diff options
Diffstat (limited to 'arch/riscv/kernel')
| -rw-r--r-- | arch/riscv/kernel/asm-offsets.c | 1 | ||||
| -rw-r--r-- | arch/riscv/kernel/cpu.c | 30 | ||||
| -rw-r--r-- | arch/riscv/kernel/cpufeature.c | 48 | ||||
| -rw-r--r-- | arch/riscv/kernel/entry.S | 22 | ||||
| -rw-r--r-- | arch/riscv/kernel/ftrace.c | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/module-sections.c | 30 | ||||
| -rw-r--r-- | arch/riscv/kernel/ptrace.c | 9 | ||||
| -rw-r--r-- | arch/riscv/kernel/setup.c | 146 | ||||
| -rw-r--r-- | arch/riscv/kernel/smp.c | 53 | ||||
| -rw-r--r-- | arch/riscv/kernel/smpboot.c | 30 | ||||
| -rw-r--r-- | arch/riscv/kernel/vdso.c | 1 | ||||
| -rw-r--r-- | arch/riscv/kernel/vdso/Makefile | 2 |
12 files changed, 160 insertions, 214 deletions
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 6a92a2fe198e..dac98348c6a3 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -39,6 +39,7 @@ void asm_offsets(void) OFFSET(TASK_STACK, task_struct, stack); OFFSET(TASK_TI, task_struct, thread_info); OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags); + OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index f8fa2c63aa89..cf2fca12414a 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -17,44 +17,36 @@ #include <asm/smp.h> /* - * Returns the hart ID of the given device tree node, or -1 if the device tree - * node isn't a RISC-V hart. + * Returns the hart ID of the given device tree node, or -ENODEV if the node + * isn't an enabled and valid RISC-V hart node. */ int riscv_of_processor_hartid(struct device_node *node) { - const char *isa, *status; + const char *isa; u32 hart; if (!of_device_is_compatible(node, "riscv")) { pr_warn("Found incompatible CPU\n"); - return -(ENODEV); + return -ENODEV; } if (of_property_read_u32(node, "reg", &hart)) { pr_warn("Found CPU without hart ID\n"); - return -(ENODEV); - } - if (hart >= NR_CPUS) { - pr_info("Found hart ID %d, which is above NR_CPUs. Disabling this hart\n", hart); - return -(ENODEV); + return -ENODEV; } - if (of_property_read_string(node, "status", &status)) { - pr_warn("CPU with hartid=%d has no \"status\" property\n", hart); - return -(ENODEV); - } - if (strcmp(status, "okay")) { - pr_info("CPU with hartid=%d has a non-okay status of \"%s\"\n", hart, status); - return -(ENODEV); + if (!of_device_is_available(node)) { + pr_info("CPU with hartid=%d is not available\n", hart); + return -ENODEV; } if (of_property_read_string(node, "riscv,isa", &isa)) { pr_warn("CPU with hartid=%d has no \"riscv,isa\" property\n", hart); - return -(ENODEV); + return -ENODEV; } if (isa[0] != 'r' || isa[1] != 'v') { pr_warn("CPU with hartid=%d has an invalid ISA of \"%s\"\n", hart, isa); - return -(ENODEV); + return -ENODEV; } return hart; @@ -106,7 +98,7 @@ static void print_isa(struct seq_file *f, const char *orig_isa) * a bit of info describing what went wrong. */ if (isa[0] != '\0') - pr_info("unsupported ISA \"%s\" in device tree", orig_isa); + pr_info("unsupported ISA \"%s\" in device tree\n", orig_isa); } static void print_mmu(struct seq_file *f, const char *mmu_type) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a6e369edbbd7..bc29b010b722 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -20,6 +20,7 @@ #include <linux/of.h> #include <asm/processor.h> #include <asm/hwcap.h> +#include <asm/smp.h> unsigned long elf_hwcap __read_mostly; #ifdef CONFIG_FPU @@ -28,7 +29,7 @@ bool has_fpu __read_mostly; void riscv_fill_hwcap(void) { - struct device_node *node = NULL; + struct device_node *node; const char *isa; size_t i; static unsigned long isa2hwcap[256] = {0}; @@ -42,36 +43,39 @@ void riscv_fill_hwcap(void) elf_hwcap = 0; - /* - * We don't support running Linux on hertergenous ISA systems. For - * now, we just check the ISA of the first "okay" processor. - */ - while ((node = of_find_node_by_type(node, "cpu"))) - if (riscv_of_processor_hartid(node) >= 0) - break; - if (!node) { - pr_warning("Unable to find \"cpu\" devicetree entry"); - return; - } + for_each_of_cpu_node(node) { + unsigned long this_hwcap = 0; - if (of_property_read_string(node, "riscv,isa", &isa)) { - pr_warning("Unable to find \"riscv,isa\" devicetree entry"); - of_node_put(node); - return; - } - of_node_put(node); + if (riscv_of_processor_hartid(node) < 0) + continue; + + if (of_property_read_string(node, "riscv,isa", &isa)) { + pr_warn("Unable to find \"riscv,isa\" devicetree entry\n"); + continue; + } - for (i = 0; i < strlen(isa); ++i) - elf_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + for (i = 0; i < strlen(isa); ++i) + this_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + + /* + * All "okay" hart should have same isa. Set HWCAP based on + * common capabilities of every "okay" hart, in case they don't + * have. + */ + if (elf_hwcap) + elf_hwcap &= this_hwcap; + else + elf_hwcap = this_hwcap; + } /* We don't support systems with F but without D, so mask those out * here. */ if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) { - pr_info("This kernel does not support systems with F but not D"); + pr_info("This kernel does not support systems with F but not D\n"); elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - pr_info("elf_hwcap is 0x%lx", elf_hwcap); + pr_info("elf_hwcap is 0x%lx\n", elf_hwcap); #ifdef CONFIG_FPU if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)) diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 13d4826ab2a1..fd9b57c8b4ce 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -144,6 +144,10 @@ _save_context: REG_L x2, PT_SP(sp) .endm +#if !IS_ENABLED(CONFIG_PREEMPT) +.set resume_kernel, restore_all +#endif + ENTRY(handle_exception) SAVE_ALL @@ -201,7 +205,7 @@ handle_syscall: REG_S s2, PT_SEPC(sp) /* Trace syscalls, but only if requested by the user. */ REG_L t0, TASK_TI_FLAGS(tp) - andi t0, t0, _TIF_SYSCALL_TRACE + andi t0, t0, _TIF_SYSCALL_WORK bnez t0, handle_syscall_trace_enter check_syscall_nr: /* Check to make sure we don't jump to a bogus syscall number. */ @@ -221,14 +225,14 @@ ret_from_syscall: REG_S a0, PT_A0(sp) /* Trace syscalls, but only if requested by the user. */ REG_L t0, TASK_TI_FLAGS(tp) - andi t0, t0, _TIF_SYSCALL_TRACE + andi t0, t0, _TIF_SYSCALL_WORK bnez t0, handle_syscall_trace_exit ret_from_exception: REG_L s0, PT_SSTATUS(sp) csrc sstatus, SR_SIE andi s0, s0, SR_SPP - bnez s0, restore_all + bnez s0, resume_kernel resume_userspace: /* Interrupts must be disabled here so flags are checked atomically */ @@ -250,6 +254,18 @@ restore_all: RESTORE_ALL sret +#if IS_ENABLED(CONFIG_PREEMPT) +resume_kernel: + REG_L s0, TASK_TI_PREEMPT_COUNT(tp) + bnez s0, restore_all +need_resched: + REG_L s0, TASK_TI_FLAGS(tp) + andi s0, s0, _TIF_NEED_RESCHED + beqz s0, restore_all + call preempt_schedule_irq + j need_resched +#endif + work_pending: /* Enter slow path for supplementary processing */ la ra, ret_from_exception diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index a840b7d074f7..b94d8db5ddcc 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -32,7 +32,7 @@ static int ftrace_check_current_call(unsigned long hook_pos, * return must be -EINVAL on failed comparison */ if (memcmp(expected, replaced, sizeof(replaced))) { - pr_err("%p: expected (%08x %08x) but get (%08x %08x)", + pr_err("%p: expected (%08x %08x) but got (%08x %08x)\n", (void *)hook_pos, expected[0], expected[1], replaced[0], replaced[1]); return -EINVAL; diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index bbbd26e19bfd..c9ae48333114 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -9,14 +9,14 @@ #include <linux/kernel.h> #include <linux/module.h> -u64 module_emit_got_entry(struct module *mod, u64 val) +unsigned long module_emit_got_entry(struct module *mod, unsigned long val) { struct mod_section *got_sec = &mod->arch.got; int i = got_sec->num_entries; struct got_entry *got = get_got_entry(val, got_sec); if (got) - return (u64)got; + return (unsigned long)got; /* There is no duplicate entry, create a new one */ got = (struct got_entry *)got_sec->shdr->sh_addr; @@ -25,10 +25,10 @@ u64 module_emit_got_entry(struct module *mod, u64 val) got_sec->num_entries++; BUG_ON(got_sec->num_entries > got_sec->max_entries); - return (u64)&got[i]; + return (unsigned long)&got[i]; } -u64 module_emit_plt_entry(struct module *mod, u64 val) +unsigned long module_emit_plt_entry(struct module *mod, unsigned long val) { struct mod_section *got_plt_sec = &mod->arch.got_plt; struct got_entry *got_plt; @@ -37,27 +37,29 @@ u64 module_emit_plt_entry(struct module *mod, u64 val) int i = plt_sec->num_entries; if (plt) - return (u64)plt; + return (unsigned long)plt; /* There is no duplicate entry, create a new one */ got_plt = (struct got_entry *)got_plt_sec->shdr->sh_addr; got_plt[i] = emit_got_entry(val); plt = (struct