First arm pullreq of the 5.1 cycle; mostly bugfixes and some cleanup patches. The new clock modelling framework is the big thing here. -- PMM The following changes since commit 648db19685b7030aa558a4ddbd3a8e53d8c9a062: Merge remote-tracking branch 'remotes/armbru/tags/pull-misc-2020-04-29' into staging (2020-04-29 15:07:33 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200430 for you to fetch changes up to 1267437e593e85498f9105b3bdab796630d2e83f: hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes (2020-04-30 11:52:29 +0100) ---------------------------------------------------------------- target-arm queue: * xlnx-zdma: Fix endianness handling of descriptor loading * nrf51: Fix last GPIO CNF address * gicv3: Use gicr_typer in arm_gicv3_icc_reset * msf2: Add EMAC block to SmartFusion2 SoC * New clock modelling framework * hw/arm: versal: Setup the ADMA with 128bit bus-width * Cadence: gem: fix wraparound in 64bit descriptors * cadence_gem: clear RX control descriptor * target/arm: Vectorize integer comparison vs zero * hw/arm/virt: dt: add kaslr-seed property * hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes ---------------------------------------------------------------- Cameron Esfahani (1): nrf51: Fix last GPIO CNF address Damien Hedde (7): hw/core/clock-vmstate: define a vmstate entry for clock state qdev: add clock input&output support to devices. qdev-clock: introduce an init array to ease the device construction hw/misc/zynq_slcr: add clock generation for uarts hw/char/cadence_uart: add clock support hw/arm/xilinx_zynq: connect uart clocks to slcr qdev-monitor: print the device's clock with info qtree Edgar E. Iglesias (7): dma/xlnx-zdma: Fix descriptor loading (MEM) wrt endianness dma/xlnx-zdma: Fix descriptor loading (REG) wrt endianness hw/arm: versal: Setup the ADMA with 128bit bus-width device_tree: Allow name wildcards in qemu_fdt_node_path() device_tree: Constify compat in qemu_fdt_node_path() hw/arm: xlnx-zcu102: Move arm_boot_info into XlnxZCU102 hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes Jerome Forissier (2): hw/arm/virt: dt: move creation of /secure-chosen to create_fdt() hw/arm/virt: dt: add kaslr-seed property Keqian Zhu (2): bugfix: Use gicr_typer in arm_gicv3_icc_reset Typo: Correct the name of CPU hotplug memory region Peter Maydell (2): hw/core/clock: introduce clock object docs/clocks: add device's clock documentation Philippe Mathieu-Daudé (3): target/arm: Restrict the Address Translate write operation to TCG accel target/arm/cpu: Use ARRAY_SIZE() to iterate over ARMCPUInfo[] target/arm/cpu: Update coding style to make checkpatch.pl happy Ramon Fried (2): Cadence: gem: fix wraparound in 64bit descriptors net: cadence_gem: clear RX control descriptor Richard Henderson (1): target/arm: Vectorize integer comparison vs zero Subbaraya Sundeep (3): hw/net: Add Smartfusion2 emac block msf2: Add EMAC block to SmartFusion2 SoC tests/boot_linux_console: Add ethernet test to SmartFusion2 Thomas Huth (1): target/arm: Make cpu_register() available for other files hw/core/Makefile.objs | 2 + hw/net/Makefile.objs | 1 + tests/Makefile.include | 1 + include/hw/arm/msf2-soc.h | 2 + include/hw/char/cadence_uart.h | 1 + include/hw/clock.h | 225 +++++++++++++ include/hw/gpio/nrf51_gpio.h | 2 +- include/hw/net/msf2-emac.h | 53 +++ include/hw/qdev-clock.h | 159 +++++++++ include/hw/qdev-core.h | 12 + include/sysemu/device_tree.h | 5 +- target/arm/cpu-qom.h | 9 +- target/arm/helper.h | 27 +- target/arm/translate.h | 5 + device_tree.c | 4 +- hw/acpi/cpu.c | 2 +- hw/arm/msf2-soc.c | 26 +- hw/arm/virt.c | 20 +- hw/arm/xilinx_zynq.c | 57 +++- hw/arm/xlnx-versal.c | 2 + hw/arm/xlnx-zcu102.c | 39 ++- hw/char/cadence_uart.c | 73 +++- hw/core/clock-vmstate.c | 25 ++ hw/core/clock.c | 130 ++++++++ hw/core/qdev-clock.c | 185 +++++++++++ hw/core/qdev.c | 12 + hw/dma/xlnx-zdma.c | 25 +- hw/intc/arm_gicv3_kvm.c | 4 +- hw/misc/zynq_slcr.c | 172 +++++++++- hw/net/cadence_gem.c | 16 +- hw/net/msf2-emac.c | 589 +++++++++++++++++++++++++++++++++ qdev-monitor.c | 9 + target/arm/cpu.c | 25 +- target/arm/cpu64.c | 16 +- target/arm/helper.c | 17 + target/arm/neon_helper.c | 24 -- target/arm/translate-a64.c | 64 +--- target/arm/translate.c | 256 ++++++++++++-- target/arm/vec_helper.c | 25 ++ MAINTAINERS | 2 + docs/devel/clocks.rst | 391 ++++++++++++++++++++++ docs/devel/index.rst | 1 + hw/char/trace-events | 3 + hw/core/trace-events | 7 + tests/acceptance/boot_linux_console.py | 15 +- 45 files changed, 2538 insertions(+), 202 deletions(-) create mode 100644 include/hw/clock.h create mode 100644 include/hw/net/msf2-emac.h create mode 100644 include/hw/qdev-clock.h create mode 100644 hw/core/clock-vmstate.c create mode 100644 hw/core/clock.c create mode 100644 hw/core/qdev-clock.c create mode 100644 hw/net/msf2-emac.c create mode 100644 docs/devel/clocks.rst From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix descriptor loading from memory wrt host endianness. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200404122718.25111-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -XXX,XX +XXX,XX @@ static void zdma_put_regaddr64(XlnxZDMA *s, unsigned int basereg, uint64_t addr) s->regs[basereg + 1] = addr >> 32; } -static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, void *buf) +static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, + XlnxZDMADescr *descr) { /* ZDMA descriptors must be aligned to their own size. */ if (addr % sizeof(XlnxZDMADescr)) { qemu_log_mask(LOG_GUEST_ERROR, "zdma: unaligned descriptor at %" PRIx64, addr); - memset(buf, 0x0, sizeof(XlnxZDMADescr)); + memset(descr, 0x0, sizeof(XlnxZDMADescr)); s->error = true; return false; } - address_space_read(s->dma_as, addr, s->attr, buf, sizeof(XlnxZDMADescr)); + descr->addr = address_space_ldq_le(s->dma_as, addr, s->attr, NULL); + descr->size = address_space_ldl_le(s->dma_as, addr + 8, s->attr, NULL); + descr->attr = address_space_ldl_le(s->dma_as, addr + 12, s->attr, NULL); return true; } @@ -XXX,XX +XXX,XX @@ static void zdma_update_descr_addr(XlnxZDMA *s, bool type, } else { addr = zdma_get_regaddr64(s, basereg); addr += sizeof(s->dsc_dst); - address_space_read(s->dma_as, addr, s->attr, (void *) &next, 8); + next = address_space_ldq_le(s->dma_as, addr, s->attr, NULL); } zdma_put_regaddr64(s, basereg, next); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix descriptor loading from registers wrt host endianness. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20200404122718.25111-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -XXX,XX +XXX,XX @@ static void zdma_put_regaddr64(XlnxZDMA *s, unsigned int basereg, uint64_t addr) s->regs[basereg + 1] = addr >> 32; } +static void zdma_load_descriptor_reg(XlnxZDMA *s, unsigned int reg, + XlnxZDMADescr *descr) +{ + descr->addr = zdma_get_regaddr64(s, reg); + descr->size = s->regs[reg + 2]; + descr->attr = s->regs[reg + 3]; +} + static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, XlnxZDMADescr *descr) { @@ -XXX,XX +XXX,XX @@ static void zdma_load_src_descriptor(XlnxZDMA *s) unsigned int ptype = ARRAY_FIELD_EX32(s->regs, ZDMA_CH_CTRL0, POINT_TYPE); if (ptype == PT_REG) { - memcpy(&s->dsc_src, &s->regs[R_ZDMA_CH_SRC_DSCR_WORD0], - sizeof(s->dsc_src)); + zdma_load_descriptor_reg(s, R_ZDMA_CH_SRC_DSCR_WORD0, &s->dsc_src); return; } @@ -XXX,XX +XXX,XX @@ static void zdma_load_dst_descriptor(XlnxZDMA *s) bool dst_type; if (ptype == PT_REG) { - memcpy(&s->dsc_dst, &s->regs[R_ZDMA_CH_DST_DSCR_WORD0], - sizeof(s->dsc_dst)); + zdma_load_descriptor_reg(s, R_ZDMA_CH_DST_DSCR_WORD0, &s->dsc_dst); return; } -- 2.20.1 From: Cameron Esfahani <dirty@apple.com> NRF51_GPIO_REG_CNF_END doesn't actually refer to the start of the last valid CNF register: it's referring to the last byte of the last valid CNF register. This hasn't been a problem up to now, as current implementation in memory.c turns an unaligned 4-byte read from 0x77f to a single byte read and the qtest only looks at the least-significant byte of the register. But when running with patches which fix unaligned accesses in memory.c, the qtest breaks. Considering NRF51 doesn't support unaligned accesses, the simplest fix is to actually set NRF51_GPIO_REG_CNF_END to the start of the last valid CNF register: 0x77c. Now, qtests work with or without the unaligned access patches. Reviewed-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Signed-off-by: Cameron Esfahani <dirty@apple.com> Message-id: 51b427f06838622da783d38ba56e3630d6d85c60.1586925392.git.dirty@apple.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/gpio/nrf51_gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/gpio/nrf51_gpio.h b/include/hw/gpio/nrf51_gpio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/gpio/nrf51_gpio.h +++ b/include/hw/gpio/nrf51_gpio.h @@ -XXX,XX +XXX,XX @@ #define NRF51_GPIO_REG_DIRSET 0x518 #define NRF51_GPIO_REG_DIRCLR 0x51C #define NRF51_GPIO_REG_CNF_START 0x700 -#define NRF51_GPIO_REG_CNF_END 0x77F +#define NRF51_GPIO_REG_CNF_END 0x77C #define NRF51_GPIO_PULLDOWN 1 #define NRF51_GPIO_PULLUP 3 -- 2.20.1 From: Keqian Zhu <zhukeqian1@huawei.com> The KVM_VGIC_ATTR macro expect the second parameter as gicr_typer, of which high 32bit is constructed by mp_affinity. For most case, the high 32bit of mp_affinity is zero, so it will always access the ICC_CTLR_EL1 of CPU0. Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com> Message-id: 20200413091552.62748-2-zhukeqian1@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_get(GICv3State *s) static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) { - ARMCPU *cpu; GICv3State *s; GICv3CPUState *c; c = (GICv3CPUState *)env->gicv3state; s = c->gic; - cpu = ARM_CPU(c->cpu); c->icc_pmr_el1 = 0; c->icc_bpr[GICV3_G0] = GIC_MIN_BPR; @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) /* Initialize to actual HW supported configuration */ kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, - KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity), + KVM_VGIC_ATTR(ICC_CTLR_EL1, c->gicr_typer), &c->icc_ctlr_el1[GICV3_NS], false, &error_abort); c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS]; -- 2.20.1 From: Keqian Zhu <zhukeqian1@huawei.com> Replace "acpi-mem-hotplug" with "acpi-cpu-hotplug" Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com> Message-id: 20200413091552.62748-4-zhukeqian1@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/acpi/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -XXX,XX +XXX,XX @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, state->devs[i].arch_id = id_list->cpus[i].arch_id; } memory_region_init_io(&state->ctrl_reg, owner, &cpu_hotplug_ops, state, - "acpi-mem-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); + "acpi-cpu-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); memory_region_add_subregion(as, base_addr, &state->ctrl_reg); } -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Modelled Ethernet MAC of Smartfusion2 SoC. Micrel KSZ8051 PHY is present on Emcraft's SOM kit hence same PHY is emulated. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-2-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/Makefile.objs | 1 + include/hw/net/msf2-emac.h | 53 ++++ hw/net/msf2-emac.c | 589 +++++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + 4 files changed, 645 insertions(+) create mode 100644 include/hw/net/msf2-emac.h create mode 100644 hw/net/msf2-emac.c diff --git a/hw/net/Makefile.objs b/hw/net/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Makefile.objs +++ b/hw/net/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ROCKER) += rocker/rocker.o rocker/rocker_fp.o \ obj-$(call lnot,$(CONFIG_ROCKER)) += rocker/qmp-norocker.o common-obj-$(CONFIG_CAN_BUS) += can/ +common-obj-$(CONFIG_MSF2) += msf2-emac.o diff --git a/include/hw/net/msf2-emac.h b/include/hw/net/msf2-emac.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/msf2-emac.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Smartfusion2 Ethernet MAC. + * + * Copyright (c) 2020 Subbaraya Sundeep <sundeep.lkml@gmail.com>. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "hw/sysbus.h" +#include "exec/memory.h" +#include "net/net.h" +#include "net/eth.h" + +#define TYPE_MSS_EMAC "msf2-emac" +#define MSS_EMAC(obj) \ + OBJECT_CHECK(MSF2EmacState, (obj), TYPE_MSS_EMAC) + +#define R_MAX (0x1a0 / 4) +#define PHY_MAX_REGS 32 + +typedef struct MSF2EmacState { + SysBusDevice parent; + + MemoryRegion mmio; + MemoryRegion *dma_mr; + AddressSpace dma_as; + + qemu_irq irq; + NICState *nic; + NICConf conf; + + uint8_t mac_addr[ETH_ALEN]; + uint32_t rx_desc; + uint16_t phy_regs[PHY_MAX_REGS]; + + uint32_t regs[R_MAX]; +} MSF2EmacState; diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/msf2-emac.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Smartfusion2 Ethernet MAC. + * + * Copyright (c) 2020 Subbaraya Sundeep <sundeep.lkml@gmail.com>. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + * + * Refer to section Ethernet MAC in the document: + * UG0331: SmartFusion2 Microcontroller Subsystem User Guide + * Datasheet URL: + * https://www.microsemi.com/document-portal/cat_view/56661-internal-documents/ + * 56758-soc?lang=en&limit=20&limitstart=220 + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/log.h" +#include "qapi/error.h" +#include "exec/address-spaces.h" +#include "hw/registerfields.h" +#include "hw/net/msf2-emac.h" +#include "hw/net/mii.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" + +REG32(CFG1, 0x0) + FIELD(CFG1, RESET, 31, 1) + FIELD(CFG1, RX_EN, 2, 1) + FIELD(CFG1, TX_EN, 0, 1) + FIELD(CFG1, LB_EN, 8, 1) +REG32(CFG2, 0x4) +REG32(IFG, 0x8) +REG32(HALF_DUPLEX, 0xc) +REG32(MAX_FRAME_LENGTH, 0x10) +REG32(MII_CMD, 0x24) + FIELD(MII_CMD, READ, 0, 1) +REG32(MII_ADDR, 0x28) + FIELD(MII_ADDR, REGADDR, 0, 5) + FIELD(MII_ADDR, PHYADDR, 8, 5) +REG32(MII_CTL, 0x2c) +REG32(MII_STS, 0x30) +REG32(STA1, 0x40) +REG32(STA2, 0x44) +REG32(FIFO_CFG0, 0x48) +REG32(FIFO_CFG4, 0x58) + FIELD(FIFO_CFG4, BCAST, 9, 1) + FIELD(FIFO_CFG4, MCAST, 8, 1) +REG32(FIFO_CFG5, 0x5C) + FIELD(FIFO_CFG5, BCAST, 9, 1) + FIELD(FIFO_CFG5, MCAST, 8, 1) +REG32(DMA_TX_CTL, 0x180) + FIELD(DMA_TX_CTL, EN, 0, 1) +REG32(DMA_TX_DESC, 0x184) +REG32(DMA_TX_STATUS, 0x188) + FIELD(DMA_TX_STATUS, PKTCNT, 16, 8) + FIELD(DMA_TX_STATUS, UNDERRUN, 1, 1) + FIELD(DMA_TX_STATUS, PKT_SENT, 0, 1) +REG32(DMA_RX_CTL, 0x18c) + FIELD(DMA_RX_CTL, EN, 0, 1) +REG32(DMA_RX_DESC, 0x190) +REG32(DMA_RX_STATUS, 0x194) + FIELD(DMA_RX_STATUS, PKTCNT, 16, 8) + FIELD(DMA_RX_STATUS, OVERFLOW, 2, 1) + FIELD(DMA_RX_STATUS, PKT_RCVD, 0, 1) +REG32(DMA_IRQ_MASK, 0x198) +REG32(DMA_IRQ, 0x19c) + +#define EMPTY_MASK (1 << 31) +#define PKT_SIZE 0x7FF +#define PHYADDR 0x1 +#define MAX_PKT_SIZE 2048 + +typedef struct { + uint32_t pktaddr; + uint32_t pktsize; + uint32_t next; +} EmacDesc; + +static uint32_t emac_get_isr(MSF2EmacState *s) +{ + uint32_t ier = s->regs[R_DMA_IRQ_MASK]; + uint32_t tx = s->regs[R_DMA_TX_STATUS] & 0xF; + uint32_t rx = s->regs[R_DMA_RX_STATUS] & 0xF; + uint32_t isr = (rx << 4) | tx; + + s->regs[R_DMA_IRQ] = ier & isr; + return s->regs[R_DMA_IRQ]; +} + +static void emac_update_irq(MSF2EmacState *s) +{ + bool intr = emac_get_isr(s); + + qemu_set_irq(s->irq, intr); +} + +static void emac_load_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +{ + address_space_read(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); + /* Convert from LE into host endianness. */ + d->pktaddr = le32_to_cpu(d->pktaddr); + d->pktsize = le32_to_cpu(d->pktsize); + d->next = le32_to_cpu(d->next); +} + +static void emac_store_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +{ + /* Convert from host endianness into LE. */ + d->pktaddr = cpu_to_le32(d->pktaddr); + d->pktsize = cpu_to_le32(d->pktsize); + d->next = cpu_to_le32(d->next); + + address_space_write(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); +} + +static void msf2_dma_tx(MSF2EmacState *s) +{ + NetClientState *nc = qemu_get_queue(s->nic); + hwaddr desc = s->regs[R_DMA_TX_DESC]; + uint8_t buf[MAX_PKT_SIZE]; + EmacDesc d; + int size; + uint8_t pktcnt; + uint32_t status; + + if (!