diff options
Diffstat (limited to 'arch/riscv/kernel')
124 files changed, 13861 insertions, 2136 deletions
diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore index b51634f6a7cd..e052ed331cc1 100644 --- a/arch/riscv/kernel/.gitignore +++ b/arch/riscv/kernel/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only /vmlinux.lds diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f40205cb9a22..f71910718053 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -4,12 +4,41 @@ # ifdef CONFIG_FTRACE -CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi.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,) + +ifdef CONFIG_KEXEC_CORE +AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) +endif + +# cmodel=medany and notrace when patching early +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_alternative.o := -mcmodel=medany +CFLAGS_cpufeature.o := -mcmodel=medany +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) +endif +ifdef CONFIG_RELOCATABLE +CFLAGS_alternative.o += -fno-pie +CFLAGS_cpufeature.o += -fno-pie +endif +ifdef CONFIG_KASAN +KASAN_SANITIZE_alternative.o := n +KASAN_SANITIZE_cpufeature.o := n +endif endif -extra-y += head.o extra-y += vmlinux.lds +obj-y += head.o +obj-y += soc.o +obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o +obj-y += copy-unaligned.o obj-y += cpu.o obj-y += cpufeature.o obj-y += entry.o @@ -21,26 +50,58 @@ obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o obj-y += sys_riscv.o +obj-y += sys_hwprobe.o obj-y += time.o obj-y += traps.o obj-y += riscv_ksyms.o obj-y += stacktrace.o obj-y += cacheinfo.o +obj-y += patch.o +obj-y += probes/ +obj-y += tests/ obj-$(CONFIG_MMU) += vdso.o vdso/ -obj-$(CONFIG_RISCV_M_MODE) += clint.o +obj-$(CONFIG_RISCV_MISALIGNED) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o +obj-$(CONFIG_RISCV_ISA_V) += vector.o +obj-$(CONFIG_RISCV_ISA_V) += kernel_mode_vector.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SMP) += cpu_ops.o + +obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o +obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o +obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o + obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o obj-$(CONFIG_RISCV_SBI) += sbi.o +ifeq ($(CONFIG_RISCV_SBI), y) +obj-$(CONFIG_SMP) += sbi-ipi.o +obj-$(CONFIG_SMP) += cpu_ops_sbi.o +endif +obj-$(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-$(CONFIG_CRASH_DUMP) += crash_dump.o +obj-$(CONFIG_CRASH_CORE) += crash_core.o + +obj-$(CONFIG_JUMP_LABEL) += jump_label.o + +obj-$(CONFIG_CFI_CLANG) += cfi.o + +obj-$(CONFIG_EFI) += efi.o +obj-$(CONFIG_COMPAT) += compat_syscall_table.o +obj-$(CONFIG_COMPAT) += compat_signal.o +obj-$(CONFIG_COMPAT) += compat_vdso/ -clean: +obj-$(CONFIG_64BIT) += pi/ +obj-$(CONFIG_ACPI) += acpi.o diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c new file mode 100644 index 000000000000..e619edc8b0cc --- /dev/null +++ b/arch/riscv/kernel/acpi.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * RISC-V Specific Low-Level ACPI Boot Support + * + * Copyright (C) 2013-2014, Linaro Ltd. + * Author: Al Stone <al.stone@linaro.org> + * Author: Graeme Gregory <graeme.gregory@linaro.org> + * Author: Hanjun Guo <hanjun.guo@linaro.org> + * Author: Tomasz Nowicki <tomasz.nowicki@linaro.org> + * Author: Naresh Bhat <naresh.bhat@linaro.org> + * + * Copyright (C) 2021-2023, Ventana Micro Systems Inc. + * Author: Sunil V L <sunilvl@ventanamicro.com> + */ + +#include <linux/acpi.h> +#include <linux/efi.h> +#include <linux/io.h> +#include <linux/memblock.h> +#include <linux/pci.h> + +int acpi_noirq = 1; /* skip ACPI IRQ initialization */ +int acpi_disabled = 1; +EXPORT_SYMBOL(acpi_disabled); + +int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */ +EXPORT_SYMBOL(acpi_pci_disabled); + +static bool param_acpi_off __initdata; +static bool param_acpi_on __initdata; +static bool param_acpi_force __initdata; + +static struct acpi_madt_rintc cpu_madt_rintc[NR_CPUS]; + +static int __init parse_acpi(char *arg) +{ + if (!arg) + return -EINVAL; + + /* "acpi=off" disables both ACPI table parsing and interpreter */ + if (strcmp(arg, "off") == 0) + param_acpi_off = true; + else if (strcmp(arg, "on") == 0) /* prefer ACPI over DT */ + param_acpi_on = true; + else if (strcmp(arg, "force") == 0) /* force ACPI to be enabled */ + param_acpi_force = true; + else + return -EINVAL; /* Core will print when we return error */ + + return 0; +} +early_param("acpi", parse_acpi); + +/* + * acpi_fadt_sanity_check() - Check FADT presence and carry out sanity + * checks on it + * + * Return 0 on success, <0 on failure + */ +static int __init acpi_fadt_sanity_check(void) +{ + struct acpi_table_header *table; + struct acpi_table_fadt *fadt; + acpi_status status; + int ret = 0; + + /* + * FADT is required on riscv; retrieve it to check its presence + * and carry out revision and ACPI HW reduced compliancy tests + */ + status = acpi_get_table(ACPI_SIG_FADT, 0, &table); + if (ACPI_FAILURE(status)) { + const char *msg = acpi_format_exception(status); + + pr_err("Failed to get FADT table, %s\n", msg); + return -ENODEV; + } + + fadt = (struct acpi_table_fadt *)table; + + /* + * The revision in the table header is the FADT's Major revision. The + * FADT also has a minor revision, which is stored in the FADT itself. + * + * TODO: Currently, we check for 6.5 as the minimum version to check + * for HW_REDUCED flag. However, once RISC-V updates are released in + * the ACPI spec, we need to update this check for exact minor revision + */ + if (table->revision < 6 || (table->revision == 6 && fadt->minor_revision < 5)) + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 6.5+\n", + table->revision, fadt->minor_revision); + + if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { + pr_err("FADT not ACPI hardware reduced compliant\n"); + ret = -EINVAL; + } + + /* + * acpi_get_table() creates FADT table mapping that + * should be released after parsing and before resuming boot + */ + acpi_put_table(table); + return ret; +} + +/* + * acpi_boot_table_init() called from setup_arch(), always. + * 1. find RSDP and get its address, and then find XSDT + * 2. extract all tables and checksums them all + * 3. check ACPI FADT HW reduced flag + * + * We can parse ACPI boot-time tables such as MADT after + * this function is called. + * + * On return ACPI is enabled if either: + * + * - ACPI tables are initialized and sanity checks passed + * - acpi=force was passed in the command line and ACPI was not disabled + * explicitly through acpi=off command line parameter + * + * ACPI is disabled on function return otherwise + */ +void __init acpi_boot_table_init(void) +{ + /* + * Enable ACPI instead of device tree unless + * - ACPI has been disabled explicitly (acpi=off), or + * - firmware has not populated ACPI ptr in EFI system table + * and ACPI has not been [force] enabled (acpi=on|force) + */ + if (param_acpi_off || + (!param_acpi_on && !param_acpi_force && + efi.acpi20 == EFI_INVALID_TABLE_ADDR)) + return; + + /* + * ACPI is disabled at this point. Enable it in order to parse + * the ACPI tables and carry out sanity checks + */ + enable_acpi(); + + /* + * If ACPI tables are initialized and FADT sanity checks passed, + * leave ACPI enabled and carry on booting; otherwise disable ACPI + * on initialization error. + * If acpi=force was passed on the command line it forces ACPI + * to be enabled even if its initialization failed. + */ + if (acpi_table_init() || acpi_fadt_sanity_check()) { + pr_err("Failed to init ACPI tables\n"); + if (!param_acpi_force) + disable_acpi(); + } +} + +static int acpi_parse_madt_rintc(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_rintc *rintc = (struct acpi_madt_rintc *)header; + int cpuid; + + if (!(rintc->flags & ACPI_MADT_ENABLED)) + return 0; + + cpuid = riscv_hartid_to_cpuid(rintc->hart_id); + /* + * When CONFIG_SMP is disabled, mapping won't be created for + * all cpus. + * CPUs more than num_possible_cpus, will be ignored. + */ + if (cpuid >= 0 && cpuid < num_possible_cpus()) + cpu_madt_rintc[cpuid] = *rintc; + + return 0; +} + +/* + * Instead of parsing (and freeing) the ACPI table, cache + * the RINTC structures since they are frequently used + * like in cpuinfo. + */ +void __init acpi_init_rintc_map(void) +{ + if (acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_madt_rintc, 0) <= 0) { + pr_err("No valid RINTC entries exist\n"); + BUG(); + } +} + +struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) +{ + return &cpu_madt_rintc[cpu]; +} + +u32 get_acpi_id_for_cpu(int cpu) +{ + return acpi_cpu_get_madt_rintc(cpu)->uid; +} + +/* + * __acpi_map_table() will be called before paging_init(), so early_ioremap() + * or early_memremap() should be called here to for ACPI table mapping. + */ +void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size) +{ + if (!size) + return NULL; + + return early_ioremap(phys, size); +} + +void __init __acpi_unmap_table(void __iomem *map, unsigned long size) +{ + if (!map || !size) + return; + + early_iounmap(map, size); +} + +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + efi_memory_desc_t *md, *region = NULL; + pgprot_t prot; + + if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP))) + return NULL; + + for_each_efi_memory_desc(md) { + u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + + if (phys < md->phys_addr || phys >= end) + continue; + + if (phys + size > end) { + pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n"); + return NULL; + } + region = md; + break; + } + + /* + * It is fine for AML to remap regions that are not represented in the + * EFI memory map at all, as it only describes normal memory, and MMIO + * regions that require a virtual mapping to make them accessible to + * the EFI runtime services. + */ + prot = PAGE_KERNEL_IO; + if (region) { + switch (region->type) { + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory\n"); + return NULL; + } + + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs. + * This particular use case only requires read access. + */ + fallthrough; + + case EFI_RUNTIME_SERVICES_CODE: + /* + * This would be unusual, but not problematic per se, + * as long as we take care not to create a writable + * mapping for executable code. + */ + prot = PAGE_KERNEL_RO; + break; + + case EFI_ACPI_RECLAIM_MEMORY: + /* + * ACPI reclaim memory is used to pass firmware tables + * and other data that is intended for consumption by + * the OS only, which may decide it wants to reclaim + * that memory and use it for something else. We never + * do that, but we usually add it to the linear map + * anyway, in which case we should use the existing + * mapping. + */ + if (memblock_is_map_memory(phys)) + return (void __iomem *)__va(phys); + fallthrough; + + default: + if (region->attribute & EFI_MEMORY_WB) + prot = PAGE_KERNEL; + else if ((region->attribute & EFI_MEMORY_WC) || + (region->attribute & EFI_MEMORY_WT)) + prot = pgprot_writecombine(PAGE_KERNEL); + } + } + + return ioremap_prot(phys, size, pgprot_val(prot)); +} + +#ifdef CONFIG_PCI + +/* + * These interfaces are defined just to enable building ACPI core. + * TODO: Update it with actual implementation when external interrupt + * controller support is added in RISC-V ACPI. + */ +int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 *val) +{ + return PCIBIOS_DEVICE_NOT_FOUND; +} + +int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 val) +{ + return PCIBIOS_DEVICE_NOT_FOUND; +} + +int acpi_pci_bus_find_domain_nr(struct pci_bus *bus) +{ + return -1; +} + +struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) +{ + return NULL; +} +#endif /* CONFIG_PCI */ diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c new file mode 100644 index 000000000000..319a1da0358b --- /dev/null +++ b/arch/riscv/kernel/alternative.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * alternative runtime patching + * inspired by the ARM64 and x86 version + * + * Copyright (C) 2021 Sifive. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/uaccess.h> +#include <asm/alternative.h> +#include <asm/module.h> +#include <asm/sections.h> +#include <asm/vdso.h> +#include <asm/vendorid_list.h> +#include <asm/sbi.h> +#include <asm/csr.h> +#include <asm/insn.h> +#include <asm/patch.h> + +struct cpu_manufacturer_info_t { + unsigned long vendor_id; + unsigned long arch_id; + unsigned long imp_id; + void (*patch_func)(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); +}; + +static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) +{ +#ifdef CONFIG_RISCV_M_MODE + cpu_mfr_info->vendor_id = csr_read(CSR_MVENDORID); + cpu_mfr_info->arch_id = csr_read(CSR_MARCHID); + cpu_mfr_info->imp_id = csr_read(CSR_MIMPID); +#else + cpu_mfr_info->vendor_id = sbi_get_mvendorid(); + cpu_mfr_info->arch_id = sbi_get_marchid(); + cpu_mfr_info->imp_id = sbi_get_mimpid(); +#endif + + switch (cpu_mfr_info->vendor_id) { +#ifdef CONFIG_ERRATA_ANDES + case ANDESTECH_VENDOR_ID: + cpu_mfr_info->patch_func = andes_errata_patch_func; + break; +#endif +#ifdef CONFIG_ERRATA_SIFIVE + case SIFIVE_VENDOR_ID: + cpu_mfr_info->patch_func = sifive_errata_patch_func; + break; +#endif +#ifdef CONFIG_ERRATA_THEAD + case THEAD_VENDOR_ID: + cpu_mfr_info->patch_func = thead_errata_patch_func; + break; +#endif + default: + cpu_mfr_info->patch_func = NULL; + } +} + +static u32 riscv_instruction_at(void *p) +{ + u16 *parcel = p; + + return (u32)parcel[0] | (u32)parcel[1] << 16; +} + +static void riscv_alternative_fix_auipc_jalr(void *ptr, u32 auipc_insn, + u32 jalr_insn, int patch_offset) +{ + u32 call[2] = { auipc_insn, jalr_insn }; + s32 imm; + + /* get and adjust new target address */ + imm = riscv_insn_extract_utype_itype_imm(auipc_insn, jalr_insn); + imm -= patch_offset; + + /* update instructions */ + riscv_insn_insert_utype_itype_imm(&call[0], &call[1], imm); + + /* patch the call place again */ + patch_text_nosync(ptr, call, sizeof(u32) * 2); +} + +static void riscv_alternative_fix_jal(void *ptr, u32 jal_insn, int patch_offset) +{ + s32 imm; + + /* get and adjust new target address */ + imm = riscv_insn_extract_jtype_imm(jal_insn); + imm -= patch_offset; + + /* update instruction */ + riscv_insn_insert_jtype_imm(&jal_insn, imm); + + /* patch the call place again */ + patch_text_nosync(ptr, &jal_insn, sizeof(u32)); +} + +void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, + int patch_offset) +{ + int num_insn = len / sizeof(u32); + int i; + + for (i = 0; i < num_insn; i++) { + u32 insn = riscv_instruction_at(alt_ptr + i * sizeof(u32)); + + /* + * May be the start of an auipc + jalr pair + * Needs to check that at least one more instruction + * is in the list. + */ + if (riscv_insn_is_auipc(insn) && i < num_insn - 1) { + u32 insn2 = riscv_instruction_at(alt_ptr + (i + 1) * sizeof(u32)); + + if (!riscv_insn_is_jalr(insn2)) + continue; + + /* if instruction pair is a call, it will use the ra register */ + if (RV_EXTRACT_RD_REG(insn) != 1) + continue; + + riscv_alternative_fix_auipc_jalr(alt_ptr + i * sizeof(u32), + insn, insn2, patch_offset); + i++; + } + + if (riscv_insn_is_jal(insn)) { + s32 imm = riscv_insn_extract_jtype_imm(insn); + + /* Don't modify jumps inside the alternative block */ + if ((alt_ptr + i * sizeof(u32) + imm) >= alt_ptr && + (alt_ptr + i * sizeof(u32) + imm) < (alt_ptr + len)) + continue; + + riscv_alternative_fix_jal(alt_ptr + i * sizeof(u32), + insn, patch_offset); + } + } +} + +/* + * This is called very early in the boot process (directly after we run + * a feature detect on the boot CPU). No need to worry about other CPUs + * here. + */ +static void __init_or_module _apply_alternatives(struct alt_entry *begin, + struct alt_entry *end, + unsigned int stage) +{ + struct cpu_manufacturer_info_t cpu_mfr_info; + + riscv_fill_cpu_mfr_info(&cpu_mfr_info); + + riscv_cpufeature_patch_func(begin, end, stage); + + if (!cpu_mfr_info.patch_func) + return; + + cpu_mfr_info.patch_func(begin, end, + cpu_mfr_info.arch_id, + cpu_mfr_info.imp_id, + stage); +} + +#ifdef CONFIG_MMU +static void __init apply_vdso_alternatives(void) +{ + const Elf_Ehdr *hdr; + const Elf_Shdr *shdr; + const Elf_Shdr *alt; + struct alt_entry *begin, *end; + + hdr = (Elf_Ehdr *)vdso_start; + shdr = (void *)hdr + hdr->e_shoff; + alt = find_section(hdr, shdr, ".alternative"); + if (!alt) + return; + + begin = (void *)hdr + alt->sh_offset, + end = (void *)hdr + alt->sh_offset + alt->sh_size, + + _apply_alternatives((struct alt_entry *)begin, + (struct alt_entry *)end, + RISCV_ALTERNATIVES_BOOT); +} +#else +static void __init apply_vdso_alternatives(void) { } +#endif + +void __init apply_boot_alternatives(void) +{ + /* If called on non-boot cpu things could go wrong */ + WARN_ON(smp_processor_id() != 0); + + _apply_alternatives((struct alt_entry *)__alt_start, + (struct alt_entry *)__alt_end, + RISCV_ALTERNATIVES_BOOT); + + apply_vdso_alternatives(); +} + +/* + * apply_early_boot_alternatives() is called from setup_vm() with MMU-off. + * + * Following requirements should be honoured for it to work correctly: + * 1) It should use PC-relative addressing for accessing kernel symbols. + * To achieve this we always use GCC cmodel=medany. + * 2) The compiler instrumentation for FTRACE will not work for setup_vm() + * so disable compiler instrumentation when FTRACE is enabled. + * + * Currently, the above requirements are honoured by using custom CFLAGS + * for alternative.o in kernel/Makefile. + */ +void __init apply_early_boot_alternatives(void) +{ +#ifdef CONFIG_RISCV_ALTERNATIVE_EARLY + _apply_alternatives((struct alt_entry *)__alt_start, + (struct alt_entry *)__alt_end, + RISCV_ALTERNATIVES_EARLY_BOOT); +#endif +} + +#ifdef CONFIG_MODULES +void apply_module_alternatives(void *start, size_t length) +{ + _apply_alternatives((struct alt_entry *)start, + (struct alt_entry *)(start + length), + RISCV_ALTERNATIVES_MODULE); +} +#endif diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 07cb9c10de4e..a03129f40c46 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -7,9 +7,17 @@ #define GENERATING_ASM_OFFSETS #include <linux/kbuild.h> +#include <linux/mm.h> #include <linux/sched.h> +#include <linux/suspend.h> +#include <asm/kvm_host.h> #include <asm/thread_info.h> #include <asm/ptrace.h> +#include <asm/cpu_ops_sbi.h> +#include <asm/stacktrace.h> +#include <asm/suspend.h> + +void asm_offsets(void); void asm_offsets(void) { @@ -27,15 +35,15 @@ 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_SP, task_struct, thread.sp); - OFFSET(TASK_STACK, task_struct, stack); - OFFSET(TASK_TI, task_struct, thread_info); 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); - OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); +#ifdef CONFIG_SHADOW_CALL_STACK + OFFSET(TASK_TI_SCS_SP, task_struct, thread_info.scs_sp); +#endif + OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu); OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]); @@ -69,6 +77,9 @@ void asm_offsets(void) OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]); OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]); OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr); +#ifdef CONFIG_STACKPROTECTOR + OFFSET(TSK_STACK_CANARY, task_struct, stack_canary); +#endif DEFINE(PT_SIZE, sizeof(struct pt_regs)); OFFSET(PT_EPC, pt_regs, epc); @@ -109,6 +120,166 @@ void asm_offsets(void) OFFSET(PT_BADADDR, pt_regs, badaddr); OFFSET(PT_CAUSE, pt_regs, cause); + OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs); + + OFFSET(HIBERN_PBE_ADDR, pbe, address); + OFFSET(HIBERN_PBE_ORIG, pbe, orig_address); + OFFSET(HIBERN_PBE_NEXT, pbe, next); + + OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero); + OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra); + OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp); + OFFSET(KVM_ARCH_GUEST_GP, kvm_vcpu_arch, guest_context.gp); + OFFSET(KVM_ARCH_GUEST_TP, kvm_vcpu_arch, guest_context.tp); + OFFSET(KVM_ARCH_GUEST_T0, kvm_vcpu_arch, guest_context.t0); + OFFSET(KVM_ARCH_GUEST_T1, kvm_vcpu_arch, guest_context.t1); + OFFSET(KVM_ARCH_GUEST_T2, kvm_vcpu_arch, guest_context.t2); + OFFSET(KVM_ARCH_GUEST_S0, kvm_vcpu_arch, guest_context.s0); + OFFSET(KVM_ARCH_GUEST_S1, kvm_vcpu_arch, guest_context.s1); + OFFSET(KVM_ARCH_GUEST_A0, kvm_vcpu_arch, guest_context.a0); + OFFSET(KVM_ARCH_GUEST_A1, kvm_vcpu_arch, guest_context.a1); + OFFSET(KVM_ARCH_GUEST_A2, kvm_vcpu_arch, guest_context.a2); + OFFSET(KVM_ARCH_GUEST_A3, kvm_vcpu_arch, guest_context.a3); + OFFSET(KVM_ARCH_GUEST_A4, kvm_vcpu_arch, guest_context.a4); + OFFSET(KVM_ARCH_GUEST_A5, kvm_vcpu_arch, guest_context.a5); + OFFSET(KVM_ARCH_GUEST_A6, kvm_vcpu_arch, guest_context.a6); + OFFSET(KVM_ARCH_GUEST_A7, kvm_vcpu_arch, guest_context.a7); + OFFSET(KVM_ARCH_GUEST_S2, kvm_vcpu_arch, guest_context.s2); + OFFSET(KVM_ARCH_GUEST_S3, kvm_vcpu_arch, guest_context.s3); + OFFSET(KVM_ARCH_GUEST_S4, kvm_vcpu_arch, guest_context.s4); + OFFSET(KVM_ARCH_GUEST_S5, kvm_vcpu_arch, guest_context.s5); + OFFSET(KVM_ARCH_GUEST_S6, kvm_vcpu_arch, guest_context.s6); + OFFSET(KVM_ARCH_GUEST_S7, kvm_vcpu_arch, guest_context.s7); + OFFSET(KVM_ARCH_GUEST_S8, kvm_vcpu_arch, guest_context.s8); + OFFSET(KVM_ARCH_GUEST_S9, kvm_vcpu_arch, guest_context.s9); + OFFSET(KVM_ARCH_GUEST_S10, kvm_vcpu_arch, guest_context.s10); + OFFSET(KVM_ARCH_GUEST_S11, kvm_vcpu_arch, guest_context.s11); + OFFSET(KVM_ARCH_GUEST_T3, kvm_vcpu_arch, guest_context.t3); + OFFSET(KVM_ARCH_GUEST_T4, kvm_vcpu_arch, guest_context.t4); + OFFSET(KVM_ARCH_GUEST_T5, kvm_vcpu_arch, guest_context.t5); + OFFSET(KVM_ARCH_GUEST_T6, kvm_vcpu_arch, guest_context.t6); + OFFSET(KVM_ARCH_GUEST_SEPC, kvm_vcpu_arch, guest_context.sepc); + OFFSET(KVM_ARCH_GUEST_SSTATUS, kvm_vcpu_arch, guest_context.sstatus); + OFFSET(KVM_ARCH_GUEST_HSTATUS, kvm_vcpu_arch, guest_context.hstatus); + OFFSET(KVM_ARCH_GUEST_SCOUNTEREN, kvm_vcpu_arch, guest_csr.scounteren); + + OFFSET(KVM_ARCH_HOST_ZERO, kvm_vcpu_arch, host_context.zero); + OFFSET(KVM_ARCH_HOST_RA, kvm_vcpu_arch, host_context.ra); + OFFSET(KVM_ARCH_HOST_SP, kvm_vcpu_arch, host_context.sp); + OFFSET(KVM_ARCH_HOST_GP, kvm_vcpu_arch, host_context.gp); + OFFSET(KVM_ARCH_HOST_TP, kvm_vcpu_arch, host_context.tp); + OFFSET(KVM_ARCH_HOST_T0, kvm_vcpu_arch, host_context.t0); + OFFSET(KVM_ARCH_HOST_T1, kvm_vcpu_arch, host_context.t1); + OFFSET(KVM_ARCH_HOST_T2, kvm_vcpu_arch, host_context.t2); + OFFSET(KVM_ARCH_HOST_S0, kvm_vcpu_arch, host_context.s0); + OFFSET(KVM_ARCH_HOST_S1, kvm_vcpu_arch, host_context.s1); + OFFSET(KVM_ARCH_HOST_A0, kvm_vcpu_arch, host_context.a0); + OFFSET(KVM_ARCH_HOST_A1, kvm_vcpu_arch, host_context.a1); + OFFSET(KVM_ARCH_HOST_A2, kvm_vcpu_arch, host_context.a2); + OFFSET(KVM_ARCH_HOST_A3, kvm_vcpu_arch, host_context.a3); + OFFSET(KVM_ARCH_HOST_A4, kvm_vcpu_arch, host_context.a4); + OFFSET(KVM_ARCH_HOST_A5, kvm_vcpu_arch, host_context.a5); + OFFSET(KVM_ARCH_HOST_A6, kvm_vcpu_arch, host_context.a6); + OFFSET(KVM_ARCH_HOST_A7, kvm_vcpu_arch, host_context.a7); + OFFSET(KVM_ARCH_HOST_S2, kvm_vcpu_arch, host_context.s2); + OFFSET(KVM_ARCH_HOST_S3, kvm_vcpu_arch, host_context.s3); + OFFSET(KVM_ARCH_HOST_S4, kvm_vcpu_arch, host_context.s4); + OFFSET(KVM_ARCH_HOST_S5, kvm_vcpu_arch, host_context.s5); + OFFSET(KVM_ARCH_HOST_S6, kvm_vcpu_arch, host_context.s6); + OFFSET(KVM_ARCH_HOST_S7, kvm_vcpu_arch, host_context.s7); + OFFSET(KVM_ARCH_HOST_S8, kvm_vcpu_arch, host_context.s8); + OFFSET(KVM_ARCH_HOST_S9, kvm_vcpu_arch, host_context.s9); + OFFSET(KVM_ARCH_HOST_S10, kvm_vcpu_arch, host_context.s10); + OFFSET(KVM_ARCH_HOST_S11, kvm_vcpu_arch, host_context.s11); + OFFSET(KVM_ARCH_HOST_T3, kvm_vcpu_arch, host_context.t3); + OFFSET(KVM_ARCH_HOST_T4, kvm_vcpu_arch, host_context.t4); + OFFSET(KVM_ARCH_HOST_T5, kvm_vcpu_arch, host_context.t5); + OFFSET(KVM_ARCH_HOST_T6, kvm_vcpu_arch, host_context.t6); + OFFSET(KVM_ARCH_HOST_SEPC, kvm_vcpu_arch, host_context.sepc); + OFFSET(KVM_ARCH_HOST_SSTATUS, kvm_vcpu_arch, host_context.sstatus); + OFFSET(KVM_ARCH_HOST_HSTATUS, kvm_vcpu_arch, host_context.hstatus); + OFFSET(KVM_ARCH_HOST_SSCRATCH, kvm_vcpu_arch, host_sscratch); + OFFSET(KVM_ARCH_HOST_STVEC, kvm_vcpu_arch, host_stvec); + OFFSET(KVM_ARCH_HOST_SCOUNTEREN, kvm_vcpu_arch, host_scounteren); + + OFFSET(KVM_ARCH_TRAP_SEPC, kvm_cpu_trap, sepc); + OFFSET(KVM_ARCH_TRAP_SCAUSE, kvm_cpu_trap, scause); + OFFSET(KVM_ARCH_TRAP_STVAL, kvm_cpu_trap, stval); + OFFSET(KVM_ARCH_TRAP_HTVAL, kvm_cpu_trap, htval); + OFFSET(KVM_ARCH_TRAP_HTINST, kvm_cpu_trap, htinst); + + /* F extension */ + + OFFSET(KVM_ARCH_FP_F_F0, kvm_cpu_context, fp.f.f[0]); + OFFSET(KVM_ARCH_FP_F_F1, kvm_cpu_context, fp.f.f[1]); + OFFSET(KVM_ARCH_FP_F_F2, kvm_cpu_context, fp.f.f[2]); + OFFSET(KVM_ARCH_FP_F_F3, kvm_cpu_context, fp.f.f[3]); + OFFSET(KVM_ARCH_FP_F_F4, kvm_cpu_context, fp.f.f[4]); + OFFSET(KVM_ARCH_FP_F_F5, kvm_cpu_context, fp.f.f[5]); + OFFSET(KVM_ARCH_FP_F_F6, kvm_cpu_context, fp.f.f[6]); + OFFSET(KVM_ARCH_FP_F_F7, kvm_cpu_context, fp.f.f[7]); + OFFSET(KVM_ARCH_FP_F_F8, kvm_cpu_context, fp.f.f[8]); + OFFSET(KVM_ARCH_FP_F_F9, kvm_cpu_context, fp.f.f[9]); + OFFSET(KVM_ARCH_FP_F_F10, kvm_cpu_context, fp.f.f[10]); + OFFSET(KVM_ARCH_FP_F_F11, kvm_cpu_context, fp.f.f[11]); + OFFSET(KVM_ARCH_FP_F_F12, kvm_cpu_context, fp.f.f[12]); + OFFSET(KVM_ARCH_FP_F_F13, kvm_cpu_context, fp.f.f[13]); + OFFSET(KVM_ARCH_FP_F_F14, kvm_cpu_context, fp.f.f[14]); + OFFSET(KVM_ARCH_FP_F_F15, kvm_cpu_context, fp.f.f[15]); + OFFSET(KVM_ARCH_FP_F_F16, kvm_cpu_context, fp.f.f[16]); + OFFSET(KVM_ARCH_FP_F_F17, kvm_cpu_context, fp.f.f[17]); + OFFSET(KVM_ARCH_FP_F_F18, kvm_cpu_context, fp.f.f[18]); + OFFSET(KVM_ARCH_FP_F_F19, kvm_cpu_context, fp.f.f[19]); + OFFSET(KVM_ARCH_FP_F_F20, kvm_cpu_context, fp.f.f[20]); + OFFSET(KVM_ARCH_FP_F_F21, kvm_cpu_context, fp.f.f[21]); + OFFSET(KVM_ARCH_FP_F_F22, kvm_cpu_context, fp.f.f[22]); + OFFSET(KVM_ARCH_FP_F_F23, kvm_cpu_context, fp.f.f[23]); + OFFSET(KVM_ARCH_FP_F_F24, kvm_cpu_context, fp.f.f[24]); + OFFSET(KVM_ARCH_FP_F_F25, kvm_cpu_context, fp.f.f[25]); + OFFSET(KVM_ARCH_FP_F_F26, kvm_cpu_context, fp.f.f[26]); + OFFSET(KVM_ARCH_FP_F_F27, kvm_cpu_context, fp.f.f[27]); + OFFSET(KVM_ARCH_FP_F_F28, kvm_cpu_context, fp.f.f[28]); + OFFSET(KVM_ARCH_FP_F_F29, kvm_cpu_context, fp.f.f[29]); + OFFSET(KVM_ARCH_FP_F_F30, kvm_cpu_context, fp.f.f[30]); + OFFSET(KVM_ARCH_FP_F_F31, kvm_cpu_context, fp.f.f[31]); + OFFSET(KVM_ARCH_FP_F_FCSR, kvm_cpu_context, fp.f.fcsr); + + /* D extension */ + + OFFSET(KVM_ARCH_FP_D_F0, kvm_cpu_context, fp.d.f[0]); + OFFSET(KVM_ARCH_FP_D_F1, kvm_cpu_context, fp.d.f[1]); + OFFSET(KVM_ARCH_FP_D_F2, kvm_cpu_context, fp.d.f[2]); + OFFSET(KVM_ARCH_FP_D_F3, kvm_cpu_context, fp.d.f[3]); + OFFSET(KVM_ARCH_FP_D_F4, kvm_cpu_context, fp.d.f[4]); + OFFSET(KVM_ARCH_FP_D_F5, kvm_cpu_context, fp.d.f[5]); + OFFSET(KVM_ARCH_FP_D_F6, kvm_cpu_context, fp.d.f[6]); + OFFSET(KVM_ARCH_FP_D_F7, kvm_cpu_context, fp.d.f[7]); + OFFSET(KVM_ARCH_FP_D_F8, kvm_cpu_context, fp.d.f[8]); + OFFSET(KVM_ARCH_FP_D_F9, kvm_cpu_context, fp.d.f[9]); + OFFSET(KVM_ARCH_FP_D_F10, kvm_cpu_context, fp.d.f[10]); + OFFSET(KVM_ARCH_FP_D_F11, kvm_cpu_context, fp.d.f[11]); + OFFSET(KVM_ARCH_FP_D_F12, kvm_cpu_context, fp.d.f[12]); + OFFSET(KVM_ARCH_FP_D_F13, kvm_cpu_context, fp.d.f[13]); + OFFSET(KVM_ARCH_FP_D_F14, kvm_cpu_context, fp.d.f[14]); + OFFSET(KVM_ARCH_FP_D_F15, kvm_cpu_context, fp.d.f[15]); + OFFSET(KVM_ARCH_FP_D_F16, kvm_cpu_context, fp.d.f[16]); + OFFSET(KVM_ARCH_FP_D_F17, kvm_cpu_context, fp.d.f[17]); + OFFSET(KVM_ARCH_FP_D_F18, kvm_cpu_context, fp.d.f[18]); + OFFSET(KVM_ARCH_FP_D_F19, kvm_cpu_context, fp.d.f[19]); + OFFSET(KVM_ARCH_FP_D_F20, kvm_cpu_context, fp.d.f[20]); + OFFSET(KVM_ARCH_FP_D_F21, kvm_cpu_context, fp.d.f[21]); + OFFSET(KVM_ARCH_FP_D_F22, kvm_cpu_context, fp.d.f[22]); + OFFSET(KVM_ARCH_FP_D_F23, kvm_cpu_context, fp.d.f[23]); + OFFSET(KVM_ARCH_FP_D_F24, kvm_cpu_context, fp.d.f[24]); + OFFSET(KVM_ARCH_FP_D_F25, kvm_cpu_context, fp.d.f[25]); + OFFSET(KVM_ARCH_FP_D_F26, kvm_cpu_context, fp.d.f[26]); + OFFSET(KVM_ARCH_FP_D_F27, kvm_cpu_context, fp.d.f[27]); + OFFSET(KVM_ARCH_FP_D_F28, kvm_cpu_context, fp.d.f[28]); + OFFSET(KVM_ARCH_FP_D_F29, kvm_cpu_context, fp.d.f[29]); + OFFSET(KVM_ARCH_FP_D_F30, kvm_cpu_context, fp.d.f[30]); + OFFSET(KVM_ARCH_FP_D_F31, kvm_cpu_context, fp.d.f[31]); + OFFSET(KVM_ARCH_FP_D_FCSR, kvm_cpu_context, fp.d.fcsr); + /* * THREAD_{F,X}* might be larger than a S-type offset can handle, but * these are used in performance-sensitive assembly so we can't resort @@ -309,4 +480,12 @@ void asm_offsets(void) * ensures the alignment is sane. */ DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN)); + + OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr); + OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr); + OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr); + + DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN)); + OFFSET(STACKFRAME_FP, stackframe, fp); + OFFSET(STACKFRAME_RA, stackframe, ra); } diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index 4c90c07d8c39..09e9b88110d1 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -3,62 +3,75 @@ * Copyright (C) 2017 SiFive */ -#include <linux/cacheinfo.h> #include <linux/cpu.h> #include <linux/of.h> -#include <linux/of_device.h> +#include <asm/cacheinfo.h> -static void ci_leaf_init(struct cacheinfo *this_leaf, - struct device_node *node, - enum cache_type type, unsigned int level) +static struct riscv_cacheinfo_ops *rv_cache_ops; + +void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops) { - this_leaf->level = level; - this_leaf->type = type; + rv_cache_ops = ops; } +EXPORT_SYMBOL_GPL(riscv_set_cacheinfo_ops); -static int __init_cache_level(unsigned int cpu) +const struct attribute_group * +cache_get_priv_group(struct cacheinfo *this_leaf) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - struct device_node *np = of_cpu_device_node_get(cpu); - struct device_node *prev = NULL; - int levels = 0, leaves = 0, level; + if (rv_cache_ops && rv_cache_ops->get_priv_group) + return rv_cache_ops->get_priv_group(this_leaf); + return NULL; +} - if (of_property_read_bool(np, "cache-size")) - ++leaves; - if (of_property_read_bool(np, "i-cache-size")) - ++leaves; - if (of_property_read_bool(np, "d-cache-size")) - ++leaves; - if (leaves > 0) - levels = 1; +static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) +{ + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); + struct cacheinfo *this_leaf; + int index; - prev = np; - while ((np = of_find_next_cache_node(np))) { - of_node_put(prev); - prev = np; - if (!of_device_is_compatible(np, "cache")) - break; - if (of_property_read_u32(np, "cache-level", &level)) - break; - if (level <= levels) - break; - if (of_property_read_bool(np, "cache-size")) - ++leaves; - if (of_property_read_bool(np, "i-cache-size")) - ++leaves; - if (of_property_read_bool(np, "d-cache-size")) - ++leaves; - levels = level; + for (index = 0; index < this_cpu_ci->num_leaves; index++) { + this_leaf = this_cpu_ci->info_list + index; + if (this_leaf->level == level && this_leaf->type == type) + return this_leaf; } - of_node_put(np); - this_cpu_ci->num_levels = levels; - this_cpu_ci->num_leaves = leaves; + return NULL; +} - return 0; +uintptr_t get_cache_size(u32 level, enum cache_type type) +{ + struct cacheinfo *this_leaf = get_cacheinfo(level, type); + + return this_leaf ? this_leaf->size : 0; } -static int __populate_cache_leaves(unsigned int cpu) +uintptr_t get_cache_geometry(u32 level, enum cache_type type) +{ + struct cacheinfo *this_leaf = get_cacheinfo(level, type); + + return this_leaf ? (this_leaf->ways_of_associativity << 16 | + this_leaf->coherency_line_size) : + 0; +} + +static void ci_leaf_init(struct cacheinfo *this_leaf, + struct device_node *node, + enum cache_type type, unsigned int level) +{ + this_leaf->level = level; + this_leaf->type = type; +} + +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; @@ -95,6 +108,3 @@ static int __populate_cache_leaves(unsigned int cpu) return 0; } - -DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level) -DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves) diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c new file mode 100644 index 000000000000..6ec9dbd7292e --- /dev/null +++ b/arch/riscv/kernel/cfi.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2023 Google LLC + */ +#include <linux/cfi.h> +#include <asm/insn.h> + +/* + * Returns the target address and the expected type when regs->epc points + * to a compiler-generated CFI trap. + */ +static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target, + u32 *type) +{ + unsigned long *regs_ptr = (unsigned long *)regs; + int rs1_num; + u32 insn; + + *target = *type = 0; + + /* + * The compiler generates the following instruction sequence + * for indirect call checks: + * + *  lw t1, -4(<reg>) + * lui t2, <hi20> + * addiw t2, t2, <lo12> + * beq t1, t2, .Ltmp1 + * ebreak ; <- regs->epc + * .Ltmp1: + * jalr <reg> + * + * We can read the expected type and the target address from the + * registers passed to the beq/jalr instructions. + */ + if (get_kernel_nofault(insn, (void *)regs->epc - 4)) + return false; + if (!riscv_insn_is_beq(insn)) + return false; + + *type = (u32)regs_ptr[RV_EXTRACT_RS1_REG(insn)]; + + if (get_kernel_nofault(insn, (void *)regs->epc) || + get_kernel_nofault(insn, (void *)regs->epc + GET_INSN_LENGTH(insn))) + return false; + + if (riscv_insn_is_jalr(insn)) + rs1_num = RV_EXTRACT_RS1_REG(insn); + else if (riscv_insn_is_c_jalr(insn)) + rs1_num = RVC_EXTRACT_C2_RS1_REG(insn); + else + return false; + + *target = regs_ptr[rs1_num]; + + return true; +} + +/* + * Checks if the ebreak trap is because of a CFI failure, and handles the trap + * if needed. Returns a bug_trap_type value similarly to report_bug. + */ +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + unsigned long target; + u32 type; + + if (!is_cfi_trap(regs->epc)) + return BUG_TRAP_TYPE_NONE; + + if (!decode_cfi_insn(regs, &target, &type)) + return report_cfi_failure_noaddr(regs, regs->epc); + + return report_cfi_failure(regs, regs->epc, &target, type); +} diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c deleted file mode 100644 index 3647980d14c3..000000000000 --- a/arch/riscv/kernel/clint.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2019 Christoph Hellwig. - */ - -#include <linux/io.h> -#include <linux/of_address.h> -#include <linux/types.h> -#include <asm/clint.h> -#include <asm/csr.h> -#include <asm/timex.h> -#include <asm/smp.h> - -/* - * This is the layout used by the SiFive clint, which is also shared by the qemu - * virt platform, and the Kendryte KD210 at least. - */ -#define CLINT_IPI_OFF 0 -#define CLINT_TIME_CMP_OFF 0x4000 -#define CLINT_TIME_VAL_OFF 0xbff8 - -u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void) -{ - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "riscv,clint0"); - if (!np) { - panic("clint not found"); - return; - } - - base = of_iomap(np, 0); - if (!base) - panic("could not map CLINT"); - - clint_ipi_base = base + CLINT_IPI_OFF; - riscv_time_cmp = base + CLINT_TIME_CMP_OFF; - riscv_time_val = base + CLINT_TIME_VAL_OFF; - - clint_clear_ipi(boot_cpu_hartid); -} diff --git a/arch/riscv/kernel/compat_signal.c b/arch/riscv/kernel/compat_signal.c new file mode 100644 index 000000000000..6ec4e34255a9 --- /dev/null +++ b/arch/riscv/kernel/compat_signal.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/compat.h> +#include <linux/signal.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> +#include <linux/linkage.h> + +#include <asm/csr.h> +#include <asm/signal32.h> +#include <asm/switch_to.h> +#include <asm/ucontext.h> +#include <asm/vdso.h> + +#define COMPAT_DEBUG_SIG 0 + +struct compat_sigcontext { + struct compat_user_regs_struct sc_regs; + union __riscv_fp_state sc_fpregs; +}; + +struct compat_ucontext { + compat_ulong_t uc_flags; + struct compat_ucontext *uc_link; + compat_stack_t uc_stack; + sigset_t uc_sigmask; + /* There's some padding here to allow sigset_t to be expanded in the + * future. Though this is unlikely, other architectures put uc_sigmask + * at the end of this structure and explicitly state it can be + * expanded, so we didn't want to box ourselves in here. */ + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; + /* We can't put uc_sigmask at the end of this structure because we need + * to be able to expand sigcontext in the future. For example, the + * vector ISA extension will almost certainly add ISA state. We want + * to ensure all user-visible ISA state can be saved and restored via a + * ucontext, so we're putting this at the end in order to allow for + * infinite extensibility. Since we know this will be extended and we + * assume sigset_t won't be extended an extreme amount, we're + * prioritizing this. */ + struct compat_sigcontext uc_mcontext; +}; + +struct compat_rt_sigframe { + struct compat_siginfo info; + struct compat_ucontext uc; +}; + +#ifdef CONFIG_FPU +static long compat_restore_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); + if (unlikely(err)) + return err; + + fstate_restore(current, regs); + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + u32 value; + + err = __get_user(value, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + if (value != 0) + return -EINVAL; + } + + return err; +} + +static long compat_save_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + fstate_save(current, regs); + err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + if (unlikely(err)) + return err; + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + err = __put_user(0, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + } + + return err; +} +#else +#define compat_save_fp_state(task, regs) (0) +#define compat_restore_fp_state(task, regs) (0) +#endif + +static long compat_restore_sigcontext(struct pt_regs *regs, + struct compat_sigcontext __user *sc) +{ + long err; + struct compat_user_regs_struct cregs; + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs)); + + cregs_to_regs(&cregs, regs); + + /* Restore the floating-point state. */ + if (has_fpu()) + err |= compat_restore_fp_state(regs, &sc->sc_fpregs); + return err; +} + +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct compat_rt_sigframe __user *frame; + struct task_struct *task; + sigset_t set; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + frame = (struct compat_rt_sigframe __user *)regs->sp; + + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + set_current_blocked(&set); + + if (compat_restore_sigcontext(regs, &frame->uc.uc_mcontext)) + goto badframe; + + if (compat_restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->a0; + +badframe: + task = current; + if (show_unhandled_signals) { + pr_info_ratelimited( + "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n", + task->comm, task_pid_nr(task), __func__, + frame, (void *)regs->epc, (void *)regs->sp); + } + force_sig(SIGSEGV); + return 0; +} + +static long compat_setup_sigcontext(struct compat_rt_sigframe __user *frame, + struct pt_regs *regs) +{ + struct compat_sigcontext __user *sc = &frame->uc.uc_mcontext; + struct compat_user_regs_struct cregs; + long err; + + regs_to_cregs(&cregs, regs); + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_to_user(&sc->sc_regs, &cregs, sizeof(sc->sc_regs)); + /* Save the floating-point state. */ + if (has_fpu()) + err |= compat_save_fp_state(regs, &sc->sc_fpregs); + return err; +} + +static inline void __user *compat_get_sigframe(struct ksignal *ksig, + struct pt_regs *regs, size_t framesize) +{ + unsigned long sp; + /* Default to using normal stack */ + sp = regs->sp; + + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user __force *)(-1UL); + + /* This is the X/Open sanctioned signal stack switching. */ + sp = sigsp(sp, ksig) - framesize; + + /* Align the stack frame. */ + sp &= ~0xfUL; + + return (void __user *)sp; +} + +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + struct compat_rt_sigframe __user *frame; + long err = 0; + + frame = compat_get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(frame, sizeof(*frame))) + return -EFAULT; + + err |= copy_siginfo_to_user32(&frame->info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(NULL, &frame->uc.uc_link); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + err |= compat_setup_sigcontext(frame, regs); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + return -EFAULT; + + regs->ra = (unsigned long)COMPAT_VDSO_SYMBOL( + current->mm->context.vdso, rt_sigreturn); + + /* + * Set up registers for signal handler. + * Registers that we don't modify keep the value they had from + * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). + */ + regs->epc = (unsigned long)ksig->ka.sa.sa_handler; + regs->sp = (unsigned long)frame; + regs->a0 = ksig->sig; /* a0: signal number */ + regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */ + regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */ + +#if COMPAT_DEBUG_SIG + pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n", + current->comm, task_pid_nr(current), ksig->sig, + (void *)regs->epc, (void *)regs->ra, frame); +#endif + + return 0; +} diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c new file mode 100644 index 000000000000..ad7f2d712f5f --- /dev/null +++ b/arch/riscv/kernel/compat_syscall_table.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define __SYSCALL_COMPAT + +#include <linux/compat.h> +#include <linux/syscalls.h> +#include <asm-generic/mman-common.h> +#include <asm-generic/syscalls.h> +#include <asm/syscall.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) asmlinkage long __riscv_##call(const struct pt_regs *); +#include <asm/unistd.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = __riscv_##call, + +asmlinkage long compat_sys_rt_sigreturn(void); + +void * const compat_sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, +#include <asm/unistd.h> +}; diff --git a/arch/riscv/kernel/compat_vdso/.gitignore b/arch/riscv/kernel/compat_vdso/.gitignore new file mode 100644 index 000000000000..19d83d846c1e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +compat_vdso.lds diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile new file mode 100644 index 000000000000..62fa393b2eb2 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -0,0 +1,78 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for compat_vdso +# + +# Symbols present in the compat_vdso +compat_vdso-syms = rt_sigreturn +compat_vdso-syms += getcpu +compat_vdso-syms += flush_icache + +COMPAT_CC := $(CC) +COMPAT_LD := $(LD) + +# binutils 2.35 does not support the zifencei extension, but in the ISA +# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI. +ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +else + COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32 +endif +COMPAT_LD_FLAGS := -melf32lriscv + +# Disable attributes, as they're useless and break the build. +COMPAT_CC_FLAGS += $(call cc-option,-mno-riscv-attribute) +COMPAT_CC_FLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) + +# Files to link into the compat_vdso +obj-compat_vdso = $(patsubst %, %.o, $(compat_vdso-syms)) note.o + +# Build rules +targets := $(obj-compat_vdso) compat_vdso.so compat_vdso.so.dbg compat_vdso.lds +obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso)) + +obj-y += compat_vdso.o +CPPFLAGS_compat_vdso.lds += -P -C -DCOMPAT_VDSO -U$(ARCH) + +# Disable profiling and instrumentation for VDSO code +GCOV_PROFILE := n +KCOV_INSTRUMENT := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n + +# Force dependency +$(obj)/compat_vdso.o: $(obj)/compat_vdso.so + +# link rule for the .so file, .lds has to be first +$(obj)/compat_vdso.so.dbg: $(obj)/compat_vdso.lds $(obj-compat_vdso) FORCE + $(call if_changed,compat_vdsold) +LDFLAGS_compat_vdso.so.dbg = -shared -S -soname=linux-compat_vdso.so.1 \ + --build-id=sha1 --hash-style=both --eh-frame-hdr + +$(obj-compat_vdso): %.o: %.S FORCE + $(call if_changed_dep,compat_vdsoas) + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# Generate VDSO offsets using helper script +gen-compat_vdsosym := $(srctree)/$(src)/gen_compat_vdso_offsets.sh +quiet_cmd_compat_vdsosym = VDSOSYM $@ + cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@ + +include/generated/compat_vdso-offsets.h: $(obj)/compat_vdso.so.dbg FORCE + $(call if_changed,compat_vdsosym) + +# actual build commands +# The DSO images are built using a special linker script +# Make sure only to export the intended __compat_vdso_xxx symbol offsets. +quiet_cmd_compat_vdsold = VDSOLD $@ + cmd_compat_vdsold = $(COMPAT_LD) $(ld_flags) $(COMPAT_LD_FLAGS) -T $(filter-out FORCE,$^) -o $@.tmp && \ + $(OBJCOPY) $(patsubst %, -G __compat_vdso_%, $(compat_vdso-syms)) $@.tmp $@ && \ + rm $@.tmp + +# actual build commands +quiet_cmd_compat_vdsoas = VDSOAS $@ + cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.S b/arch/riscv/kernel/compat_vdso/compat_vdso.S new file mode 100644 index 000000000000..ffd66237e091 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.S @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#define vdso_start compat_vdso_start +#define vdso_end compat_vdso_end + +#define __VDSO_PATH "arch/riscv/kernel/compat_vdso/compat_vdso.so" + +#include "../vdso/vdso.S" diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S new file mode 100644 index 000000000000..c7c9355d311e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/vdso.lds.S" diff --git a/arch/riscv/kernel/compat_vdso/flush_icache.S b/arch/riscv/kernel/compat_vdso/flush_icache.S new file mode 100644 index 000000000000..523dd8b96045 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/flush_icache.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/flush_icache.S" diff --git a/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh new file mode 100755 index 000000000000..8ac070c783b3 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +LC_ALL=C +sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define compat\2_offset\t0x\1/p' diff --git a/arch/riscv/kernel/compat_vdso/getcpu.S b/arch/riscv/kernel/compat_vdso/getcpu.S new file mode 100644 index 000000000000..10f463efe271 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/getcpu.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/getcpu.S" diff --git a/arch/riscv/kernel/compat_vdso/note.S b/arch/riscv/kernel/compat_vdso/note.S new file mode 100644 index 000000000000..b10312907542 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/note.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/note.S" diff --git a/arch/riscv/kernel/compat_vdso/rt_sigreturn.S b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S new file mode 100644 index 000000000000..884aada4facc --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/rt_sigreturn.S" diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S new file mode 100644 index 000000000000..2b3d9398c113 --- /dev/null +++ b/arch/riscv/kernel/copy-unaligned.S @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos Inc. */ + +#include <linux/linkage.h> +#include <asm/asm.h> + + .text + +/* void __riscv_copy_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 8 * SZREG */ +SYM_FUNC_START(__riscv_copy_words_unaligned) + andi a4, a2, ~((8*SZREG)-1) + beqz a4, 2f + add a3, a1, a4 +1: + REG_L a4, 0(a1) + REG_L a5, SZREG(a1) + REG_L a6, 2*SZREG(a1) + REG_L a7, 3*SZREG(a1) + REG_L t0, 4*SZREG(a1) + REG_L t1, 5*SZREG(a1) + REG_L t2, 6*SZREG(a1) + REG_L t3, 7*SZREG(a1) + REG_S a4, 0(a0) + REG_S a5, SZREG(a0) + REG_S a6, 2*SZREG(a0) + REG_S a7, 3*SZREG(a0) + REG_S t0, 4*SZREG(a0) + REG_S t1, 5*SZREG(a0) + REG_S t2, 6*SZREG(a0) + REG_S t3, 7*SZREG(a0) + addi a0, a0, 8*SZREG + addi a1, a1, 8*SZREG + bltu a1, a3, 1b + +2: + ret +SYM_FUNC_END(__riscv_copy_words_unaligned) + +/* void __riscv_copy_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_bytes_unaligned) + andi a4, a2, ~(8-1) + beqz a4, 2f + add a3, a1, a4 +1: + lb a4, 0(a1) + lb a5, 1(a1) + lb a6, 2(a1) + lb a7, 3(a1) + lb t0, 4(a1) + lb t1, 5(a1) + lb t2, 6(a1) + lb t3, 7(a1) + sb a4, 0(a0) + sb a5, 1(a0) + sb a6, 2(a0) + sb a7, 3(a0) + sb t0, 4(a0) + sb t1, 5(a0) + sb t2, 6(a0) + sb t3, 7(a0) + addi a0, a0, 8 + addi a1, a1, 8 + bltu a1, a3, 1b + +2: + ret +SYM_FUNC_END(__riscv_copy_bytes_unaligned) diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h new file mode 100644 index 000000000000..e3d70d35b708 --- /dev/null +++ b/arch/riscv/kernel/copy-unaligned.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos, Inc. + */ +#ifndef __RISCV_KERNEL_COPY_UNALIGNED_H +#define __RISCV_KERNEL_COPY_UNALIGNED_H + +#include <linux/types.h> + +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); + +#endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */ diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c new file mode 100644 index 000000000000..28b58fc5ad19 --- /dev/null +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/err.h> +#include <linux/irq.h> +#include <linux/cpuhotplug.h> +#include <linux/cpu.h> +#include <linux/sched/hotplug.h> +#include <asm/irq.h> +#include <asm/cpu_ops.h> +#include <asm/numa.h> +#include <asm/smp.h> + +bool cpu_has_hotplug(unsigned int cpu) +{ + if (cpu_ops->cpu_stop) + return true; + + return false; +} + +/* + * __cpu_disable runs on the processor to be shutdown. + */ +int __cpu_disable(void) +{ + unsigned int cpu = smp_processor_id(); + + if (!cpu_ops->cpu_stop) + return -EOPNOTSUPP; + + remove_cpu_topology(cpu); + numa_remove_cpu(cpu); + set_cpu_online(cpu, false); + riscv_ipi_disable(); + irq_migrate_all_off_this_cpu(); + + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +/* + * Called on the thread which is asking for a CPU to be shutdown, if the + * CPU reported dead to the hotplug core. + */ +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) +{ + int ret = 0; + + pr_notice("CPU%u: off\n", cpu); + + /* Verify from the firmware if the cpu is really stopped*/ + 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); +} + +/* + * Called from the idle thread for the CPU which has been shutdown. + */ +void __noreturn arch_cpu_idle_dead(void) +{ + idle_task_exit(); + + cpuhp_ap_report_dead(); + + cpu_ops->cpu_stop(); + /* It should never reach here */ + BUG(); +} +#endif diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 40a3c442ac5f..d11d6320fb0d 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -3,73 +3,254 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/acpi.h> +#include <linux/cpu.h> +#include <linux/ctype.h> #include <linux/init.h> #include <linux/seq_file.h> #include <linux/of.h> +#include <asm/acpi.h> +#include <asm/cpufeature.h> +#include <asm/csr.h> +#include <asm/hwcap.h> +#include <asm/sbi.h> #include <asm/smp.h> +#include <asm/pgtable.h> + +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_hartid_map(cpu); +} /* * Returns the hart ID of the given device tree node, or -ENODEV if the node * isn't an enabled and valid RISC-V hart node. */ -int riscv_of_processor_hartid(struct device_node *node) +int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) +{ + int cpu; + + *hart = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hart == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + + cpu = riscv_hartid_to_cpuid(*hart); + if (cpu < 0) + return cpu; + + if (!cpu_possible(cpu)) + return -ENODEV; + + return 0; +} + +int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) { const char *isa; - u32 hart; if (!of_device_is_compatible(node, "riscv")) { pr_warn("Found incompatible CPU\n"); return -ENODEV; } - if (of_property_read_u32(node, "reg", &hart)) { + *hart = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hart == ~0UL) { pr_warn("Found CPU without hart ID\n"); return -ENODEV; } if (!of_device_is_available(node)) { - pr_info("CPU with hartid=%d is not available\n", hart); + pr_info("CPU with hartid=%lu is not available\n", *hart); + return -ENODEV; + } + + if (of_property_read_string(node, "riscv,isa-base", &isa)) + goto old_interface; + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv32i", *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv64i", *hart); + return -ENODEV; + } + + if (!of_property_present(node, "riscv,isa-extensions")) + return -ENODEV; + + if (of_property_match_string(node, "riscv,isa-extensions", "i") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "m") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "a") < 0) { + pr_warn("CPU with hartid=%lu does not support ima", *hart); + return -ENODEV; + } + + return 0; + +old_interface: + if (!riscv_isa_fallback) { + pr_warn("CPU with hartid=%lu is invalid: this kernel does not parse \"riscv,isa\"", + *hart); return -ENODEV; } if (of_property_read_string(node, "riscv,isa", &isa)) { - pr_warn("CPU with hartid=%d has no \"riscv,isa\" property\n", hart); + pr_warn("CPU with hartid=%lu has no \"riscv,isa-base\" or \"riscv,isa\" property\n", + *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv32ima", *hart); return -ENODEV; } - if (isa[0] != 'r' || isa[1] != 'v') { - pr_warn("CPU with hartid=%d has an invalid ISA of \"%s\"\n", hart, isa); + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv64ima", *hart); return -ENODEV; } - return hart; + return 0; +} + +/* + * Find hart ID of the CPU DT node under which given DT node falls. + * + * To achieve this, we walk up the DT tree until we find an active + * RISC-V core (HART) node and extract the cpuid from it. + */ +int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) +{ + for (; node; node = node->parent) { + if (of_device_is_compatible(node, "riscv")) { + *hartid = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hartid == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + return 0; + } + } + + return -1; } +DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +unsigned long riscv_cached_mvendorid(unsigned int cpu_id) +{ + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + + return ci->mvendorid; +} +EXPORT_SYMBOL(riscv_cached_mvendorid); + +unsigned long riscv_cached_marchid(unsigned int cpu_id) +{ + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + + return ci->marchid; +} +EXPORT_SYMBOL(riscv_cached_marchid); + +unsigned long riscv_cached_mimpid(unsigned int cpu_id) +{ + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + + return ci->mimpid; +} +EXPORT_SYMBOL(riscv_cached_mimpid); + +static int riscv_cpuinfo_starting(unsigned int cpu) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); + ci->marchid = csr_read(CSR_MARCHID); + ci->mimpid = csr_read(CSR_MIMPID); +#else + ci->mvendorid = 0; + ci->marchid = 0; + ci->mimpid = 0; +#endif + + return 0; +} + +static int __init riscv_cpuinfo_init(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/cpuinfo:starting", + riscv_cpuinfo_starting, NULL); + if (ret < 0) { + pr_err("cpuinfo: failed to register hotplug callbacks.