diff options
Diffstat (limited to 'arch/riscv/kernel')
| -rw-r--r-- | arch/riscv/kernel/Makefile | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/asm-offsets.c | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/cacheinfo.c | 11 | ||||
| -rw-r--r-- | arch/riscv/kernel/entry.S | 24 | ||||
| -rw-r--r-- | arch/riscv/kernel/head.S | 1 | ||||
| -rw-r--r-- | arch/riscv/kernel/perf_callchain.c | 10 | ||||
| -rw-r--r-- | arch/riscv/kernel/riscv_ksyms.c | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/setup.c | 181 | ||||
| -rw-r--r-- | arch/riscv/kernel/stacktrace.c | 67 | ||||
| -rw-r--r-- | arch/riscv/kernel/time.c | 3 | ||||
| -rw-r--r-- | arch/riscv/kernel/vdso.c | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/vmlinux.lds.S | 63 |
12 files changed, 263 insertions, 105 deletions
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index fa896c5f7ccb..f6caf4d9ca15 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -56,5 +56,3 @@ obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_EFI) += efi.o - -clean: diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index db203442c08f..b79ffa3561fd 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -11,6 +11,8 @@ #include <asm/thread_info.h> #include <asm/ptrace.h> +void asm_offsets(void); + void asm_offsets(void) { OFFSET(TASK_THREAD_RA, task_struct, thread.ra); diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 7e849797c9c3..16e9941900c4 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -182,7 +182,6 @@ setup_trap_vector: END(_start) - __INIT ENTRY(_start_kernel) /* Mask all interrupts */ csrw CSR_IE, zero diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index cf190197a22f..0bb1854dce83 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -4,11 +4,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> -/* Kernel callchain */ -struct stackframe { - unsigned long fp; - unsigned long ra; -}; +#include <asm/stacktrace.h> /* * Get the return address for a single stackframe and return a pointer to the @@ -74,13 +70,11 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, fp = user_backtrace(entry, fp, 0); } -bool fill_callchain(unsigned long pc, void *entry) +static bool fill_callchain(void *entry, unsigned long pc) { return perf_callchain_store(entry, pc); } -void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg); void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c index 450492e1cb4e..5ab1c7e1a6ed 100644 --- a/arch/riscv/kernel/riscv_ksyms.c +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -11,5 +11,7 @@ */ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(__memset); EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(__memmove); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 117f3212a8e4..3fa3f26dde85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -4,6 +4,8 @@ * Chen Liqin <liqin.chen@sunplusct.com> * Lennox Wu <lennox.wu@sunplusct.com> * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis <mick@ics.forth.gr> */ #include <linux/init.h> @@ -22,6 +24,7 @@ #include <asm/cpu_ops.h> #include <asm/early_ioremap.h> #include <asm/setup.h> +#include <asm/set_memory.h> #include <asm/sections.h> #include <asm/sbi.h> #include <asm/tlbflush.h> @@ -51,6 +54,165 @@ atomic_t hart_lottery __section(".sdata"); unsigned long boot_cpu_hartid; static DEFINE_PER_CPU(struct cpu, cpu_devices); +/* + * Place kernel memory regions on the resource tree so that + * kexec-tools can retrieve them from /proc/iomem. While there + * also add "System RAM" regions for compatibility with other + * archs, and the rest of the known regions for completeness. + */ +static struct resource code_res = { .name = "Kernel code", }; +static struct resource data_res = { .name = "Kernel data", }; +static struct resource rodata_res = { .name = "Kernel rodata", }; +static struct resource bss_res = { .name = "Kernel bss", }; + +static int __init add_resource(struct resource *parent, + struct resource *res) +{ + int ret = 0; + + ret = insert_resource(parent, res); + if (ret < 0) { + pr_err("Failed to add a %s resource at %llx\n", + res->name, (unsigned long long) res->start); + return ret; + } + + return 1; +} + +static int __init add_kernel_resources(struct resource *res) +{ + int ret = 0; + + /* + * The memory region of the kernel image is continuous and + * was reserved on setup_bootmem, find it here and register + * it as a resource, then register the various segments of + * the image as child nodes + */ + if (!