(s->regs[R_CFG1] & R_CFG1_TX_EN_MASK)) { + return; + } + + while (1) { + emac_load_desc(s, &d, desc); + if (d.pktsize & EMPTY_MASK) { + break; + } + size = d.pktsize & PKT_SIZE; + address_space_read(&s->dma_as, d.pktaddr, MEMTXATTRS_UNSPECIFIED, + buf, size); + /* + * This is very basic way to send packets. Ideally there should be + * a FIFO and packets should be sent out from FIFO only when + * R_CFG1 bit 0 is set. + */ + if (s->regs[R_CFG1] & R_CFG1_LB_EN_MASK) { + nc->info->receive(nc, buf, size); + } else { + qemu_send_packet(nc, buf, size); + } + d.pktsize |= EMPTY_MASK; + emac_store_desc(s, &d, desc); + /* update sent packets count */ + status = s->regs[R_DMA_TX_STATUS]; + pktcnt = FIELD_EX32(status, DMA_TX_STATUS, PKTCNT); + pktcnt++; + s->regs[R_DMA_TX_STATUS] = FIELD_DP32(status, DMA_TX_STATUS, + PKTCNT, pktcnt); + s->regs[R_DMA_TX_STATUS] |= R_DMA_TX_STATUS_PKT_SENT_MASK; + desc = d.next; + } + s->regs[R_DMA_TX_STATUS] |= R_DMA_TX_STATUS_UNDERRUN_MASK; + s->regs[R_DMA_TX_CTL] &= ~R_DMA_TX_CTL_EN_MASK; +} + +static void msf2_phy_update_link(MSF2EmacState *s) +{ + /* Autonegotiation status mirrors link status. */ + if (qemu_get_queue(s->nic)->link_down) { + s->phy_regs[MII_BMSR] &= ~(MII_BMSR_AN_COMP | + MII_BMSR_LINK_ST); + } else { + s->phy_regs[MII_BMSR] |= (MII_BMSR_AN_COMP | + MII_BMSR_LINK_ST); + } +} + +static void msf2_phy_reset(MSF2EmacState *s) +{ + memset(&s->phy_regs[0], 0, sizeof(s->phy_regs)); + s->phy_regs[MII_BMCR] = 0x1140; + s->phy_regs[MII_BMSR] = 0x7968; + s->phy_regs[MII_PHYID1] = 0x0022; + s->phy_regs[MII_PHYID2] = 0x1550; + s->phy_regs[MII_ANAR] = 0x01E1; + s->phy_regs[MII_ANLPAR] = 0xCDE1; + + msf2_phy_update_link(s); +} + +static void write_to_phy(MSF2EmacState *s) +{ + uint8_t reg_addr = s->regs[R_MII_ADDR] & R_MII_ADDR_REGADDR_MASK; + uint8_t phy_addr = (s->regs[R_MII_ADDR] >> R_MII_ADDR_PHYADDR_SHIFT) & + R_MII_ADDR_REGADDR_MASK; + uint16_t data = s->regs[R_MII_CTL] & 0xFFFF; + + if (phy_addr != PHYADDR) { + return; + } + + switch (reg_addr) { + case MII_BMCR: + if (data & MII_BMCR_RESET) { + /* Phy reset */ + msf2_phy_reset(s); + data &= ~MII_BMCR_RESET; + } + if (data & MII_BMCR_AUTOEN) { + /* Complete autonegotiation immediately */ + data &= ~MII_BMCR_AUTOEN; + s->phy_regs[MII_BMSR] |= MII_BMSR_AN_COMP; + } + break; + } + + s->phy_regs[reg_addr] = data; +} + +static uint16_t read_from_phy(MSF2EmacState *s) +{ + uint8_t reg_addr = s->regs[R_MII_ADDR] & R_MII_ADDR_REGADDR_MASK; + uint8_t phy_addr = (s->regs[R_MII_ADDR] >> R_MII_ADDR_PHYADDR_SHIFT) & + R_MII_ADDR_REGADDR_MASK; + + if (phy_addr == PHYADDR) { + return s->phy_regs[reg_addr]; + } else { + return 0xFFFF; + } +} + +static void msf2_emac_do_reset(MSF2EmacState *s) +{ + memset(&s->regs[0], 0, sizeof(s->regs)); + s->regs[R_CFG1] = 0x80000000; + s->regs[R_CFG2] = 0x00007000; + s->regs[R_IFG] = 0x40605060; + s->regs[R_HALF_DUPLEX] = 0x00A1F037; + s->regs[R_MAX_FRAME_LENGTH] = 0x00000600; + s->regs[R_FIFO_CFG5] = 0X3FFFF; + + msf2_phy_reset(s); +} + +static uint64_t emac_read(void *opaque, hwaddr addr, unsigned int size) +{ + MSF2EmacState *s = opaque; + uint32_t r = 0; + + addr >>= 2; + + switch (addr) { + case R_DMA_IRQ: + r = emac_get_isr(s); + break; + default: + if (addr >= ARRAY_SIZE(s->regs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return r; + } + r = s->regs[addr]; + break; + } + return r; +} + +static void emac_write(void *opaque, hwaddr addr, uint64_t val64, + unsigned int size) +{ + MSF2EmacState *s = opaque; + uint32_t value = val64; + uint32_t enreqbits; + uint8_t pktcnt; + + addr >>= 2; + switch (addr) { + case R_DMA_TX_CTL: + s->regs[addr] = value; + if (value & R_DMA_TX_CTL_EN_MASK) { + msf2_dma_tx(s); + } + break; + case R_DMA_RX_CTL: + s->regs[addr] = value; + if (value & R_DMA_RX_CTL_EN_MASK) { + s->rx_desc = s->regs[R_DMA_RX_DESC]; + qemu_flush_queued_packets(qemu_get_queue(s->nic)); + } + break; + case R_CFG1: + s->regs[addr] = value; + if (value & R_CFG1_RESET_MASK) { + msf2_emac_do_reset(s); + } + break; + case R_FIFO_CFG0: + /* + * For our implementation, turning on modules is instantaneous, + * so the states requested via the *ENREQ bits appear in the + * *ENRPLY bits immediately. Also the reset bits to reset PE-MCXMAC + * module are not emulated here since it deals with start of frames, + * inter-packet gap and control frames. + */ + enreqbits = extract32(value, 8, 5); + s->regs[addr] = deposit32(value, 16, 5, enreqbits); + break; + case R_DMA_TX_DESC: + if (value & 0x3) { + qemu_log_mask(LOG_GUEST_ERROR, "Tx Descriptor address should be" + " 32 bit aligned\n"); + } + /* Ignore [1:0] bits */ + s->regs[addr] = value & ~3; + break; + case R_DMA_RX_DESC: + if (value & 0x3) { + qemu_log_mask(LOG_GUEST_ERROR, "Rx Descriptor address should be" + " 32 bit aligned\n"); + } + /* Ignore [1:0] bits */ + s->regs[addr] = value & ~3; + break; + case R_DMA_TX_STATUS: + if (value & R_DMA_TX_STATUS_UNDERRUN_MASK) { + s->regs[addr] &= ~R_DMA_TX_STATUS_UNDERRUN_MASK; + } + if (value & R_DMA_TX_STATUS_PKT_SENT_MASK) { + pktcnt = FIELD_EX32(s->regs[addr], DMA_TX_STATUS, PKTCNT); + pktcnt--; + s->regs[addr] = FIELD_DP32(s->regs[addr], DMA_TX_STATUS, + PKTCNT, pktcnt); + if (pktcnt == 0) { + s->regs[addr] &= ~R_DMA_TX_STATUS_PKT_SENT_MASK; + } + } + break; + case R_DMA_RX_STATUS: + if (value & R_DMA_RX_STATUS_OVERFLOW_MASK) { + s->regs[addr] &= ~R_DMA_RX_STATUS_OVERFLOW_MASK; + } + if (value & R_DMA_RX_STATUS_PKT_RCVD_MASK) { + pktcnt = FIELD_EX32(s->regs[addr], DMA_RX_STATUS, PKTCNT); + pktcnt--; + s->regs[addr] = FIELD_DP32(s->regs[addr], DMA_RX_STATUS, + PKTCNT, pktcnt); + if (pktcnt == 0) { + s->regs[addr] &= ~R_DMA_RX_STATUS_PKT_RCVD_MASK; + } + } + break; + case R_DMA_IRQ: + break; + case R_MII_CMD: + if (value & R_MII_CMD_READ_MASK) { + s->regs[R_MII_STS] = read_from_phy(s); + } + break; + case R_MII_CTL: + s->regs[addr] = value; + write_to_phy(s); + break; + case R_STA1: + s->regs[addr] = value; + /* + * R_STA1 [31:24] : octet 1 of mac address + * R_STA1 [23:16] : octet 2 of mac address + * R_STA1 [15:8] : octet 3 of mac address + * R_STA1 [7:0] : octet 4 of mac address + */ + stl_be_p(s->mac_addr, value); + break; + case R_STA2: + s->regs[addr] = value; + /* + * R_STA2 [31:24] : octet 5 of mac address + * R_STA2 [23:16] : octet 6 of mac address + */ + stw_be_p(s->mac_addr + 4, value >> 16); + break; + default: + if (addr >= ARRAY_SIZE(s->regs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return; + } + s->regs[addr] = value; + break; + } + emac_update_irq(s); +} + +static const MemoryRegionOps emac_ops = { + .read = emac_read, + .write = emac_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4 + } +}; + +static bool emac_can_rx(NetClientState *nc) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + + return (s->regs[R_CFG1] & R_CFG1_RX_EN_MASK) && + (s->regs[R_DMA_RX_CTL] & R_DMA_RX_CTL_EN_MASK); +} + +static bool addr_filter_ok(MSF2EmacState *s, const uint8_t *buf) +{ + /* The broadcast MAC address: FF:FF:FF:FF:FF:FF */ + const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, + 0xFF, 0xFF }; + bool bcast_en = true; + bool mcast_en = true; + + if (s->regs[R_FIFO_CFG5] & R_FIFO_CFG5_BCAST_MASK) { + bcast_en = true; /* Broadcast dont care for drop circuitry */ + } else if (s->regs[R_FIFO_CFG4] & R_FIFO_CFG4_BCAST_MASK) { + bcast_en = false; + } + + if (s->regs[R_FIFO_CFG5] & R_FIFO_CFG5_MCAST_MASK) { + mcast_en = true; /* Multicast dont care for drop circuitry */ + } else if (s->regs[R_FIFO_CFG4] & R_FIFO_CFG4_MCAST_MASK) { + mcast_en = false; + } + + if (!memcmp(buf, broadcast_addr, sizeof(broadcast_addr))) { + return bcast_en; + } + + if (buf[0] & 1) { + return mcast_en; + } + + return !memcmp(buf, s->mac_addr, sizeof(s->mac_addr)); +} + +static ssize_t emac_rx(NetClientState *nc, const uint8_t *buf, size_t size) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + EmacDesc d; + uint8_t pktcnt; + uint32_t status; + + if (size > (s->regs[R_MAX_FRAME_LENGTH] & 0xFFFF)) { + return size; + } + if (!addr_filter_ok(s, buf)) { + return size; + } + + emac_load_desc(s, &d, s->rx_desc); + + if (d.pktsize & EMPTY_MASK) { + address_space_write(&s->dma_as, d.pktaddr, MEMTXATTRS_UNSPECIFIED, + buf, size & PKT_SIZE); + d.pktsize = size & PKT_SIZE; + emac_store_desc(s, &d, s->rx_desc); + /* update received packets count */ + status = s->regs[R_DMA_RX_STATUS]; + pktcnt = FIELD_EX32(status, DMA_RX_STATUS, PKTCNT); + pktcnt++; + s->regs[R_DMA_RX_STATUS] = FIELD_DP32(status, DMA_RX_STATUS, + PKTCNT, pktcnt); + s->regs[R_DMA_RX_STATUS] |= R_DMA_RX_STATUS_PKT_RCVD_MASK; + s->rx_desc = d.next; + } else { + s->regs[R_DMA_RX_CTL] &= ~R_DMA_RX_CTL_EN_MASK; + s->regs[R_DMA_RX_STATUS] |= R_DMA_RX_STATUS_OVERFLOW_MASK; + } + emac_update_irq(s); + return size; +} + +static void msf2_emac_reset(DeviceState *dev) +{ + MSF2EmacState *s = MSS_EMAC(dev); + + msf2_emac_do_reset(s); +} + +static void emac_set_link(NetClientState *nc) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + + msf2_phy_update_link(s); +} + +static NetClientInfo net_msf2_emac_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = emac_can_rx, + .receive = emac_rx, + .link_status_changed = emac_set_link, +}; + +static void msf2_emac_realize(DeviceState *dev, Error **errp) +{ + MSF2EmacState *s = MSS_EMAC(dev); + + if (!s->dma_mr) { + error_setg(errp, "MSS_EMAC 'ahb-bus' link not set"); + return; + } + + address_space_init(&s->dma_as, s->dma_mr, "emac-ahb"); + + qemu_macaddr_default_if_unset(&s->conf.macaddr); + s->nic = qemu_new_nic(&net_msf2_emac_info, &s->conf, + object_get_typename(OBJECT(dev)), dev->id, s); + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static void msf2_emac_init(Object *obj) +{ + MSF2EmacState *s = MSS_EMAC(obj); + + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); + + memory_region_init_io(&s->mmio, obj, &emac_ops, s, + "msf2-emac", R_MAX * 4); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); +} + +static Property msf2_emac_properties[] = { + DEFINE_PROP_LINK("ahb-bus", MSF2EmacState, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_NIC_PROPERTIES(MSF2EmacState, conf), + DEFINE_PROP_END_OF_LIST(), +}; + +static const VMStateDescription vmstate_msf2_emac = { + .name = TYPE_MSS_EMAC, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(mac_addr, MSF2EmacState, ETH_ALEN), + VMSTATE_UINT32(rx_desc, MSF2EmacState), + VMSTATE_UINT16_ARRAY(phy_regs, MSF2EmacState, PHY_MAX_REGS), + VMSTATE_UINT32_ARRAY(regs, MSF2EmacState, R_MAX), + VMSTATE_END_OF_LIST() + } +}; + +static void msf2_emac_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = msf2_emac_realize; + dc->reset = msf2_emac_reset; + dc->vmsd = &vmstate_msf2_emac; + device_class_set_props(dc, msf2_emac_properties); +} + +static const TypeInfo msf2_emac_info = { + .name = TYPE_MSS_EMAC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MSF2EmacState), + .instance_init = msf2_emac_init, + .class_init = msf2_emac_class_init, +}; + +static void msf2_emac_register_types(void) +{ + type_register_static(&msf2_emac_info); +} + +type_init(msf2_emac_register_types) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/arm/msf2-soc.h F: include/hw/misc/msf2-sysreg.h F: include/hw/timer/mss-timer.h F: include/hw/ssi/mss-spi.h +F: hw/net/msf2-emac.c +F: include/hw/net/msf2-emac.h Emcraft M2S-FG484 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> With SmartFusion2 Ethernet MAC model in place this patch adds the same to SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-3-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/msf2-soc.h | 2 ++ hw/arm/msf2-soc.c | 26 ++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/mss-timer.h" #include "hw/misc/msf2-sysreg.h" #include "hw/ssi/mss-spi.h" +#include "hw/net/msf2-emac.h" #define TYPE_MSF2_SOC "msf2-soc" #define MSF2_SOC(obj) OBJECT_CHECK(MSF2State, (obj), TYPE_MSF2_SOC) @@ -XXX,XX +XXX,XX @@ typedef struct MSF2State { MSF2SysregState sysreg; MSSTimerState timer; MSSSpiState spi[MSF2_NUM_SPIS]; + MSF2EmacState emac; } MSF2State; #endif diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ /* * SmartFusion2 SoC emulation. * - * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * Copyright (c) 2017-2020 Subbaraya Sundeep <sundeep.lkml@gmail.com> * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -XXX,XX +XXX,XX @@ #define MSF2_TIMER_BASE 0x40004000 #define MSF2_SYSREG_BASE 0x40038000 +#define MSF2_EMAC_BASE 0x40041000 #define ENVM_BASE_ADDRESS 0x60000000 #define SRAM_BASE_ADDRESS 0x20000000 +#define MSF2_EMAC_IRQ 12 + #define MSF2_ENVM_MAX_SIZE (512 * KiB) /* @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_initfn(Object *obj) sysbus_init_child_obj(obj, "spi[*]", &s->spi[i], sizeof(s->spi[i]), TYPE_MSS_SPI); } + + sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), + TYPE_MSS_EMAC); + if (nd_table[0].used) { + qemu_check_nic_model(&nd_table[0], TYPE_MSS_EMAC); + qdev_set_nic_properties(DEVICE(&s->emac), &nd_table[0]); + } } static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) g_free(bus_name); } + dev = DEVICE(&s->emac); + object_property_set_link(OBJECT(&s->emac), OBJECT(get_system_memory()), + "ahb-bus", &error_abort); + object_property_set_bool(OBJECT(&s->emac), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, MSF2_EMAC_BASE); + sysbus_connect_irq(busdev, 0, + qdev_get_gpio_in(armv7m, MSF2_EMAC_IRQ)); + /* Below devices are not modelled yet. */ create_unimplemented_device("i2c_0", 0x40002000, 0x1000); create_unimplemented_device("dma", 0x40003000, 0x1000); @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("can", 0x40015000, 0x1000); create_unimplemented_device("rtc", 0x40017000, 0x1000); create_unimplemented_device("apb_config", 0x40020000, 0x10000); - create_unimplemented_device("emac", 0x40041000, 0x1000); create_unimplemented_device("usb", 0x40043000, 0x1000); } -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> In addition to simple serial test this patch uses ping to test the ethernet block modelled in SmartFusion2 SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-4-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): """ uboot_url = ('https://raw.githubusercontent.com/' 'Subbaraya-Sundeep/qemu-test-binaries/' - 'fa030bd77a014a0b8e360d3b7011df89283a2f0b/u-boot') - uboot_hash = 'abba5d9c24cdd2d49cdc2a8aa92976cf20737eff' + 'fe371d32e50ca682391e1e70ab98c2942aeffb01/u-boot') + uboot_hash = 'cbb8cbab970f594bf6523b9855be209c08374ae2' uboot_path = self.fetch_asset(uboot_url, asset_hash=uboot_hash) spi_url = ('https://raw.githubusercontent.com/' 'Subbaraya-Sundeep/qemu-test-binaries/' - 'fa030bd77a014a0b8e360d3b7011df89283a2f0b/spi.bin') - spi_hash = '85f698329d38de63aea6e884a86fbde70890a78a' + 'fe371d32e50ca682391e1e70ab98c2942aeffb01/spi.bin') + spi_hash = '65523a1835949b6f4553be96dec1b6a38fb05501' spi_path = self.fetch_asset(spi_url, asset_hash=spi_hash) self.vm.set_console() @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): '-drive', 'file=' + spi_path + ',if=mtd,format=raw', '-no-reboot') self.vm.launch() - self.wait_for_console_pattern('init started: BusyBox') + self.wait_for_console_pattern('Enter \'help\' for a list') + + exec_command_and_wait_for_pattern(self, 'ifconfig eth0 10.0.2.15', + 'eth0: link becomes ready') + exec_command_and_wait_for_pattern(self, 'ping -c 3 10.0.2.2', + '3 packets transmitted, 3 packets received, 0% packet loss') def do_test_arm_raspi2(self, uart_id): """ -- 2.20.1 This object may be used to represent a clock inside a clock tree. A clock may be connected to another clock so that it receives update, through a callback, whenever the source/parent clock is updated. Although only the root clock of a clock tree controls the values (represented as periods) of all clocks in tree, each clock holds a local state containing the current value so that it can be fetched independently. It will allows us to fullfill migration requirements by migrating each clock independently of others. