target-arm queue for softfreeze: this is quite big as I was on holiday last week, so this is all just sneaking in under the wire. I particularly wanted to get Philippe's patches in before freeze as that sort of code-movement patchset is painful to have to rebase. thanks -- PMM The following changes since commit ae9108f8f0746ce64d02afb1a216153a50926132: Merge remote-tracking branch 'remotes/vivier2/tags/linux-user-for-4.1-pull-request' into staging (2019-07-01 15:55:40 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190701 for you to fetch changes up to 787a7e76c2e93a48c47b324fea592c9910a70483: target/arm: Declare some M-profile functions publicly (2019-07-01 17:29:01 +0100) ---------------------------------------------------------------- target-arm queue: * hw/arm/boot: fix direct kernel boot with initrd * hw/arm/msf2-som: Exit when the cpu is not the expected one * i.mx7: fix bugs in PCI controller needed to boot recent kernels * aspeed: add RTC device * aspeed: fix some timer device bugs * aspeed: add swift-bmc board * aspeed: vic: Add support for legacy register interface * aspeed: add aspeed-xdma device * Add new sbsa-ref board for aarch64 * target/arm: code refactoring in preparation for support of compilation with TCG disabled ---------------------------------------------------------------- Adriana Kobylak (1): aspeed: Add support for the swift-bmc board Andrew Jeffery (3): aspeed/timer: Status register contains reload for stopped timer aspeed/timer: Fix match calculations aspeed: vic: Add support for legacy register interface Andrew Jones (1): hw/arm/boot: fix direct kernel boot with initrd Andrey Smirnov (5): i.mx7d: Add no-op/unimplemented APBH DMA module i.mx7d: Add no-op/unimplemented PCIE PHY IP block pci: designware: Update MSI mapping unconditionally pci: designware: Update MSI mapping when MSI address changes i.mx7d: pci: Update PCI IRQ mapping to match HW Christian Svensson (1): aspeed/timer: Ensure positive muldiv delta Cédric Le Goater (7): aspeed: add a per SoC mapping for the interrupt space aspeed: add a per SoC mapping for the memory space aspeed: introduce a configurable number of CPU per machine aspeed: add support for multiple NICs aspeed: remove the "ram" link aspeed: add a RAM memory region container aspeed/smc: add a 'sdram_base' property Eddie James (1): hw/misc/aspeed_xdma: New device Hongbo Zhang (2): hw/arm: Add arm SBSA reference machine, skeleton part hw/arm: Add arm SBSA reference machine, devices part Jan Kiszka (1): hw/arm/virt: Add support for Cortex-A7 Joel Stanley (4): hw: timer: Add ASPEED RTC device hw/arm/aspeed: Add RTC to SoC aspeed/timer: Fix behaviour running Linux aspeed: Link SCU to the watchdog Philippe Mathieu-Daudé (19): hw/arm/msf2-som: Exit when the cpu is not the expected one target/arm: Makefile cleanup (Aarch64) target/arm: Makefile cleanup (ARM) target/arm: Makefile cleanup (KVM) target/arm: Makefile cleanup (softmmu) target/arm: Add copyright boilerplate target/arm/helper: Remove unused include target/arm: Fix multiline comment syntax target/arm: Fix coding style issues target/arm: Move CPU state dumping routines to cpu.c target/arm: Declare get_phys_addr() function publicly target/arm: Move TLB related routines to tlb_helper.c target/arm/vfp_helper: Move code around target/arm/vfp_helper: Extract vfp_set_fpscr_to_host() target/arm/vfp_helper: Extract vfp_set_fpscr_from_host() target/arm/vfp_helper: Restrict the SoftFloat use to TCG target/arm: Restrict PSCI to TCG target/arm: Declare arm_log_exception() function publicly target/arm: Declare some M-profile functions publicly Samuel Ortiz (1): target/arm: Move the DC ZVA helper into op_helper hw/arm/Makefile.objs | 1 + hw/misc/Makefile.objs | 1 + hw/timer/Makefile.objs | 2 +- target/arm/Makefile.objs | 24 +- include/hw/arm/aspeed_soc.h | 53 ++- include/hw/arm/fsl-imx7.h | 14 +- include/hw/misc/aspeed_xdma.h | 30 ++ include/hw/ssi/aspeed_smc.h | 3 + include/hw/timer/aspeed_rtc.h | 31 ++ include/hw/watchdog/wdt_aspeed.h | 1 + target/arm/cpu.h | 2 - target/arm/internals.h | 69 ++- target/arm/translate.h | 5 - hw/arm/aspeed.c | 76 +++- hw/arm/aspeed_soc.c | 262 +++++++++--- hw/arm/boot.c | 3 +- hw/arm/fsl-imx7.c | 11 + hw/arm/msf2-som.c | 1 + hw/arm/sbsa-ref.c | 806 ++++++++++++++++++++++++++++++++++++ hw/arm/virt.c | 1 + hw/intc/aspeed_vic.c | 105 +++-- hw/misc/aspeed_xdma.c | 165 ++++++++ hw/pci-host/designware.c | 18 +- hw/ssi/aspeed_smc.c | 1 + hw/timer/aspeed_rtc.c | 180 ++++++++ hw/timer/aspeed_timer.c | 76 ++-- hw/watchdog/wdt_aspeed.c | 20 + target/arm/cpu.c | 232 ++++++++++- target/arm/helper.c | 498 +++++++++------------- target/arm/op_helper.c | 262 ++++++------ target/arm/tlb_helper.c | 200 +++++++++ target/arm/translate-a64.c | 128 ------ target/arm/translate.c | 91 +--- target/arm/vfp_helper.c | 199 +++++---- MAINTAINERS | 8 + default-configs/aarch64-softmmu.mak | 1 + hw/arm/Kconfig | 14 + hw/misc/trace-events | 3 + hw/timer/trace-events | 4 + 39 files changed, 2675 insertions(+), 926 deletions(-) create mode 100644 include/hw/misc/aspeed_xdma.h create mode 100644 include/hw/timer/aspeed_rtc.h create mode 100644 hw/arm/sbsa-ref.c create mode 100644 hw/misc/aspeed_xdma.c create mode 100644 hw/timer/aspeed_rtc.c create mode 100644 target/arm/tlb_helper.c From: Andrew Jones <drjones@redhat.com> Fix the condition used to check whether the initrd fits into RAM; in some cases if an initrd was also passed on the command line we would get an error stating that it was too big to fit into RAM after the kernel. Despite the error the loader continued anyway, though, so also add an exit(1) when the initrd is actually too big. Fixes: 852dc64d665f ("hw/arm/boot: Diagnose layouts that put initrd or DTB off the end of RAM") Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190618125844.4863-1-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, info->initrd_filename); exit(1); } - if (info->initrd_start + initrd_size > info->ram_size) { + if (info->initrd_start + initrd_size > ram_end) { error_report("could not load initrd '%s': " "too big to fit into RAM after the kernel", info->initrd_filename); + exit(1); } } else { initrd_size = 0; -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> This machine correctly defines its default_cpu_type to cortex-m3 and report an error if the user requested another cpu_type, however it does not exit, and this can confuse users trying to use another core: $ qemu-system-arm -M emcraft-sf2 -cpu cortex-m4 -kernel test-m4.elf qemu-system-arm: This board can only be used with CPU cortex-m3-arm-cpu [output related to M3 core ...] The CPU is indeed a M3 core: (qemu) info qom-tree /machine (emcraft-sf2-machine) /unattached (container) /device[0] (msf2-soc) /armv7m (armv7m) /cpu (cortex-m3-arm-cpu) Add the missing exit() call to return to the shell. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20190617160136.29930-1-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/msf2-som.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-som.c +++ b/hw/arm/msf2-som.c @@ -XXX,XX +XXX,XX @@ static void emcraft_sf2_s2s010_init(MachineState *machine) if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { error_report("This board can only be used with CPU %s", mc->default_cpu_type); + exit(1); } memory_region_init_ram(ddr, NULL, "ddr-ram", DDR_SIZE, -- 2.20.1 From: Jan Kiszka <jan.kiszka@siemens.com> Allow cortex-a7 to be used with the virt board; it supports the v7VE features and there is no reason to deny this type. Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: fc5404f7-4d1d-c28f-6e48-d8799c82acc0@web.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 1 + 1 file changed, 1 insertion(+) 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 int a15irqmap[] = { }; static const char *valid_cpus[] = { + ARM_CPU_TYPE_NAME("cortex-a7"), ARM_CPU_TYPE_NAME("cortex-a15"), ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), -- 2.20.1 From: Andrey Smirnov <andrew.smirnov@gmail.com> Instantiate no-op APBH DMA module. Needed to boot latest Linux kernel. Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 3 +++ hw/arm/fsl-imx7.c | 6 ++++++ 2 files changed, 9 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_PCIE_REG_SIZE = 16 * 1024, FSL_IMX7_GPR_ADDR = 0x30340000, + + FSL_IMX7_DMA_APBH_ADDR = 0x33000000, + FSL_IMX7_DMA_APBH_SIZE = 0x2000, }; enum FslIMX7IRQs { diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) */ create_unimplemented_device("lcdif", FSL_IMX7_LCDIF_ADDR, FSL_IMX7_LCDIF_SIZE); + + /* + * DMA APBH + */ + create_unimplemented_device("dma-apbh", FSL_IMX7_DMA_APBH_ADDR, + FSL_IMX7_DMA_APBH_SIZE); } static void fsl_imx7_class_init(ObjectClass *oc, void *data) -- 2.20.1 From: Andrey Smirnov <andrew.smirnov@gmail.com> Add no-op/unimplemented PCIE PHY IP block. Needed by new kernels to use PCIE. Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 3 +++ hw/arm/fsl-imx7.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_ADC2_ADDR = 0x30620000, FSL_IMX7_ADCn_SIZE = 0x1000, + FSL_IMX7_PCIE_PHY_ADDR = 0x306D0000, + FSL_IMX7_PCIE_PHY_SIZE = 0x10000, + FSL_IMX7_GPC_ADDR = 0x303A0000, FSL_IMX7_I2C1_ADDR = 0x30A20000, diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) */ create_unimplemented_device("dma-apbh", FSL_IMX7_DMA_APBH_ADDR, FSL_IMX7_DMA_APBH_SIZE); + /* + * PCIe PHY + */ + create_unimplemented_device("pcie-phy", FSL_IMX7_PCIE_PHY_ADDR, + FSL_IMX7_PCIE_PHY_SIZE); } static void fsl_imx7_class_init(ObjectClass *oc, void *data) -- 2.20.1 From: Andrey Smirnov <andrew.smirnov@gmail.com> Expression to calculate update_msi_mapping in code handling writes to DESIGNWARE_PCIE_MSI_INTR0_ENABLE is missing an ! operator and should be: !!root->msi.intr[0].enable ^ !!val; so that MSI mapping is updated when enabled transitions from either "none" -> "any" or "any" -> "none". Since that register shouldn't be written to very often, change the code to update MSI mapping unconditionally instead of trying to fix the update_msi_mapping logic. Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/pci-host/designware.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/hw/pci-host/designware.c b/hw/pci-host/designware.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/designware.c +++ b/hw/pci-host/designware.c @@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_config_write(PCIDevice *d, uint32_t address, root->msi.base |= (uint64_t)val << 32; break; - case DESIGNWARE_PCIE_MSI_INTR0_ENABLE: { - const bool update_msi_mapping = !root->msi.intr[0].enable ^ !!val; - + case DESIGNWARE_PCIE_MSI_INTR0_ENABLE: root->msi.intr[0].enable = val; - - if (update_msi_mapping) { - designware_pcie_root_update_msi_mapping(root); - } + designware_pcie_root_update_msi_mapping(root); break; - } case DESIGNWARE_PCIE_MSI_INTR0_MASK: root->msi.intr[0].mask = val; -- 2.20.1 From: Andrey Smirnov <andrew.smirnov@gmail.com> MSI mapping needs to be update when MSI address changes, so add the code to do so. Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org Acked-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/pci-host/designware.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/pci-host/designware.c b/hw/pci-host/designware.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/designware.c +++ b/hw/pci-host/designware.c @@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_config_write(PCIDevice *d, uint32_t address, case DESIGNWARE_PCIE_MSI_ADDR_LO: root->msi.base &= 0xFFFFFFFF00000000ULL; root->msi.base |= val; + designware_pcie_root_update_msi_mapping(root); break; case DESIGNWARE_PCIE_MSI_ADDR_HI: root->msi.base &= 0x00000000FFFFFFFFULL; root->msi.base |= (uint64_t)val << 32; + designware_pcie_root_update_msi_mapping(root); break; case DESIGNWARE_PCIE_MSI_INTR0_ENABLE: -- 2.20.1 From: Andrey Smirnov <andrew.smirnov@gmail.com> Datasheet for i.MX7 is incorrect and i.MX7's PCI IRQ mapping matches that of i.MX6: * INTD/MSI 122 * INTC 123 * INTB 124 * INTA 125 Fix all of the relevant code to reflect that fact. Needed by latest Linux kernels. (Reference: Linux kernel commit 538d6e9d597584e80 from an NXP employee confirming that the datasheet is incorrect and with a report of a test against hardware.) Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: added ref to kernel commit confirming the datasheet error] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 8 ++++---- hw/pci-host/designware.c | 6 ++++-- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7IRQs { FSL_IMX7_USB2_IRQ = 42, FSL_IMX7_USB3_IRQ = 40, - FSL_IMX7_PCI_INTA_IRQ = 122, - FSL_IMX7_PCI_INTB_IRQ = 123, - FSL_IMX7_PCI_INTC_IRQ = 124, - FSL_IMX7_PCI_INTD_IRQ = 125, + FSL_IMX7_PCI_INTA_IRQ = 125, + FSL_IMX7_PCI_INTB_IRQ = 124, + FSL_IMX7_PCI_INTC_IRQ = 123, + FSL_IMX7_PCI_INTD_IRQ = 122, FSL_IMX7_UART7_IRQ = 126, diff --git a/hw/pci-host/designware.c b/hw/pci-host/designware.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/designware.c +++ b/hw/pci-host/designware.c @@ -XXX,XX +XXX,XX @@ #define DESIGNWARE_PCIE_ATU_DEVFN(x) (((x) >> 16) & 0xff) #define DESIGNWARE_PCIE_ATU_UPPER_TARGET 0x91C +#define DESIGNWARE_PCIE_IRQ_MSI 3 + static DesignwarePCIEHost * designware_pcie_root_to_host(DesignwarePCIERoot *root) { @@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_msi_write(void *opaque, hwaddr addr, root->msi.intr[0].status |= BIT(val) & root->msi.intr[0].enable; if (root->msi.intr[0].status & ~root->msi.intr[0].mask) { - qemu_set_irq(host->pci.irqs[0], 1); + qemu_set_irq(host->pci.irqs[DESIGNWARE_PCIE_IRQ_MSI], 1); } } @@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_config_write(PCIDevice *d, uint32_t address, case DESIGNWARE_PCIE_MSI_INTR0_STATUS: root->msi.intr[0].status ^= val; if (!root->msi.intr[0].status) { - qemu_set_irq(host->pci.irqs[0], 0); + qemu_set_irq(host->pci.irqs[DESIGNWARE_PCIE_IRQ_MSI], 0); } break; -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> This will simplify the definition of new SoCs, like the AST2600 which should use a different CPU and a different IRQ number layout. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed_soc.h | 36 +++++++++++++++++++++++ hw/arm/aspeed_soc.c | 57 +++++++++++++++++++++++++++++++------ 2 files changed, 85 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCInfo { const char *fmc_typename; const char **spi_typename; int wdts_num; + const int *irqmap; } AspeedSoCInfo; typedef struct AspeedSoCClass { @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCClass { #define ASPEED_SOC_GET_CLASS(obj) \ OBJECT_GET_CLASS(AspeedSoCClass, (obj), TYPE_ASPEED_SOC) +enum { + ASPEED_IOMEM, + ASPEED_UART1, + ASPEED_UART2, + ASPEED_UART3, + ASPEED_UART4, + ASPEED_UART5, + ASPEED_VUART, + ASPEED_FMC, + ASPEED_SPI1, + ASPEED_SPI2, + ASPEED_VIC, + ASPEED_SDMC, + ASPEED_SCU, + ASPEED_ADC, + ASPEED_SRAM, + ASPEED_GPIO, + ASPEED_RTC, + ASPEED_TIMER1, + ASPEED_TIMER2, + ASPEED_TIMER3, + ASPEED_TIMER4, + ASPEED_TIMER5, + ASPEED_TIMER6, + ASPEED_TIMER7, + ASPEED_TIMER8, + ASPEED_WDT, + ASPEED_PWM, + ASPEED_LPC, + ASPEED_IBT, + ASPEED_I2C, + ASPEED_ETH1, + ASPEED_ETH2, +}; + #endif /* ASPEED_SOC_H */ diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ #define ASPEED_SOC_ETH1_BASE 0x1E660000 #define ASPEED_SOC_ETH2_BASE 0x1E680000 -static const int uart_irqs[] = { 9, 32, 33, 34, 10 }; -static const int timer_irqs[] = { 16, 17, 18, 35, 36, 37, 38, 39, }; +static const int aspeed_soc_ast2400_irqmap[] = { + [ASPEED_UART1] = 9, + [ASPEED_UART2] = 32, + [ASPEED_UART3] = 33, + [ASPEED_UART4] = 34, + [ASPEED_UART5] = 10, + [ASPEED_VUART] = 8, + [ASPEED_FMC] = 19, + [ASPEED_SDMC] = 0, + [ASPEED_SCU] = 21, + [ASPEED_ADC] = 31, + [ASPEED_GPIO] = 20, + [ASPEED_RTC] = 22, + [ASPEED_TIMER1] = 16, + [ASPEED_TIMER2] = 17, + [ASPEED_TIMER3] = 18, + [ASPEED_TIMER4] = 35, + [ASPEED_TIMER5] = 36, + [ASPEED_TIMER6] = 37, + [ASPEED_TIMER7] = 38, + [ASPEED_TIMER8] = 39, + [ASPEED_WDT] = 27, + [ASPEED_PWM] = 28, + [ASPEED_LPC] = 8, + [ASPEED_IBT] = 8, /* LPC */ + [ASPEED_I2C] = 12, + [ASPEED_ETH1] = 2, + [ASPEED_ETH2] = 3, +}; #define AST2400_SDRAM_BASE 0x40000000 #define AST2500_SDRAM_BASE 0x80000000 +/* AST2500 uses the same IRQs as the AST2400 */ +#define aspeed_soc_ast2500_irqmap aspeed_soc_ast2400_irqmap + static const hwaddr aspeed_soc_ast2400_spi_bases[] = { ASPEED_SOC_SPI_BASE }; static const char *aspeed_soc_ast2400_typenames[] = { "aspeed.smc.spi" }; @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .fmc_typename = "aspeed.smc.fmc", .spi_typename = aspeed_soc_ast2400_typenames, .wdts_num = 2, + .irqmap = aspeed_soc_ast2400_irqmap, }, { .name = "ast2400-a1", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .fmc_typename = "aspeed.smc.fmc", .spi_typename = aspeed_soc_ast2400_typenames, .wdts_num = 2, + .irqmap = aspeed_soc_ast2400_irqmap, }, { .name = "ast2400", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .fmc_typename = "aspeed.smc.fmc", .spi_typename = aspeed_soc_ast2400_typenames, .wdts_num = 2, + .irqmap = aspeed_soc_ast2400_irqmap, }, { .name = "ast2500-a1", .cpu_type = ARM_CPU_TYPE_NAME("arm1176"), @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .fmc_typename = "aspeed.smc.ast2500-fmc", .spi_typename = aspeed_soc_ast2500_typenames, .wdts_num = 3, + .irqmap = aspeed_soc_ast2500_irqmap, }, }; +static qemu_irq aspeed_soc_get_irq(AspeedSoCState *s, int ctrl) +{ + AspeedSoCClass *sc = ASPEED_SOC_GET_CLASS(s); + + return qdev_get_gpio_in(DEVICE(&s->vic), sc->info->irqmap[ctrl]); +} + static void aspeed_soc_init(Object *obj) { AspeedSoCState *s = ASPEED_SOC(obj); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) return; } sysbus_mmio_map(SYS_BUS_DEVICE(&s->timerctrl), 0, ASPEED_SOC_TIMER_BASE); - for (i = 0; i < ARRAY_SIZE(timer_irqs); i++) { - qemu_irq irq = qdev_get_gpio_in(DEVICE(&s->vic), timer_irqs[i]); + for (i = 0; i < ASPEED_TIMER_NR_TIMERS; i++) { + qemu_irq irq = aspeed_soc_get_irq(s, ASPEED_TIMER1 + i); sysbus_connect_irq(SYS_BUS_DEVICE(&s->timerctrl), i, irq); } /* UART - attach an 8250 to the IO space as our UART5 */ if (serial_hd(0)) { - qemu_irq uart5 = qdev_get_gpio_in(DEVICE(&s->vic), uart_irqs[4]); + qemu_irq uart5 = aspeed_soc_get_irq(s, ASPEED_UART5); serial_mm_init(get_system_memory(), ASPEED_SOC_IOMEM_BASE + ASPEED_SOC_UART_5_BASE, 2, uart5, 38400, serial_hd(0), DEVICE_LITTLE_ENDIAN); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c), 0, ASPEED_SOC_I2C_BASE); sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c), 0, - qdev_get_gpio_in(DEVICE(&s->vic), 12)); + aspeed_soc_get_irq(s, ASPEED_I2C)); /* FMC, The number of CS is set at the board level */ object_property_set_bool(OBJECT(&s->fmc), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->fmc), 1, s->fmc.ctrl->flash_window_base); sysbus_connect_irq(SYS_BUS_DEVICE(&s->fmc), 0, - qdev_get_gpio_in(DEVICE(&s->vic), 19)); + aspeed_soc_get_irq(s, ASPEED_FMC)); /* SPI */ for (i = 0; i < sc->info->spis_num; i++) { @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->ftgmac100), 0, ASPEED_SOC_ETH1_BASE); sysbus_connect_irq(SYS_BUS_DEVICE(&s->ftgmac100), 0, - qdev_get_gpio_in(DEVICE(&s->vic), 2)); + aspeed_soc_get_irq(s, ASPEED_ETH1)); } static void aspeed_soc_class_init(ObjectClass *oc, void *data) -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> This will simplify the definition of new SoCs, like the AST2600 which should use a slightly different address space and have a different set of controllers. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed_soc.h | 4 +- hw/arm/aspeed.c | 8 +-- hw/arm/aspeed_soc.c | 117 ++++++++++++++++++++++-------------- 3 files changed, 78 insertions(+), 51 deletions(-) diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCInfo { const char *name; const char *cpu_type; uint32_t silicon_rev; - hwaddr sdram_base; uint64_t sram_size; int spis_num; - const hwaddr *spi_bases; const char *fmc_typename; const char **spi_typename; int wdts_num; const int *irqmap; + const hwaddr *memmap; } AspeedSoCInfo; typedef struct AspeedSoCClass { @@ -XXX,XX +XXX,XX @@ enum { ASPEED_I2C, ASPEED_ETH1, ASPEED_ETH2, + ASPEED_SDRAM, }; #endif /* ASPEED_SOC_H */ diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, &error_abort); memory_region_allocate_system_memory(&bmc->ram, NULL, "ram", ram_size); - memory_region_add_subregion(get_system_memory(), sc->info->sdram_base, - &bmc->ram); + memory_region_add_subregion(get_system_memory(), + sc->info->memmap[ASPEED_SDRAM], &bmc->ram); object_property_add_const_link(OBJECT(&bmc->soc), "ram", OBJECT(&bmc->ram), &error_abort); @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, memory_region_init_io(&bmc->max_ram, NULL, &max_ram_ops, NULL, "max_ram", max_ram_size - ram_size); memory_region_add_subregion(get_system_memory(), - sc->info->sdram_base + ram_size, + sc->info->memmap[ASPEED_SDRAM] + ram_size, &bmc->max_ram); aspeed_board_init_flashes(&bmc->soc.fmc, cfg->fmc_model, &error_abort); @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, aspeed_board_binfo.initrd_filename = machine->initrd_filename; aspeed_board_binfo.kernel_cmdline = machine->kernel_cmdline; aspeed_board_binfo.ram_size = ram_size; - aspeed_board_binfo.loader_start = sc->info->sdram_base; + aspeed_board_binfo.loader_start = sc->info->memmap[ASPEED_SDRAM]; if (cfg->i2c_init) { cfg->i2c_init(bmc); diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ #include "hw/i2c/aspeed_i2c.h" #include "net/net.h" -#define ASPEED_SOC_UART_5_BASE 0x00184000 #define ASPEED_SOC_IOMEM_SIZE 0x00200000 -#define ASPEED_SOC_IOMEM_BASE 0x1E600000 -#define ASPEED_SOC_FMC_BASE 0x1E620000 -#define ASPEED_SOC_SPI_BASE 0x1E630000 -#define ASPEED_SOC_SPI2_BASE 0x1E631000 -#define ASPEED_SOC_VIC_BASE 0x1E6C0000 -#define ASPEED_SOC_SDMC_BASE 0x1E6E0000 -#define ASPEED_SOC_SCU_BASE 0x1E6E2000 -#define ASPEED_SOC_SRAM_BASE 0x1E720000 -#define ASPEED_SOC_TIMER_BASE 0x1E782000 -#define ASPEED_SOC_WDT_BASE 0x1E785000 -#define ASPEED_SOC_I2C_BASE 0x1E78A000 -#define ASPEED_SOC_ETH1_BASE 0x1E660000 -#define ASPEED_SOC_ETH2_BASE 0x1E680000 + +static const hwaddr aspeed_soc_ast2400_memmap[] = { + [ASPEED_IOMEM] = 0x1E600000, + [ASPEED_FMC] = 0x1E620000, + [ASPEED_SPI1] = 0x1E630000, + [ASPEED_VIC] = 0x1E6C0000, + [ASPEED_SDMC] = 0x1E6E0000, + [ASPEED_SCU] = 0x1E6E2000, + [ASPEED_ADC] = 0x1E6E9000, + [ASPEED_SRAM] = 0x1E720000, + [ASPEED_GPIO] = 0x1E780000, + [ASPEED_RTC] = 0x1E781000, + [ASPEED_TIMER1] = 0x1E782000, + [ASPEED_WDT] = 0x1E785000, + [ASPEED_PWM] = 0x1E786000, + [ASPEED_LPC] = 0x1E789000, + [ASPEED_IBT] = 0x1E789140, + [ASPEED_I2C] = 0x1E78A000, + [ASPEED_ETH1] = 0x1E660000, + [ASPEED_ETH2] = 0x1E680000, + [ASPEED_UART1] = 0x1E783000, + [ASPEED_UART5] = 0x1E784000, + [ASPEED_VUART] = 0x1E787000, + [ASPEED_SDRAM] = 0x40000000, +}; + +static const hwaddr aspeed_soc_ast2500_memmap[] = { + [ASPEED_IOMEM] = 0x1E600000, + [ASPEED_FMC] = 0x1E620000, + [ASPEED_SPI1] = 0x1E630000, + [ASPEED_SPI2] = 0x1E631000, + [ASPEED_VIC] = 0x1E6C0000, + [ASPEED_SDMC] = 0x1E6E0000, + [ASPEED_SCU] = 0x1E6E2000, + [ASPEED_ADC] = 0x1E6E9000, + [ASPEED_SRAM] = 0x1E720000, + [ASPEED_GPIO] = 0x1E780000, + [ASPEED_RTC] = 0x1E781000, + [ASPEED_TIMER1] = 0x1E782000, + [ASPEED_WDT] = 0x1E785000, + [ASPEED_PWM] = 0x1E786000, + [ASPEED_LPC] = 0x1E789000, + [ASPEED_IBT] = 0x1E789140, + [ASPEED_I2C] = 0x1E78A000, + [ASPEED_ETH1] = 0x1E660000, + [ASPEED_ETH2] = 0x1E680000, + [ASPEED_UART1] = 0x1E783000, + [ASPEED_UART5] = 0x1E784000, + [ASPEED_VUART] = 0x1E787000, + [ASPEED_SDRAM] = 0x80000000, +}; static const int aspeed_soc_ast2400_irqmap[] = { [ASPEED_UART1] = 9, @@ -XXX,XX +XXX,XX @@ static const int aspeed_soc_ast2400_irqmap[] = { [ASPEED_ETH2] = 3, }; -#define AST2400_SDRAM_BASE 0x40000000 -#define AST2500_SDRAM_BASE 0x80000000 - -/* AST2500 uses the same IRQs as the AST2400 */ #define aspeed_soc_ast2500_irqmap aspeed_soc_ast2400_irqmap -static const hwaddr aspeed_soc_ast2400_spi_bases[] = { ASPEED_SOC_SPI_BASE }; static const char *aspeed_soc_ast2400_typenames[] = { "aspeed.smc.spi" }; - -static const hwaddr aspeed_soc_ast2500_spi_bases[] = { ASPEED_SOC_SPI_BASE, - ASPEED_SOC_SPI2_BASE}; static const char *aspeed_soc_ast2500_typenames[] = { "aspeed.smc.ast2500-spi1", "aspeed.smc.ast2500-spi2" }; @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .name = "ast2400-a0", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), .silicon_rev = AST2400_A0_SILICON_REV, - .sdram_base = AST2400_SDRAM_BASE, .sram_size = 0x8000, .spis_num = 1, - .spi_bases = aspeed_soc_ast2400_spi_bases, .fmc_typename = "aspeed.smc.fmc", .spi_typename = aspeed_soc_ast2400_typenames, .wdts_num = 2, .irqmap = aspeed_soc_ast2400_irqmap, + .memmap = aspeed_soc_ast2400_memmap, }, { .name = "ast2400-a1", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), .silicon_rev = AST2400_A1_SILICON_REV, - .sdram_base = AST2400_SDRAM_BASE, .sram_size = 0x8000, .spis_num = 1, - .spi_bases = aspeed_soc_ast2400_spi_bases, .fmc_typename = "aspeed.smc.fmc", .spi_typename = aspeed_soc_ast2400_typenames, .wdts_num = 2, .irqmap = aspeed_soc_ast2400_irqmap, + .memmap = aspeed_soc_ast2400_memmap, }, { .name = "ast2400", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), .silicon_rev = AST2400_A0_SILICON_REV, - .sdram_base = AST2400_SDRAM_BASE, .sram_size = 0x8000, .spis_num = 1, - .spi_bases = aspeed_soc_ast2400_spi_bases, .fmc_typename = "aspeed.smc.fmc", .spi_typename = aspeed_soc_ast2400_typenames, .wdts_num = 2, .irqmap = aspeed_soc_ast2400_irqmap, + .memmap = aspeed_soc_ast2400_memmap, }, { .name = "ast2500-a1", .cpu_type = ARM_CPU_TYPE_NAME("arm1176"), .silicon_rev = AST2500_A1_SILICON_REV, - .sdram_base = AST2500_SDRAM_BASE, .sram_size = 0x9000, .spis_num = 2, - .spi_bases = aspeed_soc_ast2500_spi_bases, .fmc_typename = "aspeed.smc.ast2500-fmc", .spi_typename = aspeed_soc_ast2500_typenames, .wdts_num = 3, .irqmap = aspeed_soc_ast2500_irqmap, + .memmap = aspeed_soc_ast2500_memmap, }, }; @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) Error *err = NULL, *local_err = NULL; /* IO space */ - create_unimplemented_device("aspeed_soc.io", - ASPEED_SOC_IOMEM_BASE, ASPEED_SOC_IOMEM_SIZE); + create_unimplemented_device("aspeed_soc.io", sc->info->memmap[ASPEED_IOMEM], + ASPEED_SOC_IOMEM_SIZE); /* CPU */ object_property_set_bool(OBJECT(&s->cpu), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - memory_region_add_subregion(get_system_memory(), ASPEED_SOC_SRAM_BASE, - &s->sram); + memory_region_add_subregion(get_system_memory(), + sc->info->memmap[ASPEED_SRAM], &s->sram); /* SCU */ object_property_set_bool(OBJECT(&s->scu), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->scu), 0, ASPEED_SOC_SCU_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->scu), 0, sc->info->memmap[ASPEED_SCU]); /* VIC */ object_property_set_bool(OBJECT(&s->vic), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->vic), 0, ASPEED_SOC_VIC_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->vic), 0, sc->info->memmap[ASPEED_VIC]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->vic), 0, qdev_get_gpio_in(DEVICE(&s->cpu), ARM_CPU_IRQ)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->vic), 1, @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->timerctrl), 0, ASPEED_SOC_TIMER_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->timerctrl), 0, + sc->info->memmap[ASPEED_TIMER1]); for (i = 0; i < ASPEED_TIMER_NR_TIMERS; i++) { qemu_irq irq = aspeed_soc_get_irq(s, ASPEED_TIMER1 + i); sysbus_connect_irq(SYS_BUS_DEVICE(&s->timerctrl), i, irq); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) /* UART - attach an 8250 to the IO space as our UART5 */ if (serial_hd(0)) { qemu_irq uart5 = aspeed_soc_get_irq(s, ASPEED_UART5); - serial_mm_init(get_system_memory(), - ASPEED_SOC_IOMEM_BASE + ASPEED_SOC_UART_5_BASE, 2, + serial_mm_init(get_system_memory(), sc->info->memmap[ASPEED_UART5], 2, uart5, 38400, serial_hd(0), DEVICE_LITTLE_ENDIAN); } @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c), 0, ASPEED_SOC_I2C_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c), 0, sc->info->memmap[ASPEED_I2C]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c), 0, aspeed_soc_get_irq(s, ASPEED_I2C)); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->fmc), 0, ASPEED_SOC_FMC_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->fmc), 0, sc->info->memmap[ASPEED_FMC]); sysbus_mmio_map(SYS_BUS_DEVICE(&s->fmc), 1, s->fmc.ctrl->flash_window_base); sysbus_connect_irq(SYS_BUS_DEVICE(&s->fmc), 0, @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, sc->info->spi_bases[i]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, + sc->info->memmap[ASPEED_SPI1 + i]); sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 1, s->spi[i].ctrl->flash_window_base); } @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->sdmc), 0, ASPEED_SOC_SDMC_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->sdmc), 0, sc->info->memmap[ASPEED_SDMC]); /* Watch dog */ for (i = 0; i < sc->info->wdts_num; i++) { @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) return; } sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, - ASPEED_SOC_WDT_BASE + i * 0x20); + sc->info->memmap[ASPEED_WDT] + i * 0x20); } /* Net */ @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->ftgmac100), 0, ASPEED_SOC_ETH1_BASE); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ftgmac100), 0, + sc->info->memmap[ASPEED_ETH1]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->ftgmac100), 0, aspeed_soc_get_irq(s, ASPEED_ETH1)); } -- 2.20.1 From: Joel Stanley <joel@jms.id.au> The RTC is modeled to provide time and date functionality. It is initialised at zero to match the hardware. There is no modelling of the alarm functionality, which includes the IRQ line. As there is no guest code to exercise this function that is acceptable for now. Signed-off-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190618165311.27066-4-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/Makefile.objs | 2 +- include/hw/timer/aspeed_rtc.h | 31 ++++++ hw/timer/aspeed_rtc.c | 180 ++++++++++++++++++++++++++++++++++ hw/timer/trace-events | 4 + 4 files changed, 216 insertions(+), 1 deletion(-) create mode 100644 include/hw/timer/aspeed_rtc.h create mode 100644 hw/timer/aspeed_rtc.c diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/Makefile.objs +++ b/hw/timer/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_MC146818RTC) += mc146818rtc.o obj-$(CONFIG_ALLWINNER_A10_PIT) += allwinner-a10-pit.o common-obj-$(CONFIG_STM32F2XX_TIMER) += stm32f2xx_timer.o -common-obj-$(CONFIG_ASPEED_SOC) += aspeed_timer.o +common-obj-$(CONFIG_ASPEED_SOC) += aspeed_timer.o aspeed_rtc.o common-obj-$(CONFIG_SUN4V_RTC) += sun4v-rtc.o common-obj-$(CONFIG_CMSDK_APB_TIMER) += cmsdk-apb-timer.o diff --git a/include/hw/timer/aspeed_rtc.h b/include/hw/timer/aspeed_rtc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/aspeed_rtc.h @@ -XXX,XX +XXX,XX @@ +/* + * ASPEED Real Time Clock + * Joel Stanley <joel@jms.id.au> + * + * Copyright 2019 IBM Corp + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef ASPEED_RTC_H +#define ASPEED_RTC_H + +#include <stdint.h> + +#include "hw/hw.h" +#include "hw/irq.h" +#include "hw/sysbus.h" + +typedef struct AspeedRtcState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + qemu_irq irq; + + uint32_t reg[0x18]; + int offset; + +} AspeedRtcState; + +#define TYPE_ASPEED_RTC "aspeed.rtc" +#define ASPEED_RTC(obj) OBJECT_CHECK(AspeedRtcState, (obj), TYPE_ASPEED_RTC) + +#endif /* ASPEED_RTC_H */ diff --git a/hw/timer/aspeed_rtc.c b/hw/timer/aspeed_rtc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/aspeed_rtc.c @@ -XXX,XX +XXX,XX @@ +/* + * ASPEED Real Time Clock + * Joel Stanley <joel@jms.id.au> + * + * Copyright 2019 IBM Corp + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "hw/timer/aspeed_rtc.h" +#include "qemu/log.h" +#include "qemu/timer.h" + +#include "trace.h" + +#define COUNTER1 (0x00 / 4) +#define COUNTER2 (0x04 / 4) +#define ALARM (0x08 / 4) +#define CONTROL (0x10 / 4) +#define ALARM_STATUS (0x14 / 4) + +#define RTC_UNLOCKED BIT(1) +#define RTC_ENABLED BIT(0) + +static void aspeed_rtc_calc_offset(AspeedRtcState *rtc) +{ + struct tm tm; + uint32_t year, cent; + uint32_t reg1 = rtc->reg[COUNTER1]; + uint32_t reg2 = rtc->reg[COUNTER2]; + + tm.tm_mday = (reg1 >> 24) & 0x1f; + tm.tm_hour = (reg1 >> 16) & 0x1f; + tm.tm_min = (reg1 >> 8) & 0x3f; + tm.tm_sec = (reg1 >> 0) & 0x3f; + + cent = (reg2 >> 16) & 0x1f; + year = (reg2 >> 8) & 0x7f; + tm.tm_mon = ((reg2 >> 0) & 0x0f) - 1; + tm.tm_year = year + (cent * 100) - 1900; + + rtc->offset = qemu_timedate_diff(&tm); +} + +static uint32_t aspeed_rtc_get_counter(AspeedRtcState *rtc, int r) +{ + uint32_t year, cent; + struct tm now; + + qemu_get_timedate(&now, rtc->offset); + + switch (r) { + case COUNTER1: + return (now.tm_mday << 24) | (now.tm_hour << 16) | + (now.tm_min << 8) | now.tm_sec; + case COUNTER2: + cent = (now.tm_year + 1900) / 100; + year = now.tm_year % 100; + return ((cent & 0x1f) << 16) | ((year & 0x7f) << 8) | + ((now.tm_mon + 1) & 0xf); + default: + g_assert_not_reached(); + } +} + +static uint64_t aspeed_rtc_read(void *opaque, hwaddr addr, + unsigned size) +{ + AspeedRtcState *rtc = opaque; + uint64_t val; + uint32_t r = addr >> 2; + + switch (r) { + case COUNTER1: + case COUNTER2: + if (rtc->reg[CONTROL] & RTC_ENABLED) { + rtc->reg[r] = aspeed_rtc_get_counter(rtc, r); + } + /* fall through */ + case CONTROL: + val = rtc->reg[r]; + break; + case ALARM: + case ALARM_STATUS: + default: + qemu_log_mask(LOG_UNIMP, "%s: 0x%" HWADDR_PRIx "\n", __func__, addr); + return 0; + } + + trace_aspeed_rtc_read(addr, val); + + return val; +} + +static void aspeed_rtc_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + AspeedRtcState *rtc = opaque; + uint32_t r = addr >> 2; + + switch (r) { + case COUNTER1: + case COUNTER2: + if (!(rtc->reg[CONTROL] & RTC_UNLOCKED)) { + break; + } + /* fall through */ + case CONTROL: + rtc->reg[r] = val; + aspeed_rtc_calc_offset(rtc); + break; + case ALARM: + case ALARM_STATUS: + default: + qemu_log_mask(LOG_UNIMP, "%s: 0x%" HWADDR_PRIx "\n", __func__, addr); + break; + } + trace_aspeed_rtc_write(addr, val); +} + +static void aspeed_rtc_reset(DeviceState *d) +{ + AspeedRtcState *rtc = ASPEED_RTC(d); + + rtc->offset = 0; + memset(rtc->reg, 0, sizeof(rtc->reg)); +} + +static const MemoryRegionOps aspeed_rtc_ops = { + .read = aspeed_rtc_read, + .write = aspeed_rtc_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription vmstate_aspeed_rtc = { + .name = TYPE_ASPEED_RTC, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(reg, AspeedRtcState, 0x18), + VMSTATE_INT32(offset, AspeedRtcState), + VMSTATE_INT32(offset, AspeedRtcState), + VMSTATE_END_OF_LIST() + } +}; + +static void aspeed_rtc_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + AspeedRtcState *s = ASPEED_RTC(dev); + + sysbus_init_irq(sbd, &s->irq); + + memory_region_init_io(&s->iomem, OBJECT(s), &aspeed_rtc_ops, s, + "aspeed-rtc", 0x18ULL); + sysbus_init_mmio(sbd, &s->iomem); +} + +static void aspeed_rtc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = aspeed_rtc_realize; + dc->vmsd = &vmstate_aspeed_rtc; + dc->reset = aspeed_rtc_reset; +} + +static const TypeInfo aspeed_rtc_info = { + .name = TYPE_ASPEED_RTC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AspeedRtcState), + .class_init = aspeed_rtc_class_init, +}; + +static void aspeed_rtc_register_types(void) +{ + type_register_static(&aspeed_rtc_info); +} + +type_init(aspeed_rtc_register_types) diff --git a/hw/timer/trace-events b/hw/timer/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -XXX,XX +XXX,XX @@ cmsdk_apb_dualtimer_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK A cmsdk_apb_dualtimer_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB dualtimer write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" cmsdk_apb_dualtimer_reset(void) "CMSDK APB dualtimer: reset" +# hw/timer/aspeed-rtc.c +aspeed_rtc_read(uint64_t addr, uint64_t value) "addr 0x%02" PRIx64 " value 0x%08" PRIx64 +aspeed_rtc_write(uint64_t addr, uint64_t value) "addr 0x%02" PRIx64 " value 0x%08" PRIx64 + # sun4v-rtc.c sun4v_rtc_read(uint64_t addr, uint64_t value) "read: addr 0x%" PRIx64 " value 0x%" PRIx64 sun4v_rtc_write(uint64_t addr, uint64_t value) "write: addr 0x%" PRIx64 " value 0x%" PRIx64 -- 2.20.1 From: Joel Stanley <joel@jms.id.au> All systems have an RTC. The IRQ is hooked up but the model does not use it at this stage. There is no guest code that uses it, so this limitation is acceptable. Signed-off-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190618165311.27066-5-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed_soc.h | 2 ++ hw/arm/aspeed_soc.c | 13 +++++++++++++ 2 files changed, 15 insertions(+) diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/aspeed_scu.h" #include "hw/misc/aspeed_sdmc.h" #include "hw/timer/aspeed_timer.h" +#include "hw/timer/aspeed_rtc.h" #include "hw/i2c/aspeed_i2c.h" #include "hw/ssi/aspeed_smc.h" #include "hw/watchdog/wdt_aspeed.h" @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCState { ARMCPU cpu; MemoryRegion sram; AspeedVICState vic; + AspeedRtcState rtc; AspeedTimerCtrlState timerctrl; AspeedI2CState i2c; AspeedSCUState scu; diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) sysbus_init_child_obj(obj, "vic", OBJECT(&s->vic), sizeof(s->vic), TYPE_ASPEED_VIC); + sysbus_init_child_obj(obj, "rtc", OBJECT(&s->rtc), sizeof(s->rtc), + TYPE_ASPEED_RTC); + sysbus_init_child_obj(obj, "timerctrl", OBJECT(&s->timerctrl), sizeof(s->timerctrl), TYPE_ASPEED_TIMER); object_property_add_const_link(OBJECT(&s->timerctrl), "scu", @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->vic), 1, qdev_get_gpio_in(DEVICE(&s->cpu), ARM_CPU_FIQ)); + /* RTC */ + object_property_set_bool(OBJECT(&s->rtc), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->rtc), 0, sc->info->memmap[ASPEED_RTC]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->rtc), 0, + aspeed_soc_get_irq(s, ASPEED_RTC)); + /* Timer */ object_property_set_bool(OBJECT(&s->timerctrl), true, "realized", &err); if (err) { -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The current models of the Aspeed SoCs only have one CPU but future ones will support SMP. Introduce a new num_cpus field at the SoC class level to define the number of available CPUs per SoC and also introduce a 'num-cpus' property to activate the CPUs configured for the machine. The max_cpus limit of the machine should depend on the SoC definition but, unfortunately, these values are not available when the machine class is initialized. This is the reason why we add a check on num_cpus in the AspeedSoC realize handler. SMP support will be activated when models for such SoCs are implemented. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-6-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed_soc.h | 5 ++++- hw/arm/aspeed.c | 7 +++++-- hw/arm/aspeed_soc.c | 33 +++++++++++++++++++++++++++------ 3 files changed, 36 insertions(+), 9 deletions(-) diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ #define ASPEED_SPIS_NUM 2 #define ASPEED_WDTS_NUM 3 +#define ASPEED_CPUS_NUM 2 typedef struct AspeedSoCState { /*< private >*/ DeviceState parent; /*< public >*/ - ARMCPU cpu; + ARMCPU cpu[ASPEED_CPUS_NUM]; + uint32_t num_cpus; MemoryRegion sram; AspeedVICState vic; AspeedRtcState rtc; @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCInfo { int wdts_num; const int *irqmap; const hwaddr *memmap; + uint32_t num_cpus; } AspeedSoCInfo; typedef struct AspeedSoCClass { diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/tmp105.h" #include "qemu/log.h" #include "sysemu/block-backend.h" +#include "sysemu/sysemu.h" #include "hw/loader.h" #include "qemu/error-report.h" #include "qemu/units.h" static struct arm_boot_info aspeed_board_binfo = { .board_id = -1, /* device-tree-only board */ - .nb_cpus = 1, }; struct AspeedBoardState { @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, &error_abort); object_property_set_int(OBJECT(&bmc->soc), cfg->num_cs, "num-cs", &error_abort); + object_property_set_int(OBJECT(&bmc->soc), smp_cpus, "num-cpus", + &error_abort); if (machine->kernel_filename) { /* * When booting with a -kernel command line there is no u-boot @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, aspeed_board_binfo.kernel_cmdline = machine->kernel_cmdline; aspeed_board_binfo.ram_size = ram_size; aspeed_board_binfo.loader_start = sc->info->memmap[ASPEED_SDRAM]; + aspeed_board_binfo.nb_cpus = bmc->soc.num_cpus; if (cfg->i2c_init) { cfg->i2c_init(bmc); @@ -XXX,XX +XXX,XX @@ static void aspeed_machine_class_init(ObjectClass *oc, void *data) mc->desc = board->desc; mc->init = aspeed_machine_init; - mc->max_cpus = 1; + mc->max_cpus = ASPEED_CPUS_NUM; mc->no_sdcard = 1; mc->no_floppy = 1; mc->no_cdrom = 1; diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/serial.h" #include "qemu/log.h" #include "qemu/module.h" +#include "qemu/error-report.h" #include "hw/i2c/aspeed_i2c.h" #include "net/net.h" @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .wdts_num = 2, .irqmap = aspeed_soc_ast2400_irqmap, .memmap = aspeed_soc_ast2400_memmap, + .num_cpus = 1, }, { .name = "ast2400-a1", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .wdts_num = 2, .irqmap = aspeed_soc_ast2400_irqmap, .memmap = aspeed_soc_ast2400_memmap, + .num_cpus = 1, }, { .name = "ast2400", .cpu_type = ARM_CPU_TYPE_NAME("arm926"), @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .wdts_num = 2, .irqmap = aspeed_soc_ast2400_irqmap, .memmap = aspeed_soc_ast2400_memmap, + .num_cpus = 1, }, { .name = "ast2500-a1", .cpu_type = ARM_CPU_TYPE_NAME("arm1176"), @@ -XXX,XX +XXX,XX @@ static const AspeedSoCInfo aspeed_socs[] = { .wdts_num = 3, .irqmap = aspeed_soc_ast2500_irqmap, .memmap = aspeed_soc_ast2500_memmap, + .num_cpus = 1, }, }; @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) AspeedSoCClass *sc = ASPEED_SOC_GET_CLASS(s); int i; - object_initialize_child(obj, "cpu", OBJECT(&s->cpu), sizeof(s->cpu), - sc->info->cpu_type, &error_abort, NULL); + for (i = 0; i < sc->info->num_cpus; i++) { + object_initialize_child(obj, "cpu[*]", OBJECT(&s->cpu[i]), + sizeof(s->cpu[i]), sc->info->cpu_type, + &error_abort, NULL); + } sysbus_init_child_obj(obj, "scu", OBJECT(&s->scu), sizeof(s->scu), TYPE_ASPEED_SCU); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) create_unimplemented_device("aspeed_soc.io", sc->info->memmap[ASPEED_IOMEM], ASPEED_SOC_IOMEM_SIZE); + if (s->num_cpus > sc->info->num_cpus) { + warn_report("%s: invalid number of CPUs %d, using default %d", + sc->info->name, s->num_cpus, sc->info->num_cpus); + s->num_cpus = sc->info->num_cpus; + } + /* CPU */ - object_property_set_bool(OBJECT(&s->cpu), true, "realized", &err); - if (err) { - error_propagate(errp, err); - return; + for (i = 0; i < s->num_cpus; i++) { + object_property_set_bool(OBJECT(&s->cpu[i]), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } } /* SRAM */ @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->ftgmac100), 0, aspeed_soc_get_irq(s, ASPEED_ETH1)); } +static Property aspeed_soc_properties[] = { + DEFINE_PROP_UINT32("num-cpus", AspeedSoCState, num_cpus, 0), + DEFINE_PROP_END_OF_LIST(), +}; static void aspeed_soc_class_init(ObjectClass *oc, void *data) { @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_class_init(ObjectClass *oc, void *data) dc->realize = aspeed_soc_realize; /* Reason: Uses serial_hds and nd_table in realize() directly */ dc->user_creatable = false; + dc->props = aspeed_soc_properties; } static const TypeInfo aspeed_soc_type_info = { -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The Aspeed SoCs have two MACs. Extend the Aspeed model to support a second NIC. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-7-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed_soc.h | 3 ++- hw/arm/aspeed_soc.c | 33 +++++++++++++++++++-------------- 2 files changed, 21 insertions(+), 15 deletions(-) diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ #define ASPEED_SPIS_NUM 2 #define ASPEED_WDTS_NUM 3 #define ASPEED_CPUS_NUM 2 +#define ASPEED_MACS_NUM 2 typedef struct AspeedSoCState { /*< private >*/ @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCState { AspeedSMCState spi[ASPEED_SPIS_NUM]; AspeedSDMCState sdmc; AspeedWDTState wdt[ASPEED_WDTS_NUM]; - FTGMAC100State ftgmac100; + FTGMAC100State ftgmac100[ASPEED_MACS_NUM]; } AspeedSoCState; #define TYPE_ASPEED_SOC "aspeed-soc" diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) sc->info->silicon_rev); } - sysbus_init_child_obj(obj, "ftgmac100", OBJECT(&s->ftgmac100), - sizeof(s->ftgmac100), TYPE_FTGMAC100); + for (i = 0; i < ASPEED_MACS_NUM; i++) { + sysbus_init_child_obj(obj, "ftgmac100[*]", OBJECT(&s->ftgmac100[i]), + sizeof(s->ftgmac100[i]), TYPE_FTGMAC100); + } } static void aspeed_soc_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) } /* Net */ - qdev_set_nic_properties(DEVICE(&s->ftgmac100), &nd_table[0]); - object_property_set_bool(OBJECT(&s->ftgmac100), true, "aspeed", &err); - object_property_set_bool(OBJECT(&s->ftgmac100), true, "realized", - &local_err); - error_propagate(&err, local_err); - if (err) { - error_propagate(errp, err); - return; + for (i = 0; i < nb_nics; i++) { + qdev_set_nic_properties(DEVICE(&s->ftgmac100[i]), &nd_table[i]); + object_property_set_bool(OBJECT(&s->ftgmac100[i]), true, "aspeed", + &err); + object_property_set_bool(OBJECT(&s->ftgmac100[i]), true, "realized", + &local_err); + error_propagate(&err, local_err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ftgmac100[i]), 0, + sc->info->memmap[ASPEED_ETH1 + i]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->ftgmac100[i]), 0, + aspeed_soc_get_irq(s, ASPEED_ETH1 + i)); } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->ftgmac100), 0, - sc->info->memmap[ASPEED_ETH1]); - sysbus_connect_irq(SYS_BUS_DEVICE(&s->ftgmac100), 0, - aspeed_soc_get_irq(s, ASPEED_ETH1)); } static Property aspeed_soc_properties[] = { DEFINE_PROP_UINT32("num-cpus", AspeedSoCState, num_cpus, 0), -- 2.20.1 From: Joel Stanley <joel@jms.id.au> The Linux kernel driver was updated in commit 4451d3f59f2a ("clocksource/drivers/fttmr010: Fix set_next_event handler) to fix an issue observed on hardware: > RELOAD register is loaded into COUNT register when the aspeed timer > is enabled, which means the next event may be delayed because timer > interrupt won't be generated until <0xFFFFFFFF - current_count + > cycles>. When running under Qemu, the system appeared "laggy". The guest is now scheduling timer events too regularly, starving the host of CPU time. This patch modifies the timer model to attempt to schedule the timer expiry as the guest requests, but if we have missed the deadline we re interrupt and try again, which allows the guest to catch up. Provides expected behaviour with old and new guest code. Fixes: c04bd47db6b9 ("hw/timer: Add ASPEED timer device model") Signed-off-by: Joel Stanley <joel@jms.id.au> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 20190618165311.27066-8-clg@kaod.org [clg: - merged a fix from Andrew Jeffery <andrew@aj.id.au> "Fire interrupt on failure to meet deadline" https://lists.ozlabs.org/pipermail/openbmc/2019-January/014641.html - adapted commit log - checkpatch fixes ] Signed-off-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/aspeed_timer.c | 57 ++++++++++++++++++++++------------------- 1 file changed, 30 insertions(+), 27 deletions(-) diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/aspeed_timer.c +++ b/hw/timer/aspeed_timer.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t calculate_time(struct AspeedTimer *t, uint32_t ticks) static uint64_t calculate_next(struct AspeedTimer *t) { - uint64_t next = 0; - uint32_t rate = calculate_rate(t); + uint64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + uint64_t next; - while (!next) { - /* We don't know the relationship between the values in the match - * registers, so sort using MAX/MIN/zero. We sort in that order as the - * timer counts down to zero. */ - uint64_t seq[] = { - calculate_time(t, MAX(t->match[0], t->match[1])), - calculate_time(t, MIN(t->match[0], t->match[1])), - calculate_time(t, 0), - }; - uint64_t reload_ns; - uint64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + /* + * We don't know the relationship between the values in the match + * registers, so sort using MAX/MIN/zero. We sort in that order as + * the timer counts down to zero. + */ - if (now < seq[0]) { - next = seq[0]; - } else if (now < seq[1]) { - next = seq[1]; - } else if (now < seq[2]) { - next = seq[2]; - } else if (t->reload) { - reload_ns = muldiv64(t->reload, NANOSECONDS_PER_SECOND, rate); - t->start = now - ((now - t->start) % reload_ns); - } else { - /* no reload value, return 0 */ - break; - } + next = calculate_time(t, MAX(t->match[0], t->match[1])); + if (now < next) { + return next; } - return next; + next = calculate_time(t, MIN(t->match[0], t->match[1])); + if (now < next) { + return next; + } + + next = calculate_time(t, 0); + if (now < next) { + return next; + } + + /* We've missed all deadlines, fire interrupt and try again */ + timer_del(&t->timer); + + if (timer_overflow_interrupt(t)) { + t->level = !t->level; + qemu_set_irq(t->irq, t->level); + } + + t->start = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + return calculate_time(t, MAX(MAX(t->match[0], t->match[1]), 0)); } static void aspeed_timer_mod(AspeedTimer *t) -- 2.20.1 From: Andrew Jeffery <andrew@aj.id.au> From the datasheet: This register stores the current status of counter #N. When timer enable bit TMC30[N * b] is disabled, the reload register will be loaded into this counter. When timer bit TMC30[N * b] is set, the counter will start to decrement. CPU can update this register value when enable bit is set. Signed-off-by: Andrew Jeffery <andrew@aj.id.au> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-9-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/aspeed_timer.