\n"); + return ret; + } + + return 0; +} +arch_initcall(riscv_cpuinfo_init); + #ifdef CONFIG_PROC_FS -static void print_isa(struct seq_file *f, const char *isa) +static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap) { - /* Print the entire ISA as it is */ - seq_puts(f, "isa\t\t: "); - seq_write(f, isa, strlen(isa)); + + if (IS_ENABLED(CONFIG_32BIT)) + seq_write(f, "rv32", 4); + else + seq_write(f, "rv64", 4); + + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (!__riscv_isa_extension_available(isa_bitmap, riscv_isa_ext[i].id)) + continue; + + /* Only multi-letter extensions are split by underscores */ + if (strnlen(riscv_isa_ext[i].name, 2) != 1) + seq_puts(f, "_"); + + seq_printf(f, "%s", riscv_isa_ext[i].name); + } + seq_puts(f, "\n"); } -static void print_mmu(struct seq_file *f, const char *mmu_type) +static void print_mmu(struct seq_file *f) { + const char *sv_type; + +#ifdef CONFIG_MMU #if defined(CONFIG_32BIT) - if (strcmp(mmu_type, "riscv,sv32") != 0) - return; + sv_type = "sv32"; #elif defined(CONFIG_64BIT) - if (strcmp(mmu_type, "riscv,sv39") != 0 && - strcmp(mmu_type, "riscv,sv48") != 0) - return; + if (pgtable_l5_enabled) + sv_type = "sv57"; + else if (pgtable_l4_enabled) + sv_type = "sv48"; + else + sv_type = "sv39"; #endif - - seq_printf(f, "mmu\t\t: %s\n", mmu_type+6); +#else + sv_type = "none"; +#endif /* CONFIG_MMU */ + seq_printf(f, "mmu\t\t: %s\n", sv_type); } static void *c_start(struct seq_file *m, loff_t *pos) { + if (*pos == nr_cpu_ids) + return NULL; + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return (void *)(uintptr_t)(1 + *pos); @@ -89,20 +270,44 @@ static void c_stop(struct seq_file *m, void *v) static int c_show(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; - struct device_node *node = of_get_cpu_node(cpu_id, NULL); - const char *compat, *isa, *mmu; + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + struct device_node *node; + const char *compat; seq_printf(m, "processor\t: %lu\n", cpu_id); seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id)); - if (!of_property_read_string(node, "riscv,isa", &isa)) - print_isa(m, isa); - if (!of_property_read_string(node, "mmu-type", &mmu)) - print_mmu(m, mmu); - if (!of_property_read_string(node, "compatible", &compat) - && strcmp(compat, "riscv")) - seq_printf(m, "uarch\t\t: %s\n", compat); + + /* + * For historical raisins, the isa: line is limited to the lowest common + * denominator of extensions supported across all harts. A true list of + * extensions supported on this hart is printed later in the hart isa: + * line. + */ + seq_puts(m, "isa\t\t: "); + print_isa(m, NULL); + print_mmu(m); + + if (acpi_disabled) { + node = of_get_cpu_node(cpu_id, NULL); + + if (!of_property_read_string(node, "compatible", &compat) && + strcmp(compat, "riscv")) + seq_printf(m, "uarch\t\t: %s\n", compat); + + of_node_put(node); + } + + seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); + seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid); + seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid); + + /* + * Print the ISA extensions specific to this hart, which may show + * additional extensions not present across all harts. + */ + seq_puts(m, "hart isa\t: "); + print_isa(m, hart_isa[cpu_id].isa); seq_puts(m, "\n"); - of_node_put(node); return 0; } diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c new file mode 100644 index 000000000000..6a8bd8f4db07 --- /dev/null +++ b/arch/riscv/kernel/cpu_ops.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/of.h> +#include <linux/string.h> +#include <linux/sched.h> +#include <asm/cpu_ops.h> +#include <asm/cpu_ops_sbi.h> +#include <asm/sbi.h> +#include <asm/smp.h> + +const struct cpu_operations *cpu_ops __ro_after_init = &cpu_ops_spinwait; + +extern const struct cpu_operations cpu_ops_sbi; +#ifndef CONFIG_RISCV_BOOT_SPINWAIT +const struct cpu_operations cpu_ops_spinwait = { + .cpu_start = NULL, +}; +#endif + +void __init cpu_set_ops(void) +{ +#if IS_ENABLED(CONFIG_RISCV_SBI) + if (sbi_probe_extension(SBI_EXT_HSM)) { + pr_info("SBI HSM extension detected\n"); + cpu_ops = &cpu_ops_sbi; + } +#endif +} diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c new file mode 100644 index 000000000000..1cc7df740edd --- /dev/null +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * HSM extension and cpu_ops implementation. + * + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/sched/task_stack.h> +#include <asm/cpu_ops.h> +#include <asm/cpu_ops_sbi.h> +#include <asm/sbi.h> +#include <asm/smp.h> + +extern char secondary_start_sbi[]; +const struct cpu_operations cpu_ops_sbi; + +/* + * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can + * be invoked from multiple threads in parallel. Define a per cpu data + * to handle that. + */ +static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data); + +static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr, + unsigned long priv) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START, + hartid, saddr, priv, 0, 0, 0); + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + else + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +static int sbi_hsm_hart_stop(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0); + + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + else + return 0; +} + +static int sbi_hsm_hart_get_status(unsigned long hartid) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS, + hartid, 0, 0, 0, 0, 0); + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + else + return ret.value; +} +#endif + +static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) +{ + unsigned long boot_addr = __pa_symbol(secondary_start_sbi); + unsigned long hartid = cpuid_to_hartid_map(cpuid); + unsigned long hsm_data; + struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid); + + /* Make sure tidle is updated */ + smp_mb(); + bdata->task_ptr = tidle; + bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE; + /* Make sure boot data is updated */ + smp_mb(); + hsm_data = __pa(bdata); + return sbi_hsm_hart_start(hartid, boot_addr, hsm_data); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void sbi_cpu_stop(void) +{ + int ret; + + ret = sbi_hsm_hart_stop(); + pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret); +} + +static int sbi_cpu_is_stopped(unsigned int cpuid) +{ + int rc; + unsigned long hartid = cpuid_to_hartid_map(cpuid); + + rc = sbi_hsm_hart_get_status(hartid); + + if (rc == SBI_HSM_STATE_STOPPED) + return 0; + return rc; +} +#endif + +const struct cpu_operations cpu_ops_sbi = { + .cpu_start = sbi_cpu_start, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_stop = sbi_cpu_stop, + .cpu_is_stopped = sbi_cpu_is_stopped, +#endif +}; diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c new file mode 100644 index 000000000000..613872b0a21a --- /dev/null +++ b/arch/riscv/kernel/cpu_ops_spinwait.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include <linux/errno.h> +#include <linux/of.h> +#include <linux/string.h> +#include <linux/sched/task_stack.h> +#include <asm/cpu_ops.h> +#include <asm/sbi.h> +#include <asm/smp.h> + +#include "head.h" + +const struct cpu_operations cpu_ops_spinwait; +void *__cpu_spinwait_stack_pointer[NR_CPUS] __section(".data"); +void *__cpu_spinwait_task_pointer[NR_CPUS] __section(".data"); + +static void cpu_update_secondary_bootdata(unsigned int cpuid, + struct task_struct *tidle) +{ + unsigned long hartid = cpuid_to_hartid_map(cpuid); + + /* + * The hartid must be less than NR_CPUS to avoid out-of-bound access + * errors for __cpu_spinwait_stack/task_pointer. That is not always possible + * for platforms with discontiguous hartid numbering scheme. That's why + * spinwait booting is not the recommended approach for any platforms + * booting Linux in S-mode and can be disabled in the future. + */ + if (hartid == INVALID_HARTID || hartid >= (unsigned long) NR_CPUS) + return; + + /* Make sure tidle is updated */ + smp_mb(); + WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], + task_stack_page(tidle) + THREAD_SIZE); + WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle); +} + +static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle) +{ + /* + * In this protocol, all cpus boot on their own accord. _start + * selects the first cpu to boot the kernel and causes the remainder + * of the cpus to spin in a loop waiting for their stack pointer to be + * setup by that main cpu. Writing to bootdata + * (i.e __cpu_spinwait_stack_pointer) signals to the spinning cpus that they + * can continue the boot process. + */ + cpu_update_secondary_bootdata(cpuid, tidle); + + return 0; +} + +const struct cpu_operations cpu_ops_spinwait = { + .cpu_start = spinwait_cpu_start, +}; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a5ad00043104..89920f84d0a3 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -6,46 +6,537 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> +#include <linux/bitmap.h> +#include <linux/cpu.h> +#include <linux/cpuhotplug.h> +#include <linux/ctype.h> +#include <linux/jump_label.h> +#include <linux/log2.h> +#include <linux/memory.h> +#include <linux/module.h> #include <linux/of.h> -#include <asm/processor.h> +#include <asm/acpi.h> +#include <asm/alternative.h> +#include <asm/cacheflush.h> +#include <asm/cpufeature.h> #include <asm/hwcap.h> -#include <asm/smp.h> -#include <asm/switch_to.h> +#include <asm/hwprobe.h> +#include <asm/patch.h> +#include <asm/processor.h> +#include <asm/vector.h> + +#include "copy-unaligned.h" + +#define NUM_ALPHA_EXTS ('z' - 'a' + 1) + +#define MISALIGNED_ACCESS_JIFFIES_LG2 1 +#define MISALIGNED_BUFFER_SIZE 0x4000 +#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE) +#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) unsigned long elf_hwcap __read_mostly; -#ifdef CONFIG_FPU -bool has_fpu __read_mostly; -#endif -void riscv_fill_hwcap(void) +/* Host ISA bitmap */ +static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; + +/* Per-cpu ISA extensions. */ +struct riscv_isainfo hart_isa[NR_CPUS]; + +/* Performance information */ +DEFINE_PER_CPU(long, misaligned_access_speed); + +static cpumask_t fast_misaligned_access; + +/** + * riscv_isa_extension_base() - Get base extension word + * + * @isa_bitmap: ISA bitmap to use + * Return: base extension word as unsigned long value + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) +{ + if (!isa_bitmap) + return riscv_isa[0]; + return isa_bitmap[0]; +} +EXPORT_SYMBOL_GPL(riscv_isa_extension_base); + +/** + * __riscv_isa_extension_available() - Check whether given extension + * is available or not + * + * @isa_bitmap: ISA bitmap to use + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit) +{ + const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa; + + if (bit >= RISCV_ISA_EXT_MAX) + return false; + + return test_bit(bit, bmap) ? true : false; +} +EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); + +static bool riscv_isa_extension_check(int id) +{ + switch (id) { + case RISCV_ISA_EXT_ZICBOM: + if (!riscv_cbom_block_size) { + pr_err("Zicbom detected in ISA string, disabling as no cbom-block-size found\n"); + return false; + } else if (!is_power_of_2(riscv_cbom_block_size)) { + pr_err("Zicbom disabled as cbom-block-size present, but is not a power-of-2\n"); + return false; + } + return true; + case RISCV_ISA_EXT_ZICBOZ: + if (!riscv_cboz_block_size) { + pr_err("Zicboz detected in ISA string, disabling as no cboz-block-size found\n"); + return false; + } else if (!is_power_of_2(riscv_cboz_block_size)) { + pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n"); + return false; + } + return true; + case RISCV_ISA_EXT_INVALID: + return false; + } + + return true; +} + +#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size) { \ + .name = #_name, \ + .property = #_name, \ + .id = _id, \ + .subset_ext_ids = _subset_exts, \ + .subset_ext_size = _subset_exts_size \ +} + +#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0) + +/* Used to declare pure "lasso" extension (Zk for instance) */ +#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \ + _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, ARRAY_SIZE(_bundled_exts)) + +/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */ +#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \ + _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts)) + +static const unsigned int riscv_zk_bundled_exts[] = { + RISCV_ISA_EXT_ZBKB, + RISCV_ISA_EXT_ZBKC, + RISCV_ISA_EXT_ZBKX, + RISCV_ISA_EXT_ZKND, + RISCV_ISA_EXT_ZKNE, + RISCV_ISA_EXT_ZKR, + RISCV_ISA_EXT_ZKT, +}; + +static const unsigned int riscv_zkn_bundled_exts[] = { + RISCV_ISA_EXT_ZBKB, + RISCV_ISA_EXT_ZBKC, + RISCV_ISA_EXT_ZBKX, + RISCV_ISA_EXT_ZKND, + RISCV_ISA_EXT_ZKNE, + RISCV_ISA_EXT_ZKNH, +}; + +static const unsigned int riscv_zks_bundled_exts[] = { + RISCV_ISA_EXT_ZBKB, + RISCV_ISA_EXT_ZBKC, + RISCV_ISA_EXT_ZKSED, + RISCV_ISA_EXT_ZKSH +}; + +#define RISCV_ISA_EXT_ZVKN \ + RISCV_ISA_EXT_ZVKNED, \ + RISCV_ISA_EXT_ZVKNHB, \ + RISCV_ISA_EXT_ZVKB, \ + RISCV_ISA_EXT_ZVKT + +static const unsigned int riscv_zvkn_bundled_exts[] = { + RISCV_ISA_EXT_ZVKN +}; + +static const unsigned int riscv_zvknc_bundled_exts[] = { + RISCV_ISA_EXT_ZVKN, + RISCV_ISA_EXT_ZVBC +}; + +static const unsigned int riscv_zvkng_bundled_exts[] = { + RISCV_ISA_EXT_ZVKN, + RISCV_ISA_EXT_ZVKG +}; + +#define RISCV_ISA_EXT_ZVKS \ + RISCV_ISA_EXT_ZVKSED, \ + RISCV_ISA_EXT_ZVKSH, \ + RISCV_ISA_EXT_ZVKB, \ + RISCV_ISA_EXT_ZVKT + +static const unsigned int riscv_zvks_bundled_exts[] = { + RISCV_ISA_EXT_ZVKS +}; + +static const unsigned int riscv_zvksc_bundled_exts[] = { + RISCV_ISA_EXT_ZVKS, + RISCV_ISA_EXT_ZVBC +}; + +static const unsigned int riscv_zvksg_bundled_exts[] = { + RISCV_ISA_EXT_ZVKS, + RISCV_ISA_EXT_ZVKG +}; + +static const unsigned int riscv_zvbb_exts[] = { + RISCV_ISA_EXT_ZVKB +}; + +/* + * The canonical order of ISA extension names in the ISA string is defined in + * chapter 27 of the unprivileged specification. + * + * Ordinarily, for in-kernel data structures, this order is unimportant but + * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo. + * + * The specification uses vague wording, such as should, when it comes to + * ordering, so for our purposes the following rules apply: + * + * 1. All multi-letter extensions must be separated from other extensions by an + * underscore. + * + * 2. Additional standard extensions (starting with 'Z') must be sorted after + * single-letter extensions and before any higher-privileged extensions. + * + * 3. The first letter following the 'Z' conventionally indicates the most + * closely related alphabetical extension category, IMAFDQLCBKJTPVH. + * If multiple 'Z' extensions are named, they must be ordered first by + * category, then alphabetically within a category. + * + * 3. Standard supervisor-level extensions (starting with 'S') must be listed + * after standard unprivileged extensions. If multiple supervisor-level + * extensions are listed, they must be ordered alphabetically. + * + * 4. Standard machine-level extensions (starting with 'Zxm') must be listed + * after any lower-privileged, standard extensions. If multiple + * machine-level extensions are listed, they must be ordered + * alphabetically. + * + * 5. Non-standard extensions (starting with 'X') must be listed after all + * standard extensions. If multiple non-standard extensions are listed, they + * must be ordered alphabetically. + * + * An example string following the order is: + * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux + * + * New entries to this struct should follow the ordering rules described above. + */ +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_DATA(q, RISCV_ISA_EXT_q), + __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c), + __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v), + __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), + __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), + __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __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), + __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), + __RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL), + __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), + __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), + __RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS), + __RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA), + __RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH), + __RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN), + __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), + __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC), + __RISCV_ISA_EXT_DATA(zbkb, RISCV_ISA_EXT_ZBKB), + __RISCV_ISA_EXT_DATA(zbkc, RISCV_ISA_EXT_ZBKC), + __RISCV_ISA_EXT_DATA(zbkx, RISCV_ISA_EXT_ZBKX), + __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), + __RISCV_ISA_EXT_BUNDLE(zk, riscv_zk_bundled_exts), + __RISCV_ISA_EXT_BUNDLE(zkn, riscv_zkn_bundled_exts), + __RISCV_ISA_EXT_DATA(zknd, RISCV_ISA_EXT_ZKND), + __RISCV_ISA_EXT_DATA(zkne, RISCV_ISA_EXT_ZKNE), + __RISCV_ISA_EXT_DATA(zknh, RISCV_ISA_EXT_ZKNH), + __RISCV_ISA_EXT_DATA(zkr, RISCV_ISA_EXT_ZKR), + __RISCV_ISA_EXT_BUNDLE(zks, riscv_zks_bundled_exts), + __RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT), + __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_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(smaia, RISCV_ISA_EXT_SMAIA), + __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_DATA(sstc, RISCV_ISA_EXT_SSTC), + __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), +}; + +const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); + +static void __init match_isa_ext(const struct riscv_isa_ext_data *ext, const char *name, + const char *name_end, struct riscv_isainfo *isainfo) +{ + if ((name_end - name == strlen(ext->name)) && + !strncasecmp(name, ext->name, name_end - name)) { + /* + * If this is a bundle, enable all the ISA extensions that + * comprise the bundle. + */ + if (ext->subset_ext_size) { + for (int i = 0; i < ext->subset_ext_size; i++) { + if (riscv_isa_extension_check(ext->subset_ext_ids[i])) + set_bit(ext->subset_ext_ids[i], isainfo->isa); + } + } + + /* + * This is valid even for bundle extensions which uses the RISCV_ISA_EXT_INVALID id + * (rejected by riscv_isa_extension_check()). + */ + if (riscv_isa_extension_check(ext->id)) + set_bit(ext->id, isainfo->isa); + } +} + +static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo, + unsigned long *isa2hwcap, const char *isa) +{ + /* + * For all possible cpus, we have already validated in + * the boot process that they at least contain "rv" and + * whichever of "32"/"64" this kernel supports, and so this + * section can be skipped. + */ + isa += 4; + + while (*isa) { + const char *ext = isa++; + const char *ext_end = isa; + bool ext_long = false, ext_err = false; + + switch (*ext) { + case 's': + /* + * Workaround for invalid single-letter 's' & 'u' (QEMU). + * No need to set the bit in riscv_isa as 's' & 'u' are + * not valid ISA extensions. It works unless the first + * multi-letter extension in the ISA string begins with + * "Su" and is not prefixed with an underscore. + */ + if (ext[-1] != '_' && ext[1] == 'u') { + ++isa; + ext_err = true; + break; + } + fallthrough; + case 'S': + case 'x': + case 'X': + case 'z': + case 'Z': + /* + * Before attempting to parse the extension itself, we find its end. + * As multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + * + * Next, as the extensions version is currently ignored, we + * eliminate that portion. This is done by parsing backwards from + * the end of the extension, removing any numbers. This may be a + * major or minor number however, so the process is repeated if a + * minor number was found. + * + * ext_end is intended to represent the first character *after* the + * name portion of an extension, but will be decremented to the last + * character itself while eliminating the extensions version number. + * A simple re-increment solves this problem. + */ + ext_long = true; + for (; *isa && *isa != '_'; ++isa) + if (unlikely(!isalnum(*isa))) + ext_err = true; + + ext_end = isa; + if (unlikely(ext_err)) + break; + + if (!isdigit(ext_end[-1])) + break; + + while (isdigit(*--ext_end)) + ; + + if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { + ++ext_end; + break; + } + + while (isdigit(*--ext_end)) + ; + + ++ext_end; + break; + default: + /* + * Things are a little easier for single-letter extensions, as they + * are parsed forwards. + * + * After checking that our starting position is valid, we need to + * ensure that, when isa was incremented at the start of the loop, + * that it arrived at the start of the next extension. + * + * If we are already on a non-digit, there is nothing to do. Either + * we have a multi-letter extension's _, or the start of an + * extension. + * + * Otherwise we have found the current extension's major version + * number. Parse past it, and a subsequent p/minor version number + * if present. The `p` extension must not appear immediately after + * a number, so there is no fear of missing it. + * + */ + if (unlikely(!isalpha(*ext))) { + ext_err = true; + break; + } + + if (!isdigit(*isa)) + break; + + while (isdigit(*++isa)) + ; + + if (tolower(*isa) != 'p') + break; + + if (!isdigit(*++isa)) { + --isa; + break; + } + + while (isdigit(*++isa)) + ; + + break; + } + + /* + * The parser expects that at the start of an iteration isa points to the + * first character of the next extension. As we stop parsing an extension + * on meeting a non-alphanumeric character, an extra increment is needed + * where the succeeding extension is a multi-letter prefixed with an "_". + */ + if (*isa == '_') + ++isa; + + if (unlikely(ext_err)) + continue; + if (!ext_long) { + int nr = tolower(*ext) - 'a'; + + if (riscv_isa_extension_check(nr)) { + *this_hwcap |= isa2hwcap[nr]; + set_bit(nr, isainfo->isa); + } + } else { + for (int i = 0; i < riscv_isa_ext_count; i++) + match_isa_ext(&riscv_isa_ext[i], ext, ext_end, isainfo); + } + } +} + +static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) { struct device_node *node; const char *isa; - size_t i; - static unsigned long isa2hwcap[256] = {0}; + int rc; + struct acpi_table_header *rhct; + acpi_status status; + unsigned int cpu; - isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; - isa2hwcap['m'] = isa2hwcap['M'] = COMPAT_HWCAP_ISA_M; - isa2hwcap['a'] = isa2hwcap['A'] = COMPAT_HWCAP_ISA_A; - isa2hwcap['f'] = isa2hwcap['F'] = COMPAT_HWCAP_ISA_F; - isa2hwcap['d'] = isa2hwcap['D'] = COMPAT_HWCAP_ISA_D; - isa2hwcap['c'] = isa2hwcap['C'] = COMPAT_HWCAP_ISA_C; - - elf_hwcap = 0; + if (!acpi_disabled) { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) + return; + } - for_each_of_cpu_node(node) { + for_each_possible_cpu(cpu) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; unsigned long this_hwcap = 0; - if (riscv_of_processor_hartid(node) < 0) - continue; + if (acpi_disabled) { + node = of_cpu_device_node_get(cpu); + if (!node) { + pr_warn("Unable to find cpu node\n"); + continue; + } - if (of_property_read_string(node, "riscv,isa", &isa)) { - pr_warn("Unable to find \"riscv,isa\" devicetree entry\n"); - continue; + rc = of_property_read_string(node, "riscv,isa", &isa); + of_node_put(node); + if (rc) { + pr_warn("Unable to find \"riscv,isa\" devicetree entry\n"); + continue; + } + } else { + rc = acpi_get_riscv_isa(rhct, cpu, &isa); + if (rc < 0) { + pr_warn("Unable to get ISA for the hart - %d\n", cpu); + continue; + } } - for (i = 0; i < strlen(isa); ++i) - this_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa); + + /* + * These ones were as they were part of the base ISA when the + * port & dt-bindings were upstreamed, and so can be set + * unconditionally where `i` is in riscv,isa on DT systems. + */ + if (acpi_disabled) { + set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZICNTR, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa); + } /* * All "okay" hart should have same isa. Set HWCAP based on @@ -56,19 +547,482 @@ void riscv_fill_hwcap(void) elf_hwcap &= this_hwcap; else elf_hwcap = this_hwcap; + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + else + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); } - /* We don't support systems with F but without D, so mask those out - * here. */ + if (!acpi_disabled && rhct) + acpi_put_table((struct acpi_table_header *)rhct); +} + +static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) { + unsigned long this_hwcap = 0; + struct device_node *cpu_node; + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + continue; + } + + if (!of_property_present(cpu_node, "riscv,isa-extensions")) { + of_node_put(cpu_node); + continue; + } + + for (int i = 0; i < riscv_isa_ext_count; i++) { + const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i]; + + if (of_property_match_string(cpu_node, "riscv,isa-extensions", + ext->property) < 0) + continue; + + if (ext->subset_ext_size) { + for (int j = 0; j < ext->subset_ext_size; j++) { + if (riscv_isa_extension_check(ext->subset_ext_ids[i])) + set_bit(ext->subset_ext_ids[j], isainfo->isa); + } + } + + if (riscv_isa_extension_check(ext->id)) { + set_bit(ext->id, isainfo->isa); + + /* Only single letter extensions get set in hwcap */ + if (strnlen(riscv_isa_ext[i].name, 2) == 1) + this_hwcap |= isa2hwcap[riscv_isa_ext[i].id]; + } + } + + of_node_put(cpu_node); + + /* + * All "okay" harts should have same isa. Set HWCAP based on + * common capabilities of every "okay" hart, in case they don't. + */ + if (elf_hwcap) + elf_hwcap &= this_hwcap; + else + elf_hwcap = this_hwcap; + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + else + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + } + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + return -ENOENT; + + return 0; +} + +#ifdef CONFIG_RISCV_ISA_FALLBACK +bool __initdata riscv_isa_fallback = true; +#else +bool __initdata riscv_isa_fallback; +static int __init riscv_isa_fallback_setup(char *__unused) +{ + riscv_isa_fallback = true; + return 1; +} +early_param("riscv_isa_fallback", riscv_isa_fallback_setup); +#endif + +void __init riscv_fill_hwcap(void) +{ + char print_str[NUM_ALPHA_EXTS + 1]; + unsigned long isa2hwcap[26] = {0}; + int i, j; + + isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I; + isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M; + isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A; + isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F; + isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D; + isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C; + isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V; + + if (!acpi_disabled) { + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } else { + int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap); + + if (ret && riscv_isa_fallback) { + pr_info("Falling back to deprecated \"riscv,isa\"\n"); + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } + } + + /* + * We don't support systems with F but without D, so mask those out + * here. + */ if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) { pr_info("This kernel does not support systems with F but not D\n"); elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - pr_info("elf_hwcap is 0x%lx\n", elf_hwcap); + if (elf_hwcap & COMPAT_HWCAP_ISA_V) { + riscv_v_setup_vsize(); + /* + * 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)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: base ISA extensions %s\n", print_str); -#ifdef CONFIG_FPU - if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)) - has_fpu = true; -#endif + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++) + if (elf_hwcap & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ELF capabilities %s\n", print_str); +} + +unsigned long riscv_get_elf_hwcap(void) +{ + unsigned long hwcap; + + hwcap = (elf_hwcap & ((1UL << RISCV_ISA_EXT_BASE) - 1)); + + if (!riscv_v_vstate_ctrl_user_allowed()) + hwcap &= ~COMPAT_HWCAP_ISA_V; + + return hwcap; +} + +static int check_unaligned_access(void *param) +{ + 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 = param; + void *dst; + void *src; + long speed = RISCV_HWPROBE_MISALIGNED_SLOW; + + if (check_unaligned_access_emulated(cpu)) + return 0; + + /* 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. */ + __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + preempt_disable(); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + + /* + * For a fixed amount of time, repeatedly try the function, and take + * the best time in cycles as the measurement. + */ + 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_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; + } + + byte_cycles = -1ULL; + __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + mb(); + __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < byte_cycles) + byte_cycles = end_cycles - start_cycles; + } + + preempt_enable(); + + /* Don't divide by zero. */ + if (!word_cycles || !byte_cycles) { + pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n", + cpu); + + return 0; + } + + if (word_cycles < byte_cycles) + speed = RISCV_HWPROBE_MISALIGNED_FAST; + + ratio = div_u64((byte_cycles * 100), word_cycles); + pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n", + cpu, + ratio / 100, + ratio % 100, + (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow"); + + per_cpu(misaligned_access_speed, cpu) = speed; + + /* + * Set the value of fast_misaligned_access of a CPU. These operations + * are atomic to avoid race conditions. + */ + if (speed == RISCV_HWPROBE_MISALIGNED_FAST) + cpumask_set_cpu(cpu, &fast_misaligned_access); + else + cpumask_clear_cpu(cpu, &fast_misaligned_access); + + return 0; +} + +static void check_unaligned_access_nonboot_cpu(void *param) +{ + unsigned int cpu = smp_processor_id(); + struct page **pages = param; + + if (smp_processor_id() != 0) + check_unaligned_access(pages[cpu]); +} + +DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key); + +static void modify_unaligned_access_branches(cpumask_t *mask, int weight) +{ + if (cpumask_weight(mask) == weight) + static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key); + else + static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key); +} + +static void set_unaligned_access_static_branches_except_cpu(int cpu) +{ + /* + * Same as set_unaligned_access_static_branches, except excludes the + * given CPU from the result. When a CPU is hotplugged into an offline + * state, this function is called before the CPU is set to offline in + * the cpumask, and thus the CPU needs to be explicitly excluded. + */ + + cpumask_t fast_except_me; + + cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask); + cpumask_clear_cpu(cpu, &fast_except_me); + + modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1); +} + +static void set_unaligned_access_static_branches(void) +{ + /* + * This will be called after check_unaligned_access_all_cpus so the + * result of unaligned access speed for all CPUs will be available. + * + * To avoid the number of online cpus changing between reading + * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be + * held before calling this function. + */ + + cpumask_t fast_and_online; + + cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask); + + modify_unaligned_access_branches(&fast_and_online, num_online_cpus()); +} + +static int lock_and_set_unaligned_access_static_branch(void) +{ + cpus_read_lock(); + set_unaligned_access_static_branches(); + cpus_read_unlock(); + + return 0; +} + +arch_initcall_sync(lock_and_set_unaligned_access_static_branch); + +static int riscv_online_cpu(unsigned int cpu) +{ + static struct page *buf; + + /* We are already set since the last check */ + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) + 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); + +exit: + set_unaligned_access_static_branches(); + + return 0; +} + +static int riscv_offline_cpu(unsigned int cpu) +{ + set_unaligned_access_static_branches_except_cpu(cpu); + + return 0; +} + +/* Measure unaligned access on all CPUs present at boot in parallel. */ +static int check_unaligned_access_all_cpus(void) +{ + unsigned int cpu; + unsigned int cpu_count = num_possible_cpus(); + struct page **bufs = kzalloc(cpu_count * sizeof(struct page *), + GFP_KERNEL); + + if (!bufs) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return 0; + } + + /* + * 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); + + /* + * 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); + +out: + unaligned_emulation_finish(); + for_each_cpu(cpu, cpu_online_mask) { + if (bufs[cpu]) + __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); + } + + kfree(bufs); + return 0; +} + +arch_initcall(check_unaligned_access_all_cpus); + +void riscv_user_isa_enable(void) +{ + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) + csr_set(CSR_SENVCFG, ENVCFG_CBZE); } + +#ifdef CONFIG_RISCV_ALTERNATIVE +/* + * Alternative patch sites consider 48 bits when determining when to patch + * the old instruction sequence with the new. These bits are broken into a + * 16-bit vendor ID and a 32-bit patch ID. A non-zero vendor ID means the + * patch site is for an erratum, identified by the 32-bit patch ID. When + * the vendor ID is zero, the patch site is for a cpufeature. cpufeatures + * further break down patch ID into two 16-bit numbers. The lower 16 bits + * are the cpufeature ID and the upper 16 bits are used for a value specific + * to the cpufeature and patch site. If the upper 16 bits are zero, then it + * implies no specific value is specified. cpufeatures that want to control + * patching on a per-site basis will provide non-zero values and implement + * checks here. The checks return true when patching should be done, and + * false otherwise. + */ +static bool riscv_cpufeature_patch_check(u16 id, u16 value) +{ + if (!value) + return true; + + switch (id) { + case RISCV_ISA_EXT_ZICBOZ: + /* + * Zicboz alternative applications provide the maximum + * supported block size order, or zero when it doesn't + * matter. If the current block size exceeds the maximum, + * then the alternative cannot be applied. + */ + return riscv_cboz_block_size <= (1U << value); + } + + return false; +} + +void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, + struct alt_entry *end, + unsigned int stage) +{ + struct alt_entry *alt; + void *oldptr, *altptr; + u16 id, value; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return; + + for (alt = begin; alt < end; alt++) { + if (alt->vendor_id != 0) + continue; + + id = PATCH_ID_CPUFEATURE_ID(alt->patch_id); + + if (id >= RISCV_ISA_EXT_MAX) { + WARN(1, "This extension id:%d is not in ISA extension list", id); + continue; + } + + if (!__riscv_isa_extension_available(NULL, id)) + continue; + + value = PATCH_ID_CPUFEATURE_VALUE(alt->patch_id); + if (!riscv_cpufeature_patch_check(id, value)) + continue; + + oldptr = ALT_OLD_PTR(alt); + altptr = ALT_ALT_PTR(alt); + + mutex_lock(&text_mutex); + patch_text_nosync(oldptr, altptr, alt->alt_len); + riscv_alternative_fix_offsets(oldptr, alt->alt_len, oldptr - altptr); + mutex_unlock(&text_mutex); + } +} +#endif diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c new file mode 100644 index 000000000000..8706736fd4e2 --- /dev/null +++ b/arch/riscv/kernel/crash_core.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/crash_core.h> +#include <linux/pagemap.h> + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(phys_ram_base); + + vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); + vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); + vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); + vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); + vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); +#ifdef CONFIG_64BIT + vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); + vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); +#endif +#endif + vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); + vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", + kernel_map.va_kernel_pa_offset); +} diff --git a/arch/riscv/kernel/crash_dump.c b/arch/riscv/kernel/crash_dump.c new file mode 100644 index 000000000000..ea2158cee97b --- /dev/null +++ b/arch/riscv/kernel/crash_dump.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code comes from arch/arm64/kernel/crash_dump.c + * Created by: AKASHI Takahiro <takahiro.akashi@linaro.org> + * Copyright (C) 2017 Linaro Limited + */ + +#include <linux/crash_dump.h> +#include <linux/io.h> +#include <linux/uio.h> + +ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset) +{ + void *vaddr; + + if (!csize) + return 0; + + vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB); + if (!vaddr) + return -ENOMEM; + + csize = copy_to_iter(vaddr + offset, csize, iter); + + memunmap(vaddr); + return csize; +} diff --git a/arch/riscv/kernel/crash_save_regs.S b/arch/riscv/kernel/crash_save_regs.S new file mode 100644 index 000000000000..b2a1908c0463 --- /dev/null +++ b/arch/riscv/kernel/crash_save_regs.S @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis <mick@ics.forth.gr> + */ + +#include <asm/asm.h> /* For RISCV_* and REG_* macros */ +#include <asm/csr.h> /* For CSR_* macros */ +#include <asm/asm-offsets.h> /* For offsets on pt_regs */ +#include <linux/linkage.h> /* For SYM_* macros */ + +.section ".text" +SYM_CODE_START(riscv_crash_save_regs) + REG_S ra, PT_RA(a0) /* x1 */ + REG_S sp, PT_SP(a0) /* x2 */ + REG_S gp, PT_GP(a0) /* x3 */ + REG_S tp, PT_TP(a0) /* x4 */ + REG_S t0, PT_T0(a0) /* x5 */ + REG_S t1, PT_T1(a0) /* x6 */ + REG_S t2, PT_T2(a0) /* x7 */ + REG_S s0, PT_S0(a0) /* x8/fp */ + REG_S s1, PT_S1(a0) /* x9 */ + REG_S a0, PT_A0(a0) /* x10 */ + REG_S a1, PT_A1(a0) /* x11 */ + REG_S a2, PT_A2(a0) /* x12 */ + REG_S a3, PT_A3(a0) /* x13 */ + REG_S a4, PT_A4(a0) /* x14 */ + REG_S a5, PT_A5(a0) /* x15 */ + REG_S a6, PT_A6(a0) /* x16 */ + REG_S a7, PT_A7(a0) /* x17 */ + REG_S s2, PT_S2(a0) /* x18 */ + REG_S s3, PT_S3(a0) /* x19 */ + REG_S s4, PT_S4(a0) /* x20 */ + REG_S s5, PT_S5(a0) /* x21 */ + REG_S s6, PT_S6(a0) /* x22 */ + REG_S s7, PT_S7(a0) /* x23 */ + REG_S s8, PT_S8(a0) /* x24 */ + REG_S s9, PT_S9(a0) /* x25 */ + REG_S s10, PT_S10(a0) /* x26 */ + REG_S s11, PT_S11(a0) /* x27 */ + REG_S t3, PT_T3(a0) /* x28 */ + REG_S t4, PT_T4(a0) /* x29 */ + REG_S t5, PT_T5(a0) /* x30 */ + REG_S t6, PT_T6(a0) /* x31 */ + + csrr t1, CSR_STATUS + auipc t2, 0x0 + csrr t3, CSR_TVAL + csrr t4, CSR_CAUSE + + REG_S t1, PT_STATUS(a0) + REG_S t2, PT_EPC(a0) + REG_S t3, PT_BADADDR(a0) + REG_S t4, PT_CAUSE(a0) + ret +SYM_CODE_END(riscv_crash_save_regs) diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S new file mode 100644 index 000000000000..515b2dfbca75 --- /dev/null +++ b/arch/riscv/kernel/efi-header.S @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Adapted from arch/arm64/kernel/efi-header.S + */ + +#include <linux/pe.h> +#include <linux/sizes.h> +#include <asm/set_memory.h> + + .macro __EFI_PE_HEADER + .long PE_MAGIC +coff_header: +#ifdef CONFIG_64BIT + .short IMAGE_FILE_MACHINE_RISCV64 // Machine +#else + .short IMAGE_FILE_MACHINE_RISCV32 // Machine +#endif + .short section_count // NumberOfSections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 0 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short IMAGE_FILE_DEBUG_STRIPPED | \ + IMAGE_FILE_EXECUTABLE_IMAGE | \ + IMAGE_FILE_LINE_NUMS_STRIPPED // Characteristics + +optional_header: +#ifdef CONFIG_64BIT + .short PE_OPT_MAGIC_PE32PLUS // PE32+ format +#else + .short PE_OPT_MAGIC_PE32 // PE32 format +#endif + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long __pecoff_text_end - efi_header_end // SizeOfCode +#ifdef __clang__ + .long __pecoff_data_virt_size // SizeOfInitializedData +#else + .long __pecoff_data_virt_end - __pecoff_text_end // SizeOfInitializedData +#endif + .long 0 // SizeOfUninitializedData + .long __efistub_efi_pe_entry - _start // AddressOfEntryPoint + .long efi_header_end - _start // BaseOfCode +#ifdef CONFIG_32BIT + .long __pecoff_text_end - _start // BaseOfData +#endif + +extra_header_fields: + .quad 0 // ImageBase + .long PECOFF_SECTION_ALIGNMENT // SectionAlignment + .long PECOFF_FILE_ALIGNMENT // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short LINUX_EFISTUB_MAJOR_VERSION // MajorImageVersion + .short LINUX_EFISTUB_MINOR_VERSION // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _end - _start // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long efi_header_end - _start // SizeOfHeaders + .long 0 // CheckSum + .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem + .short 0 // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long (section_table - .) / 8 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + .ascii ".text\0\0\0" + .long __pecoff_text_end - efi_header_end // VirtualSize + .long efi_header_end - _start // VirtualAddress + .long __pecoff_text_end - efi_header_end // SizeOfRawData + .long efi_header_end - _start // PointerToRawData + + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long IMAGE_SCN_CNT_CODE | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_EXECUTE // Characteristics + + .ascii ".data\0\0\0" +#ifdef __clang__ + .long __pecoff_data_virt_size // VirtualSize +#else + .long __pecoff_data_virt_end - __pecoff_text_end // VirtualSize +#endif + .long __pecoff_text_end - _start // VirtualAddress +#ifdef __clang__ + .long __pecoff_data_raw_size // SizeOfRawData +#else + .long __pecoff_data_raw_end - __pecoff_text_end // SizeOfRawData +#endif + .long __pecoff_text_end - _start // PointerToRawData + + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE // Characteristics + + .set section_count, (. - section_table) / 40 + + .balign 0x1000 +efi_header_end: + .endm diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c new file mode 100644 index 000000000000..b64bf1624a05 --- /dev/null +++ b/arch/riscv/kernel/efi.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Adapted from arch/arm64/kernel/efi.c + */ + +#include <linux/efi.h> +#include <linux/init.h> + +#include <asm/efi.h> +#include <asm/pgtable.h> +#include <asm/pgtable-bits.h> + +/* + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be + * executable, everything else can be mapped with the XN bits + * set. Also take the new (optional) RO/XP bits into account. + */ +static __init pgprot_t efimem_to_pgprot_map(efi_memory_desc_t *md) +{ + u64 attr = md->attribute; + u32 type = md->type; + + if (type == EFI_MEMORY_MAPPED_IO) + return PAGE_KERNEL; + + /* R-- */ + if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) == + (EFI_MEMORY_XP | EFI_MEMORY_RO)) + return PAGE_KERNEL_READ; + + /* R-X */ + if (attr & EFI_MEMORY_RO) + return PAGE_KERNEL_READ_EXEC; + + /* RW- */ + if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) == + EFI_MEMORY_XP) || + type != EFI_RUNTIME_SERVICES_CODE) + return PAGE_KERNEL; + + /* RWX */ + return PAGE_KERNEL_EXEC; +} + +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +{ + pgprot_t prot = __pgprot(pgprot_val(efimem_to_pgprot_map(md)) & + ~(_PAGE_GLOBAL)); + int i; + + /* RISC-V maps one page at a time */ + for (i = 0; i < md->num_pages; i++) + create_pgd_mapping(mm->pgd, md->virt_addr + i * PAGE_SIZE, + md->phys_addr + i * PAGE_SIZE, + PAGE_SIZE, prot); + return 0; +} + +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) +{ + efi_memory_desc_t *md = data; + pte_t pte = ptep_get(ptep); + unsigned long val; + + if (md->attribute & EFI_MEMORY_RO) { + val = pte_val(pte) & ~_PAGE_WRITE; + val |= _PAGE_READ; + pte = __pte(val); + } + if (md->attribute & EFI_MEMORY_XP) { + val = pte_val(pte) & ~_PAGE_EXEC; + pte = __pte(val); + } + set_pte(ptep, pte); + + return 0; +} + +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md, + bool ignored) +{ + BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + /* + * Calling apply_to_page_range() is only safe on regions that are + * guaranteed to be mapped down to pages. Since we are only called + * for regions that have been mapped using efi_create_mapping() above + * (and this is checked by the generic Memory Attributes table parsing + * routines), there is no need to check that again here. + */ + return apply_to_page_range(mm, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + set_permissions, md); +} diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c new file mode 100644 index 000000000000..5bd1ec3341fe --- /dev/null +++ b/arch/riscv/kernel/elf_kexec.c @@ -0,0 +1,470 @@ +// 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> + +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; +} + +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; +} + +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; + unsigned long initrd_pbase = 0UL; + unsigned long headers_sz; + unsigned long kernel_start; + void *fdt, *headers; + 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; + + /* Add elfcorehdr */ + if (image->type == KEXEC_TYPE_CRASH) { + 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; + } + +#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_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 a1349ca64669..9d1a305d5508 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -9,74 +9,54 @@ #include <asm/asm.h> #include <asm/csr.h> +#include <asm/scs.h> #include <asm/unistd.h> +#include <asm/page.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/errata_list.h> +#include <linux/sizes.h> - .text - .altmacro - -/* - * Prepares to enter a system call or exception by saving all registers to the - * stack. - */ - .macro SAVE_ALL - LOCAL _restore_kernel_tpsp - LOCAL _save_context + .section .irqentry.text, "ax" +SYM_CODE_START(handle_exception) /* * If coming from userspace, preserve the user thread pointer and load * the kernel thread pointer. If we came from the kernel, the scratch * register will contain 0, and we should continue on the current TP. */ csrrw tp, CSR_SCRATCH, tp - bnez tp, _save_context + bnez tp, .Lsave_context -_restore_kernel_tpsp: +.Lrestore_kernel_tpsp: csrr tp, CSR_SCRATCH REG_S sp, TASK_TI_KERNEL_SP(tp) -_save_context: + +#ifdef CONFIG_VMAP_STACK + addi sp, sp, -(PT_SIZE_ON_STACK) + srli sp, sp, THREAD_SHIFT + andi sp, sp, 0x1 + bnez sp, handle_kernel_stack_overflow + REG_L sp, TASK_TI_KERNEL_SP(tp) +#endif + +.Lsave_context: REG_S sp, TASK_TI_USER_SP(tp) REG_L sp, TASK_TI_KERNEL_SP(tp) addi sp, sp, -(PT_SIZE_ON_STACK) REG_S x1, PT_RA(sp) REG_S x3, PT_GP(sp) REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x8, PT_S0(sp) - REG_S x9, PT_S1(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x18, PT_S2(sp) - REG_S x19, PT_S3(sp) - REG_S x20, PT_S4(sp) - REG_S x21, PT_S5(sp) - REG_S x22, PT_S6(sp) - REG_S x23, PT_S7(sp) - REG_S x24, PT_S8(sp) - REG_S x25, PT_S9(sp) - REG_S x26, PT_S10(sp) - REG_S x27, PT_S11(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) + save_from_x6_to_x31 /* * Disable user-mode memory access as it should only be set in the * actual user copy routines. * - * Disable the FPU to detect illegal usage of floating point in kernel - * space. + * Disable the FPU/Vector to detect illegal usage of floating point + * or vector in kernel space. */ - li t0, SR_SUM | SR_FS + li t0, SR_SUM | SR_FS_VS REG_L s0, TASK_TI_USER_SP(tp) csrrc s1, CSR_STATUS, t0 @@ -90,77 +70,6 @@ _save_context: REG_S s3, PT_BADADDR(sp) REG_S s4, PT_CAUSE(sp) REG_S s5, PT_TP(sp) - .endm - -/* - * Prepares to return from a system call or exception by restoring all - * registers from the stack. - */ - .macro RESTORE_ALL - REG_L a0, PT_STATUS(sp) - /* - * The current load reservation is effectively part of the processor's - * state, in the sense that load reservations cannot be shared between - * different hart contexts. We can't actually save and restore a load - * reservation, so instead here we clear any existing reservation -- - * it's always legal for implementations to clear load reservations at - * any point (as long as the forward progress guarantee is kept, but - * we'll ignore that here). - * - * Dangling load reservations can be the result of taking a trap in the - * middle of an LR/SC sequence, but can also be the result of a taken - * forward branch around an SC -- which is how we implement CAS. As a - * result we need to clear reservations between the last CAS and the - * jump back to the new context. While it is unlikely the store - * completes, implementations are allowed to expand reservations to be - * arbitrarily large. - */ - REG_L a2, PT_EPC(sp) - REG_SC x0, a2, PT_EPC(sp) - - csrw CSR_STATUS, a0 - csrw CSR_EPC, a2 - - REG_L x1, PT_RA(sp) - REG_L x3, PT_GP(sp) - REG_L x4, PT_TP(sp) - REG_L x5, PT_T0(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x8, PT_S0(sp) - REG_L x9, PT_S1(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - REG_L x18, PT_S2(sp) - REG_L x19, PT_S3(sp) - REG_L x20, PT_S4(sp) - REG_L x21, PT_S5(sp) - REG_L x22, PT_S6(sp) - REG_L x23, PT_S7(sp) - REG_L x24, PT_S8(sp) - REG_L x25, PT_S9(sp) - REG_L x26, PT_S10(sp) - REG_L x27, PT_S11(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) - - REG_L x2, PT_SP(sp) - .endm - -#if !IS_ENABLED(CONFIG_PREEMPT) -.set resume_kernel, restore_all -#endif - -ENTRY(handle_exception) - SAVE_ALL /* * Set the scratch register to 0, so that if a recursive exception @@ -169,12 +78,18 @@ ENTRY(handle_exception) csrw CSR_SCRATCH, x0 /* Load the global pointer */ -.option push -.option norelax - la gp, __global_pointer$ -.option pop + load_global_pointer + + /* Load the kernel shadow call stack pointer if coming from userspace */ + scs_load_current_if_task_changed s5 +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + move a0, sp + call riscv_v_context_nesting_start +#endif + move a0, sp /* pt_regs */ la ra, ret_from_exception + /* * MSB of cause differentiates between * interrupts and exceptions @@ -182,27 +97,12 @@ ENTRY(handle_exception) bge s4, zero, 1f /* Handle interrupts */ - move a0, sp /* pt_regs */ - tail do_IRQ -1: - /* - * Exceptions run with interrupts enabled or disabled depending on the - * state of SR_PIE in m/sstatus. - */ - andi t0, s1, SR_PIE - beqz t0, 1f - csrs CSR_STATUS, SR_IE - + tail do_irq 1: - /* Handle syscalls */ - li t0, EXC_SYSCALL - beq s4, t0, handle_syscall - /* Handle other exceptions */ slli t0, s4, RISCV_LGPTR la t1, excp_vect_table la t2, excp_vect_table_end - move a0, sp /* pt_regs */ add t0, t1, t0 /* Check if exception code lies within bounds */ bgeu t0, t2, 1f @@ -210,67 +110,16 @@ ENTRY(handle_exception) jr t0 1: tail do_trap_unknown +SYM_CODE_END(handle_exception) -handle_syscall: - /* save the initial A0 value (needed in signal handlers) */ - REG_S a0, PT_ORIG_A0(sp) - /* - * Advance SEPC to avoid executing the original - * scall instruction on sret - */ - addi s2, s2, 0x4 - REG_S s2, PT_EPC(sp) - /* Trace syscalls, but only if requested by the user. */ - REG_L t0, TASK_TI_FLAGS(tp) - andi t0, t0, _TIF_SYSCALL_WORK - bnez t0, handle_syscall_trace_enter -check_syscall_nr: - /* Check to make sure we don't jump to a bogus syscall number. */ - li t0, __NR_syscalls - la s0, sys_ni_syscall - /* - * The tracer can change syscall number to valid/invalid value. - * We use syscall_set_nr helper in syscall_trace_enter thus we - * cannot trust the current value in a7 and have to reload from - * the current task pt_regs. - */ - REG_L a7, PT_A7(sp) - /* - * Syscall number held in a7. - * If syscall number is above allowed value, redirect to ni_syscall. - */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer or seccomp, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - /* Call syscall */ - la s0, sys_call_table - slli t0, a7, RISCV_LGPTR - add s0, s0, t0 - REG_L s0, 0(s0) -1: - jalr s0 - -ret_from_syscall: - /* Set user a0 to kernel a0 */ - REG_S a0, PT_A0(sp) - /* - * We didn't execute the actual syscall. - * Seccomp already set return value for the current task pt_regs. - * (If it was configured with SECCOMP_RET_ERRNO/TRACE) - */ -ret_from_syscall_rejected: - /* Trace syscalls, but only if requested by the user. */ - REG_L t0, TASK_TI_FLAGS(tp) - andi t0, t0, _TIF_SYSCALL_WORK - bnez t0, handle_syscall_trace_exit - -ret_from_exception: +/* + * The ret_from_exception must be called with interrupt disabled. Here is the + * caller list: + * - handle_exception + * - ret_from_fork + */ +SYM_CODE_START_NOALIGN(ret_from_exception) REG_L s0, PT_STATUS(sp) - csrc CSR_STATUS, SR_IE #ifdef CONFIG_RISCV_M_MODE /* the MPP value is too large to be used as an immediate arg for addi */ li t0, SR_MPP @@ -278,90 +127,148 @@ ret_from_exception: #else andi s0, s0, SR_SPP #endif - bnez s0, resume_kernel - -resume_userspace: - /* Interrupts must be disabled here so flags are checked atomically */ - REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */ - andi s1, s0, _TIF_WORK_MASK - bnez s1, work_pending + bnez s0, 1f /* Save unwound kernel stack pointer in thread_info */ addi s0, sp, PT_SIZE_ON_STACK REG_S s0, TASK_TI_KERNEL_SP(tp) + /* Save the kernel shadow call stack pointer */ + scs_save_current + /* * Save TP into the scratch register , so we can find the kernel data * structures again. */ csrw CSR_SCRATCH, tp +1: +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + move a0, sp + call riscv_v_context_nesting_end +#endif + REG_L a0, PT_STATUS(sp) + /* + * The current load reservation is effectively part of the processor's + * state, in the sense that load reservations cannot be shared between + * different hart contexts. We can't actually save and restore a