diff options
Diffstat (limited to 'arch/riscv')
259 files changed, 13260 insertions, 3244 deletions
diff --git a/arch/riscv/Kbuild b/arch/riscv/Kbuild index 2c585f7a0b6e..126fb738fc44 100644 --- a/arch/riscv/Kbuild +++ b/arch/riscv/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += kernel/ mm/ net/ -obj-$(CONFIG_BUILTIN_DTB) += boot/dts/ obj-$(CONFIG_CRYPTO) += crypto/ obj-y += errata/ obj-$(CONFIG_KVM) += kvm/ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 62545946ecf4..36061f4732b7 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -24,6 +24,9 @@ config RISCV select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CRC32 if RISCV_ISA_ZBC + select ARCH_HAS_CRC64 if 64BIT && RISCV_ISA_ZBC + select ARCH_HAS_CRC_T10DIF if RISCV_ISA_ZBC select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEBUG_VM_PGTABLE @@ -32,6 +35,7 @@ config RISCV select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE + select ARCH_HAS_HW_PTE_YOUNG select ARCH_HAS_KCOV select ARCH_HAS_KERNEL_FPU_SUPPORT if 64BIT && FPU select ARCH_HAS_MEMBARRIER_CALLBACKS @@ -39,7 +43,9 @@ config RISCV select ARCH_HAS_MMIOWB select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API + select ARCH_HAS_PREEMPT_LAZY select ARCH_HAS_PREPARE_SYNC_CORE_CMD + select ARCH_HAS_PTDUMP if MMU select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_DIRECT_MAP if MMU @@ -50,7 +56,7 @@ config RISCV select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN - select ARCH_HAS_VDSO_DATA + select ARCH_HAS_VDSO_ARCH_DATA if GENERIC_VDSO_DATA_STORE select ARCH_KEEP_MEMBLOCK if ACPI select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if 64BIT && MMU select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX @@ -59,10 +65,12 @@ config RISCV select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_CFI_CLANG select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU + select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_HUGETLBFS if MMU # LLD >= 14: https://github.com/llvm/llvm-project/issues/50505 select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000 select ARCH_SUPPORTS_LTO_CLANG_THIN if LLD_VERSION >= 140000 + select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS if 64BIT && MMU select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_SUPPORTS_PER_VMA_LOCK if MMU select ARCH_SUPPORTS_RT @@ -82,6 +90,7 @@ config RISCV select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_NO_INSTR select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE + select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU select CLINT_TIMER if RISCV_M_MODE @@ -91,6 +100,7 @@ config RISCV select EDAC_SUPPORT select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE + select FUNCTION_ALIGNMENT_8B if DYNAMIC_FTRACE_WITH_CALL_OPS select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP @@ -107,14 +117,16 @@ config RISCV select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_LIB_DEVMEM_IS_ALLOWED + select GENERIC_PENDING_IRQ if SMP select GENERIC_PCI_IOMAP - select GENERIC_PTDUMP if MMU select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT + select GENERIC_VDSO_DATA_STORE if MMU select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO select HARDIRQS_SW_RESEND select HAS_IOPORT if MMU + select HAVE_ALIGNED_STRUCT_PAGE select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT @@ -133,6 +145,7 @@ config RISCV select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU + select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if 64BIT && MMU select HAVE_ARCH_USERFAULTFD_MINOR if 64BIT && USERFAULTFD select HAVE_ARCH_VMAP_STACK if MMU && 64BIT select HAVE_ASM_MODVERSIONS @@ -140,12 +153,15 @@ config RISCV select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) - select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + select FUNCTION_ALIGNMENT_4B if HAVE_DYNAMIC_FTRACE && RISCV_ISA_C + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG) select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL - select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION + select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FUNCTION_GRAPH_FREGS + select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API @@ -177,7 +193,7 @@ config RISCV select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RETHOOK if !XIP_KERNEL select HAVE_RSEQ - select HAVE_RUST if RUSTC_SUPPORTS_RISCV + select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_STACKPROTECTOR @@ -195,6 +211,7 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_ECAM if (ACPI && PCI) select PCI_MSI if PCI + select RELOCATABLE if !MMU && !PHYS_RAM_BASE_FIXED select RISCV_ALTERNATIVE if !XIP_KERNEL select RISCV_APLIC select RISCV_IMSIC @@ -206,6 +223,7 @@ config RISCV select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT select UACCESS_MEMCPY if !MMU + select VDSO_GETRANDOM if HAVE_GENERIC_VDSO select USER_STACKTRACE_SUPPORT select ZONE_DMA32 if 64BIT @@ -224,6 +242,7 @@ config CLANG_SUPPORTS_DYNAMIC_FTRACE config GCC_SUPPORTS_DYNAMIC_FTRACE def_bool CC_IS_GCC depends on $(cc-option,-fpatchable-function-entry=8) + depends on CC_HAS_MIN_FUNCTION_ALIGNMENT || !RISCV_ISA_C config HAVE_SHADOW_CALL_STACK def_bool $(cc-option,-fsanitize=shadow-call-stack) @@ -282,13 +301,6 @@ config MMU Select if you want MMU-based virtualised addressing space support by paged memory management. If unsure, say 'Y'. -config PAGE_OFFSET - hex - default 0x80000000 if !MMU && RISCV_M_MODE - default 0x80200000 if !MMU - default 0xc0000000 if 32BIT - default 0xff60000000000000 if 64BIT - config KASAN_SHADOW_OFFSET hex depends on KASAN_GENERIC @@ -506,6 +518,39 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. +choice + prompt "RISC-V spinlock type" + default RISCV_COMBO_SPINLOCKS + +config RISCV_TICKET_SPINLOCKS + bool "Using ticket spinlock" + +config RISCV_QUEUED_SPINLOCKS + bool "Using queued spinlock" + depends on SMP && MMU && NONPORTABLE + select ARCH_USE_QUEUED_SPINLOCKS + help + The queued spinlock implementation requires the forward progress + guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or + LR/SC with Ziccrse provide such guarantee. + + Select this if and only if Zabha or Ziccrse is available on your + platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms + without one of those extensions. + + If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks + when supported and otherwise ticket spinlocks. + +config RISCV_COMBO_SPINLOCKS + bool "Using combo spinlock" + depends on SMP && MMU + select ARCH_USE_QUEUED_SPINLOCKS + help + Embed both queued spinlock and ticket lock so that the spinlock + implementation can be chosen at runtime. + +endchoice + config RISCV_ALTERNATIVE bool depends on !XIP_KERNEL @@ -527,18 +572,30 @@ config RISCV_ISA_C help Adds "C" to the ISA subsets that the toolchain is allowed to emit when building Linux, which results in compressed instructions in the - Linux binary. + Linux binary. This option produces a kernel that will not run on + systems that do not support compressed instructions. If you don't know what to do here, say Y. +config RISCV_ISA_SUPM + bool "Supm extension for userspace pointer masking" + depends on 64BIT + default y + help + Add support for pointer masking in userspace (Supm) when the + underlying hardware extension (Smnpm or Ssnpm) is detected at boot. + + If this option is disabled, userspace will be unable to use + the prctl(PR_{SET,GET}_TAGGED_ADDR_CTRL) API. + config RISCV_ISA_SVNAPOT bool "Svnapot extension support for supervisor mode NAPOT pages" depends on 64BIT && MMU depends on RISCV_ALTERNATIVE default y help - Allow kernel to detect the Svnapot ISA-extension dynamically at boot - time and enable its usage. + Enable support for the Svnapot ISA-extension when it is detected + at boot. The Svnapot extension is used to mark contiguous PTEs as a range of contiguous virtual-to-physical translations for a naturally @@ -556,9 +613,8 @@ config RISCV_ISA_SVPBMT depends on RISCV_ALTERNATIVE default y help - Adds support to dynamically detect the presence of the Svpbmt - ISA-extension (Supervisor-mode: page-based memory types) and - enable its usage. + Add support for the Svpbmt ISA-extension (Supervisor-mode: + page-based memory types) in the kernel when it is detected at boot. The memory type for a page contains a combination of attributes that indicate the cacheability, idempotency, and ordering @@ -577,14 +633,15 @@ config TOOLCHAIN_HAS_V depends on AS_HAS_OPTION_ARCH config RISCV_ISA_V - bool "VECTOR extension support" + bool "Vector extension support" depends on TOOLCHAIN_HAS_V depends on FPU select DYNAMIC_SIGFRAME default y help - Say N here if you want to disable all vector related procedure - in the kernel. + Add support for the Vector extension when it is detected at boot. + When this option is disabled, neither the kernel nor userspace may + use vector procedures. If you don't know what to do here, say Y. @@ -614,12 +671,12 @@ config RISCV_ISA_V_PREEMPTIVE default y help Usually, in-kernel SIMD routines are run with preemption disabled. - Functions which envoke long running SIMD thus must yield core's + Functions which invoke long running SIMD thus must yield the core's vector unit to prevent blocking other tasks for too long. - This config allows kernel to run SIMD without explicitly disable - preemption. Enabling this config will result in higher memory - consumption due to the allocation of per-task's kernel Vector context. + This config allows the kernel to run SIMD without explicitly disabling + preemption. Enabling this config will result in higher memory consumption + due to the allocation of per-task's kernel Vector context. config RISCV_ISA_ZAWRS bool "Zawrs extension support for more efficient busy waiting" @@ -632,6 +689,40 @@ config RISCV_ISA_ZAWRS use of these instructions in the kernel when the Zawrs extension is detected at boot. +config TOOLCHAIN_HAS_ZABHA + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zabha) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zabha) + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZABHA + bool "Zabha extension support for atomic byte/halfword operations" + depends on TOOLCHAIN_HAS_ZABHA + depends on RISCV_ALTERNATIVE + default y + help + Enable the use of the Zabha ISA-extension to implement kernel + byte/halfword atomic memory operations when it is detected at boot. + + If you don't know what to do here, say Y. + +config TOOLCHAIN_HAS_ZACAS + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zacas) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zacas) + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZACAS + bool "Zacas extension support for atomic CAS" + depends on TOOLCHAIN_HAS_ZACAS + depends on RISCV_ALTERNATIVE + default y + help + Enable the use of the Zacas ISA-extension to implement kernel atomic + cmpxchg operations when it is detected at boot. + If you don't know what to do here, say Y. config TOOLCHAIN_HAS_ZBB @@ -649,6 +740,14 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb) depends on AS_HAS_OPTION_ARCH +config TOOLCHAIN_HAS_ZBA + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zba) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zba) + depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900 + depends on AS_HAS_OPTION_ARCH + config RISCV_ISA_ZBA bool "Zba extension support for bit manipulation instructions" default y @@ -663,12 +762,12 @@ config RISCV_ISA_ZBA config RISCV_ISA_ZBB bool "Zbb extension support for bit manipulation instructions" - depends on TOOLCHAIN_HAS_ZBB depends on RISCV_ALTERNATIVE default y help - Adds support to dynamically detect the presence of the ZBB - extension (basic bit manipulation) and enable its usage. + Add support for enabling optimisations in the kernel when the + Zbb extension is detected at boot. Some optimisations may + additionally depend on toolchain support for Zbb. The Zbb extension provides instructions to accelerate a number of bit-specific operations (count bit population, sign extending, @@ -699,6 +798,28 @@ config RISCV_ISA_ZBC If you don't know what to do here, say Y. +config TOOLCHAIN_HAS_ZBKB + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbkb) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbkb) + depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900 + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZBKB + bool "Zbkb extension support for bit manipulation instructions" + depends on TOOLCHAIN_HAS_ZBKB + depends on RISCV_ALTERNATIVE + default y + help + Adds support to dynamically detect the presence of the ZBKB + extension (bit manipulation for cryptography) and enable its usage. + + The Zbkb extension provides instructions to accelerate a number + of common cryptography operations (pack, zip, etc). + + If you don't know what to do here, say Y. + config RISCV_ISA_ZICBOM bool "Zicbom extension support for non-coherent DMA operation" depends on MMU @@ -707,9 +828,9 @@ config RISCV_ISA_ZICBOM select RISCV_DMA_NONCOHERENT select DMA_DIRECT_REMAP help - Adds support to dynamically detect the presence of the ZICBOM - extension (Cache Block Management Operations) and enable its - usage. + Add support for the Zicbom extension (Cache Block Management + Operations) and enable its use in the kernel when it is detected + at boot. The Zicbom extension can be used to handle for example non-coherent DMA support on devices that need it. @@ -722,12 +843,27 @@ config RISCV_ISA_ZICBOZ default y help Enable the use of the Zicboz extension (cbo.zero instruction) - when available. + in the kernel when it is detected at boot. The Zicboz extension is used for faster zeroing of memory. If you don't know what to do here, say Y. +config RISCV_ISA_ZICBOP + bool "Zicbop extension support for cache block prefetch" + depends on MMU + depends on RISCV_ALTERNATIVE + default y + help + Adds support to dynamically detect the presence of the ZICBOP + extension (Cache Block Prefetch Operations) and enable its + usage. + + The Zicbop extension can be used to prefetch cache blocks for + read/write fetch. + + If you don't know what to do here, say Y. + config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI def_bool y # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc @@ -760,8 +896,9 @@ config FPU bool "FPU support" default y help - Say N here if you want to disable all floating-point related procedure - in the kernel. + Add support for floating point operations when an FPU is detected at + boot. When this option is disabled, neither the kernel nor userspace + may use the floating point unit. If you don't know what to do here, say Y. @@ -785,10 +922,24 @@ config THREAD_SIZE_ORDER config RISCV_MISALIGNED bool + help + Embed support for detecting and emulating misaligned + scalar or vector loads and stores. + +config RISCV_SCALAR_MISALIGNED + bool + select RISCV_MISALIGNED select SYSCTL_ARCH_UNALIGN_ALLOW help Embed support for emulating misaligned loads and stores. +config RISCV_VECTOR_MISALIGNED + bool + select RISCV_MISALIGNED + depends on RISCV_ISA_V + help + Enable detecting support for vector misaligned loads and stores. + choice prompt "Unaligned Accesses Support" default RISCV_PROBE_UNALIGNED_ACCESS @@ -800,7 +951,7 @@ choice config RISCV_PROBE_UNALIGNED_ACCESS bool "Probe for hardware unaligned access support" - select RISCV_MISALIGNED + select RISCV_SCALAR_MISALIGNED help During boot, the kernel will run a series of tests to determine the speed of unaligned accesses. This probing will dynamically determine @@ -811,7 +962,7 @@ config RISCV_PROBE_UNALIGNED_ACCESS config RISCV_EMULATED_UNALIGNED_ACCESS bool "Emulate unaligned access where system support is missing" - select RISCV_MISALIGNED + select RISCV_SCALAR_MISALIGNED help If unaligned memory accesses trap into the kernel as they are not supported by the system, the kernel will emulate the unaligned @@ -840,6 +991,46 @@ config RISCV_EFFICIENT_UNALIGNED_ACCESS endchoice +choice + prompt "Vector unaligned Accesses Support" + depends on RISCV_ISA_V + default RISCV_PROBE_VECTOR_UNALIGNED_ACCESS + help + This determines the level of support for vector unaligned accesses. This + information is used by the kernel to perform optimizations. It is also + exposed to user space via the hwprobe syscall. The hardware will be + probed at boot by default. + +config RISCV_PROBE_VECTOR_UNALIGNED_ACCESS + bool "Probe speed of vector unaligned accesses" + select RISCV_VECTOR_MISALIGNED + depends on RISCV_ISA_V + help + During boot, the kernel will run a series of tests to determine the + speed of vector unaligned accesses if they are supported. This probing + will dynamically determine the speed of vector unaligned accesses on + the underlying system if they are supported. + +config RISCV_SLOW_VECTOR_UNALIGNED_ACCESS + bool "Assume the system supports slow vector unaligned memory accesses" + depends on NONPORTABLE + help + Assume that the system supports slow vector unaligned memory accesses. The + kernel and userspace programs may not be able to run at all on systems + that do not support unaligned memory accesses. + +config RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS + bool "Assume the system supports fast vector unaligned memory accesses" + depends on NONPORTABLE + help + Assume that the system supports fast vector unaligned memory accesses. When + enabled, this option improves the performance of the kernel on such + systems. However, the kernel and userspace programs will run much more + slowly, or will not be able to run at all, on systems that do not + support efficient unaligned memory accesses. + +endchoice + source "arch/riscv/Kconfig.vendor" endmenu # "Platform type" @@ -898,6 +1089,9 @@ config ARCH_SUPPORTS_KEXEC_PURGATORY config ARCH_SUPPORTS_CRASH_DUMP def_bool y +config ARCH_DEFAULT_CRASH_DUMP + def_bool y + config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION def_bool CRASH_RESERVE @@ -934,8 +1128,9 @@ config PARAVIRT_TIME_ACCOUNTING config RELOCATABLE bool "Build a relocatable kernel" - depends on MMU && 64BIT && !XIP_KERNEL + depends on !XIP_KERNEL select MODULE_SECTIONS if MODULES + select ARCH_VMLINUX_NEEDS_RELOCS help This builds a kernel as a Position Independent Executable (PIE), which retains all relocation metadata required to relocate the @@ -998,8 +1193,8 @@ config CMDLINE_FALLBACK config CMDLINE_EXTEND bool "Extend bootloader kernel arguments" help - The command-line arguments provided during boot will be - appended to the built-in command line. This is useful in + The built-in command line will be appended to the command- + line arguments provided during boot. This is useful in cases where the provided arguments are insufficient and you don't want to or cannot modify them. @@ -1128,13 +1323,14 @@ config RISCV_ISA_FALLBACK config BUILTIN_DTB bool "Built-in device tree" depends on OF && NONPORTABLE + select GENERIC_BUILTIN_DTB help Build a device tree into the Linux image. This option should be selected if no bootloader is being used. If unsure, say N. -config BUILTIN_DTB_SOURCE +config BUILTIN_DTB_NAME string "Built-in device tree source" depends on BUILTIN_DTB help diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index 2acc7d876e1f..e318119d570d 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -119,4 +119,15 @@ config ERRATA_THEAD_PMU If you don't know what to do here, say "Y". +config ERRATA_THEAD_GHOSTWRITE + bool "Apply T-Head Ghostwrite errata" + depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR + default y + help + The T-Head C9xx cores have a vulnerability in the xtheadvector + instruction set. When this errata is enabled, the CPUs will be probed + to determine if they are vulnerable and disable xtheadvector. + + If you don't know what to do here, say "Y". + endmenu # "CPU errata selection" diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index f51bb24bc84c..a9c3d2f6debc 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -24,6 +24,12 @@ config ARCH_SOPHGO help This enables support for Sophgo SoC platform hardware. +config ARCH_SPACEMIT + bool "SpacemiT SoCs" + select PINCTRL + help + This enables support for SpacemiT SoC platform hardware. + config ARCH_STARFIVE def_bool SOC_STARFIVE @@ -48,12 +54,12 @@ config ARCH_THEAD bool "T-HEAD RISC-V SoCs" depends on MMU && !XIP_KERNEL select ERRATA_THEAD + select PM_GENERIC_DOMAINS if PM help This enables support for the RISC-V based T-HEAD SoCs. config ARCH_VIRT bool "QEMU Virt Machine" - select CLINT_TIMER if RISCV_M_MODE select POWER_RESET select POWER_RESET_SYSCON select POWER_RESET_SYSCON_POWEROFF @@ -73,7 +79,6 @@ config ARCH_CANAAN config SOC_CANAAN_K210 bool "Canaan Kendryte K210 SoC" depends on !MMU && ARCH_CANAAN - select CLINT_TIMER if RISCV_M_MODE select ARCH_HAS_RESET_CONTROLLER select PINCTRL select COMMON_CLK diff --git a/arch/riscv/Kconfig.vendor b/arch/riscv/Kconfig.vendor index 6f1cdd32ed29..e14f26368963 100644 --- a/arch/riscv/Kconfig.vendor +++ b/arch/riscv/Kconfig.vendor @@ -16,4 +16,43 @@ config RISCV_ISA_VENDOR_EXT_ANDES If you don't know what to do here, say Y. endmenu +menu "SiFive" +config RISCV_ISA_VENDOR_EXT_SIFIVE + bool "SiFive vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here if you want to disable all SiFive vendor extension + support. This will cause any SiFive vendor extensions that are + requested by hardware probing to be ignored. + + If you don't know what to do here, say Y. +endmenu + +menu "T-Head" +config RISCV_ISA_VENDOR_EXT_THEAD + bool "T-Head vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here to disable detection of and support for all T-Head vendor + extensions. Without this option enabled, T-Head vendor extensions will + not be detected at boot and their presence not reported to userspace. + + If you don't know what to do here, say Y. + +config RISCV_ISA_XTHEADVECTOR + bool "xtheadvector extension support" + depends on RISCV_ISA_VENDOR_EXT_THEAD + depends on RISCV_ISA_V + depends on FPU + default y + help + Say N here if you want to disable all xtheadvector related procedures + in the kernel. This will disable vector for any T-Head board that + contains xtheadvector rather than the standard vector. + + If you don't know what to do here, say Y. +endmenu + endmenu diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index d469db9f46f4..df57654a615e 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -8,16 +8,16 @@ LDFLAGS_vmlinux := -z norelro ifeq ($(CONFIG_RELOCATABLE),y) - LDFLAGS_vmlinux += -shared -Bsymbolic -z notext --emit-relocs + LDFLAGS_vmlinux += -shared -Bsymbolic -z notext KBUILD_CFLAGS += -fPIE endif ifeq ($(CONFIG_DYNAMIC_FTRACE),y) LDFLAGS_vmlinux += --no-relax KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY ifeq ($(CONFIG_RISCV_ISA_C),y) - CC_FLAGS_FTRACE := -fpatchable-function-entry=4 + CC_FLAGS_FTRACE := -fpatchable-function-entry=8,4 else - CC_FLAGS_FTRACE := -fpatchable-function-entry=2 + CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2 endif endif @@ -82,6 +82,12 @@ else riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei endif +# Check if the toolchain supports Zacas +riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas + +# Check if the toolchain supports Zabha +riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZABHA) := $(riscv-march-y)_zabha + # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by # matching non-v and non-multi-letter extensions out with the filter ([^v_]*) KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/') @@ -92,7 +98,6 @@ KBUILD_AFLAGS += -march=$(riscv-march-y) CC_FLAGS_FPU := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/') KBUILD_CFLAGS += -mno-save-restore -KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET) ifeq ($(CONFIG_CMODEL_MEDLOW),y) KBUILD_CFLAGS += -mcmodel=medlow @@ -129,7 +134,7 @@ stack_protector_prepare: prepare0 -mstack-protector-guard-reg=tp \ -mstack-protector-guard-offset=$(shell \ awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \ - include/generated/asm-offsets.h)) + $(objtree)/include/generated/asm-offsets.h)) endif # arch specific predefines for sparse diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink index 829b9abc91f6..0e4cf8ad2f14 100644 --- a/arch/riscv/Makefile.postlink +++ b/arch/riscv/Makefile.postlink @@ -15,25 +15,12 @@ quiet_cmd_relocs_check = CHKREL $@ cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/riscv/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" -ifdef CONFIG_RELOCATABLE -quiet_cmd_cp_vmlinux_relocs = CPREL vmlinux.relocs -cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs - -quiet_cmd_relocs_strip = STRIPREL $@ -cmd_relocs_strip = $(OBJCOPY) --remove-section='.rel.*' \ - --remove-section='.rel__*' \ - --remove-section='.rela.*' \ - --remove-section='.rela__*' $@ -endif - # `@true` prevents complaint when there is nothing to be done -vmlinux: FORCE +vmlinux vmlinux.unstripped: FORCE @true ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) - $(call if_changed,cp_vmlinux_relocs) - $(call if_changed,relocs_strip) endif clean: diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index b25d524ce5eb..bfc3d0b75b9b 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -32,10 +32,7 @@ $(obj)/xipImage: vmlinux FORCE endif ifdef CONFIG_RELOCATABLE -vmlinux.relocs: vmlinux - @ (! [ -f vmlinux.relocs ] && echo "vmlinux.relocs can't be found, please remove vmlinux and try again") || true - -$(obj)/Image: vmlinux.relocs FORCE +$(obj)/Image: vmlinux.unstripped FORCE else $(obj)/Image: vmlinux FORCE endif diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile index fdae05bbf556..64a898da9aee 100644 --- a/arch/riscv/boot/dts/Makefile +++ b/arch/riscv/boot/dts/Makefile @@ -5,7 +5,6 @@ subdir-y += microchip subdir-y += renesas subdir-y += sifive subdir-y += sophgo +subdir-y += spacemit subdir-y += starfive subdir-y += thead - -obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE)) diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi index 64c3c2e6cbe0..6367112e614a 100644 --- a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi @@ -27,7 +27,8 @@ riscv,isa = "rv64imafdc"; riscv,isa-base = "rv64i"; riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", - "zifencei", "zihpm"; + "zifencei", "zihpm", "xtheadvector"; + thead,vlenb = <128>; #cooling-cells = <2>; cpu0_intc: interrupt-controller { diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 1069134f2e12..a6dda55a2d1d 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -32,8 +32,9 @@ #interrupt-cells = <0x1>; #size-cells = <0x2>; device_type = "pci"; - reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; - reg-names = "cfg", "apb"; + reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>, + <0x0 0x4300a000 0x0 0x2000>; + reg-names = "cfg", "bridge", "ctrl"; bus-range = <0x0 0x7f>; interrupt-parent = <&plic>; interrupts = <119>; diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi index 8230f06ddf48..36a9860f31da 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi @@ -20,8 +20,9 @@ #interrupt-cells = <0x1>; #size-cells = <0x2>; device_type = "pci"; - reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; - reg-names = "cfg", "apb"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>, + <0x0 0x4300a000 0x0 0x2000>; + reg-names = "cfg", "bridge", "ctrl"; bus-range = <0x0 0x7f>; interrupt-parent = <&plic>; interrupts = <119>; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi index 9a56de7b91d6..a57dca891965 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi @@ -20,8 +20,9 @@ #interrupt-cells = <0x1>; #size-cells = <0x2>; device_type = "pci"; - reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; - reg-names = "cfg", "apb"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>, + <0x0 0x4300a000 0x0 0x2000>; + reg-names = "cfg", "bridge", "ctrl"; bus-range = <0x0 0x7f>; interrupt-parent = <&plic>; interrupts = <119>; diff --git a/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi index e0ddf8f602c7..a8bcb26f4270 100644 --- a/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi +++ b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi @@ -143,7 +143,8 @@ }; l2cache: cache-controller@13400000 { - compatible = "andestech,ax45mp-cache", "cache"; + compatible = "renesas,r9a07g043f-ax45mp-cache", "andestech,ax45mp-cache", + "cache"; reg = <0x0 0x13400000 0x0 0x100000>; interrupts = <SOC_PERIPHERAL_IRQ(476) IRQ_TYPE_LEVEL_HIGH>; cache-size = <0x40000>; diff --git a/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi b/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi index 5e808242649e..86b2f15375ec 100644 --- a/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi +++ b/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi @@ -6,3 +6,7 @@ */ #include <arm64/renesas/rzg2ul-smarc-som.dtsi> + +&sbc { + status = "disabled"; +}; diff --git a/arch/riscv/boot/dts/sophgo/Makefile b/arch/riscv/boot/dts/sophgo/Makefile index 57ad82a61ea6..85966306801e 100644 --- a/arch/riscv/boot/dts/sophgo/Makefile +++ b/arch/riscv/boot/dts/sophgo/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_ARCH_SOPHGO) += cv1800b-milkv-duo.dtb dtb-$(CONFIG_ARCH_SOPHGO) += cv1812h-huashan-pi.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2002-licheerv-nano-b.dtb dtb-$(CONFIG_ARCH_SOPHGO) += sg2042-milkv-pioneer.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2044-sophgo-srd3-10.dtb diff --git a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts index 375ff2661b6e..9feb520eaec4 100644 --- a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts +++ b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts @@ -39,7 +39,54 @@ clock-frequency = <25000000>; }; +&pinctrl { + uart0_cfg: uart0-cfg { + uart0-pins { + pinmux = <PINMUX(PIN_UART0_TX, 0)>, + <PINMUX(PIN_UART0_RX, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + sdhci0_cfg: sdhci0-cfg { + sdhci0-clk-pins { + pinmux = <PINMUX(PIN_SD0_CLK, 0)>; + bias-pull-up; + drive-strength-microamp = <16100>; + power-source = <3300>; + }; + + sdhci0-cmd-pins { + pinmux = <PINMUX(PIN_SD0_CMD, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-data-pins { + pinmux = <PINMUX(PIN_SD0_D0, 0)>, + <PINMUX(PIN_SD0_D1, 0)>, + <PINMUX(PIN_SD0_D2, 0)>, + <PINMUX(PIN_SD0_D3, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-cd-pins { + pinmux = <PINMUX(PIN_SD0_CD, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; +}; + &sdhci0 { + pinctrl-0 = <&sdhci0_cfg>; + pinctrl-names = "default"; status = "okay"; bus-width = <4>; no-1-8-v; @@ -49,5 +96,7 @@ }; &uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; status = "okay"; }; diff --git a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi index ec9530972ae2..90de978f69c1 100644 --- a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi +++ b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi @@ -3,7 +3,11 @@ * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org> */ -#include "cv18xx.dtsi" +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + +#include <dt-bindings/pinctrl/pinctrl-cv1800b.h> +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" / { compatible = "sophgo,cv1800b"; @@ -12,16 +16,39 @@ device_type = "memory"; reg = <0x80000000 0x4000000>; }; -}; -&plic { - compatible = "sophgo,cv1800b-plic", "thead,c900-plic"; -}; + soc { + interrupt-parent = <&plic>; + dma-noncoherent; -&clint { - compatible = "sophgo,cv1800b-clint", "thead,c900-clint"; -}; + pinctrl: pinctrl@3001000 { + compatible = "sophgo,cv1800b-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; -&clk { - compatible = "sophgo,cv1800-clk"; + clk: clock-controller@3002000 { + compatible = "sophgo,cv1800b-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,cv1800b-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,cv1800b-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; }; diff --git a/arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi b/arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi new file mode 100644 index 000000000000..93fd9e47a195 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org> + * Copyright (C) 2023 Inochi Amaoto <inochiama@outlook.com> + */ + +/ { + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <25000000>; + + cpu0: cpu@0 { + compatible = "thead,c906", "riscv"; + device_type = "cpu"; + reg = <0>; + d-cache-block-size = <64>; + d-cache-sets = <512>; + d-cache-size = <65536>; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + mmu-type = "riscv,sv39"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv180x.dtsi index b724fb6d9689..ed06c3609fb2 100644 --- a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi +++ b/arch/riscv/boot/dts/sophgo/cv180x.dtsi @@ -12,35 +12,6 @@ #address-cells = <1>; #size-cells = <1>; - cpus: cpus { - #address-cells = <1>; - #size-cells = <0>; - timebase-frequency = <25000000>; - - cpu0: cpu@0 { - compatible = "thead,c906", "riscv"; - device_type = "cpu"; - reg = <0>; - d-cache-block-size = <64>; - d-cache-sets = <512>; - d-cache-size = <65536>; - i-cache-block-size = <64>; - i-cache-sets = <128>; - i-cache-size = <32768>; - mmu-type = "riscv,sv39"; - riscv,isa = "rv64imafdc"; - riscv,isa-base = "rv64i"; - riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", - "zifencei", "zihpm"; - - cpu0_intc: interrupt-controller { - compatible = "riscv,cpu-intc"; - interrupt-controller; - #interrupt-cells = <1>; - }; - }; - }; - osc: oscillator { compatible = "fixed-clock"; clock-output-names = "osc_25m"; @@ -49,18 +20,10 @@ soc { compatible = "simple-bus"; - interrupt-parent = <&plic>; #address-cells = <1>; #size-cells = <1>; - dma-noncoherent; ranges; - clk: clock-controller@3002000 { - reg = <0x03002000 0x1000>; - clocks = <&osc>; - #clock-cells = <1>; - }; - gpio0: gpio@3020000 { compatible = "snps,dw-apb-gpio"; reg = <0x3020000 0x1000>; @@ -75,7 +38,7 @@ reg = <0>; interrupt-controller; #interrupt-cells = <2>; - interrupts = <60 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(44) IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -93,7 +56,7 @@ reg = <0>; interrupt-controller; #interrupt-cells = <2>; - interrupts = <61 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(45) IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -111,7 +74,7 @@ reg = <0>; interrupt-controller; #interrupt-cells = <2>; - interrupts = <62 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(46) IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -129,7 +92,29 @@ reg = <0>; interrupt-controller; #interrupt-cells = <2>; - interrupts = <63 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(47) IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + saradc: adc@30f0000 { + compatible = "sophgo,cv1800b-saradc"; + reg = <0x030f0000 0x1000>; + clocks = <&clk CLK_SARADC>; + interrupts = <SOC_PERIPHERAL_IRQ(84) IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + + channel@0 { + reg = <0>; + }; + + channel@1 { + reg = <1>; + }; + + channel@2 { + reg = <2>; }; }; @@ -140,7 +125,7 @@ #size-cells = <0>; clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C0>; clock-names = "ref", "pclk"; - interrupts = <49 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(33) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -151,7 +136,7 @@ #size-cells = <0>; clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C1>; clock-names = "ref", "pclk"; - interrupts = <50 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(34) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -162,7 +147,7 @@ #size-cells = <0>; clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C2>; clock-names = "ref", "pclk"; - interrupts = <51 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(35) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -173,7 +158,7 @@ #size-cells = <0>; clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C3>; clock-names = "ref", "pclk"; - interrupts = <52 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(36) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -184,14 +169,14 @@ #size-cells = <0>; clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C4>; clock-names = "ref", "pclk"; - interrupts = <53 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(37) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; uart0: serial@4140000 { compatible = "snps,dw-apb-uart"; reg = <0x04140000 0x100>; - interrupts = <44 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(28) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_UART0>, <&clk CLK_APB_UART0>; clock-names = "baudclk", "apb_pclk"; reg-shift = <2>; @@ -202,7 +187,7 @@ uart1: serial@4150000 { compatible = "snps,dw-apb-uart"; reg = <0x04150000 0x100>; - interrupts = <45 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(29) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_UART1>, <&clk CLK_APB_UART1>; clock-names = "baudclk", "apb_pclk"; reg-shift = <2>; @@ -213,7 +198,7 @@ uart2: serial@4160000 { compatible = "snps,dw-apb-uart"; reg = <0x04160000 0x100>; - interrupts = <46 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(30) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_UART2>, <&clk CLK_APB_UART2>; clock-names = "baudclk", "apb_pclk"; reg-shift = <2>; @@ -224,7 +209,7 @@ uart3: serial@4170000 { compatible = "snps,dw-apb-uart"; reg = <0x04170000 0x100>; - interrupts = <47 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(31) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_UART3>, <&clk CLK_APB_UART3>; clock-names = "baudclk", "apb_pclk"; reg-shift = <2>; @@ -239,7 +224,7 @@ #size-cells = <0>; clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI0>; clock-names = "ssi_clk", "pclk"; - interrupts = <54 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(38) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -250,7 +235,7 @@ #size-cells = <0>; clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI1>; clock-names = "ssi_clk", "pclk"; - interrupts = <55 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(39) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -261,7 +246,7 @@ #size-cells = <0>; clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI2>; clock-names = "ssi_clk", "pclk"; - interrupts = <56 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(40) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; @@ -272,14 +257,14 @@ #size-cells = <0>; clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI3>; clock-names = "ssi_clk", "pclk"; - interrupts = <57 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(41) IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; uart4: serial@41c0000 { compatible = "snps,dw-apb-uart"; reg = <0x041c0000 0x100>; - interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(32) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_UART4>, <&clk CLK_APB_UART4>; clock-names = "baudclk", "apb_pclk"; reg-shift = <2>; @@ -290,17 +275,27 @@ sdhci0: mmc@4310000 { compatible = "sophgo,cv1800b-dwcmshc"; reg = <0x4310000 0x1000>; - interrupts = <36 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(20) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_AXI4_SD0>, <&clk CLK_SD0>; clock-names = "core", "bus"; status = "disabled"; }; + sdhci1: mmc@4320000 { + compatible = "sophgo,cv1800b-dwcmshc"; + reg = <0x4320000 0x1000>; + interrupts = <SOC_PERIPHERAL_IRQ(22) IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_AXI4_SD1>, + <&clk CLK_SD1>; + clock-names = "core", "bus"; + status = "disabled"; + }; + dmac: dma-controller@4330000 { compatible = "snps,axi-dma-1.01a"; reg = <0x04330000 0x1000>; - interrupts = <29 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <SOC_PERIPHERAL_IRQ(13) IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk CLK_SDMA_AXI>, <&clk CLK_SDMA_AXI>; clock-names = "core-clk", "cfgr-clk"; #dma-cells = <1>; @@ -309,22 +304,8 @@ 1024 1024 1024 1024>; snps,priority = <0 1 2 3 4 5 6 7>; snps,dma-masters = <2>; - snps,data-width = <4>; + snps,data-width = <2>; status = "disabled"; }; - - plic: interrupt-controller@70000000 { - reg = <0x70000000 0x4000000>; - interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - riscv,ndev = <101>; - }; - - clint: timer@74000000 { - reg = <0x74000000 0x10000>; - interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; - }; }; }; diff --git a/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts b/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts index 7b5f57853690..26b57e15adc1 100644 --- a/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts +++ b/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts @@ -43,6 +43,18 @@ clock-frequency = <25000000>; }; +&emmc { + status = "okay"; + bus-width = <4>; + max-frequency = <200000000>; + mmc-ddr-1_8v; + mmc-ddr-3_3v; + mmc-hs200-1_8v; + no-sd; + no-sdio; + non-removable; +}; + &sdhci0 { status = "okay"; bus-width = <4>; @@ -52,6 +64,17 @@ disable-wp; }; +&sdhci1 { + status = "okay"; + bus-width = <4>; + cap-sdio-irq; + max-frequency = <50000000>; + no-mmc; + no-sd; + disable-wp; + non-removable; +}; + &uart0 { status = "okay"; }; diff --git a/arch/riscv/boot/dts/sophgo/cv1812h.dtsi b/arch/riscv/boot/dts/sophgo/cv1812h.dtsi index 7fa4c1e2d1da..9a2a314d3347 100644 --- a/arch/riscv/boot/dts/sophgo/cv1812h.dtsi +++ b/arch/riscv/boot/dts/sophgo/cv1812h.dtsi @@ -3,8 +3,13 @@ * Copyright (C) 2023 Inochi Amaoto <inochiama@outlook.com> */ +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + #include <dt-bindings/interrupt-controller/irq.h> -#include "cv18xx.dtsi" +#include <dt-bindings/pinctrl/pinctrl-cv1812h.h> +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" +#include "cv181x.dtsi" / { compatible = "sophgo,cv1812h"; @@ -13,16 +18,39 @@ device_type = "memory"; reg = <0x80000000 0x10000000>; }; -}; -&plic { - compatible = "sophgo,cv1812h-plic", "thead,c900-plic"; -}; + soc { + interrupt-parent = <&plic>; + dma-noncoherent; -&clint { - compatible = "sophgo,cv1812h-clint", "thead,c900-clint"; -}; + pinctrl: pinctrl@3001000 { + compatible = "sophgo,cv1812h-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; -&clk { - compatible = "sophgo,cv1810-clk"; + clk: clock-controller@3002000 { + compatible = "sophgo,cv1812h-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,cv1812h-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,cv1812h-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; }; diff --git a/arch/riscv/boot/dts/sophgo/cv181x.dtsi b/arch/riscv/boot/dts/sophgo/cv181x.dtsi new file mode 100644 index 000000000000..bbdb30653e9a --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv181x.dtsi @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Inochi Amaoto <inochiama@outlook.com> + */ + +#include <dt-bindings/clock/sophgo,cv1800.h> +#include <dt-bindings/interrupt-controller/irq.h> + +/ { + soc { + emmc: mmc@4300000 { + compatible = "sophgo,cv1800b-dwcmshc"; + reg = <0x4300000 0x1000>; + interrupts = <SOC_PERIPHERAL_IRQ(18) IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_AXI4_EMMC>, + <&clk CLK_EMMC>; + clock-names = "core", "bus"; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts b/arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts new file mode 100644 index 000000000000..86a712b953a5 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Thomas Bonnefille <thomas.bonnefille@bootlin.com> + */ + +/dts-v1/; + +#include "sg2002.dtsi" + +/ { + model = "LicheeRV Nano B"; + compatible = "sipeed,licheerv-nano-b", "sipeed,licheerv-nano", "sophgo,sg2002"; + + aliases { + gpio0 = &gpio0; + gpio1 = &gpio1; + gpio2 = &gpio2; + gpio3 = &gpio3; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&pinctrl { + uart0_cfg: uart0-cfg { + uart0-pins { + pinmux = <PINMUX(PIN_UART0_TX, 0)>, + <PINMUX(PIN_UART0_RX, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + sdhci0_cfg: sdhci0-cfg { + sdhci0-clk-pins { + pinmux = <PINMUX(PIN_SD0_CLK, 0)>; + bias-pull-up; + drive-strength-microamp = <16100>; + power-source = <3300>; + }; + + sdhci0-cmd-pins { + pinmux = <PINMUX(PIN_SD0_CMD, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-data-pins { + pinmux = <PINMUX(PIN_SD0_D0, 0)>, + <PINMUX(PIN_SD0_D1, 0)>, + <PINMUX(PIN_SD0_D2, 0)>, + <PINMUX(PIN_SD0_D3, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-cd-pins { + pinmux = <PINMUX(PIN_SD0_CD, 0)>; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; +}; + +&sdhci0 { + pinctrl-0 = <&sdhci0_cfg>; + pinctrl-names = "default"; + status = "okay"; + bus-width = <4>; + no-1-8-v; + no-mmc; + no-sdio; + disable-wp; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2002.dtsi b/arch/riscv/boot/dts/sophgo/sg2002.dtsi new file mode 100644 index 000000000000..98001cce238e --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2002.dtsi @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Thomas Bonnefille <thomas.bonnefille@bootlin.com> + */ + +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + +#include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/pinctrl/pinctrl-sg2002.h> +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" +#include "cv181x.dtsi" + +/ { + compatible = "sophgo,sg2002"; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x10000000>; + }; + + soc { + interrupt-parent = <&plic>; + dma-noncoherent; + + pinctrl: pinctrl@3001000 { + compatible = "sophgo,sg2002-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; + + clk: clock-controller@3002000 { + compatible = "sophgo,sg2002-clk", "sophgo,sg2000-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,sg2002-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,sg2002-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; +}; + +&sdhci0 { + compatible = "sophgo,sg2002-dwcmshc"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts b/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts index a3f9d6f22566..ef3a602172b1 100644 --- a/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts +++ b/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts @@ -5,6 +5,9 @@ #include "sg2042.dtsi" +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/input/input.h> + / { model = "Milk-V Pioneer"; compatible = "milkv,pioneer", "sophgo,sg2042"; @@ -12,6 +15,18 @@ chosen { stdout-path = "serial0"; }; + + gpio-power { + compatible = "gpio-keys"; + + key-power { + label = "Power Key"; + linux,code = <KEY_POWER>; + gpios = <&port0a 22 GPIO_ACTIVE_HIGH>; + linux,input-type = <EV_KEY>; + debounce-interval = <100>; + }; + }; }; &cgi_main { @@ -27,6 +42,8 @@ }; &emmc { + pinctrl-0 = <&emmc_cfg>; + pinctrl-names = "default"; bus-width = <4>; no-sdio; no-sd; @@ -36,6 +53,8 @@ }; &i2c1 { + pinctrl-0 = <&i2c1_cfg>; + pinctrl-names = "default"; status = "okay"; mcu: syscon@17 { @@ -45,7 +64,73 @@ }; }; +&pinctrl { + emmc_cfg: sdhci-emmc-cfg { + sdhci-emmc-wp-pins { + pinmux = <PINMUX(PIN_EMMC_WP, 0)>; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + + sdhci-emmc-cd-pins { + pinmux = <PINMUX(PIN_EMMC_CD, 0)>; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-emmc-rst-pwr-pins { + pinmux = <PINMUX(PIN_EMMC_RST, 0)>, + <PINMUX(PIN_EMMC_PWR_EN, 0)>; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + i2c1_cfg: i2c1-cfg { + i2c1-pins { + pinmux = <PINMUX(PIN_IIC1_SDA, 0)>, + <PINMUX(PIN_IIC1_SCL, 0)>; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; + + sd_cfg: sdhci-sd-cfg { + sdhci-sd-cd-wp-pins { + pinmux = <PINMUX(PIN_SDIO_CD, 0)>, + <PINMUX(PIN_SDIO_WP, 0)>; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-sd-rst-pwr-pins { + pinmux = <PINMUX(PIN_SDIO_RST, 0)>, + <PINMUX(PIN_SDIO_PWR_EN, 0)>; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + uart0_cfg: uart0-cfg { + uart0-rx-pins { + pinmux = <PINMUX(PIN_UART0_TX, 0)>, + <PINMUX(PIN_UART0_RX, 0)>; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; +}; + &sd { + pinctrl-0 = <&sd_cfg>; + pinctrl-names = "default"; bus-width = <4>; no-sdio; no-mmc; @@ -54,10 +139,19 @@ }; &uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; status = "okay"; }; / { + pwmfan: pwm-fan { + compatible = "pwm-fan"; + cooling-levels = <103 128 179 230 255>; + pwms = <&pwm 0 40000 0>; + #cooling-cells = <2>; + }; + thermal-zones { soc-thermal { polling-delay-passive = <1000>; @@ -89,6 +183,28 @@ type = "hot"; }; }; + + cooling-maps { + map0 { + trip = <&soc_active1>; + cooling-device = <&pwmfan 0 1>; + }; + + map1 { + trip = <&soc_active2>; + cooling-device = <&pwmfan 1 2>; + }; + + map2 { + trip = <&soc_active3>; + cooling-device = <&pwmfan 2 3>; + }; + + map3 { + trip = <&soc_hot>; + cooling-device = <&pwmfan 3 4>; + }; + }; }; board-thermal { @@ -103,6 +219,13 @@ type = "active"; }; }; + + cooling-maps { + map4 { + trip = <&board_active>; + cooling-device = <&pwmfan 3 4>; + }; + }; }; }; }; diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi index 4e5fa6591623..85636d1798f1 100644 --- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi +++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi @@ -8,6 +8,7 @@ #include <dt-bindings/clock/sophgo,sg2042-pll.h> #include <dt-bindings/clock/sophgo,sg2042-rpgate.h> #include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/pinctrl/pinctrl-sg2042.h> #include <dt-bindings/reset/sophgo,sg2042-reset.h> #include "sg2042-cpus.dtsi" @@ -112,7 +113,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -134,7 +135,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -156,7 +157,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -165,6 +166,15 @@ }; }; + pwm: pwm@703000c000 { + compatible = "sophgo,sg2042-pwm"; + reg = <0x70 0x3000c000 0x0 0x20>; + #pwm-cells = <3>; + clocks = <&clkgen GATE_CLK_APB_PWM>; + clock-names = "apb"; + resets = <&rstgen RST_PWM>; + }; + pllclk: clock-controller@70300100c0 { compatible = "sophgo,sg2042-pll"; reg = <0x70 0x300100c0 0x0 0x40>; @@ -173,6 +183,16 @@ #clock-cells = <1>; }; + msi: msi-controller@7030010304 { + compatible = "sophgo,sg2042-msi"; + reg = <0x70 0x30010304 0x0 0x4>, + <0x70 0x30010300 0x0 0x4>; + reg-names = "clr", "doorbell"; + msi-controller; + #msi-cells = <0>; + msi-ranges = <&intc 64 IRQ_TYPE_LEVEL_HIGH 32>; + }; + rpgate: clock-controller@7030010368 { compatible = "sophgo,sg2042-rpgate"; reg = <0x70 0x30010368 0x0 0x98>; @@ -181,6 +201,11 @@ #clock-cells = <1>; }; + pinctrl: pinctrl@7030011000 { + compatible = "sophgo,sg2042-pinctrl"; + reg = <0x70 0x30011000 0x0 0x1000>; + }; + clkgen: clock-controller@7030012000 { compatible = "sophgo,sg2042-clkgen"; reg = <0x70 0x30012000 0x0 0x1000>; @@ -518,6 +543,32 @@ status = "disabled"; }; + spi0: spi@7040004000 { + compatible = "sophgo,sg2042-spi", "snps,dw-apb-ssi"; + reg = <0x70 0x40004000 0x00 0x1000>; + clocks = <&clkgen GATE_CLK_APB_SPI>; + interrupt-parent = <&intc>; + interrupts = <110 IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + num-cs = <2>; + resets = <&rstgen RST_SPI0>; + status = "disabled"; + }; + + spi1: spi@7040005000 { + compatible = "sophgo,sg2042-spi", "snps,dw-apb-ssi"; + reg = <0x70 0x40005000 0x00 0x1000>; + clocks = <&clkgen GATE_CLK_APB_SPI>; + interrupt-parent = <&intc>; + interrupts = <111 IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + num-cs = <2>; + resets = <&rstgen RST_SPI1>; + status = "disabled"; + }; + emmc: mmc@704002a000 { compatible = "sophgo,sg2042-dwcmshc"; reg = <0x70 0x4002a000 0x0 0x1000>; diff --git a/arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi b/arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi new file mode 100644 index 000000000000..2a4267078ce6 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi @@ -0,0 +1,3002 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Inochi Amaoto <inochiama@gmail.com> + */ + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <50000000>; + + cpu0: cpu@0 { + compatible = "thead,c920", "riscv"; + reg = <0>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu1: cpu@1 { + compatible = "thead,c920", "riscv"; + reg = <1>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu2: cpu@2 { + compatible = "thead,c920", "riscv"; + reg = <2>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu3: cpu@3 { + compatible = "thead,c920", "riscv"; + reg = <3>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu4: cpu@4 { + compatible = "thead,c920", "riscv"; + reg = <4>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu5: cpu@5 { + compatible = "thead,c920", "riscv"; + reg = <5>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu6: cpu@6 { + compatible = "thead,c920", "riscv"; + reg = <6>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu7: cpu@7 { + compatible = "thead,c920", "riscv"; + reg = <7>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu8: cpu@8 { + compatible = "thead,c920", "riscv"; + reg = <8>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu8_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu9: cpu@9 { + compatible = "thead,c920", "riscv"; + reg = <9>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu9_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu10: cpu@10 { + compatible = "thead,c920", "riscv"; + reg = <10>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu10_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu11: cpu@11 { + compatible = "thead,c920", "riscv"; + reg = <11>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu11_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu12: cpu@12 { + compatible = "thead,c920", "riscv"; + reg = <12>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu12_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu13: cpu@13 { + compatible = "thead,c920", "riscv"; + reg = <13>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu13_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu14: cpu@14 { + compatible = "thead,c920", "riscv"; + reg = <14>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu14_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu15: cpu@15 { + compatible = "thead,c920", "riscv"; + reg = <15>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu15_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu16: cpu@16 { + compatible = "thead,c920", "riscv"; + reg = <16>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu16_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu17: cpu@17 { + compatible = "thead,c920", "riscv"; + reg = <17>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu17_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu18: cpu@18 { + compatible = "thead,c920", "riscv"; + reg = <18>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu18_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu19: cpu@19 { + compatible = "thead,c920", "riscv"; + reg = <19>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu19_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu20: cpu@20 { + compatible = "thead,c920", "riscv"; + reg = <20>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu20_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu21: cpu@21 { + compatible = "thead,c920", "riscv"; + reg = <21>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu21_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu22: cpu@22 { + compatible = "thead,c920", "riscv"; + reg = <22>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu22_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu23: cpu@23 { + compatible = "thead,c920", "riscv"; + reg = <23>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu23_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu24: cpu@24 { + compatible = "thead,c920", "riscv"; + reg = <24>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu24_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu25: cpu@25 { + compatible = "thead,c920", "riscv"; + reg = <25>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu25_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu26: cpu@26 { + compatible = "thead,c920", "riscv"; + reg = <26>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu26_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu27: cpu@27 { + compatible = "thead,c920", "riscv"; + reg = <27>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu27_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu28: cpu@28 { + compatible = "thead,c920", "riscv"; + reg = <28>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu28_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu29: cpu@29 { + compatible = "thead,c920", "riscv"; + reg = <29>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu29_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu30: cpu@30 { + compatible = "thead,c920", "riscv"; + reg = <30>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu30_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu31: cpu@31 { + compatible = "thead,c920", "riscv"; + reg = <31>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu31_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu32: cpu@32 { + compatible = "thead,c920", "riscv"; + reg = <32>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu32_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu33: cpu@33 { + compatible = "thead,c920", "riscv"; + reg = <33>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu33_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu34: cpu@34 { + compatible = "thead,c920", "riscv"; + reg = <34>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu34_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu35: cpu@35 { + compatible = "thead,c920", "riscv"; + reg = <35>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu35_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu36: cpu@36 { + compatible = "thead,c920", "riscv"; + reg = <36>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu36_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu37: cpu@37 { + compatible = "thead,c920", "riscv"; + reg = <37>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu37_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu38: cpu@38 { + compatible = "thead,c920", "riscv"; + reg = <38>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu38_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu39: cpu@39 { + compatible = "thead,c920", "riscv"; + reg = <39>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu39_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu40: cpu@40 { + compatible = "thead,c920", "riscv"; + reg = <40>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu40_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu41: cpu@41 { + compatible = "thead,c920", "riscv"; + reg = <41>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu41_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu42: cpu@42 { + compatible = "thead,c920", "riscv"; + reg = <42>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu42_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu43: cpu@43 { + compatible = "thead,c920", "riscv"; + reg = <43>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu43_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu44: cpu@44 { + compatible = "thead,c920", "riscv"; + reg = <44>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu44_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu45: cpu@45 { + compatible = "thead,c920", "riscv"; + reg = <45>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu45_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu46: cpu@46 { + compatible = "thead,c920", "riscv"; + reg = <46>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu46_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu47: cpu@47 { + compatible = "thead,c920", "riscv"; + reg = <47>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu47_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu48: cpu@48 { + compatible = "thead,c920", "riscv"; + reg = <48>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu48_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu49: cpu@49 { + compatible = "thead,c920", "riscv"; + reg = <49>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu49_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu50: cpu@50 { + compatible = "thead,c920", "riscv"; + reg = <50>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu50_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu51: cpu@51 { + compatible = "thead,c920", "riscv"; + reg = <51>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu51_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu52: cpu@52 { + compatible = "thead,c920", "riscv"; + reg = <52>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu52_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu53: cpu@53 { + compatible = "thead,c920", "riscv"; + reg = <53>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu53_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu54: cpu@54 { + compatible = "thead,c920", "riscv"; + reg = <54>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu54_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu55: cpu@55 { + compatible = "thead,c920", "riscv"; + reg = <55>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu55_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu56: cpu@56 { + compatible = "thead,c920", "riscv"; + reg = <56>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu56_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu57: cpu@57 { + compatible = "thead,c920", "riscv"; + reg = <57>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu57_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu58: cpu@58 { + compatible = "thead,c920", "riscv"; + reg = <58>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu58_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu59: cpu@59 { + compatible = "thead,c920", "riscv"; + reg = <59>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu59_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu60: cpu@60 { + compatible = "thead,c920", "riscv"; + reg = <60>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu60_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu61: cpu@61 { + compatible = "thead,c920", "riscv"; + reg = <61>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu61_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu62: cpu@62 { + compatible = "thead,c920", "riscv"; + reg = <62>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu62_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu63: cpu@63 { + compatible = "thead,c920", "riscv"; + reg = <63>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu63_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu-map { + socket0 { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu4>; + }; + + core1 { + cpu = <&cpu5>; + }; + + core2 { + cpu = <&cpu6>; + }; + + core3 { + cpu = <&cpu7>; + }; + }; + + cluster2 { + core0 { + cpu = <&cpu8>; + }; + + core1 { + cpu = <&cpu9>; + }; + + core2 { + cpu = <&cpu10>; + }; + + core3 { + cpu = <&cpu11>; + }; + }; + + cluster3 { + core0 { + cpu = <&cpu12>; + }; + + core1 { + cpu = <&cpu13>; + }; + + core2 { + cpu = <&cpu14>; + }; + + core3 { + cpu = <&cpu15>; + }; + }; + + cluster4 { + core0 { + cpu = <&cpu16>; + }; + + core1 { + cpu = <&cpu17>; + }; + + core2 { + cpu = <&cpu18>; + }; + + core3 { + cpu = <&cpu19>; + }; + }; + + cluster5 { + core0 { + cpu = <&cpu20>; + }; + + core1 { + cpu = <&cpu21>; + }; + + core2 { + cpu = <&cpu22>; + }; + + core3 { + cpu = <&cpu23>; + }; + }; + + cluster6 { + core0 { + cpu = <&cpu24>; + }; + + core1 { + cpu = <&cpu25>; + }; + + core2 { + cpu = <&cpu26>; + }; + + core3 { + cpu = <&cpu27>; + }; + }; + + cluster7 { + core0 { + cpu = <&cpu28>; + }; + + core1 { + cpu = <&cpu29>; + }; + + core2 { + cpu = <&cpu30>; + }; + + core3 { + cpu = <&cpu31>; + }; + }; + + cluster8 { + core0 { + cpu = <&cpu32>; + }; + + core1 { + cpu = <&cpu33>; + }; + + core2 { + cpu = <&cpu34>; + }; + + core3 { + cpu = <&cpu35>; + }; + }; + + cluster9 { + core0 { + cpu = <&cpu36>; + }; + + core1 { + cpu = <&cpu37>; + }; + + core2 { + cpu = <&cpu38>; + }; + + core3 { + cpu = <&cpu39>; + }; + }; + + cluster10 { + core0 { + cpu = <&cpu40>; + }; + + core1 { + cpu = <&cpu41>; + }; + + core2 { + cpu = <&cpu42>; + }; + + core3 { + cpu = <&cpu43>; + }; + }; + + cluster11 { + core0 { + cpu = <&cpu44>; + }; + + core1 { + cpu = <&cpu45>; + }; + + core2 { + cpu = <&cpu46>; + }; + + core3 { + cpu = <&cpu47>; + }; + }; + + cluster12 { + core0 { + cpu = <&cpu48>; + }; + + core1 { + cpu = <&cpu49>; + }; + + core2 { + cpu = <&cpu50>; + }; + + core3 { + cpu = <&cpu51>; + }; + }; + + cluster13 { + core0 { + cpu = <&cpu52>; + }; + + core1 { + cpu = <&cpu53>; + }; + + core2 { + cpu = <&cpu54>; + }; + + core3 { + cpu = <&cpu55>; + }; + }; + + cluster14 { + core0 { + cpu = <&cpu56>; + }; + + core1 { + cpu = <&cpu57>; + }; + + core2 { + cpu = <&cpu58>; + }; + + core3 { + cpu = <&cpu59>; + }; + }; + + cluster15 { + core0 { + cpu = <&cpu60>; + }; + + core1 { + cpu = <&cpu61>; + }; + + core2 { + cpu = <&cpu62>; + }; + + core3 { + cpu = <&cpu63>; + }; + }; + }; + }; + + l2_cache0: cache-controller-0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache1: cache-controller-1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache2: cache-controller-2 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache3: cache-controller-3 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache4: cache-controller-4 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache5: cache-controller-5 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache6: cache-controller-6 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache7: cache-controller-7 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache8: cache-controller-8 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache9: cache-controller-9 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache10: cache-controller-10 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache11: cache-controller-11 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache12: cache-controller-12 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache13: cache-controller-13 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache14: cache-controller-14 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache15: cache-controller-15 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l3_cache: cache-controller-16 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <3>; + cache-size = <67108864>; + cache-sets = <4096>; + cache-unified; + }; + }; + + soc { + intc: interrupt-controller@6d40000000 { + compatible = "sophgo,sg2044-plic", "thead,c900-plic"; + #address-cells = <0>; + #interrupt-cells = <2>; + reg = <0x6d 0x40000000 0x0 0x4000000>; + interrupt-controller; + interrupts-extended = + <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>, + <&cpu5_intc 11>, <&cpu5_intc 9>, + <&cpu6_intc 11>, <&cpu6_intc 9>, + <&cpu7_intc 11>, <&cpu7_intc 9>, + <&cpu8_intc 11>, <&cpu8_intc 9>, + <&cpu9_intc 11>, <&cpu9_intc 9>, + <&cpu10_intc 11>, <&cpu10_intc 9>, + <&cpu11_intc 11>, <&cpu11_intc 9>, + <&cpu12_intc 11>, <&cpu12_intc 9>, + <&cpu13_intc 11>, <&cpu13_intc 9>, + <&cpu14_intc 11>, <&cpu14_intc 9>, + <&cpu15_intc 11>, <&cpu15_intc 9>, + <&cpu16_intc 11>, <&cpu16_intc 9>, + <&cpu17_intc 11>, <&cpu17_intc 9>, + <&cpu18_intc 11>, <&cpu18_intc 9>, + <&cpu19_intc 11>, <&cpu19_intc 9>, + <&cpu20_intc 11>, <&cpu20_intc 9>, + <&cpu21_intc 11>, <&cpu21_intc 9>, + <&cpu22_intc 11>, <&cpu22_intc 9>, + <&cpu23_intc 11>, <&cpu23_intc 9>, + <&cpu24_intc 11>, <&cpu24_intc 9>, + <&cpu25_intc 11>, <&cpu25_intc 9>, + <&cpu26_intc 11>, <&cpu26_intc 9>, + <&cpu27_intc 11>, <&cpu27_intc 9>, + <&cpu28_intc 11>, <&cpu28_intc 9>, + <&cpu29_intc 11>, <&cpu29_intc 9>, + <&cpu30_intc 11>, <&cpu30_intc 9>, + <&cpu31_intc 11>, <&cpu31_intc 9>, + <&cpu32_intc 11>, <&cpu32_intc 9>, + <&cpu33_intc 11>, <&cpu33_intc 9>, + <&cpu34_intc 11>, <&cpu34_intc 9>, + <&cpu35_intc 11>, <&cpu35_intc 9>, + <&cpu36_intc 11>, <&cpu36_intc 9>, + <&cpu37_intc 11>, <&cpu37_intc 9>, + <&cpu38_intc 11>, <&cpu38_intc 9>, + <&cpu39_intc 11>, <&cpu39_intc 9>, + <&cpu40_intc 11>, <&cpu40_intc 9>, + <&cpu41_intc 11>, <&cpu41_intc 9>, + <&cpu42_intc 11>, <&cpu42_intc 9>, + <&cpu43_intc 11>, <&cpu43_intc 9>, + <&cpu44_intc 11>, <&cpu44_intc 9>, + <&cpu45_intc 11>, <&cpu45_intc 9>, + <&cpu46_intc 11>, <&cpu46_intc 9>, + <&cpu47_intc 11>, <&cpu47_intc 9>, + <&cpu48_intc 11>, <&cpu48_intc 9>, + <&cpu49_intc 11>, <&cpu49_intc 9>, + <&cpu50_intc 11>, <&cpu50_intc 9>, + <&cpu51_intc 11>, <&cpu51_intc 9>, + <&cpu52_intc 11>, <&cpu52_intc 9>, + <&cpu53_intc 11>, <&cpu53_intc 9>, + <&cpu54_intc 11>, <&cpu54_intc 9>, + <&cpu55_intc 11>, <&cpu55_intc 9>, + <&cpu56_intc 11>, <&cpu56_intc 9>, + <&cpu57_intc 11>, <&cpu57_intc 9>, + <&cpu58_intc 11>, <&cpu58_intc 9>, + <&cpu59_intc 11>, <&cpu59_intc 9>, + <&cpu60_intc 11>, <&cpu60_intc 9>, + <&cpu61_intc 11>, <&cpu61_intc 9>, + <&cpu62_intc 11>, <&cpu62_intc 9>, + <&cpu63_intc 11>, <&cpu63_intc 9>; + riscv,ndev = <863>; + }; + + aclint_mswi: interrupt-controller@6d44000000 { + compatible = "sophgo,sg2044-aclint-mswi", "thead,c900-aclint-mswi"; + reg = <0x6d 0x44000000 0x0 0x4000>; + interrupts-extended = <&cpu0_intc 3>, + <&cpu1_intc 3>, + <&cpu2_intc 3>, + <&cpu3_intc 3>, + <&cpu4_intc 3>, + <&cpu5_intc 3>, + <&cpu6_intc 3>, + <&cpu7_intc 3>, + <&cpu8_intc 3>, + <&cpu9_intc 3>, + <&cpu10_intc 3>, + <&cpu11_intc 3>, + <&cpu12_intc 3>, + <&cpu13_intc 3>, + <&cpu14_intc 3>, + <&cpu15_intc 3>, + <&cpu16_intc 3>, + <&cpu17_intc 3>, + <&cpu18_intc 3>, + <&cpu19_intc 3>, + <&cpu20_intc 3>, + <&cpu21_intc 3>, + <&cpu22_intc 3>, + <&cpu23_intc 3>, + <&cpu24_intc 3>, + <&cpu25_intc 3>, + <&cpu26_intc 3>, + <&cpu27_intc 3>, + <&cpu28_intc 3>, + <&cpu29_intc 3>, + <&cpu30_intc 3>, + <&cpu31_intc 3>, + <&cpu32_intc 3>, + <&cpu33_intc 3>, + <&cpu34_intc 3>, + <&cpu35_intc 3>, + <&cpu36_intc 3>, + <&cpu37_intc 3>, + <&cpu38_intc 3>, + <&cpu39_intc 3>, + <&cpu40_intc 3>, + <&cpu41_intc 3>, + <&cpu42_intc 3>, + <&cpu43_intc 3>, + <&cpu44_intc 3>, + <&cpu45_intc 3>, + <&cpu46_intc 3>, + <&cpu47_intc 3>, + <&cpu48_intc 3>, + <&cpu49_intc 3>, + <&cpu50_intc 3>, + <&cpu51_intc 3>, + <&cpu52_intc 3>, + <&cpu53_intc 3>, + <&cpu54_intc 3>, + <&cpu55_intc 3>, + <&cpu56_intc 3>, + <&cpu57_intc 3>, + <&cpu58_intc 3>, + <&cpu59_intc 3>, + <&cpu60_intc 3>, + <&cpu61_intc 3>, + <&cpu62_intc 3>, + <&cpu63_intc 3>; + }; + + aclint_mtimer: timer@6d44004000 { + compatible = "sophgo,sg2044-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x6d 0x44004000 0x0 0x8000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu0_intc 7>, + <&cpu1_intc 7>, + <&cpu2_intc 7>, + <&cpu3_intc 7>, + <&cpu4_intc 7>, + <&cpu5_intc 7>, + <&cpu6_intc 7>, + <&cpu7_intc 7>, + <&cpu8_intc 7>, + <&cpu9_intc 7>, + <&cpu10_intc 7>, + <&cpu11_intc 7>, + <&cpu12_intc 7>, + <&cpu13_intc 7>, + <&cpu14_intc 7>, + <&cpu15_intc 7>, + <&cpu16_intc 7>, + <&cpu17_intc 7>, + <&cpu18_intc 7>, + <&cpu19_intc 7>, + <&cpu20_intc 7>, + <&cpu21_intc 7>, + <&cpu22_intc 7>, + <&cpu23_intc 7>, + <&cpu24_intc 7>, + <&cpu25_intc 7>, + <&cpu26_intc 7>, + <&cpu27_intc 7>, + <&cpu28_intc 7>, + <&cpu29_intc 7>, + <&cpu30_intc 7>, + <&cpu31_intc 7>, + <&cpu32_intc 7>, + <&cpu33_intc 7>, + <&cpu34_intc 7>, + <&cpu35_intc 7>, + <&cpu36_intc 7>, + <&cpu37_intc 7>, + <&cpu38_intc 7>, + <&cpu39_intc 7>, + <&cpu40_intc 7>, + <&cpu41_intc 7>, + <&cpu42_intc 7>, + <&cpu43_intc 7>, + <&cpu44_intc 7>, + <&cpu45_intc 7>, + <&cpu46_intc 7>, + <&cpu47_intc 7>, + <&cpu48_intc 7>, + <&cpu49_intc 7>, + <&cpu50_intc 7>, + <&cpu51_intc 7>, + <&cpu52_intc 7>, + <&cpu53_intc 7>, + <&cpu54_intc 7>, + <&cpu55_intc 7>, + <&cpu56_intc 7>, + <&cpu57_intc 7>, + <&cpu58_intc 7>, + <&cpu59_intc 7>, + <&cpu60_intc 7>, + <&cpu61_intc 7>, + <&cpu62_intc 7>, + <&cpu63_intc 7>; + }; + + aclint_sswi: interrupt-controller@6d4400c000 { + compatible = "sophgo,sg2044-aclint-sswi", "thead,c900-aclint-sswi"; + reg = <0x6d 0x4400c000 0x0 0x1000>; + #interrupt-cells = <0>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 1>, + <&cpu1_intc 1>, + <&cpu2_intc 1>, + <&cpu3_intc 1>, + <&cpu4_intc 1>, + <&cpu5_intc 1>, + <&cpu6_intc 1>, + <&cpu7_intc 1>, + <&cpu8_intc 1>, + <&cpu9_intc 1>, + <&cpu10_intc 1>, + <&cpu11_intc 1>, + <&cpu12_intc 1>, + <&cpu13_intc 1>, + <&cpu14_intc 1>, + <&cpu15_intc 1>, + <&cpu16_intc 1>, + <&cpu17_intc 1>, + <&cpu18_intc 1>, + <&cpu19_intc 1>, + <&cpu20_intc 1>, + <&cpu21_intc 1>, + <&cpu22_intc 1>, + <&cpu23_intc 1>, + <&cpu24_intc 1>, + <&cpu25_intc 1>, + <&cpu26_intc 1>, + <&cpu27_intc 1>, + <&cpu28_intc 1>, + <&cpu29_intc 1>, + <&cpu30_intc 1>, + <&cpu31_intc 1>, + <&cpu32_intc 1>, + <&cpu33_intc 1>, + <&cpu34_intc 1>, + <&cpu35_intc 1>, + <&cpu36_intc 1>, + <&cpu37_intc 1>, + <&cpu38_intc 1>, + <&cpu39_intc 1>, + <&cpu40_intc 1>, + <&cpu41_intc 1>, + <&cpu42_intc 1>, + <&cpu43_intc 1>, + <&cpu44_intc 1>, + <&cpu45_intc 1>, + <&cpu46_intc 1>, + <&cpu47_intc 1>, + <&cpu48_intc 1>, + <&cpu49_intc 1>, + <&cpu50_intc 1>, + <&cpu51_intc 1>, + <&cpu52_intc 1>, + <&cpu53_intc 1>, + <&cpu54_intc 1>, + <&cpu55_intc 1>, + <&cpu56_intc 1>, + <&cpu57_intc 1>, + <&cpu58_intc 1>, + <&cpu59_intc 1>, + <&cpu60_intc 1>, + <&cpu61_intc 1>, + <&cpu62_intc 1>, + <&cpu63_intc 1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2044-reset.h b/arch/riscv/boot/dts/sophgo/sg2044-reset.h new file mode 100644 index 000000000000..3a7bbfdb4bae --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044-reset.