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/aspeed_timer.c +++ b/hw/timer/aspeed_timer.c @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_timer_get_value(AspeedTimer *t, int reg) switch (reg) { case TIMER_REG_STATUS: - value = calculate_ticks(t, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)); + if (timer_enabled(t)) { + value = calculate_ticks(t, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)); + } else { + value = t->reload; + } break; case TIMER_REG_RELOAD: value = t->reload; -- 2.20.1 From: Andrew Jeffery <andrew@aj.id.au> If the match value exceeds reload then we don't want to include it in calculations for the next event. Signed-off-by: Andrew Jeffery <andrew@aj.id.au> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 20190618165311.27066-10-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/aspeed_timer.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/aspeed_timer.c +++ b/hw/timer/aspeed_timer.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t calculate_time(struct AspeedTimer *t, uint32_t ticks) return t->start + delta_ns; } +static inline uint32_t calculate_match(struct AspeedTimer *t, int i) +{ + return t->match[i] < t->reload ? t->match[i] : 0; +} + static uint64_t calculate_next(struct AspeedTimer *t) { uint64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); @@ -XXX,XX +XXX,XX @@ static uint64_t calculate_next(struct AspeedTimer *t) * the timer counts down to zero. */ - next = calculate_time(t, MAX(t->match[0], t->match[1])); + next = calculate_time(t, MAX(calculate_match(t, 0), calculate_match(t, 1))); if (now < next) { return next; } - next = calculate_time(t, MIN(t->match[0], t->match[1])); + next = calculate_time(t, MIN(calculate_match(t, 0), calculate_match(t, 1))); if (now < next) { return next; } @@ -XXX,XX +XXX,XX @@ static uint64_t calculate_next(struct AspeedTimer *t) qemu_set_irq(t->irq, t->level); } + next = MAX(MAX(calculate_match(t, 0), calculate_match(t, 1)), 0); t->start = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - return calculate_time(t, MAX(MAX(t->match[0], t->match[1]), 0)); + + return calculate_time(t, next); } static void aspeed_timer_mod(AspeedTimer *t) -- 2.20.1 From: Christian Svensson <bluecmd@google.com> If the host decrements the counter register that results in a negative delta. This is then passed to muldiv64 which only handles unsigned numbers resulting in bogus results. This fix ensures the delta being operated on is positive. Test case: kexec a kernel using aspeed_timer and it will freeze on the second bootup when the kernel initializes the timer. With this patch that no longer happens and the timer appears to run OK. Signed-off-by: Christian Svensson <bluecmd@google.com> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20190618165311.27066-12-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/aspeed_timer.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/aspeed_timer.c +++ b/hw/timer/aspeed_timer.c @@ -XXX,XX +XXX,XX @@ static void aspeed_timer_set_value(AspeedTimerCtrlState *s, int timer, int reg, int64_t delta = (int64_t) value - (int64_t) calculate_ticks(t, now); uint32_t rate = calculate_rate(t); - t->start += muldiv64(delta, NANOSECONDS_PER_SECOND, rate); + if (delta >= 0) { + t->start += muldiv64(delta, NANOSECONDS_PER_SECOND, rate); + } else { + t->start -= muldiv64(-delta, NANOSECONDS_PER_SECOND, rate); + } aspeed_timer_mod(t); } break; -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> It has never been used as far as I can tell from the git history. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-13-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, memory_region_allocate_system_memory(&bmc->ram, NULL, "ram", ram_size); memory_region_add_subregion(get_system_memory(), sc->info->memmap[ASPEED_SDRAM], &bmc->ram); - object_property_add_const_link(OBJECT(&bmc->soc), "ram", OBJECT(&bmc->ram), - &error_abort); max_ram_size = object_property_get_uint(OBJECT(&bmc->soc), "max-ram-size", &error_abort); -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The RAM memory region is defined after the SoC is realized when the SDMC controller has checked that the defined RAM size for the machine is correct. This is problematic for controller models requiring a link on the RAM region, for DMA support in the SMC controller for instance. Introduce a container memory region for the RAM that we can link into the controllers early, before the SoC is realized. It will be populated with the RAM region after the checks have be done. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-14-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info aspeed_board_binfo = { struct AspeedBoardState { AspeedSoCState soc; + MemoryRegion ram_container; MemoryRegion ram; MemoryRegion max_ram; }; @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, ram_addr_t max_ram_size; bmc = g_new0(AspeedBoardState, 1); + + memory_region_init(&bmc->ram_container, NULL, "aspeed-ram-container", + UINT32_MAX); + object_initialize_child(OBJECT(machine), "soc", &bmc->soc, (sizeof(bmc->soc)), cfg->soc_name, &error_abort, NULL); @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, &error_abort); memory_region_allocate_system_memory(&bmc->ram, NULL, "ram", ram_size); + memory_region_add_subregion(&bmc->ram_container, 0, &bmc->ram); memory_region_add_subregion(get_system_memory(), - sc->info->memmap[ASPEED_SDRAM], &bmc->ram); + sc->info->memmap[ASPEED_SDRAM], + &bmc->ram_container); max_ram_size = object_property_get_uint(OBJECT(&bmc->soc), "max-ram-size", &error_abort); memory_region_init_io(&bmc->max_ram, NULL, &max_ram_ops, NULL, "max_ram", max_ram_size - ram_size); - memory_region_add_subregion(get_system_memory(), - sc->info->memmap[ASPEED_SDRAM] + ram_size, - &bmc->max_ram); + memory_region_add_subregion(&bmc->ram_container, ram_size, &bmc->max_ram); aspeed_board_init_flashes(&bmc->soc.fmc, cfg->fmc_model, &error_abort); aspeed_board_init_flashes(&bmc->soc.spi[0], cfg->spi_model, &error_abort); -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The DRAM address of a DMA transaction depends on the DRAM base address of the SoC. Inform the SMC controller model with this value. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190618165311.27066-15-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/ssi/aspeed_smc.h | 3 +++ hw/arm/aspeed_soc.c | 6 ++++++ hw/ssi/aspeed_smc.c | 1 + 3 files changed, 10 insertions(+) diff --git a/include/hw/ssi/aspeed_smc.h b/include/hw/ssi/aspeed_smc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/ssi/aspeed_smc.h +++ b/include/hw/ssi/aspeed_smc.h @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSMCState { uint8_t r_timings; uint8_t conf_enable_w0; + /* for DMA support */ + uint64_t sdram_base; + AspeedSMCFlash *flashes; uint8_t snoop_index; diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) aspeed_soc_get_irq(s, ASPEED_I2C)); /* FMC, The number of CS is set at the board level */ + object_property_set_int(OBJECT(&s->fmc), sc->info->memmap[ASPEED_SDRAM], + "sdram-base", &err); + if (err) { + error_propagate(errp, err); + return; + } object_property_set_bool(OBJECT(&s->fmc), true, "realized", &err); if (err) { error_propagate(errp, err); diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_aspeed_smc = { static Property aspeed_smc_properties[] = { DEFINE_PROP_UINT32("num-cs", AspeedSMCState, num_cs, 1), + DEFINE_PROP_UINT64("sdram-base", AspeedSMCState, sdram_base, 0), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Adriana Kobylak <anoo@us.ibm.com> The Swift board is an OpenPOWER system hosting POWER processors. Add support for their BMC including the I2C devices as found on HW. Signed-off-by: Adriana Kobylak <anoo@us.ibm.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-20-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ struct AspeedBoardState { SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) +/* Swift hardware value: 0xF11AD206 */ +#define SWIFT_BMC_HW_STRAP1 ( \ + AST2500_HW_STRAP1_DEFAULTS | \ + SCU_AST2500_HW_STRAP_SPI_AUTOFETCH_ENABLE | \ + SCU_AST2500_HW_STRAP_GPIO_STRAP_ENABLE | \ + SCU_AST2500_HW_STRAP_UART_DEBUG | \ + SCU_AST2500_HW_STRAP_DDR4_ENABLE | \ + SCU_H_PLL_BYPASS_EN | \ + SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ + SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) + /* Witherspoon hardware value: 0xF10AD216 (but use romulus definition) */ #define WITHERSPOON_BMC_HW_STRAP1 ROMULUS_BMC_HW_STRAP1 @@ -XXX,XX +XXX,XX @@ static void romulus_bmc_i2c_init(AspeedBoardState *bmc) i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 11), "ds1338", 0x32); } +static void swift_bmc_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 3), "pca9552", 0x60); + + /* The swift board expects a TMP275 but a TMP105 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 7), "tmp105", 0x48); + /* The swift board expects a pca9551 but a pca9552 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 7), "pca9552", 0x60); + + /* The swift board expects an Epson RX8900 RTC but a ds1338 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 8), "ds1338", 0x32); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 8), "pca9552", 0x60); + + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 9), "tmp423", 0x4c); + /* The swift board expects a pca9539 but a pca9552 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 9), "pca9552", 0x74); + + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 10), "tmp423", 0x4c); + /* The swift board expects a pca9539 but a pca9552 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 10), "pca9552", + 0x74); + + /* The swift board expects a TMP275 but a TMP105 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 12), "tmp105", 0x48); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 12), "tmp105", 0x4a); +} + static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .num_cs = 2, .i2c_init = romulus_bmc_i2c_init, .ram = 512 * MiB, + }, { + .name = MACHINE_TYPE_NAME("swift-bmc"), + .desc = "OpenPOWER Swift BMC (ARM1176)", + .soc_name = "ast2500-a1", + .hw_strap1 = SWIFT_BMC_HW_STRAP1, + .fmc_model = "mx66l1g45g", + .spi_model = "mx66l1g45g", + .num_cs = 2, + .i2c_init = swift_bmc_i2c_init, + .ram = 512 * MiB, }, { .name = MACHINE_TYPE_NAME("witherspoon-bmc"), .desc = "OpenPOWER Witherspoon BMC (ARM1176)", -- 2.20.1 From: Eddie James <eajames@linux.ibm.com> The XDMA engine embedded in the Aspeed SOCs performs PCI DMA operations between the SOC (acting as a BMC) and a host processor in a server. The XDMA engine exists on the AST2400, AST2500, and AST2600 SOCs, so enable it for all of those. Add trace events on the important register writes in the XDMA engine. Signed-off-by: Eddie James <eajames@linux.ibm.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 20190618165311.27066-21-clg@kaod.org [clg: - changed title ] Signed-off-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/aspeed_soc.h | 3 + include/hw/misc/aspeed_xdma.h | 30 +++++++ hw/arm/aspeed_soc.c | 17 ++++ hw/misc/aspeed_xdma.c | 165 ++++++++++++++++++++++++++++++++++ hw/misc/trace-events | 3 + 6 files changed, 219 insertions(+) create mode 100644 include/hw/misc/aspeed_xdma.h create mode 100644 hw/misc/aspeed_xdma.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_ARMSSE_MHU) += armsse-mhu.o obj-$(CONFIG_PVPANIC) += pvpanic.o obj-$(CONFIG_AUX) += auxbus.o +obj-$(CONFIG_ASPEED_SOC) += aspeed_xdma.o obj-$(CONFIG_ASPEED_SOC) += aspeed_scu.o aspeed_sdmc.o obj-$(CONFIG_MSF2) += msf2-sysreg.o obj-$(CONFIG_NRF51_SOC) += nrf51_rng.o diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/aspeed_vic.h" #include "hw/misc/aspeed_scu.h" #include "hw/misc/aspeed_sdmc.h" +#include "hw/misc/aspeed_xdma.h" #include "hw/timer/aspeed_timer.h" #include "hw/timer/aspeed_rtc.h" #include "hw/i2c/aspeed_i2c.h" @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCState { AspeedTimerCtrlState timerctrl; AspeedI2CState i2c; AspeedSCUState scu; + AspeedXDMAState xdma; AspeedSMCState fmc; AspeedSMCState spi[ASPEED_SPIS_NUM]; AspeedSDMCState sdmc; @@ -XXX,XX +XXX,XX @@ enum { ASPEED_ETH1, ASPEED_ETH2, ASPEED_SDRAM, + ASPEED_XDMA, }; #endif /* ASPEED_SOC_H */ diff --git a/include/hw/misc/aspeed_xdma.h b/include/hw/misc/aspeed_xdma.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/aspeed_xdma.h @@ -XXX,XX +XXX,XX @@ +/* + * ASPEED XDMA Controller + * Eddie James <eajames@linux.ibm.com> + * + * Copyright (C) 2019 IBM Corp. + * SPDX-License-Identifer: GPL-2.0-or-later + */ + +#ifndef ASPEED_XDMA_H +#define ASPEED_XDMA_H + +#include "hw/sysbus.h" + +#define TYPE_ASPEED_XDMA "aspeed.xdma" +#define ASPEED_XDMA(obj) OBJECT_CHECK(AspeedXDMAState, (obj), TYPE_ASPEED_XDMA) + +#define ASPEED_XDMA_NUM_REGS (ASPEED_XDMA_REG_SIZE / sizeof(uint32_t)) +#define ASPEED_XDMA_REG_SIZE 0x7C + +typedef struct AspeedXDMAState { + SysBusDevice parent; + + MemoryRegion iomem; + qemu_irq irq; + + char bmc_cmdq_readp_set; + uint32_t regs[ASPEED_XDMA_NUM_REGS]; +} AspeedXDMAState; + +#endif /* ASPEED_XDMA_H */ diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static const hwaddr aspeed_soc_ast2400_memmap[] = { [ASPEED_VIC] = 0x1E6C0000, [ASPEED_SDMC] = 0x1E6E0000, [ASPEED_SCU] = 0x1E6E2000, + [ASPEED_XDMA] = 0x1E6E7000, [ASPEED_ADC] = 0x1E6E9000, [ASPEED_SRAM] = 0x1E720000, [ASPEED_GPIO] = 0x1E780000, @@ -XXX,XX +XXX,XX @@ static const hwaddr aspeed_soc_ast2500_memmap[] = { [ASPEED_VIC] = 0x1E6C0000, [ASPEED_SDMC] = 0x1E6E0000, [ASPEED_SCU] = 0x1E6E2000, + [ASPEED_XDMA] = 0x1E6E7000, [ASPEED_ADC] = 0x1E6E9000, [ASPEED_SRAM] = 0x1E720000, [ASPEED_GPIO] = 0x1E780000, @@ -XXX,XX +XXX,XX @@ static const int aspeed_soc_ast2400_irqmap[] = { [ASPEED_I2C] = 12, [ASPEED_ETH1] = 2, [ASPEED_ETH2] = 3, + [ASPEED_XDMA] = 6, }; #define aspeed_soc_ast2500_irqmap aspeed_soc_ast2400_irqmap @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) sysbus_init_child_obj(obj, "ftgmac100[*]", OBJECT(&s->ftgmac100[i]), sizeof(s->ftgmac100[i]), TYPE_FTGMAC100); } + + sysbus_init_child_obj(obj, "xdma", OBJECT(&s->xdma), sizeof(s->xdma), + TYPE_ASPEED_XDMA); } static void aspeed_soc_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->ftgmac100[i]), 0, aspeed_soc_get_irq(s, ASPEED_ETH1 + i)); } + + /* XDMA */ + object_property_set_bool(OBJECT(&s->xdma), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->xdma), 0, + sc->info->memmap[ASPEED_XDMA]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->xdma), 0, + aspeed_soc_get_irq(s, ASPEED_XDMA)); } static Property aspeed_soc_properties[] = { DEFINE_PROP_UINT32("num-cpus", AspeedSoCState, num_cpus, 0), diff --git a/hw/misc/aspeed_xdma.c b/hw/misc/aspeed_xdma.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/aspeed_xdma.c @@ -XXX,XX +XXX,XX @@ +/* + * ASPEED XDMA Controller + * Eddie James <eajames@linux.ibm.com> + * + * Copyright (C) 2019 IBM Corp + * SPDX-License-Identifer: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "hw/misc/aspeed_xdma.h" +#include "qapi/error.h" + +#include "trace.h" + +#define XDMA_BMC_CMDQ_ADDR 0x10 +#define XDMA_BMC_CMDQ_ENDP 0x14 +#define XDMA_BMC_CMDQ_WRP 0x18 +#define XDMA_BMC_CMDQ_W_MASK 0x0003FFFF +#define XDMA_BMC_CMDQ_RDP 0x1C +#define XDMA_BMC_CMDQ_RDP_MAGIC 0xEE882266 +#define XDMA_IRQ_ENG_CTRL 0x20 +#define XDMA_IRQ_ENG_CTRL_US_COMP BIT(4) +#define XDMA_IRQ_ENG_CTRL_DS_COMP BIT(5) +#define XDMA_IRQ_ENG_CTRL_W_MASK 0xBFEFF07F +#define XDMA_IRQ_ENG_STAT 0x24 +#define XDMA_IRQ_ENG_STAT_US_COMP BIT(4) +#define XDMA_IRQ_ENG_STAT_DS_COMP BIT(5) +#define XDMA_IRQ_ENG_STAT_RESET 0xF8000000 +#define XDMA_MEM_SIZE 0x1000 + +#define TO_REG(addr) ((addr) / sizeof(uint32_t)) + +static uint64_t aspeed_xdma_read(void *opaque, hwaddr addr, unsigned int size) +{ + uint32_t val = 0; + AspeedXDMAState *xdma = opaque; + + if (addr < ASPEED_XDMA_REG_SIZE) { + val = xdma->regs[TO_REG(addr)]; + } + + return (uint64_t)val; +} + +static void aspeed_xdma_write(void *opaque, hwaddr addr, uint64_t val, + unsigned int size) +{ + unsigned int idx; + uint32_t val32 = (uint32_t)val; + AspeedXDMAState *xdma = opaque; + + if (addr >= ASPEED_XDMA_REG_SIZE) { + return; + } + + switch (addr) { + case XDMA_BMC_CMDQ_ENDP: + xdma->regs[TO_REG(addr)] = val32 & XDMA_BMC_CMDQ_W_MASK; + break; + case XDMA_BMC_CMDQ_WRP: + idx = TO_REG(addr); + xdma->regs[idx] = val32 & XDMA_BMC_CMDQ_W_MASK; + xdma->regs[TO_REG(XDMA_BMC_CMDQ_RDP)] = xdma->regs[idx]; + + trace_aspeed_xdma_write(addr, val); + + if (xdma->bmc_cmdq_readp_set) { + xdma->bmc_cmdq_readp_set = 0; + } else { + xdma->regs[TO_REG(XDMA_IRQ_ENG_STAT)] |= + XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP; + + if (xdma->regs[TO_REG(XDMA_IRQ_ENG_CTRL)] & + (XDMA_IRQ_ENG_CTRL_US_COMP | XDMA_IRQ_ENG_CTRL_DS_COMP)) + qemu_irq_raise(xdma->irq); + } + break; + case XDMA_BMC_CMDQ_RDP: + trace_aspeed_xdma_write(addr, val); + + if (val32 == XDMA_BMC_CMDQ_RDP_MAGIC) { + xdma->bmc_cmdq_readp_set = 1; + } + break; + case XDMA_IRQ_ENG_CTRL: + xdma->regs[TO_REG(addr)] = val32 & XDMA_IRQ_ENG_CTRL_W_MASK; + break; + case XDMA_IRQ_ENG_STAT: + trace_aspeed_xdma_write(addr, val); + + idx = TO_REG(addr); + if (val32 & (XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP)) { + xdma->regs[idx] &= + ~(XDMA_IRQ_ENG_STAT_US_COMP | XDMA_IRQ_ENG_STAT_DS_COMP); + qemu_irq_lower(xdma->irq); + } + break; + default: + xdma->regs[TO_REG(addr)] = val32; + break; + } +} + +static const MemoryRegionOps aspeed_xdma_ops = { + .read = aspeed_xdma_read, + .write = aspeed_xdma_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 4, + .valid.max_access_size = 4, +}; + +static void aspeed_xdma_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + AspeedXDMAState *xdma = ASPEED_XDMA(dev); + + sysbus_init_irq(sbd, &xdma->irq); + memory_region_init_io(&xdma->iomem, OBJECT(xdma), &aspeed_xdma_ops, xdma, + TYPE_ASPEED_XDMA, XDMA_MEM_SIZE); + sysbus_init_mmio(sbd, &xdma->iomem); +} + +static void aspeed_xdma_reset(DeviceState *dev) +{ + AspeedXDMAState *xdma = ASPEED_XDMA(dev); + + xdma->bmc_cmdq_readp_set = 0; + memset(xdma->regs, 0, ASPEED_XDMA_REG_SIZE); + xdma->regs[TO_REG(XDMA_IRQ_ENG_STAT)] = XDMA_IRQ_ENG_STAT_RESET; + + qemu_irq_lower(xdma->irq); +} + +static const VMStateDescription aspeed_xdma_vmstate = { + .name = TYPE_ASPEED_XDMA, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AspeedXDMAState, ASPEED_XDMA_NUM_REGS), + VMSTATE_END_OF_LIST(), + }, +}; + +static void aspeed_xdma_class_init(ObjectClass *classp, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(classp); + + dc->realize = aspeed_xdma_realize; + dc->reset = aspeed_xdma_reset; + dc->vmsd = &aspeed_xdma_vmstate; +} + +static const TypeInfo aspeed_xdma_info = { + .name = TYPE_ASPEED_XDMA, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AspeedXDMAState), + .class_init = aspeed_xdma_class_init, +}; + +static void aspeed_xdma_register_type(void) +{ + type_register_static(&aspeed_xdma_info); +} +type_init(aspeed_xdma_register_type); diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ armsse_cpuid_write(uint64_t offset, uint64_t data, unsigned size) "SSE-200 CPU_I # armsse-mhu.c armsse_mhu_read(uint64_t offset, uint64_t data, unsigned size) "SSE-200 MHU read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" armsse_mhu_write(uint64_t offset, uint64_t data, unsigned size) "SSE-200 MHU write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" + +# aspeed_xdma.c +aspeed_xdma_write(uint64_t offset, uint64_t data) "XDMA write: offset 0x%" PRIx64 " data 0x%" PRIx64 -- 2.20.1 From: Andrew Jeffery <andrew@aj.id.au> The legacy interface only supported up to 32 IRQs, which became restrictive around the AST2400 generation. QEMU support for the SoCs started with the AST2400 along with an effort to reimplement and upstream drivers for Linux, so up until this point the consumers of the QEMU ASPEED support only required the 64 IRQ register interface. In an effort to support older BMC firmware, add support for the 32 IRQ interface. Signed-off-by: Andrew Jeffery <andrew@aj.id.au> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190618165311.27066-22-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/aspeed_vic.c | 105 ++++++++++++++++++++++++++----------------- 1 file changed, 63 insertions(+), 42 deletions(-) diff --git a/hw/intc/aspeed_vic.c b/hw/intc/aspeed_vic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/aspeed_vic.c +++ b/hw/intc/aspeed_vic.c @@ -XXX,XX +XXX,XX @@ static void aspeed_vic_set_irq(void *opaque, int irq, int level) static uint64_t aspeed_vic_read(void *opaque, hwaddr offset, unsigned size) { - uint64_t val; - const bool high = !!(offset & 0x4); - hwaddr n_offset = (offset & ~0x4); AspeedVICState *s = (AspeedVICState *)opaque; + hwaddr n_offset; + uint64_t val; + bool high; if (offset < AVIC_NEW_BASE_OFFSET) { - qemu_log_mask(LOG_UNIMP, "%s: Ignoring read from legacy registers " - "at 0x%" HWADDR_PRIx "[%u]\n", __func__, offset, size); - return 0; + high = false; + n_offset = offset; + } else { + high = !!(offset & 0x4); + n_offset = (offset & ~0x4); } - n_offset -= AVIC_NEW_BASE_OFFSET; - switch (n_offset) { - case 0x0: /* IRQ Status */ + case 0x80: /* IRQ Status */ + case 0x00: val = s->raw & ~s->select & s->enable; break; - case 0x08: /* FIQ Status */ + case 0x88: /* FIQ Status */ + case 0x04: val = s->raw & s->select & s->enable; break; - case 0x10: /* Raw Interrupt Status */ + case 0x90: /* Raw Interrupt Status */ + case 0x08: val = s->raw; break; - case 0x18: /* Interrupt Selection */ + case 0x98: /* Interrupt Selection */ + case 0x0c: val = s->select; break; - case 0x20: /* Interrupt Enable */ + case 0xa0: /* Interrupt Enable */ + case 0x10: val = s->enable; break; - case 0x30: /* Software Interrupt */ + case 0xb0: /* Software Interrupt */ + case 0x18: val = s->trigger; break; - case 0x40: /* Interrupt Sensitivity */ + case 0xc0: /* Interrupt Sensitivity */ + case 0x24: val = s->sense; break; - case 0x48: /* Interrupt Both Edge Trigger Control */ + case 0xc8: /* Interrupt Both Edge Trigger Control */ + case 0x28: val = s->dual_edge; break; - case 0x50: /* Interrupt Event */ + case 0xd0: /* Interrupt Event */ + case 0x2c: val = s->event; break; - case 0x60: /* Edge Triggered Interrupt Status */ + case 0xe0: /* Edge Triggered Interrupt Status */ val = s->raw & ~s->sense; break; /* Illegal */ - case 0x28: /* Interrupt Enable Clear */ - case 0x38: /* Software Interrupt Clear */ - case 0x58: /* Edge Triggered Interrupt Clear */ + case 0xa8: /* Interrupt Enable Clear */ + case 0xb8: /* Software Interrupt Clear */ + case 0xd8: /* Edge Triggered Interrupt Clear */ qemu_log_mask(LOG_GUEST_ERROR, "%s: Read of write-only register with offset 0x%" HWADDR_PRIx "\n", __func__, offset); @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_vic_read(void *opaque, hwaddr offset, unsigned size) } if (high) { val = extract64(val, 32, 19); + } else { + val = extract64(val, 0, 32); } trace_aspeed_vic_read(offset, size, val); return val; @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_vic_read(void *opaque, hwaddr offset, unsigned size) static void aspeed_vic_write(void *opaque, hwaddr offset, uint64_t data, unsigned size) { - const bool high = !!(offset & 0x4); - hwaddr n_offset = (offset & ~0x4); AspeedVICState *s = (AspeedVICState *)opaque; + hwaddr n_offset; + bool high; if (offset < AVIC_NEW_BASE_OFFSET) { - qemu_log_mask(LOG_UNIMP, - "%s: Ignoring write to legacy registers at 0x%" - HWADDR_PRIx "[%u] <- 0x%" PRIx64 "\n", __func__, offset, - size, data); - return; + high = false; + n_offset = offset; + } else { + high = !!(offset & 0x4); + n_offset = (offset & ~0x4); } - n_offset -= AVIC_NEW_BASE_OFFSET; trace_aspeed_vic_write(offset, size, data); /* Given we have members using separate enable/clear registers, deposit64() @@ -XXX,XX +XXX,XX @@ static void aspeed_vic_write(void *opaque, hwaddr offset, uint64_t data, } switch (n_offset) { - case 0x18: /* Interrupt Selection */ + case 0x98: /* Interrupt Selection */ + case 0x0c: /* Register has deposit64() semantics - overwrite requested 32 bits */ if (high) { s->select &= AVIC_L_MASK; @@ -XXX,XX +XXX,XX @@ static void aspeed_vic_write(void *opaque, hwaddr offset, uint64_t data, } s->select |= data; break; - case 0x20: /* Interrupt Enable */ + case 0xa0: /* Interrupt Enable */ + case 0x10: s->enable |= data; break; - case 0x28: /* Interrupt Enable Clear */ + case 0xa8: /* Interrupt Enable Clear */ + case 0x14: s->enable &= ~data; break; - case 0x30: /* Software Interrupt */ + case 0xb0: /* Software Interrupt */ + case 0x18: qemu_log_mask(LOG_UNIMP, "%s: Software interrupts unavailable. " "IRQs requested: 0x%016" PRIx64 "\n", __func__, data); break; - case 0x38: /* Software Interrupt Clear */ + case 0xb8: /* Software Interrupt Clear */ + case 0x1c: qemu_log_mask(LOG_UNIMP, "%s: Software interrupts unavailable. " "IRQs to be cleared: 0x%016" PRIx64 "\n", __func__, data); break; - case 0x50: /* Interrupt Event */ + case 0xd0: /* Interrupt Event */ /* Register has deposit64() semantics - overwrite the top four valid * IRQ bits, as only the top four IRQs (GPIOs) can change their event * type */ @@ -XXX,XX +XXX,XX @@ static void aspeed_vic_write(void *opaque, hwaddr offset, uint64_t data, "Ignoring invalid write to interrupt event register"); } break; - case 0x58: /* Edge Triggered Interrupt Clear */ + case 0xd8: /* Edge Triggered Interrupt Clear */ + case 0x38: s->raw &= ~(data & ~s->sense); break; - case 0x00: /* IRQ Status */ - case 0x08: /* FIQ Status */ - case 0x10: /* Raw Interrupt Status */ - case 0x40: /* Interrupt Sensitivity */ - case 0x48: /* Interrupt Both Edge Trigger Control */ - case 0x60: /* Edge Triggered Interrupt Status */ + case 0x80: /* IRQ Status */ + case 0x00: + case 0x88: /* FIQ Status */ + case 0x04: + case 0x90: /* Raw Interrupt Status */ + case 0x08: + case 0xc0: /* Interrupt Sensitivity */ + case 0x24: + case 0xc8: /* Interrupt Both Edge Trigger Control */ + case 0x28: + case 0xe0: /* Edge Triggered Interrupt Status */ qemu_log_mask(LOG_GUEST_ERROR, "%s: Write of read-only register with offset 0x%" HWADDR_PRIx "\n", __func__, offset); -- 2.20.1 From: Joel Stanley <joel@jms.id.au> The ast2500 uses the watchdog to reset the SDRAM controller. This operation is usually performed by u-boot's memory training procedure, and it is enabled by setting a bit in the SCU and then causing the watchdog to expire. Therefore, we need the watchdog to be able to access the SCU's register space. This causes the watchdog to not perform a system reset when the bit is set. In the future it could perform a reset of the SDMC model. Signed-off-by: Joel Stanley <joel@jms.id.au> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190621065242.32535-1-joel@jms.id.au Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/watchdog/wdt_aspeed.h | 1 + hw/arm/aspeed_soc.c | 2 ++ hw/watchdog/wdt_aspeed.c | 20 ++++++++++++++++++++ 3 files changed, 23 insertions(+) diff --git a/include/hw/watchdog/wdt_aspeed.h b/include/hw/watchdog/wdt_aspeed.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/watchdog/wdt_aspeed.h +++ b/include/hw/watchdog/wdt_aspeed.h @@ -XXX,XX +XXX,XX @@ typedef struct AspeedWDTState { MemoryRegion iomem; uint32_t regs[ASPEED_WDT_REGS_MAX]; + AspeedSCUState *scu; uint32_t pclk_freq; uint32_t silicon_rev; uint32_t ext_pulse_width_mask; diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) sizeof(s->wdt[i]), TYPE_ASPEED_WDT); qdev_prop_set_uint32(DEVICE(&s->wdt[i]), "silicon-rev", sc->info->silicon_rev); + object_property_add_const_link(OBJECT(&s->wdt[i]), "scu", + OBJECT(&s->scu), &error_abort); } for (i = 0; i < ASPEED_MACS_NUM; i++) { diff --git a/hw/watchdog/wdt_aspeed.c b/hw/watchdog/wdt_aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/watchdog/wdt_aspeed.c +++ b/hw/watchdog/wdt_aspeed.c @@ -XXX,XX +XXX,XX @@ #define WDT_RESTART_MAGIC 0x4755 +#define SCU_RESET_CONTROL1 (0x04 / 4) +#define SCU_RESET_SDRAM BIT(0) + static bool aspeed_wdt_is_enabled(const AspeedWDTState *s) { return s->regs[WDT_CTRL] & WDT_CTRL_ENABLE; @@ -XXX,XX +XXX,XX @@ static void aspeed_wdt_timer_expired(void *dev) { AspeedWDTState *s = ASPEED_WDT(dev); + /* Do not reset on SDRAM controller reset */ + if (s->scu->regs[SCU_RESET_CONTROL1] & SCU_RESET_SDRAM) { + timer_del(s->timer); + s->regs[WDT_CTRL] = 0; + return; + } + qemu_log_mask(CPU_LOG_RESET, "Watchdog timer expired.\n"); watchdog_perform_action(); timer_del(s->timer); @@ -XXX,XX +XXX,XX @@ static void aspeed_wdt_realize(DeviceState *dev, Error **errp) { SysBusDevice *sbd = SYS_BUS_DEVICE(dev); AspeedWDTState *s = ASPEED_WDT(dev); + Error *err = NULL; + Object *obj; + + obj = object_property_get_link(OBJECT(dev), "scu", &err); + if (!obj) { + error_propagate(errp, err); + error_prepend(errp, "required link 'scu' not found: "); + return; + } + s->scu = ASPEED_SCU(obj); if (!is_supported_silicon_rev(s->silicon_rev)) { error_setg(errp, "Unknown silicon revision: 0x%" PRIx32, -- 2.20.1 From: Hongbo Zhang <hongbo.zhang@linaro.org> For AArch64, the existing "virt" machine is primarily meant to run on KVM and execute virtualization workloads, but we need an environment as faithful as possible to physical hardware, for supporting firmware and OS development for physical Aarch64 machines. This patch introduces new machine type 'sbsa-ref' with main features: - Based on 'virt' machine type. - A new memory map. - CPU type cortex-a57. - EL2 and EL3 are enabled. - GIC version 3. - System bus AHCI controller. - System bus EHCI controller. - CDROM and hard disc on AHCI bus. - E1000E ethernet card on PCIE bus. - VGA display adaptor on PCIE bus. - No virtio devices. - No fw_cfg device. - No ACPI table supplied. - Only minimal device tree nodes. Arm Trusted Firmware and UEFI porting to this are done accordingly, and the firmware should supply ACPI tables to the guest OS. The minimal device tree nodes supplied by QEMU for this platform are only to pass the dynamic info reflecting command line input to firmware, not for loading the guest OS. To make the review easier, this task is split into two patches, the fundamental skeleton part and the peripheral devices part; this patch is the first part. Signed-off-by: Hongbo Zhang <hongbo.zhang@linaro.org> Message-id: 1561890034-15921-2-git-send-email-hongbo.zhang@linaro.org [PMM: commit message tweaks; moved some bits between patch 1 and 2 to ensure patch 1 builds cleanly; removed unneeded lines from Kconfig stanza; only provide board for qemu-system-aarch64, not qemu-system-arm; added MAINTAINERS entry] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 1 + hw/arm/sbsa-ref.c | 271 ++++++++++++++++++++++++++++ MAINTAINERS | 8 + default-configs/aarch64-softmmu.mak | 1 + hw/arm/Kconfig | 14 ++ 5 files changed, 295 insertions(+) create mode 100644 hw/arm/sbsa-ref.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_SPITZ) += spitz.o obj-$(CONFIG_TOSA) += tosa.o obj-$(CONFIG_Z2) += z2.o obj-$(CONFIG_REALVIEW) += realview.o +obj-$(CONFIG_SBSA_REF) += sbsa-ref.o obj-$(CONFIG_STELLARIS) += stellaris.o obj-$(CONFIG_COLLIE) += collie.o obj-$(CONFIG_VERSATILE) += versatilepb.o diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM SBSA Reference Platform emulation + * + * Copyright (c) 2018 Linaro Limited + * Written by Hongbo Zhang <hongbo.zhang@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/units.h" +#include "sysemu/numa.h" +#include "sysemu/sysemu.h" +#include "exec/address-spaces.h" +#include "exec/hwaddr.h" +#include "kvm_arm.h" +#include "hw/arm/boot.h" +#include "hw/boards.h" +#include "hw/intc/arm_gicv3_common.h" + +#define RAMLIMIT_GB 8192 +#define RAMLIMIT_BYTES (RAMLIMIT_GB * GiB) + +enum { + SBSA_FLASH, + SBSA_MEM, + SBSA_CPUPERIPHS, + SBSA_GIC_DIST, + SBSA_GIC_REDIST, + SBSA_SMMU, + SBSA_UART, + SBSA_RTC, + SBSA_PCIE, + SBSA_PCIE_MMIO, + SBSA_PCIE_MMIO_HIGH, + SBSA_PCIE_PIO, + SBSA_PCIE_ECAM, + SBSA_GPIO, + SBSA_SECURE_UART, + SBSA_SECURE_UART_MM, + SBSA_SECURE_MEM, + SBSA_AHCI, + SBSA_EHCI, +}; + +typedef struct MemMapEntry { + hwaddr base; + hwaddr size; +} MemMapEntry; + +typedef struct { + MachineState parent; + struct arm_boot_info bootinfo; + int smp_cpus; + void *fdt; + int fdt_size; + int psci_conduit; +} SBSAMachineState; + +#define TYPE_SBSA_MACHINE MACHINE_TYPE_NAME("sbsa-ref") +#define SBSA_MACHINE(obj) \ + OBJECT_CHECK(SBSAMachineState, (obj), TYPE_SBSA_MACHINE) + +static const MemMapEntry sbsa_ref_memmap[] = { + /* 512M boot ROM */ + [SBSA_FLASH] = { 0, 0x20000000 }, + /* 512M secure memory */ + [SBSA_SECURE_MEM] = { 0x20000000, 0x20000000 }, + /* Space reserved for CPU peripheral devices */ + [SBSA_CPUPERIPHS] = { 0x40000000, 0x00040000 }, + [SBSA_GIC_DIST] = { 0x40060000, 0x00010000 }, + [SBSA_GIC_REDIST] = { 0x40080000, 0x04000000 }, + [SBSA_UART] = { 0x60000000, 0x00001000 }, + [SBSA_RTC] = { 0x60010000, 0x00001000 }, + [SBSA_GPIO] = { 0x60020000, 0x00001000 }, + [SBSA_SECURE_UART] = { 0x60030000, 0x00001000 }, + [SBSA_SECURE_UART_MM] = { 0x60040000, 0x00001000 }, + [SBSA_SMMU] = { 0x60050000, 0x00020000 }, + /* Space here reserved for more SMMUs */ + [SBSA_AHCI] = { 0x60100000, 0x00010000 }, + [SBSA_EHCI] = { 0x60110000, 0x00010000 }, + /* Space here reserved for other devices */ + [SBSA_PCIE_PIO] = { 0x7fff0000, 0x00010000 }, + /* 32-bit address PCIE MMIO space */ + [SBSA_PCIE_MMIO] = { 0x80000000, 0x70000000 }, + /* 256M PCIE ECAM space */ + [SBSA_PCIE_ECAM] = { 0xf0000000, 0x10000000 }, + /* ~1TB PCIE MMIO space (4GB to 1024GB boundary) */ + [SBSA_PCIE_MMIO_HIGH] = { 0x100000000ULL, 0xFF00000000ULL }, + [SBSA_MEM] = { 0x10000000000ULL, RAMLIMIT_BYTES }, +}; + +static void sbsa_ref_init(MachineState *machine) +{ + SBSAMachineState *sms = SBSA_MACHINE(machine); + MachineClass *mc = MACHINE_GET_CLASS(machine); + MemoryRegion *sysmem = get_system_memory(); + MemoryRegion *secure_sysmem = NULL; + MemoryRegion *ram = g_new(MemoryRegion, 1); + const CPUArchIdList *possible_cpus; + int n, sbsa_max_cpus; + + if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a57"))) { + error_report("sbsa-ref: CPU type other than the built-in " + "cortex-a57 not supported"); + exit(1); + } + + if (kvm_enabled()) { + error_report("sbsa-ref: KVM is not supported for this machine"); + exit(1); + } + + /* + * This machine has EL3 enabled, external firmware should supply PSCI + * implementation, so the QEMU's internal PSCI is disabled. + */ + sms->psci_conduit = QEMU_PSCI_CONDUIT_DISABLED; + + sbsa_max_cpus = sbsa_ref_memmap[SBSA_GIC_REDIST].size / GICV3_REDIST_SIZE; + + if (max_cpus > sbsa_max_cpus) { + error_report("Number of SMP CPUs requested (%d) exceeds max CPUs " + "supported by machine 'sbsa-ref' (%d)", + max_cpus, sbsa_max_cpus); + exit(1); + } + + sms->smp_cpus = smp_cpus; + + if (machine->ram_size > sbsa_ref_memmap[SBSA_MEM].size) { + error_report("sbsa-ref: cannot model more than %dGB RAM", RAMLIMIT_GB); + exit(1); + } + + possible_cpus = mc->possible_cpu_arch_ids(machine); + for (n = 0; n < possible_cpus->len; n++) { + Object *cpuobj; + CPUState *cs; + + if (n >= smp_cpus) { + break; + } + + cpuobj = object_new(possible_cpus->cpus[n].type); + object_property_set_int(cpuobj, possible_cpus->cpus[n].arch_id, + "mp-affinity", NULL); + + cs = CPU(cpuobj); + cs->cpu_index = n; + + numa_cpu_pre_plug(&possible_cpus->cpus[cs->cpu_index], DEVICE(cpuobj), + &error_fatal); + + if (object_property_find(cpuobj, "reset-cbar", NULL)) { + object_property_set_int(cpuobj, + sbsa_ref_memmap[SBSA_CPUPERIPHS].base, + "reset-cbar", &error_abort); + } + + object_property_set_link(cpuobj, OBJECT(sysmem), "memory", + &error_abort); + + object_property_set_link(cpuobj, OBJECT(secure_sysmem), + "secure-memory", &error_abort); + + object_property_set_bool(cpuobj, true, "realized", &error_fatal); + object_unref(cpuobj); + } + + memory_region_allocate_system_memory(ram, NULL, "sbsa-ref.ram", + machine->ram_size); + memory_region_add_subregion(sysmem, sbsa_ref_memmap[SBSA_MEM].base, ram); + + sms->bootinfo.ram_size = machine->ram_size; + sms->bootinfo.kernel_filename = machine->kernel_filename; + sms->bootinfo.nb_cpus = smp_cpus; + sms->bootinfo.board_id = -1; + sms->bootinfo.loader_start = sbsa_ref_memmap[SBSA_MEM].base; + arm_load_kernel(ARM_CPU(first_cpu), &sms->bootinfo); +} + +static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) +{ + uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; + return arm_cpu_mp_affinity(idx, clustersz); +} + +static const CPUArchIdList *sbsa_ref_possible_cpu_arch_ids(MachineState *ms) +{ + SBSAMachineState *sms = SBSA_MACHINE(ms); + int n; + + if (ms->possible_cpus) { + assert(ms->possible_cpus->len == max_cpus); + return ms->possible_cpus; + } + + ms->possible_cpus = g_malloc0(sizeof(CPUArchIdList) + + sizeof(CPUArchId) * max_cpus); + ms->possible_cpus->len = max_cpus; + for (n = 0; n < ms->possible_cpus->len; n++) { + ms->possible_cpus->cpus[n].type = ms->cpu_type; + ms->possible_cpus->cpus[n].arch_id = + sbsa_ref_cpu_mp_affinity(sms, n); + ms->possible_cpus->cpus[n].props.has_thread_id = true; + ms->possible_cpus->cpus[n].props.thread_id = n; + } + return ms->possible_cpus; +} + +static CpuInstanceProperties +sbsa_ref_cpu_index_to_props(MachineState *ms, unsigned cpu_index) +{ + MachineClass *mc = MACHINE_GET_CLASS(ms); + const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms); + + assert(cpu_index < possible_cpus->len); + return possible_cpus->cpus[cpu_index].props; +} + +static int64_t +sbsa_ref_get_default_cpu_node_id(const MachineState *ms, int idx) +{ + return idx % nb_numa_nodes; +} + +static void sbsa_ref_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->init = sbsa_ref_init; + mc->desc = "QEMU 'SBSA Reference' ARM Virtual Machine"; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a57"); + mc->max_cpus = 512; + mc->pci_allow_0_address = true; + mc->minimum_page_bits = 12; + mc->block_default_type = IF_IDE; + mc->no_cdrom = 1; + mc->default_ram_size = 1 * GiB; + mc->default_cpus = 4; + mc->possible_cpu_arch_ids = sbsa_ref_possible_cpu_arch_ids; + mc->cpu_index_to_instance_props = sbsa_ref_cpu_index_to_props; + mc->get_default_cpu_node_id = sbsa_ref_get_default_cpu_node_id; +} + +static const TypeInfo sbsa_ref_info = { + .name = TYPE_SBSA_MACHINE, + .parent = TYPE_MACHINE, + .class_init = sbsa_ref_class_init, + .instance_size = sizeof(SBSAMachineState), +}; + +static void sbsa_ref_machine_init(void) +{ + type_register_static(&sbsa_ref_info); +} + +type_init(sbsa_ref_machine_init); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/arm/fsl-imx6.h F: include/hw/misc/imx6_*.h F: include/hw/ssi/imx_spi.h +SBSA-REF +M: Radoslaw Biernacki <radoslaw.biernacki@linaro.org> +M: Peter Maydell <peter.maydell@linaro.org> +R: Leif Lindholm <leif.lindholm@linaro.org> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/sbsa-ref.c + Sharp SL-5500 (Collie) PDA M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org diff --git a/default-configs/aarch64-softmmu.mak b/default-configs/aarch64-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/aarch64-softmmu.mak +++ b/default-configs/aarch64-softmmu.mak @@ -XXX,XX +XXX,XX @@ include arm-softmmu.mak CONFIG_XLNX_ZYNQMP_ARM=y CONFIG_XLNX_VERSAL=y +CONFIG_SBSA_REF=y diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config REALVIEW select DS1338 # I2C RTC+NVRAM select USB_OHCI +config SBSA_REF + bool + imply PCI_DEVICES + select AHCI + select ARM_SMMUV3 + select GPIO_KEY + select PCI_EXPRESS + select PCI_EXPRESS_GENERIC_BRIDGE + select PFLASH_CFI01 + select PL011 # UART + select PL031 # RTC + select PL061 # GPIO + select USB_EHCI_SYSBUS + config SABRELITE bool select FSL_IMX6 -- 2.20.1 From: Hongbo Zhang <hongbo.zhang@linaro.org> Following the previous patch, this patch adds peripheral devices to the newly introduced SBSA-ref machine. Signed-off-by: Hongbo Zhang <hongbo.zhang@linaro.org> Message-id: 1561890034-15921-3-git-send-email-hongbo.zhang@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 535 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 535 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 @@ */ #include "qemu/osdep.h" +#include "qemu-common.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/units.h" +#include "sysemu/device_tree.h" #include "sysemu/numa.h" #include "sysemu/sysemu.h" #include "exec/address-spaces.h" #include "exec/hwaddr.h" #include "kvm_arm.h" #include "hw/arm/boot.h" +#include "hw/block/flash.h" #include "hw/boards.h" +#include "hw/ide/internal.h" +#include "hw/ide/ahci_internal.h" #include "hw/intc/arm_gicv3_common.h" +#include "hw/loader.h" +#include "hw/pci-host/gpex.h" +#include "hw/usb.h" +#include "net/net.h" #define RAMLIMIT_GB 8192 #define RAMLIMIT_BYTES (RAMLIMIT_GB * GiB) +#define NUM_IRQS 256 +#define NUM_SMMU_IRQS 4 +#define NUM_SATA_PORTS 6 + +#define VIRTUAL_PMU_IRQ 7 +#define ARCH_GIC_MAINT_IRQ 9 +#define ARCH_TIMER_VIRT_IRQ 11 +#define ARCH_TIMER_S_EL1_IRQ 13 +#define ARCH_TIMER_NS_EL1_IRQ 14 +#define ARCH_TIMER_NS_EL2_IRQ 10 + enum { SBSA_FLASH, SBSA_MEM, @@ -XXX,XX +XXX,XX @@ typedef struct { void *fdt; int fdt_size; int psci_conduit; + PFlashCFI01 *flash[2]; } SBSAMachineState; #define TYPE_SBSA_MACHINE MACHINE_TYPE_NAME("sbsa-ref") @@ -XXX,XX +XXX,XX @@ static const MemMapEntry sbsa_ref_memmap[] = { [SBSA_MEM] = { 0x10000000000ULL, RAMLIMIT_BYTES }, }; +static const int sbsa_ref_irqmap[] = { + [SBSA_UART] = 1, + [SBSA_RTC] = 2, + [SBSA_PCIE] = 3, /* ... to 6 */ + [SBSA_GPIO] = 7, + [SBSA_SECURE_UART] = 8, + [SBSA_SECURE_UART_MM] = 9, + [SBSA_AHCI] = 10, + [SBSA_EHCI] = 11, +}; + +/* + * Firmware on this machine only uses ACPI table to load OS, these limited + * device tree nodes are just to let firmware know the info which varies from + * command line parameters, so it is not necessary to be fully compatible + * with the kernel CPU and NUMA binding rules. + */ +static void create_fdt(SBSAMachineState *sms) +{ + void *fdt = create_device_tree(&sms->fdt_size); + const MachineState *ms = MACHINE(sms); + int cpu; + + if (!fdt) { + error_report("create_device_tree() failed"); + exit(1); + } + + sms->fdt = fdt; + + qemu_fdt_setprop_string(fdt, "/", "compatible", "linux,sbsa-ref"); + qemu_fdt_setprop_cell(fdt, "/", "#address-cells", 0x2); + qemu_fdt_setprop_cell(fdt, "/", "#size-cells", 0x2); + + if (have_numa_distance) { + int size = nb_numa_nodes * nb_numa_nodes * 3 * sizeof(uint32_t); + uint32_t *matrix = g_malloc0(size); + int idx, i, j; + + for (i = 0; i < nb_numa_nodes; i++) { + for (j = 0; j < nb_numa_nodes; j++) { + idx = (i * nb_numa_nodes + j) * 3; + matrix[idx + 0] = cpu_to_be32(i); + matrix[idx + 1] = cpu_to_be32(j); + matrix[idx + 2] = cpu_to_be32(numa_info[i].distance[j]); + } + } + + qemu_fdt_add_subnode(fdt, "/distance-map"); + qemu_fdt_setprop(fdt, "/distance-map", "distance-matrix", + matrix, size); + g_free(matrix); + } + + qemu_fdt_add_subnode(sms->fdt, "/cpus"); + + for (cpu = sms->smp_cpus - 1; cpu >= 0; cpu--) { + char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu); + ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); + CPUState *cs = CPU(armcpu); + + qemu_fdt_add_subnode(sms->fdt, nodename); + + if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) { + qemu_fdt_setprop_cell(sms->fdt, nodename, "numa-node-id", + ms->possible_cpus->cpus[cs->cpu_index].props.node_id); + } + + g_free(nodename); + } +} + +#define SBSA_FLASH_SECTOR_SIZE (256 * KiB) + +static PFlashCFI01 *sbsa_flash_create1(SBSAMachineState *sms, + const char *name, + const char *alias_prop_name) +{ + /* + * Create a single flash device. We use the same parameters as + * the flash devices on the Versatile Express board. + */ + DeviceState *dev = qdev_create(NULL, TYPE_PFLASH_CFI01); + + qdev_prop_set_uint64(dev, "sector-length", SBSA_FLASH_SECTOR_SIZE); + qdev_prop_set_uint8(dev, "width", 4); + qdev_prop_set_uint8(dev, "device-width", 2); + qdev_prop_set_bit(dev, "big-endian", false); + qdev_prop_set_uint16(dev, "id0", 0x89); + qdev_prop_set_uint16(dev, "id1", 0x18); + qdev_prop_set_uint16(dev, "id2", 0x00); + qdev_prop_set_uint16(dev, "id3", 0x00); + qdev_prop_set_string(dev, "name", name); + object_property_add_child(OBJECT(sms), name, OBJECT(dev), + &error_abort); + object_property_add_alias(OBJECT(sms), alias_prop_name, + OBJECT(dev), "drive", &error_abort); + return PFLASH_CFI01(dev); +} + +static void sbsa_flash_create(SBSAMachineState *sms) +{ + sms->flash[0] = sbsa_flash_create1(sms, "sbsa.flash0", "pflash0"); + sms->flash[1] = sbsa_flash_create1(sms, "sbsa.flash1", "pflash1"); +} + +static void sbsa_flash_map1(PFlashCFI01 *flash, + hwaddr base, hwaddr size, + MemoryRegion *sysmem) +{ + DeviceState *dev = DEVICE(flash); + + assert(size % SBSA_FLASH_SECTOR_SIZE == 0); + assert(size / SBSA_FLASH_SECTOR_SIZE <= UINT32_MAX); + qdev_prop_set_uint32(dev, "num-blocks", size / SBSA_FLASH_SECTOR_SIZE); + qdev_init_nofail(dev); + + memory_region_add_subregion(sysmem, base, + sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), + 0)); +} + +static void sbsa_flash_map(SBSAMachineState *sms, + MemoryRegion *sysmem, + MemoryRegion *secure_sysmem) +{ + /* + * Map two flash devices to fill the SBSA_FLASH space in the memmap. + * sysmem is the system memory space. secure_sysmem is the secure view + * of the system, and the first flash device should be made visible only + * there. The second flash device is visible to both secure and nonsecure. + * If sysmem == secure_sysmem this means there is no separate Secure + * address space and both flash devices are generally visible. + */ + hwaddr flashsize = sbsa_ref_memmap[SBSA_FLASH].size / 2; + hwaddr flashbase = sbsa_ref_memmap[SBSA_FLASH].base; + + sbsa_flash_map1(sms->flash[0], flashbase, flashsize, + secure_sysmem); + sbsa_flash_map1(sms->flash[1], flashbase + flashsize, flashsize, + sysmem); +} + +static bool sbsa_firmware_init(SBSAMachineState *sms, + MemoryRegion *sysmem, + MemoryRegion *secure_sysmem) +{ + int i; + BlockBackend *pflash_blk0; + + /* Map legacy -drive if=pflash to machine properties */ + for (i = 0; i < ARRAY_SIZE(sms->flash); i++) { + pflash_cfi01_legacy_drive(sms->flash[i], + drive_get(IF_PFLASH, 0, i)); + } + + sbsa_flash_map(sms, sysmem, secure_sysmem); + + pflash_blk0 = pflash_cfi01_get_blk(sms->flash[0]); + + if (bios_name) { + char *fname; + MemoryRegion *mr; + int image_size; + + if (pflash_blk0) { + error_report("The contents of the first flash device may be " + "specified with -bios or with -drive if=pflash... " + "but you cannot use both options at once"); + exit(1); + } + + /* Fall back to -bios */ + + fname = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); + if (!fname) { + error_report("Could not find ROM image '%s'", bios_name); + exit(1); + } + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(sms->flash[0]), 0); + image_size = load_image_mr(fname, mr); + g_free(fname); + if (image_size < 0) { + error_report("Could not load ROM image '%s'", bios_name); + exit(1); + } + } + + return pflash_blk0 || bios_name; +} + +static void create_secure_ram(SBSAMachineState *sms, + MemoryRegion *secure_sysmem) +{ + MemoryRegion *secram = g_new(MemoryRegion, 1); + hwaddr base = sbsa_ref_memmap[SBSA_SECURE_MEM].base; + hwaddr size = sbsa_ref_memmap[SBSA_SECURE_MEM].size; + + memory_region_init_ram(secram, NULL, "sbsa-ref.secure-ram", size, + &error_fatal); + memory_region_add_subregion(secure_sysmem, base, secram); +} + +static void create_gic(SBSAMachineState *sms, qemu_irq *pic) +{ + DeviceState *gicdev; + SysBusDevice *gicbusdev; + const char *gictype; + uint32_t redist0_capacity, redist0_count; + int i; + + gictype = gicv3_class_name(); + + gicdev = qdev_create(NULL, gictype); + qdev_prop_set_uint32(gicdev, "revision", 3); + qdev_prop_set_uint32(gicdev, "num-cpu", smp_cpus); + /* + * Note that the num-irq property counts both internal and external + * interrupts; there are always 32 of the former (mandated by GIC spec). + */ + qdev_prop_set_uint32(gicdev, "num-irq", NUM_IRQS + 32); + qdev_prop_set_bit(gicdev, "has-security-extensions", true); + + redist0_capacity = + sbsa_ref_memmap[SBSA_GIC_REDIST].size / GICV3_REDIST_SIZE; + redist0_count = MIN(smp_cpus, redist0_capacity); + + qdev_prop_set_uint32(gicdev, "len-redist-region-count", 1); + qdev_prop_set_uint32(gicdev, "redist-region-count[0]", redist0_count); + + qdev_init_nofail(gicdev); + gicbusdev = SYS_BUS_DEVICE(gicdev); + sysbus_mmio_map(gicbusdev, 0, sbsa_ref_memmap[SBSA_GIC_DIST].base); + sysbus_mmio_map(gicbusdev, 1, sbsa_ref_memmap[SBSA_GIC_REDIST].base); + + /* + * Wire the outputs from each CPU's generic timer and the GICv3 + * maintenance interrupt signal to the appropriate GIC PPI inputs, + * and the GIC's IRQ/FIQ/VIRQ/VFIQ interrupt outputs to the CPU's inputs. + */ + for (i = 0; i < smp_cpus; i++) { + DeviceState *cpudev = DEVICE(qemu_get_cpu(i)); + int ppibase = NUM_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS; + int irq; + /* + * Mapping from the output timer irq lines from the CPU to the + * GIC PPI inputs used for this board. + */ + const int