load + * reservation, so instead here we clear any existing reservation -- + * it's always legal for implementations to clear load reservations at + * any point (as long as the forward progress guarantee is kept, but + * we'll ignore that here). + * + * Dangling load reservations can be the result of taking a trap in the + * middle of an LR/SC sequence, but can also be the result of a taken + * forward branch around an SC -- which is how we implement CAS. As a + * result we need to clear reservations between the last CAS and the + * jump back to the new context. While it is unlikely the store + * completes, implementations are allowed to expand reservations to be + * arbitrarily large. + */ + REG_L a2, PT_EPC(sp) + REG_SC x0, a2, PT_EPC(sp) + + csrw CSR_STATUS, a0 + csrw CSR_EPC, a2 + + REG_L x1, PT_RA(sp) + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x5, PT_T0(sp) + restore_from_x6_to_x31 + + REG_L x2, PT_SP(sp) -restore_all: - RESTORE_ALL #ifdef CONFIG_RISCV_M_MODE mret #else sret #endif +SYM_CODE_END(ret_from_exception) + +#ifdef CONFIG_VMAP_STACK +SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) + /* we reach here from kernel context, sscratch must be 0 */ + csrrw x31, CSR_SCRATCH, x31 + asm_per_cpu sp, overflow_stack, x31 + li x31, OVERFLOW_STACK_SIZE + add sp, sp, x31 + /* zero out x31 again and restore x31 */ + xor x31, x31, x31 + csrrw x31, CSR_SCRATCH, x31 -#if IS_ENABLED(CONFIG_PREEMPT) -resume_kernel: - REG_L s0, TASK_TI_PREEMPT_COUNT(tp) - bnez s0, restore_all - REG_L s0, TASK_TI_FLAGS(tp) - andi s0, s0, _TIF_NEED_RESCHED - beqz s0, restore_all - call preempt_schedule_irq - j restore_all -#endif + addi sp, sp, -(PT_SIZE_ON_STACK) -work_pending: - /* Enter slow path for supplementary processing */ - la ra, ret_from_exception - andi s1, s0, _TIF_NEED_RESCHED - bnez s1, work_resched -work_notifysig: - /* Handle pending signals and notify-resume requests */ - csrs CSR_STATUS, SR_IE /* Enable interrupts for do_notify_resume() */ - move a0, sp /* pt_regs */ - move a1, s0 /* current_thread_info->flags */ - tail do_notify_resume -work_resched: - tail schedule + //save context to overflow stack + REG_S x1, PT_RA(sp) + REG_S x3, PT_GP(sp) + REG_S x5, PT_T0(sp) + save_from_x6_to_x31 -/* Slow paths for ptrace. */ -handle_syscall_trace_enter: - move a0, sp - call do_syscall_trace_enter - REG_L a0, PT_A0(sp) - REG_L a1, PT_A1(sp) - REG_L a2, PT_A2(sp) - REG_L a3, PT_A3(sp) - REG_L a4, PT_A4(sp) - REG_L a5, PT_A5(sp) - REG_L a6, PT_A6(sp) - REG_L a7, PT_A7(sp) - j check_syscall_nr -handle_syscall_trace_exit: + REG_L s0, TASK_TI_KERNEL_SP(tp) + csrr s1, CSR_STATUS + csrr s2, CSR_EPC + csrr s3, CSR_TVAL + csrr s4, CSR_CAUSE + csrr s5, CSR_SCRATCH + REG_S s0, PT_SP(sp) + REG_S s1, PT_STATUS(sp) + REG_S s2, PT_EPC(sp) + REG_S s3, PT_BADADDR(sp) + REG_S s4, PT_CAUSE(sp) + REG_S s5, PT_TP(sp) move a0, sp - call do_syscall_trace_exit - j ret_from_exception - -END(handle_exception) - -ENTRY(ret_from_fork) - la ra, ret_from_exception - tail schedule_tail -ENDPROC(ret_from_fork) + tail handle_bad_stack +SYM_CODE_END(handle_kernel_stack_overflow) +#endif -ENTRY(ret_from_kernel_thread) +SYM_CODE_START(ret_from_fork) call schedule_tail + beqz s0, 1f /* not from kernel thread */ /* Call fn(arg) */ - la ra, ret_from_exception move a0, s1 - jr s0 -ENDPROC(ret_from_kernel_thread) + jalr s0 +1: + move a0, sp /* pt_regs */ + la ra, ret_from_exception + tail syscall_exit_to_user_mode +SYM_CODE_END(ret_from_fork) + +#ifdef CONFIG_IRQ_STACKS +/* + * void call_on_irq_stack(struct pt_regs *regs, + * void (*func)(struct pt_regs *)); + * + * Calls func(regs) using the per-CPU IRQ stack. + */ +SYM_FUNC_START(call_on_irq_stack) + /* Create a frame record to save ra and s0 (fp) */ + addi sp, sp, -STACKFRAME_SIZE_ON_STACK + REG_S ra, STACKFRAME_RA(sp) + REG_S s0, STACKFRAME_FP(sp) + addi s0, sp, STACKFRAME_SIZE_ON_STACK + + /* Switch to the per-CPU shadow call stack */ + scs_save_current + scs_load_irq_stack t0 + + /* Switch to the per-CPU IRQ stack and call the handler */ + load_per_cpu t0, irq_stack_ptr, t1 + li t1, IRQ_STACK_SIZE + add sp, t0, t1 + jalr a1 + + /* Switch back to the thread shadow call stack */ + scs_load_current + + /* Switch back to the thread stack and restore ra and s0 */ + addi sp, s0, -STACKFRAME_SIZE_ON_STACK + REG_L ra, STACKFRAME_RA(sp) + REG_L s0, STACKFRAME_FP(sp) + addi sp, sp, STACKFRAME_SIZE_ON_STACK + ret +SYM_FUNC_END(call_on_irq_stack) +#endif /* CONFIG_IRQ_STACKS */ /* * Integer register context switch @@ -373,7 +280,7 @@ ENDPROC(ret_from_kernel_thread) * The value of a0 and a1 must be preserved by this function, as that's how * arguments are passed to schedule_tail. */ -ENTRY(__switch_to) +SYM_FUNC_START(__switch_to) /* Save context into prev->thread */ li a4, TASK_THREAD_RA add a3, a0, a4 @@ -392,6 +299,8 @@ ENTRY(__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 kernel shadow call stack pointer */ + scs_save_current /* Restore context from next->thread */ REG_L ra, TASK_THREAD_RA_RA(a4) REG_L sp, TASK_THREAD_SP_RA(a4) @@ -407,49 +316,43 @@ ENTRY(__switch_to) REG_L s9, TASK_THREAD_S9_RA(a4) REG_L s10, TASK_THREAD_S10_RA(a4) REG_L s11, TASK_THREAD_S11_RA(a4) - /* Swap the CPU entry around. */ - lw a3, TASK_TI_CPU(a0) - lw a4, TASK_TI_CPU(a1) - sw a3, TASK_TI_CPU(a1) - sw a4, TASK_TI_CPU(a0) -#if TASK_TI != 0 -#error "TASK_TI != 0: tp will contain a 'struct thread_info', not a 'struct task_struct' so get_current() won't work." - addi tp, a1, TASK_TI -#else + /* The offset of thread_info in task_struct is zero. */ move tp, a1 -#endif + /* Switch to the next shadow call stack */ + scs_load_current ret -ENDPROC(__switch_to) +SYM_FUNC_END(__switch_to) #ifndef CONFIG_MMU #define do_page_fault do_trap_unknown #endif .section ".rodata" + .align LGREG /* Exception vector table */ -ENTRY(excp_vect_table) +SYM_DATA_START_LOCAL(excp_vect_table) RISCV_PTR do_trap_insn_misaligned - RISCV_PTR do_trap_insn_fault + ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault) RISCV_PTR do_trap_insn_illegal RISCV_PTR do_trap_break RISCV_PTR do_trap_load_misaligned RISCV_PTR do_trap_load_fault RISCV_PTR do_trap_store_misaligned RISCV_PTR do_trap_store_fault - RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */ + RISCV_PTR do_trap_ecall_u /* system call */ RISCV_PTR do_trap_ecall_s RISCV_PTR do_trap_unknown RISCV_PTR do_trap_ecall_m - RISCV_PTR do_page_fault /* instruction page fault */ + /* instruciton page fault */ + ALT_PAGE_FAULT(RISCV_PTR do_page_fault) RISCV_PTR do_page_fault /* load page fault */ RISCV_PTR do_trap_unknown RISCV_PTR do_page_fault /* store page fault */ -excp_vect_table_end: -END(excp_vect_table) +SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end) #ifndef CONFIG_MMU -ENTRY(__user_rt_sigreturn) +SYM_DATA_START(__user_rt_sigreturn) li a7, __NR_rt_sigreturn - scall -END(__user_rt_sigreturn) + ecall +SYM_DATA_END(__user_rt_sigreturn) #endif diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S index dd2205473de7..2c543f130f93 100644 --- a/arch/riscv/kernel/fpu.S +++ b/arch/riscv/kernel/fpu.S @@ -19,7 +19,7 @@ #include <asm/csr.h> #include <asm/asm-offsets.h> -ENTRY(__fstate_save) +SYM_FUNC_START(__fstate_save) li a2, TASK_THREAD_F0 add a0, a0, a2 li t1, SR_FS @@ -60,9 +60,9 @@ ENTRY(__fstate_save) sw t0, TASK_THREAD_FCSR_F0(a0) csrc CSR_STATUS, t1 ret -ENDPROC(__fstate_save) +SYM_FUNC_END(__fstate_save) -ENTRY(__fstate_restore) +SYM_FUNC_START(__fstate_restore) li a2, TASK_THREAD_F0 add a0, a0, a2 li t1, SR_FS @@ -103,4 +103,125 @@ ENTRY(__fstate_restore) fscsr t0 csrc CSR_STATUS, t1 ret -ENDPROC(__fstate_restore) +SYM_FUNC_END(__fstate_restore) + +#define get_f32(which) fmv.x.s a0, which; j 2f +#define put_f32(which) fmv.s.x which, a1; j 2f +#if __riscv_xlen == 64 +# define get_f64(which) fmv.x.d a0, which; j 2f +# define put_f64(which) fmv.d.x which, a1; j 2f +#else +# define get_f64(which) fsd which, 0(a1); j 2f +# define put_f64(which) fld which, 0(a1); j 2f +#endif + +.macro fp_access_prologue + /* + * Compute jump offset to store the correct FP register since we don't + * have indirect FP register access + */ + sll t0, a0, 3 + la t2, 1f + add t0, t0, t2 + li t1, SR_FS + csrs CSR_STATUS, t1 + jr t0 +1: +.endm + +.macro fp_access_epilogue +2: + csrc CSR_STATUS, t1 + ret +.endm + +#define fp_access_body(__access_func) \ + __access_func(f0); \ + __access_func(f1); \ + __access_func(f2); \ + __access_func(f3); \ + __access_func(f4); \ + __access_func(f5); \ + __access_func(f6); \ + __access_func(f7); \ + __access_func(f8); \ + __access_func(f9); \ + __access_func(f10); \ + __access_func(f11); \ + __access_func(f12); \ + __access_func(f13); \ + __access_func(f14); \ + __access_func(f15); \ + __access_func(f16); \ + __access_func(f17); \ + __access_func(f18); \ + __access_func(f19); \ + __access_func(f20); \ + __access_func(f21); \ + __access_func(f22); \ + __access_func(f23); \ + __access_func(f24); \ + __access_func(f25); \ + __access_func(f26); \ + __access_func(f27); \ + __access_func(f28); \ + __access_func(f29); \ + __access_func(f30); \ + __access_func(f31) + + +#ifdef CONFIG_RISCV_MISALIGNED + +/* + * Disable compressed instructions set to keep a constant offset between FP + * load/store/move instructions + */ +.option norvc +/* + * put_f32_reg - Set a FP register from a register containing the value + * a0 = FP register index to be set + * a1 = value to be loaded in the FP register + */ +SYM_FUNC_START(put_f32_reg) + fp_access_prologue + fp_access_body(put_f32) + fp_access_epilogue +SYM_FUNC_END(put_f32_reg) + +/* + * get_f32_reg - Get a FP register value and return it + * a0 = FP register index to be retrieved + */ +SYM_FUNC_START(get_f32_reg) + fp_access_prologue + fp_access_body(get_f32) + fp_access_epilogue +SYM_FUNC_END(get_f32_reg) + +/* + * put_f64_reg - Set a 64 bits FP register from a value or a pointer. + * a0 = FP register index to be set + * a1 = value/pointer to be loaded in the FP register (when xlen == 32 bits, we + * load the value to a pointer). + */ +SYM_FUNC_START(put_f64_reg) + fp_access_prologue + fp_access_body(put_f64) + fp_access_epilogue +SYM_FUNC_END(put_f64_reg) + +/* + * put_f64_reg - Get a 64 bits FP register value and returned it or store it to + * a pointer. + * a0 = FP register index to be retrieved + * a1 = If xlen == 32, pointer which should be loaded with the FP register value + * or unused if xlen == 64. In which case the FP register value is returned + * through a0 + */ +SYM_FUNC_START(get_f64_reg) + fp_access_prologue + fp_access_body(get_f64) + fp_access_epilogue +SYM_FUNC_END(get_f64_reg) + +#endif /* CONFIG_RISCV_MISALIGNED */ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index b94d8db5ddcc..f5aa24d9e1c1 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> @@ -7,9 +7,30 @@ #include <linux/ftrace.h> #include <linux/uaccess.h> +#include <linux/memory.h> #include <asm/cacheflush.h> +#include <asm/patch.h> #ifdef CONFIG_DYNAMIC_FTRACE +void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) +{ + mutex_lock(&text_mutex); + + /* + * 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; +} + +void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) +{ + riscv_patch_in_stop_machine = false; + mutex_unlock(&text_mutex); +} + static int ftrace_check_current_call(unsigned long hook_pos, unsigned int *expected) { @@ -24,7 +45,8 @@ static int ftrace_check_current_call(unsigned long hook_pos, * Read the text we want to modify; * return must be -EFAULT on read error */ - if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)hook_pos, + MCOUNT_INSN_SIZE)) return -EFAULT; /* @@ -42,68 +64,76 @@ static int ftrace_check_current_call(unsigned long hook_pos, } static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target, - bool enable) + bool enable, bool ra) { unsigned int call[2]; unsigned int nops[2] = {NOP4, NOP4}; - int ret = 0; - make_call(hook_pos, target, call); + if (ra) + make_call_ra(hook_pos, target, call); + else + make_call_t0(hook_pos, target, call); - /* replace the auipc-jalr pair at once */ - ret = probe_kernel_write((void *)hook_pos, enable ? call : nops, - MCOUNT_INSN_SIZE); - /* return must be -EPERM on write error */ - if (ret) + /* Replace the auipc-jalr pair at once. Return -EPERM on write error. */ + if (patch_text_nosync + ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE)) return -EPERM; - smp_mb(); - flush_icache_range((void *)hook_pos, (void *)hook_pos + MCOUNT_INSN_SIZE); - return 0; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - int ret = ftrace_check_current_call(rec->ip, NULL); + unsigned int call[2]; - if (ret) - return ret; + make_call_t0(rec->ip, addr, call); + + if (patch_text_nosync((void *)rec->ip, call, MCOUNT_INSN_SIZE)) + return -EPERM; - return __ftrace_modify_call(rec->ip, addr, true); + return 0; } int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int call[2]; - int ret; + unsigned int nops[2] = {NOP4, NOP4}; - make_call(rec->ip, addr, call); - ret = ftrace_check_current_call(rec->ip, call); + if (patch_text_nosync((void *)rec->ip, nops, MCOUNT_INSN_SIZE)) + return -EPERM; - if (ret) - return ret; + return 0; +} + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + int out; + + mutex_lock(&text_mutex); + out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + mutex_unlock(&text_mutex); - return __ftrace_modify_call(rec->ip, addr, false); + return out; } int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, - (unsigned long)func, true); + (unsigned long)func, true, true); if (!ret) { ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call, - (unsigned long)func, true); + (unsigned long)func, true, true); } return ret; } - -int __init ftrace_dyn_arch_init(void) -{ - return 0; -} #endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS @@ -111,15 +141,16 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { unsigned int call[2]; + unsigned long caller = rec->ip; int ret; - make_call(rec->ip, old_addr, call); - ret = ftrace_check_current_call(rec->ip, call); + make_call_t0(caller, old_addr, call); + ret = ftrace_check_current_call(caller, call); if (ret) return ret; - return __ftrace_modify_call(rec->ip, addr, true); + return __ftrace_modify_call(caller, addr, true, false); } #endif @@ -142,60 +173,33 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, */ old = *parent; - if (function_graph_enter(old, self_addr, frame_pointer, parent)) + if (!function_graph_enter(old, self_addr, frame_pointer, parent)) *parent = return_hooker; } #ifdef CONFIG_DYNAMIC_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + struct pt_regs *regs = arch_ftrace_get_regs(fregs); + unsigned long *parent = (unsigned long *)®s->ra; + + prepare_ftrace_return(parent, ip, frame_pointer(regs)); +} +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ extern void ftrace_graph_call(void); int ftrace_enable_ftrace_graph_caller(void) { - unsigned int call[2]; - static int init_graph = 1; - int ret; - - make_call(&ftrace_graph_call, &ftrace_stub, call); - - /* - * When enabling graph tracer for the first time, ftrace_graph_call - * should contains a call to ftrace_stub. Once it has been disabled, - * the 8-bytes at the position becomes NOPs. - */ - if (init_graph) { - ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call, - call); - init_graph = 0; - } else { - ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call, - NULL); - } - - if (ret) - return ret; - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, - (unsigned long)&prepare_ftrace_return, true); + (unsigned long)&prepare_ftrace_return, true, true); } int ftrace_disable_ftrace_graph_caller(void) { - unsigned int call[2]; - int ret; - - make_call(&ftrace_graph_call, &prepare_ftrace_return, call); - - /* - * This is to make sure that ftrace_enable_ftrace_graph_caller - * did the right thing. - */ - ret = ftrace_check_current_call((unsigned long)&ftrace_graph_call, - call); - - if (ret) - return ret; - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, - (unsigned long)&prepare_ftrace_return, false); + (unsigned long)&prepare_ftrace_return, false, true); } +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 84a6f0a4b120..4236a69c35cb 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -3,30 +3,45 @@ * Copyright (C) 2012 Regents of the University of California */ -#include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/asm.h> #include <linux/init.h> #include <linux/linkage.h> #include <asm/thread_info.h> #include <asm/page.h> +#include <asm/pgtable.h> #include <asm/csr.h> #include <asm/hwcap.h> #include <asm/image.h> +#include <asm/scs.h> +#include <asm/xip_fixup.h> +#include "efi-header.S" -__INIT -ENTRY(_start) +__HEAD +SYM_CODE_START(_start) /* * Image header expected by Linux boot-loaders. The image header data * structure is described in asm/image.h. * Do not modify it without modifying the structure and all bootloaders * that expects this header format!! */ +#ifdef CONFIG_EFI + /* + * This instruction decodes to "MZ" ASCII required by UEFI. + */ + c.li s4,-13 + j _start_kernel +#else /* jump to start kernel */ j _start_kernel /* reserved */ .word 0 +#endif .balign 8 +#ifdef CONFIG_RISCV_M_MODE + /* Image load offset (0MB) from start of RAM for M-mode */ + .dword 0 +#else #if __riscv_xlen == 64 /* Image load offset(2MB) from start of RAM */ .dword 0x200000 @@ -34,6 +49,7 @@ ENTRY(_start) /* Image load offset(4MB) from start of RAM */ .dword 0x400000 #endif +#endif /* Effective size of kernel image */ .dword _end - _start .dword __HEAD_FLAGS @@ -43,10 +59,137 @@ ENTRY(_start) .ascii RISCV_IMAGE_MAGIC .balign 4 .ascii RISCV_IMAGE_MAGIC2 +#ifdef CONFIG_EFI + .word pe_head_start - _start +pe_head_start: + + __EFI_PE_HEADER +#else .word 0 +#endif + +.align 2 +#ifdef CONFIG_MMU + .global relocate_enable_mmu +relocate_enable_mmu: + /* Relocate return address */ + la a1, kernel_map + XIP_FIXUP_OFFSET a1 + REG_L a1, KERNEL_MAP_VIRT_ADDR(a1) + la a2, _start + sub a1, a1, a2 + add ra, ra, a1 + + /* Point stvec to virtual address of intruction after satp write */ + la a2, 1f + add a2, a2, a1 + csrw CSR_TVEC, a2 + + /* Compute satp for kernel page tables, but don't load it yet */ + srl a2, a0, PAGE_SHIFT + la a1, satp_mode + XIP_FIXUP_OFFSET a1 + REG_L a1, 0(a1) + or a2, a2, a1 + + /* + * Load trampoline page directory, which will cause us to trap to + * stvec if VA != PA, or simply fall through if VA == PA. We need a + * full fence here because setup_vm() just wrote these PTEs and we need + * to ensure the new translations are in use. + */ + la a0, trampoline_pg_dir + XIP_FIXUP_OFFSET a0 + srl a0, a0, PAGE_SHIFT + or a0, a0, a1 + sfence.vma + csrw CSR_SATP, a0 +.align 2 +1: + /* Set trap vector to spin forever to help debug */ + la a0, .Lsecondary_park + csrw CSR_TVEC, a0 + + /* Reload the global pointer */ + load_global_pointer + + /* + * Switch to kernel page tables. A full fence is necessary in order to + * avoid using the trampoline translations, which are only correct for + * the first superpage. Fetching the fence is guaranteed to work + * because that first superpage is translated the same way. + */ + csrw CSR_SATP, a2 + sfence.vma + + ret +#endif /* CONFIG_MMU */ +#ifdef CONFIG_SMP + .global secondary_start_sbi +secondary_start_sbi: + /* Mask all interrupts */ + csrw CSR_IE, zero + csrw CSR_IP, zero + + /* Load the global pointer */ + load_global_pointer + + /* + * Disable FPU & VECTOR to detect illegal usage of + * floating point or vector in kernel space + */ + li t0, SR_FS_VS + csrc CSR_STATUS, t0 + + /* Set trap vector to spin forever to help debug */ + la a3, .Lsecondary_park + csrw CSR_TVEC, a3 + + /* a0 contains the hartid & a1 contains boot data */ + li a2, SBI_HART_BOOT_TASK_PTR_OFFSET + XIP_FIXUP_OFFSET a2 + add a2, a2, a1 + REG_L tp, (a2) + li a3, SBI_HART_BOOT_STACK_PTR_OFFSET + XIP_FIXUP_OFFSET a3 + add a3, a3, a1 + REG_L sp, (a3) + +.Lsecondary_start_common: + +#ifdef CONFIG_MMU + /* Enable virtual memory and relocate to virtual address */ + la a0, swapper_pg_dir + XIP_FIXUP_OFFSET a0 + call relocate_enable_mmu +#endif + call .Lsetup_trap_vector + scs_load_current + tail smp_callin +#endif /* CONFIG_SMP */ + +.align 2 +.Lsetup_trap_vector: + /* Set trap vector to exception handler */ + la a0, handle_exception + csrw CSR_TVEC, a0 + + /* + * Set sup0 scratch register to 0, indicating to exception vector that + * we are presently executing in kernel. + */ + csrw CSR_SCRATCH, zero + ret + +.align 2 +.Lsecondary_park: + /* We lack SMP support or have too many harts, so park this hart */ + wfi + j .Lsecondary_park + +SYM_CODE_END(_start) -.global _start_kernel -_start_kernel: +SYM_CODE_START(_start_kernel) /* Mask all interrupts */ csrw CSR_IE, zero csrw CSR_IP, zero @@ -59,6 +202,21 @@ _start_kernel: call reset_regs /* + * Setup a PMP to permit access to all of memory. Some machines may + * not implement PMPs, so we set up a quick trap handler to just skip + * touching the PMPs on any trap. + */ + la a0, .Lpmp_done + csrw CSR_TVEC, a0 + + li a0, -1 + csrw CSR_PMPADDR0, a0 + li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) + csrw CSR_PMPCFG0, a0 +.align 2 +.Lpmp_done: + + /* * The hartid in a0 is expected later on, and we have no firmware * to hand it to us. */ @@ -66,125 +224,114 @@ _start_kernel: #endif /* CONFIG_RISCV_M_MODE */ /* Load the global pointer */ -.option push -.option norelax - la gp, __global_pointer$ -.option pop + load_global_pointer /* - * Disable FPU to detect illegal usage of - * floating point in kernel space + * Disable FPU & VECTOR to detect illegal usage of + * floating point or vector in kernel space */ - li t0, SR_FS + li t0, SR_FS_VS csrc CSR_STATUS, t0 -#ifdef CONFIG_SMP +#ifdef CONFIG_RISCV_BOOT_SPINWAIT li t0, CONFIG_NR_CPUS - bgeu a0, t0, .Lsecondary_park -#endif + blt a0, t0, .Lgood_cores + tail .Lsecondary_park +.Lgood_cores: + /* The lottery system is only required for spinwait booting method */ +#ifndef CONFIG_XIP_KERNEL /* Pick one hart to run the main boot sequence */ la a3, hart_lottery li a2, 1 amoadd.w a3, a2, (a3) bnez a3, .Lsecondary_start +#else + /* hart_lottery in flash contains a magic number */ + la a3, hart_lottery + mv a2, a3 + XIP_FIXUP_OFFSET a2 + XIP_FIXUP_FLASH_OFFSET a3 + lw t1, (a3) + amoswap.w t0, t1, (a2) + /* first time here if hart_lottery in RAM is not set */ + beq t0, t1, .Lsecondary_start + +#endif /* CONFIG_XIP */ +#endif /* CONFIG_RISCV_BOOT_SPINWAIT */ + +#ifdef CONFIG_XIP_KERNEL + la sp, _end + THREAD_SIZE + XIP_FIXUP_OFFSET sp + mv s0, a0 + mv s1, a1 + call __copy_data + + /* Restore a0 & a1 copy */ + mv a0, s0 + mv a1, s1 +#endif + +#ifndef CONFIG_XIP_KERNEL /* Clear BSS for flat non-ELF images */ la a3, __bss_start la a4, __bss_stop - ble a4, a3, clear_bss_done -clear_bss: + ble a4, a3, .Lclear_bss_done +.Lclear_bss: REG_S zero, (a3) add a3, a3, RISCV_SZPTR - blt a3, a4, clear_bss -clear_bss_done: - - /* Save hart ID and DTB physical address */ - mv s0, a0 - mv s1, a1 + blt a3, a4, .Lclear_bss +.Lclear_bss_done: +#endif la a2, boot_cpu_hartid + XIP_FIXUP_OFFSET a2 REG_S a0, (a2) /* Initialize page tables and relocate to virtual addresses */ + la tp, init_task la sp, init_thread_union + THREAD_SIZE - mv a0, s1 + XIP_FIXUP_OFFSET sp + addi sp, sp, -PT_SIZE_ON_STACK + scs_load_init_stack +#ifdef CONFIG_BUILTIN_DTB + la a0, __dtb_start + XIP_FIXUP_OFFSET a0 +#else + mv a0, a1 +#endif /* CONFIG_BUILTIN_DTB */ call setup_vm #ifdef CONFIG_MMU la a0, early_pg_dir - call relocate + XIP_FIXUP_OFFSET a0 + call relocate_enable_mmu #endif /* CONFIG_MMU */ + call .Lsetup_trap_vector /* Restore C environment */ la tp, init_task - sw zero, TASK_TI_CPU(tp) la sp, init_thread_union + THREAD_SIZE + addi sp, sp, -PT_SIZE_ON_STACK + scs_load_current +#ifdef CONFIG_KASAN + call kasan_early_init +#endif /* Start the kernel */ - call parse_dtb + call soc_early_init tail start_kernel -#ifdef CONFIG_MMU -relocate: - /* Relocate return address */ - li a1, PAGE_OFFSET - la a2, _start - sub a1, a1, a2 - add ra, ra, a1 - - /* Point stvec to virtual address of intruction after satp write */ - la a2, 1f - add a2, a2, a1 - csrw CSR_TVEC, a2 - - /* Compute satp for kernel page tables, but don't load it yet */ - srl a2, a0, PAGE_SHIFT - li a1, SATP_MODE - or a2, a2, a1 - - /* - * Load trampoline page directory, which will cause us to trap to - * stvec if VA != PA, or simply fall through if VA == PA. We need a - * full fence here because setup_vm() just wrote these PTEs and we need - * to ensure the new translations are in use. - */ - la a0, trampoline_pg_dir - srl a0, a0, PAGE_SHIFT - or a0, a0, a1 - sfence.vma - csrw CSR_SATP, a0 -.align 2 -1: - /* Set trap vector to spin forever to help debug */ - la a0, .Lsecondary_park - csrw CSR_TVEC, a0 - - /* Reload the global pointer */ -.option push -.option norelax - la gp, __global_pointer$ -.option pop - - /* - * Switch to kernel page tables. A full fence is necessary in order to - * avoid using the trampoline translations, which are only correct for - * the first superpage. Fetching the fence is guarnteed to work - * because that first superpage is translated the same way. - */ - csrw CSR_SATP, a2 - sfence.vma - - ret -#endif /* CONFIG_MMU */ - +#ifdef CONFIG_RISCV_BOOT_SPINWAIT .Lsecondary_start: -#ifdef CONFIG_SMP /* Set trap vector to spin forever to help debug */ la a3, .Lsecondary_park csrw CSR_TVEC, a3 slli a3, a0, LGREG - la a1, __cpu_up_stack_pointer - la a2, __cpu_up_task_pointer + la a1, __cpu_spinwait_stack_pointer + XIP_FIXUP_OFFSET a1 + la a2, __cpu_spinwait_task_pointer + XIP_FIXUP_OFFSET a2 add a1, a3, a1 add a2, a3, a2 @@ -200,24 +347,13 @@ relocate: beqz tp, .Lwait_for_cpu_up fence -#ifdef CONFIG_MMU - /* Enable virtual memory and relocate to virtual address */ - la a0, swapper_pg_dir - call relocate -#endif + tail .Lsecondary_start_common +#endif /* CONFIG_RISCV_BOOT_SPINWAIT */ - tail smp_callin -#endif - -.align 2 -.Lsecondary_park: - /* We lack SMP support or have too many harts, so park this hart */ - wfi - j .Lsecondary_park -END(_start) +SYM_CODE_END(_start_kernel) #ifdef CONFIG_RISCV_M_MODE -ENTRY(reset_regs) +SYM_CODE_START_LOCAL(reset_regs) li sp, 0 li gp, 0 li tp, 0 @@ -246,12 +382,12 @@ ENTRY(reset_regs) li t4, 0 li t5, 0 li t6, 0 - csrw sscratch, 0 + csrw CSR_SCRATCH, 0 #ifdef CONFIG_FPU csrr t0, CSR_MISA andi t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D) - bnez t0, .Lreset_regs_done + beqz t0, .Lreset_regs_done_fpu li t1, SR_FS csrs CSR_STATUS, t1 @@ -289,12 +425,31 @@ ENTRY(reset_regs) fmv.s.x f31, zero csrw fcsr, 0 /* note that the caller must clear SR_FS */ +.Lreset_regs_done_fpu: #endif /* CONFIG_FPU */ -.Lreset_regs_done: + +#ifdef CONFIG_RISCV_ISA_V + csrr t0, CSR_MISA + li t1, COMPAT_HWCAP_ISA_V + and t0, t0, t1 + beqz t0, .Lreset_regs_done_vector + + /* + * Clear vector registers and reset vcsr + * VLMAX has a defined value, VLEN is a constant, + * and this form of vsetvli is defined to set vl to VLMAX. + */ + li t1, SR_VS + csrs CSR_STATUS, t1 + csrs CSR_VCSR, x0 + vsetvli t1, x0, e8, m8, ta, ma + vmv.v.i v0, 0 + vmv.v.i v8, 0 + vmv.v.i v16, 0 + vmv.v.i v24, 0 + /* note that the caller must clear SR_VS */ +.Lreset_regs_done_vector: +#endif /* CONFIG_RISCV_ISA_V */ ret -END(reset_regs) +SYM_CODE_END(reset_regs) #endif /* CONFIG_RISCV_M_MODE */ - -__PAGE_ALIGNED_BSS - /* Empty zero page */ - .balign PAGE_SIZE diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h index 105fb0496b24..a556fdaafed9 100644 --- a/arch/riscv/kernel/head.h +++ b/arch/riscv/kernel/head.h @@ -10,12 +10,14 @@ extern atomic_t hart_lottery; -asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void __init setup_vm(uintptr_t dtb_pa); +#ifdef CONFIG_XIP_KERNEL +asmlinkage void __init __copy_data(void); +#endif -extern void *__cpu_up_stack_pointer[]; -extern void *__cpu_up_task_pointer[]; - -void __init parse_dtb(void); +#ifdef CONFIG_RISCV_BOOT_SPINWAIT +extern void *__cpu_spinwait_stack_pointer[]; +extern void *__cpu_spinwait_task_pointer[]; +#endif #endif /* __ASM_HEAD_H */ diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S new file mode 100644 index 000000000000..d040dcf4add4 --- /dev/null +++ b/arch/riscv/kernel/hibernate-asm.S @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Hibernation low level support for RISCV. + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia <jeeheng.sia@starfivetech.com> + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> +#include <asm/csr.h> + +#include <linux/linkage.h> + +/* + * int __hibernate_cpu_resume(void) + * Switch back to the hibernated image's page table prior to restoring the CPU + * context. + * + * Always returns 0 + */ +SYM_FUNC_START(__hibernate_cpu_resume) + /* switch to hibernated image's page table. */ + csrw CSR_SATP, s0 + sfence.vma + + REG_L a0, hibernate_cpu_context + + suspend_restore_regs + + /* Return zero value. */ + mv a0, zero + + ret +SYM_FUNC_END(__hibernate_cpu_resume) + +/* + * Prepare to restore the image. + * a0: satp of saved page tables. + * a1: satp of temporary page tables. + * a2: cpu_resume. + */ +SYM_FUNC_START(hibernate_restore_image) + mv s0, a0 + mv s1, a1 + mv s2, a2 + REG_L s4, restore_pblist + REG_L a1, relocated_restore_code + + jr a1 +SYM_FUNC_END(hibernate_restore_image) + +/* + * The below code will be executed from a 'safe' page. + * It first switches to the temporary page table, then starts to copy the pages + * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume() + * to restore the CPU context. + */ +SYM_FUNC_START(hibernate_core_restore_code) + /* switch to temp page table. */ + csrw satp, s1 + sfence.vma +.Lcopy: + /* The below code will restore the hibernated image. */ + REG_L a1, HIBERN_PBE_ADDR(s4) + REG_L a0, HIBERN_PBE_ORIG(s4) + + copy_page a0, a1 + + REG_L s4, HIBERN_PBE_NEXT(s4) + bnez s4, .Lcopy + + jr s2 +SYM_FUNC_END(hibernate_core_restore_code) diff --git a/arch/riscv/kernel/hibernate.c b/arch/riscv/kernel/hibernate.c new file mode 100644 index 000000000000..671b686c0158 --- /dev/null +++ b/arch/riscv/kernel/hibernate.c @@ -0,0 +1,426 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hibernation support for RISCV + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia <jeeheng.sia@starfivetech.com> + */ + +#include <asm/barrier.h> +#include <asm/cacheflush.h> +#include <asm/mmu_context.h> +#include <asm/page.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/sections.h> +#include <asm/set_memory.h> +#include <asm/smp.h> +#include <asm/suspend.h> + +#include <linux/cpu.h> +#include <linux/memblock.h> +#include <linux/pm.h> +#include <linux/sched.h> +#include <linux/suspend.h> +#include <linux/utsname.h> + +/* The logical cpu number we should resume on, initialised to a non-cpu number. */ +static int sleep_cpu = -EINVAL; + +/* Pointer to the temporary resume page table. */ +static pgd_t *resume_pg_dir; + +/* CPU context to be saved. */ +struct suspend_context *hibernate_cpu_context; +EXPORT_SYMBOL_GPL(hibernate_cpu_context); + +unsigned long relocated_restore_code; +EXPORT_SYMBOL_GPL(relocated_restore_code); + +/** + * struct arch_hibernate_hdr_invariants - container to store kernel build version. + * @uts_version: to save the build number and date so that we do not resume with + * a different kernel. + */ +struct arch_hibernate_hdr_invariants { + char uts_version[__NEW_UTS_LEN + 1]; +}; + +/** + * struct arch_hibernate_hdr - helper parameters that help us to restore the image. + * @invariants: container to store kernel build version. + * @hartid: to make sure same boot_cpu executes the hibernate/restore code. + * @saved_satp: original page table used by the hibernated image. + * @restore_cpu_addr: the kernel's image address to restore the CPU context. + */ +static struct arch_hibernate_hdr { + struct arch_hibernate_hdr_invariants invariants; + unsigned long hartid; + unsigned long saved_satp; + unsigned long restore_cpu_addr; +} resume_hdr; + +static void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i) +{ + memset(i, 0, sizeof(*i)); + memcpy(i->uts_version, init_utsname()->version, sizeof(i->uts_version)); +} + +/* + * Check if the given pfn is in the 'nosave' section. + */ +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1); + + return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)); +} + +void notrace save_processor_state(void) +{ +} + +void notrace restore_processor_state(void) +{ +} + +/* + * Helper parameters need to be saved to the hibernation image header. + */ +int arch_hibernation_header_save(void *addr, unsigned int max_size) +{ + struct arch_hibernate_hdr *hdr = addr; + + if (max_size < sizeof(*hdr)) + return -EOVERFLOW; + + arch_hdr_invariants(&hdr->invariants); + + hdr->hartid = cpuid_to_hartid_map(sleep_cpu); + hdr->saved_satp = csr_read(CSR_SATP); + hdr->restore_cpu_addr = (unsigned long)__hibernate_cpu_resume; + + return 0; +} +EXPORT_SYMBOL_GPL(arch_hibernation_header_save); + +/* + * Retrieve the helper parameters from the hibernation image header. + */ +int arch_hibernation_header_restore(void *addr) +{ + struct arch_hibernate_hdr_invariants invariants; + struct arch_hibernate_hdr *hdr = addr; + int ret = 0; + + arch_hdr_invariants(&invariants); + + if (memcmp(&hdr->invariants, &invariants, sizeof(invariants))) { + pr_crit("Hibernate image not generated by this kernel!\n"); + return -EINVAL; + } + + sleep_cpu = riscv_hartid_to_cpuid(hdr->hartid); + if (sleep_cpu < 0) { + pr_crit("Hibernated on a CPU not known to this kernel!\n"); + sleep_cpu = -EINVAL; + return -EINVAL; + } + +#ifdef CONFIG_SMP + ret = bringup_hibernate_cpu(sleep_cpu); + if (ret) { + sleep_cpu = -EINVAL; + return ret; + } +#endif + resume_hdr = *hdr; + + return ret; +} +EXPORT_SYMBOL_GPL(arch_hibernation_header_restore); + +int swsusp_arch_suspend(void) +{ + int ret = 0; + + if (__cpu_suspend_enter(hibernate_cpu_context)) { + sleep_cpu = smp_processor_id(); + suspend_save_csrs(hibernate_cpu_context); + ret = swsusp_save(); + } else { + suspend_restore_csrs(hibernate_cpu_context); + flush_tlb_all(); + flush_icache_all(); + + /* + * Tell the hibernation core that we've just restored the memory. + */ + in_suspend = 0; + sleep_cpu = -EINVAL; + } + + return ret; +} + +static int temp_pgtable_map_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + pte_t *src_ptep; + pte_t *dst_ptep; + + if (pmd_none(READ_ONCE(*dst_pmdp))) { + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) + return -ENOMEM; + + pmd_populate_kernel(NULL, dst_pmdp, dst_ptep); + } + + dst_ptep = pte_offset_kernel(dst_pmdp, start); + src_ptep = pte_offset_kernel(src_pmdp, start); + + do { + pte_t pte = READ_ONCE(*src_ptep); + + if (pte_present(pte)) + set_pte(dst_ptep, __pte(pte_val(pte) | pgprot_val(prot))); + } while (dst_ptep++, src_ptep++, start += PAGE_SIZE, start < end); + + return 0; +} + +static int temp_pgtable_map_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; + + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) + return -ENOMEM; + + pud_populate(NULL, dst_pudp, dst_pmdp); + } + + dst_pmdp = pmd_offset(dst_pudp, start); + src_pmdp = pmd_offset(src_pudp, start); + + do { + pmd_t pmd = READ_ONCE(*src_pmdp); + + next = pmd_addr_end(start, end); + + if (pmd_none(pmd)) + continue; + + if (pmd_leaf(pmd)) { + set_pmd(dst_pmdp, __pmd(pmd_val(pmd) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pte(dst_pmdp, src_pmdp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pmdp++, src_pmdp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_map_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + pud_t *dst_pudp; + pud_t *src_pudp; + + if (p4d_none(READ_ONCE(*dst_p4dp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) + return -ENOMEM; + + p4d_populate(NULL, dst_p4dp, dst_pudp); + } + + dst_pudp = pud_offset(dst_p4dp, start); + src_pudp = pud_offset(src_p4dp, start); + + do { + pud_t pud = READ_ONCE(*src_pudp); + + next = pud_addr_end(start, end); + + if (pud_none(pud)) + continue; + + if (pud_leaf(pud)) { + set_pud(dst_pudp, __pud(pud_val(pud) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pmd(dst_pudp, src_pudp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pudp++, src_pudp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_map_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + p4d_t *dst_p4dp; + p4d_t *src_p4dp; + + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_p4dp = (p4d_t *)get_safe_page(GFP_ATOMIC); + if (!dst_p4dp) + return -ENOMEM; + + pgd_populate(NULL, dst_pgdp, dst_p4dp); + } + + dst_p4dp = p4d_offset(dst_pgdp, start); + src_p4dp = p4d_offset(src_pgdp, start); + + do { + p4d_t p4d = READ_ONCE(*src_p4dp); + + next = p4d_addr_end(start, end); + + if (p4d_none(p4d)) + continue; + + if (p4d_leaf(p4d)) { + set_p4d(dst_p4dp, __p4d(p4d_val(p4d) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pud(dst_p4dp, src_p4dp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_p4dp++, src_p4dp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_mapping(pgd_t *pgdp, unsigned long start, unsigned long end, pgprot_t prot) +{ + pgd_t *dst_pgdp = pgd_offset_pgd(pgdp, start); + pgd_t *src_pgdp = pgd_offset_k(start); + unsigned long next; + unsigned long ret; + + do { + pgd_t pgd = READ_ONCE(*src_pgdp); + + next = pgd_addr_end(start, end); + + if (pgd_none(pgd)) + continue; + + if (pgd_leaf(pgd)) { + set_pgd(dst_pgdp, __pgd(pgd_val(pgd) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_p4d(dst_pgdp, src_pgdp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pgdp++, src_pgdp++, start = next, start != end); + + return 0; +} + +static unsigned long relocate_restore_code(void) +{ + void *page = (void *)get_safe_page(GFP_ATOMIC); + + if (!page) + return -ENOMEM; + + copy_page(page, hibernate_core_restore_code); + + /* Make the page containing the relocated code executable. */ + set_memory_x((unsigned long)page, 1); + + return (unsigned long)page; +} + +int swsusp_arch_resume(void) +{ + unsigned long end = (unsigned long)pfn_to_virt(max_low_pfn); + unsigned long start = PAGE_OFFSET; + int ret; + + /* + * Memory allocated by get_safe_page() will be dealt with by the hibernation core, + * we don't need to free it here. + */ + resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!resume_pg_dir) + return -ENOMEM; + + /* + * Create a temporary page table and map the whole linear region as executable and + * writable. + */ + ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE | _PAGE_EXEC)); + if (ret) + return ret; + + /* Move the restore code to a new page so that it doesn't get overwritten by itself. */ + relocated_restore_code = relocate_restore_code(); + if (relocated_restore_code == -ENOMEM) + return -ENOMEM; + + /* + * Map the __hibernate_cpu_resume() address to the temporary page table so that the + * restore code can jumps to it after finished restore the image. The next execution + * code doesn't find itself in a different address space after switching over to the + * original page table used by the hibernated image. + * The __hibernate_cpu_resume() mapping is unnecessary for RV32 since the kernel and + * linear addresses are identical, but different for RV64. To ensure consistency, we + * map it for both RV32 and RV64 kernels. + * Additionally, we should ensure that the page is writable before restoring the image. + */ + start = (unsigned long)resume_hdr.restore_cpu_addr; + end = start + PAGE_SIZE; + + ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE)); + if (ret) + return ret; + + hibernate_restore_image(resume_hdr.saved_satp, (PFN_DOWN(__pa(resume_pg_dir)) | satp_mode), + resume_hdr.restore_cpu_addr); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP_SMP +int hibernate_resume_nonboot_cpu_disable(void) +{ + if (sleep_cpu < 0) { + pr_err("Failing to resume from hibernate on an unknown CPU\n"); + return -ENODEV; + } + + return freeze_secondary_cpus(sleep_cpu); +} +#endif + +static int __init riscv_hibernate_init(void) +{ + hibernate_cpu_context = kzalloc(sizeof(*hibernate_cpu_context), GFP_KERNEL); + + if (WARN_ON(!hibernate_cpu_context)) + return -ENOMEM; + + return 0; +} + +early_initcall(riscv_hibernate_init); diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h new file mode 100644 index 000000000000..3df30dd1c458 --- /dev/null +++ b/arch/riscv/kernel/image-vars.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Linker script variables to be set after section resolution, as + * ld.lld does not like variables assigned before SECTIONS is processed. + * Based on arch/arm64/kernel/image-vars.h + */ +#ifndef __RISCV_KERNEL_IMAGE_VARS_H +#define __RISCV_KERNEL_IMAGE_VARS_H + +#ifndef LINKER_SCRIPT +#error This file should only be included in vmlinux.lds.S +#endif + +#ifdef CONFIG_EFI + +/* + * The EFI stub has its own symbol namespace prefixed by __efistub_, to + * isolate it from the kernel proper. The following symbols are legally + * accessed by the stub, so provide some aliases to make them accessible. + * Only include data symbols here, or text symbols of functions that are + * guaranteed to be safe when executed at another offset than they were + * linked at. The routines below are all implemented in assembler in a + * position independent manner + */ +__efistub__start = _start; +__efistub__start_kernel = _start_kernel; +__efistub__end = _end; +__efistub__edata = _edata; +__efistub___init_text_end = __init_text_end; +#if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB) +__efistub_screen_info = screen_info; +#endif + +#endif + +#endif /* __RISCV_KERNEL_IMAGE_VARS_H */ diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index 3f07a91d5afb..9ceda02507ca 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -8,46 +8,109 @@ #include <linux/interrupt.h> #include <linux/irqchip.h> #include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/scs.h> #include <linux/seq_file.h> +#include <asm/sbi.h> #include <asm/smp.h> +#include <asm/softirq_stack.h> +#include <asm/stacktrace.h> -int arch_show_interrupts(struct seq_file *p, int prec) +static struct fwnode_handle *(*__get_intc_node)(void); + +void riscv_set_intc_hwnode_fn(struct fwnode_handle *(*fn)(void)) { - show_ipi_stats(p, prec); - return 0; + __get_intc_node = fn; } -asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs) +struct fwnode_handle *riscv_get_intc_hwnode(void) { - struct pt_regs *old_regs = set_irq_regs(regs); + if (__get_intc_node) + return __get_intc_node(); - irq_enter(); - switch (regs->cause & ~CAUSE_IRQ_FLAG) { - case IRQ_TIMER: - riscv_timer_interrupt(); - break; -#ifdef CONFIG_SMP - case IRQ_SOFT: - /* - * We only use software interrupts to pass IPIs, so if a non-SMP - * system gets one, then we don't know what to do. - */ - riscv_software_interrupt(); - break; + return NULL; +} +EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode); + +#ifdef CONFIG_IRQ_STACKS +#include <asm/irq_stack.h> + +DECLARE_PER_CPU(ulong *, irq_shadow_call_stack_ptr); + +#ifdef CONFIG_SHADOW_CALL_STACK +DEFINE_PER_CPU(ulong *, irq_shadow_call_stack_ptr); #endif - case IRQ_EXT: - handle_arch_irq(regs); - break; - default: - pr_alert("unexpected interrupt cause 0x%lx", regs->cause); - BUG(); + +static void init_irq_scs(void) +{ + int cpu; + + if (!scs_is_enabled()) + return; + + for_each_possible_cpu(cpu) + per_cpu(irq_shadow_call_stack_ptr, cpu) = + scs_alloc(cpu_to_node(cpu)); +} + +DEFINE_PER_CPU(ulong *, irq_stack_ptr); + +#ifdef CONFIG_VMAP_STACK +static void init_irq_stacks(void) +{ + int cpu; + ulong *p; + + for_each_possible_cpu(cpu) { + p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu)); + per_cpu(irq_stack_ptr, cpu) = p; } - irq_exit(); +} +#else +/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ +DEFINE_PER_CPU_ALIGNED(ulong [IRQ_STACK_SIZE/sizeof(ulong)], irq_stack); + +static void init_irq_stacks(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); +} +#endif /* CONFIG_VMAP_STACK */ + +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK +static void ___do_softirq(struct pt_regs *regs) +{ + __do_softirq(); +} - set_irq_regs(old_regs); +void do_softirq_own_stack(void) +{ + if (on_thread_stack()) + call_on_irq_stack(NULL, ___do_softirq); + else + __do_softirq(); +} +#endif /* CONFIG_SOFTIRQ_ON_OWN_STACK */ + +#else +static void init_irq_scs(void) {} +static void init_irq_stacks(void) {} +#endif /* CONFIG_IRQ_STACKS */ + +int arch_show_interrupts(struct seq_file *p, int prec) +{ + show_ipi_stats(p, prec); + return 0; } void __init init_IRQ(void) { + init_irq_scs(); + init_irq_stacks(); irqchip_init(); + if (!handle_arch_irq) + panic("No interrupt controller found."); + sbi_ipi_init(); } diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c new file mode 100644 index 000000000000..e6694759dbd0 --- /dev/null +++ b/arch/riscv/kernel/jump_label.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Emil Renner Berthing + * + * Based on arch/arm64/kernel/jump_label.c + */ +#include <linux/jump_label.h> +#include <linux/kernel.h> +#include <linux/memory.h> +#include <linux/mutex.h> +#include <asm/bug.h> +#include <asm/patch.h> + +#define RISCV_INSN_NOP 0x00000013U +#define RISCV_INSN_JAL 0x0000006fU + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + void *addr = (void *)jump_entry_code(entry); + u32 insn; + + if (type == JUMP_LABEL_JMP) { + long offset = jump_entry_target(entry) - jump_entry_code(entry); + + if (WARN_ON(offset & 1 || offset < -524288 || offset >= 524288)) + return; + + insn = RISCV_INSN_JAL | + (((u32)offset & GENMASK(19, 12)) << (12 - 12)) | + (((u32)offset & GENMASK(11, 11)) << (20 - 11)) | + (((u32)offset & GENMASK(10, 1)) << (21 - 1)) | + (((u32)offset & GENMASK(20, 20)) << (31 - 20)); + } else { + insn = RISCV_INSN_NOP; + } + + mutex_lock(&text_mutex); + patch_text_nosync(addr, &insn, sizeof(insn)); + mutex_unlock(&text_mutex); +} diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c new file mode 100644 index 000000000000..6afe80c7f03a --- /dev/null +++ b/arch/riscv/kernel/kernel_mode_vector.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2012 ARM Ltd. + * Author: Catalin Marinas <catalin.marinas@arm.com> + * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2021 SiFive + */ +#include <linux/compiler.h> +#include <linux/irqflags.h> +#include <linux/percpu.h> +#include <linux/preempt.h> +#include <linux/types.h> + +#include <asm/vector.h> +#include <asm/switch_to.h> +#include <asm/simd.h> +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +#include <asm/asm-prototypes.h> +#endif + +static inline void riscv_v_flags_set(u32 flags) +{ + WRITE_ONCE(current->thread.riscv_v_flags, flags); +} + +static inline void riscv_v_start(u32 flags) +{ + int orig; + + orig = riscv_v_flags(); + BUG_ON((orig & flags) != 0); + riscv_v_flags_set(orig | flags); + barrier(); +} + +static inline void riscv_v_stop(u32 flags) +{ + int orig; + + barrier(); + orig = riscv_v_flags(); + BUG_ON((orig & flags) == 0); + riscv_v_flags_set(orig & ~flags); +} + +/* + * Claim ownership of the CPU vector context for use by the calling context. + * + * The caller may freely manipulate the vector context metadata until + * put_cpu_vector_context() is called. + */ +void get_cpu_vector_context(void) +{ + /* + * disable softirqs so it is impossible for softirqs to nest + * get_cpu_vector_context() when kernel is actively using Vector. + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_disable(); + else + preempt_disable(); + + riscv_v_start(RISCV_KERNEL_MODE_V); +} + +/* + * Release the CPU vector context. + * + * Must be called from a context in which get_cpu_vector_context() was + * previously called, with no call to put_cpu_vector_context() in the + * meantime. + */ +void put_cpu_vector_context(void) +{ + riscv_v_stop(RISCV_KERNEL_MODE_V); + + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_enable(); + else + preempt_enable(); +} + +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +static __always_inline u32 *riscv_v_flags_ptr(void) +{ + return ¤t->thread.riscv_v_flags; +} + +static inline void riscv_preempt_v_set_dirty(void) +{ + *riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY; +} + +static inline void riscv_preempt_v_reset_flags(void) +{ + *riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE); +} + +static inline void riscv_v_ctx_depth_inc(void) +{ + *riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH; +} + +static inline void riscv_v_ctx_depth_dec(void) +{ + *riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH; +} + +static inline u32 riscv_v_ctx_get_depth(void) +{ + return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK; +} + +static int riscv_v_stop_kernel_context(void) +{ + if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current)) + return 1; + + riscv_preempt_v_clear_dirty(current); + riscv_v_stop(RISCV_PREEMPT_V); + return 0; +} + +static int riscv_v_start_kernel_context(bool *is_nested) +{ + struct __riscv_v_ext_state *kvstate, *uvstate; + + kvstate = ¤t->thread.kernel_vstate; + if (!kvstate->datap) + return -ENOENT; + + if (riscv_preempt_v_started(current)) { + WARN_ON(riscv_v_ctx_get_depth() == 0); + *is_nested = true; + get_cpu_vector_context(); + if (riscv_preempt_v_dirty(current)) { + __riscv_v_vstate_save(kvstate, kvstate->datap); + riscv_preempt_v_clear_dirty(current); + } + riscv_preempt_v_set_restore(current); + return 0; + } + + /* 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) { + uvstate = ¤t->thread.vstate; + __riscv_v_vstate_save(uvstate, uvstate->datap); + } + riscv_preempt_v_clear_dirty(current); + return 0; +} + +/* low-level V context handling code, called with irq disabled */ +asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs) +{ + int depth; + + if (!riscv_preempt_v_started(current)) + return; + + depth = riscv_v_ctx_get_depth(); + if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY) + riscv_preempt_v_set_dirty(); + + riscv_v_ctx_depth_inc(); +} + +asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs) +{ + struct __riscv_v_ext_state *vstate = ¤t->thread.kernel_vstate; + u32 depth; + + WARN_ON(!irqs_disabled()); + + if (!riscv_preempt_v_started(current)) + return; + + riscv_v_ctx_depth_dec(); + depth = riscv_v_ctx_get_depth(); + if (depth == 0) { + if (riscv_preempt_v_restore(current)) { + __riscv_v_vstate_restore(vstate, vstate->datap); + __riscv_v_vstate_clean(regs); + riscv_preempt_v_reset_flags(); + } + } +} +#else +#define riscv_v_start_kernel_context(nested) (-ENOENT) +#define riscv_v_stop_kernel_context() (-ENOENT) +#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */ + +/* + * kernel_vector_begin(): obtain the CPU vector registers for use by the calling + * context + * + * Must not be called unless may_use_simd() returns true. + * Task context in the vector registers is saved back to memory as necessary. + * + * A matching call to kernel_vector_end() must be made before returning from the + * calling context. + * + * The caller may freely use the vector registers until kernel_vector_end() is + * called. + */ +void kernel_vector_begin(void) +{ + bool nested = false; + + if (WARN_ON(!has_vector())) + return; + + BUG_ON(!may_use_simd()); + + if (riscv_v_start_kernel_context(&nested)) { + get_cpu_vector_context(); + riscv_v_vstate_save(¤t->thread.vstate, task_pt_regs(current)); + } + + if (!nested) + riscv_v_vstate_set_restore(current, task_pt_regs(current)); + + riscv_v_enable(); +} +EXPORT_SYMBOL_GPL(kernel_vector_begin); + +/* + * kernel_vector_end(): give the CPU vector registers back to the current task + * + * Must be called from a context in which kernel_vector_begin() was previously + * called, with no call to kernel_vector_end() in the meantime. + * + * The caller must not use the vector registers after this function is called, + * unless kernel_vector_begin() is called again in the meantime. + */ +void kernel_vector_end(void) +{ + if (WARN_ON(!has_vector())) + return; + + riscv_v_disable(); + + if (riscv_v_stop_kernel_context()) + put_cpu_vector_context(); +} +EXPORT_SYMBOL_GPL(kernel_vector_end); diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S new file mode 100644 index 000000000000..de0a4b35d01e --- /dev/null +++ b/arch/riscv/kernel/kexec_relocate.S @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 FORTH-ICS/CARV + * Nick Kossifidis <mick@ics.forth.gr> + */ + +#include <asm/asm.h> /* For RISCV_* and REG_* macros */ +#include <asm/csr.h> /* For CSR_* macros */ +#include <asm/page.h> /* For PAGE_SIZE */ +#include <linux/linkage.h> /* For SYM_* macros */ + +.section ".rodata" +SYM_CODE_START(riscv_kexec_relocate) + + /* + * s0: Pointer to the current entry + * s1: (const) Phys address to jump to after relocation + * s2: (const) Phys address of the FDT image + * s3: (const) The hartid of the current hart + * s4: (const) kernel_map.va_pa_offset, used when switching MMU off + * s5: Pointer to the destination address for the relocation + * s6: (const) Physical address of the main loop + */ + mv s0, a0 + mv s1, a1 + mv s2, a2 + mv s3, a3 + mv s4, a4 + mv s5, zero + mv s6, zero + + /* Disable / cleanup interrupts */ + csrw CSR_SIE, zero + csrw CSR_SIP, zero + + /* + * When we switch SATP.MODE to "Bare" we'll only + * play with physical addresses. However the first time + * we try to jump somewhere, the offset on the jump + * will be relative to pc which will still be on VA. To + * deal with this we set stvec to the physical address at + * the start of the loop below so that we jump there in + * any case. + */ + la s6, 1f + sub s6, s6, s4 + csrw CSR_STVEC, s6 + + /* + * With C-extension, here we get 42 Bytes and the next + * .align directive would pad zeros here up to 44 Bytes. + * So manually put a nop here to avoid zeros padding. + */ + nop + + /* Process entries in a loop */ +.align 2 +1: + REG_L t0, 0(s0) /* t0 = *image->entry */ + addi s0, s0, RISCV_SZPTR /* image->entry++ */ + + /* IND_DESTINATION entry ? -> save destination address */ + andi t1, t0, 0x1 + beqz t1, 2f + andi s5, t0, ~0x1 + j 1b + +2: + /* IND_INDIRECTION entry ? -> update next entry ptr (PA) */ + andi t1, t0, 0x2 + beqz t1, 2f + andi s0, t0, ~0x2 + csrw CSR_SATP, zero + jr s6 + +2: + /* IND_DONE entry ? -> jump to done label */ + andi t1, t0, 0x4 + beqz t1, 2f + j 4f + +2: + /* + * IND_SOURCE entry ? -> copy page word by word to the + * destination address we got from IND_DESTINATION + */ + andi t1, t0, 0x8 + beqz t1, 1b /* Unknown entry type, ignore it */ + andi t0, t0, ~0x8 + li t3, (PAGE_SIZE / RISCV_SZPTR) /* i = num words per page */ +3: /* copy loop */ + REG_L t1, (t0) /* t1 = *src_ptr */ + REG_S t1, (s5) /* *dst_ptr = *src_ptr */ + addi t0, t0, RISCV_SZPTR /* stc_ptr++ */ + addi s5, s5, RISCV_SZPTR /* dst_ptr++ */ + addi t3, t3, -0x1 /* i-- */ + beqz t3, 1b /* copy done ? */ + j 3b + +4: + /* Pass the arguments to the next kernel / Cleanup*/ + mv a0, s3 + mv a1, s2 + mv a2, s1 + + /* Cleanup */ + mv a3, zero + mv a4, zero + mv a5, zero + mv a6, zero + mv a7, zero + + mv s0, zero + mv s1, zero + mv s2, zero + mv s3, zero + mv s4, zero + mv s5, zero + mv s6, zero + mv s7, zero + mv s8, zero + mv s9, zero + mv s10, zero + mv s11, zero + + mv t0, zero + mv t1, zero + mv t2, zero + mv t3, zero + mv t4, zero + mv t5, zero + mv t6, zero + csrw CSR_SEPC, zero + csrw CSR_SCAUSE, zero + csrw CSR_SSCRATCH, zero + + /* + * Make sure the relocated code is visible + * and jump to the new kernel + */ + fence.i + + jr a2 + +SYM_CODE_END(riscv_kexec_relocate) +riscv_kexec_relocate_end: + + +/* Used for jumping to crashkernel */ +.section ".text" +SYM_CODE_START(riscv_kexec_norelocate) + /* + * s0: (const) Phys address to jump to + * s1: (const) Phys address of the FDT image + * s2: (const) The hartid of the current hart + */ + mv s0, a1 + mv s1, a2 + mv s2, a3 + + /* Disable / cleanup interrupts */ + csrw CSR_SIE, zero + csrw CSR_SIP, zero + + /* Pass the arguments to the next kernel / Cleanup*/ + mv a0, s2 + mv a1, s1 + mv a2, s0 + + /* Cleanup */ + mv a3, zero + mv a4, zero + mv a5, zero + mv a6, zero + mv a7, zero + + mv s0, zero + mv s1, zero + mv s2, zero + mv s3, zero + mv s4, zero + mv s5, zero + mv s6, zero + mv s7, zero + mv s8, zero + mv s9, zero + mv s10, zero + mv s11, zero + + mv t0, zero + mv t1, zero + mv t2, zero + mv t3, zero + mv t4, zero + mv t5, zero + mv t6, zero + csrw CSR_SEPC, zero + csrw CSR_SCAUSE, zero + csrw CSR_SSCRATCH, zero + + /* + * Switch to physical addressing + * This will also trigger a jump to CSR_STVEC + * which in this case is the address of the new + * kernel. + */ + csrw CSR_STVEC, a2 + csrw CSR_SATP, zero + +SYM_CODE_END(riscv_kexec_norelocate) + +.section ".rodata" +SYM_DATA(riscv_kexec_relocate_size, + .long riscv_kexec_relocate_end - riscv_kexec_relocate) + diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c new file mode 100644 index 000000000000..2e0266ae6bd7 --- /dev/null +++ b/arch/riscv/kernel/kgdb.c @@ -0,0 +1,371 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 SiFive + */ + +#include <linux/ptrace.h> +#include <linux/kdebug.h> +#include <linux/bug.h> +#include <linux/kgdb.h> +#include <linux/irqflags.h> +#include <linux/string.h> +#include <asm/cacheflush.h> +#include <asm/gdb_xml.h> +#include <asm/insn.h> + +enum { + NOT_KGDB_BREAK = 0, + KGDB_SW_BREAK, + KGDB_COMPILED_BREAK, + KGDB_SW_SINGLE_STEP +}; + +static unsigned long stepped_address; +static unsigned int stepped_opcode; + +static int decode_register_index(unsigned long opcode, int offset) +{ + return (opcode >> offset) & 0x1F; +} + +static int decode_register_index_short(unsigned long opcode, int offset) +{ + return ((opcode >> offset) & 0x7) + 8; +} + +/* Calculate the new address for after a step */ +static int get_step_address(struct pt_regs *regs, unsigned long *next_addr) +{ + unsigned long pc = regs->epc; + unsigned long *regs_ptr = (unsigned long *)regs; + unsigned int rs1_num, rs2_num; + int op_code; + + if (get_kernel_nofault(op_code, (void *)pc)) + return -EINVAL; + if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) { + if (riscv_insn_is_c_jalr(op_code) || + riscv_insn_is_c_jr(op_code)) { + rs1_num = decode_register_index(op_code, RVC_C2_RS1_OPOFF); + *next_addr = regs_ptr[rs1_num]; + } else if (riscv_insn_is_c_j(op_code) || + riscv_insn_is_c_jal(op_code)) { + *next_addr = RVC_EXTRACT_JTYPE_IMM(op_code) + pc; + } else if (riscv_insn_is_c_beqz(op_code)) { + rs1_num = decode_register_index_short(op_code, + RVC_C1_RS1_OPOFF); + if (!rs1_num || regs_ptr[rs1_num] == 0) + *next_addr = RVC_EXTRACT_BTYPE_IMM(op_code) + pc; + else + *next_addr = pc + 2; + } else if (riscv_insn_is_c_bnez(op_code)) { + rs1_num = + decode_register_index_short(op_code, RVC_C1_RS1_OPOFF); + if (rs1_num && regs_ptr[rs1_num] != 0) + *next_addr = RVC_EXTRACT_BTYPE_IMM(op_code) + pc; + else + *next_addr = pc + 2; + } else { + *next_addr = pc + 2; + } + } else { + if ((op_code & __INSN_OPCODE_MASK) == __INSN_BRANCH_OPCODE) { + bool result = false; + long imm = RV_EXTRACT_BTYPE_IMM(op_code); + unsigned long rs1_val = 0, rs2_val = 0; + + rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF); + rs2_num = decode_register_index(op_code, RVG_RS2_OPOFF); + if (rs1_num) + rs1_val = regs_ptr[rs1_num]; + if (rs2_num) + rs2_val = regs_ptr[rs2_num]; + + if (riscv_insn_is_beq(op_code)) + result = (rs1_val == rs2_val) ? true : false; + else if (riscv_insn_is_bne(op_code)) + result = (rs1_val != rs2_val) ? true : false; + else if (riscv_insn_is_blt(op_code)) + result = + ((long)rs1_val < + (long)rs2_val) ? true : false; + else if (riscv_insn_is_bge(op_code)) + result = + ((long)rs1_val >= + (long)rs2_val) ? true : false; + else if (riscv_insn_is_bltu(op_code)) + result = (rs1_val < rs2_val) ? true : false; + else if (riscv_insn_is_bgeu(op_code)) + result = (rs1_val >= rs2_val) ? true : false; + if (result) + *next_addr = imm + pc; + else + *next_addr = pc + 4; + } else if (riscv_insn_is_jal(op_code)) { + *next_addr = RV_EXTRACT_JTYPE_IMM(op_code) + pc; + } else if (riscv_insn_is_jalr(op_code)) { + rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF); + if (rs1_num) + *next_addr = ((unsigned long *)regs)[rs1_num]; + *next_addr += RV_EXTRACT_ITYPE_IMM(op_code); + } else if (riscv_insn_is_sret(op_code)) { + *next_addr = pc; + } else { + *next_addr = pc + 4; + } + } + return 0; +} + +static int do_single_step(struct pt_regs *regs) +{ + /* Determine where the target instruction will send us to */ + unsigned long addr = 0; + int error = get_step_address(regs, &addr); + + if (error) + return error; + + /* Store the op code in the stepped address */ + error = get_kernel_nofault(stepped_opcode, (void *)addr); + if (error) + return error; + + stepped_address = addr; + + /* Replace the op code with the break instruction */ + error = copy_to_kernel_nofault((void *)stepped_address, + arch_kgdb_ops.gdb_bpt_instr, + BREAK_INSTR_SIZE); + /* Flush and return */ + if (!error) { + flush_icache_range(addr, addr + BREAK_INSTR_SIZE); + kgdb_single_step = 1; + atomic_set(&kgdb_cpu_doing_single_step, + raw_smp_processor_id()); + } else { + stepped_address = 0; + stepped_opcode = 0; + } + return error; +} + +/* Undo a single step */ +static void undo_single_step(struct pt_regs *regs) +{ + if (stepped_opcode != 0) { + copy_to_kernel_nofault((void *)stepped_address, + (void *)&stepped_opcode, BREAK_INSTR_SIZE); + flush_icache_range(stepped_address, + stepped_address + BREAK_INSTR_SIZE); + } + stepped_address = 0; + stepped_opcode = 0; + kgdb_single_step = 0; + atomic_set(&kgdb_cpu_doing_single_step, -1); +} + +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { + {DBG_REG_ZERO, GDB_SIZEOF_REG, -1}, + {DBG_REG_RA, GDB_SIZEOF_REG, offsetof(struct pt_regs, ra)}, + {DBG_REG_SP, GDB_SIZEOF_REG, offsetof(struct pt_regs, sp)}, + {DBG_REG_GP, GDB_SIZEOF_REG, offsetof(struct pt_regs, gp)}, + {DBG_REG_TP, GDB_SIZEOF_REG, offsetof(struct pt_regs, tp)}, + {DBG_REG_T0, GDB_SIZEOF_REG, offsetof(struct pt_regs, t0)}, + {DBG_REG_T1, GDB_SIZEOF_REG, offsetof(struct pt_regs, t1)}, + {DBG_REG_T2, GDB_SIZEOF_REG, offsetof(struct pt_regs, t2)}, + {DBG_REG_FP, GDB_SIZEOF_REG, offsetof(struct pt_regs, s0)}, + {DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)}, + {DBG_REG_A0, GDB_SIZEOF_REG, offsetof(struct pt_regs, a0)}, + {DBG_REG_A1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)}, + {DBG_REG_A2, GDB_SIZEOF_REG, offsetof(struct pt_regs, a2)}, + {DBG_REG_A3, GDB_SIZEOF_REG, offsetof(struct pt_regs, a3)}, + {DBG_REG_A4, GDB_SIZEOF_REG, offsetof(struct pt_regs, a4)}, + {DBG_REG_A5, GDB_SIZEOF_REG, offsetof(struct pt_regs, a5)}, + {DBG_REG_A6, GDB_SIZEOF_REG, offsetof(struct pt_regs, a6)}, + {DBG_REG_A7, GDB_SIZEOF_REG, offsetof(struct pt_regs, a7)}, + {DBG_REG_S2, GDB_SIZEOF_REG, offsetof(struct pt_regs, s2)}, + {DBG_REG_S3, GDB_SIZEOF_REG, offsetof(struct pt_regs, s3)}, + {DBG_REG_S4, GDB_SIZEOF_REG, offsetof(struct pt_regs, s4)}, + {DBG_REG_S5, GDB_SIZEOF_REG, offsetof(struct pt_regs, s5)}, + {DBG_REG_S6, GDB_SIZEOF_REG, offsetof(struct pt_regs, s6)}, + {DBG_REG_S7, GDB_SIZEOF_REG, offsetof(struct pt_regs, s7)}, + {DBG_REG_S8, GDB_SIZEOF_REG, offsetof(struct pt_regs, s8)}, + {DBG_REG_S9, GDB_SIZEOF_REG, offsetof(struct pt_regs, s9)}, + {DBG_REG_S10, GDB_SIZEOF_REG, offsetof(struct pt_regs, s10)}, + {DBG_REG_S11, GDB_SIZEOF_REG, offsetof(struct pt_regs, s11)}, + {DBG_REG_T3, GDB_SIZEOF_REG, offsetof(struct pt_regs, t3)}, + {DBG_REG_T4, GDB_SIZEOF_REG, offsetof(struct pt_regs, t4)}, + {DBG_REG_T5, GDB_SIZEOF_REG, offsetof(struct pt_regs, t5)}, + {DBG_REG_T6, GDB_SIZEOF_REG, offsetof(struct pt_regs, t6)}, + {DBG_REG_EPC, GDB_SIZEOF_REG, offsetof(struct pt_regs, epc)}, + {DBG_REG_STATUS, GDB_SIZEOF_REG, offsetof(struct pt_regs, status)}, + {DBG_REG_BADADDR, GDB_SIZEOF_REG, offsetof(struct pt_regs, badaddr)}, + {DBG_REG_CAUSE, GDB_SIZEOF_REG, offsetof(struct pt_regs, cause)}, +}; + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + else + memset(mem, 0, dbg_reg_def[regno].size); + return dbg_reg_def[regno].name; +} + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; +} + +void +sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task) +{ + /* Initialize to zero */ + memset((char *)gdb_regs, 0, NUMREGBYTES); + + gdb_regs[DBG_REG_SP_OFF] = task->thread.sp; + gdb_regs[DBG_REG_FP_OFF] = task->thread.s[0]; + gdb_regs[DBG_REG_S1_OFF] = task->thread.s[1]; + gdb_regs[DBG_REG_S2_OFF] = task->thread.s[2]; + gdb_regs[DBG_REG_S3_OFF] = task->thread.s[3]; + gdb_regs[DBG_REG_S4_OFF] = task->thread.s[4]; + gdb_regs[DBG_REG_S5_OFF] = task->thread.s[5]; + gdb_regs[DBG_REG_S6_OFF] = task->thread.s[6]; + gdb_regs[DBG_REG_S7_OFF] = task->thread.s[7]; + gdb_regs[DBG_REG_S8_OFF] = task->thread.s[8]; + gdb_regs[DBG_REG_S9_OFF] = task->thread.s[10]; + gdb_regs[DBG_REG_S10_OFF] = task->thread.s[11]; + gdb_regs[DBG_REG_EPC_OFF] = task->thread.ra; +} + +void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) +{ + regs->epc = pc; +} + +void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, + char *remcom_out_buffer) +{ + if (!strncmp(remcom_in_buffer, gdb_xfer_read_target, + sizeof(gdb_xfer_read_target))) + strcpy(remcom_out_buffer, riscv_gdb_stub_target_desc); + else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml, + sizeof(gdb_xfer_read_cpuxml))) + strcpy(remcom_out_buffer, riscv_gdb_stub_cpuxml); +} + +static inline void kgdb_arch_update_addr(struct pt_regs *regs, + char *remcom_in_buffer) +{ + unsigned long addr; + char *ptr; + + ptr = &remcom_in_buffer[1]; + if (kgdb_hex2long(&ptr, &addr)) + regs->epc = addr; +} + +int kgdb_arch_handle_exception(int vector, int signo, int err_code, + char *remcom_in_buffer, char *remcom_out_buffer, + struct pt_regs *regs) +{ + int err = 0; + + undo_single_step(regs); + + switch (remcom_in_buffer[0]) { + case 'c': + case 'D': + case 'k': + if (remcom_in_buffer[0] == 'c') + kgdb_arch_update_addr(regs, remcom_in_buffer); + break; + case 's': + kgdb_arch_update_addr(regs, remcom_in_buffer); + err = do_single_step(regs); + break; + default: + err = -1; + } + return err; +} + +static int kgdb_riscv_kgdbbreak(unsigned long addr) +{ + if (stepped_address == addr) + return KGDB_SW_SINGLE_STEP; + if (atomic_read(&kgdb_setting_breakpoint)) + if (addr == (unsigned long)&kgdb_compiled_break) + return KGDB_COMPILED_BREAK; + + return kgdb_has_hit_break(addr); +} + +static int kgdb_riscv_notify(struct notifier_block *self, unsigned long cmd, + void *ptr) +{ + struct die_args *args = (struct die_args *)ptr; + struct pt_regs *regs = args->regs; + unsigned long flags; + int type; + + if (user_mode(regs)) + return NOTIFY_DONE; + + type = kgdb_riscv_kgdbbreak(regs->epc); + if (type == NOT_KGDB_BREAK && cmd == DIE_TRAP) + return NOTIFY_DONE; + + local_irq_save(flags); + + if (kgdb_handle_exception(type == KGDB_SW_SINGLE_STEP ? 0 : 1, + args->signr, cmd, regs)) + return NOTIFY_DONE; + + if (type == KGDB_COMPILED_BREAK) + regs->epc += 4; + + local_irq_restore(flags); + + return NOTIFY_STOP; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_riscv_notify, +}; + +int kgdb_arch_init(void) +{ + register_die_notifier(&kgdb_notifier); + + return 0; +} + +void kgdb_arch_exit(void) +{ + unregister_die_notifier(&kgdb_notifier); +} + +/* + * Global data + */ +#ifdef CONFIG_RISCV_ISA_C +const struct kgdb_arch arch_kgdb_ops = { + .gdb_bpt_instr = {0x02, 0x90}, /* c.ebreak */ +}; +#else +const struct kgdb_arch arch_kgdb_ops = { + .gdb_bpt_instr = {0x73, 0x00, 0x10, 0x00}, /* ebreak */ +}; +#endif diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c new file mode 100644 index 000000000000..ed9cad20c039 --- /dev/null +++ b/arch/riscv/kernel/machine_kexec.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 FORTH-ICS/CARV + * Nick Kossifidis <mick@ics.forth.gr> + */ + +#include <linux/kexec.h> +#include <asm/kexec.h> /* For riscv_kexec_* symbol defines */ +#include <linux/smp.h> /* For smp_send_stop () */ +#include <asm/cacheflush.h> /* For local_flush_icache_all() */ +#include <asm/barrier.h> /* For smp_wmb() */ +#include <asm/page.h> /* For PAGE_MASK */ +#include <linux/libfdt.h> /* For fdt_check_header() */ +#include <asm/set_memory.h> /* For set_memory_x() */ +#include <linux/compiler.h> /* For unreachable() */ +#include <linux/cpu.h> /* For cpu_down() */ +#include <linux/reboot.h> +#include <linux/interrupt.h> +#include <linux/irq.h> + +/* + * machine_kexec_prepare - Initialize kexec + * + * This function is called from do_kexec_load, when the user has + * provided us with an image to be loaded. Its goal is to validate + * the image and prepare the control code buffer as needed. + * Note that kimage_alloc_init has already been called and the + * control buffer has already been allocated. + */ +int +machine_kexec_prepare(struct kimage *image) +{ + struct kimage_arch *internal = &image->arch; + struct fdt_header fdt = {0}; + void *control_code_buffer = NULL; + unsigned int control_code_buffer_sz = 0; + int i = 0; + + /* Find the Flattened Device Tree and save its physical address */ + for (i = 0; i < image->nr_segments; i++) { + if (image->segment[i].memsz <= sizeof(fdt)) + continue; + + if (image->file_mode) + memcpy(&fdt, image->segment[i].buf, sizeof(fdt)); + else if (copy_from_user(&fdt, image->segment[i].buf, sizeof(fdt))) + continue; + + if (fdt_check_header(&fdt)) + continue; + + internal->fdt_addr = (unsigned long) image->segment[i].mem; + break; + } + + if (!internal->fdt_addr) { + pr_err("Device tree not included in the provided image\n"); + return -EINVAL; + } + + /* Copy the assembler code for relocation to the control page */ + if (image->type != KEXEC_TYPE_CRASH) { + control_code_buffer = page_address(image->control_code_page); + control_code_buffer_sz = page_size(image->control_code_page); + + if (unlikely(riscv_kexec_relocate_size > control_code_buffer_sz)) { + pr_err("Relocation code doesn't fit within a control page\n"); + return -EINVAL; + } + + memcpy(control_code_buffer, riscv_kexec_relocate, + riscv_kexec_relocate_size); + + /* Mark the control page executable */ + set_memory_x((unsigned long) control_code_buffer, 1); + } + + return 0; +} + + +/* + * machine_kexec_cleanup - Cleanup any leftovers from + * machine_kexec_prepare + * + * This function is called by kimage_free to handle any arch-specific + * allocations done on machine_kexec_prepare. Since we didn't do any + * allocations there, this is just an empty function. Note that the + * control buffer is freed by kimage_free. + */ +void +machine_kexec_cleanup(struct kimage *image) +{ +} + + +/* + * machine_shutdown - Prepare for a kexec reboot + * + * This function is called by kernel_kexec just before machine_kexec + * below. Its goal is to prepare the rest of the system (the other + * harts and possibly devices etc) for a kexec reboot. + */ +void machine_shutdown(void) +{ + /* + * No more interrupts on this hart + * until we are back up. + */ + local_irq_disable(); + +#if defined(CONFIG_HOTPLUG_CPU) + smp_shutdown_nonboot_cpus(smp_processor_id()); +#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; + int ret; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + /* + * First try to remove the active state. If this + * fails, try to EOI the interrupt. + */ + ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + + if (ret && irqd_irq_inprogress(&desc->irq_data) && + chip->irq_eoi) + 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 + * + * This function is called by crash_kexec just before machine_kexec + * and its goal is to shutdown non-crashing cpus and save registers. + */ +void +machine_crash_shutdown(struct pt_regs *regs) +{ + local_irq_disable(); + + /* shutdown non-crashing cpus */ + crash_smp_send_stop(); + + crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + + pr_info("Starting crashdump kernel...\n"); +} + +/* + * machine_kexec - Jump to the loaded kimage + * + * This function is called by kernel_kexec which is called by the + * reboot system call when the reboot cmd is LINUX_REBOOT_CMD_KEXEC, + * or by crash_kernel which is called by the kernel's arch-specific + * trap handler in case of a kernel panic. It's the final stage of + * the kexec process where the pre-loaded kimage is ready to be + * executed. We assume at this point that all other harts are + * suspended and this hart will be the new boot hart. + */ +void __noreturn +machine_kexec(struct kimage *image) +{ + struct kimage_arch *internal = &image->arch; + unsigned long jump_addr = (unsigned long) image->start; + unsigned long first_ind_entry = (unsigned long) &image->head; + unsigned long this_cpu_id = __smp_processor_id(); + unsigned long this_hart_id = cpuid_to_hartid_map(this_cpu_id); + unsigned long fdt_addr = internal->fdt_addr; + void *control_code_buffer = page_address(image->control_code_page); + riscv_kexec_method kexec_method = NULL; + +#ifdef CONFIG_SMP + WARN(smp_crash_stop_failed(), + "Some CPUs may be stale, kdump will be unreliable.\n"); +#endif + + if (image->type != KEXEC_TYPE_CRASH) + kexec_method = control_code_buffer; + else + kexec_method = (riscv_kexec_method) &riscv_kexec_norelocate; + + pr_notice("Will call new kernel at %08lx from hart id %lx\n", + jump_addr, this_hart_id); + pr_notice("FDT image at %08lx\n", fdt_addr); + + /* Make sure the relocation code is visible to the hart */ + local_flush_icache_all(); + + /* Jump to the relocation code */ + pr_notice("Bye...\n"); + kexec_method(first_ind_entry, jump_addr, fdt_addr, + this_hart_id, kernel_map.va_pa_offset); + unreachable(); +} diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c new file mode 100644 index 000000000000..b0bf8c1722c0 --- /dev/null +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_file for riscv, use vmlinux as the dump-capture kernel image. + * + * Copyright (C) 2021 Huawei Technologies Co, Ltd. + * + * Author: Liao Chang (liaochang1@huawei.com) + */ +#include <linux/kexec.h> + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &elf_kexec_ops, + NULL +}; diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 35a6ed76cb8b..b7561288e8da 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -3,237 +3,260 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/export.h> #include <asm/asm.h> #include <asm/csr.h> #include <asm/unistd.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> -#include <asm-generic/export.h> #include <asm/ftrace.h> .text - .macro SAVE_ABI_STATE -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi sp, sp, -48 - sd s0, 32(sp) - sd ra, 40(sp) - addi s0, sp, 48 - sd t0, 24(sp) - sd t1, 16(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - sd t2, 8(sp) -#endif -#else - addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) - addi s0, sp, 16 -#endif - .endm +#define FENTRY_RA_OFFSET 8 +#define ABI_SIZE_ON_STACK 80 +#define ABI_A0 0 +#define ABI_A1 8 +#define ABI_A2 16 +#define ABI_A3 24 +#define ABI_A4 32 +#define ABI_A5 40 +#define ABI_A6 48 +#define ABI_A7 56 +#define ABI_T0 64 +#define ABI_RA 72 - .macro RESTORE_ABI_STATE -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - ld s0, 32(sp) - ld ra, 40(sp) - addi sp, sp, 48 -#else - ld ra, 8(sp) - ld s0, 0(sp) - addi sp, sp, 16 -#endif + .macro SAVE_ABI + addi sp, sp, -ABI_SIZE_ON_STACK + + REG_S a0, ABI_A0(sp) + REG_S a1, ABI_A1(sp) + REG_S a2, ABI_A2(sp) + REG_S a3, ABI_A3(sp) + REG_S a4, ABI_A4(sp) + REG_S a5, ABI_A5(sp) + REG_S a6, ABI_A6(sp) + REG_S a7, ABI_A7(sp) + REG_S t0, ABI_T0(sp) + REG_S ra, ABI_RA(sp) .endm - .macro RESTORE_GRAPH_ARGS - ld a0, 24(sp) - ld a1, 16(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, 8(sp) -#endif + .macro RESTORE_ABI + REG_L a0, ABI_A0(sp) + REG_L a1, ABI_A1(sp) + REG_L a2, ABI_A2(sp) + REG_L a3, ABI_A3(sp) + REG_L a4, ABI_A4(sp) + REG_L a5, ABI_A5(sp) + REG_L a6, ABI_A6(sp) + REG_L a7, ABI_A7(sp) + REG_L t0, ABI_T0(sp) + REG_L ra, ABI_RA(sp) + + addi sp, sp, ABI_SIZE_ON_STACK .endm -ENTRY(ftrace_graph_caller) - addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) - addi s0, sp, 16 -ftrace_graph_call: - .global ftrace_graph_call - /* - * Calling ftrace_enable/disable_ftrace_graph_caller would overwrite the - * call below. Check ftrace_modify_all_code for details. - */ - call ftrace_stub - ld ra, 8(sp) - ld s0, 0(sp) - addi sp, sp, 16 - ret -ENDPROC(ftrace_graph_caller) - -ENTRY(ftrace_caller) - /* - * a0: the address in the caller when calling ftrace_caller - * a1: the caller's return address - * a2: the address of global variable function_trace_op - */ - ld a1, -8(s0) - addi a0, ra, -MCOUNT_INSN_SIZE - la t5, function_trace_op - ld a2, 0(t5) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* - * the graph tracer (specifically, prepare_ftrace_return) needs these - * arguments but for now the function tracer occupies the regs, so we - * save them in temporary regs to recover later. - */ - addi t0, s0, -8 - mv t1, a0 -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld t2, -16(s0) -#endif -#endif +/** +* SAVE_ABI_REGS - save regs against the pt_regs struct +* +* @all: tell if saving all the regs +* +* If all is set, all the regs will be saved, otherwise only ABI +* related regs (a0-a7,epc,ra and optional s0) will be saved. +* +* After the stack is established, +* +* 0(sp) stores the PC of the traced function which can be accessed +* by &(fregs)->regs->epc in tracing function. Note that the real +* function entry address should be computed with -FENTRY_RA_OFFSET. +* +* 8(sp) stores the function return address (i.e. parent IP) that +* can be accessed by &(fregs)->regs->ra in tracing function. +* +* The other regs are saved at the respective localtion and accessed +* by the respective pt_regs member. +* +* Here is the layout of stack for your reference. +* +* PT_SIZE_ON_STACK -> +++++++++ +* + ..... + +* + t3-t6 + +* + s2-s11+ +* + a0-a7 + --++++-> ftrace_caller saved +* + s1 + + +* + s0 + --+ +* + t0-t2 + + +* + tp + + +* + gp + + +* + sp + + +* + ra + --+ // parent IP +* sp -> + epc + --+ // PC +* +++++++++ +**/ + .macro SAVE_ABI_REGS, all=0 + addi sp, sp, -PT_SIZE_ON_STACK - SAVE_ABI_STATE -ftrace_call: - .global ftrace_call - /* - * For the dynamic ftrace to work, here we should reserve at least - * 8 bytes for a functional auipc-jalr pair. The following call - * serves this purpose. - * - * Calling ftrace_update_ftrace_func would overwrite the nops below. - * Check ftrace_modify_all_code for details. - */ - call ftrace_stub + REG_S t0, PT_EPC(sp) + REG_S x1, PT_RA(sp) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - RESTORE_GRAPH_ARGS - call ftrace_graph_caller -#endif + // save the ABI regs - RESTORE_ABI_STATE - ret -ENDPROC(ftrace_caller) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - .macro SAVE_ALL - addi sp, sp, -(PT_SIZE_ON_STACK+16) - sd s0, (PT_SIZE_ON_STACK)(sp) - sd ra, (PT_SIZE_ON_STACK+8)(sp) - addi s0, sp, (PT_SIZE_ON_STACK+16) - - sd x1, PT_RA(sp) - sd x2, PT_SP(sp) - sd x3, PT_GP(sp) - sd x4, PT_TP(sp) - sd x5, PT_T0(sp) - sd x6, PT_T1(sp) - sd x7, PT_T2(sp) - sd x8, PT_S0(sp) - sd x9, PT_S1(sp) - sd x10, PT_A0(sp) - sd x11, PT_A1(sp) - sd x12, PT_A2(sp) - sd x13, PT_A3(sp) - sd x14, PT_A4(sp) - sd x15, PT_A5(sp) - sd x16, PT_A6(sp) - sd x17, PT_A7(sp) - sd x18, PT_S2(sp) - sd x19, PT_S3(sp) - sd x20, PT_S4(sp) - sd x21, PT_S5(sp) - sd x22, PT_S6(sp) - sd x23, PT_S7(sp) - sd x24, PT_S8(sp) - sd x25, PT_S9(sp) - sd x26, PT_S10(sp) - sd x27, PT_S11(sp) - sd x28, PT_T3(sp) - sd x29, PT_T4(sp) - sd x30, PT_T5(sp) - sd x31, PT_T6(sp) - .endm + // save the leftover regs - .macro RESTORE_ALL - ld x1, PT_RA(sp) - ld x2, PT_SP(sp) - ld x3, PT_GP(sp) - ld x4, PT_TP(sp) - ld x5, PT_T0(sp) - ld x6, PT_T1(sp) - ld x7, PT_T2(sp) - ld x8, PT_S0(sp) - ld x9, PT_S1(sp) - ld x10, PT_A0(sp) - ld x11, PT_A1(sp) - ld x12, PT_A2(sp) - ld x13, PT_A3(sp) - ld x14, PT_A4(sp) - ld x15, PT_A5(sp) - ld x16, PT_A6(sp) - ld x17, PT_A7(sp) - ld x18, PT_S2(sp) - ld x19, PT_S3(sp) - ld x20, PT_S4(sp) - ld x21, PT_S5(sp) - ld x22, PT_S6(sp) - ld x23, PT_S7(sp) - ld x24, PT_S8(sp) - ld x25, PT_S9(sp) - ld x26, PT_S10(sp) - ld x27, PT_S11(sp) - ld x28, PT_T3(sp) - ld x29, PT_T4(sp) - ld x30, PT_T5(sp) - ld x31, PT_T6(sp) - - ld s0, (PT_SIZE_ON_STACK)(sp) - ld ra, (PT_SIZE_ON_STACK+8)(sp) - addi sp, sp, (PT_SIZE_ON_STACK+16) + .if \all == 1 + REG_S x2, PT_SP(sp) + REG_S x3, PT_GP(sp) + REG_S x4, PT_TP(sp) + REG_S x5, PT_T0(sp) + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) + + // save s0 if FP_TEST defined + + .else +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + REG_S x8, PT_S0(sp) +#endif + .endif .endm - .macro RESTORE_GRAPH_REG_ARGS - ld a0, PT_T0(sp) - ld a1, PT_T1(sp) + .macro RESTORE_ABI_REGS, all=0 + REG_L t0, PT_EPC(sp) + REG_L x1, PT_RA(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + + .if \all == 1 + REG_L x2, PT_SP(sp) + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + + .else #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, PT_T2(sp) + REG_L x8, PT_S0(sp) #endif + .endif + addi sp, sp, PT_SIZE_ON_STACK .endm -/* - * Most of the contents are the same as ftrace_caller. - */ -ENTRY(ftrace_regs_caller) - /* - * a3: the address of all registers in the stack - */ - ld a1, -8(s0) - addi a0, ra, -MCOUNT_INSN_SIZE - la t5, function_trace_op - ld a2, 0(t5) - addi a3, sp, -(PT_SIZE_ON_STACK+16) + .macro PREPARE_ARGS + addi a0, t0, -FENTRY_RA_OFFSET + la a1, function_trace_op + REG_L a2, 0(a1) + mv a1, ra + mv a3, sp + .endm + +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS +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 + +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + call ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi t0, s0, -8 - mv t1, a0 + addi a0, sp, ABI_RA + REG_L a1, ABI_T0(sp) + addi a1, a1, -FENTRY_RA_OFFSET #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld t2, -16(s0) + mv a2, s0 #endif +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) + call ftrace_stub #endif - SAVE_ALL + RESTORE_ABI + jr t0 +SYM_FUNC_END(ftrace_caller) -ftrace_regs_call: - .global ftrace_regs_call +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +SYM_FUNC_START(ftrace_regs_caller) + mv t1, zero + SAVE_ABI_REGS 1 + PREPARE_ARGS + +SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) call ftrace_stub -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - RESTORE_GRAPH_REG_ARGS - call ftrace_graph_caller -#endif + RESTORE_ABI_REGS 1 + bnez t1, .Ldirect + jr t0 +.Ldirect: + jr t1 +SYM_FUNC_END(ftrace_regs_caller) + +SYM_FUNC_START(ftrace_caller) + SAVE_ABI_REGS 0 + PREPARE_ARGS - RESTORE_ALL - ret -ENDPROC(ftrace_regs_caller) +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + call ftrace_stub + + RESTORE_ABI_REGS 0 + jr t0 +SYM_FUNC_END(ftrace_caller) #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + jr t0 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 8a5593ff9ff3..d7ec69ac6910 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -3,20 +3,21 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> +#include <linux/export.h> #include <asm/asm.h> #include <asm/csr.h> #include <asm/unistd.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> -#include <asm-generic/export.h> #include <asm/ftrace.h> .text .macro SAVE_ABI_STATE addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) + REG_S s0, 0*SZREG(sp) + REG_S ra, 1*SZREG(sp) addi s0, sp, 16 .endm @@ -25,36 +26,42 @@ * register if a0 was not saved. */ .macro SAVE_RET_ABI_STATE - addi sp, sp, -32 - sd s0, 16(sp) - sd ra, 24(sp) - sd a0, 8(sp) - addi s0, sp, 32 + 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 .endm .macro RESTORE_ABI_STATE - ld ra, 8(sp) - ld s0, 0(sp) + REG_L ra, 1*SZREG(sp) + REG_L s0, 0*SZREG(sp) addi sp, sp, 16 .endm .macro RESTORE_RET_ABI_STATE - ld ra, 24(sp) - ld s0, 16(sp) - ld a0, 8(sp) - addi sp, sp, 32 + 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 .endm -ENTRY(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub) #ifdef CONFIG_DYNAMIC_FTRACE - .global _mcount - .set _mcount, ftrace_stub + .global MCOUNT_NAME + .set MCOUNT_NAME, ftrace_stub #endif ret -ENDPROC(ftrace_stub) +SYM_FUNC_END(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(return_to_handler) +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + +SYM_FUNC_START(return_to_handler) /* * On implementing the frame point test, the ideal way is to compare the * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return. @@ -63,36 +70,31 @@ ENTRY(return_to_handler) * So alternatively we check the *old* frame pointer position, that is, the * value stored in -16(s0) on entry, and the s0 on return. */ -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - mv t6, s0 -#endif SAVE_RET_ABI_STATE -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - mv a0, t6 -#endif + mv a0, sp call ftrace_return_to_handler - mv a1, a0 + mv a2, a0 RESTORE_RET_ABI_STATE - jalr a1 -ENDPROC(return_to_handler) + jalr a2 +SYM_FUNC_END(return_to_handler) #endif #ifndef CONFIG_DYNAMIC_FTRACE -ENTRY(_mcount) +SYM_FUNC_START(MCOUNT_NAME) la t4, ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER la t0, ftrace_graph_return - ld t1, 0(t0) - bne t1, t4, do_ftrace_graph_caller + REG_L t1, 0(t0) + bne t1, t4, .Ldo_ftrace_graph_caller la t3, ftrace_graph_entry - ld t2, 0(t3) + REG_L t2, 0(t3) la t6, ftrace_graph_entry_stub - bne t2, t6, do_ftrace_graph_caller + bne t2, t6, .Ldo_ftrace_graph_caller #endif la t3, ftrace_trace_function - ld t5, 0(t3) - bne t5, t4, do_trace + REG_L t5, 0(t3) + bne t5, t4, .Ldo_trace ret #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -100,11 +102,11 @@ ENTRY(_mcount) * A pseudo representation for the function graph tracer: * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller) */ -do_ftrace_graph_caller: - addi a0, s0, -8 +.Ldo_ftrace_graph_caller: + addi a0, s0, -SZREG mv a1, ra #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, -16(s0) + REG_L a2, -2*SZREG(s0) #endif SAVE_ABI_STATE call prepare_ftrace_return @@ -116,14 +118,14 @@ do_ftrace_graph_caller: * A pseudo representation for the function tracer: * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller) */ -do_trace: - ld a1, -8(s0) +.Ldo_trace: + REG_L a1, -SZREG(s0) mv a0, ra SAVE_ABI_STATE jalr t5 RESTORE_ABI_STATE ret -ENDPROC(_mcount) +SYM_FUNC_END(MCOUNT_NAME) #endif -EXPORT_SYMBOL(_mcount) +EXPORT_SYMBOL(MCOUNT_NAME) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index b7401858d872..5e5a82644451 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -7,70 +7,136 @@ #include <linux/elf.h> #include <linux/err.h> #include <linux/errno.h> +#include <linux/hashtable.h> +#include <linux/kernel.h> +#include <linux/log2.h> #include <linux/moduleloader.h> +#include <linux/vmalloc.h> +#include <linux/sizes.h> +#include <linux/pgtable.h> +#include <asm/alternative.h> +#include <asm/sections.h> + +struct used_bucket { + struct list_head head; + struct hlist_head *bucket; +}; + +struct relocation_head { + struct hlist_node node; + struct list_head *rel_entry; + void *location; +}; + +struct relocation_entry { + struct list_head head; + Elf_Addr value; + unsigned int type; +}; + +struct relocation_handlers { + int (*reloc_handler)(struct module *me, void *location, Elf_Addr v); + int (*accumulate_handler)(struct module *me, void *location, + long buffer); +}; + +/* + * The auipc+jalr instruction pair can reach any PC-relative offset + * in the range [-2^31 - 2^11, 2^31 - 2^11) + */ +static bool riscv_insn_valid_32bit_offset(ptrdiff_t val) +{ +#ifdef CONFIG_32BIT + return true; +#else + return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11)); +#endif +} -static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) +static int riscv_insn_rmw(void *location, u32 keep, u32 set) +{ + __le16 *parcel = location; + u32 insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16; + + insn &= keep; + insn |= set; + + parcel[0] = cpu_to_le16(insn); + parcel[1] = cpu_to_le16(insn >> 16); + return 0; +} + +static int riscv_insn_rvc_rmw(void *location, u16 keep, u16 set) +{ + __le16 *parcel = location; + u16 insn = le16_to_cpu(*parcel); + + insn &= keep; + insn |= set; + + *parcel = cpu_to_le16(insn); + return 0; +} + +static int apply_r_riscv_32_rela(struct module *me, void *location, Elf_Addr v) { if (v != (u32)v) { pr_err("%s: value %016llx out of range for 32-bit field\n", me->name, (long long)v); return -EINVAL; } - *location = v; + *(u32 *)location = v; return 0; } -static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_riscv_64_rela(struct module *me, void *location, Elf_Addr v) { *(u64 *)location = v; return 0; } -static int apply_r_riscv_branch_rela(struct module *me, u32 *location, +static int apply_r_riscv_branch_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - location; u32 imm12 = (offset & 0x1000) << (31 - 12); u32 imm11 = (offset & 0x800) >> (11 - 7); u32 imm10_5 = (offset & 0x7e0) << (30 - 10); u32 imm4_1 = (offset & 0x1e) << (11 - 4); - *location = (*location & 0x1fff07f) | imm12 | imm11 | imm10_5 | imm4_1; - return 0; + return riscv_insn_rmw(location, 0x1fff07f, imm12 | imm11 | imm10_5 | imm4_1); } -static int apply_r_riscv_jal_rela(struct module *me, u32 *location, +static int apply_r_riscv_jal_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - location; u32 imm20 = (offset & 0x100000) << (31 - 20); u32 imm19_12 = (offset & 0xff000); u32 imm11 = (offset & 0x800) << (20 - 11); u32 imm10_1 = (offset & 0x7fe) << (30 - 10); - *location = (*location & 0xfff) | imm20 | imm19_12 | imm11 | imm10_1; - return 0; + return riscv_insn_rmw(location, 0xfff, imm20 | imm19_12 | imm11 | imm10_1); } -static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location, +static int apply_r_riscv_rvc_branch_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - location; u16 imm8 = (offset & 0x100) << (12 - 8); u16 imm7_6 = (offset & 0xc0) >> (6 - 5); u16 imm5 = (offset & 0x20) >> (5 - 2); u16 imm4_3 = (offset & 0x18) << (12 - 5); u16 imm2_1 = (offset & 0x6) << (12 - 10); - *(u16 *)location = (*(u16 *)location & 0xe383) | - imm8 | imm7_6 | imm5 | imm4_3 | imm2_1; - return 0; + return riscv_insn_rvc_rmw(location, 0xe383, + imm8 | imm7_6 | imm5 | imm4_3 | imm2_1); } -static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location, +static int apply_r_riscv_rvc_jump_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - location; u16 imm11 = (offset & 0x800) << (12 - 11); u16 imm10 = (offset & 0x400) >> (10 - 8); u16 imm9_8 = (offset & 0x300) << (12 - 11); @@ -80,41 +146,36 @@ static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location, u16 imm4 = (offset & 0x10) << (12 - 5); u16 imm3_1 = (offset & 0xe) << (12 - 10); - *(u16 *)location = (*(u16 *)location & 0xe003) | - imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1; - return 0; + return riscv_insn_rvc_rmw(location, 0xe003, + imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1); } -static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location, +static int apply_r_riscv_pcrel_hi20_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; - s32 hi20; + ptrdiff_t offset = (void *)v - location; - if (offset != (s32)offset) { + if (!riscv_insn_valid_32bit_offset(offset)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); return -EINVAL; } - hi20 = (offset + 0x800) & 0xfffff000; - *location = (*location & 0xfff) | hi20; - return 0; + return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000); } -static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, u32 *location, +static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, void *location, Elf_Addr v) { /* * v is the lo12 value to fill. It is calculated before calling this * handler. */ - *location = (*location & 0xfffff) | ((v & 0xfff) << 20); - return 0; + return riscv_insn_rmw(location, 0xfffff, (v & 0xfff) << 20); } -static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location, +static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, void *location, Elf_Addr v) { /* @@ -124,15 +185,12 @@ static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, u32 *location, u32 imm11_5 = (v & 0xfe0) << (31 - 11); u32 imm4_0 = (v & 0x1f) << (11 - 4); - *location = (*location & 0x1fff07f) | imm11_5 | imm4_0; - return 0; + return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0); } -static int apply_r_riscv_hi20_rela(struct module *me, u32 *location, +static int apply_r_riscv_hi20_rela(struct module *me, void *location, Elf_Addr v) { - s32 hi20; - if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", @@ -140,22 +198,20 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location, return -EINVAL; } - hi20 = ((s32)v + 0x800) & 0xfffff000; - *location = (*location & 0xfff) | hi20; - return 0; + return riscv_insn_rmw(location, 0xfff, ((s32)v + 0x800) & 0xfffff000); } -static int apply_r_riscv_lo12_i_rela(struct module *me, u32 *location, +static int apply_r_riscv_lo12_i_rela(struct module *me, void *location, Elf_Addr v) { /* Skip medlow checking because of filtering by HI20 already */ s32 hi20 = ((s32)v + 0x800) & 0xfffff000; s32 lo12 = ((s32)v - hi20); - *location = (*location & 0xfffff) | ((lo12 & 0xfff) << 20); - return 0; + + return riscv_insn_rmw(location, 0xfffff, (lo12 & 0xfff) << 20); } -static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location, +static int apply_r_riscv_lo12_s_rela(struct module *me, void *location, Elf_Addr v) { /* Skip medlow checking because of filtering by HI20 already */ @@ -163,20 +219,18 @@ static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location, s32 lo12 = ((s32)v - hi20); u32 imm11_5 = (lo12 & 0xfe0) << (31 - 11); u32 imm4_0 = (lo12 & 0x1f) << (11 - 4); - *location = (*location & 0x1fff07f) | imm11_5 | imm4_0; - return 0; + + return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0); } -static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location, +static int apply_r_riscv_got_hi20_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; - s32 hi20; + ptrdiff_t offset = (void *)v - location; /* Always emit the got entry */ if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { - offset = module_emit_got_entry(me, v); - offset = (void *)offset - (void *)location; + offset = (void *)module_emit_got_entry(me, v) - location; } else { pr_err( "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n", @@ -184,23 +238,19 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location, return -EINVAL; } - hi20 = (offset + 0x800) & 0xfffff000; - *location = (*location & 0xfff) | hi20; - return 0; + return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000); } -static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, +static int apply_r_riscv_call_plt_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; - s32 fill_v = offset; + ptrdiff_t offset = (void *)v - location; u32 hi20, lo12; - if (offset != fill_v) { + if (!riscv_insn_valid_32bit_offset(offset)) { /* Only emit the plt entry if offset over 32-bit range */ if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { - offset = module_emit_plt_entry(me, v); - offset = (void *)offset - (void *)location; + offset = (void *)module_emit_plt_entry(me, v) - location; } else { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", @@ -211,19 +261,17 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, hi20 = (offset + 0x800) & 0xfffff000; lo12 = (offset - hi20) & 0xfff; - *location = (*location & 0xfff) | hi20; - *(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20); - return 0; + riscv_insn_rmw(location, 0xfff, hi20); + return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20); } -static int apply_r_riscv_call_rela(struct module *me, u32 *location, +static int apply_r_riscv_call_rela(struct module *me, void *location, Elf_Addr v) { - ptrdiff_t offset = (void *)v - (void *)location; - s32 fill_v = offset; + ptrdiff_t offset = (void *)v - location; u32 hi20, lo12; - if (offset != fill_v) { + if (!riscv_insn_valid_32bit_offset(offset)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); @@ -232,18 +280,17 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location, hi20 = (offset + 0x800) & 0xfffff000; lo12 = (offset - hi20) & 0xfff; - *location = (*location & 0xfff) | hi20; - *(location + 1) = (*(location + 1) & 0xfffff) | (lo12 << 20); - return 0; + riscv_insn_rmw(location, 0xfff, hi20); + return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20); } -static int apply_r_riscv_relax_rela(struct module *me, u32 *location, +static int apply_r_riscv_relax_rela(struct module *me, void *location, Elf_Addr v) { return 0; } -static int apply_r_riscv_align_rela(struct module *me, u32 *location, +static int apply_r_riscv_align_rela(struct module *me, void *location, Elf_Addr v) { pr_err( @@ -252,59 +299,510 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location, return -EINVAL; } -static int apply_r_riscv_add32_rela(struct module *me, u32 *location, +static int apply_r_riscv_add8_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u8 *)location += (u8)v; + return 0; +} + +static int apply_r_riscv_add16_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u16 *)location += (u16)v; + return 0; +} + +static int apply_r_riscv_add32_rela(struct module *me, void *location, Elf_Addr v) { *(u32 *)location += (u32)v; return 0; } -static int apply_r_riscv_sub32_rela(struct module *me, u32 *location, +static int apply_r_riscv_add64_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u64 *)location += (u64)v; + return 0; +} + +static int apply_r_riscv_sub8_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u8 *)location -= (u8)v; + return 0; +} + +static int apply_r_riscv_sub16_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u16 *)location -= (u16)v; + return 0; +} + +static int apply_r_riscv_sub32_rela(struct module *me, void *location, Elf_Addr v) { *(u32 *)location -= (u32)v; return 0; } -static int (*reloc_handlers_rela[]) (struct module *me, u32 *location, - Elf_Addr v) = { - [R_RISCV_32] = apply_r_riscv_32_rela, - [R_RISCV_64] = apply_r_riscv_64_rela, - [R_RISCV_BRANCH] = apply_r_riscv_branch_rela, - [R_RISCV_JAL] = apply_r_riscv_jal_rela, - [R_RISCV_RVC_BRANCH] = apply_r_riscv_rcv_branch_rela, - [R_RISCV_RVC_JUMP] = apply_r_riscv_rvc_jump_rela, - [R_RISCV_PCREL_HI20] = apply_r_riscv_pcrel_hi20_rela, - [R_RISCV_PCREL_LO12_I] = apply_r_riscv_pcrel_lo12_i_rela, - [R_RISCV_PCREL_LO12_S] = apply_r_riscv_pcrel_lo12_s_rela, - [R_RISCV_HI20] = apply_r_riscv_hi20_rela, - [R_RISCV_LO12_I] = apply_r_riscv_lo12_i_rela, - [R_RISCV_LO12_S] = apply_r_riscv_lo12_s_rela, - [R_RISCV_GOT_HI20] = apply_r_riscv_got_hi20_rela, - [R_RISCV_CALL_PLT] = apply_r_riscv_call_plt_rela, - [R_RISCV_CALL] = apply_r_riscv_call_rela, - [R_RISCV_RELAX] = apply_r_riscv_relax_rela, - [R_RISCV_ALIGN] = apply_r_riscv_align_rela, - [R_RISCV_ADD32] = apply_r_riscv_add32_rela, - [R_RISCV_SUB32] = apply_r_riscv_sub32_rela, +static int apply_r_riscv_sub64_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u64 *)location -= (u64)v; + return 0; +} + +static int dynamic_linking_not_supported(struct module *me, void *location, + Elf_Addr v) +{ + pr_err("%s: Dynamic linking not supported in kernel modules PC = %p\n", + me->name, location); + return -EINVAL; +} + +static int tls_not_supported(struct module *me, void *location, Elf_Addr v) +{ + pr_err("%s: Thread local storage not supported in kernel modules PC = %p\n", + me->name, location); + return -EINVAL; +} + +static int apply_r_riscv_sub6_rela(struct module *me, void *location, Elf_Addr v) +{ + u8 *byte = location; + u8 value = v; + + *byte = (*byte - (value & 0x3f)) & 0x3f; + return 0; +} + +static int apply_r_riscv_set6_rela(struct module *me, void *location, Elf_Addr v) +{ + u8 *byte = location; + u8 value = v; + + *byte = (*byte & 0xc0) | (value & 0x3f); + return 0; +} + +static int apply_r_riscv_set8_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u8 *)location = (u8)v; + return 0; +} + +static int apply_r_riscv_set16_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u16 *)location = (u16)v; + return 0; +} + +static int apply_r_riscv_set32_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u32 *)location = (u32)v; + return 0; +} + +static int apply_r_riscv_32_pcrel_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u32 *)location = v - (uintptr_t)location; + return 0; +} + +static int apply_r_riscv_plt32_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + + if (!riscv_insn_valid_32bit_offset(offset)) { + /* Only emit the plt entry if offset over 32-bit range */ + if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { + offset = (void *)module_emit_plt_entry(me, v) - location; + } else { + pr_err("%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + } + + *(u32 *)location = (u32)offset; + return 0; +} + +static int apply_r_riscv_set_uleb128(struct module *me, void *location, Elf_Addr v) +{ + *(long *)location = v; + return 0; +} + +static int apply_r_riscv_sub_uleb128(struct module *me, void *location, Elf_Addr v) +{ + *(long *)location -= v; + return 0; +} + +static int apply_6_bit_accumulation(struct module *me, void *location, long buffer) +{ + u8 *byte = location; + u8 value = buffer; + + if (buffer > 0x3f) { + pr_err("%s: value %ld out of range for 6-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + + *byte = (*byte & 0xc0) | (value & 0x3f); + return 0; +} + +static int apply_8_bit_accumulation(struct module *me, void *location, long buffer) +{ + if (buffer > U8_MAX) { + pr_err("%s: value %ld out of range for 8-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + *(u8 *)location = (u8)buffer; + return 0; +} + +static int apply_16_bit_accumulation(struct module *me, void *location, long buffer) +{ + if (buffer > U16_MAX) { + pr_err("%s: value %ld out of range for 16-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + *(u16 *)location = (u16)buffer; + return 0; +} + +static int apply_32_bit_accumulation(struct module *me, void *location, long buffer) +{ + if (buffer > U32_MAX) { + pr_err("%s: value %ld out of range for 32-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + *(u32 *)location = (u32)buffer; + return 0; +} + +static int apply_64_bit_accumulation(struct module *me, void *location, long buffer) +{ + *(u64 *)location = (u64)buffer; + return 0; +} + +static int apply_uleb128_accumulation(struct module *me, void *location, long buffer) +{ + /* + * ULEB128 is a variable length encoding. Encode the buffer into + * the ULEB128 data format. + */ + u8 *p = location; + + while (buffer != 0) { + u8 value = buffer & 0x7f; + + buffer >>= 7; + value |= (!!buffer) << 7; + + *p++ = value; + } + return 0; +} + +/* + * Relocations defined in the riscv-elf-psabi-doc. + * This handles static linking only. + */ +static const struct relocation_handlers reloc_handlers[] = { + [R_RISCV_32] = { .reloc_handler = apply_r_riscv_32_rela }, + [R_RISCV_64] = { .reloc_handler = apply_r_riscv_64_rela }, + [R_RISCV_RELATIVE] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_COPY] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_JUMP_SLOT] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPMOD32] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPMOD64] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPREL32] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPREL64] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_TPREL32] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_TPREL64] = { .reloc_handler = dynamic_linking_not_supported }, + /* 12-15 undefined */ + [R_RISCV_BRANCH] = { .reloc_handler = apply_r_riscv_branch_rela }, + [R_RISCV_JAL] = { .reloc_handler = apply_r_riscv_jal_rela }, + [R_RISCV_CALL] = { .reloc_handler = apply_r_riscv_call_rela }, + [R_RISCV_CALL_PLT] = { .reloc_handler = apply_r_riscv_call_plt_rela }, + [R_RISCV_GOT_HI20] = { .reloc_handler = apply_r_riscv_got_hi20_rela }, + [R_RISCV_TLS_GOT_HI20] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TLS_GD_HI20] = { .reloc_handler = tls_not_supported }, + [R_RISCV_PCREL_HI20] = { .reloc_handler = apply_r_riscv_pcrel_hi20_rela }, + [R_RISCV_PCREL_LO12_I] = { .reloc_handler = apply_r_riscv_pcrel_lo12_i_rela }, + [R_RISCV_PCREL_LO12_S] = { .reloc_handler = apply_r_riscv_pcrel_lo12_s_rela }, + [R_RISCV_HI20] = { .reloc_handler = apply_r_riscv_hi20_rela }, + [R_RISCV_LO12_I] = { .reloc_handler = apply_r_riscv_lo12_i_rela }, + [R_RISCV_LO12_S] = { .reloc_handler = apply_r_riscv_lo12_s_rela }, + [R_RISCV_TPREL_HI20] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TPREL_LO12_I] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TPREL_LO12_S] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TPREL_ADD] = { .reloc_handler = tls_not_supported }, + [R_RISCV_ADD8] = { .reloc_handler = apply_r_riscv_add8_rela, + .accumulate_handler = apply_8_bit_accumulation }, + [R_RISCV_ADD16] = { .reloc_handler = apply_r_riscv_add16_rela, + .accumulate_handler = apply_16_bit_accumulation }, + [R_RISCV_ADD32] = { .reloc_handler = apply_r_riscv_add32_rela, + .accumulate_handler = apply_32_bit_accumulation }, + [R_RISCV_ADD64] = { .reloc_handler = apply_r_riscv_add64_rela, + .accumulate_handler = apply_64_bit_accumulation }, + [R_RISCV_SUB8] = { .reloc_handler = apply_r_riscv_sub8_rela, + .accumulate_handler = apply_8_bit_accumulation }, + [R_RISCV_SUB16] = { .reloc_handler = apply_r_riscv_sub16_rela, + .accumulate_handler = apply_16_bit_accumulation }, + [R_RISCV_SUB32] = { .reloc_handler = apply_r_riscv_sub32_rela, + .accumulate_handler = apply_32_bit_accumulation }, + [R_RISCV_SUB64] = { .reloc_handler = apply_r_riscv_sub64_rela, + .accumulate_handler = apply_64_bit_accumulation }, + /* 41-42 reserved for future standard use */ + [R_RISCV_ALIGN] = { .reloc_handler = apply_r_riscv_align_rela }, + [R_RISCV_RVC_BRANCH] = { .reloc_handler = apply_r_riscv_rvc_branch_rela }, + [R_RISCV_RVC_JUMP] = { .reloc_handler = apply_r_riscv_rvc_jump_rela }, + /* 46-50 reserved for future standard use */ + [R_RISCV_RELAX] = { .reloc_handler = apply_r_riscv_relax_rela }, + [R_RISCV_SUB6] = { .reloc_handler = apply_r_riscv_sub6_rela, + .accumulate_handler = apply_6_bit_accumulation }, + [R_RISCV_SET6] = { .reloc_handler = apply_r_riscv_set6_rela, + .accumulate_handler = apply_6_bit_accumulation }, + [R_RISCV_SET8] = { .reloc_handler = apply_r_riscv_set8_rela, + .accumulate_handler = apply_8_bit_accumulation }, + [R_RISCV_SET16] = { .reloc_handler = apply_r_riscv_set16_rela, + .accumulate_handler = apply_16_bit_accumulation }, + [R_RISCV_SET32] = { .reloc_handler = apply_r_riscv_set32_rela, + .accumulate_handler = apply_32_bit_accumulation }, + [R_RISCV_32_PCREL] = { .reloc_handler = apply_r_riscv_32_pcrel_rela }, + [R_RISCV_IRELATIVE] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_PLT32] = { .reloc_handler = apply_r_riscv_plt32_rela }, + [R_RISCV_SET_ULEB128] = { .reloc_handler = apply_r_riscv_set_uleb128, + .accumulate_handler = apply_uleb128_accumulation }, + [R_RISCV_SUB_ULEB128] = { .reloc_handler = apply_r_riscv_sub_uleb128, + .accumulate_handler = apply_uleb128_accumulation }, + /* 62-191 reserved for future standard use */ + /* 192-255 nonstandard ABI extensions */ }; +static void +process_accumulated_relocations(struct module *me, + struct hlist_head **relocation_hashtable, + struct list_head *used_buckets_list) +{ + /* + * Only ADD/SUB/SET/ULEB128 should end up here. + * + * Each bucket may have more than one relocation location. All + * relocations for a location are stored in a list in a bucket. + * + * Relocations are applied to a temp variable before being stored to the + * provided location to check for overflow. This also allows ULEB128 to + * properly decide how many entries are needed before storing to + * location. The final value is stored into location using the handler + * for the last relocation to an address. + * + * Three layers of indexing: + * - Each of the buckets in use + * - Groups of relocations in each bucket by location address + * - Each relocation entry for a location address + */ + struct used_bucket *bucket_iter; + struct used_bucket *bucket_iter_tmp; + struct relocation_head *rel_head_iter; + struct hlist_node *rel_head_iter_tmp; + struct relocation_entry *rel_entry_iter; + struct relocation_entry *rel_entry_iter_tmp; + int curr_type; + void *location; + long buffer; + + list_for_each_entry_safe(bucket_iter, bucket_iter_tmp, + used_buckets_list, head) { + hlist_for_each_entry_safe(rel_head_iter, rel_head_iter_tmp, + bucket_iter->bucket, node) { + buffer = 0; + location = rel_head_iter->location; + list_for_each_entry_safe(rel_entry_iter, + rel_entry_iter_tmp, + rel_head_iter->rel_entry, + head) { + curr_type = rel_entry_iter->type; + reloc_handlers[curr_type].reloc_handler( + me, &buffer, rel_entry_iter->value); + kfree(rel_entry_iter); + } + reloc_handlers[curr_type].accumulate_handler( + me, location, buffer); + kfree(rel_head_iter); + } + kfree(bucket_iter); + } + + kfree(*relocation_hashtable); +} + +static int add_relocation_to_accumulate(struct module *me, int type, + void *location, + unsigned int hashtable_bits, Elf_Addr v, + struct hlist_head *relocation_hashtable, + struct list_head *used_buckets_list) +{ + struct relocation_entry *entry; + struct relocation_head *rel_head; + struct hlist_head *current_head; + struct used_bucket *bucket; + unsigned long hash; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + + if (!entry) + return -ENOMEM; + + INIT_LIST_HEAD(&entry->head); + entry->type = type; + entry->value = v; + + hash = hash_min((uintptr_t)location, hashtable_bits); + + current_head = &relocation_hashtable[hash]; + + /* + * Search for the relocation_head for the relocations that happen at the + * provided location + */ + bool found = false; + struct relocation_head *rel_head_iter; + + hlist_for_each_entry(rel_head_iter, current_head, node) { + if (rel_head_iter->location == location) { + found = true; + rel_head = rel_head_iter; + break; + } + } + + /* + * If there has not yet been any relocations at the provided location, + * create a relocation_head for that location and populate it with this + * relocation_entry. + */ + if (!found) { + rel_head = kmalloc(sizeof(*rel_head), GFP_KERNEL); + + if (!rel_head) { + kfree(entry); + 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); + rel_head->location = location; + INIT_HLIST_NODE(&rel_head->node); + if (!current_head->first) { + bucket = + kmalloc(sizeof(struct used_bucket), GFP_KERNEL); + + if (!bucket) { + kfree(entry); + kfree(rel_head->rel_entry); + kfree(rel_head); + return -ENOMEM; + } + + INIT_LIST_HEAD(&bucket->head); + bucket->bucket = current_head; + list_add(&bucket->head, used_buckets_list); + } + hlist_add_head(&rel_head->node, current_head); + } + + /* Add relocation to head of discovered rel_head */ + list_add_tail(&entry->head, rel_head->rel_entry); + + return 0; +} + +static unsigned int +initialize_relocation_hashtable(unsigned int num_relocations, + struct hlist_head **relocation_hashtable) +{ + /* Can safely assume that bits is not greater than sizeof(long) */ + unsigned long hashtable_size = roundup_pow_of_two(num_relocations); + /* + * When hashtable_size == 1, hashtable_bits == 0. + * This is valid because the hashing algorithm returns 0 in this case. + */ + unsigned int hashtable_bits = ilog2(hashtable_size); + + /* + * Double size of hashtable if num_relocations * 1.25 is greater than + * hashtable_size. + */ + int should_double_size = ((num_relocations + (num_relocations >> 2)) > (hashtable_size)); + + hashtable_bits += should_double_size; + + hashtable_size <<= should_double_size; + + *relocation_hashtable = kmalloc_array(hashtable_size, + sizeof(**relocation_hashtable), + GFP_KERNEL); + if (!