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +/* + * Copyright (C) 2025 Inochi Amaoto <inochiama@gmail.com> + */ + +#ifndef _SG2044_RESET_H +#define _SG2044_RESET_H + +#define RST_AP_SYS 0 +#define RST_AP_SYS_CORE0 1 +#define RST_AP_SYS_CORE1 2 +#define RST_AP_SYS_CORE2 3 +#define RST_AP_SYS_CORE3 4 +#define RST_AP_PIC 5 +#define RST_AP_TDT 6 +#define RST_RP_PIC_TDT 7 +#define RST_HSDMA 8 +#define RST_SYSDMA 9 +#define RST_EFUSE0 10 +#define RST_EFUSE1 11 +#define RST_RTC 12 +#define RST_TIMER 13 +#define RST_WDT 14 +#define RST_AHB_ROM0 15 +#define RST_AHB_ROM1 16 +#define RST_I2C0 17 +#define RST_I2C1 18 +#define RST_I2C2 19 +#define RST_I2C3 20 +#define RST_GPIO0 21 +#define RST_GPIO1 22 +#define RST_GPIO2 23 +#define RST_PWM 24 +#define RST_AXI_SRAM0 25 +#define RST_AXI_SRAM1 26 +#define RST_SPIFMC0 27 +#define RST_SPIFMC1 28 +#define RST_MAILBOX 29 +#define RST_ETH0 30 +#define RST_EMMC 31 +#define RST_SD 32 +#define RST_UART0 33 +#define RST_UART1 34 +#define RST_UART2 35 +#define RST_UART3 36 +#define RST_SPI0 37 +#define RST_SPI1 38 +#define RST_MTLI 39 +#define RST_DBG_I2C 40 +#define RST_C2C0 41 +#define RST_C2C1 42 +#define RST_C2C2 43 +#define RST_C2C3 44 +#define RST_CXP 45 +#define RST_DDR0 46 +#define RST_DDR1 47 +#define RST_DDR2 48 +#define RST_DDR3 49 +#define RST_DDR4 50 +#define RST_DDR5 51 +#define RST_DDR6 52 +#define RST_DDR7 53 +#define RST_DDR8 54 +#define RST_DDR9 55 +#define RST_DDR10 56 +#define RST_DDR11 57 +#define RST_DDR12 58 +#define RST_DDR13 59 +#define RST_DDR14 60 +#define RST_DDR15 61 +#define RST_BAR 62 +#define RST_K2K 63 +#define RST_CC_SYS_X1Y1 64 +#define RST_CC_SYS_X1Y2 65 +#define RST_CC_SYS_X1Y3 66 +#define RST_CC_SYS_X1Y4 67 +#define RST_CC_SYS_X0Y1 68 +#define RST_CC_SYS_X0Y2 69 +#define RST_CC_SYS_X0Y3 70 +#define RST_CC_SYS_X0Y4 71 +#define RST_SC_X1Y1 80 +#define RST_SC_X1Y2 81 +#define RST_SC_X1Y3 82 +#define RST_SC_X1Y4 83 +#define RST_SC_X0Y1 84 +#define RST_SC_X0Y2 85 +#define RST_SC_X0Y3 86 +#define RST_SC_X0Y4 87 +#define RST_RP_CLUSTER_X1Y1_S0 160 +#define RST_RP_CLUSTER_X1Y1_S1 161 +#define RST_RP_CLUSTER_X1Y2_S0 162 +#define RST_RP_CLUSTER_X1Y2_S1 163 +#define RST_RP_CLUSTER_X1Y3_S0 164 +#define RST_RP_CLUSTER_X1Y3_S1 165 +#define RST_RP_CLUSTER_X1Y4_S0 166 +#define RST_RP_CLUSTER_X1Y4_S1 167 +#define RST_RP_CLUSTER_X0Y1_W0 168 +#define RST_RP_CLUSTER_X0Y1_W1 169 +#define RST_RP_CLUSTER_X0Y2_W0 170 +#define RST_RP_CLUSTER_X0Y2_W1 171 +#define RST_RP_CLUSTER_X0Y3_W0 172 +#define RST_RP_CLUSTER_X0Y3_W1 173 +#define RST_RP_CLUSTER_X0Y4_W0 174 +#define RST_RP_CLUSTER_X0Y4_W1 175 +#define RST_TPSYS_X1Y1 180 +#define RST_TPSYS_X1Y2 181 +#define RST_TPSYS_X1Y3 182 +#define RST_TPSYS_X1Y4 183 +#define RST_TPSYS_X0Y1 184 +#define RST_TPSYS_X0Y2 185 +#define RST_TPSYS_X0Y3 186 +#define RST_TPSYS_X0Y4 187 +#define RST_SPACC 188 +#define RST_PKA 189 +#define RST_SE_TRNG 190 +#define RST_SE_DBG 191 +#define RST_SE_FAB_FW 192 +#define RST_SE_CTRL 193 +#define RST_MAILBOX0 194 +#define RST_MAILBOX1 195 +#define RST_MAILBOX2 196 +#define RST_MAILBOX3 197 +#define RST_INTC0 198 +#define RST_INTC1 199 +#define RST_INTC2 200 +#define RST_INTC3 201 + +#endif /* _DT_BINDINGS_SG2044_RESET_H */ diff --git a/arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts b/arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts new file mode 100644 index 000000000000..54cdf4239d5f --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Inochi Amaoto <inochiama@gmail.com> + */ + +/dts-v1/; + +#include "sg2044.dtsi" + +/ { + model = "Sophgo SG2044 SRD3-10"; + compatible = "sophgo,srd3-10", "sophgo,sg2044"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&uart1 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2044.dtsi b/arch/riscv/boot/dts/sophgo/sg2044.dtsi new file mode 100644 index 000000000000..d67e45f77d6e --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044.dtsi @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Inochi Amaoto <inochiama@gmail.com> + */ + +#include <dt-bindings/interrupt-controller/irq.h> + +#include "sg2044-cpus.dtsi" +#include "sg2044-reset.h" + +/ { + compatible = "sophgo,sg2044"; + + memory@80000000 { + device_type = "memory"; + reg = <0x00000000 0x80000000 0x00000010 0x00000000>; + }; + + osc: oscillator { + compatible = "fixed-clock"; + clock-output-names = "osc"; + #clock-cells = <0>; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + uart0: serial@7030000000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30000000 0x0 0x1000>; + clock-frequency = <500000000>; + interrupt-parent = <&intc>; + interrupts = <41 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART0>; + status = "disabled"; + }; + + uart1: serial@7030001000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30001000 0x0 0x1000>; + clock-frequency = <500000000>; + interrupt-parent = <&intc>; + interrupts = <42 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART1>; + status = "disabled"; + }; + + uart2: serial@7030002000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30002000 0x0 0x1000>; + clock-frequency = <500000000>; + interrupt-parent = <&intc>; + interrupts = <43 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART2>; + status = "disabled"; + }; + + uart3: serial@7030003000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30003000 0x0 0x1000>; + clock-frequency = <500000000>; + interrupt-parent = <&intc>; + interrupts = <44 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART3>; + status = "disabled"; + }; + + rst: reset-controller@7050003000 { + compatible = "sophgo,sg2044-reset", + "sophgo,sg2042-reset"; + reg = <0x70 0x50003000 0x0 0x1000>; + #reset-cells = <1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/Makefile b/arch/riscv/boot/dts/spacemit/Makefile new file mode 100644 index 000000000000..92e13ce1c16d --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-bananapi-f3.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-milkv-jupiter.dtb diff --git a/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts b/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts new file mode 100644 index 000000000000..816ef1bc358e --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen <cyy@cyyself.name> + */ + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "Banana Pi BPI-F3"; + compatible = "bananapi,bpi-f3", "spacemit,k1"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0"; + }; + + leds { + compatible = "gpio-leds"; + + led1 { + label = "sys-led"; + gpios = <&gpio K1_GPIO(96) GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + default-state = "on"; + }; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts b/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts new file mode 100644 index 000000000000..448319214104 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen <cyy@cyyself.name> + * Copyright (C) 2025 Javier Martinez Canillas <javierm@redhat.com> + */ + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "Milk-V Jupiter (K1)"; + compatible = "milkv,jupiter", "spacemit,k1"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0"; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi b/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi new file mode 100644 index 000000000000..283663647a86 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (c) 2024 Yixun Lan <dlan@gentoo.org> + */ + +#include <dt-bindings/gpio/gpio.h> + +#define K1_PADCONF(pin, func) (((pin) << 16) | (func)) + +/* Map GPIO pin to each bank's <index, offset> */ +#define K1_GPIO(x) (x / 32) (x % 32) + +&pinctrl { + uart0_2_cfg: uart0-2-cfg { + uart0-2-pins { + pinmux = <K1_PADCONF(68, 2)>, + <K1_PADCONF(69, 2)>; + + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1.dtsi b/arch/riscv/boot/dts/spacemit/k1.dtsi new file mode 100644 index 000000000000..c0f8c5fca975 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1.dtsi @@ -0,0 +1,566 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen <cyy@cyyself.name> + */ + +#include <dt-bindings/clock/spacemit,k1-syscon.h> + +/dts-v1/; +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "SpacemiT K1"; + compatible = "spacemit,k1"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <24000000>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu_0>; + }; + core1 { + cpu = <&cpu_1>; + }; + core2 { + cpu = <&cpu_2>; + }; + core3 { + cpu = <&cpu_3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu_4>; + }; + core1 { + cpu = <&cpu_5>; + }; + core2 { + cpu = <&cpu_6>; + }; + core3 { + cpu = <&cpu_7>; + }; + }; + }; + + cpu_0: cpu@0 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <0>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_1: cpu@1 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <1>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_2: cpu@2 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <2>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_3: cpu@3 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <3>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_4: cpu@4 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <4>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_5: cpu@5 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <5>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_6: cpu@6 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <6>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_7: cpu@7 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <7>; + riscv,isa = "rv64imafdcv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cluster0_l2_cache: l2-cache0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <524288>; + cache-sets = <512>; + cache-unified; + }; + + cluster1_l2_cache: l2-cache1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <524288>; + cache-sets = <512>; + cache-unified; + }; + }; + + clocks { + vctcxo_1m: clock-1m { + compatible = "fixed-clock"; + clock-frequency = <1000000>; + clock-output-names = "vctcxo_1m"; + #clock-cells = <0>; + }; + + vctcxo_24m: clock-24m { + compatible = "fixed-clock"; + clock-frequency = <24000000>; + clock-output-names = "vctcxo_24m"; + #clock-cells = <0>; + }; + + vctcxo_3m: clock-3m { + compatible = "fixed-clock"; + clock-frequency = <3000000>; + clock-output-names = "vctcxo_3m"; + #clock-cells = <0>; + }; + + osc_32k: clock-32k { + compatible = "fixed-clock"; + clock-frequency = <32000>; + clock-output-names = "osc_32k"; + #clock-cells = <0>; + }; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + syscon_apbc: system-controller@d4015000 { + compatible = "spacemit,k1-syscon-apbc"; + reg = <0x0 0xd4015000 0x0 0x1000>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, + <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", + "vctcxo_24m"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + uart0: serial@d4017000 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017000 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART0>, + <&syscon_apbc CLK_UART0_BUS>; + clock-names = "core", "bus"; + interrupts = <42>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart2: serial@d4017100 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017100 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART2>, + <&syscon_apbc CLK_UART2_BUS>; + clock-names = "core", "bus"; + interrupts = <44>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart3: serial@d4017200 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017200 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART3>, + <&syscon_apbc CLK_UART3_BUS>; + clock-names = "core", "bus"; + interrupts = <45>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart4: serial@d4017300 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017300 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART4>, + <&syscon_apbc CLK_UART4_BUS>; + clock-names = "core", "bus"; + interrupts = <46>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart5: serial@d4017400 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017400 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART5>, + <&syscon_apbc CLK_UART5_BUS>; + clock-names = "core", "bus"; + interrupts = <47>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart6: serial@d4017500 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017500 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART6>, + <&syscon_apbc CLK_UART6_BUS>; + clock-names = "core", "bus"; + interrupts = <48>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart7: serial@d4017600 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017600 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART7>, + <&syscon_apbc CLK_UART7_BUS>; + clock-names = "core", "bus"; + interrupts = <49>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart8: serial@d4017700 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017700 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART8>, + <&syscon_apbc CLK_UART8_BUS>; + clock-names = "core", "bus"; + interrupts = <50>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart9: serial@d4017800 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017800 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART9>, + <&syscon_apbc CLK_UART9_BUS>; + clock-names = "core", "bus"; + interrupts = <51>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + gpio: gpio@d4019000 { + compatible = "spacemit,k1-gpio"; + reg = <0x0 0xd4019000 0x0 0x100>; + clocks = <&syscon_apbc CLK_GPIO>, + <&syscon_apbc CLK_GPIO_BUS>; + clock-names = "core", "bus"; + gpio-controller; + #gpio-cells = <3>; + interrupts = <58>; + interrupt-parent = <&plic>; + interrupt-controller; + #interrupt-cells = <3>; + gpio-ranges = <&pinctrl 0 0 0 32>, + <&pinctrl 1 0 32 32>, + <&pinctrl 2 0 64 32>, + <&pinctrl 3 0 96 32>; + }; + + pinctrl: pinctrl@d401e000 { + compatible = "spacemit,k1-pinctrl"; + reg = <0x0 0xd401e000 0x0 0x400>; + clocks = <&syscon_apbc CLK_AIB>, + <&syscon_apbc CLK_AIB_BUS>; + clock-names = "func", "bus"; + }; + + syscon_mpmu: system-controller@d4050000 { + compatible = "spacemit,k1-syscon-mpmu"; + reg = <0x0 0xd4050000 0x0 0x209c>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, + <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", + "vctcxo_24m"; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + }; + + pll: clock-controller@d4090000 { + compatible = "spacemit,k1-pll"; + reg = <0x0 0xd4090000 0x0 0x1000>; + clocks = <&vctcxo_24m>; + spacemit,mpmu = <&syscon_mpmu>; + #clock-cells = <1>; + }; + + syscon_apmu: system-controller@d4282800 { + compatible = "spacemit,k1-syscon-apmu"; + reg = <0x0 0xd4282800 0x0 0x400>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, + <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", + "vctcxo_24m"; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + }; + + plic: interrupt-controller@e0000000 { + compatible = "spacemit,k1-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xe0000000 0x0 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>, + <&cpu5_intc 11>, <&cpu5_intc 9>, + <&cpu6_intc 11>, <&cpu6_intc 9>, + <&cpu7_intc 11>, <&cpu7_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + riscv,ndev = <159>; + }; + + clint: timer@e4000000 { + compatible = "spacemit,k1-clint", "sifive,clint0"; + reg = <0x0 0xe4000000 0x0 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>, + <&cpu5_intc 3>, <&cpu5_intc 7>, + <&cpu6_intc 3>, <&cpu6_intc 7>, + <&cpu7_intc 3>, <&cpu7_intc 7>; + }; + + sec_uart1: serial@f0612000 { + compatible = "spacemit,k1-uart", "intel,xscale-uart"; + reg = <0x0 0xf0612000 0x0 0x100>; + interrupts = <43>; + clock-frequency = <14857000>; + reg-shift = <2>; + reg-io-width = <4>; + status = "reserved"; /* for TEE usage */ + }; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/Makefile b/arch/riscv/boot/dts/starfive/Makefile index eb2cba9205b4..1a88d79f0115 100644 --- a/arch/riscv/boot/dts/starfive/Makefile +++ b/arch/riscv/boot/dts/starfive/Makefile @@ -10,6 +10,7 @@ dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-beaglev-starlight-a1.dtb dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-beaglev-starlight.dtb dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-starfive-visionfive-v1.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-deepcomputing-fml13v01.dtb dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-milkv-mars.dtb dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-pine64-star64.dtb dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-starfive-visionfive-2-v1.2a.dtb diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi index c7771b3b6475..4baeb981d4df 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi @@ -8,6 +8,7 @@ #include "jh7110.dtsi" #include "jh7110-pinfunc.h" #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/pinctrl/starfive,jh7110-pinctrl.h> / { aliases { @@ -28,6 +29,7 @@ memory@40000000 { device_type = "memory"; reg = <0x0 0x40000000 0x1 0x0>; + bootph-pre-ram; }; gpio-restart { @@ -128,7 +130,6 @@ assigned-clocks = <&ispcrg JH7110_ISPCLK_DOM4_APB_FUNC>, <&ispcrg JH7110_ISPCLK_MIPI_RX0_PXL>; assigned-clock-rates = <49500000>, <198000000>; - status = "okay"; ports { #address-cells = <1>; @@ -151,7 +152,6 @@ &csi2rx { assigned-clocks = <&ispcrg JH7110_ISPCLK_VIN_SYS>; assigned-clock-rates = <297000000>; - status = "okay"; ports { #address-cells = <1>; @@ -176,7 +176,6 @@ &gmac0 { phy-handle = <&phy0>; phy-mode = "rgmii-id"; - status = "okay"; mdio { #address-cells = <1>; @@ -196,7 +195,6 @@ i2c-scl-falling-time-ns = <510>; pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins>; - status = "okay"; }; &i2c2 { @@ -237,7 +235,7 @@ regulator-always-on; regulator-min-microvolt = <500000>; regulator-max-microvolt = <1540000>; - regulator-name = "vdd-cpu"; + regulator-name = "vdd_cpu"; }; emmc_vdd: aldo4 { @@ -249,6 +247,13 @@ }; }; }; + + eeprom@50 { + compatible = "atmel,24c04"; + reg = <0x50>; + bootph-pre-ram; + pagesize = <16>; + }; }; &i2c6 { @@ -266,6 +271,7 @@ assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; assigned-clock-rates = <50000000>; bus-width = <8>; + bootph-pre-ram; cap-mmc-highspeed; mmc-ddr-1_8v; mmc-hs200-1_8v; @@ -283,6 +289,7 @@ assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO1_SDCARD>; assigned-clock-rates = <50000000>; bus-width = <4>; + bootph-pre-ram; no-sdio; no-mmc; cd-gpios = <&sysgpio 41 GPIO_ACTIVE_LOW>; @@ -311,7 +318,6 @@ &pwmdac { pinctrl-names = "default"; pinctrl-0 = <&pwmdac_pins>; - status = "okay"; }; &qspi { @@ -322,8 +328,9 @@ nor_flash: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; - cdns,read-delay = <5>; - spi-max-frequency = <12000000>; + bootph-pre-ram; + cdns,read-delay = <2>; + spi-max-frequency = <100000000>; cdns,tshsl-ns = <1>; cdns,tsd2d-ns = <1>; cdns,tchsh-ns = <1>; @@ -350,25 +357,25 @@ &pwm { pinctrl-names = "default"; pinctrl-0 = <&pwm_pins>; - status = "okay"; }; &spi0 { pinctrl-names = "default"; pinctrl-0 = <&spi0_pins>; - status = "okay"; - - spi_dev0: spi@0 { - compatible = "rohm,dh2228fv"; - reg = <0>; - spi-max-frequency = <10000000>; - }; }; &syscrg { - assigned-clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>, + assigned-clocks = <&syscrg JH7110_SYSCLK_CPU_ROOT>, + <&syscrg JH7110_SYSCLK_BUS_ROOT>, + <&syscrg JH7110_SYSCLK_PERH_ROOT>, + <&syscrg JH7110_SYSCLK_QSPI_REF>, + <&syscrg JH7110_SYSCLK_CPU_CORE>, <&pllclk JH7110_PLLCLK_PLL0_OUT>; - assigned-clock-rates = <500000000>, <1500000000>; + assigned-clock-parents = <&pllclk JH7110_PLLCLK_PLL0_OUT>, + <&pllclk JH7110_PLLCLK_PLL2_OUT>, + <&pllclk JH7110_PLLCLK_PLL2_OUT>, + <&syscrg JH7110_SYSCLK_QSPI_REF_SRC>; + assigned-clock-rates = <0>, <0>, <0>, <0>, <500000000>, <1500000000>; }; &sysgpio { @@ -401,6 +408,8 @@ }; i2c5_pins: i2c5-0 { + bootph-pre-ram; + i2c-pins { pinmux = <GPIOMUX(19, GPOUT_LOW, GPOEN_SYS_I2C5_CLK, @@ -409,6 +418,7 @@ GPOEN_SYS_I2C5_DATA, GPI_SYS_I2C5_DATA)>; bias-disable; /* external pull-up */ + bootph-pre-ram; input-enable; input-schmitt-enable; }; @@ -441,16 +451,16 @@ }; mmc-pins { - pinmux = <PINMUX(64, 0)>, - <PINMUX(65, 0)>, - <PINMUX(66, 0)>, - <PINMUX(67, 0)>, - <PINMUX(68, 0)>, - <PINMUX(69, 0)>, - <PINMUX(70, 0)>, - <PINMUX(71, 0)>, - <PINMUX(72, 0)>, - <PINMUX(73, 0)>; + pinmux = <PINMUX(PAD_SD0_CLK, 0)>, + <PINMUX(PAD_SD0_CMD, 0)>, + <PINMUX(PAD_SD0_DATA0, 0)>, + <PINMUX(PAD_SD0_DATA1, 0)>, + <PINMUX(PAD_SD0_DATA2, 0)>, + <PINMUX(PAD_SD0_DATA3, 0)>, + <PINMUX(PAD_SD0_DATA4, 0)>, + <PINMUX(PAD_SD0_DATA5, 0)>, + <PINMUX(PAD_SD0_DATA6, 0)>, + <PINMUX(PAD_SD0_DATA7, 0)>; bias-pull-up; drive-strength = <12>; input-enable; @@ -637,16 +647,12 @@ }; &uart0 { + bootph-pre-ram; pinctrl-names = "default"; pinctrl-0 = <&uart0_pins>; status = "okay"; }; -&usb0 { - dr_mode = "peripheral"; - status = "okay"; -}; - &U74_1 { cpu-supply = <&vdd_cpu>; }; diff --git a/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts b/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts new file mode 100644 index 000000000000..f2857d021d68 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 DeepComputing (HK) Limited + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + model = "DeepComputing FML13V01"; + compatible = "deepcomputing,fml13v01", "starfive,jh7110"; +}; + +&pcie1 { + perst-gpios = <&sysgpio 21 GPIO_ACTIVE_LOW>; + phys = <&pciephy1>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_pins>; + status = "okay"; +}; + +&sysgpio { + pcie1_pins: pcie1-0 { + clkreq-pins { + pinmux = <GPIOMUX(29, GPOUT_LOW, + GPOEN_DISABLE, + GPI_NONE)>; + bias-pull-down; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + wake-pins { + pinmux = <GPIOMUX(28, GPOUT_HIGH, + GPOEN_DISABLE, + GPI_NONE)>; + bias-pull-up; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + usb0_pins: usb0-0 { + vbus-pins { + pinmux = <GPIOMUX(25, GPOUT_SYS_USB_DRIVE_VBUS, + GPOEN_ENABLE, + GPI_NONE)>; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; + +&usb_cdns3 { + phys = <&usbphy0>, <&pciephy0>; + phy-names = "cdns3,usb2-phy", "cdns3,usb3-phy"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts b/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts index 5cb9e99e1dac..3bd62ab78523 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts @@ -15,6 +15,11 @@ starfive,tx-use-rgmii-clk; assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + status = "okay"; +}; + +&i2c0 { + status = "okay"; }; &pcie0 { @@ -35,3 +40,36 @@ rx-internal-delay-ps = <1500>; tx-internal-delay-ps = <1500>; }; + +&pwm { + status = "okay"; +}; + +&pwmdac { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&sysgpio { + usb0_pins: usb0-0 { + vbus-pins { + pinmux = <GPIOMUX(25, GPOUT_SYS_USB_DRIVE_VBUS, + GPOEN_ENABLE, + GPI_NONE)>; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts index b720cdd15ed6..31e825be2065 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts @@ -18,6 +18,7 @@ starfive,tx-use-rgmii-clk; assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + status = "okay"; }; &gmac1 { @@ -39,13 +40,16 @@ }; }; +&i2c0 { + status = "okay"; +}; + &pcie1 { status = "okay"; }; &phy0 { - rx-internal-delay-ps = <1900>; - tx-internal-delay-ps = <1500>; + rx-internal-delay-ps = <1500>; motorcomm,rx-clk-drv-microamp = <2910>; motorcomm,rx-data-drv-microamp = <2910>; motorcomm,tx-clk-adj-enabled; @@ -63,3 +67,41 @@ motorcomm,tx-clk-10-inverted; motorcomm,tx-clk-100-inverted; }; + +&pwm { + status = "okay"; +}; + +&pwmdac { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&sysgpio { + usb0_pins: usb0-0 { + vbus-pins { + pinmux = <GPIOMUX(25, GPOUT_SYS_USB_DRIVE_VBUS, + GPOEN_ENABLE, + GPI_NONE)>; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; + +&usb_cdns3 { + phys = <&usbphy0>, <&pciephy0>; + phy-names = "cdns3,usb2-phy", "cdns3,usb3-phy"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h index 256de17f5261..ae49c908e7fb 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h +++ b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h @@ -89,7 +89,7 @@ #define GPOUT_SYS_SDIO1_DATA1 59 #define GPOUT_SYS_SDIO1_DATA2 60 #define GPOUT_SYS_SDIO1_DATA3 61 -#define GPOUT_SYS_SDIO1_DATA4 63 +#define GPOUT_SYS_SDIO1_DATA4 62 #define GPOUT_SYS_SDIO1_DATA5 63 #define GPOUT_SYS_SDIO1_DATA6 64 #define GPOUT_SYS_SDIO1_DATA7 65 diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi index 18f38fc790a4..5f14afb2c24d 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -13,6 +13,10 @@ }; }; +&gmac0 { + status = "okay"; +}; + &gmac1 { phy-handle = <&phy1>; phy-mode = "rgmii-id"; @@ -29,6 +33,10 @@ }; }; +&i2c0 { + status = "okay"; +}; + &mmc0 { non-removable; }; @@ -40,3 +48,20 @@ &pcie1 { status = "okay"; }; + +&pwm { + status = "okay"; +}; + +&pwmdac { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&usb0 { + dr_mode = "peripheral"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi index 0d8339357bad..0ba74ef04679 100644 --- a/arch/riscv/boot/dts/starfive/jh7110.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi @@ -611,6 +611,8 @@ pciephy0: phy@10210000 { compatible = "starfive,jh7110-pcie-phy"; reg = <0x0 0x10210000 0x0 0x10000>; + starfive,sys-syscon = <&sys_syscon 0x18>; + starfive,stg-syscon = <&stg_syscon 0x148 0x1f4>; #phy-cells = <0>; }; @@ -1022,7 +1024,6 @@ snps,force_thresh_dma_mode; snps,axi-config = <&stmmac_axi_setup>; snps,tso; - snps,en-tx-lpi-clockgating; snps,txpbl = <16>; snps,rxpbl = <16>; starfive,syscon = <&aon_syscon 0xc 0x12>; @@ -1053,7 +1054,6 @@ snps,force_thresh_dma_mode; snps,axi-config = <&stmmac_axi_setup>; snps,tso; - snps,en-tx-lpi-clockgating; snps,txpbl = <16>; snps,rxpbl = <16>; starfive,syscon = <&sys_syscon 0x90 0x2>; diff --git a/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts index 497d961456f3..21c33f165ba9 100644 --- a/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts +++ b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts @@ -7,16 +7,21 @@ /dts-v1/; #include "th1520.dtsi" +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/leds/common.h> / { model = "BeagleV Ahead"; compatible = "beagle,beaglev-ahead", "thead,th1520"; aliases { + ethernet0 = &gmac0; gpio0 = &gpio0; gpio1 = &gpio1; gpio2 = &gpio2; gpio3 = &gpio3; + gpio4 = &gpio4; + gpio5 = &aogpio; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; @@ -33,7 +38,42 @@ memory@0 { device_type = "memory"; reg = <0x0 0x00000000 0x1 0x00000000>; + }; + + leds { + pinctrl-names = "default"; + pinctrl-0 = <&led_pins>; + compatible = "gpio-leds"; + + led-1 { + gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; + color = <LED_COLOR_ID_BLUE>; + label = "led1"; + }; + + led-2 { + gpios = <&gpio4 9 GPIO_ACTIVE_HIGH>; + color = <LED_COLOR_ID_BLUE>; + label = "led2"; + }; + led-3 { + gpios = <&gpio4 10 GPIO_ACTIVE_HIGH>; + color = <LED_COLOR_ID_BLUE>; + label = "led3"; + }; + + led-4 { + gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>; + color = <LED_COLOR_ID_BLUE>; + label = "led4"; + }; + + led-5 { + gpios = <&gpio4 12 GPIO_ACTIVE_HIGH>; + color = <LED_COLOR_ID_BLUE>; + label = "led5"; + }; }; }; @@ -59,6 +99,137 @@ status = "okay"; }; +&gmac0 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_pins>; + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + +&mdio0 { + phy0: ethernet-phy@1 { + reg = <1>; + interrupt-parent = <&gpio3>; + interrupts = <22 IRQ_TYPE_LEVEL_LOW>; + reset-gpios = <&gpio3 21 GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <50000>; + }; +}; + +&padctrl_aosys { + led_pins: led-0 { + led-pins { + pins = "AUDIO_PA8", /* GPIO4_8 */ + "AUDIO_PA9", /* GPIO4_9 */ + "AUDIO_PA10", /* GPIO4_10 */ + "AUDIO_PA11", /* GPIO4_11 */ + "AUDIO_PA12"; /* GPIO4_12 */ + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&padctrl0_apsys { + gmac0_pins: gmac0-0 { + tx-pins { + pins = "GMAC0_TX_CLK", + "GMAC0_TXEN", + "GMAC0_TXD0", + "GMAC0_TXD1", + "GMAC0_TXD2", + "GMAC0_TXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "GMAC0_RX_CLK", + "GMAC0_RXDV", + "GMAC0_RXD0", + "GMAC0_RXD1", + "GMAC0_RXD2", + "GMAC0_RXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mdc-pins { + pins = "GMAC0_MDC"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mdio-pins { + pins = "GMAC0_MDIO"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + + phy-reset-pins { + pins = "GMAC0_COL"; /* GPIO3_21 */ + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + phy-interrupt-pins { + pins = "GMAC0_CRS"; /* GPIO3_22 */ + function = "gpio"; + bias-pull-up; + drive-strength = <1>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + uart0_pins: uart0-0 { + tx-pins { + pins = "UART0_TXD"; + function = "uart"; + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "UART0_RXD"; + function = "uart"; + bias-pull-up; + drive-strength = <1>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; +}; + &sdio0 { bus-width = <4>; max-frequency = <198000000>; @@ -66,9 +237,7 @@ }; &uart0 { - status = "okay"; -}; - -&spi0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; status = "okay"; }; diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi index 78977bdbbe3d..8e76b63e0100 100644 --- a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi +++ b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi @@ -11,6 +11,11 @@ model = "Sipeed Lichee Module 4A"; compatible = "sipeed,lichee-module-4a", "thead,th1520"; + aliases { + ethernet0 = &gmac0; + ethernet1 = &gmac1; + }; + memory@0 { device_type = "memory"; reg = <0x0 0x00000000 0x2 0x00000000>; @@ -25,6 +30,12 @@ clock-frequency = <32768>; }; +&aogpio { + gpio-line-names = "", "", "", + "GPIO00", + "GPIO04"; +}; + &dmac0 { status = "okay"; }; @@ -39,6 +50,153 @@ status = "okay"; }; +&gmac0 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_pins>, <&mdio0_pins>; + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + +&gmac1 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_pins>; + phy-handle = <&phy1>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + +&gpio0 { + gpio-line-names = "", "", "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", "", "", + "", "", "", "", + "GPIO07", + "GPIO08", + "", + "GPIO01", + "GPIO02"; +}; + +&gpio1 { + gpio-line-names = "", "", "", + "GPIO11", + "GPIO12", + "GPIO13", + "GPIO14", + "", "", "", "", "", "", "", "", "", "", + "", "", "", "", "", + "GPIO06"; +}; + +&gpio2 { + gpio-line-names = "GPIO03", + "GPIO05"; +}; + +&gpio3 { + gpio-line-names = "", "", + "GPIO09", + "GPIO10"; +}; + +&mdio0 { + phy0: ethernet-phy@1 { + reg = <1>; + }; + + phy1: ethernet-phy@2 { + reg = <2>; + }; +}; + +&padctrl0_apsys { + gmac0_pins: gmac0-0 { + tx-pins { + pins = "GMAC0_TX_CLK", + "GMAC0_TXEN", + "GMAC0_TXD0", + "GMAC0_TXD1", + "GMAC0_TXD2", + "GMAC0_TXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "GMAC0_RX_CLK", + "GMAC0_RXDV", + "GMAC0_RXD0", + "GMAC0_RXD1", + "GMAC0_RXD2", + "GMAC0_RXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + gmac1_pins: gmac1-0 { + tx-pins { + pins = "GPIO2_18", /* GMAC1_TX_CLK */ + "GPIO2_20", /* GMAC1_TXEN */ + "GPIO2_21", /* GMAC1_TXD0 */ + "GPIO2_22", /* GMAC1_TXD1 */ + "GPIO2_23", /* GMAC1_TXD2 */ + "GPIO2_24"; /* GMAC1_TXD3 */ + function = "gmac1"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "GPIO2_19", /* GMAC1_RX_CLK */ + "GPIO2_25", /* GMAC1_RXDV */ + "GPIO2_30", /* GMAC1_RXD0 */ + "GPIO2_31", /* GMAC1_RXD1 */ + "GPIO3_0", /* GMAC1_RXD2 */ + "GPIO3_1"; /* GMAC1_RXD3 */ + function = "gmac1"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + mdio0_pins: mdio0-0 { + mdc-pins { + pins = "GMAC0_MDC"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mdio-pins { + pins = "GMAC0_MDIO"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; +}; + &sdio0 { bus-width = <4>; max-frequency = <198000000>; diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts b/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts index 7738d2895c5a..4020c727f09e 100644 --- a/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts +++ b/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts @@ -14,6 +14,8 @@ gpio1 = &gpio1; gpio2 = &gpio2; gpio3 = &gpio3; + gpio4 = &gpio4; + gpio5 = &aogpio; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; @@ -28,10 +30,32 @@ }; }; -&uart0 { - status = "okay"; +&padctrl0_apsys { + uart0_pins: uart0-0 { + tx-pins { + pins = "UART0_TXD"; + function = "uart"; + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "UART0_RXD"; + function = "uart"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; }; -&spi0 { +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; status = "okay"; }; diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi index 6992060e6a54..1db0054c4e09 100644 --- a/arch/riscv/boot/dts/thead/th1520.dtsi +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -6,6 +6,7 @@ #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/clock/thead,th1520-clk-ap.h> +#include <dt-bindings/power/thead,th1520-power.h> / { compatible = "thead,th1520"; @@ -216,6 +217,26 @@ #clock-cells = <0>; }; + aonsys_clk: clock-73728000 { + compatible = "fixed-clock"; + clock-frequency = <73728000>; + clock-output-names = "aonsys_clk"; + #clock-cells = <0>; + }; + + stmmac_axi_config: stmmac-axi-config { + snps,wr_osr_lmt = <15>; + snps,rd_osr_lmt = <15>; + snps,blen = <0 0 64 32 0 0 0>; + }; + + aon: aon { + compatible = "thead,th1520-aon"; + mboxes = <&mbox_910t 1>; + mbox-names = "aon"; + #power-domain-cells = <1>; + }; + soc { compatible = "simple-bus"; interrupt-parent = <&plic>; @@ -267,6 +288,50 @@ status = "disabled"; }; + gmac1: ethernet@ffe7060000 { + compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; + reg = <0xff 0xe7060000 0x0 0x2000>, <0xff 0xec004000 0x0 0x1000>; + reg-names = "dwmac", "apb"; + interrupts = <67 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>; + clock-names = "stmmaceth", "pclk"; + snps,pbl = <32>; + snps,fixed-burst; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,axi-config = <&stmmac_axi_config>; + status = "disabled"; + + mdio1: mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + + gmac0: ethernet@ffe7070000 { + compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; + reg = <0xff 0xe7070000 0x0 0x2000>, <0xff 0xec003000 0x0 0x1000>; + reg-names = "dwmac", "apb"; + interrupts = <66 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>; + clock-names = "stmmaceth", "pclk"; + snps,pbl = <32>; + snps,fixed-burst; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,axi-config = <&stmmac_axi_config>; + status = "disabled"; + + mdio0: mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + emmc: mmc@ffe7080000 { compatible = "thead,th1520-dwcmshc"; reg = <0xff 0xe7080000 0x0 0x10000>; @@ -316,18 +381,20 @@ status = "disabled"; }; - gpio2: gpio@ffe7f34000 { + gpio@ffe7f34000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xe7f34000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; clocks = <&clk CLK_GPIO2>; + clock-names = "bus"; - portc: gpio-controller@0 { + gpio2: gpio-controller@0 { compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; ngpios = <32>; + gpio-ranges = <&padctrl0_apsys 0 0 32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -335,18 +402,20 @@ }; }; - gpio3: gpio@ffe7f38000 { + gpio@ffe7f38000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xe7f38000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; clocks = <&clk CLK_GPIO3>; + clock-names = "bus"; - portd: gpio-controller@0 { + gpio3: gpio-controller@0 { compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - ngpios = <32>; + ngpios = <23>; + gpio-ranges = <&padctrl0_apsys 0 32 23>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -354,18 +423,27 @@ }; }; - gpio0: gpio@ffec005000 { + padctrl1_apsys: pinctrl@ffe7f3c000 { + compatible = "thead,th1520-pinctrl"; + reg = <0xff 0xe7f3c000 0x0 0x1000>; + clocks = <&clk CLK_PADCTRL1>; + thead,pad-group = <2>; + }; + + gpio@ffec005000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xec005000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; clocks = <&clk CLK_GPIO0>; + clock-names = "bus"; - porta: gpio-controller@0 { + gpio0: gpio-controller@0 { compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; ngpios = <32>; + gpio-ranges = <&padctrl1_apsys 0 0 32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -373,18 +451,20 @@ }; }; - gpio1: gpio@ffec006000 { + gpio@ffec006000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xec006000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; clocks = <&clk CLK_GPIO1>; + clock-names = "bus"; - portb: gpio-controller@0 { + gpio1: gpio-controller@0 { compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - ngpios = <32>; + ngpios = <31>; + gpio-ranges = <&padctrl1_apsys 0 32 31>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -392,6 +472,13 @@ }; }; + padctrl0_apsys: pinctrl@ffec007000 { + compatible = "thead,th1520-pinctrl"; + reg = <0xff 0xec007000 0x0 0x1000>; + clocks = <&clk CLK_PADCTRL0>; + thead,pad-group = <3>; + }; + uart2: serial@ffec010000 { compatible = "snps,dw-apb-uart"; reg = <0xff 0xec010000 0x0 0x4000>; @@ -410,6 +497,19 @@ #clock-cells = <1>; }; + rst: reset-controller@ffef528000 { + compatible = "thead,th1520-reset"; + reg = <0xff 0xef528000 0x0 0x4f>; + #reset-cells = <1>; + }; + + clk_vo: clock-controller@ffef528050 { + compatible = "thead,th1520-clk-vo"; + reg = <0xff 0xef528050 0x0 0xfb0>; + clocks = <&clk CLK_VIDEO_PLL>; + #clock-cells = <1>; + }; + dmac0: dma-controller@ffefc00000 { compatible = "snps,axi-dma-1.01a"; reg = <0xff 0xefc00000 0x0 0x1000>; @@ -520,17 +620,34 @@ status = "disabled"; }; - ao_gpio0: gpio@fffff41000 { + mbox_910t: mailbox@ffffc38000 { + compatible = "thead,th1520-mbox"; + reg = <0xff 0xffc38000 0x0 0x6000>, + <0xff 0xffc40000 0x0 0x6000>, + <0xff 0xffc4c000 0x0 0x2000>, + <0xff 0xffc54000 0x0 0x2000>; + reg-names = "local", "remote-icu0", "remote-icu1", "remote-icu2"; + clocks = <&clk CLK_MBOX0>, <&clk CLK_MBOX1>, <&clk CLK_MBOX2>, + <&clk CLK_MBOX3>; + clock-names = "clk-local", "clk-remote-icu0", "clk-remote-icu1", + "clk-remote-icu2"; + interrupt-parent = <&plic>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + #mbox-cells = <1>; + }; + + gpio@fffff41000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xfff41000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; - porte: gpio-controller@0 { + aogpio: gpio-controller@0 { compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - ngpios = <32>; + ngpios = <16>; + gpio-ranges = <&padctrl_aosys 0 9 16>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -538,17 +655,25 @@ }; }; - ao_gpio1: gpio@fffff52000 { + padctrl_aosys: pinctrl@fffff4a000 { + compatible = "thead,th1520-pinctrl"; + reg = <0xff 0xfff4a000 0x0 0x2000>; + clocks = <&aonsys_clk>; + thead,pad-group = <1>; + }; + + gpio@fffff52000 { compatible = "snps,dw-apb-gpio"; reg = <0xff 0xfff52000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; - portf: gpio-controller@0 { + gpio4: gpio-controller@0 { compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - ngpios = <32>; + ngpios = <23>; + gpio-ranges = <&padctrl_aosys 0 25 22>, <&padctrl_aosys 22 7 1>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 2341393cfac1..fe8bd8afb418 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -10,7 +10,6 @@ CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_CGROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y -CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y @@ -19,17 +18,14 @@ CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y -CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y CONFIG_ARCH_MICROCHIP=y -CONFIG_ARCH_RENESAS=y CONFIG_ARCH_SIFIVE=y CONFIG_ARCH_SOPHGO=y +CONFIG_ARCH_SPACEMIT=y CONFIG_SOC_STARFIVE=y CONFIG_ARCH_SUNXI=y CONFIG_ARCH_THEAD=y @@ -167,7 +163,10 @@ CONFIG_PINCTRL_SOPHGO_CV1800B=y CONFIG_PINCTRL_SOPHGO_CV1812H=y CONFIG_PINCTRL_SOPHGO_SG2000=y CONFIG_PINCTRL_SOPHGO_SG2002=y +CONFIG_PINCTRL_TH1520=y +CONFIG_GPIO_DWAPB=y CONFIG_GPIO_SIFIVE=y +CONFIG_GPIO_SPACEMIT_K1=y CONFIG_POWER_RESET_GPIO_RESTART=y CONFIG_SENSORS_SFCTEMP=m CONFIG_CPU_THERMAL=y @@ -180,6 +179,7 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_REGULATOR_AXP20X=y CONFIG_REGULATOR_GPIO=y CONFIG_MEDIA_SUPPORT=m +CONFIG_MEDIA_PLATFORM_SUPPORT=y CONFIG_VIDEO_CADENCE_CSI2RX=m CONFIG_DRM=m CONFIG_DRM_RADEON=m @@ -200,7 +200,6 @@ CONFIG_USB=y CONFIG_USB_OTG=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_XHCI_PLATFORM=y -# CONFIG_USB_XHCI_RCAR is not set CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -241,6 +240,7 @@ CONFIG_RTC_DRV_SUN6I=y CONFIG_DMADEVICES=y CONFIG_DMA_SUN6I=m CONFIG_DW_AXI_DMAC=y +CONFIG_DWMAC_THEAD=m CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y @@ -249,6 +249,8 @@ CONFIG_CLK_SOPHGO_CV1800=y CONFIG_CLK_SOPHGO_SG2042_PLL=y CONFIG_CLK_SOPHGO_SG2042_CLKGEN=y CONFIG_CLK_SOPHGO_SG2042_RPGATE=y +CONFIG_SPACEMIT_CCU=y +CONFIG_SPACEMIT_K1_CCU=y CONFIG_SUN8I_DE2_CCU=m CONFIG_SUN50I_IOMMU=y CONFIG_RPMSG_CHAR=y @@ -256,6 +258,7 @@ CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_PM_DEVFREQ=y CONFIG_IIO=y +CONFIG_THEAD_C900_ACLINT_SSWI=y CONFIG_PHY_SUN4I_USB=m CONFIG_PHY_STARFIVE_JH7110_DPHY_RX=m CONFIG_PHY_STARFIVE_JH7110_PCIE=m @@ -292,26 +295,7 @@ CONFIG_DEFAULT_SECURITY_DAC=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_PAGEALLOC=y -CONFIG_SCHED_STACK_END_CHECK=y -CONFIG_DEBUG_VM=y -CONFIG_DEBUG_VM_PGFLAGS=y -CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_DEBUG_PER_CPU_MAPS=y -CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_WQ_WATCHDOG=y -CONFIG_DEBUG_TIMEKEEPING=y -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_DEBUG_SPINLOCK=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_DEBUG_RWSEMS=y -CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_PLIST=y -CONFIG_DEBUG_SG=y -# CONFIG_RCU_TRACE is not set -CONFIG_RCU_EQS_DEBUG=y -# CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_MEMTEST=y diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig index 87ff5a1233af..ee18d1e333f2 100644 --- a/arch/riscv/configs/nommu_k210_defconfig +++ b/arch/riscv/configs/nommu_k210_defconfig @@ -35,7 +35,7 @@ CONFIG_NR_CPUS=2 CONFIG_CMDLINE="earlycon console=ttySIF0" CONFIG_CMDLINE_FORCE=y CONFIG_BUILTIN_DTB=y -CONFIG_BUILTIN_DTB_SOURCE="canaan/k210_generic" +CONFIG_BUILTIN_DTB_NAME="canaan/k210_generic" # CONFIG_SECCOMP is not set # CONFIG_STACKPROTECTOR is not set # CONFIG_GCC_PLUGINS is not set diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig index 95cbd574f291..e770d81b738e 100644 --- a/arch/riscv/configs/nommu_k210_sdcard_defconfig +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -27,7 +27,7 @@ CONFIG_NR_CPUS=2 CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro" CONFIG_CMDLINE_FORCE=y CONFIG_BUILTIN_DTB=y -CONFIG_BUILTIN_DTB_SOURCE="canaan/k210_generic" +CONFIG_BUILTIN_DTB_NAME="canaan/k210_generic" # CONFIG_SECCOMP is not set # CONFIG_STACKPROTECTOR is not set # CONFIG_GCC_PLUGINS is not set diff --git a/arch/riscv/configs/visionfive_defconfig b/arch/riscv/configs/visionfive_defconfig index fc831f261921..b7a26f86ae25 100644 --- a/arch/riscv/configs/visionfive_defconfig +++ b/arch/riscv/configs/visionfive_defconfig @@ -24,20 +24,23 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_RD_LZO is not set # CONFIG_RD_LZ4 is not set CONFIG_EXPERT=y -# CONFIG_SYSFS_SYSCALL is not set CONFIG_SOC_STARFIVE=y CONFIG_ERRATA_STARFIVE_JH7100=y CONFIG_NONPORTABLE=y CONFIG_SMP=y CONFIG_SCHED_MC=y CONFIG_NR_CPUS=4 +CONFIG_RISCV_TICKET_SPINLOCKS=y +# CONFIG_RISCV_ISA_SUPM is not set # CONFIG_RISCV_ISA_SVNAPOT is not set # CONFIG_RISCV_ISA_SVPBMT is not set # CONFIG_RISCV_ISA_V is not set # CONFIG_RISCV_ISA_ZAWRS is not set # CONFIG_RISCV_ISA_ZICBOM is not set # CONFIG_RISCV_ISA_ZICBOZ is not set +# CONFIG_RISCV_ISA_ZICBOP is not set # CONFIG_RISCV_ISA_VENDOR_EXT_ANDES is not set +# CONFIG_RISCV_ISA_VENDOR_EXT_THEAD is not set # CONFIG_COMPAT is not set # CONFIG_RISCV_ISA_FALLBACK is not set CONFIG_PM_DEBUG=y @@ -159,8 +162,8 @@ CONFIG_CPU_THERMAL=y CONFIG_WATCHDOG=y CONFIG_MFD_TPS65086=y CONFIG_DRM=y -CONFIG_DRM_I2C_NXP_TDA998X=y CONFIG_DRM_STARFIVE=y +CONFIG_DRM_I2C_NXP_TDA998X=y CONFIG_FB=y # CONFIG_FB_DEVICE is not set CONFIG_SOUND=y @@ -248,8 +251,8 @@ CONFIG_DEBUG_FS=y CONFIG_DEBUG_RODATA_TEST=y CONFIG_DEBUG_WX=y CONFIG_SOFTLOCKUP_DETECTOR=y +# CONFIG_DETECT_HUNG_TASK_BLOCKER is not set CONFIG_WQ_WATCHDOG=y -# CONFIG_SCHED_DEBUG is not set CONFIG_STACKTRACE=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/crypto/Kconfig b/arch/riscv/crypto/Kconfig index ad58dad9a580..cd9b776602f8 100644 --- a/arch/riscv/crypto/Kconfig +++ b/arch/riscv/crypto/Kconfig @@ -18,17 +18,6 @@ config CRYPTO_AES_RISCV64 - Zvkb vector crypto extension (CTR) - Zvkg vector crypto extension (XTS) -config CRYPTO_CHACHA_RISCV64 - tristate "Ciphers: ChaCha" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO - select CRYPTO_SKCIPHER - select CRYPTO_LIB_CHACHA_GENERIC - help - Length-preserving ciphers: ChaCha20 stream cipher algorithm - - Architecture: riscv64 using: - - Zvkb vector crypto extension - config CRYPTO_GHASH_RISCV64 tristate "Hash functions: GHASH" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO @@ -39,17 +28,6 @@ config CRYPTO_GHASH_RISCV64 Architecture: riscv64 using: - Zvkg vector crypto extension -config CRYPTO_SHA256_RISCV64 - tristate "Hash functions: SHA-224 and SHA-256" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO - select CRYPTO_SHA256 - help - SHA-224 and SHA-256 secure hash algorithm (FIPS 180) - - Architecture: riscv64 using: - - Zvknha or Zvknhb vector crypto extensions - - Zvkb vector crypto extension - config CRYPTO_SHA512_RISCV64 tristate "Hash functions: SHA-384 and SHA-512" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO @@ -65,7 +43,7 @@ config CRYPTO_SM3_RISCV64 tristate "Hash functions: SM3 (ShangMi 3)" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO select CRYPTO_HASH - select CRYPTO_SM3 + select CRYPTO_LIB_SM3 help SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012) diff --git a/arch/riscv/crypto/Makefile b/arch/riscv/crypto/Makefile index 247c7bc7288c..e10e8257734e 100644 --- a/arch/riscv/crypto/Makefile +++ b/arch/riscv/crypto/Makefile @@ -4,15 +4,9 @@ obj-$(CONFIG_CRYPTO_AES_RISCV64) += aes-riscv64.o aes-riscv64-y := aes-riscv64-glue.o aes-riscv64-zvkned.o \ aes-riscv64-zvkned-zvbb-zvkg.o aes-riscv64-zvkned-zvkb.o -obj-$(CONFIG_CRYPTO_CHACHA_RISCV64) += chacha-riscv64.o -chacha-riscv64-y := chacha-riscv64-glue.o chacha-riscv64-zvkb.o - obj-$(CONFIG_CRYPTO_GHASH_RISCV64) += ghash-riscv64.o ghash-riscv64-y := ghash-riscv64-glue.o ghash-riscv64-zvkg.o -obj-$(CONFIG_CRYPTO_SHA256_RISCV64) += sha256-riscv64.o -sha256-riscv64-y := sha256-riscv64-glue.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o - obj-$(CONFIG_CRYPTO_SHA512_RISCV64) += sha512-riscv64.o sha512-riscv64-y := sha512-riscv64-glue.o sha512-riscv64-zvknhb-zvkb.o diff --git a/arch/riscv/crypto/chacha-riscv64-glue.c b/arch/riscv/crypto/chacha-riscv64-glue.c deleted file mode 100644 index 10b46f36375a..000000000000 --- a/arch/riscv/crypto/chacha-riscv64-glue.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * ChaCha20 using the RISC-V vector crypto extensions - * - * Copyright (C) 2023 SiFive, Inc. - * Author: Jerry Shih <jerry.shih@sifive.com> - */ - -#include <asm/simd.h> -#include <asm/vector.h> -#include <crypto/internal/chacha.h> -#include <crypto/internal/skcipher.h> -#include <linux/linkage.h> -#include <linux/module.h> - -asmlinkage void chacha20_zvkb(const u32 key[8], const u8 *in, u8 *out, - size_t len, const u32 iv[4]); - -static int riscv64_chacha20_crypt(struct skcipher_request *req) -{ - u32 iv[CHACHA_IV_SIZE / sizeof(u32)]; - u8 block_buffer[CHACHA_BLOCK_SIZE]; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - const struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - unsigned int tail_bytes; - int err; - - iv[0] = get_unaligned_le32(req->iv); - iv[1] = get_unaligned_le32(req->iv + 4); - iv[2] = get_unaligned_le32(req->iv + 8); - iv[3] = get_unaligned_le32(req->iv + 12); - - err = skcipher_walk_virt(&walk, req, false); - while (walk.nbytes) { - nbytes = walk.nbytes & ~(CHACHA_BLOCK_SIZE - 1); - tail_bytes = walk.nbytes & (CHACHA_BLOCK_SIZE - 1); - kernel_vector_begin(); - if (nbytes) { - chacha20_zvkb(ctx->key, walk.src.virt.addr, - walk.dst.virt.addr, nbytes, iv); - iv[0] += nbytes / CHACHA_BLOCK_SIZE; - } - if (walk.nbytes == walk.total && tail_bytes > 0) { - memcpy(block_buffer, walk.src.virt.addr + nbytes, - tail_bytes); - chacha20_zvkb(ctx->key, block_buffer, block_buffer, - CHACHA_BLOCK_SIZE, iv); - memcpy(walk.dst.virt.addr + nbytes, block_buffer, - tail_bytes); - tail_bytes = 0; - } - kernel_vector_end(); - - err = skcipher_walk_done(&walk, tail_bytes); - } - - return err; -} - -static struct skcipher_alg riscv64_chacha_alg = { - .setkey = chacha20_setkey, - .encrypt = riscv64_chacha20_crypt, - .decrypt = riscv64_chacha20_crypt, - .min_keysize = CHACHA_KEY_SIZE, - .max_keysize = CHACHA_KEY_SIZE, - .ivsize = CHACHA_IV_SIZE, - .chunksize = CHACHA_BLOCK_SIZE, - .walksize = 4 * CHACHA_BLOCK_SIZE, - .base = { - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct chacha_ctx), - .cra_priority = 300, - .cra_name = "chacha20", - .cra_driver_name = "chacha20-riscv64-zvkb", - .cra_module = THIS_MODULE, - }, -}; - -static int __init riscv64_chacha_mod_init(void) -{ - if (riscv_isa_extension_available(NULL, ZVKB) && - riscv_vector_vlen() >= 128) - return crypto_register_skcipher(&riscv64_chacha_alg); - - return -ENODEV; -} - -static void __exit riscv64_chacha_mod_exit(void) -{ - crypto_unregister_skcipher(&riscv64_chacha_alg); -} - -module_init(riscv64_chacha_mod_init); -module_exit(riscv64_chacha_mod_exit); - -MODULE_DESCRIPTION("ChaCha20 (RISC-V accelerated)"); -MODULE_AUTHOR("Jerry Shih <jerry.shih@sifive.com>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("chacha20"); diff --git a/arch/riscv/crypto/ghash-riscv64-glue.c b/arch/riscv/crypto/ghash-riscv64-glue.c index 312e7891fd0a..d86073d25387 100644 --- a/arch/riscv/crypto/ghash-riscv64-glue.c +++ b/arch/riscv/crypto/ghash-riscv64-glue.c @@ -11,11 +11,16 @@ #include <asm/simd.h> #include <asm/vector.h> +#include <crypto/b128ops.h> +#include <crypto/gf128mul.h> #include <crypto/ghash.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> -#include <linux/linkage.h> +#include <crypto/utils.h> +#include <linux/errno.h> +#include <linux/kernel.h> #include <linux/module.h> +#include <linux/string.h> asmlinkage void ghash_zvkg(be128 *accumulator, const be128 *key, const u8 *data, size_t len); @@ -26,8 +31,6 @@ struct riscv64_ghash_tfm_ctx { struct riscv64_ghash_desc_ctx { be128 accumulator; - u8 buffer[GHASH_BLOCK_SIZE]; - u32 bytes; }; static int riscv64_ghash_setkey(struct crypto_shash *tfm, const u8 *key, @@ -78,50 +81,24 @@ static int riscv64_ghash_update(struct shash_desc *desc, const u8 *src, { const struct riscv64_ghash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct riscv64_ghash_desc_ctx *dctx = shash_desc_ctx(desc); - unsigned int len; - - if (dctx->bytes) { - if (dctx->bytes + srclen < GHASH_BLOCK_SIZE) { - memcpy(dctx->buffer + dctx->bytes, src, srclen); - dctx->bytes += srclen; - return 0; - } - memcpy(dctx->buffer + dctx->bytes, src, - GHASH_BLOCK_SIZE - dctx->bytes); - riscv64_ghash_blocks(tctx, dctx, dctx->buffer, - GHASH_BLOCK_SIZE); - src += GHASH_BLOCK_SIZE - dctx->bytes; - srclen -= GHASH_BLOCK_SIZE - dctx->bytes; - dctx->bytes = 0; - } - - len = round_down(srclen, GHASH_BLOCK_SIZE); - if (len) { - riscv64_ghash_blocks(tctx, dctx, src, len); - src += len; - srclen -= len; - } - if (srclen) { - memcpy(dctx->buffer, src, srclen); - dctx->bytes = srclen; - } - - return 0; + riscv64_ghash_blocks(tctx, dctx, src, + round_down(srclen, GHASH_BLOCK_SIZE)); + return srclen - round_down(srclen, GHASH_BLOCK_SIZE); } -static int riscv64_ghash_final(struct shash_desc *desc, u8 *out) +static int riscv64_ghash_finup(struct shash_desc *desc, const u8 *src, + unsigned int len, u8 *out) { const struct riscv64_ghash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct riscv64_ghash_desc_ctx *dctx = shash_desc_ctx(desc); - int i; - if (dctx->bytes) { - for (i = dctx->bytes; i < GHASH_BLOCK_SIZE; i++) - dctx->buffer[i] = 0; + if (len) { + u8 buf[GHASH_BLOCK_SIZE] = {}; - riscv64_ghash_blocks(tctx, dctx, dctx->buffer, - GHASH_BLOCK_SIZE); + memcpy(buf, src, len); + riscv64_ghash_blocks(tctx, dctx, buf, GHASH_BLOCK_SIZE); + memzero_explicit(buf, sizeof(buf)); } memcpy(out, &dctx->accumulator, GHASH_DIGEST_SIZE); @@ -131,7 +108,7 @@ static int riscv64_ghash_final(struct shash_desc *desc, u8 *out) static struct shash_alg riscv64_ghash_alg = { .init = riscv64_ghash_init, .update = riscv64_ghash_update, - .final = riscv64_ghash_final, + .finup = riscv64_ghash_finup, .setkey = riscv64_ghash_setkey, .descsize = sizeof(struct riscv64_ghash_desc_ctx), .digestsize = GHASH_DIGEST_SIZE, @@ -139,6 +116,7 @@ static struct shash_alg riscv64_ghash_alg = { .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct riscv64_ghash_tfm_ctx), .cra_priority = 300, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_name = "ghash", .cra_driver_name = "ghash-riscv64-zvkg", .cra_module = THIS_MODULE, diff --git a/arch/riscv/crypto/sha256-riscv64-glue.c b/arch/riscv/crypto/sha256-riscv64-glue.c deleted file mode 100644 index 71e051e40a64..000000000000 --- a/arch/riscv/crypto/sha256-riscv64-glue.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * SHA-256 and SHA-224 using the RISC-V vector crypto extensions - * - * Copyright (C) 2022 VRULL GmbH - * Author: Heiko Stuebner <heiko.stuebner@vrull.eu> - * - * Copyright (C) 2023 SiFive, Inc. - * Author: Jerry Shih <jerry.shih@sifive.com> - */ - -#include <asm/simd.h> -#include <asm/vector.h> -#include <crypto/internal/hash.h> -#include <crypto/internal/simd.h> -#include <crypto/sha256_base.h> -#include <linux/linkage.h> -#include <linux/module.h> - -/* - * Note: the asm function only uses the 'state' field of struct sha256_state. - * It is assumed to be the first field. - */ -asmlinkage void sha256_transform_zvknha_or_zvknhb_zvkb( - struct sha256_state *state, const u8 *data, int num_blocks); - -static int riscv64_sha256_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - /* - * Ensure struct sha256_state begins directly with the SHA-256 - * 256-bit internal state, as this is what the asm function expects. - */ - BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - - if (crypto_simd_usable()) { - kernel_vector_begin(); - sha256_base_do_update(desc, data, len, - sha256_transform_zvknha_or_zvknhb_zvkb); - kernel_vector_end(); - } else { - crypto_sha256_update(desc, data, len); - } - return 0; -} - -static int riscv64_sha256_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - if (crypto_simd_usable()) { - kernel_vector_begin(); - if (len) - sha256_base_do_update( - desc, data, len, - sha256_transform_zvknha_or_zvknhb_zvkb); - sha256_base_do_finalize( - desc, sha256_transform_zvknha_or_zvknhb_zvkb); - kernel_vector_end(); - - return sha256_base_finish(desc, out); - } - - return crypto_sha256_finup(desc, data, len, out); -} - -static int riscv64_sha256_final(struct shash_desc *desc, u8 *out) -{ - return riscv64_sha256_finup(desc, NULL, 0, out); -} - -static int riscv64_sha256_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return sha256_base_init(desc) ?: - riscv64_sha256_finup(desc, data, len, out); -} - -static struct shash_alg riscv64_sha256_algs[] = { - { - .init = sha256_base_init, - .update = riscv64_sha256_update, - .final = riscv64_sha256_final, - .finup = riscv64_sha256_finup, - .digest = riscv64_sha256_digest, - .descsize = sizeof(struct sha256_state), - .digestsize = SHA256_DIGEST_SIZE, - .base = { - .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_priority = 300, - .cra_name = "sha256", - .cra_driver_name = "sha256-riscv64-zvknha_or_zvknhb-zvkb", - .cra_module = THIS_MODULE, - }, - }, { - .init = sha224_base_init, - .update = riscv64_sha256_update, - .final = riscv64_sha256_final, - .finup = riscv64_sha256_finup, - .descsize = sizeof(struct sha256_state), - .digestsize = SHA224_DIGEST_SIZE, - .base = { - .cra_blocksize = SHA224_BLOCK_SIZE, - .cra_priority = 300, - .cra_name = "sha224", - .cra_driver_name = "sha224-riscv64-zvknha_or_zvknhb-zvkb", - .cra_module = THIS_MODULE, - }, - }, -}; - -static int __init riscv64_sha256_mod_init(void) -{ - /* Both zvknha and zvknhb provide the SHA-256 instructions. */ - if ((riscv_isa_extension_available(NULL, ZVKNHA) || - riscv_isa_extension_available(NULL, ZVKNHB)) && - riscv_isa_extension_available(NULL, ZVKB) && - riscv_vector_vlen() >= 128) - return crypto_register_shashes(riscv64_sha256_algs, - ARRAY_SIZE(riscv64_sha256_algs)); - - return -ENODEV; -} - -static void __exit riscv64_sha256_mod_exit(void) -{ - crypto_unregister_shashes(riscv64_sha256_algs, - ARRAY_SIZE(riscv64_sha256_algs)); -} - -module_init(riscv64_sha256_mod_init); -module_exit(riscv64_sha256_mod_exit); - -MODULE_DESCRIPTION("SHA-256 (RISC-V accelerated)"); -MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("sha256"); -MODULE_ALIAS_CRYPTO("sha224"); diff --git a/arch/riscv/crypto/sha512-riscv64-glue.c b/arch/riscv/crypto/sha512-riscv64-glue.c index 43b56a08aeb5..4634fca78ae2 100644 --- a/arch/riscv/crypto/sha512-riscv64-glue.c +++ b/arch/riscv/crypto/sha512-riscv64-glue.c @@ -14,7 +14,7 @@ #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sha512_base.h> -#include <linux/linkage.h> +#include <linux/kernel.h> #include <linux/module.h> /* @@ -24,8 +24,8 @@ asmlinkage void sha512_transform_zvknhb_zvkb( struct sha512_state *state, const u8 *data, int num_blocks); -static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static void sha512_block(struct sha512_state *state, const u8 *data, + int num_blocks) { /* * Ensure struct sha512_state begins directly with the SHA-512 @@ -35,35 +35,24 @@ static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, if (crypto_simd_usable()) { kernel_vector_begin(); - sha512_base_do_update(desc, data, len, - sha512_transform_zvknhb_zvkb); + sha512_transform_zvknhb_zvkb(state, data, num_blocks); kernel_vector_end(); } else { - crypto_sha512_update(desc, data, len); + sha512_generic_block_fn(state, data, num_blocks); } - return 0; } -static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - if (crypto_simd_usable()) { - kernel_vector_begin(); - if (len) - sha512_base_do_update(desc, data, len, - sha512_transform_zvknhb_zvkb); - sha512_base_do_finalize(desc, sha512_transform_zvknhb_zvkb); - kernel_vector_end(); - - return sha512_base_finish(desc, out); - } - - return crypto_sha512_finup(desc, data, len, out); + return sha512_base_do_update_blocks(desc, data, len, sha512_block); } -static int riscv64_sha512_final(struct shash_desc *desc, u8 *out) +static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - return riscv64_sha512_finup(desc, NULL, 0, out); + sha512_base_do_finup(desc, data, len, sha512_block); + return sha512_base_finish(desc, out); } static int riscv64_sha512_digest(struct shash_desc *desc, const u8 *data, @@ -77,14 +66,15 @@ static struct shash_alg riscv64_sha512_algs[] = { { .init = sha512_base_init, .update = riscv64_sha512_update, - .final = riscv64_sha512_final, .finup = riscv64_sha512_finup, .digest = riscv64_sha512_digest, - .descsize = sizeof(struct sha512_state), + .descsize = SHA512_STATE_SIZE, .digestsize = SHA512_DIGEST_SIZE, .base = { .cra_blocksize = SHA512_BLOCK_SIZE, .cra_priority = 300, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | + CRYPTO_AHASH_ALG_FINUP_MAX, .cra_name = "sha512", .cra_driver_name = "sha512-riscv64-zvknhb-zvkb", .cra_module = THIS_MODULE, @@ -92,13 +82,14 @@ static struct shash_alg riscv64_sha512_algs[] = { }, { .init = sha384_base_init, .update = riscv64_sha512_update, - .final = riscv64_sha512_final, .finup = riscv64_sha512_finup, - .descsize = sizeof(struct sha512_state), + .descsize = SHA512_STATE_SIZE, .digestsize = SHA384_DIGEST_SIZE, .base = { .cra_blocksize = SHA384_BLOCK_SIZE, .cra_priority = 300, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | + CRYPTO_AHASH_ALG_FINUP_MAX, .cra_name = "sha384", .cra_driver_name = "sha384-riscv64-zvknhb-zvkb", .cra_module = THIS_MODULE, diff --git a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S index 3a9ae210f915..89f4a10d12dd 100644 --- a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S +++ b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S @@ -43,7 +43,7 @@ // - RISC-V Vector SHA-2 Secure Hash extension ('Zvknhb') // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') -#include <linux/cfi_types.h> +#include <linux/linkage.h> .text .option arch, +zvknhb, +zvkb @@ -95,7 +95,7 @@ // void sha512_transform_zvknhb_zvkb(u64 state[8], const u8 *data, // int num_blocks); -SYM_TYPED_FUNC_START(sha512_transform_zvknhb_zvkb) +SYM_FUNC_START(sha512_transform_zvknhb_zvkb) // Setup mask for the vmerge to replace the first word (idx==0) in // message scheduling. There are 4 words, so an 8-bit mask suffices. diff --git a/arch/riscv/crypto/sm3-riscv64-glue.c b/arch/riscv/crypto/sm3-riscv64-glue.c index e1737a970c7c..abdfe4a63a27 100644 --- a/arch/riscv/crypto/sm3-riscv64-glue.c +++ b/arch/riscv/crypto/sm3-riscv64-glue.c @@ -13,8 +13,9 @@ #include <asm/vector.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> +#include <crypto/sm3.h> #include <crypto/sm3_base.h> -#include <linux/linkage.h> +#include <linux/kernel.h> #include <linux/module.h> /* @@ -24,8 +25,8 @@ asmlinkage void sm3_transform_zvksh_zvkb( struct sm3_state *state, const u8 *data, int num_blocks); -static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static void sm3_block(struct sm3_state *state, const u8 *data, + int num_blocks) { /* * Ensure struct sm3_state begins directly with the SM3 @@ -35,52 +36,36 @@ static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data, if (crypto_simd_usable()) { kernel_vector_begin(); - sm3_base_do_update(desc, data, len, sm3_transform_zvksh_zvkb); + sm3_transform_zvksh_zvkb(state, data, num_blocks); kernel_vector_end(); } else { - sm3_update(shash_desc_ctx(desc), data, len); + sm3_block_generic(state, data, num_blocks); } - return 0; } -static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - struct sm3_state *ctx; - - if (crypto_simd_usable()) { - kernel_vector_begin(); - if (len) - sm3_base_do_update(desc, data, len, - sm3_transform_zvksh_zvkb); - sm3_base_do_finalize(desc, sm3_transform_zvksh_zvkb); - kernel_vector_end(); - - return sm3_base_finish(desc, out); - } - - ctx = shash_desc_ctx(desc); - if (len) - sm3_update(ctx, data, len); - sm3_final(ctx, out); - - return 0; + return sm3_base_do_update_blocks(desc, data, len, sm3_block); } -static int riscv64_sm3_final(struct shash_desc *desc, u8 *out) +static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - return riscv64_sm3_finup(desc, NULL, 0, out); + sm3_base_do_finup(desc, data, len, sm3_block); + return sm3_base_finish(desc, out); } static struct shash_alg riscv64_sm3_alg = { .init = sm3_base_init, .update = riscv64_sm3_update, - .final = riscv64_sm3_final, .finup = riscv64_sm3_finup, - .descsize = sizeof(struct sm3_state), + .descsize = SM3_STATE_SIZE, .digestsize = SM3_DIGEST_SIZE, .base = { .cra_blocksize = SM3_BLOCK_SIZE, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | + CRYPTO_AHASH_ALG_FINUP_MAX, .cra_priority = 300, .cra_name = "sm3", .cra_driver_name = "sm3-riscv64-zvksh-zvkb", diff --git a/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S b/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S index a2b65d961c04..4fe754846f65 100644 --- a/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S +++ b/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S @@ -43,7 +43,7 @@ // - RISC-V Vector SM3 Secure Hash extension ('Zvksh') // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') -#include <linux/cfi_types.h> +#include <linux/linkage.h> .text .option arch, +zvksh, +zvkb @@ -81,7 +81,7 @@ .endm // void sm3_transform_zvksh_zvkb(u32 state[8], const u8 *data, int num_blocks); -SYM_TYPED_FUNC_START(sm3_transform_zvksh_zvkb) +SYM_FUNC_START(sm3_transform_zvksh_zvkb) // Load the state and endian-swap each 32-bit word. vsetivli zero, 8, e32, m2, ta, ma diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile index 8a2739485123..bc6c77ba837d 100644 --- a/arch/riscv/errata/Makefile +++ b/arch/riscv/errata/Makefile @@ -1,5 +1,15 @@ ifdef CONFIG_RELOCATABLE -KBUILD_CFLAGS += -fno-pie +# We can't use PIC/PIE when handling early-boot errata parsing, as the kernel +# doesn't have a GOT setup at that point. So instead just use medany: it's +# usually position-independent, so it should be good enough for the errata +# handling. +KBUILD_CFLAGS += -fno-pie -mcmodel=medany +endif + +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +ifdef CONFIG_FORTIFY_SOURCE +KBUILD_CFLAGS += -D__NO_FORTIFY +endif endif obj-$(CONFIG_ERRATA_ANDES) += andes/ diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c index fc1a34faa5f3..dcc9d1ee5ffd 100644 --- a/arch/riscv/errata/andes/errata.c +++ b/arch/riscv/errata/andes/errata.c @@ -13,7 +13,7 @@ #include <asm/alternative.h> #include <asm/cacheflush.h> #include <asm/errata_list.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/processor.h> #include <asm/sbi.h> #include <asm/vendorid_list.h> diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index cea3b96ade11..38aac2c47845 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -8,7 +8,7 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/bug.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/vendorid_list.h> #include <asm/errata_list.h> diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index f5120e07c318..0b942183f708 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -10,13 +10,14 @@ #include <linux/string.h> #include <linux/uaccess.h> #include <asm/alternative.h> +#include <asm/bugs.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/dma-noncoherent.h> #include <asm/errata_list.h> #include <asm/hwprobe.h> #include <asm/io.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/vendorid_list.h> #include <asm/vendor_extensions.h> @@ -142,6 +143,31 @@ static bool errata_probe_pmu(unsigned int stage, return true; } +static bool errata_probe_ghostwrite(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_GHOSTWRITE)) + return false; + + /* + * target-c9xx cores report arch_id and impid as 0 + * + * While ghostwrite may not affect all c9xx cores that implement + * xtheadvector, there is no futher granularity than c9xx. Assume + * vulnerable for this entire class of processors when xtheadvector is + * enabled. + */ + if (arch_id != 0 || impid != 0) + return false; + + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + ghostwrite_set_vulnerable(); + + return true; +} + static u32 thead_errata_probe(unsigned int stage, unsigned long archid, unsigned long impid) { @@ -155,6 +181,8 @@ static u32 thead_errata_probe(unsigned int stage, if (errata_probe_pmu(stage, archid, impid)) cpu_req_errata |= BIT(ERRATA_THEAD_PMU); + errata_probe_ghostwrite(stage, archid, impid); + return cpu_req_errata; } diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 1461af12da6e..bd5fc9403295 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -4,12 +4,15 @@ syscall-y += syscall_table_64.h generic-y += early_ioremap.h generic-y += flat.h +generic-y += fprobe.h generic-y += kvm_para.h generic-y += mmzone.h +generic-y += mcs_spinlock.h generic-y += parport.h -generic-y += spinlock.h generic-y += spinlock_types.h +generic-y += ticket_spinlock.h generic-y += qrwlock.h generic-y += qrwlock_types.h +generic-y += qspinlock.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 721ec275ce57..231d777d936c 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -115,24 +115,19 @@ \old_c .endm -#define _ALTERNATIVE_CFG(old_c, ...) \ - ALTERNATIVE_CFG old_c - -#define _ALTERNATIVE_CFG_2(old_c, ...) \ - ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG(old_c, ...) ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG_2(old_c, ...) ALTERNATIVE_CFG old_c #else /* !