timer_irq[] = { + [GTIMER_PHYS] = ARCH_TIMER_NS_EL1_IRQ, + [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ, + [GTIMER_HYP] = ARCH_TIMER_NS_EL2_IRQ, + [GTIMER_SEC] = ARCH_TIMER_S_EL1_IRQ, + }; + + for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { + qdev_connect_gpio_out(cpudev, irq, + qdev_get_gpio_in(gicdev, + ppibase + timer_irq[irq])); + } + + qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", 0, + qdev_get_gpio_in(gicdev, ppibase + + ARCH_GIC_MAINT_IRQ)); + qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, + qdev_get_gpio_in(gicdev, ppibase + + VIRTUAL_PMU_IRQ)); + + sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(gicbusdev, i + smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(gicbusdev, i + 2 * smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(gicbusdev, i + 3 * smp_cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + } + + for (i = 0; i < NUM_IRQS; i++) { + pic[i] = qdev_get_gpio_in(gicdev, i); + } +} + +static void create_uart(const SBSAMachineState *sms, qemu_irq *pic, int uart, + MemoryRegion *mem, Chardev *chr) +{ + hwaddr base = sbsa_ref_memmap[uart].base; + int irq = sbsa_ref_irqmap[uart]; + DeviceState *dev = qdev_create(NULL, "pl011"); + SysBusDevice *s = SYS_BUS_DEVICE(dev); + + qdev_prop_set_chr(dev, "chardev", chr); + qdev_init_nofail(dev); + memory_region_add_subregion(mem, base, + sysbus_mmio_get_region(s, 0)); + sysbus_connect_irq(s, 0, pic[irq]); +} + +static void create_rtc(const SBSAMachineState *sms, qemu_irq *pic) +{ + hwaddr base = sbsa_ref_memmap[SBSA_RTC].base; + int irq = sbsa_ref_irqmap[SBSA_RTC]; + + sysbus_create_simple("pl031", base, pic[irq]); +} + +static DeviceState *gpio_key_dev; +static void sbsa_ref_powerdown_req(Notifier *n, void *opaque) +{ + /* use gpio Pin 3 for power button event */ + qemu_set_irq(qdev_get_gpio_in(gpio_key_dev, 0), 1); +} + +static Notifier sbsa_ref_powerdown_notifier = { + .notify = sbsa_ref_powerdown_req +}; + +static void create_gpio(const SBSAMachineState *sms, qemu_irq *pic) +{ + DeviceState *pl061_dev; + hwaddr base = sbsa_ref_memmap[SBSA_GPIO].base; + int irq = sbsa_ref_irqmap[SBSA_GPIO]; + + pl061_dev = sysbus_create_simple("pl061", base, pic[irq]); + + gpio_key_dev = sysbus_create_simple("gpio-key", -1, + qdev_get_gpio_in(pl061_dev, 3)); + + /* connect powerdown request */ + qemu_register_powerdown_notifier(&sbsa_ref_powerdown_notifier); +} + +static void create_ahci(const SBSAMachineState *sms, qemu_irq *pic) +{ + hwaddr base = sbsa_ref_memmap[SBSA_AHCI].base; + int irq = sbsa_ref_irqmap[SBSA_AHCI]; + DeviceState *dev; + DriveInfo *hd[NUM_SATA_PORTS]; + SysbusAHCIState *sysahci; + AHCIState *ahci; + int i; + + dev = qdev_create(NULL, "sysbus-ahci"); + qdev_prop_set_uint32(dev, "num-ports", NUM_SATA_PORTS); + qdev_init_nofail(dev); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irq]); + + sysahci = SYSBUS_AHCI(dev); + ahci = &sysahci->ahci; + ide_drive_get(hd, ARRAY_SIZE(hd)); + for (i = 0; i < ahci->ports; i++) { + if (hd[i] == NULL) { + continue; + } + ide_create_drive(&ahci->dev[i].port, 0, hd[i]); + } +} + +static void create_ehci(const SBSAMachineState *sms, qemu_irq *pic) +{ + hwaddr base = sbsa_ref_memmap[SBSA_EHCI].base; + int irq = sbsa_ref_irqmap[SBSA_EHCI]; + + sysbus_create_simple("platform-ehci-usb", base, pic[irq]); +} + +static void create_smmu(const SBSAMachineState *sms, qemu_irq *pic, + PCIBus *bus) +{ + hwaddr base = sbsa_ref_memmap[SBSA_SMMU].base; + int irq = sbsa_ref_irqmap[SBSA_SMMU]; + DeviceState *dev; + int i; + + dev = qdev_create(NULL, "arm-smmuv3"); + + object_property_set_link(OBJECT(dev), OBJECT(bus), "primary-bus", + &error_abort); + qdev_init_nofail(dev); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); + for (i = 0; i < NUM_SMMU_IRQS; i++) { + sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, pic[irq + i]); + } +} + +static void create_pcie(SBSAMachineState *sms, qemu_irq *pic) +{ + hwaddr base_ecam = sbsa_ref_memmap[SBSA_PCIE_ECAM].base; + hwaddr size_ecam = sbsa_ref_memmap[SBSA_PCIE_ECAM].size; + hwaddr base_mmio = sbsa_ref_memmap[SBSA_PCIE_MMIO].base; + hwaddr size_mmio = sbsa_ref_memmap[SBSA_PCIE_MMIO].size; + hwaddr base_mmio_high = sbsa_ref_memmap[SBSA_PCIE_MMIO_HIGH].base; + hwaddr size_mmio_high = sbsa_ref_memmap[SBSA_PCIE_MMIO_HIGH].size; + hwaddr base_pio = sbsa_ref_memmap[SBSA_PCIE_PIO].base; + int irq = sbsa_ref_irqmap[SBSA_PCIE]; + MemoryRegion *mmio_alias, *mmio_alias_high, *mmio_reg; + MemoryRegion *ecam_alias, *ecam_reg; + DeviceState *dev; + PCIHostState *pci; + int i; + + dev = qdev_create(NULL, TYPE_GPEX_HOST); + qdev_init_nofail(dev); + + /* Map ECAM space */ + ecam_alias = g_new0(MemoryRegion, 1); + ecam_reg = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); + memory_region_init_alias(ecam_alias, OBJECT(dev), "pcie-ecam", + ecam_reg, 0, size_ecam); + memory_region_add_subregion(get_system_memory(), base_ecam, ecam_alias); + + /* Map the MMIO space */ + mmio_alias = g_new0(MemoryRegion, 1); + mmio_reg = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 1); + memory_region_init_alias(mmio_alias, OBJECT(dev), "pcie-mmio", + mmio_reg, base_mmio, size_mmio); + memory_region_add_subregion(get_system_memory(), base_mmio, mmio_alias); + + /* Map the MMIO_HIGH space */ + mmio_alias_high = g_new0(MemoryRegion, 1); + memory_region_init_alias(mmio_alias_high, OBJECT(dev), "pcie-mmio-high", + mmio_reg, base_mmio_high, size_mmio_high); + memory_region_add_subregion(get_system_memory(), base_mmio_high, + mmio_alias_high); + + /* Map IO port space */ + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 2, base_pio); + + for (i = 0; i < GPEX_NUM_IRQS; i++) { + sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, pic[irq + i]); + gpex_set_irq_num(GPEX_HOST(dev), i, irq + i); + } + + pci = PCI_HOST_BRIDGE(dev); + if (pci->bus) { + for (i = 0; i < nb_nics; i++) { + NICInfo *nd = &nd_table[i]; + + if (!nd->model) { + nd->model = g_strdup("e1000e"); + } + + pci_nic_init_nofail(nd, pci->bus, nd->model, NULL); + } + } + + pci_create_simple(pci->bus, -1, "VGA"); + + create_smmu(sms, pic, pci->bus); +} + +static void *sbsa_ref_dtb(const struct arm_boot_info *binfo, int *fdt_size) +{ + const SBSAMachineState *board = container_of(binfo, SBSAMachineState, + bootinfo); + + *fdt_size = board->fdt_size; + return board->fdt; +} + static void sbsa_ref_init(MachineState *machine) { SBSAMachineState *sms = SBSA_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) MemoryRegion *sysmem = get_system_memory(); MemoryRegion *secure_sysmem = NULL; MemoryRegion *ram = g_new(MemoryRegion, 1); + bool firmware_loaded; const CPUArchIdList *possible_cpus; int n, sbsa_max_cpus; + qemu_irq pic[NUM_IRQS]; if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a57"))) { error_report("sbsa-ref: CPU type other than the built-in " @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) exit(1); } + /* + * The Secure view of the world is the same as the NonSecure, + * but with a few extra devices. Create it as a container region + * containing the system memory at low priority; any secure-only + * devices go in at higher priority and take precedence. + */ + secure_sysmem = g_new(MemoryRegion, 1); + memory_region_init(secure_sysmem, OBJECT(machine), "secure-memory", + UINT64_MAX); + memory_region_add_subregion_overlap(secure_sysmem, 0, sysmem, -1); + + firmware_loaded = sbsa_firmware_init(sms, sysmem, + secure_sysmem ?: sysmem); + + if (machine->kernel_filename && firmware_loaded) { + error_report("sbsa-ref: No fw_cfg device on this machine, " + "so -kernel option is not supported when firmware loaded, " + "please load OS from hard disk instead"); + exit(1); + } + /* * This machine has EL3 enabled, external firmware should supply PSCI * implementation, so the QEMU's internal PSCI is disabled. @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) machine->ram_size); memory_region_add_subregion(sysmem, sbsa_ref_memmap[SBSA_MEM].base, ram); + create_fdt(sms); + + create_secure_ram(sms, secure_sysmem); + + create_gic(sms, pic); + + create_uart(sms, pic, SBSA_UART, sysmem, serial_hd(0)); + create_uart(sms, pic, SBSA_SECURE_UART, secure_sysmem, serial_hd(1)); + /* Second secure UART for RAS and MM from EL0 */ + create_uart(sms, pic, SBSA_SECURE_UART_MM, secure_sysmem, serial_hd(2)); + + create_rtc(sms, pic); + + create_gpio(sms, pic); + + create_ahci(sms, pic); + + create_ehci(sms, pic); + + create_pcie(sms, pic); + sms->bootinfo.ram_size = machine->ram_size; sms->bootinfo.kernel_filename = machine->kernel_filename; sms->bootinfo.nb_cpus = smp_cpus; sms->bootinfo.board_id = -1; sms->bootinfo.loader_start = sbsa_ref_memmap[SBSA_MEM].base; + sms->bootinfo.get_dtb = sbsa_ref_dtb; + sms->bootinfo.firmware_loaded = firmware_loaded; arm_load_kernel(ARM_CPU(first_cpu), &sms->bootinfo); } @@ -XXX,XX +XXX,XX @@ sbsa_ref_get_default_cpu_node_id(const MachineState *ms, int idx) return idx % nb_numa_nodes; } +static void sbsa_ref_instance_init(Object *obj) +{ + SBSAMachineState *sms = SBSA_MACHINE(obj); + + sbsa_flash_create(sms); +} + static void sbsa_ref_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_class_init(ObjectClass *oc, void *data) static const TypeInfo sbsa_ref_info = { .name = TYPE_SBSA_MACHINE, .parent = TYPE_MACHINE, + .instance_init = sbsa_ref_instance_init, .class_init = sbsa_ref_class_init, .instance_size = sizeof(SBSAMachineState), }; -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Group Aarch64 rules together, TCG related ones at the bottom. This will help when restricting TCG-only objects. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-2-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o obj-y += translate.o op_helper.o helper.o cpu.o obj-y += neon_helper.o iwmmxt_helper.o vec_helper.o vfp_helper.o obj-y += gdbstub.o -obj-$(TARGET_AARCH64) += cpu64.o translate-a64.o helper-a64.o gdbstub64.o -obj-$(TARGET_AARCH64) += pauth_helper.o +obj-$(TARGET_AARCH64) += cpu64.o gdbstub64.o obj-y += crypto_helper.o obj-$(CONFIG_SOFTMMU) += arm-powerctl.o @@ -XXX,XX +XXX,XX @@ target/arm/translate-sve.o: target/arm/decode-sve.inc.c target/arm/translate.o: target/arm/decode-vfp.inc.c target/arm/translate.o: target/arm/decode-vfp-uncond.inc.c +obj-$(TARGET_AARCH64) += translate-a64.o helper-a64.o obj-$(TARGET_AARCH64) += translate-sve.o sve_helper.o +obj-$(TARGET_AARCH64) += pauth_helper.o -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Group ARM objects together, TCG related ones at the bottom. This will help when restricting TCG-only objects. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-3-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_KVM) += kvm.o obj-$(call land,$(CONFIG_KVM),$(call lnot,$(TARGET_AARCH64))) += kvm32.o obj-$(call land,$(CONFIG_KVM),$(TARGET_AARCH64)) += kvm64.o obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o -obj-y += translate.o op_helper.o helper.o cpu.o -obj-y += neon_helper.o iwmmxt_helper.o vec_helper.o vfp_helper.o -obj-y += gdbstub.o +obj-y += helper.o vfp_helper.o +obj-y += cpu.o gdbstub.o obj-$(TARGET_AARCH64) += cpu64.o gdbstub64.o -obj-y += crypto_helper.o obj-$(CONFIG_SOFTMMU) += arm-powerctl.o DECODETREE = $(SRC_PATH)/scripts/decodetree.py @@ -XXX,XX +XXX,XX @@ target/arm/translate-sve.o: target/arm/decode-sve.inc.c target/arm/translate.o: target/arm/decode-vfp.inc.c target/arm/translate.o: target/arm/decode-vfp-uncond.inc.c +obj-y += translate.o op_helper.o +obj-y += crypto_helper.o +obj-y += iwmmxt_helper.o vec_helper.o neon_helper.o + obj-$(TARGET_AARCH64) += translate-a64.o helper-a64.o obj-$(TARGET_AARCH64) += translate-sve.o sve_helper.o obj-$(TARGET_AARCH64) += pauth_helper.o -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Group KVM rules together. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-4-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-y += arm-semi.o obj-$(CONFIG_SOFTMMU) += machine.o psci.o arch_dump.o monitor.o -obj-$(CONFIG_KVM) += kvm.o -obj-$(call land,$(CONFIG_KVM),$(call lnot,$(TARGET_AARCH64))) += kvm32.o -obj-$(call land,$(CONFIG_KVM),$(TARGET_AARCH64)) += kvm64.o -obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o obj-y += helper.o vfp_helper.o obj-y += cpu.o gdbstub.o obj-$(TARGET_AARCH64) += cpu64.o gdbstub64.o obj-$(CONFIG_SOFTMMU) += arm-powerctl.o +obj-$(CONFIG_KVM) += kvm.o +obj-$(call land,$(CONFIG_KVM),$(call lnot,$(TARGET_AARCH64))) += kvm32.o +obj-$(call land,$(CONFIG_KVM),$(TARGET_AARCH64)) += kvm64.o +obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o + DECODETREE = $(SRC_PATH)/scripts/decodetree.py target/arm/decode-sve.inc.c: $(SRC_PATH)/target/arm/sve.decode $(DECODETREE) -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Group SOFTMMU objects together. Since PSCI is TCG specific, keep it separate. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-5-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-y += arm-semi.o -obj-$(CONFIG_SOFTMMU) += machine.o psci.o arch_dump.o monitor.o obj-y += helper.o vfp_helper.o obj-y += cpu.o gdbstub.o obj-$(TARGET_AARCH64) += cpu64.o gdbstub64.o + +obj-$(CONFIG_SOFTMMU) += machine.o arch_dump.o monitor.o obj-$(CONFIG_SOFTMMU) += arm-powerctl.o obj-$(CONFIG_KVM) += kvm.o @@ -XXX,XX +XXX,XX @@ obj-y += translate.o op_helper.o obj-y += crypto_helper.o obj-y += iwmmxt_helper.o vec_helper.o neon_helper.o +obj-$(CONFIG_SOFTMMU) += psci.o + obj-$(TARGET_AARCH64) += translate-a64.o helper-a64.o obj-$(TARGET_AARCH64) += translate-sve.o sve_helper.o obj-$(TARGET_AARCH64) += pauth_helper.o -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Robert Bradford <robert.bradford@intel.com> Reviewed-by: Samuel Ortiz <sameo@linux.intel.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-6-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 7 +++++++ 1 file changed, 7 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 @@ +/* + * ARM generic helpers. + * + * This code is licensed under the GNU GPL v2 or later. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ #include "qemu/osdep.h" #include "qemu/units.h" #include "target/arm/idau.h" -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-7-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/gdbstub.h" #include "exec/helper-proto.h" #include "qemu/host-utils.h" -#include "sysemu/arch_init.h" #include "sysemu/sysemu.h" #include "qemu/bitops.h" #include "qemu/crc32c.h" @@ -XXX,XX +XXX,XX @@ #include "hw/semihosting/semihost.h" #include "sysemu/cpus.h" #include "sysemu/kvm.h" -#include "fpu/softfloat.h" #include "qemu/range.h" #include "qapi/qapi-commands-target.h" #include "qapi/error.h" -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Since commit 8c06fbdf36b checkpatch.pl enforce a new multiline comment syntax. Since we'll move this code around, fix its style first. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-8-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 237 ++++++++++++++++++++++++++-------------- target/arm/op_helper.c | 54 ++++++--- target/arm/vfp_helper.c | 3 +- 3 files changed, 196 insertions(+), 98 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) { - /* The TT instructions can be used by unprivileged code, but in + /* + * The TT instructions can be used by unprivileged code, but in * user-only emulation we don't have the MPU. * Luckily since we know we are NonSecure unprivileged (and that in * turn means that the A flag wasn't specified), all the bits in the @@ -XXX,XX +XXX,XX @@ static bool v7m_stack_write(ARMCPU *cpu, uint32_t addr, uint32_t value, return true; pend_fault: - /* By pending the exception at this point we are making + /* + * By pending the exception at this point we are making * the IMPDEF choice "overridden exceptions pended" (see the * MergeExcInfo() pseudocode). The other choice would be to not * pend them now and then make a choice about which to throw away @@ -XXX,XX +XXX,XX @@ static bool v7m_stack_read(ARMCPU *cpu, uint32_t *dest, uint32_t addr, return true; pend_fault: - /* By pending the exception at this point we are making + /* + * By pending the exception at this point we are making * the IMPDEF choice "overridden exceptions pended" (see the * MergeExcInfo() pseudocode). The other choice would be to not * pend them now and then make a choice about which to throw away @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_preserve_fp_state)(CPUARMState *env) */ } -/* Write to v7M CONTROL.SPSEL bit for the specified security bank. +/* + * Write to v7M CONTROL.SPSEL bit for the specified security bank. * This may change the current stack pointer between Main and Process * stack pointers if it is done for the CONTROL register for the current * security state. @@ -XXX,XX +XXX,XX @@ static void write_v7m_control_spsel_for_secstate(CPUARMState *env, } } -/* Write to v7M CONTROL.SPSEL bit. This may change the current +/* + * Write to v7M CONTROL.SPSEL bit. This may change the current * stack pointer between Main and Process stack pointers. */ static void write_v7m_control_spsel(CPUARMState *env, bool new_spsel) @@ -XXX,XX +XXX,XX @@ static void write_v7m_control_spsel(CPUARMState *env, bool new_spsel) void write_v7m_exception(CPUARMState *env, uint32_t new_exc) { - /* Write a new value to v7m.exception, thus transitioning into or out + /* + * Write a new value to v7m.exception, thus transitioning into or out * of Handler mode; this may result in a change of active stack pointer. */ bool new_is_psp, old_is_psp = v7m_using_psp(env); @@ -XXX,XX +XXX,XX @@ static void switch_v7m_security_state(CPUARMState *env, bool new_secstate) return; } - /* All the banked state is accessed by looking at env->v7m.secure + /* + * All the banked state is accessed by looking at env->v7m.secure * except for the stack pointer; rearrange the SP appropriately. */ new_ss_msp = env->v7m.other_ss_msp; @@ -XXX,XX +XXX,XX @@ static void switch_v7m_security_state(CPUARMState *env, bool new_secstate) void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest) { - /* Handle v7M BXNS: + /* + * Handle v7M BXNS: * - if the return value is a magic value, do exception return (like BX) * - otherwise bit 0 of the return value is the target security state */ @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest) } if (dest >= min_magic) { - /* This is an exception return magic value; put it where + /* + * This is an exception return magic value; put it where * do_v7m_exception_exit() expects and raise EXCEPTION_EXIT. * Note that if we ever add gen_ss_advance() singlestep support to * M profile this should count as an "instruction execution complete" @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest) void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) { - /* Handle v7M BLXNS: + /* + * Handle v7M BLXNS: * - bit 0 of the destination address is the target security state */ @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) assert(env->v7m.secure); if (dest & 1) { - /* target is Secure, so this is just a normal BLX, + /* + * Target is Secure, so this is just a normal BLX, * except that the low bit doesn't indicate Thumb/not. */ env->regs[14] = nextinst; @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) env->regs[13] = sp; env->regs[14] = 0xfeffffff; if (arm_v7m_is_handler_mode(env)) { - /* Write a dummy value to IPSR, to avoid leaking the current secure + /* + * Write a dummy value to IPSR, to avoid leaking the current secure * exception number to non-secure code. This is guaranteed not * to cause write_v7m_exception() to actually change stacks. */ @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) static uint32_t *get_v7m_sp_ptr(CPUARMState *env, bool secure, bool threadmode, bool spsel) { - /* Return a pointer to the location where we currently store the + /* + * Return a pointer to the location where we currently store the * stack pointer for the requested security state and thread mode. * This pointer will become invalid if the CPU state is updated * such that the stack pointers are switched around (eg changing @@ -XXX,XX +XXX,XX @@ static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure, mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, targets_secure, true); - /* We don't do a get_phys_addr() here because the rules for vector + /* + * We don't do a get_phys_addr() here because the rules for vector * loads are special: they always use the default memory map, and * the default memory map permits reads from all addresses. * Since there's no easy way to pass through to pmsav8_mpu_lookup() @@ -XXX,XX +XXX,XX @@ static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure, return true; load_fail: - /* All vector table fetch fails are reported as HardFault, with + /* + * All vector table fetch fails are reported as HardFault, with * HFSR.VECTTBL and .FORCED set. (FORCED is set because * technically the underlying exception is a MemManage or BusFault * that is escalated to HardFault.) This is a terminal exception, @@ -XXX,XX +XXX,XX @@ static uint32_t v7m_integrity_sig(CPUARMState *env, uint32_t lr) static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, bool ignore_faults) { - /* For v8M, push the callee-saves register part of the stack frame. + /* + * For v8M, push the callee-saves register part of the stack frame. * Compare the v8M pseudocode PushCalleeStack(). * In the tailchaining case this may not be the current stack. */ @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, return true; } - /* Write as much of the stack frame as we can. A write failure may + /* + * Write as much of the stack frame as we can. A write failure may * cause us to pend a derived exception. */ sig = v7m_integrity_sig(env, lr); @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, bool ignore_stackfaults) { - /* Do the "take the exception" parts of exception entry, + /* + * Do the "take the exception" parts of exception entry, * but not the pushing of state to the stack. This is * similar to the pseudocode ExceptionTaken() function. */ @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, if (arm_feature(env, ARM_FEATURE_V8)) { if (arm_feature(env, ARM_FEATURE_M_SECURITY) && (lr & R_V7M_EXCRET_S_MASK)) { - /* The background code (the owner of the registers in the + /* + * The background code (the owner of the registers in the * exception frame) is Secure. This means it may either already * have or now needs to push callee-saves registers. */ if (targets_secure) { if (dotailchain && !(lr & R_V7M_EXCRET_ES_MASK)) { - /* We took an exception from Secure to NonSecure + /* + * We took an exception from Secure to NonSecure * (which means the callee-saved registers got stacked) * and are now tailchaining to a Secure exception. * Clear DCRS so eventual return from this Secure @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, lr &= ~R_V7M_EXCRET_DCRS_MASK; } } else { - /* We're going to a non-secure exception; push the + /* + * We're going to a non-secure exception; push the * callee-saves registers to the stack now, if they're * not already saved. */ @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, lr |= R_V7M_EXCRET_SPSEL_MASK; } - /* Clear registers if necessary to prevent non-secure exception + /* + * Clear registers if necessary to prevent non-secure exception * code being able to see register values from secure code. * Where register values become architecturally UNKNOWN we leave * them with their previous values. */ if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { if (!targets_secure) { - /* Always clear the caller-saved registers (they have been + /* + * Always clear the caller-saved registers (they have been * pushed to the stack earlier in v7m_push_stack()). * Clear callee-saved registers if the background code is * Secure (in which case these regs were saved in @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, } if (push_failed && !ignore_stackfaults) { - /* Derived exception on callee-saves register stacking: + /* + * Derived exception on callee-saves register stacking: * we might now want to take a different exception which * targets a different security state, so try again from the top. */ @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, return; } - /* Now we've done everything that might cause a derived exception + /* + * Now we've done everything that might cause a derived exception * we can go ahead and activate whichever exception we're going to * take (which might now be the derived exception). */ @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) static bool v7m_push_stack(ARMCPU *cpu) { - /* Do the "set up stack frame" part of exception entry, + /* + * Do the "set up stack frame" part of exception entry, * similar to pseudocode PushStack(). * Return true if we generate a derived exception (and so * should ignore further stack faults trying to process @@ -XXX,XX +XXX,XX @@ static bool v7m_push_stack(ARMCPU *cpu) } } - /* Write as much of the stack frame as we can. If we fail a stack + /* + * Write as much of the stack frame as we can. If we fail a stack * write this will result in a derived exception being pended * (which may be taken in preference to the one we started with * if it has higher priority). @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) bool ftype; bool restore_s16_s31; - /* If we're not in Handler mode then jumps to magic exception-exit + /* + * If we're not in Handler mode then jumps to magic exception-exit * addresses don't have magic behaviour. However for the v8M * security extensions the magic secure-function-return has to * work in thread mode too, so to avoid doing an extra check in @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) return; } - /* In the spec pseudocode ExceptionReturn() is called directly + /* + * In the spec pseudocode ExceptionReturn() is called directly * from BXWritePC() and gets the full target PC value including * bit zero. In QEMU's implementation we treat it as a normal * jump-to-register (which is then caught later on), and so split @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) } if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { - /* EXC_RETURN.ES validation check (R_SMFL). We must do this before + /* + * EXC_RETURN.ES validation check (R_SMFL). We must do this before * we pick which FAULTMASK to clear. */ if (!env->v7m.secure && @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) } if (env->v7m.exception != ARMV7M_EXCP_NMI) { - /* Auto-clear FAULTMASK on return from other than NMI. + /* + * Auto-clear FAULTMASK on return from other than NMI. * If the security extension is implemented then this only * happens if the raw execution priority is >= 0; the * value of the ES bit in the exception return value indicates @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) /* still an irq active now */ break; case 1: - /* we returned to base exception level, no nesting. + /* + * We returned to base exception level, no nesting. * (In the pseudocode this is written using "NestedActivation != 1" * where we have 'rettobase == false'.) */ @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) if (arm_feature(env, ARM_FEATURE_V8)) { if (!arm_feature(env, ARM_FEATURE_M_SECURITY)) { - /* UNPREDICTABLE if S == 1 or DCRS == 0 or ES == 1 (R_XLCP); + /* + * UNPREDICTABLE if S == 1 or DCRS == 0 or ES == 1 (R_XLCP); * we choose to take the UsageFault. */ if ((excret & R_V7M_EXCRET_S_MASK) || @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) break; case 13: /* Return to Thread using Process stack */ case 9: /* Return to Thread using Main stack */ - /* We only need to check NONBASETHRDENA for v7M, because in + /* + * We only need to check NONBASETHRDENA for v7M, because in * v8M this bit does not exist (it is RES1). */ if (!rettobase && @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) } if (ufault) { - /* Bad exception return: instead of popping the exception + /* + * Bad exception return: instead of popping the exception * stack, directly take a usage fault on the current stack. */ env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK; @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) switch_v7m_security_state(env, return_to_secure); { - /* The stack pointer we should be reading the exception frame from + /* + * The stack pointer we should be reading the exception frame from * depends on bits in the magic exception return type value (and * for v8M isn't necessarily the stack pointer we will eventually * end up resuming execution with). Get a pointer to the location @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) v7m_stack_read(cpu, &xpsr, frameptr + 0x1c, mmu_idx); if (!pop_ok) { - /* v7m_stack_read() pended a fault, so take it (as a tail + /* + * v7m_stack_read() pended a fault, so take it (as a tail * chained exception on the same stack frame) */ qemu_log_mask(CPU_LOG_INT, "...derived exception on unstacking\n"); @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) return; } - /* Returning from an exception with a PC with bit 0 set is defined + /* + * Returning from an exception with a PC with bit 0 set is defined * behaviour on v8M (bit 0 is ignored), but for v7M it was specified * to be UNPREDICTABLE. In practice actual v7M hardware seems to ignore * the lsbit, and there are several RTOSes out there which incorrectly @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) } if (arm_feature(env, ARM_FEATURE_V8)) { - /* For v8M we have to check whether the xPSR exception field + /* + * For v8M we have to check whether the xPSR exception field * matches the EXCRET value for return to handler/thread * before we commit to changing the SP and xPSR. */ bool will_be_handler = (xpsr & XPSR_EXCP) != 0; if (return_to_handler != will_be_handler) { - /* Take an INVPC UsageFault on the current stack. + /* + * Take an INVPC UsageFault on the current stack. * By this point we will have switched to the security state * for the background state, so this UsageFault will target * that state. @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) frameptr += 0x40; } } - /* Undo stack alignment (the SPREALIGN bit indicates that the original + /* + * Undo stack alignment (the SPREALIGN bit indicates that the original * pre-exception SP was not 8-aligned and we added a padding word to * align it, so we undo this by ORing in the bit that increases it * from the current 8-aligned value to the 8-unaligned value. (Adding 4 @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) V7M_CONTROL, SFPA, sfpa); } - /* The restored xPSR exception field will be zero if we're + /* + * The restored xPSR exception field will be zero if we're * resuming in Thread mode. If that doesn't match what the * exception return excret specified then this is a UsageFault. * v7M requires we make this check here; v8M did it earlier. */ if (return_to_handler != arm_v7m_is_handler_mode(env)) { - /* Take an INVPC UsageFault by pushing the stack again; + /* + * Take an INVPC UsageFault by pushing the stack again; * we know we're v7M so this is never a Secure UsageFault. */ bool ignore_stackfaults; @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) static bool do_v7m_function_return(ARMCPU *cpu) { - /* v8M security extensions magic function return. + /* + * v8M security extensions magic function return. * We may either: * (1) throw an exception (longjump) * (2) return true if we successfully handled the function return @@ -XXX,XX +XXX,XX @@ static bool do_v7m_function_return(ARMCPU *cpu) frame_sp_p = get_v7m_sp_ptr(env, true, threadmode, spsel); frameptr = *frame_sp_p; - /* These loads may throw an exception (for MPU faults). We want to + /* + * These loads may throw an exception (for MPU faults). We want to * do them as secure, so work out what MMU index that is. */ mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true); @@ -XXX,XX +XXX,XX @@ static void arm_log_exception(int idx) static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, uint32_t addr, uint16_t *insn) { - /* Load a 16-bit portion of a v7M instruction, returning true on success, + /* + * Load a 16-bit portion of a v7M instruction, returning true on success, * or false on failure (in which case we will have pended the appropriate * exception). * We need to do the instruction fetch's MPU and SAU checks @@ -XXX,XX +XXX,XX @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, v8m_security_lookup(env, addr, MMU_INST_FETCH, mmu_idx, &sattrs); if (!sattrs.nsc || sattrs.ns) { - /* This must be the second half of the insn, and it straddles a + /* + * This must be the second half of the insn, and it straddles a * region boundary with the second half not being S&NSC. */ env->v7m.sfsr |= R_V7M_SFSR_INVEP_MASK; @@ -XXX,XX +XXX,XX @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, static bool v7m_handle_execute_nsc(ARMCPU *cpu) { - /* Check whether this attempt to execute code in a Secure & NS-Callable + /* + * Check whether this attempt to execute code in a Secure & NS-Callable * memory region is for an SG instruction; if so, then emulate the * effect of the SG instruction and return true. Otherwise pend * the correct kind of exception and return false. @@ -XXX,XX +XXX,XX @@ static bool v7m_handle_execute_nsc(ARMCPU *cpu) ARMMMUIdx mmu_idx; uint16_t insn; - /* We should never get here unless get_phys_addr_pmsav8() caused + /* + * We should never get here unless get_phys_addr_pmsav8() caused * an exception for NS executing in S&NSC memory. */ assert(!env->v7m.secure); @@ -XXX,XX +XXX,XX @@ static bool v7m_handle_execute_nsc(ARMCPU *cpu) } if (insn != 0xe97f) { - /* Not an SG instruction first half (we choose the IMPDEF + /* + * Not an SG instruction first half (we choose the IMPDEF * early-SG-check option). */ goto gen_invep; @@ -XXX,XX +XXX,XX @@ static bool v7m_handle_execute_nsc(ARMCPU *cpu) } if (insn != 0xe97f) { - /* Not an SG instruction second half (yes, both halves of the SG + /* + * Not an SG instruction second half (yes, both halves of the SG * insn have the same hex value) */ goto gen_invep; } - /* OK, we have confirmed that we really have an SG instruction. + /* + * OK, we have confirmed that we really have an SG instruction. * We know we're NS in S memory so don't need to repeat those checks. */ qemu_log_mask(CPU_LOG_INT, "...really an SG instruction at 0x%08" PRIx32 @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) arm_log_exception(cs->exception_index); - /* For exceptions we just mark as pending on the NVIC, and let that - handle it. */ + /* + * For exceptions we just mark as pending on the NVIC, and let that + * handle it. + */ switch (cs->exception_index) { case EXCP_UDEF: armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) break; case EXCP_PREFETCH_ABORT: case EXCP_DATA_ABORT: - /* Note that for M profile we don't have a guest facing FSR, but + /* + * Note that for M profile we don't have a guest facing FSR, but * the env->exception.fsr will be populated by the code that * raises the fault, in the A profile short-descriptor format. */ switch (env->exception.fsr & 0xf) { case M_FAKE_FSR_NSC_EXEC: - /* Exception generated when we try to execute code at an address + /* + * Exception generated when we try to execute code at an address * which is marked as Secure & Non-Secure Callable and the CPU * is in the Non-Secure state. The only instruction which can * be executed like this is SG (and that only if both halves of @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) } break; case M_FAKE_FSR_SFAULT: - /* Various flavours of SecureFault for attempts to execute or + /* + * Various flavours of SecureFault for attempts to execute or * access data in the wrong security state. */ switch (cs->exception_index) { @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS, false); break; default: - /* All other FSR values are either MPU faults or "can't happen + /* + * All other FSR values are either MPU faults or "can't happen * for M profile" cases. */ switch (cs->exception_index) { @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) if (arm_feature(env, ARM_FEATURE_V8)) { lr = R_V7M_EXCRET_RES1_MASK | R_V7M_EXCRET_DCRS_MASK; - /* The S bit indicates whether we should return to Secure + /* + * The S bit indicates whether we should return to Secure * or NonSecure (ie our current state). * The ES bit indicates whether we're taking this exception * to Secure or NonSecure (ie our target state). We set it @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) v7m_exception_taken(cpu, lr, false, ignore_stackfaults); } -/* Function used to synchronize QEMU's AArch64 register set with AArch32 +/* + * Function used to synchronize QEMU's AArch64 register set with AArch32 * register set. This is necessary when switching between AArch32 and AArch64 * execution state. */ @@ -XXX,XX +XXX,XX @@ void aarch64_sync_32_to_64(CPUARMState *env) env->xregs[i] = env->regs[i]; } - /* Unless we are in FIQ mode, x8-x12 come from the user registers r8-r12. + /* + * Unless we are in FIQ mode, x8-x12 come from the user registers r8-r12. * Otherwise, they come from the banked user regs. */ if (mode == ARM_CPU_MODE_FIQ) { @@ -XXX,XX +XXX,XX @@ void aarch64_sync_32_to_64(CPUARMState *env) } } - /* Registers x13-x23 are the various mode SP and FP registers. Registers + /* + * Registers x13-x23 are the various mode SP and FP registers. Registers * r13 and r14 are only copied if we are in that mode, otherwise we copy * from the mode banked register. */ @@ -XXX,XX +XXX,XX @@ void aarch64_sync_32_to_64(CPUARMState *env) env->xregs[23] = env->banked_r13[bank_number(ARM_CPU_MODE_UND)]; } - /* Registers x24-x30 are mapped to r8-r14 in FIQ mode. If we are in FIQ + /* + * Registers x24-x30 are mapped to r8-r14 in FIQ mode. If we are in FIQ * mode, then we can copy from r8-r14. Otherwise, we copy from the * FIQ bank for r8-r14. */ @@ -XXX,XX +XXX,XX @@ void aarch64_sync_32_to_64(CPUARMState *env) env->pc = env->regs[15]; } -/* Function used to synchronize QEMU's AArch32 register set with AArch64 +/* + * Function used to synchronize QEMU's AArch32 register set with AArch64 * register set. This is necessary when switching between AArch32 and AArch64 * execution state. */ @@ -XXX,XX +XXX,XX @@ void aarch64_sync_64_to_32(CPUARMState *env) env->regs[i] = env->xregs[i]; } - /* Unless we are in FIQ mode, r8-r12 come from the user registers x8-x12. + /* + * Unless we are in FIQ mode, r8-r12 come from the user registers x8-x12. * Otherwise, we copy x8-x12 into the banked user regs. */ if (mode == ARM_CPU_MODE_FIQ) { @@ -XXX,XX +XXX,XX @@ void aarch64_sync_64_to_32(CPUARMState *env) } } - /* Registers r13 & r14 depend on the current mode. + /* + * Registers r13 & r14 depend on the current mode. * If we are in a given mode, we copy the corresponding x registers to r13 * and r14. Otherwise, we copy the x register to the banked r13 and r14 * for the mode. @@ -XXX,XX +XXX,XX @@ void aarch64_sync_64_to_32(CPUARMState *env) } else { env->banked_r13[bank_number(ARM_CPU_MODE_USR)] = env->xregs[13]; - /* HYP is an exception in that it does not have its own banked r14 but + /* + * HYP is an exception in that it does not have its own banked r14 but * shares the USR r14 */ if (mode == ARM_CPU_MODE_HYP) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg) return value; } case 0x94: /* CONTROL_NS */ - /* We have to handle this here because unprivileged Secure code + /* + * We have to handle this here because unprivileged Secure code * can read the NS CONTROL register. */ if (!env->v7m.secure) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg) return env->v7m.faultmask[M_REG_NS]; case 0x98: /* SP_NS */ { - /* This gives the non-secure SP selected based on whether we're + /* + * This gives the non-secure SP selected based on whether we're * currently in handler mode or not, using the NS CONTROL.SPSEL. */ bool spsel = env->v7m.control[M_REG_NS] & R_V7M_CONTROL_SPSEL_MASK; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg) void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) { - /* We're passed bits [11..0] of the instruction; extract + /* + * We're passed bits [11..0] of the instruction; extract * SYSm and the mask bits. * Invalid combinations of SYSm and mask are UNPREDICTABLE; * we choose to treat them as if the mask bits were valid. @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) return; case 0x98: /* SP_NS */ { - /* This gives the non-secure SP selected based on whether we're + /* + * This gives the non-secure SP selected based on whether we're * currently in handler mode or not, using the NS CONTROL.SPSEL. */ bool spsel = env->v7m.control[M_REG_NS] & R_V7M_CONTROL_SPSEL_MASK; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) bool targetsec = env->v7m.secure; bool is_subpage; - /* Work out what the security state and privilege level we're + /* + * Work out what the security state and privilege level we're * interested in is... */ if (alt) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) /* ...and then figure out which MMU index this is */ mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, targetsec, targetpriv); - /* We know that the MPU and SAU don't care about the access type + /* + * We know that the MPU and SAU don't care about the access type * for our purposes beyond that we don't want to claim to be * an insn fetch, so we arbitrarily call this a read. */ - /* MPU region info only available for privileged or if + /* + * MPU region info only available for privileged or if * inspecting the other MPU state. */ if (arm_current_el(env) != 0 || alt) { @@ -XXX,XX +XXX,XX @@ bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size, void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) { - /* Implement DC ZVA, which zeroes a fixed-length block of memory. + /* + * Implement DC ZVA, which zeroes a fixed-length block of memory. * Note that we do not implement the (architecturally mandated) * alignment fault for attempts to use this on Device memory * (which matches the usual QEMU behaviour of not implementing either @@ -XXX,XX +XXX,XX @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) #ifndef CONFIG_USER_ONLY { - /* Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than + /* + * Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than * the block size so we might have to do more than one TLB lookup. * We know that in fact for any v8 CPU the page size is at least 4K * and the block size must be 2K or less, but TARGET_PAGE_SIZE is only @@ -XXX,XX +XXX,XX @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) } } if (i == maxidx) { - /* If it's all in the TLB it's fair game for just writing to; + /* + * If it's all in the TLB it's fair game for just writing to; * we know we don't need to update dirty status, etc. */ for (i = 0; i < maxidx - 1; i++) { @@ -XXX,XX +XXX,XX @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) memset(hostaddr[i], 0, blocklen - (i * TARGET_PAGE_SIZE)); return; } - /* OK, try a store and see if we can populate the tlb. This + /* + * OK, try a store and see if we can populate the tlb. This * might cause an exception if the memory isn't writable, * in which case we will longjmp out of here. We must for * this purpose use the actual register value passed to us @@ -XXX,XX +XXX,XX @@ void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) } } - /* Slow path (probably attempt to do this to an I/O device or + /* + * Slow path (probably attempt to do this to an I/O device or * similar, or clearing of a block of code we have translations * cached for). Just do a series of byte writes as the architecture * demands. It's not worth trying to use a cpu_physical_memory_map(), 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 @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn, { uint32_t syn; - /* ISV is only set for data aborts routed to EL2 and + /* + * ISV is only set for data aborts routed to EL2 and * never for stage-1 page table walks faulting on stage 2. * * Furthermore, ISV is only set for certain kinds of load/stores. @@ -XXX,XX +XXX,XX @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn, syn = syn_data_abort_no_iss(same_el, ea, 0, s1ptw, is_write, fsc); } else { - /* Fields: IL, ISV, SAS, SSE, SRT, SF and AR come from the template + /* + * Fields: IL, ISV, SAS, SSE, SRT, SF and AR come from the template * syndrome created at translation time. * Now we create the runtime syndrome with the remaining fields. */ @@ -XXX,XX +XXX,XX @@ void arm_deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type, if (target_el == 2 || arm_el_is_aa64(env, target_el) || arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) { - /* LPAE format fault status register : bottom 6 bits are + /* + * LPAE format fault status register : bottom 6 bits are * status code in the same form as needed for syndrome */ fsr = arm_fi_to_lfsc(fi); fsc = extract32(fsr, 0, 6); } else { fsr = arm_fi_to_sfsc(fi); - /* Short format FSR : this fault will never actually be reported + /* + * Short format FSR : this fault will never actually be reported * to an EL that uses a syndrome register. Use a (currently) * reserved FSR code in case the constructed syndrome does leak * into the guest somehow. @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, arm_deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi); } -/* arm_cpu_do_transaction_failed: handle a memory system error response +/* + * arm_cpu_do_transaction_failed: handle a memory system error response * (eg "no device/memory present at address") by raising an external abort * exception */ @@ -XXX,XX +XXX,XX @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn) int bt; uint32_t contextidr; - /* Links to unimplemented or non-context aware breakpoints are + /* + * Links to unimplemented or non-context aware breakpoints are * CONSTRAINED UNPREDICTABLE: either behave as if disabled, or * as if linked to an UNKNOWN context-aware breakpoint (in which * case DBGWCR<n>_EL1.LBN must indicate that breakpoint). @@ -XXX,XX +XXX,XX @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn) bt = extract64(bcr, 20, 4); - /* We match the whole register even if this is AArch32 using the + /* + * We match the whole register even if this is AArch32 using the * short descriptor format (in which case it holds both PROCID and ASID), * since we don't implement the optional v7 context ID masking. */ @@ -XXX,XX +XXX,XX @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn) case 9: /* linked VMID match (reserved if no EL2) */ case 11: /* linked context ID and VMID match (reserved if no EL2) */ default: - /* Links to Unlinked context breakpoints must generate no + /* + * Links to Unlinked context breakpoints must generate no * events; we choose to do the same for reserved values too. */ return false; @@ -XXX,XX +XXX,XX @@ static bool bp_wp_matches(ARMCPU *cpu, int n, bool is_wp) CPUARMState *env = &cpu->env; uint64_t cr; int pac, hmc, ssc, wt, lbn; - /* Note that for watchpoints the check is against the CPU security + /* + * Note that for watchpoints the check is against the CPU security * state, not the S/NS attribute on the offending data access. */ bool is_secure = arm_is_secure(env); @@ -XXX,XX +XXX,XX @@ static bool bp_wp_matches(ARMCPU *cpu, int n, bool is_wp) } cr = env->cp15.dbgwcr[n]; if (wp->hitattrs.user) { - /* The LDRT/STRT/LDT/STT "unprivileged access" instructions should + /* + * The LDRT/STRT/LDT/STT "unprivileged access" instructions should * match watchpoints as if they were accesses done at EL0, even if * the CPU is at EL1 or higher. */ @@ -XXX,XX +XXX,XX @@ static bool bp_wp_matches(ARMCPU *cpu, int n, bool is_wp) } cr = env->cp15.dbgbcr[n]; } - /* The WATCHPOINT_HIT flag guarantees us that the watchpoint is + /* + * The WATCHPOINT_HIT flag guarantees us that the watchpoint is * enabled and that the address and access type match; for breakpoints * we know the address matched; check the remaining fields, including * linked breakpoints. We rely on WCR and BCR having the same layout @@ -XXX,XX +XXX,XX @@ static bool check_watchpoints(ARMCPU *cpu) CPUARMState *env = &cpu->env; int n; - /* If watchpoints are disabled globally or we can't take debug + /* + * If watchpoints are disabled globally or we can't take debug * exceptions here then watchpoint firings are ignored. */ if (extract32(env->cp15.mdscr_el1, 15, 1) == 0 @@ -XXX,XX +XXX,XX @@ static bool check_breakpoints(ARMCPU *cpu) CPUARMState *env = &cpu->env; int n; - /* If breakpoints are disabled globally or we can't take debug + /* + * If breakpoints are disabled globally or we can't take debug * exceptions here then breakpoint firings are ignored. */ if (extract32(env->cp15.mdscr_el1, 15, 1) == 0 @@ -XXX,XX +XXX,XX @@ void HELPER(check_breakpoints)(CPUARMState *env) bool arm_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp) { - /* Called by core code when a CPU watchpoint fires; need to check if this + /* + * Called by core code when a CPU watchpoint fires; need to check if this * is also an architectural watchpoint match. */ ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len) ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; - /* In BE32 system mode, target memory is stored byteswapped (on a + /* + * In BE32 system mode, target memory is stored byteswapped (on a * little-endian host system), and by the time we reach here (via an * opcode helper) the addresses of subword accesses have been adjusted * to account for that, which means that watchpoints will not match. @@ -XXX,XX +XXX,XX @@ vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len) void arm_debug_excp_handler(CPUState *cs) { - /* Called by core code when a watchpoint or breakpoint fires; + /* + * Called by core code when a watchpoint or breakpoint fires; * need to check which one and raise the appropriate exception. */ ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ void arm_debug_excp_handler(CPUState *cs) uint64_t pc = is_a64(env) ? env->pc : env->regs[15]; bool same_el = (arm_debug_target_el(env) == arm_current_el(env)); - /* (1) GDB breakpoints should be handled first. + /* + * (1) GDB breakpoints should be handled first. * (2) Do not raise a CPU exception if no CPU breakpoint has fired, * since singlestep is also done by generating a debug internal * exception. @@ -XXX,XX +XXX,XX @@ void arm_debug_excp_handler(CPUState *cs) } env->exception.fsr = arm_debug_exception_fsr(env); - /* FAR is UNKNOWN: clear vaddress to avoid potentially exposing + /* + * FAR is UNKNOWN: clear vaddress to avoid potentially exposing * values to the guest that it shouldn't be able to see at its * exception/security level. */ diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); } - /* The exception flags are ORed together when we read fpscr so we + /* + * The exception flags are ORed together when we read fpscr so we * only need to preserve the current state in one of our * float_status values. */ -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Since we'll move this code around, fix its style first. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-9-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 11 ++++++----- target/arm/vfp_helper.c | 36 ++++++++++++++++++++++++------------ 2 files changed, 30 insertions(+), 17 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) loaded_base = 0; loaded_var = NULL; n = 0; - for(i=0;i<16;i++) { + for (i = 0; i < 16; i++) { if (insn & (1 << i)) n++; } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } } j = 0; - for(i=0;i<16;i++) { + for (i = 0; i < 16; i++) { if (insn & (1 << i)) { if (is_load) { /* load */ @@ -XXX,XX +XXX,XX @@ void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) return; } - for(i=0;i<16;i++) { + for (i = 0; i < 16; i++) { qemu_fprintf(f, "R%02d=%08x", i, env->regs[i]); - if ((i % 4) == 3) + if ((i % 4) == 3) { qemu_fprintf(f, "\n"); - else + } else { qemu_fprintf(f, " "); + } } if (arm_feature(env, ARM_FEATURE_M)) { diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_from_host(int host_bits) { int target_bits = 0; - if (host_bits & float_flag_invalid) + if (host_bits & float_flag_invalid) { target_bits |= 1; - if (host_bits & float_flag_divbyzero) + } + if (host_bits & float_flag_divbyzero) { target_bits |= 2; - if (host_bits & float_flag_overflow) + } + if (host_bits & float_flag_overflow) { target_bits |= 4; - if (host_bits & (float_flag_underflow | float_flag_output_denormal)) + } + if (host_bits & (float_flag_underflow | float_flag_output_denormal)) { target_bits |= 8; - if (host_bits & float_flag_inexact) + } + if (host_bits & float_flag_inexact) { target_bits |= 0x10; - if (host_bits & float_flag_input_denormal) + } + if (host_bits & float_flag_input_denormal) { target_bits |= 0x80; + } return target_bits; } @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_to_host(int target_bits) { int host_bits = 0; - if (target_bits & 1) + if (target_bits & 1) { host_bits |= float_flag_invalid; - if (target_bits & 2) + } + if (target_bits & 2) { host_bits |= float_flag_divbyzero; - if (target_bits & 4) + } + if (target_bits & 4) { host_bits |= float_flag_overflow; - if (target_bits & 8) + } + if (target_bits & 8) { host_bits |= float_flag_underflow; - if (target_bits & 0x10) + } + if (target_bits & 0x10) { host_bits |= float_flag_inexact; - if (target_bits & 0x80) + } + if (target_bits & 0x80) { host_bits |= float_flag_input_denormal; + } return host_bits; } -- 2.20.1 From: Samuel Ortiz <sameo@linux.intel.com> Those helpers are a software implementation of the ARM v8 memory zeroing op code. They should be moved to the op helper file, which is going to eventually be built only when TCG is enabled. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Robert Bradford <robert.bradford@intel.com> Signed-off-by: Samuel Ortiz <sameo@linux.intel.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-10-philmd@redhat.com [PMD: Rebased] Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 92 ----------------------------------------- target/arm/op_helper.c | 93 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 93 insertions(+), 92 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 @@ bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size, #endif } -void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) -{ - /* - * Implement DC ZVA, which zeroes a fixed-length block of memory. - * Note that we do not implement the (architecturally mandated) - * alignment fault for attempts to use this on Device memory - * (which matches the usual QEMU behaviour of not implementing either - * alignment faults or any memory attribute handling). - */ - - ARMCPU *cpu = env_archcpu(env); - uint64_t blocklen = 4 << cpu->dcz_blocksize; - uint64_t vaddr = vaddr_in & ~(blocklen - 1); - -#ifndef CONFIG_USER_ONLY - { - /* - * Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than - * the block size so we might have to do more than one TLB lookup. - * We know that in fact for any v8 CPU the page size is at least 4K - * and the block size must be 2K or less, but TARGET_PAGE_SIZE is only - * 1K as an artefact of legacy v5 subpage support being present in the - * same QEMU executable. So in practice the hostaddr[] array has - * two entries, given the current setting of TARGET_PAGE_BITS_MIN. - */ - int maxidx = DIV_ROUND_UP(blocklen, TARGET_PAGE_SIZE); - void *hostaddr[DIV_ROUND_UP(2 * KiB, 1 << TARGET_PAGE_BITS_MIN)]; - int try, i; - unsigned mmu_idx = cpu_mmu_index(env, false); - TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); - - assert(maxidx <= ARRAY_SIZE(hostaddr)); - - for (try = 0; try < 2; try++) { - - for (i = 0; i < maxidx; i++) { - hostaddr[i] = tlb_vaddr_to_host(env, - vaddr + TARGET_PAGE_SIZE * i, - 1, mmu_idx); - if (!hostaddr[i]) { - break; - } - } - if (i == maxidx) { - /* - * If it's all in the TLB it's fair game for just writing to; - * we know we don't need to update dirty status, etc. - */ - for (i = 0; i < maxidx - 1; i++) { - memset(hostaddr[i], 0, TARGET_PAGE_SIZE); - } - memset(hostaddr[i], 0, blocklen - (i * TARGET_PAGE_SIZE)); - return; - } - /* - * OK, try a store and see if we can populate the tlb. This - * might cause an exception if the memory isn't writable, - * in which case we will longjmp out of here. We must for - * this purpose use the actual register value passed to us - * so that we get the fault address right. - */ - helper_ret_stb_mmu(env, vaddr_in, 0, oi, GETPC()); - /* Now we can populate the other TLB entries, if any */ - for (i = 0; i < maxidx; i++) { - uint64_t va = vaddr + TARGET_PAGE_SIZE * i; - if (va != (vaddr_in & TARGET_PAGE_MASK)) { - helper_ret_stb_mmu(env, va, 0, oi, GETPC()); - } - } - } - - /* - * Slow path (probably attempt to do this to an I/O device or - * similar, or clearing of a block of code we have translations - * cached for). Just do a series of byte writes as the architecture - * demands. It's not worth trying to use a cpu_physical_memory_map(), - * memset(), unmap() sequence here because: - * + we'd need to account for the blocksize being larger than a page - * + the direct-RAM access case is almost always going to be dealt - * with in the fastpath code above, so there's no speed benefit - * + we would have to deal with the map returning NULL because the - * bounce buffer was in use - */ - for (i = 0; i < blocklen; i++) { - helper_ret_stb_mmu(env, vaddr + i, 0, oi, GETPC()); - } - } -#else - memset(g2h(vaddr), 0, blocklen); -#endif -} - /* Note that signed overflow is undefined in C. The following routines are careful to use unsigned types where modulo arithmetic is required. Failure to do so _will_ break on newer gcc. */ 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 @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/log.h" #include "qemu/main-loop.h" #include "cpu.h" @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(ror_cc)(CPUARMState *env, uint32_t x, uint32_t i) return ((uint32_t)x >> shift) | (x << (32 - shift)); } } + +void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) +{ + /* + * Implement DC ZVA, which zeroes a fixed-length block of memory. + * Note that we do not implement the (architecturally mandated) + * alignment fault for attempts to use this on Device memory + * (which matches the usual QEMU behaviour of not implementing either + * alignment faults or any memory attribute handling). + */ + + ARMCPU *cpu = env_archcpu(env); + uint64_t blocklen = 4 << cpu->dcz_blocksize; + uint64_t vaddr = vaddr_in & ~(blocklen - 1); + +#ifndef CONFIG_USER_ONLY + { + /* + * Slightly awkwardly, QEMU's TARGET_PAGE_SIZE may be less than + * the block size so we might have to do more than one TLB lookup. + * We know that in fact for any v8 CPU the page size is at least 4K + * and the block size must be 2K or less, but TARGET_PAGE_SIZE is only + * 1K as an artefact of legacy v5 subpage support being present in the + * same QEMU executable. So in practice the hostaddr[] array has + * two entries, given the current setting of TARGET_PAGE_BITS_MIN. + */ + int maxidx = DIV_ROUND_UP(blocklen, TARGET_PAGE_SIZE); + void *hostaddr[DIV_ROUND_UP(2 * KiB, 1 << TARGET_PAGE_BITS_MIN)]; + int try, i; + unsigned mmu_idx = cpu_mmu_index(env, false); + TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); + + assert(maxidx <= ARRAY_SIZE(hostaddr)); + + for (try = 0; try < 2; try++) { + + for (i = 0; i < maxidx; i++) { + hostaddr[i] = tlb_vaddr_to_host(env, + vaddr + TARGET_PAGE_SIZE * i, + 1, mmu_idx); + if (!hostaddr[i]) { + break; + } + } + if (i == maxidx) { + /* + * If it's all in the TLB it's fair game for just writing to; + * we know we don't need to update dirty status, etc. + */ + for (i = 0; i < maxidx - 1; i++) { + memset(hostaddr[i], 0, TARGET_PAGE_SIZE); + } + memset(hostaddr[i], 0, blocklen - (i * TARGET_PAGE_SIZE)); + return; + } + /* + * OK, try a store and see if we can populate the tlb. This + * might cause an exception if the memory isn't writable, + * in which case we will longjmp out of here. We must for + * this purpose use the actual register value passed to us + * so that we get the fault address right. + */ + helper_ret_stb_mmu(env, vaddr_in, 0, oi, GETPC()); + /* Now we can populate the other TLB entries, if any */ + for (i = 0; i < maxidx; i++) { + uint64_t va = vaddr + TARGET_PAGE_SIZE * i; + if (va != (vaddr_in & TARGET_PAGE_MASK)) { + helper_ret_stb_mmu(env, va, 0, oi, GETPC()); + } + } + } + + /* + * Slow path (probably attempt to do this to an I/O device or + * similar, or clearing of a block of code we have translations + * cached for). Just do a series of byte writes as the architecture + * demands. It's not worth trying to use a cpu_physical_memory_map(), + * memset(), unmap() sequence here because: + * + we'd need to account for the blocksize being larger than a page + * + the direct-RAM access case is almost always going to be dealt + * with in the fastpath code above, so there's no speed benefit + * + we would have to deal with the map returning NULL because the + * bounce buffer was in use + */ + for (i = 0; i < blocklen; i++) { + helper_ret_stb_mmu(env, vaddr + i, 0, oi, GETPC()); + } + } +#else + memset(g2h(vaddr), 0, blocklen); +#endif +} -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Suggested-by: Samuel Ortiz <sameo@linux.intel.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-11-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 - target/arm/translate.h | 5 - target/arm/cpu.c | 226 +++++++++++++++++++++++++++++++++++++ target/arm/translate-a64.c | 128 --------------------- target/arm/translate.c | 88 --------------- 5 files changed, 226 insertions(+), 223 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_interrupt(CPUState *cpu); void arm_v7m_cpu_do_interrupt(CPUState *cpu); bool arm_cpu_exec_interrupt(CPUState *cpu, int int_req); -void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags); - hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, MemTxAttrs *attrs); 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 disas_set_insn_syndrome(DisasContext *s, uint32_t syn) #ifdef TARGET_AARCH64 void a64_translate_init(void); void gen_a64_set_pc_im(uint64_t val); -void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags); extern const TranslatorOps aarch64_translator_ops; #else static inline void a64_translate_init(void) @@ -XXX,XX +XXX,XX @@ static inline void a64_translate_init(void) static inline void gen_a64_set_pc_im(uint64_t val) { } - -static inline void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) -{ -} #endif void arm_test_cc(DisasCompare *cmp, int cc); 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 @@ */ #include "qemu/osdep.h" +#include "qemu/qemu-print.h" #include "qemu-common.h" #include "target/arm/idau.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ static void arm_disas_set_info(CPUState *cpu, disassemble_info *info) #endif } +#ifdef TARGET_AARCH64 + +static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + uint32_t psr = pstate_read(env); + int i; + int el = arm_current_el(env); + const char *ns_status; + + qemu_fprintf(f, " PC=%016" PRIx64 " ", env->pc); + for (i = 0; i < 32; i++) { + if (i == 31) { + qemu_fprintf(f, " SP=%016" PRIx64 "\n", env->xregs[i]); + } else { + qemu_fprintf(f, "X%02d=%016" PRIx64 "%s", i, env->xregs[i], + (i + 2) % 3 ? " " : "\n"); + } + } + + if (arm_feature(env, ARM_FEATURE_EL3) && el != 3) { + ns_status = env->cp15.scr_el3 & SCR_NS ? "NS " : "S "; + } else { + ns_status = ""; + } + qemu_fprintf(f, "PSTATE=%08x %c%c%c%c %sEL%d%c", + psr, + psr & PSTATE_N ? 'N' : '-', + psr & PSTATE_Z ? 'Z' : '-', + psr & PSTATE_C ? 'C' : '-', + psr & PSTATE_V ? 'V' : '-', + ns_status, + el, + psr & PSTATE_SP ? 'h' : 't'); + + if (cpu_isar_feature(aa64_bti, cpu)) { + qemu_fprintf(f, " BTYPE=%d", (psr & PSTATE_BTYPE) >> 10); + } + if (!(flags & CPU_DUMP_FPU)) { + qemu_fprintf(f, "\n"); + return; + } + if (fp_exception_el(env, el) != 0) { + qemu_fprintf(f, " FPU disabled\n"); + return; + } + qemu_fprintf(f, " FPCR=%08x FPSR=%08x\n", + vfp_get_fpcr(env), vfp_get_fpsr(env)); + + if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { + int j, zcr_len = sve_zcr_len_for_el(env, el); + + for (i = 0; i <= FFR_PRED_NUM; i++) { + bool eol; + if (i == FFR_PRED_NUM) { + qemu_fprintf(f, "FFR="); + /* It's last, so end the line. */ + eol = true; + } else { + qemu_fprintf(f, "P%02d=", i); + switch (zcr_len) { + case 0: + eol = i % 8 == 7; + break; + case 1: + eol = i % 6 == 5; + break; + case 2: + case 3: + eol = i % 3 == 2; + break; + default: + /* More than one quadword per predicate. */ + eol = true; + break; + } + } + for (j = zcr_len / 4; j >= 0; j--) { + int digits; + if (j * 4 + 4 <= zcr_len + 1) { + digits = 16; + } else { + digits = (zcr_len % 4 + 1) * 4; + } + qemu_fprintf(f, "%0*" PRIx64 "%s", digits, + env->vfp.pregs[i].p[j], + j ? ":" : eol ? "\n" : " "); + } + } + + for (i = 0; i < 32; i++) { + if (zcr_len == 0) { + qemu_fprintf(f, "Z%02d=%016" PRIx64 ":%016" PRIx64 "%s", + i, env->vfp.zregs[i].d[1], + env->vfp.zregs[i].d[0], i & 1 ? "\n" : " "); + } else if (zcr_len == 1) { + qemu_fprintf(f, "Z%02d=%016" PRIx64 ":%016" PRIx64 + ":%016" PRIx64 ":%016" PRIx64 "\n", + i, env->vfp.zregs[i].d[3], env->vfp.zregs[i].d[2], + env->vfp.zregs[i].d[1], env->vfp.zregs[i].d[0]); + } else { + for (j = zcr_len; j >= 0; j--) { + bool odd = (zcr_len - j) % 2 != 0; + if (j == zcr_len) { + qemu_fprintf(f, "Z%02d[%x-%x]=", i, j, j - 1); + } else if (!odd) { + if (j > 0) { + qemu_fprintf(f, " [%x-%x]=", j, j - 1); + } else { + qemu_fprintf(f, " [%x]=", j); + } + } + qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%s", + env->vfp.zregs[i].d[j * 2 + 1], + env->vfp.zregs[i].d[j * 2], + odd || j == 0 ? "\n" : ":"); + } + } + } + } else { + for (i = 0; i < 32; i++) { + uint64_t *q = aa64_vfp_qreg(env, i); + qemu_fprintf(f, "Q%02d=%016" PRIx64 ":%016" PRIx64 "%s", + i, q[1], q[0], (i & 1 ? "\n" : " ")); + } + } +} + +#else + +static inline void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) +{ + g_assert_not_reached(); +} + +#endif + +static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + int i; + + if (is_a64(env)) { + aarch64_cpu_dump_state(cs, f, flags); + return; + } + + for (i = 0; i < 16; i++) { + qemu_fprintf(f, "R%02d=%08x", i, env->regs[i]); + if ((i % 4) == 3) { + qemu_fprintf(f, "\n"); + } else { + qemu_fprintf(f, " "); + } + } + + if (arm_feature(env, ARM_FEATURE_M)) { + uint32_t xpsr = xpsr_read(env); + const char *mode; + const char *ns_status = ""; + + if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { + ns_status = env->v7m.secure ? "S " : "NS "; + } + + if (xpsr & XPSR_EXCP) { + mode = "handler"; + } else { + if (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_NPRIV_MASK) { + mode = "unpriv-thread"; + } else { + mode = "priv-thread"; + } + } + + qemu_fprintf(f, "XPSR=%08x %c%c%c%c %c %s%s\n", + xpsr, + xpsr & XPSR_N ? 'N' : '-', + xpsr & XPSR_Z ? 'Z' : '-', + xpsr & XPSR_C ? 'C' : '-', + xpsr & XPSR_V ? 'V' : '-', + xpsr & XPSR_T ? 'T' : 'A', + ns_status, + mode); + } else { + uint32_t psr = cpsr_read(env); + const char *ns_status = ""; + + if (arm_feature(env, ARM_FEATURE_EL3) && + (psr & CPSR_M) != ARM_CPU_MODE_MON) { + ns_status = env->cp15.scr_el3 & SCR_NS ? "NS " : "S "; + } + + qemu_fprintf(f, "PSR=%08x %c%c%c%c %c %s%s%d\n", + psr, + psr & CPSR_N ? 'N' : '-', + psr & CPSR_Z ? 'Z' : '-', + psr & CPSR_C ? 'C' : '-', + psr & CPSR_V ? 'V' : '-', + psr & CPSR_T ? 'T' : 'A', + ns_status, + aarch32_mode_name(psr), (psr & 0x10) ? 32 : 26); + } + + if (flags & CPU_DUMP_FPU) { + int numvfpregs = 0; + if (arm_feature(env, ARM_FEATURE_VFP)) { + numvfpregs += 16; + } + if (arm_feature(env, ARM_FEATURE_VFP3)) { + numvfpregs += 16; + } + for (i = 0; i < numvfpregs; i++) { + uint64_t v = *aa32_vfp_dreg(env, i); + qemu_fprintf(f, "s%02d=%08x s%02d=%08x d%02d=%016" PRIx64 "\n", + i * 2, (uint32_t)v, + i * 2 + 1, (uint32_t)(v >> 32), + i, v); + } + qemu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); + } +} + uint64_t arm_cpu_mp_affinity(int idx, uint8_t clustersz) { uint32_t Aff1 = idx / clustersz; 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 @@ #include "translate.h" #include "internals.h" #include "qemu/host-utils.h" -#include "qemu/qemu-print.h" #include "hw/semihosting/semihost.h" #include "exec/gen-icount.h" @@ -XXX,XX +XXX,XX @@ static void set_btype(DisasContext *s, int val) s->btype = -1; } -void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) -{ - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - uint32_t psr = pstate_read(env); - int i; - int el = arm_current_el(env); - const char *ns_status; - - qemu_fprintf(f, " PC=%016" PRIx64 " ", env->pc); - for (i = 0; i < 32; i++) { - if (i == 31) { - qemu_fprintf(f, " SP=%016" PRIx64 "\n", env->xregs[i]); - } else { - qemu_fprintf(f, "X%02d=%016" PRIx64 "%s", i, env->xregs[i], - (i + 2) % 3 ? " " : "\n"); - } - } - - if (arm_feature(env, ARM_FEATURE_EL3) && el != 3) { - ns_status = env->cp15.scr_el3 & SCR_NS ? "NS " : "S "; - } else { - ns_status = ""; - } - qemu_fprintf(f, "PSTATE=%08x %c%c%c%c %sEL%d%c", - psr, - psr & PSTATE_N ? 'N' : '-', - psr & PSTATE_Z ? 'Z' : '-', - psr & PSTATE_C ? 'C' : '-', - psr & PSTATE_V ? 'V' : '-', - ns_status, - el, - psr & PSTATE_SP ? 'h' : 't'); - - if (cpu_isar_feature(aa64_bti, cpu)) { - qemu_fprintf(f, " BTYPE=%d", (psr & PSTATE_BTYPE) >> 10); - } - if (!(flags & CPU_DUMP_FPU)) { - qemu_fprintf(f, "\n"); - return; - } - if (fp_exception_el(env, el) != 0) { - qemu_fprintf(f, " FPU disabled\n"); - return; - } - qemu_fprintf(f, " FPCR=%08x FPSR=%08x\n", - vfp_get_fpcr(env), vfp_get_fpsr(env)); - - if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { - int j, zcr_len = sve_zcr_len_for_el(env, el); - - for (i = 0; i <= FFR_PRED_NUM; i++) { - bool eol; - if (i == FFR_PRED_NUM) { - qemu_fprintf(f, "FFR="); - /* It's last, so end the line. */ - eol = true; - } else { - qemu_fprintf(f, "P%02d=", i); - switch (zcr_len) { - case 0: - eol = i % 8 == 7; - break; - case 1: - eol = i % 6 == 5; - break; - case 2: - case 3: - eol = i % 3 == 2; - break; - default: - /* More than one quadword per predicate. */ - eol = true; - break; - } - } - for (j = zcr_len / 4; j >= 0; j--) { - int digits; - if (j * 4 + 4 <= zcr_len + 1) { - digits = 16; - } else { - digits = (zcr_len % 4 + 1) * 4; - } - qemu_fprintf(f, "%0*" PRIx64 "%s", digits, - env->vfp.pregs[i].p[j], - j ? ":" : eol ? "\n" : " "); - } - } - - for (i = 0; i < 32; i++) { - if (zcr_len == 0) { - qemu_fprintf(f, "Z%02d=%016" PRIx64 ":%016" PRIx64 "%s", - i, env->vfp.zregs[i].d[1], - env->vfp.zregs[i].d[0], i & 1 ? "\n" : " "); - } else if (zcr_len == 1) { - qemu_fprintf(f, "Z%02d=%016" PRIx64 ":%016" PRIx64 - ":%016" PRIx64 ":%016" PRIx64 "\n", - i, env->vfp.zregs[i].d[3], env->vfp.zregs[i].d[2], - env->vfp.zregs[i].d[1], env->vfp.zregs[i].d[0]); - } else { - for (j = zcr_len; j >= 0; j--) { - bool odd = (zcr_len - j) % 2 != 0; - if (j == zcr_len) { - qemu_fprintf(f, "Z%02d[%x-%x]=", i, j, j - 1); - } else if (!odd) { - if (j > 0) { - qemu_fprintf(f, " [%x-%x]=", j, j - 1); - } else { - qemu_fprintf(f, " [%x]=", j); - } - } - qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%s", - env->vfp.zregs[i].d[j * 2 + 1], - env->vfp.zregs[i].d[j * 2], - odd || j == 0 ? "\n" : ":"); - } - } - } - } else { - for (i = 0; i < 32; i++) { - uint64_t *q = aa64_vfp_qreg(env, i); - qemu_fprintf(f, "Q%02d=%016" PRIx64 ":%016" PRIx64 "%s", - i, q[1], q[0], (i & 1 ? "\n" : " ")); - } - } -} - void gen_a64_set_pc_im(uint64_t val) { tcg_gen_movi_i64(cpu_pc, val); 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 @@ #include "tcg-op-gvec.h" #include "qemu/log.h" #include "qemu/bitops.h" -#include "qemu/qemu-print.h" #include "arm_ldst.h" #include "hw/semihosting/semihost.h" @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int max_insns) translator_loop(ops, &dc.base, cpu, tb, max_insns); } -void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) -{ - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - int i; - - if (is_a64(env)) { - aarch64_cpu_dump_state(cs, f, flags); - return; - } - - for (i = 0; i < 16; i++) { - qemu_fprintf(f, "R%02d=%08x", i, env->regs[i]); - if ((i % 4) == 3) { - qemu_fprintf(f, "\n"); - } else { - qemu_fprintf(f, " "); - } - } - - if (arm_feature(env, ARM_FEATURE_M)) { - uint32_t xpsr = xpsr_read(env); - const char *mode; - const char *ns_status = ""; - - if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { - ns_status = env->v7m.secure ? "S " : "NS "; - } - - if (xpsr & XPSR_EXCP) { - mode = "handler"; - } else { - if (env->v7m.control[env->v7m.secure] & R_V7M_CONTROL_NPRIV_MASK) { - mode = "unpriv-thread"; - } else { - mode = "priv-thread"; - } - } - - qemu_fprintf(f, "XPSR=%08x %c%c%c%c %c %s%s\n", - xpsr, - xpsr & XPSR_N ? 'N' : '-', - xpsr & XPSR_Z ? 'Z' : '-', - xpsr & XPSR_C ? 'C' : '-', - xpsr & XPSR_V ? 'V' : '-', - xpsr & XPSR_T ? 'T' : 'A', - ns_status, - mode); - } else { - uint32_t psr = cpsr_read(env); - const char *ns_status = ""; - - if (arm_feature(env, ARM_FEATURE_EL3) && - (psr & CPSR_M) != ARM_CPU_MODE_MON) { - ns_status = env->cp15.scr_el3 & SCR_NS ? "NS " : "S "; - } - - qemu_fprintf(f, "PSR=%08x %c%c%c%c %c %s%s%d\n", - psr, - psr & CPSR_N ? 'N' : '-', - psr & CPSR_Z ? 'Z' : '-', - psr & CPSR_C ? 'C' : '-', - psr & CPSR_V ? 'V' : '-', - psr & CPSR_T ? 'T' : 'A', - ns_status, - aarch32_mode_name(psr), (psr & 0x10) ? 32 : 26); - } - - if (flags & CPU_DUMP_FPU) { - int numvfpregs = 0; - if (arm_feature(env, ARM_FEATURE_VFP)) { - numvfpregs += 16; - } - if (arm_feature(env, ARM_FEATURE_VFP3)) { - numvfpregs += 16; - } - for (i = 0; i < numvfpregs; i++) { - uint64_t v = *aa32_vfp_dreg(env, i); - qemu_fprintf(f, "s%02d=%08x s%02d=%08x d%02d=%016" PRIx64 "\n", - i * 2, (uint32_t)v, - i * 2 + 1, (uint32_t)(v >> 32), - i, v); - } - qemu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); - } -} - void restore_state_to_opc(CPUARMState *env, TranslationBlock *tb, target_ulong *data) { -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> In the next commit we will split the TLB related routines of this file, and this function will also be called in the new file. Declare it in the "internals.h" header. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-12-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 16 ++++++++++++++++ target/arm/helper.c | 21 +++++---------------- 2 files changed, 21 insertions(+), 16 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 int exception_target_el(CPUARMState *env) return target_el; } +#ifndef CONFIG_USER_ONLY + +/* Cacheability and shareability attributes for a memory access */ +typedef struct ARMCacheAttrs { + unsigned int attrs:8; /* as in the MAIR register encoding */ + unsigned int shareability:2; /* as in the SH field of the VMSAv8-64 PTEs */ +} ARMCacheAttrs; + +bool get_phys_addr(CPUARMState *env, target_ulong address, + MMUAccessType access_type, ARMMMUIdx mmu_idx, + hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot, + target_ulong *page_size, + ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs); + +#endif /* !CONFIG_USER_ONLY */ + #endif 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 @@ #define ARM_CPU_FREQ 1000000000 /* FIXME: 1 GHz, should be configurable */ #ifndef CONFIG_USER_ONLY -/* Cacheability and shareability attributes for a memory access */ -typedef struct ARMCacheAttrs { - unsigned int attrs:8; /* as in the MAIR register encoding */ - unsigned int shareability:2; /* as in the SH field of the VMSAv8-64 PTEs */ -} ARMCacheAttrs; - -static bool get_phys_addr(CPUARMState *env, target_ulong address, - MMUAccessType access_type, ARMMMUIdx mmu_idx, - hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot, - target_ulong *page_size, - ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs); static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, MMUAccessType access_type, ARMMMUIdx mmu_idx, @@ -XXX,XX +XXX,XX @@ static ARMCacheAttrs combine_cacheattrs(ARMCacheAttrs s1, ARMCacheAttrs s2) * @fi: set to fault info if the translation fails * @cacheattrs: (if non-NULL) set to the cacheability/shareability attributes */ -static bool get_phys_addr(CPUARMState *env, target_ulong address, - MMUAccessType access_type, ARMMMUIdx mmu_idx, - hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot, - target_ulong *page_size, - ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs) +bool get_phys_addr(CPUARMState *env, target_ulong address, + MMUAccessType access_type, ARMMMUIdx mmu_idx, + hwaddr *phys_ptr, MemTxAttrs *attrs, int *prot, + target_ulong *page_size, + ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs) { if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { /* Call ourselves recursively to do the stage 1 and then stage 2 -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> These routines are TCG specific. The arm_deliver_fault() function is only used within the new helper. Make it static. Suggested-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-13-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 1 + target/arm/internals.h | 3 - target/arm/cpu.c | 6 +- target/arm/helper.c | 53 ----------- target/arm/op_helper.c | 135 -------------------------- target/arm/tlb_helper.c | 200 +++++++++++++++++++++++++++++++++++++++ 6 files changed, 205 insertions(+), 193 deletions(-) create mode 100644 target/arm/tlb_helper.c diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ target/arm/translate-sve.o: target/arm/decode-sve.inc.c target/arm/translate.o: target/arm/decode-vfp.inc.c target/arm/translate.o: target/arm/decode-vfp-uncond.inc.c +obj-y += tlb_helper.o obj-y += translate.o op_helper.o obj-y += crypto_helper.o obj-y += iwmmxt_helper.o vec_helper.o neon_helper.o 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 @@ bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size, MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr); -void arm_deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type, - int mmu_idx, ARMMMUFaultInfo *fi) QEMU_NORETURN; - /* Return true if the stage 1 translation regime is using LPAE format page * tables */ bool arm_s1_regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx); 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_class_init(ObjectClass *oc, void *data) cc->gdb_write_register = arm_cpu_gdb_write_register; #ifndef CONFIG_USER_ONLY cc->do_interrupt = arm_cpu_do_interrupt; - cc->do_unaligned_access = arm_cpu_do_unaligned_access; - cc->do_transaction_failed = arm_cpu_do_transaction_failed; cc->get_phys_page_attrs_debug = arm_cpu_get_phys_page_attrs_debug; cc->asidx_from_attrs = arm_asidx_from_attrs; cc->vmsd = &vmstate_arm_cpu; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) #ifdef CONFIG_TCG cc->tcg_initialize = arm_translate_init; cc->tlb_fill = arm_cpu_tlb_fill; +#if !defined(CONFIG_USER_ONLY) + cc->do_unaligned_access = arm_cpu_do_unaligned_access; + cc->do_transaction_failed = arm_cpu_do_transaction_failed; +#endif /* CONFIG_TCG && !CONFIG_USER_ONLY */ #endif } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) #endif -bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size, - MMUAccessType access_type, int mmu_idx, - bool probe, uintptr_t retaddr) -{ - ARMCPU *cpu = ARM_CPU(cs); - -#ifdef CONFIG_USER_ONLY - cpu->env.exception.vaddress = address; - if (access_type == MMU_INST_FETCH) { - cs->exception_index = EXCP_PREFETCH_ABORT; - } else { - cs->exception_index = EXCP_DATA_ABORT; - } - cpu_loop_exit_restore(cs, retaddr); -#else - hwaddr phys_addr; - target_ulong page_size; - int prot, ret; - MemTxAttrs attrs = {}; - ARMMMUFaultInfo fi = {}; - - /* - * Walk the page table and (if the mapping exists) add the page - * to the TLB. On success, return true. Otherwise, if probing, - * return false. Otherwise populate fsr with ARM DFSR/IFSR fault - * register format, and signal the fault. - */ - ret = get_phys_addr(&cpu->env, address, access_type, - core_to_arm_mmu_idx(&cpu->env, mmu_idx), - &phys_addr, &attrs, &prot, &page_size, &fi, NULL); - if (likely(!ret)) { - /* - * Map a single [sub]page. Regions smaller than our declared - * target page size are handled specially, so for those we - * pass in the exact addresses. - */ - if (page_size >= TARGET_PAGE_SIZE) { - phys_addr &= TARGET_PAGE_MASK; - address &= TARGET_PAGE_MASK; - } - tlb_set_page_with_attrs(cs, address, phys_addr, attrs, - prot, mmu_idx, page_size); - return true; - } else if (probe) { - return false; - } else { - /* now we have a real cpu fault */ - cpu_restore_state(cs, retaddr, true); - arm_deliver_fault(cpu, address, access_type, mmu_idx, &fi); - } -#endif -} - /* Note that signed overflow is undefined in C. The following routines are careful to use unsigned types where modulo arithmetic is required. Failure to do so _will_ break on newer gcc. */ diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_tbl)(uint32_t ireg, uint32_t def, void *vn, return val; } -#if !defined(CONFIG_USER_ONLY) - -static inline uint32_t merge_syn_data_abort(uint32_t template_syn, - unsigned int target_el, - bool same_el, bool ea, - bool s1ptw, bool is_write, - int fsc) -{ - uint32_t syn; - - /* - * ISV is only set for data aborts routed to EL2 and - * never for stage-1 page table walks faulting on stage 2. - * - * Furthermore, ISV is only set for certain kinds of load/stores. - * If the template syndrome does not have ISV set, we should leave - * it cleared. - * - * See ARMv8 specs, D7-1974: - * ISS encoding for an exception from a Data Abort, the - * ISV field. - */ - if (!(template_syn & ARM_EL_ISV) || target_el != 2 || s1ptw) { - syn = syn_data_abort_no_iss(same_el, - ea, 0, s1ptw, is_write, fsc); - } else { - /* - * Fields: IL, ISV, SAS, SSE, SRT, SF and AR come from the template - * syndrome created at translation time. - * Now we create the runtime syndrome with the remaining fields. - */ - syn = syn_data_abort_with_iss(same_el, - 0, 0, 0, 0, 0, - ea, 0, s1ptw, is_write, fsc, - false); - /* Merge the runtime syndrome with the template syndrome. */ - syn |= template_syn; - } - return syn; -} - -void arm_deliver_fault(ARMCPU *cpu, vaddr addr, MMUAccessType access_type, - int mmu_idx, ARMMMUFaultInfo *fi) -{ - CPUARMState *env = &cpu->env; - int target_el; - bool same_el; - uint32_t syn, exc, fsr, fsc; - ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx); - - target_el = exception_target_el(env); - if (fi->stage2) { - target_el = 2; - env->cp15.hpfar_el2 = extract64(fi->s2addr, 12, 47) << 4; - } - same_el = (arm_current_el(env) == target_el); - - if (target_el == 2 || arm_el_is_aa64(env, target_el) || - arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) { - /* - * LPAE format fault status register : bottom 6 bits are - * status code in the same form as needed for syndrome - */ - fsr = arm_fi_to_lfsc(fi); - fsc = extract32(fsr, 0, 6); - } else { - fsr = arm_fi_to_sfsc(fi); - /* - * Short format FSR : this fault will never actually be reported - * to an EL that uses a syndrome register. Use a (currently) - * reserved FSR code in case the constructed syndrome does leak - * into the guest somehow. - */ - fsc = 0x3f; - } - - if (access_type == MMU_INST_FETCH) { - syn = syn_insn_abort(same_el, fi->ea, fi->s1ptw, fsc); - exc = EXCP_PREFETCH_ABORT; - } else { - syn = merge_syn_data_abort(env->exception.syndrome, target_el, - same_el, fi->ea, fi->s1ptw, - access_type == MMU_DATA_STORE, - fsc); - if (access_type == MMU_DATA_STORE - && arm_feature(env, ARM_FEATURE_V6)) { - fsr |= (1 << 11); - } - exc = EXCP_DATA_ABORT; - } - - env->exception.vaddress = addr; - env->exception.fsr = fsr; - raise_exception(env, exc, syn, target_el); -} - -/* Raise a data fault alignment exception for the specified virtual address */ -void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, - MMUAccessType access_type, - int mmu_idx, uintptr_t retaddr) -{ - ARMCPU *cpu = ARM_CPU(cs); - ARMMMUFaultInfo fi = {}; - - /* now we have a real cpu fault */ - cpu_restore_state(cs, retaddr, true); - - fi.type = ARMFault_Alignment; - arm_deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi); -} - -/* - * arm_cpu_do_transaction_failed: handle a memory system error response - * (eg "no device/memory present at address") by raising an external abort - * exception - */ -void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, - vaddr addr, unsigned size, - MMUAccessType access_type, - int mmu_idx, MemTxAttrs attrs, - MemTxResult response, uintptr_t retaddr) -{ - ARMCPU *cpu = ARM_CPU(cs); - ARMMMUFaultInfo fi = {}; - - /* now we have a real cpu fault */ - cpu_restore_state(cs, retaddr, true); - - fi.ea = arm_extabort_type(response); - fi.type = ARMFault_SyncExternal; - arm_deliver_fault(cpu, addr, access_type, mmu_idx, &fi); -} - -#endif /* !defined(CONFIG_USER_ONLY) */ - void HELPER(v8m_stackcheck)(CPUARMState *env, uint32_t newvalue) { /* diff --git a/target/arm/tlb_helper.c b/target/arm/tlb_helper.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/tlb_helper.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM TLB (Translation lookaside buffer) helpers. + * + * This code is licensed under the GNU GPL v2 or later. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "cpu.h" +#include "internals.h" +#include "exec/exec-all.h" + +#if !defined(CONFIG_USER_ONLY) + +static inline uint32_t merge_syn_data_abort(uint32_t template_syn, + unsigned int target_el, + bool same_el, bool ea, + bool s1ptw, bool is_write, + int fsc) +{ + uint32_t syn; + + /* + * ISV is only set for data aborts routed to EL2 and + * never for stage-1 page table walks faulting on stage 2. + * + * Furthermore, ISV is only set for certain kinds of load/stores. + * If the template syndrome does not have ISV set, we should leave + * it cleared. + * + * See ARMv8 specs, D7-1974: + * ISS encoding for an exception from a Data Abort, the + * ISV field. + */ + if (!(template_syn & ARM_EL_ISV) || target_el != 2 || s1ptw) { + syn = syn_data_abort_no_iss(same_el, + ea, 0, s1ptw, is_write, fsc); + } else { + /* + * Fields: IL, ISV, SAS, SSE, SRT, SF and AR come from the template + * syndrome created at translation time. + * Now we create the runtime syndrome with the remaining fields. + */ + syn = syn_data_abort_with_iss(same_el, + 0, 0, 0, 0, 0, + ea, 0, s1ptw, is_write, fsc, + false); + /* Merge the runtime syndrome with the template syndrome. */ + syn |= template_syn; + } + return syn; +} + +static void QEMU_NORETURN arm_deliver_fault(ARMCPU *cpu, vaddr addr, + MMUAccessType access_type, + int mmu_idx, ARMMMUFaultInfo *fi) +{ + CPUARMState *env = &cpu->env; + int target_el; + bool same_el; + uint32_t syn, exc, fsr, fsc; + ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx); + + target_el = exception_target_el(env); + if (fi->stage2) { + target_el = 2; + env->cp15.hpfar_el2 = extract64(fi->s2addr, 12, 47) << 4; + } + same_el = (arm_current_el(env) == target_el); + + if (target_el == 2 || arm_el_is_aa64(env, target_el) || + arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) { + /* + * LPAE format fault status register : bottom 6 bits are + * status code in the same form as needed for syndrome + */ + fsr = arm_fi_to_lfsc(fi); + fsc = extract32(fsr, 0, 6); + } else { + fsr = arm_fi_to_sfsc(fi); + /* + * Short format FSR : this fault will never actually be reported + * to an EL that uses a syndrome register. Use a (currently) + * reserved FSR code in case the constructed syndrome does leak + * into the guest somehow. + */ + fsc = 0x3f; + } + + if (access_type == MMU_INST_FETCH) { + syn = syn_insn_abort(same_el, fi->ea, fi->s1ptw, fsc); + exc = EXCP_PREFETCH_ABORT; + } else { + syn = merge_syn_data_abort(env->exception.syndrome, target_el, + same_el, fi->ea, fi->s1ptw, + access_type == MMU_DATA_STORE, + fsc); + if (access_type == MMU_DATA_STORE + && arm_feature(env, ARM_FEATURE_V6)) { + fsr |= (1 << 11); + } + exc = EXCP_DATA_ABORT; + } + + env->exception.vaddress = addr; + env->exception.fsr = fsr; + raise_exception(env, exc, syn, target_el); +} + +/* Raise a data fault alignment exception for the specified virtual address */ +void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, + MMUAccessType access_type, + int mmu_idx, uintptr_t retaddr) +{ + ARMCPU *cpu = ARM_CPU(cs); + ARMMMUFaultInfo fi = {}; + + /* now we have a real cpu fault */ + cpu_restore_state(cs, retaddr, true); + + fi.type = ARMFault_Alignment; + arm_deliver_fault(cpu, vaddr, access_type, mmu_idx, &fi); +} + +/* + * arm_cpu_do_transaction_failed: handle a memory system error response + * (eg "no device/memory present at address") by raising an external abort + * exception + */ +void arm_cpu_do_transaction_failed(CPUState *cs, hwaddr physaddr, + vaddr addr, unsigned size, + MMUAccessType access_type, + int mmu_idx, MemTxAttrs attrs, + MemTxResult response, uintptr_t retaddr) +{ + ARMCPU *cpu = ARM_CPU(cs); + ARMMMUFaultInfo fi = {}; + + /* now we have a real cpu fault */ + cpu_restore_state(cs, retaddr, true); + + fi.ea = arm_extabort_type(response); + fi.type = ARMFault_SyncExternal; + arm_deliver_fault(cpu, addr, access_type, mmu_idx, &fi); +} + +#endif /* !defined(CONFIG_USER_ONLY) */ + +bool arm_cpu_tlb_fill(CPUState *cs, vaddr address, int size, + MMUAccessType access_type, int mmu_idx, + bool probe, uintptr_t retaddr) +{ + ARMCPU *cpu = ARM_CPU(cs); + +#ifdef CONFIG_USER_ONLY + cpu->env.exception.vaddress = address; + if (access_type == MMU_INST_FETCH) { + cs->exception_index = EXCP_PREFETCH_ABORT; + } else { + cs->exception_index = EXCP_DATA_ABORT; + } + cpu_loop_exit_restore(cs, retaddr); +#else + hwaddr phys_addr; + target_ulong page_size; + int prot, ret; + MemTxAttrs attrs = {}; + ARMMMUFaultInfo fi = {}; + + /* + * Walk the page table and (if the mapping exists) add the page + * to the TLB. On success, return true. Otherwise, if probing, + * return false. Otherwise populate fsr with ARM DFSR/IFSR fault + * register format, and signal the fault. + */ + ret = get_phys_addr(&cpu->env, address, access_type, + core_to_arm_mmu_idx(&cpu->env, mmu_idx), + &phys_addr, &attrs, &prot, &page_size, &fi, NULL); + if (likely(!ret)) { + /* + * Map a single [sub]page. Regions smaller than our declared + * target page size are handled specially, so for those we + * pass in the exact addresses. + */ + if (page_size >= TARGET_PAGE_SIZE) { + phys_addr &= TARGET_PAGE_MASK; + address &= TARGET_PAGE_MASK; + } + tlb_set_page_with_attrs(cs, address, phys_addr, attrs, + prot, mmu_idx, page_size); + return true; + } else if (probe) { + return false; + } else { + /* now we have a real cpu fault */ + cpu_restore_state(cs, retaddr, true); + arm_deliver_fault(cpu, address, access_type, mmu_idx, &fi); + } +#endif +} -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> To ease the review of the next commit, move the vfp_exceptbits_to_host() function directly after vfp_exceptbits_from_host(). Amusingly the diff shows we are moving vfp_get_fpscr(). Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-15-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp_helper.c | 52 ++++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_from_host(int host_bits) return target_bits; } -uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) -{ - uint32_t i, fpscr; - - fpscr = env->vfp.xregs[ARM_VFP_FPSCR] - | (env->vfp.vec_len << 16) - | (env->vfp.vec_stride << 20); - - i = get_float_exception_flags(&env->vfp.fp_status); - i |= get_float_exception_flags(&env->vfp.standard_fp_status); - /* FZ16 does not generate an input denormal exception. */ - i |= (get_float_exception_flags(&env->vfp.fp_status_f16) - & ~float_flag_input_denormal); - fpscr |= vfp_exceptbits_from_host(i); - - i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; - fpscr |= i ? FPCR_QC : 0; - - return fpscr; -} - -uint32_t vfp_get_fpscr(CPUARMState *env) -{ - return HELPER(vfp_get_fpscr)(env); -} - /* Convert vfp exception flags to target form. */ static inline int vfp_exceptbits_to_host(int target_bits) { @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_to_host(int target_bits) return host_bits; } +uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) +{ + uint32_t i, fpscr; + + fpscr = env->vfp.xregs[ARM_VFP_FPSCR] + | (env->vfp.vec_len << 16) + | (env->vfp.vec_stride << 20); + + i = get_float_exception_flags(&env->vfp.fp_status); + i |= get_float_exception_flags(&env->vfp.standard_fp_status); + /* FZ16 does not generate an input denormal exception. */ + i |= (get_float_exception_flags(&env->vfp.fp_status_f16) + & ~float_flag_input_denormal); + fpscr |= vfp_exceptbits_from_host(i); + + i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; + fpscr |= i ? FPCR_QC : 0; + + return fpscr; +} + +uint32_t vfp_get_fpscr(CPUARMState *env) +{ + return HELPER(vfp_get_fpscr)(env); +} + void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) { int i; -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> The vfp_set_fpscr() helper contains code specific to the host floating point implementation (here the SoftFloat library). Extract this code to vfp_set_fpscr_to_host(). Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-16-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp_helper.c | 127 +++++++++++++++++++++------------------- 1 file changed, 66 insertions(+), 61 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_to_host(int target_bits) return host_bits; } -uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) -{ - uint32_t i, fpscr; - - fpscr = env->vfp.xregs[ARM_VFP_FPSCR] - | (env->vfp.vec_len << 16) - | (env->vfp.vec_stride << 20); - - i = get_float_exception_flags(&env->vfp.fp_status); - i |= get_float_exception_flags(&env->vfp.standard_fp_status); - /* FZ16 does not generate an input denormal exception. */ - i |= (get_float_exception_flags(&env->vfp.fp_status_f16) - & ~float_flag_input_denormal); - fpscr |= vfp_exceptbits_from_host(i); - - i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; - fpscr |= i ? FPCR_QC : 0; - - return fpscr; -} - -uint32_t vfp_get_fpscr(CPUARMState *env) -{ - return HELPER(vfp_get_fpscr)(env); -} - -void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) +static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val) { int i; uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR]; - /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ - if (!cpu_isar_feature(aa64_fp16, env_archcpu(env))) { - val &= ~FPCR_FZ16; - } - - if (arm_feature(env, ARM_FEATURE_M)) { - /* - * M profile FPSCR is RES0 for the QC, STRIDE, FZ16, LEN bits - * and also for the trapped-exception-handling bits IxE. - */ - val &= 0xf7c0009f; - } - - /* - * We don't implement trapped exception handling, so the - * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!) - * - * If we exclude the exception flags, IOC|DZC|OFC|UFC|IXC|IDC - * (which are stored in fp_status), and the other RES0 bits - * in between, then we clear all of the low 16 bits. - */ - env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000; - env->vfp.vec_len = (val >> 16) & 7; - env->vfp.vec_stride = (val >> 20) & 3; - - /* - * The bit we set within fpscr_q is arbitrary; the register as a - * whole being zero/non-zero is what counts. - */ - env->vfp.qc[0] = val & FPCR_QC; - env->vfp.qc[1] = 0; - env->vfp.qc[2] = 0; - env->vfp.qc[3] = 0; - changed ^= val; if (changed & (3 << 22)) { i = (val >> 22) & 3; @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) set_float_exception_flags(0, &env->vfp.standard_fp_status); } +uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) +{ + uint32_t i, fpscr; + + fpscr = env->vfp.xregs[ARM_VFP_FPSCR] + | (env->vfp.vec_len << 16) + | (env->vfp.vec_stride << 20); + + i = get_float_exception_flags(&env->vfp.fp_status); + i |= get_float_exception_flags(&env->vfp.standard_fp_status); + /* FZ16 does not generate an input denormal exception. */ + i |= (get_float_exception_flags(&env->vfp.fp_status_f16) + & ~float_flag_input_denormal); + fpscr |= vfp_exceptbits_from_host(i); + + i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; + fpscr |= i ? FPCR_QC : 0; + + return fpscr; +} + +uint32_t vfp_get_fpscr(CPUARMState *env) +{ + return HELPER(vfp_get_fpscr)(env); +} + +void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) +{ + /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ + if (!cpu_isar_feature(aa64_fp16, env_archcpu(env))) { + val &= ~FPCR_FZ16; + } + + if (arm_feature(env, ARM_FEATURE_M)) { + /* + * M profile FPSCR is RES0 for the QC, STRIDE, FZ16, LEN bits + * and also for the trapped-exception-handling bits IxE. + */ + val &= 0xf7c0009f; + } + + /* + * We don't implement trapped exception handling, so the + * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!) + * + * If we exclude the exception flags, IOC|DZC|OFC|UFC|IXC|IDC + * (which are stored in fp_status), and the other RES0 bits + * in between, then we clear all of the low 16 bits. + */ + env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000; + env->vfp.vec_len = (val >> 16) & 7; + env->vfp.vec_stride = (val >> 20) & 3; + + /* + * The bit we set within fpscr_q is arbitrary; the register as a + * whole being zero/non-zero is what counts. + */ + env->vfp.qc[0] = val & FPCR_QC; + env->vfp.qc[1] = 0; + env->vfp.qc[2] = 0; + env->vfp.qc[3] = 0; + + vfp_set_fpscr_to_host(env, val); +} + void vfp_set_fpscr(CPUARMState *env, uint32_t val) { HELPER(vfp_set_fpscr)(env, val); -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> The vfp_set_fpscr() helper contains code specific to the host floating point implementation (here the SoftFloat library). Extract this code to vfp_set_fpscr_from_host(). Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-17-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp_helper.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_to_host(int target_bits) return host_bits; } +static uint32_t vfp_get_fpscr_from_host(CPUARMState *env) +{ + uint32_t i; + + i = get_float_exception_flags(&env->vfp.fp_status); + i |= get_float_exception_flags(&env->vfp.standard_fp_status); + /* FZ16 does not generate an input denormal exception. */ + i |= (get_float_exception_flags(&env->vfp.fp_status_f16) + & ~float_flag_input_denormal); + return vfp_exceptbits_from_host(i); +} + static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val) { int i; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) | (env->vfp.vec_len << 16) | (env->vfp.vec_stride << 20); - i = get_float_exception_flags(&env->vfp.fp_status); - i |= get_float_exception_flags(&env->vfp.standard_fp_status); - /* FZ16 does not generate an input denormal exception. */ - i |= (get_float_exception_flags(&env->vfp.fp_status_f16) - & ~float_flag_input_denormal); - fpscr |= vfp_exceptbits_from_host(i); + fpscr |= vfp_get_fpscr_from_host(env); i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; fpscr |= i ? FPCR_QC : 0; -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> This code is specific to the SoftFloat floating-point implementation, which is only used by TCG. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-18-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp_helper.