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-2-damien.hedde@greensocs.com [PMM: Use uint64_t rather than unsigned long long in trace events; the dtrace backend can't handle the latter] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 1 + include/hw/clock.h | 216 ++++++++++++++++++++++++++++++++++++++++++ hw/core/clock.c | 130 +++++++++++++++++++++++++ hw/core/trace-events | 7 ++ 4 files changed, 354 insertions(+) create mode 100644 include/hw/clock.h create mode 100644 hw/core/clock.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += hotplug.o common-obj-y += vmstate-if.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o +common-obj-y += clock.o common-obj-$(CONFIG_SOFTMMU) += reset.o common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o diff --git a/include/hw/clock.h b/include/hw/clock.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ +/* + * Hardware Clocks + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_HW_CLOCK_H +#define QEMU_HW_CLOCK_H + +#include "qom/object.h" +#include "qemu/queue.h" + +#define TYPE_CLOCK "clock" +#define CLOCK(obj) OBJECT_CHECK(Clock, (obj), TYPE_CLOCK) + +typedef void ClockCallback(void *opaque); + +/* + * clock store a value representing the clock's period in 2^-32ns unit. + * It can represent: + * + periods from 2^-32ns up to 4seconds + * + frequency from ~0.25Hz 2e10Ghz + * Resolution of frequency representation decreases with frequency: + * + at 100MHz, resolution is ~2mHz + * + at 1Ghz, resolution is ~0.2Hz + * + at 10Ghz, resolution is ~20Hz + */ +#define CLOCK_SECOND (1000000000llu << 32) + +/* + * macro helpers to convert to hertz / nanosecond + */ +#define CLOCK_PERIOD_FROM_NS(ns) ((ns) * (CLOCK_SECOND / 1000000000llu)) +#define CLOCK_PERIOD_TO_NS(per) ((per) / (CLOCK_SECOND / 1000000000llu)) +#define CLOCK_PERIOD_FROM_HZ(hz) (((hz) != 0) ? CLOCK_SECOND / (hz) : 0u) +#define CLOCK_PERIOD_TO_HZ(per) (((per) != 0) ? CLOCK_SECOND / (per) : 0u) + +/** + * Clock: + * @parent_obj: parent class + * @period: unsigned integer representing the period of the clock + * @canonical_path: clock path string cache (used for trace purpose) + * @callback: called when clock changes + * @callback_opaque: argument for @callback + * @source: source (or parent in clock tree) of the clock + * @children: list of clocks connected to this one (it is their source) + * @sibling: structure used to form a clock list + */ + +typedef struct Clock Clock; + +struct Clock { + /*< private >*/ + Object parent_obj; + + /* all fields are private and should not be modified directly */ + + /* fields */ + uint64_t period; + char *canonical_path; + ClockCallback *callback; + void *callback_opaque; + + /* Clocks are organized in a clock tree */ + Clock *source; + QLIST_HEAD(, Clock) children; + QLIST_ENTRY(Clock) sibling; +}; + +/** + * clock_setup_canonical_path: + * @clk: clock + * + * compute the canonical path of the clock (used by log messages) + */ +void clock_setup_canonical_path(Clock *clk); + +/** + * clock_set_callback: + * @clk: the clock to register the callback into + * @cb: the callback function + * @opaque: the argument to the callback + * + * Register a callback called on every clock update. + */ +void clock_set_callback(Clock *clk, ClockCallback *cb, void *opaque); + +/** + * clock_clear_callback: + * @clk: the clock to delete the callback from + * + * Unregister the callback registered with clock_set_callback. + */ +void clock_clear_callback(Clock *clk); + +/** + * clock_set_source: + * @clk: the clock. + * @src: the source clock + * + * Setup @src as the clock source of @clk. The current @src period + * value is also copied to @clk and its subtree but no callback is + * called. + * Further @src update will be propagated to @clk and its subtree. + */ +void clock_set_source(Clock *clk, Clock *src); + +/** + * clock_set: + * @clk: the clock to initialize. + * @value: the clock's value, 0 means unclocked + * + * Set the local cached period value of @clk to @value. + */ +void clock_set(Clock *clk, uint64_t value); + +static inline void clock_set_hz(Clock *clk, unsigned hz) +{ + clock_set(clk, CLOCK_PERIOD_FROM_HZ(hz)); +} + +static inline void clock_set_ns(Clock *clk, unsigned ns) +{ + clock_set(clk, CLOCK_PERIOD_FROM_NS(ns)); +} + +/** + * clock_propagate: + * @clk: the clock + * + * Propagate the clock period that has been previously configured using + * @clock_set(). This will update recursively all connected clocks. + * It is an error to call this function on a clock which has a source. + * Note: this function must not be called during device inititialization + * or migration. + */ +void clock_propagate(Clock *clk); + +/** + * clock_update: + * @clk: the clock to update. + * @value: the new clock's value, 0 means unclocked + * + * Update the @clk to the new @value. All connected clocks will be informed + * of this update. This is equivalent to call @clock_set() then + * @clock_propagate(). + */ +static inline void clock_update(Clock *clk, uint64_t value) +{ + clock_set(clk, value); + clock_propagate(clk); +} + +static inline void clock_update_hz(Clock *clk, unsigned hz) +{ + clock_update(clk, CLOCK_PERIOD_FROM_HZ(hz)); +} + +static inline void clock_update_ns(Clock *clk, unsigned ns) +{ + clock_update(clk, CLOCK_PERIOD_FROM_NS(ns)); +} + +/** + * clock_get: + * @clk: the clk to fetch the clock + * + * @return: the current period. + */ +static inline uint64_t clock_get(const Clock *clk) +{ + return clk->period; +} + +static inline unsigned clock_get_hz(Clock *clk) +{ + return CLOCK_PERIOD_TO_HZ(clock_get(clk)); +} + +static inline unsigned clock_get_ns(Clock *clk) +{ + return CLOCK_PERIOD_TO_NS(clock_get(clk)); +} + +/** + * clock_is_enabled: + * @clk: a clock + * + * @return: true if the clock is running. + */ +static inline bool clock_is_enabled(const Clock *clk) +{ + return clock_get(clk) != 0; +} + +static inline void clock_init(Clock *clk, uint64_t value) +{ + clock_set(clk, value); +} +static inline void clock_init_hz(Clock *clk, uint64_t value) +{ + clock_set_hz(clk, value); +} +static inline void clock_init_ns(Clock *clk, uint64_t value) +{ + clock_set_ns(clk, value); +} + +#endif /* QEMU_HW_CLOCK_H */ diff --git a/hw/core/clock.c b/hw/core/clock.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/clock.c @@ -XXX,XX +XXX,XX @@ +/* + * Hardware Clocks + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/clock.h" +#include "trace.h" + +#define CLOCK_PATH(_clk) (_clk->canonical_path) + +void clock_setup_canonical_path(Clock *clk) +{ + g_free(clk->canonical_path); + clk->canonical_path = object_get_canonical_path(OBJECT(clk)); +} + +void clock_set_callback(Clock *clk, ClockCallback *cb, void *opaque) +{ + clk->callback = cb; + clk->callback_opaque = opaque; +} + +void clock_clear_callback(Clock *clk) +{ + clock_set_callback(clk, NULL, NULL); +} + +void clock_set(Clock *clk, uint64_t period) +{ + trace_clock_set(CLOCK_PATH(clk), CLOCK_PERIOD_TO_NS(clk->period), + CLOCK_PERIOD_TO_NS(period)); + clk->period = period; +} + +static void clock_propagate_period(Clock *clk, bool call_callbacks) +{ + Clock *child; + + QLIST_FOREACH(child, &clk->children, sibling) { + if (child->period != clk->period) { + child->period = clk->period; + trace_clock_update(CLOCK_PATH(child), CLOCK_PATH(clk), + CLOCK_PERIOD_TO_NS(clk->period), + call_callbacks); + if (call_callbacks && child->callback) { + child->callback(child->callback_opaque); + } + clock_propagate_period(child, call_callbacks); + } + } +} + +void clock_propagate(Clock *clk) +{ + assert(clk->source == NULL); + trace_clock_propagate(CLOCK_PATH(clk)); + clock_propagate_period(clk, true); +} + +void clock_set_source(Clock *clk, Clock *src) +{ + /* changing clock source is not supported */ + assert(!clk->source); + + trace_clock_set_source(CLOCK_PATH(clk), CLOCK_PATH(src)); + + clk->period = src->period; + QLIST_INSERT_HEAD(&src->children, clk, sibling); + clk->source = src; + clock_propagate_period(clk, false); +} + +static void clock_disconnect(Clock *clk) +{ + if (clk->source == NULL) { + return; + } + + trace_clock_disconnect(CLOCK_PATH(clk)); + + clk->source = NULL; + QLIST_REMOVE(clk, sibling); +} + +static void clock_initfn(Object *obj) +{ + Clock *clk = CLOCK(obj); + + QLIST_INIT(&clk->children); +} + +static void clock_finalizefn(Object *obj) +{ + Clock *clk = CLOCK(obj); + Clock *child, *next; + + /* clear our list of children */ + QLIST_FOREACH_SAFE(child, &clk->children, sibling, next) { + clock_disconnect(child); + } + + /* remove us from source's children list */ + clock_disconnect(clk); + + g_free(clk->canonical_path); +} + +static const TypeInfo clock_info = { + .name = TYPE_CLOCK, + .parent = TYPE_OBJECT, + .instance_size = sizeof(Clock), + .instance_init = clock_initfn, + .instance_finalize = clock_finalizefn, +}; + +static void clock_register_types(void) +{ + type_register_static(&clock_info); +} + +type_init(clock_register_types) diff --git a/hw/core/trace-events b/hw/core/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/core/trace-events +++ b/hw/core/trace-events @@ -XXX,XX +XXX,XX @@ resettable_phase_exit_begin(void *obj, const char *objtype, unsigned count, int resettable_phase_exit_exec(void *obj, const char *objtype, int has_method) "obj=%p(%s) method=%d" resettable_phase_exit_end(void *obj, const char *objtype, unsigned count) "obj=%p(%s) count=%d" resettable_transitional_function(void *obj, const char *objtype) "obj=%p(%s)" + +# clock.c +clock_set_source(const char *clk, const char *src) "'%s', src='%s'" +clock_disconnect(const char *clk) "'%s'" +clock_set(const char *clk, uint64_t old, uint64_t new) "'%s', ns=%"PRIu64"->%"PRIu64 +clock_propagate(const char *clk) "'%s'" +clock_update(const char *clk, const char *src, uint64_t val, int cb) "'%s', src='%s', ns=%"PRIu64", cb=%d" -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-3-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 1 + include/hw/clock.h | 9 +++++++++ hw/core/clock-vmstate.c | 25 +++++++++++++++++++++++++ 3 files changed, 35 insertions(+) create mode 100644 hw/core/clock-vmstate.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SOFTMMU) += null-machine.o common-obj-$(CONFIG_SOFTMMU) += loader.o common-obj-$(CONFIG_SOFTMMU) += machine-hmp-cmds.o common-obj-$(CONFIG_SOFTMMU) += numa.o +common-obj-$(CONFIG_SOFTMMU) += clock-vmstate.o obj-$(CONFIG_SOFTMMU) += machine-qmp-cmds.o common-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o diff --git a/include/hw/clock.h b/include/hw/clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/clock.h +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ struct Clock { QLIST_ENTRY(Clock) sibling; }; +/* + * vmstate description entry to be added in device vmsd. + */ +extern const VMStateDescription vmstate_clock; +#define VMSTATE_CLOCK(field, state) \ + VMSTATE_CLOCK_V(field, state, 0) +#define VMSTATE_CLOCK_V(field, state, version) \ + VMSTATE_STRUCT_POINTER_V(field, state, version, vmstate_clock, Clock) + /** * clock_setup_canonical_path: * @clk: clock diff --git a/hw/core/clock-vmstate.c b/hw/core/clock-vmstate.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/clock-vmstate.c @@ -XXX,XX +XXX,XX @@ +/* + * Clock migration structure + * + * Copyright GreenSocs 2019-2020 + * + * Authors: + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "migration/vmstate.h" +#include "hw/clock.h" + +const VMStateDescription vmstate_clock = { + .name = "clock", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT64(period, Clock), + VMSTATE_END_OF_LIST() + } +}; -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add functions to easily handle clocks with devices. Clock inputs and outputs should be used to handle clock propagation between devices. The API is very similar the GPIO API. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-4-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 2 +- tests/Makefile.include | 1 + include/hw/qdev-clock.h | 104 +++++++++++++++++++++++++ include/hw/qdev-core.h | 12 +++ hw/core/qdev-clock.c | 168 ++++++++++++++++++++++++++++++++++++++++ hw/core/qdev.c | 12 +++ 6 files changed, 298 insertions(+), 1 deletion(-) create mode 100644 include/hw/qdev-clock.h create mode 100644 hw/core/qdev-clock.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += hotplug.o common-obj-y += vmstate-if.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o -common-obj-y += clock.o +common-obj-y += clock.o qdev-clock.o common-obj-$(CONFIG_SOFTMMU) += reset.o common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ tests/test-qdev-global-props$(EXESUF): tests/test-qdev-global-props.o \ hw/core/fw-path-provider.o \ hw/core/reset.o \ hw/core/vmstate-if.o \ + hw/core/clock.o hw/core/qdev-clock.o \ $(test-qapi-obj-y) tests/test-vmstate$(EXESUF): tests/test-vmstate.o \ migration/vmstate.o migration/vmstate-types.o migration/qemu-file.o \ diff --git a/include/hw/qdev-clock.h b/include/hw/qdev-clock.