__ASSEMBLY__ */ -#define __ALTERNATIVE_CFG(old_c) \ - old_c "\n" +#define __ALTERNATIVE_CFG(old_c, ...) old_c "\n" +#define __ALTERNATIVE_CFG_2(old_c, ...) old_c "\n" -#define _ALTERNATIVE_CFG(old_c, ...) \ - __ALTERNATIVE_CFG(old_c) +#endif /* __ASSEMBLY__ */ -#define _ALTERNATIVE_CFG_2(old_c, ...) \ - __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG(old_c, ...) __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG_2(old_c, ...) __ALTERNATIVE_CFG_2(old_c) -#endif /* __ASSEMBLY__ */ #endif /* CONFIG_RISCV_ALTERNATIVE */ /* diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h index 613769b9cdc9..0e7cdbbec8ef 100644 --- a/arch/riscv/include/asm/arch_hweight.h +++ b/arch/riscv/include/asm/arch_hweight.h @@ -19,7 +19,7 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w) { -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -50,7 +50,7 @@ static inline unsigned int __arch_hweight8(unsigned int w) #if BITS_PER_LONG == 64 static __always_inline unsigned long __arch_hweight64(__u64 w) { -# ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, RISCV_ISA_EXT_ZBB, 1) : : : : legacy); @@ -64,7 +64,7 @@ static __always_inline unsigned long __arch_hweight64(__u64 w) return w; legacy: -# endif +#endif return __sw_hweight64(w); } #else /* BITS_PER_LONG == 64 */ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index cd627ec289f1..a9988bf21ec8 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -12,7 +12,7 @@ long long __ashlti3(long long a, int b); #ifdef CONFIG_RISCV_ISA_V #ifdef CONFIG_MMU -asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n); +asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n, bool enable_sum); #endif /* CONFIG_MMU */ void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1, @@ -52,6 +52,8 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs); +asmlinkage void ret_from_fork_user(struct pt_regs *regs); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 776354895b81..a8a2af6dfe9d 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -27,6 +27,7 @@ #define REG_ASM __REG_SEL(.dword, .word) #define SZREG __REG_SEL(8, 4) #define LGREG __REG_SEL(3, 2) +#define SRLI __REG_SEL(srliw, srli) #if __SIZEOF_POINTER__ == 8 #ifdef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index e1d9bf1deca6..b8c5726d86ac 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -14,11 +14,6 @@ #include <asm/cmpxchg.h> #include <asm/fence.h> -#define nop() __asm__ __volatile__ ("nop") -#define __nops(n) ".rept " #n "\nnop\n.endr\n" -#define nops(n) __asm__ __volatile__ (__nops(n)) - - /* These barriers need to enforce ordering on both devices or memory. */ #define __mb() RISCV_FENCE(iorw, iorw) #define __rmb() RISCV_FENCE(ir, ir) diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index fae152ea0508..d59310f74c2b 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -15,7 +15,7 @@ #include <asm/barrier.h> #include <asm/bitsperlong.h> -#if !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) +#if !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) #include <asm-generic/bitops/__ffs.h> #include <asm-generic/bitops/__fls.h> #include <asm-generic/bitops/ffs.h> @@ -175,7 +175,7 @@ legacy: variable_fls(x_); \ }) -#endif /* !defined(CONFIG_RISCV_ISA_ZBB) || defined(NO_ALTERNATIVE) */ +#endif /* !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) */ #include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/fls64.h> @@ -226,9 +226,9 @@ legacy: * @nr: Bit to set * @addr: Address to count from * - * This operation may be reordered on other architectures than x86. + * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(or, __NOP, nr, addr); } @@ -238,9 +238,9 @@ static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) * @nr: Bit to clear * @addr: Address to count from * - * This operation can be reordered on other architectures other than x86. + * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(and, __NOT, nr, addr); } @@ -253,7 +253,7 @@ static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) +static __always_inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) { return __test_and_op_bit(xor, __NOP, nr, addr); } @@ -270,7 +270,7 @@ static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void arch_set_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_set_bit(int nr, volatile unsigned long *addr) { __op_bit(or, __NOP, nr, addr); } @@ -284,7 +284,7 @@ static inline void arch_set_bit(int nr, volatile unsigned long *addr) * on non x86 architectures, so if you are writing portable code, * make sure not to rely on its reordering guarantees. */ -static inline void arch_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_clear_bit(int nr, volatile unsigned long *addr) { __op_bit(and, __NOT, nr, addr); } @@ -298,7 +298,7 @@ static inline void arch_clear_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void arch_change_bit(int nr, volatile unsigned long *addr) +static __always_inline void arch_change_bit(int nr, volatile unsigned long *addr) { __op_bit(xor, __NOP, nr, addr); } @@ -311,7 +311,7 @@ static inline void arch_change_bit(int nr, volatile unsigned long *addr) * This operation is atomic and provides acquire barrier semantics. * It can be used to implement bit locks. */ -static inline int arch_test_and_set_bit_lock( +static __always_inline int arch_test_and_set_bit_lock( unsigned long nr, volatile unsigned long *addr) { return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq); @@ -324,7 +324,7 @@ static inline int arch_test_and_set_bit_lock( * * This operation is atomic and provides release barrier semantics. */ -static inline void arch_clear_bit_unlock( +static __always_inline void arch_clear_bit_unlock( unsigned long nr, volatile unsigned long *addr) { __op_bit_ord(and, __NOT, nr, addr, .rl); @@ -345,13 +345,13 @@ static inline void arch_clear_bit_unlock( * non-atomic property here: it's a lot more instructions and we still have to * provide release semantics anyway. */ -static inline void arch___clear_bit_unlock( +static __always_inline void arch___clear_bit_unlock( unsigned long nr, volatile unsigned long *addr) { arch_clear_bit_unlock(nr, addr); } -static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, +static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { unsigned long res; diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h new file mode 100644 index 000000000000..17ca0a947730 --- /dev/null +++ b/arch/riscv/include/asm/bugs.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Interface for managing mitigations for riscv vulnerabilities. + * + * Copyright (C) 2024 Rivos Inc. + */ + +#ifndef __ASM_BUGS_H +#define __ASM_BUGS_H + +/* Watch out, ordering is important here. */ +enum mitigation_state { + UNAFFECTED, + MITIGATED, + VULNERABLE, +}; + +void ghostwrite_set_vulnerable(void); +bool ghostwrite_enable_mitigation(void); +enum mitigation_state ghostwrite_get_state(void); + +#endif /* __ASM_BUGS_H */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8de73f91bfa3..6086b38d5427 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page) flush_dcache_folio(page_folio(page)); } -/* - * RISC-V doesn't have an instruction to flush parts of the instruction cache, - * so instead we just flush the whole thing. - */ -#define flush_icache_range(start, end) flush_icache_all() #define flush_icache_user_page(vma, pg, addr, len) \ do { \ if (vma->vm_flags & VM_EXEC) \ @@ -78,8 +73,19 @@ void flush_icache_mm(struct mm_struct *mm, bool local); #endif /* CONFIG_SMP */ +/* + * RISC-V doesn't have an instruction to flush parts of the instruction cache, + * so instead we just flush the whole thing. + */ +#define flush_icache_range flush_icache_range +static inline void flush_icache_range(unsigned long start, unsigned long end) +{ + flush_icache_all(); +} + extern unsigned int riscv_cbom_block_size; extern unsigned int riscv_cboz_block_size; +extern unsigned int riscv_cbop_block_size; void riscv_init_cbo_blocksizes(void); #ifdef CONFIG_RISCV_DMA_NONCOHERENT diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h index 88e6f1499e88..da378856f1d5 100644 --- a/arch/riscv/include/asm/checksum.h +++ b/arch/riscv/include/asm/checksum.h @@ -49,8 +49,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) * ZBB only saves three instructions on 32-bit and five on 64-bit so not * worth checking if supported without Alternatives. */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index ebbce134917c..0b749e710216 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -12,30 +12,45 @@ #include <asm/fence.h> #include <asm/hwcap.h> #include <asm/insn-def.h> - -#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n) \ -({ \ - u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ - ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ - ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \ - << __s; \ - ulong __newx = (ulong)(n) << __s; \ - ulong __retx; \ - ulong __rc; \ - \ - __asm__ __volatile__ ( \ - prepend \ - "0: lr.w %0, %2\n" \ - " and %1, %0, %z4\n" \ - " or %1, %1, %z3\n" \ - " sc.w" sc_sfx " %1, %1, %2\n" \ - " bnez %1, 0b\n" \ - append \ - : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ - : "rJ" (__newx), "rJ" (~__mask) \ - : "memory"); \ - \ - r = (__typeof__(*(p)))((__retx & __mask) >> __s); \ +#include <asm/cpufeature-macros.h> +#include <asm/processor.h> + +#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append, \ + swap_append, r, p, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) { \ + __asm__ __volatile__ ( \ + prepend \ + " amoswap" swap_sfx " %0, %z2, %1\n" \ + swap_append \ + : "=&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ + ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ + ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \ + << __s; \ + ulong __newx = (ulong)(n) << __s; \ + ulong __retx; \ + ulong __rc; \ + \ + __asm__ __volatile__ ( \ + prepend \ + PREFETCHW_ASM(%5) \ + "0: lr.w %0, %2\n" \ + " and %1, %0, %z4\n" \ + " or %1, %1, %z3\n" \ + " sc.w" sc_sfx " %1, %1, %2\n" \ + " bnez %1, 0b\n" \ + sc_append \ + : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ + : "rJ" (__newx), "rJ" (~__mask), "rJ" (__ptr32b) \ + : "memory"); \ + \ + r = (__typeof__(*(p)))((__retx & __mask) >> __s); \ + } \ }) #define __arch_xchg(sfx, prepend, append, r, p, n) \ @@ -58,8 +73,13 @@ \ switch (sizeof(*__ptr)) { \ case 1: \ + __arch_xchg_masked(sc_sfx, ".b" swap_sfx, \ + prepend, sc_append, swap_append, \ + __ret, __ptr, __new); \ + break; \ case 2: \ - __arch_xchg_masked(sc_sfx, prepend, sc_append, \ + __arch_xchg_masked(sc_sfx, ".h" swap_sfx, \ + prepend, sc_append, swap_append, \ __ret, __ptr, __new); \ break; \ case 4: \ @@ -106,55 +126,90 @@ * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. */ - -#define __arch_cmpxchg_masked(sc_sfx, prepend, append, r, p, o, n) \ -({ \ - u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ - ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ - ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \ - << __s; \ - ulong __newx = (ulong)(n) << __s; \ - ulong __oldx = (ulong)(o) << __s; \ - ulong __retx; \ - ulong __rc; \ - \ - __asm__ __volatile__ ( \ - prepend \ - "0: lr.w %0, %2\n" \ - " and %1, %0, %z5\n" \ - " bne %1, %z3, 1f\n" \ - " and %1, %0, %z6\n" \ - " or %1, %1, %z4\n" \ - " sc.w" sc_sfx " %1, %1, %2\n" \ - " bnez %1, 0b\n" \ - append \ - "1:\n" \ - : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ - : "rJ" ((long)__oldx), "rJ" (__newx), \ - "rJ" (__mask), "rJ" (~__mask) \ - : "memory"); \ - \ - r = (__typeof__(*(p)))((__retx & __mask) >> __s); \ +#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + r, p, o, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \ + IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \ + r = o; \ + \ + __asm__ __volatile__ ( \ + cas_prepend \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + cas_append \ + : "+&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ + ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ + ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \ + << __s; \ + ulong __newx = (ulong)(n) << __s; \ + ulong __oldx = (ulong)(o) << __s; \ + ulong __retx; \ + ulong __rc; \ + \ + __asm__ __volatile__ ( \ + sc_prepend \ + "0: lr.w %0, %2\n" \ + " and %1, %0, %z5\n" \ + " bne %1, %z3, 1f\n" \ + " and %1, %0, %z6\n" \ + " or %1, %1, %z4\n" \ + " sc.w" sc_sfx " %1, %1, %2\n" \ + " bnez %1, 0b\n" \ + sc_append \ + "1:\n" \ + : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ + : "rJ" ((long)__oldx), "rJ" (__newx), \ + "rJ" (__mask), "rJ" (~__mask) \ + : "memory"); \ + \ + r = (__typeof__(*(p)))((__retx & __mask) >> __s); \ + } \ }) -#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n) \ +#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + r, p, co, o, n) \ ({ \ - register unsigned int __rc; \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \ + r = o; \ \ - __asm__ __volatile__ ( \ - prepend \ - "0: lr" lr_sfx " %0, %2\n" \ - " bne %0, %z3, 1f\n" \ - " sc" sc_sfx " %1, %z4, %2\n" \ - " bnez %1, 0b\n" \ - append \ - "1:\n" \ - : "=&r" (r), "=&r" (__rc), "+A" (*(p)) \ - : "rJ" (co o), "rJ" (n) \ - : "memory"); \ + __asm__ __volatile__ ( \ + cas_prepend \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + cas_append \ + : "+&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + register unsigned int __rc; \ + \ + __asm__ __volatile__ ( \ + sc_prepend \ + "0: lr" lr_sfx " %0, %2\n" \ + " bne %0, %z3, 1f\n" \ + " sc" sc_sfx " %1, %z4, %2\n" \ + " bnez %1, 0b\n" \ + sc_append \ + "1:\n" \ + : "=&r" (r), "=&r" (__rc), "+A" (*(p)) \ + : "rJ" (co o), "rJ" (n) \ + : "memory"); \ + } \ }) -#define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append) \ +#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ __typeof__(*(__ptr)) __old = (old); \ @@ -163,17 +218,28 @@ \ switch (sizeof(*__ptr)) { \ case 1: \ + __arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, __old, __new); \ + break; \ case 2: \ - __arch_cmpxchg_masked(sc_sfx, prepend, append, \ - __ret, __ptr, __old, __new); \ + __arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, __old, __new); \ break; \ case 4: \ - __arch_cmpxchg(".w", ".w" sc_sfx, prepend, append, \ - __ret, __ptr, (long), __old, __new); \ + __arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, (long)(int)(long), __old, __new); \ break; \ case 8: \ - __arch_cmpxchg(".d", ".d" sc_sfx, prepend, append, \ - __ret, __ptr, /**/, __old, __new); \ + __arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, /**/, __old, __new); \ break; \ default: \ BUILD_BUG(); \ @@ -181,17 +247,40 @@ (__typeof__(*(__ptr)))__ret; \ }) +/* + * These macros are here to improve the readability of the arch_cmpxchg_XXX() + * macros. + */ +#define SC_SFX(x) x +#define CAS_SFX(x) x +#define SC_PREPEND(x) x +#define SC_APPEND(x) x +#define CAS_PREPEND(x) x +#define CAS_APPEND(x) x + #define arch_cmpxchg_relaxed(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), "", "", "") + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(""), SC_APPEND(""), \ + CAS_PREPEND(""), CAS_APPEND("")) #define arch_cmpxchg_acquire(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER) + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER), \ + CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER)) #define arch_cmpxchg_release(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "") + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""), \ + CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND("")) #define arch_cmpxchg(ptr, o, n) \ - _arch_cmpxchg((ptr), (o), (n), ".rl", "", " fence rw, rw\n") + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(".rl"), CAS_SFX(".aqrl"), \ + SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER), \ + CAS_PREPEND(""), CAS_APPEND("")) #define arch_cmpxchg_local(ptr, o, n) \ arch_cmpxchg_relaxed((ptr), (o), (n)) @@ -226,6 +315,44 @@ arch_cmpxchg_release((ptr), (o), (n)); \ }) +#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS) + +#define system_has_cmpxchg128() riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS) + +union __u128_halves { + u128 full; + struct { + u64 low, high; + }; +}; + +#define __arch_cmpxchg128(p, o, n, cas_sfx) \ +({ \ + __typeof__(*(p)) __o = (o); \ + union __u128_halves __hn = { .full = (n) }; \ + union __u128_halves __ho = { .full = (__o) }; \ + register unsigned long t1 asm ("t1") = __hn.low; \ + register unsigned long t2 asm ("t2") = __hn.high; \ + register unsigned long t3 asm ("t3") = __ho.low; \ + register unsigned long t4 asm ("t4") = __ho.high; \ + \ + __asm__ __volatile__ ( \ + " amocas.q" cas_sfx " %0, %z3, %2" \ + : "+&r" (t3), "+&r" (t4), "+A" (*(p)) \ + : "rJ" (t1), "rJ" (t2) \ + : "memory"); \ + \ + ((u128)t4 << 64) | t3; \ +}) + +#define arch_cmpxchg128(ptr, o, n) \ + __arch_cmpxchg128((ptr), (o), (n), ".aqrl") + +#define arch_cmpxchg128_local(ptr, o, n) \ + __arch_cmpxchg128((ptr), (o), (n), "") + +#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */ + #ifdef CONFIG_RISCV_ISA_ZAWRS /* * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to @@ -240,11 +367,48 @@ static __always_inline void __cmpwait(volatile void *ptr, { unsigned long tmp; + u32 *__ptr32b; + ulong __s, __val, __mask; + asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop", 0, RISCV_ISA_EXT_ZAWRS, 1) : : : : no_zawrs); switch (size) { + case 1: + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x3) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; + case 2: + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x2) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xffff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; case 4: asm volatile( " lr.w %0, %1\n" diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h index aa103530a5c8..6081327e55f5 100644 --- a/arch/riscv/include/asm/compat.h +++ b/arch/riscv/include/asm/compat.h @@ -9,7 +9,6 @@ */ #include <linux/types.h> #include <linux/sched.h> -#include <linux/sched/task_stack.h> #include <asm-generic/compat.h> static inline int is_compat_task(void) diff --git a/arch/riscv/include/asm/cpufeature-macros.h b/arch/riscv/include/asm/cpufeature-macros.h new file mode 100644 index 000000000000..a8103edbf51f --- /dev/null +++ b/arch/riscv/include/asm/cpufeature-macros.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022-2024 Rivos, Inc + */ + +#ifndef _ASM_CPUFEATURE_MACROS_H +#define _ASM_CPUFEATURE_MACROS_H + +#include <asm/hwcap.h> +#include <asm/alternative-macros.h> + +#define STANDARD_EXT 0 + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + +static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor, + const unsigned long ext) +{ + asm goto(ALTERNATIVE("j %l[l_no]", "nop", %[vendor], %[ext], 1) + : + : [vendor] "i" (vendor), [ext] "i" (ext) + : + : l_no); + + return true; +l_no: + return false; +} + +static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor, + const unsigned long ext) +{ + asm goto(ALTERNATIVE("nop", "j %l[l_yes]", %[vendor], %[ext], 1) + : + : [vendor] "i" (vendor), [ext] "i" (ext) + : + : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) + return __riscv_has_extension_unlikely(STANDARD_EXT, ext); + + return __riscv_isa_extension_available(NULL, ext); +} + +static __always_inline bool riscv_has_extension_likely(const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) + return __riscv_has_extension_likely(STANDARD_EXT, ext); + + return __riscv_isa_extension_available(NULL, ext); +} + +#endif /* _ASM_CPUFEATURE_MACROS_H */ diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 45f9c1171a48..fbd0e4306c93 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -8,9 +8,12 @@ #include <linux/bitmap.h> #include <linux/jump_label.h> +#include <linux/workqueue.h> +#include <linux/kconfig.h> +#include <linux/percpu-defs.h> +#include <linux/threads.h> #include <asm/hwcap.h> -#include <asm/alternative-macros.h> -#include <asm/errno.h> +#include <asm/cpufeature-macros.h> /* * These are probed via a device_initcall(), via either the SBI or directly @@ -31,7 +34,9 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; -void riscv_user_isa_enable(void); +extern u32 thead_vlenb_of; + +void __init riscv_user_isa_enable(void); #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) { \ .name = #_name, \ @@ -51,6 +56,9 @@ void riscv_user_isa_enable(void); #define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \ _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \ ARRAY_SIZE(_bundled_exts), NULL) +#define __RISCV_ISA_EXT_BUNDLE_VALIDATE(_name, _bundled_exts, _validate) \ + _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \ + ARRAY_SIZE(_bundled_exts), _validate) /* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */ #define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \ @@ -58,11 +66,12 @@ void riscv_user_isa_enable(void); #define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \ _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate) -#if defined(CONFIG_RISCV_MISALIGNED) -bool check_unaligned_access_emulated_all_cpus(void); +bool __init check_unaligned_access_emulated_all_cpus(void); +void unaligned_access_init(void); +int cpu_online_unaligned_access_init(unsigned int cpu); +#if defined(CONFIG_RISCV_SCALAR_MISALIGNED) void unaligned_emulation_finish(void); bool unaligned_ctl_available(void); -DECLARE_PER_CPU(long, misaligned_access_speed); #else static inline bool unaligned_ctl_available(void) { @@ -70,6 +79,22 @@ static inline bool unaligned_ctl_available(void) } #endif +#if defined(CONFIG_RISCV_MISALIGNED) +DECLARE_PER_CPU(long, misaligned_access_speed); +bool misaligned_traps_can_delegate(void); +#else +static inline bool misaligned_traps_can_delegate(void) +{ + return false; +} +#endif + +bool __init check_vector_unaligned_access_emulated_all_cpus(void); +#if defined(CONFIG_RISCV_VECTOR_MISALIGNED) +void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused); +DECLARE_PER_CPU(long, vector_misaligned_access); +#endif + #if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key); @@ -103,61 +128,6 @@ extern const size_t riscv_isa_ext_count; extern bool riscv_isa_fallback; unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); - -#define STANDARD_EXT 0 - -bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit); -#define riscv_isa_extension_available(isa_bitmap, ext) \ - __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) - -static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor, - const unsigned long ext) -{ - asm goto(ALTERNATIVE("j %l[l_no]", "nop", %[vendor], %[ext], 1) - : - : [vendor] "i" (vendor), [ext] "i" (ext) - : - : l_no); - - return true; -l_no: - return false; -} - -static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor, - const unsigned long ext) -{ - asm goto(ALTERNATIVE("nop", "j %l[l_yes]", %[vendor], %[ext], 1) - : - : [vendor] "i" (vendor), [ext] "i" (ext) - : - : l_yes); - - return false; -l_yes: - return true; -} - -static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext) -{ - compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); - - if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) - return __riscv_has_extension_unlikely(STANDARD_EXT, ext); - - return __riscv_isa_extension_available(NULL, ext); -} - -static __always_inline bool riscv_has_extension_likely(const unsigned long ext) -{ - compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); - - if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) - return __riscv_has_extension_likely(STANDARD_EXT, ext); - - return __riscv_isa_extension_available(NULL, ext); -} - static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext) { compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 25966995da04..6fed42e37705 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -30,6 +30,12 @@ #define SR_VS_CLEAN _AC(0x00000400, UL) #define SR_VS_DIRTY _AC(0x00000600, UL) +#define SR_VS_THEAD _AC(0x01800000, UL) /* xtheadvector Status */ +#define SR_VS_OFF_THEAD _AC(0x00000000, UL) +#define SR_VS_INITIAL_THEAD _AC(0x00800000, UL) +#define SR_VS_CLEAN_THEAD _AC(0x01000000, UL) +#define SR_VS_DIRTY_THEAD _AC(0x01800000, UL) + #define SR_XS _AC(0x00018000, UL) /* Extension Status */ #define SR_XS_OFF _AC(0x00000000, UL) #define SR_XS_INITIAL _AC(0x00008000, UL) @@ -119,6 +125,10 @@ /* HSTATUS flags */ #ifdef CONFIG_64BIT +#define HSTATUS_HUPMM _AC(0x3000000000000, UL) +#define HSTATUS_HUPMM_PMLEN_0 _AC(0x0000000000000, UL) +#define HSTATUS_HUPMM_PMLEN_7 _AC(0x2000000000000, UL) +#define HSTATUS_HUPMM_PMLEN_16 _AC(0x3000000000000, UL) #define HSTATUS_VSXL _AC(0x300000000, UL) #define HSTATUS_VSXL_SHIFT 32 #endif @@ -195,6 +205,11 @@ /* xENVCFG flags */ #define ENVCFG_STCE (_AC(1, ULL) << 63) #define ENVCFG_PBMTE (_AC(1, ULL) << 62) +#define ENVCFG_ADUE (_AC(1, ULL) << 61) +#define ENVCFG_PMM (_AC(0x3, ULL) << 32) +#define ENVCFG_PMM_PMLEN_0 (_AC(0x0, ULL) << 32) +#define ENVCFG_PMM_PMLEN_7 (_AC(0x2, ULL) << 32) +#define ENVCFG_PMM_PMLEN_16 (_AC(0x3, ULL) << 32) #define ENVCFG_CBZE (_AC(1, UL) << 7) #define ENVCFG_CBCFE (_AC(1, UL) << 6) #define ENVCFG_CBIE_SHIFT 4 @@ -216,6 +231,12 @@ #define SMSTATEEN0_SSTATEEN0_SHIFT 63 #define SMSTATEEN0_SSTATEEN0 (_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT) +/* mseccfg bits */ +#define MSECCFG_PMM ENVCFG_PMM +#define MSECCFG_PMM_PMLEN_0 ENVCFG_PMM_PMLEN_0 +#define MSECCFG_PMM_PMLEN_7 ENVCFG_PMM_PMLEN_7 +#define MSECCFG_PMM_PMLEN_16 ENVCFG_PMM_PMLEN_16 + /* symbolic CSR names: */ #define CSR_CYCLE 0xc00 #define CSR_TIME 0xc01 @@ -300,6 +321,15 @@ #define CSR_STIMECMP 0x14D #define CSR_STIMECMPH 0x15D +/* xtheadvector symbolic CSR names */ +#define CSR_VXSAT 0x9 +#define CSR_VXRM 0xa + +/* xtheadvector CSR masks */ +#define CSR_VXRM_MASK 3 +#define CSR_VXRM_SHIFT 1 +#define CSR_VXSAT_MASK 1 + /* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */ #define CSR_SISELECT 0x150 #define CSR_SIREG 0x151 @@ -382,6 +412,8 @@ #define CSR_MIP 0x344 #define CSR_PMPCFG0 0x3a0 #define CSR_PMPADDR0 0x3b0 +#define CSR_MSECCFG 0x747 +#define CSR_MSECCFGH 0x757 #define CSR_MVENDORID 0xf11 #define CSR_MARCHID 0xf12 #define CSR_MIMPID 0xf13 diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h index 2293e535f865..b28ccc6cdeea 100644 --- a/arch/riscv/include/asm/entry-common.h +++ b/arch/riscv/include/asm/entry-common.h @@ -33,6 +33,7 @@ static inline int handle_misaligned_load(struct pt_regs *regs) { return -1; } + static inline int handle_misaligned_store(struct pt_regs *regs) { return -1; diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 7c8a71a526a3..6e426ed7919a 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -25,7 +25,8 @@ #ifdef CONFIG_ERRATA_THEAD #define ERRATA_THEAD_MAE 0 #define ERRATA_THEAD_PMU 1 -#define ERRATA_THEAD_NUMBER 2 +#define ERRATA_THEAD_GHOSTWRITE 2 +#define ERRATA_THEAD_NUMBER 3 #endif #ifdef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 2cddd79ff21b..22ebea3c2b26 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -20,10 +20,9 @@ extern void *return_address(unsigned int level); #define ftrace_return_address(n) return_address(n) void _mcount(void); -static inline unsigned long ftrace_call_adjust(unsigned long addr) -{ - return addr; -} +unsigned long ftrace_call_adjust(unsigned long addr); +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip); +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) /* * Let's do like x86/arm64 and ignore the compat syscalls. @@ -57,12 +56,21 @@ struct dyn_arch_ftrace { * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to * return address (original pc + 4) * + * The first 2 instructions for each tracable function is compiled to 2 nop + * instructions. Then, the kernel initializes the first instruction to auipc at + * boot time (<ftrace disable>). The second instruction is patched to jalr to + * start the trace. + * + *<Image>: + * 0: nop + * 4: nop + * *<ftrace enable>: - * 0: auipc t0/ra, 0x? - * 4: jalr t0/ra, ?(t0/ra) + * 0: auipc t0, 0x? + * 4: jalr t0, ?(t0) * *<ftrace disable>: - * 0: nop + * 0: auipc t0, 0x? * 4: nop * * Dynamic ftrace generates probes to call sites, so we must deal with @@ -75,11 +83,9 @@ struct dyn_arch_ftrace { #define AUIPC_OFFSET_MASK (0xfffff000) #define AUIPC_PAD (0x00001000) #define JALR_SHIFT 20 -#define JALR_RA (0x000080e7) -#define AUIPC_RA (0x00000097) #define JALR_T0 (0x000282e7) #define AUIPC_T0 (0x00000297) -#define NOP4 (0x00000013) +#define JALR_RANGE (JALR_SIGN_MASK - 1) #define to_jalr_t0(offset) \ (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0) @@ -92,31 +98,19 @@ struct dyn_arch_ftrace { #define make_call_t0(caller, callee, call) \ do { \ unsigned int offset = \ - (unsigned long) callee - (unsigned long) caller; \ + (unsigned long) (callee) - (unsigned long) (caller); \ call[0] = to_auipc_t0(offset); \ call[1] = to_jalr_t0(offset); \ } while (0) -#define to_jalr_ra(offset) \ - (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_RA) - -#define to_auipc_ra(offset) \ - ((offset & JALR_SIGN_MASK) ? \ - (((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_RA) : \ - ((offset & AUIPC_OFFSET_MASK) | AUIPC_RA)) - -#define make_call_ra(caller, callee, call) \ -do { \ - unsigned int offset = \ - (unsigned long) callee - (unsigned long) caller; \ - call[0] = to_auipc_ra(offset); \ - call[1] = to_jalr_ra(offset); \ -} while (0) - /* - * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. + * Only the jalr insn in the auipc+jalr is patched, so we make it 4 + * bytes here. */ -#define MCOUNT_INSN_SIZE 8 +#define MCOUNT_INSN_SIZE 4 +#define MCOUNT_AUIPC_SIZE 4 +#define MCOUNT_JALR_SIZE 4 +#define MCOUNT_NOP4_SIZE 4 #ifndef __ASSEMBLY__ struct dyn_ftrace; @@ -125,13 +119,20 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS #define arch_ftrace_get_regs(regs) NULL +#define HAVE_ARCH_FTRACE_REGS struct ftrace_ops; -struct ftrace_regs { +struct ftrace_regs; +#define arch_ftrace_regs(fregs) ((struct __arch_ftrace_regs *)(fregs)) + +struct __arch_ftrace_regs { unsigned long epc; unsigned long ra; unsigned long sp; unsigned long s0; unsigned long t1; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + unsigned long direct_tramp; +#endif union { unsigned long args[8]; struct { @@ -143,6 +144,13 @@ struct ftrace_regs { unsigned long a5; unsigned long a6; unsigned long a7; +#ifdef CONFIG_CC_IS_CLANG + unsigned long t2; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; +#endif }; }; }; @@ -150,42 +158,66 @@ struct ftrace_regs { static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs) { - return fregs->epc; + return arch_ftrace_regs(fregs)->epc; } static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long pc) { - fregs->epc = pc; + arch_ftrace_regs(fregs)->epc = pc; } static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs) { - return fregs->sp; + return arch_ftrace_regs(fregs)->sp; +} + +static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->s0; } static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n) { if (n < 8) - return fregs->args[n]; + return arch_ftrace_regs(fregs)->args[n]; return 0; } static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs) { - return fregs->a0; + return arch_ftrace_regs(fregs)->a0; +} + +static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->ra; } static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, unsigned long ret) { - fregs->a0 = ret; + arch_ftrace_regs(fregs)->a0 = ret; } static __always_inline void ftrace_override_function_with_return(struct ftrace_regs *fregs) { - fregs->epc = fregs->ra; + arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra; +} + +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(®s->a_regs, afregs->args, sizeof(afregs->args)); + regs->epc = afregs->epc; + regs->ra = afregs->ra; + regs->sp = afregs->sp; + regs->s0 = afregs->s0; + regs->t1 = afregs->t1; + return regs; } int ftrace_regs_query_register_offset(const char *name); @@ -194,35 +226,17 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); #define ftrace_graph_func ftrace_graph_func +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr) { - fregs->t1 = addr; + arch_ftrace_regs(fregs)->t1 = addr; } +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long a1; - unsigned long a0; - unsigned long s0; - unsigned long ra; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->a0; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->s0; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h index fc8130f995c1..90c86b115e00 100644 --- a/arch/riscv/include/asm/futex.h +++ b/arch/riscv/include/asm/futex.h @@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __enable_user_access(); __asm__ __volatile__ ( - "1: lr.w.aqrl %[v],%[u] \n" + "1: lr.w %[v],%[u] \n" " bne %[v],%z[ov],3f \n" "2: sc.w.aqrl %[t],%z[nv],%[u] \n" " bnez %[t],1b \n" @@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r]) \ _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r]) \ : [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp) - : [ov] "Jr" (oldval), [nv] "Jr" (newval) + : [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval) : "memory"); __disable_user_access(); diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index faf3624d8057..446126497768 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm, #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); + unsigned long addr, pte_t *ptep, + unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 46d9de54179e..affd63e11b0a 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -93,6 +93,19 @@ #define RISCV_ISA_EXT_ZCMOP 84 #define RISCV_ISA_EXT_ZAWRS 85 #define RISCV_ISA_EXT_SVVPTC 86 +#define RISCV_ISA_EXT_SMMPM 87 +#define RISCV_ISA_EXT_SMNPM 88 +#define RISCV_ISA_EXT_SSNPM 89 +#define RISCV_ISA_EXT_ZABHA 90 +#define RISCV_ISA_EXT_ZICCRSE 91 +#define RISCV_ISA_EXT_SVADE 92 +#define RISCV_ISA_EXT_SVADU 93 +#define RISCV_ISA_EXT_ZFBFMIN 94 +#define RISCV_ISA_EXT_ZVFBFMIN 95 +#define RISCV_ISA_EXT_ZVFBFWMA 96 +#define RISCV_ISA_EXT_ZAAMO 97 +#define RISCV_ISA_EXT_ZALRSC 98 +#define RISCV_ISA_EXT_ZICBOP 99 #define RISCV_ISA_EXT_XLINUXENVCFG 127 @@ -101,8 +114,10 @@ #ifdef CONFIG_RISCV_M_MODE #define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SMAIA +#define RISCV_ISA_EXT_SUPM RISCV_ISA_EXT_SMNPM #else #define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SSAIA +#define RISCV_ISA_EXT_SUPM RISCV_ISA_EXT_SSNPM #endif #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index ffb9484531af..7fe0a379474a 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _ASM_HWPROBE_H @@ -8,7 +8,7 @@ #include <uapi/asm/hwprobe.h> -#define RISCV_HWPROBE_MAX_KEY 9 +#define RISCV_HWPROBE_MAX_KEY 13 static inline bool riscv_hwprobe_key_is_valid(__s64 key) { @@ -21,6 +21,8 @@ static inline bool hwprobe_key_is_bitmask(__s64 key) case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: case RISCV_HWPROBE_KEY_IMA_EXT_0: case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0: return true; } diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h index e0b319af3681..8927a6ea1127 100644 --- a/arch/riscv/include/asm/image.h +++ b/arch/riscv/include/asm/image.h @@ -30,6 +30,8 @@ RISCV_HEADER_VERSION_MINOR) #ifndef __ASSEMBLY__ +#define riscv_image_flag_field(flags, field)\ + (((flags) >> field##_SHIFT) & field##_MASK) /** * struct riscv_image_header - riscv kernel image header * @code0: Executable code diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index 9a913010cdd9..d5adbaec1d01 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -18,6 +18,13 @@ #define INSN_I_RD_SHIFT 7 #define INSN_I_OPCODE_SHIFT 0 +#define INSN_S_SIMM7_SHIFT 25 +#define INSN_S_RS2_SHIFT 20 +#define INSN_S_RS1_SHIFT 15 +#define INSN_S_FUNC3_SHIFT 12 +#define INSN_S_SIMM5_SHIFT 7 +#define INSN_S_OPCODE_SHIFT 0 + #ifdef __ASSEMBLY__ #ifdef CONFIG_AS_HAS_INSN @@ -30,6 +37,10 @@ .insn i \opcode, \func3, \rd, \rs1, \simm12 .endm + .macro insn_s, opcode, func3, rs2, simm12, rs1 + .insn s \opcode, \func3, \rs2, \simm12(\rs1) + .endm + #else #include <asm/gpr-num.h> @@ -51,10 +62,20 @@ (\simm12 << INSN_I_SIMM12_SHIFT)) .endm + .macro insn_s, opcode, func3, rs2, simm12, rs1 + .4byte ((\opcode << INSN_S_OPCODE_SHIFT) | \ + (\func3 << INSN_S_FUNC3_SHIFT) | \ + (.L__gpr_num_\rs2 << INSN_S_RS2_SHIFT) | \ + (.L__gpr_num_\rs1 << INSN_S_RS1_SHIFT) | \ + ((\simm12 & 0x1f) << INSN_S_SIMM5_SHIFT) | \ + (((\simm12 >> 5) & 0x7f) << INSN_S_SIMM7_SHIFT)) + .endm + #endif #define __INSN_R(...) insn_r __VA_ARGS__ #define __INSN_I(...) insn_i __VA_ARGS__ +#define __INSN_S(...) insn_s __VA_ARGS__ #else /* ! __ASSEMBLY__ */ @@ -66,6 +87,9 @@ #define __INSN_I(opcode, func3, rd, rs1, simm12) \ ".insn i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" +#define __INSN_S(opcode, func3, rs2, simm12, rs1) \ + ".insn s " opcode ", " func3 ", " rs2 ", " simm12 "(" rs1 ")\n" + #else #include <linux/stringify.h> @@ -92,12 +116,26 @@ " (\\simm12 << " __stringify(INSN_I_SIMM12_SHIFT) "))\n" \ " .endm\n" +#define DEFINE_INSN_S \ + __DEFINE_ASM_GPR_NUMS \ +" .macro insn_s, opcode, func3, rs2, simm12, rs1\n" \ +" .4byte ((\\opcode << " __stringify(INSN_S_OPCODE_SHIFT) ") |" \ +" (\\func3 << " __stringify(INSN_S_FUNC3_SHIFT) ") |" \ +" (.L__gpr_num_\\rs2 << " __stringify(INSN_S_RS2_SHIFT) ") |" \ +" (.L__gpr_num_\\rs1 << " __stringify(INSN_S_RS1_SHIFT) ") |" \ +" ((\\simm12 & 0x1f) << " __stringify(INSN_S_SIMM5_SHIFT) ") |" \ +" (((\\simm12 >> 5) & 0x7f) << " __stringify(INSN_S_SIMM7_SHIFT) "))\n" \ +" .endm\n" + #define UNDEFINE_INSN_R \ " .purgem insn_r\n" #define UNDEFINE_INSN_I \ " .purgem insn_i\n" +#define UNDEFINE_INSN_S \ +" .purgem insn_s\n" + #define __INSN_R(opcode, func3, func7, rd, rs1, rs2) \ DEFINE_INSN_R \ "insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \ @@ -108,6 +146,11 @@ "insn_i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" \ UNDEFINE_INSN_I +#define __INSN_S(opcode, func3, rs2, simm12, rs1) \ + DEFINE_INSN_S \ + "insn_s " opcode ", " func3 ", " rs2 ", " simm12 ", " rs1 "\n" \ + UNDEFINE_INSN_S + #endif #endif /* ! __ASSEMBLY__ */ @@ -120,6 +163,10 @@ __INSN_I(RV_##opcode, RV_##func3, RV_##rd, \ RV_##rs1, RV_##simm12) +#define INSN_S(opcode, func3, rs2, simm12, rs1) \ + __INSN_S(RV_##opcode, RV_##func3, RV_##rs2, \ + RV_##simm12, RV_##rs1) + #define RV_OPCODE(v) __ASM_STR(v) #define RV_FUNC3(v) __ASM_STR(v) #define RV_FUNC7(v) __ASM_STR(v) @@ -133,6 +180,7 @@ #define RV___RS2(v) __RV_REG(v) #define RV_OPCODE_MISC_MEM RV_OPCODE(15) +#define RV_OPCODE_OP_IMM RV_OPCODE(19) #define RV_OPCODE_SYSTEM RV_OPCODE(115) #define HFENCE_VVMA(vaddr, asid) \ @@ -196,8 +244,29 @@ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(4)) +#define PREFETCH_I(base, offset) \ + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(0), \ + SIMM12((offset) & 0xfe0), RS1(base)) + +#define PREFETCH_R(base, offset) \ + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(1), \ + SIMM12((offset) & 0xfe0), RS1(base)) + +#define PREFETCH_W(base, offset) \ + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3), \ + SIMM12((offset) & 0xfe0), RS1(base)) + #define RISCV_PAUSE ".4byte 0x100000f" #define ZAWRS_WRS_NTO ".4byte 0x00d00073" #define ZAWRS_WRS_STO ".4byte 0x01d00073" +#define RISCV_NOP4 ".4byte 0x00000013" + +#define RISCV_INSN_NOP4 _AC(0x00000013, U) + +#ifndef __ASSEMBLY__ +#define nop() __asm__ __volatile__ ("nop") +#define __nops(n) ".rept " #n "\nnop\n.endr\n" +#define nops(n) __asm__ __volatile__ (__nops(n)) +#endif #endif /* __ASM_INSN_DEF_H */ diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 1c5c641075d2..a0e51840b9db 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -136,8 +136,8 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) #include <asm-generic/io.h> #ifdef CONFIG_MMU -#define arch_memremap_wb(addr, size) \ - ((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL)) +#define arch_memremap_wb(addr, size, flags) \ + ((__force void *)ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL))) #endif #endif /* _ASM_RISCV_IO_H */ diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h index 1c768d02bd0c..87a71cc6d146 100644 --- a/arch/riscv/include/asm/jump_label.h +++ b/arch/riscv/include/asm/jump_label.h @@ -16,21 +16,28 @@ #define JUMP_LABEL_NOP_SIZE 4 +#define JUMP_TABLE_ENTRY(key, label) \ + ".pushsection __jump_table, \"aw\" \n\t" \ + ".align " RISCV_LGPTR " \n\t" \ + ".long 1b - ., " label " - . \n\t" \ + "" RISCV_PTR " " key " - . \n\t" \ + ".popsection \n\t" + +/* This macro is also expanded on the Rust side. */ +#define ARCH_STATIC_BRANCH_ASM(key, label) \ + " .align 2 \n\t" \ + " .option push \n\t" \ + " .option norelax \n\t" \ + " .option norvc \n\t" \ + "1: nop \n\t" \ + " .option pop \n\t" \ + JUMP_TABLE_ENTRY(key, label) + static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { asm goto( - " .align 2 \n\t" - " .option push \n\t" - " .option norelax \n\t" - " .option norvc \n\t" - "1: nop \n\t" - " .option pop \n\t" - " .pushsection __jump_table, \"aw\" \n\t" - " .align " RISCV_LGPTR " \n\t" - " .long 1b - ., %l[label] - . \n\t" - " " RISCV_PTR " %0 - . \n\t" - " .popsection \n\t" + ARCH_STATIC_BRANCH_ASM("%0", "%l[label]") : : "i"(&((char *)key)[branch]) : : label); return false; @@ -38,21 +45,20 @@ label: return true; } +#define ARCH_STATIC_BRANCH_JUMP_ASM(key, label) \ + " .align 2 \n\t" \ + " .option push \n\t" \ + " .option norelax \n\t" \ + " .option norvc \n\t" \ + "1: j " label " \n\t" \ + " .option pop \n\t" \ + JUMP_TABLE_ENTRY(key, label) + static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { asm goto( - " .align 2 \n\t" - " .option push \n\t" - " .option norelax \n\t" - " .option norvc \n\t" - "1: j %l[label] \n\t" - " .option pop \n\t" - " .pushsection __jump_table, \"aw\" \n\t" - " .align " RISCV_LGPTR " \n\t" - " .long 1b - ., %l[label] - . \n\t" - " " RISCV_PTR " %0 - . \n\t" - " .popsection \n\t" + ARCH_STATIC_BRANCH_JUMP_ASM("%0", "%l[label]") : : "i"(&((char *)key)[branch]) : : label); return false; diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h index 2b56769cb530..b9ee8346cc8c 100644 --- a/arch/riscv/include/asm/kexec.h +++ b/arch/riscv/include/asm/kexec.h @@ -56,6 +56,7 @@ extern riscv_kexec_method riscv_kexec_norelocate; #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops elf_kexec_ops; +extern const struct kexec_file_ops image_kexec_ops; struct purgatory_info; int arch_kexec_apply_relocations_add(struct purgatory_info *pi, @@ -67,6 +68,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, struct kimage; int arch_kimage_file_post_load_cleanup(struct kimage *image); #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup + +int load_extra_segments(struct kimage *image, unsigned long kernel_start, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len); #endif #endif diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 7388edd88986..d08bf7fb3aee 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) else set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_disable(); + local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_enable(); return true; } diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h index 46677daf708b..cc11c4544cff 100644 --- a/arch/riscv/include/asm/kgdb.h +++ b/arch/riscv/include/asm/kgdb.h @@ -19,16 +19,9 @@ #ifndef __ASSEMBLY__ +void arch_kgdb_breakpoint(void); extern unsigned long kgdb_compiled_break; -static inline void arch_kgdb_breakpoint(void) -{ - asm(".global kgdb_compiled_break\n" - ".option norvc\n" - "kgdb_compiled_break: ebreak\n" - ".option rvc\n"); -} - #endif /* !__ASSEMBLY__ */ #define DBG_REG_ZERO "zero" diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 1f37b600ca47..3b643b9efc07 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -63,9 +63,6 @@ struct kvm_vcpu_aia { /* CPU AIA CSR context of Guest VCPU */ struct kvm_vcpu_aia_csr guest_csr; - /* CPU AIA CSR context upon Guest VCPU reset */ - struct kvm_vcpu_aia_csr guest_reset_csr; - /* Guest physical address of IMSIC for this VCPU */ gpa_t imsic_addr; diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 2e2254fd2a2a..85cfebc32e4c 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -87,6 +87,11 @@ struct kvm_vcpu_stat { u64 csr_exit_kernel; u64 signal_exits; u64 exits; + u64 instr_illegal_exits; + u64 load_misaligned_exits; + u64 store_misaligned_exits; + u64 load_access_exits; + u64 store_access_exits; }; struct kvm_arch_memory_slot { @@ -114,6 +119,9 @@ struct kvm_arch { /* AIA Guest/VM context */ struct kvm_aia aia; + + /* KVM_CAP_RISCV_MP_STATE_RESET */ + bool mp_state_reset; }; struct kvm_cpu_trap { @@ -188,6 +196,12 @@ struct kvm_vcpu_smstateen_csr { unsigned long sstateen0; }; +struct kvm_vcpu_reset_state { + spinlock_t lock; + unsigned long pc; + unsigned long a1; +}; + struct kvm_vcpu_arch { /* VCPU ran at least once */ bool ran_atleast_once; @@ -222,12 +236,8 @@ struct kvm_vcpu_arch { /* CPU Smstateen CSR context of Guest VCPU */ struct kvm_vcpu_smstateen_csr smstateen_csr; - /* CPU context upon Guest VCPU reset */ - struct kvm_cpu_context guest_reset_context; - spinlock_t reset_cntx_lock; - - /* CPU CSR context upon Guest VCPU reset */ - struct kvm_vcpu_csr guest_reset_csr; + /* CPU reset state of Guest VCPU */ + struct kvm_vcpu_reset_state reset_state; /* * VCPU interrupts @@ -286,7 +296,15 @@ struct kvm_vcpu_arch { } sta; }; -static inline void kvm_arch_sync_events(struct kvm *kvm) {} +/* + * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, + * arrived in guest context. For riscv, any event that arrives while a vCPU is + * loaded is considered to be "in guest". + */ +static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) +{ + return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; +} #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 diff --git a/arch/riscv/include/asm/kvm_nacl.h b/arch/riscv/include/asm/kvm_nacl.h new file mode 100644 index 000000000000..4124d5e06a0f --- /dev/null +++ b/arch/riscv/include/asm/kvm_nacl.h @@ -0,0 +1,245 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#ifndef __KVM_NACL_H +#define __KVM_NACL_H + +#include <linux/jump_label.h> +#include <linux/percpu.h> +#include <asm/byteorder.h> +#include <asm/csr.h> +#include <asm/sbi.h> + +struct kvm_vcpu_arch; + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_available); +#define kvm_riscv_nacl_available() \ + static_branch_unlikely(&kvm_riscv_nacl_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available); +#define kvm_riscv_nacl_sync_csr_available() \ + static_branch_unlikely(&kvm_riscv_nacl_sync_csr_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available); +#define kvm_riscv_nacl_sync_hfence_available() \ + static_branch_unlikely(&kvm_riscv_nacl_sync_hfence_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available); +#define kvm_riscv_nacl_sync_sret_available() \ + static_branch_unlikely(&kvm_riscv_nacl_sync_sret_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available); +#define kvm_riscv_nacl_autoswap_csr_available() \ + static_branch_unlikely(&kvm_riscv_nacl_autoswap_csr_available) + +struct kvm_riscv_nacl { + void *shmem; + phys_addr_t shmem_phys; +}; +DECLARE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl); + +void __kvm_riscv_nacl_hfence(void *shmem, + unsigned long control, + unsigned long page_num, + unsigned long page_count); + +void __kvm_riscv_nacl_switch_to(struct kvm_vcpu_arch *vcpu_arch, + unsigned long sbi_ext_id, + unsigned long sbi_func_id); + +int kvm_riscv_nacl_enable(void); + +void kvm_riscv_nacl_disable(void); + +void kvm_riscv_nacl_exit(void); + +int kvm_riscv_nacl_init(void); + +#ifdef CONFIG_32BIT +#define lelong_to_cpu(__x) le32_to_cpu(__x) +#define cpu_to_lelong(__x) cpu_to_le32(__x) +#else +#define lelong_to_cpu(__x) le64_to_cpu(__x) +#define cpu_to_lelong(__x) cpu_to_le64(__x) +#endif + +#define nacl_shmem() \ + this_cpu_ptr(&kvm_riscv_nacl)->shmem + +#define nacl_scratch_read_long(__shmem, __offset) \ +({ \ + unsigned long *__p = (__shmem) + \ + SBI_NACL_SHMEM_SCRATCH_OFFSET + \ + (__offset); \ + lelong_to_cpu(*__p); \ +}) + +#define nacl_scratch_write_long(__shmem, __offset, __val) \ +do { \ + unsigned long *__p = (__shmem) + \ + SBI_NACL_SHMEM_SCRATCH_OFFSET + \ + (__offset); \ + *__p = cpu_to_lelong(__val); \ +} while (0) + +#define nacl_scratch_write_longs(__shmem, __offset, __array, __count) \ +do { \ + unsigned int __i; \ + unsigned long *__p = (__shmem) + \ + SBI_NACL_SHMEM_SCRATCH_OFFSET + \ + (__offset); \ + for (__i = 0; __i < (__count); __i++) \ + __p[__i] = cpu_to_lelong((__array)[__i]); \ +} while (0) + +#define nacl_sync_hfence(__e) \ + sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_HFENCE, \ + (__e), 0, 0, 0, 0, 0) + +#define nacl_hfence_mkconfig(__type, __order, __vmid, __asid) \ +({ \ + unsigned long __c = SBI_NACL_SHMEM_HFENCE_CONFIG_PEND; \ + __c |= ((__type) & SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK) \ + << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT; \ + __c |= (((__order) - SBI_NACL_SHMEM_HFENCE_ORDER_BASE) & \ + SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK) \ + << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT; \ + __c |= ((__vmid) & SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK) \ + << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT; \ + __c |= ((__asid) & SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK); \ + __c; \ +}) + +#define nacl_hfence_mkpnum(__order, __addr) \ + ((__addr) >> (__order)) + +#define nacl_hfence_mkpcount(__order, __size) \ + ((__size) >> (__order)) + +#define nacl_hfence_gvma(__shmem, __gpa, __gpsz, __order) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA, \ + __order, 0, 0), \ + nacl_hfence_mkpnum(__order, __gpa), \ + nacl_hfence_mkpcount(__order, __gpsz)) + +#define nacl_hfence_gvma_all(__shmem) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL, \ + 0, 0, 0), 0, 0) + +#define nacl_hfence_gvma_vmid(__shmem, __vmid, __gpa, __gpsz, __order) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID, \ + __order, __vmid, 0), \ + nacl_hfence_mkpnum(__order, __gpa), \ + nacl_hfence_mkpcount(__order, __gpsz)) + +#define nacl_hfence_gvma_vmid_all(__shmem, __vmid) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL, \ + 0, __vmid, 0), 0, 0) + +#define nacl_hfence_vvma(__shmem, __vmid, __gva, __gvsz, __order) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA, \ + __order, __vmid, 0), \ + nacl_hfence_mkpnum(__order, __gva), \ + nacl_hfence_mkpcount(__order, __gvsz)) + +#define nacl_hfence_vvma_all(__shmem, __vmid) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL, \ + 0, __vmid, 0), 0, 0) + +#define nacl_hfence_vvma_asid(__shmem, __vmid, __asid, __gva, __gvsz, __order)\ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID, \ + __order, __vmid, __asid), \ + nacl_hfence_mkpnum(__order, __gva), \ + nacl_hfence_mkpcount(__order, __gvsz)) + +#define nacl_hfence_vvma_asid_all(__shmem, __vmid, __asid) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL, \ + 0, __vmid, __asid), 0, 0) + +#define nacl_csr_read(__shmem, __csr) \ +({ \ + unsigned long *__a = (__shmem) + SBI_NACL_SHMEM_CSR_OFFSET; \ + lelong_to_cpu(__a[SBI_NACL_SHMEM_CSR_INDEX(__csr)]); \ +}) + +#define nacl_csr_write(__shmem, __csr, __val) \ +do { \ + void *__s = (__shmem); \ + unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \ + unsigned long *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \ + u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \ + __a[__i] = cpu_to_lelong(__val); \ + __b[__i >> 3] |= 1U << (__i & 0x7); \ +} while (0) + +#define nacl_csr_swap(__shmem, __csr, __val) \ +({ \ + void *__s = (__shmem); \ + unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \ + unsigned long *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \ + u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \ + unsigned long __r = lelong_to_cpu(__a[__i]); \ + __a[__i] = cpu_to_lelong(__val); \ + __b[__i >> 3] |= 1U << (__i & 0x7); \ + __r; \ +}) + +#define nacl_sync_csr(__csr) \ + sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_CSR, \ + (__csr), 0, 0, 0, 0, 0) + +/* + * Each ncsr_xyz() macro defined below has it's own static-branch so every + * use of ncsr_xyz() macro emits a patchable direct jump. This means multiple + * back-to-back ncsr_xyz() macro usage will emit multiple patchable direct + * jumps which is sub-optimal. + * + * Based on the above, it is recommended to avoid multiple back-to-back + * ncsr_xyz() macro usage. + */ + +#define ncsr_read(__csr) \ +({ \ + unsigned long __r; \ + if (kvm_riscv_nacl_available()) \ + __r = nacl_csr_read(nacl_shmem(), __csr); \ + else \ + __r = csr_read(__csr); \ + __r; \ +}) + +#define ncsr_write(__csr, __val) \ +do { \ + if (kvm_riscv_nacl_sync_csr_available()) \ + nacl_csr_write(nacl_shmem(), __csr, __val); \ + else \ + csr_write(__csr, __val); \ +} while (0) + +#define ncsr_swap(__csr, __val) \ +({ \ + unsigned long __r; \ + if (kvm_riscv_nacl_sync_csr_available()) \ + __r = nacl_csr_swap(nacl_shmem(), __csr, __val); \ + else \ + __r = csr_swap(__csr, __val); \ + __r; \ +}) + +#define nsync_csr(__csr) \ +do { \ + if (kvm_riscv_nacl_sync_csr_available()) \ + nacl_sync_csr(__csr); \ +} while (0) + +#endif diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index b96705258cf9..439ab2b3534f 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -55,6 +55,9 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type, u64 flags); +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1); +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); @@ -85,6 +88,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental; extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor; diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h index 27f5bccdd8b0..57a798a4cb0d 100644 --- a/arch/riscv/include/asm/kvm_vcpu_vector.h +++ b/arch/riscv/include/asm/kvm_vcpu_vector.h @@ -33,8 +33,7 @@ void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, unsigned long *isa); void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx); void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx); -int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx); +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu); #else @@ -62,8 +61,7 @@ static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cn { } -static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx) +static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) { return 0; } diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index c9e03e9da3dc..1cc90465d75b 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -26,8 +26,15 @@ typedef struct { unsigned long exec_fdpic_loadmap; unsigned long interp_fdpic_loadmap; #endif + unsigned long flags; +#ifdef CONFIG_RISCV_ISA_SUPM + u8 pmlen; +#endif } mm_context_t; +/* Lock the pointer masking mode because this mm is multithreaded */ +#define MM_CONTEXT_LOCK_PMLEN 0 + #define cntx2asid(cntx) ((cntx) & SATP_ASID_MASK) #define cntx2version(cntx) ((cntx) & ~SATP_ASID_MASK) diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h index 7030837adc1a..8c4bc49a3a0f 100644 --- a/arch/riscv/include/asm/mmu_context.h +++ b/arch/riscv/include/asm/mmu_context.h @@ -20,6 +20,9 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { +#ifdef CONFIG_RISCV_ISA_SUPM + next->context.pmlen = 0; +#endif switch_mm(prev, next, NULL); } @@ -30,11 +33,21 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_MMU atomic_long_set(&mm->context.id, 0); #endif + if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM)) + clear_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags); return 0; } DECLARE_STATIC_KEY_FALSE(use_asid_allocator); +#ifdef CONFIG_RISCV_ISA_SUPM +#define mm_untag_mask mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL >> mm->context.pmlen; +} +#endif + #include <asm-generic/mmu_context.h> #endif /* _ASM_RISCV_MMU_CONTEXT_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 32d308a3355f..572a141ddecd 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -12,9 +12,7 @@ #include <linux/pfn.h> #include <linux/const.h> -#define PAGE_SHIFT CONFIG_PAGE_SHIFT -#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#include <vdso/page.h> #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) @@ -26,21 +24,22 @@ * When not using MMU this corresponds to the first free page in * physical memory (aligned on a page boundary). */ -#ifdef CONFIG_64BIT #ifdef CONFIG_MMU -#define PAGE_OFFSET kernel_map.page_offset -#else -#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) -#endif -/* - * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so - * define the PAGE_OFFSET value for SV48 and SV39. - */ +#ifdef CONFIG_64BIT +#define PAGE_OFFSET_L5 _AC(0xff60000000000000, UL) #define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) #define PAGE_OFFSET_L3 _AC(0xffffffd600000000, UL) +#ifdef CONFIG_XIP_KERNEL +#define PAGE_OFFSET PAGE_OFFSET_L3 +#else +#define PAGE_OFFSET kernel_map.page_offset +#endif /* CONFIG_XIP_KERNEL */ #else -#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) +#define PAGE_OFFSET _AC(0xc0000000, UL) #endif /* CONFIG_64BIT */ +#else +#define PAGE_OFFSET ((unsigned long)phys_ram_base) +#endif /* CONFIG_MMU */ #ifndef __ASSEMBLY__ @@ -97,14 +96,9 @@ typedef struct page *pgtable_t; #define MIN_MEMBLOCK_ADDR 0 #endif -#ifdef CONFIG_MMU #define ARCH_PFN_OFFSET (PFN_DOWN((unsigned long)phys_ram_base)) -#else -#define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT) -#endif /* CONFIG_MMU */ struct kernel_mapping { - unsigned long page_offset; unsigned long virt_addr; unsigned long virt_offset; uintptr_t phys_addr; @@ -118,12 +112,14 @@ struct kernel_mapping { uintptr_t xiprom; uintptr_t xiprom_sz; #else + unsigned long page_offset; unsigned long va_kernel_pa_offset; #endif }; extern struct kernel_mapping kernel_map; extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) @@ -194,9 +190,6 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define virt_to_page(vaddr) (pfn_to_page(virt_to_pfn(vaddr))) #define page_to_virt(page) (pfn_to_virt(page_to_pfn(page))) -#define page_to_phys(page) (pfn_to_phys(page_to_pfn(page))) -#define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr))) - #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) unsigned long kaslr_offset(void); diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index 665bbc9b2f84..bcc928fd3785 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -8,6 +8,7 @@ #ifndef _ASM_RISCV_PERF_EVENT_H #define _ASM_RISCV_PERF_EVENT_H +#ifdef CONFIG_PERF_EVENTS #include <linux/perf_event.h> #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs @@ -17,4 +18,6 @@ (regs)->sp = current_stack_pointer; \ (regs)->status = SR_PP; \ } +#endif + #endif /* _ASM_RISCV_PERF_EVENT_H */ diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index f52264304f77..770ce18a7328 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -12,18 +12,9 @@ #include <asm/tlb.h> #ifdef CONFIG_MMU -#define __HAVE_ARCH_PUD_ALLOC_ONE #define __HAVE_ARCH_PUD_FREE #include <asm-generic/pgalloc.h> -static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt) -{ - if (riscv_use_sbi_for_rfence()) - tlb_remove_ptdesc(tlb, pt); - else - tlb_remove_page_ptdesc(tlb, pt); -} - static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { @@ -88,15 +79,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, } } -#define pud_alloc_one pud_alloc_one -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - if (pgtable_l4_enabled) - return __pud_alloc_one(mm, addr); - - return NULL; -} - #define pud_free pud_free static inline void pud_free(struct mm_struct *mm, pud_t *pud) { @@ -107,46 +89,15 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long addr) { - if (pgtable_l4_enabled) { - struct ptdesc *ptdesc = virt_to_ptdesc(pud); - - pagetable_pud_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); - } -} - -#define p4d_alloc_one p4d_alloc_one -static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - if (pgtable_l5_enabled) { - gfp_t gfp = GFP_PGTABLE_USER; - - if (mm == &init_mm) - gfp = GFP_PGTABLE_KERNEL; - return (p4d_t *)get_zeroed_page(gfp); - } - - return NULL; -} - -static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); - free_page((unsigned long)p4d); -} - -#define p4d_free p4d_free -static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) -{ - if (pgtable_l5_enabled) - __p4d_free(mm, p4d); + if (pgtable_l4_enabled) + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); } static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr) { if (pgtable_l5_enabled) - riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -161,9 +112,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pgd = (pgd_t *)__get_free_page(GFP_KERNEL); + pgd = __pgd_alloc(mm, 0); if (likely(pgd != NULL)) { - memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); /* Copy kernel mappings */ sync_kernel_mappings(pgd); } @@ -175,10 +125,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { - struct ptdesc *ptdesc = virt_to_ptdesc(pmd); - - pagetable_pmd_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -186,10 +133,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - struct ptdesc *ptdesc = page_ptdesc(pte); - - pagetable_pte_dtor(ptdesc); - riscv_tlb_remove_ptdesc(tlb, ptdesc); + tlb_remove_ptdesc(tlb, page_ptdesc(pte)); } #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 0897dd99ab8d..7de05db7d3bd 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -184,7 +184,7 @@ static inline int pud_none(pud_t pud) static inline int pud_bad(pud_t pud) { - return !pud_present(pud); + return !pud_present(pud) || (pud_val(pud) & _PAGE_LEAF); } #define pud_leaf pud_leaf @@ -262,8 +262,6 @@ static inline unsigned long _pmd_pfn(pmd_t pmd) return __page_val_to_pfn(pmd_val(pmd)); } -#define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot) - #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e)) @@ -401,6 +399,7 @@ p4d_t *p4d_offset(pgd_t *pgd, unsigned long address); #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pte_devmap(pte_t pte); static inline pte_t pmd_pte(pmd_t pmd); +static inline pte_t pud_pte(pud_t pud); static inline int pmd_devmap(pmd_t pmd) { @@ -409,7 +408,7 @@ static inline int pmd_devmap(pmd_t pmd) static inline int pud_devmap(pud_t pud) { - return 0; + return pte_devmap(pud_pte(pud)); } static inline int pgd_devmap(pgd_t pgd) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index e79f15293492..5bd5aae60d53 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -12,7 +12,11 @@ #include <asm/pgtable-bits.h> #ifndef CONFIG_MMU -#define KERNEL_LINK_ADDR PAGE_OFFSET +#ifdef CONFIG_RELOCATABLE +#define KERNEL_LINK_ADDR UL(0) +#else +#define KERNEL_LINK_ADDR _AC(CONFIG_PHYS_RAM_BASE, UL) +#endif #define KERN_VIRT_SIZE (UL(-1)) #else @@ -87,7 +91,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -113,6 +117,7 @@ #include <asm/tlbflush.h> #include <linux/mm_types.h> #include <asm/compat.h> +#include <asm/cpufeature.h> #define __page_val_to_pfn(_val) (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT) @@ -284,7 +289,6 @@ static inline pte_t pud_pte(pud_t pud) } #ifdef CONFIG_RISCV_ISA_SVNAPOT -#include <asm/cpufeature.h> static __always_inline bool has_svnapot(void) { @@ -339,7 +343,13 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val); } -#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) +#define pte_pgprot pte_pgprot +static inline pgprot_t pte_pgprot(pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); +} static inline int pte_present(pte_t pte) { @@ -656,6 +666,17 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot) } /* + * Both Svade and Svadu control the hardware behavior when the PTE A/D bits need to be set. By + * default the M-mode firmware enables the hardware updating scheme when only Svadu is present in + * DT. + */ +#define arch_has_hw_pte_young arch_has_hw_pte_young +static inline bool arch_has_hw_pte_young(void) +{ + return riscv_has_extension_unlikely(RISCV_ISA_EXT_SVADU); +} + +/* * THP functions */ static inline pmd_t pte_pmd(pte_t pte) @@ -663,6 +684,11 @@ static inline pmd_t pte_pmd(pte_t pte) return __pmd(pte_val(pte)); } +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd; @@ -688,6 +714,18 @@ static inline unsigned long pud_pfn(pud_t pud) return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); } +#define pmd_pgprot pmd_pgprot +static inline pgprot_t pmd_pgprot(pmd_t pmd) +{ + return pte_pgprot(pmd_pte(pmd)); +} + +#define pud_pgprot pud_pgprot +static inline pgprot_t pud_pgprot(pud_t pud) +{ + return pte_pgprot(pud_pte(pud)); +} + static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); @@ -757,6 +795,30 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) return pte_pmd(pte_mkdevmap(pmd_pte(pmd))); } +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return pte_special(pmd_pte(pmd)); +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pte_pmd(pte_mkspecial(pmd_pte(pmd))); +} +#endif + +#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return pte_special(pud_pte(pud)); +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pte_pud(pte_mkspecial(pud_pte(pud))); +} +#endif + static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { @@ -838,6 +900,103 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define pmdp_collapse_flush pmdp_collapse_flush extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); + +static inline pud_t pud_wrprotect(pud_t pud) +{ + return pte_pud(pte_wrprotect(pud_pte(pud))); +} + +static inline int pud_trans_huge(pud_t pud) +{ + return pud_leaf(pud); +} + +static inline int pud_dirty(pud_t pud) +{ + return pte_dirty(pud_pte(pud)); +} + +static inline pud_t pud_mkyoung(pud_t pud) +{ + return pte_pud(pte_mkyoung(pud_pte(pud))); +} + +static inline pud_t pud_mkold(pud_t pud) +{ + return pte_pud(pte_mkold(pud_pte(pud))); +} + +static inline pud_t pud_mkdirty(pud_t pud) +{ + return pte_pud(pte_mkdirty(pud_pte(pud))); +} + +static inline pud_t pud_mkclean(pud_t pud) +{ + return pte_pud(pte_mkclean(pud_pte(pud))); +} + +static inline pud_t pud_mkwrite(pud_t pud) +{ + return pte_pud(pte_mkwrite_novma(pud_pte(pud))); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud; +} + +static inline pud_t pud_mkdevmap(pud_t pud) +{ + return pte_pud(pte_mkdevmap(pud_pte(pud))); +} + +static inline int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty); +} + +static inline int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + return ptep_test_and_clear_young(vma, address, (pte_t *)pudp); +} + +static inline int pud_young(pud_t pud) +{ + return pte_young(pud_pte(pud)); +} + +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + pte_t *ptep = (pte_t *)pudp; + + update_mmu_cache(vma, address, ptep); +} + +static inline pud_t pudp_establish(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(vma->vm_mm, pudp, pud); + return __pud(atomic_long_xchg((atomic_long_t *)pudp, pud_val(pud))); +} + +static inline pud_t pud_mkinvalid(pud_t pud) +{ + return __pud(pud_val(pud) & ~(_PAGE_PRESENT | _PAGE_PROT_NONE)); +} + +extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp); + +static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) +{ + return pte_pud(pte_modify(pud_pte(pud), newprot)); +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* @@ -869,7 +1028,7 @@ extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -static inline int pte_swp_exclusive(pte_t pte) +static inline bool pte_swp_exclusive(pte_t pte) { return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; } @@ -916,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MAX LONG_MAX #ifdef CONFIG_COMPAT #define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) @@ -963,6 +1121,25 @@ void misc_mem_init(void); extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) #endif /* !__ASSEMBLY__ */ #endif /* _ASM_RISCV_PGTABLE_H */ diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index efa1b3519b23..24d3af4d3807 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -13,6 +13,9 @@ #include <vdso/processor.h> #include <asm/ptrace.h> +#include <asm/insn-def.h> +#include <asm/alternative-macros.h> +#include <asm/hwcap.h> #define arch_get_mmap_end(addr, len, flags) \ ({ \ @@ -52,7 +55,6 @@ #endif #ifndef __ASSEMBLY__ -#include <linux/cpumask.h> struct task_struct; struct pt_regs; @@ -79,6 +81,10 @@ struct pt_regs; * Thus, the task does not own preempt_v. Any use of Vector will have to * save preempt_v, if dirty, and fallback to non-preemptible kernel-mode * Vector. + * - bit 29: The thread voluntarily calls schedule() while holding an active + * preempt_v. All preempt_v context should be dropped in such case because + * V-regs are caller-saved. Only sstatus.VS=ON is persisted across a + * schedule() call. * - bit 30: The in-kernel preempt_v context is saved, and requries to be * restored when returning to the context that owns the preempt_v. * - bit 31: The in-kernel preempt_v context is dirty, as signaled by the @@ -93,6 +99,7 @@ struct pt_regs; #define RISCV_PREEMPT_V 0x00000100 #define RISCV_PREEMPT_V_DIRTY 0x80000000 #define RISCV_PREEMPT_V_NEED_RESTORE 0x40000000 +#define RISCV_PREEMPT_V_IN_SCHEDULE 0x20000000 /* CPU-specific state of a task */ struct thread_struct { @@ -102,6 +109,8 @@ struct thread_struct { unsigned long s[12]; /* s[0]: frame pointer */ struct __riscv_d_ext_state fstate; unsigned long bad_cause; + unsigned long envcfg; + unsigned long sum; u32 riscv_v_flags; u32 vstate_ctrl; struct __riscv_v_ext_state vstate; @@ -135,6 +144,27 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, #define KSTK_EIP(tsk) (task_pt_regs(tsk)->epc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) +#define PREFETCH_ASM(x) \ + ALTERNATIVE(__nops(1), PREFETCH_R(x, 0), 0, \ + RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP) + +#define PREFETCHW_ASM(x) \ + ALTERNATIVE(__nops(1), PREFETCH_W(x, 0), 0, \ + RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP) + +#ifdef CONFIG_RISCV_ISA_ZICBOP +#define ARCH_HAS_PREFETCH +static inline void prefetch(const void *x) +{ + __asm__ __volatile__(PREFETCH_ASM(%0) : : "r" (x) : "memory"); +} + +#define ARCH_HAS_PREFETCHW +static inline void prefetchw(const void *x) +{ + __asm__ __volatile__(PREFETCHW_ASM(%0) : : "r" (x) : "memory"); +} +#endif /* CONFIG_RISCV_ISA_ZICBOP */ /* Do necessary setup to start up a newly executed thread. */ extern void start_thread(struct pt_regs *regs, @@ -177,6 +207,14 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); #define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2) riscv_set_icache_flush_ctx(arg1, arg2) extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread); +#ifdef CONFIG_RISCV_ISA_SUPM +/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ +long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg); +long get_tagged_addr_ctrl(struct task_struct *task); +#define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(current, arg) +#define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PROCESSOR_H */ diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index b5b0adcc85c1..a7dc0e330757 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -23,14 +23,16 @@ struct pt_regs { unsigned long t2; unsigned long s0; unsigned long s1; - unsigned long a0; - unsigned long a1; - unsigned long a2; - unsigned long a3; - unsigned long a4; - unsigned long a5; - unsigned long a6; - unsigned long a7; + struct_group(a_regs, + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + ); unsigned long s2; unsigned long s3; unsigned long s4; @@ -173,7 +175,7 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, return 0; } -static inline int regs_irqs_disabled(struct pt_regs *regs) +static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->status & SR_PIE); } diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h new file mode 100644 index 000000000000..d766e2b9e6df --- /dev/null +++ b/arch/riscv/include/asm/runtime-const.