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "qemu/log.h" #include "cpu.h" #include "exec/helper-proto.h" -#include "fpu/softfloat.h" #include "internals.h" - +#ifdef CONFIG_TCG +#include "qemu/log.h" +#include "fpu/softfloat.h" +#endif /* VFP support. We follow the convention used for VFP instructions: Single precision routines have a "s" suffix, double precision a "d" suffix. */ +#ifdef CONFIG_TCG + /* Convert host exception flags to vfp form. */ static inline int vfp_exceptbits_from_host(int host_bits) { @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val) set_float_exception_flags(0, &env->vfp.standard_fp_status); } +#else + +static uint32_t vfp_get_fpscr_from_host(CPUARMState *env) +{ + return 0; +} + +static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val) +{ +} + +#endif + uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) { uint32_t i, fpscr; @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val) HELPER(vfp_set_fpscr)(env, val); } +#ifdef CONFIG_TCG + #define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p)) #define VFP_BINOP(name) \ @@ -XXX,XX +XXX,XX @@ float64 HELPER(frint64_d)(float64 f, void *fpst) { return frint_d(f, fpst, 64); } + +#endif -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Under KVM, the kernel gets the HVC call and handle the PSCI requests. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-20-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) 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 @@ vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len); /* Callback function for when a watchpoint or breakpoint triggers. */ void arm_debug_excp_handler(CPUState *cs); -#ifdef CONFIG_USER_ONLY +#if defined(CONFIG_USER_ONLY) || !defined(CONFIG_TCG) static inline bool arm_is_psci_call(ARMCPU *cpu, int excp_type) { return false; } +static inline void arm_handle_psci_call(ARMCPU *cpu) +{ + g_assert_not_reached(); +} #else /* Return true if the r0/x0 value indicates that this SMC/HVC is a PSCI call. */ bool arm_is_psci_call(ARMCPU *cpu, int excp_type); -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> In few commits we will split the M-profile functions from this file, and this function will also be called in the new file. Declare it in the "internals.h" header. Since it is in the middle of a block of M profile functions, move it previous to this block to ease the later refactor. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-21-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 2 ++ target/arm/helper.c | 76 +++++++++++++++++++++--------------------- 2 files changed, 40 insertions(+), 38 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 @@ bool get_phys_addr(CPUARMState *env, target_ulong address, target_ulong *page_size, ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs); +void arm_log_exception(int idx); + #endif /* !CONFIG_USER_ONLY */ #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t arm_phys_excp_target_el(CPUState *cs, uint32_t excp_idx, return target_el; } +void arm_log_exception(int idx) +{ + if (qemu_loglevel_mask(CPU_LOG_INT)) { + const char *exc = NULL; + static const char * const excnames[] = { + [EXCP_UDEF] = "Undefined Instruction", + [EXCP_SWI] = "SVC", + [EXCP_PREFETCH_ABORT] = "Prefetch Abort", + [EXCP_DATA_ABORT] = "Data Abort", + [EXCP_IRQ] = "IRQ", + [EXCP_FIQ] = "FIQ", + [EXCP_BKPT] = "Breakpoint", + [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit", + [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage", + [EXCP_HVC] = "Hypervisor Call", + [EXCP_HYP_TRAP] = "Hypervisor Trap", + [EXCP_SMC] = "Secure Monitor Call", + [EXCP_VIRQ] = "Virtual IRQ", + [EXCP_VFIQ] = "Virtual FIQ", + [EXCP_SEMIHOST] = "Semihosting call", + [EXCP_NOCP] = "v7M NOCP UsageFault", + [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", + [EXCP_STKOF] = "v8M STKOF UsageFault", + [EXCP_LAZYFP] = "v7M exception during lazy FP stacking", + [EXCP_LSERR] = "v8M LSERR UsageFault", + [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", + }; + + if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { + exc = excnames[idx]; + } + if (!exc) { + exc = "unknown"; + } + qemu_log_mask(CPU_LOG_INT, "Taking exception %d [%s]\n", idx, exc); + } +} + /* * Return true if the v7M CPACR permits access to the FPU for the specified * security state and privilege level. @@ -XXX,XX +XXX,XX @@ static bool do_v7m_function_return(ARMCPU *cpu) return true; } -static void arm_log_exception(int idx) -{ - if (qemu_loglevel_mask(CPU_LOG_INT)) { - const char *exc = NULL; - static const char * const excnames[] = { - [EXCP_UDEF] = "Undefined Instruction", - [EXCP_SWI] = "SVC", - [EXCP_PREFETCH_ABORT] = "Prefetch Abort", - [EXCP_DATA_ABORT] = "Data Abort", - [EXCP_IRQ] = "IRQ", - [EXCP_FIQ] = "FIQ", - [EXCP_BKPT] = "Breakpoint", - [EXCP_EXCEPTION_EXIT] = "QEMU v7M exception exit", - [EXCP_KERNEL_TRAP] = "QEMU intercept of kernel commpage", - [EXCP_HVC] = "Hypervisor Call", - [EXCP_HYP_TRAP] = "Hypervisor Trap", - [EXCP_SMC] = "Secure Monitor Call", - [EXCP_VIRQ] = "Virtual IRQ", - [EXCP_VFIQ] = "Virtual FIQ", - [EXCP_SEMIHOST] = "Semihosting call", - [EXCP_NOCP] = "v7M NOCP UsageFault", - [EXCP_INVSTATE] = "v7M INVSTATE UsageFault", - [EXCP_STKOF] = "v8M STKOF UsageFault", - [EXCP_LAZYFP] = "v7M exception during lazy FP stacking", - [EXCP_LSERR] = "v8M LSERR UsageFault", - [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", - }; - - if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { - exc = excnames[idx]; - } - if (!exc) { - exc = "unknown"; - } - qemu_log_mask(CPU_LOG_INT, "Taking exception %d [%s]\n", idx, exc); - } -} - static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, uint32_t addr, uint16_t *insn) { -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> In the next commit we will split the M-profile functions from this file. Some function will be called out of helper.c. Declare them in the "internals.h" header. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190701132516.26392-22-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 42 ++++++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 38 ++------------------------------------ 2 files changed, 44 insertions(+), 36 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 uint32_t v7m_sp_limit(CPUARMState *env) } } +/** + * v7m_cpacr_pass: + * Return true if the v7M CPACR permits access to the FPU for the specified + * security state and privilege level. + */ +static inline bool v7m_cpacr_pass(CPUARMState *env, + bool is_secure, bool is_priv) +{ + switch (extract32(env->v7m.cpacr[is_secure], 20, 2)) { + case 0: + case 2: /* UNPREDICTABLE: we treat like 0 */ + return false; + case 1: + return is_priv; + case 3: + return true; + default: + g_assert_not_reached(); + } +} + /** * aarch32_mode_name(): Return name of the AArch32 CPU mode * @psr: Program Status Register indicating CPU mode @@ -XXX,XX +XXX,XX @@ static inline int exception_target_el(CPUARMState *env) #ifndef CONFIG_USER_ONLY +/* Security attributes for an address, as returned by v8m_security_lookup. */ +typedef struct V8M_SAttributes { + bool subpage; /* true if these attrs don't cover the whole TARGET_PAGE */ + bool ns; + bool nsc; + uint8_t sregion; + bool srvalid; + uint8_t iregion; + bool irvalid; +} V8M_SAttributes; + +void v8m_security_lookup(CPUARMState *env, uint32_t address, + MMUAccessType access_type, ARMMMUIdx mmu_idx, + V8M_SAttributes *sattrs); + +bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, + MMUAccessType access_type, ARMMMUIdx mmu_idx, + hwaddr *phys_ptr, MemTxAttrs *txattrs, + int *prot, bool *is_subpage, + ARMMMUFaultInfo *fi, uint32_t *mregion); + /* Cacheability and shareability attributes for a memory access */ typedef struct ARMCacheAttrs { unsigned int attrs:8; /* as in the MAIR register encoding */ 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 bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, target_ulong *page_size_ptr, ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs); - -/* Security attributes for an address, as returned by v8m_security_lookup. */ -typedef struct V8M_SAttributes { - bool subpage; /* true if these attrs don't cover the whole TARGET_PAGE */ - bool ns; - bool nsc; - uint8_t sregion; - bool srvalid; - uint8_t iregion; - bool irvalid; -} V8M_SAttributes; - -static void v8m_security_lookup(CPUARMState *env, uint32_t address, - MMUAccessType access_type, ARMMMUIdx mmu_idx, - V8M_SAttributes *sattrs); #endif static void switch_mode(CPUARMState *env, int mode); @@ -XXX,XX +XXX,XX @@ void arm_log_exception(int idx) } } -/* - * Return true if the v7M CPACR permits access to the FPU for the specified - * security state and privilege level. - */ -static bool v7m_cpacr_pass(CPUARMState *env, bool is_secure, bool is_priv) -{ - switch (extract32(env->v7m.cpacr[is_secure], 20, 2)) { - case 0: - case 2: /* UNPREDICTABLE: we treat like 0 */ - return false; - case 1: - return is_priv; - case 3: - return true; - default: - g_assert_not_reached(); - } -} - /* * What kind of stack write are we doing? This affects how exceptions * generated during the stacking are treated. @@ -XXX,XX +XXX,XX @@ static bool v8m_is_sau_exempt(CPUARMState *env, (address >= 0xe00ff000 && address <= 0xe00fffff); } -static void v8m_security_lookup(CPUARMState *env, uint32_t address, +void v8m_security_lookup(CPUARMState *env, uint32_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, V8M_SAttributes *sattrs) { @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, } } -static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, +bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, bool *is_subpage, -- 2.20.1 Arm queue; some of the simpler stuff, things other have reviewed (thanks!), etc. -- PMM The following changes since commit 5d2f557b47dfbf8f23277a5bdd8473d4607c681a: Merge remote-tracking branch 'remotes/kraxel/tags/vga-20200605-pull-request' into staging (2020-06-05 13:53:05 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200605 for you to fetch changes up to 2c35a39eda0b16c2ed85c94cec204bf5efb97812: target/arm: Convert Neon one-register-and-immediate insns to decodetree (2020-06-05 17:23:10 +0100) ---------------------------------------------------------------- target-arm queue: hw/ssi/imx_spi: Handle tx burst lengths other than 8 correctly hw/input/pxa2xx_keypad: Replace hw_error() by qemu_log_mask() hw/arm/pxa2xx: Replace printf() call by qemu_log_mask() target/arm: Convert crypto insns to gvec hw/adc/stm32f2xx_adc: Correct memory region size and access size tests/acceptance: Add a boot test for the xlnx-versal-virt machine docs/system: Document Aspeed boards raspi: Add model of the USB controller target/arm: Convert 2-reg-and-shift and 1-reg-imm Neon insns to decodetree ---------------------------------------------------------------- Cédric Le Goater (1): docs/system: Document Aspeed boards Eden Mikitas (2): hw/ssi/imx_spi: changed while statement to prevent underflow hw/ssi/imx_spi: Removed unnecessary cast of rx data received from slave Paul Zimmerman (7): raspi: add BCM2835 SOC MPHI emulation dwc-hsotg (dwc2) USB host controller register definitions dwc-hsotg (dwc2) USB host controller state definitions dwc-hsotg (dwc2) USB host controller emulation usb: add short-packet handling to usb-storage driver wire in the dwc-hsotg (dwc2) USB host controller emulation raspi2 acceptance test: add test for dwc-hsotg (dwc2) USB host Peter Maydell (9): target/arm: Convert Neon VSHL and VSLI 2-reg-shift insn to decodetree target/arm: Convert Neon VSHR 2-reg-shift insns to decodetree target/arm: Convert Neon VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree target/arm: Convert VQSHLU, VQSHL 2-reg-shift insns to decodetree target/arm: Convert Neon narrowing shifts with op==8 to decodetree target/arm: Convert Neon narrowing shifts with op==9 to decodetree target/arm: Convert Neon VSHLL, VMOVL to decodetree target/arm: Convert VCVT fixed-point ops to decodetree target/arm: Convert Neon one-register-and-immediate insns to decodetree Philippe Mathieu-Daudé (3): hw/input/pxa2xx_keypad: Replace hw_error() by qemu_log_mask() hw/arm/pxa2xx: Replace printf() call by qemu_log_mask() hw/adc/stm32f2xx_adc: Correct memory region size and access size Richard Henderson (6): target/arm: Convert aes and sm4 to gvec helpers target/arm: Convert rax1 to gvec helpers target/arm: Convert sha512 and sm3 to gvec helpers target/arm: Convert sha1 and sha256 to gvec helpers target/arm: Split helper_crypto_sha1_3reg target/arm: Split helper_crypto_sm3tt Thomas Huth (1): tests/acceptance: Add a boot test for the xlnx-versal-virt machine docs/system/arm/aspeed.rst | 85 ++ docs/system/target-arm.rst | 1 + hw/usb/hcd-dwc2.h | 190 +++++ include/hw/arm/bcm2835_peripherals.h | 5 +- include/hw/misc/bcm2835_mphi.h | 44 + include/hw/usb/dwc2-regs.h | 899 ++++++++++++++++++++ target/arm/helper.h | 45 +- target/arm/translate-a64.h | 3 + target/arm/vec_internal.h | 33 + target/arm/neon-dp.decode | 214 ++++- hw/adc/stm32f2xx_adc.c | 4 +- hw/arm/bcm2835_peripherals.c | 38 +- hw/arm/pxa2xx.c | 66 +- hw/input/pxa2xx_keypad.c | 10 +- hw/misc/bcm2835_mphi.c | 191 +++++ hw/ssi/imx_spi.c | 4 +- hw/usb/dev-storage.c | 15 +- hw/usb/hcd-dwc2.c | 1417 ++++++++++++++++++++++++++++++++ target/arm/crypto_helper.c | 267 ++++-- target/arm/translate-a64.c | 198 ++--- target/arm/translate-neon.inc.c | 796 ++++++++++++++---- target/arm/translate.c | 539 +----------- target/arm/vec_helper.c | 12 +- hw/misc/Makefile.objs | 1 + hw/usb/Kconfig | 5 + hw/usb/Makefile.objs | 1 + hw/usb/trace-events | 50 ++ tests/acceptance/boot_linux_console.py | 35 +- 28 files changed, 4258 insertions(+), 910 deletions(-) create mode 100644 docs/system/arm/aspeed.rst create mode 100644 hw/usb/hcd-dwc2.h create mode 100644 include/hw/misc/bcm2835_mphi.h create mode 100644 include/hw/usb/dwc2-regs.h create mode 100644 target/arm/vec_internal.h create mode 100644 hw/misc/bcm2835_mphi.c create mode 100644 hw/usb/hcd-dwc2.c From: Eden Mikitas <e.mikitas@gmail.com> The while statement in question only checked if tx_burst is not 0. tx_burst is a signed int, which is assigned the value put by the guest driver in ECSPI_CONREG. The burst length can be anywhere between 1 and 4096, and since tx_burst is always decremented by 8 it could possibly underflow, causing an infinite loop. Signed-off-by: Eden Mikitas <e.mikitas@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/imx_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/imx_spi.c +++ b/hw/ssi/imx_spi.c @@ -XXX,XX +XXX,XX @@ static void imx_spi_flush_txfifo(IMXSPIState *s) rx = 0; - while (tx_burst) { + while (tx_burst > 0) { uint8_t byte = tx & 0xff; DPRINTF("writing 0x%02x\n", (uint32_t)byte); -- 2.20.1 From: Eden Mikitas <e.mikitas@gmail.com> When inserting the value retrieved (rx) from the spi slave, rx is pushed to rx_fifo after being cast to uint8_t. rx_fifo is a fifo32, and the rx register the driver uses is also 32 bit. This zeroes the 24 most significant bits of rx. This proved problematic with devices that expect to use the whole 32 bits of the rx register. Signed-off-by: Eden Mikitas <e.mikitas@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/imx_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/imx_spi.c +++ b/hw/ssi/imx_spi.c @@ -XXX,XX +XXX,XX @@ static void imx_spi_flush_txfifo(IMXSPIState *s) if (fifo32_is_full(&s->rx_fifo)) { s->regs[ECSPI_STATREG] |= ECSPI_STATREG_RO; } else { - fifo32_push(&s->rx_fifo, (uint8_t)rx); + fifo32_push(&s->rx_fifo, rx); } if (s->burst_length <= 0) { -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> hw_error() calls exit(). This a bit overkill when we can log the accesses as unimplemented or guest error. When fuzzing the devices, we don't want the whole process to exit. Replace some hw_error() calls by qemu_log_mask() (missed in commit 5a0001ec7e). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200525114123.21317-2-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/input/pxa2xx_keypad.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/input/pxa2xx_keypad.c b/hw/input/pxa2xx_keypad.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/pxa2xx_keypad.c +++ b/hw/input/pxa2xx_keypad.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -#include "hw/hw.h" +#include "qemu/log.h" #include "hw/irq.h" #include "migration/vmstate.h" #include "hw/arm/pxa.h" @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_keypad_read(void *opaque, hwaddr offset, return s->kpkdi; break; default: - hw_error("%s: Bad offset " REG_FMT "\n", __func__, offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_keypad_write(void *opaque, hwaddr offset, break; default: - hw_error("%s: Bad offset " REG_FMT "\n", __func__, offset); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, offset); } } -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Replace printf() calls by qemu_log_mask(), which is disabled by default. This avoid flooding the terminal when fuzzing the device. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200525114123.21317-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx.c | 66 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 49 insertions(+), 17 deletions(-) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/blockdev.h" #include "sysemu/qtest.h" #include "qemu/cutils.h" +#include "qemu/log.h" static struct { hwaddr io_base; @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_pm_read(void *opaque, hwaddr addr, return s->pm_regs[addr >> 2]; default: fail: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pm_write(void *opaque, hwaddr addr, s->pm_regs[addr >> 2] = value; break; } - - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_cm_read(void *opaque, hwaddr addr, return s->cm_regs[CCCR >> 2] | (3 << 28); default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_cm_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_mm_read(void *opaque, hwaddr addr, return s->mm_regs[addr >> 2]; /* fall through */ default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_mm_write(void *opaque, hwaddr addr, } default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_ssp_read(void *opaque, hwaddr addr, case SSACD: return s->ssacd; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_ssp_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_rtc_read(void *opaque, hwaddr addr, else return s->last_swcr; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_rtc_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_i2c_read(void *opaque, hwaddr addr, s->ibmr = 0; return s->ibmr; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_i2c_write(void *opaque, hwaddr addr, break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_i2s_read(void *opaque, hwaddr addr, } return 0; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_i2s_write(void *opaque, hwaddr addr, } break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } @@ -XXX,XX +XXX,XX @@ static uint64_t pxa2xx_fir_read(void *opaque, hwaddr addr, case ICFOR: return s->rx_len; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad read offset 0x%"HWADDR_PRIx"\n", + __func__, addr); break; } return 0; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_fir_write(void *opaque, hwaddr addr, case ICFOR: break; default: - printf("%s: Bad register " REG_FMT "\n", __func__, addr); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad write offset 0x%"HWADDR_PRIx"\n", + __func__, addr); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> With this conversion, we will be able to use the same helpers with sve. In particular, pass 3 vector parameters for the 3-operand operations; for advsimd the destination register is also an input. This also fixes a bug in which we failed to clear the high bits of the SVE register after an AdvSIMD operation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 6 ++-- target/arm/vec_internal.h | 33 +++++++++++++++++ target/arm/crypto_helper.c | 72 +++++++++++++++++++++++++++----------- target/arm/translate-a64.c | 55 ++++++++++++++++++----------- target/arm/translate.c | 27 +++++++------- target/arm/vec_helper.c | 12 +------ 6 files changed, 138 insertions(+), 67 deletions(-) create mode 100644 target/arm/vec_internal.h diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(neon_qzip8, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_2(neon_qzip16, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha1_3reg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) DEF_HELPER_FLAGS_3(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/vec_internal.h @@ -XXX,XX +XXX,XX @@ +/* + * ARM AdvSIMD / SVE Vector Helpers + * + * Copyright (c) 2020 Linaro + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_ARM_VEC_INTERNALS_H +#define TARGET_ARM_VEC_INTERNALS_H + +static inline void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) +{ + uint64_t *d = vd + opr_sz; + uintptr_t i; + + for (i = opr_sz; i < max_sz; i += 8) { + *d++ = 0; + } +} + +#endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" +#include "tcg/tcg-gvec-desc.h" #include "crypto/aes.h" +#include "vec_internal.h" union CRYPTO_STATE { uint8_t bytes[16]; @@ -XXX,XX +XXX,XX @@ union CRYPTO_STATE { #define CR_ST_WORD(state, i) (state.words[i]) #endif -void HELPER(crypto_aese)(void *vd, void *vm, uint32_t decrypt) +static void do_crypto_aese(uint64_t *rd, uint64_t *rn, + uint64_t *rm, bool decrypt) { static uint8_t const * const sbox[2] = { AES_sbox, AES_isbox }; static uint8_t const * const shift[2] = { AES_shifts, AES_ishifts }; - uint64_t *rd = vd; - uint64_t *rm = vm; union CRYPTO_STATE rk = { .l = { rm[0], rm[1] } }; - union CRYPTO_STATE st = { .l = { rd[0], rd[1] } }; + union CRYPTO_STATE st = { .l = { rn[0], rn[1] } }; int i; - assert(decrypt < 2); - /* xor state vector with round key */ rk.l[0] ^= st.l[0]; rk.l[1] ^= st.l[1]; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_aese)(void *vd, void *vm, uint32_t decrypt) rd[1] = st.l[1]; } -void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t decrypt) +void HELPER(crypto_aese)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + bool decrypt = simd_data(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_aese(vd + i, vn + i, vm + i, decrypt); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + +static void do_crypto_aesmc(uint64_t *rd, uint64_t *rm, bool decrypt) { static uint32_t const mc[][256] = { { /* MixColumns lookup table */ @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t decrypt) 0xbe805d9f, 0xb58d5491, 0xa89a4f83, 0xa397468d, } }; - uint64_t *rd = vd; - uint64_t *rm = vm; union CRYPTO_STATE st = { .l = { rm[0], rm[1] } }; int i; - assert(decrypt < 2); - for (i = 0; i < 16; i += 4) { CR_ST_WORD(st, i >> 2) = mc[decrypt][CR_ST_BYTE(st, i)] ^ @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t decrypt) rd[1] = st.l[1]; } +void HELPER(crypto_aesmc)(void *vd, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + bool decrypt = simd_data(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_aesmc(vd + i, vm + i, decrypt); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + /* * SHA-1 logical functions */ @@ -XXX,XX +XXX,XX @@ static uint8_t const sm4_sbox[] = { 0x79, 0xee, 0x5f, 0x3e, 0xd7, 0xcb, 0x39, 0x48, }; -void HELPER(crypto_sm4e)(void *vd, void *vn) +static void do_crypto_sm4e(uint64_t *rd, uint64_t *rn, uint64_t *rm) { - uint64_t *rd = vd; - uint64_t *rn = vn; - union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; - union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE d = { .l = { rn[0], rn[1] } }; + union CRYPTO_STATE n = { .l = { rm[0], rm[1] } }; uint32_t t, i; for (i = 0; i < 4; i++) { @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm4e)(void *vd, void *vn) rd[1] = d.l[1]; } -void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm) +void HELPER(crypto_sm4e)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_sm4e(vd + i, vn + i, vm + i); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} + +static void do_crypto_sm4ekey(uint64_t *rd, uint64_t *rn, uint64_t *rm) { - uint64_t *rd = vd; - uint64_t *rn = vn; - uint64_t *rm = vm; union CRYPTO_STATE d; union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm) rd[0] = d.l[0]; rd[1] = d.l[1]; } + +void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + + for (i = 0; i < opr_sz; i += 16) { + do_crypto_sm4ekey(vd + i, vn + i, vm + i); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} 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 operation using an out-of-line helper. */ +static void gen_gvec_op2_ool(DisasContext *s, bool is_q, int rd, + int rn, int data, gen_helper_gvec_2 *fn) +{ + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); +} + /* Expand a 3-operand operation using an out-of-line helper. */ static void gen_gvec_op3_ool(DisasContext *s, bool is_q, int rd, int rn, int rm, int data, gen_helper_gvec_3 *fn) @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); int decrypt; - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; - TCGv_i32 tcg_decrypt; - CryptoThreeOpIntFn *genfn; + gen_helper_gvec_2 *genfn2 = NULL; + gen_helper_gvec_3 *genfn3 = NULL; if (!dc_isar_feature(aa64_aes, s) || size != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) switch (opcode) { case 0x4: /* AESE */ decrypt = 0; - genfn = gen_helper_crypto_aese; + genfn3 = gen_helper_crypto_aese; break; case 0x6: /* AESMC */ decrypt = 0; - genfn = gen_helper_crypto_aesmc; + genfn2 = gen_helper_crypto_aesmc; break; case 0x5: /* AESD */ decrypt = 1; - genfn = gen_helper_crypto_aese; + genfn3 = gen_helper_crypto_aese; break; case 0x7: /* AESIMC */ decrypt = 1; - genfn = gen_helper_crypto_aesmc; + genfn2 = gen_helper_crypto_aesmc; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_decrypt = tcg_const_i32(decrypt); - - genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_decrypt); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_i32(tcg_decrypt); + if (genfn2) { + gen_gvec_op2_ool(s, true, rd, rn, decrypt, genfn2); + } else { + gen_gvec_op3_ool(s, true, rd, rd, rn, decrypt, genfn3); + } } /* Crypto three-reg SHA @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); bool feature; - CryptoThreeOpFn *genfn; + CryptoThreeOpFn *genfn = NULL; + gen_helper_gvec_3 *oolfn = NULL; if (o == 0) { switch (opcode) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) break; case 2: /* SM4EKEY */ feature = dc_isar_feature(aa64_sm4, s); - genfn = gen_helper_crypto_sm4ekey; + oolfn = gen_helper_crypto_sm4ekey; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) return; } + if (oolfn) { + gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); + return; + } + if (genfn) { TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; bool feature; CryptoTwoOpFn *genfn; + gen_helper_gvec_3 *oolfn = NULL; switch (opcode) { case 0: /* SHA512SU0 */ @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) break; case 1: /* SM4E */ feature = dc_isar_feature(aa64_sm4, s); - genfn = gen_helper_crypto_sm4e; + oolfn = gen_helper_crypto_sm4e; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) return; } + if (oolfn) { + gen_gvec_op3_ool(s, true, rd, rd, rn, 0, oolfn); + return; + } + tcg_rd_ptr = vec_full_reg_ptr(s, rd); tcg_rn_ptr = vec_full_reg_ptr(s, rn); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) { return 1; } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rm); - - /* Bit 6 is the lowest opcode bit; it distinguishes between - * encryption (AESE/AESMC) and decryption (AESD/AESIMC) - */ - tmp3 = tcg_const_i32(extract32(insn, 6, 1)); - + /* + * Bit 6 is the lowest opcode bit; it distinguishes + * between encryption (AESE/AESMC) and decryption + * (AESD/AESIMC). + */ if (op == NEON_2RM_AESE) { - gen_helper_crypto_aese(ptr1, ptr2, tmp3); + tcg_gen_gvec_3_ool(vfp_reg_offset(true, rd), + vfp_reg_offset(true, rd), + vfp_reg_offset(true, rm), + 16, 16, extract32(insn, 6, 1), + gen_helper_crypto_aese); } else { - gen_helper_crypto_aesmc(ptr1, ptr2, tmp3); + tcg_gen_gvec_2_ool(vfp_reg_offset(true, rd), + vfp_reg_offset(true, rm), + 16, 16, extract32(insn, 6, 1), + gen_helper_crypto_aesmc); } - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_i32(tmp3); break; case NEON_2RM_SHA1H: if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 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 @@ #include "exec/helper-proto.h" #include "tcg/tcg-gvec-desc.h" #include "fpu/softfloat.h" - +#include "vec_internal.h" /* Note that vector data is stored in host-endian 64-bit chunks, so addressing units smaller than that needs a host-endian fixup. */ @@ -XXX,XX +XXX,XX @@ #define H4(x) (x) #endif -static void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) -{ - uint64_t *d = vd + opr_sz; - uintptr_t i; - - for (i = opr_sz; i < max_sz; i += 8) { - *d++ = 0; - } -} - /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ static int16_t inl_qrdmlah_s16(int16_t src1, int16_t src2, int16_t src3, uint32_t *sat) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> With this conversion, we will be able to use the same helpers with sve. This also fixes a bug in which we failed to clear the high bits of the SVE register after an AdvSIMD operation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-3-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 | 2 ++ target/arm/translate-a64.h | 3 ++ target/arm/crypto_helper.c | 11 +++++++ target/arm/translate-a64.c | 59 ++++++++++++++++++++------------------ 4 files changed, 47 insertions(+), 28 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) bool disas_sve(DisasContext *, uint32_t); +void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm, uint32_t desc) } clear_tail(vd, opr_sz, simd_maxsz(desc)); } + +void HELPER(crypto_rax1)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = n[i] ^ rol64(m[i], 1); + } + clear_tail(vd, opr_sz, simd_maxsz(desc)); +} diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(tcg_rn_ptr); } +static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) +{ + tcg_gen_rotli_i64(d, m, 1); + tcg_gen_xor_i64(d, d, n); +} + +static void gen_rax1_vec(unsigned vece, TCGv_vec d, TCGv_vec n, TCGv_vec m) +{ + tcg_gen_rotli_vec(vece, d, m, 1); + tcg_gen_xor_vec(vece, d, d, n); +} + +void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_rotli_vec, 0 }; + static const GVecGen3 op = { + .fni8 = gen_rax1_i64, + .fniv = gen_rax1_vec, + .opt_opc = vecop_list, + .fno = gen_helper_crypto_rax1, + .vece = MO_64, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &op); +} + /* Crypto three-reg SHA512 * 31 21 20 16 15 14 13 12 11 10 9 5 4 0 * +-----------------------+------+---+---+-----+--------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) bool feature; CryptoThreeOpFn *genfn = NULL; gen_helper_gvec_3 *oolfn = NULL; + GVecGen3Fn *gvecfn = NULL; if (o == 0) { switch (opcode) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) break; case 3: /* RAX1 */ feature = dc_isar_feature(aa64_sha3, s); - genfn = NULL; + gvecfn = gen_gvec_rax1; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) if (oolfn) { gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); - return; - } - - if (genfn) { + } else if (gvecfn) { + gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); + } else { TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; tcg_rd_ptr = vec_full_reg_ptr(s, rd); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(tcg_rd_ptr); tcg_temp_free_ptr(tcg_rn_ptr); tcg_temp_free_ptr(tcg_rm_ptr); - } else { - TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; - int pass; - - tcg_op1 = tcg_temp_new_i64(); - tcg_op2 = tcg_temp_new_i64(); - tcg_res[0] = tcg_temp_new_i64(); - tcg_res[1] = tcg_temp_new_i64(); - - for (pass = 0; pass < 2; pass++) { - read_vec_element(s, tcg_op1, rn, pass, MO_64); - read_vec_element(s, tcg_op2, rm, pass, MO_64); - - tcg_gen_rotli_i64(tcg_res[pass], tcg_op2, 1); - tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1); - } - write_vec_element(s, tcg_res[0], rd, 0, MO_64); - write_vec_element(s, tcg_res[1], rd, 1, MO_64); - - tcg_temp_free_i64(tcg_op1); - tcg_temp_free_i64(tcg_op2); - tcg_temp_free_i64(tcg_res[0]); - tcg_temp_free_i64(tcg_res[1]); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Do not yet convert the helpers to loop over opr_sz, but the descriptor allows the vector tail to be cleared. Which fixes an existing bug vs SVE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-4-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 | 15 +++++++----- target/arm/crypto_helper.c | 37 +++++++++++++++++++++++----- target/arm/translate-a64.c | 50 ++++++++++++-------------------------- 3 files changed, 55 insertions(+), 47 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) DEF_HELPER_FLAGS_2(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_3(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha512su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) -DEF_HELPER_FLAGS_3(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ union CRYPTO_STATE { #define CR_ST_WORD(state, i) (state.words[i]) #endif +/* + * The caller has not been converted to full gvec, and so only + * modifies the low 16 bytes of the vector register. + */ +static void clear_tail_16(void *vd, uint32_t desc) +{ + int opr_sz = simd_oprsz(desc); + int max_sz = simd_maxsz(desc); + + assert(opr_sz == 16); + clear_tail(vd, opr_sz, max_sz); +} + static void do_crypto_aese(uint64_t *rd, uint64_t *rn, uint64_t *rm, bool decrypt) { @@ -XXX,XX +XXX,XX @@ static uint64_t s1_512(uint64_t x) return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6); } -void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm) rd[0] = d0; rd[1] = d1; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm) rd[0] = d0; rd[1] = d1; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha512su0)(void *vd, void *vn) +void HELPER(crypto_sha512su0)(void *vd, void *vn, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512su0)(void *vd, void *vn) rd[0] = d0; rd[1] = d1; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm) rd[0] += s1_512(rn[0]) + rm[0]; rd[1] += s1_512(rn[1]) + rm[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm) +void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm) +void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); bool feature; - CryptoThreeOpFn *genfn = NULL; gen_helper_gvec_3 *oolfn = NULL; GVecGen3Fn *gvecfn = NULL; @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SHA512H */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512h; + oolfn = gen_helper_crypto_sha512h; break; case 1: /* SHA512H2 */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512h2; + oolfn = gen_helper_crypto_sha512h2; break; case 2: /* SHA512SU1 */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512su1; + oolfn = gen_helper_crypto_sha512su1; break; case 3: /* RAX1 */ feature = dc_isar_feature(aa64_sha3, s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SM3PARTW1 */ feature = dc_isar_feature(aa64_sm3, s); - genfn = gen_helper_crypto_sm3partw1; + oolfn = gen_helper_crypto_sm3partw1; break; case 1: /* SM3PARTW2 */ feature = dc_isar_feature(aa64_sm3, s); - genfn = gen_helper_crypto_sm3partw2; + oolfn = gen_helper_crypto_sm3partw2; break; case 2: /* SM4EKEY */ feature = dc_isar_feature(aa64_sm4, s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) if (oolfn) { gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn); - } else if (gvecfn) { - gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); } else { - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_rm_ptr = vec_full_reg_ptr(s, rm); - - genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); + gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64); } } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 10, 2); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; bool feature; - CryptoTwoOpFn *genfn; - gen_helper_gvec_3 *oolfn = NULL; switch (opcode) { case 0: /* SHA512SU0 */ feature = dc_isar_feature(aa64_sha512, s); - genfn = gen_helper_crypto_sha512su0; break; case 1: /* SM4E */ feature = dc_isar_feature(aa64_sm4, s); - oolfn = gen_helper_crypto_sm4e; break; default: unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) return; } - if (oolfn) { - gen_gvec_op3_ool(s, true, rd, rd, rn, 0, oolfn); - return; + switch (opcode) { + case 0: /* SHA512SU0 */ + gen_gvec_op2_ool(s, true, rd, rn, 0, gen_helper_crypto_sha512su0); + break; + case 1: /* SM4E */ + gen_gvec_op3_ool(s, true, rd, rd, rn, 0, gen_helper_crypto_sm4e); + break; + default: + g_assert_not_reached(); } - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - - genfn(tcg_rd_ptr, tcg_rn_ptr); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); } /* Crypto four-register -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Do not yet convert the helpers to loop over opr_sz, but the descriptor allows the vector tail to be cleared. Which fixes an existing bug vs SVE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-5-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 | 12 ++-- target/arm/neon-dp.decode | 12 ++-- target/arm/crypto_helper.c | 24 +++++-- target/arm/translate-a64.c | 34 ++++----- target/arm/translate-neon.inc.c | 124 +++++--------------------------- target/arm/translate.c | 24 ++----- 6 files changed, 67 insertions(+), 163 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha1_3reg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_2(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr) +DEF_HELPER_FLAGS_3(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr, i32) -DEF_HELPER_FLAGS_3(crypto_sha256h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) -DEF_HELPER_FLAGS_2(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr) -DEF_HELPER_FLAGS_3(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(crypto_sha256h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VPADD_3s 1111 001 0 0 . .. .... .... 1011 . . . 1 .... @3same_q0 VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same +@3same_crypto .... .... .... .... .... .... .... .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 q=1 + SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp -SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp -SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp -SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto VFMA_fp_3s 1111 001 0 0 . 0 . .... .... 1100 ... 1 .... @3same_fp VFMS_fp_3s 1111 001 0 0 . 1 . .... .... 1100 ... 1 .... @3same_fp diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha1_3reg)(void *vd, void *vn, void *vm, uint32_t op) rd[1] = d.l[1]; } -void HELPER(crypto_sha1h)(void *vd, void *vm) +void HELPER(crypto_sha1h)(void *vd, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rm = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha1h)(void *vd, void *vm) rd[0] = m.l[0]; rd[1] = m.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha1su1)(void *vd, void *vm) +void HELPER(crypto_sha1su1)(void *vd, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rm = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha1su1)(void *vd, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } /* @@ -XXX,XX +XXX,XX @@ static uint32_t s1(uint32_t x) return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10); } -void HELPER(crypto_sha256h)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha256h)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256h)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha256h2)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha256h2)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256h2)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha256su0)(void *vd, void *vm) +void HELPER(crypto_sha256su0)(void *vd, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rm = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256su0)(void *vd, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } -void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm) +void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm, uint32_t desc) { uint64_t *rd = vd; uint64_t *rn = vn; @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sha256su1)(void *vd, void *vn, void *vm) rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(vd, desc); } /* diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - CryptoThreeOpFn *genfn; - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; + gen_helper_gvec_3 *genfn; bool feature; if (size != 0) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) return; } - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_rm_ptr = vec_full_reg_ptr(s, rm); - if (genfn) { - genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr); + gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); } else { TCGv_i32 tcg_opcode = tcg_const_i32(opcode); + TCGv_ptr tcg_rd_ptr = vec_full_reg_ptr(s, rd); + TCGv_ptr tcg_rn_ptr = vec_full_reg_ptr(s, rn); + TCGv_ptr tcg_rm_ptr = vec_full_reg_ptr(s, rm); gen_helper_crypto_sha1_3reg(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr, tcg_opcode); - tcg_temp_free_i32(tcg_opcode); - } - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); + tcg_temp_free_i32(tcg_opcode); + tcg_temp_free_ptr(tcg_rd_ptr); + tcg_temp_free_ptr(tcg_rn_ptr); + tcg_temp_free_ptr(tcg_rm_ptr); + } } /* Crypto two-reg SHA @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 12, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - CryptoTwoOpFn *genfn; + gen_helper_gvec_2 *genfn; bool feature; - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; if (size != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - - genfn(tcg_rd_ptr, tcg_rn_ptr); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); + gen_gvec_op2_ool(s, true, rd, rn, 0, genfn); } static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_CMP(VCGE_S, TCG_COND_GE) DO_3SAME_CMP(VCGE_U, TCG_COND_GEU) DO_3SAME_CMP(VCEQ, TCG_COND_EQ) -static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) -{ - tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, - 0, gen_helper_gvec_pmul_b); -} +#define WRAP_OOL_FN(WRAPNAME, FUNC) \ + static void WRAPNAME(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, \ + uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) \ + { \ + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, 0, FUNC); \ + } + +WRAP_OOL_FN(gen_VMUL_p_3s, gen_helper_gvec_pmul_b) static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_SHA1_3s(DisasContext *s, arg_SHA1_3s *a) return true; } -static bool trans_SHA256H_3s(DisasContext *s, arg_SHA256H_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha2, s)) { - return false; +#define DO_SHA2(NAME, FUNC) \ + WRAP_OOL_FN(gen_##NAME##_3s, FUNC) \ + static bool trans_##NAME##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (!dc_isar_feature(aa32_sha2, s)) { \ + return false; \ + } \ + return do_3same(s, a, gen_##NAME##_3s); \ } - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - gen_helper_crypto_sha256h(ptr1, ptr2, ptr3); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} - -static bool trans_SHA256H2_3s(DisasContext *s, arg_SHA256H2_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha2, s)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - gen_helper_crypto_sha256h2(ptr1, ptr2, ptr3); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} - -static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha2, s)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - gen_helper_crypto_sha256su1(ptr1, ptr2, ptr3); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} +DO_SHA2(SHA256H, gen_helper_crypto_sha256h) +DO_SHA2(SHA256H2, gen_helper_crypto_sha256h2) +DO_SHA2(SHA256SU1, gen_helper_crypto_sha256su1) #define DO_3SAME_64(INSN, FUNC) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int vec_size; uint32_t imm; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; - TCGv_ptr ptr1, ptr2; + TCGv_ptr ptr1; TCGv_i64 tmp64; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) { return 1; } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rm); - - gen_helper_crypto_sha1h(ptr1, ptr2); - - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); + tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0, + gen_helper_crypto_sha1h); break; case NEON_2RM_SHA1SU1: if ((rm | rd) & 1) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } else if (!dc_isar_feature(aa32_sha1, s)) { return 1; } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rm); - if (q) { - gen_helper_crypto_sha256su0(ptr1, ptr2); - } else { - gen_helper_crypto_sha1su1(ptr1, ptr2); - } - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); + tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0, + q ? gen_helper_crypto_sha256su0 + : gen_helper_crypto_sha1su1); break; - case NEON_2RM_VMVN: tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size); break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than passing an opcode to a helper, fully decode the operation at translate time. Use clear_tail_16 to zap the balance of the SVE register with the AdvSIMD write. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-6-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 | 5 +- target/arm/neon-dp.decode | 6 +- target/arm/crypto_helper.c | 99 +++++++++++++++++++++------------ target/arm/translate-a64.c | 29 ++++------ target/arm/translate-neon.inc.c | 46 ++++----------- 5 files changed, 93 insertions(+), 92 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(neon_qzip32, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_4(crypto_aese, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_aesmc, TCG_CALL_NO_RWG, void, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(crypto_sha1_3reg, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1su0, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1c, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1p, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sha1m, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_sha1h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(crypto_sha1su1, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same @3same_crypto .... .... .... .... .... .... .... .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 q=1 -SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA1C_3s 1111 001 0 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA1P_3s 1111 001 0 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA1M_3s 1111 001 0 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto +SHA1SU0_3s 1111 001 0 0 . 11 .... .... 1100 . 1 . 