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/qdev-clock.h @@ -XXX,XX +XXX,XX @@ +/* + * Device's clock input and output + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QDEV_CLOCK_H +#define QDEV_CLOCK_H + +#include "hw/clock.h" + +/** + * qdev_init_clock_in: + * @dev: the device to add an input clock to + * @name: the name of the clock (can't be NULL). + * @callback: optional callback to be called on update or NULL. + * @opaque: argument for the callback + * @returns: a pointer to the newly added clock + * + * Add an input clock to device @dev as a clock named @name. + * This adds a child<> property. + * The callback will be called with @opaque as opaque parameter. + */ +Clock *qdev_init_clock_in(DeviceState *dev, const char *name, + ClockCallback *callback, void *opaque); + +/** + * qdev_init_clock_out: + * @dev: the device to add an output clock to + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the newly added clock + * + * Add an output clock to device @dev as a clock named @name. + * This adds a child<> property. + */ +Clock *qdev_init_clock_out(DeviceState *dev, const char *name); + +/** + * qdev_get_clock_in: + * @dev: the device which has the clock + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the clock + * + * Get the input clock @name from @dev or NULL if does not exist. + */ +Clock *qdev_get_clock_in(DeviceState *dev, const char *name); + +/** + * qdev_get_clock_out: + * @dev: the device which has the clock + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the clock + * + * Get the output clock @name from @dev or NULL if does not exist. + */ +Clock *qdev_get_clock_out(DeviceState *dev, const char *name); + +/** + * qdev_connect_clock_in: + * @dev: a device + * @name: the name of an input clock in @dev + * @source: the source clock (an output clock of another device for example) + * + * Set the source clock of input clock @name of device @dev to @source. + * @source period update will be propagated to @name clock. + */ +static inline void qdev_connect_clock_in(DeviceState *dev, const char *name, + Clock *source) +{ + clock_set_source(qdev_get_clock_in(dev, name), source); +} + +/** + * qdev_alias_clock: + * @dev: the device which has the clock + * @name: the name of the clock in @dev (can't be NULL) + * @alias_dev: the device to add the clock + * @alias_name: the name of the clock in @container + * @returns: a pointer to the clock + * + * Add a clock @alias_name in @alias_dev which is an alias of the clock @name + * in @dev. The direction _in_ or _out_ will the same as the original. + * An alias clock must not be modified or used by @alias_dev and should + * typically be only only for device composition purpose. + */ +Clock *qdev_alias_clock(DeviceState *dev, const char *name, + DeviceState *alias_dev, const char *alias_name); + +/** + * qdev_finalize_clocklist: + * @dev: the device being finalized + * + * Clear the clocklist from @dev. Only used internally in qdev. + */ +void qdev_finalize_clocklist(DeviceState *dev); + +#endif /* QDEV_CLOCK_H */ diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -XXX,XX +XXX,XX @@ struct NamedGPIOList { QLIST_ENTRY(NamedGPIOList) node; }; +typedef struct Clock Clock; +typedef struct NamedClockList NamedClockList; + +struct NamedClockList { + char *name; + Clock *clock; + bool output; + bool alias; + QLIST_ENTRY(NamedClockList) node; +}; + /** * DeviceState: * @realized: Indicates whether the device has been fully constructed. @@ -XXX,XX +XXX,XX @@ struct DeviceState { bool allow_unplug_during_migration; BusState *parent_bus; QLIST_HEAD(, NamedGPIOList) gpios; + QLIST_HEAD(, NamedClockList) clocks; QLIST_HEAD(, BusState) child_bus; int num_child_bus; int instance_id_alias; diff --git a/hw/core/qdev-clock.c b/hw/core/qdev-clock.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/qdev-clock.c @@ -XXX,XX +XXX,XX @@ +/* + * Device's clock input and output + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-core.h" +#include "qapi/error.h" + +/* + * qdev_init_clocklist: + * Add a new clock in a device + */ +static NamedClockList *qdev_init_clocklist(DeviceState *dev, const char *name, + bool output, Clock *clk) +{ + NamedClockList *ncl; + + /* + * Clock must be added before realize() so that we can compute the + * clock's canonical path during device_realize(). + */ + assert(!dev->realized); + + /* + * The ncl structure is freed by qdev_finalize_clocklist() which will + * be called during @dev's device_finalize(). + */ + ncl = g_new0(NamedClockList, 1); + ncl->name = g_strdup(name); + ncl->output = output; + ncl->alias = (clk != NULL); + + /* + * Trying to create a clock whose name clashes with some other + * clock or property is a bug in the caller and we will abort(). + */ + if (clk == NULL) { + clk = CLOCK(object_new(TYPE_CLOCK)); + object_property_add_child(OBJECT(dev), name, OBJECT(clk), &error_abort); + if (output) { + /* + * Remove object_new()'s initial reference. + * Note that for inputs, the reference created by object_new() + * will be deleted in qdev_finalize_clocklist(). + */ + object_unref(OBJECT(clk)); + } + } else { + object_property_add_link(OBJECT(dev), name, + object_get_typename(OBJECT(clk)), + (Object **) &ncl->clock, + NULL, OBJ_PROP_LINK_STRONG, &error_abort); + } + + ncl->clock = clk; + + QLIST_INSERT_HEAD(&dev->clocks, ncl, node); + return ncl; +} + +void qdev_finalize_clocklist(DeviceState *dev) +{ + /* called by @dev's device_finalize() */ + NamedClockList *ncl, *ncl_next; + + QLIST_FOREACH_SAFE(ncl, &dev->clocks, node, ncl_next) { + QLIST_REMOVE(ncl, node); + if (!ncl->output && !ncl->alias) { + /* + * We kept a reference on the input clock to ensure it lives up to + * this point so we can safely remove the callback. + * It avoids having a callback to a deleted object if ncl->clock + * is still referenced somewhere else (eg: by a clock output). + */ + clock_clear_callback(ncl->clock); + object_unref(OBJECT(ncl->clock)); + } + g_free(ncl->name); + g_free(ncl); + } +} + +Clock *qdev_init_clock_out(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_init_clocklist(dev, name, true, NULL); + + return ncl->clock; +} + +Clock *qdev_init_clock_in(DeviceState *dev, const char *name, + ClockCallback *callback, void *opaque) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_init_clocklist(dev, name, false, NULL); + + if (callback) { + clock_set_callback(ncl->clock, callback, opaque); + } + return ncl->clock; +} + +static NamedClockList *qdev_get_clocklist(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + QLIST_FOREACH(ncl, &dev->clocks, node) { + if (strcmp(name, ncl->name) == 0) { + return ncl; + } + } + + return NULL; +} + +Clock *qdev_get_clock_in(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_get_clocklist(dev, name); + assert(!ncl->output); + + return ncl->clock; +} + +Clock *qdev_get_clock_out(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_get_clocklist(dev, name); + assert(ncl->output); + + return ncl->clock; +} + +Clock *qdev_alias_clock(DeviceState *dev, const char *name, + DeviceState *alias_dev, const char *alias_name) +{ + NamedClockList *ncl; + + assert(name && alias_name); + + ncl = qdev_get_clocklist(dev, name); + + qdev_init_clocklist(alias_dev, alias_name, ncl->output, ncl->clock); + + return ncl->clock; +} diff --git a/hw/core/qdev.c b/hw/core/qdev.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "hw/boards.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "migration/vmstate.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void device_set_realized(Object *obj, bool value, Error **errp) DeviceClass *dc = DEVICE_GET_CLASS(dev); HotplugHandler *hotplug_ctrl; BusState *bus; + NamedClockList *ncl; Error *local_err = NULL; bool unattached_parent = false; static int unattached_count; @@ -XXX,XX +XXX,XX @@ static void device_set_realized(Object *obj, bool value, Error **errp) */ g_free(dev->canonical_path); dev->canonical_path = object_get_canonical_path(OBJECT(dev)); + QLIST_FOREACH(ncl, &dev->clocks, node) { + if (ncl->alias) { + continue; + } else { + clock_setup_canonical_path(ncl->clock); + } + } if (qdev_get_vmsd(dev)) { if (vmstate_register_with_alias_id(VMSTATE_IF(dev), @@ -XXX,XX +XXX,XX @@ static void device_initfn(Object *obj) dev->allow_unplug_during_migration = false; QLIST_INIT(&dev->gpios); + QLIST_INIT(&dev->clocks); } static void device_post_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void device_finalize(Object *obj) */ } + qdev_finalize_clocklist(dev); + /* Only send event if the device had been completely realized */ if (dev->pending_deleted_event) { g_assert(dev->canonical_path); -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Introduce a function and macro helpers to setup several clocks in a device from a static array description. An element of the array describes the clock (name and direction) as well as the related callback and an optional offset to store the created object pointer in the device state structure. The array must be terminated by a special element QDEV_CLOCK_END. This is based on the original work of Frederic Konrad. 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> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-5-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/qdev-clock.h | 55 +++++++++++++++++++++++++++++++++++++++++ hw/core/qdev-clock.c | 17 +++++++++++++ 2 files changed, 72 insertions(+) diff --git a/include/hw/qdev-clock.h b/include/hw/qdev-clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-clock.h +++ b/include/hw/qdev-clock.h @@ -XXX,XX +XXX,XX @@ Clock *qdev_alias_clock(DeviceState *dev, const char *name, */ void qdev_finalize_clocklist(DeviceState *dev); +/** + * ClockPortInitElem: + * @name: name of the clock (can't be NULL) + * @output: indicates whether the clock is input or output + * @callback: for inputs, optional callback to be called on clock's update + * with device as opaque + * @offset: optional offset to store the ClockIn or ClockOut pointer in device + * state structure (0 means unused) + */ +struct ClockPortInitElem { + const char *name; + bool is_output; + ClockCallback *callback; + size_t offset; +}; + +#define clock_offset_value(devstate, field) \ + (offsetof(devstate, field) + \ + type_check(Clock *, typeof_field(devstate, field))) + +#define QDEV_CLOCK(out_not_in, devstate, field, cb) { \ + .name = (stringify(field)), \ + .is_output = out_not_in, \ + .callback = cb, \ + .offset = clock_offset_value(devstate, field), \ +} + +/** + * QDEV_CLOCK_(IN|OUT): + * @devstate: structure type. @dev argument of qdev_init_clocks below must be + * a pointer to that same type. + * @field: a field in @_devstate (must be Clock*) + * @callback: (for input only) callback (or NULL) to be called with the device + * state as argument + * + * The name of the clock will be derived from @field + */ +#define QDEV_CLOCK_IN(devstate, field, callback) \ + QDEV_CLOCK(false, devstate, field, callback) + +#define QDEV_CLOCK_OUT(devstate, field) \ + QDEV_CLOCK(true, devstate, field, NULL) + +#define QDEV_CLOCK_END { .name = NULL } + +typedef struct ClockPortInitElem ClockPortInitArray[]; + +/** + * qdev_init_clocks: + * @dev: the device to add clocks to + * @clocks: a QDEV_CLOCK_END-terminated array which contains the + * clocks information. + */ +void qdev_init_clocks(DeviceState *dev, const ClockPortInitArray clocks); + #endif /* QDEV_CLOCK_H */ diff --git a/hw/core/qdev-clock.c b/hw/core/qdev-clock.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev-clock.c +++ b/hw/core/qdev-clock.c @@ -XXX,XX +XXX,XX @@ Clock *qdev_init_clock_in(DeviceState *dev, const char *name, return ncl->clock; } +void qdev_init_clocks(DeviceState *dev, const ClockPortInitArray clocks) +{ + const struct ClockPortInitElem *elem; + + for (elem = &clocks[0]; elem->name != NULL; elem++) { + Clock **clkp; + /* offset cannot be inside the DeviceState part */ + assert(elem->offset > sizeof(DeviceState)); + clkp = (Clock **)(((void *) dev) + elem->offset); + if (elem->is_output) { + *clkp = qdev_init_clock_out(dev, elem->name); + } else { + *clkp = qdev_init_clock_in(dev, elem->name, elem->callback, dev); + } + } +} + static NamedClockList *qdev_get_clocklist(DeviceState *dev, const char *name) { NamedClockList *ncl; -- 2.20.1 Add the documentation about the clock inputs and outputs in devices. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-6-damien.hedde@greensocs.com [PMM: Editing pass for minor grammar, style and Sphinx formatting fixes] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/devel/clocks.rst | 391 ++++++++++++++++++++++++++++++++++++++++++ docs/devel/index.rst | 1 + 2 files changed, 392 insertions(+) create mode 100644 docs/devel/clocks.rst diff --git a/docs/devel/clocks.rst b/docs/devel/clocks.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/clocks.rst @@ -XXX,XX +XXX,XX @@ +Modelling a clock tree in QEMU +============================== + +What are clocks? +---------------- + +Clocks are QOM objects developed for the purpose of modelling the +distribution of clocks in QEMU. + +They allow us to model the clock distribution of a platform and detect +configuration errors in the clock tree such as badly configured PLL, clock +source selection or disabled clock. + +The object is *Clock* and its QOM name is ``clock`` (in C code, the macro +``TYPE_CLOCK``). + +Clocks are typically used with devices where they are used to model inputs +and outputs. They are created in a similar way to GPIOs. Inputs and outputs +of different devices can be connected together. + +In these cases a Clock object is a child of a Device object, but this +is not a requirement. Clocks can be independent of devices. For +example it is possible to create a clock outside of any device to +model the main clock source of a machine. + +Here is an example of clocks:: + + +---------+ +----------------------+ +--------------+ + | Clock 1 | | Device B | | Device C | + | | | +-------+ +-------+ | | +-------+ | + | |>>-+-->>|Clock 2| |Clock 3|>>--->>|Clock 6| | + +---------+ | | | (in) | | (out) | | | | (in) | | + | | +-------+ +-------+ | | +-------+ | + | | +-------+ | +--------------+ + | | |Clock 4|>> + | | | (out) | | +--------------+ + | | +-------+ | | Device D | + | | +-------+ | | +-------+ | + | | |Clock 5|>>--->>|Clock 7| | + | | | (out) | | | | (in) | | + | | +-------+ | | +-------+ | + | +----------------------+ | | + | | +-------+ | + +----------------------------->>|Clock 8| | + | | (in) | | + | +-------+ | + +--------------+ + +Clocks are defined in the ``include/hw/clock.h`` header and device +related functions are defined in the ``include/hw/qdev-clock.h`` +header. + +The clock state +--------------- + +The state of a clock is its period; it is stored as an integer +representing it in units of 2 :sup:`-32` ns. The special value of 0 is used to +represent the clock being inactive or gated. The clocks do not model +the signal itself (pin toggling) or other properties such as the duty +cycle. + +All clocks contain this state: outputs as well as inputs. This allows +the current period of a clock to be fetched at any time. When a clock +is updated, the value is immediately propagated to all connected +clocks in the tree. + +To ease interaction with clocks, helpers with a unit suffix are defined for +every clock state setter or getter. The suffixes are: + +- ``_ns`` for handling periods in nanoseconds +- ``_hz`` for handling frequencies in hertz + +The 0 period value is converted to 0 in hertz and vice versa. 