diff options
56 files changed, 734 insertions, 538 deletions
diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt index 1638c2cb17f1..c0a2d8f56046 100644 --- a/Documentation/features/vm/ioremap_prot/arch-support.txt +++ b/Documentation/features/vm/ioremap_prot/arch-support.txt @@ -20,7 +20,7 @@ | openrisc: | TODO | | parisc: | TODO | | powerpc: | ok | - | riscv: | TODO | + | riscv: | ok | | s390: | ok | | sh: | ok | | sparc: | TODO | diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 53da3457a539..d235396c4514 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -47,8 +47,8 @@ config RISCV select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_DIRECT_MAP if MMU select ARCH_HAS_SET_MEMORY if MMU - select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL - select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL + select ARCH_HAS_STRICT_KERNEL_RWX if MMU + select ARCH_HAS_STRICT_MODULE_RWX if MMU select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST @@ -84,7 +84,7 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT select ARCH_WANT_HUGE_PMD_SHARE if 64BIT - select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_NO_INSTR @@ -112,6 +112,7 @@ config RISCV select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO && 64BIT select GENERIC_IDLE_POLL_SETUP select GENERIC_IOREMAP if MMU + select HAVE_IOREMAP_PROT if MMU select GENERIC_IRQ_IPI if SMP select GENERIC_IRQ_IPI_MUX if SMP select GENERIC_IRQ_MULTI_HANDLER @@ -129,13 +130,13 @@ config RISCV select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT - select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL - select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL + select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if MMU && 64BIT select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT select HAVE_ARCH_KFENCE if MMU && 64BIT select HAVE_ARCH_KSTACK_ERASE - select HAVE_ARCH_KGDB if !XIP_KERNEL + select HAVE_ARCH_KGDB select HAVE_ARCH_KGDB_QXFER_PKT select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -153,7 +154,7 @@ config RISCV select HAVE_CONTEXT_TRACKING_USER select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU - select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) + select HAVE_DYNAMIC_FTRACE if MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) select FUNCTION_ALIGNMENT_4B if HAVE_DYNAMIC_FTRACE && RISCV_ISA_C select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI) @@ -161,7 +162,7 @@ config RISCV select HAVE_FTRACE_GRAPH_FUNC select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_FUNCTION_GRAPH_FREGS - select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE + select HAVE_FUNCTION_TRACER if HAVE_DYNAMIC_FTRACE select HAVE_EBPF_JIT if MMU select HAVE_GENERIC_TIF_BITS select HAVE_GUP_FAST if MMU @@ -170,16 +171,16 @@ config RISCV select HAVE_GCC_PLUGINS select HAVE_GENERIC_VDSO if MMU select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_KERNEL_BZIP2 if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_GZIP if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_LZ4 if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_LZMA if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_LZO if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_UNCOMPRESSED if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_ZSTD if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KERNEL_XZ if !XIP_KERNEL && !EFI_ZBOOT - select HAVE_KPROBES if !XIP_KERNEL - select HAVE_KRETPROBES if !XIP_KERNEL + select HAVE_KERNEL_BZIP2 if !EFI_ZBOOT + select HAVE_KERNEL_GZIP if !EFI_ZBOOT + select HAVE_KERNEL_LZ4 if !EFI_ZBOOT + select HAVE_KERNEL_LZMA if !EFI_ZBOOT + select HAVE_KERNEL_LZO if !EFI_ZBOOT + select HAVE_KERNEL_UNCOMPRESSED if !EFI_ZBOOT + select HAVE_KERNEL_ZSTD if !EFI_ZBOOT + select HAVE_KERNEL_XZ if !EFI_ZBOOT + select HAVE_KPROBES + select HAVE_KRETPROBES # https://github.com/ClangBuiltLinux/linux/issues/1881 select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD select HAVE_MOVE_PMD @@ -190,9 +191,9 @@ config RISCV select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_POSIX_CPU_TIMERS_TASK_WORK - select HAVE_PREEMPT_DYNAMIC_KEY if !XIP_KERNEL + select HAVE_PREEMPT_DYNAMIC_KEY select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RETHOOK if !XIP_KERNEL + select HAVE_RETHOOK select HAVE_RSEQ select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG select HAVE_SAMPLE_FTRACE_DIRECT @@ -213,7 +214,7 @@ config RISCV select PCI_ECAM if (ACPI && PCI) select PCI_MSI if PCI select RELOCATABLE if !MMU && !PHYS_RAM_BASE_FIXED - select RISCV_ALTERNATIVE if !XIP_KERNEL + select RISCV_ALTERNATIVE select RISCV_APLIC select RISCV_IMSIC select RISCV_INTC @@ -537,7 +538,6 @@ endchoice config RISCV_ALTERNATIVE bool - depends on !XIP_KERNEL help This Kconfig allows the kernel to automatically patch the erratum or cpufeature required by the execution platform at run @@ -1126,7 +1126,6 @@ config PARAVIRT_TIME_ACCOUNTING config RELOCATABLE bool "Build a relocatable kernel" - depends on !XIP_KERNEL select MODULE_SECTIONS if MODULES select ARCH_VMLINUX_NEEDS_RELOCS help @@ -1143,7 +1142,7 @@ config RELOCATABLE config RANDOMIZE_BASE bool "Randomize the address of the kernel image" select RELOCATABLE - depends on MMU && 64BIT && !XIP_KERNEL + depends on MMU && 64BIT help Randomizes the virtual address at which the kernel image is loaded, as a security feature that deters exploit attempts @@ -1233,7 +1232,7 @@ config EFI_STUB config EFI bool "UEFI runtime support" - depends on OF && !XIP_KERNEL + depends on OF depends on MMU default y select ARCH_SUPPORTS_ACPI if 64BIT @@ -1284,44 +1283,6 @@ config PHYS_RAM_BASE explicitly specified to run early relocations of read-write data from flash to RAM. -config XIP_KERNEL - bool "Kernel Execute-In-Place from ROM" - depends on MMU && SPARSEMEM && NONPORTABLE - # This prevents XIP from being enabled by all{yes,mod}config, which - # fail to build since XIP doesn't support large kernels. - depends on !COMPILE_TEST - select PHYS_RAM_BASE_FIXED - help - Execute-In-Place allows the kernel to run from non-volatile storage - directly addressable by the CPU, such as NOR flash. This saves RAM - space since the text section of the kernel is not loaded from flash - to RAM. Read-write sections, such as the data section and stack, - are still copied to RAM. The XIP kernel is not compressed since - it has to run directly from flash, so it will take more space to - store it. The flash address used to link the kernel object files, - and for storing it, is configuration dependent. Therefore, if you - say Y here, you must know the proper physical address where to - store the kernel image depending on your own flash memory usage. - - Also note that the make target becomes "make xipImage" rather than - "make zImage" or "make Image". The final kernel binary to put in - ROM memory will be arch/riscv/boot/xipImage. - - SPARSEMEM is required because the kernel text and rodata that are - flash resident are not backed by memmap, then any attempt to get - a struct page on those regions will trigger a fault. - - If unsure, say N. - -config XIP_PHYS_ADDR - hex "XIP Kernel Physical Location" - depends on XIP_KERNEL - default "0x21000000" - help - This is the physical address in your flash memory the kernel will - be linked for and stored to. This address is dependent on your - own flash usage. - config RISCV_ISA_FALLBACK bool "Permit falling back to parsing riscv,isa for extension support by default" default y diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index d621b85dd63b..c174ac0ec46b 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -2,7 +2,7 @@ menu "SoC selection" config ARCH_ANDES bool "Andes SoCs" - depends on MMU && !XIP_KERNEL + depends on MMU select ERRATA_ANDES help This enables support for Andes SoC platform hardware. @@ -33,7 +33,7 @@ config ARCH_RENESAS config ARCH_SIFIVE bool "SiFive SoCs" - select ERRATA_SIFIVE if !XIP_KERNEL + select ERRATA_SIFIVE help This enables support for SiFive SoC platform hardware. @@ -61,7 +61,7 @@ config SOC_STARFIVE config ARCH_SUNXI bool "Allwinner sun20i SoCs" - depends on MMU && !XIP_KERNEL + depends on MMU select ERRATA_THEAD select SUN4I_TIMER help @@ -78,7 +78,7 @@ config ARCH_TENSTORRENT config ARCH_THEAD bool "T-HEAD RISC-V SoCs" - depends on MMU && !XIP_KERNEL + depends on MMU select ERRATA_THEAD select PM_GENERIC_DOMAINS if PM help diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 371da75a47f9..ce0cc737f870 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -28,7 +28,6 @@ endif export BITS ifeq ($(CONFIG_ARCH_RV64I),y) BITS := 64 - UTS_MACHINE := riscv64 KBUILD_CFLAGS += -mabi=lp64 KBUILD_AFLAGS += -mabi=lp64 @@ -39,13 +38,14 @@ ifeq ($(CONFIG_ARCH_RV64I),y) -Cno-redzone else BITS := 32 - UTS_MACHINE := riscv32 KBUILD_CFLAGS += -mabi=ilp32 KBUILD_AFLAGS += -mabi=ilp32 KBUILD_LDFLAGS += -melf32lriscv endif +UTS_MACHINE := riscv$(BITS) + # LLVM has an issue with target-features and LTO: https://github.com/llvm/llvm-project/issues/59350 # Ensure it is aware of linker relaxation with LTO, otherwise relocations may # be incorrect: https://github.com/llvm/llvm-project/issues/65090 @@ -150,7 +150,6 @@ ifdef CONFIG_RISCV_M_MODE boot-image-$(CONFIG_SOC_CANAAN_K210) := loader.bin endif boot-image-$(CONFIG_EFI_ZBOOT) := vmlinuz.efi -boot-image-$(CONFIG_XIP_KERNEL) := xipImage KBUILD_IMAGE := $(boot)/$(boot-image-y) libs-y += arch/riscv/lib/ @@ -218,8 +217,6 @@ define archhelp echo ' Image.xz - Compressed kernel image (arch/riscv/boot/Image.xz)' echo ' vmlinuz.efi - Compressed EFI kernel image (arch/riscv/boot/vmlinuz.efi)' echo ' Default when CONFIG_EFI_ZBOOT=y' - echo ' xipImage - Execute-in-place kernel image (arch/riscv/boot/xipImage)' - echo ' Default when CONFIG_XIP_KERNEL=y' echo ' install - Install kernel using (your) ~/bin/$(INSTALLKERNEL) or' echo ' (distribution) /sbin/$(INSTALLKERNEL) or install to ' echo ' $$(INSTALL_PATH)' diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index 5301adf5f3f5..fcfbe3f814d6 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -20,17 +20,6 @@ OBJCOPYFLAGS_xipImage :=-O binary -R .note -R .note.gnu.build-id -R .comment -S targets := Image Image.* loader loader.o loader.lds loader.bin xipImage -ifeq ($(CONFIG_XIP_KERNEL),y) - -quiet_cmd_mkxip = $(quiet_cmd_objcopy) -cmd_mkxip = $(cmd_objcopy) - -$(obj)/xipImage: vmlinux FORCE - $(call if_changed,mkxip) - @$(kecho) ' Physical Address of xipImage: $(CONFIG_XIP_PHYS_ADDR)' - -endif - $(obj)/Image: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 0b942183f708..6f1c683f0ec0 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -153,7 +153,7 @@ static bool errata_probe_ghostwrite(unsigned int stage, * target-c9xx cores report arch_id and impid as 0 * * While ghostwrite may not affect all c9xx cores that implement - * xtheadvector, there is no futher granularity than c9xx. Assume + * xtheadvector, there is no further granularity than c9xx. Assume * vulnerable for this entire class of processors when xtheadvector is * enabled. */ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index 41ec5cdec367..5b90ba5314ee 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -40,6 +40,7 @@ asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs); #define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs) DECLARE_DO_ERROR_INFO(do_trap_unknown); +DECLARE_DO_ERROR_INFO(do_trap_hardware_error); DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned); DECLARE_DO_ERROR_INFO(do_trap_insn_fault); DECLARE_DO_ERROR_INFO(do_trap_insn_illegal); diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 3f33dc54f94b..616b8b332ac5 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -46,7 +46,7 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) #endif /* - * First, the atomic ops that have no ordering constraints and therefor don't + * First, the atomic ops that have no ordering constraints and therefore don't * have the AQ or RL bits set. These don't return anything, so there's only * one version to worry about. */ @@ -81,7 +81,7 @@ ATOMIC_OPS(xor, xor, i) /* * Atomic ops that have ordered, relaxed, acquire, and release variants. - * There's two flavors of these: the arithmatic ops have both fetch and return + * There's two flavors of these: the arithmetic ops have both fetch and return * versions, while the logical ops only have fetch versions. */ #define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix) \ diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index c7aea7886d22..aa4961b0e208 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -59,8 +59,8 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); #endif /* - * Provides information on the availiable set of ISA extensions to userspace, - * via a bitmap that coorespends to each single-letter ISA extension. This is + * Provides information on the available set of ISA extensions to userspace, + * via a bitmap that corresponds to each single-letter ISA extension. This is * essentially defunct, but will remain for compatibility with userspace. */ #define ELF_HWCAP riscv_get_elf_hwcap() diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index c78017061b17..709a36fb4323 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -29,11 +29,7 @@ #define PAGE_OFFSET_L5 _AC(0xff60000000000000, UL) #define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) #define PAGE_OFFSET_L3 _AC(0xffffffd600000000, UL) -#ifdef CONFIG_XIP_KERNEL -#define PAGE_OFFSET PAGE_OFFSET_L3 -#else #define PAGE_OFFSET kernel_map.page_offset -#endif /* CONFIG_XIP_KERNEL */ #else #define PAGE_OFFSET _AC(0xc0000000, UL) #endif /* CONFIG_64BIT */ @@ -104,15 +100,8 @@ struct kernel_mapping { /* Offset between linear mapping virtual address and kernel load address */ unsigned long va_pa_offset; /* Offset between kernel mapping virtual address and kernel load address */ -#ifdef CONFIG_XIP_KERNEL - unsigned long va_kernel_xip_text_pa_offset; - unsigned long va_kernel_xip_data_pa_offset; - uintptr_t xiprom; - uintptr_t xiprom_sz; -#else unsigned long page_offset; unsigned long va_kernel_pa_offset; -#endif }; extern struct kernel_mapping kernel_map; @@ -131,16 +120,7 @@ extern unsigned long vmemmap_start_pfn; void *linear_mapping_pa_to_va(unsigned long x); #endif -#ifdef CONFIG_XIP_KERNEL -#define kernel_mapping_pa_to_va(y) ({ \ - unsigned long _y = (unsigned long)(y); \ - (_y < phys_ram_base) ? \ - (void *)(_y + kernel_map.va_kernel_xip_text_pa_offset) : \ - (void *)(_y + kernel_map.va_kernel_xip_data_pa_offset); \ - }) -#else #define kernel_mapping_pa_to_va(y) ((void *)((unsigned long)(y) + kernel_map.va_kernel_pa_offset)) -#endif #define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x) @@ -150,16 +130,7 @@ void *linear_mapping_pa_to_va(unsigned long x); phys_addr_t linear_mapping_va_to_pa(unsigned long x); #endif -#ifdef CONFIG_XIP_KERNEL -#define kernel_mapping_va_to_pa(y) ({ \ - unsigned long _y = (unsigned long)(y); \ - (_y < kernel_map.virt_addr + kernel_map.xiprom_sz) ? \ - (_y - kernel_map.va_kernel_xip_text_pa_offset) : \ - (_y - kernel_map.va_kernel_xip_data_pa_offset); \ - }) -#else #define kernel_mapping_va_to_pa(y) ((unsigned long)(y) - kernel_map.va_kernel_pa_offset) -#endif #define __va_to_pa_nodebug(x) ({ \ unsigned long _x = x; \ @@ -190,7 +161,10 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) -unsigned long kaslr_offset(void); +static inline unsigned long kaslr_offset(void) +{ + return kernel_map.virt_offset; +} static __always_inline void *pfn_to_kaddr(unsigned long pfn) { diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index a66d49bb26a8..a1a7c6520a09 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -134,21 +134,6 @@ #include <linux/page_table_check.h> -#ifdef CONFIG_XIP_KERNEL -#define XIP_FIXUP(addr) ({ \ - extern char _sdata[], _start[], _end[]; \ - uintptr_t __rom_start_data = CONFIG_XIP_PHYS_ADDR \ - + (uintptr_t)&_sdata - (uintptr_t)&_start; \ - uintptr_t __rom_end_data = CONFIG_XIP_PHYS_ADDR \ - + (uintptr_t)&_end - (uintptr_t)&_start; \ - uintptr_t __a = (uintptr_t)(addr); \ - (__a >= __rom_start_data && __a < __rom_end_data) ? \ - __a - __rom_start_data + CONFIG_PHYS_RAM_BASE : __a; \ - }) -#else -#define XIP_FIXUP(addr) (addr) -#endif /* CONFIG_XIP_KERNEL */ - struct pt_alloc_ops { pte_t *(*get_pte_virt)(phys_addr_t pa); phys_addr_t (*alloc_pte)(uintptr_t va); @@ -1272,13 +1257,8 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) extern char _start[]; extern void *_dtb_early_va; extern uintptr_t _dtb_early_pa; -#if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_MMU) -#define dtb_early_va (*(void **)XIP_FIXUP(&_dtb_early_va)) -#define dtb_early_pa (*(uintptr_t *)XIP_FIXUP(&_dtb_early_pa)) -#else #define dtb_early_va _dtb_early_va #define dtb_early_pa _dtb_early_pa -#endif /* CONFIG_XIP_KERNEL */ extern u64 satp_mode; void paging_init(void); diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 4c3dd94d0f63..812517b2cec1 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -86,7 +86,7 @@ struct pt_regs; * preempt_v. All preempt_v context should be dropped in such case because * V-regs are caller-saved. Only sstatus.VS=ON is persisted across a * schedule() call. - * - bit 30: The in-kernel preempt_v context is saved, and requries to be + * - bit 30: The in-kernel preempt_v context is saved, and is required to be * restored when returning to the context that owns