diff options
Diffstat (limited to 'arch/riscv/kernel')
26 files changed, 858 insertions, 429 deletions
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 506cc4a9a45a..95cf25d48405 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -38,6 +38,7 @@ extra-y += vmlinux.lds obj-y += head.o obj-y += soc.o obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o +obj-y += copy-unaligned.o obj-y += cpu.o obj-y += cpufeature.o obj-y += entry.o @@ -91,6 +92,8 @@ obj-$(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 diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 5ee03ebab80e..56cb2c986c48 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -215,9 +215,9 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size) early_iounmap(map, size); } -void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { - return memremap(phys, size, MEMREMAP_WB); + return (void __iomem *)memremap(phys, size, MEMREMAP_WB); } #ifdef CONFIG_PCI diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index 6b75788c18e6..85056153fa23 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -27,8 +27,6 @@ struct cpu_manufacturer_info_t { void (*patch_func)(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); - void (*feature_probe_func)(unsigned int cpu, unsigned long archid, - unsigned long impid); }; static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) @@ -43,7 +41,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info cpu_mfr_info->imp_id = sbi_get_mimpid(); #endif - cpu_mfr_info->feature_probe_func = NULL; switch (cpu_mfr_info->vendor_id) { #ifdef CONFIG_ERRATA_SIFIVE case SIFIVE_VENDOR_ID: @@ -53,7 +50,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info #ifdef CONFIG_ERRATA_THEAD case THEAD_VENDOR_ID: cpu_mfr_info->patch_func = thead_errata_patch_func; - cpu_mfr_info->feature_probe_func = thead_feature_probe_func; break; #endif default: @@ -143,20 +139,6 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, } } -/* Called on each CPU as it starts */ -void probe_vendor_features(unsigned int cpu) -{ - struct cpu_manufacturer_info_t cpu_mfr_info; - - riscv_fill_cpu_mfr_info(&cpu_mfr_info); - if (!cpu_mfr_info.feature_probe_func) - return; - - cpu_mfr_info.feature_probe_func(cpu, - cpu_mfr_info.arch_id, - cpu_mfr_info.imp_id); -} - /* * 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 @@ -211,7 +193,6 @@ void __init apply_boot_alternatives(void) /* If called on non-boot cpu things could go wrong */ WARN_ON(smp_processor_id() != 0); - probe_vendor_features(0); _apply_alternatives((struct alt_entry *)__alt_start, (struct alt_entry *)__alt_end, RISCV_ALTERNATIVES_BOOT); diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c new file mode 100644 index 000000000000..820158d7a291 --- /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 <asm/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/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c index 651f2b009c28..ad7f2d712f5f 100644 --- a/arch/riscv/kernel/compat_syscall_table.c +++ b/arch/riscv/kernel/compat_syscall_table.c @@ -9,11 +9,15 @@ #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, asmlinkage long compat_sys_rt_sigreturn(void); void * const compat_sys_call_table[__NR_syscalls] = { - [0 ... __NR_syscalls - 1] = sys_ni_syscall, + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 189345773e7e..b86e5e2c3aea 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -11,7 +11,13 @@ compat_vdso-syms += flush_icache COMPAT_CC := $(CC) COMPAT_LD := $(LD) -COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +# 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. diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S new file mode 100644 index 000000000000..cfdecfbaad62 --- /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 */ +ENTRY(__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 +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 */ +ENTRY(__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 +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.c b/arch/riscv/kernel/cpu.c index a2fc952318e9..c17dacb1141c 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -17,6 +17,11 @@ #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. @@ -41,7 +46,7 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) return 0; } -int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) +int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) { const char *isa; @@ -61,16 +66,53 @@ int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *har 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=%lu 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)) + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv32ima", *hart); return -ENODEV; + } - if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv64ima", *hart); return -ENODEV; + } return 0; } @@ -160,132 +202,46 @@ arch_initcall(riscv_cpuinfo_init); #ifdef CONFIG_PROC_FS -#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \ - { \ - .uprop = #UPROP, \ - .isa_ext_id = EXTID, \ - } - -/* - * 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. - */ -static struct riscv_isa_ext_data isa_ext_arr[] = { - __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(zicsr, RISCV_ISA_EXT_ZICSR), - __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), - __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), - __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), - __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), - __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), - __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), - __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), - __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), - __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), -}; - -static void print_isa_ext(struct seq_file *f) +static void print_isa(struct seq_file *f) { - struct riscv_isa_ext_data *edata; - int i = 0, arr_sz; - - arr_sz = ARRAY_SIZE(isa_ext_arr) - 1; + seq_puts(f, "isa\t\t: "); - /* No extension support available */ - if (arr_sz <= 0) - return; + if (IS_ENABLED(CONFIG_32BIT)) + seq_write(f, "rv32", 4); + else + seq_write(f, "rv64", 4); - for (i = 0; i <= arr_sz; i++) { - edata = &isa_ext_arr[i]; - if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id)) + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id)) continue; - seq_printf(f, "_%s", edata->uprop); - } -} - -/* - * These are the only valid base (single letter) ISA extensions as per the spec. - * It also specifies the canonical order in which it appears in the spec. - * Some of the extension may just be a place holder for now (B, K, P, J). - * This should be updated once corresponding extensions are ratified. - */ -static const char base_riscv_exts[13] = "imafdqcbkjpvh"; -static void print_isa(struct seq_file *f, const char *isa) -{ - int i; + /* Only multi-letter extensions are split by underscores */ + if (strnlen(riscv_isa_ext[i].name, 2) != 1) + seq_puts(f, "_"); - seq_puts(f, "isa\t\t: "); - /* Print the rv[64/32] part */ - seq_write(f, isa, 4); - for (i = 0; i < sizeof(base_riscv_exts); i++) { - if (__riscv_isa_extension_available(NULL, base_riscv_exts[i] - 'a')) - /* Print only enabled the base ISA extensions */ - seq_write(f, &base_riscv_exts[i], 1); + seq_printf(f, "%s", riscv_isa_ext[i].name); } - print_isa_ext(f); + seq_puts(f, "\n"); } static void print_mmu(struct seq_file *f) { - char sv_type[16]; + const char *sv_type; #ifdef CONFIG_MMU #if defined(CONFIG_32BIT) - strncpy(sv_type, "sv32", 5); + sv_type = "sv32"; #elif defined(CONFIG_64BIT) if (pgtable_l5_enabled) - strncpy(sv_type, "sv57", 5); + sv_type = "sv57"; else if (pgtable_l4_enabled) - strncpy(sv_type, "sv48", 5); + sv_type = "sv48"; else - strncpy(sv_type, "sv39", 5); + sv_type = "sv39"; #endif #else - strncpy(sv_type, "none", 5); + sv_type = "none"; #endif /* CONFIG_MMU */ seq_printf(f, "mmu\t\t: %s\n", sv_type); } @@ -316,27 +272,21 @@ static int c_show(struct seq_file *m, void *v) unsigned long cpu_id = (unsigned long)v - 1; struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); struct device_node *node; - const char *compat, *isa; + 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)); + print_isa(m); + print_mmu(m); if (acpi_disabled) { node = of_get_cpu_node(cpu_id, NULL); - if (!of_property_read_string(node, "riscv,isa", &isa)) - print_isa(m, isa); - print_mmu(m); if (!of_property_read_string(node, "compatible", &compat) && strcmp(compat, "riscv")) seq_printf(m, "uarch\t\t: %s\n", compat); of_node_put(node); - } else { - if (!acpi_get_riscv_isa(NULL, cpu_id, &isa)) - print_isa(m, isa); - - print_mmu(m); } seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index bdcf460ea53d..1cfbba65d11a 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -13,18 +13,24 @@ #include <linux/memory.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_device.h> #include <asm/acpi.h> #include <asm/alternative.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.