0 .... @3same_crypto SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... @3same_crypto SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... @3same_crypto SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... @3same_crypto diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ union CRYPTO_STATE { }; #ifdef HOST_WORDS_BIGENDIAN -#define CR_ST_BYTE(state, i) (state.bytes[(15 - (i)) ^ 8]) -#define CR_ST_WORD(state, i) (state.words[(3 - (i)) ^ 2]) +#define CR_ST_BYTE(state, i) ((state).bytes[(15 - (i)) ^ 8]) +#define CR_ST_WORD(state, i) ((state).words[(3 - (i)) ^ 2]) #else -#define CR_ST_BYTE(state, i) (state.bytes[i]) -#define CR_ST_WORD(state, i) (state.words[i]) +#define CR_ST_BYTE(state, i) ((state).bytes[i]) +#define CR_ST_WORD(state, i) ((state).words[i]) #endif /* @@ -XXX,XX +XXX,XX @@ static uint32_t maj(uint32_t x, uint32_t y, uint32_t z) return (x & y) | ((x | y) & z); } -void HELPER(crypto_sha1_3reg)(void *vd, void *vn, void *vm, uint32_t op) +void HELPER(crypto_sha1su0)(void *vd, void *vn, void *vm, uint32_t desc) +{ + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t d0, d1; + + d0 = d[1] ^ d[0] ^ m[0]; + d1 = n[0] ^ d[1] ^ m[1]; + d[0] = d0; + d[1] = d1; + + clear_tail_16(vd, desc); +} + +static inline void crypto_sha1_3reg(uint64_t *rd, uint64_t *rn, + uint64_t *rm, uint32_t desc, + uint32_t (*fn)(union CRYPTO_STATE *d)) { - uint64_t *rd = vd; - uint64_t *rn = vn; - uint64_t *rm = vm; union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + int i; - if (op == 3) { /* sha1su0 */ - d.l[0] ^= d.l[1] ^ m.l[0]; - d.l[1] ^= n.l[0] ^ m.l[1]; - } else { - int i; + for (i = 0; i < 4; i++) { + uint32_t t = fn(&d); - for (i = 0; i < 4; i++) { - uint32_t t; + t += rol32(CR_ST_WORD(d, 0), 5) + CR_ST_WORD(n, 0) + + CR_ST_WORD(m, i); - switch (op) { - case 0: /* sha1c */ - t = cho(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); - break; - case 1: /* sha1p */ - t = par(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); - break; - case 2: /* sha1m */ - t = maj(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); - break; - default: - g_assert_not_reached(); - } - t += rol32(CR_ST_WORD(d, 0), 5) + CR_ST_WORD(n, 0) - + CR_ST_WORD(m, i); - - CR_ST_WORD(n, 0) = CR_ST_WORD(d, 3); - CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); - CR_ST_WORD(d, 2) = ror32(CR_ST_WORD(d, 1), 2); - CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); - CR_ST_WORD(d, 0) = t; - } + CR_ST_WORD(n, 0) = CR_ST_WORD(d, 3); + CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); + CR_ST_WORD(d, 2) = ror32(CR_ST_WORD(d, 1), 2); + CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); + CR_ST_WORD(d, 0) = t; } rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(rd, desc); +} + +static uint32_t do_sha1c(union CRYPTO_STATE *d) +{ + return cho(CR_ST_WORD(*d, 1), CR_ST_WORD(*d, 2), CR_ST_WORD(*d, 3)); +} + +void HELPER(crypto_sha1c)(void *vd, void *vn, void *vm, uint32_t desc) +{ + crypto_sha1_3reg(vd, vn, vm, desc, do_sha1c); +} + +static uint32_t do_sha1p(union CRYPTO_STATE *d) +{ + return par(CR_ST_WORD(*d, 1), CR_ST_WORD(*d, 2), CR_ST_WORD(*d, 3)); +} + +void HELPER(crypto_sha1p)(void *vd, void *vn, void *vm, uint32_t desc) +{ + crypto_sha1_3reg(vd, vn, vm, desc, do_sha1p); +} + +static uint32_t do_sha1m(union CRYPTO_STATE *d) +{ + return maj(CR_ST_WORD(*d, 1), CR_ST_WORD(*d, 2), CR_ST_WORD(*d, 3)); +} + +void HELPER(crypto_sha1m)(void *vd, void *vn, void *vm, uint32_t desc) +{ + crypto_sha1_3reg(vd, vn, vm, desc, do_sha1m); } void HELPER(crypto_sha1h)(void *vd, void *vm, uint32_t desc) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SHA1C */ + genfn = gen_helper_crypto_sha1c; + feature = dc_isar_feature(aa64_sha1, s); + break; case 1: /* SHA1P */ + genfn = gen_helper_crypto_sha1p; + feature = dc_isar_feature(aa64_sha1, s); + break; case 2: /* SHA1M */ + genfn = gen_helper_crypto_sha1m; + feature = dc_isar_feature(aa64_sha1, s); + break; case 3: /* SHA1SU0 */ - genfn = NULL; + genfn = gen_helper_crypto_sha1su0; feature = dc_isar_feature(aa64_sha1, s); break; case 4: /* SHA256H */ @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - - if (genfn) { - gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); - } else { - TCGv_i32 tcg_opcode = tcg_const_i32(opcode); - TCGv_ptr tcg_rd_ptr = vec_full_reg_ptr(s, rd); - TCGv_ptr tcg_rn_ptr = vec_full_reg_ptr(s, rn); - TCGv_ptr tcg_rm_ptr = vec_full_reg_ptr(s, rm); - - gen_helper_crypto_sha1_3reg(tcg_rd_ptr, tcg_rn_ptr, - tcg_rm_ptr, tcg_opcode); - - tcg_temp_free_i32(tcg_opcode); - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); - } + gen_gvec_op3_ool(s, true, rd, rn, rm, 0, genfn); } /* Crypto two-reg SHA diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) DO_VQRDMLAH(VQRDMLAH, gen_gvec_sqrdmlah_qc) DO_VQRDMLAH(VQRDMLSH, gen_gvec_sqrdmlsh_qc) -static bool trans_SHA1_3s(DisasContext *s, arg_SHA1_3s *a) -{ - TCGv_ptr ptr1, ptr2, ptr3; - TCGv_i32 tmp; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !dc_isar_feature(aa32_sha1, s)) { - return false; +#define DO_SHA1(NAME, FUNC) \ + WRAP_OOL_FN(gen_##NAME##_3s, FUNC) \ + static bool trans_##NAME##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (!dc_isar_feature(aa32_sha1, s)) { \ + return false; \ + } \ + return do_3same(s, a, gen_##NAME##_3s); \ } - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - - if ((a->vn | a->vm | a->vd) & 1) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - ptr1 = vfp_reg_ptr(true, a->vd); - ptr2 = vfp_reg_ptr(true, a->vn); - ptr3 = vfp_reg_ptr(true, a->vm); - tmp = tcg_const_i32(a->optype); - gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp); - tcg_temp_free_i32(tmp); - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - - return true; -} +DO_SHA1(SHA1C, gen_helper_crypto_sha1c) +DO_SHA1(SHA1P, gen_helper_crypto_sha1p) +DO_SHA1(SHA1M, gen_helper_crypto_sha1m) +DO_SHA1(SHA1SU0, gen_helper_crypto_sha1su0) #define DO_SHA2(NAME, FUNC) \ WRAP_OOL_FN(gen_##NAME##_3s, FUNC) \ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than passing an opcode to a helper, fully decode the operation at translate time. Use clear_tail_16 to zap the balance of the SVE register with the AdvSIMD write. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200514212831.31248-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 5 ++++- target/arm/crypto_helper.c | 24 ++++++++++++++++++------ target/arm/translate-a64.c | 21 +++++---------------- 3 files changed, 27 insertions(+), 23 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt1a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt1b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt2a, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(crypto_sm3tt2b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG, diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/crypto_helper.c +++ b/target/arm/crypto_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail_16(vd, desc); } -void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, - uint32_t opcode) +static inline void QEMU_ALWAYS_INLINE +crypto_sm3tt(uint64_t *rd, uint64_t *rn, uint64_t *rm, + uint32_t desc, uint32_t opcode) { - uint64_t *rd = vd; - uint64_t *rn = vn; - uint64_t *rm = vm; union CRYPTO_STATE d = { .l = { rd[0], rd[1] } }; union CRYPTO_STATE n = { .l = { rn[0], rn[1] } }; union CRYPTO_STATE m = { .l = { rm[0], rm[1] } }; + uint32_t imm2 = simd_data(desc); uint32_t t; assert(imm2 < 4); @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, /* SM3TT2B */ t = cho(CR_ST_WORD(d, 3), CR_ST_WORD(d, 2), CR_ST_WORD(d, 1)); } else { - g_assert_not_reached(); + qemu_build_not_reached(); } t += CR_ST_WORD(d, 0) + CR_ST_WORD(m, imm2); @@ -XXX,XX +XXX,XX @@ void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2, rd[0] = d.l[0]; rd[1] = d.l[1]; + + clear_tail_16(rd, desc); } +#define DO_SM3TT(NAME, OPCODE) \ + void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ + { crypto_sm3tt(vd, vn, vm, desc, OPCODE); } + +DO_SM3TT(crypto_sm3tt1a, 0) +DO_SM3TT(crypto_sm3tt1b, 1) +DO_SM3TT(crypto_sm3tt2a, 2) +DO_SM3TT(crypto_sm3tt2b, 3) + +#undef DO_SM3TT + static uint8_t const sm4_sbox[] = { 0xd6, 0x90, 0xe9, 0xfe, 0xcc, 0xe1, 0x3d, 0xb7, 0x16, 0xb6, 0x14, 0xc2, 0x28, 0xfb, 0x2c, 0x05, diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) */ static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) { + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_crypto_sm3tt1a, gen_helper_crypto_sm3tt1b, + gen_helper_crypto_sm3tt2a, gen_helper_crypto_sm3tt2b, + }; int opcode = extract32(insn, 10, 2); int imm2 = extract32(insn, 12, 2); int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; - TCGv_i32 tcg_imm2, tcg_opcode; if (!dc_isar_feature(aa64_sm3, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) return; } - tcg_rd_ptr = vec_full_reg_ptr(s, rd); - tcg_rn_ptr = vec_full_reg_ptr(s, rn); - tcg_rm_ptr = vec_full_reg_ptr(s, rm); - tcg_imm2 = tcg_const_i32(imm2); - tcg_opcode = tcg_const_i32(opcode); - - gen_helper_crypto_sm3tt(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr, tcg_imm2, - tcg_opcode); - - tcg_temp_free_ptr(tcg_rd_ptr); - tcg_temp_free_ptr(tcg_rn_ptr); - tcg_temp_free_ptr(tcg_rm_ptr); - tcg_temp_free_i32(tcg_imm2); - tcg_temp_free_i32(tcg_opcode); + gen_gvec_op3_ool(s, true, rd, rn, rm, imm2, fns[opcode]); } /* C3.6 Data processing - SIMD, inc Crypto -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The ADC region size is 256B, split as: - [0x00 - 0x4f] defined - [0x50 - 0xff] reserved All registers are 32-bit (thus when the datasheet mentions the last defined register is 0x4c, it means its address range is 0x4c .. 0x4f. This model implementation is also 32-bit. Set MemoryRegionOps 'impl' fields. See: 'RM0033 Reference manual Rev 8', Table 10.13.18 "ADC register map". Reported-by: Seth Kintigh <skintigh@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200603055915.17678-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/adc/stm32f2xx_adc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/adc/stm32f2xx_adc.c b/hw/adc/stm32f2xx_adc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/adc/stm32f2xx_adc.c +++ b/hw/adc/stm32f2xx_adc.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps stm32f2xx_adc_ops = { .read = stm32f2xx_adc_read, .write = stm32f2xx_adc_write, .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 4, + .impl.max_access_size = 4, }; static const VMStateDescription vmstate_stm32f2xx_adc = { @@ -XXX,XX +XXX,XX @@ static void stm32f2xx_adc_init(Object *obj) sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); memory_region_init_io(&s->mmio, obj, &stm32f2xx_adc_ops, s, - TYPE_STM32F2XX_ADC, 0xFF); + TYPE_STM32F2XX_ADC, 0x100); sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); } -- 2.20.1 From: Thomas Huth <thuth@redhat.com> As described by Edgar here: https://www.mail-archive.com/qemu-devel@nongnu.org/msg605124.html we can use the Ubuntu kernel for testing the xlnx-versal-virt machine. So let's add a boot test for this now. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200525141237.15243-1-thuth@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(LinuxKernelTest): console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) + def test_aarch64_xlnx_versal_virt(self): + """ + :avocado: tags=arch:aarch64 + :avocado: tags=machine:xlnx-versal-virt + :avocado: tags=device:pl011 + :avocado: tags=device:arm_gicv3 + """ + kernel_url = ('http://ports.ubuntu.com/ubuntu-ports/dists/' + 'bionic-updates/main/installer-arm64/current/images/' + 'netboot/ubuntu-installer/arm64/linux') + kernel_hash = '5bfc54cf7ed8157d93f6e5b0241e727b6dc22c50' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + + initrd_url = ('http://ports.ubuntu.com/ubuntu-ports/dists/' + 'bionic-updates/main/installer-arm64/current/images/' + 'netboot/ubuntu-installer/arm64/initrd.gz') + initrd_hash = 'd385d3e88d53e2004c5d43cbe668b458a094f772' + initrd_path = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + + self.vm.set_console() + self.vm.add_args('-m', '2G', + '-kernel', kernel_path, + '-initrd', initrd_path) + self.vm.launch() + self.wait_for_console_pattern('Checked W+X mappings: passed') + def test_arm_virt(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200602135050.593692-1-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/aspeed.rst | 85 ++++++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 1 + 2 files changed, 86 insertions(+) create mode 100644 docs/system/arm/aspeed.rst diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/aspeed.rst @@ -XXX,XX +XXX,XX @@ +Aspeed family boards (``*-bmc``, ``ast2500-evb``, ``ast2600-evb``) +================================================================== + +The QEMU Aspeed machines model BMCs of various OpenPOWER systems and +Aspeed evaluation boards. They are based on different releases of the +Aspeed SoC : the AST2400 integrating an ARM926EJ-S CPU (400MHz), the +AST2500 with an ARM1176JZS CPU (800MHz) and more recently the AST2600 +with dual cores ARM Cortex A7 CPUs (1.2GHz). + +The SoC comes with RAM, Gigabit ethernet, USB, SD/MMC, USB, SPI, I2C, +etc. + +AST2400 SoC based machines : + +- ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC + +AST2500 SoC based machines : + +- ``ast2500-evb`` Aspeed AST2500 Evaluation board +- ``romulus-bmc`` OpenPOWER Romulus POWER9 BMC +- ``witherspoon-bmc`` OpenPOWER Witherspoon POWER9 BMC +- ``sonorapass-bmc`` OCP SonoraPass BMC +- ``swift-bmc`` OpenPOWER Swift BMC POWER9 + +AST2600 SoC based machines : + +- ``ast2600-evb`` Aspeed AST2600 Evaluation board (Cortex A7) +- ``tacoma-bmc`` OpenPOWER Witherspoon POWER9 AST2600 BMC + +Supported devices +----------------- + + * SMP (for the AST2600 Cortex-A7) + * Interrupt Controller (VIC) + * Timer Controller + * RTC Controller + * I2C Controller + * System Control Unit (SCU) + * SRAM mapping + * X-DMA Controller (basic interface) + * Static Memory Controller (SMC or FMC) - Only SPI Flash support + * SPI Memory Controller + * USB 2.0 Controller + * SD/MMC storage controllers + * SDRAM controller (dummy interface for basic settings and training) + * Watchdog Controller + * GPIO Controller (Master only) + * UART + * Ethernet controllers + + +Missing devices +--------------- + + * Coprocessor support + * ADC (out of tree implementation) + * PWM and Fan Controller + * LPC Bus Controller + * Slave GPIO Controller + * Super I/O Controller + * Hash/Crypto Engine + * PCI-Express 1 Controller + * Graphic Display Controller + * PECI Controller + * MCTP Controller + * Mailbox Controller + * Virtual UART + * eSPI Controller + * I3C Controller + +Boot options +------------ + +The Aspeed machines can be started using the -kernel option to load a +Linux kernel or from a firmare image which can be downloaded from the +OpenPOWER jenkins : + + https://openpower.xyz/ + +The image should be attached as an MTD drive. Run : + +.. code-block:: bash + + $ qemu-system-arm -M romulus-bmc -nic user \ + -drive file=flash-romulus,format=raw,if=mtd -nographic diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/realview arm/versatile arm/vexpress + arm/aspeed arm/musicpal arm/nseries arm/orangepi -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add BCM2835 SOC MPHI (Message-based Parallel Host Interface) emulation. It is very basic, only providing the FIQ interrupt needed to allow the dwc-otg USB host controller driver in the Raspbian kernel to function. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Acked-by: Philippe Mathieu-Daude <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200520235349.21215-2-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 2 + include/hw/misc/bcm2835_mphi.h | 44 ++++++ hw/arm/bcm2835_peripherals.c | 17 +++ hw/misc/bcm2835_mphi.c | 191 +++++++++++++++++++++++++++ hw/misc/Makefile.objs | 1 + 5 files changed, 255 insertions(+) create mode 100644 include/hw/misc/bcm2835_mphi.h create mode 100644 hw/misc/bcm2835_mphi.c diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/bcm2835_property.h" #include "hw/misc/bcm2835_rng.h" #include "hw/misc/bcm2835_mbox.h" +#include "hw/misc/bcm2835_mphi.h" #include "hw/misc/bcm2835_thermal.h" #include "hw/sd/sdhci.h" #include "hw/sd/bcm2835_sdhost.h" @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { qemu_irq irq, fiq; BCM2835SystemTimerState systmr; + BCM2835MphiState mphi; UnimplementedDeviceState armtmr; UnimplementedDeviceState cprman; UnimplementedDeviceState a2w; diff --git a/include/hw/misc/bcm2835_mphi.h b/include/hw/misc/bcm2835_mphi.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/bcm2835_mphi.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 SOC MPHI state definitions + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef HW_MISC_BCM2835_MPHI_H +#define HW_MISC_BCM2835_MPHI_H + +#include "hw/irq.h" +#include "hw/sysbus.h" + +#define MPHI_MMIO_SIZE 0x1000 + +typedef struct BCM2835MphiState BCM2835MphiState; + +struct BCM2835MphiState { + SysBusDevice parent_obj; + qemu_irq irq; + MemoryRegion iomem; + + uint32_t outdda; + uint32_t outddb; + uint32_t ctrl; + uint32_t intstat; + uint32_t swirq; +}; + +#define TYPE_BCM2835_MPHI "bcm2835-mphi" + +#define BCM2835_MPHI(obj) \ + OBJECT_CHECK(BCM2835MphiState, (obj), TYPE_BCM2835_MPHI) + +#endif diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) OBJECT(&s->sdhci.sdbus)); object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhost", OBJECT(&s->sdhost.sdbus)); + + /* Mphi */ + sysbus_init_child_obj(obj, "mphi", &s->mphi, sizeof(s->mphi), + TYPE_BCM2835_MPHI); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->gpio), "sd-bus"); + /* Mphi */ + object_property_set_bool(OBJECT(&s->mphi), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + memory_region_add_subregion(&s->peri_mr, MPHI_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->mphi), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mphi), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, + INTERRUPT_HOSTPORT)); + create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); create_unimp(s, &s->cprman, "bcm2835-cprman", CPRMAN_OFFSET, 0x1000); create_unimp(s, &s->a2w, "bcm2835-a2w", A2W_OFFSET, 0x1000); diff --git a/hw/misc/bcm2835_mphi.c b/hw/misc/bcm2835_mphi.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/bcm2835_mphi.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 SOC MPHI emulation + * + * Very basic emulation, only providing the FIQ interrupt needed to + * allow the dwc-otg USB host controller driver in the Raspbian kernel + * to function. + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/misc/bcm2835_mphi.h" +#include "migration/vmstate.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/main-loop.h" + +static inline void mphi_raise_irq(BCM2835MphiState *s) +{ + qemu_set_irq(s->irq, 1); +} + +static inline void mphi_lower_irq(BCM2835MphiState *s) +{ + qemu_set_irq(s->irq, 0); +} + +static uint64_t mphi_reg_read(void *ptr, hwaddr addr, unsigned size) +{ + BCM2835MphiState *s = ptr; + uint32_t val = 0; + + switch (addr) { + case 0x28: /* outdda */ + val = s->outdda; + break; + case 0x2c: /* outddb */ + val = s->outddb; + break; + case 0x4c: /* ctrl */ + val = s->ctrl; + val |= 1 << 17; + break; + case 0x50: /* intstat */ + val = s->intstat; + break; + case 0x1f0: /* swirq_set */ + val = s->swirq; + break; + case 0x1f4: /* swirq_clr */ + val = s->swirq; + break; + default: + qemu_log_mask(LOG_UNIMP, "read from unknown register"); + break; + } + + return val; +} + +static void mphi_reg_write(void *ptr, hwaddr addr, uint64_t val, unsigned size) +{ + BCM2835MphiState *s = ptr; + int do_irq = 0; + + switch (addr) { + case 0x28: /* outdda */ + s->outdda = val; + break; + case 0x2c: /* outddb */ + s->outddb = val; + if (val & (1 << 29)) { + do_irq = 1; + } + break; + case 0x4c: /* ctrl */ + s->ctrl = val; + if (val & (1 << 16)) { + do_irq = -1; + } + break; + case 0x50: /* intstat */ + s->intstat = val; + if (val & ((1 << 16) | (1 << 29))) { + do_irq = -1; + } + break; + case 0x1f0: /* swirq_set */ + s->swirq |= val; + do_irq = 1; + break; + case 0x1f4: /* swirq_clr */ + s->swirq &= ~val; + do_irq = -1; + break; + default: + qemu_log_mask(LOG_UNIMP, "write to unknown register"); + return; + } + + if (do_irq > 0) { + mphi_raise_irq(s); + } else if (do_irq < 0) { + mphi_lower_irq(s); + } +} + +static const MemoryRegionOps mphi_mmio_ops = { + .read = mphi_reg_read, + .write = mphi_reg_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void mphi_reset(DeviceState *dev) +{ + BCM2835MphiState *s = BCM2835_MPHI(dev); + + s->outdda = 0; + s->outddb = 0; + s->ctrl = 0; + s->intstat = 0; + s->swirq = 0; +} + +static void mphi_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + BCM2835MphiState *s = BCM2835_MPHI(dev); + + sysbus_init_irq(sbd, &s->irq); +} + +static void mphi_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + BCM2835MphiState *s = BCM2835_MPHI(obj); + + memory_region_init_io(&s->iomem, obj, &mphi_mmio_ops, s, "mphi", MPHI_MMIO_SIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +const VMStateDescription vmstate_mphi_state = { + .name = "mphi", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(outdda, BCM2835MphiState), + VMSTATE_UINT32(outddb, BCM2835MphiState), + VMSTATE_UINT32(ctrl, BCM2835MphiState), + VMSTATE_UINT32(intstat, BCM2835MphiState), + VMSTATE_UINT32(swirq, BCM2835MphiState), + VMSTATE_END_OF_LIST() + } +}; + +static void mphi_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = mphi_realize; + dc->reset = mphi_reset; + dc->vmsd = &vmstate_mphi_state; +} + +static const TypeInfo bcm2835_mphi_type_info = { + .name = TYPE_BCM2835_MPHI, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835MphiState), + .instance_init = mphi_init, + .class_init = mphi_class_init, +}; + +static void bcm2835_mphi_register_types(void) +{ + type_register_static(&bcm2835_mphi_type_info); +} + +type_init(bcm2835_mphi_register_types) diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_OMAP) += omap_l4.o common-obj-$(CONFIG_OMAP) += omap_sdrc.o common-obj-$(CONFIG_OMAP) += omap_tap.o common-obj-$(CONFIG_RASPI) += bcm2835_mbox.o +common-obj-$(CONFIG_RASPI) += bcm2835_mphi.o common-obj-$(CONFIG_RASPI) += bcm2835_property.o common-obj-$(CONFIG_RASPI) += bcm2835_rng.o common-obj-$(CONFIG_RASPI) += bcm2835_thermal.o -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Import the dwc-hsotg (dwc2) register definitions file from the Linux kernel. This is a copy of drivers/usb/dwc2/hw.h from the mainline Linux kernel, the only changes being to the header, and two instances of 'u32' changed to 'uint32_t' to allow it to compile. Checkpatch throws a boatload of errors due to the tab indentation, but I would rather import it as-is than reformat it. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-3-pauldzim@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/usb/dwc2-regs.h | 899 +++++++++++++++++++++++++++++++++++++ 1 file changed, 899 insertions(+) create mode 100644 include/hw/usb/dwc2-regs.h diff --git a/include/hw/usb/dwc2-regs.h b/include/hw/usb/dwc2-regs.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/usb/dwc2-regs.h @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Imported from the Linux kernel file drivers/usb/dwc2/hw.h, commit + * a89bae709b3492b478480a2c9734e7e9393b279c ("usb: dwc2: Move + * UTMI_PHY_DATA defines closer") + * + * hw.h - DesignWare HS OTG Controller hardware definitions + * + * Copyright 2004-2013 Synopsys, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions, and the following disclaimer, + * without modification. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. The names of the above-listed copyright holders may not be used + * to endorse or promote products derived from this software without + * specific prior written permission. + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation; either version 2 of the License, or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS + * IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, + * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR + * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF + * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING + * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __DWC2_HW_H__ +#define __DWC2_HW_H__ + +#define HSOTG_REG(x) (x) + +#define GOTGCTL HSOTG_REG(0x000) +#define GOTGCTL_CHIRPEN BIT(27) +#define GOTGCTL_MULT_VALID_BC_MASK (0x1f << 22) +#define GOTGCTL_MULT_VALID_BC_SHIFT 22 +#define GOTGCTL_OTGVER BIT(20) +#define GOTGCTL_BSESVLD BIT(19) +#define GOTGCTL_ASESVLD BIT(18) +#define GOTGCTL_DBNC_SHORT BIT(17) +#define GOTGCTL_CONID_B BIT(16) +#define GOTGCTL_DBNCE_FLTR_BYPASS BIT(15) +#define GOTGCTL_DEVHNPEN BIT(11) +#define GOTGCTL_HSTSETHNPEN BIT(10) +#define GOTGCTL_HNPREQ BIT(9) +#define GOTGCTL_HSTNEGSCS BIT(8) +#define GOTGCTL_SESREQ BIT(1) +#define GOTGCTL_SESREQSCS BIT(0) + +#define GOTGINT HSOTG_REG(0x004) +#define GOTGINT_DBNCE_DONE BIT(19) +#define GOTGINT_A_DEV_TOUT_CHG BIT(18) +#define GOTGINT_HST_NEG_DET BIT(17) +#define GOTGINT_HST_NEG_SUC_STS_CHNG BIT(9) +#define GOTGINT_SES_REQ_SUC_STS_CHNG BIT(8) +#define GOTGINT_SES_END_DET BIT(2) + +#define GAHBCFG HSOTG_REG(0x008) +#define GAHBCFG_AHB_SINGLE BIT(23) +#define GAHBCFG_NOTI_ALL_DMA_WRIT BIT(22) +#define GAHBCFG_REM_MEM_SUPP BIT(21) +#define GAHBCFG_P_TXF_EMP_LVL BIT(8) +#define GAHBCFG_NP_TXF_EMP_LVL BIT(7) +#define GAHBCFG_DMA_EN BIT(5) +#define GAHBCFG_HBSTLEN_MASK (0xf << 1) +#define GAHBCFG_HBSTLEN_SHIFT 1 +#define GAHBCFG_HBSTLEN_SINGLE 0 +#define GAHBCFG_HBSTLEN_INCR 1 +#define GAHBCFG_HBSTLEN_INCR4 3 +#define GAHBCFG_HBSTLEN_INCR8 5 +#define GAHBCFG_HBSTLEN_INCR16 7 +#define GAHBCFG_GLBL_INTR_EN BIT(0) +#define GAHBCFG_CTRL_MASK (GAHBCFG_P_TXF_EMP_LVL | \ + GAHBCFG_NP_TXF_EMP_LVL | \ + GAHBCFG_DMA_EN | \ + GAHBCFG_GLBL_INTR_EN) + +#define GUSBCFG HSOTG_REG(0x00C) +#define GUSBCFG_FORCEDEVMODE BIT(30) +#define GUSBCFG_FORCEHOSTMODE BIT(29) +#define GUSBCFG_TXENDDELAY BIT(28) +#define GUSBCFG_ICTRAFFICPULLREMOVE BIT(27) +#define GUSBCFG_ICUSBCAP BIT(26) +#define GUSBCFG_ULPI_INT_PROT_DIS BIT(25) +#define GUSBCFG_INDICATORPASSTHROUGH BIT(24) +#define GUSBCFG_INDICATORCOMPLEMENT BIT(23) +#define GUSBCFG_TERMSELDLPULSE BIT(22) +#define GUSBCFG_ULPI_INT_VBUS_IND BIT(21) +#define GUSBCFG_ULPI_EXT_VBUS_DRV BIT(20) +#define GUSBCFG_ULPI_CLK_SUSP_M BIT(19) +#define GUSBCFG_ULPI_AUTO_RES BIT(18) +#define GUSBCFG_ULPI_FS_LS BIT(17) +#define GUSBCFG_OTG_UTMI_FS_SEL BIT(16) +#define GUSBCFG_PHY_LP_CLK_SEL BIT(15) +#define GUSBCFG_USBTRDTIM_MASK (0xf << 10) +#define GUSBCFG_USBTRDTIM_SHIFT 10 +#define GUSBCFG_HNPCAP BIT(9) +#define GUSBCFG_SRPCAP BIT(8) +#define GUSBCFG_DDRSEL BIT(7) +#define GUSBCFG_PHYSEL BIT(6) +#define GUSBCFG_FSINTF BIT(5) +#define GUSBCFG_ULPI_UTMI_SEL BIT(4) +#define GUSBCFG_PHYIF16 BIT(3) +#define GUSBCFG_PHYIF8 (0 << 3) +#define GUSBCFG_TOUTCAL_MASK (0x7 << 0) +#define GUSBCFG_TOUTCAL_SHIFT 0 +#define GUSBCFG_TOUTCAL_LIMIT 0x7 +#define GUSBCFG_TOUTCAL(_x) ((_x) << 0) + +#define GRSTCTL HSOTG_REG(0x010) +#define GRSTCTL_AHBIDLE BIT(31) +#define GRSTCTL_DMAREQ BIT(30) +#define GRSTCTL_TXFNUM_MASK (0x1f << 6) +#define GRSTCTL_TXFNUM_SHIFT 6 +#define GRSTCTL_TXFNUM_LIMIT 0x1f +#define GRSTCTL_TXFNUM(_x) ((_x) << 6) +#define GRSTCTL_TXFFLSH BIT(5) +#define GRSTCTL_RXFFLSH BIT(4) +#define GRSTCTL_IN_TKNQ_FLSH BIT(3) +#define GRSTCTL_FRMCNTRRST BIT(2) +#define GRSTCTL_HSFTRST BIT(1) +#define GRSTCTL_CSFTRST BIT(0) + +#define GINTSTS HSOTG_REG(0x014) +#define GINTMSK HSOTG_REG(0x018) +#define GINTSTS_WKUPINT BIT(31) +#define GINTSTS_SESSREQINT BIT(30) +#define GINTSTS_DISCONNINT BIT(29) +#define GINTSTS_CONIDSTSCHNG BIT(28) +#define GINTSTS_LPMTRANRCVD BIT(27) +#define GINTSTS_PTXFEMP BIT(26) +#define GINTSTS_HCHINT BIT(25) +#define GINTSTS_PRTINT BIT(24) +#define GINTSTS_RESETDET BIT(23) +#define GINTSTS_FET_SUSP BIT(22) +#define GINTSTS_INCOMPL_IP BIT(21) +#define GINTSTS_INCOMPL_SOOUT BIT(21) +#define GINTSTS_INCOMPL_SOIN BIT(20) +#define GINTSTS_OEPINT BIT(19) +#define GINTSTS_IEPINT BIT(18) +#define GINTSTS_EPMIS BIT(17) +#define GINTSTS_RESTOREDONE BIT(16) +#define GINTSTS_EOPF BIT(15) +#define GINTSTS_ISOUTDROP BIT(14) +#define GINTSTS_ENUMDONE BIT(13) +#define GINTSTS_USBRST BIT(12) +#define GINTSTS_USBSUSP BIT(11) +#define GINTSTS_ERLYSUSP BIT(10) +#define GINTSTS_I2CINT BIT(9) +#define GINTSTS_ULPI_CK_INT BIT(8) +#define GINTSTS_GOUTNAKEFF BIT(7) +#define GINTSTS_GINNAKEFF BIT(6) +#define GINTSTS_NPTXFEMP BIT(5) +#define GINTSTS_RXFLVL BIT(4) +#define GINTSTS_SOF BIT(3) +#define GINTSTS_OTGINT BIT(2) +#define GINTSTS_MODEMIS BIT(1) +#define GINTSTS_CURMODE_HOST BIT(0) + +#define GRXSTSR HSOTG_REG(0x01C) +#define GRXSTSP HSOTG_REG(0x020) +#define GRXSTS_FN_MASK (0x7f << 25) +#define GRXSTS_FN_SHIFT 25 +#define GRXSTS_PKTSTS_MASK (0xf << 17) +#define GRXSTS_PKTSTS_SHIFT 17 +#define GRXSTS_PKTSTS_GLOBALOUTNAK 1 +#define GRXSTS_PKTSTS_OUTRX 2 +#define GRXSTS_PKTSTS_HCHIN 2 +#define GRXSTS_PKTSTS_OUTDONE 3 +#define GRXSTS_PKTSTS_HCHIN_XFER_COMP 3 +#define GRXSTS_PKTSTS_SETUPDONE 4 +#define GRXSTS_PKTSTS_DATATOGGLEERR 5 +#define GRXSTS_PKTSTS_SETUPRX 6 +#define GRXSTS_PKTSTS_HCHHALTED 7 +#define GRXSTS_HCHNUM_MASK (0xf << 0) +#define GRXSTS_HCHNUM_SHIFT 0 +#define GRXSTS_DPID_MASK (0x3 << 15) +#define GRXSTS_DPID_SHIFT 15 +#define GRXSTS_BYTECNT_MASK (0x7ff << 4) +#define GRXSTS_BYTECNT_SHIFT 4 +#define GRXSTS_EPNUM_MASK (0xf << 0) +#define GRXSTS_EPNUM_SHIFT 0 + +#define GRXFSIZ HSOTG_REG(0x024) +#define GRXFSIZ_DEPTH_MASK (0xffff << 0) +#define GRXFSIZ_DEPTH_SHIFT 0 + +#define GNPTXFSIZ HSOTG_REG(0x028) +/* Use FIFOSIZE_* constants to access this register */ + +#define GNPTXSTS HSOTG_REG(0x02C) +#define GNPTXSTS_NP_TXQ_TOP_MASK (0x7f << 24) +#define GNPTXSTS_NP_TXQ_TOP_SHIFT 24 +#define GNPTXSTS_NP_TXQ_SPC_AVAIL_MASK (0xff << 16) +#define GNPTXSTS_NP_TXQ_SPC_AVAIL_SHIFT 16 +#define GNPTXSTS_NP_TXQ_SPC_AVAIL_GET(_v) (((_v) >> 16) & 0xff) +#define GNPTXSTS_NP_TXF_SPC_AVAIL_MASK (0xffff << 0) +#define GNPTXSTS_NP_TXF_SPC_AVAIL_SHIFT 0 +#define GNPTXSTS_NP_TXF_SPC_AVAIL_GET(_v) (((_v) >> 0) & 0xffff) + +#define GI2CCTL HSOTG_REG(0x0030) +#define GI2CCTL_BSYDNE BIT(31) +#define GI2CCTL_RW BIT(30) +#define GI2CCTL_I2CDATSE0 BIT(28) +#define GI2CCTL_I2CDEVADDR_MASK (0x3 << 26) +#define GI2CCTL_I2CDEVADDR_SHIFT 26 +#define GI2CCTL_I2CSUSPCTL BIT(25) +#define GI2CCTL_ACK BIT(24) +#define GI2CCTL_I2CEN BIT(23) +#define GI2CCTL_ADDR_MASK (0x7f << 16) +#define GI2CCTL_ADDR_SHIFT 16 +#define GI2CCTL_REGADDR_MASK (0xff << 8) +#define GI2CCTL_REGADDR_SHIFT 8 +#define GI2CCTL_RWDATA_MASK (0xff << 0) +#define GI2CCTL_RWDATA_SHIFT 0 + +#define GPVNDCTL HSOTG_REG(0x0034) +#define GGPIO HSOTG_REG(0x0038) +#define GGPIO_STM32_OTG_GCCFG_PWRDWN BIT(16) + +#define GUID HSOTG_REG(0x003c) +#define GSNPSID HSOTG_REG(0x0040) +#define GHWCFG1 HSOTG_REG(0x0044) +#define GSNPSID_ID_MASK GENMASK(31, 16) + +#define GHWCFG2 HSOTG_REG(0x0048) +#define GHWCFG2_OTG_ENABLE_IC_USB BIT(31) +#define GHWCFG2_DEV_TOKEN_Q_DEPTH_MASK (0x1f << 26) +#define GHWCFG2_DEV_TOKEN_Q_DEPTH_SHIFT 26 +#define GHWCFG2_HOST_PERIO_TX_Q_DEPTH_MASK (0x3 << 24) +#define GHWCFG2_HOST_PERIO_TX_Q_DEPTH_SHIFT 24 +#define GHWCFG2_NONPERIO_TX_Q_DEPTH_MASK (0x3 << 22) +#define GHWCFG2_NONPERIO_TX_Q_DEPTH_SHIFT 22 +#define GHWCFG2_MULTI_PROC_INT BIT(20) +#define GHWCFG2_DYNAMIC_FIFO BIT(19) +#define GHWCFG2_PERIO_EP_SUPPORTED BIT(18) +#define GHWCFG2_NUM_HOST_CHAN_MASK (0xf << 14) +#define GHWCFG2_NUM_HOST_CHAN_SHIFT 14 +#define GHWCFG2_NUM_DEV_EP_MASK (0xf << 10) +#define GHWCFG2_NUM_DEV_EP_SHIFT 10 +#define GHWCFG2_FS_PHY_TYPE_MASK (0x3 << 8) +#define GHWCFG2_FS_PHY_TYPE_SHIFT 8 +#define GHWCFG2_FS_PHY_TYPE_NOT_SUPPORTED 0 +#define GHWCFG2_FS_PHY_TYPE_DEDICATED 1 +#define GHWCFG2_FS_PHY_TYPE_SHARED_UTMI 2 +#define GHWCFG2_FS_PHY_TYPE_SHARED_ULPI 3 +#define GHWCFG2_HS_PHY_TYPE_MASK (0x3 << 6) +#define GHWCFG2_HS_PHY_TYPE_SHIFT 6 +#define GHWCFG2_HS_PHY_TYPE_NOT_SUPPORTED 0 +#define GHWCFG2_HS_PHY_TYPE_UTMI 1 +#define GHWCFG2_HS_PHY_TYPE_ULPI 2 +#define GHWCFG2_HS_PHY_TYPE_UTMI_ULPI 3 +#define GHWCFG2_POINT2POINT BIT(5) +#define GHWCFG2_ARCHITECTURE_MASK (0x3 << 3) +#define GHWCFG2_ARCHITECTURE_SHIFT 3 +#define GHWCFG2_SLAVE_ONLY_ARCH 0 +#define GHWCFG2_EXT_DMA_ARCH 1 +#define GHWCFG2_INT_DMA_ARCH 2 +#define GHWCFG2_OP_MODE_MASK (0x7 << 0) +#define GHWCFG2_OP_MODE_SHIFT 0 +#define GHWCFG2_OP_MODE_HNP_SRP_CAPABLE 0 +#define GHWCFG2_OP_MODE_SRP_ONLY_CAPABLE 1 +#define GHWCFG2_OP_MODE_NO_HNP_SRP_CAPABLE 2 +#define GHWCFG2_OP_MODE_SRP_CAPABLE_DEVICE 3 +#define GHWCFG2_OP_MODE_NO_SRP_CAPABLE_DEVICE 4 +#define GHWCFG2_OP_MODE_SRP_CAPABLE_HOST 5 +#define GHWCFG2_OP_MODE_NO_SRP_CAPABLE_HOST 6 +#define GHWCFG2_OP_MODE_UNDEFINED 7 + +#define GHWCFG3 HSOTG_REG(0x004c) +#define GHWCFG3_DFIFO_DEPTH_MASK (0xffff << 16) +#define GHWCFG3_DFIFO_DEPTH_SHIFT 16 +#define GHWCFG3_OTG_LPM_EN BIT(15) +#define GHWCFG3_BC_SUPPORT BIT(14) +#define GHWCFG3_OTG_ENABLE_HSIC BIT(13) +#define GHWCFG3_ADP_SUPP BIT(12) +#define GHWCFG3_SYNCH_RESET_TYPE BIT(11) +#define GHWCFG3_OPTIONAL_FEATURES BIT(10) +#define GHWCFG3_VENDOR_CTRL_IF BIT(9) +#define GHWCFG3_I2C BIT(8) +#define GHWCFG3_OTG_FUNC BIT(7) +#define GHWCFG3_PACKET_SIZE_CNTR_WIDTH_MASK (0x7 << 4) +#define GHWCFG3_PACKET_SIZE_CNTR_WIDTH_SHIFT 4 +#define GHWCFG3_XFER_SIZE_CNTR_WIDTH_MASK (0xf << 0) +#define GHWCFG3_XFER_SIZE_CNTR_WIDTH_SHIFT 0 + +#define GHWCFG4 HSOTG_REG(0x0050) +#define GHWCFG4_DESC_DMA_DYN BIT(31) +#define GHWCFG4_DESC_DMA BIT(30) +#define GHWCFG4_NUM_IN_EPS_MASK (0xf << 26) +#define GHWCFG4_NUM_IN_EPS_SHIFT 26 +#define GHWCFG4_DED_FIFO_EN BIT(25) +#define GHWCFG4_DED_FIFO_SHIFT 25 +#define GHWCFG4_SESSION_END_FILT_EN BIT(24) +#define GHWCFG4_B_VALID_FILT_EN BIT(23) +#define GHWCFG4_A_VALID_FILT_EN BIT(22) +#define GHWCFG4_VBUS_VALID_FILT_EN BIT(21) +#define GHWCFG4_IDDIG_FILT_EN BIT(20) +#define GHWCFG4_NUM_DEV_MODE_CTRL_EP_MASK (0xf << 16) +#define GHWCFG4_NUM_DEV_MODE_CTRL_EP_SHIFT 16 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_MASK (0x3 << 14) +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_SHIFT 14 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_8 0 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_16 1 +#define GHWCFG4_UTMI_PHY_DATA_WIDTH_8_OR_16 2 +#define GHWCFG4_ACG_SUPPORTED BIT(12) +#define GHWCFG4_IPG_ISOC_SUPPORTED BIT(11) +#define GHWCFG4_SERVICE_INTERVAL_SUPPORTED BIT(10) +#define GHWCFG4_XHIBER BIT(7) +#define GHWCFG4_HIBER BIT(6) +#define GHWCFG4_MIN_AHB_FREQ BIT(5) +#define GHWCFG4_POWER_OPTIMIZ BIT(4) +#define GHWCFG4_NUM_DEV_PERIO_IN_EP_MASK (0xf << 0) +#define GHWCFG4_NUM_DEV_PERIO_IN_EP_SHIFT 0 + +#define GLPMCFG HSOTG_REG(0x0054) +#define GLPMCFG_INVSELHSIC BIT(31) +#define GLPMCFG_HSICCON BIT(30) +#define GLPMCFG_RSTRSLPSTS BIT(29) +#define GLPMCFG_ENBESL BIT(28) +#define GLPMCFG_LPM_RETRYCNT_STS_MASK (0x7 << 25) +#define GLPMCFG_LPM_RETRYCNT_STS_SHIFT 25 +#define GLPMCFG_SNDLPM BIT(24) +#define GLPMCFG_RETRY_CNT_MASK (0x7 << 21) +#define GLPMCFG_RETRY_CNT_SHIFT 21 +#define GLPMCFG_LPM_REJECT_CTRL_CONTROL BIT(21) +#define GLPMCFG_LPM_ACCEPT_CTRL_ISOC BIT(22) +#define GLPMCFG_LPM_CHNL_INDX_MASK (0xf << 17) +#define GLPMCFG_LPM_CHNL_INDX_SHIFT 17 +#define GLPMCFG_L1RESUMEOK BIT(16) +#define GLPMCFG_SLPSTS BIT(15) +#define GLPMCFG_COREL1RES_MASK (0x3 << 13) +#define GLPMCFG_COREL1RES_SHIFT 13 +#define GLPMCFG_HIRD_THRES_MASK (0x1f << 8) +#define GLPMCFG_HIRD_THRES_SHIFT 8 +#define GLPMCFG_HIRD_THRES_EN (0x10 << 8) +#define GLPMCFG_ENBLSLPM BIT(7) +#define GLPMCFG_BREMOTEWAKE BIT(6) +#define GLPMCFG_HIRD_MASK (0xf << 2) +#define GLPMCFG_HIRD_SHIFT 2 +#define GLPMCFG_APPL1RES BIT(1) +#define GLPMCFG_LPMCAP BIT(0) + +#define GPWRDN HSOTG_REG(0x0058) +#define GPWRDN_MULT_VAL_ID_BC_MASK (0x1f << 24) +#define GPWRDN_MULT_VAL_ID_BC_SHIFT 24 +#define GPWRDN_ADP_INT BIT(23) +#define GPWRDN_BSESSVLD BIT(22) +#define GPWRDN_IDSTS BIT(21) +#define GPWRDN_LINESTATE_MASK (0x3 << 19) +#define GPWRDN_LINESTATE_SHIFT 19 +#define GPWRDN_STS_CHGINT_MSK BIT(18) +#define GPWRDN_STS_CHGINT BIT(17) +#define GPWRDN_SRP_DET_MSK BIT(16) +#define GPWRDN_SRP_DET BIT(15) +#define GPWRDN_CONNECT_DET_MSK BIT(14) +#define GPWRDN_CONNECT_DET BIT(13) +#define GPWRDN_DISCONN_DET_MSK BIT(12) +#define GPWRDN_DISCONN_DET BIT(11) +#define GPWRDN_RST_DET_MSK BIT(10) +#define GPWRDN_RST_DET BIT(9) +#define GPWRDN_LNSTSCHG_MSK BIT(8) +#define GPWRDN_LNSTSCHG BIT(7) +#define GPWRDN_DIS_VBUS BIT(6) +#define GPWRDN_PWRDNSWTCH BIT(5) +#define GPWRDN_PWRDNRSTN BIT(4) +#define GPWRDN_PWRDNCLMP BIT(3) +#define GPWRDN_RESTORE BIT(2) +#define GPWRDN_PMUACTV BIT(1) +#define GPWRDN_PMUINTSEL BIT(0) + +#define GDFIFOCFG HSOTG_REG(0x005c) +#define GDFIFOCFG_EPINFOBASE_MASK (0xffff << 16) +#define GDFIFOCFG_EPINFOBASE_SHIFT 16 +#define GDFIFOCFG_GDFIFOCFG_MASK (0xffff << 0) +#define GDFIFOCFG_GDFIFOCFG_SHIFT 0 + +#define ADPCTL HSOTG_REG(0x0060) +#define ADPCTL_AR_MASK (0x3 << 27) +#define ADPCTL_AR_SHIFT 27 +#define ADPCTL_ADP_TMOUT_INT_MSK BIT(26) +#define ADPCTL_ADP_SNS_INT_MSK BIT(25) +#define ADPCTL_ADP_PRB_INT_MSK BIT(24) +#define ADPCTL_ADP_TMOUT_INT BIT(23) +#define ADPCTL_ADP_SNS_INT BIT(22) +#define ADPCTL_ADP_PRB_INT BIT(21) +#define ADPCTL_ADPENA BIT(20) +#define ADPCTL_ADPRES BIT(19) +#define ADPCTL_ENASNS BIT(18) +#define ADPCTL_ENAPRB BIT(17) +#define ADPCTL_RTIM_MASK (0x7ff << 6) +#define ADPCTL_RTIM_SHIFT 6 +#define ADPCTL_PRB_PER_MASK (0x3 << 4) +#define ADPCTL_PRB_PER_SHIFT 4 +#define ADPCTL_PRB_DELTA_MASK (0x3 << 2) +#define ADPCTL_PRB_DELTA_SHIFT 2 +#define ADPCTL_PRB_DSCHRG_MASK (0x3 << 0) +#define ADPCTL_PRB_DSCHRG_SHIFT 0 + +#define GREFCLK HSOTG_REG(0x0064) +#define GREFCLK_REFCLKPER_MASK (0x1ffff << 15) +#define GREFCLK_REFCLKPER_SHIFT 15 +#define GREFCLK_REF_CLK_MODE BIT(14) +#define GREFCLK_SOF_CNT_WKUP_ALERT_MASK (0x3ff) +#define GREFCLK_SOF_CNT_WKUP_ALERT_SHIFT 0 + +#define GINTMSK2 HSOTG_REG(0x0068) +#define GINTMSK2_WKUP_ALERT_INT_MSK BIT(0) + +#define GINTSTS2 HSOTG_REG(0x006c) +#define GINTSTS2_WKUP_ALERT_INT BIT(0) + +#define HPTXFSIZ HSOTG_REG(0x100) +/* Use FIFOSIZE_* constants to access this register */ + +#define DPTXFSIZN(_a) HSOTG_REG(0x104 + (((_a) - 1) * 4)) +/* Use FIFOSIZE_* constants to access this register */ + +/* These apply to the GNPTXFSIZ, HPTXFSIZ and DPTXFSIZN registers */ +#define FIFOSIZE_DEPTH_MASK (0xffff << 16) +#define FIFOSIZE_DEPTH_SHIFT 16 +#define FIFOSIZE_STARTADDR_MASK (0xffff << 0) +#define FIFOSIZE_STARTADDR_SHIFT 0 +#define FIFOSIZE_DEPTH_GET(_x) (((_x) >> 16) & 0xffff) + +/* Device mode registers */ + +#define DCFG HSOTG_REG(0x800) +#define DCFG_DESCDMA_EN BIT(23) +#define DCFG_EPMISCNT_MASK (0x1f << 18) +#define DCFG_EPMISCNT_SHIFT 18 +#define DCFG_EPMISCNT_LIMIT 0x1f +#define DCFG_EPMISCNT(_x) ((_x) << 18) +#define DCFG_IPG_ISOC_SUPPORDED BIT(17) +#define DCFG_PERFRINT_MASK (0x3 << 11) +#define DCFG_PERFRINT_SHIFT 11 +#define DCFG_PERFRINT_LIMIT 0x3 +#define DCFG_PERFRINT(_x) ((_x) << 11) +#define DCFG_DEVADDR_MASK (0x7f << 4) +#define DCFG_DEVADDR_SHIFT 4 +#define DCFG_DEVADDR_LIMIT 0x7f +#define DCFG_DEVADDR(_x) ((_x) << 4) +#define DCFG_NZ_STS_OUT_HSHK BIT(2) +#define DCFG_DEVSPD_MASK (0x3 << 0) +#define DCFG_DEVSPD_SHIFT 0 +#define DCFG_DEVSPD_HS 0 +#define DCFG_DEVSPD_FS 1 +#define DCFG_DEVSPD_LS 2 +#define DCFG_DEVSPD_FS48 3 + +#define DCTL HSOTG_REG(0x804) +#define DCTL_SERVICE_INTERVAL_SUPPORTED BIT(19) +#define DCTL_PWRONPRGDONE BIT(11) +#define DCTL_CGOUTNAK BIT(10) +#define DCTL_SGOUTNAK BIT(9) +#define DCTL_CGNPINNAK BIT(8) +#define DCTL_SGNPINNAK BIT(7) +#define DCTL_TSTCTL_MASK (0x7 << 4) +#define DCTL_TSTCTL_SHIFT 4 +#define DCTL_GOUTNAKSTS BIT(3) +#define DCTL_GNPINNAKSTS BIT(2) +#define DCTL_SFTDISCON BIT(1) +#define DCTL_RMTWKUPSIG BIT(0) + +#define DSTS HSOTG_REG(0x808) +#define DSTS_SOFFN_MASK (0x3fff << 8) +#define DSTS_SOFFN_SHIFT 8 +#define DSTS_SOFFN_LIMIT 0x3fff +#define DSTS_SOFFN(_x) ((_x) << 8) +#define DSTS_ERRATICERR BIT(3) +#define DSTS_ENUMSPD_MASK (0x3 << 1) +#define DSTS_ENUMSPD_SHIFT 1 +#define DSTS_ENUMSPD_HS 0 +#define DSTS_ENUMSPD_FS 1 +#define DSTS_ENUMSPD_LS 2 +#define DSTS_ENUMSPD_FS48 3 +#define DSTS_SUSPSTS BIT(0) + +#define DIEPMSK HSOTG_REG(0x810) +#define DIEPMSK_NAKMSK BIT(13) +#define DIEPMSK_BNAININTRMSK BIT(9) +#define DIEPMSK_TXFIFOUNDRNMSK BIT(8) +#define DIEPMSK_TXFIFOEMPTY BIT(7) +#define DIEPMSK_INEPNAKEFFMSK BIT(6) +#define DIEPMSK_INTKNEPMISMSK BIT(5) +#define DIEPMSK_INTKNTXFEMPMSK BIT(4) +#define DIEPMSK_TIMEOUTMSK BIT(3) +#define DIEPMSK_AHBERRMSK BIT(2) +#define DIEPMSK_EPDISBLDMSK BIT(1) +#define DIEPMSK_XFERCOMPLMSK BIT(0) + +#define DOEPMSK HSOTG_REG(0x814) +#define DOEPMSK_BNAMSK BIT(9) +#define DOEPMSK_BACK2BACKSETUP BIT(6) +#define DOEPMSK_STSPHSERCVDMSK BIT(5) +#define DOEPMSK_OUTTKNEPDISMSK BIT(4) +#define DOEPMSK_SETUPMSK BIT(3) +#define DOEPMSK_AHBERRMSK BIT(2) +#define DOEPMSK_EPDISBLDMSK BIT(1) +#define DOEPMSK_XFERCOMPLMSK BIT(0) + +#define DAINT HSOTG_REG(0x818) +#define DAINTMSK HSOTG_REG(0x81C) +#define DAINT_OUTEP_SHIFT 16 +#define DAINT_OUTEP(_x) (1 << ((_x) + 16)) +#define DAINT_INEP(_x) (1 << (_x)) + +#define DTKNQR1 HSOTG_REG(0x820) +#define DTKNQR2 HSOTG_REG(0x824) +#define DTKNQR3 HSOTG_REG(0x830) +#define DTKNQR4 HSOTG_REG(0x834) +#define DIEPEMPMSK HSOTG_REG(0x834) + +#define DVBUSDIS HSOTG_REG(0x828) +#define DVBUSPULSE HSOTG_REG(0x82C) + +#define DIEPCTL0 HSOTG_REG(0x900) +#define DIEPCTL(_a) HSOTG_REG(0x900 + ((_a) * 0x20)) + +#define DOEPCTL0 HSOTG_REG(0xB00) +#define DOEPCTL(_a) HSOTG_REG(0xB00 + ((_a) * 0x20)) + +/* EP0 specialness: + * bits[29..28] - reserved (no SetD0PID, SetD1PID) + * bits[25..22] - should always be zero, this isn't a periodic endpoint + * bits[10..0] - MPS setting different for EP0 + */ +#define D0EPCTL_MPS_MASK (0x3 << 0) +#define D0EPCTL_MPS_SHIFT 0 +#define D0EPCTL_MPS_64 0 +#define D0EPCTL_MPS_32 1 +#define D0EPCTL_MPS_16 2 +#define D0EPCTL_MPS_8 3 + +#define DXEPCTL_EPENA BIT(31) +#define DXEPCTL_EPDIS BIT(30) +#define DXEPCTL_SETD1PID BIT(29) +#define DXEPCTL_SETODDFR BIT(29) +#define DXEPCTL_SETD0PID BIT(28) +#define DXEPCTL_SETEVENFR BIT(28) +#define DXEPCTL_SNAK BIT(27) +#define DXEPCTL_CNAK BIT(26) +#define DXEPCTL_TXFNUM_MASK (0xf << 22) +#define DXEPCTL_TXFNUM_SHIFT 22 +#define DXEPCTL_TXFNUM_LIMIT 0xf +#define DXEPCTL_TXFNUM(_x) ((_x) << 22) +#define DXEPCTL_STALL BIT(21) +#define DXEPCTL_SNP BIT(20) +#define DXEPCTL_EPTYPE_MASK (0x3 << 18) +#define DXEPCTL_EPTYPE_CONTROL (0x0 << 18) +#define DXEPCTL_EPTYPE_ISO (0x1 << 18) +#define DXEPCTL_EPTYPE_BULK (0x2 << 18) +#define DXEPCTL_EPTYPE_INTERRUPT (0x3 << 18) + +#define DXEPCTL_NAKSTS BIT(17) +#define DXEPCTL_DPID BIT(16) +#define DXEPCTL_EOFRNUM BIT(16) +#define DXEPCTL_USBACTEP BIT(15) +#define DXEPCTL_NEXTEP_MASK (0xf << 11) +#define DXEPCTL_NEXTEP_SHIFT 11 +#define DXEPCTL_NEXTEP_LIMIT 0xf +#define DXEPCTL_NEXTEP(_x) ((_x) << 11) +#define DXEPCTL_MPS_MASK (0x7ff << 0) +#define DXEPCTL_MPS_SHIFT 0 +#define DXEPCTL_MPS_LIMIT 0x7ff +#define DXEPCTL_MPS(_x) ((_x) << 0) + +#define DIEPINT(_a) HSOTG_REG(0x908 + ((_a) * 0x20)) +#define DOEPINT(_a) HSOTG_REG(0xB08 + ((_a) * 0x20)) +#define DXEPINT_SETUP_RCVD BIT(15) +#define DXEPINT_NYETINTRPT BIT(14) +#define DXEPINT_NAKINTRPT BIT(13) +#define DXEPINT_BBLEERRINTRPT BIT(12) +#define DXEPINT_PKTDRPSTS BIT(11) +#define DXEPINT_BNAINTR BIT(9) +#define DXEPINT_TXFIFOUNDRN BIT(8) +#define DXEPINT_OUTPKTERR BIT(8) +#define DXEPINT_TXFEMP BIT(7) +#define DXEPINT_INEPNAKEFF BIT(6) +#define DXEPINT_BACK2BACKSETUP BIT(6) +#define DXEPINT_INTKNEPMIS BIT(5) +#define DXEPINT_STSPHSERCVD BIT(5) +#define DXEPINT_INTKNTXFEMP BIT(4) +#define DXEPINT_OUTTKNEPDIS BIT(4) +#define DXEPINT_TIMEOUT BIT(3) +#define DXEPINT_SETUP BIT(3) +#define DXEPINT_AHBERR BIT(2) +#define DXEPINT_EPDISBLD BIT(1) +#define DXEPINT_XFERCOMPL BIT(0) + +#define DIEPTSIZ0 HSOTG_REG(0x910) +#define DIEPTSIZ0_PKTCNT_MASK (0x3 << 19) +#define DIEPTSIZ0_PKTCNT_SHIFT 19 +#define DIEPTSIZ0_PKTCNT_LIMIT 0x3 +#define DIEPTSIZ0_PKTCNT(_x) ((_x) << 19) +#define DIEPTSIZ0_XFERSIZE_MASK (0x7f << 0) +#define DIEPTSIZ0_XFERSIZE_SHIFT 0 +#define DIEPTSIZ0_XFERSIZE_LIMIT 0x7f +#define DIEPTSIZ0_XFERSIZE(_x) ((_x) << 0) + +#define DOEPTSIZ0 HSOTG_REG(0xB10) +#define DOEPTSIZ0_SUPCNT_MASK (0x3 << 29) +#define DOEPTSIZ0_SUPCNT_SHIFT 29 +#define DOEPTSIZ0_SUPCNT_LIMIT 0x3 +#define DOEPTSIZ0_SUPCNT(_x) ((_x) << 29) +#define DOEPTSIZ0_PKTCNT BIT(19) +#define DOEPTSIZ0_XFERSIZE_MASK (0x7f << 0) +#define DOEPTSIZ0_XFERSIZE_SHIFT 0 + +#define DIEPTSIZ(_a) HSOTG_REG(0x910 + ((_a) * 0x20)) +#define DOEPTSIZ(_a) HSOTG_REG(0xB10 + ((_a) * 0x20)) +#define DXEPTSIZ_MC_MASK (0x3 << 29) +#define DXEPTSIZ_MC_SHIFT 29 +#define DXEPTSIZ_MC_LIMIT 0x3 +#define DXEPTSIZ_MC(_x) ((_x) << 29) +#define DXEPTSIZ_PKTCNT_MASK (0x3ff << 19) +#define DXEPTSIZ_PKTCNT_SHIFT 19 +#define DXEPTSIZ_PKTCNT_LIMIT 0x3ff +#define DXEPTSIZ_PKTCNT_GET(_v) (((_v) >> 19) & 0x3ff) +#define DXEPTSIZ_PKTCNT(_x) ((_x) << 19) +#define DXEPTSIZ_XFERSIZE_MASK (0x7ffff << 0) +#define DXEPTSIZ_XFERSIZE_SHIFT 0 +#define DXEPTSIZ_XFERSIZE_LIMIT 0x7ffff +#define DXEPTSIZ_XFERSIZE_GET(_v) (((_v) >> 0) & 0x7ffff) +#define DXEPTSIZ_XFERSIZE(_x) ((_x) << 0) + +#define DIEPDMA(_a) HSOTG_REG(0x914 + ((_a) * 0x20)) +#define DOEPDMA(_a) HSOTG_REG(0xB14 + ((_a) * 0x20)) + +#define DTXFSTS(_a) HSOTG_REG(0x918 + ((_a) * 0x20)) + +#define PCGCTL HSOTG_REG(0x0e00) +#define PCGCTL_IF_DEV_MODE BIT(31) +#define PCGCTL_P2HD_PRT_SPD_MASK (0x3 << 29) +#define PCGCTL_P2HD_PRT_SPD_SHIFT 29 +#define PCGCTL_P2HD_DEV_ENUM_SPD_MASK (0x3 << 27) +#define PCGCTL_P2HD_DEV_ENUM_SPD_SHIFT 27 +#define PCGCTL_MAC_DEV_ADDR_MASK (0x7f << 20) +#define PCGCTL_MAC_DEV_ADDR_SHIFT 20 +#define PCGCTL_MAX_TERMSEL BIT(19) +#define PCGCTL_MAX_XCVRSELECT_MASK (0x3 << 17) +#define PCGCTL_MAX_XCVRSELECT_SHIFT 17 +#define PCGCTL_PORT_POWER BIT(16) +#define PCGCTL_PRT_CLK_SEL_MASK (0x3 << 14) +#define PCGCTL_PRT_CLK_SEL_SHIFT 14 +#define PCGCTL_ESS_REG_RESTORED BIT(13) +#define PCGCTL_EXTND_HIBER_SWITCH BIT(12) +#define PCGCTL_EXTND_HIBER_PWRCLMP BIT(11) +#define PCGCTL_ENBL_EXTND_HIBER BIT(10) +#define PCGCTL_RESTOREMODE BIT(9) +#define PCGCTL_RESETAFTSUSP BIT(8) +#define PCGCTL_DEEP_SLEEP BIT(7) +#define PCGCTL_PHY_IN_SLEEP BIT(6) +#define PCGCTL_ENBL_SLEEP_GATING BIT(5) +#define PCGCTL_RSTPDWNMODULE BIT(3) +#define PCGCTL_PWRCLMP BIT(2) +#define PCGCTL_GATEHCLK BIT(1) +#define PCGCTL_STOPPCLK BIT(0) + +#define PCGCCTL1 HSOTG_REG(0xe04) +#define PCGCCTL1_TIMER (0x3 << 1) +#define PCGCCTL1_GATEEN BIT(0) + +#define EPFIFO(_a) HSOTG_REG(0x1000 + ((_a) * 0x1000)) + +/* Host Mode Registers */ + +#define HCFG HSOTG_REG(0x0400) +#define HCFG_MODECHTIMEN BIT(31) +#define HCFG_PERSCHEDENA BIT(26) +#define HCFG_FRLISTEN_MASK (0x3 << 24) +#define HCFG_FRLISTEN_SHIFT 24 +#define HCFG_FRLISTEN_8 (0 << 24) +#define FRLISTEN_8_SIZE 8 +#define HCFG_FRLISTEN_16 BIT(24) +#define FRLISTEN_16_SIZE 16 +#define HCFG_FRLISTEN_32 (2 << 24) +#define FRLISTEN_32_SIZE 32 +#define HCFG_FRLISTEN_64 (3 << 24) +#define FRLISTEN_64_SIZE 64 +#define HCFG_DESCDMA BIT(23) +#define HCFG_RESVALID_MASK (0xff << 8) +#define HCFG_RESVALID_SHIFT 8 +#define HCFG_ENA32KHZ BIT(7) +#define HCFG_FSLSSUPP BIT(2) +#define HCFG_FSLSPCLKSEL_MASK (0x3 << 0) +#define HCFG_FSLSPCLKSEL_SHIFT 0 +#define HCFG_FSLSPCLKSEL_30_60_MHZ 0 +#define HCFG_FSLSPCLKSEL_48_MHZ 1 +#define HCFG_FSLSPCLKSEL_6_MHZ 2 + +#define HFIR HSOTG_REG(0x0404) +#define HFIR_FRINT_MASK (0xffff << 0) +#define HFIR_FRINT_SHIFT 0 +#define HFIR_RLDCTRL BIT(16) + +#define HFNUM HSOTG_REG(0x0408) +#define HFNUM_FRREM_MASK (0xffff << 16) +#define HFNUM_FRREM_SHIFT 16 +#define HFNUM_FRNUM_MASK (0xffff << 0) +#define HFNUM_FRNUM_SHIFT 0 +#define HFNUM_MAX_FRNUM 0x3fff + +#define HPTXSTS HSOTG_REG(0x0410) +#define TXSTS_QTOP_ODD BIT(31) +#define TXSTS_QTOP_CHNEP_MASK (0xf << 27) +#define TXSTS_QTOP_CHNEP_SHIFT 27 +#define TXSTS_QTOP_TOKEN_MASK (0x3 << 25) +#define TXSTS_QTOP_TOKEN_SHIFT 25 +#define TXSTS_QTOP_TERMINATE BIT(24) +#define TXSTS_QSPCAVAIL_MASK (0xff << 16) +#define TXSTS_QSPCAVAIL_SHIFT 16 +#define TXSTS_FSPCAVAIL_MASK (0xffff << 0) +#define TXSTS_FSPCAVAIL_SHIFT 0 + +#define HAINT HSOTG_REG(0x0414) +#define HAINTMSK HSOTG_REG(0x0418) +#define HFLBADDR HSOTG_REG(0x041c) + +#define HPRT0 HSOTG_REG(0x0440) +#define HPRT0_SPD_MASK (0x3 << 17) +#define HPRT0_SPD_SHIFT 17 +#define HPRT0_SPD_HIGH_SPEED 0 +#define HPRT0_SPD_FULL_SPEED 1 +#define HPRT0_SPD_LOW_SPEED 2 +#define HPRT0_TSTCTL_MASK (0xf << 13) +#define HPRT0_TSTCTL_SHIFT 13 +#define HPRT0_PWR BIT(12) +#define HPRT0_LNSTS_MASK (0x3 << 10) +#define HPRT0_LNSTS_SHIFT 10 +#define HPRT0_RST BIT(8) +#define HPRT0_SUSP BIT(7) +#define HPRT0_RES BIT(6) +#define HPRT0_OVRCURRCHG BIT(5) +#define HPRT0_OVRCURRACT BIT(4) +#define HPRT0_ENACHG BIT(3) +#define HPRT0_ENA BIT(2) +#define HPRT0_CONNDET BIT(1) +#define HPRT0_CONNSTS BIT(0) + +#define HCCHAR(_ch) HSOTG_REG(0x0500 + 0x20 * (_ch)) +#define HCCHAR_CHENA BIT(31) +#define HCCHAR_CHDIS BIT(30) +#define HCCHAR_ODDFRM BIT(29) +#define HCCHAR_DEVADDR_MASK (0x7f << 22) +#define HCCHAR_DEVADDR_SHIFT 22 +#define HCCHAR_MULTICNT_MASK (0x3 << 20) +#define HCCHAR_MULTICNT_SHIFT 20 +#define HCCHAR_EPTYPE_MASK (0x3 << 18) +#define HCCHAR_EPTYPE_SHIFT 18 +#define HCCHAR_LSPDDEV BIT(17) +#define HCCHAR_EPDIR BIT(15) +#define HCCHAR_EPNUM_MASK (0xf << 11) +#define HCCHAR_EPNUM_SHIFT 11 +#define HCCHAR_MPS_MASK (0x7ff << 0) +#define HCCHAR_MPS_SHIFT 0 + +#define HCSPLT(_ch) HSOTG_REG(0x0504 + 0x20 * (_ch)) +#define HCSPLT_SPLTENA BIT(31) +#define HCSPLT_COMPSPLT BIT(16) +#define HCSPLT_XACTPOS_MASK (0x3 << 14) +#define HCSPLT_XACTPOS_SHIFT 14 +#define HCSPLT_XACTPOS_MID 0 +#define HCSPLT_XACTPOS_END 1 +#define HCSPLT_XACTPOS_BEGIN 2 +#define HCSPLT_XACTPOS_ALL 3 +#define HCSPLT_HUBADDR_MASK (0x7f << 7) +#define HCSPLT_HUBADDR_SHIFT 7 +#define HCSPLT_PRTADDR_MASK (0x7f << 0) +#define HCSPLT_PRTADDR_SHIFT 0 + +#define HCINT(_ch) HSOTG_REG(0x0508 + 0x20 * (_ch)) +#define HCINTMSK(_ch) HSOTG_REG(0x050c + 0x20 * (_ch)) +#define HCINTMSK_RESERVED14_31 (0x3ffff << 14) +#define HCINTMSK_FRM_LIST_ROLL BIT(13) +#define HCINTMSK_XCS_XACT BIT(12) +#define HCINTMSK_BNA BIT(11) +#define HCINTMSK_DATATGLERR BIT(10) +#define HCINTMSK_FRMOVRUN BIT(9) +#define HCINTMSK_BBLERR BIT(8) +#define HCINTMSK_XACTERR BIT(7) +#define HCINTMSK_NYET BIT(6) +#define HCINTMSK_ACK BIT(5) +#define HCINTMSK_NAK BIT(4) +#define HCINTMSK_STALL BIT(3) +#define HCINTMSK_AHBERR BIT(2) +#define HCINTMSK_CHHLTD BIT(1) +#define HCINTMSK_XFERCOMPL BIT(0) + +#define HCTSIZ(_ch) HSOTG_REG(0x0510 + 0x20 * (_ch)) +#define TSIZ_DOPNG BIT(31) +#define TSIZ_SC_MC_PID_MASK (0x3 << 29) +#define TSIZ_SC_MC_PID_SHIFT 29 +#define TSIZ_SC_MC_PID_DATA0 0 +#define TSIZ_SC_MC_PID_DATA2 1 +#define TSIZ_SC_MC_PID_DATA1 2 +#define TSIZ_SC_MC_PID_MDATA 3 +#define TSIZ_SC_MC_PID_SETUP 3 +#define TSIZ_PKTCNT_MASK (0x3ff << 19) +#define TSIZ_PKTCNT_SHIFT 19 +#define TSIZ_NTD_MASK (0xff << 8) +#define TSIZ_NTD_SHIFT 8 +#define TSIZ_SCHINFO_MASK (0xff << 0) +#define TSIZ_SCHINFO_SHIFT 0 +#define TSIZ_XFERSIZE_MASK (0x7ffff << 0) +#define TSIZ_XFERSIZE_SHIFT 0 + +#define HCDMA(_ch) HSOTG_REG(0x0514 + 0x20 * (_ch)) + +#define HCDMAB(_ch) HSOTG_REG(0x051c + 0x20 * (_ch)) + +#define HCFIFO(_ch) HSOTG_REG(0x1000 + 0x1000 * (_ch)) + +/** + * struct dwc2_dma_desc - DMA descriptor structure, + * used for both host and gadget modes + * + * @status: DMA descriptor status quadlet + * @buf: DMA descriptor data buffer pointer + * + * DMA Descriptor structure contains two quadlets: + * Status quadlet and Data buffer pointer. + */ +struct dwc2_dma_desc { + uint32_t status; + uint32_t buf; +} __packed; + +/* Host Mode DMA descriptor status quadlet */ + +#define HOST_DMA_A BIT(31) +#define HOST_DMA_STS_MASK (0x3 << 28) +#define HOST_DMA_STS_SHIFT 28 +#define HOST_DMA_STS_PKTERR BIT(28) +#define HOST_DMA_EOL BIT(26) +#define HOST_DMA_IOC BIT(25) +#define HOST_DMA_SUP BIT(24) +#define HOST_DMA_ALT_QTD BIT(23) +#define HOST_DMA_QTD_OFFSET_MASK (0x3f << 17) +#define HOST_DMA_QTD_OFFSET_SHIFT 17 +#define HOST_DMA_ISOC_NBYTES_MASK (0xfff << 0) +#define HOST_DMA_ISOC_NBYTES_SHIFT 0 +#define HOST_DMA_NBYTES_MASK (0x1ffff << 0) +#define HOST_DMA_NBYTES_SHIFT 0 +#define HOST_DMA_NBYTES_LIMIT 131071 + +/* Device Mode DMA descriptor status quadlet */ + +#define DEV_DMA_BUFF_STS_MASK (0x3 << 30) +#define DEV_DMA_BUFF_STS_SHIFT 30 +#define DEV_DMA_BUFF_STS_HREADY 0 +#define DEV_DMA_BUFF_STS_DMABUSY 1 +#define DEV_DMA_BUFF_STS_DMADONE 2 +#define DEV_DMA_BUFF_STS_HBUSY 3 +#define DEV_DMA_STS_MASK (0x3 << 28) +#define DEV_DMA_STS_SHIFT 28 +#define DEV_DMA_STS_SUCC 0 +#define DEV_DMA_STS_BUFF_FLUSH 1 +#define DEV_DMA_STS_BUFF_ERR 3 +#define DEV_DMA_L BIT(27) +#define DEV_DMA_SHORT BIT(26) +#define DEV_DMA_IOC BIT(25) +#define DEV_DMA_SR BIT(24) +#define DEV_DMA_MTRF BIT(23) +#define DEV_DMA_ISOC_PID_MASK (0x3 << 23) +#define DEV_DMA_ISOC_PID_SHIFT 23 +#define DEV_DMA_ISOC_PID_DATA0 0 +#define DEV_DMA_ISOC_PID_DATA2 1 +#define DEV_DMA_ISOC_PID_DATA1 2 +#define DEV_DMA_ISOC_PID_MDATA 3 +#define DEV_DMA_ISOC_FRNUM_MASK (0x7ff << 12) +#define DEV_DMA_ISOC_FRNUM_SHIFT 12 +#define DEV_DMA_ISOC_TX_NBYTES_MASK (0xfff << 0) +#define DEV_DMA_ISOC_TX_NBYTES_LIMIT 0xfff +#define DEV_DMA_ISOC_RX_NBYTES_MASK (0x7ff << 0) +#define DEV_DMA_ISOC_RX_NBYTES_LIMIT 0x7ff +#define DEV_DMA_ISOC_NBYTES_SHIFT 0 +#define DEV_DMA_NBYTES_MASK (0xffff << 0) +#define DEV_DMA_NBYTES_SHIFT 0 +#define DEV_DMA_NBYTES_LIMIT 0xffff + +#define MAX_DMA_DESC_NUM_GENERIC 64 +#define MAX_DMA_DESC_NUM_HS_ISOC 256 + +#endif /* __DWC2_HW_H__ */ -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add the dwc-hsotg (dwc2) USB host controller state definitions. Mostly based on hw/usb/hcd-ehci.h. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-4-pauldzim@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-dwc2.h | 190 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 190 insertions(+) create mode 100644 hw/usb/hcd-dwc2.h diff --git a/hw/usb/hcd-dwc2.h b/hw/usb/hcd-dwc2.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/hcd-dwc2.h @@ -XXX,XX +XXX,XX @@ +/* + * dwc-hsotg (dwc2) USB host controller state definitions + * + * Based on hw/usb/hcd-ehci.h + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef HW_USB_DWC2_H +#define HW_USB_DWC2_H + +#include "qemu/timer.h" +#include "hw/irq.h" +#include "hw/sysbus.h" +#include "hw/usb.h" +#include "sysemu/dma.h" + +#define DWC2_MMIO_SIZE 0x11000 + +#define DWC2_NB_CHAN 8 /* Number of host channels */ +#define DWC2_MAX_XFER_SIZE 65536 /* Max transfer size expected in HCTSIZ */ + +typedef struct DWC2Packet DWC2Packet; +typedef struct DWC2State DWC2State; +typedef struct DWC2Class DWC2Class; + +enum async_state { + DWC2_ASYNC_NONE = 0, + DWC2_ASYNC_INITIALIZED, + DWC2_ASYNC_INFLIGHT, + DWC2_ASYNC_FINISHED, +}; + +struct DWC2Packet { + USBPacket packet; + uint32_t devadr; + uint32_t epnum; + uint32_t epdir; + uint32_t mps; + uint32_t pid; + uint32_t index; + uint32_t pcnt; + uint32_t len; + int32_t async; + bool small; + bool needs_service; +}; + +struct DWC2State { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + USBBus bus; + qemu_irq irq; + MemoryRegion *dma_mr; + AddressSpace dma_as; + MemoryRegion container; + MemoryRegion hsotg; + MemoryRegion fifos; + + union { +#define DWC2_GLBREG_SIZE 0x70 + uint32_t glbreg[DWC2_GLBREG_SIZE / sizeof(uint32_t)]; + struct { + uint32_t gotgctl; /* 00 */ + uint32_t gotgint; /* 04 */ + uint32_t gahbcfg; /* 08 */ + uint32_t gusbcfg; /* 0c */ + uint32_t grstctl; /* 10 */ + uint32_t gintsts; /* 14 */ + uint32_t gintmsk; /* 18 */ + uint32_t grxstsr; /* 1c */ + uint32_t grxstsp; /* 20 */ + uint32_t grxfsiz; /* 24 */ + uint32_t gnptxfsiz; /* 28 */ + uint32_t gnptxsts; /* 2c */ + uint32_t gi2cctl; /* 30 */ + uint32_t gpvndctl; /* 34 */ + uint32_t ggpio; /* 38 */ + uint32_t guid; /* 3c */ + uint32_t gsnpsid; /* 40 */ + uint32_t ghwcfg1; /* 44 */ + uint32_t ghwcfg2; /* 48 */ + uint32_t ghwcfg3; /* 4c */ + uint32_t ghwcfg4; /* 50 */ + uint32_t glpmcfg; /* 54 */ + uint32_t gpwrdn; /* 58 */ + uint32_t gdfifocfg; /* 5c */ + uint32_t gadpctl; /* 60 */ + uint32_t grefclk; /* 64 */ + uint32_t gintmsk2; /* 68 */ + uint32_t gintsts2; /* 6c */ + }; + }; + + union { +#define DWC2_FSZREG_SIZE 0x04 + uint32_t fszreg[DWC2_FSZREG_SIZE / sizeof(uint32_t)]; + struct { + uint32_t hptxfsiz; /* 100 */ + }; + }; + + union { +#define DWC2_HREG0_SIZE 0x44 + uint32_t hreg0[DWC2_HREG0_SIZE / sizeof(uint32_t)]; + struct { + uint32_t hcfg; /* 400 */ + uint32_t hfir; /* 404 */ + uint32_t hfnum; /* 408 */ + uint32_t rsvd0; /* 40c */ + uint32_t hptxsts; /* 410 */ + uint32_t haint; /* 414 */ + uint32_t haintmsk; /* 418 */ + uint32_t hflbaddr; /* 41c */ + uint32_t rsvd1[8]; /* 420-43c */ + uint32_t hprt0; /* 440 */ + }; + }; + +#define DWC2_HREG1_SIZE (0x20 * DWC2_NB_CHAN) + uint32_t hreg1[DWC2_HREG1_SIZE / sizeof(uint32_t)]; + +#define hcchar(_ch) hreg1[((_ch) << 3) + 0] /* 500, 520, ... */ +#define hcsplt(_ch) hreg1[((_ch) << 3) + 1] /* 504, 524, ... */ +#define hcint(_ch) hreg1[((_ch) << 3) + 2] /* 508, 528, ... */ +#define hcintmsk(_ch) hreg1[((_ch) << 3) + 3] /* 50c, 52c, ... */ +#define hctsiz(_ch) hreg1[((_ch) << 3) + 4] /* 510, 530, ... */ +#define hcdma(_ch) hreg1[((_ch) << 3) + 5] /* 514, 534, ... */ +#define hcdmab(_ch) hreg1[((_ch) << 3) + 7] /* 51c, 53c, ... */ + + union { +#define DWC2_PCGREG_SIZE 0x08 + uint32_t pcgreg[DWC2_PCGREG_SIZE / sizeof(uint32_t)]; + struct { + uint32_t pcgctl; /* e00 */ + uint32_t pcgcctl1; /* e04 */ + }; + }; + + /* TODO - implement FIFO registers for slave mode */ +#define DWC2_HFIFO_SIZE (0x1000 * DWC2_NB_CHAN) + + /* + * Internal state + */ + QEMUTimer *eof_timer; + QEMUTimer *frame_timer; + QEMUBH *async_bh; + int64_t sof_time; + int64_t usb_frame_time; + int64_t usb_bit_time; + uint32_t usb_version; + uint16_t frame_number; + uint16_t fi; + uint16_t next_chan; + bool working; + USBPort uport; + DWC2Packet packet[DWC2_NB_CHAN]; /* one packet per chan */ + uint8_t usb_buf[DWC2_NB_CHAN][DWC2_MAX_XFER_SIZE]; /* one buffer per chan */ +}; + +struct DWC2Class { + /*< private >*/ + SysBusDeviceClass parent_class; + ResettablePhases parent_phases; + + /*< public >*/ +}; + +#define TYPE_DWC2_USB "dwc2-usb" +#define DWC2_USB(obj) \ + OBJECT_CHECK(DWC2State, (obj), TYPE_DWC2_USB) +#define DWC2_CLASS(klass) \ + OBJECT_CLASS_CHECK(DWC2Class, (klass), TYPE_DWC2_USB) +#define DWC2_GET_CLASS(obj) \ + OBJECT_GET_CLASS(DWC2Class, (obj), TYPE_DWC2_USB) + +#endif -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add the dwc-hsotg (dwc2) USB host controller emulation code. Based on hw/usb/hcd-ehci.c and hw/usb/hcd-ohci.c. Note that to use this with the dwc-otg driver in the Raspbian kernel, you must pass the option "dwc_otg.fiq_fsm_enable=0" on the kernel command line. Emulation of slave mode and of descriptor-DMA mode has not been implemented yet. These modes are seldom used. I have used some on-line sources of information while developing this emulation, including: http://www.capital-micro.com/PDF/CME-M7_Family_User_Guide_EN.pdf which has a pretty complete description of the controller starting on page 370. https://sourceforge.net/p/wive-ng/wive-ng-mt/ci/master/tree/docs/DataSheets/RT3050_5x_V2.0_081408_0902.pdf which has a description of the controller registers starting on page 130. Thanks to Felippe Mathieu-Daude for providing a cleaner method of implementing the memory regions for the controller registers. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-5-pauldzim@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-dwc2.c | 1417 ++++++++++++++++++++++++++++++++++++++++++ hw/usb/Kconfig | 5 + hw/usb/Makefile.objs | 1 + hw/usb/trace-events | 50 ++ 4 files changed, 1473 insertions(+) create mode 100644 hw/usb/hcd-dwc2.c diff --git a/hw/usb/hcd-dwc2.c b/hw/usb/hcd-dwc2.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/hcd-dwc2.c @@ -XXX,XX +XXX,XX @@ +/* + * dwc-hsotg (dwc2) USB host controller emulation + * + * Based on hw/usb/hcd-ehci.c and hw/usb/hcd-ohci.c + * + * Note that to use this emulation with the dwc-otg driver in the + * Raspbian kernel, you must pass the option "dwc_otg.fiq_fsm_enable=0" + * on the kernel command line. + * + * Some useful documentation used to develop this emulation can be + * found online (as of April 2020) at: + * + * http://www.capital-micro.com/PDF/CME-M7_Family_User_Guide_EN.pdf + * which has a pretty complete description of the controller starting + * on page 370. + * + * https://sourceforge.net/p/wive-ng/wive-ng-mt/ci/master/tree/docs/DataSheets/RT3050_5x_V2.0_081408_0902.pdf + * which has a description of the controller registers starting on + * page 130. + * + * Copyright (c) 2020 Paul Zimmerman <pauldzim@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "hw/usb/dwc2-regs.h" +#include "hw/usb/hcd-dwc2.h" +#include "migration/vmstate.h" +#include "trace.h" +#include "qemu/log.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "hw/qdev-properties.h" + +#define USB_HZ_FS 12000000 +#define USB_HZ_HS 96000000 +#define USB_FRMINTVL 12000 + +/* nifty macros from Arnon's EHCI version */ +#define get_field(data, field) \ + (((data) & field##_MASK) >> field##_SHIFT) + +#define set_field(data, newval, field) do { \ + uint32_t val = *(data); \ + val &= ~field##_MASK; \ + val |= ((newval) << field##_SHIFT) & field##_MASK; \ + *(data) = val; \ +} while (0) + +#define get_bit(data, bitmask) \ + (!!((data) & (bitmask))) + +/* update irq line */ +static inline void dwc2_update_irq(DWC2State *s) +{ + static int oldlevel; + int level = 0; + + if ((s->gintsts & s->gintmsk) && (s->gahbcfg & GAHBCFG_GLBL_INTR_EN)) { + level = 1; + } + if (level != oldlevel) { + oldlevel = level; + trace_usb_dwc2_update_irq(level); + qemu_set_irq(s->irq, level); + } +} + +/* flag interrupt condition */ +static inline void dwc2_raise_global_irq(DWC2State *s, uint32_t intr) +{ + if (!(s->gintsts & intr)) { + s->gintsts |= intr; + trace_usb_dwc2_raise_global_irq(intr); + dwc2_update_irq(s); + } +} + +static inline void dwc2_lower_global_irq(DWC2State *s, uint32_t intr) +{ + if (s->gintsts & intr) { + s->gintsts &= ~intr; + trace_usb_dwc2_lower_global_irq(intr); + dwc2_update_irq(s); + } +} + +static inline void dwc2_raise_host_irq(DWC2State *s, uint32_t host_intr) +{ + if (!(s->haint & host_intr)) { + s->haint |= host_intr; + s->haint &= 0xffff; + trace_usb_dwc2_raise_host_irq(host_intr); + if (s->haint & s->haintmsk) { + dwc2_raise_global_irq(s, GINTSTS_HCHINT); + } + } +} + +static inline void dwc2_lower_host_irq(DWC2State *s, uint32_t host_intr) +{ + if (s->haint & host_intr) { + s->haint &= ~host_intr; + trace_usb_dwc2_lower_host_irq(host_intr); + if (!(s->haint & s->haintmsk)) { + dwc2_lower_global_irq(s, GINTSTS_HCHINT); + } + } +} + +static inline void dwc2_update_hc_irq(DWC2State *s, int index) +{ + uint32_t host_intr = 1 << (index >> 3); + + if (s->hreg1[index + 2] & s->hreg1[index + 3]) { + dwc2_raise_host_irq(s, host_intr); + } else { + dwc2_lower_host_irq(s, host_intr); + } +} + +/* set a timer for EOF */ +static void dwc2_eof_timer(DWC2State *s) +{ + timer_mod(s->eof_timer, s->sof_time + s->usb_frame_time); +} + +/* Set a timer for EOF and generate SOF event */ +static void dwc2_sof(DWC2State *s) +{ + s->sof_time += s->usb_frame_time; + trace_usb_dwc2_sof(s->sof_time); + dwc2_eof_timer(s); + dwc2_raise_global_irq(s, GINTSTS_SOF); +} + +/* Do frame processing on frame boundary */ +static void dwc2_frame_boundary(void *opaque) +{ + DWC2State *s = opaque; + int64_t now; + uint16_t frcnt; + + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + /* Frame boundary, so do EOF stuff here */ + + /* Increment frame number */ + frcnt = (uint16_t)((now - s->sof_time) / s->fi); + s->frame_number = (s->frame_number + frcnt) & 0xffff; + s->hfnum = s->frame_number & HFNUM_MAX_FRNUM; + + /* Do SOF stuff here */ + dwc2_sof(s); +} + +/* Start sending SOF tokens on the USB bus */ +static void dwc2_bus_start(DWC2State *s) +{ + trace_usb_dwc2_bus_start(); + s->sof_time = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + dwc2_eof_timer(s); +} + +/* Stop sending SOF tokens on the USB bus */ +static void dwc2_bus_stop(DWC2State *s) +{ + trace_usb_dwc2_bus_stop(); + timer_del(s->eof_timer); +} + +static USBDevice *dwc2_find_device(DWC2State *s, uint8_t addr) +{ + USBDevice *dev; + + trace_usb_dwc2_find_device(addr); + + if (!(s->hprt0 & HPRT0_ENA)) { + trace_usb_dwc2_port_disabled(0); + } else { + dev = usb_find_device(&s->uport, addr); + if (dev != NULL) { + trace_usb_dwc2_device_found(0); + return dev; + } + } + + trace_usb_dwc2_device_not_found(); + return NULL; +} + +static const char *pstatus[] = { + "USB_RET_SUCCESS", "USB_RET_NODEV", "USB_RET_NAK", "USB_RET_STALL", + "USB_RET_BABBLE", "USB_RET_IOERROR", "USB_RET_ASYNC", + "USB_RET_ADD_TO_QUEUE", "USB_RET_REMOVE_FROM_QUEUE" +}; + +static uint32_t pintr[] = { + HCINTMSK_XFERCOMPL, HCINTMSK_XACTERR, HCINTMSK_NAK, HCINTMSK_STALL, + HCINTMSK_BBLERR, HCINTMSK_XACTERR, HCINTMSK_XACTERR, HCINTMSK_XACTERR, + HCINTMSK_XACTERR +}; + +static const char *types[] = { + "Ctrl", "Isoc", "Bulk", "Intr" +}; + +static const char *dirs[] = { + "Out", "In" +}; + +static void dwc2_handle_packet(DWC2State *s, uint32_t devadr, USBDevice *dev, + USBEndpoint *ep, uint32_t index, bool send) +{ + DWC2Packet *p; + uint32_t hcchar = s->hreg1[index]; + uint32_t hctsiz = s->hreg1[index + 4]; + uint32_t hcdma = s->hreg1[index + 5]; + uint32_t chan, epnum, epdir, eptype, mps, pid, pcnt, len, tlen, intr = 0; + uint32_t tpcnt, stsidx, actual = 0; + bool do_intr = false, done = false; + + epnum = get_field(hcchar, HCCHAR_EPNUM); + epdir = get_bit(hcchar, HCCHAR_EPDIR); + eptype = get_field(hcchar, HCCHAR_EPTYPE); + mps = get_field(hcchar, HCCHAR_MPS); + pid = get_field(hctsiz, TSIZ_SC_MC_PID); + pcnt = get_field(hctsiz, TSIZ_PKTCNT); + len = get_field(hctsiz, TSIZ_XFERSIZE); + assert(len <= DWC2_MAX_XFER_SIZE); + chan = index >> 3; + p = &s->packet[chan]; + + trace_usb_dwc2_handle_packet(chan, dev, &p->packet, epnum, types[eptype], + dirs[epdir], mps, len, pcnt); + + if (eptype == USB_ENDPOINT_XFER_CONTROL && pid == TSIZ_SC_MC_PID_SETUP) { + pid = USB_TOKEN_SETUP; + } else { + pid = epdir ? USB_TOKEN_IN : USB_TOKEN_OUT; + } + + if (send) { + tlen = len; + if (p->small) { + if (tlen > mps) { + tlen = mps; + } + } + + if (pid != USB_TOKEN_IN) { + trace_usb_dwc2_memory_read(hcdma, tlen); + if (dma_memory_read(&s->dma_as, hcdma, + s->usb_buf[chan], tlen) != MEMTX_OK) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: dma_memory_read failed\n", + __func__); + } + } + + usb_packet_init(&p->packet); + usb_packet_setup(&p->packet, pid, ep, 0, hcdma, + pid != USB_TOKEN_IN, true); + usb_packet_addbuf(&p->packet, s->usb_buf[chan], tlen); + p->async = DWC2_ASYNC_NONE; + usb_handle_packet(dev, &p->packet); + } else { + tlen = p->len; + } + + stsidx = -p->packet.status; + assert(stsidx < sizeof(pstatus) / sizeof(*pstatus)); + actual = p->packet.actual_length; + trace_usb_dwc2_packet_status(pstatus[stsidx], actual); + +babble: + if (p->packet.status != USB_RET_SUCCESS && + p->packet.status != USB_RET_NAK && + p->packet.status != USB_RET_STALL && + p->packet.status != USB_RET_ASYNC) { + trace_usb_dwc2_packet_error(pstatus[stsidx]); + } + + if (p->packet.status == USB_RET_ASYNC) { + trace_usb_dwc2_async_packet(&p->packet, chan, dev, epnum, + dirs[epdir], tlen); + usb_device_flush_ep_queue(dev, ep); + assert(p->async != DWC2_ASYNC_INFLIGHT); + p->devadr = devadr; + p->epnum = epnum; + p->epdir = epdir; + p->mps = mps; + p->pid = pid; + p->index = index; + p->pcnt = pcnt; + p->len = tlen; + p->async = DWC2_ASYNC_INFLIGHT; + p->needs_service = false; + return; + } + + if (p->packet.status == USB_RET_SUCCESS) { + if (actual > tlen) { + p->packet.status = USB_RET_BABBLE; + goto babble; + } + + if (pid == USB_TOKEN_IN) { + trace_usb_dwc2_memory_write(hcdma, actual); + if (dma_memory_write(&s->dma_as, hcdma, s->usb_buf[chan], + actual) != MEMTX_OK) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: dma_memory_write failed\n", + __func__); + } + } + + tpcnt = actual / mps; + if (actual % mps) { + tpcnt++; + if (pid == USB_TOKEN_IN) { + done = true; + } + } + + pcnt -= tpcnt < pcnt ? tpcnt : pcnt; + set_field(&hctsiz, pcnt, TSIZ_PKTCNT); + len -= actual < len ? actual : len; + set_field(&hctsiz, len, TSIZ_XFERSIZE); + s->hreg1[index + 4] = hctsiz; + hcdma += actual; + s->hreg1[index + 5] = hcdma; + + if (!pcnt || len == 0 || actual == 0) { + done = true; + } + } else { + intr |= pintr[stsidx]; + if (p->packet.status == USB_RET_NAK && + (eptype == USB_ENDPOINT_XFER_CONTROL || + eptype == USB_ENDPOINT_XFER_BULK)) { + /* + * for ctrl/bulk, automatically retry on NAK, + * but send the interrupt anyway + */ + intr &= ~HCINTMSK_RESERVED14_31; + s->hreg1[index + 2] |= intr; + do_intr = true; + } else { + intr |= HCINTMSK_CHHLTD; + done = true; + } + } + + usb_packet_cleanup(&p->packet); + + if (done) { + hcchar &= ~HCCHAR_CHENA; + s->hreg1[index] = hcchar; + if (!(intr & HCINTMSK_CHHLTD)) { + intr |= HCINTMSK_CHHLTD | HCINTMSK_XFERCOMPL; + } + intr &= ~HCINTMSK_RESERVED14_31; + s->hreg1[index + 2] |= intr; + p->needs_service = false; + trace_usb_dwc2_packet_done(pstatus[stsidx], actual, len, pcnt); + dwc2_update_hc_irq(s, index); + return; + } + + p->devadr = devadr; + p->epnum = epnum; + p->epdir = epdir; + p->mps = mps; + p->pid = pid; + p->index = index; + p->pcnt = pcnt; + p->len = len; + p->needs_service = true; + trace_usb_dwc2_packet_next(pstatus[stsidx], len, pcnt); + if (do_intr) { + dwc2_update_hc_irq(s, index); + } +} + +/* Attach or detach a device on root hub */ + +static const char *speeds[] = { + "low", "full", "high" +}; + +static void dwc2_attach(USBPort *port) +{ + DWC2State *s = port->opaque; + int hispd = 0; + + trace_usb_dwc2_attach(port); + assert(port->index == 0); + + if (!port->dev || !port->dev->attached) { + return; + } + + assert(port->dev->speed <= USB_SPEED_HIGH); + trace_usb_dwc2_attach_speed(speeds[port->dev->speed]); + s->hprt0 &= ~HPRT0_SPD_MASK; + + switch (port->dev->speed) { + case USB_SPEED_LOW: + s->hprt0 |= HPRT0_SPD_LOW_SPEED << HPRT0_SPD_SHIFT; + break; + case USB_SPEED_FULL: + s->hprt0 |= HPRT0_SPD_FULL_SPEED << HPRT0_SPD_SHIFT; + break; + case USB_SPEED_HIGH: + s->hprt0 |= HPRT0_SPD_HIGH_SPEED << HPRT0_SPD_SHIFT; + hispd = 1; + break; + } + + if (hispd) { + s->usb_frame_time = NANOSECONDS_PER_SECOND / 8000; /* 125000 */ + if (NANOSECONDS_PER_SECOND >= USB_HZ_HS) { + s->usb_bit_time = NANOSECONDS_PER_SECOND / USB_HZ_HS; /* 10.4 */ + } else { + s->usb_bit_time = 1; + } + } else { + s->usb_frame_time = NANOSECONDS_PER_SECOND / 1000; /* 1000000 */ + if (NANOSECONDS_PER_SECOND >= USB_HZ_FS) { + s->usb_bit_time = NANOSECONDS_PER_SECOND / USB_HZ_FS; /* 83.3 */ + } else { + s->usb_bit_time = 1; + } + } + + s->fi = USB_FRMINTVL - 1; + s->hprt0 |= HPRT0_CONNDET | HPRT0_CONNSTS; + + dwc2_bus_start(s); + dwc2_raise_global_irq(s, GINTSTS_PRTINT); +} + +static void dwc2_detach(USBPort *port) +{ + DWC2State *s = port->opaque; + + trace_usb_dwc2_detach(port); + assert(port->index == 0); + + dwc2_bus_stop(s); + + s->hprt0 &= ~(HPRT0_SPD_MASK | HPRT0_SUSP | HPRT0_ENA | HPRT0_CONNSTS); + s->hprt0 |= HPRT0_CONNDET | HPRT0_ENACHG; + + dwc2_raise_global_irq(s, GINTSTS_PRTINT); +} + +static void dwc2_child_detach(USBPort *port, USBDevice *child) +{ + trace_usb_dwc2_child_detach(port, child); + assert(port->index == 0); +} + +static void dwc2_wakeup(USBPort *port) +{ + DWC2State *s = port->opaque; + + trace_usb_dwc2_wakeup(port); + assert(port->index == 0); + + if (s->hprt0 & HPRT0_SUSP) { + s->hprt0 |= HPRT0_RES; + dwc2_raise_global_irq(s, GINTSTS_PRTINT); + } + + qemu_bh_schedule(s->async_bh); +} + +static void dwc2_async_packet_complete(USBPort *port, USBPacket *packet) +{ + DWC2State *s = port->opaque; + DWC2Packet *p; + USBDevice *dev; + USBEndpoint *ep; + + assert(port->index == 0); + p = container_of(packet, DWC2Packet, packet); + dev = dwc2_find_device(s, p->devadr); + ep = usb_ep_get(dev, p->pid, p->epnum); + trace_usb_dwc2_async_packet_complete(port, packet, p->index >> 3, dev, + p->epnum, dirs[p->epdir], p->len); + assert(p->async == DWC2_ASYNC_INFLIGHT); + + if (packet->status == USB_RET_REMOVE_FROM_QUEUE) { + usb_cancel_packet(packet); + usb_packet_cleanup(packet); + return; + } + + dwc2_handle_packet(s, p->devadr, dev, ep, p->index, false); + + p->async = DWC2_ASYNC_FINISHED; + qemu_bh_schedule(s->async_bh); +} + +static USBPortOps dwc2_port_ops = { + .attach = dwc2_attach, + .detach = dwc2_detach, + .child_detach = dwc2_child_detach, + .wakeup = dwc2_wakeup, + .complete = dwc2_async_packet_complete, +}; + +static uint32_t dwc2_get_frame_remaining(DWC2State *s) +{ + uint32_t fr = 0; + int64_t tks; + + tks = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - s->sof_time; + if (tks < 0) { + tks = 0; + } + + /* avoid muldiv if possible */ + if (tks >= s->usb_frame_time) { + goto out; + } + if (tks < s->usb_bit_time) { + fr = s->fi; + goto out; + } + + /* tks = number of ns since SOF, divided by 83 (fs) or 10 (hs) */ + tks = tks / s->usb_bit_time; + if (tks >= (int64_t)s->fi) { + goto out; + } + + /* remaining = frame interval minus tks */ + fr = (uint32_t)((int64_t)s->fi - tks); + +out: + return fr; +} + +static void dwc2_work_bh(void *opaque) +{ + DWC2State *s = opaque; + DWC2Packet *p; + USBDevice *dev; + USBEndpoint *ep; + int64_t t_now, expire_time; + int chan; + bool found = false; + + trace_usb_dwc2_work_bh(); + if (s->working) { + return; + } + s->working = true; + + t_now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + chan = s->next_chan; + + do { + p = &s->packet[chan]; + if (p->needs_service) { + dev = dwc2_find_device(s, p->devadr); + ep = usb_ep_get(dev, p->pid, p->epnum); + trace_usb_dwc2_work_bh_service(s->next_chan, chan, dev, p->epnum); + dwc2_handle_packet(s, p->devadr, dev, ep, p->index, true); + found = true; + } + if (++chan == DWC2_NB_CHAN) { + chan = 0; + } + if (found) { + s->next_chan = chan; + trace_usb_dwc2_work_bh_next(chan); + } + } while (chan != s->next_chan); + + if (found) { + expire_time = t_now + NANOSECONDS_PER_SECOND / 4000; + timer_mod(s->frame_timer, expire_time); + } + s->working = false; +} + +static void dwc2_enable_chan(DWC2State *s, uint32_t index) +{ + USBDevice *dev; + USBEndpoint *ep; + uint32_t hcchar; + uint32_t hctsiz; + uint32_t devadr, epnum, epdir, eptype, pid, len; + DWC2Packet *p; + + assert((index >> 3) < DWC2_NB_CHAN); + p = &s->packet[index >> 3]; + hcchar = s->hreg1[index]; + hctsiz = s->hreg1[index + 4]; + devadr = get_field(hcchar, HCCHAR_DEVADDR); + epnum = get_field(hcchar, HCCHAR_EPNUM); + epdir = get_bit(hcchar, HCCHAR_EPDIR); + eptype = get_field(hcchar, HCCHAR_EPTYPE); + pid = get_field(hctsiz, TSIZ_SC_MC_PID); + len = get_field(hctsiz, TSIZ_XFERSIZE); + + dev = dwc2_find_device(s, devadr); + + trace_usb_dwc2_enable_chan(index >> 3, dev, &p->packet, epnum); + if (dev == NULL) { + return; + } + + if (eptype == USB_ENDPOINT_XFER_CONTROL && pid == TSIZ_SC_MC_PID_SETUP) { + pid = USB_TOKEN_SETUP; + } else { + pid = epdir ? USB_TOKEN_IN : USB_TOKEN_OUT; + } + + ep = usb_ep_get(dev, pid, epnum); + + /* + * Hack: Networking doesn't like us delivering large transfers, it kind + * of works but the latency is horrible. So if the transfer is <= the mtu + * size, we take that as a hint that this might be a network transfer, + * and do the transfer packet-by-packet. + */ + if (len > 1536) { + p->small = false; + } else { + p->small = true; + } + + dwc2_handle_packet(s, devadr, dev, ep, index, true); + qemu_bh_schedule(s->async_bh); +} + +static const char *glbregnm[] = { + "GOTGCTL ", "GOTGINT ", "GAHBCFG ", "GUSBCFG ", "GRSTCTL ", + "GINTSTS ", "GINTMSK ", "GRXSTSR ", "GRXSTSP ", "GRXFSIZ ", + "GNPTXFSIZ", "GNPTXSTS ", "GI2CCTL ", "GPVNDCTL ", "GGPIO ", + "GUID ", "GSNPSID ", "GHWCFG1 ", "GHWCFG2 ", "GHWCFG3 ", + "GHWCFG4 ", "GLPMCFG ", "GPWRDN ", "GDFIFOCFG", "GADPCTL ", + "GREFCLK ", "GINTMSK2 ", "GINTSTS2 " +}; + +static uint64_t dwc2_glbreg_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr <= GINTSTS2); + val = s->glbreg[index]; + + switch (addr) { + case GRSTCTL: + /* clear any self-clearing bits that were set */ + val &= ~(GRSTCTL_TXFFLSH | GRSTCTL_RXFFLSH | GRSTCTL_IN_TKNQ_FLSH | + GRSTCTL_FRMCNTRRST | GRSTCTL_HSFTRST | GRSTCTL_CSFTRST); + s->glbreg[index] = val; + break; + default: + break; + } + + trace_usb_dwc2_glbreg_read(addr, glbregnm[index], val); + return val; +} + +static void dwc2_glbreg_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + int iflg = 0; + + assert(addr <= GINTSTS2); + mmio = &s->glbreg[index]; + old = *mmio; + + switch (addr) { + case GOTGCTL: + /* don't allow setting of read-only bits */ + val &= ~(GOTGCTL_MULT_VALID_BC_MASK | GOTGCTL_BSESVLD | + GOTGCTL_ASESVLD | GOTGCTL_DBNC_SHORT | GOTGCTL_CONID_B | + GOTGCTL_HSTNEGSCS | GOTGCTL_SESREQSCS); + /* don't allow clearing of read-only bits */ + val |= old & (GOTGCTL_MULT_VALID_BC_MASK | GOTGCTL_BSESVLD | + GOTGCTL_ASESVLD | GOTGCTL_DBNC_SHORT | GOTGCTL_CONID_B | + GOTGCTL_HSTNEGSCS | GOTGCTL_SESREQSCS); + break; + case GAHBCFG: + if ((val & GAHBCFG_GLBL_INTR_EN) && !(old & GAHBCFG_GLBL_INTR_EN)) { + iflg = 1; + } + break; + case GRSTCTL: + val |= GRSTCTL_AHBIDLE; + val &= ~GRSTCTL_DMAREQ; + if (!(old & GRSTCTL_TXFFLSH) && (val & GRSTCTL_TXFFLSH)) { + /* TODO - TX fifo flush */ + qemu_log_mask(LOG_UNIMP, "Tx FIFO flush not implemented\n"); + } + if (!(old & GRSTCTL_RXFFLSH) && (val & GRSTCTL_RXFFLSH)) { + /* TODO - RX fifo flush */ + qemu_log_mask(LOG_UNIMP, "Rx FIFO flush not implemented\n"); + } + if (!(old & GRSTCTL_IN_TKNQ_FLSH) && (val & GRSTCTL_IN_TKNQ_FLSH)) { + /* TODO - device IN token queue flush */ + qemu_log_mask(LOG_UNIMP, "Token queue flush not implemented\n"); + } + if (!(old & GRSTCTL_FRMCNTRRST) && (val & GRSTCTL_FRMCNTRRST)) { + /* TODO - host frame counter reset */ + qemu_log_mask(LOG_UNIMP, "Frame counter reset not implemented\n"); + } + if (!(old & GRSTCTL_HSFTRST) && (val & GRSTCTL_HSFTRST)) { + /* TODO - host soft reset */ + qemu_log_mask(LOG_UNIMP, "Host soft reset not implemented\n"); + } + if (!(old & GRSTCTL_CSFTRST) && (val & GRSTCTL_CSFTRST)) { + /* TODO - core soft reset */ + qemu_log_mask(LOG_UNIMP, "Core soft reset not implemented\n"); + } + /* don't allow clearing of self-clearing bits */ + val |= old & (GRSTCTL_TXFFLSH | GRSTCTL_RXFFLSH | + GRSTCTL_IN_TKNQ_FLSH | GRSTCTL_FRMCNTRRST | + GRSTCTL_HSFTRST | GRSTCTL_CSFTRST); + break; + case GINTSTS: + /* clear the write-1-to-clear bits */ + val |= ~old; + val = ~val; + /* don't allow clearing of read-only bits */ + val |= old & (GINTSTS_PTXFEMP | GINTSTS_HCHINT | GINTSTS_PRTINT | + GINTSTS_OEPINT | GINTSTS_IEPINT | GINTSTS_GOUTNAKEFF | + GINTSTS_GINNAKEFF | GINTSTS_NPTXFEMP | GINTSTS_RXFLVL | + GINTSTS_OTGINT | GINTSTS_CURMODE_HOST); + iflg = 1; + break; + case GINTMSK: + iflg = 1; + break; + default: + break; + } + + trace_usb_dwc2_glbreg_write(addr, glbregnm[index], orig, old, val); + *mmio = val; + + if (iflg) { + dwc2_update_irq(s); + } +} + +static uint64_t dwc2_fszreg_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr == HPTXFSIZ); + val = s->fszreg[index]; + + trace_usb_dwc2_fszreg_read(addr, val); + return val; +} + +static void dwc2_fszreg_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + + assert(addr == HPTXFSIZ); + mmio = &s->fszreg[index]; + old = *mmio; + + trace_usb_dwc2_fszreg_write(addr, orig, old, val); + *mmio = val; +} + +static const char *hreg0nm[] = { + "HCFG ", "HFIR ", "HFNUM ", "<rsvd> ", "HPTXSTS ", + "HAINT ", "HAINTMSK ", "HFLBADDR ", "<rsvd> ", "<rsvd> ", + "<rsvd> ", "<rsvd> ", "<rsvd> ", "<rsvd> ", "<rsvd> ", + "<rsvd> ", "HPRT0 " +}; + +static uint64_t dwc2_hreg0_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr >= HCFG && addr <= HPRT0); + val = s->hreg0[index]; + + switch (addr) { + case HFNUM: + val = (dwc2_get_frame_remaining(s) << HFNUM_FRREM_SHIFT) | + (s->hfnum << HFNUM_FRNUM_SHIFT); + break; + default: + break; + } + + trace_usb_dwc2_hreg0_read(addr, hreg0nm[index], val); + return val; +} + +static void dwc2_hreg0_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + USBDevice *dev = s->uport.dev; + uint64_t orig = val; + uint32_t *mmio; + uint32_t tval, told, old; + int prst = 0; + int iflg = 0; + + assert(addr >= HCFG && addr <= HPRT0); + mmio = &s->hreg0[index]; + old = *mmio; + + switch (addr) { + case HFIR: + break; + case HFNUM: + case HPTXSTS: + case HAINT: + qemu_log_mask(LOG_GUEST_ERROR, "%s: write to read-only register\n", + __func__); + return; + case HAINTMSK: + val &= 0xffff; + break; + case HPRT0: + /* don't allow clearing of read-only bits */ + val |= old & (HPRT0_SPD_MASK | HPRT0_LNSTS_MASK | HPRT0_OVRCURRACT | + HPRT0_CONNSTS); + /* don't allow clearing of self-clearing bits */ + val |= old & (HPRT0_SUSP | HPRT0_RES); + /* don't allow setting of self-setting bits */ + if (!(old & HPRT0_ENA) && (val & HPRT0_ENA)) { + val &= ~HPRT0_ENA; + } + /* clear the write-1-to-clear bits */ + tval = val & (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + told = old & (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + tval |= ~told; + tval = ~tval; + tval &= (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + val &= ~(HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_ENA | + HPRT0_CONNDET); + val |= tval; + if (!(val & HPRT0_RST) && (old & HPRT0_RST)) { + if (dev && dev->attached) { + val |= HPRT0_ENA | HPRT0_ENACHG; + prst = 1; + } + } + if (val & (HPRT0_OVRCURRCHG | HPRT0_ENACHG | HPRT0_CONNDET)) { + iflg = 1; + } else { + iflg = -1; + } + break; + default: + break; + } + + if (prst) { + trace_usb_dwc2_hreg0_write(addr, hreg0nm[index], orig, old, + val & ~HPRT0_CONNDET); + trace_usb_dwc2_hreg0_action("call usb_port_reset"); + usb_port_reset(&s->uport); + val &= ~HPRT0_CONNDET; + } else { + trace_usb_dwc2_hreg0_write(addr, hreg0nm[index], orig, old, val); + } + + *mmio = val; + + if (iflg > 0) { + trace_usb_dwc2_hreg0_action("enable PRTINT"); + dwc2_raise_global_irq(s, GINTSTS_PRTINT); + } else if (iflg < 0) { + trace_usb_dwc2_hreg0_action("disable PRTINT"); + dwc2_lower_global_irq(s, GINTSTS_PRTINT); + } +} + +static const char *hreg1nm[] = { + "HCCHAR ", "HCSPLT ", "HCINT ", "HCINTMSK", "HCTSIZ ", "HCDMA ", + "<rsvd> ", "HCDMAB " +}; + +static uint64_t dwc2_hreg1_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr >= HCCHAR(0) && addr <= HCDMAB(DWC2_NB_CHAN - 1)); + val = s->hreg1[index]; + + trace_usb_dwc2_hreg1_read(addr, hreg1nm[index & 7], addr >> 5, val); + return val; +} + +static void dwc2_hreg1_write(void *ptr, hwaddr addr, int index, uint64_t val, + unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + int iflg = 0; + int enflg = 0; + int disflg = 0; + + assert(addr >= HCCHAR(0) && addr <= HCDMAB(DWC2_NB_CHAN - 1)); + mmio = &s->hreg1[index]; + old = *mmio; + + switch (HSOTG_REG(0x500) + (addr & 0x1c)) { + case HCCHAR(0): + if ((val & HCCHAR_CHDIS) && !(old & HCCHAR_CHDIS)) { + val &= ~(HCCHAR_CHENA | HCCHAR_CHDIS); + disflg = 1; + } else { + val |= old & HCCHAR_CHDIS; + if ((val & HCCHAR_CHENA) && !(old & HCCHAR_CHENA)) { + val &= ~HCCHAR_CHDIS; + enflg = 1; + } else { + val |= old & HCCHAR_CHENA; + } + } + break; + case HCINT(0): + /* clear the write-1-to-clear bits */ + val |= ~old; + val = ~val; + val &= ~HCINTMSK_RESERVED14_31; + iflg = 1; + break; + case HCINTMSK(0): + val &= ~HCINTMSK_RESERVED14_31; + iflg = 1; + break; + case HCDMAB(0): + qemu_log_mask(LOG_GUEST_ERROR, "%s: write to read-only register\n", + __func__); + return; + default: + break; + } + + trace_usb_dwc2_hreg1_write(addr, hreg1nm[index & 7], index >> 3, orig, + old, val); + *mmio = val; + + if (disflg) { + /* set ChHltd in HCINT */ + s->hreg1[(index & ~7) + 2] |= HCINTMSK_CHHLTD; + iflg = 1; + } + + if (enflg) { + dwc2_enable_chan(s, index & ~7); + } + + if (iflg) { + dwc2_update_hc_irq(s, index & ~7); + } +} + +static const char *pcgregnm[] = { + "PCGCTL ", "PCGCCTL1 " +}; + +static uint64_t dwc2_pcgreg_read(void *ptr, hwaddr addr, int index, + unsigned size) +{ + DWC2State *s = ptr; + uint32_t val; + + assert(addr >= PCGCTL && addr <= PCGCCTL1); + val = s->pcgreg[index]; + + trace_usb_dwc2_pcgreg_read(addr, pcgregnm[index], val); + return val; +} + +static void dwc2_pcgreg_write(void *ptr, hwaddr addr, int index, + uint64_t val, unsigned size) +{ + DWC2State *s = ptr; + uint64_t orig = val; + uint32_t *mmio; + uint32_t old; + + assert(addr >= PCGCTL && addr <= PCGCCTL1); + mmio = &s->pcgreg[index]; + old = *mmio; + + trace_usb_dwc2_pcgreg_write(addr, pcgregnm[index], orig, old, val); + *mmio = val; +} + +static uint64_t dwc2_hsotg_read(void *ptr, hwaddr addr, unsigned size) +{ + uint64_t val; + + switch (addr) { + case HSOTG_REG(0x000) ... HSOTG_REG(0x0fc): + val = dwc2_glbreg_read(ptr, addr, (addr - HSOTG_REG(0x000)) >> 2, size); + break; + case HSOTG_REG(0x100): + val = dwc2_fszreg_read(ptr, addr, (addr - HSOTG_REG(0x100)) >> 2, size); + break; + case HSOTG_REG(0x104) ... HSOTG_REG(0x3fc): + /* Gadget-mode registers, just return 0 for now */ + val = 0; + break; + case HSOTG_REG(0x400) ... HSOTG_REG(0x4fc): + val = dwc2_hreg0_read(ptr, addr, (addr - HSOTG_REG(0x400)) >> 2, size); + break; + case HSOTG_REG(0x500) ... HSOTG_REG(0x7fc): + val = dwc2_hreg1_read(ptr, addr, (addr - HSOTG_REG(0x500)) >> 2, size); + break; + case HSOTG_REG(0x800) ... HSOTG_REG(0xdfc): + /* Gadget-mode registers, just return 0 for now */ + val = 0; + break; + case HSOTG_REG(0xe00) ... HSOTG_REG(0xffc): + val = dwc2_pcgreg_read(ptr, addr, (addr - HSOTG_REG(0xe00)) >> 2, size); + break; + default: + g_assert_not_reached(); + } + + return val; +} + +static void dwc2_hsotg_write(void *ptr, hwaddr addr, uint64_t val, + unsigned size) +{ + switch (addr) { + case HSOTG_REG(0x000) ... HSOTG_REG(0x0fc): + dwc2_glbreg_write(ptr, addr, (addr - HSOTG_REG(0x000)) >> 2, val, size); + break; + case HSOTG_REG(0x100): + dwc2_fszreg_write(ptr, addr, (addr - HSOTG_REG(0x100)) >> 2, val, size); + break; + case HSOTG_REG(0x104) ... HSOTG_REG(0x3fc): + /* Gadget-mode registers, do nothing for now */ + break; + case HSOTG_REG(0x400) ... HSOTG_REG(0x4fc): + dwc2_hreg0_write(ptr, addr, (addr - HSOTG_REG(0x400)) >> 2, val, size); + break; + case HSOTG_REG(0x500) ... HSOTG_REG(0x7fc): + dwc2_hreg1_write(ptr, addr, (addr - HSOTG_REG(0x500)) >> 2, val, size); + break; + case HSOTG_REG(0x800) ... HSOTG_REG(0xdfc): + /* Gadget-mode registers, do nothing for now */ + break; + case HSOTG_REG(0xe00) ... HSOTG_REG(0xffc): + dwc2_pcgreg_write(ptr, addr, (addr - HSOTG_REG(0xe00)) >> 2, val, size); + break; + default: + g_assert_not_reached(); + } +} + +static const MemoryRegionOps dwc2_mmio_hsotg_ops = { + .read = dwc2_hsotg_read, + .write = dwc2_hsotg_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static uint64_t dwc2_hreg2_read(void *ptr, hwaddr addr, unsigned size) +{ + /* TODO - implement FIFOs to support slave mode */ + trace_usb_dwc2_hreg2_read(addr, addr >> 12, 0); + qemu_log_mask(LOG_UNIMP, "FIFO read not implemented\n"); + return 0; +} + +static void dwc2_hreg2_write(void *ptr, hwaddr addr, uint64_t val, + unsigned size) +{ + uint64_t orig = val; + + /* TODO - implement FIFOs to support slave mode */ + trace_usb_dwc2_hreg2_write(addr, addr >> 12, orig, 0, val); + qemu_log_mask(LOG_UNIMP, "FIFO write not implemented\n"); +} + +static const MemoryRegionOps dwc2_mmio_hreg2_ops = { + .read = dwc2_hreg2_read, + .write = dwc2_hreg2_write, + .impl.min_access_size = 4, + .impl.max_access_size = 4, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void dwc2_wakeup_endpoint(USBBus *bus, USBEndpoint *ep, + unsigned int stream) +{ + DWC2State *s = container_of(bus, DWC2State, bus); + + trace_usb_dwc2_wakeup_endpoint(ep, stream); + + /* TODO - do something here? */ + qemu_bh_schedule(s->async_bh); +} + +static USBBusOps dwc2_bus_ops = { + .wakeup_endpoint = dwc2_wakeup_endpoint, +}; + +static void dwc2_work_timer(void *opaque) +{ + DWC2State *s = opaque; + + trace_usb_dwc2_work_timer(); + qemu_bh_schedule(s->async_bh); +} + +static void dwc2_reset_enter(Object *obj, ResetType type) +{ + DWC2Class *c = DWC2_GET_CLASS(obj); + DWC2State *s = DWC2_USB(obj); + int i; + + trace_usb_dwc2_reset_enter(); + + if (c->parent_phases.enter) { + c->parent_phases.enter(obj, type); + } + + timer_del(s->frame_timer); + qemu_bh_cancel(s->async_bh); + + if (s->uport.dev && s->uport.dev->attached) { + usb_detach(&s->uport); + } + + dwc2_bus_stop(s); + + s->gotgctl = GOTGCTL_BSESVLD | GOTGCTL_ASESVLD | GOTGCTL_CONID_B; + s->gotgint = 0; + s->gahbcfg = 0; + s->gusbcfg = 5 << GUSBCFG_USBTRDTIM_SHIFT; + s->grstctl = GRSTCTL_AHBIDLE; + s->gintsts = GINTSTS_CONIDSTSCHNG | GINTSTS_PTXFEMP | GINTSTS_NPTXFEMP | + GINTSTS_CURMODE_HOST; + s->gintmsk = 0; + s->grxstsr = 0; + s->grxstsp = 0; + s->grxfsiz = 1024; + s->gnptxfsiz = 1024 << FIFOSIZE_DEPTH_SHIFT; + s->gnptxsts = (4 << FIFOSIZE_DEPTH_SHIFT) | 1024; + s->gi2cctl = GI2CCTL_I2CDATSE0 | GI2CCTL_ACK; + s->gpvndctl = 0; + s->ggpio = 0; + s->guid = 0; + s->gsnpsid = 0x4f54294a; + s->ghwcfg1 = 0; + s->ghwcfg2 = (8 << GHWCFG2_DEV_TOKEN_Q_DEPTH_SHIFT) | + (4 << GHWCFG2_HOST_PERIO_TX_Q_DEPTH_SHIFT) | + (4 << GHWCFG2_NONPERIO_TX_Q_DEPTH_SHIFT) | + GHWCFG2_DYNAMIC_FIFO | + GHWCFG2_PERIO_EP_SUPPORTED | + ((DWC2_NB_CHAN - 1) << GHWCFG2_NUM_HOST_CHAN_SHIFT) | + (GHWCFG2_INT_DMA_ARCH << GHWCFG2_ARCHITECTURE_SHIFT) | + (GHWCFG2_OP_MODE_NO_SRP_CAPABLE_HOST << GHWCFG2_OP_MODE_SHIFT); + s->ghwcfg3 = (4096 << GHWCFG3_DFIFO_DEPTH_SHIFT) | + (4 << GHWCFG3_PACKET_SIZE_CNTR_WIDTH_SHIFT) | + (4 << GHWCFG3_XFER_SIZE_CNTR_WIDTH_SHIFT); + s->ghwcfg4 = 0; + s->glpmcfg = 0; + s->gpwrdn = GPWRDN_PWRDNRSTN; + s->gdfifocfg = 0; + s->gadpctl = 0; + s->grefclk = 0; + s->gintmsk2 = 0; + s->gintsts2 = 0; + + s->hptxfsiz = 500 << FIFOSIZE_DEPTH_SHIFT; + + s->hcfg = 2 << HCFG_RESVALID_SHIFT; + s->hfir = 60000; + s->hfnum = 0x3fff; + s->hptxsts = (16 << TXSTS_QSPCAVAIL_SHIFT) | 32768; + s->haint = 0; + s->haintmsk = 0; + s->hprt0 = 0; + + memset(s->hreg1, 0, sizeof(s->hreg1)); + memset(s->pcgreg, 0, sizeof(s->pcgreg)); + + s->sof_time = 0; + s->frame_number = 0; + s->fi = USB_FRMINTVL - 1; + s->next_chan = 0; + s->working = false; + + for (i = 0; i < DWC2_NB_CHAN; i++) { + s->packet[i].needs_service = false; + } +} + +static void dwc2_reset_hold(Object *obj) +{ + DWC2Class *c = DWC2_GET_CLASS(obj); + DWC2State *s = DWC2_USB(obj); + + trace_usb_dwc2_reset_hold(); + + if (c->parent_phases.hold) { + c->parent_phases.hold(obj); + } + + dwc2_update_irq(s); +} + +static void dwc2_reset_exit(Object *obj) +{ + DWC2Class *c = DWC2_GET_CLASS(obj); + DWC2State *s = DWC2_USB(obj); + + trace_usb_dwc2_reset_exit(); + + if (c->parent_phases.exit) { + c->parent_phases.exit(obj); + } + + s->hprt0 = HPRT0_PWR; + if (s->uport.dev && s->uport.dev->attached) { + usb_attach(&s->uport); + usb_device_reset(s->uport.dev); + } +} + +static void dwc2_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + DWC2State *s = DWC2_USB(dev); + Object *obj; + Error *err = NULL; + + obj = object_property_get_link(OBJECT(dev), "dma-mr", &err); + if (err) { + error_setg(errp, "dwc2: required dma-mr link not found: %s", + error_get_pretty(err)); + return; + } + assert(obj != NULL); + + s->dma_mr = MEMORY_REGION(obj); + address_space_init(&s->dma_as, s->dma_mr, "dwc2"); + + usb_bus_new(&s->bus, sizeof(s->bus), &dwc2_bus_ops, dev); + usb_register_port(&s->bus, &s->uport, s, 0, &dwc2_port_ops, + USB_SPEED_MASK_LOW | USB_SPEED_MASK_FULL | + (s->usb_version == 2 ? USB_SPEED_MASK_HIGH : 0)); + s->uport.dev = 0; + + s->usb_frame_time = NANOSECONDS_PER_SECOND / 1000; /* 1000000 */ + if (NANOSECONDS_PER_SECOND >= USB_HZ_FS) { + s->usb_bit_time = NANOSECONDS_PER_SECOND / USB_HZ_FS; /* 83.3 */ + } else { + s->usb_bit_time = 1; + } + + s->fi = USB_FRMINTVL - 1; + s->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, dwc2_frame_boundary, s); + s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, dwc2_work_timer, s); + s->async_bh = qemu_bh_new(dwc2_work_bh, s); + + sysbus_init_irq(sbd, &s->irq); +} + +static void dwc2_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + DWC2State *s = DWC2_USB(obj); + + memory_region_init(&s->container, obj, "dwc2", DWC2_MMIO_SIZE); + sysbus_init_mmio(sbd, &s->container); + + memory_region_init_io(&s->hsotg, obj, &dwc2_mmio_hsotg_ops, s, + "dwc2-io", 4 * KiB); + memory_region_add_subregion(&s->container, 0x0000, &s->hsotg); + + memory_region_init_io(&s->fifos, obj, &dwc2_mmio_hreg2_ops, s, + "dwc2-fifo", 64 * KiB); + memory_region_add_subregion(&s->container, 0x1000, &s->fifos); +} + +static const VMStateDescription vmstate_dwc2_state_packet = { + .name = "dwc2/packet", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(devadr, DWC2Packet), + VMSTATE_UINT32(epnum, DWC2Packet), + VMSTATE_UINT32(epdir, DWC2Packet), + VMSTATE_UINT32(mps, DWC2Packet), + VMSTATE_UINT32(pid, DWC2Packet), + VMSTATE_UINT32(index, DWC2Packet), + VMSTATE_UINT32(pcnt, DWC2Packet), + VMSTATE_UINT32(len, DWC2Packet), + VMSTATE_INT32(async, DWC2Packet), + VMSTATE_BOOL(small, DWC2Packet), + VMSTATE_BOOL(needs_service, DWC2Packet), + VMSTATE_END_OF_LIST() + }, +}; + +const VMStateDescription vmstate_dwc2_state = { + .name = "dwc2", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(glbreg, DWC2State, + DWC2_GLBREG_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(fszreg, DWC2State, + DWC2_FSZREG_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(hreg0, DWC2State, + DWC2_HREG0_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(hreg1, DWC2State, + DWC2_HREG1_SIZE / sizeof(uint32_t)), + VMSTATE_UINT32_ARRAY(pcgreg, DWC2State, + DWC2_PCGREG_SIZE / sizeof(uint32_t)), + + VMSTATE_TIMER_PTR(eof_timer, DWC2State), + VMSTATE_TIMER_PTR(frame_timer, DWC2State), + VMSTATE_INT64(sof_time, DWC2State), + VMSTATE_INT64(usb_frame_time, DWC2State), + VMSTATE_INT64(usb_bit_time, DWC2State), + VMSTATE_UINT32(usb_version, DWC2State), + VMSTATE_UINT16(frame_number, DWC2State), + VMSTATE_UINT16(fi, DWC2State), + VMSTATE_UINT16(next_chan, DWC2State), + VMSTATE_BOOL(working, DWC2State), + + VMSTATE_STRUCT_ARRAY(packet, DWC2State, DWC2_NB_CHAN, 1, + vmstate_dwc2_state_packet, DWC2Packet), + VMSTATE_UINT8_2DARRAY(usb_buf, DWC2State, DWC2_NB_CHAN, + DWC2_MAX_XFER_SIZE), + + VMSTATE_END_OF_LIST() + } +}; + +static Property dwc2_usb_properties[] = { + DEFINE_PROP_UINT32("usb_version", DWC2State, usb_version, 2), + DEFINE_PROP_END_OF_LIST(), +}; + +static void dwc2_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + DWC2Class *c = DWC2_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + dc->realize = dwc2_realize; + dc->vmsd = &vmstate_dwc2_state; + set_bit(DEVICE_CATEGORY_USB, dc->categories); + device_class_set_props(dc, dwc2_usb_properties); + resettable_class_set_parent_phases(rc, dwc2_reset_enter, dwc2_reset_hold, + dwc2_reset_exit, &c->parent_phases); +} + +static const TypeInfo dwc2_usb_type_info = { + .name = TYPE_DWC2_USB, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(DWC2State), + .instance_init = dwc2_init, + .class_size = sizeof(DWC2Class), + .class_init = dwc2_class_init, +}; + +static void dwc2_usb_register_types(void) +{ + type_register_static(&dwc2_usb_type_info); +} + +type_init(dwc2_usb_register_types) diff --git a/hw/usb/Kconfig b/hw/usb/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Kconfig +++ b/hw/usb/Kconfig @@ -XXX,XX +XXX,XX @@ config USB_MUSB bool select USB +config USB_DWC2 + bool + default y + select USB + config TUSB6010 bool select USB_MUSB diff --git a/hw/usb/Makefile.objs b/hw/usb/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Makefile.objs +++ b/hw/usb/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_USB_EHCI_SYSBUS) += hcd-ehci-sysbus.o common-obj-$(CONFIG_USB_XHCI) += hcd-xhci.o common-obj-$(CONFIG_USB_XHCI_NEC) += hcd-xhci-nec.o common-obj-$(CONFIG_USB_MUSB) += hcd-musb.o +common-obj-$(CONFIG_USB_DWC2) += hcd-dwc2.o common-obj-$(CONFIG_TUSB6010) += tusb6010.o common-obj-$(CONFIG_IMX) += chipidea.o diff --git a/hw/usb/trace-events b/hw/usb/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/trace-events +++ b/hw/usb/trace-events @@ -XXX,XX +XXX,XX @@ usb_xhci_xfer_error(void *xfer, uint32_t ret) "%p: ret %d" usb_xhci_unimplemented(const char *item, int nr) "%s (0x%x)" usb_xhci_enforced_limit(const char *item) "%s" +# hcd-dwc2.c +usb_dwc2_update_irq(uint32_t level) "level=%d" +usb_dwc2_raise_global_irq(uint32_t intr) "0x%08x" +usb_dwc2_lower_global_irq(uint32_t intr) "0x%08x" +usb_dwc2_raise_host_irq(uint32_t intr) "0x%04x" +usb_dwc2_lower_host_irq(uint32_t intr) "0x%04x" +usb_dwc2_sof(int64_t next) "next SOF %" PRId64 +usb_dwc2_bus_start(void) "start SOFs" +usb_dwc2_bus_stop(void) "stop SOFs" +usb_dwc2_find_device(uint8_t addr) "%d" +usb_dwc2_port_disabled(uint32_t pnum) "port %d disabled" +usb_dwc2_device_found(uint32_t pnum) "device found on port %d" +usb_dwc2_device_not_found(void) "device not found" +usb_dwc2_handle_packet(uint32_t chan, void *dev, void *pkt, uint32_t ep, const char *type, const char *dir, uint32_t mps, uint32_t len, uint32_t pcnt) "ch %d dev %p pkt %p ep %d type %s dir %s mps %d len %d pcnt %d" +usb_dwc2_memory_read(uint32_t addr, uint32_t len) "addr %d len %d" +usb_dwc2_packet_status(const char *status, uint32_t len) "status %s len %d" +usb_dwc2_packet_error(const char *status) "ERROR %s" +usb_dwc2_async_packet(void *pkt, uint32_t chan, void *dev, uint32_t ep, const char *dir, uint32_t len) "pkt %p ch %d dev %p ep %d %s len %d" +usb_dwc2_memory_write(uint32_t addr, uint32_t len) "addr %d len %d" +usb_dwc2_packet_done(const char *status, uint32_t actual, uint32_t len, uint32_t pcnt) "status %s actual %d len %d pcnt %d" +usb_dwc2_packet_next(const char *status, uint32_t len, uint32_t pcnt) "status %s len %d pcnt %d" +usb_dwc2_attach(void *port) "port %p" +usb_dwc2_attach_speed(const char *speed) "%s-speed device attached" +usb_dwc2_detach(void *port) "port %p" +usb_dwc2_child_detach(void *port, void *child) "port %p child %p" +usb_dwc2_wakeup(void *port) "port %p" +usb_dwc2_async_packet_complete(void *port, void *pkt, uint32_t chan, void *dev, uint32_t ep, const char *dir, uint32_t len) "port %p packet %p ch %d dev %p ep %d %s len %d" +usb_dwc2_work_bh(void) "" +usb_dwc2_work_bh_service(uint32_t first, uint32_t current, void *dev, uint32_t ep) "first %d servicing %d dev %p ep %d" +usb_dwc2_work_bh_next(uint32_t chan) "next %d" +usb_dwc2_enable_chan(uint32_t chan, void *dev, void *pkt, uint32_t ep) "ch %d dev %p pkt %p ep %d" +usb_dwc2_glbreg_read(uint64_t addr, const char *reg, uint32_t val) " 0x%04" PRIx64 " %s val 0x%08x" +usb_dwc2_glbreg_write(uint64_t addr, const char *reg, uint64_t val, uint32_t old, uint64_t result) "0x%04" PRIx64 " %s val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_fszreg_read(uint64_t addr, uint32_t val) " 0x%04" PRIx64 " HPTXFSIZ val 0x%08x" +usb_dwc2_fszreg_write(uint64_t addr, uint64_t val, uint32_t old, uint64_t result) "0x%04" PRIx64 " HPTXFSIZ val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg0_read(uint64_t addr, const char *reg, uint32_t val) " 0x%04" PRIx64 " %s val 0x%08x" +usb_dwc2_hreg0_write(uint64_t addr, const char *reg, uint64_t val, uint32_t old, uint64_t result) " 0x%04" PRIx64 " %s val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg1_read(uint64_t addr, const char *reg, uint64_t chan, uint32_t val) " 0x%04" PRIx64 " %s%" PRId64 " val 0x%08x" +usb_dwc2_hreg1_write(uint64_t addr, const char *reg, uint64_t chan, uint64_t val, uint32_t old, uint64_t result) " 0x%04" PRIx64 " %s%" PRId64 " val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_pcgreg_read(uint64_t addr, const char *reg, uint32_t val) " 0x%04" PRIx64 " %s val 0x%08x" +usb_dwc2_pcgreg_write(uint64_t addr, const char *reg, uint64_t val, uint32_t old, uint64_t result) "0x%04" PRIx64 " %s val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg2_read(uint64_t addr, uint64_t fifo, uint32_t val) " 0x%04" PRIx64 " FIFO%" PRId64 " val 0x%08x" +usb_dwc2_hreg2_write(uint64_t addr, uint64_t fifo, uint64_t val, uint32_t old, uint64_t result) " 0x%04" PRIx64 " FIFO%" PRId64 " val 0x%08" PRIx64 " old 0x%08x result 0x%08" PRIx64 +usb_dwc2_hreg0_action(const char *s) "%s" +usb_dwc2_wakeup_endpoint(void *ep, uint32_t stream) "endp %p stream %d" +usb_dwc2_work_timer(void) "" +usb_dwc2_reset_enter(void) "=== RESET enter ===" +usb_dwc2_reset_hold(void) "=== RESET hold ===" +usb_dwc2_reset_exit(void) "=== RESET exit ===" + # desc.c usb_desc_device(int addr, int len, int ret) "dev %d query device, len %d, ret %d" usb_desc_device_qualifier(int addr, int len, int ret) "dev %d query device qualifier, len %d, ret %d" -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> The dwc-hsotg (dwc2) USB host depends on a short packet to indicate the end of an IN transfer. The usb-storage driver currently doesn't provide this, so fix it. I have tested this change rather extensively using a PC emulation with xhci, ehci, and uhci controllers, and have not observed any regressions. Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Message-id: 20200520235349.21215-6-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/dev-storage.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/hw/usb/dev-storage.c b/hw/usb/dev-storage.