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_RUNTIME_CONST_H +#define _ASM_RISCV_RUNTIME_CONST_H + +#include <asm/asm.h> +#include <asm/alternative.h> +#include <asm/cacheflush.h> +#include <asm/insn-def.h> +#include <linux/memory.h> +#include <asm/text-patching.h> + +#include <linux/uaccess.h> + +#ifdef CONFIG_32BIT +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + "lui %[__ret],0x89abd\n\t" \ + "addi %[__ret],%[__ret],-0x211\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret)); \ + __ret; \ +}) +#else +/* + * Loading 64-bit constants into a register from immediates is a non-trivial + * task on riscv64. To get it somewhat performant, load 32 bits into two + * different registers and then combine the results. + * + * If the processor supports the Zbkb extension, we can combine the final + * "slli,slli,srli,add" into the single "pack" instruction. If the processor + * doesn't support Zbkb but does support the Zbb extension, we can + * combine the final "slli,srli,add" into one instruction "add.uw". + */ +#define RISCV_RUNTIME_CONST_64_PREAMBLE \ + ".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + "lui %[__ret],0x89abd\n\t" \ + "lui %[__tmp],0x1234\n\t" \ + "addiw %[__ret],%[__ret],-0x211\n\t" \ + "addiw %[__tmp],%[__tmp],0x567\n\t" \ + +#define RISCV_RUNTIME_CONST_64_BASE \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "slli %[__ret],%[__ret],32\n\t" \ + "srli %[__ret],%[__ret],32\n\t" \ + "add %[__ret],%[__ret],%[__tmp]\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBA \ + ".option push\n\t" \ + ".option arch,+zba\n\t" \ + ".option norvc\n\t" \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "add.uw %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBKB \ + ".option push\n\t" \ + ".option arch,+zbkb\n\t" \ + ".option norvc\n\t" \ + "pack %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + +#if defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) \ + && defined(CONFIG_RISCV_ISA_ZBKB) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE_2( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBKB) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#else +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + RISCV_RUNTIME_CONST_64_BASE \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#endif +#endif + +#define runtime_const_shift_right_32(val, sym) \ +({ \ + u32 __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + SRLI " %[__ret],%[__val],12\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret) \ + : [__val] "r" (val)); \ + __ret; \ +}) + +#define runtime_const_init(type, sym) do { \ + extern s32 __start_runtime_##type##_##sym[]; \ + extern s32 __stop_runtime_##type##_##sym[]; \ + \ + runtime_const_fixup(__runtime_fixup_##type, \ + (unsigned long)(sym), \ + __start_runtime_##type##_##sym, \ + __stop_runtime_##type##_##sym); \ +} while (0) + +static inline void __runtime_fixup_caches(void *where, unsigned int insns) +{ + /* On riscv there are currently only cache-wide flushes so va is ignored. */ + __always_unused uintptr_t va = (uintptr_t)where; + + flush_icache_range(va, va + 4 * insns); +} + +/* + * The 32-bit immediate is stored in a lui+addi pairing. + * lui holds the upper 20 bits of the immediate in the first 20 bits of the instruction. + * addi holds the lower 12 bits of the immediate in the first 12 bits of the instruction. + */ +static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, unsigned int val) +{ + unsigned int lower_immediate, upper_immediate; + u32 lui_insn, addi_insn, addi_insn_mask; + __le32 lui_res, addi_res; + + /* Mask out upper 12 bit of addi */ + addi_insn_mask = 0x000fffff; + + lui_insn = (u32)le16_to_cpu(lui_parcel[0]) | (u32)le16_to_cpu(lui_parcel[1]) << 16; + addi_insn = (u32)le16_to_cpu(addi_parcel[0]) | (u32)le16_to_cpu(addi_parcel[1]) << 16; + + lower_immediate = sign_extend32(val, 11); + upper_immediate = (val - lower_immediate); + + if (upper_immediate & 0xfffff000) { + /* replace upper 20 bits of lui with upper immediate */ + lui_insn &= 0x00000fff; + lui_insn |= upper_immediate & 0xfffff000; + } else { + /* replace lui with nop if immediate is small enough to fit in addi */ + lui_insn = RISCV_INSN_NOP4; + /* + * lui is being skipped, so do a load instead of an add. A load + * is performed by adding with the x0 register. Setting rs to + * zero with the following mask will accomplish this goal. + */ + addi_insn_mask &= 0x07fff; + } + + if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) { + /* replace upper 12 bits of addi with lower 12 bits of val */ + addi_insn &= addi_insn_mask; + addi_insn |= (lower_immediate & 0x00000fff) << 20; + } else { + /* replace addi with nop if lower_immediate is empty */ + addi_insn = RISCV_INSN_NOP4; + } + + addi_res = cpu_to_le32(addi_insn); + lui_res = cpu_to_le32(lui_insn); + mutex_lock(&text_mutex); + patch_insn_write(addi_parcel, &addi_res, sizeof(addi_res)); + patch_insn_write(lui_parcel, &lui_res, sizeof(lui_res)); + mutex_unlock(&text_mutex); +} + +static inline void __runtime_fixup_ptr(void *where, unsigned long val) +{ +#ifdef CONFIG_32BIT + __runtime_fixup_32(where, where + 4, val); + __runtime_fixup_caches(where, 2); +#else + __runtime_fixup_32(where, where + 8, val); + __runtime_fixup_32(where + 4, where + 12, val >> 32); + __runtime_fixup_caches(where, 4); +#endif +} + +/* + * Replace the least significant 5 bits of the srli/srliw immediate that is + * located at bits 20-24 + */ +static inline void __runtime_fixup_shift(void *where, unsigned long val) +{ + __le16 *parcel = where; + __le32 res; + u32 insn; + + insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16; + + insn &= 0xfe0fffff; + insn |= (val & 0b11111) << 20; + + res = cpu_to_le32(insn); + mutex_lock(&text_mutex); + patch_text_nosync(where, &res, sizeof(insn)); + mutex_unlock(&text_mutex); +} + +static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), + unsigned long val, s32 *start, s32 *end) +{ + while (start < end) { + fn(*start + (void *)start, val); + start++; + } +} + +#endif /* _ASM_RISCV_RUNTIME_CONST_H */ diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 98f631b051db..341e74238aa0 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -34,6 +34,8 @@ enum sbi_ext_id { SBI_EXT_PMU = 0x504D55, SBI_EXT_DBCN = 0x4442434E, SBI_EXT_STA = 0x535441, + SBI_EXT_NACL = 0x4E41434C, + SBI_EXT_FWFT = 0x46574654, /* Experimentals extensions must lie within this range */ SBI_EXT_EXPERIMENTAL_START = 0x08000000, @@ -158,6 +160,7 @@ struct riscv_pmu_snapshot_data { }; #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) +#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0) #define RISCV_PMU_RAW_EVENT_IDX 0x20000 #define RISCV_PLAT_FW_EVENT 0xFFFF @@ -281,6 +284,152 @@ struct sbi_sta_struct { #define SBI_SHMEM_DISABLE -1 +enum sbi_ext_nacl_fid { + SBI_EXT_NACL_PROBE_FEATURE = 0x0, + SBI_EXT_NACL_SET_SHMEM = 0x1, + SBI_EXT_NACL_SYNC_CSR = 0x2, + SBI_EXT_NACL_SYNC_HFENCE = 0x3, + SBI_EXT_NACL_SYNC_SRET = 0x4, +}; + +enum sbi_ext_nacl_feature { + SBI_NACL_FEAT_SYNC_CSR = 0x0, + SBI_NACL_FEAT_SYNC_HFENCE = 0x1, + SBI_NACL_FEAT_SYNC_SRET = 0x2, + SBI_NACL_FEAT_AUTOSWAP_CSR = 0x3, +}; + +#define SBI_NACL_SHMEM_ADDR_SHIFT 12 +#define SBI_NACL_SHMEM_SCRATCH_OFFSET 0x0000 +#define SBI_NACL_SHMEM_SCRATCH_SIZE 0x1000 +#define SBI_NACL_SHMEM_SRET_OFFSET 0x0000 +#define SBI_NACL_SHMEM_SRET_SIZE 0x0200 +#define SBI_NACL_SHMEM_AUTOSWAP_OFFSET (SBI_NACL_SHMEM_SRET_OFFSET + \ + SBI_NACL_SHMEM_SRET_SIZE) +#define SBI_NACL_SHMEM_AUTOSWAP_SIZE 0x0080 +#define SBI_NACL_SHMEM_UNUSED_OFFSET (SBI_NACL_SHMEM_AUTOSWAP_OFFSET + \ + SBI_NACL_SHMEM_AUTOSWAP_SIZE) +#define SBI_NACL_SHMEM_UNUSED_SIZE 0x0580 +#define SBI_NACL_SHMEM_HFENCE_OFFSET (SBI_NACL_SHMEM_UNUSED_OFFSET + \ + SBI_NACL_SHMEM_UNUSED_SIZE) +#define SBI_NACL_SHMEM_HFENCE_SIZE 0x0780 +#define SBI_NACL_SHMEM_DBITMAP_OFFSET (SBI_NACL_SHMEM_HFENCE_OFFSET + \ + SBI_NACL_SHMEM_HFENCE_SIZE) +#define SBI_NACL_SHMEM_DBITMAP_SIZE 0x0080 +#define SBI_NACL_SHMEM_CSR_OFFSET (SBI_NACL_SHMEM_DBITMAP_OFFSET + \ + SBI_NACL_SHMEM_DBITMAP_SIZE) +#define SBI_NACL_SHMEM_CSR_SIZE ((__riscv_xlen / 8) * 1024) +#define SBI_NACL_SHMEM_SIZE (SBI_NACL_SHMEM_CSR_OFFSET + \ + SBI_NACL_SHMEM_CSR_SIZE) + +#define SBI_NACL_SHMEM_CSR_INDEX(__csr_num) \ + ((((__csr_num) & 0xc00) >> 2) | ((__csr_num) & 0xff)) + +#define SBI_NACL_SHMEM_HFENCE_ENTRY_SZ ((__riscv_xlen / 8) * 4) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_MAX \ + (SBI_NACL_SHMEM_HFENCE_SIZE / \ + SBI_NACL_SHMEM_HFENCE_ENTRY_SZ) +#define SBI_NACL_SHMEM_HFENCE_ENTRY(__num) \ + (SBI_NACL_SHMEM_HFENCE_OFFSET + \ + (__num) * SBI_NACL_SHMEM_HFENCE_ENTRY_SZ) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(__num) \ + SBI_NACL_SHMEM_HFENCE_ENTRY(__num) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(__num)\ + (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + (__riscv_xlen / 8)) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(__num)\ + (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + \ + ((__riscv_xlen / 8) * 3)) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS 1 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT \ + (__riscv_xlen - SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS) - 1) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK << \ + SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS 3 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS 4 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS) - 1) + +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA 0x0 +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL 0x1 +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID 0x2 +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL 0x3 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA 0x4 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL 0x5 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID 0x6 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL 0x7 + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS 1 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS 7 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS) - 1) +#define SBI_NACL_SHMEM_HFENCE_ORDER_BASE 12 + +#if __riscv_xlen == 32 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 9 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 7 +#else +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 16 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 14 +#endif +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT \ + SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS) - 1) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS) - 1) + +#define SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS BIT(0) +#define SBI_NACL_SHMEM_AUTOSWAP_HSTATUS ((__riscv_xlen / 8) * 1) + +#define SBI_NACL_SHMEM_SRET_X(__i) ((__riscv_xlen / 8) * (__i)) +#define SBI_NACL_SHMEM_SRET_X_LAST 31 + +/* SBI function IDs for FW feature extension */ +#define SBI_EXT_FWFT_SET 0x0 +#define SBI_EXT_FWFT_GET 0x1 + +enum sbi_fwft_feature_t { + SBI_FWFT_MISALIGNED_EXC_DELEG = 0x0, + SBI_FWFT_LANDING_PAD = 0x1, + SBI_FWFT_SHADOW_STACK = 0x2, + SBI_FWFT_DOUBLE_TRAP = 0x3, + SBI_FWFT_PTE_AD_HW_UPDATING = 0x4, + SBI_FWFT_POINTER_MASKING_PMLEN = 0x5, + SBI_FWFT_LOCAL_RESERVED_START = 0x6, + SBI_FWFT_LOCAL_RESERVED_END = 0x3fffffff, + SBI_FWFT_LOCAL_PLATFORM_START = 0x40000000, + SBI_FWFT_LOCAL_PLATFORM_END = 0x7fffffff, + + SBI_FWFT_GLOBAL_RESERVED_START = 0x80000000, + SBI_FWFT_GLOBAL_RESERVED_END = 0xbfffffff, + SBI_FWFT_GLOBAL_PLATFORM_START = 0xc0000000, + SBI_FWFT_GLOBAL_PLATFORM_END = 0xffffffff, +}; + +#define SBI_FWFT_PLATFORM_FEATURE_BIT BIT(30) +#define SBI_FWFT_GLOBAL_FEATURE_BIT BIT(31) + +#define SBI_FWFT_SET_FLAG_LOCK BIT(0) + /* SBI spec version fields */ #define SBI_SPEC_VERSION_DEFAULT 0x1 #define SBI_SPEC_VERSION_MAJOR_SHIFT 24 @@ -298,6 +447,11 @@ struct sbi_sta_struct { #define SBI_ERR_ALREADY_STARTED -7 #define SBI_ERR_ALREADY_STOPPED -8 #define SBI_ERR_NO_SHMEM -9 +#define SBI_ERR_INVALID_STATE -10 +#define SBI_ERR_BAD_RANGE -11 +#define SBI_ERR_TIMEOUT -12 +#define SBI_ERR_IO -13 +#define SBI_ERR_DENIED_LOCKED -14 extern unsigned long sbi_spec_version; struct sbiret { @@ -349,6 +503,23 @@ int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask, unsigned long asid); long sbi_probe_extension(int ext); +int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags); +int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature, + unsigned long value, unsigned long flags); +/** + * sbi_fwft_set_online_cpus() - Set a feature on all online cpus + * @feature: The feature to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +static inline int sbi_fwft_set_online_cpus(u32 feature, unsigned long value, + unsigned long flags) +{ + return sbi_fwft_set_cpumask(cpu_online_mask, feature, value, flags); +} + /* Check if current SBI specification version is 0.1 or not */ static inline int sbi_spec_is_0_1(void) { @@ -382,11 +553,21 @@ static inline int sbi_err_map_linux_errno(int err) case SBI_SUCCESS: return 0; case SBI_ERR_DENIED: + case SBI_ERR_DENIED_LOCKED: return -EPERM; case SBI_ERR_INVALID_PARAM: + case SBI_ERR_INVALID_STATE: return -EINVAL; + case SBI_ERR_BAD_RANGE: + return -ERANGE; case SBI_ERR_INVALID_ADDRESS: return -EFAULT; + case SBI_ERR_NO_SHMEM: + return -ENOMEM; + case SBI_ERR_TIMEOUT: + return -ETIMEDOUT; + case SBI_ERR_IO: + return -EIO; case SBI_ERR_NOT_SUPPORTED: case SBI_ERR_FAILURE: default: diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index ab92fc84e1fc..ea263d3683ef 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -42,6 +42,7 @@ static inline int set_kernel_memory(char *startp, char *endp, int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); bool kernel_page_present(struct page *page); #endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h new file mode 100644 index 000000000000..52f11bfd0079 --- /dev/null +++ b/arch/riscv/include/asm/spinlock.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_RISCV_SPINLOCK_H +#define __ASM_RISCV_SPINLOCK_H + +#ifdef CONFIG_QUEUED_SPINLOCKS +#define _Q_PENDING_LOOPS (1 << 9) +#endif + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS + +#define __no_arch_spinlock_redefine +#include <asm/ticket_spinlock.h> +#include <asm/qspinlock.h> +#include <asm/jump_label.h> + +/* + * TODO: Use an alternative instead of a static key when we are able to parse + * the extensions string earlier in the boot process. + */ +DECLARE_STATIC_KEY_TRUE(qspinlock_key); + +#define SPINLOCK_BASE_DECLARE(op, type, type_lock) \ +static __always_inline type arch_spin_##op(type_lock lock) \ +{ \ + if (static_branch_unlikely(&qspinlock_key)) \ + return queued_spin_##op(lock); \ + return ticket_spin_##op(lock); \ +} + +SPINLOCK_BASE_DECLARE(lock, void, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(unlock, void, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(is_locked, int, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(is_contended, int, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(trylock, bool, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(value_unlocked, int, arch_spinlock_t) + +#elif defined(CONFIG_RISCV_QUEUED_SPINLOCKS) + +#include <asm/qspinlock.h> + +#else + +#include <asm/ticket_spinlock.h> + +#endif + +#include <asm/qrwlock.h> + +#endif /* __ASM_RISCV_SPINLOCK_H */ diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 4ffb022b097f..dc5782b5fbad 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -18,6 +18,10 @@ struct suspend_context { unsigned long ie; #ifdef CONFIG_MMU unsigned long satp; + unsigned long stimecmp; +#if __riscv_xlen < 64 + unsigned long stimecmph; +#endif #endif }; diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 7594df37cc9f..0e71eb82f920 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -70,6 +70,24 @@ static __always_inline bool has_fpu(void) { return false; } #define __switch_to_fpu(__prev, __next) do { } while (0) #endif +static inline void envcfg_update_bits(struct task_struct *task, + unsigned long mask, unsigned long val) +{ + unsigned long envcfg; + + envcfg = (task->thread.envcfg & ~mask) | val; + task->thread.envcfg = envcfg; + if (task == current) + csr_write(CSR_ENVCFG, envcfg); +} + +static inline void __switch_to_envcfg(struct task_struct *next) +{ + asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0", + 0, RISCV_ISA_EXT_XLINUXENVCFG, 1) + :: "r" (next->thread.envcfg) : "memory"); +} + extern struct task_struct *__switch_to(struct task_struct *, struct task_struct *); @@ -99,10 +117,11 @@ do { \ __set_prev_cpu(__prev->thread); \ if (has_fpu()) \ __switch_to_fpu(__prev, __next); \ - if (has_vector()) \ + if (has_vector() || has_xtheadvector()) \ __switch_to_vector(__prev, __next); \ if (switch_to_should_flush_icache(__next)) \ local_flush_icache_all(); \ + __switch_to_envcfg(__next); \ ((last) = __switch_to(__prev, __next)); \ } while (0) diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 121fff429dce..34313387f977 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -30,6 +30,13 @@ static inline int syscall_get_nr(struct task_struct *task, return regs->a7; } +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->a7 = nr; +} + static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { @@ -62,8 +69,23 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { args[0] = regs->orig_a0; - args++; - memcpy(args, ®s->a1, 5 * sizeof(args[0])); + args[1] = regs->a1; + args[2] = regs->a2; + args[3] = regs->a3; + args[4] = regs->a4; + args[5] = regs->a5; +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->orig_a0 = args[0]; + regs->a1 = args[1]; + regs->a2 = args[2]; + regs->a3 = args[3]; + regs->a4 = args[4]; + regs->a5 = args[5]; } static inline int syscall_get_arch(struct task_struct *task) diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/text-patching.h index 7228e266b9a1..7228e266b9a1 100644 --- a/arch/riscv/include/asm/patch.h +++ b/arch/riscv/include/asm/text-patching.h diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 9c10fb180f43..f5916a70879a 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -107,9 +107,10 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); * - pending work-to-be-done flags are in lowest half-word * - other flags in upper half-word(s) */ -#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ -#define TIF_SIGPENDING 2 /* signal pending */ -#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_NEED_RESCHED 0 /* rescheduling necessary */ +#define TIF_NEED_RESCHED_LAZY 1 /* Lazy rescheduling needed */ +#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ +#define TIF_SIGPENDING 3 /* signal pending */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ #define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ @@ -117,9 +118,10 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define TIF_32BIT 11 /* compat-mode 32bit process */ #define TIF_RISCV_V_DEFER_RESTORE 12 /* restore Vector before returing to user */ +#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) -#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_RISCV_V_DEFER_RESTORE (1 << TIF_RISCV_V_DEFER_RESTORE) diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index 1f6c38420d8e..50b63b5c15bd 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -10,24 +10,6 @@ struct mmu_gather; static void tlb_flush(struct mmu_gather *tlb); -#ifdef CONFIG_MMU -#include <linux/swap.h> - -/* - * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to - * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use - * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this - * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the - * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h - * for more details. - */ -static inline void __tlb_remove_table(void *table) -{ - free_page_and_swap_cache(table); -} - -#endif /* CONFIG_MMU */ - #define tlb_flush tlb_flush #include <asm-generic/tlb.h> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 72e559934952..1a20dd746a49 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -56,12 +56,13 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); #endif bool arch_tlbbatch_should_defer(struct mm_struct *mm); void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr); + struct mm_struct *mm, unsigned long start, unsigned long end); void arch_flush_tlb_batched_pending(struct mm_struct *mm); void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 72ec1d9bd3f3..525e50db24f7 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -9,8 +9,41 @@ #define _ASM_RISCV_UACCESS_H #include <asm/asm-extable.h> +#include <asm/cpufeature.h> #include <asm/pgtable.h> /* for TASK_SIZE */ +#ifdef CONFIG_RISCV_ISA_SUPM +static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr) +{ + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) { + u8 pmlen = mm->context.pmlen; + + /* Virtual addresses are sign-extended; physical addresses are zero-extended. */ + if (IS_ENABLED(CONFIG_MMU)) + return (long)(addr << pmlen) >> pmlen; + else + return (addr << pmlen) >> pmlen; + } + + return addr; +} + +#define untagged_addr(addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr_remote(current->mm, __addr); \ +}) + +#define untagged_addr_remote(mm, addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + mmap_assert_locked(mm); \ + (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ +}) + +#define access_ok(addr, size) likely(__access_ok(untagged_addr(addr), size)) +#else +#define untagged_addr(addr) (addr) +#endif + /* * User space memory access functions */ @@ -29,6 +62,19 @@ __asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory") /* + * This is the smallest unsigned integer type that can fit a value + * (up to 'long long') + */ +#define __inttype(x) __typeof__( \ + __typefits(x, char, \ + __typefits(x, short, \ + __typefits(x, int, \ + __typefits(x, long, 0ULL))))) + +#define __typefits(x, type, not) \ + __builtin_choose_expr(sizeof(x) <= sizeof(type), (unsigned type)0, not) + +/* * The exception table consists of pairs of addresses: the first is the * address of an instruction that is allowed to fault, and the second is * the address at which the program should continue. No registers are @@ -50,27 +96,59 @@ * call. */ -#define __get_user_asm(insn, x, ptr, err) \ +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define __get_user_asm(insn, x, ptr, label) \ + asm_goto_output( \ + "1:\n" \ + " " insn " %0, %1\n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, %l2, %0) \ + : "=&r" (x) \ + : "m" (*(ptr)) : : label) +#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ +#define __get_user_asm(insn, x, ptr, label) \ do { \ - __typeof__(x) __x; \ + long __gua_err = 0; \ __asm__ __volatile__ ( \ "1:\n" \ " " insn " %1, %2\n" \ "2:\n" \ _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 2b, %0, %1) \ - : "+r" (err), "=&r" (__x) \ + : "+r" (__gua_err), "=&r" (x) \ : "m" (*(ptr))); \ - (x) = __x; \ + if (__gua_err) \ + goto label; \ } while (0) +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ #ifdef CONFIG_64BIT -#define __get_user_8(x, ptr, err) \ - __get_user_asm("ld", x, ptr, err) +#define __get_user_8(x, ptr, label) \ + __get_user_asm("ld", x, ptr, label) #else /* !CONFIG_64BIT */ -#define __get_user_8(x, ptr, err) \ + +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define __get_user_8(x, ptr, label) \ do { \ u32 __user *__ptr = (u32 __user *)(ptr); \ u32 __lo, __hi; \ + asm_goto_output( \ + "1:\n" \ + " lw %0, %2\n" \ + "2:\n" \ + " lw %1, %3\n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, %l4, %0) \ + _ASM_EXTABLE_UACCESS_ERR(2b, %l4, %0) \ + : "=&r" (__lo), "=r" (__hi) \ + : "m" (__ptr[__LSW]), "m" (__ptr[__MSW]) \ + : : label); \ + (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ + (((u64)__hi << 32) | __lo))); \ +} while (0) +#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ +#define __get_user_8(x, ptr, label) \ +do { \ + u32 __user *__ptr = (u32 __user *)(ptr); \ + u32 __lo, __hi; \ + long __gu8_err = 0; \ __asm__ __volatile__ ( \ "1:\n" \ " lw %1, %3\n" \ @@ -79,35 +157,62 @@ do { \ "3:\n" \ _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 3b, %0, %1) \ _ASM_EXTABLE_UACCESS_ERR_ZERO(2b, 3b, %0, %1) \ - : "+r" (err), "=&r" (__lo), "=r" (__hi) \ + : "+r" (__gu8_err), "=&r" (__lo), "=r" (__hi) \ : "m" (__ptr[__LSW]), "m" (__ptr[__MSW])); \ - if (err) \ + if (__gu8_err) { \ __hi = 0; \ - (x) = (__typeof__(x))((__typeof__((x)-(x)))( \ + goto label; \ + } \ + (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ (((u64)__hi << 32) | __lo))); \ } while (0) +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + #endif /* CONFIG_64BIT */ -#define __get_user_nocheck(x, __gu_ptr, __gu_err) \ +unsigned long __must_check __asm_copy_to_user_sum_enabled(void __user *to, + const void *from, unsigned long n); +unsigned long __must_check __asm_copy_from_user_sum_enabled(void *to, + const void __user *from, unsigned long n); + +#define __get_user_nocheck(x, __gu_ptr, label) \ do { \ + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ + !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ + if (__asm_copy_from_user_sum_enabled(&(x), __gu_ptr, sizeof(*__gu_ptr))) \ + goto label; \ + break; \ + } \ switch (sizeof(*__gu_ptr)) { \ case 1: \ - __get_user_asm("lb", (x), __gu_ptr, __gu_err); \ + __get_user_asm("lb", (x), __gu_ptr, label); \ break; \ case 2: \ - __get_user_asm("lh", (x), __gu_ptr, __gu_err); \ + __get_user_asm("lh", (x), __gu_ptr, label); \ break; \ case 4: \ - __get_user_asm("lw", (x), __gu_ptr, __gu_err); \ + __get_user_asm("lw", (x), __gu_ptr, label); \ break; \ case 8: \ - __get_user_8((x), __gu_ptr, __gu_err); \ + __get_user_8((x), __gu_ptr, label); \ break; \ default: \ BUILD_BUG(); \ } \ } while (0) +#define __get_user_error(x, ptr, err) \ +do { \ + __label__ __gu_failed; \ + \ + __get_user_nocheck(x, ptr, __gu_failed); \ + err = 0; \ + break; \ +__gu_failed: \ + x = 0; \ + err = -EFAULT; \ +} while (0) + /** * __get_user: - Get a simple variable from user space, with less checking. * @x: Variable to store result. @@ -130,15 +235,18 @@ do { \ */ #define __get_user(x, ptr) \ ({ \ - const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \ + const __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \ long __gu_err = 0; \ + __typeof__(x) __gu_val; \ \ __chk_user_ptr(__gu_ptr); \ \ __enable_user_access(); \ - __get_user_nocheck(x, __gu_ptr, __gu_err); \ + __get_user_error(__gu_val, __gu_ptr, __gu_err); \ __disable_user_access(); \ \ + (x) = __gu_val; \ + \ __gu_err; \ }) @@ -168,61 +276,73 @@ do { \ ((x) = (__force __typeof__(x))0, -EFAULT); \ }) -#define __put_user_asm(insn, x, ptr, err) \ +#define __put_user_asm(insn, x, ptr, label) \ do { \ __typeof__(*(ptr)) __x = x; \ - __asm__ __volatile__ ( \ + asm goto( \ "1:\n" \ - " " insn " %z2, %1\n" \ - "2:\n" \ - _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %0) \ - : "+r" (err), "=m" (*(ptr)) \ - : "rJ" (__x)); \ + " " insn " %z0, %1\n" \ + _ASM_EXTABLE(1b, %l2) \ + : : "rJ" (__x), "m"(*(ptr)) : : label); \ } while (0) #ifdef CONFIG_64BIT -#define __put_user_8(x, ptr, err) \ - __put_user_asm("sd", x, ptr, err) +#define __put_user_8(x, ptr, label) \ + __put_user_asm("sd", x, ptr, label) #else /* !CONFIG_64BIT */ -#define __put_user_8(x, ptr, err) \ +#define __put_user_8(x, ptr, label) \ do { \ u32 __user *__ptr = (u32 __user *)(ptr); \ u64 __x = (__typeof__((x)-(x)))(x); \ - __asm__ __volatile__ ( \ + asm goto( \ "1:\n" \ - " sw %z3, %1\n" \ + " sw %z0, %2\n" \ "2:\n" \ - " sw %z4, %2\n" \ - "3:\n" \ - _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %0) \ - _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %0) \ - : "+r" (err), \ - "=m" (__ptr[__LSW]), \ - "=m" (__ptr[__MSW]) \ - : "rJ" (__x), "rJ" (__x >> 32)); \ + " sw %z1, %3\n" \ + _ASM_EXTABLE(1b, %l4) \ + _ASM_EXTABLE(2b, %l4) \ + : : "rJ" (__x), "rJ" (__x >> 32), \ + "m" (__ptr[__LSW]), \ + "m" (__ptr[__MSW]) : : label); \ } while (0) #endif /* CONFIG_64BIT */ -#define __put_user_nocheck(x, __gu_ptr, __pu_err) \ +#define __put_user_nocheck(x, __gu_ptr, label) \ do { \ + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ + !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ + __inttype(x) val = (__inttype(x))x; \ + if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \ + goto label; \ + break; \ + } \ switch (sizeof(*__gu_ptr)) { \ case 1: \ - __put_user_asm("sb", (x), __gu_ptr, __pu_err); \ + __put_user_asm("sb", (x), __gu_ptr, label); \ break; \ case 2: \ - __put_user_asm("sh", (x), __gu_ptr, __pu_err); \ + __put_user_asm("sh", (x), __gu_ptr, label); \ break; \ case 4: \ - __put_user_asm("sw", (x), __gu_ptr, __pu_err); \ + __put_user_asm("sw", (x), __gu_ptr, label); \ break; \ case 8: \ - __put_user_8((x), __gu_ptr, __pu_err); \ + __put_user_8((x), __gu_ptr, label); \ break; \ default: \ BUILD_BUG(); \ } \ } while (0) +#define __put_user_error(x, ptr, err) \ +do { \ + __label__ err_label; \ + __put_user_nocheck(x, ptr, err_label); \ + break; \ +err_label: \ + (err) = -EFAULT; \ +} while (0) + /** * __put_user: - Write a simple value into user space, with less checking. * @x: Value to copy to user space. @@ -246,14 +366,14 @@ do { \ */ #define __put_user(x, ptr) \ ({ \ - __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \ __typeof__(*__gu_ptr) __val = (x); \ long __pu_err = 0; \ \ __chk_user_ptr(__gu_ptr); \ \ __enable_user_access(); \ - __put_user_nocheck(__val, __gu_ptr, __pu_err); \ + __put_user_error(__val, __gu_ptr, __pu_err); \ __disable_user_access(); \ \ __pu_err; \ @@ -293,13 +413,13 @@ unsigned long __must_check __asm_copy_from_user(void *to, static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { - return __asm_copy_from_user(to, from, n); + return __asm_copy_from_user(to, untagged_addr(from), n); } static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - return __asm_copy_to_user(to, from, n); + return __asm_copy_to_user(untagged_addr(to), from, n); } extern long strncpy_from_user(char *dest, const char __user *src, long count); @@ -314,27 +434,49 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) { might_fault(); return access_ok(to, n) ? - __clear_user(to, n) : n; + __clear_user(untagged_addr(to), n) : n; } #define __get_kernel_nofault(dst, src, type, err_label) \ -do { \ - long __kr_err = 0; \ - \ - __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ - if (unlikely(__kr_err)) \ - goto err_label; \ -} while (0) + __get_user_nocheck(*((type *)(dst)), (type *)(src), err_label) #define __put_kernel_nofault(dst, src, type, err_label) \ -do { \ - long __kr_err = 0; \ - \ - __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ - if (unlikely(__kr_err)) \ - goto err_label; \ + __put_user_nocheck(*((type *)(src)), (type *)(dst), err_label) + +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr, len))) + return 0; + __enable_user_access(); + return 1; +} +#define user_access_begin user_access_begin +#define user_access_end __disable_user_access + +static inline unsigned long user_access_save(void) { return 0UL; } +static inline void user_access_restore(unsigned long enabled) { } + +/* + * We want the unsafe accessors to always be inlined and use + * the error labels - thus the macro games. + */ +#define unsafe_put_user(x, ptr, label) \ + __put_user_nocheck(x, (ptr), label) + +#define unsafe_get_user(x, ptr, label) do { \ + __inttype(*(ptr)) __gu_val; \ + __get_user_nocheck(__gu_val, (ptr), label); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) +#define unsafe_copy_to_user(_dst, _src, _len, label) \ + if (__asm_copy_to_user_sum_enabled(_dst, _src, _len)) \ + goto label; + +#define unsafe_copy_from_user(_dst, _src, _len, label) \ + if (__asm_copy_from_user_sum_enabled(_dst, _src, _len)) \ + goto label; + #else /* CONFIG_MMU */ #include <asm-generic/uaccess.h> #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h index 3fc7deda9190..5008f76cdc27 100644 --- a/arch/riscv/include/asm/uprobes.h +++ b/arch/riscv/include/asm/uprobes.h @@ -4,7 +4,7 @@ #define _ASM_RISCV_UPROBES_H #include <asm/probes.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/bug.h> #define MAX_UINSN_BYTES 8 diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index f891478829a5..c130d8100232 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -14,7 +14,7 @@ */ #ifdef CONFIG_MMU -#define __VVAR_PAGES 2 +#define __VDSO_PAGES 4 #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> diff --git a/arch/riscv/include/asm/vdso/data.h b/arch/riscv/include/asm/vdso/arch_data.h index dc2f76f58b76..da57a3786f7a 100644 --- a/arch/riscv/include/asm/vdso/data.h +++ b/arch/riscv/include/asm/vdso/arch_data.h @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __RISCV_ASM_VDSO_DATA_H -#define __RISCV_ASM_VDSO_DATA_H +#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H +#define __RISCV_ASM_VDSO_ARCH_DATA_H #include <linux/types.h> #include <vdso/datapage.h> #include <asm/hwprobe.h> -struct arch_vdso_data { +struct vdso_arch_data { /* Stash static answers to the hwprobe queries when all CPUs are selected. */ __u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1]; @@ -14,4 +14,4 @@ struct arch_vdso_data { __u8 homogeneous_cpus; }; -#endif /* __RISCV_ASM_VDSO_DATA_H */ +#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */ diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h new file mode 100644 index 000000000000..c6d66895c1f5 --- /dev/null +++ b/arch/riscv/include/asm/vdso/getrandom.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved. + */ +#ifndef __ASM_VDSO_GETRANDOM_H +#define __ASM_VDSO_GETRANDOM_H + +#ifndef __ASSEMBLY__ + +#include <asm/unistd.h> + +static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, unsigned int _flags) +{ + register long ret asm("a0"); + register long nr asm("a7") = __NR_getrandom; + register void *buffer asm("a0") = _buffer; + register size_t len asm("a1") = _len; + register unsigned int flags asm("a2") = _flags; + + asm volatile ("ecall\n" + : "=r" (ret) + : "r" (nr), "r" (buffer), "r" (len), "r" (flags) + : "memory"); + + return ret; +} + +#endif /* !__ASSEMBLY__ */ + +#endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index ba3283cf7acc..29164f84f93c 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -69,7 +69,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #endif /* CONFIG_GENERIC_TIME_VSYSCALL */ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { /* * The purpose of csr_read(CSR_TIME) is to trap the system into @@ -79,18 +79,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return csr_read(CSR_TIME); } -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return _timens_data; -} -#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h index 82fd5d83bd60..1140b54b4bc8 100644 --- a/arch/riscv/include/asm/vdso/vsyscall.h +++ b/arch/riscv/include/asm/vdso/vsyscall.h @@ -4,21 +4,8 @@ #ifndef __ASSEMBLY__ -#include <linux/timekeeper_internal.h> #include <vdso/datapage.h> -extern struct vdso_data *vdso_data; - -/* - * Update the vDSO data page to keep in sync with kernel timekeeping. - */ -static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void) -{ - return vdso_data; -} - -#define __arch_get_k_vdso_data __riscv_get_k_vdso_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index be7d309cca8a..b61786d43c20 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -18,9 +18,31 @@ #include <asm/cpufeature.h> #include <asm/csr.h> #include <asm/asm.h> +#include <asm/vendorid_list.h> +#include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> + +#define __riscv_v_vstate_or(_val, TYPE) ({ \ + typeof(_val) _res = _val; \ + if (has_xtheadvector()) \ + _res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD; \ + else \ + _res = (_res & ~SR_VS) | SR_VS_##TYPE; \ + _res; \ +}) + +#define __riscv_v_vstate_check(_val, TYPE) ({ \ + bool _res; \ + if (has_xtheadvector()) \ + _res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD; \ + else \ + _res = ((_val) & SR_VS) == SR_VS_##TYPE; \ + _res; \ +}) extern unsigned long riscv_v_vsize; int riscv_v_setup_vsize(void); +bool insn_is_vector(u32 insn_buf); bool riscv_v_first_use_handler(struct pt_regs *regs); void kernel_vector_begin(void); void kernel_vector_end(void); @@ -40,39 +62,67 @@ static __always_inline bool has_vector(void) return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X); } +static __always_inline bool has_xtheadvector_no_alternatives(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR); + else + return false; +} + +static __always_inline bool has_xtheadvector(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID, + RISCV_ISA_VENDOR_EXT_XTHEADVECTOR); + else + return false; +} + static inline void __riscv_v_vstate_clean(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN; + regs->status = __riscv_v_vstate_or(regs->status, CLEAN); } static inline void __riscv_v_vstate_dirty(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY; + regs->status = __riscv_v_vstate_or(regs->status, DIRTY); } static inline void riscv_v_vstate_off(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_OFF; + regs->status = __riscv_v_vstate_or(regs->status, OFF); } static inline void riscv_v_vstate_on(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL; + regs->status = __riscv_v_vstate_or(regs->status, INITIAL); } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { - return (regs->status & SR_VS) != 0; + return !__riscv_v_vstate_check(regs->status, OFF); } static __always_inline void riscv_v_enable(void) { - csr_set(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_set(CSR_SSTATUS, SR_VS_THEAD); + else + csr_set(CSR_SSTATUS, SR_VS); } static __always_inline void riscv_v_disable(void) { - csr_clear(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_clear(CSR_SSTATUS, SR_VS_THEAD); + else + csr_clear(CSR_SSTATUS, SR_VS); +} + +static __always_inline bool riscv_v_is_on(void) +{ + return !!(csr_read(CSR_SSTATUS) & SR_VS); } static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) @@ -81,10 +131,36 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) "csrr %0, " __stringify(CSR_VSTART) "\n\t" "csrr %1, " __stringify(CSR_VTYPE) "\n\t" "csrr %2, " __stringify(CSR_VL) "\n\t" - "csrr %3, " __stringify(CSR_VCSR) "\n\t" - "csrr %4, " __stringify(CSR_VLENB) "\n\t" : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), - "=r" (dest->vcsr), "=r" (dest->vlenb) : :); + "=r" (dest->vcsr) : :); + + if (has_xtheadvector()) { + unsigned long status; + + /* + * CSR_VCSR is defined as + * [2:1] - vxrm[1:0] + * [0] - vxsat + * The earlier vector spec implemented by T-Head uses separate + * registers for the same bit-elements, so just combine those + * into the existing output field. + * + * Additionally T-Head cores need FS to be enabled when accessing + * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions. + * Though the cores do not implement the VXRM and VXSAT fields in the + * FCSR CSR that vector-0.7.1 specifies. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT; + + dest->vlenb = riscv_v_vsize / 32; + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + dest->vcsr = csr_read(CSR_VCSR); + dest->vlenb = csr_read(CSR_VLENB); + } } static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) @@ -95,9 +171,25 @@ static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src "vsetvl x0, %2, %1\n\t" ".option pop\n\t" "csrw " __stringify(CSR_VSTART) ", %0\n\t" - "csrw " __stringify(CSR_VCSR) ", %3\n\t" - : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl), - "r" (src->vcsr) :); + : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl)); + + if (has_xtheadvector()) { + unsigned long status = csr_read(CSR_SSTATUS); + + /* + * Similar to __vstate_csr_save above, restore values for the + * separate VXRM and VXSAT CSRs from the vcsr variable. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + + csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK); + csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK); + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + csr_write(CSR_VCSR, src->vcsr); + } } static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, @@ -107,19 +199,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, riscv_v_enable(); __vstate_csr_save(save_to); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V8T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V16T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V24T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vse8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } riscv_v_disable(); } @@ -129,19 +235,33 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ unsigned long vl; riscv_v_enable(); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vle8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V8T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V16T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V24T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vle8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } __vstate_csr_restore(restore_from); riscv_v_disable(); } @@ -151,33 +271,41 @@ static inline void __riscv_v_vstate_discard(void) unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1); riscv_v_enable(); + if (has_xtheadvector()) + asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4"); + else + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + ".option pop\n\t": "=&r" (vl)); + asm volatile ( ".option push\n\t" ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" "vmv.v.i v0, -1\n\t" "vmv.v.i v8, -1\n\t" "vmv.v.i v16, -1\n\t" "vmv.v.i v24, -1\n\t" "vsetvl %0, x0, %1\n\t" ".option pop\n\t" - : "=&r" (vl) : "r" (vtype_inval) : "memory"); + : "=&r" (vl) : "r" (vtype_inval)); + riscv_v_disable(); } static inline void riscv_v_vstate_discard(struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_OFF) - return; - - __riscv_v_vstate_discard(); - __riscv_v_vstate_dirty(regs); + if (riscv_v_vstate_query(regs)) { + __riscv_v_vstate_discard(); + __riscv_v_vstate_dirty(regs); + } } static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(regs->status, DIRTY)) { __riscv_v_vstate_save(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -186,7 +314,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { __riscv_v_vstate_restore(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -195,7 +323,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_set_restore(struct task_struct *task, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE); riscv_v_vstate_on(regs); } @@ -243,6 +371,11 @@ static inline void __switch_to_vector(struct task_struct *prev, struct pt_regs *regs; if (riscv_preempt_v_started(prev)) { + if (riscv_v_is_on()) { + WARN_ON(prev->thread.riscv_v_flags & RISCV_V_CTX_DEPTH_MASK); + riscv_v_disable(); + prev->thread.riscv_v_flags |= RISCV_PREEMPT_V_IN_SCHEDULE; + } if (riscv_preempt_v_dirty(prev)) { __riscv_v_vstate_save(&prev->thread.kernel_vstate, prev->thread.kernel_vstate.datap); @@ -253,10 +386,16 @@ static inline void __switch_to_vector(struct task_struct *prev, riscv_v_vstate_save(&prev->thread.vstate, regs); } - if (riscv_preempt_v_started(next)) - riscv_preempt_v_set_restore(next); - else + if (riscv_preempt_v_started(next)) { + if (next->thread.riscv_v_flags & RISCV_PREEMPT_V_IN_SCHEDULE) { + next->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_IN_SCHEDULE; + riscv_v_enable(); + } else { + riscv_preempt_v_set_restore(next); + } + } else { riscv_v_vstate_set_restore(next, task_pt_regs(next)); + } } void riscv_v_vstate_ctrl_init(struct task_struct *tsk); @@ -268,6 +407,9 @@ struct pt_regs; static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; } static __always_inline bool has_vector(void) { return false; } +static __always_inline bool insn_is_vector(u32 insn_buf) { return false; } +static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; } +static __always_inline bool has_xtheadvector(void) { return false; } static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; } diff --git a/arch/riscv/include/asm/vendor_extensions/sifive.h b/arch/riscv/include/asm/vendor_extensions/sifive.h new file mode 100644 index 000000000000..ac00e500361c --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/sifive.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_H + +#include <asm/vendor_extensions.h> + +#include <linux/types.h> + +#define RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD 0 +#define RISCV_ISA_VENDOR_EXT_XSFVQMACCQOQ 1 +#define RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF 2 +#define RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ 3 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_sifive; + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h new file mode 100644 index 000000000000..90a61abd033c --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_HWPROBE_H + +#include <linux/cpumask.h> + +#include <uapi/asm/hwprobe.h> + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE +void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h new file mode 100644 index 000000000000..e85c75b3b340 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H + +#include <asm/vendor_extensions.h> + +#include <linux/types.h> + +/* + * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX. + */ +#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR 0 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead; + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void disable_xtheadvector(void); +#else +static inline void disable_xtheadvector(void) { } +#endif + +/* Extension specific helpers */ + +/* + * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older + * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for + * vsetvli t4, x0, e8, m8, d1 + */ +#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t" + +/* + * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same + * encoding as the standard vse8.v and vle8.v, compilers seem to optimize + * the call resulting in a different encoding and then using a value for + * the "mop" field that is not part of vector-0.7.1 + * So encode specific variants for vstate_save and _restore. + */ +#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t" +#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t" +#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t" +#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t" +#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t" +#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t" +#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t" +#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t" + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h new file mode 100644 index 000000000000..65a9c5612466 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H + +#include <linux/cpumask.h> + +#include <uapi/asm/hwprobe.h> + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h new file mode 100644 index 000000000000..6b9293e984a9 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2024 Rivos, Inc + */ + +#ifndef _ASM_RISCV_SYS_HWPROBE_H +#define _ASM_RISCV_SYS_HWPROBE_H + +#include <asm/cpufeature.h> + +#define VENDOR_EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + } while (false) + +/* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + * + * _extension_checks is an arbitrary C block to set the values of pair->value + * and missing. It should be filled with VENDOR_EXT_KEY expressions. + */ +#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks) \ + do { \ + int cpu; \ + u64 missing = 0; \ + for_each_cpu(cpu, (cpus)) { \ + struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu]; \ + _extension_checks \ + } \ + (pair)->value &= ~missing; \ + } while (false) \ + +#endif /* _ASM_RISCV_SYS_HWPROBE_H */ diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h index 2f2bb0c84f9a..a5150cdf34d8 100644 --- a/arch/riscv/include/asm/vendorid_list.h +++ b/arch/riscv/include/asm/vendorid_list.h @@ -6,6 +6,7 @@ #define ASM_VENDOR_LIST_H #define ANDES_VENDOR_ID 0x31e +#define MICROCHIP_VENDOR_ID 0x029 #define SIFIVE_VENDOR_ID 0x489 #define THEAD_VENDOR_ID 0x5b7 diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 1e153cda57db..aaf6ad970499 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _UAPI_ASM_HWPROBE_H @@ -72,6 +72,16 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_EXT_ZCF (1ULL << 46) #define RISCV_HWPROBE_EXT_ZCMOP (1ULL << 47) #define RISCV_HWPROBE_EXT_ZAWRS (1ULL << 48) +#define RISCV_HWPROBE_EXT_SUPM (1ULL << 49) +#define RISCV_HWPROBE_EXT_ZICNTR (1ULL << 50) +#define RISCV_HWPROBE_EXT_ZIHPM (1ULL << 51) +#define RISCV_HWPROBE_EXT_ZFBFMIN (1ULL << 52) +#define RISCV_HWPROBE_EXT_ZVFBFMIN (1ULL << 53) +#define RISCV_HWPROBE_EXT_ZVFBFWMA (1ULL << 54) +#define RISCV_HWPROBE_EXT_ZICBOM (1ULL << 55) +#define RISCV_HWPROBE_EXT_ZAAMO (1ULL << 56) +#define RISCV_HWPROBE_EXT_ZALRSC (1ULL << 57) +#define RISCV_HWPROBE_EXT_ZABHA (1ULL << 58) #define RISCV_HWPROBE_KEY_CPUPERF_0 5 #define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) #define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) @@ -88,6 +98,14 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW 2 #define RISCV_HWPROBE_MISALIGNED_SCALAR_FAST 3 #define RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED 4 +#define RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF 10 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN 0 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW 2 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_FAST 3 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED 4 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 11 +#define RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE 12 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0 13 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ /* Flags */ diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index e97db3296456..5f59fd226cc5 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -175,6 +175,15 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZCF, KVM_RISCV_ISA_EXT_ZCMOP, KVM_RISCV_ISA_EXT_ZAWRS, + KVM_RISCV_ISA_EXT_SMNPM, + KVM_RISCV_ISA_EXT_SSNPM, + KVM_RISCV_ISA_EXT_SVADE, + KVM_RISCV_ISA_EXT_SVADU, + KVM_RISCV_ISA_EXT_SVVPTC, + KVM_RISCV_ISA_EXT_ZABHA, + KVM_RISCV_ISA_EXT_ZICCRSE, + KVM_RISCV_ISA_EXT_ZAAMO, + KVM_RISCV_ISA_EXT_ZALRSC, KVM_RISCV_ISA_EXT_MAX, }; @@ -194,6 +203,7 @@ enum KVM_RISCV_SBI_EXT_ID { KVM_RISCV_SBI_EXT_VENDOR, KVM_RISCV_SBI_EXT_DBCN, KVM_RISCV_SBI_EXT_STA, + KVM_RISCV_SBI_EXT_SUSP, KVM_RISCV_SBI_EXT_MAX, }; @@ -207,9 +217,6 @@ struct kvm_riscv_sbi_sta { #define KVM_RISCV_TIMER_STATE_OFF 0 #define KVM_RISCV_TIMER_STATE_ON 1 -#define KVM_REG_SIZE(id) \ - (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) - /* If you need to interpret the index values, here is the key: */ #define KVM_REG_RISCV_TYPE_MASK 0x00000000FF000000 #define KVM_REG_RISCV_TYPE_SHIFT 24 diff --git a/arch/riscv/include/uapi/asm/vendor/sifive.h b/arch/riscv/include/uapi/asm/vendor/sifive.h new file mode 100644 index 000000000000..9f3278a4b298 --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/sifive.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCDOD (1 << 0) +#define RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCQOQ (1 << 1) +#define RISCV_HWPROBE_VENDOR_EXT_XSFVFNRCLIPXFQF (1 << 2) +#define RISCV_HWPROBE_VENDOR_EXT_XSFVFWMACCQQQ (1 << 3) diff --git a/arch/riscv/include/uapi/asm/vendor/thead.h b/arch/riscv/include/uapi/asm/vendor/thead.h new file mode 100644 index 000000000000..43790ebe5faf --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/thead.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR (1 << 0) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 7f88cc4931f5..c7b542573407 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -9,8 +9,8 @@ CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif -CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) -CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init) +CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init) ifdef CONFIG_KEXEC_CORE AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) @@ -36,9 +36,14 @@ KASAN_SANITIZE_alternative.o := n KASAN_SANITIZE_cpufeature.o := n KASAN_SANITIZE_sbi_ecall.o := n endif +ifdef CONFIG_FORTIFY_SOURCE +CFLAGS_alternative.o += -D__NO_FORTIFY +CFLAGS_cpufeature.o += -D__NO_FORTIFY +CFLAGS_sbi_ecall.o += -D__NO_FORTIFY +endif endif -extra-y += vmlinux.lds +always-$(KBUILD_BUILTIN) += vmlinux.lds obj-y += head.o obj-y += soc.o @@ -70,7 +75,8 @@ obj-$(CONFIG_MMU) += vdso.o vdso/ obj-$(CONFIG_RISCV_MISALIGNED) += traps_misaligned.o obj-$(CONFIG_RISCV_MISALIGNED) += unaligned_access_speed.o -obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) += copy-unaligned.o +obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) += copy-unaligned.o +obj-$(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS) += vec-copy-unaligned.o obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_FPU) += kernel_mode_fpu.o @@ -101,7 +107,7 @@ obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o obj-$(CONFIG_PARAVIRT) += paravirt.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KEXEC_CORE) += kexec_relocate.o crash_save_regs.o machine_kexec.o -obj-$(CONFIG_KEXEC_FILE) += elf_kexec.o machine_kexec_file.o +obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o kexec_image.o machine_kexec_file.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o @@ -117,3 +123,5 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ obj-$(CONFIG_64BIT) += pi/ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o + +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 6e0d333f57e5..3f6d5a6789e8 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -210,7 +210,7 @@ void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size) if (!size) return NULL; - return early_ioremap(phys, size); + return early_memremap(phys, size); } void __init __acpi_unmap_table(void __iomem *map, unsigned long size) @@ -218,7 +218,7 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size) if (!map || !size) return; - early_iounmap(map, size); + early_memunmap(map, size); } void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) @@ -305,7 +305,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) } } - return ioremap_prot(phys, size, pgprot_val(prot)); + return ioremap_prot(phys, size, prot); } #ifdef CONFIG_PCI diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index 0128b161bfda..7eb3cb1215c6 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -18,7 +18,7 @@ #include <asm/sbi.h> #include <asm/csr.h> #include <asm/insn.h> -#include <asm/patch.h> +#include <asm/text-patching.h> struct cpu_manufacturer_info_t { unsigned long vendor_id; diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index e94180ba432f..6e8c0d6feae9 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -4,8 +4,6 @@ * Copyright (C) 2017 SiFive */ -#define GENERATING_ASM_OFFSETS - #include <linux/kbuild.h> #include <linux/mm.h> #include <linux/sched.h> @@ -36,9 +34,9 @@ void asm_offsets(void) OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]); OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]); OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]); + OFFSET(TASK_THREAD_SUM, task_struct, thread.sum); OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); - OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags); OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); @@ -349,6 +347,10 @@ void asm_offsets(void) offsetof(struct task_struct, thread.s[11]) - offsetof(struct task_struct, thread.ra) ); + DEFINE(TASK_THREAD_SUM_RA, + offsetof(struct task_struct, thread.sum) + - offsetof(struct task_struct, thread.ra) + ); DEFINE(TASK_THREAD_F0_F0, offsetof(struct task_struct, thread.fstate.f[0]) @@ -496,21 +498,34 @@ void asm_offsets(void) DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN)); OFFSET(STACKFRAME_FP, stackframe, fp); OFFSET(STACKFRAME_RA, stackframe, ra); +#ifdef CONFIG_FUNCTION_TRACER + DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS - DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct ftrace_regs), STACK_ALIGN)); - DEFINE(FREGS_EPC, offsetof(struct ftrace_regs, epc)); - DEFINE(FREGS_RA, offsetof(struct ftrace_regs, ra)); - DEFINE(FREGS_SP, offsetof(struct ftrace_regs, sp)); - DEFINE(FREGS_S0, offsetof(struct ftrace_regs, s0)); - DEFINE(FREGS_T1, offsetof(struct ftrace_regs, t1)); - DEFINE(FREGS_A0, offsetof(struct ftrace_regs, a0)); - DEFINE(FREGS_A1, offsetof(struct ftrace_regs, a1)); - DEFINE(FREGS_A2, offsetof(struct ftrace_regs, a2)); - DEFINE(FREGS_A3, offsetof(struct ftrace_regs, a3)); - DEFINE(FREGS_A4, offsetof(struct ftrace_regs, a4)); - DEFINE(FREGS_A5, offsetof(struct ftrace_regs, a5)); - DEFINE(FREGS_A6, offsetof(struct ftrace_regs, a6)); - DEFINE(FREGS_A7, offsetof(struct ftrace_regs, a7)); + DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct __arch_ftrace_regs), STACK_ALIGN)); + DEFINE(FREGS_EPC, offsetof(struct __arch_ftrace_regs, epc)); + DEFINE(FREGS_RA, offsetof(struct __arch_ftrace_regs, ra)); + DEFINE(FREGS_SP, offsetof(struct __arch_ftrace_regs, sp)); + DEFINE(FREGS_S0, offsetof(struct __arch_ftrace_regs, s0)); + DEFINE(FREGS_T1, offsetof(struct __arch_ftrace_regs, t1)); +#ifdef CONFIG_CC_IS_CLANG + DEFINE(FREGS_T2, offsetof(struct __arch_ftrace_regs, t2)); + DEFINE(FREGS_T3, offsetof(struct __arch_ftrace_regs, t3)); + DEFINE(FREGS_T4, offsetof(struct __arch_ftrace_regs, t4)); + DEFINE(FREGS_T5, offsetof(struct __arch_ftrace_regs, t5)); + DEFINE(FREGS_T6, offsetof(struct __arch_ftrace_regs, t6)); +#endif + DEFINE(FREGS_A0, offsetof(struct __arch_ftrace_regs, a0)); + DEFINE(FREGS_A1, offsetof(struct __arch_ftrace_regs, a1)); + DEFINE(FREGS_A2, offsetof(struct __arch_ftrace_regs, a2)); + DEFINE(FREGS_A3, offsetof(struct __arch_ftrace_regs, a3)); + DEFINE(FREGS_A4, offsetof(struct __arch_ftrace_regs, a4)); + DEFINE(FREGS_A5, offsetof(struct __arch_ftrace_regs, a5)); + DEFINE(FREGS_A6, offsetof(struct __arch_ftrace_regs, a6)); + DEFINE(FREGS_A7, offsetof(struct __arch_ftrace_regs, a7)); #endif } diff --git a/arch/riscv/kernel/bugs.c b/arch/riscv/kernel/bugs.c new file mode 100644 index 000000000000..3655fe7d678c --- /dev/null +++ b/arch/riscv/kernel/bugs.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Rivos Inc. + */ + +#include <linux/cpu.h> +#include <linux/device.h> +#include <linux/sprintf.h> + +#include <asm/bugs.h> +#include <asm/vendor_extensions/thead.h> + +static enum mitigation_state ghostwrite_state; + +void ghostwrite_set_vulnerable(void) +{ + ghostwrite_state = VULNERABLE; +} + +/* + * Vendor extension alternatives will use the value set at the time of boot + * alternative patching, thus this must be called before boot alternatives are + * patched (and after extension probing) to be effective. + * + * Returns true if mitgated, false otherwise. + */ +bool ghostwrite_enable_mitigation(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR) && + ghostwrite_state == VULNERABLE && !cpu_mitigations_off()) { + disable_xtheadvector(); + ghostwrite_state = MITIGATED; + return true; + } + + return false; +} + +enum mitigation_state ghostwrite_get_state(void) +{ + return ghostwrite_state; +} + +ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) { + switch (ghostwrite_state) { + case UNAFFECTED: + return sprintf(buf, "Not affected\n"); + case MITIGATED: + return sprintf(buf, "Mitigation: xtheadvector disabled\n"); + case VULNERABLE: + fallthrough; + default: + return sprintf(buf, "Vulnerable\n"); + } + } else { + return sprintf(buf, "Not affected\n"); + } +} diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index b320b1d9aa01..26b085dbdd07 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -80,8 +80,7 @@ int populate_cache_leaves(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf = this_cpu_ci->info_list; - struct device_node *np = of_cpu_device_node_get(cpu); - struct device_node *prev = NULL; + struct device_node *np, *prev; int levels = 1, level = 1; if (!acpi_disabled) { @@ -105,11 +104,15 @@ int populate_cache_leaves(unsigned int cpu) return 0; } - if (of_property_read_bool(np, "cache-size")) + np = of_cpu_device_node_get(cpu); + if (!np) + return -ENOENT; + + if (of_property_present(np, "cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level); - if (of_property_read_bool(np, "i-cache-size")) + if (of_property_present(np, "i-cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); - if (of_property_read_bool(np, "d-cache-size")) + if (of_property_present(np, "d-cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); prev = np; @@ -122,11 +125,11 @@ int populate_cache_leaves(unsigned int cpu) break; if (level <= levels) break; - if (of_property_read_bool(np, "cache-size")) + if (of_property_present(np, "cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level); - if (of_property_read_bool(np, "i-cache-size")) + if (of_property_present(np, "i-cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); - if (of_property_read_bool(np, "d-cache-size")) + if (of_property_present(np, "d-cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); levels = level; } diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h index e3d70d35b708..85d4d11450cb 100644 --- a/arch/riscv/kernel/copy-unaligned.h +++ b/arch/riscv/kernel/copy-unaligned.h @@ -10,4 +10,9 @@ void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size); void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size); +#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS +void __riscv_copy_vec_words_unaligned(void *dst, const void *src, size_t size); +void __riscv_copy_vec_bytes_unaligned(void *dst, const void *src, size_t size); +#endif + #endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */ diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c index 28b58fc5ad19..a1e38ecfc8be 100644 --- a/arch/riscv/kernel/cpu-hotplug.c +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -58,7 +58,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) if (cpu_ops->cpu_is_stopped) ret = cpu_ops->cpu_is_stopped(cpu); if (ret) - pr_warn("CPU%d may not have stopped: %d\n", cpu, ret); + pr_warn("CPU%u may not have stopped: %d\n", cpu, ret); } /* diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 3a8eeaa9310c..743d53415572 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -17,17 +17,24 @@ #include <linux/of.h> #include <asm/acpi.h> #include <asm/alternative.h> +#include <asm/bugs.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.h> -#include <asm/patch.h> +#include <asm/text-patching.h> +#include <asm/hwprobe.h> #include <asm/processor.h> #include <asm/sbi.h> #include <asm/vector.h> #include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> #define NUM_ALPHA_EXTS ('z' - 'a' + 1) +static bool any_cpu_has_zicboz; +static bool any_cpu_has_zicbop; +static bool any_cpu_has_zicbom; + unsigned long elf_hwcap __read_mostly; /* Host ISA bitmap */ @@ -36,6 +43,8 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; /* Per-cpu ISA extensions. */ struct riscv_isainfo hart_isa[NR_CPUS]; +u32 thead_vlenb_of; + /** * riscv_isa_extension_base() - Get base extension word * @@ -46,9 +55,7 @@ struct riscv_isainfo hart_isa[NR_CPUS]; */ unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) { - if (!isa_bitmap) - return riscv_isa[0]; - return isa_bitmap[0]; + return !isa_bitmap ? riscv_isa[0] : isa_bitmap[0]; } EXPORT_SYMBOL_GPL(riscv_isa_extension_base); @@ -69,10 +76,19 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned i if (bit >= RISCV_ISA_EXT_MAX) return false; - return test_bit(bit, bmap) ? true : false; + return test_bit(bit, bmap); } EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); +static int riscv_ext_f_depends(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_f)) + return 0; + + return -EPROBE_DEFER; +} + static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data, const unsigned long *isa_bitmap) { @@ -84,6 +100,8 @@ static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data, pr_err("Zicbom disabled as cbom-block-size present, but is not a power-of-2\n"); return -EINVAL; } + + any_cpu_has_zicbom = true; return 0; } @@ -98,6 +116,98 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data, pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n"); return -EINVAL; } + any_cpu_has_zicboz = true; + return 0; +} + +static int riscv_ext_zicbop_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!riscv_cbop_block_size) { + pr_err("Zicbop detected in ISA string, disabling as no cbop-block-size found\n"); + return -EINVAL; + } + if (!is_power_of_2(riscv_cbop_block_size)) { + pr_err("Zicbop disabled as cbop-block-size present, but is not a power-of-2\n"); + return -EINVAL; + } + any_cpu_has_zicbop = true; + return 0; +} + +static int riscv_ext_f_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_FPU)) + return -EINVAL; + + /* + * Due to extension ordering, d is checked before f, so no deferral + * is required. + */ + if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_d)) { + pr_warn_once("This kernel does not support systems with F but not D\n"); + return -EINVAL; + } + + return 0; +} + +static int riscv_ext_d_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_FPU)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_vector_x_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_vector_float_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_FPU)) + return -EINVAL; + + /* + * The kernel doesn't support systems that don't implement both of + * F and D, so if any of the vector extensions that do floating point + * are to be usable, both floating point extensions need to be usable. + * + * Since this function validates vector only, and v/Zve* are probed + * after f/d, there's no need for a deferral here. + */ + if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_d)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_vector_crypto_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + /* + * It isn't the kernel's job to check that the binding is correct, so + * it should be enough to check that any of the vector extensions are + * enabled, which in-turn means that vector is usable in this kernel + */ + if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32X)) + return -EPROBE_DEFER; + return 0; } @@ -132,6 +242,43 @@ static int riscv_ext_zcf_validate(const struct riscv_isa_ext_data *data, return -EPROBE_DEFER; } +static int riscv_vector_f_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32F)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_zvfbfwma_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZFBFMIN) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVFBFMIN)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + /* SVADE has already been detected, use SVADE only */ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_SVADE)) + return -EOPNOTSUPP; + + return 0; +} + +static const unsigned int riscv_a_exts[] = { + RISCV_ISA_EXT_ZAAMO, + RISCV_ISA_EXT_ZALRSC, +}; + static const unsigned int riscv_zk_bundled_exts[] = { RISCV_ISA_EXT_ZBKB, RISCV_ISA_EXT_ZBKC, @@ -303,17 +450,17 @@ static const unsigned int riscv_c_exts[] = { const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i), __RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m), - __RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a), - __RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f), - __RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d), + __RISCV_ISA_EXT_SUPERSET(a, RISCV_ISA_EXT_a, riscv_a_exts), + __RISCV_ISA_EXT_DATA_VALIDATE(f, RISCV_ISA_EXT_f, riscv_ext_f_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(d, RISCV_ISA_EXT_d, riscv_ext_d_validate), __RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q), __RISCV_ISA_EXT_SUPERSET(c, RISCV_ISA_EXT_c, riscv_c_exts), - __RISCV_ISA_EXT_SUPERSET(v, RISCV_ISA_EXT_v, riscv_v_exts), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(v, RISCV_ISA_EXT_v, riscv_v_exts, riscv_ext_vector_float_validate), __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), - __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts, - riscv_ext_zicbom_validate), - __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts, - riscv_ext_zicboz_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts, riscv_ext_zicbom_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zicbop, RISCV_ISA_EXT_ZICBOP, riscv_ext_zicbop_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts, riscv_ext_zicboz_validate), + __RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE), __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), __RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND), __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), @@ -322,9 +469,13 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), __RISCV_ISA_EXT_DATA(zimop, RISCV_ISA_EXT_ZIMOP), + __RISCV_ISA_EXT_DATA(zaamo, RISCV_ISA_EXT_ZAAMO), + __RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA), __RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS), + __RISCV_ISA_EXT_DATA(zalrsc, RISCV_ISA_EXT_ZALRSC), __RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS), __RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA), + __RISCV_ISA_EXT_DATA_VALIDATE(zfbfmin, RISCV_ISA_EXT_ZFBFMIN, riscv_ext_f_depends), __RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH), __RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN), __RISCV_ISA_EXT_DATA(zca, RISCV_ISA_EXT_ZCA), @@ -350,34 +501,41 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED), __RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH), __RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO), - __RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts), - __RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC), - __RISCV_ISA_EXT_SUPERSET(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts), - __RISCV_ISA_EXT_DATA(zve32x, RISCV_ISA_EXT_ZVE32X), - __RISCV_ISA_EXT_SUPERSET(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts), - __RISCV_ISA_EXT_SUPERSET(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts), - __RISCV_ISA_EXT_SUPERSET(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvbc, RISCV_ISA_EXT_ZVBC, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts, riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zve32x, RISCV_ISA_EXT_ZVE32X, riscv_ext_vector_x_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts, riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts, riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts, riscv_ext_vector_x_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfmin, RISCV_ISA_EXT_ZVFBFMIN, riscv_vector_f_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfwma, RISCV_ISA_EXT_ZVFBFWMA, riscv_ext_zvfbfwma_validate), __RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH), __RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN), - __RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB), - __RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG), - __RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts), - __RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts), - __RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED), - __RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts), - __RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA), - __RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB), - __RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts), - __RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts), - __RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED), - __RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH), - __RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts), - __RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkb, RISCV_ISA_EXT_ZVKB, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkg, RISCV_ISA_EXT_ZVKG, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkn, riscv_zvkn_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvknc, riscv_zvknc_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkned, RISCV_ISA_EXT_ZVKNED, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkng, riscv_zvkng_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvknha, RISCV_ISA_EXT_ZVKNHA, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvknhb, RISCV_ISA_EXT_ZVKNHB, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvks, riscv_zvks_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksc, riscv_zvksc_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvksed, RISCV_ISA_EXT_ZVKSED, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvksh, RISCV_ISA_EXT_ZVKSH, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksg, riscv_zvksg_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkt, RISCV_ISA_EXT_ZVKT, riscv_ext_vector_crypto_validate), __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), + __RISCV_ISA_EXT_DATA(smmpm, RISCV_ISA_EXT_SMMPM), + __RISCV_ISA_EXT_SUPERSET(smnpm, RISCV_ISA_EXT_SMNPM, riscv_xlinuxenvcfg_exts), __RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN), __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_SUPERSET(ssnpm, RISCV_ISA_EXT_SSNPM, riscv_xlinuxenvcfg_exts), __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), + __RISCV_ISA_EXT_DATA(svade, RISCV_ISA_EXT_SVADE), + __RISCV_ISA_EXT_DATA_VALIDATE(svadu, RISCV_ISA_EXT_SVADU, riscv_ext_svadu_validate), __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), @@ -454,7 +612,7 @@ static void __init riscv_resolve_isa(unsigned long *source_isa, if (bit < RISCV_ISA_EXT_BASE) *this_hwcap |= isa2hwcap[bit]; } - } while (loop && memcmp(prev_resolved_isa, resolved_isa, sizeof(prev_resolved_isa))); + } while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX)); } static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap) @@ -770,9 +928,50 @@ static void __init riscv_fill_vendor_ext_list(int cpu) } } +static int has_thead_homogeneous_vlenb(void) +{ + int cpu; + u32 prev_vlenb = 0; + u32 vlenb; + + /* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */ + if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return 0; + + for_each_possible_cpu(cpu) { + struct device_node *cpu_node; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + return -ENOENT; + } + + if (of_property_read_u32(cpu_node, "thead,vlenb", &vlenb)) { + of_node_put(cpu_node); + + if (prev_vlenb) + return -ENOENT; + continue; + } + + if (prev_vlenb && vlenb != prev_vlenb) { + of_node_put(cpu_node); + return -ENOENT; + } + + prev_vlenb = vlenb; + of_node_put(cpu_node); + } + + thead_vlenb_of = vlenb; + return 0; +} + static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) { unsigned int cpu; + bool mitigated; for_each_possible_cpu(cpu) { unsigned long this_hwcap = 0; @@ -823,6 +1022,17 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) riscv_fill_vendor_ext_list(cpu); } + /* + * Execute ghostwrite mitigation immediately after detecting extensions + * to disable xtheadvector if necessary. + */ + mitigated = ghostwrite_enable_mitigation(); + + if (!mitigated && has_xtheadvector_no_alternatives() && has_thead_homogeneous_vlenb() < 0) { + pr_warn("Unsupported heterogeneous vlenb detected, vector extension disabled.