*relocation_hashtable) + return 0; + + __hash_init(*relocation_hashtable, hashtable_size); + + return hashtable_bits; +} + int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, unsigned int symindex, unsigned int relsec, struct module *me) { Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr; - int (*handler)(struct module *me, u32 *location, Elf_Addr v); + int (*handler)(struct module *me, void *location, Elf_Addr v); Elf_Sym *sym; - u32 *location; + void *location; unsigned int i, type; + unsigned int j_idx = 0; Elf_Addr v; int res; + unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel); + struct hlist_head *relocation_hashtable; + struct list_head used_buckets_list; + unsigned int hashtable_bits; + + hashtable_bits = initialize_relocation_hashtable(num_relocations, + &relocation_hashtable); + + if (!relocation_hashtable) + return -ENOMEM; + + INIT_LIST_HEAD(&used_buckets_list); pr_debug("Applying relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + for (i = 0; i < num_relocations; i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr + rel[i].r_offset; @@ -322,8 +820,8 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, type = ELF_RISCV_R_TYPE(rel[i].r_info); - if (type < ARRAY_SIZE(reloc_handlers_rela)) - handler = reloc_handlers_rela[type]; + if (type < ARRAY_SIZE(reloc_handlers)) + handler = reloc_handlers[type].reloc_handler; else handler = NULL; @@ -336,9 +834,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, v = sym->st_value + rel[i].r_addend; if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) { - unsigned int j; + unsigned int j = j_idx; + bool found = false; - for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) { + do { unsigned long hi20_loc = sechdrs[sechdrs[relsec].sh_info].sh_addr + rel[j].r_offset; @@ -367,22 +866,65 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, hi20 = (offset + 0x800) & 0xfffff000; lo12 = offset - hi20; v = lo12; + found = true; break; } - } - if (j == sechdrs[relsec].sh_size / sizeof(*rel)) { + + j++; + if (j > sechdrs[relsec].sh_size / sizeof(*rel)) + j = 0; + + } while (j_idx != j); + + if (!found) { pr_err( "%s: Can not find HI20 relocation information\n", me->name); return -EINVAL; } + + /* Record the previous j-loop end index */ + j_idx = j; } - res = handler(me, location, v); + if (reloc_handlers[type].accumulate_handler) + res = add_relocation_to_accumulate(me, type, location, + hashtable_bits, v, + relocation_hashtable, + &used_buckets_list); + else + res = handler(me, location, v); if (res) return res; } + process_accumulated_relocations(me, &relocation_hashtable, + &used_buckets_list); + + return 0; +} + +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) +void *module_alloc(unsigned long size) +{ + return __vmalloc_node_range(size, 1, MODULES_VADDR, + MODULES_END, GFP_KERNEL, + PAGE_KERNEL, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, + __builtin_return_address(0)); +} +#endif + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + + s = find_section(hdr, sechdrs, ".alternative"); + if (s) + apply_module_alternatives((void *)s->sh_addr, s->sh_size); + return 0; } diff --git a/arch/riscv/kernel/module.lds b/arch/riscv/kernel/module.lds deleted file mode 100644 index 295ecfb341a2..000000000000 --- a/arch/riscv/kernel/module.lds +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2017 Andes Technology Corporation */ - -SECTIONS { - .plt (NOLOAD) : { BYTE(0) } - .got (NOLOAD) : { BYTE(0) } - .got.plt (NOLOAD) : { BYTE(0) } -} diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c new file mode 100644 index 000000000000..8e114f5930ce --- /dev/null +++ b/arch/riscv/kernel/paravirt.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "riscv-pv: " fmt + +#include <linux/cpuhotplug.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/jump_label.h> +#include <linux/kconfig.h> +#include <linux/kernel.h> +#include <linux/percpu-defs.h> +#include <linux/printk.h> +#include <linux/static_call.h> +#include <linux/types.h> + +#include <asm/barrier.h> +#include <asm/page.h> +#include <asm/paravirt.h> +#include <asm/sbi.h> + +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; + +static u64 native_steal_clock(int cpu) +{ + return 0; +} + +DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); + +static bool steal_acc = true; +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); + +DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64); + +static bool __init has_pv_steal_clock(void) +{ + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_STA) > 0) { + pr_info("SBI STA extension detected\n"); + return true; + } + + return false; +} + +static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi, + unsigned long flags) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM, + lo, hi, flags, 0, 0, 0); + if (ret.error) { + if (lo == SBI_STA_SHMEM_DISABLE && hi == SBI_STA_SHMEM_DISABLE) + pr_warn("Failed to disable steal-time shmem"); + else + pr_warn("Failed to set steal-time shmem"); + return sbi_err_map_linux_errno(ret.error); + } + + return 0; +} + +static int pv_time_cpu_online(unsigned int cpu) +{ + struct sbi_sta_struct *st = this_cpu_ptr(&steal_time); + phys_addr_t pa = __pa(st); + unsigned long lo = (unsigned long)pa; + unsigned long hi = IS_ENABLED(CONFIG_32BIT) ? upper_32_bits((u64)pa) : 0; + + return sbi_sta_steal_time_set_shmem(lo, hi, 0); +} + +static int pv_time_cpu_down_prepare(unsigned int cpu) +{ + return sbi_sta_steal_time_set_shmem(SBI_STA_SHMEM_DISABLE, + SBI_STA_SHMEM_DISABLE, 0); +} + +static u64 pv_time_steal_clock(int cpu) +{ + struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu); + u32 sequence; + u64 steal; + + /* + * Check the sequence field before and after reading the steal + * field. Repeat the read if it is different or odd. + */ + do { + sequence = READ_ONCE(st->sequence); + virt_rmb(); + steal = READ_ONCE(st->steal); + virt_rmb(); + } while ((le32_to_cpu(sequence) & 1) || + sequence != READ_ONCE(st->sequence)); + + return le64_to_cpu(steal); +} + +int __init pv_time_init(void) +{ + int ret; + + if (!has_pv_steal_clock()) + return 0; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "riscv/pv_time:online", + pv_time_cpu_online, + pv_time_cpu_down_prepare); + if (ret < 0) + return ret; + + static_call_update(pv_steal_clock, pv_time_steal_clock); + + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + + pr_info("Computing paravirt steal-time\n"); + + return 0; +} diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c new file mode 100644 index 000000000000..37e87fdcf6a0 --- /dev/null +++ b/arch/riscv/kernel/patch.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 SiFive + */ + +#include <linux/spinlock.h> +#include <linux/mm.h> +#include <linux/memory.h> +#include <linux/string.h> +#include <linux/uaccess.h> +#include <linux/stop_machine.h> +#include <asm/kprobes.h> +#include <asm/cacheflush.h> +#include <asm/fixmap.h> +#include <asm/ftrace.h> +#include <asm/patch.h> +#include <asm/sections.h> + +struct patch_insn { + void *addr; + u32 *insns; + int ninsns; + atomic_t cpu_count; +}; + +int riscv_patch_in_stop_machine = false; + +#ifdef CONFIG_MMU + +static inline bool is_kernel_exittext(uintptr_t addr) +{ + return system_state < SYSTEM_RUNNING && + addr >= (uintptr_t)__exittext_begin && + addr < (uintptr_t)__exittext_end; +} + +/* + * The fix_to_virt(, idx) needs a const value (not a dynamic variable of + * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses". + * So use '__always_inline' and 'const unsigned int fixmap' here. + */ +static __always_inline void *patch_map(void *addr, const unsigned int fixmap) +{ + uintptr_t uintaddr = (uintptr_t) addr; + struct page *page; + + if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) + page = phys_to_page(__pa_symbol(addr)); + else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + page = vmalloc_to_page(addr); + else + return addr; + + BUG_ON(!page); + + return (void *)set_fixmap_offset(fixmap, page_to_phys(page) + + (uintaddr & ~PAGE_MASK)); +} + +static void patch_unmap(int fixmap) +{ + clear_fixmap(fixmap); +} +NOKPROBE_SYMBOL(patch_unmap); + +static int __patch_insn_set(void *addr, u8 c, size_t len) +{ + void *waddr = addr; + bool across_pages = (((uintptr_t)addr & ~PAGE_MASK) + len) > PAGE_SIZE; + + /* + * Only two pages can be mapped at a time for writing. + */ + if (len + offset_in_page(addr) > 2 * PAGE_SIZE) + return -EINVAL; + /* + * Before reaching here, it was expected to lock the text_mutex + * already, so we don't need to give another lock here and could + * ensure that it was safe between each cores. + */ + lockdep_assert_held(&text_mutex); + + if (across_pages) + patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); + + waddr = patch_map(addr, FIX_TEXT_POKE0); + + memset(waddr, c, len); + + patch_unmap(FIX_TEXT_POKE0); + + if (across_pages) + patch_unmap(FIX_TEXT_POKE1); + + return 0; +} +NOKPROBE_SYMBOL(__patch_insn_set); + +static int __patch_insn_write(void *addr, const void *insn, size_t len) +{ + void *waddr = addr; + bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE; + int ret; + + /* + * Only two pages can be mapped at a time for writing. + */ + if (len + offset_in_page(addr) > 2 * PAGE_SIZE) + return -EINVAL; + + /* + * Before reaching here, it was expected to lock the text_mutex + * already, so we don't need to give another lock here and could + * ensure that it was safe between each cores. + * + * We're currently using stop_machine() for ftrace & kprobes, and while + * that ensures text_mutex is held before installing the mappings it + * does not ensure text_mutex is held by the calling thread. That's + * safe but triggers a lockdep failure, so just elide it for that + * specific case. + */ + if (!riscv_patch_in_stop_machine) + lockdep_assert_held(&text_mutex); + + if (across_pages) + patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); + + waddr = patch_map(addr, FIX_TEXT_POKE0); + + ret = copy_to_kernel_nofault(waddr, insn, len); + + patch_unmap(FIX_TEXT_POKE0); + + if (across_pages) + patch_unmap(FIX_TEXT_POKE1); + + return ret; +} +NOKPROBE_SYMBOL(__patch_insn_write); +#else +static int __patch_insn_set(void *addr, u8 c, size_t len) +{ + memset(addr, c, len); + + return 0; +} +NOKPROBE_SYMBOL(__patch_insn_set); + +static int __patch_insn_write(void *addr, const void *insn, size_t len) +{ + return copy_to_kernel_nofault(addr, insn, len); +} +NOKPROBE_SYMBOL(__patch_insn_write); +#endif /* CONFIG_MMU */ + +static int patch_insn_set(void *addr, u8 c, size_t len) +{ + size_t patched = 0; + size_t size; + int ret = 0; + + /* + * __patch_insn_set() can only work on 2 pages at a time so call it in a + * loop with len <= 2 * PAGE_SIZE. + */ + while (patched < len && !ret) { + size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched); + ret = __patch_insn_set(addr + patched, c, size); + + patched += size; + } + + return ret; +} +NOKPROBE_SYMBOL(patch_insn_set); + +int patch_text_set_nosync(void *addr, u8 c, size_t len) +{ + u32 *tp = addr; + int ret; + + ret = patch_insn_set(tp, c, len); + + if (!ret) + flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len); + + return ret; +} +NOKPROBE_SYMBOL(patch_text_set_nosync); + +static int patch_insn_write(void *addr, const void *insn, size_t len) +{ + size_t patched = 0; + size_t size; + int ret = 0; + + /* + * Copy the instructions to the destination address, two pages at a time + * because __patch_insn_write() can only handle len <= 2 * PAGE_SIZE. + */ + while (patched < len && !ret) { + size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched); + ret = __patch_insn_write(addr + patched, insn + patched, size); + + patched += size; + } + + return ret; +} +NOKPROBE_SYMBOL(patch_insn_write); + +int patch_text_nosync(void *addr, const void *insns, size_t len) +{ + u32 *tp = addr; + int ret; + + ret = patch_insn_write(tp, insns, len); + + if (!ret) + flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len); + + return ret; +} +NOKPROBE_SYMBOL(patch_text_nosync); + +static int patch_text_cb(void *data) +{ + struct patch_insn *patch = data; + unsigned long len; + int i, ret = 0; + + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { + for (i = 0; ret == 0 && i < patch->ninsns; i++) { + len = GET_INSN_LENGTH(patch->insns[i]); + ret = patch_text_nosync(patch->addr + i * len, + &patch->insns[i], len); + } + atomic_inc(&patch->cpu_count); + } else { + while (atomic_read(&patch->cpu_count) <= num_online_cpus()) + cpu_relax(); + smp_mb(); + } + + return ret; +} +NOKPROBE_SYMBOL(patch_text_cb); + +int patch_text(void *addr, u32 *insns, int ninsns) +{ + int ret; + struct patch_insn patch = { + .addr = addr, + .insns = insns, + .ninsns = ninsns, + .cpu_count = ATOMIC_INIT(0), + }; + + /* + * kprobes takes text_mutex, before calling patch_text(), but as we call + * calls stop_machine(), the lockdep assertion in patch_insn_write() + * gets confused by the context in which the lock is taken. + * Instead, ensure the lock is held before calling stop_machine(), and + * set riscv_patch_in_stop_machine to skip the check in + * patch_insn_write(). + */ + lockdep_assert_held(&text_mutex); + riscv_patch_in_stop_machine = true; + ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask); + riscv_patch_in_stop_machine = false; + return ret; +} +NOKPROBE_SYMBOL(patch_text); diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index cf190197a22f..3348a61de7d9 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -4,11 +4,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> -/* Kernel callchain */ -struct stackframe { - unsigned long fp; - unsigned long ra; -}; +#include <asm/stacktrace.h> /* * Get the return address for a single stackframe and return a pointer to the @@ -19,8 +15,8 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, { struct stackframe buftail; unsigned long ra = 0; - unsigned long *user_frame_tail = - (unsigned long *)(fp - sizeof(struct stackframe)); + unsigned long __user *user_frame_tail = + (unsigned long __user *)(fp - sizeof(struct stackframe)); /* Check accessibility of one struct frame_tail beyond */ if (!access_ok(user_frame_tail, sizeof(buftail))) @@ -62,10 +58,6 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, { unsigned long fp = 0; - /* RISC-V does not support perf in guest mode. */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - return; - fp = regs->s0; perf_callchain_store(entry, regs->epc); @@ -74,21 +66,13 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, fp = user_backtrace(entry, fp, 0); } -bool fill_callchain(unsigned long pc, void *entry) +static bool fill_callchain(void *entry, unsigned long pc) { - return perf_callchain_store(entry, pc); + return perf_callchain_store(entry, pc) == 0; } -void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg); void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - /* RISC-V does not support perf in guest mode. */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - pr_warn("RISC-V does not support perf in guest mode!"); - return; - } - walk_stackframe(NULL, regs, fill_callchain, entry); } diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c deleted file mode 100644 index 91626d9ae5f2..000000000000 --- a/arch/riscv/kernel/perf_event.c +++ /dev/null @@ -1,485 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> - * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2009 Jaswinder Singh Rajput - * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra - * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> - * Copyright (C) 2009 Google, Inc., Stephane Eranian - * Copyright 2014 Tilera Corporation. All Rights Reserved. - * Copyright (C) 2018 Andes Technology Corporation - * - * Perf_events support for RISC-V platforms. - * - * Since the spec. (as of now, Priv-Spec 1.10) does not provide enough - * functionality for perf event to fully work, this file provides - * the very basic framework only. - * - * For platform portings, please check Documentations/riscv/pmu.txt. - * - * The Copyright line includes x86 and tile ones. - */ - -#include <linux/kprobes.h> -#include <linux/kernel.h> -#include <linux/kdebug.h> -#include <linux/mutex.h> -#include <linux/bitmap.h> -#include <linux/irq.h> -#include <linux/perf_event.h> -#include <linux/atomic.h> -#include <linux/of.h> -#include <asm/perf_event.h> - -static const struct riscv_pmu *riscv_pmu __read_mostly; -static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); - -/* - * Hardware & cache maps and their methods - */ - -static const int riscv_hw_event_map[] = { - [PERF_COUNT_HW_CPU_CYCLES] = RISCV_PMU_CYCLE, - [PERF_COUNT_HW_INSTRUCTIONS] = RISCV_PMU_INSTRET, - [PERF_COUNT_HW_CACHE_REFERENCES] = RISCV_OP_UNSUPP, - [PERF_COUNT_HW_CACHE_MISSES] = RISCV_OP_UNSUPP, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = RISCV_OP_UNSUPP, - [PERF_COUNT_HW_BRANCH_MISSES] = RISCV_OP_UNSUPP, - [PERF_COUNT_HW_BUS_CYCLES] = RISCV_OP_UNSUPP, -}; - -#define C(x) PERF_COUNT_HW_CACHE_##x -static const int riscv_cache_event_map[PERF_COUNT_HW_CACHE_MAX] -[PERF_COUNT_HW_CACHE_OP_MAX] -[PERF_COUNT_HW_CACHE_RESULT_MAX] = { - [C(L1D)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = RISCV_OP_UNSUPP, - [C(RESULT_MISS)] = RISCV_OP_UNSUPP, - }, - }, -}; - -static int riscv_map_hw_event(u64 config) -{ - if (config >= riscv_pmu->max_events) - return -EINVAL; - - return riscv_pmu->hw_events[config]; -} - -int riscv_map_cache_decode(u64 config, unsigned int *type, - unsigned int *op, unsigned int *result) -{ - return -ENOENT; -} - -static int riscv_map_cache_event(u64 config) -{ - unsigned int type, op, result; - int err = -ENOENT; - int code; - - err = riscv_map_cache_decode(config, &type, &op, &result); - if (!riscv_pmu->cache_events || err) - return err; - - if (type >= PERF_COUNT_HW_CACHE_MAX || - op >= PERF_COUNT_HW_CACHE_OP_MAX || - result >= PERF_COUNT_HW_CACHE_RESULT_MAX) - return -EINVAL; - - code = (*riscv_pmu->cache_events)[type][op][result]; - if (code == RISCV_OP_UNSUPP) - return -EINVAL; - - return code; -} - -/* - * Low-level functions: reading/writing counters - */ - -static inline u64 read_counter(int idx) -{ - u64 val = 0; - - switch (idx) { - case RISCV_PMU_CYCLE: - val = csr_read(CSR_CYCLE); - break; - case RISCV_PMU_INSTRET: - val = csr_read(CSR_INSTRET); - break; - default: - WARN_ON_ONCE(idx < 0 || idx > RISCV_MAX_COUNTERS); - return -EINVAL; - } - - return val; -} - -static inline void write_counter(int idx, u64 value) -{ - /* currently not supported */ - WARN_ON_ONCE(1); -} - -/* - * pmu->read: read and update the counter - * - * Other architectures' implementation often have a xxx_perf_event_update - * routine, which can return counter values when called in the IRQ, but - * return void when being called by the pmu->read method. - */ -static void riscv_pmu_read(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - u64 prev_raw_count, new_raw_count; - u64 oldval; - int idx = hwc->idx; - u64 delta; - - do { - prev_raw_count = local64_read(&hwc->prev_count); - new_raw_count = read_counter(idx); - - oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count); - } while (oldval != prev_raw_count); - - /* - * delta is the value to update the counter we maintain in the kernel. - */ - delta = (new_raw_count - prev_raw_count) & - ((1ULL << riscv_pmu->counter_width) - 1); - local64_add(delta, &event->count); - /* - * Something like local64_sub(delta, &hwc->period_left) here is - * needed if there is an interrupt for perf. - */ -} - -/* - * State transition functions: - * - * stop()/start() & add()/del() - */ - -/* - * pmu->stop: stop the counter - */ -static void riscv_pmu_stop(struct perf_event *event, int flags) -{ - struct hw_perf_event *hwc = &event->hw; - - WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); - hwc->state |= PERF_HES_STOPPED; - - if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { - riscv_pmu->pmu->read(event); - hwc->state |= PERF_HES_UPTODATE; - } -} - -/* - * pmu->start: start the event. - */ -static void riscv_pmu_start(struct perf_event *event, int flags) -{ - struct hw_perf_event *hwc = &event->hw; - - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) - return; - - if (flags & PERF_EF_RELOAD) { - WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); - - /* - * Set the counter to the period to the next interrupt here, - * if you have any. - */ - } - - hwc->state = 0; - perf_event_update_userpage(event); - - /* - * Since we cannot write to counters, this serves as an initialization - * to the delta-mechanism in pmu->read(); otherwise, the delta would be - * wrong when pmu->read is called for the first time. - */ - local64_set(&hwc->prev_count, read_counter(hwc->idx)); -} - -/* - * pmu->add: add the event to PMU. - */ -static int riscv_pmu_add(struct perf_event *event, int flags) -{ - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; - - if (cpuc->n_events == riscv_pmu->num_counters) - return -ENOSPC; - - /* - * We don't have general conunters, so no binding-event-to-counter - * process here. - * - * Indexing using hwc->config generally not works, since config may - * contain extra information, but here the only info we have in - * hwc->config is the event index. - */ - hwc->idx = hwc->config; - cpuc->events[hwc->idx] = event; - cpuc->n_events++; - - hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; - - if (flags & PERF_EF_START) - riscv_pmu->pmu->start(event, PERF_EF_RELOAD); - - return 0; -} - -/* - * pmu->del: delete the event from PMU. - */ -static void riscv_pmu_del(struct perf_event *event, int flags) -{ - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; - - cpuc->events[hwc->idx] = NULL; - cpuc->n_events--; - riscv_pmu->pmu->stop(event, PERF_EF_UPDATE); - perf_event_update_userpage(event); -} - -/* - * Interrupt: a skeletion for reference. - */ - -static DEFINE_MUTEX(pmc_reserve_mutex); - -irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) -{ - return IRQ_NONE; -} - -static int reserve_pmc_hardware(void) -{ - int err = 0; - - mutex_lock(&pmc_reserve_mutex); - if (riscv_pmu->irq >= 0 && riscv_pmu->handle_irq) { - err = request_irq(riscv_pmu->irq, riscv_pmu->handle_irq, - IRQF_PERCPU, "riscv-base-perf", NULL); - } - mutex_unlock(&pmc_reserve_mutex); - - return err; -} - -void release_pmc_hardware(void) -{ - mutex_lock(&pmc_reserve_mutex); - if (riscv_pmu->irq >= 0) - free_irq(riscv_pmu->irq, NULL); - mutex_unlock(&pmc_reserve_mutex); -} - -/* - * Event Initialization/Finalization - */ - -static atomic_t riscv_active_events = ATOMIC_INIT(0); - -static void riscv_event_destroy(struct perf_event *event) -{ - if (atomic_dec_return(&riscv_active_events) == 0) - release_pmc_hardware(); -} - -static int riscv_event_init(struct perf_event *event) -{ - struct perf_event_attr *attr = &event->attr; - struct hw_perf_event *hwc = &event->hw; - int err; - int code; - - if (atomic_inc_return(&riscv_active_events) == 1) { - err = reserve_pmc_hardware(); - - if (err) { - pr_warn("PMC hardware not available\n"); - atomic_dec(&riscv_active_events); - return -EBUSY; - } - } - - switch (event->attr.type) { - case PERF_TYPE_HARDWARE: - code = riscv_pmu->map_hw_event(attr->config); - break; - case PERF_TYPE_HW_CACHE: - code = riscv_pmu->map_cache_event(attr->config); - break; - case PERF_TYPE_RAW: - return -EOPNOTSUPP; - default: - return -ENOENT; - } - - event->destroy = riscv_event_destroy; - if (code < 0) { - event->destroy(event); - return code; - } - - /* - * idx is set to -1 because the index of a general event should not be - * decided until binding to some counter in pmu->add(). - * - * But since we don't have such support, later in pmu->add(), we just - * use hwc->config as the index instead. - */ - hwc->config = code; - hwc->idx = -1; - - return 0; -} - -/* - * Initialization - */ - -static struct pmu min_pmu = { - .name = "riscv-base", - .event_init = riscv_event_init, - .add = riscv_pmu_add, - .del = riscv_pmu_del, - .start = riscv_pmu_start, - .stop = riscv_pmu_stop, - .read = riscv_pmu_read, -}; - -static const struct riscv_pmu riscv_base_pmu = { - .pmu = &min_pmu, - .max_events = ARRAY_SIZE(riscv_hw_event_map), - .map_hw_event = riscv_map_hw_event, - .hw_events = riscv_hw_event_map, - .map_cache_event = riscv_map_cache_event, - .cache_events = &riscv_cache_event_map, - .counter_width = 63, - .num_counters = RISCV_BASE_COUNTERS + 0, - .handle_irq = &riscv_base_pmu_handle_irq, - - /* This means this PMU has no IRQ. */ - .irq = -1, -}; - -static const struct of_device_id riscv_pmu_of_ids[] = { - {.compatible = "riscv,base-pmu", .data = &riscv_base_pmu}, - { /* sentinel value */ } -}; - -int __init init_hw_perf_events(void) -{ - struct device_node *node = of_find_node_by_type(NULL, "pmu"); - const struct of_device_id *of_id; - - riscv_pmu = &riscv_base_pmu; - - if (node) { - of_id = of_match_node(riscv_pmu_of_ids, node); - - if (of_id) - riscv_pmu = of_id->data; - of_node_put(node); - } - - perf_pmu_register(riscv_pmu->pmu, "cpu", PERF_TYPE_RAW); - return 0; -} -arch_initcall(init_hw_perf_events); diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c index 04a38fbeb9c7..fd304a248de6 100644 --- a/arch/riscv/kernel/perf_regs.c +++ b/arch/riscv/kernel/perf_regs.c @@ -36,8 +36,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile new file mode 100644 index 000000000000..07915dc9279e --- /dev/null +++ b/arch/riscv/kernel/pi/Makefile @@ -0,0 +1,39 @@ +# SPDX-License-Identifier: GPL-2.0 +# This file was copied from arm64/kernel/pi/Makefile. + +KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ + -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \ + $(call cc-option,-mbranch-protection=none) \ + -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ + -D__DISABLE_EXPORTS -ffreestanding \ + -fno-asynchronous-unwind-tables -fno-unwind-tables \ + $(call cc-option,-fno-addrsig) + +KBUILD_CFLAGS += -mcmodel=medany + +CFLAGS_cmdline_early.o += -D__NO_FORTIFY +CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY + +GCOV_PROFILE := n +KASAN_SANITIZE := n +KCSAN_SANITIZE := n +UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +$(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ + --remove-section=.note.gnu.property \ + --prefix-alloc-sections=.init.pi +$(obj)/%.pi.o: $(obj)/%.o FORCE + $(call if_changed,objcopy) + +$(obj)/lib-%.o: $(srctree)/lib/%.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/string.o: $(srctree)/lib/string.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE + $(call if_changed_rule,cc_o_c) + +obj-y := cmdline_early.pi.o fdt_early.pi.o string.pi.o ctype.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o +extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c new file mode 100644 index 000000000000..f6d4dedffb84 --- /dev/null +++ b/arch/riscv/kernel/pi/cmdline_early.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/types.h> +#include <linux/init.h> +#include <linux/libfdt.h> +#include <linux/string.h> +#include <asm/pgtable.h> +#include <asm/setup.h> + +static char early_cmdline[COMMAND_LINE_SIZE]; + +/* + * Declare the functions that are exported (but prefixed) here so that LLVM + * does not complain it lacks the 'static' keyword (which, if added, makes + * LLVM complain because the function is actually unused in this file). + */ +u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa); +bool set_nokaslr_from_cmdline(uintptr_t dtb_pa); + +static char *get_early_cmdline(uintptr_t dtb_pa) +{ + const char *fdt_cmdline = NULL; + unsigned int fdt_cmdline_size = 0; + int chosen_node; + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { + chosen_node = fdt_path_offset((void *)dtb_pa, "/chosen"); + if (chosen_node >= 0) { + fdt_cmdline = fdt_getprop((void *)dtb_pa, chosen_node, + "bootargs", NULL); + if (fdt_cmdline) { + fdt_cmdline_size = strlen(fdt_cmdline); + strscpy(early_cmdline, fdt_cmdline, + COMMAND_LINE_SIZE); + } + } + } + + if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || + IS_ENABLED(CONFIG_CMDLINE_FORCE) || + fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) { + strlcat(early_cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + } + + return early_cmdline; +} + +static u64 match_noXlvl(char *cmdline) +{ + if (strstr(cmdline, "no4lvl")) + return SATP_MODE_48; + else if (strstr(cmdline, "no5lvl")) + return SATP_MODE_57; + + return 0; +} + +u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa) +{ + char *cmdline = get_early_cmdline(dtb_pa); + + return match_noXlvl(cmdline); +} + +static bool match_nokaslr(char *cmdline) +{ + return strstr(cmdline, "nokaslr"); +} + +bool set_nokaslr_from_cmdline(uintptr_t dtb_pa) +{ + char *cmdline = get_early_cmdline(dtb_pa); + + return match_nokaslr(cmdline); +} diff --git a/arch/riscv/kernel/pi/fdt_early.c b/arch/riscv/kernel/pi/fdt_early.c new file mode 100644 index 000000000000..899610e042ab --- /dev/null +++ b/arch/riscv/kernel/pi/fdt_early.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/types.h> +#include <linux/init.h> +#include <linux/libfdt.h> + +/* + * Declare the functions that are exported (but prefixed) here so that LLVM + * does not complain it lacks the 'static' keyword (which, if added, makes + * LLVM complain because the function is actually unused in this file). + */ +u64 get_kaslr_seed(uintptr_t dtb_pa); + +u64 get_kaslr_seed(uintptr_t dtb_pa) +{ + int node, len; + fdt64_t *prop; + u64 ret; + + node = fdt_path_offset((void *)dtb_pa, "/chosen"); + if (node < 0) + return 0; + + prop = fdt_getprop_w((void *)dtb_pa, node, "kaslr-seed", &len); + if (!prop || len != sizeof(u64)) + return 0; + + ret = fdt64_to_cpu(*prop); + *prop = 0; + return ret; +} diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile new file mode 100644 index 000000000000..8265ff497977 --- /dev/null +++ b/arch/riscv/kernel/probes/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_KPROBES) += kprobes.o decode-insn.o simulate-insn.o +obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o +obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o +obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o +CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c new file mode 100644 index 000000000000..65d9590bfb9f --- /dev/null +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <asm/sections.h> + +#include "decode-insn.h" +#include "simulate-insn.h" + +/* Return: + * INSN_REJECTED If instruction is one not allowed to kprobe, + * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. + */ +enum probe_insn __kprobes +riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) +{ + probe_opcode_t insn = *addr; + + /* + * Reject instructions list: + */ + RISCV_INSN_REJECTED(system, insn); + RISCV_INSN_REJECTED(fence, insn); + + /* + * Simulate instructions list: + * TODO: the REJECTED ones below need to be implemented + */ +#ifdef CONFIG_RISCV_ISA_C + RISCV_INSN_REJECTED(c_jal, insn); + RISCV_INSN_REJECTED(c_ebreak, insn); + + RISCV_INSN_SET_SIMULATE(c_j, insn); + RISCV_INSN_SET_SIMULATE(c_jr, insn); + RISCV_INSN_SET_SIMULATE(c_jalr, insn); + RISCV_INSN_SET_SIMULATE(c_beqz, insn); + RISCV_INSN_SET_SIMULATE(c_bnez, insn); +#endif + + RISCV_INSN_SET_SIMULATE(jal, insn); + RISCV_INSN_SET_SIMULATE(jalr, insn); + RISCV_INSN_SET_SIMULATE(auipc, insn); + RISCV_INSN_SET_SIMULATE(branch, insn); + + return INSN_GOOD; +} diff --git a/arch/riscv/kernel/probes/decode-insn.h b/arch/riscv/kernel/probes/decode-insn.h new file mode 100644 index 000000000000..42269a7d676d --- /dev/null +++ b/arch/riscv/kernel/probes/decode-insn.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RISCV_KERNEL_KPROBES_DECODE_INSN_H +#define _RISCV_KERNEL_KPROBES_DECODE_INSN_H + +#include <asm/sections.h> +#include <asm/kprobes.h> + +enum probe_insn { + INSN_REJECTED, + INSN_GOOD_NO_SLOT, + INSN_GOOD, +}; + +enum probe_insn __kprobes +riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi); + +#endif /* _RISCV_KERNEL_KPROBES_DECODE_INSN_H */ diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c new file mode 100644 index 000000000000..7142ec42e889 --- /dev/null +++ b/arch/riscv/kernel/probes/ftrace.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kprobes.h> + +/* Ftrace callback handler for kprobes -- called under preepmt disabled */ +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct kprobe *p; + struct pt_regs *regs; + struct kprobe_ctlblk *kcb; + int bit; + + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto out; + + regs = ftrace_get_regs(fregs); + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + unsigned long orig_ip = instruction_pointer(regs); + + instruction_pointer_set(regs, ip); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) { + /* + * Emulate singlestep (and also recover regs->pc) + * as if there is a nop + */ + instruction_pointer_set(regs, + (unsigned long)p->addr + MCOUNT_INSN_SIZE); + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + instruction_pointer_set(regs, orig_ip); + } + + /* + * If pre_handler returns !0, it changes regs->pc. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); + } +out: + ftrace_test_recursion_unlock(bit); +} +NOKPROBE_SYMBOL(kprobe_ftrace_handler); + +int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.api.insn = NULL; + return 0; +} diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c new file mode 100644 index 000000000000..2f08c14a933d --- /dev/null +++ b/arch/riscv/kernel/probes/kprobes.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#define pr_fmt(fmt) "kprobes: " fmt + +#include <linux/kprobes.h> +#include <linux/extable.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> +#include <asm/ptrace.h> +#include <linux/uaccess.h> +#include <asm/sections.h> +#include <asm/cacheflush.h> +#include <asm/bug.h> +#include <asm/patch.h> + +#include "decode-insn.h" + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static void __kprobes +post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *); + +static void __kprobes arch_prepare_ss_slot(struct kprobe *p) +{ + u32 insn = __BUG_INSN_32; + unsigned long offset = GET_INSN_LENGTH(p->opcode); + + p->ainsn.api.restore = (unsigned long)p->addr + offset; + + patch_text(p->ainsn.api.insn, &p->opcode, 1); + patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset), + &insn, 1); +} + +static void __kprobes arch_prepare_simulate(struct kprobe *p) +{ + p->ainsn.api.restore = 0; +} + +static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (p->ainsn.api.handler) + p->ainsn.api.handler((u32)p->opcode, + (unsigned long)p->addr, regs); + + post_kprobe_handler(p, kcb, regs); +} + +static bool __kprobes arch_check_kprobe(struct kprobe *p) +{ + unsigned long tmp = (unsigned long)p->addr - p->offset; + unsigned long addr = (unsigned long)p->addr; + + while (tmp <= addr) { + if (tmp == addr) + return true; + + tmp += GET_INSN_LENGTH(*(u16 *)tmp); + } + + return false; +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + u16 *insn = (u16 *)p->addr; + + if ((unsigned long)insn & 0x1) + return -EILSEQ; + + if (!arch_check_kprobe(p)) + return -EILSEQ; + + /* copy instruction */ + p->opcode = (kprobe_opcode_t)(*insn++); + if (GET_INSN_LENGTH(p->opcode) == 4) + p->opcode |= (kprobe_opcode_t)(*insn) << 16; + + /* decode instruction */ + switch (riscv_probe_decode_insn(p->addr, &p->ainsn.api)) { + case INSN_REJECTED: /* insn not supported */ + return -EINVAL; + + case INSN_GOOD_NO_SLOT: /* insn need simulation */ + p->ainsn.api.insn = NULL; + break; + + case INSN_GOOD: /* instruction uses slot */ + p->ainsn.api.insn = get_insn_slot(); + if (!p->ainsn.api.insn) + return -ENOMEM; + break; + } + + /* prepare the instruction */ + if (p->ainsn.api.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} + +#ifdef CONFIG_MMU +void *alloc_insn_page(void) +{ + return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_READ_EXEC, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, + __builtin_return_address(0)); +} +#endif + +/* install breakpoint in text */ +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + u32 insn = (p->opcode & __INSN_LENGTH_MASK) == __INSN_LENGTH_32 ? + __BUG_INSN_32 : __BUG_INSN_16; + + patch_text(p->addr, &insn, 1); +} + +/* remove breakpoint from text */ +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + patch_text(p->addr, &p->opcode, 1); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ +} + +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} + +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +static void __kprobes set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} + +/* + * Interrupts need to be disabled before single-step mode is set, and not + * reenabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start of + * out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_status = regs->status; + regs->status &= ~SR_SPIE; +} + +static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + regs->status = kcb->saved_status; +} + +static void __kprobes setup_singlestep(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + unsigned long slot; + + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + if (p->ainsn.api.insn) { + /* prepare for single stepping */ + slot = (unsigned long)p->ainsn.api.insn; + + /* IRQs and single stepping do not mix well. */ + kprobes_save_local_irqflag(kcb, regs); + + instruction_pointer_set(regs, slot); + } else { + /* insn simulation */ + arch_simulate_insn(p, regs); + } +} + +static int __kprobes reenter_kprobe(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + pr_warn("Failed to recover from reentered kprobes.\n"); + dump_kprobe(p); + BUG(); + break; + default: + WARN_ON(1); + return 0; + } + + return 1; +} + +static void __kprobes +post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs) +{ + /* return addr restore if non-branching insn */ + if (cur->ainsn.api.restore != 0) + regs->epc = cur->ainsn.api.restore; + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + return; + } + + /* call post handler */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) { + /* post_handler can hit breakpoint and single step + * again, so we enable D-flag for recursive exception. + */ + cur->post_handler(cur, regs, 0); + } + + reset_current_kprobe(); +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->epc = (unsigned long) cur->addr; + BUG_ON(!instruction_pointer(regs)); + + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else { + kprobes_restore_local_irqflag(kcb, regs); + reset_current_kprobe(); + } + + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + } + return 0; +} + +bool __kprobes +kprobe_breakpoint_handler(struct pt_regs *regs) +{ + struct kprobe *p, *cur_kprobe; + struct kprobe_ctlblk *kcb; + unsigned long addr = instruction_pointer(regs); + + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe((kprobe_opcode_t *) addr); + + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return true; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. + * + * pre_handler can hit a breakpoint and can step thru + * before return. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) + setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); + } + return true; + } + + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ + return false; +} + +bool __kprobes +kprobe_single_step_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long addr = instruction_pointer(regs); + struct kprobe *cur = kprobe_running(); + + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.api.insn[0] + GET_INSN_LENGTH(cur->opcode) == addr)) { + kprobes_restore_local_irqflag(kcb, regs); + post_kprobe_handler(cur, kcb, regs); + return true; + } + /* not ours, kprobes should ignore it */ + return false; +} + +/* + * Provide a blacklist of symbols identifying ranges which cannot be kprobed. + * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). + */ +int __init arch_populate_kprobe_blacklist(void) +{ + int ret; + + ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, + (unsigned long)__irqentry_text_end); + return ret; +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} + +int __init arch_init_kprobes(void) +{ + return 0; +} diff --git a/arch/riscv/kernel/probes/rethook.c b/arch/riscv/kernel/probes/rethook.c new file mode 100644 index 000000000000..5c27c1f50989 --- /dev/null +++ b/arch/riscv/kernel/probes/rethook.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Generic return hook for riscv. + */ + +#include <linux/kprobes.h> +#include <linux/rethook.h> +#include "rethook.h" + +/* This is called from arch_rethook_trampoline() */ +unsigned long __used arch_rethook_trampoline_callback(struct pt_regs *regs) +{ + return rethook_trampoline_handler(regs, regs->s0); +} + +NOKPROBE_SYMBOL(arch_rethook_trampoline_callback); + +void arch_rethook_prepare(struct rethook_node *rhn, struct pt_regs *regs, bool mcount) +{ + rhn->ret_addr = regs->ra; + rhn->frame = regs->s0; + + /* replace return addr with trampoline */ + regs->ra = (unsigned long)arch_rethook_trampoline; +} + +NOKPROBE_SYMBOL(arch_rethook_prepare); diff --git a/arch/riscv/kernel/probes/rethook.h b/arch/riscv/kernel/probes/rethook.h new file mode 100644 index 000000000000..4758f7e3ce88 --- /dev/null +++ b/arch/riscv/kernel/probes/rethook.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __RISCV_RETHOOK_H +#define __RISCV_RETHOOK_H + +unsigned long arch_rethook_trampoline_callback(struct pt_regs *regs); +void arch_rethook_prepare(struct rethook_node *rhn, struct pt_regs *regs, bool mcount); + +#endif diff --git a/arch/riscv/kernel/probes/rethook_trampoline.S b/arch/riscv/kernel/probes/rethook_trampoline.S new file mode 100644 index 000000000000..f2cd83d9b0f0 --- /dev/null +++ b/arch/riscv/kernel/probes/rethook_trampoline.S @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Author: Patrick Stählin <me@packi.ch> + */ +#include <linux/linkage.h> + +#include <asm/asm.h> +#include <asm/asm-offsets.h> + + .text + .altmacro + + .macro save_all_base_regs + REG_S x1, PT_RA(sp) + REG_S x3, PT_GP(sp) + REG_S x4, PT_TP(sp) + REG_S x5, PT_T0(sp) + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) + .endm + + .macro restore_all_base_regs + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x5, PT_T0(sp) + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + .endm + +SYM_CODE_START(arch_rethook_trampoline) + addi sp, sp, -(PT_SIZE_ON_STACK) + save_all_base_regs + + move a0, sp /* pt_regs */ + + call arch_rethook_trampoline_callback + + /* use the result as the return-address */ + move ra, a0 + + restore_all_base_regs + addi sp, sp, PT_SIZE_ON_STACK + + ret +SYM_CODE_END(arch_rethook_trampoline) diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c new file mode 100644 index 000000000000..6c166029079c --- /dev/null +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/kprobes.h> + +#include "decode-insn.h" +#include "simulate-insn.h" + +static inline bool rv_insn_reg_get_val(struct pt_regs *regs, u32 index, + unsigned long *ptr) +{ + if (index == 0) + *ptr = 0; + else if (index <= 31) + *ptr = *((unsigned long *)regs + index); + else + return false; + + return true; +} + +static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index, + unsigned long val) +{ + if (index == 0) + return true; + else if (index <= 31) + *((unsigned long *)regs + index) = val; + else + return false; + + return true; +} + +bool __kprobes simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 31 30 21 20 19 12 11 7 6 0 + * imm [20] | imm[10:1] | imm[11] | imm[19:12] | rd | opcode + * 1 10 1 8 5 JAL/J + */ + bool ret; + u32 imm; + u32 index = (opcode >> 7) & 0x1f; + + ret = rv_insn_reg_set_val(regs, index, addr + 4); + if (!ret) + return ret; + + imm = ((opcode >> 21) & 0x3ff) << 1; + imm |= ((opcode >> 20) & 0x1) << 11; + imm |= ((opcode >> 12) & 0xff) << 12; + imm |= ((opcode >> 31) & 0x1) << 20; + + instruction_pointer_set(regs, addr + sign_extend32((imm), 20)); + + return ret; +} + +bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 31 20 19 15 14 12 11 7 6 0 + * offset[11:0] | rs1 | 010 | rd | opcode + * 12 5 3 5 JALR/JR + */ + bool ret; + unsigned long base_addr; + u32 imm = (opcode >> 20) & 0xfff; + u32 rd_index = (opcode >> 7) & 0x1f; + u32 rs1_index = (opcode >> 15) & 0x1f; + + ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); + if (!ret) + return ret; + + ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); + if (!ret) + return ret; + + instruction_pointer_set(regs, (base_addr + sign_extend32((imm), 11))&~1); + + return ret; +} + +#define auipc_rd_idx(opcode) \ + ((opcode >> 7) & 0x1f) + +#define auipc_imm(opcode) \ + ((((opcode) >> 12) & 0xfffff) << 12) + +#if __riscv_xlen == 64 +#define auipc_offset(opcode) sign_extend64(auipc_imm(opcode), 31) +#elif __riscv_xlen == 32 +#define auipc_offset(opcode) auipc_imm(opcode) +#else +#error "Unexpected __riscv_xlen" +#endif + +bool __kprobes simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * auipc instruction: + * 31 12 11 7 6 0 + * | imm[31:12] | rd | opcode | + * 20 5 7 + */ + + u32 rd_idx = auipc_rd_idx(opcode); + unsigned long rd_val = addr + auipc_offset(opcode); + + if (!rv_insn_reg_set_val(regs, rd_idx, rd_val)) + return false; + + instruction_pointer_set(regs, addr + 4); + + return true; +} + +#define branch_rs1_idx(opcode) \ + (((opcode) >> 15) & 0x1f) + +#define branch_rs2_idx(opcode) \ + (((opcode) >> 20) & 0x1f) + +#define branch_funct3(opcode) \ + (((opcode) >> 12) & 0x7) + +#define branch_imm(opcode) \ + (((((opcode) >> 8) & 0xf ) << 1) | \ + ((((opcode) >> 25) & 0x3f) << 5) | \ + ((((opcode) >> 7) & 0x1 ) << 11) | \ + ((((opcode) >> 31) & 0x1 ) << 12)) + +#define branch_offset(opcode) \ + sign_extend32((branch_imm(opcode)), 12) + +bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * branch instructions: + * 31 30 25 24 20 19 15 14 12 11 8 7 6 0 + * | imm[12] | imm[10:5] | rs2 | rs1 | funct3 | imm[4:1] | imm[11] | opcode | + * 1 6 5 5 3 4 1 7 + * imm[12|10:5] rs2 rs1 000 imm[4:1|11] 1100011 BEQ + * imm[12|10:5] rs2 rs1 001 imm[4:1|11] 1100011 BNE + * imm[12|10:5] rs2 rs1 100 imm[4:1|11] 1100011 BLT + * imm[12|10:5] rs2 rs1 101 imm[4:1|11] 1100011 BGE + * imm[12|10:5] rs2 rs1 110 imm[4:1|11] 1100011 BLTU + * imm[12|10:5] rs2 rs1 111 imm[4:1|11] 1100011 BGEU + */ + + s32 offset; + s32 offset_tmp; + unsigned long rs1_val; + unsigned long rs2_val; + + if (!rv_insn_reg_get_val(regs, branch_rs1_idx(opcode), &rs1_val) || + !rv_insn_reg_get_val(regs, branch_rs2_idx(opcode), &rs2_val)) + return false; + + offset_tmp = branch_offset(opcode); + switch (branch_funct3(opcode)) { + case RVG_FUNCT3_BEQ: + offset = (rs1_val == rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BNE: + offset = (rs1_val != rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BLT: + offset = ((long)rs1_val < (long)rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BGE: + offset = ((long)rs1_val >= (long)rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BLTU: + offset = (rs1_val < rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BGEU: + offset = (rs1_val >= rs2_val) ? offset_tmp : 4; + break; + default: + return false; + } + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 15 13 12 2 1 0 + * | funct3 | offset[11|4|9:8|10|6|7|3:1|5] | opcode | + * 3 11 2 + */ + + s32 offset; + + offset = ((opcode >> 3) & 0x7) << 1; + offset |= ((opcode >> 11) & 0x1) << 4; + offset |= ((opcode >> 2) & 0x1) << 5; + offset |= ((opcode >> 7) & 0x1) << 6; + offset |= ((opcode >> 6) & 0x1) << 7; + offset |= ((opcode >> 9) & 0x3) << 8; + offset |= ((opcode >> 8) & 0x1) << 10; + offset |= ((opcode >> 12) & 0x1) << 11; + + instruction_pointer_set(regs, addr + sign_extend32(offset, 11)); + + return true; +} + +static bool __kprobes simulate_c_jr_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_jalr) +{ + /* + * 15 12 11 7 6 2 1 0 + * | funct4 | rs1 | rs2 | op | + * 4 5 5 2 + */ + + unsigned long jump_addr; + + u32 rs1 = (opcode >> 7) & 0x1f; + + if (rs1 == 0) /* C.JR is only valid when rs1 != x0 */ + return false; + + if (!rv_insn_reg_get_val(regs, rs1, &jump_addr)) + return false; + + if (is_jalr && !rv_insn_reg_set_val(regs, 1, addr + 2)) + return false; + + instruction_pointer_set(regs, jump_addr); + + return true; +} + +bool __kprobes simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, false); +} + +bool __kprobes simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, true); +} + +static bool __kprobes simulate_c_bnez_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_bnez) +{ + /* + * 15 13 12 10 9 7 6 2 1 0 + * | funct3 | offset[8|4:3] | rs1' | offset[7:6|2:1|5] | op | + * 3 3 3 5 2 + */ + + s32 offset; + u32 rs1; + unsigned long rs1_val; + + rs1 = 0x8 | ((opcode >> 7) & 0x7); + + if (!rv_insn_reg_get_val(regs, rs1, &rs1_val)) + return false; + + if ((rs1_val != 0 && is_bnez) || (rs1_val == 0 && !is_bnez)) { + offset = ((opcode >> 3) & 0x3) << 1; + offset |= ((opcode >> 10) & 0x3) << 3; + offset |= ((opcode >> 2) & 0x1) << 5; + offset |= ((opcode >> 5) & 0x3) << 6; + offset |= ((opcode >> 12) & 0x1) << 8; + offset = sign_extend32(offset, 8); + } else { + offset = 2; + } + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, true); +} + +bool __kprobes simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, false); +} diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h new file mode 100644 index 000000000000..44ebbc444db9 --- /dev/null +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RISCV_KERNEL_PROBES_SIMULATE_INSN_H +#define _RISCV_KERNEL_PROBES_SIMULATE_INSN_H + +#include <asm/insn.h> + +#define RISCV_INSN_REJECTED(name, code) \ + do { \ + if (riscv_insn_is_##name(code)) { \ + return INSN_REJECTED; \ + } \ + } while (0) + +#define RISCV_INSN_SET_SIMULATE(name, code) \ + do { \ + if (riscv_insn_is_##name(code)) { \ + api->handler = simulate_##name; \ + return INSN_GOOD_NO_SLOT; \ + } \ + } while (0) + +bool simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs); + +#endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */ diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c new file mode 100644 index 000000000000..4b3dc8beaf77 --- /dev/null +++ b/arch/riscv/kernel/probes/uprobes.