the preempt_v. * - bit 31: The in-kernel preempt_v context is dirty, as signaled by the * trap entry code. Any context switches out-of current task need to save diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h index ab7714aa93bd..023a412fe38d 100644 --- a/arch/riscv/include/asm/scs.h +++ b/arch/riscv/include/asm/scs.h @@ -10,7 +10,6 @@ /* Load init_shadow_call_stack to gp. */ .macro scs_load_init_stack la gp, init_shadow_call_stack - XIP_FIXUP_OFFSET gp .endm /* Load the per-CPU IRQ shadow call stack to gp. */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index 87389e93325a..ef59e1716a2c 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -47,7 +47,7 @@ bool kernel_page_present(struct page *page); #endif /* __ASSEMBLER__ */ -#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_XIP_KERNEL) +#if defined(CONFIG_STRICT_KERNEL_RWX) #ifdef CONFIG_64BIT #define SECTION_ALIGN (1 << 21) #else diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 7ac80e9f2288..0ecc67641b09 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -105,7 +105,7 @@ static inline void riscv_ipi_set_virq_range(int virq, int nr) #endif /* CONFIG_SMP */ -#if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP) +#if defined(CONFIG_HOTPLUG_CPU) bool cpu_has_hotplug(unsigned int cpu); #else static inline bool cpu_has_hotplug(unsigned int cpu) diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h index 5ba77f60bf0b..764ffe8f6479 100644 --- a/arch/riscv/include/asm/string.h +++ b/arch/riscv/include/asm/string.h @@ -28,6 +28,15 @@ extern asmlinkage __kernel_size_t strlen(const char *); #define __HAVE_ARCH_STRNCMP extern asmlinkage int strncmp(const char *cs, const char *ct, size_t count); + +#define __HAVE_ARCH_STRNLEN +extern asmlinkage __kernel_size_t strnlen(const char *, size_t); + +#define __HAVE_ARCH_STRCHR +extern asmlinkage char *strchr(const char *, int); + +#define __HAVE_ARCH_STRRCHR +extern asmlinkage char *strrchr(const char *, int); #endif /* For those files which don't want to check by kasan. */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 36918c9200c9..55019fdfa9ec 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -120,7 +120,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #include <asm-generic/thread_info_tif.h> #define TIF_32BIT 16 /* compat-mode 32bit process */ -#define TIF_RISCV_V_DEFER_RESTORE 17 /* restore Vector before returing to user */ +#define TIF_RISCV_V_DEFER_RESTORE 17 /* restore Vector before returning to user */ #define _TIF_RISCV_V_DEFER_RESTORE BIT(TIF_RISCV_V_DEFER_RESTORE) diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h deleted file mode 100644 index f3d56299bc22..000000000000 --- a/arch/riscv/include/asm/xip_fixup.h +++ /dev/null @@ -1,49 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * XIP fixup macros, only useful in assembly. - */ -#ifndef _ASM_RISCV_XIP_FIXUP_H -#define _ASM_RISCV_XIP_FIXUP_H - -#include <linux/pgtable.h> - -#ifdef CONFIG_XIP_KERNEL -.macro XIP_FIXUP_OFFSET reg - /* Fix-up address in Flash into address in RAM early during boot before - * MMU is up. Because generated code "thinks" data is in Flash, but it - * is actually in RAM (actually data is also in Flash, but Flash is - * read-only, thus we need to use the data residing in RAM). - * - * The start of data in Flash is _sdata and the start of data in RAM is - * CONFIG_PHYS_RAM_BASE. So this fix-up essentially does this: - * reg += CONFIG_PHYS_RAM_BASE - _start - */ - li t0, CONFIG_PHYS_RAM_BASE - add \reg, \reg, t0 - la t0, _sdata - sub \reg, \reg, t0 -.endm -.macro XIP_FIXUP_FLASH_OFFSET reg - /* In linker script, at the transition from read-only section to - * writable section, the VMA is increased while LMA remains the same. - * (See in linker script how _sdata, __data_loc and LOAD_OFFSET is - * changed) - * - * Consequently, early during boot before MMU is up, the generated code - * reads the "writable" section at wrong addresses, because VMA is used - * by compiler to generate code, but the data is located in Flash using - * LMA. - */ - la t0, _sdata - sub \reg, \reg, t0 - la t0, __data_loc - add \reg, \reg, t0 -.endm -#else -.macro XIP_FIXUP_OFFSET reg -.endm -.macro XIP_FIXUP_FLASH_OFFSET reg -.endm -#endif /* CONFIG_XIP_KERNEL */ - -#endif diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h index 66b13a522880..eb4f0209c696 100644 --- a/arch/riscv/include/uapi/asm/setup.h +++ b/arch/riscv/include/uapi/asm/setup.h @@ -3,6 +3,6 @@ #ifndef _UAPI_ASM_RISCV_SETUP_H #define _UAPI_ASM_RISCV_SETUP_H -#define COMMAND_LINE_SIZE 1024 +#define COMMAND_LINE_SIZE 2048 #endif /* _UAPI_ASM_RISCV_SETUP_H */ diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 322ea92aa39f..068e0b404b6f 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -69,7 +69,7 @@ static int __init acpi_fadt_sanity_check(void) /* * FADT is required on riscv; retrieve it to check its presence - * and carry out revision and ACPI HW reduced compliancy tests + * and carry out revision and ACPI HW reduced compliance tests */ status = acpi_get_table(ACPI_SIG_FADT, 0, &table); if (ACPI_FAILURE(status)) { @@ -85,12 +85,12 @@ static int __init acpi_fadt_sanity_check(void) * 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 + * ACPI 6.6 is required for RISC-V as it introduces RISC-V specific + * tables such as RHCT (RISC-V Hart Capabilities Table) and RIMT + * (RISC-V I/O Mapping Table). */ - 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", + if (table->revision < 6 || (table->revision == 6 && fadt->minor_revision < 6)) + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 6.6+\n", table->revision, fadt->minor_revision); if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c index 3f50d3dd76c6..a0ee426f6d93 100644 --- a/arch/riscv/kernel/cpu-hotplug.c +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -43,7 +43,6 @@ int __cpu_disable(void) 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. @@ -75,4 +74,3 @@ void __noreturn arch_cpu_idle_dead(void) /* It should never reach here */ BUG(); } -#endif diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 60eb221296a6..d011fb51c59a 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -498,6 +498,7 @@ SYM_DATA_START_LOCAL(excp_vect_table) RISCV_PTR do_trap_unknown /* cause=16 */ RISCV_PTR do_trap_unknown /* cause=17 */ RISCV_PTR do_trap_software_check /* cause=18 is sw check exception */ + RISCV_PTR do_trap_hardware_error /* hardware error (19) */ SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end) #ifndef CONFIG_MMU diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 8d18d6727f0f..b430edfb83f4 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -148,7 +148,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long ad /* * This is called early on, and isn't wrapped by - * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * ftrace_arch_code_modify_{prepare,post_process}() and therefore 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. diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 9c99c5ad6fe8..f6a8ca49e627 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -14,7 +14,6 @@ #include <asm/hwcap.h> #include <asm/image.h> #include <asm/scs.h> -#include <asm/xip_fixup.h> #include <asm/usercfi.h> #include "efi-header.S" @@ -75,13 +74,12 @@ pe_head_start: 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 */ + /* Point stvec to virtual address of instruction after satp write */ la a2, 1f add a2, a2, a1 csrw CSR_TVEC, a2 @@ -89,7 +87,6 @@ relocate_enable_mmu: /* 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 @@ -100,7 +97,6 @@ relocate_enable_mmu: * 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 @@ -154,11 +150,9 @@ secondary_start_sbi: /* 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) @@ -167,7 +161,6 @@ secondary_start_sbi: #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 @@ -269,40 +262,13 @@ SYM_CODE_START(_start_kernel) .