\n"); + disable_xtheadvector(); + } + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) return -ENOENT; @@ -875,23 +1085,14 @@ void __init riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X)) { + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X) || + has_xtheadvector_no_alternatives()) { /* * This cannot fail when called on the boot hart */ riscv_v_setup_vsize(); } - if (elf_hwcap & COMPAT_HWCAP_ISA_V) { - /* - * ISA string in device tree might have 'v' flag, but - * CONFIG_RISCV_ISA_V is disabled in kernel. - * Clear V flag in elf_hwcap if CONFIG_RISCV_ISA_V is disabled. - */ - if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) - elf_hwcap &= ~COMPAT_HWCAP_ISA_V; - } - memset(print_str, 0, sizeof(print_str)); for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++) if (riscv_isa[0] & BIT_MASK(i)) @@ -917,10 +1118,21 @@ unsigned long riscv_get_elf_hwcap(void) return hwcap; } -void riscv_user_isa_enable(void) +void __init riscv_user_isa_enable(void) { - if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) - csr_set(CSR_ENVCFG, ENVCFG_CBZE); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ)) + current->thread.envcfg |= ENVCFG_CBZE; + else if (any_cpu_has_zicboz) + pr_warn("Zicboz disabled as it is unavailable on some harts\n"); + + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOM)) + current->thread.envcfg |= ENVCFG_CBCFE; + else if (any_cpu_has_zicbom) + pr_warn("Zicbom disabled as it is unavailable on some harts\n"); + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOP) && + any_cpu_has_zicbop) + pr_warn("Zicbop disabled as it is unavailable on some harts\n"); } #ifdef CONFIG_RISCV_ALTERNATIVE diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S index 515b2dfbca75..2efc3aaf4a8c 100644 --- a/arch/riscv/kernel/efi-header.S +++ b/arch/riscv/kernel/efi-header.S @@ -9,7 +9,7 @@ #include <asm/set_memory.h> .macro __EFI_PE_HEADER - .long PE_MAGIC + .long IMAGE_NT_SIGNATURE coff_header: #ifdef CONFIG_64BIT .short IMAGE_FILE_MACHINE_RISCV64 // Machine @@ -27,9 +27,9 @@ coff_header: optional_header: #ifdef CONFIG_64BIT - .short PE_OPT_MAGIC_PE32PLUS // PE32+ format + .short IMAGE_NT_OPTIONAL_HDR64_MAGIC // PE32+ format #else - .short PE_OPT_MAGIC_PE32 // PE32 format + .short IMAGE_NT_OPTIONAL_HDR32_MAGIC // PE32 format #endif .byte 0x02 // MajorLinkerVersion .byte 0x14 // MinorLinkerVersion @@ -64,7 +64,7 @@ extra_header_fields: .long efi_header_end - _start // SizeOfHeaders .long 0 // CheckSum .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem - .short 0 // DllCharacteristics + .short IMAGE_DLLCHARACTERISTICS_NX_COMPAT // DllCharacteristics .quad 0 // SizeOfStackReserve .quad 0 // SizeOfStackCommit .quad 0 // SizeOfHeapReserve diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c deleted file mode 100644 index 3c37661801f9..000000000000 --- a/arch/riscv/kernel/elf_kexec.c +++ /dev/null @@ -1,482 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Load ELF vmlinux file for the kexec_file_load syscall. - * - * Copyright (C) 2021 Huawei Technologies Co, Ltd. - * - * Author: Liao Chang (liaochang1@huawei.com) - * - * Based on kexec-tools' kexec-elf-riscv.c, heavily modified - * for kernel. - */ - -#define pr_fmt(fmt) "kexec_image: " fmt - -#include <linux/elf.h> -#include <linux/kexec.h> -#include <linux/slab.h> -#include <linux/of.h> -#include <linux/libfdt.h> -#include <linux/types.h> -#include <linux/memblock.h> -#include <linux/vmalloc.h> -#include <asm/setup.h> - -int arch_kimage_file_post_load_cleanup(struct kimage *image) -{ - kvfree(image->arch.fdt); - image->arch.fdt = NULL; - - vfree(image->elf_headers); - image->elf_headers = NULL; - image->elf_headers_sz = 0; - - return kexec_image_post_load_cleanup_default(image); -} - -static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr, - struct kexec_elf_info *elf_info, unsigned long old_pbase, - unsigned long new_pbase) -{ - int i; - int ret = 0; - size_t size; - struct kexec_buf kbuf; - const struct elf_phdr *phdr; - - kbuf.image = image; - - for (i = 0; i < ehdr->e_phnum; i++) { - phdr = &elf_info->proghdrs[i]; - if (phdr->p_type != PT_LOAD) - continue; - - size = phdr->p_filesz; - if (size > phdr->p_memsz) - size = phdr->p_memsz; - - kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; - kbuf.bufsz = size; - kbuf.buf_align = phdr->p_align; - kbuf.mem = phdr->p_paddr - old_pbase + new_pbase; - kbuf.memsz = phdr->p_memsz; - kbuf.top_down = false; - ret = kexec_add_buffer(&kbuf); - if (ret) - break; - } - - return ret; -} - -/* - * Go through the available phsyical memory regions and find one that hold - * an image of the specified size. - */ -static int elf_find_pbase(struct kimage *image, unsigned long kernel_len, - struct elfhdr *ehdr, struct kexec_elf_info *elf_info, - unsigned long *old_pbase, unsigned long *new_pbase) -{ - int i; - int ret; - struct kexec_buf kbuf; - const struct elf_phdr *phdr; - unsigned long lowest_paddr = ULONG_MAX; - unsigned long lowest_vaddr = ULONG_MAX; - - for (i = 0; i < ehdr->e_phnum; i++) { - phdr = &elf_info->proghdrs[i]; - if (phdr->p_type != PT_LOAD) - continue; - - if (lowest_paddr > phdr->p_paddr) - lowest_paddr = phdr->p_paddr; - - if (lowest_vaddr > phdr->p_vaddr) - lowest_vaddr = phdr->p_vaddr; - } - - kbuf.image = image; - kbuf.buf_min = lowest_paddr; - kbuf.buf_max = ULONG_MAX; - - /* - * Current riscv boot protocol requires 2MB alignment for - * RV64 and 4MB alignment for RV32 - * - */ - kbuf.buf_align = PMD_SIZE; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE); - kbuf.top_down = false; - ret = arch_kexec_locate_mem_hole(&kbuf); - if (!ret) { - *old_pbase = lowest_paddr; - *new_pbase = kbuf.mem; - image->start = ehdr->e_entry - lowest_vaddr + kbuf.mem; - } - return ret; -} - -#ifdef CONFIG_CRASH_DUMP -static int get_nr_ram_ranges_callback(struct resource *res, void *arg) -{ - unsigned int *nr_ranges = arg; - - (*nr_ranges)++; - return 0; -} - -static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) -{ - struct crash_mem *cmem = arg; - - cmem->ranges[cmem->nr_ranges].start = res->start; - cmem->ranges[cmem->nr_ranges].end = res->end; - cmem->nr_ranges++; - - return 0; -} - -static int prepare_elf_headers(void **addr, unsigned long *sz) -{ - struct crash_mem *cmem; - unsigned int nr_ranges; - int ret; - - nr_ranges = 1; /* For exclusion of crashkernel region */ - walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); - - cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); - if (!cmem) - return -ENOMEM; - - cmem->max_nr_ranges = nr_ranges; - cmem->nr_ranges = 0; - ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); - if (ret) - goto out; - - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); - if (!ret) - ret = crash_prepare_elf64_headers(cmem, true, addr, sz); - -out: - kfree(cmem); - return ret; -} - -static char *setup_kdump_cmdline(struct kimage *image, char *cmdline, - unsigned long cmdline_len) -{ - int elfcorehdr_strlen; - char *cmdline_ptr; - - cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); - if (!cmdline_ptr) - return NULL; - - elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", - image->elf_load_addr); - - if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) { - pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n"); - kfree(cmdline_ptr); - return NULL; - } - - memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len); - /* Ensure it's nul terminated */ - cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0'; - return cmdline_ptr; -} -#endif - -static void *elf_kexec_load(struct kimage *image, char *kernel_buf, - unsigned long kernel_len, char *initrd, - unsigned long initrd_len, char *cmdline, - unsigned long cmdline_len) -{ - int ret; - void *fdt; - unsigned long old_kernel_pbase = ULONG_MAX; - unsigned long new_kernel_pbase = 0UL; - unsigned long initrd_pbase = 0UL; - unsigned long kernel_start; - struct elfhdr ehdr; - struct kexec_buf kbuf; - struct kexec_elf_info elf_info; - char *modified_cmdline = NULL; - - ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info); - if (ret) - return ERR_PTR(ret); - - ret = elf_find_pbase(image, kernel_len, &ehdr, &elf_info, - &old_kernel_pbase, &new_kernel_pbase); - if (ret) - goto out; - kernel_start = image->start; - - /* Add the kernel binary to the image */ - ret = riscv_kexec_elf_load(image, &ehdr, &elf_info, - old_kernel_pbase, new_kernel_pbase); - if (ret) - goto out; - - kbuf.image = image; - kbuf.buf_min = new_kernel_pbase + kernel_len; - kbuf.buf_max = ULONG_MAX; - -#ifdef CONFIG_CRASH_DUMP - /* Add elfcorehdr */ - if (image->type == KEXEC_TYPE_CRASH) { - void *headers; - unsigned long headers_sz; - ret = prepare_elf_headers(&headers, &headers_sz); - if (ret) { - pr_err("Preparing elf core header failed\n"); - goto out; - } - - kbuf.buffer = headers; - kbuf.bufsz = headers_sz; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - kbuf.memsz = headers_sz; - kbuf.buf_align = ELF_CORE_HEADER_ALIGN; - kbuf.top_down = true; - - ret = kexec_add_buffer(&kbuf); - if (ret) { - vfree(headers); - goto out; - } - image->elf_headers = headers; - image->elf_load_addr = kbuf.mem; - image->elf_headers_sz = headers_sz; - - kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf.bufsz, kbuf.memsz); - - /* Setup cmdline for kdump kernel case */ - modified_cmdline = setup_kdump_cmdline(image, cmdline, - cmdline_len); - if (!modified_cmdline) { - pr_err("Setting up cmdline for kdump kernel failed\n"); - ret = -EINVAL; - goto out; - } - cmdline = modified_cmdline; - } -#endif - -#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY - /* Add purgatory to the image */ - kbuf.top_down = true; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - ret = kexec_load_purgatory(image, &kbuf); - if (ret) { - pr_err("Error loading purgatory ret=%d\n", ret); - goto out; - } - kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem); - - ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry", - &kernel_start, - sizeof(kernel_start), 0); - if (ret) - pr_err("Error update purgatory ret=%d\n", ret); -#endif /* CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY */ - - /* Add the initrd to the image */ - if (initrd != NULL) { - kbuf.buffer = initrd; - kbuf.bufsz = kbuf.memsz = initrd_len; - kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = true; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - ret = kexec_add_buffer(&kbuf); - if (ret) - goto out; - initrd_pbase = kbuf.mem; - kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_pbase); - } - - /* Add the DTB to the image */ - fdt = of_kexec_alloc_and_setup_fdt(image, initrd_pbase, - initrd_len, cmdline, 0); - if (!fdt) { - pr_err("Error setting up the new device tree.\n"); - ret = -EINVAL; - goto out; - } - - fdt_pack(fdt); - kbuf.buffer = fdt; - kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); - kbuf.buf_align = PAGE_SIZE; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - kbuf.top_down = true; - ret = kexec_add_buffer(&kbuf); - if (ret) { - pr_err("Error add DTB kbuf ret=%d\n", ret); - goto out_free_fdt; - } - /* Cache the fdt buffer address for memory cleanup */ - image->arch.fdt = fdt; - kexec_dprintk("Loaded device tree at 0x%lx\n", kbuf.mem); - goto out; - -out_free_fdt: - kvfree(fdt); -out: - kfree(modified_cmdline); - kexec_free_elf_info(&elf_info); - return ret ? ERR_PTR(ret) : NULL; -} - -#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) -#define RISCV_IMM_BITS 12 -#define RISCV_IMM_REACH (1LL << RISCV_IMM_BITS) -#define RISCV_CONST_HIGH_PART(x) \ - (((x) + (RISCV_IMM_REACH >> 1)) & ~(RISCV_IMM_REACH - 1)) -#define RISCV_CONST_LOW_PART(x) ((x) - RISCV_CONST_HIGH_PART(x)) - -#define ENCODE_ITYPE_IMM(x) \ - (RV_X(x, 0, 12) << 20) -#define ENCODE_BTYPE_IMM(x) \ - ((RV_X(x, 1, 4) << 8) | (RV_X(x, 5, 6) << 25) | \ - (RV_X(x, 11, 1) << 7) | (RV_X(x, 12, 1) << 31)) -#define ENCODE_UTYPE_IMM(x) \ - (RV_X(x, 12, 20) << 12) -#define ENCODE_JTYPE_IMM(x) \ - ((RV_X(x, 1, 10) << 21) | (RV_X(x, 11, 1) << 20) | \ - (RV_X(x, 12, 8) << 12) | (RV_X(x, 20, 1) << 31)) -#define ENCODE_CBTYPE_IMM(x) \ - ((RV_X(x, 1, 2) << 3) | (RV_X(x, 3, 2) << 10) | (RV_X(x, 5, 1) << 2) | \ - (RV_X(x, 6, 2) << 5) | (RV_X(x, 8, 1) << 12)) -#define ENCODE_CJTYPE_IMM(x) \ - ((RV_X(x, 1, 3) << 3) | (RV_X(x, 4, 1) << 11) | (RV_X(x, 5, 1) << 2) | \ - (RV_X(x, 6, 1) << 7) | (RV_X(x, 7, 1) << 6) | (RV_X(x, 8, 2) << 9) | \ - (RV_X(x, 10, 1) << 8) | (RV_X(x, 11, 1) << 12)) -#define ENCODE_UJTYPE_IMM(x) \ - (ENCODE_UTYPE_IMM(RISCV_CONST_HIGH_PART(x)) | \ - (ENCODE_ITYPE_IMM(RISCV_CONST_LOW_PART(x)) << 32)) -#define ENCODE_UITYPE_IMM(x) \ - (ENCODE_UTYPE_IMM(x) | (ENCODE_ITYPE_IMM(x) << 32)) - -#define CLEAN_IMM(type, x) \ - ((~ENCODE_##type##_IMM((uint64_t)(-1))) & (x)) - -int arch_kexec_apply_relocations_add(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab) -{ - const char *strtab, *name, *shstrtab; - const Elf_Shdr *sechdrs; - Elf64_Rela *relas; - int i, r_type; - - /* String & section header string table */ - sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; - strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset; - shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; - - relas = (void *)pi->ehdr + relsec->sh_offset; - - for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) { - const Elf_Sym *sym; /* symbol to relocate */ - unsigned long addr; /* final location after relocation */ - unsigned long val; /* relocated symbol value */ - unsigned long sec_base; /* relocated symbol value */ - void *loc; /* tmp location to modify */ - - sym = (void *)pi->ehdr + symtab->sh_offset; - sym += ELF64_R_SYM(relas[i].r_info); - - if (sym->st_name) - name = strtab + sym->st_name; - else - name = shstrtab + sechdrs[sym->st_shndx].sh_name; - - loc = pi->purgatory_buf; - loc += section->sh_offset; - loc += relas[i].r_offset; - - if (sym->st_shndx == SHN_ABS) - sec_base = 0; - else if (sym->st_shndx >= pi->ehdr->e_shnum) { - pr_err("Invalid section %d for symbol %s\n", - sym->st_shndx, name); - return -ENOEXEC; - } else - sec_base = pi->sechdrs[sym->st_shndx].sh_addr; - - val = sym->st_value; - val += sec_base; - val += relas[i].r_addend; - - addr = section->sh_addr + relas[i].r_offset; - - r_type = ELF64_R_TYPE(relas[i].r_info); - - switch (r_type) { - case R_RISCV_BRANCH: - *(u32 *)loc = CLEAN_IMM(BTYPE, *(u32 *)loc) | - ENCODE_BTYPE_IMM(val - addr); - break; - case R_RISCV_JAL: - *(u32 *)loc = CLEAN_IMM(JTYPE, *(u32 *)loc) | - ENCODE_JTYPE_IMM(val - addr); - break; - /* - * With no R_RISCV_PCREL_LO12_S, R_RISCV_PCREL_LO12_I - * sym is expected to be next to R_RISCV_PCREL_HI20 - * in purgatory relsec. Handle it like R_RISCV_CALL - * sym, instead of searching the whole relsec. - */ - case R_RISCV_PCREL_HI20: - case R_RISCV_CALL_PLT: - case R_RISCV_CALL: - *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | - ENCODE_UJTYPE_IMM(val - addr); - break; - case R_RISCV_RVC_BRANCH: - *(u32 *)loc = CLEAN_IMM(CBTYPE, *(u32 *)loc) | - ENCODE_CBTYPE_IMM(val - addr); - break; - case R_RISCV_RVC_JUMP: - *(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) | - ENCODE_CJTYPE_IMM(val - addr); - break; - case R_RISCV_ADD16: - *(u16 *)loc += val; - break; - case R_RISCV_SUB16: - *(u16 *)loc -= val; - break; - case R_RISCV_ADD32: - *(u32 *)loc += val; - break; - case R_RISCV_SUB32: - *(u32 *)loc -= val; - break; - /* It has been applied by R_RISCV_PCREL_HI20 sym */ - case R_RISCV_PCREL_LO12_I: - case R_RISCV_ALIGN: - case R_RISCV_RELAX: - break; - default: - pr_err("Unknown rela relocation: %d\n", r_type); - return -ENOEXEC; - } - } - return 0; -} - -const struct kexec_file_ops elf_kexec_ops = { - .probe = kexec_elf_probe, - .load = elf_kexec_load, -}; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c200d329d4bd..75656afa2d6b 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -23,21 +23,21 @@ REG_S a0, TASK_TI_A0(tp) csrr a0, CSR_CAUSE /* Exclude IRQs */ - blt a0, zero, _new_vmalloc_restore_context_a0 + blt a0, zero, .Lnew_vmalloc_restore_context_a0 REG_S a1, TASK_TI_A1(tp) /* Only check new_vmalloc if we are in page/protection fault */ li a1, EXC_LOAD_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_STORE_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_INST_PAGE_FAULT - bne a0, a1, _new_vmalloc_restore_context_a1 + bne a0, a1, .Lnew_vmalloc_restore_context_a1 -_new_vmalloc_kernel_address: +.Lnew_vmalloc_kernel_address: /* Is it a kernel address? */ csrr a0, CSR_TVAL - bge a0, zero, _new_vmalloc_restore_context_a1 + bge a0, zero, .Lnew_vmalloc_restore_context_a1 /* Check if a new vmalloc mapping appeared that could explain the trap */ REG_S a2, TASK_TI_A2(tp) @@ -69,7 +69,7 @@ _new_vmalloc_kernel_address: /* Check the value of new_vmalloc for this cpu */ REG_L a2, 0(a0) and a2, a2, a1 - beq a2, zero, _new_vmalloc_restore_context + beq a2, zero, .Lnew_vmalloc_restore_context /* Atomically reset the current cpu bit in new_vmalloc */ amoxor.d a0, a1, (a0) @@ -83,11 +83,11 @@ _new_vmalloc_kernel_address: csrw CSR_SCRATCH, x0 sret -_new_vmalloc_restore_context: +.Lnew_vmalloc_restore_context: REG_L a2, TASK_TI_A2(tp) -_new_vmalloc_restore_context_a1: +.Lnew_vmalloc_restore_context_a1: REG_L a1, TASK_TI_A1(tp) -_new_vmalloc_restore_context_a0: +.Lnew_vmalloc_restore_context_a0: REG_L a0, TASK_TI_A0(tp) .endm @@ -278,6 +278,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #else sret #endif +SYM_INNER_LABEL(ret_from_exception_end, SYM_L_GLOBAL) SYM_CODE_END(ret_from_exception) ASM_NOKPROBE(ret_from_exception) @@ -318,17 +319,21 @@ SYM_CODE_END(handle_kernel_stack_overflow) ASM_NOKPROBE(handle_kernel_stack_overflow) #endif -SYM_CODE_START(ret_from_fork) +SYM_CODE_START(ret_from_fork_kernel_asm) + call schedule_tail + move a0, s1 /* fn_arg */ + move a1, s0 /* fn */ + move a2, sp /* pt_regs */ + call ret_from_fork_kernel + j ret_from_exception +SYM_CODE_END(ret_from_fork_kernel_asm) + +SYM_CODE_START(ret_from_fork_user_asm) call schedule_tail - beqz s0, 1f /* not from kernel thread */ - /* Call fn(arg) */ - move a0, s1 - jalr s0 -1: move a0, sp /* pt_regs */ - call syscall_exit_to_user_mode + call ret_from_fork_user j ret_from_exception -SYM_CODE_END(ret_from_fork) +SYM_CODE_END(ret_from_fork_user_asm) #ifdef CONFIG_IRQ_STACKS /* @@ -396,9 +401,18 @@ SYM_FUNC_START(__switch_to) REG_S s9, TASK_THREAD_S9_RA(a3) REG_S s10, TASK_THREAD_S10_RA(a3) REG_S s11, TASK_THREAD_S11_RA(a3) + + /* save the user space access flag */ + csrr s0, CSR_STATUS + REG_S s0, TASK_THREAD_SUM_RA(a3) + /* Save the kernel shadow call stack pointer */ scs_save_current /* Restore context from next->thread */ + REG_L s0, TASK_THREAD_SUM_RA(a4) + li s1, SR_SUM + and s0, s0, s1 + csrs CSR_STATUS, s0 REG_L ra, TASK_THREAD_RA_RA(a4) REG_L sp, TASK_THREAD_SP_RA(a4) REG_L s0, TASK_THREAD_S0_RA(a4) diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S index 327cf527dd7e..f74f6b60e347 100644 --- a/arch/riscv/kernel/fpu.S +++ b/arch/riscv/kernel/fpu.S @@ -170,7 +170,7 @@ SYM_FUNC_END(__fstate_restore) __access_func(f31) -#ifdef CONFIG_RISCV_MISALIGNED +#ifdef CONFIG_RISCV_SCALAR_MISALIGNED /* * Disable compressed instructions set to keep a constant offset between FP @@ -224,4 +224,4 @@ SYM_FUNC_START(get_f64_reg) fp_access_epilogue SYM_FUNC_END(get_f64_reg) -#endif /* CONFIG_RISCV_MISALIGNED */ +#endif /* CONFIG_RISCV_SCALAR_MISALIGNED */ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 4b95c574fd04..4c6c24380cfd 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -8,98 +8,129 @@ #include <linux/ftrace.h> #include <linux/uaccess.h> #include <linux/memory.h> +#include <linux/irqflags.h> #include <linux/stop_machine.h> #include <asm/cacheflush.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE -void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) +unsigned long ftrace_call_adjust(unsigned long addr) { - mutex_lock(&text_mutex); + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return addr + 8 + MCOUNT_AUIPC_SIZE; - /* - * The code sequences we use for ftrace can't be patched while the - * kernel is running, so we need to use stop_machine() to modify them - * for now. This doesn't play nice with text_mutex, we use this flag - * to elide the check. - */ - riscv_patch_in_stop_machine = true; + return addr + MCOUNT_AUIPC_SIZE; } -void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) { - riscv_patch_in_stop_machine = false; + return fentry_ip - MCOUNT_AUIPC_SIZE; +} + +void arch_ftrace_update_code(int command) +{ + mutex_lock(&text_mutex); + command |= FTRACE_MAY_SLEEP; + ftrace_modify_all_code(command); mutex_unlock(&text_mutex); + flush_icache_all(); } -static int ftrace_check_current_call(unsigned long hook_pos, - unsigned int *expected) +static int __ftrace_modify_call(unsigned long source, unsigned long target, bool validate) { + unsigned int call[2], offset; unsigned int replaced[2]; - unsigned int nops[2] = {NOP4, NOP4}; - - /* we expect nops at the hook position */ - if (!expected) - expected = nops; - /* - * Read the text we want to modify; - * return must be -EFAULT on read error - */ - if (copy_from_kernel_nofault(replaced, (void *)hook_pos, - MCOUNT_INSN_SIZE)) - return -EFAULT; + offset = target - source; + call[1] = to_jalr_t0(offset); - /* - * Make sure it is what we expect it to be; - * return must be -EINVAL on failed comparison - */ - if (memcmp(expected, replaced, sizeof(replaced))) { - pr_err("%p: expected (%08x %08x) but got (%08x %08x)\n", - (void *)hook_pos, expected[0], expected[1], replaced[0], - replaced[1]); - return -EINVAL; + if (validate) { + call[0] = to_auipc_t0(offset); + /* + * Read the text we want to modify; + * return must be -EFAULT on read error + */ + if (copy_from_kernel_nofault(replaced, (void *)source, 2 * MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (replaced[0] != call[0]) { + pr_err("%p: expected (%08x) but got (%08x)\n", + (void *)source, call[0], replaced[0]); + return -EINVAL; + } } + /* Replace the jalr at once. Return -EPERM on write error. */ + if (patch_insn_write((void *)(source + MCOUNT_AUIPC_SIZE), call + 1, MCOUNT_JALR_SIZE)) + return -EPERM; + return 0; } -static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target, - bool enable, bool ra) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +static const struct ftrace_ops *riscv64_rec_get_ops(struct dyn_ftrace *rec) { - unsigned int call[2]; - unsigned int nops[2] = {NOP4, NOP4}; + const struct ftrace_ops *ops = NULL; - if (ra) - make_call_ra(hook_pos, target, call); - else - make_call_t0(hook_pos, target, call); + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + WARN_ON_ONCE(!ops); + } - /* Replace the auipc-jalr pair at once. Return -EPERM on write error. */ - if (patch_insn_write((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE)) - return -EPERM; + if (!ops) + ops = &ftrace_list_ops; - return 0; + return ops; +} + +static int ftrace_rec_set_ops(const struct dyn_ftrace *rec, const struct ftrace_ops *ops) +{ + unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8); + + return patch_text_nosync((void *)literal, &ops, sizeof(ops)); +} + +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, &ftrace_nop_ops); } +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, riscv64_rec_get_ops(rec)); +} +#else +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; } +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; } +#endif + int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned int call[2]; + unsigned long distance, orig_addr, pc = rec->ip - MCOUNT_AUIPC_SIZE; + int ret; - make_call_t0(rec->ip, addr, call); + ret = ftrace_rec_update_ops(rec); + if (ret) + return ret; - if (patch_insn_write((void *)rec->ip, call, MCOUNT_INSN_SIZE)) - return -EPERM; + orig_addr = (unsigned long)&ftrace_caller; + distance = addr > orig_addr ? addr - orig_addr : orig_addr - addr; + if (distance > JALR_RANGE) + addr = FTRACE_ADDR; - return 0; + return __ftrace_modify_call(pc, addr, false); } -int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, - unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int nops[2] = {NOP4, NOP4}; + u32 nop4 = RISCV_INSN_NOP4; + int ret; - if (patch_insn_write((void *)rec->ip, nops, MCOUNT_INSN_SIZE)) + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; + + if (patch_insn_write((void *)rec->ip, &nop4, MCOUNT_NOP4_SIZE)) return -EPERM; return 0; @@ -114,75 +145,71 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, */ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { - int out; + unsigned long pc = rec->ip - MCOUNT_AUIPC_SIZE; + unsigned int nops[2], offset; + int ret; - mutex_lock(&text_mutex); - out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); - mutex_unlock(&text_mutex); + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; - return out; -} + offset = (unsigned long) &ftrace_caller - pc; + nops[0] = to_auipc_t0(offset); + nops[1] = RISCV_INSN_NOP4; -int ftrace_update_ftrace_func(ftrace_func_t func) -{ - int ret = __ftrace_modify_call((unsigned long)&ftrace_call, - (unsigned long)func, true, true); + mutex_lock(&text_mutex); + ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE); + mutex_unlock(&text_mutex); return ret; } -struct ftrace_modify_param { - int command; - atomic_t cpu_count; -}; - -static int __ftrace_modify_code(void *data) +ftrace_func_t ftrace_call_dest = ftrace_stub; +int ftrace_update_ftrace_func(ftrace_func_t func) { - struct ftrace_modify_param *param = data; - - if (atomic_inc_return(¶m->cpu_count) == num_online_cpus()) { - ftrace_modify_all_code(param->command); - /* - * Make sure the patching store is effective *before* we - * increment the counter which releases all waiting CPUs - * by using the release variant of atomic increment. The - * release pairs with the call to local_flush_icache_all() - * on the waiting CPU. - */ - atomic_inc_return_release(¶m->cpu_count); - } else { - while (atomic_read(¶m->cpu_count) <= num_online_cpus()) - cpu_relax(); - - local_flush_icache_all(); - } + /* + * When using CALL_OPS, the function to call is associated with the + * call site, and we don't have a global function pointer to update. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return 0; + WRITE_ONCE(ftrace_call_dest, func); + /* + * The data fence ensure that the update to ftrace_call_dest happens + * before the write to function_trace_op later in the generic ftrace. + * If the sequence is not enforced, then an old ftrace_call_dest may + * race loading a new function_trace_op set in ftrace_modify_all_code + */ + smp_wmb(); + /* + * Updating ftrace dpes not take stop_machine path, so irqs should not + * be disabled. + */ + WARN_ON(irqs_disabled()); + smp_call_function(ftrace_sync_ipi, NULL, 1); return 0; } -void arch_ftrace_update_code(int command) +#else /* CONFIG_DYNAMIC_FTRACE */ +unsigned long ftrace_call_adjust(unsigned long addr) { - struct ftrace_modify_param param = { command, ATOMIC_INIT(0) }; - - stop_machine(__ftrace_modify_code, ¶m, cpu_online_mask); + return addr; } -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { - unsigned int call[2]; - unsigned long caller = rec->ip; + unsigned long caller = rec->ip - MCOUNT_AUIPC_SIZE; int ret; - make_call_t0(caller, old_addr, call); - ret = ftrace_check_current_call(caller, call); - + ret = ftrace_rec_update_ops(rec); if (ret) return ret; - return __ftrace_modify_call(caller, addr, true, false); + return __ftrace_modify_call(caller, FTRACE_ADDR, true); } #endif @@ -210,25 +237,25 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } #ifdef CONFIG_DYNAMIC_FTRACE -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(&fregs->ra, ip, fregs->s0); -} -#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ -extern void ftrace_graph_call(void); -int ftrace_enable_ftrace_graph_caller(void) -{ - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, - (unsigned long)&prepare_ftrace_return, true, true); -} + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0; + unsigned long *parent = &arch_ftrace_regs(fregs)->ra; + unsigned long old; -int ftrace_disable_ftrace_graph_caller(void) -{ - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, - (unsigned long)&prepare_ftrace_return, false, true); + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs)) + *parent = return_hooker; } -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 356d5397b2a2..bdf3352acf4c 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -131,6 +131,12 @@ secondary_start_sbi: csrw CSR_IE, zero csrw CSR_IP, zero +#ifndef CONFIG_RISCV_M_MODE + /* Enable time CSR */ + li t0, 0x2 + csrw CSR_SCOUNTEREN, t0 +#endif + /* Load the global pointer */ load_global_pointer @@ -226,6 +232,10 @@ SYM_CODE_START(_start_kernel) * to hand it to us. */ csrr a0, CSR_MHARTID +#else + /* Enable time CSR */ + li t0, 0x2 + csrw CSR_SCOUNTEREN, t0 #endif /* CONFIG_RISCV_M_MODE */ /* Load the global pointer */ diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c index 11ad789c60c6..b4c1a6a3fbd2 100644 --- a/arch/riscv/kernel/jump_label.c +++ b/arch/riscv/kernel/jump_label.c @@ -10,9 +10,9 @@ #include <linux/mutex.h> #include <asm/bug.h> #include <asm/cacheflush.h> -#include <asm/patch.h> +#include <asm/text-patching.h> +#include <asm/insn-def.h> -#define RISCV_INSN_NOP 0x00000013U #define RISCV_INSN_JAL 0x0000006fU bool arch_jump_label_transform_queue(struct jump_entry *entry, @@ -33,12 +33,18 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, (((u32)offset & GENMASK(10, 1)) << (21 - 1)) | (((u32)offset & GENMASK(20, 20)) << (31 - 20)); } else { - insn = RISCV_INSN_NOP; + insn = RISCV_INSN_NOP4; } - mutex_lock(&text_mutex); - patch_insn_write(addr, &insn, sizeof(insn)); - mutex_unlock(&text_mutex); + if (early_boot_irqs_disabled) { + riscv_patch_in_stop_machine = 1; + patch_insn_write(addr, &insn, sizeof(insn)); + riscv_patch_in_stop_machine = 0; + } else { + mutex_lock(&text_mutex); + patch_insn_write(addr, &insn, sizeof(insn)); + mutex_unlock(&text_mutex); + } return true; } diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c index 6afe80c7f03a..99972a48e86b 100644 --- a/arch/riscv/kernel/kernel_mode_vector.c +++ b/arch/riscv/kernel/kernel_mode_vector.c @@ -143,7 +143,7 @@ static int riscv_v_start_kernel_context(bool *is_nested) /* Transfer the ownership of V from user to kernel, then save */ riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY); - if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(task_pt_regs(current)->status, DIRTY)) { uvstate = ¤t->thread.vstate; __riscv_v_vstate_save(uvstate, uvstate->datap); } @@ -160,7 +160,7 @@ asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs) return; depth = riscv_v_ctx_get_depth(); - if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY) + if (depth == 0 && __riscv_v_vstate_check(regs->status, DIRTY)) riscv_preempt_v_set_dirty(); riscv_v_ctx_depth_inc(); @@ -208,7 +208,7 @@ void kernel_vector_begin(void) { bool nested = false; - if (WARN_ON(!has_vector())) + if (WARN_ON(!(has_vector() || has_xtheadvector()))) return; BUG_ON(!may_use_simd()); @@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(kernel_vector_begin); */ void kernel_vector_end(void) { - if (WARN_ON(!has_vector())) + if (WARN_ON(!(has_vector() || has_xtheadvector()))) return; riscv_v_disable(); diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c new file mode 100644 index 000000000000..f4755d49b89e --- /dev/null +++ b/arch/riscv/kernel/kexec_elf.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Copyright (C) 2021 Huawei Technologies Co, Ltd. + * + * Author: Liao Chang (liaochang1@huawei.com) + * + * Based on kexec-tools' kexec-elf-riscv.c, heavily modified + * for kernel. + */ + +#define pr_fmt(fmt) "kexec_image: " fmt + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/slab.h> +#include <linux/of.h> +#include <linux/libfdt.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <asm/setup.h> + +static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr, + struct kexec_elf_info *elf_info, unsigned long old_pbase, + unsigned long new_pbase) +{ + int i; + int ret = 0; + size_t size; + struct kexec_buf kbuf; + const struct elf_phdr *phdr; + + kbuf.image = image; + + for (i = 0; i < ehdr->e_phnum; i++) { + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + size = phdr->p_filesz; + if (size > phdr->p_memsz) + size = phdr->p_memsz; + + kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; + kbuf.bufsz = size; + kbuf.buf_align = phdr->p_align; + kbuf.mem = phdr->p_paddr - old_pbase + new_pbase; + kbuf.memsz = phdr->p_memsz; + kbuf.top_down = false; + ret = kexec_add_buffer(&kbuf); + if (ret) + break; + } + + return ret; +} + +/* + * Go through the available phsyical memory regions and find one that hold + * an image of the specified size. + */ +static int elf_find_pbase(struct kimage *image, unsigned long kernel_len, + struct elfhdr *ehdr, struct kexec_elf_info *elf_info, + unsigned long *old_pbase, unsigned long *new_pbase) +{ + int i; + int ret; + struct kexec_buf kbuf; + const struct elf_phdr *phdr; + unsigned long lowest_paddr = ULONG_MAX; + unsigned long lowest_vaddr = ULONG_MAX; + + for (i = 0; i < ehdr->e_phnum; i++) { + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + if (lowest_paddr > phdr->p_paddr) + lowest_paddr = phdr->p_paddr; + + if (lowest_vaddr > phdr->p_vaddr) + lowest_vaddr = phdr->p_vaddr; + } + + kbuf.image = image; + kbuf.buf_min = lowest_paddr; + kbuf.buf_max = ULONG_MAX; + + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 + * + */ + kbuf.buf_align = PMD_SIZE; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE); + kbuf.top_down = false; + ret = arch_kexec_locate_mem_hole(&kbuf); + if (!ret) { + *old_pbase = lowest_paddr; + *new_pbase = kbuf.mem; + image->start = ehdr->e_entry - lowest_vaddr + kbuf.mem; + } + return ret; +} + +static void *elf_kexec_load(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + unsigned long old_kernel_pbase = ULONG_MAX; + unsigned long new_kernel_pbase = 0UL; + struct elfhdr ehdr; + struct kexec_elf_info elf_info; + + ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info); + if (ret) + return ERR_PTR(ret); + + ret = elf_find_pbase(image, kernel_len, &ehdr, &elf_info, + &old_kernel_pbase, &new_kernel_pbase); + if (ret) + goto out; + + /* Add the kernel binary to the image */ + ret = riscv_kexec_elf_load(image, &ehdr, &elf_info, + old_kernel_pbase, new_kernel_pbase); + if (ret) + goto out; + + ret = load_extra_segments(image, image->start, kernel_len, + initrd, initrd_len, cmdline, cmdline_len); +out: + kexec_free_elf_info(&elf_info); + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops elf_kexec_ops = { + .probe = kexec_elf_probe, + .load = elf_kexec_load, +}; diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c new file mode 100644 index 000000000000..26a81774a78a --- /dev/null +++ b/arch/riscv/kernel/kexec_image.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V Kexec image loader + * + */ + +#define pr_fmt(fmt) "kexec_file(Image): " fmt + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/pe.h> +#include <linux/string.h> +#include <asm/byteorder.h> +#include <asm/image.h> + +static int image_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct riscv_image_header *h = (const struct riscv_image_header *)kernel_buf; + + if (!h || kernel_len < sizeof(*h)) + return -EINVAL; + + /* According to Documentation/riscv/boot-image-header.rst, + * use "magic2" field to check when version >= 0.2. + */ + + if (h->version >= RISCV_HEADER_VERSION && + memcmp(&h->magic2, RISCV_IMAGE_MAGIC2, sizeof(h->magic2))) + return -EINVAL; + + return 0; +} + +static void *image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct riscv_image_header *h; + u64 flags; + bool be_image, be_kernel; + struct kexec_buf kbuf; + int ret; + + /* Check Image header */ + h = (struct riscv_image_header *)kernel; + if (!h->image_size) { + ret = -EINVAL; + goto out; + } + + /* Check endianness */ + flags = le64_to_cpu(h->flags); + be_image = riscv_image_flag_field(flags, RISCV_IMAGE_FLAG_BE); + be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + if (be_image != be_kernel) { + ret = -EINVAL; + goto out; + } + + /* Load the kernel image */ + kbuf.image = image; + kbuf.buf_min = 0; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = le64_to_cpu(h->image_size); + kbuf.buf_align = le64_to_cpu(h->text_offset); + + ret = kexec_add_buffer(&kbuf); + if (ret) { + pr_err("Error add kernel image ret=%d\n", ret); + goto out; + } + + image->start = kbuf.mem; + + pr_info("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kbuf.mem, kbuf.bufsz, kbuf.memsz); + + ret = load_extra_segments(image, kbuf.mem, kbuf.memsz, + initrd, initrd_len, cmdline, cmdline_len); + +out: + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops image_kexec_ops = { + .probe = image_probe, + .load = image_load, +}; diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index 2e0266ae6bd7..9f3db3503dab 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -254,6 +254,12 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) regs->epc = pc; } +noinline void arch_kgdb_breakpoint(void) +{ + asm(".global kgdb_compiled_break\n" + "kgdb_compiled_break: ebreak\n"); +} + void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, char *remcom_out_buffer) { diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index 3c830a6f7ef4..2306ce3e5f22 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -114,29 +114,6 @@ void machine_shutdown(void) #endif } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - /* * machine_crash_shutdown - Prepare to kexec after a kernel crash * diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c index b0bf8c1722c0..e36104af2e24 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -7,8 +7,369 @@ * Author: Liao Chang (liaochang1@huawei.com) */ #include <linux/kexec.h> +#include <linux/elf.h> +#include <linux/slab.h> +#include <linux/of.h> +#include <linux/libfdt.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <linux/vmalloc.h> +#include <asm/setup.h> const struct kexec_file_ops * const kexec_file_loaders[] = { &elf_kexec_ops, + &image_kexec_ops, NULL }; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + kvfree(image->arch.fdt); + image->arch.fdt = NULL; + + vfree(image->elf_headers); + image->elf_headers = NULL; + image->elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} + +#ifdef CONFIG_CRASH_DUMP +static int get_nr_ram_ranges_callback(struct resource *res, void *arg) +{ + unsigned int *nr_ranges = arg; + + (*nr_ranges)++; + return 0; +} + +static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) +{ + struct crash_mem *cmem = arg; + + cmem->ranges[cmem->nr_ranges].start = res->start; + cmem->ranges[cmem->nr_ranges].end = res->end; + cmem->nr_ranges++; + + return 0; +} + +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + struct crash_mem *cmem; + unsigned int nr_ranges; + int ret; + + nr_ranges = 1; /* For exclusion of crashkernel region */ + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + + cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); + if (ret) + goto out; + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + if (!ret) + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + +out: + kfree(cmem); + return ret; +} + +static char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len) +{ + int elfcorehdr_strlen; + char *cmdline_ptr; + + cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); + if (!cmdline_ptr) + return NULL; + + elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", + image->elf_load_addr); + + if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) { + pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n"); + kfree(cmdline_ptr); + return NULL; + } + + memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len); + /* Ensure it's nul terminated */ + cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0'; + return cmdline_ptr; +} +#endif + +#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) +#define RISCV_IMM_BITS 12 +#define RISCV_IMM_REACH (1LL << RISCV_IMM_BITS) +#define RISCV_CONST_HIGH_PART(x) \ + (((x) + (RISCV_IMM_REACH >> 1)) & ~(RISCV_IMM_REACH - 1)) +#define RISCV_CONST_LOW_PART(x) ((x) - RISCV_CONST_HIGH_PART(x)) + +#define ENCODE_ITYPE_IMM(x) \ + (RV_X(x, 0, 12) << 20) +#define ENCODE_BTYPE_IMM(x) \ + ((RV_X(x, 1, 4) << 8) | (RV_X(x, 5, 6) << 25) | \ + (RV_X(x, 11, 1) << 7) | (RV_X(x, 12, 1) << 31)) +#define ENCODE_UTYPE_IMM(x) \ + (RV_X(x, 12, 20) << 12) +#define ENCODE_JTYPE_IMM(x) \ + ((RV_X(x, 1, 10) << 21) | (RV_X(x, 11, 1) << 20) | \ + (RV_X(x, 12, 8) << 12) | (RV_X(x, 20, 1) << 31)) +#define ENCODE_CBTYPE_IMM(x) \ + ((RV_X(x, 1, 2) << 3) | (RV_X(x, 3, 2) << 10) | (RV_X(x, 5, 1) << 2) | \ + (RV_X(x, 6, 2) << 5) | (RV_X(x, 8, 1) << 12)) +#define ENCODE_CJTYPE_IMM(x) \ + ((RV_X(x, 1, 3) << 3) | (RV_X(x, 4, 1) << 11) | (RV_X(x, 5, 1) << 2) | \ + (RV_X(x, 6, 1) << 7) | (RV_X(x, 7, 1) << 6) | (RV_X(x, 8, 2) << 9) | \ + (RV_X(x, 10, 1) << 8) | (RV_X(x, 11, 1) << 12)) +#define ENCODE_UJTYPE_IMM(x) \ + (ENCODE_UTYPE_IMM(RISCV_CONST_HIGH_PART(x)) | \ + (ENCODE_ITYPE_IMM(RISCV_CONST_LOW_PART(x)) << 32)) +#define ENCODE_UITYPE_IMM(x) \ + (ENCODE_UTYPE_IMM(x) | (ENCODE_ITYPE_IMM(x) << 32)) + +#define CLEAN_IMM(type, x) \ + ((~ENCODE_##type##_IMM((uint64_t)(-1))) & (x)) + +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab) +{ + const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; + Elf64_Rela *relas; + int i, r_type; + + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; + + relas = (void *)pi->ehdr + relsec->sh_offset; + + for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) { + const Elf_Sym *sym; /* symbol to relocate */ + unsigned long addr; /* final location after relocation */ + unsigned long val; /* relocated symbol value */ + unsigned long sec_base; /* relocated symbol value */ + void *loc; /* tmp location to modify */ + + sym = (void *)pi->ehdr + symtab->sh_offset; + sym += ELF64_R_SYM(relas[i].r_info); + + if (sym->st_name) + name = strtab + sym->st_name; + else + name = shstrtab + sechdrs[sym->st_shndx].sh_name; + + loc = pi->purgatory_buf; + loc += section->sh_offset; + loc += relas[i].r_offset; + + if (sym->st_shndx == SHN_ABS) + sec_base = 0; + else if (sym->st_shndx >= pi->ehdr->e_shnum) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); + return -ENOEXEC; + } else + sec_base = pi->sechdrs[sym->st_shndx].sh_addr; + + val = sym->st_value; + val += sec_base; + val += relas[i].r_addend; + + addr = section->sh_addr + relas[i].r_offset; + + r_type = ELF64_R_TYPE(relas[i].r_info); + + switch (r_type) { + case R_RISCV_BRANCH: + *(u32 *)loc = CLEAN_IMM(BTYPE, *(u32 *)loc) | + ENCODE_BTYPE_IMM(val - addr); + break; + case R_RISCV_JAL: + *(u32 *)loc = CLEAN_IMM(JTYPE, *(u32 *)loc) | + ENCODE_JTYPE_IMM(val - addr); + break; + /* + * With no R_RISCV_PCREL_LO12_S, R_RISCV_PCREL_LO12_I + * sym is expected to be next to R_RISCV_PCREL_HI20 + * in purgatory relsec. Handle it like R_RISCV_CALL + * sym, instead of searching the whole relsec. + */ + case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: + case R_RISCV_CALL: + *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | + ENCODE_UJTYPE_IMM(val - addr); + break; + case R_RISCV_RVC_BRANCH: + *(u32 *)loc = CLEAN_IMM(CBTYPE, *(u32 *)loc) | + ENCODE_CBTYPE_IMM(val - addr); + break; + case R_RISCV_RVC_JUMP: + *(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) | + ENCODE_CJTYPE_IMM(val - addr); + break; + case R_RISCV_ADD16: + *(u16 *)loc += val; + break; + case R_RISCV_SUB16: + *(u16 *)loc -= val; + break; + case R_RISCV_ADD32: + *(u32 *)loc += val; + break; + case R_RISCV_SUB32: + *(u32 *)loc -= val; + break; + /* It has been applied by R_RISCV_PCREL_HI20 sym */ + case R_RISCV_PCREL_LO12_I: + case R_RISCV_ALIGN: + case R_RISCV_RELAX: + break; + case R_RISCV_64: + *(u64 *)loc = val; + break; + default: + pr_err("Unknown rela relocation: %d\n", r_type); + return -ENOEXEC; + } + } + return 0; +} + + +int load_extra_segments(struct kimage *image, unsigned long kernel_start, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + void *fdt; + unsigned long initrd_pbase = 0UL; + struct kexec_buf kbuf; + char *modified_cmdline = NULL; + + kbuf.image = image; + kbuf.buf_min = kernel_start + kernel_len; + kbuf.buf_max = ULONG_MAX; + +#ifdef CONFIG_CRASH_DUMP + /* Add elfcorehdr */ + if (image->type == KEXEC_TYPE_CRASH) { + void *headers; + unsigned long headers_sz; + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out; + } + image->elf_headers = headers; + image->elf_load_addr = kbuf.mem; + image->elf_headers_sz = headers_sz; + + kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + + /* Setup cmdline for kdump kernel case */ + modified_cmdline = setup_kdump_cmdline(image, cmdline, + cmdline_len); + if (!modified_cmdline) { + pr_err("Setting up cmdline for kdump kernel failed\n"); + ret = -EINVAL; + goto out; + } + cmdline = modified_cmdline; + } +#endif + +#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY + /* Add purgatory to the image */ + kbuf.top_down = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_load_purgatory(image, &kbuf); + if (ret) { + pr_err("Error loading purgatory ret=%d\n", ret); + goto out; + } + kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem); + + ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry", + &kernel_start, + sizeof(kernel_start), 0); + if (ret) + pr_err("Error update purgatory ret=%d\n", ret); +#endif /* CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY */ + + /* Add the initrd to the image */ + if (initrd != NULL) { + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + initrd_pbase = kbuf.mem; + kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_pbase); + } + + /* Add the DTB to the image */ + fdt = of_kexec_alloc_and_setup_fdt(image, initrd_pbase, + initrd_len, cmdline, 0); + if (!fdt) { + pr_err("Error setting up the new device tree.\n"); + ret = -EINVAL; + goto out; + } + + fdt_pack(fdt); + kbuf.buffer = fdt; + kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); + kbuf.buf_align = PAGE_SIZE; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.top_down = true; + ret = kexec_add_buffer(&kbuf); + if (ret) { + pr_err("Error add DTB kbuf ret=%d\n", ret); + goto out_free_fdt; + } + /* Cache the fdt buffer address for memory cleanup */ + image->arch.fdt = fdt; + kexec_dprintk("Loaded device tree at 0x%lx\n", kbuf.mem); + goto out; + +out_free_fdt: + kvfree(fdt); +out: + kfree(modified_cmdline); + return ret; +} diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 745dd4c4a69c..48f6c4f7dca0 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -13,7 +13,6 @@ .text -#define FENTRY_RA_OFFSET 8 #define ABI_SIZE_ON_STACK 80 #define ABI_A0 0 #define ABI_A1 8 @@ -56,16 +55,13 @@ addi sp, sp, ABI_SIZE_ON_STACK .endm -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS - /** * SAVE_ABI_REGS - save regs against the ftrace_regs struct * * After the stack is established, * * 0(sp) stores the PC of the traced function which can be accessed -* by &(fregs)->epc in tracing function. Note that the real -* function entry address should be computed with -FENTRY_RA_OFFSET. +* by &(fregs)->epc in tracing function. * * 8(sp) stores the function return address (i.e. parent IP) that * can be accessed by &(fregs)->ra in tracing function. @@ -86,17 +82,20 @@ * +++++++++ **/ .macro SAVE_ABI_REGS - mv t4, sp // Save original SP in T4 addi sp, sp, -FREGS_SIZE_ON_STACK - REG_S t0, FREGS_EPC(sp) REG_S x1, FREGS_RA(sp) - REG_S t4, FREGS_SP(sp) // Put original SP on stack #ifdef HAVE_FUNCTION_GRAPH_FP_TEST REG_S x8, FREGS_S0(sp) #endif REG_S x6, FREGS_T1(sp) - +#ifdef CONFIG_CC_IS_CLANG + REG_S x7, FREGS_T2(sp) + REG_S x28, FREGS_T3(sp) + REG_S x29, FREGS_T4(sp) + REG_S x30, FREGS_T5(sp) + REG_S x31, FREGS_T6(sp) +#endif // save the arguments REG_S x10, FREGS_A0(sp) REG_S x11, FREGS_A1(sp) @@ -106,16 +105,25 @@ REG_S x15, FREGS_A5(sp) REG_S x16, FREGS_A6(sp) REG_S x17, FREGS_A7(sp) + mv a0, sp + addi a0, a0, FREGS_SIZE_ON_STACK + REG_S a0, FREGS_SP(sp) // Put original SP on stack .endm - .macro RESTORE_ABI_REGS, all=0 + .macro RESTORE_ABI_REGS REG_L t0, FREGS_EPC(sp) REG_L x1, FREGS_RA(sp) #ifdef HAVE_FUNCTION_GRAPH_FP_TEST REG_L x8, FREGS_S0(sp) #endif REG_L x6, FREGS_T1(sp) - +#ifdef CONFIG_CC_IS_CLANG + REG_L x7, FREGS_T2(sp) + REG_L x28, FREGS_T3(sp) + REG_L x29, FREGS_T4(sp) + REG_L x30, FREGS_T5(sp) + REG_L x31, FREGS_T6(sp) +#endif // restore the arguments REG_L x10, FREGS_A0(sp) REG_L x11, FREGS_A1(sp) @@ -130,60 +138,71 @@ .endm .macro PREPARE_ARGS - addi a0, t0, -FENTRY_RA_OFFSET + addi a0, t0, -MCOUNT_JALR_SIZE // ip (callsite's jalr insn) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + mv a1, ra // parent_ip + REG_L a2, -16(t0) // op + REG_L ra, FTRACE_OPS_FUNC(a2) // op->func +#else la a1, function_trace_op - REG_L a2, 0(a1) - mv a1, ra - mv a3, sp + REG_L a2, 0(a1) // op + mv a1, ra // parent_ip +#endif + mv a3, sp // regs .endm -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ - -#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS SYM_FUNC_START(ftrace_caller) - SAVE_ABI - - addi a0, t0, -FENTRY_RA_OFFSET - la a1, function_trace_op - REG_L a2, 0(a1) - mv a1, ra - mv a3, sp +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * When CALL_OPS is enabled (2 or 4) nops [8B] are placed before the + * function entry, these are later overwritten with the pointer to the + * associated struct ftrace_ops. + * + * -8: &ftrace_ops of the associated tracer function. + *<ftrace enable>: + * 0: auipc t0/ra, 0x? + * 4: jalr t0/ra, ?(t0/ra) + * + * -8: &ftrace_nop_ops + *<ftrace disable>: + * 0: nop + * 4: nop + * + * t0 is set to ip+8 after the jalr is executed at the callsite, + * so we find the associated op at t0-16. + */ + REG_L t1, -16(t0) // op Should be SZ_REG instead of 16 -SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - call ftrace_stub - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi a0, sp, ABI_RA - REG_L a1, ABI_T0(sp) - addi a1, a1, -FENTRY_RA_OFFSET -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - mv a2, s0 +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + REG_L t1, FTRACE_OPS_DIRECT_CALL(t1) + bnez t1, ftrace_caller_direct #endif -SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) - call ftrace_stub #endif - RESTORE_ABI - jr t0 -SYM_FUNC_END(ftrace_caller) - -#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ -SYM_FUNC_START(ftrace_caller) - mv t1, zero SAVE_ABI_REGS PREPARE_ARGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + jalr ra +#else SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - call ftrace_stub - + REG_L ra, ftrace_call_dest + jalr ra, 0(ra) +#endif RESTORE_ABI_REGS - bnez t1, .Ldirect +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + bnez t1, ftrace_caller_direct +#endif jr t0 -.Ldirect: +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) jr t1 +#endif SYM_FUNC_END(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ - #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS SYM_CODE_START(ftrace_stub_direct_tramp) jr t0 diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 3a42f6287909..da4a4000e57e 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -26,12 +26,12 @@ * register if a0 was not saved. */ .macro SAVE_RET_ABI_STATE - addi sp, sp, -4*SZREG - REG_S s0, 2*SZREG(sp) - REG_S ra, 3*SZREG(sp) - REG_S a0, 1*SZREG(sp) - REG_S a1, 0*SZREG(sp) - addi s0, sp, 4*SZREG + addi sp, sp, -FREGS_SIZE_ON_STACK + REG_S ra, FREGS_RA(sp) + REG_S s0, FREGS_S0(sp) + REG_S a0, FREGS_A0(sp) + REG_S a1, FREGS_A1(sp) + addi s0, sp, FREGS_SIZE_ON_STACK .endm .macro RESTORE_ABI_STATE @@ -41,11 +41,11 @@ .endm .macro RESTORE_RET_ABI_STATE - REG_L ra, 3*SZREG(sp) - REG_L s0, 2*SZREG(sp) - REG_L a0, 1*SZREG(sp) - REG_L a1, 0*SZREG(sp) - addi sp, sp, 4*SZREG + REG_L ra, FREGS_RA(sp) + REG_L s0, FREGS_S0(sp) + REG_L a0, FREGS_A0(sp) + REG_L a1, FREGS_A1(sp) + addi sp, sp, FREGS_SIZE_ON_STACK .endm SYM_TYPED_FUNC_START(ftrace_stub) diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index e264e59e596e..75551ac6504c 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleloader.h> +#include <linux/sort.h> unsigned long module_emit_got_entry(struct module *mod, unsigned long val) { @@ -55,43 +56,70 @@ unsigned long module_emit_plt_entry(struct module *mod, unsigned long val) return (unsigned long)&plt[i]; } -static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y) +#define cmp_3way(a, b) ((a) < (b) ? -1 : (a) > (b)) + +static int cmp_rela(const void *a, const void *b) { - return x->r_info == y->r_info && x->r_addend == y->r_addend; + const Elf_Rela *x = a, *y = b; + int i; + + /* sort by type, symbol index and addend */ + i = cmp_3way(x->r_info, y->r_info); + if (i == 0) + i = cmp_3way(x->r_addend, y->r_addend); + return i; } static bool duplicate_rela(const Elf_Rela *rela, int idx) { - int i; - for (i = 0; i < idx; i++) { - if (is_rela_equal(&rela[i], &rela[idx])) - return true; - } - return false; + /* + * Entries are sorted by type, symbol index and addend. That means + * that, if a duplicate entry exists, it must be in the preceding slot. + */ + return idx > 0 && cmp_rela(rela + idx, rela + idx - 1) == 0; } -static void count_max_entries(Elf_Rela *relas, int num, +static void count_max_entries(const Elf_Rela *relas, size_t num, unsigned int *plts, unsigned int *gots) { - unsigned int type, i; - - for (i = 0; i < num; i++) { - type = ELF_RISCV_R_TYPE(relas[i].r_info); - if (type == R_RISCV_CALL_PLT) { - if (!duplicate_rela(relas, i)) - (*plts)++; - } else if (type == R_RISCV_GOT_HI20) { - if (!duplicate_rela(relas, i)) - (*gots)++; + for (size_t i = 0; i < num; i++) { + if (duplicate_rela(relas, i)) + continue; + + switch (ELF_R_TYPE(relas[i].r_info)) { + case R_RISCV_CALL_PLT: + case R_RISCV_PLT32: + (*plts)++; + break; + case R_RISCV_GOT_HI20: + (*gots)++; + break; + default: + unreachable(); } } } +static bool rela_needs_plt_got_entry(const Elf_Rela *rela) +{ + switch (ELF_R_TYPE(rela->r_info)) { + case R_RISCV_CALL_PLT: + case R_RISCV_GOT_HI20: + case R_RISCV_PLT32: + return true; + default: + return false; + } +} + int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { + size_t num_scratch_relas = 0; unsigned int num_plts = 0; unsigned int num_gots = 0; + Elf_Rela *scratch = NULL; + size_t scratch_size = 0; int i; /* @@ -121,9 +149,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, /* Calculate the maxinum number of entries */ for (i = 0; i < ehdr->e_shnum; i++) { + size_t num_relas = sechdrs[i].sh_size / sizeof(Elf_Rela); Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset; - int num_rela = sechdrs[i].sh_size / sizeof(Elf_Rela); Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info; + size_t scratch_size_needed; if (sechdrs[i].sh_type != SHT_RELA) continue; @@ -132,7 +161,28 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (!(dst_sec->sh_flags & SHF_EXECINSTR)) continue; - count_max_entries(relas, num_rela, &num_plts, &num_gots); + /* + * apply_relocate_add() relies on HI20 and LO12 relocation pairs being + * close together, so sort a copy of the section to avoid interfering. + */ + scratch_size_needed = (num_scratch_relas + num_relas) * sizeof(*scratch); + if (scratch_size_needed > scratch_size) { + scratch_size = scratch_size_needed; + scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); + if (!scratch) + return -ENOMEM; + } + + for (size_t j = 0; j < num_relas; j++) + if (rela_needs_plt_got_entry(&relas[j])) + scratch[num_scratch_relas++] = relas[j]; + } + + if (scratch) { + /* sort the accumulated PLT/GOT relocations so duplicates are adjacent */ + sort(scratch, num_scratch_relas, sizeof(*scratch), cmp_rela, NULL); + count_max_entries(scratch, num_scratch_relas, &num_plts, &num_gots); + kvfree(scratch); } mod->arch.plt.shdr->sh_type = SHT_NOBITS; diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 1cd461f3d872..7f6147c18033 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -23,7 +23,7 @@ struct used_bucket { struct relocation_head { struct hlist_node node; - struct list_head *rel_entry; + struct list_head rel_entry; void *location; }; @@ -634,7 +634,7 @@ process_accumulated_relocations(struct module *me, location = rel_head_iter->location; list_for_each_entry_safe(rel_entry_iter, rel_entry_iter_tmp, - rel_head_iter->rel_entry, + &rel_head_iter->rel_entry, head) { curr_type = rel_entry_iter->type; reloc_handlers[curr_type].reloc_handler( @@ -648,7 +648,7 @@ process_accumulated_relocations(struct module *me, kfree(bucket_iter); } - kfree(*relocation_hashtable); + kvfree(*relocation_hashtable); } static int add_relocation_to_accumulate(struct module *me, int type, @@ -704,16 +704,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, return -ENOMEM; } - rel_head->rel_entry = - kmalloc(sizeof(struct list_head), GFP_KERNEL); - - if (!rel_head->rel_entry) { - kfree(entry); - kfree(rel_head); - return -ENOMEM; - } - - INIT_LIST_HEAD(rel_head->rel_entry); + INIT_LIST_HEAD(&rel_head->rel_entry); rel_head->location = location; INIT_HLIST_NODE(&rel_head->node); if (!current_head->first) { @@ -722,7 +713,6 @@ static int add_relocation_to_accumulate(struct module *me, int type, if (!bucket) { kfree(entry); - kfree(rel_head->rel_entry); kfree(rel_head); return -ENOMEM; } @@ -735,7 +725,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, } /* Add relocation to head of discovered rel_head */ - list_add_tail(&entry->head, rel_head->rel_entry); + list_add_tail(&entry->head, &rel_head->rel_entry); return 0; } @@ -762,9 +752,10 @@ initialize_relocation_hashtable(unsigned int num_relocations, hashtable_size <<= should_double_size; - *relocation_hashtable = kmalloc_array(hashtable_size, - sizeof(**relocation_hashtable), - GFP_KERNEL); + /* Number of relocations may be large, so kvmalloc it */ + *relocation_hashtable = kvmalloc_array(hashtable_size, + sizeof(**relocation_hashtable), + GFP_KERNEL); if (!*relocation_hashtable) return 0; @@ -869,7 +860,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, } j++; - if (j > sechdrs[relsec].sh_size / sizeof(*rel)) + if (j == num_relocations) j = 0; } while (j_idx != j); diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 34ef522f07a8..db13c9ddf9e3 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -13,7 +13,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/ftrace.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/sections.h> struct patch_insn { diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index c7468af77c66..b465bc9eb870 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -28,11 +28,21 @@ static bool fill_callchain(void *entry, unsigned long pc) void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + if (perf_guest_state()) { + /* TODO: We don't support guest os callchain now */ + return; + } + arch_stack_walk_user(fill_callchain, entry, regs); } void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + if (perf_guest_state()) { + /* TODO: We don't support guest os callchain now */ + return; + } + walk_stackframe(NULL, regs, fill_callchain, entry); } diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile index d5bf1bc7de62..81d69d45c06c 100644 --- a/arch/riscv/kernel/pi/Makefile +++ b/arch/riscv/kernel/pi/Makefile @@ -16,8 +16,12 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS)) KBUILD_CFLAGS += -mcmodel=medany CFLAGS_cmdline_early.o += -D__NO_FORTIFY -CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY CFLAGS_fdt_early.o += -D__NO_FORTIFY +# lib/string.c already defines __NO_FORTIFY +CFLAGS_ctype.o += -D__NO_FORTIFY +CFLAGS_lib-fdt.o += -D__NO_FORTIFY +CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY +CFLAGS_archrandom_early.o += -D__NO_FORTIFY $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ --remove-section=.note.gnu.property \ diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 474a65213657..c0738d6c6498 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -12,7 +12,7 @@ #include <asm/sections.h> #include <asm/cacheflush.h> #include <asm/bug.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include "decode-insn.h" @@ -30,7 +30,7 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p) p->ainsn.api.restore = (unsigned long)p->addr + len; patch_text_nosync(p->ainsn.api.insn, &p->opcode, len); - patch_text_nosync(p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); + patch_text_nosync((void *)p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); } static void __kprobes arch_prepare_simulate(struct kprobe *p) diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c index 4b3dc8beaf77..cc15f7ca6cc1 100644 --- a/arch/riscv/kernel/probes/uprobes.c +++ b/arch/riscv/kernel/probes/uprobes.c @@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, /* Initialize the slot */ void *kaddr = kmap_atomic(page); void *dst = kaddr + (vaddr & ~PAGE_MASK); + unsigned long start = (unsigned long)dst; memcpy(dst, src, len); @@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, *(uprobe_opcode_t *)dst = __BUG_INSN_32; } + flush_icache_range(start, start + len); kunmap_atomic(kaddr); - - /* - * We probably need flush_icache_user_page() but it needs vma. - * This should work on most of architectures by default. If - * architecture needs to do something different it can define - * its own version of the function. - */ - flush_dcache_page(page); } diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index e3142d8a6e28..a0a40889d79a 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -7,6 +7,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/bitfield.h> #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -16,7 +17,9 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/personality.h> +#include <linux/entry-common.h> +#include <asm/asm-prototypes.h> #include <asm/unistd.h> #include <asm/processor.h> #include <asm/csr.h> @@ -35,7 +38,8 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif -extern asmlinkage void ret_from_fork(void); +extern asmlinkage void ret_from_fork_kernel_asm(void); +extern asmlinkage void ret_from_fork_user_asm(void); void noinstr arch_cpu_idle(void) { @@ -56,7 +60,7 @@ int get_unalign_ctl(struct task_struct *tsk, unsigned long adr) if (!unaligned_ctl_available()) return -EINVAL; - return put_user(tsk->thread.align_ctl, (unsigned long __user *)adr); + return put_user(tsk->thread.align_ctl, (unsigned int __user *)adr); } void __show_regs(struct pt_regs *regs) @@ -180,12 +184,16 @@ void flush_thread(void) memset(¤t->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE); #endif +#ifdef CONFIG_RISCV_ISA_SUPM + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + envcfg_update_bits(current, ENVCFG_PMM, ENVCFG_PMM_PMLEN_0); +#endif } void arch_release_task_struct(struct task_struct *tsk) { /* Free the vector context of datap. */ - if (has_vector()) + if (has_vector() || has_xtheadvector()) riscv_v_thread_free(tsk); } @@ -201,6 +209,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs) +{ + fn(fn_arg); + + syscall_exit_to_user_mode(regs); +} + +asmlinkage void ret_from_fork_user(struct pt_regs *regs) +{ + syscall_exit_to_user_mode(regs); +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; @@ -208,6 +228,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); + /* Ensure all threads in this mm have the same pointer masking mode. */ + if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM) && p->mm && (clone_flags & CLONE_VM)) + set_bit(MM_CONTEXT_LOCK_PMLEN, &p->mm->context.flags); + memset(&p->thread.s, 0, sizeof(p->thread.s)); /* p->thread holds context to be restored by __switch_to() */ @@ -219,6 +243,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.s[0] = (unsigned long)args->fn; p->thread.s[1] = (unsigned long)args->fn_arg; + p->thread.ra = (unsigned long)ret_from_fork_kernel_asm; } else { *childregs = *(current_pt_regs()); /* Turn off status.VS */ @@ -228,12 +253,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (clone_flags & CLONE_SETTLS) childregs->tp = tls; childregs->a0 = 0; /* Return value of fork() */ - p->thread.s[0] = 0; + p->thread.ra = (unsigned long)ret_from_fork_user_asm; } p->thread.riscv_v_flags = 0; - if (has_vector()) + if (has_vector() || has_xtheadvector()) riscv_v_thread_alloc(p); - p->thread.ra = (unsigned long)ret_from_fork; p->thread.sp = (unsigned long)childregs; /* kernel sp */ return 0; } @@ -242,3 +266,154 @@ void __init arch_task_cache_init(void) { riscv_v_setup_ctx_cache(); } + +#ifdef CONFIG_RISCV_ISA_SUPM +enum { + PMLEN_0 = 0, + PMLEN_7 = 7, + PMLEN_16 = 16, +}; + +static bool have_user_pmlen_7; +static bool have_user_pmlen_16; + +/* + * Control the relaxed ABI allowing tagged user addresses into the kernel. + */ +static unsigned int tagged_addr_disabled; + +long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg) +{ + unsigned long valid_mask = PR_PMLEN_MASK | PR_TAGGED_ADDR_ENABLE; + struct thread_info *ti = task_thread_info(task); + struct mm_struct *mm = task->mm; + unsigned long pmm; + u8 pmlen; + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return -EINVAL; + + if (is_compat_thread(ti)) + return -EINVAL; + + if (arg & ~valid_mask) + return -EINVAL; + + /* + * Prefer the smallest PMLEN that satisfies the user's request, + * in case choosing a larger PMLEN has a performance impact. + */ + pmlen = FIELD_GET(PR_PMLEN_MASK, arg); + if (pmlen == PMLEN_0) { + pmm = ENVCFG_PMM_PMLEN_0; + } else if (pmlen <= PMLEN_7 && have_user_pmlen_7) { + pmlen = PMLEN_7; + pmm = ENVCFG_PMM_PMLEN_7; + } else if (pmlen <= PMLEN_16 && have_user_pmlen_16) { + pmlen = PMLEN_16; + pmm = ENVCFG_PMM_PMLEN_16; + } else { + return -EINVAL; + } + + /* + * Do not allow the enabling of the tagged address ABI if globally + * disabled via sysctl abi.tagged_addr_disabled, if pointer masking + * is disabled for userspace. + */ + if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen)) + return -EINVAL; + + if (!