdef CONFIG_USER_ONLY /* * Break with true ARMv8 and add back old-style VFP short-vector support. -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Share the code to set AArch32 max features so that we no longer have code drift between qemu{-system,}-{arm,aarch64}. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 2 + target/arm/cpu64.c | 50 +----------------- target/arm/cpu_tcg.c | 114 ++++++++++++++++++++++------------------- 3 files changed, 65 insertions(+), 101 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 @@ static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu); #endif +void aa32_max_features(ARMCPU *cpu); + #endif diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); uint64_t t; - uint32_t u; if (kvm_enabled() || hvf_enabled()) { /* With KVM or HVF, '-cpu max' is identical to '-cpu host' */ @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 1); cpu->isar.id_aa64zfr0 = t; - /* Replicate the same data to the 32-bit id registers. */ - u = cpu->isar.id_isar5; - u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */ - u = FIELD_DP32(u, ID_ISAR5, SHA1, 1); - u = FIELD_DP32(u, ID_ISAR5, SHA2, 1); - u = FIELD_DP32(u, ID_ISAR5, CRC32, 1); - u = FIELD_DP32(u, ID_ISAR5, RDM, 1); - u = FIELD_DP32(u, ID_ISAR5, VCMA, 1); - cpu->isar.id_isar5 = u; - - u = cpu->isar.id_isar6; - u = FIELD_DP32(u, ID_ISAR6, JSCVT, 1); - u = FIELD_DP32(u, ID_ISAR6, DP, 1); - u = FIELD_DP32(u, ID_ISAR6, FHM, 1); - u = FIELD_DP32(u, ID_ISAR6, SB, 1); - u = FIELD_DP32(u, ID_ISAR6, SPECRES, 1); - u = FIELD_DP32(u, ID_ISAR6, BF16, 1); - u = FIELD_DP32(u, ID_ISAR6, I8MM, 1); - cpu->isar.id_isar6 = u; - - u = cpu->isar.id_pfr0; - u = FIELD_DP32(u, ID_PFR0, DIT, 1); - cpu->isar.id_pfr0 = u; - - u = cpu->isar.id_pfr2; - u = FIELD_DP32(u, ID_PFR2, SSBS, 1); - cpu->isar.id_pfr2 = u; - - u = cpu->isar.id_mmfr3; - u = FIELD_DP32(u, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->isar.id_mmfr3 = u; - - u = cpu->isar.id_mmfr4; - u = FIELD_DP32(u, ID_MMFR4, HPDS, 1); /* AA32HPD */ - u = FIELD_DP32(u, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ - u = FIELD_DP32(u, ID_MMFR4, CNP, 1); /* TTCNP */ - u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */ - cpu->isar.id_mmfr4 = u; - t = cpu->isar.id_aa64dfr0; t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ cpu->isar.id_aa64dfr0 = t; - u = cpu->isar.id_dfr0; - u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ - cpu->isar.id_dfr0 = u; - - u = cpu->isar.mvfr1; - u = FIELD_DP32(u, MVFR1, FPHP, 3); /* v8.2-FP16 */ - u = FIELD_DP32(u, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ - cpu->isar.mvfr1 = u; + /* Replicate the same data to the 32-bit id registers. */ + aa32_max_features(cpu); #ifdef CONFIG_USER_ONLY /* diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ #endif #include "cpregs.h" + +/* Share AArch32 -cpu max features with AArch64. */ +void aa32_max_features(ARMCPU *cpu) +{ + uint32_t t; + + /* Add additional features supported by QEMU */ + t = cpu->isar.id_isar5; + t = FIELD_DP32(t, ID_ISAR5, AES, 2); + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = t; + + t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); + t = FIELD_DP32(t, ID_ISAR6, DP, 1); + t = FIELD_DP32(t, ID_ISAR6, FHM, 1); + t = FIELD_DP32(t, ID_ISAR6, SB, 1); + t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); + t = FIELD_DP32(t, ID_ISAR6, BF16, 1); + t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); + cpu->isar.id_isar6 = t; + + t = cpu->isar.mvfr1; + t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ + t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + cpu->isar.mvfr1 = t; + + t = cpu->isar.mvfr2; + t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ + t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ + cpu->isar.mvfr2 = t; + + t = cpu->isar.id_mmfr3; + t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ + cpu->isar.id_mmfr3 = t; + + t = cpu->isar.id_mmfr4; + t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ + t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ + cpu->isar.id_mmfr4 = t; + + t = cpu->isar.id_pfr0; + t = FIELD_DP32(t, ID_PFR0, DIT, 1); + cpu->isar.id_pfr0 = t; + + t = cpu->isar.id_pfr2; + t = FIELD_DP32(t, ID_PFR2, SSBS, 1); + cpu->isar.id_pfr2 = t; + + t = cpu->isar.id_dfr0; + t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ + cpu->isar.id_dfr0 = t; +} + #ifndef CONFIG_USER_ONLY static uint64_t l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) { @@ -XXX,XX +XXX,XX @@ static void arm_v7m_class_init(ObjectClass *oc, void *data) static void arm_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - uint32_t t; /* aarch64_a57_initfn, advertising none of the aarch64 features */ cpu->dtb_compatible = "arm,cortex-a57"; @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) cpu->ccsidr[2] = 0x70ffe07a; /* 2048KB L2 cache */ define_cortex_a72_a57_a53_cp_reginfo(cpu); - /* Add additional features supported by QEMU */ - t = cpu->isar.id_isar5; - t = FIELD_DP32(t, ID_ISAR5, AES, 2); - t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); - t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); - t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); - t = FIELD_DP32(t, ID_ISAR5, RDM, 1); - t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); - cpu->isar.id_isar5 = t; - - t = cpu->isar.id_isar6; - t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); - t = FIELD_DP32(t, ID_ISAR6, DP, 1); - t = FIELD_DP32(t, ID_ISAR6, FHM, 1); - t = FIELD_DP32(t, ID_ISAR6, SB, 1); - t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); - t = FIELD_DP32(t, ID_ISAR6, BF16, 1); - t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); - cpu->isar.id_isar6 = t; - - t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ - t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ - cpu->isar.mvfr1 = t; - - t = cpu->isar.mvfr2; - t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ - t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ - cpu->isar.mvfr2 = t; - - t = cpu->isar.id_mmfr3; - t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->isar.id_mmfr3 = t; - - t = cpu->isar.id_mmfr4; - t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ - t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ - t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ - t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ - cpu->isar.id_mmfr4 = t; - - t = cpu->isar.id_pfr0; - t = FIELD_DP32(t, ID_PFR0, DIT, 1); - cpu->isar.id_pfr0 = t; - - t = cpu->isar.id_pfr2; - t = FIELD_DP32(t, ID_PFR2, SSBS, 1); - cpu->isar.id_pfr2 = t; - - t = cpu->isar.id_dfr0; - t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ - cpu->isar.id_dfr0 = t; + aa32_max_features(cpu); #ifdef CONFIG_USER_ONLY /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Update the legacy feature names to the current names. Provide feature names for id changes that were not marked. Sort the field updates into increasing bitfield order. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 100 +++++++++++++++++++++---------------------- target/arm/cpu_tcg.c | 48 ++++++++++----------- 2 files changed, 74 insertions(+), 74 deletions(-) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->midr = t; t = cpu->isar.id_aa64isar0; - t = FIELD_DP64(t, ID_AA64ISAR0, AES, 2); /* AES + PMULL */ - t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, SHA2, 2); /* SHA512 */ + t = FIELD_DP64(t, ID_AA64ISAR0, AES, 2); /* FEAT_PMULL */ + t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); /* FEAT_SHA1 */ + t = FIELD_DP64(t, ID_AA64ISAR0, SHA2, 2); /* FEAT_SHA512 */ t = FIELD_DP64(t, ID_AA64ISAR0, CRC32, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, ATOMIC, 2); - t = FIELD_DP64(t, ID_AA64ISAR0, RDM, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, SHA3, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, SM3, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, SM4, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, FHM, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, TS, 2); /* v8.5-CondM */ - t = FIELD_DP64(t, ID_AA64ISAR0, TLB, 2); /* FEAT_TLBIRANGE */ - t = FIELD_DP64(t, ID_AA64ISAR0, RNDR, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, ATOMIC, 2); /* FEAT_LSE */ + t = FIELD_DP64(t, ID_AA64ISAR0, RDM, 1); /* FEAT_RDM */ + t = FIELD_DP64(t, ID_AA64ISAR0, SHA3, 1); /* FEAT_SHA3 */ + t = FIELD_DP64(t, ID_AA64ISAR0, SM3, 1); /* FEAT_SM3 */ + t = FIELD_DP64(t, ID_AA64ISAR0, SM4, 1); /* FEAT_SM4 */ + t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); /* FEAT_DotProd */ + t = FIELD_DP64(t, ID_AA64ISAR0, FHM, 1); /* FEAT_FHM */ + t = FIELD_DP64(t, ID_AA64ISAR0, TS, 2); /* FEAT_FlagM2 */ + t = FIELD_DP64(t, ID_AA64ISAR0, TLB, 2); /* FEAT_TLBIRANGE */ + t = FIELD_DP64(t, ID_AA64ISAR0, RNDR, 1); /* FEAT_RNG */ cpu->isar.id_aa64isar0 = t; t = cpu->isar.id_aa64isar1; - t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); - t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* ARMv8.4-RCPC */ - t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); /* FEAT_DPB2 */ + t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); /* FEAT_JSCVT */ + t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); /* FEAT_FCMA */ + t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* FEAT_LRCPC2 */ + t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); /* FEAT_FRINTTS */ + t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); /* FEAT_SB */ + t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); /* FEAT_SPECRES */ + t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 1); /* FEAT_BF16 */ + t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); /* FEAT_I8MM */ cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; + t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); /* FEAT_FP16 */ + t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); /* FEAT_FP16 */ t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); - t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); - t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); - t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); - t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); + t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ + t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ cpu->isar.id_aa64pfr0 = t; t = cpu->isar.id_aa64pfr1; - t = FIELD_DP64(t, ID_AA64PFR1, BT, 1); - t = FIELD_DP64(t, ID_AA64PFR1, SSBS, 2); + t = FIELD_DP64(t, ID_AA64PFR1, BT, 1); /* FEAT_BTI */ + t = FIELD_DP64(t, ID_AA64PFR1, SSBS, 2); /* FEAT_SSBS2 */ /* * Begin with full support for MTE. This will be downgraded to MTE=0 * during realize if the board provides no tag memory, much like * we do for EL2 with the virtualization=on property. */ - t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); + t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ cpu->isar.id_aa64pfr1 = t; t = cpu->isar.id_aa64mmfr0; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_aa64mmfr0 = t; t = cpu->isar.id_aa64mmfr1; - t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* HPD */ - t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1); - t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); - t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 2); /* ATS1E1 */ - t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* VMID16 */ - t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* TTS2UXN */ + t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* FEAT_VMID16 */ + t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); /* FEAT_VHE */ + t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* FEAT_HPDS */ + t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1); /* FEAT_LOR */ + t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 2); /* FEAT_PAN2 */ + t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* FEAT_XNX */ cpu->isar.id_aa64mmfr1 = t; t = cpu->isar.id_aa64mmfr2; - t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1); - t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* TTCNP */ - t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* TTST */ - t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */ - t = FIELD_DP64(t, ID_AA64MMFR2, TTL, 1); /* FEAT_TTL */ - t = FIELD_DP64(t, ID_AA64MMFR2, BBM, 2); /* FEAT_BBM at level 2 */ + t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* FEAT_TTCNP */ + t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1); /* FEAT_UAO */ + t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */ + t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* FEAT_TTST */ + t = FIELD_DP64(t, ID_AA64MMFR2, TTL, 1); /* FEAT_TTL */ + t = FIELD_DP64(t, ID_AA64MMFR2, BBM, 2); /* FEAT_BBM at level 2 */ cpu->isar.id_aa64mmfr2 = t; t = cpu->isar.id_aa64zfr0; t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* PMULL */ - t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, F32MM, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* FEAT_SVE_PMULL128 */ + t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); /* FEAT_SVE_BitPerm */ + t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 1); /* FEAT_BF16 */ + t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); /* FEAT_SVE_SHA3 */ + t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); /* FEAT_SVE_SM4 */ + t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); /* FEAT_I8MM */ + t = FIELD_DP64(t, ID_AA64ZFR0, F32MM, 1); /* FEAT_F32MM */ + t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 1); /* FEAT_F64MM */ cpu->isar.id_aa64zfr0 = t; t = cpu->isar.id_aa64dfr0; - t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ + t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_aa64dfr0 = t; /* Replicate the same data to the 32-bit id registers. */ diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) /* Add additional features supported by QEMU */ t = cpu->isar.id_isar5; - t = FIELD_DP32(t, ID_ISAR5, AES, 2); - t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); - t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, AES, 2); /* FEAT_PMULL */ + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); /* FEAT_SHA1 */ + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); /* FEAT_SHA256 */ t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); - t = FIELD_DP32(t, ID_ISAR5, RDM, 1); - t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); /* FEAT_RDM */ + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); /* FEAT_FCMA */ cpu->isar.id_isar5 = t; t = cpu->isar.id_isar6; - t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); - t = FIELD_DP32(t, ID_ISAR6, DP, 1); - t = FIELD_DP32(t, ID_ISAR6, FHM, 1); - t = FIELD_DP32(t, ID_ISAR6, SB, 1); - t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); - t = FIELD_DP32(t, ID_ISAR6, BF16, 1); - t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); + t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); /* FEAT_JSCVT */ + t = FIELD_DP32(t, ID_ISAR6, DP, 1); /* Feat_DotProd */ + t = FIELD_DP32(t, ID_ISAR6, FHM, 1); /* FEAT_FHM */ + t = FIELD_DP32(t, ID_ISAR6, SB, 1); /* FEAT_SB */ + t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); /* FEAT_SPECRES */ + t = FIELD_DP32(t, ID_ISAR6, BF16, 1); /* FEAT_AA32BF16 */ + t = FIELD_DP32(t, ID_ISAR6, I8MM, 1); /* FEAT_AA32I8MM */ cpu->isar.id_isar6 = t; t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ - t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + t = FIELD_DP32(t, MVFR1, FPHP, 3); /* FEAT_FP16 */ + t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* FEAT_FP16 */ cpu->isar.mvfr1 = t; t = cpu->isar.mvfr2; - t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ - t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ + t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ + t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ cpu->isar.mvfr2 = t; t = cpu->isar.id_mmfr3; - t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ + t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* FEAT_PAN2 */ cpu->isar.id_mmfr3 = t; t = cpu->isar.id_mmfr4; - t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ - t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ - t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ - t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ + t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* FEAT_AA32HPD */ + t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* FEAT_TTCNP */ + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* FEAT_XNX*/ cpu->isar.id_mmfr4 = t; t = cpu->isar.id_pfr0; - t = FIELD_DP32(t, ID_PFR0, DIT, 1); + t = FIELD_DP32(t, ID_PFR0, DIT, 1); /* FEAT_DIT */ cpu->isar.id_pfr0 = t; t = cpu->isar.id_pfr2; - t = FIELD_DP32(t, ID_PFR2, SSBS, 1); + t = FIELD_DP32(t, ID_PFR2, SSBS, 1); /* FEAT_SSBS */ cpu->isar.id_pfr2 = t; t = cpu->isar.id_dfr0; - t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ + t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_dfr0 = t; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use FIELD_DP{32,64} to manipulate id_pfr1 and id_aa64pfr0 during arm_cpu_realizefn. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 22 +++++++++++++--------- 1 file changed, 13 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_realizefn(DeviceState *dev, Error **errp) */ unset_feature(env, ARM_FEATURE_EL3); - /* Disable the security extension feature bits in the processor feature - * registers as well. These are id_pfr1[7:4] and id_aa64pfr0[15:12]. + /* + * Disable the security extension feature bits in the processor + * feature registers as well. */ - cpu->isar.id_pfr1 &= ~0xf0; - cpu->isar.id_aa64pfr0 &= ~0xf000; + cpu->isar.id_pfr1 = FIELD_DP32(cpu->isar.id_pfr1, ID_PFR1, SECURITY, 0); + cpu->isar.id_aa64pfr0 = FIELD_DP64(cpu->isar.id_aa64pfr0, + ID_AA64PFR0, EL3, 0); } if (!cpu->has_el2) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (!arm_feature(env, ARM_FEATURE_EL2)) { - /* Disable the hypervisor feature bits in the processor feature - * registers if we don't have EL2. These are id_pfr1[15:12] and - * id_aa64pfr0_el1[11:8]. + /* + * Disable the hypervisor feature bits in the processor feature + * registers if we don't have EL2. */ - cpu->isar.id_aa64pfr0 &= ~0xf00; - cpu->isar.id_pfr1 &= ~0xf000; + cpu->isar.id_aa64pfr0 = FIELD_DP64(cpu->isar.id_aa64pfr0, + ID_AA64PFR0, EL2, 0); + cpu->isar.id_pfr1 = FIELD_DP32(cpu->isar.id_pfr1, + ID_PFR1, VIRTUALIZATION, 0); } #ifndef CONFIG_USER_ONLY -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The only portion of FEAT_Debugv8p2 that is relevant to QEMU is CONTEXTIDR_EL2, which is also conditionally implemented with FEAT_VHE. The rest of the debug extension concerns the External debug interface, which is outside the scope of QEMU. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu.c | 1 + target/arm/cpu64.c | 1 + target/arm/cpu_tcg.c | 2 ++ 4 files changed, 5 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_BTI (Branch Target Identification) - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) +- FEAT_Debugv8p2 (Debug changes for v8.2) - FEAT_DotProd (Advanced SIMD dot product instructions) - FEAT_FCMA (Floating-point complex number instructions) - FEAT_FHM (Floating-point half-precision multiplication instructions) 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_realizefn(DeviceState *dev, Error **errp) * feature registers as well. */ cpu->isar.id_pfr1 = FIELD_DP32(cpu->isar.id_pfr1, ID_PFR1, SECURITY, 0); + cpu->isar.id_dfr0 = FIELD_DP32(cpu->isar.id_dfr0, ID_DFR0, COPSDBG, 0); cpu->isar.id_aa64pfr0 = FIELD_DP64(cpu->isar.id_aa64pfr0, ID_AA64PFR0, EL3, 0); } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_aa64zfr0 = t; t = cpu->isar.id_aa64dfr0; + t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 8); /* FEAT_Debugv8p2 */ t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_aa64dfr0 = t; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_pfr2 = t; t = cpu->isar.id_dfr0; + t = FIELD_DP32(t, ID_DFR0, COPDBG, 8); /* FEAT_Debugv8p2 */ + t = FIELD_DP32(t, ID_DFR0, COPSDBG, 8); /* FEAT_Debugv8p2 */ t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_dfr0 = t; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This extension concerns changes to the External Debug interface, with Secure and Non-secure access to the debug registers, and all of it is outside the scope of QEMU. Indicating support for this is mandatory with FEAT_SEL2, which we do implement. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 2 +- target/arm/cpu_tcg.c | 4 ++-- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) - FEAT_Debugv8p2 (Debug changes for v8.2) +- FEAT_Debugv8p4 (Debug changes for v8.4) - FEAT_DotProd (Advanced SIMD dot product instructions) - FEAT_FCMA (Floating-point complex number instructions) - FEAT_FHM (Floating-point half-precision multiplication instructions) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_aa64zfr0 = t; t = cpu->isar.id_aa64dfr0; - t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 8); /* FEAT_Debugv8p2 */ + t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 9); /* FEAT_Debugv8p4 */ t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_aa64dfr0 = t; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_pfr2 = t; t = cpu->isar.id_dfr0; - t = FIELD_DP32(t, ID_DFR0, COPDBG, 8); /* FEAT_Debugv8p2 */ - t = FIELD_DP32(t, ID_DFR0, COPSDBG, 8); /* FEAT_Debugv8p2 */ + t = FIELD_DP32(t, ID_DFR0, COPDBG, 9); /* FEAT_Debugv8p4 */ + t = FIELD_DP32(t, ID_DFR0, COPSDBG, 9); /* FEAT_Debugv8p4 */ t = FIELD_DP32(t, ID_DFR0, PERFMON, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_dfr0 = t; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add only the system registers required to implement zero error records. This means that all values for ERRSELR are out of range, which means that it and all of the indexed error record registers need not be implemented. Add the EL2 registers required for injecting virtual SError. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 +++ target/arm/helper.c | 84 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 89 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { uint64_t tfsr_el[4]; /* tfsre0_el1 is index 0. */ uint64_t gcr_el1; uint64_t rgsr_el1; + + /* Minimal RAS registers */ + uint64_t disr_el1; + uint64_t vdisr_el2; + uint64_t vsesr_el2; } cp15; struct { 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 debug_lpae_cp_reginfo[] = { .access = PL0_R, .type = ARM_CP_CONST|ARM_CP_64BIT, .resetvalue = 0 }, }; +/* + * Check for traps to RAS registers, which are controlled + * by HCR_EL2.TERR and SCR_EL3.TERR. + */ +static CPAccessResult access_terr(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + int el = arm_current_el(env); + + if (el < 2 && (arm_hcr_el2_eff(env) & HCR_TERR)) { + return CP_ACCESS_TRAP_EL2; + } + if (el < 3 && (env->cp15.scr_el3 & SCR_TERR)) { + return CP_ACCESS_TRAP_EL3; + } + return CP_ACCESS_OK; +} + +static uint64_t disr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + int el = arm_current_el(env); + + if (el < 2 && (arm_hcr_el2_eff(env) & HCR_AMO)) { + return env->cp15.vdisr_el2; + } + if (el < 3 && (env->cp15.scr_el3 & SCR_EA)) { + return 0; /* RAZ/WI */ + } + return env->cp15.disr_el1; +} + +static void disr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t val) +{ + int el = arm_current_el(env); + + if (el < 2 && (arm_hcr_el2_eff(env) & HCR_AMO)) { + env->cp15.vdisr_el2 = val; + return; + } + if (el < 3 && (env->cp15.scr_el3 & SCR_EA)) { + return; /* RAZ/WI */ + } + env->cp15.disr_el1 = val; +} + +/* + * Minimal RAS implementation with no Error Records. + * Which means that all of the Error Record registers: + * ERXADDR_EL1 + * ERXCTLR_EL1 + * ERXFR_EL1 + * ERXMISC0_EL1 + * ERXMISC1_EL1 + * ERXMISC2_EL1 + * ERXMISC3_EL1 + * ERXPFGCDN_EL1 (RASv1p1) + * ERXPFGCTL_EL1 (RASv1p1) + * ERXPFGF_EL1 (RASv1p1) + * ERXSTATUS_EL1 + * and + * ERRSELR_EL1 + * may generate UNDEFINED, which is the effect we get by not + * listing them at all. + */ +static const ARMCPRegInfo minimal_ras_reginfo[] = { + { .name = "DISR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 1, .opc2 = 1, + .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.disr_el1), + .readfn = disr_read, .writefn = disr_write, .raw_writefn = raw_write }, + { .name = "ERRIDR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 5, .crm = 3, .opc2 = 0, + .access = PL1_R, .accessfn = access_terr, + .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "VDISR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 1, .opc2 = 1, + .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.vdisr_el2) }, + { .name = "VSESR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 2, .opc2 = 3, + .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.vsesr_el2) }, +}; + /* Return the exception level to which exceptions should be taken * via SVEAccessTrap. If an exception should be routed through * AArch64.AdvSIMDFPAccessTrap, return 0; fp_exception_el should @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_ssbs, cpu)) { define_one_arm_cp_reg(cpu, &ssbs_reginfo); } + if (cpu_isar_feature(any_ras, cpu)) { + define_arm_cp_regs(cpu, minimal_ras_reginfo); + } if (cpu_isar_feature(aa64_vh, cpu) || cpu_isar_feature(aa64_debugv8p2, cpu)) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Enable writes to the TERR and TEA bits when RAS is enabled. These bits are otherwise RES0. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 9 +++++++++ 1 file changed, 9 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) } valid_mask &= ~SCR_NET; + if (cpu_isar_feature(aa64_ras, cpu)) { + valid_mask |= SCR_TERR; + } if (cpu_isar_feature(aa64_lor, cpu)) { valid_mask |= SCR_TLOR; } @@ -XXX,XX +XXX,XX @@ static void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) } } else { valid_mask &= ~(SCR_RW | SCR_ST); + if (cpu_isar_feature(aa32_ras, cpu)) { + valid_mask |= SCR_TERR; + } } if (!arm_feature(env, ARM_FEATURE_EL2)) { @@ -XXX,XX +XXX,XX @@ static void do_hcr_write(CPUARMState *env, uint64_t value, uint64_t valid_mask) if (cpu_isar_feature(aa64_vh, cpu)) { valid_mask |= HCR_E2H; } + if (cpu_isar_feature(aa64_ras, cpu)) { + valid_mask |= HCR_TERR | HCR_TEA; + } if (cpu_isar_feature(aa64_lor, cpu)) { valid_mask |= HCR_TLOR; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Virtual SError exceptions are raised by setting HCR_EL2.VSE, and are routed to EL1 just like other virtual exceptions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/internals.h | 8 ++++++++ target/arm/syndrome.h | 5 +++++ target/arm/cpu.c | 38 +++++++++++++++++++++++++++++++++++++- target/arm/helper.c | 40 +++++++++++++++++++++++++++++++++++++++- 5 files changed, 91 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 @@ #define EXCP_LSERR 21 /* v8M LSERR SecureFault */ #define EXCP_UNALIGNED 22 /* v7M UNALIGNED UsageFault */ #define EXCP_DIVBYZERO 23 /* v7M DIVBYZERO UsageFault */ +#define EXCP_VSERR 24 /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 @@ -XXX,XX +XXX,XX @@ enum { #define CPU_INTERRUPT_FIQ CPU_INTERRUPT_TGT_EXT_1 #define CPU_INTERRUPT_VIRQ CPU_INTERRUPT_TGT_EXT_2 #define CPU_INTERRUPT_VFIQ CPU_INTERRUPT_TGT_EXT_3 +#define CPU_INTERRUPT_VSERR CPU_INTERRUPT_TGT_INT_0 /* The usual mapping for an AArch64 system register to its AArch32 * counterpart is for the 32 bit world to have access to the lower 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_cpu_update_vserr: Update CPU_INTERRUPT_VSERR bit + * + * Update the CPU_INTERRUPT_VSERR bit in cs->interrupt_request, + * following a change to the HCR_EL2.VSE bit. + */ +void arm_cpu_update_vserr(ARMCPU *cpu); + /** * arm_mmu_idx_el: * @env: The cpu environment diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pcalignment(void) return (EC_PCALIGNMENT << ARM_EL_EC_SHIFT) | ARM_EL_IL; } +static inline uint32_t syn_serror(uint32_t extra) +{ + return (EC_SERROR << ARM_EL_EC_SHIFT) | ARM_EL_IL | extra; +} + #endif /* TARGET_ARM_SYNDROME_H */ 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 bool arm_cpu_has_work(CPUState *cs) return (cpu->power_state != PSCI_OFF) && cs->interrupt_request & (CPU_INTERRUPT_FIQ | CPU_INTERRUPT_HARD - | CPU_INTERRUPT_VFIQ | CPU_INTERRUPT_VIRQ + | CPU_INTERRUPT_VFIQ | CPU_INTERRUPT_VIRQ | CPU_INTERRUPT_VSERR | CPU_INTERRUPT_EXITTB); } @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, return false; } return !