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/highmem.h> +#include <linux/ptrace.h> +#include <linux/uprobes.h> +#include <asm/insn.h> + +#include "decode-insn.h" + +#define UPROBE_TRAP_NR UINT_MAX + +bool is_swbp_insn(uprobe_opcode_t *insn) +{ +#ifdef CONFIG_RISCV_ISA_C + return (*insn & 0xffff) == UPROBE_SWBP_INSN; +#else + return *insn == UPROBE_SWBP_INSN; +#endif +} + +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return riscv_insn_is_ebreak(*insn) || riscv_insn_is_c_ebreak(*insn); +} + +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, + unsigned long addr) +{ + probe_opcode_t opcode; + + opcode = *(probe_opcode_t *)(&auprobe->insn[0]); + + auprobe->insn_size = GET_INSN_LENGTH(opcode); + + switch (riscv_probe_decode_insn(&opcode, &auprobe->api)) { + case INSN_REJECTED: + return -EINVAL; + + case INSN_GOOD_NO_SLOT: + auprobe->simulate = true; + break; + + case INSN_GOOD: + auprobe->simulate = false; + break; + + default: + return -EINVAL; + } + + return 0; +} + +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + utask->autask.saved_cause = current->thread.bad_cause; + current->thread.bad_cause = UPROBE_TRAP_NR; + + instruction_pointer_set(regs, utask->xol_vaddr); + + return 0; +} + +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + WARN_ON_ONCE(current->thread.bad_cause != UPROBE_TRAP_NR); + current->thread.bad_cause = utask->autask.saved_cause; + + instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size); + + return 0; +} + +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + if (t->thread.bad_cause != UPROBE_TRAP_NR) + return true; + + return false; +} + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + probe_opcode_t insn; + unsigned long addr; + + if (!auprobe->simulate) + return false; + + insn = *(probe_opcode_t *)(&auprobe->insn[0]); + addr = instruction_pointer(regs); + + if (auprobe->api.handler) + auprobe->api.handler(insn, addr, regs); + + return true; +} + +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + current->thread.bad_cause = utask->autask.saved_cause; + /* + * Task has received a fatal signal, so reset back to probbed + * address. + */ + instruction_pointer_set(regs, utask->vaddr); +} + +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CHAIN_CALL) + return regs->sp <= ret->stack; + else + return regs->sp < ret->stack; +} + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, + struct pt_regs *regs) +{ + unsigned long ra; + + ra = regs->ra; + + regs->ra = trampoline_vaddr; + + return ra; +} + +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} + +bool uprobe_breakpoint_handler(struct pt_regs *regs) +{ + if (uprobe_pre_sstep_notifier(regs)) + return true; + + return false; +} + +bool uprobe_single_step_handler(struct pt_regs *regs) +{ + if (uprobe_post_sstep_notifier(regs)) + return true; + + return false; +} + +void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + /* Initialize the slot */ + void *kaddr = kmap_atomic(page); + void *dst = kaddr + (vaddr & ~PAGE_MASK); + + memcpy(dst, src, len); + + /* Add ebreak behind opcode to simulate singlestep */ + if (vaddr) { + dst += GET_INSN_LENGTH(*(probe_opcode_t *)src); + *(uprobe_opcode_t *)dst = __BUG_INSN_32; + } + + 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 95a3031e5c7c..92922dbd5b5c 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -10,6 +10,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/tick.h> #include <linux/ptrace.h> @@ -18,24 +19,56 @@ #include <asm/unistd.h> #include <asm/processor.h> #include <asm/csr.h> +#include <asm/stacktrace.h> #include <asm/string.h> #include <asm/switch_to.h> #include <asm/thread_info.h> +#include <asm/cpuidle.h> +#include <asm/vector.h> +#include <asm/cpufeature.h> + +register unsigned long gp_in_global __asm__("gp"); + +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) +#include <linux/stackprotector.h> +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_kernel_thread(void); void arch_cpu_idle(void) { - wait_for_interrupt(); - local_irq_enable(); + cpu_do_idle(); } -void show_regs(struct pt_regs *regs) +int set_unalign_ctl(struct task_struct *tsk, unsigned int val) +{ + if (!unaligned_ctl_available()) + return -EINVAL; + + tsk->thread.align_ctl = val; + return 0; +} + +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); +} + +void __show_regs(struct pt_regs *regs) { show_regs_print_info(KERN_DEFAULT); - pr_cont("epc: " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n", + if (!user_mode(regs)) { + pr_cont("epc : %pS\n", (void *)regs->epc); + pr_cont(" ra : %pS\n", (void *)regs->ra); + } + + pr_cont("epc : " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n", regs->epc, regs->ra, regs->sp); pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n", regs->gp, regs->tp, regs->t0); @@ -61,12 +94,46 @@ void show_regs(struct pt_regs *regs) pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n", regs->status, regs->badaddr, regs->cause); } +void show_regs(struct pt_regs *regs) +{ + __show_regs(regs); + if (!user_mode(regs)) + dump_backtrace(regs, NULL, KERN_DEFAULT); +} + +#ifdef CONFIG_COMPAT +static bool compat_mode_supported __read_mostly; + +bool compat_elf_check_arch(Elf32_Ehdr *hdr) +{ + return compat_mode_supported && + hdr->e_machine == EM_RISCV && + hdr->e_ident[EI_CLASS] == ELFCLASS32; +} + +static int __init compat_mode_detect(void) +{ + unsigned long tmp = csr_read(CSR_STATUS); + + csr_write(CSR_STATUS, (tmp & ~SR_UXL) | SR_UXL_32); + compat_mode_supported = + (csr_read(CSR_STATUS) & SR_UXL) == SR_UXL_32; + + csr_write(CSR_STATUS, tmp); + + pr_info("riscv: ELF compat mode %s", + compat_mode_supported ? "supported" : "unsupported"); + + return 0; +} +early_initcall(compat_mode_detect); +#endif void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { regs->status = SR_PIE; - if (has_fpu) { + if (has_fpu()) { regs->status |= SR_FS_INITIAL; /* * Restore the initial value to the FP register @@ -76,7 +143,15 @@ void start_thread(struct pt_regs *regs, unsigned long pc, } regs->epc = pc; regs->sp = sp; - set_fs(USER_DS); + +#ifdef CONFIG_64BIT + regs->status &= ~SR_UXL; + + if (is_compat_task()) + regs->status |= SR_UXL_32; + else + regs->status |= SR_UXL_64; +#endif } void flush_thread(void) @@ -90,41 +165,74 @@ void flush_thread(void) fstate_off(current, task_pt_regs(current)); memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate)); #endif +#ifdef CONFIG_RISCV_ISA_V + /* Reset vector state */ + riscv_v_vstate_ctrl_init(current); + riscv_v_vstate_off(task_pt_regs(current)); + kfree(current->thread.vstate.datap); + memset(¤t->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); + clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE); +#endif +} + +void arch_release_task_struct(struct task_struct *tsk) +{ + /* Free the vector context of datap. */ + if (has_vector()) + riscv_v_thread_free(tsk); } int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { fstate_save(src, task_pt_regs(src)); *dst = *src; + /* clear entire V context, including datap for a new task */ + memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); + memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state)); + clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE); + return 0; } -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); + memset(&p->thread.s, 0, sizeof(p->thread.s)); + /* p->thread holds context to be restored by __switch_to() */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(args->fn)) { /* Kernel thread */ - const register unsigned long gp __asm__ ("gp"); memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp; + childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; - p->thread.ra = (unsigned long)ret_from_kernel_thread; - p->thread.s[0] = usp; /* fn */ - p->thread.s[1] = arg; + p->thread.s[0] = (unsigned long)args->fn; + p->thread.s[1] = (unsigned long)args->fn_arg; } else { *childregs = *(current_pt_regs()); + /* Turn off status.VS */ + riscv_v_vstate_off(childregs); if (usp) /* User fork */ childregs->sp = usp; if (clone_flags & CLONE_SETTLS) - childregs->tp = childregs->a5; + childregs->tp = tls; childregs->a0 = 0; /* Return value of fork() */ - p->thread.ra = (unsigned long)ret_from_fork; + p->thread.s[0] = 0; } + p->thread.riscv_v_flags = 0; + if (has_vector()) + riscv_v_thread_alloc(p); + p->thread.ra = (unsigned long)ret_from_fork; p->thread.sp = (unsigned long)childregs; /* kernel sp */ return 0; } + +void __init arch_task_cache_init(void) +{ + riscv_v_setup_ctx_cache(); +} diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 407464201b91..e8515aa9d80b 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -7,36 +7,35 @@ * Copied from arch/tile/kernel/ptrace.c */ +#include <asm/vector.h> #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/thread_info.h> +#include <asm/switch_to.h> #include <linux/audit.h> +#include <linux/compat.h> #include <linux/ptrace.h> #include <linux/elf.h> #include <linux/regset.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> -#include <linux/tracehook.h> - -#define CREATE_TRACE_POINTS -#include <trace/events/syscalls.h> enum riscv_regset { REGSET_X, #ifdef CONFIG_FPU REGSET_F, #endif +#ifdef CONFIG_RISCV_ISA_V + REGSET_V, +#endif }; static int riscv_gpr_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + struct membuf to) { - struct pt_regs *regs; - - regs = task_pt_regs(target); - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, regs, 0, -1); + return membuf_write(&to, task_pt_regs(target), + sizeof(struct user_regs_struct)); } static int riscv_gpr_set(struct task_struct *target, @@ -44,32 +43,25 @@ static int riscv_gpr_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - int ret; struct pt_regs *regs; regs = task_pt_regs(target); - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1); - return ret; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1); } #ifdef CONFIG_FPU static int riscv_fpr_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + struct membuf to) { - int ret; struct __riscv_d_ext_state *fstate = &target->thread.fstate; - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0, - offsetof(struct __riscv_d_ext_state, fcsr)); - if (!ret) { - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, fstate, 0, - offsetof(struct __riscv_d_ext_state, fcsr) + - sizeof(fstate->fcsr)); - } + if (target == current) + fstate_save(current, task_pt_regs(current)); - return ret; + membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr)); + membuf_store(&to, fstate->fcsr); + return membuf_zero(&to, 4); // explicitly pad } static int riscv_fpr_set(struct task_struct *target, @@ -92,14 +84,82 @@ static int riscv_fpr_set(struct task_struct *target, } #endif +#ifdef CONFIG_RISCV_ISA_V +static int riscv_vr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + struct __riscv_v_regset_state ptrace_vstate; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -EINVAL; + + /* + * Ensure the vector registers have been saved to the memory before + * copying them to membuf. + */ + if (target == current) { + get_cpu_vector_context(); + riscv_v_vstate_save(¤t->thread.vstate, task_pt_regs(current)); + put_cpu_vector_context(); + } + + ptrace_vstate.vstart = vstate->vstart; + ptrace_vstate.vl = vstate->vl; + ptrace_vstate.vtype = vstate->vtype; + ptrace_vstate.vcsr = vstate->vcsr; + ptrace_vstate.vlenb = vstate->vlenb; + + /* Copy vector header from vstate. */ + membuf_write(&to, &ptrace_vstate, sizeof(struct __riscv_v_regset_state)); + + /* Copy all the vector registers from vstate. */ + return membuf_write(&to, vstate->datap, riscv_v_vsize); +} + +static int riscv_vr_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; + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + struct __riscv_v_regset_state ptrace_vstate; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -EINVAL; + + /* Copy rest of the vstate except datap */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ptrace_vstate, 0, + sizeof(struct __riscv_v_regset_state)); + if (unlikely(ret)) + return ret; + + if (vstate->vlenb != ptrace_vstate.vlenb) + return -EINVAL; + + vstate->vstart = ptrace_vstate.vstart; + vstate->vl = ptrace_vstate.vl; + vstate->vtype = ptrace_vstate.vtype; + vstate->vcsr = ptrace_vstate.vcsr; + + /* Copy all the vector registers. */ + pos = 0; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap, + 0, riscv_v_vsize); + return ret; +} +#endif + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, .n = ELF_NGREG, .size = sizeof(elf_greg_t), .align = sizeof(elf_greg_t), - .get = &riscv_gpr_get, - .set = &riscv_gpr_set, + .regset_get = riscv_gpr_get, + .set = riscv_gpr_set, }, #ifdef CONFIG_FPU [REGSET_F] = { @@ -107,8 +167,19 @@ static const struct user_regset riscv_user_regset[] = { .n = ELF_NFPREG, .size = sizeof(elf_fpreg_t), .align = sizeof(elf_fpreg_t), - .get = &riscv_fpr_get, - .set = &riscv_fpr_set, + .regset_get = riscv_fpr_get, + .set = riscv_fpr_set, + }, +#endif +#ifdef CONFIG_RISCV_ISA_V + [REGSET_V] = { + .core_note_type = NT_RISCV_VECTOR, + .align = 16, + .n = ((32 * RISCV_MAX_VLENB) + + sizeof(struct __riscv_v_regset_state)) / sizeof(__u32), + .size = sizeof(__u32), + .regset_get = riscv_vr_get, + .set = riscv_vr_set, }, #endif }; @@ -120,14 +191,107 @@ static const struct user_regset_view riscv_user_native_view = { .n = ARRAY_SIZE(riscv_user_regset), }; -const struct user_regset_view *task_user_regset_view(struct task_struct *task) +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(epc), + REG_OFFSET_NAME(ra), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(gp), + REG_OFFSET_NAME(tp), + REG_OFFSET_NAME(t0), + REG_OFFSET_NAME(t1), + REG_OFFSET_NAME(t2), + REG_OFFSET_NAME(s0), + REG_OFFSET_NAME(s1), + REG_OFFSET_NAME(a0), + REG_OFFSET_NAME(a1), + REG_OFFSET_NAME(a2), + REG_OFFSET_NAME(a3), + REG_OFFSET_NAME(a4), + REG_OFFSET_NAME(a5), + REG_OFFSET_NAME(a6), + REG_OFFSET_NAME(a7), + REG_OFFSET_NAME(s2), + REG_OFFSET_NAME(s3), + REG_OFFSET_NAME(s4), + REG_OFFSET_NAME(s5), + REG_OFFSET_NAME(s6), + REG_OFFSET_NAME(s7), + REG_OFFSET_NAME(s8), + REG_OFFSET_NAME(s9), + REG_OFFSET_NAME(s10), + REG_OFFSET_NAME(s11), + REG_OFFSET_NAME(t3), + REG_OFFSET_NAME(t4), + REG_OFFSET_NAME(t5), + REG_OFFSET_NAME(t6), + REG_OFFSET_NAME(status), + REG_OFFSET_NAME(badaddr), + REG_OFFSET_NAME(cause), + REG_OFFSET_NAME(orig_a0), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { - return &riscv_user_native_view; + return (addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; } void ptrace_disable(struct task_struct *child) { - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); } long arch_ptrace(struct task_struct *child, long request, @@ -144,43 +308,83 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -/* - * Allows PTRACE_SYSCALL to work. These are called from entry.S in - * {handle,ret_from}_syscall. - */ -__visible void do_syscall_trace_enter(struct pt_regs *regs) +#ifdef CONFIG_COMPAT +static int compat_riscv_gpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) { - if (test_thread_flag(TIF_SYSCALL_TRACE)) - if (tracehook_report_syscall_entry(regs)) - syscall_set_nr(current, regs, -1); + struct compat_user_regs_struct cregs; - /* - * Do the secure computing after ptrace; failures should be fast. - * If this fails we might have return value in a0 from seccomp - * (via SECCOMP_RET_ERRNO/TRACE). - */ - if (secure_computing() == -1) { - syscall_set_nr(current, regs, -1); - return; - } + regs_to_cregs(&cregs, task_pt_regs(target)); -#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) - trace_sys_enter(regs, syscall_get_nr(current, regs)); -#endif + return membuf_write(&to, &cregs, + sizeof(struct compat_user_regs_struct)); +} + +static int compat_riscv_gpr_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; + struct compat_user_regs_struct cregs; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1); - audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); + cregs_to_regs(&cregs, task_pt_regs(target)); + + return ret; } -__visible void do_syscall_trace_exit(struct pt_regs *regs) +static const struct user_regset compat_riscv_user_regset[] = { + [REGSET_X] = { + .core_note_type = NT_PRSTATUS, + .n = ELF_NGREG, + .size = sizeof(compat_elf_greg_t), + .align = sizeof(compat_elf_greg_t), + .regset_get = compat_riscv_gpr_get, + .set = compat_riscv_gpr_set, + }, +#ifdef CONFIG_FPU + [REGSET_F] = { + .core_note_type = NT_PRFPREG, + .n = ELF_NFPREG, + .size = sizeof(elf_fpreg_t), + .align = sizeof(elf_fpreg_t), + .regset_get = riscv_fpr_get, + .set = riscv_fpr_set, + }, +#endif +}; + +static const struct user_regset_view compat_riscv_user_native_view = { + .name = "riscv", + .e_machine = EM_RISCV, + .regsets = compat_riscv_user_regset, + .n = ARRAY_SIZE(compat_riscv_user_regset), +}; + +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) { - audit_syscall_exit(regs); + long ret = -EIO; + + switch (request) { + default: + ret = compat_ptrace_request(child, request, caddr, cdata); + break; + } - if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); + return ret; +} +#endif /* CONFIG_COMPAT */ -#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) - trace_sys_exit(regs, regs_return_value(regs)); +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_32BIT)) + return &compat_riscv_user_native_view; + else #endif + return &riscv_user_native_view; } diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index ee5878d968cc..912288572226 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -12,7 +12,7 @@ static void default_power_off(void) wait_for_interrupt(); } -void (*pm_power_off)(void) = default_power_off; +void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); void machine_restart(char *cmd) @@ -23,10 +23,12 @@ void machine_restart(char *cmd) void machine_halt(void) { - pm_power_off(); + do_kernel_power_off(); + default_power_off(); } void machine_power_off(void) { - pm_power_off(); + do_kernel_power_off(); + default_power_off(); } diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c index 4800cf703186..a72879b4249a 100644 --- a/arch/riscv/kernel/riscv_ksyms.c +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -9,8 +9,12 @@ /* * Assembly functions that may be used (directly or indirectly) by modules */ -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(__asm_copy_to_user); -EXPORT_SYMBOL(__asm_copy_from_user); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(strcmp); +EXPORT_SYMBOL(strlen); +EXPORT_SYMBOL(strncmp); +EXPORT_SYMBOL(__memset); +EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(__memmove); diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c new file mode 100644 index 000000000000..a4559695ce62 --- /dev/null +++ b/arch/riscv/kernel/sbi-ipi.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Multiplex several IPIs over a single HW IPI. + * + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "riscv: " fmt +#include <linux/cpu.h> +#include <linux/init.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <asm/sbi.h> + +static int sbi_ipi_virq; + +static void sbi_ipi_handle(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + + chained_irq_enter(chip, desc); + + csr_clear(CSR_IP, IE_SIE); + ipi_mux_process(); + + chained_irq_exit(chip, desc); +} + +static int sbi_ipi_starting_cpu(unsigned int cpu) +{ + enable_percpu_irq(sbi_ipi_virq, irq_get_trigger_type(sbi_ipi_virq)); + return 0; +} + +void __init sbi_ipi_init(void) +{ + int virq; + struct irq_domain *domain; + + if (riscv_ipi_have_virq_range()) + return; + + domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), + DOMAIN_BUS_ANY); + if (!domain) { + pr_err("unable to find INTC IRQ domain\n"); + return; + } + + sbi_ipi_virq = irq_create_mapping(domain, RV_IRQ_SOFT); + if (!sbi_ipi_virq) { + pr_err("unable to create INTC IRQ mapping\n"); + return; + } + + virq = ipi_mux_create(BITS_PER_BYTE, sbi_send_ipi); + if (virq <= 0) { + pr_err("unable to create muxed IPIs\n"); + irq_dispose_mapping(sbi_ipi_virq); + return; + } + + irq_set_chained_handler(sbi_ipi_virq, sbi_ipi_handle); + + /* + * Don't disable IPI when CPU goes offline because + * the masking/unmasking of virtual IPIs is done + * via generic IPI-Mux + */ + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "irqchip/sbi-ipi:starting", + sbi_ipi_starting_cpu, NULL); + + riscv_ipi_set_virq_range(virq, BITS_PER_BYTE, false); + pr_info("providing IPIs using SBI IPI extension\n"); +} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f6c7c3e82d28..e66e0999a800 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -1,17 +1,686 @@ // SPDX-License-Identifier: GPL-2.0-only +/* + * SBI initialilization and all extension implementation. + * + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ +#include <linux/bits.h> #include <linux/init.h> +#include <linux/mm.h> #include <linux/pm.h> +#include <linux/reboot.h> #include <asm/sbi.h> +#include <asm/smp.h> +#include <asm/tlbflush.h> -static void sbi_power_off(void) +/* default SBI version is 0.1 */ +unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT; +EXPORT_SYMBOL(sbi_spec_version); + +static void (*__sbi_set_timer)(uint64_t stime) __ro_after_init; +static void (*__sbi_send_ipi)(unsigned int cpu) __ro_after_init; +static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) __ro_after_init; + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5) +{ + struct sbiret ret; + + register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); + register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); + register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); + register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); + register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); + register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); + register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); + register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); + asm volatile ("ecall" + : "+r" (a0), "+r" (a1) + : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) + : "memory"); + ret.error = a0; + ret.value = a1; + + return ret; +} +EXPORT_SYMBOL(sbi_ecall); + +int sbi_err_map_linux_errno(int err) +{ + switch (err) { + case SBI_SUCCESS: + return 0; + case SBI_ERR_DENIED: + return -EPERM; + case SBI_ERR_INVALID_PARAM: + return -EINVAL; + case SBI_ERR_INVALID_ADDRESS: + return -EFAULT; + case SBI_ERR_NOT_SUPPORTED: + case SBI_ERR_FAILURE: + default: + return -ENOTSUPP; + }; +} +EXPORT_SYMBOL(sbi_err_map_linux_errno); + +#ifdef CONFIG_RISCV_SBI_V01 +static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mask) +{ + unsigned long cpuid, hartid; + unsigned long hmask = 0; + + /* + * There is no maximum hartid concept in RISC-V and NR_CPUS must not be + * associated with hartid. As SBI v0.1 is only kept for backward compatibility + * and will be removed in the future, there is no point in supporting hartid + * greater than BITS_PER_LONG (32 for RV32 and 64 for RV64). Ideally, SBI v0.2 + * should be used for platforms with hartid greater than BITS_PER_LONG. + */ + for_each_cpu(cpuid, cpu_mask) { + hartid = cpuid_to_hartid_map(cpuid); + if (hartid >= BITS_PER_LONG) { + pr_warn("Unable to send any request to hartid > BITS_PER_LONG for SBI v0.1\n"); + break; + } + hmask |= BIT(hartid); + } + + return hmask; +} + +/** + * sbi_console_putchar() - Writes given character to the console device. + * @ch: The data to be written to the console. + * + * Return: None + */ +void sbi_console_putchar(int ch) +{ + sbi_ecall(SBI_EXT_0_1_CONSOLE_PUTCHAR, 0, ch, 0, 0, 0, 0, 0); +} +EXPORT_SYMBOL(sbi_console_putchar); + +/** + * sbi_console_getchar() - Reads a byte from console device. + * + * Returns the value read from console. + */ +int sbi_console_getchar(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_0_1_CONSOLE_GETCHAR, 0, 0, 0, 0, 0, 0, 0); + + return ret.error; +} +EXPORT_SYMBOL(sbi_console_getchar); + +/** + * sbi_shutdown() - Remove all the harts from executing supervisor code. + * + * Return: None + */ +void sbi_shutdown(void) +{ + sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0); +} +EXPORT_SYMBOL(sbi_shutdown); + +/** + * __sbi_set_timer_v01() - Program the timer for next timer event. + * @stime_value: The value after which next timer event should fire. + * + * Return: None + */ +static void __sbi_set_timer_v01(uint64_t stime_value) +{ +#if __riscv_xlen == 32 + sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, + stime_value >> 32, 0, 0, 0, 0); +#else + sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, 0, 0, 0, 0, 0); +#endif +} + +static void __sbi_send_ipi_v01(unsigned int cpu) +{ + unsigned long hart_mask = + __sbi_v01_cpumask_to_hartmask(cpumask_of(cpu)); + sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)(&hart_mask), + 0, 0, 0, 0, 0); +} + +static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) +{ + int result = 0; + unsigned long hart_mask; + + if (!cpu_mask || cpumask_empty(cpu_mask)) + cpu_mask = cpu_online_mask; + hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask); + + /* v0.2 function IDs are equivalent to v0.1 extension IDs */ + switch (fid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0, + (unsigned long)&hart_mask, 0, 0, 0, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0, + (unsigned long)&hart_mask, start, size, + 0, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0, + (unsigned long)&hart_mask, start, size, + arg4, 0, 0); + break; + default: + pr_err("SBI call [%d]not supported in SBI v0.1\n", fid); + result = -EINVAL; + } + + return result; +} + +static void sbi_set_power_off(void) +{ + pm_power_off = sbi_shutdown; +} +#else +static void __sbi_set_timer_v01(uint64_t stime_value) +{ + pr_warn("Timer extension is not available in SBI v%lu.%lu\n", + sbi_major_version(), sbi_minor_version()); +} + +static void __sbi_send_ipi_v01(unsigned int cpu) +{ + pr_warn("IPI extension is not available in SBI v%lu.%lu\n", + sbi_major_version(), sbi_minor_version()); +} + +static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) +{ + pr_warn("remote fence extension is not available in SBI v%lu.%lu\n", + sbi_major_version(), sbi_minor_version()); + + return 0; +} + +static void sbi_set_power_off(void) {} +#endif /* CONFIG_RISCV_SBI_V01 */ + +static void __sbi_set_timer_v02(uint64_t stime_value) +{ +#if __riscv_xlen == 32 + sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, + stime_value >> 32, 0, 0, 0, 0); +#else + sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, 0, + 0, 0, 0, 0); +#endif +} + +static void __sbi_send_ipi_v02(unsigned int cpu) +{ + int result; + struct sbiret ret = {0}; + + ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI, + 1UL, cpuid_to_hartid_map(cpu), 0, 0, 0, 0); + if (ret.error) { + result = sbi_err_map_linux_errno(ret.error); + pr_err("%s: hbase = [%lu] failed (error [%d])\n", + __func__, cpuid_to_hartid_map(cpu), result); + } +} + +static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask, + unsigned long hbase, unsigned long start, + unsigned long size, unsigned long arg4, + unsigned long arg5) +{ + struct sbiret ret = {0}; + int ext = SBI_EXT_RFENCE; + int result = 0; + + switch (fid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + ret = sbi_ecall(ext, fid, hmask, hbase, 0, 0, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, arg4, 0); + break; + + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, arg4, 0); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, arg4, 0); + break; + default: + pr_err("unknown function ID [%lu] for SBI extension [%d]\n", + fid, ext); + result = -EINVAL; + } + + if (ret.error) { + result = sbi_err_map_linux_errno(ret.error); + pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n", + __func__, hbase, hmask, result); + } + + return result; +} + +static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) +{ + unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0; + int result; + + if (!cpu_mask || cpumask_empty(cpu_mask)) + cpu_mask = cpu_online_mask; + + for_each_cpu(cpuid, cpu_mask) { + hartid = cpuid_to_hartid_map(cpuid); + if (hmask) { + if (hartid + BITS_PER_LONG <= htop || + hbase + BITS_PER_LONG <= hartid) { + result = __sbi_rfence_v02_call(fid, hmask, + hbase, start, size, arg4, arg5); + if (result) + return result; + hmask = 0; + } else if (hartid < hbase) { + /* shift the mask to fit lower hartid */ + hmask <<= hbase - hartid; + hbase = hartid; + } + } + if (!hmask) { + hbase = hartid; + htop = hartid; + } else if (hartid > htop) { + htop = hartid; + } + hmask |= BIT(hartid - hbase); + } + + if (hmask) { + result = __sbi_rfence_v02_call(fid, hmask, hbase, + start, size, arg4, arg5); + if (result) + return result; + } + + return 0; +} + +/** + * sbi_set_timer() - Program the timer for next timer event. + * @stime_value: The value after which next timer event should fire. + * + * Return: None. + */ +void sbi_set_timer(uint64_t stime_value) +{ + __sbi_set_timer(stime_value); +} + +/** + * sbi_send_ipi() - Send an IPI to any hart. + * @cpu: Logical id of the target CPU. + */ +void sbi_send_ipi(unsigned int cpu) +{ + __sbi_send_ipi(cpu); +} +EXPORT_SYMBOL(sbi_send_ipi); + +/** + * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts. + * @cpu_mask: A cpu mask containing all the target harts. + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_remote_fence_i(const struct cpumask *cpu_mask) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I, + cpu_mask, 0, 0, 0, 0); +} +EXPORT_SYMBOL(sbi_remote_fence_i); + +/** + * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given + * remote harts for a virtual address range belonging to a specific ASID or not. + * + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the virtual address + * @size: Total size of the virtual address range. + * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID + * for flushing all address spaces. + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long asid) +{ + if (asid == FLUSH_TLB_NO_ASID) + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, + cpu_mask, start, size, 0, 0); + else + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, + cpu_mask, start, size, asid, 0); +} +EXPORT_SYMBOL(sbi_remote_sfence_vma_asid); + +/** + * sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote + * harts for the specified guest physical address range. + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the guest physical address + * @size: Total size of the guest physical address range. + * + * Return: None + */ +int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA, + cpu_mask, start, size, 0, 0); +} +EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma); + +/** + * sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given + * remote harts for a guest physical address range belonging to a specific VMID. + * + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the guest physical address + * @size: Total size of the guest physical address range. + * @vmid: The value of guest ID (VMID). + * + * Return: 0 if success, Error otherwise. + */ +int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long vmid) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID, + cpu_mask, start, size, vmid, 0); +} +EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid); + +/** + * sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote + * harts for the current guest virtual address range. + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the current guest virtual address + * @size: Total size of the current guest virtual address range. + * + * Return: None + */ +int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA, + cpu_mask, start, size, 0, 0); +} +EXPORT_SYMBOL(sbi_remote_hfence_vvma); + +/** + * sbi_remote_hfence_vvma_asid() - Execute HFENCE.VVMA instructions on given + * remote harts for current guest virtual address range belonging to a specific + * ASID. + * + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the current guest virtual address + * @size: Total size of the current guest virtual address range. + * @asid: The value of address space identifier (ASID). + * + * Return: None + */ +int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long asid) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID, + cpu_mask, start, size, asid, 0); +} +EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid); + +static void sbi_srst_reset(unsigned long type, unsigned long reason) +{ + sbi_ecall(SBI_EXT_SRST, SBI_EXT_SRST_RESET, type, reason, + 0, 0, 0, 0); + pr_warn("%s: type=0x%lx reason=0x%lx failed\n", + __func__, type, reason); +} + +static int sbi_srst_reboot(struct notifier_block *this, + unsigned long mode, void *cmd) { - sbi_shutdown(); + sbi_srst_reset((mode == REBOOT_WARM || mode == REBOOT_SOFT) ? + SBI_SRST_RESET_TYPE_WARM_REBOOT : + SBI_SRST_RESET_TYPE_COLD_REBOOT, + SBI_SRST_RESET_REASON_NONE); + return NOTIFY_DONE; } -static int __init sbi_init(void) +static struct notifier_block sbi_srst_reboot_nb; + +static void sbi_srst_power_off(void) { - pm_power_off = sbi_power_off; + sbi_srst_reset(SBI_SRST_RESET_TYPE_SHUTDOWN, + SBI_SRST_RESET_REASON_NONE); +} + +/** + * sbi_probe_extension() - Check if an SBI extension ID is supported or not. + * @extid: The extension ID to be probed. + * + * Return: 1 or an extension specific nonzero value if yes, 0 otherwise. + */ +long sbi_probe_extension(int extid) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid, + 0, 0, 0, 0, 0); + if (!ret.error) + return ret.value; + return 0; } -early_initcall(sbi_init); +EXPORT_SYMBOL(sbi_probe_extension); + +static long __sbi_base_ecall(int fid) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0); + if (!ret.error) + return ret.value; + else + return sbi_err_map_linux_errno(ret.error); +} + +static inline long sbi_get_spec_version(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION); +} + +static inline long sbi_get_firmware_id(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_ID); +} + +static inline long sbi_get_firmware_version(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); +} + +long sbi_get_mvendorid(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_MVENDORID); +} +EXPORT_SYMBOL_GPL(sbi_get_mvendorid); + +long sbi_get_marchid(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_MARCHID); +} +EXPORT_SYMBOL_GPL(sbi_get_marchid); + +long sbi_get_mimpid(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_MIMPID); +} +EXPORT_SYMBOL_GPL(sbi_get_mimpid); + +bool sbi_debug_console_available; + +int sbi_debug_console_write(const char *bytes, unsigned int num_bytes) +{ + phys_addr_t base_addr; + struct sbiret ret; + + if (!sbi_debug_console_available) + return -EOPNOTSUPP; + + if (is_vmalloc_addr(bytes)) + base_addr = page_to_phys(vmalloc_to_page(bytes)) + + offset_in_page(bytes); + else + base_addr = __pa(bytes); + if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes)) + num_bytes = PAGE_SIZE - offset_in_page(bytes); + + if (IS_ENABLED(CONFIG_32BIT)) + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE, + num_bytes, lower_32_bits(base_addr), + upper_32_bits(base_addr), 0, 0, 0); + else + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE, + num_bytes, base_addr, 0, 0, 0, 0); + + if (ret.error == SBI_ERR_FAILURE) + return -EIO; + return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value; +} + +int sbi_debug_console_read(char *bytes, unsigned int num_bytes) +{ + phys_addr_t base_addr; + struct sbiret ret; + + if (!sbi_debug_console_available) + return -EOPNOTSUPP; + + if (is_vmalloc_addr(bytes)) + base_addr = page_to_phys(vmalloc_to_page(bytes)) + + offset_in_page(bytes); + else + base_addr = __pa(bytes); + if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes)) + num_bytes = PAGE_SIZE - offset_in_page(bytes); + + if (IS_ENABLED(CONFIG_32BIT)) + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ, + num_bytes, lower_32_bits(base_addr), + upper_32_bits(base_addr), 0, 0, 0); + else + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ, + num_bytes, base_addr, 0, 0, 0, 0); + + if (ret.error == SBI_ERR_FAILURE) + return -EIO; + return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value; +} + +void __init sbi_init(void) +{ + int ret; + + sbi_set_power_off(); + ret = sbi_get_spec_version(); + if (ret > 0) + sbi_spec_version = ret; + + pr_info("SBI specification v%lu.%lu detected\n", + sbi_major_version(), sbi_minor_version()); + + if (!sbi_spec_is_0_1()) { + pr_info("SBI implementation ID=0x%lx Version=0x%lx\n", + sbi_get_firmware_id(), sbi_get_firmware_version()); + if (sbi_probe_extension(SBI_EXT_TIME)) { + __sbi_set_timer = __sbi_set_timer_v02; + pr_info("SBI TIME extension detected\n"); + } else { + __sbi_set_timer = __sbi_set_timer_v01; + } + if (sbi_probe_extension(SBI_EXT_IPI)) { + __sbi_send_ipi = __sbi_send_ipi_v02; + pr_info("SBI IPI extension detected\n"); + } else { + __sbi_send_ipi = __sbi_send_ipi_v01; + } + if (sbi_probe_extension(SBI_EXT_RFENCE)) { + __sbi_rfence = __sbi_rfence_v02; + pr_info("SBI RFENCE extension detected\n"); + } else { + __sbi_rfence = __sbi_rfence_v01; + } + 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; + sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot; + 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)) { + pr_info("SBI DBCN extension detected\n"); + sbi_debug_console_available = true; + } + } else { + __sbi_set_timer = __sbi_set_timer_v01; + __sbi_send_ipi = __sbi_send_ipi_v01; + __sbi_rfence = __sbi_rfence_v01; + } +} diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 365ff8420bfe..4f73c0ae44b2 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -4,83 +4,335 @@ * Chen Liqin <liqin.chen@sunplusct.com> * Lennox Wu <lennox.wu@sunplusct.com> * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis <mick@ics.forth.gr> */ +#include <linux/acpi.h> +#include <linux/cpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/sched.h> #include <linux/console.h> -#include <linux/screen_info.h> #include <linux/of_fdt.h> -#include <linux/of_platform.h> #include <linux/sched/task.h> -#include <linux/swiotlb.h> +#include <linux/smp.h> +#include <linux/efi.h> +#include <linux/crash_dump.h> +#include <linux/panic_notifier.h> -#include <asm/clint.h> +#include <asm/acpi.h> +#include <asm/alternative.h> +#include <asm/cacheflush.h> +#include <asm/cpufeature.h> +#include <asm/early_ioremap.h> +#include <asm/pgtable.h> #include <asm/setup.h> +#include <asm/set_memory.h> #include <asm/sections.h> -#include <asm/pgtable.h> -#include <asm/smp.h> +#include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/thread_info.h> +#include <asm/kasan.h> +#include <asm/efi.h> #include "head.h" -#ifdef CONFIG_DUMMY_CONSOLE -struct screen_info screen_info = { - .orig_video_lines = 30, - .orig_video_cols = 80, - .orig_video_mode = 0, - .orig_video_ega_bx = 0, - .orig_video_isVGA = 1, - .orig_video_points = 8 -}; +/* + * The lucky hart to first increment this variable will boot the other cores. + * This is used before the kernel initializes the BSS so it can't be in the + * BSS. + */ +atomic_t hart_lottery __section(".sdata") +#ifdef CONFIG_XIP_KERNEL += ATOMIC_INIT(0xC001BEEF) #endif - -/* The lucky hart to first increment this variable will boot the other cores */ -atomic_t hart_lottery; +; unsigned long boot_cpu_hartid; -void __init parse_dtb(void) +/* + * Place kernel memory regions on the resource tree so that + * kexec-tools can retrieve them from /proc/iomem. While there + * also add "System RAM" regions for compatibility with other + * archs, and the rest of the known regions for completeness. + */ +static struct resource kimage_res = { .name = "Kernel image", }; +static struct resource code_res = { .name = "Kernel code", }; +static struct resource data_res = { .name = "Kernel data", }; +static struct resource rodata_res = { .name = "Kernel rodata", }; +static struct resource bss_res = { .name = "Kernel bss", }; +#ifdef CONFIG_CRASH_DUMP +static struct resource elfcorehdr_res = { .name = "ELF Core hdr", }; +#endif + +static int __init add_resource(struct resource *parent, + struct resource *res) +{ + int ret = 0; + + ret = insert_resource(parent, res); + if (ret < 0) { + pr_err("Failed to add a %s resource at %llx\n", + res->name, (unsigned long long) res->start); + return ret; + } + + return 1; +} + +static int __init add_kernel_resources(void) +{ + int ret = 0; + + /* + * The memory region of the kernel image is continuous and + * was reserved on setup_bootmem, register it here as a + * resource, with the various segments of the image as + * child nodes. + */ + + code_res.start = __pa_symbol(_text); + code_res.end = __pa_symbol(_etext) - 1; + code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + rodata_res.start = __pa_symbol(__start_rodata); + rodata_res.end = __pa_symbol(__end_rodata) - 1; + rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + data_res.start = __pa_symbol(_data); + data_res.end = __pa_symbol(_edata) - 1; + data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + bss_res.start = __pa_symbol(__bss_start); + bss_res.end = __pa_symbol(__bss_stop) - 1; + bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + kimage_res.start = code_res.start; + kimage_res.end = bss_res.end; + kimage_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + ret = add_resource(&iomem_resource, &kimage_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &code_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &rodata_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &data_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &bss_res); + + return ret; +} + +static void __init init_resources(void) { - if (early_init_dt_scan(dtb_early_va)) - return; + struct memblock_region *region = NULL; + struct resource *res = NULL; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int num_resources = 0, res_idx = 0; + int ret = 0; + + /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */ + num_resources = memblock.memory.cnt + memblock.reserved.cnt + 1; + 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); + + /* + * Start by adding the reserved regions, if they overlap + * with /memory regions, insert_resource later on will take + * care of it. + */ + ret = add_kernel_resources(); + if (ret < 0) + goto error; + +#ifdef CONFIG_CRASH_DUMP + if (elfcorehdr_size > 0) { + elfcorehdr_res.start = elfcorehdr_addr; + elfcorehdr_res.end = elfcorehdr_addr + elfcorehdr_size - 1; + elfcorehdr_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + add_resource(&iomem_resource, &elfcorehdr_res); + } +#endif + + for_each_reserved_mem_region(region) { + res = &mem_res[res_idx--]; + + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE; + res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1; + + /* + * Ignore any other reserved regions within + * system memory. + */ + if (memblock_is_memory(res->start)) { + /* Re-use this pre-allocated resource */ + res_idx++; + continue; + } + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + /* Add /memory regions to the resource tree */ + for_each_mem_region(region) { + res = &mem_res[res_idx--]; + + if (unlikely(memblock_is_nomap(region))) { + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE; + } else { + res->name = "System RAM"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + } + + res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + /* Clean-up any unused pre-allocated resources */ + if (res_idx >= 0) + memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res)); + return; + + error: + /* Better an empty resource tree than an inconsistent one */ + release_child_resources(&iomem_resource); + memblock_free(mem_res, mem_res_sz); +} + + +static void __init parse_dtb(void) +{ + /* Early scan of device tree from init memory */ + if (early_init_dt_scan(dtb_early_va)) { + const char *name = of_flat_dt_get_machine_name(); + + if (name) { + pr_info("Machine model: %s\n", name); + dump_stack_set_arch_desc("%s (DT)", name); + } + } else { + pr_err("No DTB passed to the kernel\n"); + } - pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE - strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); #endif } +extern void __init init_rt_signal_env(void); + void __init setup_arch(char **cmdline_p) { - init_mm.start_code = (unsigned long) _stext; - init_mm.end_code = (unsigned long) _etext; - init_mm.end_data = (unsigned long) _edata; - init_mm.brk = (unsigned long) _end; + parse_dtb(); + setup_initial_init_mm(_stext, _etext, _edata, _end); *cmdline_p = boot_command_line; + early_ioremap_setup(); + sbi_init(); + jump_label_init(); parse_early_param(); - setup_bootmem(); + efi_init(); paging_init(); + + /* Parse the ACPI tables for possible boot-time configuration */ + acpi_boot_table_init(); + +#if IS_ENABLED(CONFIG_BUILTIN_DTB) + unflatten_and_copy_device_tree(); +#else unflatten_device_tree(); - clint_init_boot_cpu(); +#endif + misc_mem_init(); + + init_resources(); -#ifdef CONFIG_SWIOTLB - swiotlb_init(1); +#ifdef CONFIG_KASAN + kasan_init(); #endif #ifdef CONFIG_SMP setup_smp(); #endif -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif + if (!acpi_disabled) + acpi_init_rintc_map(); + riscv_init_cbo_blocksizes(); riscv_fill_hwcap(); + init_rt_signal_env(); + apply_boot_alternatives(); + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && + riscv_isa_extension_available(NULL, ZICBOM)) + riscv_noncoherent_supported(); + riscv_set_dma_cache_alignment(); + + riscv_user_isa_enable(); +} + +bool arch_cpu_is_hotpluggable(int cpu) +{ + return cpu_has_hotplug(cpu); +} + +void free_initmem(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) { + set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx); + if (IS_ENABLED(CONFIG_64BIT)) + set_kernel_memory(__init_begin, __init_end, set_memory_nx); + } + + free_initmem_default(POISON_FREE_INITMEM); +} + +static int dump_kernel_offset(struct notifier_block *self, + unsigned long v, void *p) +{ + pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n", + kernel_map.virt_offset, + KERNEL_LINK_ADDR); + + return 0; +} + +static struct notifier_block kernel_offset_notifier = { + .notifier_call = dump_kernel_offset +}; + +static int __init register_kernel_offset_dumper(void) +{ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_offset_notifier); + + return 0; } +device_initcall(register_kernel_offset_dumper); diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 17ba190e84a5..501e66debf69 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -6,18 +6,27 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/compat.h> #include <linux/signal.h> #include <linux/uaccess.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/linkage.h> +#include <linux/entry-common.h> #include <asm/ucontext.h> #include <asm/vdso.h> +#include <asm/signal.h> +#include <asm/signal32.h> #include <asm/switch_to.h> +#include <asm/vector.h> #include <asm/csr.h> +#include <asm/cacheflush.h> + +unsigned long signal_minsigstksz __ro_after_init; extern u32 __user_rt_sigreturn[2]; +static size_t riscv_v_sc_size __ro_after_init; #define DEBUG_SIG 0 @@ -35,26 +44,13 @@ static long restore_fp_state(struct pt_regs *regs, { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; - size_t i; err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); if (unlikely(err)) return err; fstate_restore(current, regs); - - /* We support no other extension state at this time. */ - for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { - u32 value; - - err = __get_user(value, &sc_fpregs->q.reserved[i]); - if (unlikely(err)) - break; - if (value != 0) - return -EINVAL; - } - - return err; + return 0; } static long save_fp_state(struct pt_regs *regs, @@ -62,52 +58,189 @@ static long save_fp_state(struct pt_regs *regs, { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; - size_t i; fstate_save(current, regs); err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + return err; +} +#else +#define save_fp_state(task, regs) (0) +#define restore_fp_state(task, regs) (0) +#endif + +#ifdef CONFIG_RISCV_ISA_V + +static long save_v_state(struct pt_regs *regs, void __user **sc_vec) +{ + struct __riscv_ctx_hdr __user *hdr; + struct __sc_riscv_v_state __user *state; + void __user *datap; + long err; + + hdr = *sc_vec; + /* Place state to the user's signal context space after the hdr */ + state = (struct __sc_riscv_v_state __user *)(hdr + 1); + /* Point datap right after the end of __sc_riscv_v_state */ + datap = state + 1; + + /* datap is designed to be 16 byte aligned for better performance */ + WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16))); + + get_cpu_vector_context(); + riscv_v_vstate_save(¤t->thread.vstate, regs); + put_cpu_vector_context(); + + /* Copy everything of vstate but datap. */ + err = __copy_to_user(&state->v_state, ¤t->thread.vstate, + offsetof(struct __riscv_v_ext_state, datap)); + /* Copy the pointer datap itself. */ + err |= __put_user((__force void *)datap, &state->v_state.datap); + /* Copy the whole vector content to user space datap. */ + err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize); + /* Copy magic to the user space after saving all vector conetext */ + err |= __put_user(RISCV_V_MAGIC, &hdr->magic); + err |= __put_user(riscv_v_sc_size, &hdr->size); if (unlikely(err)) return err; - /* We support no other extension state at this time. */ - for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { - err = __put_user(0, &sc_fpregs->q.reserved[i]); - if (unlikely(err)) - break; - } + /* Only progress the sv_vec if everything has done successfully */ + *sc_vec += riscv_v_sc_size; + return 0; +} + +/* + * Restore Vector extension context from the user's signal frame. This function + * assumes a valid extension header. So magic and size checking must be done by + * the caller. + */ +static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) +{ + long err; + struct __sc_riscv_v_state __user *state = sc_vec; + void __user *datap; + + /* Copy everything of __sc_riscv_v_state except datap. */ + err = __copy_from_user(¤t->thread.vstate, &state->v_state, + offsetof(struct __riscv_v_ext_state, datap)); + if (unlikely(err)) + return err; + + /* Copy the pointer datap itself. */ + err = __get_user(datap, &state->v_state.datap); + if (unlikely(err)) + return err; + /* + * Copy the whole vector content from user space datap. Use + * copy_from_user to prevent information leak. + */ + err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); + if (unlikely(err)) + return err; + + riscv_v_vstate_set_restore(current, regs); return err; } #else -#define save_fp_state(task, regs) (0) -#define restore_fp_state(task, regs) (0) +#define save_v_state(task, regs) (0) +#define __restore_v_state(task, regs) (0) #endif static long restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) { + void __user *sc_ext_ptr = &sc->sc_extdesc.hdr; + __u32 rsvd; long err; /* sc_regs is structured the same as the start of pt_regs */ err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs)); + if (unlikely(err)) + return err; + /* Restore the floating-point state. */ - if (has_fpu) - err |= restore_fp_state(regs, &sc->sc_fpregs); + if (has_fpu()) { + err = restore_fp_state(regs, &sc->sc_fpregs); + if (unlikely(err)) + return err; + } + + /* Check the reserved word before extensions parsing */ + err = __get_user(rsvd, &sc->sc_extdesc.reserved); + if (unlikely(err)) + return err; + if (unlikely(rsvd)) + return -EINVAL; + + while (!err) { + __u32 magic, size; + struct __riscv_ctx_hdr __user *head = sc_ext_ptr; + + err |= __get_user(magic, &head->magic); + err |= __get_user(size, &head->size); + if (unlikely(err)) + return err; + + sc_ext_ptr += sizeof(*head); + switch (magic) { + case END_MAGIC: + if (size != END_HDR_SIZE) + return -EINVAL; + + return 0; + case RISCV_V_MAGIC: + if (!has_vector() || !riscv_v_vstate_query(regs) || + size != riscv_v_sc_size) + return -EINVAL; + + err = __restore_v_state(regs, sc_ext_ptr); + break; + default: + return -EINVAL; + } + sc_ext_ptr = (void __user *)head + size; + } return err; } +static size_t get_rt_frame_size(bool cal_all) +{ + struct rt_sigframe __user *frame; + size_t frame_size; + size_t total_context_size = 0; + + frame_size = sizeof(*frame); + + if (has_vector()) { + 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; + + frame_size = round_up(frame_size, 16); + return frame_size; +} + SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; struct task_struct *task; sigset_t set; + size_t frame_size = get_rt_frame_size(false); /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; frame = (struct rt_sigframe __user *)regs->sp; - if (!access_ok(frame, sizeof(*frame))) + if (!access_ok(frame, frame_size)) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) @@ -121,6 +254,8 @@ SYSCALL_DEFINE0(rt_sigreturn) if (restore_altstack(&frame->uc.uc_stack)) goto badframe; + regs->cause = -1UL; + return regs->a0; badframe: @@ -139,12 +274,23 @@ static long setup_sigcontext(struct rt_sigframe __user *frame, struct pt_regs *regs) { struct sigcontext __user *sc = &frame->uc.uc_mcontext; + struct __riscv_ctx_hdr __user *sc_ext_ptr = &sc->sc_extdesc.hdr; long err; + /* sc_regs is structured the same as the start of pt_regs */ err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs)); /* Save the floating-point state. */ - if (has_fpu) + if (has_fpu()) err |= save_fp_state(regs, &sc->sc_fpregs); + /* Save the vector state. */ + if (has_vector() && 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); + /* And put END __riscv_ctx_hdr at the end. */ + err |= __put_user(END_MAGIC, &sc_ext_ptr->magic); + err |= __put_user(END_HDR_SIZE, &sc_ext_ptr->size); + return err; } @@ -176,9 +322,11 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, { struct rt_sigframe __user *frame; long err = 0; + unsigned long __maybe_unused addr; + size_t frame_size = get_rt_frame_size(false); - frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(frame, sizeof(*frame))) + frame = get_sigframe(ksig, regs, frame_size); + if (!access_ok(frame, frame_size)) return -EFAULT; err |= copy_siginfo_to_user(&frame->info, &ksig->info); @@ -204,7 +352,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn, sizeof(frame->sigreturn_code))) return -EFAULT; - regs->ra = (unsigned long)&frame->sigreturn_code; + + addr = (unsigned long)&frame->sigreturn_code; + /* Make sure the two instructions are pushed to icache. */ + flush_icache_range(addr, addr + sizeof(frame->sigreturn_code)); + + regs->ra = addr; #endif /* CONFIG_MMU */ /* @@ -234,87 +387,102 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) sigset_t *oldset = sigmask_to_save(); int ret; - /* Are we from a system call? */ - if (regs->cause == EXC_SYSCALL) { - /* Avoid additional syscall restarting via ret_from_exception */ - regs->cause = -1UL; - /* If so, check system call restarting.. */ - switch (regs->a0) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - regs->a0 = -EINTR; - break; - - case -ERESTARTSYS: - if (!