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_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) + unsigned long elf_hwcap __read_mostly; /* Host ISA bitmap */ @@ -99,29 +105,252 @@ static bool riscv_isa_extension_check(int id) return true; } -void __init riscv_fill_hwcap(void) +#define __RISCV_ISA_EXT_DATA(_name, _id) { \ + .name = #_name, \ + .property = #_name, \ + .id = _id, \ +} + +/* + * 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(b, RISCV_ISA_EXT_b), + __RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k), + __RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j), + __RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p), + __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(zicsr, RISCV_ISA_EXT_ZICSR), + __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), + __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), + __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), + __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), + __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), + __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), + __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 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 until multi-letter + * extension starting with "Su" appears. + */ + 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; + +#define SET_ISA_EXT_MAP(name, bit) \ + do { \ + if ((ext_end - ext == strlen(name)) && \ + !strncasecmp(ext, name, strlen(name)) && \ + riscv_isa_extension_check(bit)) \ + set_bit(bit, isainfo->isa); \ + } while (false) \ + + 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++) + SET_ISA_EXT_MAP(riscv_isa_ext[i].name, + riscv_isa_ext[i].id); + } +#undef SET_ISA_EXT_MAP + } +} + +static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) { struct device_node *node; const char *isa; - char print_str[NUM_ALPHA_EXTS + 1]; - int i, j, rc; - unsigned long isa2hwcap[26] = {0}; + int rc; struct acpi_table_header *rhct; acpi_status status; unsigned int cpu; - 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; - - elf_hwcap = 0; - - bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); - if (!acpi_disabled) { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); if (ACPI_FAILURE(status)) @@ -153,176 +382,7 @@ void __init riscv_fill_hwcap(void) } } - /* - * 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 until multi-letter - * extension starting with "Su" appears. - */ - 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; - -#define SET_ISA_EXT_MAP(name, bit) \ - do { \ - if ((ext_end - ext == sizeof(name) - 1) && \ - !strncasecmp(ext, name, sizeof(name) - 1) && \ - riscv_isa_extension_check(bit)) \ - set_bit(bit, isainfo->isa); \ - } while (false) \ - - 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 { - /* sorted alphabetically */ - SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA); - SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA); - SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF); - SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC); - SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL); - SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT); - SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); - SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA); - SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB); - SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS); - SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM); - SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ); - SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE); - } -#undef SET_ISA_EXT_MAP - } - - /* - * Linux requires the following extensions, so we may as well - * always set them. - */ - set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); - set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); + riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa); /* * These ones were as they were part of the base ISA when the @@ -330,6 +390,8 @@ void __init riscv_fill_hwcap(void) * 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); } @@ -352,9 +414,107 @@ void __init riscv_fill_hwcap(void) 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++) { + if (of_property_match_string(cpu_node, "riscv,isa-extensions", + riscv_isa_ext[i].property) < 0) + continue; + + if (!riscv_isa_extension_check(riscv_isa_ext[i].id)) + continue; + + /* 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]; + + set_bit(riscv_isa_ext[i].id, isainfo->isa); + } + + 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); + } - /* We don't support systems with F but without D, so mask those out - * here. */ + 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; @@ -396,6 +556,103 @@ unsigned long riscv_get_elf_hwcap(void) return hwcap; } +void check_unaligned_access(int cpu) +{ + u64 start_cycles, end_cycles; + u64 word_cycles; + u64 byte_cycles; + int ratio; + unsigned long start_jiffies, now; + struct page *page; + void *dst; + void *src; + long speed = RISCV_HWPROBE_MISALIGNED_SLOW; + + page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE)); + if (!page) { + pr_warn("Can't alloc pages to measure memcpy performance"); + return; + } + + /* Make an unaligned destination buffer. */ + dst = (void *)((unsigned long)page_address(page) | 0x1); + /* Unalign src as well, but differently (off by 1 + 2 = 3). */ + src = dst + (MISALIGNED_BUFFER_SIZE / 2); + src += 2; + word_cycles = -1ULL; + /* Do a warmup. */ + __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); + + goto out; + } + + 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; + +out: + __free_pages(page, get_order(MISALIGNED_BUFFER_SIZE)); +} + +static int check_unaligned_access_boot_cpu(void) +{ + check_unaligned_access(0); + return 0; +} + +arch_initcall(check_unaligned_access_boot_cpu); + #ifdef CONFIG_RISCV_ALTERNATIVE /* * Alternative patch sites consider 48 bits when determining when to patch diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index b351a3c01355..55f1d7856b54 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -18,4 +18,6 @@ void arch_crash_save_vmcoreinfo(void) vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); #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/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..f4099059ed8f 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -260,7 +260,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, cmdline = modified_cmdline; } -#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY +#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY /* Add purgatory to the image */ kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; @@ -274,14 +274,14 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, sizeof(kernel_start), 0); if (ret) pr_err("Error update purgatory ret=%d\n", ret); -#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */ +#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 = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * 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); diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 11c3b94c4534..3710ea5d160f 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -289,10 +289,6 @@ clear_bss: blt a3, a4, clear_bss clear_bss_done: #endif - /* Save hart ID and DTB physical address */ - mv s0, a0 - mv s1, a1 - la a2, boot_cpu_hartid XIP_FIXUP_OFFSET a2 REG_S a0, (a2) @@ -306,7 +302,7 @@ clear_bss_done: la a0, __dtb_start XIP_FIXUP_OFFSET a0 #else - mv a0, s1 + mv a0, a1 #endif /* CONFIG_BUILTIN_DTB */ call setup_vm #ifdef CONFIG_MMU diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index d0577cc6a081..a8efa053c4a5 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -84,6 +84,9 @@ void do_softirq_own_stack(void) : [sp] "r" (sp) : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", "t0", "t1", "t2", "t3", "t4", "t5", "t6", +#ifndef CONFIG_FRAME_POINTER + "s0", +#endif "memory"); } else #endif diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 8a6e5a9e842a..8818a8fa9ff3 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/asm.h> #include <asm/csr.h> #include <asm/unistd.h> @@ -47,15 +48,19 @@ addi sp, sp, 4*SZREG .endm -ENTRY(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub) #ifdef CONFIG_DYNAMIC_FTRACE .global MCOUNT_NAME .set MCOUNT_NAME, ftrace_stub #endif ret -ENDPROC(ftrace_stub) +SYM_FUNC_END(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + ENTRY(return_to_handler) /* * On implementing the frame point test, the ideal way is to compare the diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c index 64f6183b4717..65d9590bfb9f 100644 --- a/arch/riscv/kernel/probes/decode-insn.c +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -29,13 +29,14 @@ riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) * TODO: the REJECTED ones below need to be implemented */ #ifdef CONFIG_RISCV_ISA_C - RISCV_INSN_REJECTED(c_j, insn); - RISCV_INSN_REJECTED(c_jr, insn); RISCV_INSN_REJECTED(c_jal, insn); - RISCV_INSN_REJECTED(c_jalr, insn); - RISCV_INSN_REJECTED(c_beqz, insn); - RISCV_INSN_REJECTED(c_bnez, 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); diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index 7441ac8a6843..d3099d67816d 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -188,3 +188,108 @@ bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *r 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 index 61e35db31001..44ebbc444db9 100644 --- a/arch/riscv/kernel/probes/simulate-insn.h +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -24,5 +24,10 @@ 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/ptrace.c b/arch/riscv/kernel/ptrace.c index 1d572cf3140f..487303e3ef22 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -25,9 +25,6 @@ enum riscv_regset { #ifdef CONFIG_FPU REGSET_F, #endif -#ifdef CONFIG_RISCV_ISA_V - REGSET_V, -#endif }; static int riscv_gpr_get(struct task_struct *target, @@ -84,61 +81,6 @@ 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; - - 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) - riscv_v_vstate_save(current, task_pt_regs(current)); - - /* Copy vector header from vstate. */ - membuf_write(&to, vstate, offsetof(struct __riscv_v_ext_state, datap)); - membuf_zero(&to, sizeof(vstate->datap)); - - /* 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, size; - struct __riscv_v_ext_state *vstate = &target->thread.