0 always means +that the clock is disabled. + +Adding a new clock +------------------ + +Adding clocks to a device must be done during the init method of the Device +instance. + +To add an input clock to a device, the function ``qdev_init_clock_in()`` +must be used. It takes the name, a callback and an opaque parameter +for the callback (this will be explained in a following section). +Output is simpler; only the name is required. Typically:: + + qdev_init_clock_in(DEVICE(dev), "clk_in", clk_in_callback, dev); + qdev_init_clock_out(DEVICE(dev), "clk_out"); + +Both functions return the created Clock pointer, which should be saved in the +device's state structure for further use. + +These objects will be automatically deleted by the QOM reference mechanism. + +Note that it is possible to create a static array describing clock inputs and +outputs. The function ``qdev_init_clocks()`` must be called with the array as +parameter to initialize the clocks: it has the same behaviour as calling the +``qdev_init_clock_in/out()`` for each clock in the array. To ease the array +construction, some macros are defined in ``include/hw/qdev-clock.h``. +As an example, the following creates 2 clocks to a device: one input and one +output. + +.. code-block:: c + + /* device structure containing pointers to the clock objects */ + typedef struct MyDeviceState { + DeviceState parent_obj; + Clock *clk_in; + Clock *clk_out; + } MyDeviceState; + + /* + * callback for the input clock (see "Callback on input clock + * change" section below for more information). + */ + static void clk_in_callback(void *opaque); + + /* + * static array describing clocks: + * + a clock input named "clk_in", whose pointer is stored in + * the clk_in field of a MyDeviceState structure with callback + * clk_in_callback. + * + a clock output named "clk_out" whose pointer is stored in + * the clk_out field of a MyDeviceState structure. + */ + static const ClockPortInitArray mydev_clocks = { + QDEV_CLOCK_IN(MyDeviceState, clk_in, clk_in_callback), + QDEV_CLOCK_OUT(MyDeviceState, clk_out), + QDEV_CLOCK_END + }; + + /* device initialization function */ + static void mydev_init(Object *obj) + { + /* cast to MyDeviceState */ + MyDeviceState *mydev = MYDEVICE(obj); + /* create and fill the pointer fields in the MyDeviceState */ + qdev_init_clocks(mydev, mydev_clocks); + [...] + } + +An alternative way to create a clock is to simply call +``object_new(TYPE_CLOCK)``. In that case the clock will neither be an +input nor an output of a device. After the whole QOM hierarchy of the +clock has been set ``clock_setup_canonical_path()`` should be called. + +At creation, the period of the clock is 0: the clock is disabled. You can +change it using ``clock_set_ns()`` or ``clock_set_hz()``. + +Note that if you are creating a clock with a fixed period which will never +change (for example the main clock source of a board), then you'll have +nothing else to do. This value will be propagated to other clocks when +connecting the clocks together and devices will fetch the right value during +the first reset. + +Retrieving clocks from a device +------------------------------- + +``qdev_get_clock_in()`` and ``dev_get_clock_out()`` are available to +get the clock inputs or outputs of a device. For example: + +.. code-block:: c + + Clock *clk = qdev_get_clock_in(DEVICE(mydev), "clk_in"); + +or: + +.. code-block:: c + + Clock *clk = qdev_get_clock_out(DEVICE(mydev), "clk_out"); + +Connecting two clocks together +------------------------------ + +To connect two clocks together, use the ``clock_set_source()`` function. +Given two clocks ``clk1``, and ``clk2``, ``clock_set_source(clk2, clk1);`` +configures ``clk2`` to follow the ``clk1`` period changes. Every time ``clk1`` +is updated, ``clk2`` will be updated too. + +When connecting clock between devices, prefer using the +``qdev_connect_clock_in()`` function to set the source of an input +device clock. For example, to connect the input clock ``clk2`` of +``devB`` to the output clock ``clk1`` of ``devA``, do: + +.. code-block:: c + + qdev_connect_clock_in(devB, "clk2", qdev_get_clock_out(devA, "clk1")) + +We used ``qdev_get_clock_out()`` above, but any clock can drive an +input clock, even another input clock. The following diagram shows +some examples of connections. Note also that a clock can drive several +other clocks. + +:: + + +------------+ +--------------------------------------------------+ + | Device A | | Device B | + | | | +---------------------+ | + | | | | Device C | | + | +-------+ | | +-------+ | +-------+ +-------+ | +-------+ | + | |Clock 1|>>-->>|Clock 2|>>+-->>|Clock 3| |Clock 5|>>>>|Clock 6|>> + | | (out) | | | | (in) | | | | (in) | | (out) | | | (out) | | + | +-------+ | | +-------+ | | +-------+ +-------+ | +-------+ | + +------------+ | | +---------------------+ | + | | | + | | +--------------+ | + | | | Device D | | + | | | +-------+ | | + | +-->>|Clock 4| | | + | | | (in) | | | + | | +-------+ | | + | +--------------+ | + +--------------------------------------------------+ + +In the above example, when *Clock 1* is updated by *Device A*, three +clocks get the new clock period value: *Clock 2*, *Clock 3* and *Clock 4*. + +It is not possible to disconnect a clock or to change the clock connection +after it is connected. + +Unconnected input clocks +------------------------ + +A newly created input clock is disabled (period of 0). This means the +clock will be considered as disabled until the period is updated. If +the clock remains unconnected it will always keep its initial value +of 0. If this is not the desired behaviour, ``clock_set()``, +``clock_set_ns()`` or ``clock_set_hz()`` should be called on the Clock +object during device instance init. For example: + +.. code-block:: c + + clk = qdev_init_clock_in(DEVICE(dev), "clk-in", clk_in_callback, + dev); + /* set initial value to 10ns / 100MHz */ + clock_set_ns(clk, 10); + +Fetching clock frequency/period +------------------------------- + +To get the current state of a clock, use the functions ``clock_get()``, +``clock_get_ns()`` or ``clock_get_hz()``. + +It is also possible to register a callback on clock frequency changes. +Here is an example: + +.. code-block:: c + + void clock_callback(void *opaque) { + MyDeviceState *s = (MyDeviceState *) opaque; + /* + * 'opaque' is the argument passed to qdev_init_clock_in(); + * usually this will be the device state pointer. + */ + + /* do something with the new period */ + fprintf(stdout, "device new period is %" PRIu64 "ns\n", + clock_get_ns(dev->my_clk_input)); + } + +Changing a clock period +----------------------- + +A device can change its outputs using the ``clock_update()``, +``clock_update_ns()`` or ``clock_update_hz()`` function. It will trigger +updates on every connected input. + +For example, let's say that we have an output clock *clkout* and we +have a pointer to it in the device state because we did the following +in init phase: + +.. code-block:: c + + dev->clkout = qdev_init_clock_out(DEVICE(dev), "clkout"); + +Then at any time (apart from the cases listed below), it is possible to +change the clock value by doing: + +.. code-block:: c + + clock_update_hz(dev->clkout, 1000 * 1000 * 1000); /* 1GHz */ + +Because updating a clock may trigger any side effects through +connected clocks and their callbacks, this operation must be done +while holding the qemu io lock. + +For the same reason, one can update clocks only when it is allowed to have +side effects on other objects. In consequence, it is forbidden: + +* during migration, +* and in the enter phase of reset. + +Note that calling ``clock_update[_ns|_hz]()`` is equivalent to calling +``clock_set[_ns|_hz]()`` (with the same arguments) then +``clock_propagate()`` on the clock. Thus, setting the clock value can +be separated from triggering the side-effects. This is often required +to factorize code to handle reset and migration in devices. + +Aliasing clocks +--------------- + +Sometimes, one needs to forward, or inherit, a clock from another +device. Typically, when doing device composition, a device might +expose a sub-device's clock without interfering with it. The function +``qdev_alias_clock()`` can be used to achieve this behaviour. Note +that it is possible to expose the clock under a different name. +``qdev_alias_clock()`` works for both input and output clocks. + +For example, if device B is a child of device A, +``device_a_instance_init()`` may do something like this: + +.. code-block:: c + + void device_a_instance_init(Object *obj) + { + AState *A = DEVICE_A(obj); + BState *B; + /* create object B as child of A */ + [...] + qdev_alias_clock(B, "clk", A, "b_clk"); + /* + * Now A has a clock "b_clk" which is an alias to + * the clock "clk" of its child B. + */ + } + +This function does not return any clock object. The new clock has the +same direction (input or output) as the original one. This function +only adds a link to the existing clock. In the above example, object B +remains the only object allowed to use the clock and device A must not +try to change the clock period or set a callback to the clock. This +diagram describes the example with an input clock:: + + +--------------------------+ + | Device A | + | +--------------+ | + | | Device B | | + | | +-------+ | | + >>"b_clk">>>| "clk" | | | + | (in) | | (in) | | | + | | +-------+ | | + | +--------------+ | + +--------------------------+ + +Migration +--------- + +Clock state is not migrated automatically. Every device must handle its +clock migration. Alias clocks must not be migrated. + +To ensure clock states are restored correctly during migration, there +are two solutions. + +Clock states can be migrated by adding an entry into the device +vmstate description. You should use the ``VMSTATE_CLOCK`` macro for this. +This is typically used to migrate an input clock state. For example: + +.. code-block:: c + + MyDeviceState { + DeviceState parent_obj; + [...] /* some fields */ + Clock *clk; + }; + + VMStateDescription my_device_vmstate = { + .name = "my_device", + .fields = (VMStateField[]) { + [...], /* other migrated fields */ + VMSTATE_CLOCK(clk, MyDeviceState), + VMSTATE_END_OF_LIST() + } + }; + +The second solution is to restore the clock state using information already +at our disposal. This can be used to restore output clock states using the +device state. The functions ``clock_set[_ns|_hz]()`` can be used during the +``post_load()`` migration callback. + +When adding clock support to an existing device, if you care about +migration compatibility you will need to be careful, as simply adding +a ``VMSTATE_CLOCK()`` line will break compatibility. Instead, you can +put the ``VMSTATE_CLOCK()`` line into a vmstate subsection with a +suitable ``needed`` function, and use ``clock_set()`` in a +``pre_load()`` function to set the default value that will be used if +the source virtual machine in the migration does not send the clock +state. + +Care should be taken not to use ``clock_update[_ns|_hz]()`` or +``clock_propagate()`` during the whole migration procedure because it +will trigger side effects to other devices in an unknown state. diff --git a/docs/devel/index.rst b/docs/devel/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -XXX,XX +XXX,XX @@ Contents: bitops reset s390-dasd-ipl + clocks -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add some clocks to zynq_slcr + the main input clock (ps_clk) + the reference clock outputs for each uart (uart0 & 1) This commit also transitional the slcr to multi-phase reset as it is required to initialize the clocks correctly. The clock frequencies are computed using the internal pll & uart configuration registers and the input ps_clk frequency. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Acked-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-7-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 172 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 168 insertions(+), 4 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 "qemu/log.h" #include "qemu/module.h" #include "hw/registerfields.h" +#include "hw/qdev-clock.h" #ifndef ZYNQ_SLCR_ERR_DEBUG #define ZYNQ_SLCR_ERR_DEBUG 0 @@ -XXX,XX +XXX,XX @@ REG32(LOCKSTA, 0x00c) REG32(ARM_PLL_CTRL, 0x100) REG32(DDR_PLL_CTRL, 0x104) REG32(IO_PLL_CTRL, 0x108) +/* fields for [ARM|DDR|IO]_PLL_CTRL registers */ + FIELD(xxx_PLL_CTRL, PLL_RESET, 0, 1) + FIELD(xxx_PLL_CTRL, PLL_PWRDWN, 1, 1) + FIELD(xxx_PLL_CTRL, PLL_BYPASS_QUAL, 3, 1) + FIELD(xxx_PLL_CTRL, PLL_BYPASS_FORCE, 4, 1) + FIELD(xxx_PLL_CTRL, PLL_FPDIV, 12, 7) REG32(PLL_STATUS, 0x10c) REG32(ARM_PLL_CFG, 0x110) REG32(DDR_PLL_CFG, 0x114) @@ -XXX,XX +XXX,XX @@ REG32(SMC_CLK_CTRL, 0x148) REG32(LQSPI_CLK_CTRL, 0x14c) REG32(SDIO_CLK_CTRL, 0x150) REG32(UART_CLK_CTRL, 0x154) + FIELD(UART_CLK_CTRL, CLKACT0, 0, 1) + FIELD(UART_CLK_CTRL, CLKACT1, 1, 1) + FIELD(UART_CLK_CTRL, SRCSEL, 4, 2) + FIELD(UART_CLK_CTRL, DIVISOR, 8, 6) REG32(SPI_CLK_CTRL, 0x158) REG32(CAN_CLK_CTRL, 0x15c) REG32(CAN_MIOCLK_CTRL, 0x160) @@ -XXX,XX +XXX,XX @@ typedef struct ZynqSLCRState { MemoryRegion iomem; uint32_t regs[ZYNQ_SLCR_NUM_REGS]; + + Clock *ps_clk; + Clock *uart0_ref_clk; + Clock *uart1_ref_clk; } ZynqSLCRState; -static void zynq_slcr_reset(DeviceState *d) +/* + * return the output frequency of ARM/DDR/IO pll + * using input frequency and PLL_CTRL register + */ +static uint64_t zynq_slcr_compute_pll(uint64_t input, uint32_t ctrl_reg) { - ZynqSLCRState *s = ZYNQ_SLCR(d); + uint32_t mult = ((ctrl_reg & R_xxx_PLL_CTRL_PLL_FPDIV_MASK) >> + R_xxx_PLL_CTRL_PLL_FPDIV_SHIFT); + + /* first, check if pll is bypassed */ + if (ctrl_reg & R_xxx_PLL_CTRL_PLL_BYPASS_FORCE_MASK) { + return input; + } + + /* is pll disabled ? */ + if (ctrl_reg & (R_xxx_PLL_CTRL_PLL_RESET_MASK | + R_xxx_PLL_CTRL_PLL_PWRDWN_MASK)) { + return 0; + } + + /* frequency multiplier -> period division */ + return input / mult; +} + +/* + * return the output period of a clock given: + * + the periods in an array corresponding to input mux selector + * + the register xxx_CLK_CTRL value + * + enable bit index in ctrl register + * + * This function makes the assumption that the ctrl_reg value is organized as + * follows: + * + bits[13:8] clock frequency divisor + * + bits[5:4] clock mux selector (index in array) + * + bits[index] clock enable + */ +static uint64_t zynq_slcr_compute_clock(const uint64_t periods[], + uint32_t ctrl_reg, + unsigned index) +{ + uint32_t srcsel = extract32(ctrl_reg, 4, 2); /* bits [5:4] */ + uint32_t divisor = extract32(ctrl_reg, 8, 6); /* bits [13:8] */ + + /* first, check if clock is disabled */ + if (((ctrl_reg >> index) & 1u) == 0) { + return 0; + } + + /* + * according to the Zynq technical ref. manual UG585 v1.12.2 in + * Clocks chapter, section 25.10.1 page 705: + * "The 6-bit divider provides a divide range of 1 to 63" + * We follow here what is implemented in linux kernel and consider + * the 