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/dev-storage.c +++ b/hw/usb/dev-storage.c @@ -XXX,XX +XXX,XX @@ static void usb_msd_copy_data(MSDState *s, USBPacket *p) usb_packet_copy(p, scsi_req_get_buf(s->req) + s->scsi_off, len); s->scsi_len -= len; s->scsi_off += len; + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; if (s->scsi_len == 0 || s->data_len == 0) { scsi_req_continue(s->req); @@ -XXX,XX +XXX,XX @@ static void usb_msd_command_complete(SCSIRequest *req, uint32_t status, size_t r if (s->data_len) { int len = (p->iov.size - p->actual_length); usb_packet_skip(p, len); + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; } if (s->data_len == 0) { @@ -XXX,XX +XXX,XX @@ static void usb_msd_handle_data(USBDevice *dev, USBPacket *p) int len = p->iov.size - p->actual_length; if (len) { usb_packet_skip(p, len); + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; if (s->data_len == 0) { s->mode = USB_MSDM_CSW; @@ -XXX,XX +XXX,XX @@ static void usb_msd_handle_data(USBDevice *dev, USBPacket *p) int len = p->iov.size - p->actual_length; if (len) { usb_packet_skip(p, len); + if (len > s->data_len) { + len = s->data_len; + } s->data_len -= len; if (s->data_len == 0) { s->mode = USB_MSDM_CSW; } } } - if (p->actual_length < p->iov.size) { + if (p->actual_length < p->iov.size && (p->short_not_ok || + s->scsi_len >= p->ep->max_packet_size)) { DPRINTF("Deferring packet %p [wait data-in]\n", p); s->packet = p; p->status = USB_RET_ASYNC; -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Wire the dwc-hsotg (dwc2) emulation into Qemu Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Reviewed-by: Philippe Mathieu-Daude <f4bug@amsat.org> Message-id: 20200520235349.21215-7-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 3 ++- hw/arm/bcm2835_peripherals.c | 21 ++++++++++++++++++++- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/bcm2835_sdhost.h" #include "hw/gpio/bcm2835_gpio.h" #include "hw/timer/bcm2835_systmr.h" +#include "hw/usb/hcd-dwc2.h" #include "hw/misc/unimp.h" #define TYPE_BCM2835_PERIPHERALS "bcm2835-peripherals" @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { UnimplementedDeviceState ave0; UnimplementedDeviceState bscsl; UnimplementedDeviceState smi; - UnimplementedDeviceState dwc2; + DWC2State dwc2; UnimplementedDeviceState sdramc; } BCM2835PeripheralState; diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) /* Mphi */ sysbus_init_child_obj(obj, "mphi", &s->mphi, sizeof(s->mphi), TYPE_BCM2835_MPHI); + + /* DWC2 */ + sysbus_init_child_obj(obj, "dwc2", &s->dwc2, sizeof(s->dwc2), + TYPE_DWC2_USB); + + object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", + OBJECT(&s->gpu_bus_mr)); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, INTERRUPT_HOSTPORT)); + /* DWC2 */ + object_property_set_bool(OBJECT(&s->dwc2), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + memory_region_add_subregion(&s->peri_mr, USB_OTG_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->dwc2), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->dwc2), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, + INTERRUPT_USB)); + create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); create_unimp(s, &s->cprman, "bcm2835-cprman", CPRMAN_OFFSET, 0x1000); create_unimp(s, &s->a2w, "bcm2835-a2w", A2W_OFFSET, 0x1000); @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) create_unimp(s, &s->otp, "bcm2835-otp", OTP_OFFSET, 0x80); create_unimp(s, &s->dbus, "bcm2835-dbus", DBUS_OFFSET, 0x8000); create_unimp(s, &s->ave0, "bcm2835-ave0", AVE0_OFFSET, 0x8000); - create_unimp(s, &s->dwc2, "dwc-usb2", USB_OTG_OFFSET, 0x1000); create_unimp(s, &s->sdramc, "bcm2835-sdramc", SDRAMC_OFFSET, 0x100); } -- 2.20.1 From: Paul Zimmerman <pauldzim@gmail.com> Add a check for functional dwc-hsotg (dwc2) USB host emulation to the Raspi 2 acceptance test Signed-off-by: Paul Zimmerman <pauldzim@gmail.com> Reviewed-by: Philippe Mathieu-Daude <f4bug@amsat.org> Message-id: 20200520235349.21215-8-pauldzim@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 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(LinuxKernelTest): self.vm.set_console() kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + - serial_kernel_cmdline[uart_id]) + serial_kernel_cmdline[uart_id] + + ' root=/dev/mmcblk0p2 rootwait ' + + 'dwc_otg.fiq_fsm_enable=0') self.vm.add_args('-kernel', kernel_path, '-dtb', dtb_path, - '-append', kernel_command_line) + '-append', kernel_command_line, + '-device', 'usb-kbd') self.vm.launch() console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) + console_pattern = 'Product: QEMU USB Keyboard' + self.wait_for_console_pattern(console_pattern) def test_arm_raspi2_uart0(self): """ -- 2.20.1 Convert the VSHL and VSLI insns from the Neon 2-registers-and-a-shift group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-2-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 25 ++++++++++++++++++++++ target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 18 +++++++--------- 3 files changed, 71 insertions(+), 10 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VRECPS_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 1 .... @3same_fp VRSQRTS_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 1 .... @3same_fp VMAXNM_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 1 .... @3same_fp VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp + +###################################################################### +# 2-reg-and-shift grouping: +# 1111 001 U 1 D immH:3 immL:3 Vd:4 opc:4 L Q M 1 Vm:4 +###################################################################### +&2reg_shift vm vd q shift size + +@2reg_shl_d .... ... . . . shift:6 .... .... 1 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=3 +@2reg_shl_s .... ... . . . 1 shift:5 .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 +@2reg_shl_h .... ... . . . 01 shift:4 .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 +@2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 + +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h +VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b + +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h +VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) DO_3S_FP_PAIR(VPADD, gen_helper_vfp_adds) DO_3S_FP_PAIR(VPMAX, gen_helper_vfp_maxs) DO_3S_FP_PAIR(VPMIN, gen_helper_vfp_mins) + +static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) +{ + /* Handle a 2-reg-shift insn which can be vectorized. */ + int vec_size = a->q ? 16 : 8; + int rd_ofs = neon_reg_offset(a->vd, 0); + int rm_ofs = neon_reg_offset(a->vm, 0); + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fn(a->size, rd_ofs, rm_ofs, a->shift, vec_size, vec_size); + return true; +} + +#define DO_2SH(INSN, FUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_vector_2sh(s, a, FUNC); \ + } \ + +DO_2SH(VSHL, tcg_gen_gvec_shli) +DO_2SH(VSLI, gen_gvec_sli) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if ((insn & 0x00380080) != 0) { /* Two registers and shift. */ op = (insn >> 8) & 0xf; + + switch (op) { + case 5: /* VSHL, VSLI */ + return 1; /* handled by decodetree */ + default: + break; + } + if (insn & (1 << 7)) { /* 64-bit shift. */ if (op > 7) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) gen_gvec_sri(size, rd_ofs, rm_ofs, shift, vec_size, vec_size); return 0; - - case 5: /* VSHL, VSLI */ - if (u) { /* VSLI */ - gen_gvec_sli(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { /* VSHL */ - tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; } if (size == 3) { -- 2.20.1 Convert the VSHR 2-reg-shift insns to decodetree. Note that unlike the legacy decoder, we present the right shift amount to the trans_ function as a positive integer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-3-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 25 ++++++++++++++++++++ target/arm/translate-neon.inc.c | 41 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 21 +---------------- 3 files changed, 67 insertions(+), 20 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp ###################################################################### &2reg_shift vm vd q shift size +# Right shifts are encoded as N - shift, where N is the element size in bits. +%neon_rshift_i6 16:6 !function=rsub_64 +%neon_rshift_i5 16:5 !function=rsub_32 +%neon_rshift_i4 16:4 !function=rsub_16 +%neon_rshift_i3 16:3 !function=rsub_8 + +@2reg_shr_d .... ... . . . ...... .... .... 1 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=3 shift=%neon_rshift_i6 +@2reg_shr_s .... ... . . . 1 ..... .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 shift=%neon_rshift_i5 +@2reg_shr_h .... ... . . . 01 .... .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 +@2reg_shr_b .... ... . . . 001 ... .... .... 0 q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i3 + @2reg_shl_d .... ... . . . shift:6 .... .... 1 q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=3 @2reg_shl_s .... ... . . . 1 shift:5 .... .... 0 q:1 . . .... \ @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h +VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b + +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h +VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b + VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static inline int plus1(DisasContext *s, int x) return x + 1; } +static inline int rsub_64(DisasContext *s, int x) +{ + return 64 - x; +} + +static inline int rsub_32(DisasContext *s, int x) +{ + return 32 - x; +} +static inline int rsub_16(DisasContext *s, int x) +{ + return 16 - x; +} +static inline int rsub_8(DisasContext *s, int x) +{ + return 8 - x; +} + /* Include the generated Neon decoder */ #include "decode-neon-dp.inc.c" #include "decode-neon-ls.inc.c" @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) DO_2SH(VSHL, tcg_gen_gvec_shli) DO_2SH(VSLI, gen_gvec_sli) + +static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a) +{ + /* Signed shift out of range results in all-sign-bits */ + a->shift = MIN(a->shift, (8 << a->size) - 1); + return do_vector_2sh(s, a, tcg_gen_gvec_sari); +} + +static void gen_zero_rd_2sh(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_dup_imm(vece, rd_ofs, oprsz, maxsz, 0); +} + +static bool trans_VSHR_U_2sh(DisasContext *s, arg_2reg_shift *a) +{ + /* Shift out of range is architecturally valid and results in zero. */ + if (a->shift >= (8 << a->size)) { + return do_vector_2sh(s, a, gen_zero_rd_2sh); + } else { + return do_vector_2sh(s, a, tcg_gen_gvec_shri); + } +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) op = (insn >> 8) & 0xf; switch (op) { + case 0: /* VSHR */ case 5: /* VSHL, VSLI */ return 1; /* handled by decodetree */ default: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } switch (op) { - case 0: /* VSHR */ - /* Right shift comes here negative. */ - shift = -shift; - /* Shifts larger than the element size are architecturally - * valid. Unsigned results in all zeros; signed results - * in all sign bits. - */ - if (!u) { - tcg_gen_gvec_sari(size, rd_ofs, rm_ofs, - MIN(shift, (8 << size) - 1), - vec_size, vec_size); - } else if (shift >= 8 << size) { - tcg_gen_gvec_dup_imm(MO_8, rd_ofs, vec_size, - vec_size, 0); - } else { - tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - case 1: /* VSRA */ /* Right shift comes here negative. */ shift = -shift; -- 2.20.1 Convert the VSRA, VSRI, VRSHR, VRSRA 2-reg-shift insns to decodetree. (These are the last instructions in the group that are vectorized; the rest all require looping over each element.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-4-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 35 ++++++++++++++++++++++ target/arm/translate-neon.inc.c | 7 +++++ target/arm/translate.c | 52 +++------------------------------ 3 files changed, 46 insertions(+), 48 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h VSHR_U_2sh 1111 001 1 1 . ...... .... 0000 . . . 1 .... @2reg_shr_b +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_d +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_s +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_h +VSRA_S_2sh 1111 001 0 1 . ...... .... 0001 . . . 1 .... @2reg_shr_b + +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_d +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_s +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_h +VSRA_U_2sh 1111 001 1 1 . ...... .... 0001 . . . 1 .... @2reg_shr_b + +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_d +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_s +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_h +VRSHR_S_2sh 1111 001 0 1 . ...... .... 0010 . . . 1 .... @2reg_shr_b + +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_d +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_s +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_h +VRSHR_U_2sh 1111 001 1 1 . ...... .... 0010 . . . 1 .... @2reg_shr_b + +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_d +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_s +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_h +VRSRA_S_2sh 1111 001 0 1 . ...... .... 0011 . . . 1 .... @2reg_shr_b + +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_d +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_s +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_h +VRSRA_U_2sh 1111 001 1 1 . ...... .... 0011 . . . 1 .... @2reg_shr_b + +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_d +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_s +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_h +VSRI_2sh 1111 001 1 1 . ...... .... 0100 . . . 1 .... @2reg_shr_b + VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s VSHL_2sh 1111 001 0 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) DO_2SH(VSHL, tcg_gen_gvec_shli) DO_2SH(VSLI, gen_gvec_sli) +DO_2SH(VSRI, gen_gvec_sri) +DO_2SH(VSRA_S, gen_gvec_ssra) +DO_2SH(VSRA_U, gen_gvec_usra) +DO_2SH(VRSHR_S, gen_gvec_srshr) +DO_2SH(VRSHR_U, gen_gvec_urshr) +DO_2SH(VRSRA_S, gen_gvec_srsra) +DO_2SH(VRSRA_U, gen_gvec_ursra) static bool trans_VSHR_S_2sh(DisasContext *s, arg_2reg_shift *a) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) switch (op) { case 0: /* VSHR */ + case 1: /* VSRA */ + case 2: /* VRSHR */ + case 3: /* VRSRA */ + case 4: /* VSRI */ case 5: /* VSHL, VSLI */ return 1; /* handled by decodetree */ default: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) shift = shift - (1 << (size + 3)); } - switch (op) { - case 1: /* VSRA */ - /* Right shift comes here negative. */ - shift = -shift; - if (u) { - gen_gvec_usra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { - gen_gvec_ssra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - - case 2: /* VRSHR */ - /* Right shift comes here negative. */ - shift = -shift; - if (u) { - gen_gvec_urshr(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { - gen_gvec_srshr(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - - case 3: /* VRSRA */ - /* Right shift comes here negative. */ - shift = -shift; - if (u) { - gen_gvec_ursra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } else { - gen_gvec_srsra(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } - return 0; - - case 4: /* VSRI */ - if (!u) { - return 1; - } - /* Right shift comes here negative. */ - shift = -shift; - gen_gvec_sri(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - return 0; - } - if (size == 3) { count = q + 1; } else { -- 2.20.1 Convert the VQSHLU and QVSHL 2-reg-shift insns to decodetree. These are the last of the simple shift-by-immediate insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-5-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 15 +++++ target/arm/translate-neon.inc.c | 108 +++++++++++++++++++++++++++++++ target/arm/translate.c | 110 +------------------------------- 3 files changed, 126 insertions(+), 107 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_d VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_s VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_h VSLI_2sh 1111 001 1 1 . ...... .... 0101 . . . 1 .... @2reg_shl_b + +VQSHLU_64_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_d +VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_s +VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_h +VQSHLU_2sh 1111 001 1 1 . ...... .... 0110 . . . 1 .... @2reg_shl_b + +VQSHL_S_64_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d +VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s +VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h +VQSHL_S_2sh 1111 001 0 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b + +VQSHL_U_64_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d +VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s +VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h +VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSHR_U_2sh(DisasContext *s, arg_2reg_shift *a) return do_vector_2sh(s, a, tcg_gen_gvec_shri); } } + +static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, + NeonGenTwo64OpEnvFn *fn) +{ + /* + * 2-reg-and-shift operations, size == 3 case, where the + * function needs to be passed cpu_env. + */ + TCGv_i64 constimm; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * To avoid excessive duplication of ops we implement shift + * by immediate using the variable shift operations. + */ + constimm = tcg_const_i64(dup_const(a->size, a->shift)); + + for (pass = 0; pass < a->q + 1; pass++) { + TCGv_i64 tmp = tcg_temp_new_i64(); + + neon_load_reg64(tmp, a->vm + pass); + fn(tmp, cpu_env, tmp, constimm); + neon_store_reg64(tmp, a->vd + pass); + } + tcg_temp_free_i64(constimm); + return true; +} + +static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, + NeonGenTwoOpEnvFn *fn) +{ + /* + * 2-reg-and-shift operations, size < 3 case, where the + * helper needs to be passed cpu_env. + */ + TCGv_i32 constimm; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * To avoid excessive duplication of ops we implement shift + * by immediate using the variable shift operations. + */ + constimm = tcg_const_i32(dup_const(a->size, a->shift)); + + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + fn(tmp, cpu_env, tmp, constimm); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_i32(constimm); + return true; +} + +#define DO_2SHIFT_ENV(INSN, FUNC) \ + static bool trans_##INSN##_64_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_2shift_env_64(s, a, gen_helper_neon_##FUNC##64); \ + } \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + static NeonGenTwoOpEnvFn * const fns[] = { \ + gen_helper_neon_##FUNC##8, \ + gen_helper_neon_##FUNC##16, \ + gen_helper_neon_##FUNC##32, \ + }; \ + assert(a->size < ARRAY_SIZE(fns)); \ + return do_2shift_env_32(s, a, fns[a->size]); \ + } + +DO_2SHIFT_ENV(VQSHLU, qshlu_s) +DO_2SHIFT_ENV(VQSHL_U, qshl_u) +DO_2SHIFT_ENV(VQSHL_S, qshl_s) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_neon_rsb(int size, TCGv_i32 t0, TCGv_i32 t1) } } -#define GEN_NEON_INTEGER_OP_ENV(name) do { \ - switch ((size << 1) | u) { \ - case 0: \ - gen_helper_neon_##name##_s8(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 1: \ - gen_helper_neon_##name##_u8(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 2: \ - gen_helper_neon_##name##_s16(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 3: \ - gen_helper_neon_##name##_u16(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 4: \ - gen_helper_neon_##name##_s32(tmp, cpu_env, tmp, tmp2); \ - break; \ - case 5: \ - gen_helper_neon_##name##_u32(tmp, cpu_env, tmp, tmp2); \ - break; \ - default: return 1; \ - }} while (0) - static TCGv_i32 neon_load_scratch(int scratch) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int size; int shift; int pass; - int count; int u; int vec_size; uint32_t imm; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 3: /* VRSRA */ case 4: /* VSRI */ case 5: /* VSHL, VSLI */ + case 6: /* VQSHLU */ + case 7: /* VQSHL */ return 1; /* handled by decodetree */ default: break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op < 8) { - /* Shift by immediate: - VSHR, VSRA, VRSHR, VRSRA, VSRI, VSHL, VQSHL, VQSHLU. */ - if (q && ((rd | rm) & 1)) { - return 1; - } - if (!u && (op == 4 || op == 6)) { - return 1; - } - /* Right shifts are encoded as N - shift, where N is the - element size in bits. */ - if (op <= 4) { - shift = shift - (1 << (size + 3)); - } - - if (size == 3) { - count = q + 1; - } else { - count = q ? 4: 2; - } - - /* To avoid excessive duplication of ops we implement shift - * by immediate using the variable shift operations. - */ - imm = dup_const(size, shift); - - for (pass = 0; pass < count; pass++) { - if (size == 3) { - neon_load_reg64(cpu_V0, rm + pass); - tcg_gen_movi_i64(cpu_V1, imm); - switch (op) { - case 6: /* VQSHLU */ - gen_helper_neon_qshlu_s64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - break; - case 7: /* VQSHL */ - if (u) { - gen_helper_neon_qshl_u64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } else { - gen_helper_neon_qshl_s64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } - break; - default: - g_assert_not_reached(); - } - neon_store_reg64(cpu_V0, rd + pass); - } else { /* size < 3 */ - /* Operands in T0 and T1. */ - tmp = neon_load_reg(rm, pass); - tmp2 = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp2, imm); - switch (op) { - case 6: /* VQSHLU */ - switch (size) { - case 0: - gen_helper_neon_qshlu_s8(tmp, cpu_env, - tmp, tmp2); - break; - case 1: - gen_helper_neon_qshlu_s16(tmp, cpu_env, - tmp, tmp2); - break; - case 2: - gen_helper_neon_qshlu_s32(tmp, cpu_env, - tmp, tmp2); - break; - default: - abort(); - } - break; - case 7: /* VQSHL */ - GEN_NEON_INTEGER_OP_ENV(qshl); - break; - default: - g_assert_not_reached(); - } - tcg_temp_free_i32(tmp2); - neon_store_reg(rd, pass, tmp); - } - } /* for pass */ - } else if (op < 10) { + if (op < 10) { /* Shift by immediate and narrow: VSHRN, VRSHRN, VQSHRN, VQRSHRN. */ int input_unsigned = (op == 8) ? !u : u; -- 2.20.1 Convert the Neon narrowing shifts where op==8 to decodetree: * VSHRN * VRSHRN * VQSHRUN * VQRSHRUN Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-6-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 27 ++++++ target/arm/translate-neon.inc.c | 167 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 1 + 3 files changed, 195 insertions(+) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shl_b .... ... . . . 001 shift:3 .... .... 0 q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 +# Narrowing right shifts: here the Q bit is part of the opcode decode +@2reg_shrn_d .... ... . . . 1 ..... .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=3 q=0 \ + shift=%neon_rshift_i5 +@2reg_shrn_s .... ... . . . 01 .... .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 q=0 \ + shift=%neon_rshift_i4 +@2reg_shrn_h .... ... . . . 001 ... .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 \ + shift=%neon_rshift_i3 + VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h @@ -XXX,XX +XXX,XX @@ VQSHL_U_64_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_d VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_s VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_h VQSHL_U_2sh 1111 001 1 1 . ...... .... 0111 . . . 1 .... @2reg_shl_b + +VSHRN_64_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_d +VSHRN_32_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_s +VSHRN_16_2sh 1111 001 0 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h + +VRSHRN_64_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d +VRSHRN_32_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s +VRSHRN_16_2sh 1111 001 0 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h + +VQSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_d +VQSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_s +VQSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h + +VQRSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d +VQRSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s +VQRSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, DO_2SHIFT_ENV(VQSHLU, qshlu_s) DO_2SHIFT_ENV(VQSHL_U, qshl_u) DO_2SHIFT_ENV(VQSHL_S, qshl_s) + +static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, + NeonGenTwo64OpFn *shiftfn, + NeonGenNarrowEnvFn *narrowfn) +{ + /* 2-reg-and-shift narrowing-shift operations, size == 3 case */ + TCGv_i64 constimm, rm1, rm2; + TCGv_i32 rd; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vm & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * This is always a right shift, and the shiftfn is always a + * left-shift helper, which thus needs the negated shift count. + */ + constimm = tcg_const_i64(-a->shift); + rm1 = tcg_temp_new_i64(); + rm2 = tcg_temp_new_i64(); + + /* Load both inputs first to avoid potential overwrite if rm == rd */ + neon_load_reg64(rm1, a->vm); + neon_load_reg64(rm2, a->vm + 1); + + shiftfn(rm1, rm1, constimm); + rd = tcg_temp_new_i32(); + narrowfn(rd, cpu_env, rm1); + neon_store_reg(a->vd, 0, rd); + + shiftfn(rm2, rm2, constimm); + rd = tcg_temp_new_i32(); + narrowfn(rd, cpu_env, rm2); + neon_store_reg(a->vd, 1, rd); + + tcg_temp_free_i64(rm1); + tcg_temp_free_i64(rm2); + tcg_temp_free_i64(constimm); + + return true; +} + +static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, + NeonGenTwoOpFn *shiftfn, + NeonGenNarrowEnvFn *narrowfn) +{ + /* 2-reg-and-shift narrowing-shift operations, size < 3 case */ + TCGv_i32 constimm, rm1, rm2, rm3, rm4; + TCGv_i64 rtmp; + uint32_t imm; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vm & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * This is always a right shift, and the shiftfn is always a + * left-shift helper, which thus needs the negated shift count + * duplicated into each lane of the immediate value. + */ + if (a->size == 1) { + imm = (uint16_t)(-a->shift); + imm |= imm << 16; + } else { + /* size == 2 */ + imm = -a->shift; + } + constimm = tcg_const_i32(imm); + + /* Load all inputs first to avoid potential overwrite */ + rm1 = neon_load_reg(a->vm, 0); + rm2 = neon_load_reg(a->vm, 1); + rm3 = neon_load_reg(a->vm + 1, 0); + rm4 = neon_load_reg(a->vm + 1, 1); + rtmp = tcg_temp_new_i64(); + + shiftfn(rm1, rm1, constimm); + shiftfn(rm2, rm2, constimm); + + tcg_gen_concat_i32_i64(rtmp, rm1, rm2); + tcg_temp_free_i32(rm2); + + narrowfn(rm1, cpu_env, rtmp); + neon_store_reg(a->vd, 0, rm1); + + shiftfn(rm3, rm3, constimm); + shiftfn(rm4, rm4, constimm); + tcg_temp_free_i32(constimm); + + tcg_gen_concat_i32_i64(rtmp, rm3, rm4); + tcg_temp_free_i32(rm4); + + narrowfn(rm3, cpu_env, rtmp); + tcg_temp_free_i64(rtmp); + neon_store_reg(a->vd, 1, rm3); + return true; +} + +#define DO_2SN_64(INSN, FUNC, NARROWFUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_2shift_narrow_64(s, a, FUNC, NARROWFUNC); \ + } +#define DO_2SN_32(INSN, FUNC, NARROWFUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_2shift_narrow_32(s, a, FUNC, NARROWFUNC); \ + } + +static void gen_neon_narrow_u32(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src) +{ + tcg_gen_extrl_i64_i32(dest, src); +} + +static void gen_neon_narrow_u16(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src) +{ + gen_helper_neon_narrow_u16(dest, src); +} + +static void gen_neon_narrow_u8(TCGv_i32 dest, TCGv_ptr env, TCGv_i64 src) +{ + gen_helper_neon_narrow_u8(dest, src); +} + +DO_2SN_64(VSHRN_64, gen_ushl_i64, gen_neon_narrow_u32) +DO_2SN_32(VSHRN_32, gen_ushl_i32, gen_neon_narrow_u16) +DO_2SN_32(VSHRN_16, gen_helper_neon_shl_u16, gen_neon_narrow_u8) + +DO_2SN_64(VRSHRN_64, gen_helper_neon_rshl_u64, gen_neon_narrow_u32) +DO_2SN_32(VRSHRN_32, gen_helper_neon_rshl_u32, gen_neon_narrow_u16) +DO_2SN_32(VRSHRN_16, gen_helper_neon_rshl_u16, gen_neon_narrow_u8) + +DO_2SN_64(VQSHRUN_64, gen_sshl_i64, gen_helper_neon_unarrow_sat32) +DO_2SN_32(VQSHRUN_32, gen_sshl_i32, gen_helper_neon_unarrow_sat16) +DO_2SN_32(VQSHRUN_16, gen_helper_neon_shl_s16, gen_helper_neon_unarrow_sat8) + +DO_2SN_64(VQRSHRUN_64, gen_helper_neon_rshl_s64, gen_helper_neon_unarrow_sat32) +DO_2SN_32(VQRSHRUN_32, gen_helper_neon_rshl_s32, gen_helper_neon_unarrow_sat16) +DO_2SN_32(VQRSHRUN_16, gen_helper_neon_rshl_s16, gen_helper_neon_unarrow_sat8) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 5: /* VSHL, VSLI */ case 6: /* VQSHLU */ case 7: /* VQSHL */ + case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ return 1; /* handled by decodetree */ default: break; -- 2.20.1 Convert the remaining Neon narrowing shifts to decodetree: * VQSHRN * VQRSHRN Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-7-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 20 ++++++ target/arm/translate-neon.inc.c | 15 +++++ target/arm/translate.c | 110 +------------------------------- 3 files changed, 37 insertions(+), 108 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VQSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 0 . 1 .... @2reg_shrn_h VQRSHRUN_64_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_d VQRSHRUN_32_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_s VQRSHRUN_16_2sh 1111 001 1 1 . ...... .... 1000 . 1 . 1 .... @2reg_shrn_h + +# VQSHRN with signed input +VQSHRN_S64_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_d +VQSHRN_S32_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_s +VQSHRN_S16_2sh 1111 001 0 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h + +# VQRSHRN with signed input +VQRSHRN_S64_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d +VQRSHRN_S32_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s +VQRSHRN_S16_2sh 1111 001 0 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h + +# VQSHRN with unsigned input +VQSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_d +VQSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_s +VQSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h + +# VQRSHRN with unsigned input +VQRSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d +VQRSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s +VQRSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_2SN_32(VQSHRUN_16, gen_helper_neon_shl_s16, gen_helper_neon_unarrow_sat8) DO_2SN_64(VQRSHRUN_64, gen_helper_neon_rshl_s64, gen_helper_neon_unarrow_sat32) DO_2SN_32(VQRSHRUN_32, gen_helper_neon_rshl_s32, gen_helper_neon_unarrow_sat16) DO_2SN_32(VQRSHRUN_16, gen_helper_neon_rshl_s16, gen_helper_neon_unarrow_sat8) +DO_2SN_64(VQSHRN_S64, gen_sshl_i64, gen_helper_neon_narrow_sat_s32) +DO_2SN_32(VQSHRN_S32, gen_sshl_i32, gen_helper_neon_narrow_sat_s16) +DO_2SN_32(VQSHRN_S16, gen_helper_neon_shl_s16, gen_helper_neon_narrow_sat_s8) + +DO_2SN_64(VQRSHRN_S64, gen_helper_neon_rshl_s64, gen_helper_neon_narrow_sat_s32) +DO_2SN_32(VQRSHRN_S32, gen_helper_neon_rshl_s32, gen_helper_neon_narrow_sat_s16) +DO_2SN_32(VQRSHRN_S16, gen_helper_neon_rshl_s16, gen_helper_neon_narrow_sat_s8) + +DO_2SN_64(VQSHRN_U64, gen_ushl_i64, gen_helper_neon_narrow_sat_u32) +DO_2SN_32(VQSHRN_U32, gen_ushl_i32, gen_helper_neon_narrow_sat_u16) +DO_2SN_32(VQSHRN_U16, gen_helper_neon_shl_u16, gen_helper_neon_narrow_sat_u8) + +DO_2SN_64(VQRSHRN_U64, gen_helper_neon_rshl_u64, gen_helper_neon_narrow_sat_u32) +DO_2SN_32(VQRSHRN_U32, gen_helper_neon_rshl_u32, gen_helper_neon_narrow_sat_u16) +DO_2SN_32(VQRSHRN_U16, gen_helper_neon_rshl_u16, gen_helper_neon_narrow_sat_u8) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src) } } -static inline void gen_neon_shift_narrow(int size, TCGv_i32 var, TCGv_i32 shift, - int q, int u) -{ - if (q) { - if (u) { - switch (size) { - case 1: gen_helper_neon_rshl_u16(var, var, shift); break; - case 2: gen_helper_neon_rshl_u32(var, var, shift); break; - default: abort(); - } - } else { - switch (size) { - case 1: gen_helper_neon_rshl_s16(var, var, shift); break; - case 2: gen_helper_neon_rshl_s32(var, var, shift); break; - default: abort(); - } - } - } else { - if (u) { - switch (size) { - case 1: gen_helper_neon_shl_u16(var, var, shift); break; - case 2: gen_ushl_i32(var, var, shift); break; - default: abort(); - } - } else { - switch (size) { - case 1: gen_helper_neon_shl_s16(var, var, shift); break; - case 2: gen_sshl_i32(var, var, shift); break; - default: abort(); - } - } - } -} - static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u) { if (u) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 6: /* VQSHLU */ case 7: /* VQSHL */ case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ + case 9: /* VQSHRN, VQRSHRN */ return 1; /* handled by decodetree */ default: break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op < 10) { - /* Shift by immediate and narrow: - VSHRN, VRSHRN, VQSHRN, VQRSHRN. */ - int input_unsigned = (op == 8) ? !u : u; - if (rm & 1) { - return 1; - } - shift = shift - (1 << (size + 3)); - size++; - if (size == 3) { - tmp64 = tcg_const_i64(shift); - neon_load_reg64(cpu_V0, rm); - neon_load_reg64(cpu_V1, rm + 1); - for (pass = 0; pass < 2; pass++) { - TCGv_i64 in; - if (pass == 0) { - in = cpu_V0; - } else { - in = cpu_V1; - } - if (q) { - if (input_unsigned) { - gen_helper_neon_rshl_u64(cpu_V0, in, tmp64); - } else { - gen_helper_neon_rshl_s64(cpu_V0, in, tmp64); - } - } else { - if (input_unsigned) { - gen_ushl_i64(cpu_V0, in, tmp64); - } else { - gen_sshl_i64(cpu_V0, in, tmp64); - } - } - tmp = tcg_temp_new_i32(); - gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); - neon_store_reg(rd, pass, tmp); - } /* for pass */ - tcg_temp_free_i64(tmp64); - } else { - if (size == 1) { - imm = (uint16_t)shift; - imm |= imm << 16; - } else { - /* size == 2 */ - imm = (uint32_t)shift; - } - tmp2 = tcg_const_i32(imm); - tmp4 = neon_load_reg(rm + 1, 0); - tmp5 = neon_load_reg(rm + 1, 1); - for (pass = 0; pass < 2; pass++) { - if (pass == 0) { - tmp = neon_load_reg(rm, 0); - } else { - tmp = tmp4; - } - gen_neon_shift_narrow(size, tmp, tmp2, q, - input_unsigned); - if (pass == 0) { - tmp3 = neon_load_reg(rm, 1); - } else { - tmp3 = tmp5; - } - gen_neon_shift_narrow(size, tmp3, tmp2, q, - input_unsigned); - tcg_gen_concat_i32_i64(cpu_V0, tmp, tmp3); - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(tmp3); - tmp = tcg_temp_new_i32(); - gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0); - neon_store_reg(rd, pass, tmp); - } /* for pass */ - tcg_temp_free_i32(tmp2); - } - } else if (op == 10) { + if (op == 10) { /* VSHLL, VMOVL */ if (q || (rd & 1)) { return 1; -- 2.20.1 Convert the VSHLL and VMOVL insns from the 2-reg-shift group to decodetree. Since the loop always has two passes, we unroll it to avoid the awkward reassignment of one TCGv to another. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-8-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 16 +++++++ target/arm/translate-neon.inc.c | 81 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 46 +------------------ 3 files changed, 99 insertions(+), 44 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp &2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 \ shift=%neon_rshift_i3 +# Long left shifts: again Q is part of opcode decode +@2reg_shll_s .... ... . . . 1 shift:5 .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 q=0 +@2reg_shll_h .... ... . . . 01 shift:4 .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 q=0 +@2reg_shll_b .... ... . . . 001 shift:3 .... .... 0 . . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0 + VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h @@ -XXX,XX +XXX,XX @@ VQSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 0 . 1 .... @2reg_shrn_h VQRSHRN_U64_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_d VQRSHRN_U32_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_s VQRSHRN_U16_2sh 1111 001 1 1 . ...... .... 1001 . 1 . 1 .... @2reg_shrn_h + +VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s +VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h +VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b + +VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s +VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h +VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_2SN_32(VQSHRN_U16, gen_helper_neon_shl_u16, gen_helper_neon_narrow_sat_u8) DO_2SN_64(VQRSHRN_U64, gen_helper_neon_rshl_u64, gen_helper_neon_narrow_sat_u32) DO_2SN_32(VQRSHRN_U32, gen_helper_neon_rshl_u32, gen_helper_neon_narrow_sat_u16) DO_2SN_32(VQRSHRN_U16, gen_helper_neon_rshl_u16, gen_helper_neon_narrow_sat_u8) + +static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, + NeonGenWidenFn *widenfn, bool u) +{ + TCGv_i64 tmp; + TCGv_i32 rm0, rm1; + uint64_t widen_mask = 0; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if (a->vd & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * This is a widen-and-shift operation. The shift is always less + * than the width of the source type, so after widening the input + * vector we can simply shift the whole 64-bit widened register, + * and then clear the potential overflow bits resulting from left + * bits of the narrow input appearing as right bits of the left + * neighbour narrow input. Calculate a mask of bits to clear. + */ + if ((a->shift != 0) && (a->size < 2 || u)) { + int esize = 8 << a->size; + widen_mask = MAKE_64BIT_MASK(0, esize); + widen_mask >>= esize - a->shift; + widen_mask = dup_const(a->size + 1, widen_mask); + } + + rm0 = neon_load_reg(a->vm, 0); + rm1 = neon_load_reg(a->vm, 1); + tmp = tcg_temp_new_i64(); + + widenfn(tmp, rm0); + if (a->shift != 0) { + tcg_gen_shli_i64(tmp, tmp, a->shift); + tcg_gen_andi_i64(tmp, tmp, ~widen_mask); + } + neon_store_reg64(tmp, a->vd); + + widenfn(tmp, rm1); + if (a->shift != 0) { + tcg_gen_shli_i64(tmp, tmp, a->shift); + tcg_gen_andi_i64(tmp, tmp, ~widen_mask); + } + neon_store_reg64(tmp, a->vd + 1); + tcg_temp_free_i64(tmp); + return true; +} + +static bool trans_VSHLL_S_2sh(DisasContext *s, arg_2reg_shift *a) +{ + NeonGenWidenFn *widenfn[] = { + gen_helper_neon_widen_s8, + gen_helper_neon_widen_s16, + tcg_gen_ext_i32_i64, + }; + return do_vshll_2sh(s, a, widenfn[a->size], false); +} + +static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) +{ + NeonGenWidenFn *widenfn[] = { + gen_helper_neon_widen_u8, + gen_helper_neon_widen_u16, + tcg_gen_extu_i32_i64, + }; + return do_vshll_2sh(s, a, widenfn[a->size], true); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 7: /* VQSHL */ case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ case 9: /* VQSHRN, VQRSHRN */ + case 10: /* VSHLL, including VMOVL */ return 1; /* handled by decodetree */ default: break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op == 10) { - /* VSHLL, VMOVL */ - if (q || (rd & 1)) { - return 1; - } - tmp = neon_load_reg(rm, 0); - tmp2 = neon_load_reg(rm, 1); - for (pass = 0; pass < 2; pass++) { - if (pass == 1) - tmp = tmp2; - - gen_neon_widen(cpu_V0, tmp, size, u); - - if (shift != 0) { - /* The shift is less than the width of the source - type, so we can just shift the whole register. */ - tcg_gen_shli_i64(cpu_V0, cpu_V0, shift); - /* Widen the result of shift: we need to clear - * the potential overflow bits resulting from - * left bits of the narrow input appearing as - * right bits of left the neighbour narrow - * input. */ - if (size < 2 || !u) { - uint64_t imm64; - if (size == 0) { - imm = (0xffu >> (8 - shift)); - imm |= imm << 16; - } else if (size == 1) { - imm = 0xffff >> (16 - shift); - } else { - /* size == 2 */ - imm = 0xffffffff >> (32 - shift); - } - if (size < 2) { - imm64 = imm | (((uint64_t)imm) << 32); - } else { - imm64 = imm; - } - tcg_gen_andi_i64(cpu_V0, cpu_V0, ~imm64); - } - } - neon_store_reg64(cpu_V0, rd + pass); - } - } else if (op >= 14) { + if (op >= 14) { /* VCVT fixed-point. */ TCGv_ptr fpst; TCGv_i32 shiftv; -- 2.20.1 Convert the VCVT fixed-point conversion operations in the Neon 2-regs-and-shift group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-9-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 11 +++++ target/arm/translate-neon.inc.c | 49 +++++++++++++++++++++ target/arm/translate.c | 75 +-------------------------------- 3 files changed, 62 insertions(+), 73 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shll_b .... ... . . . 001 shift:3 .... .... 0 . . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0 +# We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings. +@2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5 + VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h @@ -XXX,XX +XXX,XX @@ VSHLL_S_2sh 1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b + +# VCVT fixed<->float conversions +# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101 +VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt +VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt +VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt +VCVT_FU_2sh 1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) }; return do_vshll_2sh(s, a, widenfn[a->size], true); } + +static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, + NeonGenTwoSingleOPFn *fn) +{ + /* FP operations in 2-reg-and-shift group */ + TCGv_i32 tmp, shiftv; + TCGv_ptr fpstatus; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpstatus = get_fpstatus_ptr(1); + shiftv = tcg_const_i32(a->shift); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + tmp = neon_load_reg(a->vm, pass); + fn(tmp, tmp, shiftv, fpstatus); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_ptr(fpstatus); + tcg_temp_free_i32(shiftv); + return true; +} + +#define DO_FP_2SH(INSN, FUNC) \ + static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a) \ + { \ + return do_fp_2sh(s, a, FUNC); \ + } + +DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos) +DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos) +DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero) +DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int q; int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs; int size; - int shift; int pass; int u; int vec_size; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } else if (insn & (1 << 4)) { if ((insn & 0x00380080) != 0) { - /* Two registers and shift. */ - op = (insn >> 8) & 0xf; - - switch (op) { - case 0: /* VSHR */ - case 1: /* VSRA */ - case 2: /* VRSHR */ - case 3: /* VRSRA */ - case 4: /* VSRI */ - case 5: /* VSHL, VSLI */ - case 6: /* VQSHLU */ - case 7: /* VQSHL */ - case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */ - case 9: /* VQSHRN, VQRSHRN */ - case 10: /* VSHLL, including VMOVL */ - return 1; /* handled by decodetree */ - default: - break; - } - - if (insn & (1 << 7)) { - /* 64-bit shift. */ - if (op > 7) { - return 1; - } - size = 3; - } else { - size = 2; - while ((insn & (1 << (size + 19))) == 0) - size--; - } - shift = (insn >> 16) & ((1 << (3 + size)) - 1); - if (op >= 14) { - /* VCVT fixed-point. */ - TCGv_ptr fpst; - TCGv_i32 shiftv; - VFPGenFixPointFn *fn; - - if (!(insn & (1 << 21)) || (q && ((rd | rm) & 1))) { - return 1; - } - - if (!(op & 1)) { - if (u) { - fn = gen_helper_vfp_ultos; - } else { - fn = gen_helper_vfp_sltos; - } - } else { - if (u) { - fn = gen_helper_vfp_touls_round_to_zero; - } else { - fn = gen_helper_vfp_tosls_round_to_zero; - } - } - - /* We have already masked out the must-be-1 top bit of imm6, - * hence this 32-shift where the ARM ARM has 64-imm6. - */ - shift = 32 - shift; - fpst = get_fpstatus_ptr(1); - shiftv = tcg_const_i32(shift); - for (pass = 0; pass < (q ? 4 : 2); pass++) { - TCGv_i32 tmpf = neon_load_reg(rm, pass); - fn(tmpf, tmpf, shiftv, fpst); - neon_store_reg(rd, pass, tmpf); - } - tcg_temp_free_ptr(fpst); - tcg_temp_free_i32(shiftv); - } else { - return 1; - } + /* Two registers and shift: handled by decodetree */ + return 1; } else { /* (insn & 0x00380080) == 0 */ int invert, reg_ofs, vec_size; -- 2.20.1 Convert the insns in the one-register-and-immediate group to decodetree. In the new decode, our asimd_imm_const() function returns a 64-bit value rather than a 32-bit one, which means we don't need to treat cmode=14 op=1 as a special case in the decoder (it is the only encoding where the two halves of the 64-bit value are different). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200522145520.6778-10-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 22 ++++++ target/arm/translate-neon.inc.c | 118 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 101 +-------------------------- 3 files changed, 142 insertions(+), 99 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt VCVT_FU_2sh 1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt + +###################################################################### +# 1-reg-and-modified-immediate grouping: +# 1111 001 i 1 D 000 imm:3 Vd:4 cmode:4 0 Q op 1 Vm:4 +###################################################################### + +&1reg_imm vd q imm cmode op + +%asimd_imm_value 24:1 16:3 0:4 + +@1reg_imm .... ... . . . ... ... .... .... . q:1 . . .... \ + &1reg_imm imm=%asimd_imm_value vd=%vd_dp + +# The cmode/op bits here decode VORR/VBIC/VMOV/VMNV, but +# not in a way we can conveniently represent in decodetree without +# a lot of repetition: +# VORR: op=0, (cmode & 1) && cmode < 12 +# VBIC: op=1, (cmode & 1) && cmode < 12 +# VMOV: everything else +# So we have a single decode line and check the cmode/op in the +# trans function. +Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos) DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos) DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero) DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero) + +static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) +{ + /* + * Expand the encoded constant. + * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. + * We choose to not special-case this and will behave as if a + * valid constant encoding of 0 had been given. + * cmode = 15 op = 1 must UNDEF; we assume decode has handled that. + */ + switch (cmode) { + case 0: case 1: + /* no-op */ + break; + case 2: case 3: + imm <<= 8; + break; + case 4: case 5: + imm <<= 16; + break; + case 6: case 7: + imm <<= 24; + break; + case 8: case 9: + imm |= imm << 16; + break; + case 10: case 11: + imm = (imm << 8) | (imm << 24); + break; + case 12: + imm = (imm << 8) | 0xff; + break; + case 13: + imm = (imm << 16) | 0xffff; + break; + case 14: + if (op) { + /* + * This is the only case where the top and bottom 32 bits + * of the encoded constant differ. + */ + uint64_t imm64 = 0; + int n; + + for (n = 0; n < 8; n++) { + if (imm & (1 << n)) { + imm64 |= (0xffULL << (n * 8)); + } + } + return imm64; + } + imm |= (imm << 8) | (imm << 16) | (imm << 24); + break; + case 15: + imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) + | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); + break; + } + if (op) { + imm = ~imm; + } + return dup_const(MO_32, imm); +} + +static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, + GVecGen2iFn *fn) +{ + uint64_t imm; + int reg_ofs, vec_size; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + return false; + } + + if (a->vd & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + reg_ofs = neon_reg_offset(a->vd, 0); + vec_size = a->q ? 16 : 8; + imm = asimd_imm_const(a->imm, a->cmode, a->op); + + fn(MO_64, reg_ofs, reg_ofs, imm, vec_size, vec_size); + return true; +} + +static void gen_VMOV_1r(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, c); +} + +static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a) +{ + /* Handle decode of cmode/op here between VORR/VBIC/VMOV */ + GVecGen2iFn *fn; + + if ((a->cmode & 1) && a->cmode < 12) { + /* for op=1, the imm will be inverted, so BIC becomes AND. */ + fn = a->op ? tcg_gen_gvec_andi : tcg_gen_gvec_ori; + } else { + /* There is one unallocated cmode/op combination in this space */ + if (a->cmode == 15 && a->op == 1) { + return false; + } + fn = gen_VMOV_1r; + } + return do_1reg_imm(s, a, fn); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* Three register same length: handled by decodetree */ return 1; } else if (insn & (1 << 4)) { - if ((insn & 0x00380080) != 0) { - /* Two registers and shift: handled by decodetree */ - return 1; - } else { /* (insn & 0x00380080) == 0 */ - int invert, reg_ofs, vec_size; - - if (q && (rd & 1)) { - return 1; - } - - op = (insn >> 8) & 0xf; - /* One register and immediate. */ - imm = (u << 7) | ((insn >> 12) & 0x70) | (insn & 0xf); - invert = (insn & (1 << 5)) != 0; - /* Note that op = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. - * We choose to not special-case this and will behave as if a - * valid constant encoding of 0 had been given. - */ - switch (op) { - case 0: case 1: - /* no-op */ - break; - case 2: case 3: - imm <<= 8; - break; - case 4: case 5: - imm <<= 16; - break; - case 6: case 7: - imm <<= 24; - break; - case 8: case 9: - imm |= imm << 16; - break; - case 10: case 11: - imm = (imm << 8) | (imm << 24); - break; - case 12: - imm = (imm << 8) | 0xff; - break; - case 13: - imm = (imm << 16) | 0xffff; - break; - case 14: - imm |= (imm << 8) | (imm << 16) | (imm << 24); - if (invert) { - imm = ~imm; - } - break; - case 15: - if (invert) { - return 1; - } - imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) - | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); - break; - } - if (invert) { - imm = ~imm; - } - - reg_ofs = neon_reg_offset(rd, 0); - vec_size = q ? 16 : 8; - - if (op & 1 && op < 12) { - if (invert) { - /* The immediate value has already been inverted, - * so BIC becomes AND. - */ - tcg_gen_gvec_andi(MO_32, reg_ofs, reg_ofs, imm, - vec_size, vec_size); - } else { - tcg_gen_gvec_ori(MO_32, reg_ofs, reg_ofs, imm, - vec_size, vec_size); - } - } else { - /* VMOV, VMVN. */ - if (op == 14 && invert) { - TCGv_i64 t64 = tcg_temp_new_i64(); - - for (pass = 0; pass <= q; ++pass) { - uint64_t val = 0; - int n; - - for (n = 0; n < 8; n++) { - if (imm & (1 << (n + pass * 8))) { - val |= 0xffull << (n * 8); - } - } - tcg_gen_movi_i64(t64, val); - neon_store_reg64(t64, rd + pass); - } - tcg_temp_free_i64(t64); - } else { - tcg_gen_gvec_dup_imm(MO_32, reg_ofs, vec_size, - vec_size, imm); - } - } - } + /* Two registers and shift or reg and imm: handled by decodetree */ + return 1; } else { /* (insn & 0x00800010 == 0x00800000) */ if (size != 3) { op = (insn >> 8) & 0xf; -- 2.20.1