(ksig->ka.sa.sa_flags & SA_RESTART)) { - regs->a0 = -EINTR; - break; - } - /* fallthrough */ - case -ERESTARTNOINTR: - regs->a0 = regs->orig_a0; - regs->epc -= 0x4; - break; - } - } + rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ - ret = setup_rt_frame(ksig, oldset, regs); + if (is_compat_task()) + ret = compat_setup_rt_frame(ksig, oldset, regs); + else + ret = setup_rt_frame(ksig, oldset, regs); signal_setup_done(ret, ksig, 0); } -static void do_signal(struct pt_regs *regs) +void arch_do_signal_or_restart(struct pt_regs *regs) { + unsigned long continue_addr = 0, restart_addr = 0; + int retval = 0; struct ksignal ksig; + bool syscall = (regs->cause == EXC_SYSCALL); - if (get_signal(&ksig)) { - /* Actually deliver the signal */ - handle_signal(&ksig, regs); - return; - } + /* If we were from a system call, check for system call restarting */ + if (syscall) { + continue_addr = regs->epc; + restart_addr = continue_addr - 4; + retval = regs->a0; - /* Did we come from a system call? */ - if (regs->cause == EXC_SYSCALL) { /* Avoid additional syscall restarting via ret_from_exception */ regs->cause = -1UL; - /* Restart the system call - no handlers present */ - switch (regs->a0) { + /* + * Prepare for system call restart. We do this here so that a + * debugger will see the already changed PC. + */ + switch (retval) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: - regs->a0 = regs->orig_a0; - regs->epc -= 0x4; - break; case -ERESTART_RESTARTBLOCK: - regs->a0 = regs->orig_a0; - regs->a7 = __NR_restart_syscall; - regs->epc -= 0x4; + regs->a0 = regs->orig_a0; + regs->epc = restart_addr; break; } } /* + * Get the signal to deliver. When running under ptrace, at this point + * the debugger may change all of our registers. + */ + if (get_signal(&ksig)) { + /* + * Depending on the signal settings, we may need to revert the + * decision to restart the system call, but skip this if a + * debugger has chosen to restart at a different PC. + */ + if (regs->epc == restart_addr && + (retval == -ERESTARTNOHAND || + retval == -ERESTART_RESTARTBLOCK || + (retval == -ERESTARTSYS && + !(ksig.ka.sa.sa_flags & SA_RESTART)))) { + regs->a0 = -EINTR; + regs->epc = continue_addr; + } + + /* Actually deliver the signal */ + handle_signal(&ksig, regs); + return; + } + + /* + * Handle restarting a different system call. As above, if a debugger + * has chosen to restart at a different PC, ignore the restart. + */ + if (syscall && regs->epc == restart_addr && retval == -ERESTART_RESTARTBLOCK) + regs->a7 = __NR_restart_syscall; + + /* * If there is no signal to deliver, we just put the saved * sigmask back. */ restore_saved_sigmask(); } -/* - * notification of userspace execution resumption - * - triggered by the _TIF_WORK_MASK flags - */ -asmlinkage __visible void do_notify_resume(struct pt_regs *regs, - unsigned long thread_info_flags) +void init_rt_signal_env(void); +void __init init_rt_signal_env(void) { - /* Handle pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs); + riscv_v_sc_size = sizeof(struct __riscv_ctx_hdr) + + sizeof(struct __sc_riscv_v_state) + riscv_v_vsize; + /* + * Determine the stack space required for guaranteed signal delivery. + * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry + * in the auxiliary array at process startup. + */ + signal_minsigstksz = get_rt_frame_size(true); +} - if (thread_info_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(regs); - } +#ifdef CONFIG_DYNAMIC_SIGFRAME +bool sigaltstack_size_valid(size_t ss_size) +{ + return ss_size > get_rt_frame_size(false); } +#endif /* CONFIG_DYNAMIC_SIGFRAME */ diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index eb878abcaaf8..45dd4035416e 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -9,26 +9,34 @@ */ #include <linux/cpu.h> +#include <linux/clockchips.h> #include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/kexec.h> +#include <linux/percpu.h> #include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/delay.h> +#include <linux/irq.h> +#include <linux/irq_work.h> -#include <asm/clint.h> -#include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> +#include <asm/cpu_ops.h> enum ipi_message_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, + IPI_IRQ_WORK, + IPI_TIMER, IPI_MAX }; -unsigned long __cpuid_to_hartid_map[NR_CPUS] = { +unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = INVALID_HARTID }; @@ -37,13 +45,12 @@ void __init smp_setup_processor_id(void) cpuid_to_hartid_map(0) = boot_cpu_hartid; } -/* A collection of single bit ipi messages. */ -static struct { - unsigned long stats[IPI_MAX] ____cacheline_aligned; - unsigned long bits ____cacheline_aligned; -} ipi_data[NR_CPUS] __cacheline_aligned; +static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev); +static int ipi_virq_base __ro_after_init; +static int nr_ipi __ro_after_init = IPI_MAX; +static struct irq_desc *ipi_desc[IPI_MAX] __read_mostly; -int riscv_hartid_to_cpuid(int hartid) +int riscv_hartid_to_cpuid(unsigned long hartid) { int i; @@ -51,119 +58,160 @@ int riscv_hartid_to_cpuid(int hartid) if (cpuid_to_hartid_map(i) == hartid) return i; - pr_err("Couldn't find cpu id for hartid [%d]\n", hartid); - return i; + return -ENOENT; } -void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out) +static void ipi_stop(void) { - int cpu; - - cpumask_clear(out); - for_each_cpu(cpu, in) - cpumask_set_cpu(cpuid_to_hartid_map(cpu), out); + set_cpu_online(smp_processor_id(), false); + while (1) + wait_for_interrupt(); } -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +#ifdef CONFIG_KEXEC_CORE +static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); + +static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) { - return phys_id == cpuid_to_hartid_map(cpu); + crash_save_cpu(regs, cpu); + + atomic_dec(&waiting_for_crash_ipi); + + local_irq_disable(); + +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_has_hotplug(cpu)) + cpu_ops->cpu_stop(); +#endif + + for(;;) + wait_for_interrupt(); +} +#else +static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ + unreachable(); } +#endif -/* Unsupported */ -int setup_profiling_timer(unsigned int multiplier) +static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) { - return -EINVAL; + __ipi_send_mask(ipi_desc[op], mask); } -static void ipi_stop(void) +static void send_ipi_single(int cpu, enum ipi_message_type op) { - set_cpu_online(smp_processor_id(), false); - while (1) - wait_for_interrupt(); + __ipi_send_mask(ipi_desc[op], cpumask_of(cpu)); } -static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) { - struct cpumask hartid_mask; - int cpu; + send_ipi_single(smp_processor_id(), IPI_IRQ_WORK); +} +#endif - smp_mb__before_atomic(); - for_each_cpu(cpu, mask) - set_bit(op, &ipi_data[cpu].bits); - smp_mb__after_atomic(); +static irqreturn_t handle_IPI(int irq, void *data) +{ + int ipi = irq - ipi_virq_base; + + switch (ipi) { + case IPI_RESCHEDULE: + scheduler_ipi(); + break; + case IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; + case IPI_CPU_STOP: + ipi_stop(); + break; + case IPI_CPU_CRASH_STOP: + ipi_cpu_crash_stop(smp_processor_id(), get_irq_regs()); + break; + case IPI_IRQ_WORK: + irq_work_run(); + break; +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + case IPI_TIMER: + tick_receive_broadcast(); + break; +#endif + default: + pr_warn("CPU%d: unhandled IPI%d\n", smp_processor_id(), ipi); + break; + } - riscv_cpuid_to_hartid_mask(mask, &hartid_mask); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(&hartid_mask)); - else - clint_send_ipi_mask(&hartid_mask); + return IRQ_HANDLED; } -static void send_ipi_single(int cpu, enum ipi_message_type op) +void riscv_ipi_enable(void) { - int hartid = cpuid_to_hartid_map(cpu); + int i; - smp_mb__before_atomic(); - set_bit(op, &ipi_data[cpu].bits); - smp_mb__after_atomic(); + if (WARN_ON_ONCE(!ipi_virq_base)) + return; - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(cpumask_of(hartid))); - else - clint_send_ipi_single(hartid); + for (i = 0; i < nr_ipi; i++) + enable_percpu_irq(ipi_virq_base + i, 0); } -static inline void clear_ipi(void) +void riscv_ipi_disable(void) { - if (IS_ENABLED(CONFIG_RISCV_SBI)) - csr_clear(CSR_IP, IE_SIE); - else - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + int i; + + if (WARN_ON_ONCE(!ipi_virq_base)) + return; + + for (i = 0; i < nr_ipi; i++) + disable_percpu_irq(ipi_virq_base + i); } -void riscv_software_interrupt(void) +bool riscv_ipi_have_virq_range(void) { - unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits; - unsigned long *stats = ipi_data[smp_processor_id()].stats; - - clear_ipi(); + return (ipi_virq_base) ? true : false; +} - while (true) { - unsigned long ops; +DEFINE_STATIC_KEY_FALSE(riscv_ipi_for_rfence); +EXPORT_SYMBOL_GPL(riscv_ipi_for_rfence); - /* Order bit clearing and data access. */ - mb(); +void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence) +{ + int i, err; - ops = xchg(pending_ipis, 0); - if (ops == 0) - return; + if (WARN_ON(ipi_virq_base)) + return; - if (ops & (1 << IPI_RESCHEDULE)) { - stats[IPI_RESCHEDULE]++; - scheduler_ipi(); - } + WARN_ON(nr < IPI_MAX); + nr_ipi = min(nr, IPI_MAX); + ipi_virq_base = virq; - if (ops & (1 << IPI_CALL_FUNC)) { - stats[IPI_CALL_FUNC]++; - generic_smp_call_function_interrupt(); - } + /* Request IPIs */ + for (i = 0; i < nr_ipi; i++) { + err = request_percpu_irq(ipi_virq_base + i, handle_IPI, + "IPI", &ipi_dummy_dev); + WARN_ON(err); - if (ops & (1 << IPI_CPU_STOP)) { - stats[IPI_CPU_STOP]++; - ipi_stop(); - } + ipi_desc[i] = irq_to_desc(ipi_virq_base + i); + irq_set_status_flags(ipi_virq_base + i, IRQ_HIDDEN); + } - BUG_ON((ops >> IPI_MAX) != 0); + /* Enabled IPIs for boot CPU immediately */ + riscv_ipi_enable(); - /* Order data access and bit testing. */ - mb(); - } + /* Update RFENCE static key */ + if (use_for_rfence) + static_branch_enable(&riscv_ipi_for_rfence); + else + static_branch_disable(&riscv_ipi_for_rfence); } static const char * const ipi_names[] = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNC] = "Function call interrupts", [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", }; void show_ipi_stats(struct seq_file *p, int prec) @@ -174,7 +222,7 @@ void show_ipi_stats(struct seq_file *p, int prec) seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : ""); for_each_online_cpu(cpu) - seq_printf(p, "%10lu ", ipi_data[cpu].stats[i]); + seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu)); seq_printf(p, " %s\n", ipi_names[i]); } } @@ -189,6 +237,13 @@ void arch_send_call_function_single_ipi(int cpu) send_ipi_single(cpu, IPI_CALL_FUNC); } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void tick_broadcast(const struct cpumask *mask) +{ + send_ipi_mask(mask, IPI_TIMER); +} +#endif + void smp_send_stop(void) { unsigned long timeout; @@ -214,8 +269,66 @@ void smp_send_stop(void) cpumask_pr_args(cpu_online_mask)); } -void smp_send_reschedule(int cpu) +#ifdef CONFIG_KEXEC_CORE +/* + * The number of CPUs online, not counting this CPU (which may not be + * fully online and so not counted in num_online_cpus()). + */ +static inline unsigned int num_other_online_cpus(void) +{ + unsigned int this_cpu_online = cpu_online(smp_processor_id()); + + return num_online_cpus() - this_cpu_online; +} + +void crash_smp_send_stop(void) +{ + static int cpus_stopped; + cpumask_t mask; + unsigned long timeout; + + /* + * This function can be called twice in panic path, but obviously + * we execute this only once. + */ + if (cpus_stopped) + return; + + cpus_stopped = 1; + + /* + * If this cpu is the only one alive at this point in time, online or + * not, there are no stop messages to be sent around, so just back out. + */ + if (num_other_online_cpus() == 0) + return; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); + + pr_crit("SMP: stopping secondary CPUs\n"); + send_ipi_mask(&mask, IPI_CPU_CRASH_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + udelay(1); + + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(&mask)); +} + +bool smp_crash_stop_failed(void) +{ + return (atomic_read(&waiting_for_crash_ipi) > 0); +} +#endif + +void arch_smp_send_reschedule(int cpu) { send_ipi_single(cpu, IPI_RESCHEDULE); } -EXPORT_SYMBOL_GPL(smp_send_reschedule); +EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 8bc01f0ca73b..519b6bd946e5 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -8,6 +8,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> #include <linux/arch_topology.h> #include <linux/module.h> #include <linux/init.h> @@ -24,64 +25,133 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> -#include <asm/clint.h> + +#include <asm/cpufeature.h> +#include <asm/cpu_ops.h> +#include <asm/cpufeature.h> #include <asm/irq.h> #include <asm/mmu_context.h> +#include <asm/numa.h> #include <asm/tlbflush.h> #include <asm/sections.h> -#include <asm/sbi.h> #include <asm/smp.h> +#include <uapi/asm/hwcap.h> +#include <asm/vector.h> #include "head.h" -void *__cpu_up_stack_pointer[NR_CPUS]; -void *__cpu_up_task_pointer[NR_CPUS]; static DECLARE_COMPLETION(cpu_running); void __init smp_prepare_boot_cpu(void) { - init_cpu_topology(); } void __init smp_prepare_cpus(unsigned int max_cpus) { int cpuid; + unsigned int curr_cpuid; + + init_cpu_topology(); + + curr_cpuid = smp_processor_id(); + store_cpu_topology(curr_cpuid); + numa_store_cpu_info(curr_cpuid); + numa_add_cpu(curr_cpuid); /* This covers non-smp usecase mandated by "nosmp" option */ if (max_cpus == 0) return; for_each_possible_cpu(cpuid) { - if (cpuid == smp_processor_id()) + if (cpuid == curr_cpuid) continue; set_cpu_present(cpuid, true); + numa_store_cpu_info(cpuid); } } -void __init setup_smp(void) +#ifdef CONFIG_ACPI +static unsigned int cpu_count = 1; + +static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const unsigned long end) +{ + unsigned long hart; + static bool found_boot_cpu; + struct acpi_madt_rintc *processor = (struct acpi_madt_rintc *)header; + + /* + * Each RINTC structure in MADT will have a flag. If ACPI_MADT_ENABLED + * bit in the flag is not enabled, it means OS should not try to enable + * the cpu to which RINTC belongs. + */ + if (!(processor->flags & ACPI_MADT_ENABLED)) + return 0; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + hart = processor->hart_id; + if (hart == INVALID_HARTID) { + pr_warn("Invalid hartid\n"); + return 0; + } + + if (hart == cpuid_to_hartid_map(0)) { + BUG_ON(found_boot_cpu); + found_boot_cpu = true; + early_map_cpu_to_node(0, acpi_numa_get_nid(cpu_count)); + return 0; + } + + if (cpu_count >= NR_CPUS) { + pr_warn("NR_CPUS is too small for the number of ACPI tables.\n"); + return 0; + } + + cpuid_to_hartid_map(cpu_count) = hart; + early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count)); + cpu_count++; + + return 0; +} + +static void __init acpi_parse_and_init_cpus(void) +{ + acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0); +} +#else +#define acpi_parse_and_init_cpus(...) do { } while (0) +#endif + +static void __init of_parse_and_init_cpus(void) { struct device_node *dn; - int hart; + unsigned long hart; bool found_boot_cpu = false; int cpuid = 1; + int rc; for_each_of_cpu_node(dn) { - hart = riscv_of_processor_hartid(dn); - if (hart < 0) + rc = riscv_early_of_processor_hartid(dn, &hart); + if (rc < 0) continue; if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = 1; + early_map_cpu_to_node(0, of_node_to_nid(dn)); continue; } if (cpuid >= NR_CPUS) { - pr_warn("Invalid cpuid [%d] for hartid [%d]\n", + pr_warn("Invalid cpuid [%d] for hartid [%lu]\n", cpuid, hart); - break; + continue; } cpuid_to_hartid_map(cpuid) = hart; + early_map_cpu_to_node(cpuid, of_node_to_nid(dn)); cpuid++; } @@ -90,38 +160,48 @@ void __init setup_smp(void) if (cpuid > nr_cpu_ids) pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n", cpuid, nr_cpu_ids); +} + +void __init setup_smp(void) +{ + int cpuid; - for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) { + cpu_set_ops(); + + if (acpi_disabled) + of_parse_and_init_cpus(); + else + acpi_parse_and_init_cpus(); + + for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) set_cpu_possible(cpuid, true); - } +} + +static int start_secondary_cpu(int cpu, struct task_struct *tidle) +{ + if (cpu_ops->cpu_start) + return cpu_ops->cpu_start(cpu, tidle); + + return -EOPNOTSUPP; } int __cpu_up(unsigned int cpu, struct task_struct *tidle) { int ret = 0; - int hartid = cpuid_to_hartid_map(cpu); tidle->thread_info.cpu = cpu; - /* - * On RISC-V systems, all harts boot on their own accord. Our _start - * selects the first hart to boot the kernel and causes the remainder - * of the harts to spin in a loop waiting for their stack pointer to be - * setup by that main hart. Writing __cpu_up_stack_pointer signals to - * the spinning harts that they can continue the boot process. - */ - smp_mb(); - WRITE_ONCE(__cpu_up_stack_pointer[hartid], - task_stack_page(tidle) + THREAD_SIZE); - WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle); - - lockdep_assert_held(&cpu_running); - wait_for_completion_timeout(&cpu_running, + ret = start_secondary_cpu(cpu, tidle); + if (!ret) { + wait_for_completion_timeout(&cpu_running, msecs_to_jiffies(1000)); - if (!cpu_online(cpu)) { - pr_crit("CPU%u: failed to come online\n", cpu); - ret = -EIO; + if (!cpu_online(cpu)) { + pr_crit("CPU%u: failed to come online\n", cpu); + ret = -EIO; + } + } else { + pr_crit("CPU%u: failed to start\n", cpu); } return ret; @@ -134,21 +214,30 @@ void __init smp_cpus_done(unsigned int max_cpus) /* * C entry point for a secondary processor. */ -asmlinkage __visible void __init smp_callin(void) +asmlinkage __visible void smp_callin(void) { struct mm_struct *mm = &init_mm; - - if (!IS_ENABLED(CONFIG_RISCV_SBI)) - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + unsigned int curr_cpuid = smp_processor_id(); /* All kernel threads share the same mm context. */ mmgrab(mm); current->active_mm = mm; - trap_init(); - notify_cpu_starting(smp_processor_id()); - update_siblings_masks(smp_processor_id()); - set_cpu_online(smp_processor_id(), 1); + store_cpu_topology(curr_cpuid); + notify_cpu_starting(curr_cpuid); + + riscv_ipi_enable(); + + numa_add_cpu(curr_cpuid); + set_cpu_online(curr_cpuid, 1); + + if (has_vector()) { + if (riscv_v_setup_vsize()) + elf_hwcap &= ~COMPAT_HWCAP_ISA_V; + } + + riscv_user_isa_enable(); + /* * Remote TLB flushes are ignored while the CPU is offline, so emit * a local TLB flush right now just in case. @@ -159,7 +248,6 @@ asmlinkage __visible void __init smp_callin(void) * Disable preemption before enabling interrupts, so we don't try to * schedule a CPU that hasn't actually started yet. */ - preempt_disable(); local_irq_enable(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c new file mode 100644 index 000000000000..a0516172a33c --- /dev/null +++ b/arch/riscv/kernel/soc.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#include <linux/init.h> +#include <linux/libfdt.h> +#include <linux/pgtable.h> +#include <asm/soc.h> + +/* + * This is called extremly early, before parse_dtb(), to allow initializing + * SoC hardware before memory or any device driver initialization. + */ +void __init soc_early_init(void) +{ + void (*early_fn)(const void *fdt); + const struct of_device_id *s; + const void *fdt = dtb_early_va; + + for (s = (void *)&__soc_early_init_table_start; + (void *)s < (void *)&__soc_early_init_table_end; s++) { + if (!fdt_node_check_compatible(fdt, 0, s->compatible)) { + early_fn = s->data; + early_fn(fdt); + return; + } + } +} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 0940681d2f68..64a9c093aef9 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -12,27 +12,27 @@ #include <linux/stacktrace.h> #include <linux/ftrace.h> +#include <asm/stacktrace.h> + #ifdef CONFIG_FRAME_POINTER -struct stackframe { - unsigned long fp; - unsigned long ra; -}; +extern asmlinkage void ret_from_exception(void); void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, - bool (*fn)(unsigned long, void *), void *arg) + bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; + int level = 0; if (regs) { fp = frame_pointer(regs); sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp __asm__ ("sp"); fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = current_stack_pointer; pc = (unsigned long)walk_stackframe; + level = -1; } else { /* task blocked in __switch_to */ fp = task->thread.s[0]; @@ -44,7 +44,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, unsigned long low, high; struct stackframe *frame; - if (unlikely(!__kernel_text_address(pc) || fn(pc, arg))) + if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc)))) break; /* Validate frame pointer */ @@ -55,16 +55,29 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, /* Unwind stack frame */ frame = (struct stackframe *)fp - 1; sp = fp; - fp = frame->fp; - pc = ftrace_graph_ret_addr(current, NULL, frame->ra, - (unsigned long *)(fp - 8)); + if (regs && (regs->epc == pc) && (frame->fp & 0x7)) { + fp = frame->ra; + pc = regs->ra; + } else { + fp = frame->fp; + pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + &frame->ra); + if (pc == (unsigned long)ret_from_exception) { + if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) + break; + + pc = ((struct pt_regs *)sp)->epc; + fp = ((struct pt_regs *)sp)->s0; + } + } + } } #else /* !CONFIG_FRAME_POINTER */ -static void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) +void notrace walk_stackframe(struct task_struct *task, + struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long sp, pc; unsigned long *ksp; @@ -73,8 +86,7 @@ static void notrace walk_stackframe(struct task_struct *task, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp __asm__ ("sp"); - sp = current_sp; + sp = current_stack_pointer; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ @@ -87,83 +99,57 @@ static void notrace walk_stackframe(struct task_struct *task, ksp = (unsigned long *)sp; while (!kstack_end(ksp)) { - if (__kernel_text_address(pc) && unlikely(fn(pc, arg))) + if (__kernel_text_address(pc) && unlikely(!fn(arg, pc))) break; - pc = (*ksp++) - 0x4; + pc = READ_ONCE_NOCHECK(*ksp++) - 0x4; } } #endif /* CONFIG_FRAME_POINTER */ - -static bool print_trace_address(unsigned long pc, void *arg) +static bool print_trace_address(void *arg, unsigned long pc) { - print_ip_sym(pc); - return false; + const char *loglvl = arg; + + print_ip_sym(loglvl, pc); + return true; } -void show_stack(struct task_struct *task, unsigned long *sp) +noinline void dump_backtrace(struct pt_regs *regs, struct task_struct *task, + const char *loglvl) { - pr_cont("Call Trace:\n"); - walk_stackframe(task, NULL, print_trace_address, NULL); + walk_stackframe(task, regs, print_trace_address, (void *)loglvl); } +void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) +{ + pr_cont("%sCall Trace:\n", loglvl); + dump_backtrace(NULL, task, loglvl); +} -static bool save_wchan(unsigned long pc, void *arg) +static bool save_wchan(void *arg, unsigned long pc) { if (!in_sched_functions(pc)) { unsigned long *p = arg; *p = pc; - return true; + return false; } - return false; + return true; } -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc = 0; - if (likely(task && task != current && task->state != TASK_RUNNING)) - walk_stackframe(task, NULL, save_wchan, &pc); + if (!try_get_task_stack(task)) + return 0; + walk_stackframe(task, NULL, save_wchan, &pc); + put_task_stack(task); return pc; } - -#ifdef CONFIG_STACKTRACE - -static bool __save_trace(unsigned long pc, void *arg, bool nosched) -{ - struct stack_trace *trace = arg; - - if (unlikely(nosched && in_sched_functions(pc))) - return false; - if (unlikely(trace->skip > 0)) { - trace->skip--; - return false; - } - - trace->entries[trace->nr_entries++] = pc; - return (trace->nr_entries >= trace->max_entries); -} - -static bool save_trace(unsigned long pc, void *arg) +noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) { - return __save_trace(pc, arg, false); + walk_stackframe(task, regs, consume_entry, cookie); } - -/* - * Save stack-backtrace addresses into a stack_trace buffer. - */ -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) -{ - walk_stackframe(tsk, NULL, save_trace, trace); -} -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); - -void save_stack_trace(struct stack_trace *trace) -{ - save_stack_trace_tsk(NULL, trace); -} -EXPORT_SYMBOL_GPL(save_stack_trace); - -#endif /* CONFIG_STACKTRACE */ diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c new file mode 100644 index 000000000000..239509367e42 --- /dev/null +++ b/arch/riscv/kernel/suspend.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "suspend: " fmt + +#include <linux/ftrace.h> +#include <linux/suspend.h> +#include <asm/csr.h> +#include <asm/sbi.h> +#include <asm/suspend.h> + +void suspend_save_csrs(struct suspend_context *context) +{ + context->scratch = csr_read(CSR_SCRATCH); + context->tvec = csr_read(CSR_TVEC); + context->ie = csr_read(CSR_IE); + + /* + * No need to save/restore IP CSR (i.e. MIP or SIP) because: + * + * 1. For no-MMU (M-mode) kernel, the bits in MIP are set by + * external devices (such as interrupt controller, timer, etc). + * 2. For MMU (S-mode) kernel, the bits in SIP are set by + * M-mode firmware and external devices (such as interrupt + * controller, etc). + */ + +#ifdef CONFIG_MMU + context->satp = csr_read(CSR_SATP); +#endif +} + +void suspend_restore_csrs(struct suspend_context *context) +{ + csr_write(CSR_SCRATCH, context->scratch); + csr_write(CSR_TVEC, context->tvec); + csr_write(CSR_IE, context->ie); + +#ifdef CONFIG_MMU + csr_write(CSR_SATP, context->satp); +#endif +} + +int cpu_suspend(unsigned long arg, + int (*finish)(unsigned long arg, + unsigned long entry, + unsigned long context)) +{ + int rc = 0; + struct suspend_context context = { 0 }; + + /* Finisher should be non-NULL */ + if (!finish) + return -EINVAL; + + /* Save additional CSRs*/ + suspend_save_csrs(&context); + + /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka finishers) hence disable + * graph tracing during their execution. + */ + pause_graph_tracing(); + + /* Save context on stack */ + if (__cpu_suspend_enter(&context)) { + /* Call the finisher */ + rc = finish(arg, __pa_symbol(__cpu_resume_enter), + (ulong)&context); + + /* + * Should never reach here, unless the suspend finisher + * fails. Successful cpu_suspend() should return from + * __cpu_resume_entry() + */ + if (!rc) + rc = -EOPNOTSUPP; + } + + /* Enable function graph tracer */ + unpause_graph_tracing(); + + /* Restore additional CSRs */ + suspend_restore_csrs(&context); + + return rc; +} + +#ifdef CONFIG_RISCV_SBI +static int sbi_system_suspend(unsigned long sleep_type, + unsigned long resume_addr, + unsigned long opaque) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND, + sleep_type, resume_addr, opaque, 0, 0, 0); + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + + return ret.value; +} + +static int sbi_system_suspend_enter(suspend_state_t state) +{ + return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend); +} + +static const struct platform_suspend_ops sbi_system_suspend_ops = { + .valid = suspend_valid_only_mem, + .enter = sbi_system_suspend_enter, +}; + +static int __init sbi_system_suspend_init(void) +{ + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_SUSP) > 0) { + pr_info("SBI SUSP extension detected\n"); + if (IS_ENABLED(CONFIG_SUSPEND)) + suspend_set_ops(&sbi_system_suspend_ops); + } + + return 0; +} + +arch_initcall(sbi_system_suspend_init); +#endif /* CONFIG_RISCV_SBI */ diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S new file mode 100644 index 000000000000..2d54f309c140 --- /dev/null +++ b/arch/riscv/kernel/suspend_entry.S @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include <linux/linkage.h> +#include <linux/cfi_types.h> +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> +#include <asm/csr.h> +#include <asm/xip_fixup.h> + + .text + .altmacro + .option norelax + +SYM_FUNC_START(__cpu_suspend_enter) + /* Save registers (except A0 and T0-T6) */ + REG_S ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) + REG_S sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) + REG_S gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) + REG_S tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) + REG_S s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) + REG_S s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) + REG_S a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) + REG_S a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) + REG_S a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) + REG_S a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) + REG_S a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) + REG_S a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) + REG_S a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) + REG_S s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) + REG_S s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) + REG_S s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) + REG_S s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) + REG_S s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) + REG_S s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) + REG_S s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) + REG_S s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) + REG_S s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) + REG_S s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + + /* Save CSRs */ + csrr t0, CSR_EPC + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) + csrr t0, CSR_STATUS + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) + csrr t0, CSR_TVAL + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) + csrr t0, CSR_CAUSE + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) + + /* Return non-zero value */ + li a0, 1 + + /* Return to C code */ + ret +SYM_FUNC_END(__cpu_suspend_enter) + +SYM_TYPED_FUNC_START(__cpu_resume_enter) + /* Load the global pointer */ + load_global_pointer + +#ifdef CONFIG_MMU + /* Save A0 and A1 */ + add t0, a0, zero + add t1, a1, zero + + /* Enable MMU */ + la a0, swapper_pg_dir + XIP_FIXUP_OFFSET a0 + call relocate_enable_mmu + + /* Restore A0 and A1 */ + add a0, t0, zero + add a1, t1, zero +#endif + + /* Make A0 point to suspend context */ + add a0, a1, zero + + /* Restore CSRs */ + suspend_restore_csrs + + /* Restore registers (except A0 and T0-T6) */ + suspend_restore_regs + + /* Return zero value */ + add a0, zero, zero + + /* Return to C code */ + ret +SYM_FUNC_END(__cpu_resume_enter) diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c new file mode 100644 index 000000000000..a7c56b41efd2 --- /dev/null +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -0,0 +1,411 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * The hwprobe interface, for allowing userspace to probe to see which features + * are supported by the hardware. See Documentation/arch/riscv/hwprobe.rst for + * more details. + */ +#include <linux/syscalls.h> +#include <asm/cacheflush.h> +#include <asm/cpufeature.h> +#include <asm/hwprobe.h> +#include <asm/sbi.h> +#include <asm/switch_to.h> +#include <asm/uaccess.h> +#include <asm/unistd.h> +#include <asm/vector.h> +#include <vdso/vsyscall.h> + + +static void hwprobe_arch_id(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + u64 id = -1ULL; + bool first = true; + int cpu; + + for_each_cpu(cpu, cpus) { + u64 cpu_id; + + switch (pair->key) { + case RISCV_HWPROBE_KEY_MVENDORID: + cpu_id = riscv_cached_mvendorid(cpu); + break; + case RISCV_HWPROBE_KEY_MIMPID: + cpu_id = riscv_cached_mimpid(cpu); + break; + case RISCV_HWPROBE_KEY_MARCHID: + cpu_id = riscv_cached_marchid(cpu); + break; + } + + if (first) { + id = cpu_id; + first = false; + } + + /* + * If there's a mismatch for the given set, return -1 in the + * value. + */ + if (id != cpu_id) { + id = -1ULL; + break; + } + } + + pair->value = id; +} + +static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + int cpu; + u64 missing = 0; + + pair->value = 0; + if (has_fpu()) + pair->value |= RISCV_HWPROBE_IMA_FD; + + if (riscv_isa_extension_available(NULL, c)) + pair->value |= RISCV_HWPROBE_IMA_C; + + if (has_vector()) + pair->value |= RISCV_HWPROBE_IMA_V; + + /* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + */ + for_each_cpu(cpu, cpus) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + +#define EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_EXT_##ext; \ + } while (false) + + /* + * Only use EXT_KEY() for extensions which can be exposed to userspace, + * regardless of the kernel's configuration, as no other checks, besides + * presence in the hart_isa bitmap, are made. + */ + EXT_KEY(ZBA); + EXT_KEY(ZBB); + EXT_KEY(ZBS); + EXT_KEY(ZICBOZ); + EXT_KEY(ZBC); + + EXT_KEY(ZBKB); + EXT_KEY(ZBKC); + EXT_KEY(ZBKX); + EXT_KEY(ZKND); + EXT_KEY(ZKNE); + EXT_KEY(ZKNH); + EXT_KEY(ZKSED); + EXT_KEY(ZKSH); + EXT_KEY(ZKT); + EXT_KEY(ZIHINTNTL); + EXT_KEY(ZTSO); + EXT_KEY(ZACAS); + EXT_KEY(ZICOND); + + if (has_vector()) { + EXT_KEY(ZVBB); + EXT_KEY(ZVBC); + EXT_KEY(ZVKB); + EXT_KEY(ZVKG); + EXT_KEY(ZVKNED); + EXT_KEY(ZVKNHA); + EXT_KEY(ZVKNHB); + EXT_KEY(ZVKSED); + EXT_KEY(ZVKSH); + EXT_KEY(ZVKT); + EXT_KEY(ZVFH); + EXT_KEY(ZVFHMIN); + } + + if (has_fpu()) { + EXT_KEY(ZFH); + EXT_KEY(ZFHMIN); + EXT_KEY(ZFA); + } +#undef EXT_KEY + } + + /* Now turn off reporting features if any CPU is missing it. */ + pair->value &= ~missing; +} + +static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext) +{ + struct riscv_hwprobe pair; + + hwprobe_isa_ext0(&pair, cpus); + return (pair.value & ext); +} + +static u64 hwprobe_misaligned(const struct cpumask *cpus) +{ + int cpu; + u64 perf = -1ULL; + + for_each_cpu(cpu, cpus) { + int this_perf = per_cpu(misaligned_access_speed, cpu); + + if (perf == -1ULL) + perf = this_perf; + + if (perf != this_perf) { + perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN; + break; + } + } + + if (perf == -1ULL) + return RISCV_HWPROBE_MISALIGNED_UNKNOWN; + + return perf; +} + +static void hwprobe_one_pair(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + switch (pair->key) { + case RISCV_HWPROBE_KEY_MVENDORID: + case RISCV_HWPROBE_KEY_MARCHID: + case RISCV_HWPROBE_KEY_MIMPID: + hwprobe_arch_id(pair, cpus); + break; + /* + * The kernel already assumes that the base single-letter ISA + * extensions are supported on all harts, and only supports the + * IMA base, so just cheat a bit here and tell that to + * userspace. + */ + case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: + pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA; + break; + + case RISCV_HWPROBE_KEY_IMA_EXT_0: + hwprobe_isa_ext0(pair, cpus); + break; + + case RISCV_HWPROBE_KEY_CPUPERF_0: + pair->value = hwprobe_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; + + /* + * For forward compatibility, unknown keys don't fail the whole + * call, but get their element key set to -1 and value set to 0 + * indicating they're unrecognized. + */ + default: + pair->key = -1; + pair->value = 0; + break; + } +} + +static int hwprobe_get_values(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + size_t out; + int ret; + cpumask_t cpus; + + /* Check the reserved flags. */ + if (flags != 0) + return -EINVAL; + + /* + * The interface supports taking in a CPU mask, and returns values that + * are consistent across that mask. Allow userspace to specify NULL and + * 0 as a shortcut to all online CPUs. + */ + cpumask_clear(&cpus); + if (!cpusetsize && !cpus_user) { + cpumask_copy(&cpus, cpu_online_mask); + } else { + if (cpusetsize > cpumask_size()) + cpusetsize = cpumask_size(); + + ret = copy_from_user(&cpus, cpus_user, cpusetsize); + if (ret) + return -EFAULT; + + /* + * Userspace must provide at least one online CPU, without that + * there's no way to define what is supported. + */ + cpumask_and(&cpus, &cpus, cpu_online_mask); + if (cpumask_empty(&cpus)) + return -EINVAL; + } + + for (out = 0; out < pair_count; out++, pairs++) { + struct riscv_hwprobe pair; + + if (get_user(pair.key, &pairs->key)) + return -EFAULT; + + pair.value = 0; + hwprobe_one_pair(&pair, &cpus); + ret = put_user(pair.key, &pairs->key); + if (ret == 0) + ret = put_user(pair.value, &pairs->value); + + if (ret) + return -EFAULT; + } + + return 0; +} + +static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + cpumask_t cpus, one_cpu; + bool clear_all = false; + size_t i; + int ret; + + if (flags != RISCV_HWPROBE_WHICH_CPUS) + return -EINVAL; + + if (!cpusetsize || !cpus_user) + return -EINVAL; + + if (cpusetsize > cpumask_size()) + cpusetsize = cpumask_size(); + + ret = copy_from_user(&cpus, cpus_user, cpusetsize); + if (ret) + return -EFAULT; + + if (cpumask_empty(&cpus)) + cpumask_copy(&cpus, cpu_online_mask); + + cpumask_and(&cpus, &cpus, cpu_online_mask); + + cpumask_clear(&one_cpu); + + for (i = 0; i < pair_count; i++) { + struct riscv_hwprobe pair, tmp; + int cpu; + + ret = copy_from_user(&pair, &pairs[i], sizeof(pair)); + if (ret) + return -EFAULT; + + if (!riscv_hwprobe_key_is_valid(pair.key)) { + clear_all = true; + pair = (struct riscv_hwprobe){ .key = -1, }; + ret = copy_to_user(&pairs[i], &pair, sizeof(pair)); + if (ret) + return -EFAULT; + } + + if (clear_all) + continue; + + tmp = (struct riscv_hwprobe){ .key = pair.key, }; + + for_each_cpu(cpu, &cpus) { + cpumask_set_cpu(cpu, &one_cpu); + + hwprobe_one_pair(&tmp, &one_cpu); + + if (!riscv_hwprobe_pair_cmp(&tmp, &pair)) + cpumask_clear_cpu(cpu, &cpus); + + cpumask_clear_cpu(cpu, &one_cpu); + } + } + + if (clear_all) + cpumask_clear(&cpus); + + ret = copy_to_user(cpus_user, &cpus, cpusetsize); + if (ret) + return -EFAULT; + + return 0; +} + +static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + if (flags & RISCV_HWPROBE_WHICH_CPUS) + return hwprobe_get_cpus(pairs, pair_count, cpusetsize, + cpus_user, flags); + + return hwprobe_get_values(pairs, pair_count, cpusetsize, + cpus_user, flags); +} + +#ifdef CONFIG_MMU + +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; + u64 id_bitsmash = 0; + struct riscv_hwprobe pair; + int key; + + /* + * Initialize vDSO data with the answers for the "all CPUs" case, to + * save a syscall in the common case. + */ + for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) { + pair.key = key; + hwprobe_one_pair(&pair, cpu_online_mask); + + WARN_ON_ONCE(pair.key < 0); + + avd->all_cpu_hwprobe_values[key] = pair.value; + /* + * Smash together the vendor, arch, and impl IDs to see if + * they're all 0 or any negative. + */ + if (key <= RISCV_HWPROBE_KEY_MIMPID) + id_bitsmash |= pair.value; + } + + /* + * If the arch, vendor, and implementation ID are all the same across + * all harts, then assume all CPUs are the same, and allow the vDSO to + * answer queries for arbitrary masks. However if all values are 0 (not + * populated) or any value returns -1 (varies across CPUs), then the + * vDSO should defer to the kernel for exotic cpu masks. + */ + avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1; + return 0; +} + +arch_initcall_sync(init_hwprobe_vdso_data); + +#endif /* CONFIG_MMU */ + +SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, + size_t, pair_count, size_t, cpusetsize, unsigned long __user *, + cpus, unsigned int, flags) +{ + return do_riscv_hwprobe(pairs, pair_count, cpusetsize, + cpus, flags); +} diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index f3619f59d85c..f1c1416a9f1e 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -6,8 +6,8 @@ */ #include <linux/syscalls.h> -#include <asm/unistd.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h> static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -16,6 +16,7 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, { if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } @@ -27,7 +28,9 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, { return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0); } -#else +#endif + +#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) @@ -38,7 +41,7 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, */ return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12); } -#endif /* !CONFIG_64BIT */ +#endif /* * Allows the instruction cache to be flushed from userspace. Despite RISC-V @@ -65,3 +68,9 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, return 0; } + +/* Not defined using SYSCALL_DEFINE0 to avoid error injection */ +asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused) +{ + return -ENOSYS; +} diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c index f1ead9df96ca..dda913764903 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -7,13 +7,16 @@ #include <linux/linkage.h> #include <linux/syscalls.h> #include <asm-generic/syscalls.h> -#include <asm/vdso.h> #include <asm/syscall.h> #undef __SYSCALL -#define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL(nr, call) asmlinkage long __riscv_##call(const struct pt_regs *); +#include <asm/unistd.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = __riscv_##call, -void *sys_call_table[__NR_syscalls] = { - [0 ... __NR_syscalls - 1] = sys_ni_syscall, +void * const sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug new file mode 100644 index 000000000000..5dba64e8e977 --- /dev/null +++ b/arch/riscv/kernel/tests/Kconfig.debug @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "arch/riscv/kernel Testing and Coverage" + +config AS_HAS_ULEB128 + def_bool $(as-instr,.reloc label$(comma) R_RISCV_SET_ULEB128$(comma) 127\n.reloc label$(comma) R_RISCV_SUB_ULEB128$(comma) 127\nlabel:\n.word 0) + +menuconfig RUNTIME_KERNEL_TESTING_MENU + bool "arch/riscv/kernel runtime Testing" + def_bool y + help + Enable riscv kernel runtime testing. + +if RUNTIME_KERNEL_TESTING_MENU + +config RISCV_MODULE_LINKING_KUNIT + bool "KUnit test riscv module linking at runtime" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this option to test riscv module linking at boot. This will + enable a module called "test_module_linking". + + KUnit tests run during boot and output the results to the debug log + in TAP format (http://testanything.org/). Only useful for kernel devs + running the KUnit test harness, and not intended for inclusion into a + production build. + + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + +endif # RUNTIME_TESTING_MENU + +endmenu # "arch/riscv/kernel runtime Testing" diff --git a/arch/riscv/kernel/tests/Makefile b/arch/riscv/kernel/tests/Makefile new file mode 100644 index 000000000000..7d6c76cffe20 --- /dev/null +++ b/arch/riscv/kernel/tests/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_RISCV_MODULE_LINKING_KUNIT) += module_test/ diff --git a/arch/riscv/kernel/tests/module_test/Makefile b/arch/riscv/kernel/tests/module_test/Makefile new file mode 100644 index 000000000000..d7a6fd8943de --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/Makefile @@ -0,0 +1,15 @@ +obj-m += test_module_linking.o + +test_sub := test_sub6.o test_sub8.o test_sub16.o test_sub32.o test_sub64.o + +test_set := test_set6.o test_set8.o test_set16.o test_set32.o + +test_module_linking-objs += $(test_sub) + +test_module_linking-objs += $(test_set) + +ifeq ($(CONFIG_AS_HAS_ULEB128),y) +test_module_linking-objs += test_uleb128.o +endif + +test_module_linking-objs += test_module_linking_main.o diff --git a/arch/riscv/kernel/tests/module_test/test_module_linking_main.c b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c new file mode 100644 index 000000000000..8df5fa5b834e --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Rivos Inc. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <kunit/test.h> + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test module linking"); + +extern int test_set32(void); +extern int test_set16(void); +extern int test_set8(void); +extern int test_set6(void); +extern long test_sub64(void); +extern int test_sub32(void); +extern int test_sub16(void); +extern int test_sub8(void); +extern int test_sub6(void); + +#ifdef CONFIG_AS_HAS_ULEB128 +extern int test_uleb_basic(void); +extern int test_uleb_large(void); +#endif + +#define CHECK_EQ(lhs, rhs) KUNIT_ASSERT_EQ(test, lhs, rhs) + +void run_test_set(struct kunit *test); +void run_test_sub(struct kunit *test); +void run_test_uleb(struct kunit *test); + +void run_test_set(struct kunit *test) +{ + int val32 = test_set32(); + int val16 = test_set16(); + int val8 = test_set8(); + int val6 = test_set6(); + + CHECK_EQ(val32, 0); + CHECK_EQ(val16, 0); + CHECK_EQ(val8, 0); + CHECK_EQ(val6, 0); +} + +void run_test_sub(struct kunit *test) +{ + int val64 = test_sub64(); + int val32 = test_sub32(); + int val16 = test_sub16(); + int val8 = test_sub8(); + int val6 = test_sub6(); + + CHECK_EQ(val64, 0); + CHECK_EQ(val32, 0); + CHECK_EQ(val16, 0); + CHECK_EQ(val8, 0); + CHECK_EQ(val6, 0); +} + +#ifdef CONFIG_AS_HAS_ULEB128 +void run_test_uleb(struct kunit *test) +{ + int val_uleb = test_uleb_basic(); + int val_uleb2 = test_uleb_large(); + + CHECK_EQ(val_uleb, 0); + CHECK_EQ(val_uleb2, 0); +} +#endif + +static struct kunit_case __refdata riscv_module_linking_test_cases[] = { + KUNIT_CASE(run_test_set), + KUNIT_CASE(run_test_sub), +#ifdef CONFIG_AS_HAS_ULEB128 + KUNIT_CASE(run_test_uleb), +#endif + {} +}; + +static struct kunit_suite riscv_module_linking_test_suite = { + .name = "riscv_checksum", + .test_cases = riscv_module_linking_test_cases, +}; + +kunit_test_suites(&riscv_module_linking_test_suite); diff --git a/arch/riscv/kernel/tests/module_test/test_set16.S b/arch/riscv/kernel/tests/module_test/test_set16.S new file mode 100644 index 000000000000..2be0e441a12e --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set16.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set16 +test_set16: + lw a0, set16 + la t0, set16 +#ifdef CONFIG_32BIT + slli t0, t0, 16 + srli t0, t0, 16 +#else + slli t0, t0, 48 + srli t0, t0, 48 +#endif + sub a0, a0, t0 + ret +.data +set16: + .reloc set16, R_RISCV_SET16, set16 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_set32.S b/arch/riscv/kernel/tests/module_test/test_set32.S new file mode 100644 index 000000000000..de0444537e67 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set32.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set32 +test_set32: + lw a0, set32 + la t0, set32 +#ifndef CONFIG_32BIT + slli t0, t0, 32 + srli t0, t0, 32 +#endif + sub a0, a0, t0 + ret +.data +set32: + .reloc set32, R_RISCV_SET32, set32 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_set6.S b/arch/riscv/kernel/tests/module_test/test_set6.S new file mode 100644 index 000000000000..c39ce4c219eb --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set6.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set6 +test_set6: + lw a0, set6 + la t0, set6 +#ifdef CONFIG_32BIT + slli t0, t0, 26 + srli t0, t0, 26 +#else + slli t0, t0, 58 + srli t0, t0, 58 +#endif + sub a0, a0, t0 + ret +.data +set6: + .reloc set6, R_RISCV_SET6, set6 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_set8.S b/arch/riscv/kernel/tests/module_test/test_set8.S new file mode 100644 index 000000000000..a656173f6f99 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set8.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set8 +test_set8: + lw a0, set8 + la t0, set8 +#ifdef CONFIG_32BIT + slli t0, t0, 24 + srli t0, t0, 24 +#else + slli t0, t0, 56 + srli t0, t0, 56 +#endif + sub a0, a0, t0 + ret +.data +set8: + .reloc set8, R_RISCV_SET8, set8 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub16.S b/arch/riscv/kernel/tests/module_test/test_sub16.S new file mode 100644 index 000000000000..80f731d599ba --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub16.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub16 +test_sub16: + lh a0, sub16 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub16: + .reloc sub16, R_RISCV_ADD16, second + .reloc sub16, R_RISCV_SUB16, first + .half 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub32.S b/arch/riscv/kernel/tests/module_test/test_sub32.S new file mode 100644 index 000000000000..a341686e12df --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub32.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub32 +test_sub32: + lw a0, sub32 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub32: + .reloc sub32, R_RISCV_ADD32, second + .reloc sub32, R_RISCV_SUB32, first + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub6.S b/arch/riscv/kernel/tests/module_test/test_sub6.S new file mode 100644 index 000000000000..e8b61c1ec527 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub6.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub6 +test_sub6: + lb a0, sub6 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub6: + .reloc sub6, R_RISCV_SET6, second + .reloc sub6, R_RISCV_SUB6, first + .byte 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub64.S b/arch/riscv/kernel/tests/module_test/test_sub64.S new file mode 100644 index 000000000000..a59e8afa88fd --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub64.S @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub64 +test_sub64: +#ifdef CONFIG_32BIT + lw a0, sub64 +#else + ld a0, sub64 +#endif + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub64: + .reloc sub64, R_RISCV_ADD64, second + .reloc sub64, R_RISCV_SUB64, first + .word 0 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub8.S b/arch/riscv/kernel/tests/module_test/test_sub8.S new file mode 100644 index 000000000000..ac5d0ec98de3 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub8.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub8 +test_sub8: + lb a0, sub8 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub8: + .reloc sub8, R_RISCV_ADD8, second + .reloc sub8, R_RISCV_SUB8, first + .byte 0 diff --git a/arch/riscv/kernel/tests/module_test/test_uleb128.S b/arch/riscv/kernel/tests/module_test/test_uleb128.S new file mode 100644 index 000000000000..8515ed7cd8c1 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_uleb128.S @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_uleb_basic +test_uleb_basic: + lw a0, second + addi a0, a0, -127 + ret + +.global test_uleb_large +test_uleb_large: + lw a0, fourth + addi a0, a0, -0x07e8 + ret + +.data +first: + .space 127 +second: + .reloc second, R_RISCV_SET_ULEB128, second + .reloc second, R_RISCV_SUB_ULEB128, first + .word 0 +third: + .space 1000 +fourth: + .reloc fourth, R_RISCV_SET_ULEB128, fourth + .reloc fourth, R_RISCV_SUB_ULEB128, third + .word 0 diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 6a53c02e9c73..ba3477197789 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,25 +4,48 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> +#include <linux/of_clk.h> +#include <linux/clockchips.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> #include <asm/processor.h> +#include <asm/timex.h> +#include <asm/paravirt.h> -unsigned long riscv_timebase; +unsigned long riscv_timebase __ro_after_init; EXPORT_SYMBOL_GPL(riscv_timebase); void __init time_init(void) { struct device_node *cpu; + struct acpi_table_rhct *rhct; + acpi_status status; u32 prop; - cpu = of_find_node_by_path("/cpus"); - if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop)) - panic(KERN_WARNING "RISC-V system with no 'timebase-frequency' in DTS\n"); - of_node_put(cpu); - riscv_timebase = prop; + if (acpi_disabled) { + cpu = of_find_node_by_path("/cpus"); + if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop)) + panic("RISC-V system with no 'timebase-frequency' in DTS\n"); + + of_node_put(cpu); + riscv_timebase = prop; + of_clk_init(NULL); + } else { + status = acpi_get_table(ACPI_SIG_RHCT, 0, (struct acpi_table_header **)&rhct); + if (ACPI_FAILURE(status)) + panic("RISC-V ACPI system with no RHCT table\n"); + + riscv_timebase = rhct->time_base_freq; + acpi_put_table((struct acpi_table_header *)rhct); + } lpj_fine = riscv_timebase / HZ; + timer_probe(); + + tick_setup_hrtimer_broadcast(); + + pv_time_init(); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f4cad5163bf2..a1b9be3c4332 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -12,40 +12,94 @@ #include <linux/signal.h> #include <linux/kdebug.h> #include <linux/uaccess.h> +#include <linux/kprobes.h> +#include <linux/uprobes.h> +#include <asm/uprobes.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/irq.h> +#include <linux/kexec.h> +#include <linux/entry-common.h> +#include <asm/asm-prototypes.h> +#include <asm/bug.h> +#include <asm/cfi.h> +#include <asm/csr.h> #include <asm/processor.h> #include <asm/ptrace.h> -#include <asm/csr.h> +#include <asm/syscall.h> +#include <asm/thread_info.h> +#include <asm/vector.h> +#include <asm/irq_stack.h> int show_unhandled_signals = 1; -extern asmlinkage void handle_exception(void); - static DEFINE_SPINLOCK(die_lock); +static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) +{ + const void __user *uaddr = (__force const void __user *)insns; + + if (!user_mode(regs)) + return get_kernel_nofault(*val, insns); + + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; + + return copy_from_user_nofault(val, uaddr, sizeof(*val)); +} + +static void dump_instr(const char *loglvl, struct pt_regs *regs) +{ + char str[sizeof("0000 ") * 12 + 2 + 1], *p = str; + const u16 *insns = (u16 *)instruction_pointer(regs); + long bad; + u16 val; + int i; + + for (i = -10; i < 2; i++) { + bad = copy_code(regs, &val, &insns[i]); + if (!bad) { + p += sprintf(p, i == 0 ? "(%04hx) " : "%04hx ", val); + } else { + printk("%sCode: Unable to access instruction at 0x%px.