0 value as a bypass (no division). + */ + /* frequency divisor -> period multiplication */ + return periods[srcsel] * (divisor ? divisor : 1u); +} + +/* + * macro helper around zynq_slcr_compute_clock to avoid repeating + * the register name. + */ +#define ZYNQ_COMPUTE_CLK(state, plls, reg, enable_field) \ + zynq_slcr_compute_clock((plls), (state)->regs[reg], \ + reg ## _ ## enable_field ## _SHIFT) + +/** + * Compute and set the ouputs clocks periods. + * But do not propagate them further. Connected clocks + * will not receive any updates (See zynq_slcr_compute_clocks()) + */ +static void zynq_slcr_compute_clocks(ZynqSLCRState *s) +{ + uint64_t ps_clk = clock_get(s->ps_clk); + + /* consider outputs clocks are disabled while in reset */ + if (device_is_in_reset(DEVICE(s))) { + ps_clk = 0; + } + + uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); + uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); + uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); + + uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; + + /* compute uartX reference clocks */ + clock_set(s->uart0_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); + clock_set(s->uart1_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); +} + +/** + * Propagate the outputs clocks. + * zynq_slcr_compute_clocks() should have been called before + * to configure them. + */ +static void zynq_slcr_propagate_clocks(ZynqSLCRState *s) +{ + clock_propagate(s->uart0_ref_clk); + clock_propagate(s->uart1_ref_clk); +} + +static void zynq_slcr_ps_clk_callback(void *opaque) +{ + ZynqSLCRState *s = (ZynqSLCRState *) opaque; + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} + +static void zynq_slcr_reset_init(Object *obj, ResetType type) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); int i; DB_PRINT("RESET\n"); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset(DeviceState *d) s->regs[R_DDRIOB + 12] = 0x00000021; } +static void zynq_slcr_reset_hold(Object *obj) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); + + /* will disable all output clocks */ + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} + +static void zynq_slcr_reset_exit(Object *obj) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); + + /* will compute output clocks according to ps_clk and registers */ + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} static bool zynq_slcr_check_offset(hwaddr offset, bool rnw) { @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_write(void *opaque, hwaddr offset, qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); } break; + case R_IO_PLL_CTRL: + case R_ARM_PLL_CTRL: + case R_DDR_PLL_CTRL: + case R_UART_CLK_CTRL: + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); + break; } } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps slcr_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; +static const ClockPortInitArray zynq_slcr_clocks = { + QDEV_CLOCK_IN(ZynqSLCRState, ps_clk, zynq_slcr_ps_clk_callback), + QDEV_CLOCK_OUT(ZynqSLCRState, uart0_ref_clk), + QDEV_CLOCK_OUT(ZynqSLCRState, uart1_ref_clk), + QDEV_CLOCK_END +}; + static void zynq_slcr_init(Object *obj) { ZynqSLCRState *s = ZYNQ_SLCR(obj); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_init(Object *obj) memory_region_init_io(&s->iomem, obj, &slcr_ops, s, "slcr", ZYNQ_SLCR_MMIO_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->iomem); + + qdev_init_clocks(DEVICE(obj), zynq_slcr_clocks); } static const VMStateDescription vmstate_zynq_slcr = { .name = "zynq_slcr", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(regs, ZynqSLCRState, ZYNQ_SLCR_NUM_REGS), + VMSTATE_CLOCK_V(ps_clk, ZynqSLCRState, 3), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_zynq_slcr = { static void zynq_slcr_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->vmsd = &vmstate_zynq_slcr; - dc->reset = zynq_slcr_reset; + rc->phases.enter = zynq_slcr_reset_init; + rc->phases.hold = zynq_slcr_reset_hold; + rc->phases.exit = zynq_slcr_reset_exit; } static const TypeInfo zynq_slcr_info = { -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Switch the cadence uart to multi-phase reset and add the reference clock input. The input clock frequency is added to the migration structure. The reference clock controls the baudrate generation. If it disabled, any input characters and events are ignored. If this clock remains unconnected, the uart behaves as before (it default to a 50MHz ref clock). Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-8-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/char/cadence_uart.h | 1 + hw/char/cadence_uart.c | 73 +++++++++++++++++++++++++++++----- hw/char/trace-events | 3 ++ 3 files changed, 67 insertions(+), 10 deletions(-) diff --git a/include/hw/char/cadence_uart.h b/include/hw/char/cadence_uart.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/cadence_uart.h +++ b/include/hw/char/cadence_uart.h @@ -XXX,XX +XXX,XX @@ typedef struct { CharBackend chr; qemu_irq irq; QEMUTimer *fifo_trigger_handle; + Clock *refclk; } CadenceUARTState; static inline DeviceState *cadence_uart_create(hwaddr addr, diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "hw/char/cadence_uart.h" #include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "trace.h" #ifdef CADENCE_UART_ERR_DEBUG #define DB_PRINT(...) do { \ @@ -XXX,XX +XXX,XX @@ #define LOCAL_LOOPBACK (0x2 << UART_MR_CHMODE_SH) #define REMOTE_LOOPBACK (0x3 << UART_MR_CHMODE_SH) -#define UART_INPUT_CLK 50000000 +#define UART_DEFAULT_REF_CLK (50 * 1000 * 1000) #define R_CR (0x00/4) #define R_MR (0x04/4) @@ -XXX,XX +XXX,XX @@ static void uart_send_breaks(CadenceUARTState *s) static void uart_parameters_setup(CadenceUARTState *s) { QEMUSerialSetParams ssp; - unsigned int baud_rate, packet_size; + unsigned int baud_rate, packet_size, input_clk; + input_clk = clock_get_hz(s->refclk); - baud_rate = (s->r[R_MR] & UART_MR_CLKS) ? - UART_INPUT_CLK / 8 : UART_INPUT_CLK; + baud_rate = (s->r[R_MR] & UART_MR_CLKS) ? input_clk / 8 : input_clk; + baud_rate /= (s->r[R_BRGR] * (s->r[R_BDIV] + 1)); + trace_cadence_uart_baudrate(baud_rate); + + ssp.speed = baud_rate; - ssp.speed = baud_rate / (s->r[R_BRGR] * (s->r[R_BDIV] + 1)); packet_size = 1; switch (s->r[R_MR] & UART_MR_PAR) { @@ -XXX,XX +XXX,XX @@ static void uart_parameters_setup(CadenceUARTState *s) } packet_size += ssp.data_bits + ssp.stop_bits; + if (ssp.speed == 0) { + /* + * Avoid division-by-zero below. + * TODO: find something better + */ + ssp.speed = 1; + } s->char_tx_time = (NANOSECONDS_PER_SECOND / ssp.speed) * packet_size; qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_PARAMS, &ssp); } @@ -XXX,XX +XXX,XX @@ static void uart_receive(void *opaque, const uint8_t *buf, int size) CadenceUARTState *s = opaque; uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { uart_write_rx_fifo(opaque, buf, size); } @@ -XXX,XX +XXX,XX @@ static void uart_event(void *opaque, QEMUChrEvent event) CadenceUARTState *s = opaque; uint8_t buf = '\0'; + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if (event == CHR_EVENT_BREAK) { uart_write_rx_fifo(opaque, &buf, 1); } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps uart_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static void cadence_uart_reset(DeviceState *dev) +static void cadence_uart_reset_init(Object *obj, ResetType type) { - CadenceUARTState *s = CADENCE_UART(dev); + CadenceUARTState *s = CADENCE_UART(obj); s->r[R_CR] = 0x00000128; s->r[R_IMR] = 0; @@ -XXX,XX +XXX,XX @@ static void cadence_uart_reset(DeviceState *dev) s->r[R_BRGR] = 0x0000028B; s->r[R_BDIV] = 0x0000000F; s->r[R_TTRIG] = 0x00000020; +} + +static void cadence_uart_reset_hold(Object *obj) +{ + CadenceUARTState *s = CADENCE_UART(obj); uart_rx_reset(s); uart_tx_reset(s); @@ -XXX,XX +XXX,XX @@ static void cadence_uart_realize(DeviceState *dev, Error **errp) uart_event, NULL, s, NULL, true); } +static void cadence_uart_refclk_update(void *opaque) +{ + CadenceUARTState *s = opaque; + + /* recompute uart's speed on clock change */ + uart_parameters_setup(s); +} + static void cadence_uart_init(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void cadence_uart_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq); + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", + cadence_uart_refclk_update, s); + /* initialize the frequency in case the clock remains unconnected */ + clock_set_hz(s->refclk, UART_DEFAULT_REF_CLK); + s->char_tx_time = (NANOSECONDS_PER_SECOND / 9600) * 10; } +static int cadence_uart_pre_load(void *opaque) +{ + CadenceUARTState *s = opaque; + + /* the frequency will be overriden if the refclk field is present */ + clock_set_hz(s->refclk, UART_DEFAULT_REF_CLK); + return 0; +} + static int cadence_uart_post_load(void *opaque, int version_id) { CadenceUARTState *s = opaque; @@ -XXX,XX +XXX,XX @@ static int cadence_uart_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_cadence_uart = { .name = "cadence_uart", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, + .pre_load = cadence_uart_pre_load, .post_load = cadence_uart_post_load, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(r, CadenceUARTState, CADENCE_UART_R_MAX), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_cadence_uart = { VMSTATE_UINT32(tx_count, CadenceUARTState), VMSTATE_UINT32(rx_wpos, CadenceUARTState), VMSTATE_TIMER_PTR(fifo_trigger_handle, CadenceUARTState), + VMSTATE_CLOCK_V(refclk, CadenceUARTState, 3), VMSTATE_END_OF_LIST() - } + }, }; static Property cadence_uart_properties[] = { @@ -XXX,XX +XXX,XX @@ static Property cadence_uart_properties[] = { static void cadence_uart_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->realize = cadence_uart_realize; dc->vmsd = &vmstate_cadence_uart; - dc->reset = cadence_uart_reset; + rc->phases.enter = cadence_uart_reset_init; + rc->phases.hold = cadence_uart_reset_hold; device_class_set_props(dc, cadence_uart_properties); } diff --git a/hw/char/trace-events b/hw/char/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -XXX,XX +XXX,XX @@ exynos_uart_wo_read(uint32_t channel, const char *name, uint32_t reg) "UART%d: T exynos_uart_rxsize(uint32_t channel, uint32_t size) "UART%d: Rx FIFO size: %d" exynos_uart_channel_error(uint32_t channel) "Wrong UART channel number: %d" exynos_uart_rx_timeout(uint32_t channel, uint32_t stat, uint32_t intsp) "UART%d: Rx timeout stat=0x%x intsp=0x%x" + +# hw/char/cadence_uart.c +cadence_uart_baudrate(unsigned baudrate) "baudrate %u" -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add the connection between the slcr's output clocks and the uarts inputs. Also add the main board clock 'ps_clk', which is hard-coded to 33.33MHz (the default frequency). This clock is used to feed the slcr's input clock. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-9-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 57 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 49 insertions(+), 8 deletions(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/cadence_uart.h" #include "hw/net/cadence_gem.h" #include "hw/cpu/a9mpcore.h" +#include "hw/qdev-clock.h" +#include "sysemu/reset.h" + +#define TYPE_ZYNQ_MACHINE MACHINE_TYPE_NAME("xilinx-zynq-a9") +#define ZYNQ_MACHINE(obj) \ + OBJECT_CHECK(ZynqMachineState, (obj), TYPE_ZYNQ_MACHINE) + +/* board base frequency: 33.333333 MHz */ +#define PS_CLK_FREQUENCY (100 * 1000 * 1000 / 3) #define NUM_SPI_FLASHES 4 #define NUM_QSPI_FLASHES 2 @@ -XXX,XX +XXX,XX @@ static const int dma_irqs[8] = { 0xe3401000 + ARMV7_IMM16(extract32((val), 16, 16)), /* movt r1 ... */ \ 0xe5801000 + (addr) +typedef struct ZynqMachineState { + MachineState parent; + Clock *ps_clk; +} ZynqMachineState; + static void zynq_write_board_setup(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, static void zynq_init(MachineState *machine) { + ZynqMachineState *zynq_machine = ZYNQ_MACHINE(machine); ARMCPU *cpu; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *ocm_ram = g_new(MemoryRegion, 1); - DeviceState *dev; + DeviceState *dev, *slcr; SysBusDevice *busdev; qemu_irq pic[64]; int n; @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) 1, 0x0066, 0x0022, 0x0000, 0x0000, 0x0555, 0x2aa, 0); - dev = qdev_create(NULL, "xilinx,zynq_slcr"); - qdev_init_nofail(dev); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xF8000000); + /* Create slcr, keep a pointer to connect clocks */ + slcr = qdev_create(NULL, "xilinx,zynq_slcr"); + qdev_init_nofail(slcr); + sysbus_mmio_map(SYS_BUS_DEVICE(slcr), 0, 0xF8000000); + + /* Create the main clock source, and feed slcr with it */ + zynq_machine->ps_clk = CLOCK(object_new(TYPE_CLOCK)); + object_property_add_child(OBJECT(zynq_machine), "ps_clk", + OBJECT(zynq_machine->ps_clk), &error_abort); + object_unref(OBJECT(zynq_machine->ps_clk)); + clock_set_hz(zynq_machine->ps_clk, PS_CLK_FREQUENCY); + qdev_connect_clock_in(slcr, "ps_clk", zynq_machine->ps_clk); dev = qdev_create(NULL, TYPE_A9MPCORE_PRIV); qdev_prop_set_uint32(dev, "num-cpu", 1); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_create_simple(TYPE_CHIPIDEA, 0xE0002000, pic[53 - IRQ_OFFSET]); sysbus_create_simple(TYPE_CHIPIDEA, 0xE0003000, pic[76 - IRQ_OFFSET]); - cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); - cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); + dev = cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); + qdev_connect_clock_in(dev, "refclk", + qdev_get_clock_out(slcr, "uart0_ref_clk")); + dev = cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); + qdev_connect_clock_in(dev, "refclk", + qdev_get_clock_out(slcr, "uart1_ref_clk")); sysbus_create_varargs("cadence_ttc", 0xF8001000, pic[42-IRQ_OFFSET], pic[43-IRQ_OFFSET], pic[44-IRQ_OFFSET], NULL); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) arm_load_kernel(ARM_CPU(first_cpu), machine, &zynq_binfo); } -static void zynq_machine_init(MachineClass *mc) +static void zynq_machine_class_init(ObjectClass *oc, void *data) { + MachineClass *mc = MACHINE_CLASS(oc); mc->desc = "Xilinx Zynq Platform Baseboard for Cortex-A9"; mc->init = zynq_init; mc->max_cpus = 1; @@ -XXX,XX +XXX,XX @@ static void zynq_machine_init(MachineClass *mc) mc->default_ram_id = "zynq.ext_ram"; } -DEFINE_MACHINE("xilinx-zynq-a9", zynq_machine_init) +static const TypeInfo zynq_machine_type = { + .name = TYPE_ZYNQ_MACHINE, + .parent = TYPE_MACHINE, + .class_init = zynq_machine_class_init, + .instance_size = sizeof(ZynqMachineState), +}; + +static void zynq_machine_register_types(void) +{ + type_register_static(&zynq_machine_type); +} + +type_init(zynq_machine_register_types) -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> This prints the clocks attached to a DeviceState when using "info qtree" monitor command. For every clock, it displays the direction, the name and if the clock is forwarded. For input clock, it displays also the frequency. This is based on the original work of Frederic Konrad. Here follows a sample of `info qtree` output on xilinx_zynq machine after linux boot with only one uart clocked: > bus: main-system-bus > type System > [...] > dev: cadence_uart, id "" > gpio-out "sysbus-irq" 1 > clock-in "refclk" freq_hz=0.000000e+00 > chardev = "" > mmio 00000000e0001000/0000000000001000 > dev: cadence_uart, id "" > gpio-out "sysbus-irq" 1 > clock-in "refclk" freq_hz=1.375661e+07 > chardev = "serial0" > mmio 00000000e0000000/0000000000001000 > [...] > dev: xilinx,zynq_slcr, id "" > clock-out "uart1_ref_clk" freq_hz=0.000000e+00 > clock-out "uart0_ref_clk" freq_hz=1.375661e+07 > clock-in "ps_clk" freq_hz=3.333333e+07 > mmio 00000000f8000000/0000000000001000 Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-10-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qdev-monitor.