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 @@ -312,20 +278,16 @@ SYM_CODE_START(_start_kernel) add a3, a3, RISCV_SZPTR 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 - 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 */ @@ -335,7 +297,6 @@ SYM_CODE_START(_start_kernel) call setup_vm #ifdef CONFIG_MMU la a0, early_pg_dir - XIP_FIXUP_OFFSET a0 call relocate_enable_mmu #endif /* CONFIG_MMU */ @@ -374,9 +335,7 @@ SYM_CODE_START(_start_kernel) slli a3, a0, LGREG 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 diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h index a556fdaafed9..05a04bef442b 100644 --- a/arch/riscv/kernel/head.h +++ b/arch/riscv/kernel/head.h @@ -11,9 +11,6 @@ extern atomic_t hart_lottery; asmlinkage void __init setup_vm(uintptr_t dtb_pa); -#ifdef CONFIG_XIP_KERNEL -asmlinkage void __init __copy_data(void); -#endif #ifdef CONFIG_RISCV_BOOT_SPINWAIT extern void *__cpu_spinwait_stack_pointer[]; diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 48f6c4f7dca0..082fe0b0e3c0 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -66,7 +66,7 @@ * 8(sp) stores the function return address (i.e. parent IP) that * can be accessed by &(fregs)->ra in tracing function. * -* The other regs are saved at the respective localtion and accessed +* The other regs are saved at the respective location and accessed * by the respective ftrace_regs member. * * Here is the layout of stack for your reference. diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index 1675cbad8619..98eaac6f6606 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -148,7 +148,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, return -ENOEXEC; } - /* Calculate the maxinum number of entries */ + /* Calculate the maximum number of entries */ for (i = 0; i < ehdr->e_shnum; i++) { size_t num_relas = sechdrs[i].sh_size / sizeof(Elf_Rela); Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset; diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 8723390c7cad..9e2afabf94e8 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -149,7 +149,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p) /* * Interrupts need to be disabled before single-step mode is set, and not - * reenabled until after single-step mode ends. + * re-enabled 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 diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c index f0d0691a8688..eb177d0ce8ab 100644 --- a/arch/riscv/kernel/probes/uprobes.c +++ b/arch/riscv/kernel/probes/uprobes.c @@ -111,7 +111,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) current->thread.bad_cause = utask->autask.saved_cause; /* - * Task has received a fatal signal, so reset back to probbed + * Task has received a fatal signal, so reset back to probed * address. */ instruction_pointer_set(regs, utask->vaddr); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index b5bc5fc65cea..c89cc272440b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -46,11 +46,7 @@ * 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 -; +atomic_t hart_lottery __section(".sdata"); unsigned long boot_cpu_hartid; EXPORT_SYMBOL_GPL(boot_cpu_hartid); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index d85916a3660c..8b628580fe11 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -251,18 +251,14 @@ asmlinkage __visible void smp_callin(void) set_cpu_online(curr_cpuid, true); /* - * Remote cache and TLB flushes are ignored while the CPU is offline, - * so flush them both right now just in case. + * Remote instruction cache and TLB flushes are ignored while the CPU + * is offline, so flush them both right now just in case. */ local_flush_icache_all(); local_flush_tlb_all(); #ifndef CONFIG_HOTPLUG_PARALLEL complete(&cpu_running); #endif - /* - * Disable preemption before enabling interrupts, so we don't try to - * schedule a CPU that hasn't actually started yet. - */ local_irq_enable(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c index a0516172a33c..7d69e3b6bab4 100644 --- a/arch/riscv/kernel/soc.c +++ b/arch/riscv/kernel/soc.c @@ -8,7 +8,7 @@ #include <asm/soc.h> /* - * This is called extremly early, before parse_dtb(), to allow initializing + * This is called extremely early, before parse_dtb(), to allow initializing * SoC hardware before memory or any device driver initialization. */ void __init soc_early_init(void) diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index aff93090c4ef..3efbf7874f3b 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -78,7 +78,7 @@ int cpu_suspend(unsigned long arg, suspend_save_csrs(&context); /* - * Function graph tracer state gets incosistent when the kernel + * Function graph tracer state gets inconsistent when the kernel * calls functions that never return (aka finishers) hence disable * graph tracing during their execution. */ diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S index 2d54f309c140..d71b55fd6259 100644 --- a/arch/riscv/kernel/suspend_entry.S +++ b/arch/riscv/kernel/suspend_entry.S @@ -10,7 +10,6 @@ #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/csr.h> -#include <asm/xip_fixup.h> .text .altmacro @@ -70,7 +69,6 @@ SYM_TYPED_FUNC_START(__cpu_resume_enter) /* Enable MMU */ la a0, swapper_pg_dir - XIP_FIXUP_OFFSET a0 call relocate_enable_mmu /* Restore A0 and A1 */ diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 461279a7bd86..8c62c771a656 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -142,11 +142,7 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } } -#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) \ { \ @@ -165,6 +161,8 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ DO_ERROR_INFO(do_trap_unknown, SIGILL, ILL_ILLTRP, "unknown exception"); +DO_ERROR_INFO(do_trap_hardware_error, + SIGBUS, BUS_MCEERR_AR, "hardware error"); DO_ERROR_INFO(do_trap_insn_misaligned, SIGBUS, BUS_ADRALN, "instruction address misaligned"); DO_ERROR_INFO(do_trap_insn_fault, diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index b36a6a56f404..485ab1d105d3 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -16,7 +16,7 @@ #include "copy-unaligned.h" -#define MISALIGNED_ACCESS_JIFFIES_LG2 1 +#define MISALIGNED_ACCESS_NS 8000000 #define MISALIGNED_BUFFER_SIZE 0x4000 #define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE) #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) @@ -29,109 +29,125 @@ static long unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNO static cpumask_t fast_misaligned_access; -#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS -static int check_unaligned_access(void *param) +static u64 __maybe_unused +measure_cycles(void (*func)(void *dst, const void *src, size_t len), + void *dst, void *src, size_t len) { - 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_SCALAR_SLOW; - - if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) - return 0; + u64 start_cycles, end_cycles, cycles = -1ULL; + u64 start_ns; - /* 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); + func(dst, src, len); + 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_ns = ktime_get_mono_fast_ns(); + while (ktime_get_mono_fast_ns() < start_ns + MISALIGNED_ACCESS_NS) { 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); + func(dst, src, len); /* 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; + if ((end_cycles - start_cycles) < cycles) + 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(); + preempt_enable(); - 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; - } + return cycles; +} - preempt_enable(); +/* + * Return: + * 1 if unaligned accesses are fast + * 0 if unaligned accesses are slow + * -1 if check cannot be done + */ +static int __maybe_unused +compare_unaligned_access(void (*word_copy)(void *dst, const void *src, size_t len), + void (*byte_copy)(void *dst, const void *src, size_t len), + void *buf, const char *type) +{ + int cpu = smp_processor_id(); + u64 word_cycles; + u64 byte_cycles; + void *dst, *src; + bool fast; + int ratio; + + /* Make an unaligned destination buffer. */ + dst = (void *)((unsigned long)buf | 0x1); + /* Unalign src as well, but differently (off by 1 + 2 = 3). */ + src = dst + (MISALIGNED_BUFFER_SIZE / 2); + src += 2; + + word_cycles = measure_cycles(word_copy, dst, src, MISALIGNED_COPY_SIZE); + byte_cycles = measure_cycles(byte_copy, dst, src, MISALIGNED_COPY_SIZE); /* 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); + pr_warn("cpu%d: rdtime lacks granularity needed to measure %s unaligned access speed\n", + cpu, type); - return 0; + return -1; } - if (word_cycles < byte_cycles) - speed = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; + fast = word_cycles < byte_cycles; 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", + pr_info("cpu%d: %s unaligned word access speed is %d.