(res->start <= code_res.start && res->end >= data_res.end)) + return 0; + + res->name = "Kernel image"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + /* + * We removed a part of this region on setup_bootmem so + * we need to expand the resource for the bss to fit in. + */ + res->end = bss_res.end; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + return ret; + + ret = add_resource(res, &code_res); + if (ret < 0) + return ret; + + ret = add_resource(res, &rodata_res); + if (ret < 0) + return ret; + + ret = add_resource(res, &data_res); + if (ret < 0) + return ret; + + ret = add_resource(res, &bss_res); + + return ret; +} + +static void __init init_resources(void) +{ + struct memblock_region *region = NULL; + struct resource *res = NULL; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; + + code_res.start = __pa_symbol(_text); + code_res.end = __pa_symbol(_etext) - 1; + code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + rodata_res.start = __pa_symbol(__start_rodata); + rodata_res.end = __pa_symbol(__end_rodata) - 1; + rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + data_res.start = __pa_symbol(_data); + data_res.end = __pa_symbol(_edata) - 1; + data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + bss_res.start = __pa_symbol(__bss_start); + bss_res.end = __pa_symbol(__bss_stop) - 1; + bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); + /* + * Start by adding the reserved regions, if they overlap + * with /memory regions, insert_resource later on will take + * care of it. + */ + for_each_reserved_mem_region(region) { + res = &mem_res[i++]; + + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1; + + ret = add_kernel_resources(res); + if (ret < 0) + goto error; + else if (ret) + continue; + + /* + * Ignore any other reserved regions within + * system memory. + */ + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); + continue; + } + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + /* Add /memory regions to the resource tree */ + for_each_mem_region(region) { + res = &mem_res[i++]; + + if (unlikely(memblock_is_nomap(region))) { + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + } else { + res->name = "System RAM"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + } + + res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + return; + + error: + /* Better an empty resource tree than an inconsistent one */ + release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); +} + + static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ @@ -81,6 +243,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); setup_bootmem(); paging_init(); + init_resources(); #if IS_ENABLED(CONFIG_BUILTIN_DTB) unflatten_and_copy_device_tree(); #else @@ -90,6 +253,11 @@ void __init setup_arch(char **cmdline_p) pr_err("No DTB found in kernel mappings\n"); #endif + if (IS_ENABLED(CONFIG_RISCV_SBI)) + sbi_init(); + + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + protect_kernel_text_data(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); #endif @@ -98,10 +266,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); #endif -#if IS_ENABLED(CONFIG_RISCV_SBI) - sbi_init(); -#endif - #ifdef CONFIG_SMP setup_smp(); #endif @@ -123,3 +287,12 @@ static int __init topology_init(void) return 0; } subsys_initcall(topology_init); + +void free_initmem(void) +{ + unsigned long init_begin = (unsigned long)__init_begin; + unsigned long init_end = (unsigned long)__init_end; + + set_memory_rw_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT); + free_initmem_default(POISON_FREE_INITMEM); +} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 595342910c3f..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -12,17 +12,14 @@ #include <linux/stacktrace.h> #include <linux/ftrace.h> -register unsigned long sp_in_global __asm__("sp"); +#include <asm/stacktrace.h> -#ifdef CONFIG_FRAME_POINTER +register const unsigned long sp_in_global __asm__("sp"); -struct stackframe { - unsigned long fp; - unsigned long ra; -}; +#ifdef CONFIG_FRAME_POINTER void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, - bool (*fn)(unsigned long, void *), void *arg) + bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; @@ -31,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ @@ -46,7 +42,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, unsigned long low, high; struct stackframe *frame; - if (unlikely(!