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/qdev-monitor.c b/qdev-monitor.c index XXXXXXX..XXXXXXX 100644 --- a/qdev-monitor.c +++ b/qdev-monitor.c @@ -XXX,XX +XXX,XX @@ #include "migration/misc.h" #include "migration/migration.h" #include "qemu/cutils.h" +#include "hw/clock.h" /* * Aliases were a bad idea from the start. Let's keep them @@ -XXX,XX +XXX,XX @@ static void qdev_print(Monitor *mon, DeviceState *dev, int indent) ObjectClass *class; BusState *child; NamedGPIOList *ngl; + NamedClockList *ncl; qdev_printf("dev: %s, id \"%s\"\n", object_get_typename(OBJECT(dev)), dev->id ? dev->id : ""); @@ -XXX,XX +XXX,XX @@ static void qdev_print(Monitor *mon, DeviceState *dev, int indent) ngl->num_out); } } + QLIST_FOREACH(ncl, &dev->clocks, node) { + qdev_printf("clock-%s%s \"%s\" freq_hz=%e\n", + ncl->output ? "out" : "in", + ncl->alias ? " (alias)" : "", + ncl->name, + CLOCK_PERIOD_TO_HZ(1.0 * clock_get(ncl->clock))); + } class = object_get_class(OBJECT(dev)); do { qdev_print_props(mon, dev, DEVICE_CLASS(class)->props_, indent); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Setup the ADMA with 128bit bus-width. This matters when FIXED BURST mode is used. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200417153800.27399-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic) dev = qdev_create(NULL, "xlnx.zdma"); s->lpd.iou.adma[i] = SYS_BUS_DEVICE(dev); + object_property_set_int(OBJECT(s->lpd.iou.adma[i]), 128, "bus-width", + &error_abort); object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); qdev_init_nofail(dev); -- 2.20.1 From: Ramon Fried <rfried.dev@gmail.com> Wraparound of TX descriptor cyclic buffer only updated the low 32 bits of the descriptor. Fix that by checking if we're working with 64bit descriptors. Signed-off-by: Ramon Fried <rfried.dev@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200417171736.441607-1-rfried.dev@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { tx_desc_set_last(desc); - packet_desc_addr = s->regs[GEM_TXQBASE]; + + if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + packet_desc_addr = s->regs[GEM_TBQPH]; + packet_desc_addr <<= 32; + } else { + packet_desc_addr = 0; + } + packet_desc_addr |= s->regs[GEM_TXQBASE]; } else { packet_desc_addr += 4 * gem_get_desc_len(s, false); } -- 2.20.1 From: Ramon Fried <rfried.dev@gmail.com> The RX ring descriptors control field is used for setting SOF and EOF (start of frame and end of frame). The SOF and EOF weren't cleared from the previous descriptors, causing inconsistencies in ring buffer. Fix that by clearing the control field of every descriptors we're processing. Signed-off-by: Ramon Fried <rfried.dev@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200418085145.489726-1-rfried.dev@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static inline void rx_desc_set_sof(uint32_t *desc) desc[1] |= DESC_1_RX_SOF; } +static inline void rx_desc_clear_control(uint32_t *desc) +{ + desc[1] = 0; +} + static inline void rx_desc_set_eof(uint32_t *desc) { desc[1] |= DESC_1_RX_EOF; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) rxbuf_ptr += MIN(bytes_to_copy, rxbufsize); bytes_to_copy -= MIN(bytes_to_copy, rxbufsize); + rx_desc_clear_control(s->rx_desc[q]); + /* Update the descriptor. */ if (first_desc) { rx_desc_set_sof(s->rx_desc[q]); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These instructions are often used in glibc's string routines. They were the final uses of the 32-bit at a time neon helpers. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200418162808.4680-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 27 ++-- target/arm/translate.h | 5 + target/arm/neon_helper.c | 24 ---- target/arm/translate-a64.c | 64 +++------- target/arm/translate.c | 256 +++++++++++++++++++++++++++++++------ target/arm/vec_helper.c | 25 ++++ 6 files changed, 278 insertions(+), 123 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_hsub_u16, i32, i32, i32) DEF_HELPER_2(neon_hsub_s32, s32, s32, s32) DEF_HELPER_2(neon_hsub_u32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u8, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s8, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u16, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s16, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s32, i32, i32, i32) -DEF_HELPER_2(neon_cge_u8, i32, i32, i32) -DEF_HELPER_2(neon_cge_s8, i32, i32, i32) -DEF_HELPER_2(neon_cge_u16, i32, i32, i32) -DEF_HELPER_2(neon_cge_s16, i32, i32, i32) -DEF_HELPER_2(neon_cge_u32, i32, i32, i32) -DEF_HELPER_2(neon_cge_s32, i32, i32, i32) - DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) DEF_HELPER_2(neon_pmin_u16, i32, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_mul_u16, i32, i32, i32) DEF_HELPER_2(neon_tst_u8, i32, i32, i32) DEF_HELPER_2(neon_tst_u16, i32, i32, i32) DEF_HELPER_2(neon_tst_u32, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u8, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u16, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u32, i32, i32, i32) DEF_HELPER_1(neon_clz_u8, i32, i32) DEF_HELPER_1(neon_clz_u16, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(frint32_d, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(frint64_d, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_3(gvec_ceq0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_clt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_clt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cle0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cgt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/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 @@ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) uint64_t vfp_expand_imm(int size, uint8_t imm8); /* Vector operations shared between ARM and AArch64. */ +extern const GVecGen2 ceq0_op[4]; +extern const GVecGen2 clt0_op[4]; +extern const GVecGen2 cgt0_op[4]; +extern const GVecGen2 cle0_op[4]; +extern const GVecGen2 cge0_op[4]; extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_hsub_u32)(uint32_t src1, uint32_t src2) return dest; } -#define NEON_FN(dest, src1, src2) dest = (src1 > src2) ? ~0 : 0 -NEON_VOP(cgt_s8, neon_s8, 4) -NEON_VOP(cgt_u8, neon_u8, 4) -NEON_VOP(cgt_s16, neon_s16, 2) -NEON_VOP(cgt_u16, neon_u16, 2) -NEON_VOP(cgt_s32, neon_s32, 1) -NEON_VOP(cgt_u32, neon_u32, 1) -#undef NEON_FN - -#define NEON_FN(dest, src1, src2) dest = (src1 >= src2) ? ~0 : 0 -NEON_VOP(cge_s8, neon_s8, 4) -NEON_VOP(cge_u8, neon_u8, 4) -NEON_VOP(cge_s16, neon_s16, 2) -NEON_VOP(cge_u16, neon_u16, 2) -NEON_VOP(cge_s32, neon_s32, 1) -NEON_VOP(cge_u32, neon_u32, 1) -#undef NEON_FN - #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) @@ -XXX,XX +XXX,XX @@ NEON_VOP(tst_u16, neon_u16, 2) NEON_VOP(tst_u32, neon_u32, 1) #undef NEON_FN -#define NEON_FN(dest, src1, src2) dest = (src1 == src2) ? -1 : 0 -NEON_VOP(ceq_u8, neon_u8, 4) -NEON_VOP(ceq_u16, neon_u16, 2) -NEON_VOP(ceq_u32, neon_u32, 1) -#undef NEON_FN - /* Count Leading Sign/Zero Bits. */ static inline int do_clz8(uint8_t x) { diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm, is_q ? 16 : 8, vec_full_reg_size(s)); } +/* Expand a 2-operand AdvSIMD vector operation using an op descriptor. */ +static void gen_gvec_op2(DisasContext *s, bool is_q, int rd, + int rn, const GVecGen2 *gvec_op) +{ + tcg_gen_gvec_2(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), + is_q ? 16 : 8, vec_full_reg_size(s), gvec_op); +} + /* Expand a 2-operand + immediate AdvSIMD vector operation using * an op descriptor. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; + case 0x8: /* CMGT, CMGE */ + gen_gvec_op2(s, is_q, rd, rn, u ? &cge0_op[size] : &cgt0_op[size]); + return; + case 0x9: /* CMEQ, CMLE */ + gen_gvec_op2(s, is_q, rd, rn, u ? &cle0_op[size] : &ceq0_op[size]); + return; + case 0xa: /* CMLT */ + gen_gvec_op2(s, is_q, rd, rn, &clt0_op[size]); + return; case 0xb: if (u) { /* ABS, NEG */ gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_neg, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) for (pass = 0; pass < (is_q ? 4 : 2); pass++) { TCGv_i32 tcg_op = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); - TCGCond cond; read_vec_element_i32(s, tcg_op, rn, pass, MO_32); if (size == 2) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0xa: /* CMLT */ - /* 32 bit integer comparison against zero, result is - * test ? (2^32 - 1) : 0. We implement via setcond(test) - * and inverting. - */ - cond = TCG_COND_LT; - do_cmop: - tcg_gen_setcondi_i32(cond, tcg_res, tcg_op, 0); - tcg_gen_neg_i32(tcg_res, tcg_res); - break; - case 0x8: /* CMGT, CMGE */ - cond = u ? TCG_COND_GE : TCG_COND_GT; - goto do_cmop; - case 0x9: /* CMEQ, CMLE */ - cond = u ? TCG_COND_LE : TCG_COND_EQ; - goto do_cmop; case 0x4: /* CLS */ if (u) { tcg_gen_clzi_i32(tcg_res, tcg_op, 32); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) genfn(tcg_res, cpu_env, tcg_op); break; } - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - case 0xa: /* CMLT */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_cgt_s8, gen_helper_neon_cgt_s16 }, - { gen_helper_neon_cge_s8, gen_helper_neon_cge_s16 }, - { gen_helper_neon_ceq_u8, gen_helper_neon_ceq_u16 }, - }; - NeonGenTwoOpFn *genfn; - int comp; - bool reverse; - TCGv_i32 tcg_zero = tcg_const_i32(0); - - /* comp = index into [CMGT, CMGE, CMEQ, CMLE, CMLT] */ - comp = (opcode - 0x8) * 2 + u; - /* ...but LE, LT are implemented as reverse GE, GT */ - reverse = (comp > 2); - if (reverse) { - comp = 4 - comp; - } - genfn = fns[comp][size]; - if (reverse) { - genfn(tcg_res, tcg_zero, tcg_op); - } else { - genfn(tcg_res, tcg_op, tcg_zero); - } - tcg_temp_free_i32(tcg_zero); - break; - } case 0x4: /* CLS, CLZ */ if (u) { if (size == 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 int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, return 1; } +static void gen_ceq0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_EQ, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_ceq0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_EQ, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_ceq0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_EQ, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +static const TCGOpcode vecop_list_cmp[] = { + INDEX_op_cmp_vec, 0 +}; + +const GVecGen2 ceq0_op[4] = { + { .fno = gen_helper_gvec_ceq0_b, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_ceq0_h, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_ceq0_i32, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_ceq0_i64, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cle0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_LE, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cle0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_LE, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cle0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_LE, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cle0_op[4] = { + { .fno = gen_helper_gvec_cle0_b, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cle0_h, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cle0_i32, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cle0_i64, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cge0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_GE, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cge0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_GE, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cge0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_GE, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cge0_op[4] = { + { .fno = gen_helper_gvec_cge0_b, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cge0_h, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cge0_i32, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cge0_i64, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_clt0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_LT, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_clt0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_LT, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_clt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_LT, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 clt0_op[4] = { + { .fno = gen_helper_gvec_clt0_b, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_clt0_h, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_clt0_i32, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_clt0_i64, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cgt0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_GT, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cgt0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_GT, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cgt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_GT, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cgt0_op[4] = { + { .fno = gen_helper_gvec_cgt0_b, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cgt0_h, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cgt0_i32, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cgt0_i64, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { tcg_gen_vec_sar8i_i64(a, a, shift); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_abs(size, rd_ofs, rm_ofs, vec_size, vec_size); break; + case NEON_2RM_VCEQ0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &ceq0_op[size]); + break; + case NEON_2RM_VCGT0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cgt0_op[size]); + break; + case NEON_2RM_VCLE0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cle0_op[size]); + break; + case NEON_2RM_VCGE0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cge0_op[size]); + break; + case NEON_2RM_VCLT0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &clt0_op[size]); + break; + default: elementwise: for (pass = 0; pass < (q ? 