(arg & PR_TAGGED_ADDR_ENABLE)) + pmlen = PMLEN_0; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + if (test_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags) && mm->context.pmlen != pmlen) { + mmap_write_unlock(mm); + return -EBUSY; + } + + envcfg_update_bits(task, ENVCFG_PMM, pmm); + mm->context.pmlen = pmlen; + + mmap_write_unlock(mm); + + return 0; +} + +long get_tagged_addr_ctrl(struct task_struct *task) +{ + struct thread_info *ti = task_thread_info(task); + long ret = 0; + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return -EINVAL; + + if (is_compat_thread(ti)) + return -EINVAL; + + /* + * The mm context's pmlen is set only when the tagged address ABI is + * enabled, so the effective PMLEN must be extracted from envcfg.PMM. + */ + switch (task->thread.envcfg & ENVCFG_PMM) { + case ENVCFG_PMM_PMLEN_7: + ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_7); + break; + case ENVCFG_PMM_PMLEN_16: + ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_16); + break; + } + + if (task->mm->context.pmlen) + ret |= PR_TAGGED_ADDR_ENABLE; + + return ret; +} + +static bool try_to_set_pmm(unsigned long value) +{ + csr_set(CSR_ENVCFG, value); + return (csr_read_clear(CSR_ENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value; +} + +/* + * Global sysctl to disable the tagged user addresses support. This control + * only prevents the tagged address ABI enabling via prctl() and does not + * disable it for tasks that already opted in to the relaxed ABI. + */ + +static const struct ctl_table tagged_addr_sysctl_table[] = { + { + .procname = "tagged_addr_disabled", + .mode = 0644, + .data = &tagged_addr_disabled, + .maxlen = sizeof(int), + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +}; + +static int __init tagged_addr_init(void) +{ + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return 0; + + /* + * envcfg.PMM is a WARL field. Detect which values are supported. + * Assume the supported PMLEN values are the same on all harts. + */ + csr_clear(CSR_ENVCFG, ENVCFG_PMM); + have_user_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7); + have_user_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16); + + if (!register_sysctl("abi", tagged_addr_sysctl_table)) + return -EINVAL; + + return 0; +} +core_initcall(tagged_addr_init); +#endif /* CONFIG_RISCV_ISA_SUPM */ diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 92731ff8c79a..ea67e9fb7a58 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -28,6 +28,9 @@ enum riscv_regset { #ifdef CONFIG_RISCV_ISA_V REGSET_V, #endif +#ifdef CONFIG_RISCV_ISA_SUPM + REGSET_TAGGED_ADDR_CTRL, +#endif }; static int riscv_gpr_get(struct task_struct *target, @@ -152,6 +155,35 @@ static int riscv_vr_set(struct task_struct *target, } #endif +#ifdef CONFIG_RISCV_ISA_SUPM +static int tagged_addr_ctrl_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + long ctrl = get_tagged_addr_ctrl(target); + + if (IS_ERR_VALUE(ctrl)) + return ctrl; + + return membuf_write(&to, &ctrl, sizeof(ctrl)); +} + +static int tagged_addr_ctrl_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + long ctrl; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); + if (ret) + return ret; + + return set_tagged_addr_ctrl(target, ctrl); +} +#endif + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -182,6 +214,16 @@ static const struct user_regset riscv_user_regset[] = { .set = riscv_vr_set, }, #endif +#ifdef CONFIG_RISCV_ISA_SUPM + [REGSET_TAGGED_ADDR_CTRL] = { + .core_note_type = NT_RISCV_TAGGED_ADDR_CTRL, + .n = 1, + .size = sizeof(long), + .align = sizeof(long), + .regset_get = tagged_addr_ctrl_get, + .set = tagged_addr_ctrl_set, + }, +#endif }; static const struct user_regset_view riscv_user_native_view = { diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index 1989b8cade1b..53836a9235e3 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -299,6 +299,76 @@ static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask, return 0; } +static bool sbi_fwft_supported; + +struct fwft_set_req { + u32 feature; + unsigned long value; + unsigned long flags; + atomic_t error; +}; + +static void cpu_sbi_fwft_set(void *arg) +{ + struct fwft_set_req *req = arg; + int ret; + + ret = sbi_fwft_set(req->feature, req->value, req->flags); + if (ret) + atomic_set(&req->error, ret); +} + +/** + * sbi_fwft_set() - Set a feature on the local hart + * @feature: The feature ID to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags) +{ + struct sbiret ret; + + if (!sbi_fwft_supported) + return -EOPNOTSUPP; + + ret = sbi_ecall(SBI_EXT_FWFT, SBI_EXT_FWFT_SET, + feature, value, flags, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +/** + * sbi_fwft_set_cpumask() - Set a feature for the specified cpumask + * @mask: CPU mask of cpus that need the feature to be set + * @feature: The feature ID to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature, + unsigned long value, unsigned long flags) +{ + struct fwft_set_req req = { + .feature = feature, + .value = value, + .flags = flags, + .error = ATOMIC_INIT(0), + }; + + if (!sbi_fwft_supported) + return -EOPNOTSUPP; + + if (feature & SBI_FWFT_GLOBAL_FEATURE_BIT) + return -EINVAL; + + on_each_cpu_mask(mask, cpu_sbi_fwft_set, &req, 1); + + return atomic_read(&req.error); +} + /** * sbi_set_timer() - Program the timer for next timer event. * @stime_value: The value after which next timer event should fire. @@ -609,7 +679,7 @@ void __init sbi_init(void) } else { __sbi_rfence = __sbi_rfence_v01; } - if ((sbi_spec_version >= sbi_mk_version(0, 3)) && + if (sbi_spec_version >= sbi_mk_version(0, 3) && sbi_probe_extension(SBI_EXT_SRST)) { pr_info("SBI SRST extension detected\n"); pm_power_off = sbi_srst_power_off; @@ -617,11 +687,16 @@ void __init sbi_init(void) sbi_srst_reboot_nb.priority = 192; register_restart_handler(&sbi_srst_reboot_nb); } - if ((sbi_spec_version >= sbi_mk_version(2, 0)) && - (sbi_probe_extension(SBI_EXT_DBCN) > 0)) { + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_DBCN) > 0) { pr_info("SBI DBCN extension detected\n"); sbi_debug_console_available = true; } + if (sbi_spec_version >= sbi_mk_version(3, 0) && + sbi_probe_extension(SBI_EXT_FWFT)) { + pr_info("SBI FWFT extension detected\n"); + sbi_fwft_supported = true; + } } else { __sbi_set_timer = __sbi_set_timer_v01; __sbi_send_ipi = __sbi_send_ipi_v01; diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index a2cde65b69e9..14888e5ea19a 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata") #endif ; unsigned long boot_cpu_hartid; +EXPORT_SYMBOL_GPL(boot_cpu_hartid); /* * Place kernel memory regions on the resource tree so that @@ -66,6 +67,9 @@ static struct resource bss_res = { .name = "Kernel bss", }; static struct resource elfcorehdr_res = { .name = "ELF Core hdr", }; #endif +static int num_standard_resources; +static struct resource *standard_resources; + static int __init add_resource(struct resource *parent, struct resource *res) { @@ -139,7 +143,7 @@ static void __init init_resources(void) struct resource *res = NULL; struct resource *mem_res = NULL; size_t mem_res_sz = 0; - int num_resources = 0, res_idx = 0; + int num_resources = 0, res_idx = 0, non_resv_res = 0; int ret = 0; /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */ @@ -147,9 +151,7 @@ static void __init init_resources(void) res_idx = num_resources - 1; mem_res_sz = num_resources * sizeof(*mem_res); - mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); - if (!mem_res) - panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); + mem_res = memblock_alloc_or_panic(mem_res_sz, SMP_CACHE_BYTES); /* * Start by adding the reserved regions, if they overlap @@ -195,6 +197,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { res = &mem_res[res_idx--]; + non_resv_res++; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -212,6 +215,9 @@ static void __init init_resources(void) goto error; } + num_standard_resources = non_resv_res; + standard_resources = &mem_res[res_idx + 1]; + /* Clean-up any unused pre-allocated resources */ if (res_idx >= 0) memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res)); @@ -223,11 +229,38 @@ static void __init init_resources(void) memblock_free(mem_res, mem_res_sz); } +static int __init reserve_memblock_reserved_regions(void) +{ + u64 i, j; + + for (i = 0; i < num_standard_resources; i++) { + struct resource *mem = &standard_resources[i]; + phys_addr_t r_start, r_end, mem_size = resource_size(mem); + + if (!memblock_is_region_reserved(mem->start, mem_size)) + continue; + + for_each_reserved_mem_range(j, &r_start, &r_end) { + resource_size_t start, end; + + start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start); + end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end); + + if (start > mem->end || end < mem->start) + continue; + + reserve_region_with_split(mem, start, end, "Reserved"); + } + } + + return 0; +} +arch_initcall(reserve_memblock_reserved_regions); static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va)) { + if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) { const char *name = of_flat_dt_get_machine_name(); if (name) { @@ -237,11 +270,42 @@ static void __init parse_dtb(void) } else { pr_err("No DTB passed to the kernel\n"); } +} -#ifdef CONFIG_CMDLINE_FORCE - strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); - pr_info("Forcing kernel command line to: %s\n", boot_command_line); +#if defined(CONFIG_RISCV_COMBO_SPINLOCKS) +DEFINE_STATIC_KEY_TRUE(qspinlock_key); +EXPORT_SYMBOL(qspinlock_key); #endif + +static void __init riscv_spinlock_init(void) +{ + char *using_ext = NULL; + + if (IS_ENABLED(CONFIG_RISCV_TICKET_SPINLOCKS)) { + pr_info("Ticket spinlock: enabled\n"); + return; + } + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && + IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && + riscv_isa_extension_available(NULL, ZABHA) && + riscv_isa_extension_available(NULL, ZACAS)) { + using_ext = "using Zabha"; + } else if (riscv_isa_extension_available(NULL, ZICCRSE)) { + using_ext = "using Ziccrse"; + } +#if defined(CONFIG_RISCV_COMBO_SPINLOCKS) + else { + static_branch_disable(&qspinlock_key); + pr_info("Ticket spinlock: enabled\n"); + return; + } +#endif + + if (!using_ext) + pr_err("Queued spinlock without Zabha or Ziccrse"); + else + pr_info("Queued spinlock %s: enabled\n", using_ext); } extern void __init init_rt_signal_env(void); @@ -288,8 +352,8 @@ void __init setup_arch(char **cmdline_p) riscv_init_cbo_blocksizes(); riscv_fill_hwcap(); - init_rt_signal_env(); apply_boot_alternatives(); + init_rt_signal_env(); if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && riscv_isa_extension_available(NULL, ZICBOM)) @@ -297,6 +361,7 @@ void __init setup_arch(char **cmdline_p) riscv_set_dma_cache_alignment(); riscv_user_isa_enable(); + riscv_spinlock_init(); } bool arch_cpu_is_hotpluggable(int cpu) diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index dcd282419456..08378fea3a11 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -189,7 +189,7 @@ static long restore_sigcontext(struct pt_regs *regs, return 0; case RISCV_V_MAGIC: - if (!has_vector() || !riscv_v_vstate_query(regs) || + if (!(has_vector() || has_xtheadvector()) || !riscv_v_vstate_query(regs) || size != riscv_v_sc_size) return -EINVAL; @@ -211,16 +211,10 @@ static size_t get_rt_frame_size(bool cal_all) frame_size = sizeof(*frame); - if (has_vector()) { + if (has_vector() || has_xtheadvector()) { if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) total_context_size += riscv_v_sc_size; } - /* - * Preserved a __riscv_ctx_hdr for END signal context header if an - * extension uses __riscv_extra_ext_header - */ - if (total_context_size) - total_context_size += sizeof(struct __riscv_ctx_hdr); frame_size += total_context_size; @@ -284,7 +278,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame, if (has_fpu()) err |= save_fp_state(regs, &sc->sc_fpregs); /* Save the vector state. */ - if (has_vector() && riscv_v_vstate_query(regs)) + if ((has_vector() || has_xtheadvector()) && riscv_v_vstate_query(regs)) err |= save_v_state(regs, (void __user **)&sc_ext_ptr); /* Write zero to fp-reserved space and check it on restore_sigcontext */ err |= __put_user(0, &sc->sc_extdesc.reserved); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index c180a647a30e..e650dec44817 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -43,10 +43,13 @@ enum ipi_message_type { unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = INVALID_HARTID }; +EXPORT_SYMBOL_GPL(__cpuid_to_hartid_map); void __init smp_setup_processor_id(void) { cpuid_to_hartid_map(0) = boot_cpu_hartid; + + pr_info("Booting Linux on hartid %lu\n", boot_cpu_hartid); } static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 0f8f1c95ac38..601a321e0f17 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -231,9 +231,11 @@ asmlinkage __visible void smp_callin(void) riscv_ipi_enable(); numa_add_cpu(curr_cpuid); - set_cpu_online(curr_cpuid, true); - riscv_user_isa_enable(); + pr_debug("CPU%u: Booted secondary hartid %lu\n", curr_cpuid, + cpuid_to_hartid_map(curr_cpuid)); + + set_cpu_online(curr_cpuid, true); /* * Remote cache and TLB flushes are ignored while the CPU is offline, diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 153a2db4c5fa..3fe9e6edef8f 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -17,6 +17,7 @@ #ifdef CONFIG_FRAME_POINTER extern asmlinkage void handle_exception(void); +extern unsigned long ret_from_exception_end; static inline int fp_is_valid(unsigned long fp, unsigned long sp) { @@ -71,8 +72,9 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->fp; pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); - if (pc == (unsigned long)handle_exception) { - if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) + if (pc >= (unsigned long)handle_exception && + pc < (unsigned long)&ret_from_exception_end) { + if (unlikely(!fn(arg, pc))) break; pc = ((struct pt_regs *)sp)->epc; diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index c8cec0cc5833..24b3f57d467f 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -14,7 +14,7 @@ void suspend_save_csrs(struct suspend_context *context) { - if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG)) context->envcfg = csr_read(CSR_ENVCFG); context->tvec = csr_read(CSR_TVEC); context->ie = csr_read(CSR_IE); @@ -30,6 +30,13 @@ void suspend_save_csrs(struct suspend_context *context) */ #ifdef CONFIG_MMU + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) { + context->stimecmp = csr_read(CSR_STIMECMP); +#if __riscv_xlen < 64 + context->stimecmph = csr_read(CSR_STIMECMPH); +#endif + } + context->satp = csr_read(CSR_SATP); #endif } @@ -37,12 +44,19 @@ void suspend_save_csrs(struct suspend_context *context) void suspend_restore_csrs(struct suspend_context *context) { csr_write(CSR_SCRATCH, 0); - if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG)) csr_write(CSR_ENVCFG, context->envcfg); csr_write(CSR_TVEC, context->tvec); csr_write(CSR_IE, context->ie); #ifdef CONFIG_MMU + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) { + csr_write(CSR_STIMECMP, context->stimecmp); +#if __riscv_xlen < 64 + csr_write(CSR_STIMECMPH, context->stimecmph); +#endif + } + csr_write(CSR_SATP, context->satp); #endif } diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index cea0ca2bf2a2..0b170e18a2be 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -15,6 +15,8 @@ #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/vector.h> +#include <asm/vendor_extensions/sifive_hwprobe.h> +#include <asm/vendor_extensions/thead_hwprobe.h> #include <vdso/vsyscall.h> @@ -94,7 +96,10 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, * regardless of the kernel's configuration, as no other checks, besides * presence in the hart_isa bitmap, are made. */ + EXT_KEY(ZAAMO); + EXT_KEY(ZABHA); EXT_KEY(ZACAS); + EXT_KEY(ZALRSC); EXT_KEY(ZAWRS); EXT_KEY(ZBA); EXT_KEY(ZBB); @@ -106,10 +111,13 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, EXT_KEY(ZCA); EXT_KEY(ZCB); EXT_KEY(ZCMOP); + EXT_KEY(ZICBOM); EXT_KEY(ZICBOZ); + EXT_KEY(ZICNTR); EXT_KEY(ZICOND); EXT_KEY(ZIHINTNTL); EXT_KEY(ZIHINTPAUSE); + EXT_KEY(ZIHPM); EXT_KEY(ZIMOP); EXT_KEY(ZKND); EXT_KEY(ZKNE); @@ -131,6 +139,8 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, EXT_KEY(ZVE64D); EXT_KEY(ZVE64F); EXT_KEY(ZVE64X); + EXT_KEY(ZVFBFMIN); + EXT_KEY(ZVFBFWMA); EXT_KEY(ZVFH); EXT_KEY(ZVFHMIN); EXT_KEY(ZVKB); @@ -147,9 +157,13 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, EXT_KEY(ZCD); EXT_KEY(ZCF); EXT_KEY(ZFA); + EXT_KEY(ZFBFMIN); EXT_KEY(ZFH); EXT_KEY(ZFHMIN); } + + if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM)) + EXT_KEY(SUPM); #undef EXT_KEY } @@ -157,7 +171,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, pair->value &= ~missing; } -static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext) +static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext) { struct riscv_hwprobe pair; @@ -201,6 +215,43 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus) } #endif +#ifdef CONFIG_RISCV_VECTOR_MISALIGNED +static u64 hwprobe_vec_misaligned(const struct cpumask *cpus) +{ + int cpu; + u64 perf = -1ULL; + + /* Return if supported or not even if speed wasn't probed */ + for_each_cpu(cpu, cpus) { + int this_perf = per_cpu(vector_misaligned_access, cpu); + + if (perf == -1ULL) + perf = this_perf; + + if (perf != this_perf) { + perf = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + break; + } + } + + if (perf == -1ULL) + return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + + return perf; +} +#else +static u64 hwprobe_vec_misaligned(const struct cpumask *cpus) +{ + if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS)) + return RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + + if (IS_ENABLED(CONFIG_RISCV_SLOW_VECTOR_UNALIGNED_ACCESS)) + return RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + + return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; +} +#endif + static void hwprobe_one_pair(struct riscv_hwprobe *pair, const struct cpumask *cpus) { @@ -229,11 +280,20 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, pair->value = hwprobe_misaligned(cpus); break; + case RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF: + pair->value = hwprobe_vec_misaligned(cpus); + break; + case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE: pair->value = 0; if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ)) pair->value = riscv_cboz_block_size; break; + case RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE: + pair->value = 0; + if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOM)) + pair->value = riscv_cbom_block_size; + break; case RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS: pair->value = user_max_virt_addr(); break; @@ -242,6 +302,14 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, pair->value = riscv_timebase; break; + case RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0: + hwprobe_isa_vendor_ext_sifive_0(pair, cpus); + break; + + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: + hwprobe_isa_vendor_ext_thead_0(pair, cpus); + break; + /* * For forward compatibility, unknown keys don't fail the whole * call, but get their element key set to -1 and value set to 0 @@ -401,8 +469,7 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, static int __init init_hwprobe_vdso_data(void) { - struct vdso_data *vd = __arch_get_k_vdso_data(); - struct arch_vdso_data *avd = &vd->arch_data; + struct vdso_arch_data *avd = vdso_k_arch_data; u64 id_bitsmash = 0; struct riscv_hwprobe pair; int key; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 51ebfd23e007..9c83848797a7 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -35,7 +35,7 @@ int show_unhandled_signals = 1; -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) { @@ -81,7 +81,7 @@ void die(struct pt_regs *regs, const char *str) oops_enter(); - spin_lock_irqsave(&die_lock, flags); + raw_spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); @@ -100,7 +100,7 @@ void die(struct pt_regs *regs, const char *str) bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irqrestore(&die_lock, flags); + raw_spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) @@ -198,47 +198,57 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re DO_ERROR_INFO(do_trap_load_fault, SIGSEGV, SEGV_ACCERR, "load access fault"); -asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs) +enum misaligned_access_type { + MISALIGNED_STORE, + MISALIGNED_LOAD, +}; +static const struct { + const char *type_str; + int (*handler)(struct pt_regs *regs); +} misaligned_handler[] = { + [MISALIGNED_STORE] = { + .type_str = "Oops - store (or AMO) address misaligned", + .handler = handle_misaligned_store, + }, + [MISALIGNED_LOAD] = { + .type_str = "Oops - load address misaligned", + .handler = handle_misaligned_load, + }, +}; + +static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type) { + irqentry_state_t state; + if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); + local_irq_enable(); + } else { + state = irqentry_nmi_enter(regs); + } - if (handle_misaligned_load(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - load address misaligned"); + if (misaligned_handler[type].handler(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + misaligned_handler[type].type_str); + if (user_mode(regs)) { + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { - irqentry_state_t state = irqentry_nmi_enter(regs); - - if (handle_misaligned_load(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - load address misaligned"); - irqentry_nmi_exit(regs, state); } } -asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs) +asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs) { - if (user_mode(regs)) { - irqentry_enter_from_user_mode(regs); - - if (handle_misaligned_store(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - store (or AMO) address misaligned"); - - irqentry_exit_to_user_mode(regs); - } else { - irqentry_state_t state = irqentry_nmi_enter(regs); - - if (handle_misaligned_store(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - store (or AMO) address misaligned"); + do_trap_misaligned(regs, MISALIGNED_LOAD); +} - irqentry_nmi_exit(regs, state); - } +asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs) +{ + do_trap_misaligned(regs, MISALIGNED_STORE); } + DO_ERROR_INFO(do_trap_store_fault, SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault"); DO_ERROR_INFO(do_trap_ecall_s, diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index d4fd8af7aaf5..93043924fe6c 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -16,6 +16,8 @@ #include <asm/entry-common.h> #include <asm/hwprobe.h> #include <asm/cpufeature.h> +#include <asm/sbi.h> +#include <asm/vector.h> #define INSN_MATCH_LB 0x3 #define INSN_MASK_LB 0x707f @@ -87,6 +89,13 @@ #define INSN_MATCH_C_FSWSP 0xe002 #define INSN_MASK_C_FSWSP 0xe003 +#define INSN_MATCH_C_LHU 0x8400 +#define INSN_MASK_C_LHU 0xfc43 +#define INSN_MATCH_C_LH 0x8440 +#define INSN_MASK_C_LH 0xfc43 +#define INSN_MATCH_C_SH 0x8c00 +#define INSN_MASK_C_SH 0xfc43 + #define INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4) #if defined(CONFIG_64BIT) @@ -136,8 +145,6 @@ #define REG_PTR(insn, pos, regs) \ (ulong *)((ulong)(regs) + REG_OFFSET(insn, pos)) -#define GET_RM(insn) (((insn) >> 12) & 7) - #define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs)) #define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs)) #define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs)) @@ -269,7 +276,7 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset, int __ret; \ \ if (user_mode(regs)) { \ - __ret = __get_user(insn, (type __user *) insn_addr); \ + __ret = get_user(insn, (type __user *) insn_addr); \ } else { \ insn = *(type *)insn_addr; \ __ret = 0; \ @@ -322,12 +329,37 @@ union reg_data { u64 data_u64; }; -static bool unaligned_ctl __read_mostly; - /* sysctl hooks */ int unaligned_enabled __read_mostly = 1; /* Enabled by default */ -int handle_misaligned_load(struct pt_regs *regs) +#ifdef CONFIG_RISCV_VECTOR_MISALIGNED +static int handle_vector_misaligned_load(struct pt_regs *regs) +{ + unsigned long epc = regs->epc; + unsigned long insn; + + if (get_insn(regs, epc, &insn)) + return -1; + + /* Only return 0 when in check_vector_unaligned_access_emulated */ + if (*this_cpu_ptr(&vector_misaligned_access) == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + *this_cpu_ptr(&vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + regs->epc = epc + INSN_LEN(insn); + return 0; + } + + /* If vector instruction we don't emulate it yet */ + regs->epc = epc; + return -1; +} +#else +static int handle_vector_misaligned_load(struct pt_regs *regs) +{ + return -1; +} +#endif + +static int handle_scalar_misaligned_load(struct pt_regs *regs) { union reg_data val; unsigned long epc = regs->epc; @@ -337,9 +369,7 @@ int handle_misaligned_load(struct pt_regs *regs) perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); -#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED; -#endif if (!unaligned_enabled) return -1; @@ -407,6 +437,13 @@ int handle_misaligned_load(struct pt_regs *regs) fp = 1; len = 4; #endif + } else if ((insn & INSN_MASK_C_LHU) == INSN_MATCH_C_LHU) { + len = 2; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LH) == INSN_MATCH_C_LH) { + len = 2; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; } else { regs->epc = epc; return -1; @@ -435,7 +472,7 @@ int handle_misaligned_load(struct pt_regs *regs) return 0; } -int handle_misaligned_store(struct pt_regs *regs) +static int handle_scalar_misaligned_store(struct pt_regs *regs) { union reg_data val; unsigned long epc = regs->epc; @@ -506,6 +543,9 @@ int handle_misaligned_store(struct pt_regs *regs) len = 4; val.data_ulong = GET_F32_RS2C(insn, regs); #endif + } else if ((insn & INSN_MASK_C_SH) == INSN_MATCH_C_SH) { + len = 2; + val.data_ulong = GET_RS2S(insn, regs); } else { regs->epc = epc; return -1; @@ -526,45 +566,144 @@ int handle_misaligned_store(struct pt_regs *regs) return 0; } -static bool check_unaligned_access_emulated(int cpu) +int handle_misaligned_load(struct pt_regs *regs) +{ + unsigned long epc = regs->epc; + unsigned long insn; + + if (IS_ENABLED(CONFIG_RISCV_VECTOR_MISALIGNED)) { + if (get_insn(regs, epc, &insn)) + return -1; + + if (insn_is_vector(insn)) + return handle_vector_misaligned_load(regs); + } + + if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED)) + return handle_scalar_misaligned_load(regs); + + return -1; +} + +int handle_misaligned_store(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED)) + return handle_scalar_misaligned_store(regs); + + return -1; +} + +#ifdef CONFIG_RISCV_VECTOR_MISALIGNED +void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused) +{ + long *mas_ptr = this_cpu_ptr(&vector_misaligned_access); + unsigned long tmp_var; + + *mas_ptr = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + + kernel_vector_begin(); + /* + * In pre-13.0.0 versions of GCC, vector registers cannot appear in + * the clobber list. This inline asm clobbers v0, but since we do not + * currently build the kernel with V enabled, the v0 clobber arg is not + * needed (as the compiler will not emit vector code itself). If the kernel + * is changed to build with V enabled, the clobber arg will need to be + * added here. + */ + __asm__ __volatile__ ( + ".balign 4\n\t" + ".option push\n\t" + ".option arch, +zve32x\n\t" + " vsetivli zero, 1, e16, m1, ta, ma\n\t" // Vectors of 16b + " vle16.v v0, (%[ptr])\n\t" // Load bytes + ".option pop\n\t" + : : [ptr] "r" ((u8 *)&tmp_var + 1)); + kernel_vector_end(); +} + +bool __init check_vector_unaligned_access_emulated_all_cpus(void) +{ + int cpu; + + /* + * While being documented as very slow, schedule_on_each_cpu() is used since + * kernel_vector_begin() expects irqs to be enabled or it will panic() + */ + schedule_on_each_cpu(check_vector_unaligned_access_emulated); + + for_each_online_cpu(cpu) + if (per_cpu(vector_misaligned_access, cpu) + == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) + return false; + + return true; +} +#else +bool __init check_vector_unaligned_access_emulated_all_cpus(void) +{ + return false; +} +#endif + +static bool all_cpus_unaligned_scalar_access_emulated(void) { + int cpu; + + for_each_online_cpu(cpu) + if (per_cpu(misaligned_access_speed, cpu) != + RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED) + return false; + + return true; +} + +#ifdef CONFIG_RISCV_SCALAR_MISALIGNED + +static bool unaligned_ctl __read_mostly; + +static void check_unaligned_access_emulated(void *arg __always_unused) +{ + int cpu = smp_processor_id(); long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); unsigned long tmp_var, tmp_val; - bool misaligned_emu_detected; *mas_ptr = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; __asm__ __volatile__ ( " "REG_L" %[tmp], 1(%[ptr])\n" : [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory"); +} + +static int cpu_online_check_unaligned_access_emulated(unsigned int cpu) +{ + long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); + + check_unaligned_access_emulated(NULL); - misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED); /* * If unaligned_ctl is already set, this means that we detected that all * CPUS uses emulated misaligned access at boot time. If that changed * when hotplugging the new cpu, this is something we don't handle. */ - if (unlikely(unaligned_ctl && !misaligned_emu_detected)) { + if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED))) { pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n"); - while (true) - cpu_relax(); + return -EINVAL; } - return misaligned_emu_detected; + return 0; } -bool check_unaligned_access_emulated_all_cpus(void) +bool __init check_unaligned_access_emulated_all_cpus(void) { - int cpu; - /* * We can only support PR_UNALIGN controls if all CPUs have misaligned * accesses emulated since tasks requesting such control can run on any * CPU. */ - for_each_online_cpu(cpu) - if (!check_unaligned_access_emulated(cpu)) - return false; + on_each_cpu(check_unaligned_access_emulated, NULL, 1); + + if (!all_cpus_unaligned_scalar_access_emulated()) + return false; unaligned_ctl = true; return true; @@ -574,3 +713,78 @@ bool unaligned_ctl_available(void) { return unaligned_ctl; } +#else +bool __init check_unaligned_access_emulated_all_cpus(void) +{ + return false; +} +static int cpu_online_check_unaligned_access_emulated(unsigned int cpu) +{ + return 0; +} +#endif + +static bool misaligned_traps_delegated; + +#ifdef CONFIG_RISCV_SBI + +static int cpu_online_sbi_unaligned_setup(unsigned int cpu) +{ + if (sbi_fwft_set(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0) && + misaligned_traps_delegated) { + pr_crit("Misaligned trap delegation non homogeneous (expected delegated)"); + return -EINVAL; + } + + return 0; +} + +void __init unaligned_access_init(void) +{ + int ret; + + ret = sbi_fwft_set_online_cpus(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0); + if (ret) + return; + + misaligned_traps_delegated = true; + pr_info("SBI misaligned access exception delegation ok\n"); + /* + * Note that we don't have to take any specific action here, if + * the delegation is successful, then + * check_unaligned_access_emulated() will verify that indeed the + * platform traps on misaligned accesses. + */ +} +#else +void __init unaligned_access_init(void) {} + +static int cpu_online_sbi_unaligned_setup(unsigned int cpu __always_unused) +{ + return 0; +} + +#endif + +int cpu_online_unaligned_access_init(unsigned int cpu) +{ + int ret; + + ret = cpu_online_sbi_unaligned_setup(cpu); + if (ret) + return ret; + + return cpu_online_check_unaligned_access_emulated(cpu); +} + +bool misaligned_traps_can_delegate(void) +{ + /* + * Either we successfully requested misaligned traps delegation for all + * CPUs, or the SBI does not implement the FWFT extension but delegated + * the exception by default. + */ + return misaligned_traps_delegated || + all_cpus_unaligned_scalar_access_emulated(); +} +EXPORT_SYMBOL_GPL(misaligned_traps_can_delegate); diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index 160628a2116d..ae2068425fbc 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -6,11 +6,13 @@ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/jump_label.h> +#include <linux/kthread.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/types.h> #include <asm/cpufeature.h> #include <asm/hwprobe.h> +#include <asm/vector.h> #include "copy-unaligned.h" @@ -19,10 +21,15 @@ #define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE) #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) -DEFINE_PER_CPU(long, misaligned_access_speed); +DEFINE_PER_CPU(long, misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; +DEFINE_PER_CPU(long, vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + +static long unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; +static long unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; -#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS static cpumask_t fast_misaligned_access; + +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS static int check_unaligned_access(void *param) { int cpu = smp_processor_id(); @@ -118,7 +125,7 @@ static int check_unaligned_access(void *param) return 0; } -static void check_unaligned_access_nonboot_cpu(void *param) +static void __init check_unaligned_access_nonboot_cpu(void *param) { unsigned int cpu = smp_processor_id(); struct page **pages = param; @@ -127,6 +134,50 @@ static void check_unaligned_access_nonboot_cpu(void *param) check_unaligned_access(pages[cpu]); } +/* Measure unaligned access speed on all CPUs present at boot in parallel. */ +static void __init check_unaligned_access_speed_all_cpus(void) +{ + unsigned int cpu; + unsigned int cpu_count = num_possible_cpus(); + struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL); + + if (!bufs) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return; + } + + /* + * Allocate separate buffers for each CPU so there's no fighting over + * cache lines. + */ + for_each_cpu(cpu, cpu_online_mask) { + bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!bufs[cpu]) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + goto out; + } + } + + /* Check everybody except 0, who stays behind to tend jiffies. */ + on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1); + + /* Check core 0. */ + smp_call_on_cpu(0, check_unaligned_access, bufs[0], true); + +out: + for_each_cpu(cpu, cpu_online_mask) { + if (bufs[cpu]) + __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); + } + + kfree(bufs); +} +#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */ +static void __init check_unaligned_access_speed_all_cpus(void) +{ +} +#endif + DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key); static void modify_unaligned_access_branches(cpumask_t *mask, int weight) @@ -172,7 +223,7 @@ static void set_unaligned_access_static_branches(void) modify_unaligned_access_branches(&fast_and_online, num_online_cpus()); } -static int lock_and_set_unaligned_access_static_branch(void) +static int __init lock_and_set_unaligned_access_static_branch(void) { cpus_read_lock(); set_unaligned_access_static_branches(); @@ -185,20 +236,33 @@ arch_initcall_sync(lock_and_set_unaligned_access_static_branch); static int riscv_online_cpu(unsigned int cpu) { - static struct page *buf; + int ret = cpu_online_unaligned_access_init(cpu); + + if (ret) + return ret; /* We are already set since the last check */ - if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + goto exit; + } else if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; goto exit; - - buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); - if (!buf) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - return -ENOMEM; } - check_unaligned_access(buf); - __free_pages(buf, MISALIGNED_BUFFER_ORDER); +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS + { + static struct page *buf; + + buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!buf) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return -ENOMEM; + } + + check_unaligned_access(buf); + __free_pages(buf, MISALIGNED_BUFFER_ORDER); + } +#endif exit: set_unaligned_access_static_branches(); @@ -213,69 +277,216 @@ static int riscv_offline_cpu(unsigned int cpu) return 0; } -/* Measure unaligned access speed on all CPUs present at boot in parallel. */ -static int check_unaligned_access_speed_all_cpus(void) +#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS +static void check_vector_unaligned_access(struct work_struct *work __always_unused) { - unsigned int cpu; - unsigned int cpu_count = num_possible_cpus(); - struct page **bufs = kcalloc(cpu_count, sizeof(*bufs), GFP_KERNEL); + int cpu = smp_processor_id(); + u64 start_cycles, end_cycles; + u64 word_cycles; + u64 byte_cycles; + int ratio; + unsigned long start_jiffies, now; + struct page *page; + void *dst; + void *src; + long speed = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; - if (!bufs) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - return 0; + if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) + return; + + page = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!page) { + pr_warn("Allocation failure, not measuring vector misaligned performance\n"); + return; } + /* Make an unaligned destination buffer. */ + dst = (void *)((unsigned long)page_address(page) | 0x1); + /* Unalign src as well, but differently (off by 1 + 2 = 3). */ + src = dst + (MISALIGNED_BUFFER_SIZE / 2); + src += 2; + word_cycles = -1ULL; + + /* Do a warmup. */ + kernel_vector_begin(); + __riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + /* - * Allocate separate buffers for each CPU so there's no fighting over - * cache lines. + * For a fixed amount of time, repeatedly try the function, and take + * the best time in cycles as the measurement. */ - for_each_cpu(cpu, cpu_online_mask) { - bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); - if (!bufs[cpu]) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - goto out; - } + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + /* Ensure the CSR read can't reorder WRT to the copy. */ + mb(); + __riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + /* Ensure the copy ends before the end time is snapped. */ + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < word_cycles) + word_cycles = end_cycles - start_cycles; } - /* Check everybody except 0, who stays behind to tend jiffies. */ - on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1); + byte_cycles = -1ULL; + __riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); - /* Check core 0. */ - smp_call_on_cpu(0, check_unaligned_access, bufs[0], true); + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + /* Ensure the CSR read can't reorder WRT to the copy. */ + mb(); + __riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + /* Ensure the copy ends before the end time is snapped. */ + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < byte_cycles) + byte_cycles = end_cycles - start_cycles; + } - /* - * Setup hotplug callbacks for any new CPUs that come online or go - * offline. - */ - cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", - riscv_online_cpu, riscv_offline_cpu); + kernel_vector_end(); -out: - for_each_cpu(cpu, cpu_online_mask) { - if (bufs[cpu]) - __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); + /* Don't divide by zero. */ + if (!word_cycles || !byte_cycles) { + pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned vector access speed\n", + cpu); + + goto free; } - kfree(bufs); + if (word_cycles < byte_cycles) + speed = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + + ratio = div_u64((byte_cycles * 100), word_cycles); + pr_info("cpu%d: Ratio of vector byte access time to vector unaligned word access is %d.%02d, unaligned accesses are %s\n", + cpu, + ratio / 100, + ratio % 100, + (speed == RISCV_HWPROBE_MISALIGNED_VECTOR_FAST) ? "fast" : "slow"); + + per_cpu(vector_misaligned_access, cpu) = speed; + +free: + __free_pages(page, MISALIGNED_BUFFER_ORDER); +} + +/* Measure unaligned access speed on all CPUs present at boot in parallel. */ +static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) +{ + schedule_on_each_cpu(check_vector_unaligned_access); + + return 0; +} +#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */ +static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) +{ return 0; } +#endif -static int check_unaligned_access_all_cpus(void) +static int riscv_online_cpu_vec(unsigned int cpu) { - bool all_cpus_emulated = check_unaligned_access_emulated_all_cpus(); + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; + return 0; + } + +#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS + if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) + return 0; - if (!all_cpus_emulated) - return check_unaligned_access_speed_all_cpus(); + check_vector_unaligned_access_emulated(NULL); + check_vector_unaligned_access(NULL); +#endif return 0; } -#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */ -static int check_unaligned_access_all_cpus(void) + +static const char * const speed_str[] __initconst = { NULL, NULL, "slow", "fast", "unsupported" }; + +static int __init set_unaligned_scalar_speed_param(char *str) { - check_unaligned_access_emulated_all_cpus(); + if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_FAST])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED; + else + return -EINVAL; + + return 1; +} +__setup("unaligned_scalar_speed=", set_unaligned_scalar_speed_param); + +static int __init set_unaligned_vector_speed_param(char *str) +{ + if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_FAST])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + else + return -EINVAL; + + return 1; +} +__setup("unaligned_vector_speed=", set_unaligned_vector_speed_param); + +static int __init check_unaligned_access_all_cpus(void) +{ + int cpu; + + unaligned_access_init(); + + if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n", + speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param); + for_each_online_cpu(cpu) + per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; + } else if (!check_unaligned_access_emulated_all_cpus()) { + check_unaligned_access_speed_all_cpus(); + } + + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + if (!has_vector() && + unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) { + pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n", + speed_str[unaligned_vector_speed_param]); + } else { + pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n", + speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param); + } + } + + if (!has_vector()) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + for_each_online_cpu(cpu) + per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; + } else if (!check_vector_unaligned_access_emulated_all_cpus() && + IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { + kthread_run(vec_check_unaligned_access_speed_all_cpus, + NULL, "vec_check_unaligned_access_speed_all_cpus"); + } + + /* + * Setup hotplug callbacks for any new CPUs that come online or go + * offline. + */ + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", + riscv_online_cpu, riscv_offline_cpu); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", + riscv_online_cpu_vec, NULL); return 0; } -#endif arch_initcall(check_unaligned_access_all_cpus); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 98315b98256d..3a8e038b10a2 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -13,33 +13,17 @@ #include <linux/err.h> #include <asm/page.h> #include <asm/vdso.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <vdso/datapage.h> #include <vdso/vsyscall.h> -enum vvar_pages { - VVAR_DATA_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_NR_PAGES, -}; - -enum rv_vdso_map { - RV_VDSO_MAP_VVAR, - RV_VDSO_MAP_VDSO, -}; - -#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) - -static union vdso_data_store vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = vdso_data_store.data; +#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT) struct __vdso_info { const char *name; const char *vdso_code_start; const char *vdso_code_end; unsigned long vdso_pages; - /* Data Mapping */ - struct vm_special_mapping *dm; /* Code Mapping */ struct vm_special_mapping *cm; }; @@ -86,112 +70,29 @@ static void __init __vdso_init(struct __vdso_info *vdso_info) vdso_info->cm->pages = vdso_pagelist; } -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return (struct vdso_data *)(vvar_page); -} - -/* - * The vvar mapping contains data for a specific time namespace, so when a task - * changes namespace we must unmap its vvar data for the old namespace. - * Subsequent faults will map in data for the new namespace. - * - * For more details see timens_setup_vdso_data(). - */ -int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) -{ - struct mm_struct *mm = task->mm; - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, vdso_info.dm)) - zap_vma_pages(vma); -#ifdef CONFIG_COMPAT - if (vma_is_special_mapping(vma, compat_vdso_info.dm)) - zap_vma_pages(vma); -#endif - } - - mmap_read_unlock(mm); - return 0; -} -#endif - -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct page *timens_page = find_timens_vvar_page(vma); - unsigned long pfn; - - switch (vmf->pgoff) { - case VVAR_DATA_PAGE_OFFSET: - if (timens_page) - pfn = page_to_pfn(timens_page); - else - pfn = sym_to_pfn(vdso_data); - break; -#ifdef CONFIG_TIME_NS - case VVAR_TIMENS_PAGE_OFFSET: - /* - * If a task belongs to a time namespace then a namespace - * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and - * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET - * offset. - * See also the comment near timens_setup_vdso_data(). - */ - if (!timens_page) - return VM_FAULT_SIGBUS; - pfn = sym_to_pfn(vdso_data); - break; -#endif /* CONFIG_TIME_NS */ - default: - return VM_FAULT_SIGBUS; - } - - return vmf_insert_pfn(vma, vmf->address, pfn); -} - -static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { - [RV_VDSO_MAP_VVAR] = { - .name = "[vvar]", - .fault = vvar_fault, - }, - [RV_VDSO_MAP_VDSO] = { - .name = "[vdso]", - .mremap = vdso_mremap, - }, +static struct vm_special_mapping rv_vdso_map __ro_after_init = { + .name = "[vdso]", + .mremap = vdso_mremap, }; static struct __vdso_info vdso_info __ro_after_init = { .name = "vdso", .vdso_code_start = vdso_start, .vdso_code_end = vdso_end, - .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR], - .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO], + .cm = &rv_vdso_map, }; #ifdef CONFIG_COMPAT -static struct vm_special_mapping rv_compat_vdso_maps[] __ro_after_init = { - [RV_VDSO_MAP_VVAR] = { - .name = "[vvar]", - .fault = vvar_fault, - }, - [RV_VDSO_MAP_VDSO] = { - .name = "[vdso]", - .mremap = vdso_mremap, - }, +static struct vm_special_mapping rv_compat_vdso_map __ro_after_init = { + .name = "[vdso]", + .mremap = vdso_mremap, }; static struct __vdso_info compat_vdso_info __ro_after_init = { .name = "compat_vdso", .vdso_code_start = compat_vdso_start, .vdso_code_end = compat_vdso_end, - .dm = &rv_compat_vdso_maps[RV_VDSO_MAP_VVAR], - .cm = &rv_compat_vdso_maps[RV_VDSO_MAP_VDSO], + .cm = &rv_compat_vdso_map, }; #endif @@ -214,7 +115,7 @@ static int __setup_additional_pages(struct mm_struct *mm, unsigned long vdso_base, vdso_text_len, vdso_mapping_len; void *ret; - BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES); vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT; /* Be sure to map the data page */ @@ -226,8 +127,7 @@ static int __setup_additional_pages(struct mm_struct *mm, goto up_fail; } - ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm); + ret = vdso_install_vvar_mapping(mm, vdso_base); if (IS_ERR(ret)) goto up_fail; @@ -236,7 +136,7 @@ static int __setup_additional_pages(struct mm_struct *mm, ret = _install_special_mapping(mm, vdso_base, vdso_text_len, - (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), + (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_SEALED_SYSMAP), vdso_info->cm); if (IS_ERR(ret)) diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 960feb1526ca..9ebb5e590f93 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -2,7 +2,7 @@ # Copied from arch/tile/kernel/vdso/Makefile # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include # Symbols present in the vdso vdso-syms = rt_sigreturn ifdef CONFIG_64BIT @@ -13,16 +13,29 @@ vdso-syms += flush_icache vdso-syms += hwprobe vdso-syms += sys_hwprobe +ifdef CONFIG_VDSO_GETRANDOM +vdso-syms += getrandom +endif + # Files to link into the vdso obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o +ifdef CONFIG_VDSO_GETRANDOM +obj-vdso += vgetrandom-chacha.o +endif + ccflags-y := -fno-stack-protector ccflags-y += -DDISABLE_BRANCH_PROFILING +ccflags-y += -fno-builtin ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) endif +ifneq ($(c-getrandom-y),) + CFLAGS_getrandom.o += -fPIC -include $(c-getrandom-y) +endif + CFLAGS_hwprobe.o += -fPIC # Build rules @@ -37,6 +50,7 @@ endif # Disable -pg to prevent insert call site CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) +CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) # Force dependency @@ -44,9 +58,9 @@ $(obj)/vdso.o: $(obj)/vdso.so # link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,vdsold) + $(call if_changed,vdsold_and_check) LDFLAGS_vdso.so.dbg = -shared -soname=linux-vdso.so.1 \ - --build-id=sha1 --hash-style=both --eh-frame-hdr + --build-id=sha1 --eh-frame-hdr # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -64,7 +78,8 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE # actual build commands # The DSO images are built using a special linker script # Make sure only to export the intended __vdso_xxx symbol offsets. -quiet_cmd_vdsold = VDSOLD $@ - cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \ +quiet_cmd_vdsold_and_check = VDSOLD $@ + cmd_vdsold_and_check = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \ $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ - rm $@.tmp + rm $@.tmp && \ + $(cmd_vdso_check) diff --git a/arch/riscv/kernel/vdso/getrandom.c b/arch/riscv/kernel/vdso/getrandom.c new file mode 100644 index 000000000000..f21922e8cebd --- /dev/null +++ b/arch/riscv/kernel/vdso/getrandom.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved. + */ +#include <linux/types.h> + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len); +} diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index 1e926e4b5881..2ddeba6c68dd 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -16,8 +16,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count, size_t cpusetsize, unsigned long *cpus, unsigned int flags) { - const struct vdso_data *vd = __arch_get_vdso_data(); - const struct arch_vdso_data *avd = &vd->arch_data; + const struct vdso_arch_data *avd = &vdso_u_arch_data; bool all_cpus = !cpusetsize && !cpus; struct riscv_hwprobe *p = pairs; struct riscv_hwprobe *end = pairs + pair_count; @@ -51,8 +50,7 @@ static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count, size_t cpusetsize, unsigned long *cpus, unsigned int flags) { - const struct vdso_data *vd = __arch_get_vdso_data(); - const struct arch_vdso_data *avd = &vd->arch_data; + const struct vdso_arch_data *avd = &vdso_u_arch_data; struct riscv_hwprobe *p = pairs; struct riscv_hwprobe *end = pairs + pair_count; unsigned char *c = (unsigned char *)cpus; diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index cbe2a179331d..c29ef12a63bb 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -4,15 +4,14 @@ */ #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> OUTPUT_ARCH(riscv) SECTIONS { - PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); -#ifdef CONFIG_TIME_NS - PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); -#endif + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -31,7 +30,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.*) *(.dynbss) *(.bss .bss.* .gnu.linkonce.b.*) - } + } :text .note : { *(.note.*) } :text :note @@ -81,6 +80,9 @@ VERSION #ifndef COMPAT_VDSO __vdso_riscv_hwprobe; #endif +#if defined(CONFIG_VDSO_GETRANDOM) && !defined(COMPAT_VDSO) + __vdso_getrandom; +#endif local: *; }; } diff --git a/arch/riscv/kernel/vdso/vgetrandom-chacha.S b/arch/riscv/kernel/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000000..5f0dad8f2373 --- /dev/null +++ b/arch/riscv/kernel/vdso/vgetrandom-chacha.S @@ -0,0 +1,249 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved. + * + * Based on arch/loongarch/vdso/vgetrandom-chacha.S. + */ + +#include <asm/asm.h> +#include <linux/linkage.h> + +.text + +.macro ROTRI rd rs imm + slliw t0, \rs, 32 - \imm + srliw \rd, \rs, \imm + or \rd, \rd, t0 +.endm + +.macro OP_4REG op d0 d1 d2 d3 s0 s1 s2 s3 + \op \d0, \d0, \s0 + \op \d1, \d1, \s1 + \op \d2, \d2, \s2 + \op \d3, \d3, \s3 +.endm + +/* + * a0: output bytes + * a1: 32-byte key input + * a2: 8-byte counter input/output + * a3: number of 64-byte blocks to write to output + */ +SYM_FUNC_START(__arch_chacha20_blocks_nostack) + +#define output a0 +#define key a1 +#define counter a2 +#define nblocks a3 +#define i a4 +#define state0 s0 +#define state1 s1 +#define state2 s2 +#define state3 s3 +#define state4 s4 +#define state5 s5 +#define state6 s6 +#define state7 s7 +#define state8 s8 +#define state9 s9 +#define state10 s10 +#define state11 s11 +#define state12 a5 +#define state13 a6 +#define state14 a7 +#define state15 t1 +#define cnt t2 +#define copy0 t3 +#define copy1 t4 +#define copy2 t5 +#define copy3 t6 + +/* Packs to be used with OP_4REG */ +#define line0 state0, state1, state2, state3 +#define line1 state4, state5, state6, state7 +#define line2 state8, state9, state10, state11 +#define line3 state12, state13, state14, state15 + +#define line1_perm state5, state6, state7, state4 +#define line2_perm state10, state11, state8, state9 +#define line3_perm state15, state12, state13, state14 + +#define copy copy0, copy1, copy2, copy3 + +#define _16 16, 16, 16, 16 +#define _20 20, 20, 20, 20 +#define _24 24, 24, 24, 24 +#define _25 25, 25, 25, 25 + + /* + * The ABI requires s0-s9 saved. + * This does not violate the stack-less requirement: no sensitive data + * is spilled onto the stack. + */ + addi sp, sp, -12*SZREG + REG_S s0, (sp) + REG_S s1, SZREG(sp) + REG_S s2, 2*SZREG(sp) + REG_S s3, 3*SZREG(sp) + REG_S s4, 4*SZREG(sp) + REG_S s5, 5*SZREG(sp) + REG_S s6, 6*SZREG(sp) + REG_S s7, 7*SZREG(sp) + REG_S s8, 8*SZREG(sp) + REG_S s9, 9*SZREG(sp) + REG_S s10, 10*SZREG(sp) + REG_S s11, 11*SZREG(sp) + + ld cnt, (counter) + + li copy0, 0x61707865 + li copy1, 0x3320646e + li copy2, 0x79622d32 + li copy3, 0x6b206574 + +.Lblock: + /* state[0,1,2,3] = "expand 32-byte k" */ + mv state0, copy0 + mv state1, copy1 + mv state2, copy2 + mv state3, copy3 + + /* state[4,5,..,11] = key */ + lw state4, (key) + lw state5, 4(key) + lw state6, 8(key) + lw state7, 12(key) + lw state8, 16(key) + lw state9, 20(key) + lw state10, 24(key) + lw state11, 28(key) + + /* state[12,13] = counter */ + mv state12, cnt + srli state13, cnt, 32 + + /* state[14,15] = 0 */ + mv state14, zero + mv state15, zero + + li i, 10 +.Lpermute: + /* odd round */ + OP_4REG addw line0, line1 + OP_4REG xor line3, line0 + OP_4REG ROTRI line3, _16 + + OP_4REG addw line2, line3 + OP_4REG xor line1, line2 + OP_4REG ROTRI line1, _20 + + OP_4REG addw line0, line1 + OP_4REG xor line3, line0 + OP_4REG ROTRI line3, _24 + + OP_4REG addw line2, line3 + OP_4REG xor line1, line2 + OP_4REG ROTRI line1, _25 + + /* even round */ + OP_4REG addw line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG ROTRI line3_perm, _16 + + OP_4REG addw line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG ROTRI line1_perm, _20 + + OP_4REG addw line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG ROTRI line3_perm, _24 + + OP_4REG addw line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG ROTRI line1_perm, _25 + + addi i, i, -1 + bnez i, .Lpermute + + /* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */ + OP_4REG addw line0, copy + sw state0, (output) + sw state1, 4(output) + sw state2, 8(output) + sw state3, 12(output) + + /* from now on state[0,1,2,3] are scratch registers */ + + /* state[0,1,2,3] = lo(key) */ + lw state0, (key) + lw state1, 4(key) + lw state2, 8(key) + lw state3, 12(key) + + /* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */ + OP_4REG addw line1, line0 + sw state4, 16(output) + sw state5, 20(output) + sw state6, 24(output) + sw state7, 28(output) + + /* state[0,1,2,3] = hi(key) */ + lw state0, 16(key) + lw state1, 20(key) + lw state2, 24(key) + lw state3, 28(key) + + /* output[8,9,10,11] = tmp[0,1,2,3] + state[8,9,10,11] */ + OP_4REG addw line2, line0 + sw state8, 32(output) + sw state9, 36(output) + sw state10, 40(output) + sw state11, 44(output) + + /* output[12,13,14,15] = state[12,13,14,15] + [cnt_lo, cnt_hi, 0, 0] */ + addw state12, state12, cnt + srli state0, cnt, 32 + addw state13, state13, state0 + sw state12, 48(output) + sw state13, 52(output) + sw state14, 56(output) + sw state15, 60(output) + + /* ++counter */ + addi cnt, cnt, 1 + + /* output += 64 */ + addi output, output, 64 + /* --nblocks */ + addi nblocks, nblocks, -1 + bnez nblocks, .Lblock + + /* counter = [cnt_lo, cnt_hi] */ + sd cnt, (counter) + + /* Zero out the potentially sensitive regs, in case nothing uses these + * again. As at now copy[0,1,2,3] just contains "expand 32-byte k" and + * state[0,...,11] are s0-s11 those we'll restore in the epilogue, we + * only need to zero state[12,...,15]. + */ + mv state12, zero + mv state13, zero + mv state14, zero + mv state15, zero + + REG_L s0, (sp) + REG_L s1, SZREG(sp) + REG_L s2, 2*SZREG(sp) + REG_L s3, 3*SZREG(sp) + REG_L s4, 4*SZREG(sp) + REG_L s5, 5*SZREG(sp) + REG_L s6, 6*SZREG(sp) + REG_L s7, 7*SZREG(sp) + REG_L s8, 8*SZREG(sp) + REG_L s9, 9*SZREG(sp) + REG_L s10, 10*SZREG(sp) + REG_L s11, 11*SZREG(sp) + addi sp, sp, 12*SZREG + + ret +SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/riscv/kernel/vec-copy-unaligned.S b/arch/riscv/kernel/vec-copy-unaligned.S new file mode 100644 index 000000000000..7ce4de6f6e69 --- /dev/null +++ b/arch/riscv/kernel/vec-copy-unaligned.S @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024 Rivos Inc. */ + +#include <linux/args.h> +#include <linux/linkage.h> +#include <asm/asm.h> + + .text + +#define WORD_EEW 32 + +#define WORD_SEW CONCATENATE(e, WORD_EEW) +#define VEC_L CONCATENATE(vle, WORD_EEW).v +#define VEC_S CONCATENATE(vse, WORD_EEW).v + +/* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using word loads and stores. */ +/* Note: The size is truncated to a multiple of WORD_EEW */ +SYM_FUNC_START(__riscv_copy_vec_words_unaligned) + andi a4, a2, ~(WORD_EEW-1) + beqz a4, 2f + add a3, a1, a4 + .option push + .option arch, +zve32x +1: + vsetivli t0, 8, WORD_SEW, m8, ta, ma + VEC_L v0, (a1) + VEC_S v0, (a0) + addi a0, a0, WORD_EEW + addi a1, a1, WORD_EEW + bltu a1, a3, 1b + +2: + .option pop + ret +SYM_FUNC_END(__riscv_copy_vec_words_unaligned) + +/* void __riscv_copy_vec_bytes_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using only byte accesses. */ +/* Note: The size is truncated to a multiple of 8 */ +SYM_FUNC_START(__riscv_copy_vec_bytes_unaligned) + andi a4, a2, ~(8-1) + beqz a4, 2f + add a3, a1, a4 + .option push + .option arch, +zve32x +1: + vsetivli t0, 8, e8, m8, ta, ma + vle8.v v0, (a1) + vse8.v v0, (a0) + addi a0, a0, 8 + addi a1, a1, 8 + bltu a1, a3, 1b + +2: + .option pop + ret +SYM_FUNC_END(__riscv_copy_vec_bytes_unaligned) diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c index 682b3feee451..184f780c932d 100644 --- a/arch/riscv/kernel/vector.c +++ b/arch/riscv/kernel/vector.c @@ -33,7 +33,17 @@ int riscv_v_setup_vsize(void) { unsigned long this_vsize; - /* There are 32 vector registers with vlenb length. */ + /* + * There are 32 vector registers with vlenb length. + * + * If the thead,vlenb property was provided by the firmware, use that + * instead of probing the CSRs. + */ + if (thead_vlenb_of) { + riscv_v_vsize = thead_vlenb_of * 32; + return 0; + } + riscv_v_enable(); this_vsize = csr_read(CSR_VLENB) * 32; riscv_v_disable(); @@ -53,7 +63,7 @@ int riscv_v_setup_vsize(void) void __init riscv_v_setup_ctx_cache(void) { - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return; riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx", @@ -66,7 +76,7 @@ void __init riscv_v_setup_ctx_cache(void) #endif } -static bool insn_is_vector(u32 insn_buf) +bool insn_is_vector(u32 insn_buf) { u32 opcode = insn_buf & __INSN_OPCODE_MASK; u32 width, csr; @@ -173,7 +183,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs) u32 __user *epc = (u32 __user *)regs->epc; u32 insn = (u32)regs->badaddr; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return false; /* Do not handle if V is not supported, or disabled */ @@ -216,7 +226,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk) bool inherit; int cur, next; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return; next = riscv_v_ctrl_get_next(tsk); @@ -238,7 +248,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk) long riscv_v_vstate_ctrl_get_current(void) { - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return -EINVAL; return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK; @@ -249,7 +259,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) bool inherit; int cur, next; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return -EINVAL; if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK) @@ -287,7 +297,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) #ifdef CONFIG_SYSCTL -static struct ctl_table riscv_v_default_vstate_table[] = { +static const struct ctl_table riscv_v_default_vstate_table[] = { { .procname = "riscv_v_default_allow", .data = &riscv_v_implicit_uacc, @@ -299,7 +309,7 @@ static struct ctl_table riscv_v_default_vstate_table[] = { static int __init riscv_v_sysctl_init(void) { - if (has_vector()) + if (has_vector() || has_xtheadvector()) if (!register_sysctl("abi", riscv_v_default_vstate_table)) return -EINVAL; return 0; @@ -309,7 +319,7 @@ static int __init riscv_v_sysctl_init(void) static int __init riscv_v_sysctl_init(void) { return 0; } #endif /* ! CONFIG_SYSCTL */ -static int riscv_v_init(void) +static int __init riscv_v_init(void) { return riscv_v_sysctl_init(); } diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c index a8126d118341..92d8ff81f42c 100644 --- a/arch/riscv/kernel/vendor_extensions.c +++ b/arch/riscv/kernel/vendor_extensions.c @@ -6,6 +6,8 @@ #include <asm/vendorid_list.h> #include <asm/vendor_extensions.h> #include <asm/vendor_extensions/andes.h> +#include <asm/vendor_extensions/sifive.h> +#include <asm/vendor_extensions/thead.h> #include <linux/array_size.h> #include <linux/types.h> @@ -14,6 +16,12 @@ struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[] = { #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES &riscv_isa_vendor_ext_list_andes, #endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE + &riscv_isa_vendor_ext_list_sifive, +#endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + &riscv_isa_vendor_ext_list_thead, +#endif }; const size_t riscv_isa_vendor_ext_list_size = ARRAY_SIZE(riscv_isa_vendor_ext_list); @@ -41,6 +49,18 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap; break; #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE + case SIFIVE_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_sifive.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_sifive.per_hart_isa_bitmap; + break; + #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + case THEAD_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap; + break; + #endif default: return false; } @@ -51,6 +71,6 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig if (bit >= RISCV_ISA_VENDOR_EXT_MAX) return false; - return test_bit(bit, bmap->isa) ? true : false; + return test_bit(bit, bmap->isa); } EXPORT_SYMBOL_GPL(__riscv_isa_vendor_extension_available); diff --git a/arch/riscv/kernel/vendor_extensions/Makefile b/arch/riscv/kernel/vendor_extensions/Makefile index 6a61aed944f1..a4eca96d1c8a 100644 --- a/arch/riscv/kernel/vendor_extensions/Makefile +++ b/arch/riscv/kernel/vendor_extensions/Makefile @@ -1,3 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_ANDES) += andes.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE) += sifive.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE) += sifive_hwprobe.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead_hwprobe.o diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c new file mode 100644 index 000000000000..8fcf67e8c07f --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/sifive.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/cpufeature.h> +#include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/sifive.h> + +#include <linux/array_size.h> +#include <linux/types.h> + +/* All SiFive vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { + __RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF), + __RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ), + __RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD), + __RISCV_ISA_EXT_DATA(xsfvqmaccqoq, RISCV_ISA_VENDOR_EXT_XSFVQMACCQOQ), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_sifive = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_sifive), + .ext_data = riscv_isa_vendor_ext_sifive, +}; diff --git a/arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c b/arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c new file mode 100644 index 000000000000..1f77f6309763 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/vendor_extensions/sifive.h> +#include <asm/vendor_extensions/sifive_hwprobe.h> +#include <asm/vendor_extensions/vendor_hwprobe.h> + +#include <linux/cpumask.h> +#include <linux/types.h> + +#include <uapi/asm/hwprobe.h> +#include <uapi/asm/vendor/sifive.h> + +void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_sifive.per_hart_isa_bitmap, { + VENDOR_EXT_KEY(XSFVQMACCDOD); + VENDOR_EXT_KEY(XSFVQMACCQOQ); + VENDOR_EXT_KEY(XSFVFNRCLIPXFQF); + VENDOR_EXT_KEY(XSFVFWMACCQQQ); + }); +} diff --git a/arch/riscv/kernel/vendor_extensions/thead.c b/arch/riscv/kernel/vendor_extensions/thead.c new file mode 100644 index 000000000000..519dbf70710a --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/cpufeature.h> +#include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> + +#include <linux/array_size.h> +#include <linux/cpumask.h> +#include <linux/types.h> + +/* All T-Head vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_thead[] = { + __RISCV_ISA_EXT_DATA(xtheadvector, RISCV_ISA_VENDOR_EXT_XTHEADVECTOR), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_thead), + .ext_data = riscv_isa_vendor_ext_thead, +}; + +void disable_xtheadvector(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap[cpu].isa); + + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap.isa); +} diff --git a/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c new file mode 100644 index 000000000000..2eba34011786 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/vendor_extensions/thead.h> +#include <asm/vendor_extensions/thead_hwprobe.h> +#include <asm/vendor_extensions/vendor_hwprobe.h> + +#include <linux/cpumask.h> +#include <linux/types.h> + +#include <uapi/asm/hwprobe.h> +#include <uapi/asm/vendor/thead.h> + +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap, { + VENDOR_EXT_KEY(XTHEADVECTOR); + }); +} diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 002ca58dd998..61bd5ba6680a 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -97,6 +97,9 @@ SECTIONS { EXIT_DATA } + + RUNTIME_CONST_VARIABLES + PERCPU_SECTION(L1_CACHE_BYTES) .rel.dyn : { diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index 26d1727f0550..704c2899197e 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -18,7 +18,7 @@ menuconfig VIRTUALIZATION if VIRTUALIZATION config KVM - tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)" + tristate "Kernel-based Virtual Machine (KVM) support" depends on RISCV_SBI && MMU select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQ_ROUTING @@ -32,6 +32,7 @@ config KVM select KVM_XFER_TO_GUEST_WORK select KVM_GENERIC_MMU_NOTIFIER select SCHED_INFO + select GUEST_PERF_EVENTS if PERF_EVENTS help Support hosting virtualized guest machines. diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index c2cacfbc06a0..4e0bba91d284 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -9,27 +9,31 @@ include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o +# Ordered alphabetically +kvm-y += aia.o +kvm-y += aia_aplic.o +kvm-y += aia_device.o +kvm-y += aia_imsic.o kvm-y += main.o -kvm-y += vm.o -kvm-y += vmid.o -kvm-y += tlb.o kvm-y += mmu.o +kvm-y += nacl.o +kvm-y += tlb.o kvm-y += vcpu.o kvm-y += vcpu_exit.o kvm-y += vcpu_fp.o -kvm-y += vcpu_vector.o kvm-y += vcpu_insn.o kvm-y += vcpu_onereg.o -kvm-y += vcpu_switch.