%02dx byte access speed (%s)\n", cpu, + type, ratio / 100, ratio % 100, - (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) ? "fast" : "slow"); + fast ? "fast" : "slow"); - per_cpu(misaligned_access_speed, cpu) = speed; + return fast; +} + +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS +static int check_unaligned_access(struct page *page) +{ + void *buf = page_address(page); + int cpu = smp_processor_id(); + int ret; + + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) + return 0; + + ret = compare_unaligned_access(__riscv_copy_words_unaligned, + __riscv_copy_bytes_unaligned, + buf, "scalar"); + if (ret < 0) + return 0; /* * Set the value of fast_misaligned_access of a CPU. These operations * are atomic to avoid race conditions. */ - if (speed == RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) + if (ret) { + per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; cpumask_set_cpu(cpu, &fast_misaligned_access); - else + } else { + per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; cpumask_clear_cpu(cpu, &fast_misaligned_access); + } return 0; } -static void __init check_unaligned_access_nonboot_cpu(void *param) +static void __init _check_unaligned_access(void *param) { unsigned int cpu = smp_processor_id(); struct page **pages = param; - if (smp_processor_id() != 0) - check_unaligned_access(pages[cpu]); + check_unaligned_access(pages[cpu]); } /* Measure unaligned access speed on all CPUs present at boot in parallel. */ @@ -158,11 +174,7 @@ static void __init check_unaligned_access_speed_all_cpus(void) } } - /* 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); + on_each_cpu(_check_unaligned_access, bufs, 1); out: for_each_cpu(cpu, cpu_online_mask) { @@ -281,15 +293,8 @@ static int riscv_offline_cpu(unsigned int cpu) static void check_vector_unaligned_access(struct work_struct *work __always_unused) { int cpu = smp_processor_id(); - u64 start_cycles, end_cycles; - u64 word_cycles; - u64 byte_cycles; - int ratio; - unsigned long start_jiffies, now; struct page *page; - void *dst; - void *src; - long speed = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + int ret; if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) return; @@ -300,76 +305,20 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus return; } - /* Make an unaligned destination buffer. */ - dst = (void *)((unsigned long)page_address(page) | 0x1); - /* Unalign src as well, but differently (off by 1 + 2 = 3). */ - src = dst + (MISALIGNED_BUFFER_SIZE / 2); - src += 2; - word_cycles = -1ULL; - - /* Do a warmup. */ kernel_vector_begin(); - __riscv_copy_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); - - start_jiffies = jiffies; - while ((now = jiffies) == start_jiffies) - cpu_relax(); - - /* - * 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_vec_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); - /* Ensure the copy ends before the end time is snapped. */ - mb(); - end_cycles = get_cycles64(); - if ((end_cycles - start_cycles) < word_cycles) - word_cycles = end_cycles - start_cycles; - } - - byte_cycles = -1ULL; - __riscv_copy_vec_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(); - /* Ensure the CSR read can't reorder WRT to the copy. */ - mb(); - __riscv_copy_vec_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); - /* Ensure the copy ends before the end time is snapped. */ - mb(); - end_cycles = get_cycles64(); - if ((end_cycles - start_cycles) < byte_cycles) - byte_cycles = end_cycles - start_cycles; - } + ret = compare_unaligned_access(__riscv_copy_vec_words_unaligned, + __riscv_copy_vec_bytes_unaligned, + page_address(page), "vector"); kernel_vector_end(); - /* Don't divide by zero. */ - if (!word_cycles || !byte_cycles) { - pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned vector access speed\n", - cpu); - + if (ret < 0) goto free; - } - if (word_cycles < byte_cycles) - speed = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; - - ratio = div_u64((byte_cycles * 100), word_cycles); - pr_info("cpu%d: Ratio of vector byte access time to vector unaligned word access is %d.%02d, unaligned accesses are %s\n", - cpu, - ratio / 100, - ratio % 100, - (speed == RISCV_HWPROBE_MISALIGNED_VECTOR_FAST) ? "fast" : "slow"); - - per_cpu(vector_misaligned_access, cpu) = speed; + if (ret) + per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + else + per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; free: __free_pages(page, MISALIGNED_BUFFER_ORDER); @@ -494,4 +443,4 @@ static int __init check_unaligned_access_all_cpus(void) return 0; } -arch_initcall(check_unaligned_access_all_cpus); +late_initcall(check_unaligned_access_all_cpus); diff --git a/arch/riscv/kernel/vdso_cfi/.gitignore b/arch/riscv/kernel/vdso_cfi/.gitignore new file mode 100644 index 000000000000..220b6ebece4f --- /dev/null +++ b/arch/riscv/kernel/vdso_cfi/.gitignore @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copied source files from the main vdso directory +*.c +*.S +!vdso-cfi.S +vdso.lds +*.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso_cfi/Makefile b/arch/riscv/kernel/vdso_cfi/Makefile index 8ebd190782b0..10292498b765 100644 --- a/arch/riscv/kernel/vdso_cfi/Makefile +++ b/arch/riscv/kernel/vdso_cfi/Makefile @@ -23,3 +23,6 @@ $(vdso_c_objects): $(obj)/%.c: $(src)/%.c # Include the main VDSO Makefile which contains all the build rules and sources # The VDSO_CFI_BUILD variable will be passed to it to enable CFI compilation include $(src)/Makefile + +# Clean rules - remove the copied source files +clean-files += $(notdir $(vdso_c_sources)) $(notdir $(vdso_S_sources)) diff --git a/arch/riscv/kernel/vmcore_info.c b/arch/riscv/kernel/vmcore_info.c index d5e448aa90e7..c27efceec3cc 100644 --- a/arch/riscv/kernel/vmcore_info.c +++ b/arch/riscv/kernel/vmcore_info.c @@ -3,6 +3,11 @@ #include <linux/vmcore_info.h> #include <linux/pagemap.h> +static inline u64 get_satp_value(void) +{ + return csr_read(CSR_SATP); +} + void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_ram_base); @@ -19,13 +24,8 @@ void arch_crash_save_vmcoreinfo(void) #endif #endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); -#ifdef CONFIG_XIP_KERNEL - /* TODO: Communicate with crash-utility developers on the information to - * export. The XIP case is more complicated, because the virtual-physical - * address offset depends on whether the address is in ROM or in RAM. - */ -#else vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", kernel_map.va_kernel_pa_offset); -#endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + vmcoreinfo_append_str("NUMBER(satp)=0x%llx\n", get_satp_value()); } diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 997f9eb3b22b..1f4f8496941a 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -7,10 +7,6 @@ #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 @@ -176,4 +172,3 @@ SECTIONS DISCARDS } -#endif /* CONFIG_XIP_KERNEL */ diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c index 439c20c2775a..993b25ea94d6 100644 --- a/arch/riscv/kvm/tlb.c +++ b/arch/riscv/kvm/tlb.c @@ -182,7 +182,7 @@ void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) /* * Flush VS-stage TLB entries for implementation where VS-stage - * TLB does not cahce guest physical address and VMID. + * TLB does not cache guest physical address and VMID. */ if (static_branch_unlikely(&kvm_riscv_vsstage_tlb_no_gpa)) kvm_riscv_local_hfence_vvma_all(vmid); diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index 18ef07b3f13a..a935ed96bc17 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -694,7 +694,7 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, pmc->counter_val += perf_event_read_value(pmc->perf_event, &enabled, &running); /* - * The counter and overflow indicies in the snapshot region are w.r.to + * The counter and overflow indices in the snapshot region are w.r.to * cbase. Modify the set bit in the counter mask instead of the pmc_index * which indicates the absolute counter index. */ diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index e220c35764eb..6f767b2a349d 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -7,6 +7,9 @@ ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),) lib-y += strcmp.o lib-y += strlen.o lib-y += strncmp.o +lib-y += strnlen.o +lib-y += strchr.o +lib-y += strrchr.o endif lib-y += csum.o ifeq ($(CONFIG_MMU), y) diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c index 75bd0abffd63..5d4379768e5d 100644 --- a/arch/riscv/lib/csum.c +++ b/arch/riscv/lib/csum.c @@ -269,7 +269,7 @@ unsigned int do_csum(const unsigned char *buff, int len) * on machines with fast misaligned accesses. * * There is some duplicate code between the "with_alignment" and - * "no_alignment" implmentations, but the overlap is too awkward to be + * "no_alignment" implementations, but the overlap is too awkward to be * able to fit in one function without introducing multiple static * branches. The largest chunk of overlap was delegated into the * do_csum_common function. diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S index cb3e2e7ef0ba..410e598d4677 100644 --- a/arch/riscv/lib/memmove.S +++ b/arch/riscv/lib/memmove.S @@ -40,8 +40,8 @@ SYM_FUNC_START(__memmove) * Both Copy Modes: t1 - Temporary for load-store * Both Copy Modes: t2 - Temporary for load-store * Both Copy Modes: a5 - dest to src alignment offset - * Both Copy Modes: a6 - Shift ammount - * Both Copy Modes: a7 - Inverse Shift ammount + * Both Copy Modes: a6 - Shift