\n", + loglvl, &insns[i]); + return; + } + } + printk("%sCode: %s\n", loglvl, str); +} + void die(struct pt_regs *regs, const char *str) { static int die_counter; int ret; + long cause; + unsigned long flags; oops_enter(); - spin_lock_irq(&die_lock); + spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); pr_emerg("%s [#%d]\n", str, ++die_counter); print_modules(); - show_regs(regs); + if (regs) { + show_regs(regs); + dump_instr(KERN_EMERG, regs); + } - ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV); + cause = regs ? regs->cause : -1; + ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV); + + if (kexec_should_crash(current)) + crash_kexec(regs); bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irq(&die_lock); + spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) @@ -53,7 +107,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) @@ -66,7 +120,8 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) tsk->comm, task_pid_nr(tsk), signo, code, addr); print_vma_addr(KERN_CONT " in ", instruction_pointer(regs)); pr_cont("\n"); - show_regs(regs); + __show_regs(regs); + dump_instr(KERN_EMERG, regs); } force_sig_fault(signo, code, (void __user *)addr); @@ -75,6 +130,8 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) static void do_trap_error(struct pt_regs *regs, int signo, int code, unsigned long addr, const char *str) { + current->thread.bad_cause = regs->cause; + if (user_mode(regs)) { do_trap(regs, signo, code, addr); } else { @@ -83,10 +140,23 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } } -#define DO_ERROR_INFO(name, signo, code, str) \ -asmlinkage __visible void name(struct pt_regs *regs) \ -{ \ - do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ +#if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_RISCV_ALTERNATIVE) +#define __trap_section __noinstr_section(".xip.traps") +#else +#define __trap_section noinstr +#endif +#define DO_ERROR_INFO(name, signo, code, str) \ +asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ +{ \ + if (user_mode(regs)) { \ + irqentry_enter_from_user_mode(regs); \ + do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + irqentry_exit_to_user_mode(regs); \ + } else { \ + irqentry_state_t state = irqentry_nmi_enter(regs); \ + do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + irqentry_nmi_exit(regs, state); \ + } \ } DO_ERROR_INFO(do_trap_unknown, @@ -95,18 +165,81 @@ DO_ERROR_INFO(do_trap_insn_misaligned, SIGBUS, BUS_ADRALN, "instruction address misaligned"); DO_ERROR_INFO(do_trap_insn_fault, SIGSEGV, SEGV_ACCERR, "instruction access fault"); -DO_ERROR_INFO(do_trap_insn_illegal, - SIGILL, ILL_ILLOPC, "illegal instruction"); -DO_ERROR_INFO(do_trap_load_misaligned, - SIGBUS, BUS_ADRALN, "load address misaligned"); + +asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *regs) +{ + bool handled; + + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + local_irq_enable(); + + handled = riscv_v_first_use_handler(regs); + + local_irq_disable(); + + if (!handled) + do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, + "Oops - illegal instruction"); + + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, + "Oops - illegal instruction"); + + irqentry_nmi_exit(regs, state); + } +} + DO_ERROR_INFO(do_trap_load_fault, SIGSEGV, SEGV_ACCERR, "load access fault"); -DO_ERROR_INFO(do_trap_store_misaligned, - SIGBUS, BUS_ADRALN, "store (or AMO) address misaligned"); + +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_load(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + "Oops - load address misaligned"); + + 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) +{ + 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"); + + irqentry_nmi_exit(regs, state); + } +} DO_ERROR_INFO(do_trap_store_fault, SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault"); -DO_ERROR_INFO(do_trap_ecall_u, - SIGILL, ILL_ILLTRP, "environment call from U-mode"); DO_ERROR_INFO(do_trap_ecall_s, SIGILL, ILL_ILLTRP, "environment call from S-mode"); DO_ERROR_INFO(do_trap_ecall_m, @@ -116,21 +249,132 @@ static inline unsigned long get_break_insn_length(unsigned long pc) { bug_insn_t insn; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; - return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL); + + return GET_INSN_LENGTH(insn); +} + +static bool probe_single_step_handler(struct pt_regs *regs) +{ + bool user = user_mode(regs); + + return user ? uprobe_single_step_handler(regs) : kprobe_single_step_handler(regs); +} + +static bool probe_breakpoint_handler(struct pt_regs *regs) +{ + bool user = user_mode(regs); + + return user ? uprobe_breakpoint_handler(regs) : kprobe_breakpoint_handler(regs); } -asmlinkage __visible void do_trap_break(struct pt_regs *regs) +void handle_break(struct pt_regs *regs) { + if (probe_single_step_handler(regs)) + return; + + if (probe_breakpoint_handler(regs)) + return; + + current->thread.bad_cause = regs->cause; + if (user_mode(regs)) force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc); - else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN) +#ifdef CONFIG_KGDB + else if (notify_die(DIE_TRAP, "EBREAK", regs, 0, regs->cause, SIGTRAP) + == NOTIFY_STOP) + return; +#endif + else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) regs->epc += get_break_insn_length(regs->epc); else die(regs, "Kernel BUG"); } +asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + handle_break(regs); + + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + handle_break(regs); + + irqentry_nmi_exit(regs, state); + } +} + +asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) +{ + if (user_mode(regs)) { + long syscall = regs->a7; + + regs->epc += 4; + regs->orig_a0 = regs->a0; + + riscv_v_vstate_discard(regs); + + syscall = syscall_enter_from_user_mode(regs, syscall); + + if (syscall >= 0 && syscall < NR_syscalls) + syscall_handler(regs, syscall); + else if (syscall != -1) + regs->a0 = -ENOSYS; + + syscall_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + do_trap_error(regs, SIGILL, ILL_ILLTRP, regs->epc, + "Oops - environment call from U-mode"); + + irqentry_nmi_exit(regs, state); + } + +} + +#ifdef CONFIG_MMU +asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs) +{ + irqentry_state_t state = irqentry_enter(regs); + + handle_page_fault(regs); + + local_irq_disable(); + + irqentry_exit(regs, state); +} +#endif + +static void noinstr handle_riscv_irq(struct pt_regs *regs) +{ + struct pt_regs *old_regs; + + irq_enter_rcu(); + old_regs = set_irq_regs(regs); + handle_arch_irq(regs); + set_irq_regs(old_regs); + irq_exit_rcu(); +} + +asmlinkage void noinstr do_irq(struct pt_regs *regs) +{ + irqentry_state_t state = irqentry_enter(regs); + + if (IS_ENABLED(CONFIG_IRQ_STACKS) && on_thread_stack()) + call_on_irq_stack(regs, handle_riscv_irq); + else + handle_riscv_irq(regs); + + irqentry_exit(regs, state); +} + #ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long pc) { @@ -138,7 +382,7 @@ int is_valid_bugaddr(unsigned long pc) if (pc < VMALLOC_START) return 0; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) return (insn == __BUG_INSN_32); @@ -147,15 +391,27 @@ int is_valid_bugaddr(unsigned long pc) } #endif /* CONFIG_GENERIC_BUG */ -void __init trap_init(void) +#ifdef CONFIG_VMAP_STACK +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], + overflow_stack)__aligned(16); + +asmlinkage void handle_bad_stack(struct pt_regs *regs) { - /* - * Set sup0 scratch register to 0, indicating to exception vector - * that we are presently executing in the kernel - */ - csr_write(CSR_SCRATCH, 0); - /* Set the exception vector address */ - csr_write(CSR_TVEC, &handle_exception); - /* Enable all interrupts */ - csr_write(CSR_IE, -1); + unsigned long tsk_stk = (unsigned long)current->stack; + unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); + + console_verbose(); + + pr_emerg("Insufficient stack space to handle exception!\n"); + pr_emerg("Task stack: [0x%016lx..0x%016lx]\n", + tsk_stk, tsk_stk + THREAD_SIZE); + pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n", + ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE); + + __show_regs(regs); + panic("Kernel stack overflow"); + + for (;;) + wait_for_interrupt(); } +#endif diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c new file mode 100644 index 000000000000..8ded225e8c5b --- /dev/null +++ b/arch/riscv/kernel/traps_misaligned.c @@ -0,0 +1,647 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/perf_event.h> +#include <linux/irq.h> +#include <linux/stringify.h> + +#include <asm/processor.h> +#include <asm/ptrace.h> +#include <asm/csr.h> +#include <asm/entry-common.h> +#include <asm/hwprobe.h> +#include <asm/cpufeature.h> + +#define INSN_MATCH_LB 0x3 +#define INSN_MASK_LB 0x707f +#define INSN_MATCH_LH 0x1003 +#define INSN_MASK_LH 0x707f +#define INSN_MATCH_LW 0x2003 +#define INSN_MASK_LW 0x707f +#define INSN_MATCH_LD 0x3003 +#define INSN_MASK_LD 0x707f +#define INSN_MATCH_LBU 0x4003 +#define INSN_MASK_LBU 0x707f +#define INSN_MATCH_LHU 0x5003 +#define INSN_MASK_LHU 0x707f +#define INSN_MATCH_LWU 0x6003 +#define INSN_MASK_LWU 0x707f +#define INSN_MATCH_SB 0x23 +#define INSN_MASK_SB 0x707f +#define INSN_MATCH_SH 0x1023 +#define INSN_MASK_SH 0x707f +#define INSN_MATCH_SW 0x2023 +#define INSN_MASK_SW 0x707f +#define INSN_MATCH_SD 0x3023 +#define INSN_MASK_SD 0x707f + +#define INSN_MATCH_FLW 0x2007 +#define INSN_MASK_FLW 0x707f +#define INSN_MATCH_FLD 0x3007 +#define INSN_MASK_FLD 0x707f +#define INSN_MATCH_FLQ 0x4007 +#define INSN_MASK_FLQ 0x707f +#define INSN_MATCH_FSW 0x2027 +#define INSN_MASK_FSW 0x707f +#define INSN_MATCH_FSD 0x3027 +#define INSN_MASK_FSD 0x707f +#define INSN_MATCH_FSQ 0x4027 +#define INSN_MASK_FSQ 0x707f + +#define INSN_MATCH_C_LD 0x6000 +#define INSN_MASK_C_LD 0xe003 +#define INSN_MATCH_C_SD 0xe000 +#define INSN_MASK_C_SD 0xe003 +#define INSN_MATCH_C_LW 0x4000 +#define INSN_MASK_C_LW 0xe003 +#define INSN_MATCH_C_SW 0xc000 +#define INSN_MASK_C_SW 0xe003 +#define INSN_MATCH_C_LDSP 0x6002 +#define INSN_MASK_C_LDSP 0xe003 +#define INSN_MATCH_C_SDSP 0xe002 +#define INSN_MASK_C_SDSP 0xe003 +#define INSN_MATCH_C_LWSP 0x4002 +#define INSN_MASK_C_LWSP 0xe003 +#define INSN_MATCH_C_SWSP 0xc002 +#define INSN_MASK_C_SWSP 0xe003 + +#define INSN_MATCH_C_FLD 0x2000 +#define INSN_MASK_C_FLD 0xe003 +#define INSN_MATCH_C_FLW 0x6000 +#define INSN_MASK_C_FLW 0xe003 +#define INSN_MATCH_C_FSD 0xa000 +#define INSN_MASK_C_FSD 0xe003 +#define INSN_MATCH_C_FSW 0xe000 +#define INSN_MASK_C_FSW 0xe003 +#define INSN_MATCH_C_FLDSP 0x2002 +#define INSN_MASK_C_FLDSP 0xe003 +#define INSN_MATCH_C_FSDSP 0xa002 +#define INSN_MASK_C_FSDSP 0xe003 +#define INSN_MATCH_C_FLWSP 0x6002 +#define INSN_MASK_C_FLWSP 0xe003 +#define INSN_MATCH_C_FSWSP 0xe002 +#define INSN_MASK_C_FSWSP 0xe003 + +#define INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4) + +#if defined(CONFIG_64BIT) +#define LOG_REGBYTES 3 +#define XLEN 64 +#else +#define LOG_REGBYTES 2 +#define XLEN 32 +#endif +#define REGBYTES (1 << LOG_REGBYTES) +#define XLEN_MINUS_16 ((XLEN) - 16) + +#define SH_RD 7 +#define SH_RS1 15 +#define SH_RS2 20 +#define SH_RS2C 2 + +#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) +#define RVC_LW_IMM(x) ((RV_X(x, 6, 1) << 2) | \ + (RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 5, 1) << 6)) +#define RVC_LD_IMM(x) ((RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 5, 2) << 6)) +#define RVC_LWSP_IMM(x) ((RV_X(x, 4, 3) << 2) | \ + (RV_X(x, 12, 1) << 5) | \ + (RV_X(x, 2, 2) << 6)) +#define RVC_LDSP_IMM(x) ((RV_X(x, 5, 2) << 3) | \ + (RV_X(x, 12, 1) << 5) | \ + (RV_X(x, 2, 3) << 6)) +#define RVC_SWSP_IMM(x) ((RV_X(x, 9, 4) << 2) | \ + (RV_X(x, 7, 2) << 6)) +#define RVC_SDSP_IMM(x) ((RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 7, 3) << 6)) +#define RVC_RS1S(insn) (8 + RV_X(insn, SH_RD, 3)) +#define RVC_RS2S(insn) (8 + RV_X(insn, SH_RS2C, 3)) +#define RVC_RS2(insn) RV_X(insn, SH_RS2C, 5) + +#define SHIFT_RIGHT(x, y) \ + ((y) < 0 ? ((x) << -(y)) : ((x) >> (y))) + +#define REG_MASK \ + ((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES)) + +#define REG_OFFSET(insn, pos) \ + (SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK) + +#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)) +#define GET_RS2S(insn, regs) (*REG_PTR(RVC_RS2S(insn), 0, regs)) +#define GET_RS2C(insn, regs) (*REG_PTR(insn, SH_RS2C, regs)) +#define GET_SP(regs) (*REG_PTR(2, 0, regs)) +#define SET_RD(insn, regs, val) (*REG_PTR(insn, SH_RD, regs) = (val)) +#define IMM_I(insn) ((s32)(insn) >> 20) +#define IMM_S(insn) (((s32)(insn) >> 25 << 5) | \ + (s32)(((insn) >> 7) & 0x1f)) +#define MASK_FUNCT3 0x7000 + +#define GET_PRECISION(insn) (((insn) >> 25) & 3) +#define GET_RM(insn) (((insn) >> 12) & 7) +#define PRECISION_S 0 +#define PRECISION_D 1 + +#ifdef CONFIG_FPU + +#define FP_GET_RD(insn) (insn >> 7 & 0x1F) + +extern void put_f32_reg(unsigned long fp_reg, unsigned long value); + +static int set_f32_rd(unsigned long insn, struct pt_regs *regs, + unsigned long val) +{ + unsigned long fp_reg = FP_GET_RD(insn); + + put_f32_reg(fp_reg, val); + regs->status |= SR_FS_DIRTY; + + return 0; +} + +extern void put_f64_reg(unsigned long fp_reg, unsigned long value); + +static int set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val) +{ + unsigned long fp_reg = FP_GET_RD(insn); + unsigned long value; + +#if __riscv_xlen == 32 + value = (unsigned long) &val; +#else + value = val; +#endif + put_f64_reg(fp_reg, value); + regs->status |= SR_FS_DIRTY; + + return 0; +} + +#if __riscv_xlen == 32 +extern void get_f64_reg(unsigned long fp_reg, u64 *value); + +static u64 get_f64_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F; + u64 val; + + get_f64_reg(fp_reg, &val); + regs->status |= SR_FS_DIRTY; + + return val; +} +#else + +extern unsigned long get_f64_reg(unsigned long fp_reg); + +static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F; + unsigned long val; + + val = get_f64_reg(fp_reg); + regs->status |= SR_FS_DIRTY; + + return val; +} + +#endif + +extern unsigned long get_f32_reg(unsigned long fp_reg); + +static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F; + unsigned long val; + + val = get_f32_reg(fp_reg); + regs->status |= SR_FS_DIRTY; + + return val; +} + +#else /* CONFIG_FPU */ +static void set_f32_rd(unsigned long insn, struct pt_regs *regs, + unsigned long val) {} + +static void set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val) {} + +static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + return 0; +} + +static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + return 0; +} + +#endif + +#define GET_F64_RS2(insn, regs) (get_f64_rs(insn, 20, regs)) +#define GET_F64_RS2C(insn, regs) (get_f64_rs(insn, 2, regs)) +#define GET_F64_RS2S(insn, regs) (get_f64_rs(RVC_RS2S(insn), 0, regs)) + +#define GET_F32_RS2(insn, regs) (get_f32_rs(insn, 20, regs)) +#define GET_F32_RS2C(insn, regs) (get_f32_rs(insn, 2, regs)) +#define GET_F32_RS2S(insn, regs) (get_f32_rs(RVC_RS2S(insn), 0, regs)) + +#ifdef CONFIG_RISCV_M_MODE +static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val) +{ + u8 val; + + asm volatile("lbu %0, %1" : "=&r" (val) : "m" (*addr)); + *r_val = val; + + return 0; +} + +static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val) +{ + asm volatile ("sb %0, %1\n" : : "r" (val), "m" (*addr)); + + return 0; +} + +static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn) +{ + register ulong __mepc asm ("a2") = mepc; + ulong val, rvc_mask = 3, tmp; + + asm ("and %[tmp], %[addr], 2\n" + "bnez %[tmp], 1f\n" +#if defined(CONFIG_64BIT) + __stringify(LWU) " %[insn], (%[addr])\n" +#else + __stringify(LW) " %[insn], (%[addr])\n" +#endif + "and %[tmp], %[insn], %[rvc_mask]\n" + "beq %[tmp], %[rvc_mask], 2f\n" + "sll %[insn], %[insn], %[xlen_minus_16]\n" + "srl %[insn], %[insn], %[xlen_minus_16]\n" + "j 2f\n" + "1:\n" + "lhu %[insn], (%[addr])\n" + "and %[tmp], %[insn], %[rvc_mask]\n" + "bne %[tmp], %[rvc_mask], 2f\n" + "lhu %[tmp], 2(%[addr])\n" + "sll %[tmp], %[tmp], 16\n" + "add %[insn], %[insn], %[tmp]\n" + "2:" + : [insn] "=&r" (val), [tmp] "=&r" (tmp) + : [addr] "r" (__mepc), [rvc_mask] "r" (rvc_mask), + [xlen_minus_16] "i" (XLEN_MINUS_16)); + + *r_insn = val; + + return 0; +} +#else +static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val) +{ + if (user_mode(regs)) { + return __get_user(*r_val, (u8 __user *)addr); + } else { + *r_val = *addr; + return 0; + } +} + +static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val) +{ + if (user_mode(regs)) { + return __put_user(val, (u8 __user *)addr); + } else { + *addr = val; + return 0; + } +} + +#define __read_insn(regs, insn, insn_addr) \ +({ \ + int __ret; \ + \ + if (user_mode(regs)) { \ + __ret = __get_user(insn, insn_addr); \ + } else { \ + insn = *(__force u16 *)insn_addr; \ + __ret = 0; \ + } \ + \ + __ret; \ +}) + +static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn) +{ + ulong insn = 0; + + if (epc & 0x2) { + ulong tmp = 0; + u16 __user *insn_addr = (u16 __user *)epc; + + if (__read_insn(regs, insn, insn_addr)) + return -EFAULT; + /* __get_user() uses regular "lw" which sign extend the loaded + * value make sure to clear higher order bits in case we "or" it + * below with the upper 16 bits half. + */ + insn &= GENMASK(15, 0); + if ((insn & __INSN_LENGTH_MASK) != __INSN_LENGTH_32) { + *r_insn = insn; + return 0; + } + insn_addr++; + if (__read_insn(regs, tmp, insn_addr)) + return -EFAULT; + *r_insn = (tmp << 16) | insn; + + return 0; + } else { + u32 __user *insn_addr = (u32 __user *)epc; + + if (__read_insn(regs, insn, insn_addr)) + return -EFAULT; + if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) { + *r_insn = insn; + return 0; + } + insn &= GENMASK(15, 0); + *r_insn = insn; + + return 0; + } +} +#endif + +union reg_data { + u8 data_bytes[8]; + ulong data_ulong; + 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) +{ + union reg_data val; + unsigned long epc = regs->epc; + unsigned long insn; + unsigned long addr = regs->badaddr; + int i, fp = 0, shift = 0, len = 0; + + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); + + *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED; + + if (!unaligned_enabled) + return -1; + + if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS)) + return -1; + + if (get_insn(regs, epc, &insn)) + return -1; + + regs->epc = 0; + + if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) { + len = 4; + shift = 8 * (sizeof(unsigned long) - len); +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) { + len = 8; + shift = 8 * (sizeof(unsigned long) - len); + } else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) { + len = 4; +#endif + } else if ((insn & INSN_MASK_FLD) == INSN_MATCH_FLD) { + fp = 1; + len = 8; + } else if ((insn & INSN_MASK_FLW) == INSN_MATCH_FLW) { + fp = 1; + len = 4; + } else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) { + len = 2; + shift = 8 * (sizeof(unsigned long) - len); + } else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) { + len = 2; +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) { + len = 8; + shift = 8 * (sizeof(unsigned long) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP && + ((insn >> SH_RD) & 0x1f)) { + len = 8; + shift = 8 * (sizeof(unsigned long) - len); +#endif + } else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) { + len = 4; + shift = 8 * (sizeof(unsigned long) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP && + ((insn >> SH_RD) & 0x1f)) { + len = 4; + shift = 8 * (sizeof(unsigned long) - len); + } else if ((insn & INSN_MASK_C_FLD) == INSN_MATCH_C_FLD) { + fp = 1; + len = 8; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_FLDSP) == INSN_MATCH_C_FLDSP) { + fp = 1; + len = 8; +#if defined(CONFIG_32BIT) + } else if ((insn & INSN_MASK_C_FLW) == INSN_MATCH_C_FLW) { + fp = 1; + len = 4; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_FLWSP) == INSN_MATCH_C_FLWSP) { + fp = 1; + len = 4; +#endif + } else { + regs->epc = epc; + return -1; + } + + if (!IS_ENABLED(CONFIG_FPU) && fp) + return -EOPNOTSUPP; + + val.data_u64 = 0; + for (i = 0; i < len; i++) { + if (load_u8(regs, (void *)(addr + i), &val.data_bytes[i])) + return -1; + } + + if (!fp) + SET_RD(insn, regs, val.data_ulong << shift >> shift); + else if (len == 8) + set_f64_rd(insn, regs, val.data_u64); + else + set_f32_rd(insn, regs, val.data_ulong); + + regs->epc = epc + INSN_LEN(insn); + + return 0; +} + +int handle_misaligned_store(struct pt_regs *regs) +{ + union reg_data val; + unsigned long epc = regs->epc; + unsigned long insn; + unsigned long addr = regs->badaddr; + int i, len = 0, fp = 0; + + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); + + if (!unaligned_enabled) + return -1; + + if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS)) + return -1; + + if (get_insn(regs, epc, &insn)) + return -1; + + regs->epc = 0; + + val.data_ulong = GET_RS2(insn, regs); + + if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) { + len = 4; +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) { + len = 8; +#endif + } else if ((insn & INSN_MASK_FSD) == INSN_MATCH_FSD) { + fp = 1; + len = 8; + val.data_u64 = GET_F64_RS2(insn, regs); + } else if ((insn & INSN_MASK_FSW) == INSN_MATCH_FSW) { + fp = 1; + len = 4; + val.data_ulong = GET_F32_RS2(insn, regs); + } else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) { + len = 2; +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { + len = 8; + val.data_ulong = GET_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) { + len = 8; + val.data_ulong = GET_RS2C(insn, regs); +#endif + } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { + len = 4; + val.data_ulong = GET_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) { + len = 4; + val.data_ulong = GET_RS2C(insn, regs); + } else if ((insn & INSN_MASK_C_FSD) == INSN_MATCH_C_FSD) { + fp = 1; + len = 8; + val.data_u64 = GET_F64_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_FSDSP) == INSN_MATCH_C_FSDSP) { + fp = 1; + len = 8; + val.data_u64 = GET_F64_RS2C(insn, regs); +#if !defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_C_FSW) == INSN_MATCH_C_FSW) { + fp = 1; + len = 4; + val.data_ulong = GET_F32_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_FSWSP) == INSN_MATCH_C_FSWSP) { + fp = 1; + len = 4; + val.data_ulong = GET_F32_RS2C(insn, regs); +#endif + } else { + regs->epc = epc; + return -1; + } + + if (!IS_ENABLED(CONFIG_FPU) && fp) + return -EOPNOTSUPP; + + for (i = 0; i < len; i++) { + if (store_u8(regs, (void *)(addr + i), val.data_bytes[i])) + return -1; + } + + regs->epc = epc + INSN_LEN(insn); + + return 0; +} + +bool check_unaligned_access_emulated(int cpu) +{ + 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_UNKNOWN; + + __asm__ __volatile__ ( + " "REG_L" %[tmp], 1(%[ptr])\n" + : [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory"); + + misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_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)) { + pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n"); + while (true) + cpu_relax(); + } + + return misaligned_emu_detected; +} + +void unaligned_emulation_finish(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_present_cpu(cpu) { + if (per_cpu(misaligned_access_speed, cpu) != + RISCV_HWPROBE_MISALIGNED_EMULATED) { + return; + } + } + unaligned_ctl = true; +} + +bool unaligned_ctl_available(void) +{ + return unaligned_ctl; +} diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 484d95a70907..2cf76218a5bd 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -11,13 +11,24 @@ #include <linux/slab.h> #include <linux/binfmts.h> #include <linux/err.h> - +#include <asm/page.h> #include <asm/vdso.h> +#include <linux/time_namespace.h> +#include <vdso/datapage.h> +#include <vdso/vsyscall.h> + +enum vvar_pages { + VVAR_DATA_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, + VVAR_NR_PAGES, +}; -extern char vdso_start[], vdso_end[]; +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; -static unsigned int vdso_pages; -static struct page **vdso_pagelist; +#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) /* * The vDSO data page. @@ -26,70 +37,252 @@ static union { struct vdso_data data; u8 page[PAGE_SIZE]; } vdso_data_store __page_aligned_data; -static struct vdso_data *vdso_data = &vdso_data_store.data; +struct vdso_data *vdso_data = &vdso_data_store.data; -static int __init vdso_init(void) +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; +}; + +static struct __vdso_info vdso_info; +#ifdef CONFIG_COMPAT +static struct __vdso_info compat_vdso_info; +#endif + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static void __init __vdso_init(struct __vdso_info *vdso_info) { unsigned int i; + struct page **vdso_pagelist; + unsigned long pfn; + + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) + panic("vDSO is not a valid ELF object!\n"); + + vdso_info->vdso_pages = ( + vdso_info->vdso_code_end - + vdso_info->vdso_code_start) >> + PAGE_SHIFT; + + vdso_pagelist = kcalloc(vdso_info->vdso_pages, + sizeof(struct page *), + GFP_KERNEL); + if (vdso_pagelist == NULL) + panic("vDSO kcalloc failed!\n"); + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_info->vdso_code_start); + + for (i = 0; i < vdso_info->vdso_pages; i++) + vdso_pagelist[i] = pfn_to_page(pfn + i); - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; - vdso_pagelist = - kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL); - if (unlikely(vdso_pagelist == NULL)) { - pr_err("vdso: pagelist allocation failed\n"); - return -ENOMEM; + 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 } - for (i = 0; i < vdso_pages; i++) { - struct page *pg; + 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; - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); - vdso_pagelist[i] = pg; + 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; } - vdso_pagelist[i] = virt_to_page(vdso_data); + + 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 __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], +}; + +#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 __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], +}; +#endif + +static int __init vdso_init(void) +{ + __vdso_init(&vdso_info); +#ifdef CONFIG_COMPAT + __vdso_init(&compat_vdso_info); +#endif return 0; } arch_initcall(vdso_init); -int arch_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp) +static int __setup_additional_pages(struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp, + struct __vdso_info *vdso_info) { - struct mm_struct *mm = current->mm; - unsigned long vdso_base, vdso_len; - int ret; + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; + + BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_len = (vdso_pages + 1) << PAGE_SHIFT; + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + VVAR_SIZE; - down_write(&mm->mmap_sem); - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { - ret = vdso_base; - goto end; + ret = ERR_PTR(vdso_base); + goto up_fail; } - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm); + if (IS_ERR(ret)) + goto up_fail; + + vdso_base += VVAR_SIZE; mm->context.vdso = (void *)vdso_base; - ret = install_special_mapping(mm, vdso_base, vdso_len, + ret = + _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_pagelist); + vdso_info->cm); + + if (IS_ERR(ret)) + goto up_fail; - if (unlikely(ret)) - mm->context.vdso = NULL; + return 0; + +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); +} + +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp, + &compat_vdso_info); + mmap_write_unlock(mm); -end: - up_write(&mm->mmap_sem); return ret; } +#endif -const char *arch_vma_name(struct vm_area_struct *vma) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) - return "[vdso]"; - return NULL; + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info); + mmap_write_unlock(mm); + + return ret; } diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore index 97c2d69d0289..3a19def868ec 100644 --- a/arch/riscv/kernel/vdso/.gitignore +++ b/arch/riscv/kernel/vdso/.gitignore @@ -1,2 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only vdso.lds *.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 49a5852fd07d..9b517fe1b8a8 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -1,71 +1,75 @@ # SPDX-License-Identifier: GPL-2.0-only # Copied from arch/tile/kernel/vdso/Makefile +# Include the generic Makefile to check the built vdso. +include $(srctree)/lib/vdso/Makefile # Symbols present in the vdso vdso-syms = rt_sigreturn ifdef CONFIG_64BIT -vdso-syms += gettimeofday -vdso-syms += clock_gettime -vdso-syms += clock_getres +vdso-syms += vgettimeofday endif vdso-syms += getcpu vdso-syms += flush_icache +vdso-syms += hwprobe +vdso-syms += sys_hwprobe # Files to link into the vdso -obj-vdso = $(patsubst %, %.o, $(vdso-syms)) +obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o + +ccflags-y := -fno-stack-protector +ccflags-y += -DDISABLE_BRANCH_PROFILING + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) +endif + +CFLAGS_hwprobe.o += -fPIC # Build rules -targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o +targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) -obj-y += vdso.o vdso-syms.o +obj-y += vdso.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +ifneq ($(filter vgettimeofday, $(vdso-syms)),) +CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY +endif + +# Disable -pg to prevent insert call site +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) -# Disable gcov profiling for VDSO code +# Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n +KCOV_INSTRUMENT := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n # Force dependency $(obj)/vdso.o: $(obj)/vdso.so # link rule for the .so file, .lds has to be first -SYSCFLAGS_vdso.so.dbg = $(c_flags) -$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE +$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) - -# We also create a special relocatable object that should mirror the symbol -# table and layout of the linked DSO. With ld -R we can then refer to -# these symbols in the kernel code rather than hand-coded addresses. - -SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id -Wl,--hash-style=both -$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE - $(call if_changed,vdsold) - -LDFLAGS_vdso-syms.o := -r -R -$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE - $(call if_changed,ld) +LDFLAGS_vdso.so.dbg = -shared -S -soname=linux-vdso.so.1 \ + --build-id=sha1 --hash-style=both --eh-frame-hdr # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) +# Generate VDSO offsets using helper script +gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +quiet_cmd_vdsosym = VDSOSYM $@ + cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ + +include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE + $(call if_changed,vdsosym) + # actual build commands # The DSO images are built using a special linker script -# Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions. # Make sure only to export the intended __vdso_xxx symbol offsets. quiet_cmd_vdsold = VDSOLD $@ - cmd_vdsold = $(CC) $(KBUILD_CFLAGS) $(call cc-option, -no-pie) -nostdlib -nostartfiles $(SYSCFLAGS_$(@F)) \ - -Wl,-T,$(filter-out FORCE,$^) -o $@.tmp && \ - $(CROSS_COMPILE)objcopy \ - $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so + cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \ + $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ + rm $@.tmp diff --git a/arch/riscv/kernel/vdso/clock_getres.S b/arch/riscv/kernel/vdso/clock_getres.S deleted file mode 100644 index 91378a52eb22..000000000000 --- a/arch/riscv/kernel/vdso/clock_getres.S +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2017 SiFive - */ - -#include <linux/linkage.h> -#include <asm/unistd.h> - - .text -/* int __vdso_clock_getres(clockid_t clock_id, struct timespec *res); */ -ENTRY(__vdso_clock_getres) - .cfi_startproc - /* For now, just do the syscall. */ - li a7, __NR_clock_getres - ecall - ret - .cfi_endproc -ENDPROC(__vdso_clock_getres) diff --git a/arch/riscv/kernel/vdso/clock_gettime.S b/arch/riscv/kernel/vdso/clock_gettime.S deleted file mode 100644 index 5371fd9bc01f..000000000000 --- a/arch/riscv/kernel/vdso/clock_gettime.S +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2017 SiFive - */ - -#include <linux/linkage.h> -#include <asm/unistd.h> - - .text -/* int __vdso_clock_gettime(clockid_t clock_id, struct timespec *tp); */ -ENTRY(__vdso_clock_gettime) - .cfi_startproc - /* For now, just do the syscall. */ - li a7, __NR_clock_gettime - ecall - ret - .cfi_endproc -ENDPROC(__vdso_clock_gettime) diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S index 82f97d67c23e..8f884227e8bc 100644 --- a/arch/riscv/kernel/vdso/flush_icache.S +++ b/arch/riscv/kernel/vdso/flush_icache.S @@ -8,7 +8,7 @@ .text /* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */ -ENTRY(__vdso_flush_icache) +SYM_FUNC_START(__vdso_flush_icache) .cfi_startproc #ifdef CONFIG_SMP li a7, __NR_riscv_flush_icache @@ -19,4 +19,4 @@ ENTRY(__vdso_flush_icache) #endif ret .cfi_endproc -ENDPROC(__vdso_flush_icache) +SYM_FUNC_END(__vdso_flush_icache) diff --git a/arch/riscv/kernel/vdso/gen_vdso_offsets.sh b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh new file mode 100755 index 000000000000..c2e5613f3495 --- /dev/null +++ b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +LC_ALL=C +sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define \2_offset\t0x\1/p' diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S index bb0c05e2ffba..9c1bd531907f 100644 --- a/arch/riscv/kernel/vdso/getcpu.S +++ b/arch/riscv/kernel/vdso/getcpu.S @@ -8,11 +8,11 @@ .text /* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */ -ENTRY(__vdso_getcpu) +SYM_FUNC_START(__vdso_getcpu) .cfi_startproc /* For now, just do the syscall. */ li a7, __NR_getcpu ecall ret .cfi_endproc -ENDPROC(__vdso_getcpu) +SYM_FUNC_END(__vdso_getcpu) diff --git a/arch/riscv/kernel/vdso/gettimeofday.S b/arch/riscv/kernel/vdso/gettimeofday.S deleted file mode 100644 index e6fb8af88632..000000000000 --- a/arch/riscv/kernel/vdso/gettimeofday.S +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2017 SiFive - */ - -#include <linux/linkage.h> -#include <asm/unistd.h> - - .text -/* int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); */ -ENTRY(__vdso_gettimeofday) - .cfi_startproc - /* For now, just do the syscall. */ - li a7, __NR_gettimeofday - ecall - ret - .cfi_endproc -ENDPROC(__vdso_gettimeofday) diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c new file mode 100644 index 000000000000..1e926e4b5881 --- /dev/null +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2023 Rivos, Inc + */ + +#include <linux/string.h> +#include <linux/types.h> +#include <vdso/datapage.h> +#include <vdso/helpers.h> + +extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags); + +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; + bool all_cpus = !cpusetsize && !cpus; + struct riscv_hwprobe *p = pairs; + struct riscv_hwprobe *end = pairs + pair_count; + + /* + * Defer to the syscall for exotic requests. The vdso has answers + * stashed away only for the "all cpus" case. If all CPUs are + * homogeneous, then this function can handle requests for arbitrary + * masks. + */ + if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus)) + return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags); + + /* This is something we can handle, fill out the pairs. */ + while (p < end) { + if (riscv_hwprobe_key_is_valid(p->key)) { + p->value = avd->all_cpu_hwprobe_values[p->key]; + + } else { + p->key = -1; + p->value = 0; + } + + p++; + } + + return 0; +} + +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; + struct riscv_hwprobe *p = pairs; + struct riscv_hwprobe *end = pairs + pair_count; + unsigned char *c = (unsigned char *)cpus; + bool empty_cpus = true; + bool clear_all = false; + int i; + + if (!cpusetsize || !cpus) + return -EINVAL; + + for (i = 0; i < cpusetsize; i++) { + if (c[i]) { + empty_cpus = false; + break; + } + } + + if (empty_cpus || flags != RISCV_HWPROBE_WHICH_CPUS || !avd->homogeneous_cpus) + return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags); + + while (p < end) { + if (riscv_hwprobe_key_is_valid(p->key)) { + struct riscv_hwprobe t = { + .key = p->key, + .value = avd->all_cpu_hwprobe_values[p->key], + }; + + if (!riscv_hwprobe_pair_cmp(&t, p)) + clear_all = true; + } else { + clear_all = true; + p->key = -1; + p->value = 0; + } + p++; + } + + if (clear_all) { + for (i = 0; i < cpusetsize; i++) + c[i] = 0; + } + + return 0; +} + +/* Add a prototype to avoid -Wmissing-prototypes warning. */ +int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags); + +int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags) +{ + if (flags & RISCV_HWPROBE_WHICH_CPUS) + return riscv_vdso_get_cpus(pairs, pair_count, cpusetsize, + cpus, flags); + + return riscv_vdso_get_values(pairs, pair_count, cpusetsize, + cpus, flags); +} diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S new file mode 100644 index 000000000000..2a956c942211 --- /dev/null +++ b/arch/riscv/kernel/vdso/note.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/elfnote.h> +#include <linux/version.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S index 0573705eac76..3dc022aa8931 100644 --- a/arch/riscv/kernel/vdso/rt_sigreturn.S +++ b/arch/riscv/kernel/vdso/rt_sigreturn.S @@ -7,10 +7,10 @@ #include <asm/unistd.h> .text -ENTRY(__vdso_rt_sigreturn) +SYM_FUNC_START(__vdso_rt_sigreturn) .cfi_startproc .cfi_signal_frame li a7, __NR_rt_sigreturn - scall + ecall .cfi_endproc -ENDPROC(__vdso_rt_sigreturn) +SYM_FUNC_END(__vdso_rt_sigreturn) diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S new file mode 100644 index 000000000000..77e57f830521 --- /dev/null +++ b/arch/riscv/kernel/vdso/sys_hwprobe.S @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos, Inc */ + +#include <linux/linkage.h> +#include <asm/unistd.h> + +.text +SYM_FUNC_START(riscv_hwprobe) + .cfi_startproc + li a7, __NR_riscv_hwprobe + ecall + ret + + .cfi_endproc +SYM_FUNC_END(riscv_hwprobe) diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S index df222245be05..83f1c899e8d8 100644 --- a/arch/riscv/kernel/vdso/vdso.S +++ b/arch/riscv/kernel/vdso/vdso.S @@ -7,12 +7,16 @@ #include <linux/linkage.h> #include <asm/page.h> +#ifndef __VDSO_PATH +#define __VDSO_PATH "arch/riscv/kernel/vdso/vdso.so" +#endif + __PAGE_ALIGNED_DATA .globl vdso_start, vdso_end .balign PAGE_SIZE vdso_start: - .incbin "arch/riscv/kernel/vdso/vdso.so" + .incbin __VDSO_PATH .balign PAGE_SIZE vdso_end: diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index f66a091cb890..cbe2a179331d 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -2,11 +2,17 @@ /* * Copyright (C) 2012 Regents of the University of California */ +#include <asm/page.h> +#include <asm/vdso.h> OUTPUT_ARCH(riscv) SECTIONS { + PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -17,28 +23,31 @@ SECTIONS .gnu.version_d : { *(.gnu.version_d) } .gnu.version_r : { *(.gnu.version_r) } - .note : { *(.note.*) } :text :note .dynamic : { *(.dynamic) } :text :dynamic + .rodata : { + *(.rodata .rodata.* .gnu.linkonce.r.*) + *(.got.plt) *(.got) + *(.data .data.* .gnu.linkonce.d.*) + *(.dynbss) + *(.bss .bss.* .gnu.linkonce.b.*) + } + + .note : { *(.note.*) } :text :note + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr .eh_frame : { KEEP (*(.eh_frame)) } :text - .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) } - /* - * This linker script is used both with -r and with -shared. - * For the layouts to match, we need to skip more than enough - * space for the dynamic symbol table, etc. If this amount is - * insufficient, ld -shared will error; simply increase it here. + * Text is well-separated from actual data: there's plenty of + * stuff that isn't used at runtime in between. */ - . = 0x800; + . = ALIGN(16); .text : { *(.text .text.*) } :text - .data : { - *(.got.plt) *(.got) - *(.data .data.* .gnu.linkonce.d.*) - *(.dynbss) - *(.bss .bss.* .gnu.linkonce.b.*) + . = ALIGN(4); + .alternative : { + *(.alternative) } } @@ -62,11 +71,16 @@ VERSION LINUX_4.15 { global: __vdso_rt_sigreturn; +#ifdef HAS_VGETTIMEOFDAY __vdso_gettimeofday; __vdso_clock_gettime; __vdso_clock_getres; +#endif __vdso_getcpu; __vdso_flush_icache; +#ifndef COMPAT_VDSO + __vdso_riscv_hwprobe; +#endif local: *; }; } diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c new file mode 100644 index 000000000000..b35057802584 --- /dev/null +++ b/arch/riscv/kernel/vdso/vgettimeofday.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copied from arch/arm64/kernel/vdso/vgettimeofday.c + * + * Copyright (C) 2018 ARM Ltd. + * Copyright (C) 2020 SiFive + */ + +#include <linux/time.h> +#include <linux/types.h> +#include <vdso/gettime.h> + +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +{ + return __cvdso_clock_gettime(clock, ts); +} + +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) +{ + return __cvdso_gettimeofday(tv, tz); +} + +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) +{ + return __cvdso_clock_getres(clock_id, res); +} diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c new file mode 100644 index 000000000000..6727d1d3b8f2 --- /dev/null +++ b/arch/riscv/kernel/vector.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 SiFive + * Author: Andy Chiu <andy.chiu@sifive.com> + */ +#include <linux/export.h> +#include <linux/sched/signal.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/uaccess.h> +#include <linux/prctl.h> + +#include <asm/thread_info.h> +#include <asm/processor.h> +#include <asm/insn.h> +#include <asm/vector.h> +#include <asm/csr.h> +#include <asm/elf.h> +#include <asm/ptrace.h> +#include <asm/bug.h> + +static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE); +static struct kmem_cache *riscv_v_user_cachep; +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +static struct kmem_cache *riscv_v_kernel_cachep; +#endif + +unsigned long riscv_v_vsize __read_mostly; +EXPORT_SYMBOL_GPL(riscv_v_vsize); + +int riscv_v_setup_vsize(void) +{ + unsigned long this_vsize; + + /* There are 32 vector registers with vlenb length. */ + riscv_v_enable(); + this_vsize = csr_read(CSR_VLENB) * 32; + riscv_v_disable(); + + if (!riscv_v_vsize) { + riscv_v_vsize = this_vsize; + return 0; + } + + if (riscv_v_vsize != this_vsize) { + WARN(1, "RISCV_ISA_V only supports one vlenb on SMP systems"); + return -EOPNOTSUPP; + } + + return 0; +} + +void __init riscv_v_setup_ctx_cache(void) +{ + if (!has_vector()) + return; + + riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx", + riscv_v_vsize, 16, SLAB_PANIC, + 0, riscv_v_vsize, NULL); +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx", + riscv_v_vsize, 16, + SLAB_PANIC, NULL); +#endif +} + +static bool insn_is_vector(u32 insn_buf) +{ + u32 opcode = insn_buf & __INSN_OPCODE_MASK; + u32 width, csr; + + /* + * All V-related instructions, including CSR operations are 4-Byte. So, + * do not handle if the instruction length is not 4-Byte. + */ + if (unlikely(GET_INSN_LENGTH(insn_buf) != 4)) + return false; + + switch (opcode) { + case RVV_OPCODE_VECTOR: + return true; + case RVV_OPCODE_VL: + case RVV_OPCODE_VS: + width = RVV_EXRACT_VL_VS_WIDTH(insn_buf); + if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 || + width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64) + return true; + + break; + case RVG_OPCODE_SYSTEM: + csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf); + if ((csr >= CSR_VSTART && csr <= CSR_VCSR) || + (csr >= CSR_VL && csr <= CSR_VLENB)) + return true; + } + + return false; +} + +static int riscv_v_thread_zalloc(struct kmem_cache *cache, + struct __riscv_v_ext_state *ctx) +{ + void *datap; + + datap = kmem_cache_zalloc(cache, GFP_KERNEL); + if (!datap) + return -ENOMEM; + + ctx->datap = datap; + memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap)); + return 0; +} + +void riscv_v_thread_alloc(struct task_struct *tsk) +{ +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate); +#endif +} + +void riscv_v_thread_free(struct task_struct *tsk) +{ + if (tsk->thread.vstate.datap) + kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap); +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + if (tsk->thread.kernel_vstate.datap) + kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap); +#endif +} + +#define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK) +#define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2) +#define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) +#define VSTATE_CTRL_GET_INHERIT(x) (!!((x) & PR_RISCV_V_VSTATE_CTRL_INHERIT)) +static inline int riscv_v_ctrl_get_cur(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_CUR(tsk->thread.vstate_ctrl); +} + +static inline int riscv_v_ctrl_get_next(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_NEXT(tsk->thread.vstate_ctrl); +} + +static inline bool riscv_v_ctrl_test_inherit(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_INHERIT(tsk->thread.vstate_ctrl); +} + +static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt, + bool inherit) +{ + unsigned long ctrl; + + ctrl = cur & PR_RISCV_V_VSTATE_CTRL_CUR_MASK; + ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt); + if (inherit) + ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK; + tsk->thread.vstate_ctrl |= ctrl; +} + +bool riscv_v_vstate_ctrl_user_allowed(void) +{ + return riscv_v_ctrl_get_cur(current) == PR_RISCV_V_VSTATE_CTRL_ON; +} +EXPORT_SYMBOL_GPL(riscv_v_vstate_ctrl_user_allowed); + +bool riscv_v_first_use_handler(struct pt_regs *regs) +{ + u32 __user *epc = (u32 __user *)regs->epc; + u32 insn = (u32)regs->badaddr; + + /* Do not handle if V is not supported, or disabled */ + if (!(ELF_HWCAP & COMPAT_HWCAP_ISA_V)) + return false; + + /* If V has been enabled then it is not the first-use trap */ + if (riscv_v_vstate_query(regs)) + return false; + + /* Get the instruction */ + if (!insn) { + if (__get_user(insn, epc)) + return false; + } + + /* Filter out non-V instructions */ + if (!insn_is_vector(insn)) + return false; + + /* Sanity check. datap should be null by the time of the first-use trap */ + WARN_ON(current->thread.vstate.datap); + + /* + * Now we sure that this is a V instruction. And it executes in the + * context where VS has been off. So, try to allocate the user's V + * context and resume execution. + */ + if (riscv_v_thread_zalloc(riscv_v_user_cachep, ¤t->thread.vstate)) { + force_sig(SIGBUS); + return true; + } + riscv_v_vstate_on(regs); + riscv_v_vstate_set_restore(current, regs); + return true; +} + +void riscv_v_vstate_ctrl_init(struct task_struct *tsk) +{ + bool inherit; + int cur, next; + + if (!has_vector()) + return; + + next = riscv_v_ctrl_get_next(tsk); + if (!next) { + if (READ_ONCE(riscv_v_implicit_uacc)) + cur = PR_RISCV_V_VSTATE_CTRL_ON; + else + cur = PR_RISCV_V_VSTATE_CTRL_OFF; + } else { + cur = next; + } + /* Clear next mask if inherit-bit is not set */ + inherit = riscv_v_ctrl_test_inherit(tsk); + if (!inherit) + next = PR_RISCV_V_VSTATE_CTRL_DEFAULT; + + riscv_v_ctrl_set(tsk, cur, next, inherit); +} + +long riscv_v_vstate_ctrl_get_current(void) +{ + if (!has_vector()) + return -EINVAL; + + return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK; +} + +long riscv_v_vstate_ctrl_set_current(unsigned long arg) +{ + bool inherit; + int cur, next; + + if (!has_vector()) + return -EINVAL; + + if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK) + return -EINVAL; + + cur = VSTATE_CTRL_GET_CUR(arg); + switch (cur) { + case PR_RISCV_V_VSTATE_CTRL_OFF: + /* Do not allow user to turn off V if current is not off */ + if (riscv_v_ctrl_get_cur(current) != PR_RISCV_V_VSTATE_CTRL_OFF) + return -EPERM; + + break; + case PR_RISCV_V_VSTATE_CTRL_ON: + break; + case PR_RISCV_V_VSTATE_CTRL_DEFAULT: + cur = riscv_v_ctrl_get_cur(current); + break; + default: + return -EINVAL; + } + + next = VSTATE_CTRL_GET_NEXT(arg); + inherit = VSTATE_CTRL_GET_INHERIT(arg); + switch (next) { + case PR_RISCV_V_VSTATE_CTRL_DEFAULT: + case PR_RISCV_V_VSTATE_CTRL_OFF: + case PR_RISCV_V_VSTATE_CTRL_ON: + riscv_v_ctrl_set(current, cur, next, inherit); + return 0; + } + + return -EINVAL; +} + +#ifdef CONFIG_SYSCTL + +static struct ctl_table riscv_v_default_vstate_table[] = { + { + .procname = "riscv_v_default_allow", + .data = &riscv_v_implicit_uacc, + .maxlen = sizeof(riscv_v_implicit_uacc), + .mode = 0644, + .proc_handler = proc_dobool, + }, +}; + +static int __init riscv_v_sysctl_init(void) +{ + if (has_vector()) + if (!register_sysctl("abi", riscv_v_default_vstate_table)) + return -EINVAL; + return 0; +} + +#else /* ! CONFIG_SYSCTL */ +static int __init riscv_v_sysctl_init(void) { return 0; } +#endif /* ! CONFIG_SYSCTL */ + +static int riscv_v_init(void) +{ + return riscv_v_sysctl_init(); +} +core_initcall(riscv_v_init); diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S new file mode 100644 index 000000000000..8c3daa1b0531 --- /dev/null +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + * Copyright (C) 2020 Vitaly Wool, Konsulko AB + */ + +#include <asm/pgtable.h> +#define LOAD_OFFSET KERNEL_LINK_ADDR +/* No __ro_after_init data in the .rodata section - which will always be ro */ +#define RO_AFTER_INIT_DATA + +#include <asm/vmlinux.lds.h> +#include <asm/page.h> +#include <asm/cache.h> +#include <asm/thread_info.h> + +OUTPUT_ARCH(riscv) +ENTRY(_start) + +jiffies = jiffies_64; + +SECTIONS +{ + /* Beginning of code and text segment */ + . = LOAD_OFFSET; + _xiprom = .; + _start = .; + HEAD_TEXT_SECTION + INIT_TEXT_SECTION(PAGE_SIZE) + /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; + .exit.text : + { + EXIT_TEXT + } + __exittext_end = .; + + .text : { + _text = .; + _stext = .; + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + ENTRY_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT + _etext = .; + } + RO_DATA(L1_CACHE_BYTES) + .srodata : { + *(.srodata*) + } + .init.rodata : { + INIT_SETUP(16) + INIT_CALLS + CON_INITCALL + INIT_RAM_FS + } + _exiprom = .; /* End of XIP ROM area */ + + +/* + * From this point, stuff is considered writable and will be copied to RAM + */ + __data_loc = ALIGN(PAGE_SIZE); /* location in file */ + . = KERNEL_LINK_ADDR + XIP_OFFSET; /* location in memory */ + +#undef LOAD_OFFSET +#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK)) + + _sdata = .; /* Start of data section */ + _data = .; + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) + _edata = .; + __start_ro_after_init = .; + .data.ro_after_init : AT(ADDR(.data.ro_after_init) - LOAD_OFFSET) { + *(.data..ro_after_init) + } + __end_ro_after_init = .; + + . = ALIGN(PAGE_SIZE); + __init_begin = .; + .init.data : { + INIT_DATA + } + .exit.data : { + EXIT_DATA + } + . = ALIGN(8); + __soc_early_init_table : { + __soc_early_init_table_start = .; + KEEP(*(__soc_early_init_table)) + __soc_early_init_table_end = .; + } + __soc_builtin_dtb_table : { + __soc_builtin_dtb_table_start = .; + KEEP(*(__soc_builtin_dtb_table)) + __soc_builtin_dtb_table_end = .; + } + + __init_end = .; + + . = ALIGN(16); + .xip.traps : { + __xip_traps_start = .; + *(.xip.traps) + __xip_traps_end = .; + } + + . = ALIGN(PAGE_SIZE); + .sdata : { + __global_pointer$ = . + 0x800; + *(.sdata*) + *(.sbss*) + } + + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + + PERCPU_SECTION(L1_CACHE_BYTES) + + .rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) { + *(.rel.dyn*) + } + + /* + * End of copied data. We need a dummy section to get its LMA. + * Also located before final ALIGN() as trailing padding is not stored + * in the resulting binary file and useless to copy. + */ + .data.endmark : AT(ADDR(.data.endmark) - LOAD_OFFSET) { } + _edata_loc = LOADADDR(.data.endmark); + + . = ALIGN(PAGE_SIZE); + _end = .; + + STABS_DEBUG + DWARF_DEBUG + + DISCARDS +} diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 12f42f96d46e..002ca58dd998 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -4,12 +4,24 @@ * Copyright (C) 2017 SiFive */ -#define LOAD_OFFSET PAGE_OFFSET +#define RO_EXCEPTION_TABLE_ALIGN 4 +#define RUNTIME_DISCARD_EXIT + +#ifdef CONFIG_XIP_KERNEL +#include "vmlinux-xip.lds.S" +#else + +#include <asm/pgtable.h> +#define LOAD_OFFSET KERNEL_LINK_ADDR + #include <asm/vmlinux.lds.h> #include <asm/page.h> #include <asm/cache.h> #include <asm/thread_info.h> +#include <asm/set_memory.h> +#include "image-vars.h" +#include <linux/sizes.h> OUTPUT_ARCH(riscv) ENTRY(_start) @@ -20,64 +32,144 @@ SECTIONS /* Beginning of code and text segment */ . = LOAD_OFFSET; _start = .; - __init_begin = .; HEAD_TEXT_SECTION - INIT_TEXT_SECTION(PAGE_SIZE) - INIT_DATA_SECTION(16) - /* we have to discard exit text and such at runtime, not link time */ - .exit.text : - { - EXIT_TEXT - } - .exit.data : - { - EXIT_DATA - } - PERCPU_SECTION(L1_CACHE_BYTES) - __init_end = .; + . = ALIGN(PAGE_SIZE); .text : { _text = .; _stext = .; TEXT_TEXT SCHED_TEXT - CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT ENTRY_TEXT IRQENTRY_TEXT - *(.fixup) + SOFTIRQENTRY_TEXT _etext = .; } + . = ALIGN(SECTION_ALIGN); + __init_begin = .; + __init_text_begin = .; + .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) ALIGN(SECTION_ALIGN) { \ + _sinittext = .; \ + INIT_TEXT \ + _einittext = .; \ + } + + . = ALIGN(8); + __soc_early_init_table : { + __soc_early_init_table_start = .; + KEEP(*(__soc_early_init_table)) + __soc_early_init_table_end = .; + } + __soc_builtin_dtb_table : { + __soc_builtin_dtb_table_start = .; + KEEP(*(__soc_builtin_dtb_table)) + __soc_builtin_dtb_table_end = .; + } + /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; + .exit.text : + { + EXIT_TEXT + } + __exittext_end = .; + + __init_text_end = .; + . = ALIGN(SECTION_ALIGN); +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_text_end = .; +#endif + /* Start of init data section */ + __init_data_begin = .; + INIT_DATA_SECTION(16) + + .init.pi : { + KEEP(*(.init.pi*)) + } + + .init.bss : { + KEEP(*(.init.bss*)) /* from the EFI stub */ + } + .exit.data : + { + EXIT_DATA + } + PERCPU_SECTION(L1_CACHE_BYTES) + + .rel.dyn : { + *(.rel.dyn*) + } + + .rela.dyn : ALIGN(8) { + __rela_dyn_start = .; + *(.rela .rela*) + __rela_dyn_end = .; + } + + __init_data_end = .; + + . = ALIGN(8); + .alternative : { + __alt_start = .; + KEEP(*(.alternative)) + __alt_end = .; + } + __init_end = .; + /* Start of data section */ _sdata = .; - RO_DATA(L1_CACHE_BYTES) + RO_DATA(SECTION_ALIGN) .srodata : { *(.srodata*) } - RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) + . = ALIGN(SECTION_ALIGN); + _data = .; + + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) .sdata : { __global_pointer$ = . + 0x800; *(.sdata*) - /* End of data section */ - _edata = .; - *(.sbss*) } - BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + .got : { *(.got*) } - EXCEPTION_TABLE(0x10) +#ifdef CONFIG_RELOCATABLE + .data.rel : { *(.data.rel*) } + .plt : { *(.plt) } + .dynamic : { *(.dynamic) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .hash : { *(.hash) } + .gnu.hash : { *(.gnu.hash) } +#endif - .rel.dyn : { - *(.rel.dyn*) - } +#ifdef CONFIG_EFI + .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } + __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end); + __pecoff_data_raw_end = ABSOLUTE(.); +#endif + + /* End of data section */ + _edata = .; + + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end); + __pecoff_data_virt_end = ABSOLUTE(.); +#endif _end = .; STABS_DEBUG DWARF_DEBUG + ELF_DETAILS + .riscv.attributes 0 : { *(.riscv.attributes) } DISCARDS } +#endif /* CONFIG_XIP_KERNEL */ |