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o kvm-y += vcpu_sbi.o -kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o kvm-y += vcpu_sbi_base.o -kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_hsm.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_sbi_pmu.o +kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_sta.o +kvm-y += vcpu_sbi_system.o +kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o +kvm-y += vcpu_switch.o kvm-y += vcpu_timer.o -kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o -kvm-y += aia.o -kvm-y += aia_device.o -kvm-y += aia_aplic.o -kvm-y += aia_imsic.o +kvm-y += vcpu_vector.o +kvm-y += vm.o +kvm-y += vmid.o diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 2967d305c442..19afd1f23537 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -16,6 +16,7 @@ #include <linux/percpu.h> #include <linux/spinlock.h> #include <asm/cpufeature.h> +#include <asm/kvm_nacl.h> struct aia_hgei_control { raw_spinlock_t lock; @@ -51,7 +52,7 @@ static int aia_find_hgei(struct kvm_vcpu *owner) return hgei; } -static void aia_set_hvictl(bool ext_irq_pending) +static inline unsigned long aia_hvictl_value(bool ext_irq_pending) { unsigned long hvictl; @@ -62,7 +63,7 @@ static void aia_set_hvictl(bool ext_irq_pending) hvictl = (IRQ_S_EXT << HVICTL_IID_SHIFT) & HVICTL_IID; hvictl |= ext_irq_pending; - csr_write(CSR_HVICTL, hvictl); + return hvictl; } #ifdef CONFIG_32BIT @@ -88,7 +89,7 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; if (kvm_riscv_aia_available()) - csr->vsieh = csr_read(CSR_VSIEH); + csr->vsieh = ncsr_read(CSR_VSIEH); } #endif @@ -115,7 +116,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) hgei = aia_find_hgei(vcpu); if (hgei > 0) - return !!(csr_read(CSR_HGEIP) & BIT(hgei)); + return !!(ncsr_read(CSR_HGEIP) & BIT(hgei)); return false; } @@ -128,45 +129,73 @@ void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) return; #ifdef CONFIG_32BIT - csr_write(CSR_HVIPH, vcpu->arch.aia_context.guest_csr.hviph); + ncsr_write(CSR_HVIPH, vcpu->arch.aia_context.guest_csr.hviph); #endif - aia_set_hvictl(!!(csr->hvip & BIT(IRQ_VS_EXT))); + ncsr_write(CSR_HVICTL, aia_hvictl_value(!!(csr->hvip & BIT(IRQ_VS_EXT)))); } void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + void *nsh; if (!kvm_riscv_aia_available()) return; - csr_write(CSR_VSISELECT, csr->vsiselect); - csr_write(CSR_HVIPRIO1, csr->hviprio1); - csr_write(CSR_HVIPRIO2, csr->hviprio2); + if (kvm_riscv_nacl_sync_csr_available()) { + nsh = nacl_shmem(); + nacl_csr_write(nsh, CSR_VSISELECT, csr->vsiselect); + nacl_csr_write(nsh, CSR_HVIPRIO1, csr->hviprio1); + nacl_csr_write(nsh, CSR_HVIPRIO2, csr->hviprio2); +#ifdef CONFIG_32BIT + nacl_csr_write(nsh, CSR_VSIEH, csr->vsieh); + nacl_csr_write(nsh, CSR_HVIPH, csr->hviph); + nacl_csr_write(nsh, CSR_HVIPRIO1H, csr->hviprio1h); + nacl_csr_write(nsh, CSR_HVIPRIO2H, csr->hviprio2h); +#endif + } else { + csr_write(CSR_VSISELECT, csr->vsiselect); + csr_write(CSR_HVIPRIO1, csr->hviprio1); + csr_write(CSR_HVIPRIO2, csr->hviprio2); #ifdef CONFIG_32BIT - csr_write(CSR_VSIEH, csr->vsieh); - csr_write(CSR_HVIPH, csr->hviph); - csr_write(CSR_HVIPRIO1H, csr->hviprio1h); - csr_write(CSR_HVIPRIO2H, csr->hviprio2h); + csr_write(CSR_VSIEH, csr->vsieh); + csr_write(CSR_HVIPH, csr->hviph); + csr_write(CSR_HVIPRIO1H, csr->hviprio1h); + csr_write(CSR_HVIPRIO2H, csr->hviprio2h); #endif + } } void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + void *nsh; if (!kvm_riscv_aia_available()) return; - csr->vsiselect = csr_read(CSR_VSISELECT); - csr->hviprio1 = csr_read(CSR_HVIPRIO1); - csr->hviprio2 = csr_read(CSR_HVIPRIO2); + if (kvm_riscv_nacl_available()) { + nsh = nacl_shmem(); + csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT); + csr->hviprio1 = nacl_csr_read(nsh, CSR_HVIPRIO1); + csr->hviprio2 = nacl_csr_read(nsh, CSR_HVIPRIO2); #ifdef CONFIG_32BIT - csr->vsieh = csr_read(CSR_VSIEH); - csr->hviph = csr_read(CSR_HVIPH); - csr->hviprio1h = csr_read(CSR_HVIPRIO1H); - csr->hviprio2h = csr_read(CSR_HVIPRIO2H); + csr->vsieh = nacl_csr_read(nsh, CSR_VSIEH); + csr->hviph = nacl_csr_read(nsh, CSR_HVIPH); + csr->hviprio1h = nacl_csr_read(nsh, CSR_HVIPRIO1H); + csr->hviprio2h = nacl_csr_read(nsh, CSR_HVIPRIO2H); #endif + } else { + csr->vsiselect = csr_read(CSR_VSISELECT); + csr->hviprio1 = csr_read(CSR_HVIPRIO1); + csr->hviprio2 = csr_read(CSR_HVIPRIO2); +#ifdef CONFIG_32BIT + csr->vsieh = csr_read(CSR_VSIEH); + csr->hviph = csr_read(CSR_HVIPH); + csr->hviprio1h = csr_read(CSR_HVIPRIO1H); + csr->hviprio2h = csr_read(CSR_HVIPRIO2H); +#endif + } } int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, @@ -250,20 +279,20 @@ static u8 aia_get_iprio8(struct kvm_vcpu *vcpu, unsigned int irq) switch (bitpos / BITS_PER_LONG) { case 0: - hviprio = csr_read(CSR_HVIPRIO1); + hviprio = ncsr_read(CSR_HVIPRIO1); break; case 1: #ifndef CONFIG_32BIT - hviprio = csr_read(CSR_HVIPRIO2); + hviprio = ncsr_read(CSR_HVIPRIO2); break; #else - hviprio = csr_read(CSR_HVIPRIO1H); + hviprio = ncsr_read(CSR_HVIPRIO1H); break; case 2: - hviprio = csr_read(CSR_HVIPRIO2); + hviprio = ncsr_read(CSR_HVIPRIO2); break; case 3: - hviprio = csr_read(CSR_HVIPRIO2H); + hviprio = ncsr_read(CSR_HVIPRIO2H); break; #endif default: @@ -283,20 +312,20 @@ static void aia_set_iprio8(struct kvm_vcpu *vcpu, unsigned int irq, u8 prio) switch (bitpos / BITS_PER_LONG) { case 0: - hviprio = csr_read(CSR_HVIPRIO1); + hviprio = ncsr_read(CSR_HVIPRIO1); break; case 1: #ifndef CONFIG_32BIT - hviprio = csr_read(CSR_HVIPRIO2); + hviprio = ncsr_read(CSR_HVIPRIO2); break; #else - hviprio = csr_read(CSR_HVIPRIO1H); + hviprio = ncsr_read(CSR_HVIPRIO1H); break; case 2: - hviprio = csr_read(CSR_HVIPRIO2); + hviprio = ncsr_read(CSR_HVIPRIO2); break; case 3: - hviprio = csr_read(CSR_HVIPRIO2H); + hviprio = ncsr_read(CSR_HVIPRIO2H); break; #endif default: @@ -308,20 +337,20 @@ static void aia_set_iprio8(struct kvm_vcpu *vcpu, unsigned int irq, u8 prio) switch (bitpos / BITS_PER_LONG) { case 0: - csr_write(CSR_HVIPRIO1, hviprio); + ncsr_write(CSR_HVIPRIO1, hviprio); break; case 1: #ifndef CONFIG_32BIT - csr_write(CSR_HVIPRIO2, hviprio); + ncsr_write(CSR_HVIPRIO2, hviprio); break; #else - csr_write(CSR_HVIPRIO1H, hviprio); + ncsr_write(CSR_HVIPRIO1H, hviprio); break; case 2: - csr_write(CSR_HVIPRIO2, hviprio); + ncsr_write(CSR_HVIPRIO2, hviprio); break; case 3: - csr_write(CSR_HVIPRIO2H, hviprio); + ncsr_write(CSR_HVIPRIO2H, hviprio); break; #endif default: @@ -377,7 +406,7 @@ int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num, return KVM_INSN_ILLEGAL_TRAP; /* First try to emulate in kernel space */ - isel = csr_read(CSR_VSISELECT) & ISELECT_MASK; + isel = ncsr_read(CSR_VSISELECT) & ISELECT_MASK; if (isel >= ISELECT_IPRIO0 && isel <= ISELECT_IPRIO15) return aia_rmw_iprio(vcpu, isel, val, new_val, wr_mask); else if (isel >= IMSIC_FIRST && isel <= IMSIC_LAST && @@ -499,6 +528,10 @@ static int aia_hgei_init(void) hgctrl->free_bitmap = 0; } + /* Skip SGEI interrupt setup for zero guest external interrupts */ + if (!kvm_riscv_aia_nr_hgei) + goto skip_sgei_interrupt; + /* Find INTC irq domain */ domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY); @@ -522,11 +555,16 @@ static int aia_hgei_init(void) return rc; } +skip_sgei_interrupt: return 0; } static void aia_hgei_exit(void) { + /* Do nothing for zero guest external interrupts */ + if (!kvm_riscv_aia_nr_hgei) + return; + /* Free per-CPU SGEI interrupt */ free_percpu_irq(hgei_parent_irq, &aia_hgei); } @@ -536,7 +574,7 @@ void kvm_riscv_aia_enable(void) if (!kvm_riscv_aia_available()) return; - aia_set_hvictl(false); + csr_write(CSR_HVICTL, aia_hvictl_value(false)); csr_write(CSR_HVIPRIO1, 0x0); csr_write(CSR_HVIPRIO2, 0x0); #ifdef CONFIG_32BIT @@ -552,7 +590,7 @@ void kvm_riscv_aia_enable(void) csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) - csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF)); + csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF)); } void kvm_riscv_aia_disable(void) @@ -572,7 +610,7 @@ void kvm_riscv_aia_disable(void) csr_clear(CSR_HIE, BIT(IRQ_S_GEXT)); disable_percpu_irq(hgei_parent_irq); - aia_set_hvictl(false); + csr_write(CSR_HVICTL, aia_hvictl_value(false)); raw_spin_lock_irqsave(&hgctrl->lock, flags); diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index da6ff1bade0d..f59d1c0c8c43 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -143,7 +143,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH || sm == APLIC_SOURCECFG_SM_LEVEL_LOW) { if (!pending) - goto skip_write_pending; + goto noskip_write_pending; if ((irqd->state & APLIC_IRQ_STATE_INPUT) && sm == APLIC_SOURCECFG_SM_LEVEL_LOW) goto skip_write_pending; @@ -152,6 +152,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) goto skip_write_pending; } +noskip_write_pending: if (pending) irqd->state |= APLIC_IRQ_STATE_PENDING; else diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 39cd26af5a69..806c41931cde 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -12,36 +12,6 @@ #include <linux/kvm_host.h> #include <linux/uaccess.h> -static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) -{ - struct kvm_vcpu *tmp_vcpu; - - for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { - tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); - mutex_unlock(&tmp_vcpu->mutex); - } -} - -static void unlock_all_vcpus(struct kvm *kvm) -{ - unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); -} - -static bool lock_all_vcpus(struct kvm *kvm) -{ - struct kvm_vcpu *tmp_vcpu; - unsigned long c; - - kvm_for_each_vcpu(c, tmp_vcpu, kvm) { - if (!mutex_trylock(&tmp_vcpu->mutex)) { - unlock_vcpus(kvm, c - 1); - return false; - } - } - - return true; -} - static int aia_create(struct kvm_device *dev, u32 type) { int ret; @@ -53,7 +23,7 @@ static int aia_create(struct kvm_device *dev, u32 type) return -EEXIST; ret = -EBUSY; - if (!lock_all_vcpus(kvm)) + if (kvm_trylock_all_vcpus(kvm)) return ret; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -65,7 +35,7 @@ static int aia_create(struct kvm_device *dev, u32 type) kvm->arch.aia.in_kernel = true; out_unlock: - unlock_all_vcpus(kvm); + kvm_unlock_all_vcpus(kvm); return ret; } @@ -526,12 +496,10 @@ int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu) void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; - struct kvm_vcpu_aia_csr *reset_csr = - &vcpu->arch.aia_context.guest_reset_csr; if (!kvm_riscv_aia_available()) return; - memcpy(csr, reset_csr, sizeof(*csr)); + memset(csr, 0, sizeof(*csr)); /* Proceed only if AIA was initialized successfully */ if (!kvm_riscv_aia_initialized(vcpu->kvm)) diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index a8085cd8215e..29ef9c2133a9 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -974,7 +974,6 @@ int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu, if (imsic->vsfile_cpu >= 0) { writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE); - kvm_vcpu_kick(vcpu); } else { eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)]; set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip); diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index f3427f6de608..4b24705dc63a 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -10,8 +10,8 @@ #include <linux/err.h> #include <linux/module.h> #include <linux/kvm_host.h> -#include <asm/csr.h> #include <asm/cpufeature.h> +#include <asm/kvm_nacl.h> #include <asm/sbi.h> long kvm_arch_dev_ioctl(struct file *filp, @@ -22,6 +22,12 @@ long kvm_arch_dev_ioctl(struct file *filp, int kvm_arch_enable_virtualization_cpu(void) { + int rc; + + rc = kvm_riscv_nacl_enable(); + if (rc) + return rc; + csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT); csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT); @@ -49,11 +55,21 @@ void kvm_arch_disable_virtualization_cpu(void) csr_write(CSR_HVIP, 0); csr_write(CSR_HEDELEG, 0); csr_write(CSR_HIDELEG, 0); + + kvm_riscv_nacl_disable(); +} + +static void kvm_riscv_teardown(void) +{ + kvm_riscv_aia_exit(); + kvm_riscv_nacl_exit(); + kvm_unregister_perf_callbacks(); } static int __init riscv_kvm_init(void) { int rc; + char slist[64]; const char *str; if (!riscv_isa_extension_available(NULL, h)) { @@ -71,16 +87,53 @@ static int __init riscv_kvm_init(void) return -ENODEV; } + rc = kvm_riscv_nacl_init(); + if (rc && rc != -ENODEV) + return rc; + kvm_riscv_gstage_mode_detect(); kvm_riscv_gstage_vmid_detect(); rc = kvm_riscv_aia_init(); - if (rc && rc != -ENODEV) + if (rc && rc != -ENODEV) { + kvm_riscv_nacl_exit(); return rc; + } kvm_info("hypervisor extension available\n"); + if (kvm_riscv_nacl_available()) { + rc = 0; + slist[0] = '\0'; + if (kvm_riscv_nacl_sync_csr_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "sync_csr"); + rc++; + } + if (kvm_riscv_nacl_sync_hfence_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "sync_hfence"); + rc++; + } + if (kvm_riscv_nacl_sync_sret_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "sync_sret"); + rc++; + } + if (kvm_riscv_nacl_autoswap_csr_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "autoswap_csr"); + rc++; + } + kvm_info("using SBI nested acceleration with %s\n", + (rc) ? slist : "no features"); + } + switch (kvm_riscv_gstage_mode()) { case HGATP_MODE_SV32X4: str = "Sv32x4"; @@ -105,9 +158,11 @@ static int __init riscv_kvm_init(void) kvm_info("AIA available with %d guest external interrupts\n", kvm_riscv_aia_nr_hgei); + kvm_register_perf_callbacks(NULL); + rc = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (rc) { - kvm_riscv_aia_exit(); + kvm_riscv_teardown(); return rc; } @@ -117,8 +172,8 @@ module_init(riscv_kvm_init); static void __exit riscv_kvm_exit(void) { - kvm_riscv_aia_exit(); - kvm_exit(); + + kvm_riscv_teardown(); } module_exit(riscv_kvm_exit); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index b63650f9b966..1087ea74567b 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -15,7 +15,7 @@ #include <linux/vmalloc.h> #include <linux/kvm_host.h> #include <linux/sched/signal.h> -#include <asm/csr.h> +#include <asm/kvm_nacl.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -601,6 +601,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, bool logging = (memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY)) ? true : false; unsigned long vma_pagesize, mmu_seq; + struct page *page; /* We need minimum second+third level pages */ ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels); @@ -631,7 +632,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, /* * Read mmu_invalidate_seq so that KVM can detect if the results of - * vma_lookup() or gfn_to_pfn_prot() become stale priort to acquiring + * vma_lookup() or __kvm_faultin_pfn() become stale prior to acquiring * kvm->mmu_lock. * * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs @@ -647,7 +648,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, return -EFAULT; } - hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable); + hfn = kvm_faultin_pfn(vcpu, gfn, is_write, &writable, &page); if (hfn == KVM_PFN_ERR_HWPOISON) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, vma_pageshift, current); @@ -669,7 +670,6 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, goto out_unlock; if (writable) { - kvm_set_pfn_dirty(hfn); mark_page_dirty(kvm, gfn); ret = gstage_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT, vma_pagesize, false, true); @@ -682,9 +682,8 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, kvm_err("Failed to map in G-stage\n"); out_unlock: + kvm_release_faultin_page(kvm, page, ret && ret != -EEXIST, writable); spin_unlock(&kvm->mmu_lock); - kvm_set_pfn_accessed(hfn); - kvm_release_pfn_clean(hfn); return ret; } @@ -732,7 +731,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID; hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN; - csr_write(CSR_HGATP, hgatp); + ncsr_write(CSR_HGATP, hgatp); if (!kvm_riscv_gstage_vmid_bits()) kvm_riscv_local_hfence_gvma_all(); diff --git a/arch/riscv/kvm/nacl.c b/arch/riscv/kvm/nacl.c new file mode 100644 index 000000000000..08a95ad9ada2 --- /dev/null +++ b/arch/riscv/kvm/nacl.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#include <linux/kvm_host.h> +#include <linux/vmalloc.h> +#include <asm/kvm_nacl.h> + +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available); +DEFINE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl); + +void __kvm_riscv_nacl_hfence(void *shmem, + unsigned long control, + unsigned long page_num, + unsigned long page_count) +{ + int i, ent = -1, try_count = 5; + unsigned long *entp; + +again: + for (i = 0; i < SBI_NACL_SHMEM_HFENCE_ENTRY_MAX; i++) { + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(i); + if (lelong_to_cpu(*entp) & SBI_NACL_SHMEM_HFENCE_CONFIG_PEND) + continue; + + ent = i; + break; + } + + if (ent < 0) { + if (try_count) { + nacl_sync_hfence(-1UL); + goto again; + } else { + pr_warn("KVM: No free entry in NACL shared memory\n"); + return; + } + } + + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(i); + *entp = cpu_to_lelong(control); + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(i); + *entp = cpu_to_lelong(page_num); + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(i); + *entp = cpu_to_lelong(page_count); +} + +int kvm_riscv_nacl_enable(void) +{ + int rc; + struct sbiret ret; + struct kvm_riscv_nacl *nacl; + + if (!kvm_riscv_nacl_available()) + return 0; + nacl = this_cpu_ptr(&kvm_riscv_nacl); + + ret = sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SET_SHMEM, + nacl->shmem_phys, 0, 0, 0, 0, 0); + rc = sbi_err_map_linux_errno(ret.error); + if (rc) + return rc; + + return 0; +} + +void kvm_riscv_nacl_disable(void) +{ + if (!kvm_riscv_nacl_available()) + return; + + sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SET_SHMEM, + SBI_SHMEM_DISABLE, SBI_SHMEM_DISABLE, 0, 0, 0, 0); +} + +void kvm_riscv_nacl_exit(void) +{ + int cpu; + struct kvm_riscv_nacl *nacl; + + if (!kvm_riscv_nacl_available()) + return; + + /* Allocate per-CPU shared memory */ + for_each_possible_cpu(cpu) { + nacl = per_cpu_ptr(&kvm_riscv_nacl, cpu); + if (!nacl->shmem) + continue; + + free_pages((unsigned long)nacl->shmem, + get_order(SBI_NACL_SHMEM_SIZE)); + nacl->shmem = NULL; + nacl->shmem_phys = 0; + } +} + +static long nacl_probe_feature(long feature_id) +{ + struct sbiret ret; + + if (!kvm_riscv_nacl_available()) + return 0; + + ret = sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_PROBE_FEATURE, + feature_id, 0, 0, 0, 0, 0); + return ret.value; +} + +int kvm_riscv_nacl_init(void) +{ + int cpu; + struct page *shmem_page; + struct kvm_riscv_nacl *nacl; + + if (sbi_spec_version < sbi_mk_version(1, 0) || + sbi_probe_extension(SBI_EXT_NACL) <= 0) + return -ENODEV; + + /* Enable NACL support */ + static_branch_enable(&kvm_riscv_nacl_available); + + /* Probe NACL features */ + if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_CSR)) + static_branch_enable(&kvm_riscv_nacl_sync_csr_available); + if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_HFENCE)) + static_branch_enable(&kvm_riscv_nacl_sync_hfence_available); + if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_SRET)) + static_branch_enable(&kvm_riscv_nacl_sync_sret_available); + if (nacl_probe_feature(SBI_NACL_FEAT_AUTOSWAP_CSR)) + static_branch_enable(&kvm_riscv_nacl_autoswap_csr_available); + + /* Allocate per-CPU shared memory */ + for_each_possible_cpu(cpu) { + nacl = per_cpu_ptr(&kvm_riscv_nacl, cpu); + + shmem_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, + get_order(SBI_NACL_SHMEM_SIZE)); + if (!shmem_page) { + kvm_riscv_nacl_exit(); + return -ENOMEM; + } + nacl->shmem = page_to_virt(shmem_page); + nacl->shmem_phys = page_to_phys(shmem_page); + } + + return 0; +} diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c index 23c0e82b5103..2f91ea5f8493 100644 --- a/arch/riscv/kvm/tlb.c +++ b/arch/riscv/kvm/tlb.c @@ -14,6 +14,7 @@ #include <asm/csr.h> #include <asm/cpufeature.h> #include <asm/insn-def.h> +#include <asm/kvm_nacl.h> #define has_svinval() riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL) @@ -186,18 +187,24 @@ void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) void kvm_riscv_hfence_gvma_vmid_all_process(struct kvm_vcpu *vcpu) { - struct kvm_vmid *vmid; + struct kvm_vmid *v = &vcpu->kvm->arch.vmid; + unsigned long vmid = READ_ONCE(v->vmid); - vmid = &vcpu->kvm->arch.vmid; - kvm_riscv_local_hfence_gvma_vmid_all(READ_ONCE(vmid->vmid)); + if (kvm_riscv_nacl_available()) + nacl_hfence_gvma_vmid_all(nacl_shmem(), vmid); + else + kvm_riscv_local_hfence_gvma_vmid_all(vmid); } void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu) { - struct kvm_vmid *vmid; + struct kvm_vmid *v = &vcpu->kvm->arch.vmid; + unsigned long vmid = READ_ONCE(v->vmid); - vmid = &vcpu->kvm->arch.vmid; - kvm_riscv_local_hfence_vvma_all(READ_ONCE(vmid->vmid)); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_all(nacl_shmem(), vmid); + else + kvm_riscv_local_hfence_vvma_all(vmid); } static bool vcpu_hfence_dequeue(struct kvm_vcpu *vcpu, @@ -251,6 +258,7 @@ static bool vcpu_hfence_enqueue(struct kvm_vcpu *vcpu, void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) { + unsigned long vmid; struct kvm_riscv_hfence d = { 0 }; struct kvm_vmid *v = &vcpu->kvm->arch.vmid; @@ -259,26 +267,41 @@ void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) case KVM_RISCV_HFENCE_UNKNOWN: break; case KVM_RISCV_HFENCE_GVMA_VMID_GPA: - kvm_riscv_local_hfence_gvma_vmid_gpa( - READ_ONCE(v->vmid), - d.addr, d.size, d.order); + vmid = READ_ONCE(v->vmid); + if (kvm_riscv_nacl_available()) + nacl_hfence_gvma_vmid(nacl_shmem(), vmid, + d.addr, d.size, d.order); + else + kvm_riscv_local_hfence_gvma_vmid_gpa(vmid, d.addr, + d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_GVA: kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); - kvm_riscv_local_hfence_vvma_asid_gva( - READ_ONCE(v->vmid), d.asid, - d.addr, d.size, d.order); + vmid = READ_ONCE(v->vmid); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_asid(nacl_shmem(), vmid, d.asid, + d.addr, d.size, d.order); + else + kvm_riscv_local_hfence_vvma_asid_gva(vmid, d.asid, d.addr, + d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_ALL: kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); - kvm_riscv_local_hfence_vvma_asid_all( - READ_ONCE(v->vmid), d.asid); + vmid = READ_ONCE(v->vmid); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_asid_all(nacl_shmem(), vmid, d.asid); + else + kvm_riscv_local_hfence_vvma_asid_all(vmid, d.asid); break; case KVM_RISCV_HFENCE_VVMA_GVA: kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); - kvm_riscv_local_hfence_vvma_gva( - READ_ONCE(v->vmid), - d.addr, d.size, d.order); + vmid = READ_ONCE(v->vmid); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma(nacl_shmem(), vmid, + d.addr, d.size, d.order); + else + kvm_riscv_local_hfence_vvma_gva(vmid, d.addr, + d.size, d.order); break; default: break; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 8d7d381737ee..e0a01af426ff 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -17,8 +17,8 @@ #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/kvm_host.h> -#include <asm/csr.h> #include <asm/cacheflush.h> +#include <asm/kvm_nacl.h> #include <asm/kvm_vcpu_vector.h> #define CREATE_TRACE_POINTS @@ -34,7 +34,12 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { STATS_DESC_COUNTER(VCPU, csr_exit_user), STATS_DESC_COUNTER(VCPU, csr_exit_kernel), STATS_DESC_COUNTER(VCPU, signal_exits), - STATS_DESC_COUNTER(VCPU, exits) + STATS_DESC_COUNTER(VCPU, exits), + STATS_DESC_COUNTER(VCPU, instr_illegal_exits), + STATS_DESC_COUNTER(VCPU, load_misaligned_exits), + STATS_DESC_COUNTER(VCPU, store_misaligned_exits), + STATS_DESC_COUNTER(VCPU, load_access_exits), + STATS_DESC_COUNTER(VCPU, store_access_exits), }; const struct kvm_stats_header kvm_vcpu_stats_header = { @@ -46,12 +51,33 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) +static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu, + bool kvm_sbi_reset) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; - struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; - struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context; + void *vector_datap = cntx->vector.datap; + + memset(cntx, 0, sizeof(*cntx)); + memset(csr, 0, sizeof(*csr)); + memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr)); + + /* Restore datap as it's not a part of the guest context. */ + cntx->vector.datap = vector_datap; + + if (kvm_sbi_reset) + kvm_riscv_vcpu_sbi_load_reset_state(vcpu); + + /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ + cntx->sstatus = SR_SPP | SR_SPIE; + + cntx->hstatus |= HSTATUS_VTW; + cntx->hstatus |= HSTATUS_SPVP; + cntx->hstatus |= HSTATUS_SPV; +} + +static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) +{ bool loaded; /** @@ -66,11 +92,7 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.last_exit_cpu = -1; - memcpy(csr, reset_csr, sizeof(*csr)); - - spin_lock(&vcpu->arch.reset_cntx_lock); - memcpy(cntx, reset_cntx, sizeof(*cntx)); - spin_unlock(&vcpu->arch.reset_cntx_lock); + kvm_riscv_vcpu_context_reset(vcpu, kvm_sbi_reset); kvm_riscv_vcpu_fp_reset(vcpu); @@ -105,8 +127,6 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int rc; - struct kvm_cpu_context *cntx; - struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; spin_lock_init(&vcpu->arch.mp_state_lock); @@ -126,24 +146,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU hfence queue */ spin_lock_init(&vcpu->arch.hfence_lock); - /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ - spin_lock_init(&vcpu->arch.reset_cntx_lock); + spin_lock_init(&vcpu->arch.reset_state.lock); - spin_lock(&vcpu->arch.reset_cntx_lock); - cntx = &vcpu->arch.guest_reset_context; - cntx->sstatus = SR_SPP | SR_SPIE; - cntx->hstatus = 0; - cntx->hstatus |= HSTATUS_VTW; - cntx->hstatus |= HSTATUS_SPVP; - cntx->hstatus |= HSTATUS_SPV; - spin_unlock(&vcpu->arch.reset_cntx_lock); - - if (kvm_riscv_vcpu_alloc_vector_context(vcpu, cntx)) + if (kvm_riscv_vcpu_alloc_vector_context(vcpu)) return -ENOMEM; - /* By default, make CY, TM, and IR counters accessible in VU mode */ - reset_csr->scounteren = 0x7; - /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); @@ -162,7 +169,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_sbi_init(vcpu); /* Reset VCPU */ - kvm_riscv_reset_vcpu(vcpu); + kvm_riscv_reset_vcpu(vcpu, false); return 0; } @@ -226,6 +233,13 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) return (vcpu->arch.guest_context.sstatus & SR_SPP) ? true : false; } +#ifdef CONFIG_GUEST_PERF_EVENTS +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_context.sepc; +} +#endif + vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; @@ -361,10 +375,10 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; /* Read current HVIP and VSIE CSRs */ - csr->vsie = csr_read(CSR_VSIE); + csr->vsie = ncsr_read(CSR_VSIE); /* Sync-up HVIP.VSSIP bit changes does by Guest */ - hvip = csr_read(CSR_HVIP); + hvip = ncsr_read(CSR_HVIP); if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) { if (hvip & (1UL << IRQ_VS_SOFT)) { if (!test_and_set_bit(IRQ_VS_SOFT, @@ -504,6 +518,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, case KVM_MP_STATE_STOPPED: __kvm_riscv_vcpu_power_off(vcpu); break; + case KVM_MP_STATE_INIT_RECEIVED: + if (vcpu->kvm->arch.mp_state_reset) + kvm_riscv_reset_vcpu(vcpu, false); + else + ret = -EINVAL; + break; default: ret = -EINVAL; } @@ -544,6 +564,10 @@ static void kvm_riscv_vcpu_setup_config(struct kvm_vcpu *vcpu) if (riscv_isa_extension_available(isa, ZICBOZ)) cfg->henvcfg |= ENVCFG_CBZE; + if (riscv_isa_extension_available(isa, SVADU) && + !riscv_isa_extension_available(isa, SVADE)) + cfg->henvcfg |= ENVCFG_ADUE; + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { cfg->hstateen0 |= SMSTATEEN0_HSENVCFG; if (riscv_isa_extension_available(isa, SSAIA)) @@ -561,26 +585,49 @@ static void kvm_riscv_vcpu_setup_config(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + void *nsh; struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; - csr_write(CSR_VSSTATUS, csr->vsstatus); - csr_write(CSR_VSIE, csr->vsie); - csr_write(CSR_VSTVEC, csr->vstvec); - csr_write(CSR_VSSCRATCH, csr->vsscratch); - csr_write(CSR_VSEPC, csr->vsepc); - csr_write(CSR_VSCAUSE, csr->vscause); - csr_write(CSR_VSTVAL, csr->vstval); - csr_write(CSR_HEDELEG, cfg->hedeleg); - csr_write(CSR_HVIP, csr->hvip); - csr_write(CSR_VSATP, csr->vsatp); - csr_write(CSR_HENVCFG, cfg->henvcfg); - if (IS_ENABLED(CONFIG_32BIT)) - csr_write(CSR_HENVCFGH, cfg->henvcfg >> 32); - if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { - csr_write(CSR_HSTATEEN0, cfg->hstateen0); + if (kvm_riscv_nacl_sync_csr_available()) { + nsh = nacl_shmem(); + nacl_csr_write(nsh, CSR_VSSTATUS, csr->vsstatus); + nacl_csr_write(nsh, CSR_VSIE, csr->vsie); + nacl_csr_write(nsh, CSR_VSTVEC, csr->vstvec); + nacl_csr_write(nsh, CSR_VSSCRATCH, csr->vsscratch); + nacl_csr_write(nsh, CSR_VSEPC, csr->vsepc); + nacl_csr_write(nsh, CSR_VSCAUSE, csr->vscause); + nacl_csr_write(nsh, CSR_VSTVAL, csr->vstval); + nacl_csr_write(nsh, CSR_HEDELEG, cfg->hedeleg); + nacl_csr_write(nsh, CSR_HVIP, csr->hvip); + nacl_csr_write(nsh, CSR_VSATP, csr->vsatp); + nacl_csr_write(nsh, CSR_HENVCFG, cfg->henvcfg); if (IS_ENABLED(CONFIG_32BIT)) - csr_write(CSR_HSTATEEN0H, cfg->hstateen0 >> 32); + nacl_csr_write(nsh, CSR_HENVCFGH, cfg->henvcfg >> 32); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { + nacl_csr_write(nsh, CSR_HSTATEEN0, cfg->hstateen0); + if (IS_ENABLED(CONFIG_32BIT)) + nacl_csr_write(nsh, CSR_HSTATEEN0H, cfg->hstateen0 >> 32); + } + } else { + csr_write(CSR_VSSTATUS, csr->vsstatus); + csr_write(CSR_VSIE, csr->vsie); + csr_write(CSR_VSTVEC, csr->vstvec); + csr_write(CSR_VSSCRATCH, csr->vsscratch); + csr_write(CSR_VSEPC, csr->vsepc); + csr_write(CSR_VSCAUSE, csr->vscause); + csr_write(CSR_VSTVAL, csr->vstval); + csr_write(CSR_HEDELEG, cfg->hedeleg); + csr_write(CSR_HVIP, csr->hvip); + csr_write(CSR_VSATP, csr->vsatp); + csr_write(CSR_HENVCFG, cfg->henvcfg); + if (IS_ENABLED(CONFIG_32BIT)) + csr_write(CSR_HENVCFGH, cfg->henvcfg >> 32); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { + csr_write(CSR_HSTATEEN0, cfg->hstateen0); + if (IS_ENABLED(CONFIG_32BIT)) + csr_write(CSR_HSTATEEN0H, cfg->hstateen0 >> 32); + } } kvm_riscv_gstage_update_hgatp(vcpu); @@ -603,6 +650,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + void *nsh; struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; vcpu->cpu = -1; @@ -618,15 +666,28 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.isa); kvm_riscv_vcpu_host_vector_restore(&vcpu->arch.host_context); - csr->vsstatus = csr_read(CSR_VSSTATUS); - csr->vsie = csr_read(CSR_VSIE); - csr->vstvec = csr_read(CSR_VSTVEC); - csr->vsscratch = csr_read(CSR_VSSCRATCH); - csr->vsepc = csr_read(CSR_VSEPC); - csr->vscause = csr_read(CSR_VSCAUSE); - csr->vstval = csr_read(CSR_VSTVAL); - csr->hvip = csr_read(CSR_HVIP); - csr->vsatp = csr_read(CSR_VSATP); + if (kvm_riscv_nacl_available()) { + nsh = nacl_shmem(); + csr->vsstatus = nacl_csr_read(nsh, CSR_VSSTATUS); + csr->vsie = nacl_csr_read(nsh, CSR_VSIE); + csr->vstvec = nacl_csr_read(nsh, CSR_VSTVEC); + csr->vsscratch = nacl_csr_read(nsh, CSR_VSSCRATCH); + csr->vsepc = nacl_csr_read(nsh, CSR_VSEPC); + csr->vscause = nacl_csr_read(nsh, CSR_VSCAUSE); + csr->vstval = nacl_csr_read(nsh, CSR_VSTVAL); + csr->hvip = nacl_csr_read(nsh, CSR_HVIP); + csr->vsatp = nacl_csr_read(nsh, CSR_VSATP); + } else { + csr->vsstatus = csr_read(CSR_VSSTATUS); + csr->vsie = csr_read(CSR_VSIE); + csr->vstvec = csr_read(CSR_VSTVEC); + csr->vsscratch = csr_read(CSR_VSSCRATCH); + csr->vsepc = csr_read(CSR_VSEPC); + csr->vscause = csr_read(CSR_VSCAUSE); + csr->vstval = csr_read(CSR_VSTVAL); + csr->hvip = csr_read(CSR_HVIP); + csr->vsatp = csr_read(CSR_VSATP); + } } static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) @@ -651,7 +712,7 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) - kvm_riscv_reset_vcpu(vcpu); + kvm_riscv_reset_vcpu(vcpu, true); if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu)) kvm_riscv_gstage_update_hgatp(vcpu); @@ -681,7 +742,7 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; - csr_write(CSR_HVIP, csr->hvip); + ncsr_write(CSR_HVIP, csr->hvip); kvm_riscv_vcpu_aia_update_hvip(vcpu); } @@ -691,6 +752,7 @@ static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu * struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + vcpu->arch.host_scounteren = csr_swap(CSR_SCOUNTEREN, csr->scounteren); vcpu->arch.host_senvcfg = csr_swap(CSR_SENVCFG, csr->senvcfg); if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN) && (cfg->hstateen0 & SMSTATEEN0_SSTATEEN0)) @@ -704,6 +766,7 @@ static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *v struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + csr->scounteren = csr_swap(CSR_SCOUNTEREN, vcpu->arch.host_scounteren); csr->senvcfg = csr_swap(CSR_SENVCFG, vcpu->arch.host_senvcfg); if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN) && (cfg->hstateen0 & SMSTATEEN0_SSTATEEN0)) @@ -718,11 +781,81 @@ static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *v * This must be noinstr as instrumentation may make use of RCU, and this is not * safe during the EQS. */ -static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu) +static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu, + struct kvm_cpu_trap *trap) { + void *nsh; + struct kvm_cpu_context *gcntx = &vcpu->arch.guest_context; + struct kvm_cpu_context *hcntx = &vcpu->arch.host_context; + + /* + * We save trap CSRs (such as SEPC, SCAUSE, STVAL, HTVAL, and + * HTINST) here because we do local_irq_enable() after this + * function in kvm_arch_vcpu_ioctl_run() which can result in + * an interrupt immediately after local_irq_enable() and can + * potentially change trap CSRs. + */ + kvm_riscv_vcpu_swap_in_guest_state(vcpu); guest_state_enter_irqoff(); - __kvm_riscv_switch_to(&vcpu->arch); + + if (kvm_riscv_nacl_sync_sret_available()) { + nsh = nacl_shmem(); + + if (kvm_riscv_nacl_autoswap_csr_available()) { + hcntx->hstatus = + nacl_csr_read(nsh, CSR_HSTATUS); + nacl_scratch_write_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET + + SBI_NACL_SHMEM_AUTOSWAP_HSTATUS, + gcntx->hstatus); + nacl_scratch_write_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET, + SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS); + } else if (kvm_riscv_nacl_sync_csr_available()) { + hcntx->hstatus = nacl_csr_swap(nsh, + CSR_HSTATUS, gcntx->hstatus); + } else { + hcntx->hstatus = csr_swap(CSR_HSTATUS, gcntx->hstatus); + } + + nacl_scratch_write_longs(nsh, + SBI_NACL_SHMEM_SRET_OFFSET + + SBI_NACL_SHMEM_SRET_X(1), + &gcntx->ra, + SBI_NACL_SHMEM_SRET_X_LAST); + + __kvm_riscv_nacl_switch_to(&vcpu->arch, SBI_EXT_NACL, + SBI_EXT_NACL_SYNC_SRET); + + if (kvm_riscv_nacl_autoswap_csr_available()) { + nacl_scratch_write_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET, + 0); + gcntx->hstatus = nacl_scratch_read_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET + + SBI_NACL_SHMEM_AUTOSWAP_HSTATUS); + } else { + gcntx->hstatus = csr_swap(CSR_HSTATUS, hcntx->hstatus); + } + + trap->htval = nacl_csr_read(nsh, CSR_HTVAL); + trap->htinst = nacl_csr_read(nsh, CSR_HTINST); + } else { + hcntx->hstatus = csr_swap(CSR_HSTATUS, gcntx->hstatus); + + __kvm_riscv_switch_to(&vcpu->arch); + + gcntx->hstatus = csr_swap(CSR_HSTATUS, hcntx->hstatus); + + trap->htval = csr_read(CSR_HTVAL); + trap->htinst = csr_read(CSR_HTINST); + } + + trap->sepc = gcntx->sepc; + trap->scause = csr_read(CSR_SCAUSE); + trap->stval = csr_read(CSR_STVAL); + vcpu->arch.last_exit_cpu = vcpu->cpu; guest_state_exit_irqoff(); kvm_riscv_vcpu_swap_in_host_state(vcpu); @@ -839,22 +972,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) guest_timing_enter_irqoff(); - kvm_riscv_vcpu_enter_exit(vcpu); + kvm_riscv_vcpu_enter_exit(vcpu, &trap); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; - /* - * Save SCAUSE, STVAL, HTVAL, and HTINST because we might - * get an interrupt between __kvm_riscv_switch_to() and - * local_irq_enable() which can potentially change CSRs. - */ - trap.sepc = vcpu->arch.guest_context.sepc; - trap.scause = csr_read(CSR_SCAUSE); - trap.stval = csr_read(CSR_STVAL); - trap.htval = csr_read(CSR_HTVAL); - trap.htinst = csr_read(CSR_HTINST); - /* Syncup interrupts state with HW */ kvm_riscv_vcpu_sync_interrupts(vcpu); diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index fa98e5c024b2..6e0c18412795 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -165,6 +165,17 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, vcpu->arch.guest_context.sstatus |= SR_SPP; } +static inline int vcpu_redirect(struct kvm_vcpu *vcpu, struct kvm_cpu_trap *trap) +{ + int ret = -EFAULT; + + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { + kvm_riscv_vcpu_trap_redirect(vcpu, trap); + ret = 1; + } + return ret; +} + /* * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on * proper exit to userspace. @@ -183,14 +194,32 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, run->exit_reason = KVM_EXIT_UNKNOWN; switch (trap->scause) { case EXC_INST_ILLEGAL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ILLEGAL_INSN); + vcpu->stat.instr_illegal_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_LOAD_MISALIGNED: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_MISALIGNED_LOAD); + vcpu->stat.load_misaligned_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_STORE_MISALIGNED: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_MISALIGNED_STORE); + vcpu->stat.store_misaligned_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_LOAD_ACCESS: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ACCESS_LOAD); + vcpu->stat.load_access_exits++; + ret = vcpu_redirect(vcpu, trap); + break; case EXC_STORE_ACCESS: - if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { - kvm_riscv_vcpu_trap_redirect(vcpu, trap); - ret = 1; - } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ACCESS_STORE); + vcpu->stat.store_access_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_INST_ACCESS: + ret = vcpu_redirect(vcpu, trap); break; case EXC_VIRTUAL_INST_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index b319c4c13c54..2e1b646f0d61 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -15,6 +15,7 @@ #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/kvm_vcpu_vector.h> +#include <asm/pgtable.h> #include <asm/vector.h> #define KVM_RISCV_BASE_ISA_MASK GENMASK(25, 0) @@ -34,14 +35,22 @@ static const unsigned long kvm_isa_ext_arr[] = { [KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m, [KVM_RISCV_ISA_EXT_V] = RISCV_ISA_EXT_v, /* Multi letter extensions (alphabetically sorted) */ + [KVM_RISCV_ISA_EXT_SMNPM] = RISCV_ISA_EXT_SSNPM, KVM_ISA_EXT_ARR(SMSTATEEN), KVM_ISA_EXT_ARR(SSAIA), KVM_ISA_EXT_ARR(SSCOFPMF), + KVM_ISA_EXT_ARR(SSNPM), KVM_ISA_EXT_ARR(SSTC), + KVM_ISA_EXT_ARR(SVADE), + KVM_ISA_EXT_ARR(SVADU), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(SVVPTC), + KVM_ISA_EXT_ARR(ZAAMO), + KVM_ISA_EXT_ARR(ZABHA), KVM_ISA_EXT_ARR(ZACAS), + KVM_ISA_EXT_ARR(ZALRSC), KVM_ISA_EXT_ARR(ZAWRS), KVM_ISA_EXT_ARR(ZBA), KVM_ISA_EXT_ARR(ZBB), @@ -60,6 +69,7 @@ static const unsigned long kvm_isa_ext_arr[] = { KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), KVM_ISA_EXT_ARR(ZICBOZ), + KVM_ISA_EXT_ARR(ZICCRSE), KVM_ISA_EXT_ARR(ZICNTR), KVM_ISA_EXT_ARR(ZICOND), KVM_ISA_EXT_ARR(ZICSR), @@ -110,6 +120,12 @@ static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_SSCOFPMF: /* Sscofpmf depends on interrupt filtering defined in ssaia */ return __riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSAIA); + case KVM_RISCV_ISA_EXT_SVADU: + /* + * The henvcfg.ADUE is read-only zero if menvcfg.ADUE is zero. + * Guest OS can use Svadu only when host OS enable Svadu. + */ + return arch_has_hw_pte_young(); case KVM_RISCV_ISA_EXT_V: return riscv_v_vstate_ctrl_user_allowed(); default: @@ -127,12 +143,18 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_C: case KVM_RISCV_ISA_EXT_I: case KVM_RISCV_ISA_EXT_M: + case KVM_RISCV_ISA_EXT_SMNPM: /* There is not architectural config bit to disable sscofpmf completely */ case KVM_RISCV_ISA_EXT_SSCOFPMF: + case KVM_RISCV_ISA_EXT_SSNPM: case KVM_RISCV_ISA_EXT_SSTC: case KVM_RISCV_ISA_EXT_SVINVAL: case KVM_RISCV_ISA_EXT_SVNAPOT: + case KVM_RISCV_ISA_EXT_SVVPTC: + case KVM_RISCV_ISA_EXT_ZAAMO: + case KVM_RISCV_ISA_EXT_ZABHA: case KVM_RISCV_ISA_EXT_ZACAS: + case KVM_RISCV_ISA_EXT_ZALRSC: case KVM_RISCV_ISA_EXT_ZAWRS: case KVM_RISCV_ISA_EXT_ZBA: case KVM_RISCV_ISA_EXT_ZBB: @@ -149,6 +171,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_ZFA: case KVM_RISCV_ISA_EXT_ZFH: case KVM_RISCV_ISA_EXT_ZFHMIN: + case KVM_RISCV_ISA_EXT_ZICCRSE: case KVM_RISCV_ISA_EXT_ZICNTR: case KVM_RISCV_ISA_EXT_ZICOND: case KVM_RISCV_ISA_EXT_ZICSR: @@ -181,6 +204,12 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) /* Extensions which can be disabled using Smstateen */ case KVM_RISCV_ISA_EXT_SSAIA: return riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN); + case KVM_RISCV_ISA_EXT_SVADE: + /* + * The henvcfg.ADUE is read-only zero if menvcfg.ADUE is zero. + * Svade can't be disabled unless we support Svadu. + */ + return arch_has_hw_pte_young(); default: break; } diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 2707a51b082c..78ac3216a54d 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -666,6 +666,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba .type = etype, .size = sizeof(struct perf_event_attr), .pinned = true, + .disabled = true, /* * It should never reach here if the platform doesn't support the sscofpmf * extension as mode filtering won't work without it. diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 7de128be8db9..6e09b518a5d1 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -71,6 +71,10 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = { .ext_ptr = &vcpu_sbi_ext_dbcn, }, { + .ext_idx = KVM_RISCV_SBI_EXT_SUSP, + .ext_ptr = &vcpu_sbi_ext_susp, + }, + { .ext_idx = KVM_RISCV_SBI_EXT_STA, .ext_ptr = &vcpu_sbi_ext_sta, }, @@ -139,9 +143,9 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_vcpu *tmp; kvm_for_each_vcpu(i, tmp, vcpu->kvm) { - spin_lock(&vcpu->arch.mp_state_lock); + spin_lock(&tmp->arch.mp_state_lock); WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); - spin_unlock(&vcpu->arch.mp_state_lock); + spin_unlock(&tmp->arch.mp_state_lock); } kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); @@ -152,6 +156,34 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1) +{ + spin_lock(&vcpu->arch.reset_state.lock); + vcpu->arch.reset_state.pc = pc; + vcpu->arch.reset_state.a1 = a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); +} + +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + struct kvm_vcpu_reset_state *reset_state = &vcpu->arch.reset_state; + + cntx->a0 = vcpu->vcpu_id; + + spin_lock(&vcpu->arch.reset_state.lock); + cntx->sepc = reset_state->pc; + cntx->a1 = reset_state->a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + cntx->sstatus &= ~SR_SIE; + csr->vsatp = 0; +} + int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -486,19 +518,22 @@ void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu) struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; const struct kvm_riscv_sbi_extension_entry *entry; const struct kvm_vcpu_sbi_extension *ext; - int i; + int idx, i; for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { entry = &sbi_ext[i]; ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; if (ext->probe && !ext->probe(vcpu)) { - scontext->ext_status[entry->ext_idx] = - KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE; + scontext->ext_status[idx] = KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE; continue; } - scontext->ext_status[entry->ext_idx] = ext->default_disabled ? + scontext->ext_status[idx] = ext->default_disabled ? KVM_RISCV_SBI_EXT_STATUS_DISABLED : KVM_RISCV_SBI_EXT_STATUS_ENABLED; } diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c index dce667f4b6ab..f26207f84bab 100644 --- a/arch/riscv/kvm/vcpu_sbi_hsm.c +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -9,12 +9,12 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/wordpart.h> #include <asm/sbi.h> #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) { - struct kvm_cpu_context *reset_cntx; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; struct kvm_vcpu *target_vcpu; unsigned long target_vcpuid = cp->a0; @@ -31,17 +31,7 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) goto out; } - spin_lock(&target_vcpu->arch.reset_cntx_lock); - reset_cntx = &target_vcpu->arch.guest_reset_context; - /* start address */ - reset_cntx->sepc = cp->a1; - /* target vcpu id to start */ - reset_cntx->a0 = target_vcpuid; - /* private data passed from kernel */ - reset_cntx->a1 = cp->a2; - spin_unlock(&target_vcpu->arch.reset_cntx_lock); - - kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu); + kvm_riscv_vcpu_sbi_request_reset(target_vcpu, cp->a1, cp->a2); __kvm_riscv_vcpu_power_on(target_vcpu); @@ -79,12 +69,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) return SBI_ERR_INVALID_PARAM; - if (!kvm_riscv_vcpu_stopped(target_vcpu)) - return SBI_HSM_STATE_STARTED; - else if (vcpu->stat.generic.blocking) + if (kvm_riscv_vcpu_stopped(target_vcpu)) + return SBI_HSM_STATE_STOPPED; + else if (target_vcpu->stat.generic.blocking) return SBI_HSM_STATE_SUSPENDED; else - return SBI_HSM_STATE_STOPPED; + return SBI_HSM_STATE_STARTED; } static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, @@ -109,7 +99,7 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, } return 0; case SBI_EXT_HSM_HART_SUSPEND: - switch (cp->a0) { + switch (lower_32_bits(cp->a0)) { case SBI_HSM_SUSPEND_RET_DEFAULT: kvm_riscv_vcpu_wfi(vcpu); break; diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index 9c2ab3dfa93a..b17fad091bab 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, u64 next_cycle; if (cp->a6 != SBI_EXT_TIME_SET_TIMER) { - retdata->err_val = SBI_ERR_INVALID_PARAM; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; return 0; } @@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; + unsigned long hart_bit = 0, sentmask = 0; if (cp->a6 != SBI_EXT_IPI_SEND_IPI) { - retdata->err_val = SBI_ERR_INVALID_PARAM; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; return 0; } @@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, if (hbase != -1UL) { if (tmp->vcpu_id < hbase) continue; - if (!(hmask & (1UL << (tmp->vcpu_id - hbase)))) + hart_bit = tmp->vcpu_id - hbase; + if (hart_bit >= __riscv_xlen) + goto done; + if (!(hmask & (1UL << hart_bit))) continue; } ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT); if (ret < 0) break; + sentmask |= 1UL << hart_bit; kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD); } +done: + if (hbase != -1UL && (hmask ^ sentmask)) + retdata->err_val = SBI_ERR_INVALID_PARAM; + return ret; } @@ -94,7 +103,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: - if (cp->a2 == 0 && cp->a3 == 0) + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask); else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, @@ -102,7 +111,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: - if (cp->a2 == 0 && cp->a3 == 0) + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, hbase, hmask, cp->a4); else @@ -118,9 +127,9 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: /* * Until nested virtualization is implemented, the - * SBI HFENCE calls should be treated as NOPs + * SBI HFENCE calls should return not supported + * hence fallthrough. */ - break; default: retdata->err_val = SBI_ERR_NOT_SUPPORTED; } diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c new file mode 100644 index 000000000000..359be90b0fc5 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_system.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#include <linux/kvm_host.h> +#include <linux/wordpart.h> + +#include <asm/kvm_vcpu_sbi.h> +#include <asm/sbi.h> + +static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + unsigned long hva, i; + struct kvm_vcpu *tmp; + + switch (funcid) { + case SBI_EXT_SUSP_SYSTEM_SUSPEND: + if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + if (!(cp->sstatus & SR_SPP)) { + retdata->err_val = SBI_ERR_FAILURE; + return 0; + } + + hva = kvm_vcpu_gfn_to_hva_prot(vcpu, cp->a1 >> PAGE_SHIFT, NULL); + if (kvm_is_error_hva(hva)) { + retdata->err_val = SBI_ERR_INVALID_ADDRESS; + return 0; + } + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (tmp == vcpu) + continue; + if (!kvm_riscv_vcpu_stopped(tmp)) { + retdata->err_val = SBI_ERR_DENIED; + return 0; + } + } + + kvm_riscv_vcpu_sbi_request_reset(vcpu, cp->a1, cp->a2); + + /* userspace provides the suspend implementation */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + retdata->uexit = true; + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + break; + } + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp = { + .extid_start = SBI_EXT_SUSP, + .extid_end = SBI_EXT_SUSP, + .default_disabled = true, + .handler = kvm_sbi_ext_susp_handler, +}; diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S index 0c26189aa01c..47686bcb21e0 100644 --- a/arch/riscv/kvm/vcpu_switch.S +++ b/arch/riscv/kvm/vcpu_switch.S @@ -11,11 +11,7 @@ #include <asm/asm-offsets.h> #include <asm/csr.h> - .text - .altmacro - .option norelax - -SYM_FUNC_START(__kvm_riscv_switch_to) +.macro SAVE_HOST_GPRS /* Save Host GPRs (except A0 and T0-T6) */ REG_S ra, (KVM_ARCH_HOST_RA)(a0) REG_S sp, (KVM_ARCH_HOST_SP)(a0) @@ -40,39 +36,33 @@ SYM_FUNC_START(__kvm_riscv_switch_to) REG_S s9, (KVM_ARCH_HOST_S9)(a0) REG_S s10, (KVM_ARCH_HOST_S10)(a0) REG_S s11, (KVM_ARCH_HOST_S11)(a0) +.endm +.macro SAVE_HOST_AND_RESTORE_GUEST_CSRS __resume_addr /* Load Guest CSR values */ REG_L t0, (KVM_ARCH_GUEST_SSTATUS)(a0) - REG_L t1, (KVM_ARCH_GUEST_HSTATUS)(a0) - REG_L t2, (KVM_ARCH_GUEST_SCOUNTEREN)(a0) - la t4, .Lkvm_switch_return - REG_L t5, (KVM_ARCH_GUEST_SEPC)(a0) + la t1, \__resume_addr + REG_L t2, (KVM_ARCH_GUEST_SEPC)(a0) /* Save Host and Restore Guest SSTATUS */ csrrw t0, CSR_SSTATUS, t0 - /* Save Host and Restore Guest HSTATUS */ - csrrw t1, CSR_HSTATUS, t1 - - /* Save Host and Restore Guest SCOUNTEREN */ - csrrw t2, CSR_SCOUNTEREN, t2 - /* Save Host STVEC and change it to return path */ - csrrw t4, CSR_STVEC, t4 + csrrw t1, CSR_STVEC, t1 + + /* Restore Guest SEPC */ + csrw CSR_SEPC, t2 /* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */ csrrw t3, CSR_SSCRATCH, a0 - /* Restore Guest SEPC */ - csrw CSR_SEPC, t5 - /* Store Host CSR values */ REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0) - REG_S t1, (KVM_ARCH_HOST_HSTATUS)(a0) - REG_S t2, (KVM_ARCH_HOST_SCOUNTEREN)(a0) + REG_S t1, (KVM_ARCH_HOST_STVEC)(a0) REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0) - REG_S t4, (KVM_ARCH_HOST_STVEC)(a0) +.endm +.macro RESTORE_GUEST_GPRS /* Restore Guest GPRs (except A0) */ REG_L ra, (KVM_ARCH_GUEST_RA)(a0) REG_L sp, (KVM_ARCH_GUEST_SP)(a0) @@ -107,13 +97,9 @@ SYM_FUNC_START(__kvm_riscv_switch_to) /* Restore Guest A0 */ REG_L a0, (KVM_ARCH_GUEST_A0)(a0) +.endm - /* Resume Guest */ - sret - - /* Back to Host */ - .align 2 -.Lkvm_switch_return: +.macro SAVE_GUEST_GPRS /* Swap Guest A0 with SSCRATCH */ csrrw a0, CSR_SSCRATCH, a0 @@ -148,39 +134,33 @@ SYM_FUNC_START(__kvm_riscv_switch_to) REG_S t4, (KVM_ARCH_GUEST_T4)(a0) REG_S t5, (KVM_ARCH_GUEST_T5)(a0) REG_S t6, (KVM_ARCH_GUEST_T6)(a0) +.endm +.macro SAVE_GUEST_AND_RESTORE_HOST_CSRS /* Load Host CSR values */ - REG_L t1, (KVM_ARCH_HOST_STVEC)(a0) - REG_L t2, (KVM_ARCH_HOST_SSCRATCH)(a0) - REG_L t3, (KVM_ARCH_HOST_SCOUNTEREN)(a0) - REG_L t4, (KVM_ARCH_HOST_HSTATUS)(a0) - REG_L t5, (KVM_ARCH_HOST_SSTATUS)(a0) - - /* Save Guest SEPC */ - csrr t0, CSR_SEPC + REG_L t0, (KVM_ARCH_HOST_STVEC)(a0) + REG_L t1, (KVM_ARCH_HOST_SSCRATCH)(a0) + REG_L t2, (KVM_ARCH_HOST_SSTATUS)(a0) /* Save Guest A0 and Restore Host SSCRATCH */ - csrrw t2, CSR_SSCRATCH, t2 + csrrw t1, CSR_SSCRATCH, t1 - /* Restore Host STVEC */ - csrw CSR_STVEC, t1 - - /* Save Guest and Restore Host SCOUNTEREN */ - csrrw t3, CSR_SCOUNTEREN, t3 + /* Save Guest SEPC */ + csrr t3, CSR_SEPC - /* Save Guest and Restore Host HSTATUS */ - csrrw t4, CSR_HSTATUS, t4 + /* Restore Host STVEC */ + csrw CSR_STVEC, t0 /* Save Guest and Restore Host SSTATUS */ - csrrw t5, CSR_SSTATUS, t5 + csrrw t2, CSR_SSTATUS, t2 /* Store Guest CSR values */ - REG_S t0, (KVM_ARCH_GUEST_SEPC)(a0) - REG_S t2, (KVM_ARCH_GUEST_A0)(a0) - REG_S t3, (KVM_ARCH_GUEST_SCOUNTEREN)(a0) - REG_S t4, (KVM_ARCH_GUEST_HSTATUS)(a0) - REG_S t5, (KVM_ARCH_GUEST_SSTATUS)(a0) + REG_S t1, (KVM_ARCH_GUEST_A0)(a0) + REG_S t2, (KVM_ARCH_GUEST_SSTATUS)(a0) + REG_S t3, (KVM_ARCH_GUEST_SEPC)(a0) +.endm +.macro RESTORE_HOST_GPRS /* Restore Host GPRs (except A0 and T0-T6) */ REG_L ra, (KVM_ARCH_HOST_RA)(a0) REG_L sp, (KVM_ARCH_HOST_SP)(a0) @@ -205,11 +185,68 @@ SYM_FUNC_START(__kvm_riscv_switch_to) REG_L s9, (KVM_ARCH_HOST_S9)(a0) REG_L s10, (KVM_ARCH_HOST_S10)(a0) REG_L s11, (KVM_ARCH_HOST_S11)(a0) +.endm + + .text + .altmacro + .option norelax + + /* + * Parameters: + * A0 <= Pointer to struct kvm_vcpu_arch + */ +SYM_FUNC_START(__kvm_riscv_switch_to) + SAVE_HOST_GPRS + + SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_switch_return + + RESTORE_GUEST_GPRS + + /* Resume Guest using SRET */ + sret + + /* Back to Host */ + .align 2 +.Lkvm_switch_return: + SAVE_GUEST_GPRS + + SAVE_GUEST_AND_RESTORE_HOST_CSRS + + RESTORE_HOST_GPRS /* Return to C code */ ret SYM_FUNC_END(__kvm_riscv_switch_to) + /* + * Parameters: + * A0 <= Pointer to struct kvm_vcpu_arch + * A1 <= SBI extension ID + * A2 <= SBI function ID + */ +SYM_FUNC_START(__kvm_riscv_nacl_switch_to) + SAVE_HOST_GPRS + + SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_nacl_switch_return + + /* Resume Guest using SBI nested acceleration */ + add a6, a2, zero + add a7, a1, zero + ecall + + /* Back to Host */ + .align 2 +.Lkvm_nacl_switch_return: + SAVE_GUEST_GPRS + + SAVE_GUEST_AND_RESTORE_HOST_CSRS + + RESTORE_HOST_GPRS + + /* Return to C code */ + ret +SYM_FUNC_END(__kvm_riscv_nacl_switch_to) + SYM_CODE_START(__kvm_riscv_unpriv_trap) /* * We assume that faulting unpriv load/store instruction is diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index 75486b25ac45..ff672fa71fcc 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -11,8 +11,8 @@ #include <linux/kvm_host.h> #include <linux/uaccess.h> #include <clocksource/timer-riscv.h> -#include <asm/csr.h> #include <asm/delay.h> +#include <asm/kvm_nacl.h> #include <asm/kvm_vcpu_timer.h> static u64 kvm_riscv_current_cycles(struct kvm_guest_timer *gt) @@ -72,12 +72,12 @@ static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t) static int kvm_riscv_vcpu_update_vstimecmp(struct kvm_vcpu *vcpu, u64 ncycles) { #if defined(CONFIG_32BIT) - csr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF); - csr_write(CSR_VSTIMECMPH, ncycles >> 32); + ncsr_write(CSR_VSTIMECMP, ncycles & 0xFFFFFFFF); + ncsr_write(CSR_VSTIMECMPH, ncycles >> 32); #else - csr_write(CSR_VSTIMECMP, ncycles); + ncsr_write(CSR_VSTIMECMP, ncycles); #endif - return 0; + return 0; } static int kvm_riscv_vcpu_update_hrtimer(struct kvm_vcpu *vcpu, u64 ncycles) @@ -248,18 +248,19 @@ int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu) if (t->init_done) return -EINVAL; - hrtimer_init(&t->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL); t->init_done = true; t->next_set = false; /* Enable sstc for every vcpu if available in hardware */ if (riscv_isa_extension_available(NULL, SSTC)) { t->sstc_enabled = true; - t->hrt.function = kvm_riscv_vcpu_vstimer_expired; + hrtimer_setup(&t->hrt, kvm_riscv_vcpu_vstimer_expired, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); t->timer_next_event = kvm_riscv_vcpu_update_vstimecmp; } else { t->sstc_enabled = false; - t->hrt.function = kvm_riscv_vcpu_hrtimer_expired; + hrtimer_setup(&t->hrt, kvm_riscv_vcpu_hrtimer_expired, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); t->timer_next_event = kvm_riscv_vcpu_update_hrtimer; } @@ -289,10 +290,10 @@ static void kvm_riscv_vcpu_update_timedelta(struct kvm_vcpu *vcpu) struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; #if defined(CONFIG_32BIT) - csr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta)); - csr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32)); + ncsr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta)); + ncsr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32)); #else - csr_write(CSR_HTIMEDELTA, gt->time_delta); + ncsr_write(CSR_HTIMEDELTA, gt->time_delta); #endif } @@ -306,10 +307,10 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu) return; #if defined(CONFIG_32BIT) - csr_write(CSR_VSTIMECMP, (u32)t->next_cycles); - csr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32)); + ncsr_write(CSR_VSTIMECMP, (u32)t->next_cycles); + ncsr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32)); #else - csr_write(CSR_VSTIMECMP, t->next_cycles); + ncsr_write(CSR_VSTIMECMP, t->next_cycles); #endif /* timer should be enabled for the remaining operations */ @@ -327,10 +328,10 @@ void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu) return; #if defined(CONFIG_32BIT) - t->next_cycles = csr_read(CSR_VSTIMECMP); - t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32; + t->next_cycles = ncsr_read(CSR_VSTIMECMP); + t->next_cycles |= (u64)ncsr_read(CSR_VSTIMECMPH) << 32; #else - t->next_cycles = csr_read(CSR_VSTIMECMP); + t->next_cycles = ncsr_read(CSR_VSTIMECMP); #endif } diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c index d92d1348045c..a5f88cb717f3 100644 --- a/arch/riscv/kvm/vcpu_vector.c +++ b/arch/riscv/kvm/vcpu_vector.c @@ -22,6 +22,9 @@ void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu) struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; cntx->sstatus &= ~SR_VS; + + cntx->vector.vlenb = riscv_v_vsize / 32; + if (riscv_isa_extension_available(isa, v)) { cntx->sstatus |= SR_VS_INITIAL; WARN_ON(!cntx->vector.datap); @@ -70,13 +73,11 @@ void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx) __kvm_riscv_vector_restore(cntx); } -int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx) +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) { - cntx->vector.datap = kmalloc(riscv_v_vsize, GFP_KERNEL); - if (!cntx->vector.datap) + vcpu->arch.guest_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL); + if (!vcpu->arch.guest_context.vector.datap) return -ENOMEM; - cntx->vector.vlenb = riscv_v_vsize / 32; vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL); if (!vcpu->arch.host_context.vector.datap) @@ -87,7 +88,7 @@ int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu) { - kfree(vcpu->arch.guest_reset_context.vector.datap); + kfree(vcpu->arch.guest_context.vector.datap); kfree(vcpu->arch.host_context.vector.datap); } #endif diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7396b8654f45..b27ec8f96697 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -209,6 +209,19 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) return r; } +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) +{ + switch (cap->cap) { + case KVM_CAP_RISCV_MP_STATE_RESET: + if (cap->flags) + return -EINVAL; + kvm->arch.mp_state_reset = true; + return 0; + default: + return -EINVAL; + } +} + int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -EINVAL; diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 8eec6b69a875..0baec92d2f55 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-y += crypto/ lib-y += delay.o lib-y += memcpy.o lib-y += memset.o @@ -15,8 +16,12 @@ endif lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o -lib-$(CONFIG_RISCV_ISA_ZBC) += crc32.o - +obj-$(CONFIG_CRC32_ARCH) += crc32-riscv.o +crc32-riscv-y := crc32.o crc32_msb.o crc32_lsb.o +obj-$(CONFIG_CRC64_ARCH) += crc64-riscv.o +crc64-riscv-y := crc64.o crc64_msb.o crc64_lsb.o +obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-riscv.o +crc-t10dif-riscv-y := crc-t10dif.o crc16_msb.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RISCV_ISA_V) += xor.o lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o diff --git a/arch/riscv/lib/crc-clmul-consts.h b/arch/riscv/lib/crc-clmul-consts.h new file mode 100644 index 000000000000..8d73449235ef --- /dev/null +++ b/arch/riscv/lib/crc-clmul-consts.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * CRC constants generated by: + * + * ./scripts/gen-crc-consts.py riscv_clmul crc16_msb_0x8bb7,crc32_msb_0x04c11db7,crc32_lsb_0xedb88320,crc32_lsb_0x82f63b78,crc64_msb_0x42f0e1eba9ea3693,crc64_lsb_0x9a6c9329ac4bc9b5 + * + * Do not edit manually. + */ + +struct crc_clmul_consts { + unsigned long fold_across_2_longs_const_hi; + unsigned long fold_across_2_longs_const_lo; + unsigned long barrett_reduction_const_1; + unsigned long barrett_reduction_const_2; +}; + +/* + * Constants generated for most-significant-bit-first CRC-16 using + * G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0 + */ +static const struct crc_clmul_consts crc16_msb_0x8bb7_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x0000000000001faa, /* x^192 mod G */ + .fold_across_2_longs_const_lo = 0x000000000000a010, /* x^128 mod G */ + .barrett_reduction_const_1 = 0xfb2d2bfc0e99d245, /* floor(x^79 / G) */ + .barrett_reduction_const_2 = 0x0000000000008bb7, /* G - x^16 */ +#else + .fold_across_2_longs_const_hi = 0x00005890, /* x^96 mod G */ + .fold_across_2_longs_const_lo = 0x0000f249, /* x^64 mod G */ + .barrett_reduction_const_1 = 0xfb2d2bfc, /* floor(x^47 / G) */ + .barrett_reduction_const_2 = 0x00008bb7, /* G - x^16 */ +#endif +}; + +/* + * Constants generated for most-significant-bit-first CRC-32 using + * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 + + * x^5 + x^4 + x^2 + x^1 + x^0 + */ +static const struct crc_clmul_consts crc32_msb_0x04c11db7_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x00000000c5b9cd4c, /* x^192 mod G */ + .fold_across_2_longs_const_lo = 0x00000000e8a45605, /* x^128 mod G */ + .barrett_reduction_const_1 = 0x826880efa40da72d, /* floor(x^95 / G) */ + .barrett_reduction_const_2 = 0x0000000004c11db7, /* G - x^32 */ +#else + .fold_across_2_longs_const_hi = 0xf200aa66, /* x^96 mod G */ + .fold_across_2_longs_const_lo = 0x490d678d, /* x^64 mod G */ + .barrett_reduction_const_1 = 0x826880ef, /* floor(x^63 / G) */ + .barrett_reduction_const_2 = 0x04c11db7, /* G - x^32 */ +#endif +}; + +/* + * Constants generated for least-significant-bit-first CRC-32 using + * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 + + * x^5 + x^4 + x^2 + x^1 + x^0 + */ +static const struct crc_clmul_consts crc32_lsb_0xedb88320_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x65673b4600000000, /* x^191 mod G */ + .fold_across_2_longs_const_lo = 0x9ba54c6f00000000, /* x^127 mod G */ + .barrett_reduction_const_1 = 0xb4e5b025f7011641, /* floor(x^95 / G) */ + .barrett_reduction_const_2 = 0x00000000edb88320, /* (G - x^32) * x^32 */ +#else + .fold_across_2_longs_const_hi = 0xccaa009e, /* x^95 mod G */ + .fold_across_2_longs_const_lo = 0xb8bc6765, /* x^63 mod G */ + .barrett_reduction_const_1 = 0xf7011641, /* floor(x^63 / G) */ + .barrett_reduction_const_2 = 0xedb88320, /* (G - x^32) * x^0 */ +#endif +}; + +/* + * Constants generated for least-significant-bit-first CRC-32 using + * G(x) = x^32 + x^28 + x^27 + x^26 + x^25 + x^23 + x^22 + x^20 + x^19 + x^18 + + * x^14 + x^13 + x^11 + x^10 + x^9 + x^8 + x^6 + x^0 + */ +static const struct crc_clmul_consts crc32_lsb_0x82f63b78_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x3743f7bd00000000, /* x^191 mod G */ + .fold_across_2_longs_const_lo = 0x3171d43000000000, /* x^127 mod G */ + .barrett_reduction_const_1 = 0x4869ec38dea713f1, /* floor(x^95 / G) */ + .barrett_reduction_const_2 = 0x0000000082f63b78, /* (G - x^32) * x^32 */ +#else + .fold_across_2_longs_const_hi = 0x493c7d27, /* x^95 mod G */ + .fold_across_2_longs_const_lo = 0xdd45aab8, /* x^63 mod G */ + .barrett_reduction_const_1 = 0xdea713f1, /* floor(x^63 / G) */ + .barrett_reduction_const_2 = 0x82f63b78, /* (G - x^32) * x^0 */ +#endif +}; + +/* + * Constants generated for most-significant-bit-first CRC-64 using + * G(x) = x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 + + * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 + + * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 + + * x^7 + x^4 + x^1 + x^0 + */ +#ifdef CONFIG_64BIT +static const struct crc_clmul_consts crc64_msb_0x42f0e1eba9ea3693_consts __maybe_unused = { + .fold_across_2_longs_const_hi = 0x4eb938a7d257740e, /* x^192 mod G */ + .fold_across_2_longs_const_lo = 0x05f5c3c7eb52fab6, /* x^128 mod G */ + .barrett_reduction_const_1 = 0xabc694e836627c39, /* floor(x^127 / G) */ + .barrett_reduction_const_2 = 0x42f0e1eba9ea3693, /* G - x^64 */ +}; +#endif + +/* + * Constants generated for least-significant-bit-first CRC-64 using + * G(x) = x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + + * x^47 + x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + + * x^26 + x^23 + x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + + * x^4 + x^3 + x^0 + */ +#ifdef CONFIG_64BIT +static const struct crc_clmul_consts crc64_lsb_0x9a6c9329ac4bc9b5_consts __maybe_unused = { + .fold_across_2_longs_const_hi = 0xeadc41fd2ba3d420, /* x^191 mod G */ + .fold_across_2_longs_const_lo = 0x21e9761e252621ac, /* x^127 mod G */ + .barrett_reduction_const_1 = 0x27ecfa329aef9f77, /* floor(x^127 / G) */ + .barrett_reduction_const_2 = 0x9a6c9329ac4bc9b5, /* (G - x^64) * x^0 */ +}; +#endif diff --git a/arch/riscv/lib/crc-clmul-template.h b/arch/riscv/lib/crc-clmul-template.h new file mode 100644 index 000000000000..77187e7f1762 --- /dev/null +++ b/arch/riscv/lib/crc-clmul-template.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2025 Google LLC */ + +/* + * This file is a "template" that generates a CRC function optimized using the + * RISC-V Zbc (scalar carryless multiplication) extension. The includer of this + * file must define the following parameters to specify the type of CRC: + * + * crc_t: the data type of the CRC, e.g. u32 for a 32-bit CRC + * LSB_CRC: 0 for a msb (most-significant-bit) first CRC, i.e. natural + * mapping between bits and polynomial coefficients + * 1 for a lsb (least-significant-bit) first CRC, i.e. reflected + * mapping between bits and polynomial coefficients + */ + +#include <asm/byteorder.h> +#include <linux/minmax.h> + +#define CRC_BITS (8 * sizeof(crc_t)) /* a.k.a. 'n' */ + +static inline unsigned long clmul(unsigned long a, unsigned long b) +{ + unsigned long res; + + asm(".option push\n" + ".option arch,+zbc\n" + "clmul %0, %1, %2\n" + ".option pop\n" + : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +static inline unsigned long clmulh(unsigned long a, unsigned long b) +{ + unsigned long res; + + asm(".option push\n" + ".option arch,+zbc\n" + "clmulh %0, %1, %2\n" + ".option pop\n" + : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +static inline unsigned long clmulr(unsigned long a, unsigned long b) +{ + unsigned long res; + + asm(".option push\n" + ".option arch,+zbc\n" + "clmulr %0, %1, %2\n" + ".option pop\n" + : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +/* + * crc_load_long() loads one "unsigned long" of aligned data bytes, producing a + * polynomial whose bit order matches the CRC's bit order. + */ +#ifdef CONFIG_64BIT +# if LSB_CRC +# define crc_load_long(x) le64_to_cpup(x) +# else +# define crc_load_long(x) be64_to_cpup(x) +# endif +#else +# if LSB_CRC +# define crc_load_long(x) le32_to_cpup(x) +# else +# define crc_load_long(x) be32_to_cpup(x) +# endif +#endif + +/* XOR @crc into the end of @msgpoly that represents the high-order terms. */ +static inline unsigned long +crc_clmul_prep(crc_t crc, unsigned long msgpoly) +{ +#if LSB_CRC + return msgpoly ^ crc; +#else + return msgpoly ^ ((unsigned long)crc << (BITS_PER_LONG - CRC_BITS)); +#endif +} + +/* + * Multiply the long-sized @msgpoly by x^n (a.k.a. x^CRC_BITS) and reduce it + * modulo the generator polynomial G. This gives the CRC of @msgpoly. + */ +static inline crc_t +crc_clmul_long(unsigned long msgpoly, const struct crc_clmul_consts *consts) +{ + unsigned long tmp; + + /* + * First step of Barrett reduction with integrated multiplication by + * x^n: calculate floor((msgpoly * x^n) / G). This is the value by + * which G needs to be multiplied to cancel out the x^n and higher terms + * of msgpoly * x^n. Do it using the following formula: + * + * msb-first: + * floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G)) / x^(BITS_PER_LONG-1)) + * lsb-first: + * floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G) * x) / x^BITS_PER_LONG) + * + * barrett_reduction_const_1 contains floor(x^(BITS_PER_LONG-1+n) / G), + * which fits a long exactly. Using any lower power of x there would + * not carry enough precision through the calculation, while using any + * higher power of x would require extra instructions to handle a wider + * multiplication. In the msb-first case, using this power of x results + * in needing a floored division by x^(BITS_PER_LONG-1), which matches + * what clmulr produces. In the lsb-first case, a factor of x gets + * implicitly introduced by each carryless multiplication (shown as + * '* x' above), and the floored division instead needs to be by + * x^BITS_PER_LONG which matches what clmul produces. + */ +#if LSB_CRC + tmp = clmul(msgpoly, consts->barrett_reduction_const_1); +#else + tmp = clmulr(msgpoly, consts->barrett_reduction_const_1); +#endif + + /* + * Second step of Barrett reduction: + * + * crc := (msgpoly * x^n) + (G * floor((msgpoly * x^n) / G)) + * + * This reduces (msgpoly * x^n) modulo G by adding the appropriate + * multiple of G to it. The result uses only the x^0..x^(n-1) terms. + * HOWEVER, since the unreduced value (msgpoly * x^n) is zero in those + * terms in the first place, it is more efficient to do the equivalent: + * + * crc := ((G - x^n) * floor((msgpoly * x^n) / G)) mod x^n + * + * In the lsb-first case further modify it to the following which avoids + * a shift, as the crc ends up in the physically low n bits from clmulr: + * + * product := ((G - x^n) * x^(BITS_PER_LONG - n)) * floor((msgpoly * x^n) / G) * x + * crc := floor(product / x^(BITS_PER_LONG + 1 - n)) mod x^n + * + * barrett_reduction_const_2 contains the constant multiplier (G - x^n) + * or (G - x^n) * x^(BITS_PER_LONG - n) from the formulas above. The + * cast of the result to crc_t is essential, as it applies the mod x^n! + */ +#if LSB_CRC + return clmulr(tmp, consts->barrett_reduction_const_2); +#else + return clmul(tmp, consts->barrett_reduction_const_2); +#endif +} + +/* Update @crc with the data from @msgpoly. */ +static inline crc_t +crc_clmul_update_long(crc_t crc, unsigned long msgpoly, + const struct crc_clmul_consts *consts) +{ + return crc_clmul_long(crc_clmul_prep(crc, msgpoly), consts); +} + +/* Update @crc with 1 <= @len < sizeof(unsigned long) bytes of data. */ +static inline crc_t +crc_clmul_update_partial(crc_t crc, const u8 *p, size_t len, + const struct crc_clmul_consts *consts) +{ + unsigned long msgpoly; + size_t i; + +#if LSB_CRC + msgpoly = (unsigned long)p[0] << (BITS_PER_LONG - 8); + for (i = 1; i < len; i++) + msgpoly = (msgpoly >> 8) ^ ((unsigned long)p[i] << (BITS_PER_LONG - 8)); +#else + msgpoly = p[0]; + for (i = 1; i < len; i++) + msgpoly = (msgpoly << 8) ^ p[i]; +#endif + + if (len >= sizeof(crc_t)) { + #if LSB_CRC + msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len); + #else + msgpoly ^= (unsigned long)crc << (8*len - CRC_BITS); + #endif + return crc_clmul_long(msgpoly, consts); + } +#if LSB_CRC + msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len); + return crc_clmul_long(msgpoly, consts) ^ (crc >> (8*len)); +#else + msgpoly ^= crc >> (CRC_BITS - 8*len); + return crc_clmul_long(msgpoly, consts) ^ (crc << (8*len)); +#endif +} + +static inline crc_t +crc_clmul(crc_t crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + size_t align; + + /* This implementation assumes that the CRC fits in an unsigned long. */ + BUILD_BUG_ON(sizeof(crc_t) > sizeof(unsigned long)); + + /* If the buffer is not long-aligned, align it. */ + align = (unsigned long)p % sizeof(unsigned long); + if (align && len) { + align = min(sizeof(unsigned long) - align, len); + crc = crc_clmul_update_partial(crc, p, align, consts); + p += align; + len -= align; + } + + if (len >= 4 * sizeof(unsigned long)) { + unsigned long m0, m1; + + m0 = crc_clmul_prep(crc, crc_load_long(p)); + m1 = crc_load_long(p + sizeof(unsigned long)); + p += 2 * sizeof(unsigned long); + len -= 2 * sizeof(unsigned long); + /* + * Main loop. Each iteration starts with a message polynomial + * (x^BITS_PER_LONG)*m0 + m1, then logically extends it by two + * more longs of data to form x^(3*BITS_PER_LONG)*m0 + + * x^(2*BITS_PER_LONG)*m1 + x^BITS_PER_LONG*m2 + m3, then + * "folds" that back into a congruent (modulo G) value that uses + * just m0 and m1 again. This is done by multiplying m0 by the + * precomputed constant (x^(3*BITS_PER_LONG) mod G) and m1 by + * the precomputed constant (x^(2*BITS_PER_LONG) mod G), then + * adding the results to m2 and m3 as appropriate. Each such + * multiplication produces a result twice the length of a long, + * which in RISC-V is two instructions clmul and clmulh. + * + * This could be changed to fold across more than 2 longs at a + * time if there is a CPU that can take advantage of it. + */ + do { + unsigned long p0, p1, p2, p3; + + p0 = clmulh(m0, consts->fold_across_2_longs_const_hi); + p1 = clmul(m0, consts->fold_across_2_longs_const_hi); + p2 = clmulh(m1, consts->fold_across_2_longs_const_lo); + p3 = clmul(m1, consts->fold_across_2_longs_const_lo); + m0 = (LSB_CRC ? p1 ^ p3 : p0 ^ p2) ^ crc_load_long(p); + m1 = (LSB_CRC ? p0 ^ p2 : p1 ^ p3) ^ + crc_load_long(p + sizeof(unsigned long)); + + p += 2 * sizeof(unsigned long); + len -= 2 * sizeof(unsigned long); + } while (len >= 2 * sizeof(unsigned long)); + + crc = crc_clmul_long(m0, consts); + crc = crc_clmul_update_long(crc, m1, consts); + } + + while (len >= sizeof(unsigned long)) { + crc = crc_clmul_update_long(crc, crc_load_long(p), consts); + p += sizeof(unsigned long); + len -= sizeof(unsigned long); + } + + if (len) + crc = crc_clmul_update_partial(crc, p, len, consts); + + return crc; +} diff --git a/arch/riscv/lib/crc-clmul.h b/arch/riscv/lib/crc-clmul.h new file mode 100644 index 000000000000..dd1736245815 --- /dev/null +++ b/arch/riscv/lib/crc-clmul.