(env->daif & PSTATE_I); + case EXCP_VSERR: + if (!(hcr_el2 & HCR_AMO) || (hcr_el2 & HCR_TGE)) { + /* VIRQs are only taken when hypervized. */ + return false; + } + return !(env->daif & PSTATE_A); default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static bool arm_cpu_exec_interrupt(CPUState *cs, int interrupt_request) goto found; } } + if (interrupt_request & CPU_INTERRUPT_VSERR) { + excp_idx = EXCP_VSERR; + target_el = 1; + if (arm_excp_unmasked(cs, excp_idx, target_el, + cur_el, secure, hcr_el2)) { + /* Taking a virtual abort clears HCR_EL2.VSE */ + env->cp15.hcr_el2 &= ~HCR_VSE; + cpu_reset_interrupt(cs, CPU_INTERRUPT_VSERR); + goto found; + } + } return false; found: @@ -XXX,XX +XXX,XX @@ void arm_cpu_update_vfiq(ARMCPU *cpu) } } +void arm_cpu_update_vserr(ARMCPU *cpu) +{ + /* + * Update the interrupt level for VSERR, which is the HCR_EL2.VSE bit. + */ + CPUARMState *env = &cpu->env; + CPUState *cs = CPU(cpu); + + bool new_state = env->cp15.hcr_el2 & HCR_VSE; + + if (new_state != ((cs->interrupt_request & CPU_INTERRUPT_VSERR) != 0)) { + if (new_state) { + cpu_interrupt(cs, CPU_INTERRUPT_VSERR); + } else { + cpu_reset_interrupt(cs, CPU_INTERRUPT_VSERR); + } + } +} + #ifndef CONFIG_USER_ONLY static void arm_cpu_set_irq(void *opaque, int irq, int level) { 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 uint64_t isr_read(CPUARMState *env, const ARMCPRegInfo *ri) } } - /* External aborts are not possible in QEMU so A bit is always clear */ + if (hcr_el2 & HCR_AMO) { + if (cs->interrupt_request & CPU_INTERRUPT_VSERR) { + ret |= CPSR_A; + } + } + return ret; } @@ -XXX,XX +XXX,XX @@ static void do_hcr_write(CPUARMState *env, uint64_t value, uint64_t valid_mask) g_assert(qemu_mutex_iothread_locked()); arm_cpu_update_virq(cpu); arm_cpu_update_vfiq(cpu); + arm_cpu_update_vserr(cpu); } static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) @@ -XXX,XX +XXX,XX @@ void arm_log_exception(CPUState *cs) [EXCP_LSERR] = "v8M LSERR UsageFault", [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", [EXCP_DIVBYZERO] = "v7M DIVBYZERO UsageFault", + [EXCP_VSERR] = "Virtual SERR", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32(CPUState *cs) mask = CPSR_A | CPSR_I | CPSR_F; offset = 4; break; + case EXCP_VSERR: + { + /* + * Note that this is reported as a data abort, but the DFAR + * has an UNKNOWN value. Construct the SError syndrome from + * AET and ExT fields. + */ + ARMMMUFaultInfo fi = { .type = ARMFault_AsyncExternal, }; + + if (extended_addresses_enabled(env)) { + env->exception.fsr = arm_fi_to_lfsc(&fi); + } else { + env->exception.fsr = arm_fi_to_sfsc(&fi); + } + env->exception.fsr |= env->cp15.vsesr_el2 & 0xd000; + A32_BANKED_CURRENT_REG_SET(env, dfsr, env->exception.fsr); + qemu_log_mask(CPU_LOG_INT, "...with IFSR 0x%x\n", + env->exception.fsr); + + new_mode = ARM_CPU_MODE_ABT; + addr = 0x10; + mask = CPSR_A | CPSR_I; + offset = 8; + } + break; case EXCP_SMC: new_mode = ARM_CPU_MODE_MON; addr = 0x08; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) case EXCP_VFIQ: addr += 0x100; break; + case EXCP_VSERR: + addr += 0x180; + /* Construct the SError syndrome from IDS and ISS fields. */ + env->exception.syndrome = syn_serror(env->cp15.vsesr_el2 & 0x1ffffff); + env->cp15.esr_el[new_el] = env->exception.syndrome; + break; default: cpu_abort(cs, "Unhandled exception 0x%x\n", cs->exception_index); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Check for and defer any pending virtual SError. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 1 + target/arm/a32.decode | 16 ++++++++------ target/arm/t32.decode | 18 ++++++++-------- target/arm/op_helper.c | 43 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-a64.c | 17 +++++++++++++++ target/arm/translate.c | 23 ++++++++++++++++++++ 6 files changed, 103 insertions(+), 15 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_1(wfe, void, env) DEF_HELPER_1(yield, void, env) DEF_HELPER_1(pre_hvc, void, env) DEF_HELPER_2(pre_smc, void, env, i32) +DEF_HELPER_1(vesb, void, env) DEF_HELPER_3(cpsr_write, void, env, i32, i32) DEF_HELPER_2(cpsr_write_eret, void, env, i32) diff --git a/target/arm/a32.decode b/target/arm/a32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/a32.decode +++ b/target/arm/a32.decode @@ -XXX,XX +XXX,XX @@ SMULTT .... 0001 0110 .... 0000 .... 1110 .... @rd0mn { { - YIELD ---- 0011 0010 0000 1111 ---- 0000 0001 - WFE ---- 0011 0010 0000 1111 ---- 0000 0010 - WFI ---- 0011 0010 0000 1111 ---- 0000 0011 + [ + YIELD ---- 0011 0010 0000 1111 ---- 0000 0001 + WFE ---- 0011 0010 0000 1111 ---- 0000 0010 + WFI ---- 0011 0010 0000 1111 ---- 0000 0011 - # TODO: Implement SEV, SEVL; may help SMP performance. - # SEV ---- 0011 0010 0000 1111 ---- 0000 0100 - # SEVL ---- 0011 0010 0000 1111 ---- 0000 0101 + # TODO: Implement SEV, SEVL; may help SMP performance. + # SEV ---- 0011 0010 0000 1111 ---- 0000 0100 + # SEVL ---- 0011 0010 0000 1111 ---- 0000 0101 + + ESB ---- 0011 0010 0000 1111 ---- 0001 0000 + ] # The canonical nop ends in 00000000, but the whole of the # rest of the space executes as nop if otherwise unsupported. diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ CLZ 1111 1010 1011 ---- 1111 .... 1000 .... @rdm [ # Hints, and CPS { - YIELD 1111 0011 1010 1111 1000 0000 0000 0001 - WFE 1111 0011 1010 1111 1000 0000 0000 0010 - WFI 1111 0011 1010 1111 1000 0000 0000 0011 + [ + YIELD 1111 0011 1010 1111 1000 0000 0000 0001 + WFE 1111 0011 1010 1111 1000 0000 0000 0010 + WFI 1111 0011 1010 1111 1000 0000 0000 0011 - # TODO: Implement SEV, SEVL; may help SMP performance. - # SEV 1111 0011 1010 1111 1000 0000 0000 0100 - # SEVL 1111 0011 1010 1111 1000 0000 0000 0101 + # TODO: Implement SEV, SEVL; may help SMP performance. + # SEV 1111 0011 1010 1111 1000 0000 0000 0100 + # SEVL 1111 0011 1010 1111 1000 0000 0000 0101 - # For M-profile minimal-RAS ESB can be a NOP, which is the - # default behaviour since it is in the hint space. - # ESB 1111 0011 1010 1111 1000 0000 0001 0000 + ESB 1111 0011 1010 1111 1000 0000 0001 0000 + ] # The canonical nop ends in 0000 0000, but the whole rest # of the space is "reserved hint, behaves as nop". 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(probe_access)(CPUARMState *env, target_ulong ptr, access_type, mmu_idx, ra); } } + +/* + * This function corresponds to AArch64.vESBOperation(). + * Note that the AArch32 version is not functionally different. + */ +void HELPER(vesb)(CPUARMState *env) +{ + /* + * The EL2Enabled() check is done inside arm_hcr_el2_eff, + * and will return HCR_EL2.VSE == 0, so nothing happens. + */ + uint64_t hcr = arm_hcr_el2_eff(env); + bool enabled = !(hcr & HCR_TGE) && (hcr & HCR_AMO); + bool pending = enabled && (hcr & HCR_VSE); + bool masked = (env->daif & PSTATE_A); + + /* If VSE pending and masked, defer the exception. */ + if (pending && masked) { + uint32_t syndrome; + + if (arm_el_is_aa64(env, 1)) { + /* Copy across IDS and ISS from VSESR. */ + syndrome = env->cp15.vsesr_el2 & 0x1ffffff; + } else { + ARMMMUFaultInfo fi = { .type = ARMFault_AsyncExternal }; + + if (extended_addresses_enabled(env)) { + syndrome = arm_fi_to_lfsc(&fi); + } else { + syndrome = arm_fi_to_sfsc(&fi); + } + /* Copy across AET and ExT from VSESR. */ + syndrome |= env->cp15.vsesr_el2 & 0xd000; + } + + /* Set VDISR_EL2.A along with the syndrome. */ + env->cp15.vdisr_el2 = syndrome | (1u << 31); + + /* Clear pending virtual SError */ + env->cp15.hcr_el2 &= ~HCR_VSE; + cpu_reset_interrupt(env_cpu(env), CPU_INTERRUPT_VSERR); + } +} 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_hint(DisasContext *s, uint32_t insn, gen_helper_autib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); } break; + case 0b10000: /* ESB */ + /* Without RAS, we must implement this as NOP. */ + if (dc_isar_feature(aa64_ras, s)) { + /* + * QEMU does not have a source of physical SErrors, + * so we are only concerned with virtual SErrors. + * The pseudocode in the ARM for this case is + * if PSTATE.EL IN {EL0, EL1} && EL2Enabled() then + * AArch64.vESBOperation(); + * Most of the condition can be evaluated at translation time. + * Test for EL2 present, and defer test for SEL2 to runtime. + */ + if (s->current_el <= 1 && arm_dc_feature(s, ARM_FEATURE_EL2)) { + gen_helper_vesb(cpu_env); + } + } + break; case 0b11000: /* PACIAZ */ if (s->pauth_active) { gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], 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_WFI(DisasContext *s, arg_WFI *a) return true; } +static bool trans_ESB(DisasContext *s, arg_ESB *a) +{ + /* + * For M-profile, minimal-RAS ESB can be a NOP. + * Without RAS, we must implement this as NOP. + */ + if (!arm_dc_feature(s, ARM_FEATURE_M) && dc_isar_feature(aa32_ras, s)) { + /* + * QEMU does not have a source of physical SErrors, + * so we are only concerned with virtual SErrors. + * The pseudocode in the ARM for this case is + * if PSTATE.EL IN {EL0, EL1} && EL2Enabled() then + * AArch32.vESBOperation(); + * Most of the condition can be evaluated at translation time. + * Test for EL2 present, and defer test for SEL2 to runtime. + */ + if (s->current_el <= 1 && arm_dc_feature(s, ARM_FEATURE_EL2)) { + gen_helper_vesb(cpu_env); + } + } + return true; +} + static bool trans_NOP(DisasContext *s, arg_NOP *a) { return true; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 1 + target/arm/cpu_tcg.c | 1 + 3 files changed, 3 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_PMULL (PMULL, PMULL2 instructions) - FEAT_PMUv3p1 (PMU Extensions v3.1) - FEAT_PMUv3p4 (PMU Extensions v3.4) +- FEAT_RAS (Reliability, availability, and serviceability) - FEAT_RDM (Advanced SIMD rounding double multiply accumulate instructions) - FEAT_RNG (Random number generator) - FEAT_SB (Speculation Barrier) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); /* FEAT_FP16 */ t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); /* FEAT_FP16 */ + t = FIELD_DP64(t, ID_AA64PFR0, RAS, 1); /* FEAT_RAS */ t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) t = cpu->isar.id_pfr0; t = FIELD_DP32(t, ID_PFR0, DIT, 1); /* FEAT_DIT */ + t = FIELD_DP32(t, ID_PFR0, RAS, 1); /* FEAT_RAS */ cpu->isar.id_pfr0 = t; t = cpu->isar.id_pfr2; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This feature is AArch64 only, and applies to physical SErrors, which QEMU does not implement, thus the feature is a nop. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_FlagM2 (Enhancements to flag manipulation instructions) - FEAT_HPDS (Hierarchical permission disables) - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) +- FEAT_IESB (Implicit error synchronization event) - FEAT_JSCVT (JavaScript conversion instructions) - FEAT_LOR (Limited ordering regions) - FEAT_LPA (Large Physical Address space) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64mmfr2; t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* FEAT_TTCNP */ t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1); /* FEAT_UAO */ + t = FIELD_DP64(t, ID_AA64MMFR2, IESB, 1); /* FEAT_IESB */ t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */ t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* FEAT_TTST */ t = FIELD_DP64(t, ID_AA64MMFR2, TTL, 1); /* FEAT_TTL */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This extension concerns branch speculation, which TCG does not implement. Thus we can trivially enable this feature. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 1 + target/arm/cpu_tcg.c | 1 + 3 files changed, 3 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_BBM at level 2 (Translation table break-before-make levels) - FEAT_BF16 (AArch64 BFloat16 instructions) - FEAT_BTI (Branch Target Identification) +- FEAT_CSV2 (Cache speculation variant 2) - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) - FEAT_Debugv8p2 (Debug changes for v8.2) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ + t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 1); /* FEAT_CSV2 */ cpu->isar.id_aa64pfr0 = t; t = cpu->isar.id_aa64pfr1; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_mmfr4 = t; t = cpu->isar.id_pfr0; + t = FIELD_DP32(t, ID_PFR0, CSV2, 2); /* FEAT_CVS2 */ t = FIELD_DP32(t, ID_PFR0, DIT, 1); /* FEAT_DIT */ t = FIELD_DP32(t, ID_PFR0, RAS, 1); /* FEAT_RAS */ cpu->isar.id_pfr0 = t; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> There is no branch prediction in TCG, therefore there is no need to actually include the context number into the predictor. Therefore all we need to do is add the state for SCXTNUM_ELx. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 3 ++ target/arm/cpu.h | 16 +++++++++ target/arm/cpu.c | 5 +++ target/arm/cpu64.c | 3 +- target/arm/helper.c | 61 ++++++++++++++++++++++++++++++++++- 5 files changed, 86 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_BF16 (AArch64 BFloat16 instructions) - FEAT_BTI (Branch Target Identification) - FEAT_CSV2 (Cache speculation variant 2) +- FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) +- FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) +- FEAT_CSV2_2 (Cache speculation variant 2, version 2) - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) - FEAT_Debugv8p2 (Debug changes for v8.2) 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 CPUArchState { ARMPACKey apdb; ARMPACKey apga; } keys; + + uint64_t scxtnum_el[4]; #endif #if defined(CONFIG_USER_ONLY) @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_WXN (1U << 19) #define SCTLR_ST (1U << 20) /* up to ??, RAZ in v6 */ #define SCTLR_UWXN (1U << 20) /* v7 onward, AArch32 only */ +#define SCTLR_TSCXT (1U << 20) /* FEAT_CSV2_1p2, AArch64 only */ #define SCTLR_FI (1U << 21) /* up to v7, v8 RES0 */ #define SCTLR_IESB (1U << 21) /* v8.2-IESB, AArch64 only */ #define SCTLR_U (1U << 22) /* up to v6, RAO in v7 */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; } +static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) +{ + int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); + if (key >= 2) { + return true; /* FEAT_CSV2_2 */ + } + if (key == 1) { + key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); + return key >= 2; /* FEAT_CSV2_1p2 */ + } + return false; +} + static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; 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(DeviceState *dev) */ env->cp15.gcr_el1 = 0x1ffff; } + /* + * Disable access to SCXTNUM_EL0 from CSV2_1p2. + * This is not yet exposed from the Linux kernel in any way. + */ + env->cp15.sctlr_el[1] |= SCTLR_TSCXT; #else /* Reset into the highest available EL */ if (arm_feature(env, ARM_FEATURE_EL3)) { diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ - t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 1); /* FEAT_CSV2 */ + t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 2); /* FEAT_CSV2_2 */ cpu->isar.id_aa64pfr0 = t; t = cpu->isar.id_aa64pfr1; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) * we do for EL2 with the virtualization=on property. */ t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ + t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ cpu->isar.id_aa64pfr1 = t; t = cpu->isar.id_aa64mmfr0; 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_mte, cpu)) { valid_mask |= SCR_ATA; } + if (cpu_isar_feature(aa64_scxtnum, cpu)) { + valid_mask |= SCR_ENSCXT; + } } else { valid_mask &= ~(SCR_RW | SCR_ST); if (cpu_isar_feature(aa32_ras, cpu)) { @@ -XXX,XX +XXX,XX @@ static void do_hcr_write(CPUARMState *env, uint64_t value, uint64_t valid_mask) if (cpu_isar_feature(aa64_mte, cpu)) { valid_mask |= HCR_ATA | HCR_DCT | HCR_TID5; } + if (cpu_isar_feature(aa64_scxtnum, cpu)) { + valid_mask |= HCR_ENSCXT; + } } /* Clear RES0 bits. */ @@ -XXX,XX +XXX,XX @@ static void define_arm_vh_e2h_redirects_aliases(ARMCPU *cpu) { K(3, 0, 5, 6, 0), K(3, 4, 5, 6, 0), K(3, 5, 5, 6, 0), "TFSR_EL1", "TFSR_EL2", "TFSR_EL12", isar_feature_aa64_mte }, + { K(3, 0, 13, 0, 7), K(3, 4, 13, 0, 7), K(3, 5, 13, 0, 7), + "SCXTNUM_EL1", "SCXTNUM_EL2", "SCXTNUM_EL12", + isar_feature_aa64_scxtnum }, + /* TODO: ARMv8.2-SPE -- PMSCR_EL2 */ /* TODO: ARMv8.4-Trace -- TRFCR_EL2 */ }; @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo mte_el0_cacheop_reginfo[] = { }, }; -#endif +static CPAccessResult access_scxtnum(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + uint64_t hcr = arm_hcr_el2_eff(env); + int el = arm_current_el(env); + + if (el == 0 && !((hcr & HCR_E2H) && (hcr & HCR_TGE))) { + if (env->cp15.sctlr_el[1] & SCTLR_TSCXT) { + if (hcr & HCR_TGE) { + return CP_ACCESS_TRAP_EL2; + } + return CP_ACCESS_TRAP; + } + } else if (el < 2 && (env->cp15.sctlr_el[2] & SCTLR_TSCXT)) { + return CP_ACCESS_TRAP_EL2; + } + if (el < 2 && arm_is_el2_enabled(env) && !(hcr & HCR_ENSCXT)) { + return CP_ACCESS_TRAP_EL2; + } + if (el < 3 + && arm_feature(env, ARM_FEATURE_EL3) + && !(env->cp15.scr_el3 & SCR_ENSCXT)) { + return CP_ACCESS_TRAP_EL3; + } + return CP_ACCESS_OK; +} + +static const ARMCPRegInfo scxtnum_reginfo[] = { + { .name = "SCXTNUM_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 13, .crm = 0, .opc2 = 7, + .access = PL0_RW, .accessfn = access_scxtnum, + .fieldoffset = offsetof(CPUARMState, scxtnum_el[0]) }, + { .name = "SCXTNUM_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 13, .crm = 0, .opc2 = 7, + .access = PL1_RW, .accessfn = access_scxtnum, + .fieldoffset = offsetof(CPUARMState, scxtnum_el[1]) }, + { .name = "SCXTNUM_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 13, .crm = 0, .opc2 = 7, + .access = PL2_RW, .accessfn = access_scxtnum, + .fieldoffset = offsetof(CPUARMState, scxtnum_el[2]) }, + { .name = "SCXTNUM_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 13, .crm = 0, .opc2 = 7, + .access = PL3_RW, + .fieldoffset = offsetof(CPUARMState, scxtnum_el[3]) }, +}; +#endif /* TARGET_AARCH64 */ static CPAccessResult access_predinv(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, mte_tco_ro_reginfo); define_arm_cp_regs(cpu, mte_el0_cacheop_reginfo); } + + if (cpu_isar_feature(aa64_scxtnum, cpu)) { + define_arm_cp_regs(cpu, scxtnum_reginfo); + } #endif if (cpu_isar_feature(any_predinv, cpu)) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This extension concerns cache speculation, which TCG does not implement. Thus we can trivially enable this feature. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 1 + target/arm/cpu_tcg.c | 1 + 3 files changed, 3 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) - FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) - FEAT_CSV2_2 (Cache speculation variant 2, version 2) +- FEAT_CSV3 (Cache speculation variant 3) - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) - FEAT_Debugv8p2 (Debug changes for v8.2) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 2); /* FEAT_CSV2_2 */ + t = FIELD_DP64(t, ID_AA64PFR0, CSV3, 1); /* FEAT_CSV3 */ cpu->isar.id_aa64pfr0 = t; t = cpu->isar.id_aa64pfr1; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_pfr0 = t; t = cpu->isar.id_pfr2; + t = FIELD_DP32(t, ID_PFR2, CSV3, 1); /* FEAT_CSV3 */ t = FIELD_DP32(t, ID_PFR2, SSBS, 1); /* FEAT_SSBS */ cpu->isar.id_pfr2 = t; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This extension concerns not merging memory access, which TCG does not implement. Thus we can trivially enable this feature. Add a comment to handle_hint for the DGH instruction, but no code. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu64.c | 1 + target/arm/translate-a64.c | 1 + 3 files changed, 3 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) - FEAT_CSV2_2 (Cache speculation variant 2, version 2) - FEAT_CSV3 (Cache speculation variant 3) +- FEAT_DGH (Data gathering hint) - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) - FEAT_Debugv8p2 (Debug changes for v8.2) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); /* FEAT_SB */ t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); /* FEAT_SPECRES */ t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 1); /* FEAT_BF16 */ + t = FIELD_DP64(t, ID_AA64ISAR1, DGH, 1); /* FEAT_DGH */ t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); /* FEAT_I8MM */ cpu->isar.id_aa64isar1 = t; 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_hint(DisasContext *s, uint32_t insn, break; case 0b00100: /* SEV */ case 0b00101: /* SEVL */ + case 0b00110: /* DGH */ /* we treat all as NOP at least for now */ break; case 0b00111: /* XPACLRI */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Enable the a76 for virt and sbsa board use. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/virt.rst | 1 + hw/arm/sbsa-ref.c | 1 + hw/arm/virt.c | 1 + target/arm/cpu64.c | 66 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ Supported guest CPU types: - ``cortex-a53`` (64-bit) - ``cortex-a57`` (64-bit) - ``cortex-a72`` (64-bit) +- ``cortex-a76`` (64-bit) - ``a64fx`` (64-bit) - ``host`` (with KVM only) - ``max`` (same as ``host`` for KVM; best possible emulation with TCG) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { static const char * const valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), + ARM_CPU_TYPE_NAME("cortex-a76"), ARM_CPU_TYPE_NAME("max"), }; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), + ARM_CPU_TYPE_NAME("cortex-a76"), ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("host"), ARM_CPU_TYPE_NAME("max"), 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_cortex_a72_a57_a53_cp_reginfo(cpu); } +static void aarch64_a76_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,cortex-a76"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + + /* Ordered by B2.4 AArch64 registers by functional group */ + cpu->clidr = 0x82000023; + cpu->ctr = 0x8444C004; + cpu->dcz_blocksize = 4; + cpu->isar.id_aa64dfr0 = 0x0000000010305408ull; + cpu->isar.id_aa64isar0 = 0x0000100010211120ull; + cpu->isar.id_aa64isar1 = 0x0000000000100001ull; + cpu->isar.id_aa64mmfr0 = 0x0000000000101122ull; + cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; + cpu->isar.id_aa64mmfr2 = 0x0000000000001011ull; + cpu->isar.id_aa64pfr0 = 0x1100000010111112ull; /* GIC filled in later */ + cpu->isar.id_aa64pfr1 = 0x0000000000000010ull; + cpu->id_afr0 = 0x00000000; + cpu->isar.id_dfr0 = 0x04010088; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00010142; + cpu->isar.id_isar5 = 0x01011121; + cpu->isar.id_isar6 = 0x00000010; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02122211; + cpu->isar.id_mmfr4 = 0x00021110; + cpu->isar.id_pfr0 = 0x10010131; + cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ + cpu->isar.id_pfr2 = 0x00000011; + cpu->midr = 0x414fd0b1; /* r4p1 */ + cpu->revidr = 0; + + /* From B2.18 CCSIDR_EL1 */ + cpu->ccsidr[0] = 0x701fe01a; /* 64KB L1 dcache */ + cpu->ccsidr[1] = 0x201fe01a; /* 64KB L1 icache */ + cpu->ccsidr[2] = 0x707fe03a; /* 512KB L2 cache */ + + /* From B2.93 SCTLR_EL3 */ + cpu->reset_sctlr = 0x30c50838; + + /* From B4.23 ICH_VTR_EL2 */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + + /* From B5.1 AdvSIMD AArch64 register summary */ + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x13211111; + cpu->isar.mvfr2 = 0x00000043; +} + void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) { /* @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, + { .name = "cortex-a76", .initfn = aarch64_a76_initfn }, { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, #if defined(CONFIG_KVM) || defined(CONFIG_HVF) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Enable the n1 for virt and sbsa board use. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220506180242.216785-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/virt.rst | 1 + hw/arm/sbsa-ref.c | 1 + hw/arm/virt.c | 1 + target/arm/cpu64.c | 66 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ Supported guest CPU types: - ``cortex-a76`` (64-bit) - ``a64fx`` (64-bit) - ``host`` (with KVM only) +- ``neoverse-n1`` (64-bit) - ``max`` (same as ``host`` for KVM; best possible emulation with TCG) Note that the default is ``cortex-a15``, so for an AArch64 guest you must diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const char * const valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), ARM_CPU_TYPE_NAME("cortex-a76"), + ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("max"), }; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a72"), ARM_CPU_TYPE_NAME("cortex-a76"), ARM_CPU_TYPE_NAME("a64fx"), + ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("host"), ARM_CPU_TYPE_NAME("max"), }; 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_a76_initfn(Object *obj) cpu->isar.mvfr2 = 0x00000043; } +static void aarch64_neoverse_n1_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,neoverse-n1"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + + /* Ordered by B2.4 AArch64 registers by functional group */ + cpu->clidr = 0x82000023; + cpu->ctr = 0x8444c004; + cpu->dcz_blocksize = 4; + cpu->isar.id_aa64dfr0 = 0x0000000110305408ull; + cpu->isar.id_aa64isar0 = 0x0000100010211120ull; + cpu->isar.id_aa64isar1 = 0x0000000000100001ull; + cpu->isar.id_aa64mmfr0 = 0x0000000000101125ull; + cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; + cpu->isar.id_aa64mmfr2 = 0x0000000000001011ull; + cpu->isar.id_aa64pfr0 = 0x1100000010111112ull; /* GIC filled in later */ + cpu->isar.id_aa64pfr1 = 0x0000000000000020ull; + cpu->id_afr0 = 0x00000000; + cpu->isar.id_dfr0 = 0x04010088; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00010142; + cpu->isar.id_isar5 = 0x01011121; + cpu->isar.id_isar6 = 0x00000010; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02122211; + cpu->isar.id_mmfr4 = 0x00021110; + cpu->isar.id_pfr0 = 0x10010131; + cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ + cpu->isar.id_pfr2 = 0x00000011; + cpu->midr = 0x414fd0c1; /* r4p1 */ + cpu->revidr = 0; + + /* From B2.23 CCSIDR_EL1 */ + cpu->ccsidr[0] = 0x701fe01a; /* 64KB L1 dcache */ + cpu->ccsidr[1] = 0x201fe01a; /* 64KB L1 icache */ + cpu->ccsidr[2] = 0x70ffe03a; /* 1MB L2 cache */ + + /* From B2.98 SCTLR_EL3 */ + cpu->reset_sctlr = 0x30c50838; + + /* From B4.23 ICH_VTR_EL2 */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + + /* From B5.1 AdvSIMD AArch64 register summary */ + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x13211111; + cpu->isar.mvfr2 = 0x00000043; +} + void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) { /* @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, { .name = "cortex-a76", .initfn = aarch64_a76_initfn }, { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, + { .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, #if defined(CONFIG_KVM) || defined(CONFIG_HVF) { .name = "host", .initfn = aarch64_host_initfn }, -- 2.25.1 From: Leif Lindholm <quic_llindhol@quicinc.com> The sbsa-ref machine is continuously evolving. Some of the changes we want to make in the near future, to align with real components (e.g. the GIC-700), will break compatibility for existing firmware. Introduce two new properties to the DT generated on machine generation: - machine-version-major To be incremented when a platform change makes the machine incompatible with existing firmware. - machine-version-minor To be incremented when functionality is added to the machine without causing incompatibility with existing firmware. to be reset to 0 when machine-version-major is incremented. This versioning scheme is *neither*: - A QEMU versioned machine type; a given version of QEMU will emulate a given version of the platform. - A reflection of level of SBSA (now SystemReady SR) support provided. The version will increment on guest-visible functional changes only, akin to a revision ID register found on a physical platform. These properties are both introduced with the value 0. (Hence, a machine where the DT is lacking these nodes is equivalent to version 0.0.) Signed-off-by: Leif Lindholm <quic_llindhol@quicinc.com> Message-id: 20220505113947.75714-1-quic_llindhol@quicinc.com Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Radoslaw Biernacki <rad@semihalf.com> Cc: Cédric Le Goater <clg@kaod.