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, vstate, 0, - offsetof(struct __riscv_v_ext_state, datap)); - if (unlikely(ret)) - return ret; - - /* Skip copy datap. */ - size = sizeof(vstate->datap); - count -= size; - ubuf += size; - - /* 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, @@ -158,17 +100,6 @@ static const struct user_regset riscv_user_regset[] = { .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_ext_state)) / sizeof(__u32), - .size = sizeof(__u32), - .regset_get = riscv_vr_get, - .set = riscv_vr_set, - }, -#endif }; static const struct user_regset_view riscv_user_native_view = { diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 971fe776e2f8..32c2e1eb71bd 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -178,6 +178,11 @@ static void __init init_resources(void) if (ret < 0) goto error; } + if (crashk_low_res.start != crashk_low_res.end) { + ret = add_resource(&iomem_resource, &crashk_low_res); + if (ret < 0) + goto error; + } #endif #ifdef CONFIG_CRASH_DUMP @@ -311,6 +316,7 @@ void __init setup_arch(char **cmdline_p) if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && riscv_isa_extension_available(NULL, ZICBOM)) riscv_noncoherent_supported(); + riscv_set_dma_cache_alignment(); } static int __init topology_init(void) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 85bbce0f758c..40420afbb1a0 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -61,11 +61,6 @@ int riscv_hartid_to_cpuid(unsigned long hartid) return -ENOENT; } -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == cpuid_to_hartid_map(cpu); -} - static void ipi_stop(void) { set_cpu_online(smp_processor_id(), false); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index f4d6acb38dd0..1b8da4e40a4d 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -26,6 +26,7 @@ #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> #include <asm/cpu_ops.h> +#include <asm/cpufeature.h> #include <asm/irq.h> #include <asm/mmu_context.h> #include <asm/numa.h> @@ -245,7 +246,7 @@ asmlinkage __visible void smp_callin(void) numa_add_cpu(curr_cpuid); set_cpu_online(curr_cpuid, 1); - probe_vendor_features(curr_cpuid); + check_unaligned_access(curr_cpuid); if (has_vector()) { if (riscv_v_setup_vsize()) diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S index 12b52afe09a4..f7960c7c5f9e 100644 --- a/arch/riscv/kernel/suspend_entry.S +++ b/arch/riscv/kernel/suspend_entry.S @@ -5,6 +5,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> @@ -58,7 +59,7 @@ ENTRY(__cpu_suspend_enter) ret END(__cpu_suspend_enter) -ENTRY(__cpu_resume_enter) +SYM_TYPED_FUNC_START(__cpu_resume_enter) /* Load the global pointer */ .option push .option norelax @@ -94,4 +95,4 @@ ENTRY(__cpu_resume_enter) /* Return to C code */ ret -END(__cpu_resume_enter) +SYM_FUNC_END(__cpu_resume_enter) diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 26ef5526bfb4..473159b5f303 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -335,3 +335,9 @@ SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, return do_riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags); } + +/* 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 44b1420a2270..dda913764903 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -10,9 +10,13 @@ #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 * const sys_call_table[__NR_syscalls] = { - [0 ... __NR_syscalls - 1] = sys_ni_syscall, + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f910dfccbf5d..19807c4d3805 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -21,6 +21,7 @@ #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> @@ -271,7 +272,8 @@ void handle_break(struct pt_regs *regs) == NOTIFY_STOP) return; #endif - else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN) + 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"); @@ -297,7 +299,7 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) { if (user_mode(regs)) { - ulong syscall = regs->a7; + long syscall = regs->a7; regs->epc += 4; regs->orig_a0 = regs->a0; @@ -306,9 +308,9 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) syscall = syscall_enter_from_user_mode(regs, syscall); - if (syscall < NR_syscalls) + if (syscall >= 0 && syscall < NR_syscalls) syscall_handler(regs, syscall); - else + else if (syscall != -1) regs->a0 = -ENOSYS; syscall_exit_to_user_mode(regs); @@ -372,6 +374,9 @@ asmlinkage void noinstr do_irq(struct pt_regs *regs) : [sp] "r" (sp), [regs] "r" (regs) : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", "t0", "t1", "t2", "t3", "t4", "t5", "t6", +#ifndef CONFIG_FRAME_POINTER + "s0", +#endif "memory"); } else #endif |