amount + * Both Copy Modes: a7 - Inverse Shift amount * Both Copy Modes: a2 - Alternate breakpoint for unrolled loops */ diff --git a/arch/riscv/lib/strchr.S b/arch/riscv/lib/strchr.S new file mode 100644 index 000000000000..48c3a9da53e3 --- /dev/null +++ b/arch/riscv/lib/strchr.S @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Copyright (C) 2025 Feng Jiang <jiangfeng@kylinos.cn> + */ + +#include <linux/linkage.h> +#include <asm/asm.h> + +/* char *strchr(const char *s, int c) */ +SYM_FUNC_START(strchr) + /* + * Parameters + * a0 - The string to be searched + * a1 - The character to search for + * + * Returns + * a0 - Address of first occurrence of 'c' or 0 + * + * Clobbers + * t0 + */ + andi a1, a1, 0xff +1: + lbu t0, 0(a0) + beq t0, a1, 2f + addi a0, a0, 1 + bnez t0, 1b + li a0, 0 +2: + ret +SYM_FUNC_END(strchr) + +SYM_FUNC_ALIAS_WEAK(__pi_strchr, strchr) +EXPORT_SYMBOL(strchr) diff --git a/arch/riscv/lib/strnlen.S b/arch/riscv/lib/strnlen.S new file mode 100644 index 000000000000..53afa7b5b314 --- /dev/null +++ b/arch/riscv/lib/strnlen.S @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Base on arch/riscv/lib/strlen.S + * + * Copyright (C) Feng Jiang <jiangfeng@kylinos.cn> + */ + +#include <linux/linkage.h> +#include <asm/asm.h> +#include <asm/alternative-macros.h> +#include <asm/hwcap.h> + +/* size_t strnlen(const char *s, size_t count) */ +SYM_FUNC_START(strnlen) + + __ALTERNATIVE_CFG("nop", "j strnlen_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) + + + /* + * Returns + * a0 - String length + * + * Parameters + * a0 - String to measure + * a1 - Max length of string + * + * Clobbers + * t0, t1, t2 + */ + addi t1, a0, -1 + add t2, a0, a1 +1: + addi t1, t1, 1 + beq t1, t2, 2f + lbu t0, 0(t1) + bnez t0, 1b +2: + sub a0, t1, a0 + ret + + +/* + * Variant of strnlen using the ZBB extension if available + */ +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) +strnlen_zbb: + +#ifdef CONFIG_CPU_BIG_ENDIAN +# define CZ clz +# define SHIFT sll +#else +# define CZ ctz +# define SHIFT srl +#endif + +.option push +.option arch,+zbb + + /* + * Returns + * a0 - String length + * + * Parameters + * a0 - String to measure + * a1 - Max length of string + * + * Clobbers + * t0, t1, t2, t3, t4 + */ + + /* If maxlen is 0, return 0. */ + beqz a1, 3f + + /* Number of irrelevant bytes in the first word. */ + andi t2, a0, SZREG-1 + + /* Align pointer. */ + andi t0, a0, -SZREG + + li t3, SZREG + sub t3, t3, t2 + slli t2, t2, 3 + + /* Aligned boundary. */ + add t4, a0, a1 + andi t4, t4, -SZREG + + /* Get the first word. */ + REG_L t1, 0(t0) + + /* + * Shift away the partial data we loaded to remove the irrelevant bytes + * preceding the string with the effect of adding NUL bytes at the + * end of the string's first word. + */ + SHIFT t1, t1, t2 + + /* Convert non-NUL into 0xff and NUL into 0x00. */ + orc.b t1, t1 + + /* Convert non-NUL into 0x00 and NUL into 0xff. */ + not t1, t1 + + /* + * Search for the first set bit (corresponding to a NUL byte in the + * original chunk). + */ + CZ t1, t1 + + /* + * The first chunk is special: compare against the number + * of valid bytes in this chunk. + */ + srli a0, t1, 3 + + /* Limit the result by maxlen. */ + minu a0, a0, a1 + + bgtu t3, a0, 2f + + /* Prepare for the word comparison loop. */ + addi t2, t0, SZREG + li t3, -1 + + /* + * Our critical loop is 4 instructions and processes data in + * 4 byte or 8 byte chunks. + */ + .p2align 3 +1: + REG_L t1, SZREG(t0) + addi t0, t0, SZREG + orc.b t1, t1 + bgeu t0, t4, 4f + beq t1, t3, 1b +4: + not t1, t1 + CZ t1, t1 + srli t1, t1, 3 + + /* Get number of processed bytes. */ + sub t2, t0, t2 + + /* Add number of characters in the first word. */ + add a0, a0, t2 + + /* Add number of characters in the last word. */ + add a0, a0, t1 + + /* Ensure the final result does not exceed maxlen. */ + minu a0, a0, a1 +2: + ret +3: + mv a0, a1 + ret + +.option pop +#endif +SYM_FUNC_END(strnlen) +SYM_FUNC_ALIAS(__pi_strnlen, strnlen) +EXPORT_SYMBOL(strnlen) diff --git a/arch/riscv/lib/strrchr.S b/arch/riscv/lib/strrchr.S new file mode 100644 index 000000000000..ac58b20ca21d --- /dev/null +++ b/arch/riscv/lib/strrchr.S @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Copyright (C) 2025 Feng Jiang <jiangfeng@kylinos.cn> + */ + +#include <linux/linkage.h> +#include <asm/asm.h> + +/* char *strrchr(const char *s, int c) */ +SYM_FUNC_START(strrchr) + /* + * Parameters + * a0 - The string to be searched + * a1 - The character to seaerch for + * + * Returns + * a0 - Address of last occurrence of 'c' or 0 + * + * Clobbers + * t0, t1 + */ + andi a1, a1, 0xff + mv t1, a0 + li a0, 0 +1: + lbu t0, 0(t1) + bne t0, a1, 2f + mv a0, t1 +2: + addi t1, t1, 1 + bnez t0, 1b + ret +SYM_FUNC_END(strrchr) + +SYM_FUNC_ALIAS_WEAK(__pi_strrchr, strrchr) +EXPORT_SYMBOL(strrchr) diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index d83a612464f6..f8ead7cb7c7d 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -29,7 +29,7 @@ void flush_icache_all(void) * Make sure all previous writes to the D$ are ordered before making * the IPI. The RISC-V spec states that a hart must execute a data fence * before triggering a remote fence.i in order to make the modification - * visable for remote harts. + * visible for remote harts. * * IPIs on RISC-V are triggered by MMIO writes to either CLINT or * S-IMSIC, so the fence ensures previous data writes "happen before" diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b5c50956bb8a..decd7df40fa4 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -41,20 +41,17 @@ u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1]; struct kernel_mapping kernel_map __ro_after_init; EXPORT_SYMBOL(kernel_map); -#ifdef CONFIG_XIP_KERNEL -#define kernel_map (*(struct kernel_mapping *)XIP_FIXUP(&kernel_map)) -#endif #ifdef CONFIG_64BIT -u64 satp_mode __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_57 : SATP_MODE_39; +u64 satp_mode __ro_after_init = SATP_MODE_57; #else u64 satp_mode __ro_after_init = SATP_MODE_32; #endif EXPORT_SYMBOL(satp_mode); #ifdef CONFIG_64BIT -bool pgtable_l4_enabled __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL); -bool pgtable_l5_enabled __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL); +bool pgtable_l4_enabled __ro_after_init = true; +bool pgtable_l5_enabled __ro_after_init = true; EXPORT_SYMBOL(pgtable_l4_enabled); EXPORT_SYMBOL(pgtable_l5_enabled); #endif @@ -190,9 +187,6 @@ void __init arch_mm_preinit(void) /* Limit the memory size via mem. */ static phys_addr_t memory_limit; -#ifdef CONFIG_XIP_KERNEL -#define memory_limit (*(phys_addr_t *)XIP_FIXUP(&memory_limit)) -#endif /* CONFIG_XIP_KERNEL */ static int __init early_mem(char *p) { @@ -216,10 +210,7 @@ static void __init setup_bootmem(void) phys_addr_t max_mapped_addr; phys_addr_t phys_ram_end, vmlinux_start; - if (IS_ENABLED(CONFIG_XIP_KERNEL)) - vmlinux_start = __pa_symbol(&_sdata); - else - vmlinux_start = __pa_symbol(&_start); + vmlinux_start = __pa_symbol(&_start); memblock_enforce_memory_limit(memory_limit); @@ -239,12 +230,10 @@ static void __init setup_bootmem(void) * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. */ - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { - phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; + phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; #ifdef CONFIG_SPARSEMEM_VMEMMAP - vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; #endif - } /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -357,13 +346,6 @@ static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); -#ifdef CONFIG_XIP_KERNEL -#define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops)) -#define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir)) -#define fixmap_pte ((pte_t *)XIP_FIXUP(fixmap_pte)) -#define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir)) -#endif /* CONFIG_XIP_KERNEL */ - static const pgprot_t protection_map[16] = { [VM_NONE] = PAGE_NONE, [VM_READ] = PAGE_READ, @@ -460,32 +442,14 @@ static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss; static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); -#ifdef CONFIG_XIP_KERNEL -#define trampoline_pmd ((pmd_t *)XIP_FIXUP(trampoline_pmd)) -#define fixmap_pmd ((pmd_t *)XIP_FIXUP(fixmap_pmd)) -#define early_pmd ((pmd_t *)XIP_FIXUP(early_pmd)) -#endif /* CONFIG_XIP_KERNEL */ - static p4d_t trampoline_p4d[PTRS_PER_P4D] __page_aligned_bss; static p4d_t fixmap_p4d[PTRS_PER_P4D] __page_aligned_bss; static p4d_t early_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -#ifdef CONFIG_XIP_KERNEL -#define trampoline_p4d ((p4d_t *)XIP_FIXUP(trampoline_p4d)) -#define fixmap_p4d ((p4d_t *)XIP_FIXUP(fixmap_p4d)) -#define early_p4d ((p4d_t *)XIP_FIXUP(early_p4d)) -#endif /* CONFIG_XIP_KERNEL */ - static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss; static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss; static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE); -#ifdef CONFIG_XIP_KERNEL -#define trampoline_pud ((pud_t *)XIP_FIXUP(trampoline_pud)) -#define fixmap_pud ((pud_t *)XIP_FIXUP(fixmap_pud)) -#define early_pud ((pud_t *)XIP_FIXUP(early_pud)) -#endif /* CONFIG_XIP_KERNEL */ - static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) { /* Before MMU is enabled */ @@ -756,21 +720,6 @@ static uintptr_t __meminit best_map_size(phys_addr_t pa, uintptr_t va, phys_addr return PAGE_SIZE; } -#ifdef CONFIG_XIP_KERNEL -#define phys_ram_base (*(phys_addr_t *)XIP_FIXUP(&phys_ram_base)) -extern char _xiprom[], _exiprom[], __data_loc; - -/* called from head.S with MMU off */ -asmlinkage void __init __copy_data(void) -{ - void *from = (void *)(&__data_loc); - void *to = (void *)CONFIG_PHYS_RAM_BASE; - size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata)); - - memcpy(to, from, sz); -} -#endif - #ifdef CONFIG_STRICT_KERNEL_RWX static __meminit pgprot_t pgprot_from_va(uintptr_t va) { @@ -806,7 +755,7 @@ static __meminit pgprot_t pgprot_from_va(uintptr_t va) } #endif /* CONFIG_STRICT_KERNEL_RWX */ -#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL) +#if defined(CONFIG_64BIT) u64 __pi_set_satp_mode_from_cmdline(uintptr_t dtb_pa); u64 __pi_set_satp_mode_from_fdt(uintptr_t dtb_pa); @@ -931,28 +880,6 @@ retry: #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing." #endif -#ifdef CONFIG_XIP_KERNEL -static void __init create_kernel_page_table(pgd_t *pgdir, - __always_unused bool early) -{ - uintptr_t va, start_va, end_va; - - /* Map the flash resident part */ - end_va = kernel_map.virt_addr + kernel_map.xiprom_sz; - for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE) - create_pgd_mapping(pgdir, va, - kernel_map.xiprom + (va - kernel_map.virt_addr), - PMD_SIZE, PAGE_KERNEL_EXEC); - - /* Map the data in RAM */ - start_va = kernel_map.virt_addr + (uintptr_t)&_sdata - (uintptr_t)&_start; - end_va = kernel_map.virt_addr + kernel_map.size; - for (va = start_va; va < end_va; va += PMD_SIZE) - create_pgd_mapping(pgdir, va, - kernel_map.phys_addr + (va - start_va), - PMD_SIZE, PAGE_KERNEL); -} -#else static void __init create_kernel_page_table(pgd_t *pgdir, bool early) { uintptr_t va, end_va; @@ -965,7 +892,6 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early) early ? PAGE_KERNEL_EXEC : pgprot_from_va(va)); } -#endif /* * Setup a 4MB mapping that encompasses the device tree: for 64-bit kernel, @@ -1075,11 +1001,6 @@ static int __init print_nokaslr(char *p) return 0; } early_param("nokaslr", print_nokaslr); - -unsigned long kaslr_offset(void) -{ - return kernel_map.virt_offset; -} #endif asmlinkage void __init setup_vm(uintptr_t dtb_pa) @@ -1107,27 +1028,11 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset; -#ifdef CONFIG_XIP_KERNEL - kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR; - kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); - - phys_ram_base = CONFIG_PHYS_RAM_BASE; -#ifdef CONFIG_SPARSEMEM_VMEMMAP - vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; -#endif - kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; - kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); - - kernel_map.va_kernel_xip_text_pa_offset = kernel_map.virt_addr - kernel_map.xiprom; - kernel_map.va_kernel_xip_data_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr - + (uintptr_t)&_sdata - (uintptr_t)&_start; -#else kernel_map.phys_addr = (uintptr_t)(&_start); kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr; kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr; -#endif -#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL) +#if defined(CONFIG_64BIT) set_satp_mode(dtb_pa); set_mmap_rnd_bits_max(); #endif @@ -1200,13 +1105,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) if (pgtable_l4_enabled) create_pud_mapping(trampoline_pud, kernel_map.virt_addr, (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE); -#ifdef CONFIG_XIP_KERNEL - create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr, - kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC); -#else create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr, kernel_map.phys_addr, PMD_SIZE, PAGE_KERNEL_EXEC); -#endif #else /* Setup trampoline PGD */ create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr, @@ -1450,6 +1350,8 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { + WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); + /* * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we * can't use hugepage mappings for 2-level page table because in case of diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c index 559d291fac5c..b1836e9481ce 100644 --- a/arch/riscv/mm/physaddr.c +++ b/arch/riscv/mm/physaddr.c @@ -9,7 +9,7 @@ phys_addr_t __virt_to_phys(unsigned long x) { /* - * Boundary checking aginst the kernel linear mapping space. + * Boundary checking against the kernel linear mapping space. */ WARN(!is_linear_mapping(x) && !is_kernel_mapping(x), "virt_to_phys used for non-linear address: %p (%pS)\n", @@ -25,7 +25,7 @@ phys_addr_t __phys_addr_symbol(unsigned long x) unsigned long kernel_end = kernel_start + kernel_map.size; /* - * Boundary checking aginst the kernel image mapping. + * Boundary checking against the kernel image mapping. * __pa_symbol should only be used on kernel symbol addresses. */ VIRTUAL_BUG_ON(x < kernel_start || x > kernel_end); diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index 530e497ca2f9..b0358a78f11a 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -2,7 +2,7 @@ purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),) -purgatory-y += strcmp.o strlen.o strncmp.o +purgatory-y += strcmp.o strlen.o strncmp.o strnlen.o strchr.o strrchr.o endif targets += $(purgatory-y) @@ -32,6 +32,15 @@ $(obj)/strncmp.o: $(srctree)/arch/riscv/lib/strncmp.S FORCE $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE $(call if_changed_rule,cc_o_c) +$(obj)/strnlen.o: $(srctree)/arch/riscv/lib/strnlen.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strchr.o: $(srctree)/arch/riscv/lib/strchr.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strrchr.o: $(srctree)/arch/riscv/lib/strrchr.S FORCE + $(call if_changed_rule,as_o_S) + CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY CFLAGS_string.o := -D__DISABLE_EXPORTS CFLAGS_ctype.o := -D__DISABLE_EXPORTS diff --git a/arch/riscv/purgatory/kexec-purgatory.S b/arch/riscv/purgatory/kexec-purgatory.S index 0e9188815718..32c53581b8f2 100644 --- a/arch/riscv/purgatory/kexec-purgatory.S +++ b/arch/riscv/purgatory/kexec-purgatory.S @@ -6,9 +6,9 @@ kexec_purgatory: .globl kexec_purgatory .incbin "arch/riscv/purgatory/purgatory.ro" -.Lkexec_purgatroy_end: +.Lkexec_purgatory_end: .align 8 kexec_purgatory_size: .globl kexec_purgatory_size - .quad .Lkexec_purgatroy_end - kexec_purgatory + .quad .Lkexec_purgatory_end - kexec_purgatory diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 77c3774c1c49..8ff5adcfe1e0 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2526,6 +2526,17 @@ config STRING_HELPERS_KUNIT_TEST depends on KUNIT default KUNIT_ALL_TESTS +config STRING_KUNIT_BENCH + bool "Benchmark string functions at runtime" + depends on STRING_KUNIT_TEST + help + Enable performance measurement for string functions. + + This measures the execution efficiency of string functions + during the KUnit test run. + + If unsure, say N. + config FFS_KUNIT_TEST tristate "KUnit test ffs-family functions at runtime" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/tests/string_kunit.c b/lib/tests/string_kunit.c index f9a8e557ba77..0819ace5b027 100644 --- a/lib/tests/string_kunit.c +++ b/lib/tests/string_kunit.c @@ -6,10 +6,18 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <kunit/test.h> +#include <linux/ktime.h> +#include <linux/math64.h> +#include <linux/minmax.h> +#include <linux/mm.h> #include <linux/module.h> +#include <linux/prandom.h> #include <linux/printk.