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static void create_fdt(SBSAMachineState *sms) qemu_fdt_setprop_cell(fdt, "/", "#address-cells", 0x2); qemu_fdt_setprop_cell(fdt, "/", "#size-cells", 0x2); + /* + * This versioning scheme is for informing platform fw only. It is neither: + * - A QEMU versioned machine type; a given version of QEMU will emulate + * a given version of the platform. + * - A reflection of level of SBSA (now SystemReady SR) support provided. + * + * machine-version-major: updated when changes breaking fw compatibility + * are introduced. + * machine-version-minor: updated when features are added that don't break + * fw compatibility. + */ + qemu_fdt_setprop_cell(fdt, "/", "machine-version-major", 0); + qemu_fdt_setprop_cell(fdt, "/", "machine-version-minor", 0); + if (ms->numa_state->have_numa_distance) { int size = nb_numa_nodes * nb_numa_nodes * 3 * sizeof(uint32_t); uint32_t *matrix = g_malloc0(size); -- 2.25.1 From: Gavin Shan <gshan@redhat.com> This adds cluster-id in CPU instance properties, which will be used by arm/virt machine. Besides, the cluster-id is also verified or dumped in various spots: * hw/core/machine.c::machine_set_cpu_numa_node() to associate CPU with its NUMA node. * hw/core/machine.c::machine_numa_finish_cpu_init() to record CPU slots with no NUMA mapping set. * hw/core/machine-hmp-cmds.c::hmp_hotpluggable_cpus() to dump cluster-id. Signed-off-by: Gavin Shan <gshan@redhat.com> Reviewed-by: Yanan Wang <wangyanan55@huawei.com> Acked-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20220503140304.855514-2-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qapi/machine.json | 6 ++++-- hw/core/machine-hmp-cmds.c | 4 ++++ hw/core/machine.c | 16 ++++++++++++++++ 3 files changed, 24 insertions(+), 2 deletions(-) diff --git a/qapi/machine.json b/qapi/machine.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/machine.json +++ b/qapi/machine.json @@ -XXX,XX +XXX,XX @@ # @node-id: NUMA node ID the CPU belongs to # @socket-id: socket number within node/board the CPU belongs to # @die-id: die number within socket the CPU belongs to (since 4.1) -# @core-id: core number within die the CPU belongs to +# @cluster-id: cluster number within die the CPU belongs to (since 7.1) +# @core-id: core number within cluster the CPU belongs to # @thread-id: thread number within core the CPU belongs to # -# Note: currently there are 5 properties that could be present +# Note: currently there are 6 properties that could be present # but management should be prepared to pass through other # properties with device_add command to allow for future # interface extension. This also requires the filed names to be kept in @@ -XXX,XX +XXX,XX @@ 'data': { '*node-id': 'int', '*socket-id': 'int', '*die-id': 'int', + '*cluster-id': 'int', '*core-id': 'int', '*thread-id': 'int' } diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine-hmp-cmds.c +++ b/hw/core/machine-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ void hmp_hotpluggable_cpus(Monitor *mon, const QDict *qdict) if (c->has_die_id) { monitor_printf(mon, " die-id: \"%" PRIu64 "\"\n", c->die_id); } + if (c->has_cluster_id) { + monitor_printf(mon, " cluster-id: \"%" PRIu64 "\"\n", + c->cluster_id); + } if (c->has_core_id) { monitor_printf(mon, " core-id: \"%" PRIu64 "\"\n", c->core_id); } diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ void machine_set_cpu_numa_node(MachineState *machine, return; } + if (props->has_cluster_id && !slot->props.has_cluster_id) { + error_setg(errp, "cluster-id is not supported"); + return; + } + if (props->has_socket_id && !slot->props.has_socket_id) { error_setg(errp, "socket-id is not supported"); return; @@ -XXX,XX +XXX,XX @@ void machine_set_cpu_numa_node(MachineState *machine, continue; } + if (props->has_cluster_id && + props->cluster_id != slot->props.cluster_id) { + continue; + } + if (props->has_die_id && props->die_id != slot->props.die_id) { continue; } @@ -XXX,XX +XXX,XX @@ static char *cpu_slot_to_string(const CPUArchId *cpu) } g_string_append_printf(s, "die-id: %"PRId64, cpu->props.die_id); } + if (cpu->props.has_cluster_id) { + if (s->len) { + g_string_append_printf(s, ", "); + } + g_string_append_printf(s, "cluster-id: %"PRId64, cpu->props.cluster_id); + } if (cpu->props.has_core_id) { if (s->len) { g_string_append_printf(s, ", "); -- 2.25.1 From: Gavin Shan <gshan@redhat.com> The CPU topology isn't enabled on arm/virt machine yet, but we're going to do it in next patch. After the CPU topology is enabled by next patch, "thread-id=1" becomes invalid because the CPU core is preferred on arm/virt machine. It means these two CPUs have 0/1 as their core IDs, but their thread IDs are all 0. It will trigger test failure as the following message indicates: [14/21 qemu:qtest+qtest-aarch64 / qtest-aarch64/numa-test ERROR 1.48s killed by signal 6 SIGABRT >>> G_TEST_DBUS_DAEMON=/home/gavin/sandbox/qemu.main/tests/dbus-vmstate-daemon.sh \ QTEST_QEMU_STORAGE_DAEMON_BINARY=./storage-daemon/qemu-storage-daemon \ QTEST_QEMU_BINARY=./qemu-system-aarch64 \ QTEST_QEMU_IMG=./qemu-img MALLOC_PERTURB_=83 \ /home/gavin/sandbox/qemu.main/build/tests/qtest/numa-test --tap -k ―――――――――――――――――――――――――――――――――――――――――――――― stderr: qemu-system-aarch64: -numa cpu,node-id=0,thread-id=1: no match found This fixes the issue by providing comprehensive SMP configurations in aarch64_numa_cpu(). The SMP configurations aren't used before the CPU topology is enabled in next patch. Signed-off-by: Gavin Shan <gshan@redhat.com> Reviewed-by: Yanan Wang <wangyanan55@huawei.com> Message-id: 20220503140304.855514-3-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/numa-test.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/numa-test.c +++ b/tests/qtest/numa-test.c @@ -XXX,XX +XXX,XX @@ static void aarch64_numa_cpu(const void *data) QTestState *qts; g_autofree char *cli = NULL; - cli = make_cli(data, "-machine smp.cpus=2 " + cli = make_cli(data, "-machine " + "smp.cpus=2,smp.sockets=1,smp.clusters=1,smp.cores=1,smp.threads=2 " "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 " "-numa cpu,node-id=1,thread-id=0 " "-numa cpu,node-id=0,thread-id=1"); -- 2.25.1 From: Gavin Shan <gshan@redhat.com> Currently, the SMP configuration isn't considered when the CPU topology is populated. In this case, it's impossible to provide the default CPU-to-NUMA mapping or association based on the socket ID of the given CPU. This takes account of SMP configuration when the CPU topology is populated. The die ID for the given CPU isn't assigned since it's not supported on arm/virt machine. Besides, the used SMP configuration in qtest/numa-test/aarch64_numa_cpu() is corrcted to avoid testing failure Signed-off-by: Gavin Shan <gshan@redhat.com> Reviewed-by: Yanan Wang <wangyanan55@huawei.com> Acked-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20220503140304.855514-4-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) int n; unsigned int max_cpus = ms->smp.max_cpus; VirtMachineState *vms = VIRT_MACHINE(ms); + MachineClass *mc = MACHINE_GET_CLASS(vms); if (ms->possible_cpus) { assert(ms->possible_cpus->len == max_cpus); @@ -XXX,XX +XXX,XX @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) ms->possible_cpus->cpus[n].type = ms->cpu_type; ms->possible_cpus->cpus[n].arch_id = virt_cpu_mp_affinity(vms, n); + + assert(!mc->smp_props.dies_supported); + ms->possible_cpus->cpus[n].props.has_socket_id = true; + ms->possible_cpus->cpus[n].props.socket_id = + n / (ms->smp.clusters * ms->smp.cores * ms->smp.threads); + ms->possible_cpus->cpus[n].props.has_cluster_id = true; + ms->possible_cpus->cpus[n].props.cluster_id = + (n / (ms->smp.cores * ms->smp.threads)) % ms->smp.clusters; + ms->possible_cpus->cpus[n].props.has_core_id = true; + ms->possible_cpus->cpus[n].props.core_id = + (n / ms->smp.threads) % ms->smp.cores; ms->possible_cpus->cpus[n].props.has_thread_id = true; - ms->possible_cpus->cpus[n].props.thread_id = n; + ms->possible_cpus->cpus[n].props.thread_id = + n % ms->smp.threads; } return ms->possible_cpus; } -- 2.25.1 From: Gavin Shan <gshan@redhat.com> In aarch64_numa_cpu(), the CPU and NUMA association is something like below. Two threads in the same core/cluster/socket are associated with two individual NUMA nodes, which is unreal as Igor Mammedov mentioned. We don't expect the association to break NUMA-to-socket boundary, which matches with the real world. NUMA-node socket cluster core thread ------------------------------------------ 0 0 0 0 0 1 0 0 0 1 This corrects the topology for CPUs and their association with NUMA nodes. After this patch is applied, the CPU and NUMA association becomes something like below, which looks real. Besides, socket/cluster/core/thread IDs are all checked when the NUMA node IDs are verified. It helps to check if the CPU topology is properly populated or not. NUMA-node socket cluster core thread ------------------------------------------ 0 1 0 0 0 1 0 0 0 0 Suggested-by: Igor Mammedov <imammedo@redhat.com> Signed-off-by: Gavin Shan <gshan@redhat.com> Acked-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20220503140304.855514-5-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/numa-test.