4 : 2); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: abort(); } break; - case NEON_2RM_VCGT0: case NEON_2RM_VCLE0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_cgt_s8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_cgt_s16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_cgt_s32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - if (op == NEON_2RM_VCLE0) { - tcg_gen_not_i32(tmp, tmp); - } - break; - case NEON_2RM_VCGE0: case NEON_2RM_VCLT0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_cge_s8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_cge_s16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_cge_s32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - if (op == NEON_2RM_VCLT0) { - tcg_gen_not_i32(tmp, tmp); - } - break; - case NEON_2RM_VCEQ0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_ceq_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_ceq_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_ceq_u32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - break; case NEON_2RM_VCGT0_F: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) } } #endif + +#define DO_CMP0(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + *(TYPE *)(vd + i) = -(nn OP 0); \ + } \ + clear_tail(vd, opr_sz, simd_maxsz(desc)); \ +} + +DO_CMP0(gvec_ceq0_b, int8_t, ==) +DO_CMP0(gvec_clt0_b, int8_t, <) +DO_CMP0(gvec_cle0_b, int8_t, <=) +DO_CMP0(gvec_cgt0_b, int8_t, >) +DO_CMP0(gvec_cge0_b, int8_t, >=) + +DO_CMP0(gvec_ceq0_h, int16_t, ==) +DO_CMP0(gvec_clt0_h, int16_t, <) +DO_CMP0(gvec_cle0_h, int16_t, <=) +DO_CMP0(gvec_cgt0_h, int16_t, >) +DO_CMP0(gvec_cge0_h, int16_t, >=) + +#undef DO_CMP0 -- 2.20.1 From: Jerome Forissier <jerome@forissier.org> The /secure-chosen node is currently used only by create_uart(), but this will change. Therefore move the creation of this node to create_fdt(). Signed-off-by: Jerome Forissier <jerome@forissier.org> Message-id: 20200420121807.8204-2-jerome@forissier.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); + if (vms->secure) { + qemu_fdt_add_subnode(fdt, "/secure-chosen"); + } + /* Clock node, for the benefit of the UART. The kernel device tree * binding documentation claims the PL011 node clock properties are * optional but in practice if you omit them the kernel refuses to @@ -XXX,XX +XXX,XX @@ static void create_uart(const VirtMachineState *vms, int uart, qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled"); qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay"); - qemu_fdt_add_subnode(vms->fdt, "/secure-chosen"); qemu_fdt_setprop_string(vms->fdt, "/secure-chosen", "stdout-path", nodename); } -- 2.20.1 From: Jerome Forissier <jerome@forissier.org> Generate random seeds to be used by the non-secure and/or secure OSes for ASLR. The seeds are 64-bit random values exported via the DT properties /chosen/kaslr-seed [1] and /secure-chosen/kaslr-seed, the latter being used by OP-TEE [2]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e5bc0c37c97e1 [2] https://github.com/OP-TEE/optee_os/commit/ef262691fe0e Signed-off-by: Jerome Forissier <jerome@forissier.org> Message-id: 20200420121807.8204-3-jerome@forissier.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) 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 @@ #include "hw/acpi/generic_event_device.h" #include "hw/virtio/virtio-iommu.h" #include "hw/char/pl011.h" +#include "qemu/guest-random.h" #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ @@ -XXX,XX +XXX,XX @@ static bool cpu_type_valid(const char *cpu) return false; } +static void create_kaslr_seed(VirtMachineState *vms, const char *node) +{ + Error *err = NULL; + uint64_t seed; + + if (qemu_guest_getrandom(&seed, sizeof(seed), &err)) { + error_free(err); + return; + } + qemu_fdt_setprop_u64(vms->fdt, node, "kaslr-seed", seed); +} + static void create_fdt(VirtMachineState *vms) { MachineState *ms = MACHINE(vms); @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); + create_kaslr_seed(vms, "/chosen"); if (vms->secure) { qemu_fdt_add_subnode(fdt, "/secure-chosen"); + create_kaslr_seed(vms, "/secure-chosen"); } /* Clock node, for the benefit of the UART. The kernel device tree -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Under KVM these registers are written by the hardware. Restrict the writefn handlers to TCG to avoid when building without TCG: LINK aarch64-softmmu/qemu-system-aarch64 target/arm/helper.o: In function `do_ats_write': target/arm/helper.c:3524: undefined reference to `raise_exception' Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-2-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 17 +++++++++++++++++ 1 file changed, 17 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 CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri, return CP_ACCESS_OK; } +#ifdef CONFIG_TCG static uint64_t do_ats_write(CPUARMState *env, uint64_t value, MMUAccessType access_type, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, } return par64; } +#endif /* CONFIG_TCG */ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; uint64_t par64; ARMMMUIdx mmu_idx; @@ -XXX,XX +XXX,XX @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) par64 = do_ats_write(env, value, access_type, mmu_idx); A32_BANKED_CURRENT_REG_SET(env, par, par64); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } static void ats1h_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; uint64_t par64; par64 = do_ats_write(env, value, access_type, ARMMMUIdx_E2); A32_BANKED_CURRENT_REG_SET(env, par, par64); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } static CPAccessResult at_s1e2_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static CPAccessResult at_s1e2_access(CPUARMState *env, const ARMCPRegInfo *ri, static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; ARMMMUIdx mmu_idx; int secure = arm_is_secure_below_el3(env); @@ -XXX,XX +XXX,XX @@ static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, } env->cp15.par_el[1] = do_ats_write(env, value, access_type, mmu_idx); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } #endif -- 2.20.1 From: Thomas Huth <thuth@redhat.com> Make cpu_register() (renamed to arm_cpu_register()) available from internals.h so we can register CPUs also from other files in the future. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-3-philmd@redhat.com Message-ID: <20190921150420.30743-2-thuth@redhat.com> [PMD: Only take cpu_register() from Thomas's patch] Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu-qom.h | 9 ++++++++- target/arm/cpu.c | 10 ++-------- target/arm/cpu64.c | 8 +------- 3 files changed, 11 insertions(+), 16 deletions(-) diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-qom.h +++ b/target/arm/cpu-qom.h @@ -XXX,XX +XXX,XX @@ struct arm_boot_info; #define TYPE_ARM_MAX_CPU "max-" TYPE_ARM_CPU -typedef struct ARMCPUInfo ARMCPUInfo; +typedef struct ARMCPUInfo { + const char *name; + void (*initfn)(Object *obj); + void (*class_init)(ObjectClass *oc, void *data); +} ARMCPUInfo; + +void arm_cpu_register(const ARMCPUInfo *info); +void aarch64_cpu_register(const ARMCPUInfo *info); /** * ARMCPUClass: diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) #endif /* !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) */ -struct ARMCPUInfo { - const char *name; - void (*initfn)(Object *obj); - void (*class_init)(ObjectClass *oc, void *data); -}; - static const ARMCPUInfo arm_cpus[] = { #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) { .name = "arm926", .initfn = arm926_initfn }, @@ -XXX,XX +XXX,XX @@ static void cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; } -static void cpu_register(const ARMCPUInfo *info) +void arm_cpu_register(const ARMCPUInfo *info) { TypeInfo type_info = { .parent = TYPE_ARM_CPU, @@ -XXX,XX +XXX,XX @@ static void arm_cpu_register_types(void) type_register_static(&idau_interface_type_info); while (info->name) { - cpu_register(info); + arm_cpu_register(info); info++; } 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_max_set_sve_max_vq, NULL, NULL, &error_fatal); } -struct ARMCPUInfo { - const char *name; - void (*initfn)(Object *obj); - void (*class_init)(ObjectClass *oc, void *data); -}; - static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, @@ -XXX,XX +XXX,XX @@ static void cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; } -static void aarch64_cpu_register(const ARMCPUInfo *info) +void aarch64_cpu_register(const ARMCPUInfo *info) { TypeInfo type_info = { .parent = TYPE_AARCH64_CPU, -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-4-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 8 +++----- target/arm/cpu64.c | 8 +++----- 2 files changed, 6 insertions(+), 10 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 const ARMCPUInfo arm_cpus[] = { { .name = "any", .initfn = arm_max_initfn }, #endif #endif - { .name = NULL } }; static Property arm_cpu_properties[] = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo idau_interface_type_info = { static void arm_cpu_register_types(void) { - const ARMCPUInfo *info = arm_cpus; + size_t i; type_register_static(&arm_cpu_type_info); type_register_static(&idau_interface_type_info); - while (info->name) { - arm_cpu_register(info); - info++; + for (i = 0; i < ARRAY_SIZE(arm_cpus); ++i) { + arm_cpu_register(&arm_cpus[i]); } #ifdef CONFIG_KVM 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 const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, - { .name = NULL } }; static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp) @@ -XXX,XX +XXX,XX @@ static const TypeInfo aarch64_cpu_type_info = { static void aarch64_cpu_register_types(void) { - const ARMCPUInfo *info = aarch64_cpus; + size_t i; type_register_static(&aarch64_cpu_type_info); - while (info->name) { - aarch64_cpu_register(info); - info++; + for (i = 0; i < ARRAY_SIZE(aarch64_cpus); ++i) { + aarch64_cpu_register(&aarch64_cpus[i]); } } -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> We will move this code in the next commit. Clean it up first to avoid checkpatch.pl errors. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-5-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 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 bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) CPUARMState *env = &cpu->env; bool ret = false; - /* ARMv7-M interrupt masking works differently than -A or -R. + /* + * ARMv7-M interrupt masking works differently than -A or -R. * There is no FIQ/IRQ distinction. Instead of I and F bits * masking FIQ and IRQ interrupts, an exception is taken only * if it is higher priority than the current execution priority @@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj) static void arm1136_r2_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - /* What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an + /* + * What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an * older core than plain "arm1136". In particular this does not * have the v6K features. * These ID register values are correct for 1136 but may be wrong @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_cpus[] = { { .name = "arm926", .initfn = arm926_initfn }, { .name = "arm946", .initfn = arm946_initfn }, { .name = "arm1026", .initfn = arm1026_initfn }, - /* What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an + /* + * What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an * older core than plain "arm1136". In particular this does not * have the v6K features. */ -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Allow name wildcards in qemu_fdt_node_path(). This is useful to find all nodes with a given compatibility string. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 3 +++ device_tree.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); * NULL. If there is no error but no matching node was found, the * returned array contains a single element equal to NULL. If an error * was encountered when parsing the blob, the function returns NULL + * + * @name may be NULL to wildcard names and only match compatibility + * strings. */ char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, Error **errp); diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, offset = len; break; } - if (!strcmp(iter_name, name)) { + if (!name || !strcmp(iter_name, name)) { char *path; path = g_malloc(path_len); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Make compat in qemu_fdt_node_path() const char *. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-3-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 2 +- device_tree.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); * @name may be NULL to wildcard names and only match compatibility * strings. */ -char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, +char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat, Error **errp); /** diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ char **qemu_fdt_node_unit_path(void *fdt, const char *name, Error **errp) return path_array; } -char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, +char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat, Error **errp) { int offset, len, ret; -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Move arm_boot_info into XlnxZCU102. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-4-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ typedef struct XlnxZCU102 { bool secure; bool virt; + + struct arm_boot_info binfo; } XlnxZCU102; #define TYPE_ZCU102_MACHINE MACHINE_TYPE_NAME("xlnx-zcu102") #define ZCU102_MACHINE(obj) \ OBJECT_CHECK(XlnxZCU102, (obj), TYPE_ZCU102_MACHINE) -static struct arm_boot_info xlnx_zcu102_binfo; static bool zcu102_get_secure(Object *obj, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) /* TODO create and connect IDE devices for ide_drive_get() */ - xlnx_zcu102_binfo.ram_size = ram_size; - xlnx_zcu102_binfo.loader_start = 0; - arm_load_kernel(s->soc.boot_cpu_ptr, machine, &xlnx_zcu102_binfo); + s->binfo.ram_size = ram_size; + s->binfo.loader_start = 0; + arm_load_kernel(s->soc.boot_cpu_ptr, machine, &s->binfo); } static void xlnx_zcu102_machine_instance_init(Object *obj) -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Disable unsupported FDT firmware nodes if a user passes us a DTB with nodes enabled that the machine cannot support due to lack of EL3 or EL2 support. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-5-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qemu/log.h" #include "sysemu/qtest.h" +#include "sysemu/device_tree.h" typedef struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ static void zcu102_set_virt(Object *obj, bool value, Error **errp) s->virt = value; } +static void zcu102_modify_dtb(const struct arm_boot_info *binfo, void *fdt) +{ + XlnxZCU102 *s = container_of(binfo, XlnxZCU102, binfo); + bool method_is_hvc; + char **node_path; + const char *r; + int prop_len; + int i; + + /* If EL3 is enabled, we keep all firmware nodes active. */ + if (!s->secure) { + node_path = qemu_fdt_node_path(fdt, NULL, "xlnx,zynqmp-firmware", + &error_fatal); + + for (i = 0; node_path && node_path[i]; i++) { + r = qemu_fdt_getprop(fdt, node_path[i], "method", &prop_len, NULL); + method_is_hvc = r && !strcmp("hvc", r); + + /* Allow HVC based firmware if EL2 is enabled. */ + if (method_is_hvc && s->virt) { + continue; + } + qemu_fdt_setprop_string(fdt, node_path[i], "status", "disabled"); + } + g_strfreev(node_path); + } +} + static void xlnx_zcu102_init(MachineState *machine) { XlnxZCU102 *s = ZCU102_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) s->binfo.ram_size = ram_size; s->binfo.loader_start = 0; + s->binfo.modify_dtb = zcu102_modify_dtb; arm_load_kernel(s->soc.boot_cpu_ptr, machine, &s->binfo); } -- 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