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2025 Google LLC */ + +#ifndef _RISCV_CRC_CLMUL_H +#define _RISCV_CRC_CLMUL_H + +#include <linux/types.h> +#include "crc-clmul-consts.h" + +u16 crc16_msb_clmul(u16 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +u32 crc32_msb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +#ifdef CONFIG_64BIT +u64 crc64_msb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +#endif + +#endif /* _RISCV_CRC_CLMUL_H */ diff --git a/arch/riscv/lib/crc-t10dif.c b/arch/riscv/lib/crc-t10dif.c new file mode 100644 index 000000000000..e6b0051ccd86 --- /dev/null +++ b/arch/riscv/lib/crc-t10dif.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized CRC-T10DIF function + * + * Copyright 2025 Google LLC + */ + +#include <asm/hwcap.h> +#include <asm/alternative-macros.h> +#include <linux/crc-t10dif.h> +#include <linux/module.h> + +#include "crc-clmul.h" + +u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc16_msb_clmul(crc, p, len, &crc16_msb_0x8bb7_consts); + return crc_t10dif_generic(crc, p, len); +} +EXPORT_SYMBOL(crc_t10dif_arch); + +MODULE_DESCRIPTION("RISC-V optimized CRC-T10DIF function"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc16_msb.c b/arch/riscv/lib/crc16_msb.c new file mode 100644 index 000000000000..554d295e95f5 --- /dev/null +++ b/arch/riscv/lib/crc16_msb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized most-significant-bit-first CRC16 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u16 crc_t; +#define LSB_CRC 0 +#include "crc-clmul-template.h" + +u16 crc16_msb_clmul(u16 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc32.c b/arch/riscv/lib/crc32.c index d7dc599af3ef..a3188b7d9c40 100644 --- a/arch/riscv/lib/crc32.c +++ b/arch/riscv/lib/crc32.c @@ -1,294 +1,53 @@ -// SPDX-License-Identifier: GPL-2.0-only +// SPDX-License-Identifier: GPL-2.0-or-later /* - * Accelerated CRC32 implementation with Zbc extension. + * RISC-V optimized CRC32 functions * - * Copyright (C) 2024 Intel Corporation + * Copyright 2025 Google LLC */ #include <asm/hwcap.h> #include <asm/alternative-macros.h> -#include <asm/byteorder.h> - -#include <linux/types.h> -#include <linux/minmax.h> -#include <linux/crc32poly.h> #include <linux/crc32.h> -#include <linux/byteorder/generic.h> - -/* - * Refer to https://www.corsix.org/content/barrett-reduction-polynomials for - * better understanding of how this math works. - * - * let "+" denotes polynomial add (XOR) - * let "-" denotes polynomial sub (XOR) - * let "*" denotes polynomial multiplication - * let "/" denotes polynomial floor division - * let "S" denotes source data, XLEN bit wide - * let "P" denotes CRC32 polynomial - * let "T" denotes 2^(XLEN+32) - * let "QT" denotes quotient of T/P, with the bit for 2^XLEN being implicit - * - * crc32(S, P) - * => S * (2^32) - S * (2^32) / P * P - * => lowest 32 bits of: S * (2^32) / P * P - * => lowest 32 bits of: S * (2^32) * (T / P) / T * P - * => lowest 32 bits of: S * (2^32) * quotient / T * P - * => lowest 32 bits of: S * quotient / 2^XLEN * P - * => lowest 32 bits of: (clmul_high_part(S, QT) + S) * P - * => clmul_low_part(clmul_high_part(S, QT) + S, P) - * - * In terms of below implementations, the BE case is more intuitive, since the - * higher order bit sits at more significant position. - */ - -#if __riscv_xlen == 64 -/* Slide by XLEN bits per iteration */ -# define STEP_ORDER 3 - -/* Each below polynomial quotient has an implicit bit for 2^XLEN */ +#include <linux/module.h> -/* Polynomial quotient of (2^(XLEN+32))/CRC32_POLY, in LE format */ -# define CRC32_POLY_QT_LE 0x5a72d812fb808b20 +#include "crc-clmul.h" -/* Polynomial quotient of (2^(XLEN+32))/CRC32C_POLY, in LE format */ -# define CRC32C_POLY_QT_LE 0xa434f61c6f5389f8 - -/* Polynomial quotient of (2^(XLEN+32))/CRC32_POLY, in BE format, it should be - * the same as the bit-reversed version of CRC32_POLY_QT_LE - */ -# define CRC32_POLY_QT_BE 0x04d101df481b4e5a - -static inline u64 crc32_le_prep(u32 crc, unsigned long const *ptr) +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) { - return (u64)crc ^ (__force u64)__cpu_to_le64(*ptr); + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc32_lsb_clmul(crc, p, len, + &crc32_lsb_0xedb88320_consts); + return crc32_le_base(crc, p, len); } +EXPORT_SYMBOL(crc32_le_arch); -static inline u32 crc32_le_zbc(unsigned long s, u32 poly, unsigned long poly_qt) +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) { - u32 crc; - - /* We don't have a "clmulrh" insn, so use clmul + slli instead. */ - asm volatile (".option push\n" - ".option arch,+zbc\n" - "clmul %0, %1, %2\n" - "slli %0, %0, 1\n" - "xor %0, %0, %1\n" - "clmulr %0, %0, %3\n" - "srli %0, %0, 32\n" - ".option pop\n" - : "=&r" (crc) - : "r" (s), - "r" (poly_qt), - "r" ((u64)poly << 32) - :); - return crc; -} - -static inline u64 crc32_be_prep(u32 crc, unsigned long const *ptr) -{ - return ((u64)crc << 32) ^ (__force u64)__cpu_to_be64(*ptr); -} - -#elif __riscv_xlen == 32 -# define STEP_ORDER 2 -/* Each quotient should match the upper half of its analog in RV64 */ -# define CRC32_POLY_QT_LE 0xfb808b20 -# define CRC32C_POLY_QT_LE 0x6f5389f8 -# define CRC32_POLY_QT_BE 0x04d101df - -static inline u32 crc32_le_prep(u32 crc, unsigned long const *ptr) -{ - return crc ^ (__force u32)__cpu_to_le32(*ptr); -} - -static inline u32 crc32_le_zbc(unsigned long s, u32 poly, unsigned long poly_qt) -{ - u32 crc; - - /* We don't have a "clmulrh" insn, so use clmul + slli instead. */ - asm volatile (".option push\n" - ".option arch,+zbc\n" - "clmul %0, %1, %2\n" - "slli %0, %0, 1\n" - "xor %0, %0, %1\n" - "clmulr %0, %0, %3\n" - ".option pop\n" - : "=&r" (crc) - : "r" (s), - "r" (poly_qt), - "r" (poly) - :); - return crc; -} - -static inline u32 crc32_be_prep(u32 crc, unsigned long const *ptr) -{ - return crc ^ (__force u32)__cpu_to_be32(*ptr); -} - -#else -# error "Unexpected __riscv_xlen" -#endif - -static inline u32 crc32_be_zbc(unsigned long s) -{ - u32 crc; - - asm volatile (".option push\n" - ".option arch,+zbc\n" - "clmulh %0, %1, %2\n" - "xor %0, %0, %1\n" - "clmul %0, %0, %3\n" - ".option pop\n" - : "=&r" (crc) - : "r" (s), - "r" (CRC32_POLY_QT_BE), - "r" (CRC32_POLY_BE) - :); - return crc; -} - -#define STEP (1 << STEP_ORDER) -#define OFFSET_MASK (STEP - 1) - -typedef u32 (*fallback)(u32 crc, unsigned char const *p, size_t len); - -static inline u32 crc32_le_unaligned(u32 crc, unsigned char const *p, - size_t len, u32 poly, - unsigned long poly_qt) -{ - size_t bits = len * 8; - unsigned long s = 0; - u32 crc_low = 0; - - for (int i = 0; i < len; i++) - s = ((unsigned long)*p++ << (__riscv_xlen - 8)) | (s >> 8); - - s ^= (unsigned long)crc << (__riscv_xlen - bits); - if (__riscv_xlen == 32 || len < sizeof(u32)) - crc_low = crc >> bits; - - crc = crc32_le_zbc(s, poly, poly_qt); - crc ^= crc_low; - - return crc; -} - -static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, - size_t len, u32 poly, - unsigned long poly_qt, - fallback crc_fb) -{ - size_t offset, head_len, tail_len; - unsigned long const *p_ul; - unsigned long s; - - asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, - RISCV_ISA_EXT_ZBC, 1) - : : : : legacy); - - /* Handle the unaligned head. */ - offset = (unsigned long)p & OFFSET_MASK; - if (offset && len) { - head_len = min(STEP - offset, len); - crc = crc32_le_unaligned(crc, p, head_len, poly, poly_qt); - p += head_len; - len -= head_len; - } - - tail_len = len & OFFSET_MASK; - len = len >> STEP_ORDER; - p_ul = (unsigned long const *)p; - - for (int i = 0; i < len; i++) { - s = crc32_le_prep(crc, p_ul); - crc = crc32_le_zbc(s, poly, poly_qt); - p_ul++; - } - - /* Handle the tail bytes. */ - p = (unsigned char const *)p_ul; - if (tail_len) - crc = crc32_le_unaligned(crc, p, tail_len, poly, poly_qt); - - return crc; - -legacy: - return crc_fb(crc, p, len); -} - -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, CRC32_POLY_LE, CRC32_POLY_QT_LE, - crc32_le_base); + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc32_msb_clmul(crc, p, len, + &crc32_msb_0x04c11db7_consts); + return crc32_be_base(crc, p, len); } +EXPORT_SYMBOL(crc32_be_arch); -u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) +u32 crc32c_arch(u32 crc, const u8 *p, size_t len) { - return crc32_le_generic(crc, p, len, CRC32C_POLY_LE, - CRC32C_POLY_QT_LE, __crc32c_le_base); + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc32_lsb_clmul(crc, p, len, + &crc32_lsb_0x82f63b78_consts); + return crc32c_base(crc, p, len); } +EXPORT_SYMBOL(crc32c_arch); -static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p, - size_t len) +u32 crc32_optimizations(void) { - size_t bits = len * 8; - unsigned long s = 0; - u32 crc_low = 0; - - s = 0; - for (int i = 0; i < len; i++) - s = *p++ | (s << 8); - - if (__riscv_xlen == 32 || len < sizeof(u32)) { - s ^= crc >> (32 - bits); - crc_low = crc << bits; - } else { - s ^= (unsigned long)crc << (bits - 32); - } - - crc = crc32_be_zbc(s); - crc ^= crc_low; - - return crc; + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; } +EXPORT_SYMBOL(crc32_optimizations); -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len) -{ - size_t offset, head_len, tail_len; - unsigned long const *p_ul; - unsigned long s; - - asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, - RISCV_ISA_EXT_ZBC, 1) - : : : : legacy); - - /* Handle the unaligned head. */ - offset = (unsigned long)p & OFFSET_MASK; - if (offset && len) { - head_len = min(STEP - offset, len); - crc = crc32_be_unaligned(crc, p, head_len); - p += head_len; - len -= head_len; - } - - tail_len = len & OFFSET_MASK; - len = len >> STEP_ORDER; - p_ul = (unsigned long const *)p; - - for (int i = 0; i < len; i++) { - s = crc32_be_prep(crc, p_ul); - crc = crc32_be_zbc(s); - p_ul++; - } - - /* Handle the tail bytes. */ - p = (unsigned char const *)p_ul; - if (tail_len) - crc = crc32_be_unaligned(crc, p, tail_len); - - return crc; - -legacy: - return crc32_be_base(crc, p, len); -} +MODULE_DESCRIPTION("RISC-V optimized CRC32 functions"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc32_lsb.c b/arch/riscv/lib/crc32_lsb.c new file mode 100644 index 000000000000..72fd67e7470c --- /dev/null +++ b/arch/riscv/lib/crc32_lsb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized least-significant-bit-first CRC32 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u32 crc_t; +#define LSB_CRC 1 +#include "crc-clmul-template.h" + +u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc32_msb.c b/arch/riscv/lib/crc32_msb.c new file mode 100644 index 000000000000..fdbeaccc369f --- /dev/null +++ b/arch/riscv/lib/crc32_msb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized most-significant-bit-first CRC32 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u32 crc_t; +#define LSB_CRC 0 +#include "crc-clmul-template.h" + +u32 crc32_msb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc64.c b/arch/riscv/lib/crc64.c new file mode 100644 index 000000000000..f0015a27836a --- /dev/null +++ b/arch/riscv/lib/crc64.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized CRC64 functions + * + * Copyright 2025 Google LLC + */ + +#include <asm/hwcap.h> +#include <asm/alternative-macros.h> +#include <linux/crc64.h> +#include <linux/module.h> + +#include "crc-clmul.h" + +u64 crc64_be_arch(u64 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc64_msb_clmul(crc, p, len, + &crc64_msb_0x42f0e1eba9ea3693_consts); + return crc64_be_generic(crc, p, len); +} +EXPORT_SYMBOL(crc64_be_arch); + +u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc64_lsb_clmul(crc, p, len, + &crc64_lsb_0x9a6c9329ac4bc9b5_consts); + return crc64_nvme_generic(crc, p, len); +} +EXPORT_SYMBOL(crc64_nvme_arch); + +MODULE_DESCRIPTION("RISC-V optimized CRC64 functions"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc64_lsb.c b/arch/riscv/lib/crc64_lsb.c new file mode 100644 index 000000000000..c5371bb85d90 --- /dev/null +++ b/arch/riscv/lib/crc64_lsb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized least-significant-bit-first CRC64 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u64 crc_t; +#define LSB_CRC 1 +#include "crc-clmul-template.h" + +u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc64_msb.c b/arch/riscv/lib/crc64_msb.c new file mode 100644 index 000000000000..1925d1dbe225 --- /dev/null +++ b/arch/riscv/lib/crc64_msb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized most-significant-bit-first CRC64 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u64 crc_t; +#define LSB_CRC 0 +#include "crc-clmul-template.h" + +u64 crc64_msb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crypto/Kconfig b/arch/riscv/lib/crypto/Kconfig new file mode 100644 index 000000000000..47c99ea97ce2 --- /dev/null +++ b/arch/riscv/lib/crypto/Kconfig @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config CRYPTO_CHACHA_RISCV64 + tristate + depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default CRYPTO_LIB_CHACHA + select CRYPTO_ARCH_HAVE_LIB_CHACHA + select CRYPTO_LIB_CHACHA_GENERIC + +config CRYPTO_SHA256_RISCV64 + tristate + depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default CRYPTO_LIB_SHA256 + select CRYPTO_ARCH_HAVE_LIB_SHA256 + select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD + select CRYPTO_LIB_SHA256_GENERIC diff --git a/arch/riscv/lib/crypto/Makefile b/arch/riscv/lib/crypto/Makefile new file mode 100644 index 000000000000..b7cb877a2c07 --- /dev/null +++ b/arch/riscv/lib/crypto/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_CRYPTO_CHACHA_RISCV64) += chacha-riscv64.o +chacha-riscv64-y := chacha-riscv64-glue.o chacha-riscv64-zvkb.o + +obj-$(CONFIG_CRYPTO_SHA256_RISCV64) += sha256-riscv64.o +sha256-riscv64-y := sha256.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o diff --git a/arch/riscv/lib/crypto/chacha-riscv64-glue.c b/arch/riscv/lib/crypto/chacha-riscv64-glue.c new file mode 100644 index 000000000000..8c3f11d79be3 --- /dev/null +++ b/arch/riscv/lib/crypto/chacha-riscv64-glue.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ChaCha stream cipher (RISC-V optimized) + * + * Copyright (C) 2023 SiFive, Inc. + * Author: Jerry Shih <jerry.shih@sifive.com> + */ + +#include <asm/simd.h> +#include <asm/vector.h> +#include <crypto/chacha.h> +#include <crypto/internal/simd.h> +#include <linux/linkage.h> +#include <linux/module.h> + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_zvkb); + +asmlinkage void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out, + size_t nblocks, int nrounds); + +void hchacha_block_arch(const struct chacha_state *state, + u32 out[HCHACHA_OUT_WORDS], int nrounds) +{ + hchacha_block_generic(state, out, nrounds); +} +EXPORT_SYMBOL(hchacha_block_arch); + +void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) +{ + u8 block_buffer[CHACHA_BLOCK_SIZE]; + unsigned int full_blocks = bytes / CHACHA_BLOCK_SIZE; + unsigned int tail_bytes = bytes % CHACHA_BLOCK_SIZE; + + if (!static_branch_likely(&use_zvkb) || !crypto_simd_usable()) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + + kernel_vector_begin(); + if (full_blocks) { + chacha_zvkb(state, src, dst, full_blocks, nrounds); + src += full_blocks * CHACHA_BLOCK_SIZE; + dst += full_blocks * CHACHA_BLOCK_SIZE; + } + if (tail_bytes) { + memcpy(block_buffer, src, tail_bytes); + chacha_zvkb(state, block_buffer, block_buffer, 1, nrounds); + memcpy(dst, block_buffer, tail_bytes); + } + kernel_vector_end(); +} +EXPORT_SYMBOL(chacha_crypt_arch); + +bool chacha_is_arch_optimized(void) +{ + return static_key_enabled(&use_zvkb); +} +EXPORT_SYMBOL(chacha_is_arch_optimized); + +static int __init riscv64_chacha_mod_init(void) +{ + if (riscv_isa_extension_available(NULL, ZVKB) && + riscv_vector_vlen() >= 128) + static_branch_enable(&use_zvkb); + return 0; +} +subsys_initcall(riscv64_chacha_mod_init); + +static void __exit riscv64_chacha_mod_exit(void) +{ +} +module_exit(riscv64_chacha_mod_exit); + +MODULE_DESCRIPTION("ChaCha stream cipher (RISC-V optimized)"); +MODULE_AUTHOR("Jerry Shih <jerry.shih@sifive.com>"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/crypto/chacha-riscv64-zvkb.S b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S index bf057737ac69..b777d0b4e379 100644 --- a/arch/riscv/crypto/chacha-riscv64-zvkb.S +++ b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S @@ -46,11 +46,11 @@ .text .option arch, +zvkb -#define KEYP a0 +#define STATEP a0 #define INP a1 #define OUTP a2 -#define LEN a3 -#define IVP a4 +#define NBLOCKS a3 +#define NROUNDS a4 #define CONSTS0 a5 #define CONSTS1 a6 @@ -59,7 +59,7 @@ #define TMP t1 #define VL t2 #define STRIDE t3 -#define NROUNDS t4 +#define ROUND_CTR t4 #define KEY0 s0 #define KEY1 s1 #define KEY2 s2 @@ -132,14 +132,16 @@ vror.vi \b3, \b3, 32 - 7 .endm -// void chacha20_zvkb(const u32 key[8], const u8 *in, u8 *out, size_t len, -// const u32 iv[4]); +// void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out, +// size_t nblocks, int nrounds); // -// |len| must be nonzero and a multiple of 64 (CHACHA_BLOCK_SIZE). -// The counter is treated as 32-bit, following the RFC7539 convention. -SYM_FUNC_START(chacha20_zvkb) - srli LEN, LEN, 6 // Bytes to blocks - +// |nblocks| is the number of 64-byte blocks to process, and must be nonzero. +// +// |state| gives the ChaCha state matrix, including the 32-bit counter in +// state->x[12] following the RFC7539 convention; note that this differs from +// the original Salsa20 paper which uses a 64-bit counter in state->x[12..13]. +// The updated 32-bit counter is written back to state->x[12] before returning. +SYM_FUNC_START(chacha_zvkb) addi sp, sp, -96 sd s0, 0(sp) sd s1, 8(sp) @@ -157,26 +159,26 @@ SYM_FUNC_START(chacha20_zvkb) li STRIDE, 64 // Set up the initial state matrix in scalar registers. - li CONSTS0, 0x61707865 // "expa" little endian - li CONSTS1, 0x3320646e // "nd 3" little endian - li CONSTS2, 0x79622d32 // "2-by" little endian - li CONSTS3, 0x6b206574 // "te k" little endian - lw KEY0, 0(KEYP) - lw KEY1, 4(KEYP) - lw KEY2, 8(KEYP) - lw KEY3, 12(KEYP) - lw KEY4, 16(KEYP) - lw KEY5, 20(KEYP) - lw KEY6, 24(KEYP) - lw KEY7, 28(KEYP) - lw COUNTER, 0(IVP) - lw NONCE0, 4(IVP) - lw NONCE1, 8(IVP) - lw NONCE2, 12(IVP) + lw CONSTS0, 0(STATEP) + lw CONSTS1, 4(STATEP) + lw CONSTS2, 8(STATEP) + lw CONSTS3, 12(STATEP) + lw KEY0, 16(STATEP) + lw KEY1, 20(STATEP) + lw KEY2, 24(STATEP) + lw KEY3, 28(STATEP) + lw KEY4, 32(STATEP) + lw KEY5, 36(STATEP) + lw KEY6, 40(STATEP) + lw KEY7, 44(STATEP) + lw COUNTER, 48(STATEP) + lw NONCE0, 52(STATEP) + lw NONCE1, 56(STATEP) + lw NONCE2, 60(STATEP) .Lblock_loop: // Set vl to the number of blocks to process in this iteration. - vsetvli VL, LEN, e32, m1, ta, ma + vsetvli VL, NBLOCKS, e32, m1, ta, ma // Set up the initial state matrix for the next VL blocks in v0-v15. // v{i} holds the i'th 32-bit word of the state matrix for all blocks. @@ -203,16 +205,16 @@ SYM_FUNC_START(chacha20_zvkb) // v{16+i} holds the i'th 32-bit word for all blocks. vlsseg8e32.v v16, (INP), STRIDE - li NROUNDS, 20 + mv ROUND_CTR, NROUNDS .Lnext_doubleround: - addi NROUNDS, NROUNDS, -2 + addi ROUND_CTR, ROUND_CTR, -2 // column round chacha_round v0, v4, v8, v12, v1, v5, v9, v13, \ v2, v6, v10, v14, v3, v7, v11, v15 // diagonal round chacha_round v0, v5, v10, v15, v1, v6, v11, v12, \ v2, v7, v8, v13, v3, v4, v9, v14 - bnez NROUNDS, .Lnext_doubleround + bnez ROUND_CTR, .Lnext_doubleround // Load the second half of the input data for each block into v24-v31. // v{24+i} holds the {8+i}'th 32-bit word for all blocks. @@ -271,12 +273,13 @@ SYM_FUNC_START(chacha20_zvkb) // Update the counter, the remaining number of blocks, and the input and // output pointers according to the number of blocks processed (VL). add COUNTER, COUNTER, VL - sub LEN, LEN, VL + sub NBLOCKS, NBLOCKS, VL slli TMP, VL, 6 add OUTP, OUTP, TMP add INP, INP, TMP - bnez LEN, .Lblock_loop + bnez NBLOCKS, .Lblock_loop + sw COUNTER, 48(STATEP) ld s0, 0(sp) ld s1, 8(sp) ld s2, 16(sp) @@ -291,4 +294,4 @@ SYM_FUNC_START(chacha20_zvkb) ld s11, 88(sp) addi sp, sp, 96 ret -SYM_FUNC_END(chacha20_zvkb) +SYM_FUNC_END(chacha_zvkb) diff --git a/arch/riscv/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S index 8ebcc17de4dc..fad501ad0617 100644 --- a/arch/riscv/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S +++ b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S @@ -43,7 +43,7 @@ // - RISC-V Vector SHA-2 Secure Hash extension ('Zvknha' or 'Zvknhb') // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') -#include <linux/cfi_types.h> +#include <linux/linkage.h> .text .option arch, +zvknha, +zvkb @@ -106,9 +106,9 @@ sha256_4rounds \last, \k3, W3, W0, W1, W2 .endm -// void sha256_transform_zvknha_or_zvknhb_zvkb(u32 state[8], const u8 *data, -// int num_blocks); -SYM_TYPED_FUNC_START(sha256_transform_zvknha_or_zvknhb_zvkb) +// void sha256_transform_zvknha_or_zvknhb_zvkb(u32 state[SHA256_STATE_WORDS], +// const u8 *data, size_t nblocks); +SYM_FUNC_START(sha256_transform_zvknha_or_zvknhb_zvkb) // Load the round constants into K0-K15. vsetivli zero, 4, e32, m1, ta, ma diff --git a/arch/riscv/lib/crypto/sha256.c b/arch/riscv/lib/crypto/sha256.c new file mode 100644 index 000000000000..71808397dff4 --- /dev/null +++ b/arch/riscv/lib/crypto/sha256.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * SHA-256 (RISC-V accelerated) + * + * Copyright (C) 2022 VRULL GmbH + * Author: Heiko Stuebner <heiko.stuebner@vrull.eu> + * + * Copyright (C) 2023 SiFive, Inc. + * Author: Jerry Shih <jerry.shih@sifive.com> + */ + +#include <asm/vector.h> +#include <crypto/internal/sha2.h> +#include <linux/kernel.h> +#include <linux/module.h> + +asmlinkage void sha256_transform_zvknha_or_zvknhb_zvkb( + u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_extensions); + +void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks) +{ + if (static_branch_likely(&have_extensions)) { + kernel_vector_begin(); + sha256_transform_zvknha_or_zvknhb_zvkb(state, data, nblocks); + kernel_vector_end(); + } else { + sha256_blocks_generic(state, data, nblocks); + } +} +EXPORT_SYMBOL_GPL(sha256_blocks_simd); + +void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks) +{ + sha256_blocks_generic(state, data, nblocks); +} +EXPORT_SYMBOL_GPL(sha256_blocks_arch); + +bool sha256_is_arch_optimized(void) +{ + return static_key_enabled(&have_extensions); +} +EXPORT_SYMBOL_GPL(sha256_is_arch_optimized); + +static int __init riscv64_sha256_mod_init(void) +{ + /* Both zvknha and zvknhb provide the SHA-256 instructions. */ + if ((riscv_isa_extension_available(NULL, ZVKNHA) || + riscv_isa_extension_available(NULL, ZVKNHB)) && + riscv_isa_extension_available(NULL, ZVKB) && + riscv_vector_vlen() >= 128) + static_branch_enable(&have_extensions); + return 0; +} +subsys_initcall(riscv64_sha256_mod_init); + +static void __exit riscv64_sha256_mod_exit(void) +{ +} +module_exit(riscv64_sha256_mod_exit); + +MODULE_DESCRIPTION("SHA-256 (RISC-V accelerated)"); +MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c index 7fb12c59e571..9408f50ca59a 100644 --- a/arch/riscv/lib/csum.c +++ b/arch/riscv/lib/csum.c @@ -40,12 +40,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, uproto = (__force unsigned int)htonl(proto); sum += uproto; - /* - * Zbb support saves 4 instructions, so not worth checking without - * alternatives if supported - */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; /* @@ -157,12 +152,7 @@ do_csum_with_alignment(const unsigned char *buff, int len) csum = do_csum_common(ptr, end, data); #ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT - /* - * Zbb support saves 6 instructions, so not worth checking without - * alternatives if supported - */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; /* @@ -244,12 +234,7 @@ do_csum_no_alignment(const unsigned char *buff, int len) end = (const unsigned long *)(buff + len); csum = do_csum_common(ptr, end, data); - /* - * Zbb support saves 6 instructions, so not worth checking without - * alternatives if supported - */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; /* diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c index be38a93cedae..7bbdfc6d4552 100644 --- a/arch/riscv/lib/riscv_v_helpers.c +++ b/arch/riscv/lib/riscv_v_helpers.c @@ -16,8 +16,11 @@ #ifdef CONFIG_MMU size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD; int __asm_vector_usercopy(void *dst, void *src, size_t n); +int __asm_vector_usercopy_sum_enabled(void *dst, void *src, size_t n); int fallback_scalar_usercopy(void *dst, void *src, size_t n); -asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n) +int fallback_scalar_usercopy_sum_enabled(void *dst, void *src, size_t n); +asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n, + bool enable_sum) { size_t remain, copied; @@ -26,7 +29,8 @@ asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n) goto fallback; kernel_vector_begin(); - remain = __asm_vector_usercopy(dst, src, n); + remain = enable_sum ? __asm_vector_usercopy(dst, src, n) : + __asm_vector_usercopy_sum_enabled(dst, src, n); kernel_vector_end(); if (remain) { @@ -40,6 +44,7 @@ asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n) return remain; fallback: - return fallback_scalar_usercopy(dst, src, n); + return enable_sum ? fallback_scalar_usercopy(dst, src, n) : + fallback_scalar_usercopy_sum_enabled(dst, src, n); } #endif diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S index 57a5c0066231..65027e742af1 100644 --- a/arch/riscv/lib/strcmp.S +++ b/arch/riscv/lib/strcmp.S @@ -8,7 +8,8 @@ /* int strcmp(const char *cs, const char *ct) */ SYM_FUNC_START(strcmp) - ALTERNATIVE("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB) + __ALTERNATIVE_CFG("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) /* * Returns @@ -43,7 +44,7 @@ SYM_FUNC_START(strcmp) * The code was published as part of the bitmanip manual * in Appendix A. */ -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) strcmp_zbb: .option push diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S index 962983b73251..eb4d2b7ed22b 100644 --- a/arch/riscv/lib/strlen.S +++ b/arch/riscv/lib/strlen.S @@ -8,7 +8,8 @@ /* int strlen(const char *s) */ SYM_FUNC_START(strlen) - ALTERNATIVE("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB) + __ALTERNATIVE_CFG("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) /* * Returns @@ -33,7 +34,7 @@ SYM_FUNC_START(strlen) /* * Variant of strlen using the ZBB extension if available */ -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) strlen_zbb: #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S index 7b2d0ff9ed6c..062000c468c8 100644 --- a/arch/riscv/lib/strncmp.S +++ b/arch/riscv/lib/strncmp.S @@ -8,7 +8,8 @@ /* int strncmp(const char *cs, const char *ct, size_t count) */ SYM_FUNC_START(strncmp) - ALTERNATIVE("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB) + __ALTERNATIVE_CFG("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) /* * Returns @@ -46,7 +47,7 @@ SYM_FUNC_START(strncmp) /* * Variant of strncmp using the ZBB extension if available */ -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) strncmp_zbb: .option push diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 6a9f116bb545..4efea1b3326c 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -17,14 +17,43 @@ SYM_FUNC_START(__asm_copy_to_user) ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_ZVE32X, CONFIG_RISCV_ISA_V) REG_L t0, riscv_v_usercopy_threshold bltu a2, t0, fallback_scalar_usercopy - tail enter_vector_usercopy + li a3, 1 + tail enter_vector_usercopy #endif -SYM_FUNC_START(fallback_scalar_usercopy) +SYM_FUNC_END(__asm_copy_to_user) +EXPORT_SYMBOL(__asm_copy_to_user) +SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user) +EXPORT_SYMBOL(__asm_copy_from_user) +SYM_FUNC_START(fallback_scalar_usercopy) /* Enable access to user memory */ - li t6, SR_SUM - csrs CSR_STATUS, t6 + li t6, SR_SUM + csrs CSR_STATUS, t6 + mv t6, ra + call fallback_scalar_usercopy_sum_enabled + + /* Disable access to user memory */ + mv ra, t6 + li t6, SR_SUM + csrc CSR_STATUS, t6 + ret +SYM_FUNC_END(fallback_scalar_usercopy) + +SYM_FUNC_START(__asm_copy_to_user_sum_enabled) +#ifdef CONFIG_RISCV_ISA_V + ALTERNATIVE("j fallback_scalar_usercopy_sum_enabled", "nop", 0, RISCV_ISA_EXT_ZVE32X, CONFIG_RISCV_ISA_V) + REG_L t0, riscv_v_usercopy_threshold + bltu a2, t0, fallback_scalar_usercopy_sum_enabled + li a3, 0 + tail enter_vector_usercopy +#endif +SYM_FUNC_END(__asm_copy_to_user_sum_enabled) +SYM_FUNC_ALIAS(__asm_copy_from_user_sum_enabled, __asm_copy_to_user_sum_enabled) +EXPORT_SYMBOL(__asm_copy_from_user_sum_enabled) +EXPORT_SYMBOL(__asm_copy_to_user_sum_enabled) + +SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled) /* * Save the terminal address which will be used to compute the number * of bytes copied in case of a fixup exception. @@ -178,23 +207,12 @@ SYM_FUNC_START(fallback_scalar_usercopy) bltu a0, t0, 4b /* t0 - end of dst */ .Lout_copy_user: - /* Disable access to user memory */ - csrc CSR_STATUS, t6 li a0, 0 ret - - /* Exception fixup code */ 10: - /* Disable access to user memory */ - csrc CSR_STATUS, t6 sub a0, t5, a0 ret -SYM_FUNC_END(__asm_copy_to_user) -SYM_FUNC_END(fallback_scalar_usercopy) -EXPORT_SYMBOL(__asm_copy_to_user) -SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user) -EXPORT_SYMBOL(__asm_copy_from_user) - +SYM_FUNC_END(fallback_scalar_usercopy_sum_enabled) SYM_FUNC_START(__clear_user) diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S index 7c45f26de4f7..03b5560609a2 100644 --- a/arch/riscv/lib/uaccess_vector.S +++ b/arch/riscv/lib/uaccess_vector.S @@ -24,7 +24,18 @@ SYM_FUNC_START(__asm_vector_usercopy) /* Enable access to user memory */ li t6, SR_SUM csrs CSR_STATUS, t6 + mv t6, ra + call __asm_vector_usercopy_sum_enabled + + /* Disable access to user memory */ + mv ra, t6 + li t6, SR_SUM + csrc CSR_STATUS, t6 + ret +SYM_FUNC_END(__asm_vector_usercopy) + +SYM_FUNC_START(__asm_vector_usercopy_sum_enabled) loop: vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma fixup vle8.v vData, (pSrc), 10f @@ -36,8 +47,6 @@ loop: /* Exception fixup for vector load is shared with normal exit */ 10: - /* Disable access to user memory */ - csrc CSR_STATUS, t6 mv a0, iNum ret @@ -49,4 +58,4 @@ loop: csrr t2, CSR_VSTART sub iNum, iNum, t2 j 10b -SYM_FUNC_END(__asm_vector_usercopy) +SYM_FUNC_END(__asm_vector_usercopy_sum_enabled) diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index cbe4d775ef56..b916a68d324a 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -19,7 +19,7 @@ obj-y += context.o obj-y += pmem.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PTDUMP_CORE) += ptdump.o +obj-$(CONFIG_PTDUMP) += ptdump.o obj-$(CONFIG_KASAN) += kasan_init.o ifdef CONFIG_KASAN diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index b81672729887..4ca5aafce22e 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -24,7 +24,20 @@ void flush_icache_all(void) if (num_online_cpus() < 2) return; - else if (riscv_use_sbi_for_rfence()) + + /* + * Make sure all previous writes to the D$ are ordered before making + * the IPI. The RISC-V spec states that a hart must execute a data fence + * before triggering a remote fence.i in order to make the modification + * visable for remote harts. + * + * IPIs on RISC-V are triggered by MMIO writes to either CLINT or + * S-IMSIC, so the fence ensures previous data writes "happen before" + * the MMIO. + */ + RISCV_FENCE(w, o); + + if (riscv_use_sbi_for_rfence()) sbi_remote_fence_i(NULL); else on_each_cpu(ipi_remote_fence_i, NULL, 1); @@ -101,6 +114,9 @@ EXPORT_SYMBOL_GPL(riscv_cbom_block_size); unsigned int riscv_cboz_block_size; EXPORT_SYMBOL_GPL(riscv_cboz_block_size); +unsigned int riscv_cbop_block_size; +EXPORT_SYMBOL_GPL(riscv_cbop_block_size); + static void __init cbo_get_block_size(struct device_node *node, const char *name, u32 *block_size, unsigned long *first_hartid) @@ -125,8 +141,8 @@ static void __init cbo_get_block_size(struct device_node *node, void __init riscv_init_cbo_blocksizes(void) { - unsigned long cbom_hartid, cboz_hartid; - u32 cbom_block_size = 0, cboz_block_size = 0; + unsigned long cbom_hartid, cboz_hartid, cbop_hartid; + u32 cbom_block_size = 0, cboz_block_size = 0, cbop_block_size = 0; struct device_node *node; struct acpi_table_header *rhct; acpi_status status; @@ -138,13 +154,15 @@ void __init riscv_init_cbo_blocksizes(void) &cbom_block_size, &cbom_hartid); cbo_get_block_size(node, "riscv,cboz-block-size", &cboz_block_size, &cboz_hartid); + cbo_get_block_size(node, "riscv,cbop-block-size", + &cbop_block_size, &cbop_hartid); } } else { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); if (ACPI_FAILURE(status)) return; - acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL); + acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, &cbop_block_size); acpi_put_table((struct acpi_table_header *)rhct); } @@ -153,6 +171,9 @@ void __init riscv_init_cbo_blocksizes(void) if (cboz_block_size) riscv_cboz_block_size = cboz_block_size; + + if (cbop_block_size) + riscv_cbop_block_size = cbop_block_size; } #ifdef CONFIG_SMP @@ -172,7 +193,7 @@ static void set_icache_stale_mask(void) stale_cpu = cpumask_test_cpu(cpu, mask); cpumask_setall(mask); - cpumask_assign_cpu(cpu, mask, stale_cpu); + __assign_cpu(cpu, mask, stale_cpu); put_cpu(); } #endif diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 4abe3de23225..55c20ad1f744 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -158,7 +158,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu) * * - We get a zero back from the cmpxchg and end up waiting on the * lock. Taking the lock synchronises with the rollover and so - * we are forced to see the updated verion. + * we are forced to see the updated version. * * - We get a valid context back from the cmpxchg then we continue * using old ASID because __flush_context() would have marked ASID diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index a9f2b4af8f3f..0194324a0c50 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -22,6 +22,57 @@ #include "../kernel/head.h" +static void show_pte(unsigned long addr) +{ + pgd_t *pgdp, pgd; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + struct mm_struct *mm = current->mm; + + if (!mm) + mm = &init_mm; + + pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n", + current->comm, PAGE_SIZE / SZ_1K, VA_BITS, + mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd)); + + pgdp = pgd_offset(mm, addr); + pgd = pgdp_get(pgdp); + pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd)); + if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd)) + goto out; + + p4dp = p4d_offset(pgdp, addr); + p4d = p4dp_get(p4dp); + pr_cont(", p4d=%016lx", p4d_val(p4d)); + if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d)) + goto out; + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + pr_cont(", pud=%016lx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud)) + goto out; + + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get(pmdp); + pr_cont(", pmd=%016lx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd)) + goto out; + + ptep = pte_offset_map(pmdp, addr); + if (!ptep) + goto out; + + pte = ptep_get(ptep); + pr_cont(", pte=%016lx", pte_val(pte)); + pte_unmap(ptep); +out: + pr_cont("\n"); +} + static void die_kernel_fault(const char *msg, unsigned long addr, struct pt_regs *regs) { @@ -31,6 +82,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, addr); bust_spinlocks(0); + show_pte(addr); die(regs, "Oops"); make_task_dead(SIGKILL); } diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 42314f093922..375dd96bb4a0 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -148,22 +148,25 @@ unsigned long hugetlb_mask_last_page(struct hstate *h) static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, - unsigned long pte_num) + unsigned long ncontig) { - pte_t orig_pte = ptep_get(ptep); - unsigned long i; - - for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) { - pte_t pte = ptep_get_and_clear(mm, addr, ptep); - - if (pte_dirty(pte)) - orig_pte = pte_mkdirty(orig_pte); - - if (pte_young(pte)) - orig_pte = pte_mkyoung(orig_pte); + pte_t pte, tmp_pte; + bool present; + + pte = ptep_get_and_clear(mm, addr, ptep); + present = pte_present(pte); + while (--ncontig) { + ptep++; + addr += PAGE_SIZE; + tmp_pte = ptep_get_and_clear(mm, addr, ptep); + if (present) { + if (pte_dirty(tmp_pte)) + pte = pte_mkdirty(pte); + if (pte_young(tmp_pte)) + pte = pte_mkyoung(pte); + } } - - return orig_pte; + return pte; } static pte_t get_clear_contig_flush(struct mm_struct *mm, @@ -212,6 +215,26 @@ static void clear_flush(struct mm_struct *mm, flush_tlb_range(&vma, saddr, addr); } +static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize) +{ + unsigned long hugepage_shift; + + if (sz >= PGDIR_SIZE) + hugepage_shift = PGDIR_SHIFT; + else if (sz >= P4D_SIZE) + hugepage_shift = P4D_SHIFT; + else if (sz >= PUD_SIZE) + hugepage_shift = PUD_SHIFT; + else if (sz >= PMD_SIZE) + hugepage_shift = PMD_SHIFT; + else + hugepage_shift = PAGE_SHIFT; + + *pgsize = 1 << hugepage_shift; + + return sz >> hugepage_shift; +} + /* * When dealing with NAPOT mappings, the privileged specification indicates that * "if an update needs to be made, the OS generally should first mark all of the @@ -226,22 +249,10 @@ void set_huge_pte_at(struct mm_struct *mm, pte_t pte, unsigned long sz) { - unsigned long hugepage_shift, pgsize; + size_t pgsize; int i, pte_num; - if (sz >= PGDIR_SIZE) - hugepage_shift = PGDIR_SHIFT; - else if (sz >= P4D_SIZE) - hugepage_shift = P4D_SHIFT; - else if (sz >= PUD_SIZE) - hugepage_shift = PUD_SHIFT; - else if (sz >= PMD_SIZE) - hugepage_shift = PMD_SHIFT; - else - hugepage_shift = PAGE_SHIFT; - - pte_num = sz >> hugepage_shift; - pgsize = 1 << hugepage_shift; + pte_num = num_contig_ptes_from_size(sz, &pgsize); if (!pte_present(pte)) { for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) @@ -293,15 +304,16 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) + pte_t *ptep, unsigned long sz) { + size_t pgsize; pte_t orig_pte = ptep_get(ptep); int pte_num; if (!pte_napot(orig_pte)) return ptep_get_and_clear(mm, addr, ptep); - pte_num = napot_pte_num(napot_cont_order(orig_pte)); + pte_num = num_contig_ptes_from_size(sz, &pgsize); return get_clear_contig(mm, addr, ptep, pte_num); } @@ -351,6 +363,7 @@ void huge_pte_clear(struct mm_struct *mm, pte_t *ptep, unsigned long sz) { + size_t pgsize; pte_t pte = ptep_get(ptep); int i, pte_num; @@ -359,8 +372,9 @@ void huge_pte_clear(struct mm_struct *mm, return; } - pte_num = napot_pte_num(napot_cont_order(pte)); - for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + pte_num = num_contig_ptes_from_size(sz, &pgsize); + + for (i = 0; i < pte_num; i++, addr += pgsize, ptep++) pte_clear(mm, addr, ptep); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..8d0374d7ce8e 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -20,19 +20,18 @@ #include <linux/dma-map-ops.h> #include <linux/crash_dump.h> #include <linux/hugetlb.h> -#ifdef CONFIG_RELOCATABLE -#include <linux/elf.h> -#endif #include <linux/kfence.h> #include <linux/execmem.h> #include <asm/fixmap.h> #include <asm/io.h> #include <asm/kasan.h> +#include <asm/module.h> #include <asm/numa.h> #include <asm/pgtable.h> #include <asm/sections.h> #include <asm/soc.h> +#include <asm/sparsemem.h> #include <asm/tlbflush.h> #include "../kernel/head.h" @@ -62,6 +61,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled); phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -163,7 +169,7 @@ static void __init print_vm_layout(void) static void print_vm_layout(void) { } #endif /* CONFIG_DEBUG_VM */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit); #ifdef CONFIG_FLATMEM @@ -184,7 +190,6 @@ void __init mem_init(void) } swiotlb_init(swiotlb, SWIOTLB_VERBOSE); - memblock_free_all(); print_vm_layout(); } @@ -240,8 +245,12 @@ static void __init setup_bootmem(void) * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. */ - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) + if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif + } /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -256,8 +265,12 @@ static void __init setup_bootmem(void) */ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) { max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; - memblock_cap_memory_range(phys_ram_base, - max_mapped_addr - phys_ram_base); + if (memblock_end_of_DRAM() > max_mapped_addr) { + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + pr_warn("Physical memory overflows the linear mapping size: region above %pa removed", + &max_mapped_addr); + } } /* @@ -279,10 +292,8 @@ static void __init setup_bootmem(void) phys_ram_end = memblock_end_of_DRAM(); min_low_pfn = PFN_UP(phys_ram_base); max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); - high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); - set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); reserve_initrd_mem(); @@ -307,6 +318,44 @@ static void __init setup_bootmem(void) hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); } +#ifdef CONFIG_RELOCATABLE +extern unsigned long __rela_dyn_start, __rela_dyn_end; + +static void __init relocate_kernel(void) +{ + Elf_Rela *rela = (Elf_Rela *)&__rela_dyn_start; + /* + * This holds the offset between the linked virtual address and the + * relocated virtual address. + */ + uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR; + /* + * This holds the offset between kernel linked virtual address and + * physical address. + */ + uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr; + + for ( ; rela < (Elf_Rela *)&__rela_dyn_end; rela++) { + Elf_Addr addr = (rela->r_offset - va_kernel_link_pa_offset); + Elf_Addr relocated_addr = rela->r_addend; + + if (rela->r_info != R_RISCV_RELATIVE) + continue; + + /* + * Make sure to not relocate vdso symbols like rt_sigreturn + * which are linked from the address 0 in vmlinux since + * vdso symbol addresses are actually used as an offset from + * mm->context.vdso in VDSO_OFFSET macro. + */ + if (relocated_addr >= KERNEL_LINK_ADDR) + relocated_addr += reloc_offset; + + *(Elf_Addr *)addr = relocated_addr; + } +} +#endif /* CONFIG_RELOCATABLE */ + #ifdef CONFIG_MMU struct pt_alloc_ops pt_ops __meminitdata; @@ -393,7 +442,12 @@ static phys_addr_t __meminit alloc_pte_late(uintptr_t va) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - BUG_ON(!ptdesc || !pagetable_pte_ctor(ptdesc)); + /* + * We do not know which mm the PTE page is associated to at this point. + * Passing NULL to the ctor is the safe option, though it may result + * in unnecessary work (e.g. initialising the ptlock for init_mm). + */ + BUG_ON(!ptdesc || !pagetable_pte_ctor(NULL, ptdesc)); return __pa((pte_t *)ptdesc_address(ptdesc)); } @@ -473,7 +527,8 @@ static phys_addr_t __meminit alloc_pmd_late(uintptr_t va) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - BUG_ON(!ptdesc || !pagetable_pmd_ctor(ptdesc)); + /* See comment in alloc_pte_late() regarding NULL passed the ctor */ + BUG_ON(!ptdesc || !pagetable_pmd_ctor(NULL, ptdesc)); return __pa((pmd_t *)ptdesc_address(ptdesc)); } @@ -535,11 +590,11 @@ static phys_addr_t __init alloc_pud_fixmap(uintptr_t va) static phys_addr_t __meminit alloc_pud_late(uintptr_t va) { - unsigned long vaddr; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); - vaddr = __get_free_page(GFP_KERNEL); - BUG_ON(!vaddr); - return __pa(vaddr); + BUG_ON(!ptdesc); + pagetable_pud_ctor(ptdesc); + return __pa((pud_t *)ptdesc_address(ptdesc)); } static p4d_t *__init get_p4d_virt_early(phys_addr_t pa) @@ -573,11 +628,11 @@ static phys_addr_t __init alloc_p4d_fixmap(uintptr_t va) static phys_addr_t __meminit alloc_p4d_late(uintptr_t va) { - unsigned long vaddr; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); - vaddr = __get_free_page(GFP_KERNEL); - BUG_ON(!vaddr); - return __pa(vaddr); + BUG_ON(!ptdesc); + pagetable_p4d_ctor(ptdesc); + return __pa((p4d_t *)ptdesc_address(ptdesc)); } static void __meminit create_pud_mapping(pud_t *pudp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, @@ -807,6 +862,8 @@ static __init void set_satp_mode(uintptr_t dtb_pa) uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK; u64 satp_mode_cmdline = __pi_set_satp_mode_from_cmdline(dtb_pa); + kernel_map.page_offset = PAGE_OFFSET_L5; + if (satp_mode_cmdline == SATP_MODE_57) { disable_pgtable_l5(); } else if (satp_mode_cmdline == SATP_MODE_48) { @@ -877,44 +934,6 @@ retry: #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing." #endif -#ifdef CONFIG_RELOCATABLE -extern unsigned long __rela_dyn_start, __rela_dyn_end; - -static void __init relocate_kernel(void) -{ - Elf64_Rela *rela = (Elf64_Rela *)&__rela_dyn_start; - /* - * This holds the offset between the linked virtual address and the - * relocated virtual address. - */ - uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR; - /* - * This holds the offset between kernel linked virtual address and - * physical address. - */ - uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr; - - for ( ; rela < (Elf64_Rela *)&__rela_dyn_end; rela++) { - Elf64_Addr addr = (rela->r_offset - va_kernel_link_pa_offset); - Elf64_Addr relocated_addr = rela->r_addend; - - if (rela->r_info != R_RISCV_RELATIVE) - continue; - - /* - * Make sure to not relocate vdso symbols like rt_sigreturn - * which are linked from the address 0 in vmlinux since - * vdso symbol addresses are actually used as an offset from - * mm->context.vdso in VDSO_OFFSET macro. - */ - if (relocated_addr >= KERNEL_LINK_ADDR) - relocated_addr += reloc_offset; - - *(Elf64_Addr *)addr = relocated_addr; - } -} -#endif /* CONFIG_RELOCATABLE */ - #ifdef CONFIG_XIP_KERNEL static void __init create_kernel_page_table(pgd_t *pgdir, __always_unused bool early) @@ -1092,15 +1111,13 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset; #ifdef CONFIG_XIP_KERNEL -#ifdef CONFIG_64BIT - kernel_map.page_offset = PAGE_OFFSET_L3; -#else - kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); -#endif kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR; kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); @@ -1108,7 +1125,6 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.va_kernel_xip_data_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr + (uintptr_t)&_sdata - (uintptr_t)&_start; #else - kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL); kernel_map.phys_addr = (uintptr_t)(&_start); kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr; kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr; @@ -1155,7 +1171,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) * makes the kernel cross over a PUD_SIZE boundary, raise a bug * since a part of the kernel would not get mapped. */ - BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size); + if (IS_ENABLED(CONFIG_64BIT)) + BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size); relocate_kernel(); #endif @@ -1359,6 +1376,12 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) { dtb_early_va = (void *)dtb_pa; dtb_early_pa = dtb_pa; + +#ifdef CONFIG_RELOCATABLE + kernel_map.virt_addr = (uintptr_t)_start; + kernel_map.phys_addr = (uintptr_t)_start; + relocate_kernel(); +#endif } static inline void setup_vm_final(void) @@ -1377,21 +1400,19 @@ static void __init arch_reserve_crashkernel(void) { unsigned long long low_size = 0; unsigned long long crash_base, crash_size; - char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; - ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, &low_size, &high); if (ret) return; - reserve_crashkernel_generic(cmdline, crash_size, crash_base, - low_size, high); + reserve_crashkernel_generic(crash_size, crash_base, low_size, high); } void __init paging_init(void) @@ -1558,7 +1579,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) return; } - pagetable_pte_dtor(ptdesc); + pagetable_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1566,7 +1587,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) pmd_clear(pmd); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap) { struct page *page = pud_page(*pud); struct ptdesc *ptdesc = page_ptdesc(page); @@ -1579,7 +1600,8 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) return; } - pagetable_pmd_dtor(ptdesc); + if (!is_vmemmap) + pagetable_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1703,7 +1725,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); if (pgtable_l4_enabled) - free_pmd_table(pmd_base, pudp); + free_pmd_table(pmd_base, pudp, is_vmemmap); } } diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index c301c8d291d2..41c635d6aca4 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -32,7 +32,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned pte_t *ptep, *p; if (pmd_none(pmdp_get(pmd))) { - p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -54,7 +54,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned unsigned long next; if (pud_none(pudp_get(pud))) { - p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -85,7 +85,7 @@ static void __init kasan_populate_pud(p4d_t *p4d, unsigned long next; if (p4d_none(p4dp_get(p4d))) { - p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -116,7 +116,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd, unsigned long next; if (pgd_none(pgdp_get(pgd))) { - p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); + p = memblock_alloc_or_panic(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -385,7 +385,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d, next = pud_addr_end(vaddr, end); if (pud_none(pudp_get(pud_k))) { - p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; } @@ -405,7 +405,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd, next = p4d_addr_end(vaddr, end); if (p4d_none(p4dp_get(p4d_k))) { - p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; } @@ -424,7 +424,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long next = pgd_addr_end(vaddr, end); if (pgd_none(pgdp_get(pgd_k))) { - p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; } diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 271d01a5ba4d..d815448758a1 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -386,6 +386,21 @@ int set_direct_map_default_noflush(struct page *page) PAGE_KERNEL, __pgprot(_PAGE_EXEC)); } +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + pgprot_t set, clear; + + if (valid) { + set = PAGE_KERNEL; + clear = __pgprot(_PAGE_EXEC); + } else { + set = __pgprot(0); + clear = __pgprot(_PAGE_PRESENT); + } + + return __set_memory((unsigned long)page_address(page), nr, set, clear); +} + #ifdef CONFIG_DEBUG_PAGEALLOC static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) { diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index 4ae67324f992..8b6c0a112a8d 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -154,4 +154,14 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, flush_tlb_mm(vma->vm_mm); return pmd; } + +pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp) +{ + VM_WARN_ON_ONCE(!pud_present(*pudp)); + pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); + + flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); + return old; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c index 18706f457da7..559d291fac5c 100644 --- a/arch/riscv/mm/physaddr.c +++ b/arch/riscv/mm/physaddr.c @@ -12,7 +12,7 @@ phys_addr_t __virt_to_phys(unsigned long x) * Boundary checking aginst the kernel linear mapping space. */ WARN(!is_linear_mapping(x) && !is_kernel_mapping(x), - "virt_to_phys used for non-linear address: %pK (%pS)\n", + "virt_to_phys used for non-linear address: %p (%pS)\n", (void *)x, (void *)x); return __va_to_pa_nodebug(x); diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 9d5f657a251b..32922550a50a 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -318,6 +318,38 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, } } +static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte) +{ + note_page(pt_st, addr, 4, pte_val(pte)); +} + +static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd) +{ + note_page(pt_st, addr, 3, pmd_val(pmd)); +} + +static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud) +{ + note_page(pt_st, addr, 2, pud_val(pud)); +} + +static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d) +{ + note_page(pt_st, addr, 1, p4d_val(p4d)); +} + +static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd) +{ + note_page(pt_st, addr, 0, pgd_val(pgd)); +} + +static void note_page_flush(struct ptdump_state *pt_st) +{ + pte_t pte_zero = {0}; + + note_page(pt_st, 0, -1, pte_val(pte_zero)); +} + static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo) { struct pg_state st = { @@ -325,7 +357,12 @@ static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo) .marker = pinfo->markers, .level = -1, .ptdump = { - .note_page = note_page, + .note_page_pte = note_page_pte, + .note_page_pmd = note_page_pmd, + .note_page_pud = note_page_pud, + .note_page_p4d = note_page_p4d, + .note_page_pgd = note_page_pgd, + .note_page_flush = note_page_flush, .range = (struct ptdump_range[]) { {pinfo->base_addr, pinfo->end}, {0, 0} @@ -347,7 +384,12 @@ bool ptdump_check_wx(void) .level = -1, .check_wx = true, .ptdump = { - .note_page = note_page, + .note_page_pte = note_page_pte, + .note_page_pmd = note_page_pmd, + .note_page_pud = note_page_pud, + .note_page_p4d = note_page_p4d, + .note_page_pgd = note_page_pgd, + .note_page_flush = note_page_flush, .range = (struct ptdump_range[]) { {KERN_VIRT_START, ULONG_MAX}, {0, 0} diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 9b6e86ce3867..e737ba7949b1 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -4,8 +4,30 @@ #include <linux/smp.h> #include <linux/sched.h> #include <linux/hugetlb.h> +#include <linux/mmu_notifier.h> #include <asm/sbi.h> #include <asm/mmu_context.h> +#include <asm/cpufeature.h> + +#define has_svinval() riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL) + +static inline void local_sfence_inval_ir(void) +{ + asm volatile(SFENCE_INVAL_IR() ::: "memory"); +} + +static inline void local_sfence_w_inval(void) +{ + asm volatile(SFENCE_W_INVAL() ::: "memory"); +} + +static inline void local_sinval_vma(unsigned long vma, unsigned long asid) +{ + if (asid != FLUSH_TLB_NO_ASID) + asm volatile(SINVAL_VMA(%0, %1) : : "r" (vma), "r" (asid) : "memory"); + else + asm volatile(SINVAL_VMA(%0, zero) : : "r" (vma) : "memory"); +} /* * Flush entire TLB if number of entries to be flushed is greater @@ -26,6 +48,16 @@ static void local_flush_tlb_range_threshold_asid(unsigned long start, return; } + if (has_svinval()) { + local_sfence_w_inval(); + for (i = 0; i < nr_ptes_in_range; ++i) { + local_sinval_vma(start, asid); + start += stride; + } + local_sfence_inval_ir(); + return; + } + for (i = 0; i < nr_ptes_in_range; ++i) { local_flush_tlb_page_asid(start, asid); start += stride; @@ -78,10 +110,17 @@ static void __ipi_flush_tlb_range_asid(void *info) local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); } -static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid, +static inline unsigned long get_mm_asid(struct mm_struct *mm) +{ + return mm ? cntx2asid(atomic_long_read(&mm->context.id)) : FLUSH_TLB_NO_ASID; +} + +static void __flush_tlb_range(struct mm_struct *mm, + const struct cpumask *cmask, unsigned long start, unsigned long size, unsigned long stride) { + unsigned long asid = get_mm_asid(mm); unsigned int cpu; if (cpumask_empty(cmask)) @@ -105,30 +144,26 @@ static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid, } put_cpu(); -} -static inline unsigned long get_mm_asid(struct mm_struct *mm) -{ - return cntx2asid(atomic_long_read(&mm->context.id)); + if (mm) + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, start + size); } void flush_tlb_mm(struct mm_struct *mm) { - __flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm), - 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); + __flush_tlb_range(mm, mm_cpumask(mm), 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); } void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned int page_size) { - __flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm), - start, end - start, page_size); + __flush_tlb_range(mm, mm_cpumask(mm), start, end - start, page_size); } void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) { - __flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm), + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), addr, PAGE_SIZE, PAGE_SIZE); } @@ -161,13 +196,13 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, } } - __flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm), + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), start, end - start, stride_size); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - __flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID, + __flush_tlb_range(NULL, cpu_online_mask, start, end - start, PAGE_SIZE); } @@ -175,9 +210,16 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - __flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm), + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), start, end - start, PMD_SIZE); } + +void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), + start, end - start, PUD_SIZE); +} #endif bool arch_tlbbatch_should_defer(struct mm_struct *mm) @@ -186,10 +228,10 @@ bool arch_tlbbatch_should_defer(struct mm_struct *mm) } void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr) + struct mm_struct *mm, unsigned long start, unsigned long end) { cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } void arch_flush_tlb_batched_pending(struct mm_struct *mm) @@ -199,7 +241,7 @@ void arch_flush_tlb_batched_pending(struct mm_struct *mm) void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { - __flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0, - FLUSH_TLB_MAX_SIZE, PAGE_SIZE); + __flush_tlb_range(NULL, &batch->cpumask, + 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); cpumask_clear(&batch->cpumask); } diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 1d1c78d4cff1..e7b032dfd17f 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -608,6 +608,21 @@ static inline u32 rv_fence(u8 pred, u8 succ) return rv_i_insn(imm11_0, 0, 0, 0, 0xf); } +static inline void emit_fence_r_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x2, 0x3), ctx); +} + +static inline void emit_fence_rw_w(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x1), ctx); +} + +static inline void emit_fence_rw_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x3), ctx); +} + static inline u32 rv_nop(void) { return rv_i_insn(0, 0, 0, 0, 0x13); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 4cc631fa7039..10e01ff06312 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -10,7 +10,7 @@ #include <linux/filter.h> #include <linux/memory.h> #include <linux/stop_machine.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cfi.h> #include <asm/percpu.h> #include "bpf_jit.h" @@ -473,11 +473,212 @@ static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx) emit(hash, ctx); } -static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, - struct rv_jit_context *ctx) +static int emit_load_8(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lb(rd, off, rs), ctx); + else + emit(rv_lbu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lb(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_16(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lh(rd, off, rs), ctx); + else + emit(rv_lhu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lh(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_32(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lw(rd, off, rs), ctx); + else + emit(rv_lwu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lw(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_64(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_ld(rd, off, rs, ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit_ld(rd, 0, RV_REG_T1, ctx); + return ctx->ninsns - insns_start; +} + +static void emit_store_8(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit(rv_sb(rd, off, rs), ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit(rv_sb(RV_REG_T1, 0, rs), ctx); +} + +static void emit_store_16(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit(rv_sh(rd, off, rs), ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit(rv_sh(RV_REG_T1, 0, rs), ctx); +} + +static void emit_store_32(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit_sw(rd, off, rs, ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit_sw(RV_REG_T1, 0, rs, ctx); +} + +static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit_sd(rd, off, rs, ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit_sd(RV_REG_T1, 0, rs, ctx); +} + +static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + s32 imm = insn->imm; + s16 off = insn->off; + + switch (imm) { + /* dst_reg = load_acquire(src_reg + off16) */ + case BPF_LOAD_ACQ: + switch (BPF_SIZE(code)) { + case BPF_B: + emit_load_8(false, rd, off, rs, ctx); + break; + case BPF_H: + emit_load_16(false, rd, off, rs, ctx); + break; + case BPF_W: + emit_load_32(false, rd, off, rs, ctx); + break; + case BPF_DW: + emit_load_64(false, rd, off, rs, ctx); + break; + } + emit_fence_r_rw(ctx); + + /* If our next insn is a redundant zext, return 1 to tell + * build_body() to skip it. + */ + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; + break; + /* store_release(dst_reg + off16, src_reg) */ + case BPF_STORE_REL: + emit_fence_rw_w(ctx); + switch (BPF_SIZE(code)) { + case BPF_B: + emit_store_8(rd, off, rs, ctx); + break; + case BPF_H: + emit_store_16(rd, off, rs, ctx); + break; + case BPF_W: + emit_store_32(rd, off, rs, ctx); + break; + case BPF_DW: + emit_store_64(rd, off, rs, ctx); + break; + } + break; + default: + pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm); + return -EINVAL; + } + + return 0; +} + +static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) { - u8 r0; + u8 r0, code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; int jmp_offset; + bool is64; + + if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) { + pr_err_once("bpf-jit: 1- and 2-byte RMW atomics are not supported\n"); + return -EINVAL; + } + is64 = BPF_SIZE(code) == BPF_DW; if (off) { if (is_12b_int(off)) { @@ -554,9 +755,14 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); jmp_offset = ninsns_rvoff(-6); emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); - emit(rv_fence(0x3, 0x3), ctx); + emit_fence_rw_rw(ctx); break; + default: + pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm); + return -EINVAL; } + + return 0; } #define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0) @@ -1650,8 +1856,8 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: { - int insn_len, insns_start; bool sign_ext; + int insn_len; sign_ext = BPF_MODE(insn->code) == BPF_MEMSX || BPF_MODE(insn->code) == BPF_PROBE_MEMSX; @@ -1663,78 +1869,16 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, switch (BPF_SIZE(code)) { case BPF_B: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lb(rd, off, rs), ctx); - else - emit(rv_lbu(rd, off, rs), ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lb(rd, 0, RV_REG_T1), ctx); - else - emit(rv_lbu(rd, 0, RV_REG_T1), ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_8(sign_ext, rd, off, rs, ctx); break; case BPF_H: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lh(rd, off, rs), ctx); - else - emit(rv_lhu(rd, off, rs), ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lh(rd, 0, RV_REG_T1), ctx); - else - emit(rv_lhu(rd, 0, RV_REG_T1), ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_16(sign_ext, rd, off, rs, ctx); break; case BPF_W: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lw(rd, off, rs), ctx); - else - emit(rv_lwu(rd, off, rs), ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lw(rd, 0, RV_REG_T1), ctx); - else - emit(rv_lwu(rd, 0, RV_REG_T1), ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_32(sign_ext, rd, off, rs, ctx); break; case BPF_DW: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - emit_ld(rd, off, rs, ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - emit_ld(rd, 0, RV_REG_T1, ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_64(sign_ext, rd, off, rs, ctx); break; } @@ -1879,49 +2023,27 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, /* STX: *(size *)(dst + off) = src */ case BPF_STX | BPF_MEM | BPF_B: - if (is_12b_int(off)) { - emit(rv_sb(rd, off, rs), ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit(rv_sb(RV_REG_T1, 0, rs), ctx); + emit_store_8(rd, off, rs, ctx); break; case BPF_STX | BPF_MEM | BPF_H: - if (is_12b_int(off)) { - emit(rv_sh(rd, off, rs), ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit(rv_sh(RV_REG_T1, 0, rs), ctx); + emit_store_16(rd, off, rs, ctx); break; case BPF_STX | BPF_MEM | BPF_W: - if (is_12b_int(off)) { - emit_sw(rd, off, rs, ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit_sw(RV_REG_T1, 0, rs, ctx); + emit_store_32(rd, off, rs, ctx); break; case BPF_STX | BPF_MEM | BPF_DW: - if (is_12b_int(off)) { - emit_sd(rd, off, rs, ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit_sd(RV_REG_T1, 0, rs, ctx); + emit_store_64(rd, off, rs, ctx); break; + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: - emit_atomic(rd, rs, off, imm, - BPF_SIZE(code) == BPF_DW, ctx); + if (bpf_atomic_is_load_store(insn)) + ret = emit_atomic_ld_st(rd, rs, insn, ctx); + else + ret = emit_atomic_rmw(rd, rs, insn, ctx); + if (ret) + return ret; break; case BPF_STX | BPF_PROBE_MEM32 | BPF_B: diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 6de753c667f4..f6ca5cfa6b2f 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -9,7 +9,7 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/memory.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cfi.h> #include "bpf_jit.h" @@ -26,9 +26,8 @@ static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) int ret; ret = bpf_jit_emit_insn(insn, ctx, extra_pass); - /* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */ if (ret > 0) - i++; + i++; /* skip the next instruction */ if (offset) offset[i] = ctx->ninsns; if (ret < 0) diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S index 0e6ca6d5ae4b..c5db2f072c34 100644 --- a/arch/riscv/purgatory/entry.S +++ b/arch/riscv/purgatory/entry.S @@ -12,6 +12,7 @@ .text +.align 2 SYM_CODE_START(purgatory_start) lla sp, .Lstack |