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/tests/qtest/numa-test.c b/tests/qtest/numa-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/numa-test.c +++ b/tests/qtest/numa-test.c @@ -XXX,XX +XXX,XX @@ static void aarch64_numa_cpu(const void *data) g_autofree char *cli = NULL; cli = make_cli(data, "-machine " - "smp.cpus=2,smp.sockets=1,smp.clusters=1,smp.cores=1,smp.threads=2 " + "smp.cpus=2,smp.sockets=2,smp.clusters=1,smp.cores=1,smp.threads=1 " "-numa node,nodeid=0,memdev=ram -numa node,nodeid=1 " - "-numa cpu,node-id=1,thread-id=0 " - "-numa cpu,node-id=0,thread-id=1"); + "-numa cpu,node-id=0,socket-id=1,cluster-id=0,core-id=0,thread-id=0 " + "-numa cpu,node-id=1,socket-id=0,cluster-id=0,core-id=0,thread-id=0"); qts = qtest_init(cli); cpus = get_cpus(qts, &resp); g_assert(cpus); while ((e = qlist_pop(cpus))) { QDict *cpu, *props; - int64_t thread, node; + int64_t socket, cluster, core, thread, node; cpu = qobject_to(QDict, e); g_assert(qdict_haskey(cpu, "props")); @@ -XXX,XX +XXX,XX @@ static void aarch64_numa_cpu(const void *data) g_assert(qdict_haskey(props, "node-id")); node = qdict_get_int(props, "node-id"); + g_assert(qdict_haskey(props, "socket-id")); + socket = qdict_get_int(props, "socket-id"); + g_assert(qdict_haskey(props, "cluster-id")); + cluster = qdict_get_int(props, "cluster-id"); + g_assert(qdict_haskey(props, "core-id")); + core = qdict_get_int(props, "core-id"); g_assert(qdict_haskey(props, "thread-id")); thread = qdict_get_int(props, "thread-id"); - if (thread == 0) { + if (socket == 0 && cluster == 0 && core == 0 && thread == 0) { g_assert_cmpint(node, ==, 1); - } else if (thread == 1) { + } else if (socket == 1 && cluster == 0 && core == 0 && thread == 0) { g_assert_cmpint(node, ==, 0); } else { g_assert(false); -- 2.25.1 From: Gavin Shan <gshan@redhat.com> When CPU-to-NUMA association isn't explicitly provided by users, the default one is given by mc->get_default_cpu_node_id(). However, the CPU topology isn't fully considered in the default association and this causes CPU topology broken warnings on booting Linux guest. For example, the following warning messages are observed when the Linux guest is booted with the following command lines. /home/gavin/sandbox/qemu.main/build/qemu-system-aarch64 \ -accel kvm -machine virt,gic-version=host \ -cpu host \ -smp 6,sockets=2,cores=3,threads=1 \ -m 1024M,slots=16,maxmem=64G \ -object memory-backend-ram,id=mem0,size=128M \ -object memory-backend-ram,id=mem1,size=128M \ -object memory-backend-ram,id=mem2,size=128M \ -object memory-backend-ram,id=mem3,size=128M \ -object memory-backend-ram,id=mem4,size=128M \ -object memory-backend-ram,id=mem4,size=384M \ -numa node,nodeid=0,memdev=mem0 \ -numa node,nodeid=1,memdev=mem1 \ -numa node,nodeid=2,memdev=mem2 \ -numa node,nodeid=3,memdev=mem3 \ -numa node,nodeid=4,memdev=mem4 \ -numa node,nodeid=5,memdev=mem5 : alternatives: patching kernel code BUG: arch topology borken the CLS domain not a subset of the MC domain <the above error log repeats> BUG: arch topology borken the DIE domain not a subset of the NODE domain With current implementation of mc->get_default_cpu_node_id(), CPU#0 to CPU#5 are associated with NODE#0 to NODE#5 separately. That's incorrect because CPU#0/1/2 should be associated with same NUMA node because they're seated in same socket. This fixes the issue by considering the socket ID when the default CPU-to-NUMA association is provided in virt_possible_cpu_arch_ids(). With this applied, no more CPU topology broken warnings are seen from the Linux guest. The 6 CPUs are associated with NODE#0/1, but there are no CPUs associated with NODE#2/3/4/5. Signed-off-by: Gavin Shan <gshan@redhat.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Yanan Wang <wangyanan55@huawei.com> Message-id: 20220503140304.855514-6-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index) static int64_t virt_get_default_cpu_node_id(const MachineState *ms, int idx) { - return idx % ms->numa_state->num_nodes; + int64_t socket_id = ms->possible_cpus->cpus[idx].props.socket_id; + + return socket_id % ms->numa_state->num_nodes; } static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) -- 2.25.1 From: Gavin Shan <gshan@redhat.com> When the PPTT table is built, the CPU topology is re-calculated, but it's unecessary because the CPU topology has been populated in virt_possible_cpu_arch_ids() on arm/virt machine. This reworks build_pptt() to avoid by reusing the existing IDs in ms->possible_cpus. Currently, the only user of build_pptt() is arm/virt machine. Signed-off-by: Gavin Shan <gshan@redhat.com> Tested-by: Yanan Wang <wangyanan55@huawei.com> Reviewed-by: Yanan Wang <wangyanan55@huawei.com> Acked-by: Igor Mammedov <imammedo@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20220503140304.855514-7-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/acpi/aml-build.c | 111 +++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 63 deletions(-) diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void build_pptt(GArray *table_data, BIOSLinker *linker, MachineState *ms, const char *oem_id, const char *oem_table_id) { MachineClass *mc = MACHINE_GET_CLASS(ms); - GQueue *list = g_queue_new(); - guint pptt_start = table_data->len; - guint parent_offset; - guint length, i; - int uid = 0; - int socket; + CPUArchIdList *cpus = ms->possible_cpus; + int64_t socket_id = -1, cluster_id = -1, core_id = -1; + uint32_t socket_offset = 0, cluster_offset = 0, core_offset = 0; + uint32_t pptt_start = table_data->len; + int n; AcpiTable table = { .sig = "PPTT", .rev = 2, .oem_id = oem_id, .oem_table_id = oem_table_id }; acpi_table_begin(&table, table_data); - for (socket = 0; socket < ms->smp.sockets; socket++) { - g_queue_push_tail(list, - GUINT_TO_POINTER(table_data->len - pptt_start)); - build_processor_hierarchy_node( - table_data, - /* - * Physical package - represents the boundary - * of a physical package - */ - (1 << 0), - 0, socket, NULL, 0); - } - - if (mc->smp_props.clusters_supported) { - length = g_queue_get_length(list); - for (i = 0; i < length; i++) { - int cluster; - - parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list)); - for (cluster = 0; cluster < ms->smp.clusters; cluster++) { - g_queue_push_tail(list, - GUINT_TO_POINTER(table_data->len - pptt_start)); - build_processor_hierarchy_node( - table_data, - (0 << 0), /* not a physical package */ - parent_offset, cluster, NULL, 0); - } + /* + * This works with the assumption that cpus[n].props.*_id has been + * sorted from top to down levels in mc->possible_cpu_arch_ids(). + * Otherwise, the unexpected and duplicated containers will be + * created. + */ + for (n = 0; n < cpus->len; n++) { + if (cpus->cpus[n].props.socket_id != socket_id) { + assert(cpus->cpus[n].props.socket_id > socket_id); + socket_id = cpus->cpus[n].props.socket_id; + cluster_id = -1; + core_id = -1; + socket_offset = table_data->len - pptt_start; + build_processor_hierarchy_node(table_data, + (1 << 0), /* Physical package */ + 0, socket_id, NULL, 0); } - } - length = g_queue_get_length(list); - for (i = 0; i < length; i++) { - int core; - - parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list)); - for (core = 0; core < ms->smp.cores; core++) { - if (ms->smp.threads > 1) { - g_queue_push_tail(list, - GUINT_TO_POINTER(table_data->len - pptt_start)); - build_processor_hierarchy_node( - table_data, - (0 << 0), /* not a physical package */ - parent_offset, core, NULL, 0); - } else { - build_processor_hierarchy_node( - table_data, - (1 << 1) | /* ACPI Processor ID valid */ - (1 << 3), /* Node is a Leaf */ - parent_offset, uid++, NULL, 0); + if (mc->smp_props.clusters_supported) { + if (cpus->cpus[n].props.cluster_id != cluster_id) { + assert(cpus->cpus[n].props.cluster_id > cluster_id); + cluster_id = cpus->cpus[n].props.cluster_id; + core_id = -1; + cluster_offset = table_data->len - pptt_start; + build_processor_hierarchy_node(table_data, + (0 << 0), /* Not a physical package */ + socket_offset, cluster_id, NULL, 0); } + } else { + cluster_offset = socket_offset; } - } - length = g_queue_get_length(list); - for (i = 0; i < length; i++) { - int thread; + if (ms->smp.threads == 1) { + build_processor_hierarchy_node(table_data, + (1 << 1) | /* ACPI Processor ID valid */ + (1 << 3), /* Node is a Leaf */ + cluster_offset, n, NULL, 0); + } else { + if (cpus->cpus[n].props.core_id != core_id) { + assert(cpus->cpus[n].props.core_id > core_id); + core_id = cpus->cpus[n].props.core_id; + core_offset = table_data->len - pptt_start; + build_processor_hierarchy_node(table_data, + (0 << 0), /* Not a physical package */ + cluster_offset, core_id, NULL, 0); + } - parent_offset = GPOINTER_TO_UINT(g_queue_pop_head(list)); - for (thread = 0; thread < ms->smp.threads; thread++) { - build_processor_hierarchy_node( - table_data, + build_processor_hierarchy_node(table_data, (1 << 1) | /* ACPI Processor ID valid */ (1 << 2) | /* Processor is a Thread */ (1 << 3), /* Node is a Leaf */ - parent_offset, uid++, NULL, 0); + core_offset, n, NULL, 0); } } - g_queue_free(list); acpi_table_end(linker, &table); } -- 2.25.1