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/time64.h> +#include <linux/units.h> +#include <linux/vmalloc.h> #define STRCMP_LARGE_BUF_LEN 2048 #define STRCMP_CHANGE_POINT 1337 @@ -17,6 +25,12 @@ #define STRCMP_TEST_EXPECT_LOWER(test, fn, ...) KUNIT_EXPECT_LT(test, fn(__VA_ARGS__), 0) #define STRCMP_TEST_EXPECT_GREATER(test, fn, ...) KUNIT_EXPECT_GT(test, fn(__VA_ARGS__), 0) +#define STRING_TEST_MAX_LEN 128 +#define STRING_TEST_MAX_OFFSET 16 + +#define STRING_BENCH_SEED 888 +#define STRING_BENCH_WORKLOAD (1 * MEGA) + static void string_test_memset16(struct kunit *test) { unsigned i, j, k; @@ -104,6 +118,64 @@ static void string_test_memset64(struct kunit *test) } } +static void string_test_strlen(struct kunit *test) +{ + size_t buf_size; + char *buf, *s; + + buf_size = PAGE_ALIGN(STRING_TEST_MAX_LEN + STRING_TEST_MAX_OFFSET + 1); + buf = vmalloc(buf_size); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf); + + memset(buf, 'A', buf_size); + + for (size_t offset = 0; offset < STRING_TEST_MAX_OFFSET; offset++) { + for (size_t len = 0; len <= STRING_TEST_MAX_LEN; len++) { + s = buf + buf_size - 1 - offset - len; + s[len] = '\0'; + KUNIT_EXPECT_EQ_MSG(test, strlen(s), len, + "offset:%zu len:%zu", offset, len); + s[len] = 'A'; + } + } + + vfree(buf); +} + +static void string_test_strnlen(struct kunit *test) +{ + size_t buf_size; + char *buf, *s; + + buf_size = PAGE_ALIGN(STRING_TEST_MAX_LEN + STRING_TEST_MAX_OFFSET + 1); + buf = vmalloc(buf_size); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf); + + memset(buf, 'A', buf_size); + + for (size_t offset = 0; offset < STRING_TEST_MAX_OFFSET; offset++) { + for (size_t len = 0; len <= STRING_TEST_MAX_LEN; len++) { + s = buf + buf_size - 1 - offset - len; + s[len] = '\0'; + + if (len > 0) + KUNIT_EXPECT_EQ(test, strnlen(s, len - 1), len - 1); + if (len > 1) + KUNIT_EXPECT_EQ(test, strnlen(s, len - 2), len - 2); + + KUNIT_EXPECT_EQ(test, strnlen(s, len), len); + + KUNIT_EXPECT_EQ(test, strnlen(s, len + 1), len); + KUNIT_EXPECT_EQ(test, strnlen(s, len + 2), len); + KUNIT_EXPECT_EQ(test, strnlen(s, len + 10), len); + + s[len] = 'A'; + } + } + + vfree(buf); +} + static void string_test_strchr(struct kunit *test) { const char *test_string = "abcdefghijkl"; @@ -127,6 +199,36 @@ static void string_test_strchr(struct kunit *test) KUNIT_ASSERT_NULL(test, result); } +static void string_test_strrchr(struct kunit *test) +{ + size_t buf_size; + char *buf, *s; + + buf_size = PAGE_ALIGN(STRING_TEST_MAX_LEN + STRING_TEST_MAX_OFFSET + 1); + buf = vmalloc(buf_size); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf); + + memset(buf, 'A', buf_size); + + for (size_t offset = 0; offset < STRING_TEST_MAX_OFFSET; offset++) { + for (size_t len = 0; len <= STRING_TEST_MAX_LEN; len++) { + s = buf + buf_size - 1 - offset - len; + s[len] = '\0'; + + KUNIT_EXPECT_PTR_EQ(test, strrchr(s, 'Z'), NULL); + + if (len > 0) + KUNIT_EXPECT_PTR_EQ(test, strrchr(s, 'A'), s + len - 1); + else + KUNIT_EXPECT_PTR_EQ(test, strrchr(s, 'A'), NULL); + + s[len] = 'A'; + } + } + + vfree(buf); +} + static void string_test_strnchr(struct kunit *test) { const char *test_string = "abcdefghijkl"; @@ -614,12 +716,180 @@ static void string_test_strends(struct kunit *test) KUNIT_EXPECT_TRUE(test, strends("", "")); } +#if IS_ENABLED(CONFIG_STRING_KUNIT_BENCH) +/* Target string lengths for benchmarking */ +static const size_t bench_lens[] = { + 0, 1, 7, 8, 16, 31, 64, 127, 512, 1024, 3173, 4096, +}; + +/** + * alloc_max_bench_buffer() - Allocate buffer for the max test case. + * @test: KUnit context for managed allocation. + * @lens: Array of lengths used in the benchmark cases. + * @count: Number of elements in the @lens array. + * @buf_len: [out] Pointer to store the actually allocated buffer + * size (including NUL character). + * + * Return: Pointer to the allocated memory, or NULL on failure. + */ +static void *alloc_max_bench_buffer(struct kunit *test, const size_t *lens, + size_t count, size_t *buf_len) +{ + size_t max_len = 0; + void *buf; + + for (size_t i = 0; i < count; i++) + max_len = max(lens[i], max_len); + + /* Add space for NUL character */ + max_len += 1; + + buf = kunit_kzalloc(test, max_len, GFP_KERNEL); + if (!buf) + return NULL; + + if (buf_len) + *buf_len = max_len; + + return buf; +} + +/** + * fill_random_string() - Populate a buffer with a random NUL-terminated string. + * @buf: Buffer to fill. + * @len: Length of the buffer in bytes. + * + * Fills the buffer with random non-NUL bytes and ensures the string is + * properly NUL-terminated. + */ +static void fill_random_string(char *buf, size_t len) +{ + struct rnd_state state; + + if (!buf || !len) + return; + + /* Use a fixed seed to ensure deterministic benchmark results */ + prandom_seed_state(&state, STRING_BENCH_SEED); + prandom_bytes_state(&state, buf, len); + + /* Replace NUL characters to avoid early string termination */ + for (size_t i = 0; i < len; i++) { + if (buf[i] == '\0') + buf[i] = 0x01; + } + + buf[len - 1] = '\0'; +} + +/** + * STRING_BENCH() - Benchmark string functions. + * @iters: Number of iterations to run. + * @func: Function to benchmark. + * @...: Variable arguments passed to @func. + * + * Disables preemption and measures the total time in nanoseconds to execute + * @func(@__VA_ARGS__) for @iters times, including a small warm-up phase. + * + * Context: Disables preemption during measurement. + * Return: Total execution time in nanoseconds (u64). + */ +#define STRING_BENCH(iters, func, ...) \ +({ \ + /* Volatile function pointer prevents dead code elimination */ \ + typeof(func) (* volatile __func) = (func); \ + size_t __bn_iters = (iters); \ + size_t __bn_warm_iters; \ + u64 __bn_t; \ + \ + /* Use 10% of the given iterations (maximum 50) to warm up */ \ + __bn_warm_iters = max(__bn_iters / 10, 50U); \ + \ + for (size_t __bn_i = 0; __bn_i < __bn_warm_iters; __bn_i++) \ + (void)__func(__VA_ARGS__); \ + \ + preempt_disable(); \ + __bn_t = ktime_get_ns(); \ + for (size_t __bn_i = 0; __bn_i < __bn_iters; __bn_i++) \ + (void)__func(__VA_ARGS__); \ + __bn_t = ktime_get_ns() - __bn_t; \ + preempt_enable(); \ + __bn_t; \ +}) + +/** + * STRING_BENCH_BUF() - Benchmark harness for single-buffer functions. + * @test: KUnit context. + * @buf_name: Local char * variable name to be defined. + * @buf_size: Local size_t variable name to be defined. + * @func: Function to benchmark. + * @...: Extra arguments for @func. + * + * Prepares a randomized, NUL-terminated buffer and iterates through lengths + * in bench_lens, defining @buf_name and @buf_size in each loop. + */ +#define STRING_BENCH_BUF(test, buf_name, buf_size, func, ...) \ +do { \ + size_t _bn_i, _bn_iters, _bn_size = 0; \ + u64 _bn_t, _bn_mbps = 0, _bn_lat = 0; \ + char *_bn_buf; \ + \ + _bn_buf = alloc_max_bench_buffer(test, bench_lens, \ + ARRAY_SIZE(bench_lens), &_bn_size); \ + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, _bn_buf); \ + \ + fill_random_string(_bn_buf, _bn_size); \ + \ + for (_bn_i = 0; _bn_i < ARRAY_SIZE(bench_lens); _bn_i++) { \ + size_t buf_size = bench_lens[_bn_i]; \ + char *buf_name = _bn_buf + _bn_size - buf_size - 1; \ + _bn_iters = STRING_BENCH_WORKLOAD / max(buf_size, 1U); \ + \ + _bn_t = STRING_BENCH(_bn_iters, func, ##__VA_ARGS__); \ + if (_bn_t > 0) { \ + _bn_mbps = (u64)(buf_size) * _bn_iters * \ + (NSEC_PER_SEC / MEGA); \ + _bn_mbps = div64_u64(_bn_mbps, _bn_t); \ + _bn_lat = div64_u64(_bn_t, _bn_iters); \ + } \ + kunit_info(test, "len=%zu: %llu MB/s (%llu ns/call)\n", \ + buf_size, _bn_mbps, _bn_lat); \ + } \ +} while (0) +#else +#define STRING_BENCH_BUF(test, buf_name, buf_size, func, ...) \ + kunit_skip(test, "not enabled") +#endif /* IS_ENABLED(CONFIG_STRING_KUNIT_BENCH) */ + +static void string_bench_strlen(struct kunit *test) +{ + STRING_BENCH_BUF(test, buf, len, strlen, buf); +} + +static void string_bench_strnlen(struct kunit *test) +{ + STRING_BENCH_BUF(test, buf, len, strnlen, buf, len); +} + +static void string_bench_strchr(struct kunit *test) +{ + STRING_BENCH_BUF(test, buf, len, strchr, buf, '\0'); +} + +static void string_bench_strrchr(struct kunit *test) +{ + STRING_BENCH_BUF(test, buf, len, strrchr, buf, '\0'); +} + static struct kunit_case string_test_cases[] = { KUNIT_CASE(string_test_memset16), KUNIT_CASE(string_test_memset32), KUNIT_CASE(string_test_memset64), + KUNIT_CASE(string_test_strlen), + KUNIT_CASE(string_test_strnlen), KUNIT_CASE(string_test_strchr), KUNIT_CASE(string_test_strnchr), + KUNIT_CASE(string_test_strrchr), KUNIT_CASE(string_test_strspn), KUNIT_CASE(string_test_strcmp), KUNIT_CASE(string_test_strcmp_long_strings), @@ -636,6 +906,10 @@ static struct kunit_case string_test_cases[] = { KUNIT_CASE(string_test_strtomem), KUNIT_CASE(string_test_memtostr), KUNIT_CASE(string_test_strends), + KUNIT_CASE(string_bench_strlen), + KUNIT_CASE(string_bench_strnlen), + KUNIT_CASE(string_bench_strchr), + KUNIT_CASE(string_bench_strrchr), {} }; diff --git a/tools/testing/selftests/riscv/cfi/Makefile b/tools/testing/selftests/riscv/cfi/Makefile index 96a4dc4b69c3..93b4738c0e2e 100644 --- a/tools/testing/selftests/riscv/cfi/Makefile +++ b/tools/testing/selftests/riscv/cfi/Makefile @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + CFLAGS += $(KHDR_INCLUDES) CFLAGS += -I$(top_srcdir)/tools/include |