__kernel_text_address(pc) || fn(pc, arg))) + if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) break; /* Validate frame pointer */ @@ -66,7 +62,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, #else /* !CONFIG_FRAME_POINTER */ void notrace walk_stackframe(struct task_struct *task, - struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) + struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long sp, pc; unsigned long *ksp; @@ -88,7 +84,7 @@ void notrace walk_stackframe(struct task_struct *task, ksp = (unsigned long *)sp; while (!kstack_end(ksp)) { - if (__kernel_text_address(pc) && unlikely(fn(pc, arg))) + if (__kernel_text_address(pc) && unlikely(!fn(arg, pc))) break; pc = (*ksp++) - 0x4; } @@ -96,13 +92,12 @@ void notrace walk_stackframe(struct task_struct *task, #endif /* CONFIG_FRAME_POINTER */ - -static bool print_trace_address(unsigned long pc, void *arg) +static bool print_trace_address(void *arg, unsigned long pc) { const char *loglvl = arg; print_ip_sym(loglvl, pc); - return false; + return true; } void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) @@ -111,14 +106,14 @@ void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) walk_stackframe(task, NULL, print_trace_address, (void *)loglvl); } -static bool save_wchan(unsigned long pc, void *arg) +static bool save_wchan(void *arg, unsigned long pc) { if (!in_sched_functions(pc)) { unsigned long *p = arg; *p = pc; - return true; + return false; } - return false; + return true; } unsigned long get_wchan(struct task_struct *task) @@ -130,42 +125,12 @@ unsigned long get_wchan(struct task_struct *task) return pc; } - #ifdef CONFIG_STACKTRACE -static bool __save_trace(unsigned long pc, void *arg, bool nosched) -{ - struct stack_trace *trace = arg; - - if (unlikely(nosched && in_sched_functions(pc))) - return false; - if (unlikely(trace->skip > 0)) { - trace->skip--; - return false; - } - - trace->entries[trace->nr_entries++] = pc; - return (trace->nr_entries >= trace->max_entries); -} - -static bool save_trace(unsigned long pc, void *arg) -{ - return __save_trace(pc, arg, false); -} - -/* - * Save stack-backtrace addresses into a stack_trace buffer. - */ -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) -{ - walk_stackframe(tsk, NULL, save_trace, trace); -} -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); - -void save_stack_trace(struct stack_trace *trace) +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) { - save_stack_trace_tsk(NULL, trace); + walk_stackframe(task, regs, consume_entry, cookie); } -EXPORT_SYMBOL_GPL(save_stack_trace); #endif /* CONFIG_STACKTRACE */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 3ffbd6cbdb86..de03cb22d0e9 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -29,8 +29,30 @@ SECTIONS HEAD_TEXT_SECTION . = ALIGN(PAGE_SIZE); + .text : { + _text = .; + _stext = .; + TEXT_TEXT + SCHED_TEXT + CPUIDLE_TEXT + LOCK_TEXT + KPROBES_TEXT + ENTRY_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT + *(.fixup) + _etext = .; + } + + . = ALIGN(SECTION_ALIGN); __init_begin = .; - INIT_TEXT_SECTION(PAGE_SIZE) + __init_text_begin = .; + .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) ALIGN(SECTION_ALIGN) { \ + _sinittext = .; \ + INIT_TEXT \ + _einittext = .; \ + } + . = ALIGN(8); __soc_early_init_table : { __soc_early_init_table_start = .; @@ -47,35 +69,28 @@ SECTIONS { EXIT_TEXT } + + __init_text_end = .; + . = ALIGN(SECTION_ALIGN); +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_text_end = .; +#endif + /* Start of init data section */ + __init_data_begin = .; + INIT_DATA_SECTION(16) .exit.data : { EXIT_DATA } PERCPU_SECTION(L1_CACHE_BYTES) - __init_end = .; - . = ALIGN(SECTION_ALIGN); - .text : { - _text = .; - _stext = .; - TEXT_TEXT - SCHED_TEXT - CPUIDLE_TEXT - LOCK_TEXT - KPROBES_TEXT - ENTRY_TEXT - IRQENTRY_TEXT - SOFTIRQENTRY_TEXT - *(.fixup) - _etext = .; + .rel.dyn : { + *(.rel.dyn*) } -#ifdef CONFIG_EFI - . = ALIGN(PECOFF_SECTION_ALIGNMENT); - __pecoff_text_end = .; -#endif - - INIT_DATA_SECTION(16) + __init_data_end = .; + __init_end = .; /* Start of data section */ _sdata = .; @@ -105,10 +120,6 @@ SECTIONS BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) - .rel.dyn : { - *(.rel.dyn*) - } - #ifdef CONFIG_EFI . = ALIGN(PECOFF_SECTION_ALIGNMENT); __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end); |