plt_entry *)plt_sec->shdr->sh_addr; - plt[i] = emit_plt_entry(val, (u64)&plt[i], (u64)&got_plt[i]); + plt[i] = emit_plt_entry(val, + (unsigned long)&plt[i], + (unsigned long)&got_plt[i]); plt_sec->num_entries++; got_plt_sec->num_entries++; BUG_ON(plt_sec->num_entries > plt_sec->max_entries); - return (u64)&plt[i]; + return (unsigned long)&plt[i]; } -static int is_rela_equal(const Elf64_Rela *x, const Elf64_Rela *y) +static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y) { return x->r_info == y->r_info && x->r_addend == y->r_addend; } -static bool duplicate_rela(const Elf64_Rela *rela, int idx) +static bool duplicate_rela(const Elf_Rela *rela, int idx) { int i; for (i = 0; i < idx; i++) { @@ -67,13 +69,13 @@ static bool duplicate_rela(const Elf64_Rela *rela, int idx) return false; } -static void count_max_entries(Elf64_Rela *relas, int num, +static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts, unsigned int *gots) { unsigned int type, i; for (i = 0; i < num; i++) { - type = ELF64_R_TYPE(relas[i].r_info); + type = ELF_RISCV_R_TYPE(relas[i].r_info); if (type == R_RISCV_CALL_PLT) { if (!duplicate_rela(relas, i)) (*plts)++; @@ -118,9 +120,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, /* Calculate the maxinum number of entries */ for (i = 0; i < ehdr->e_shnum; i++) { - Elf64_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset; - int num_rela = sechdrs[i].sh_size / sizeof(Elf64_Rela); - Elf64_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info; + Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset; + int num_rela = sechdrs[i].sh_size / sizeof(Elf_Rela); + Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info; if (sechdrs[i].sh_type != SHT_RELA) continue; diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 60f1e02eed36..2ae5e0284f56 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -18,12 +18,15 @@ #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/thread_info.h> +#include <linux/audit.h> #include <linux/ptrace.h> #include <linux/elf.h> #include <linux/regset.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/tracehook.h> + +#define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> enum riscv_regset { @@ -163,15 +166,19 @@ void do_syscall_trace_enter(struct pt_regs *regs) if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, syscall_get_nr(current, regs)); #endif + + audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); } void do_syscall_trace_exit(struct pt_regs *regs) { + audit_syscall_exit(regs); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) - trace_sys_exit(regs, regs->regs[0]); + trace_sys_exit(regs, regs_return_value(regs)); #endif } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index fc8006a042eb..ecb654f6a79e 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -23,7 +23,6 @@ #include <linux/mm.h> #include <linux/memblock.h> #include <linux/sched.h> -#include <linux/initrd.h> #include <linux/console.h> #include <linux/screen_info.h> #include <linux/of_fdt.h> @@ -61,151 +60,29 @@ EXPORT_SYMBOL(empty_zero_page); atomic_t hart_lottery; unsigned long boot_cpu_hartid; -unsigned long __cpuid_to_hartid_map[NR_CPUS] = { - [0 ... NR_CPUS-1] = INVALID_HARTID -}; - -void __init smp_setup_processor_id(void) -{ - cpuid_to_hartid_map(0) = boot_cpu_hartid; -} - -#ifdef CONFIG_BLK_DEV_INITRD -static void __init setup_initrd(void) -{ - unsigned long size; - - if (initrd_start >= initrd_end) { - printk(KERN_INFO "initrd not found or empty"); - goto disable; - } - if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { - printk(KERN_ERR "initrd extends beyond end of memory"); - goto disable; - } - - size = initrd_end - initrd_start; - memblock_reserve(__pa(initrd_start), size); - initrd_below_start_ok = 1; - - printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n", - (void *)(initrd_start), size); - return; -disable: - pr_cont(" - disabling initrd\n"); - initrd_start = 0; - initrd_end = 0; -} -#endif /* CONFIG_BLK_DEV_INITRD */ - -pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; -pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); - -#ifndef __PAGETABLE_PMD_FOLDED -#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT) -pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss; -pmd_t trampoline_pmd[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); -#endif - -asmlinkage void __init setup_vm(void) -{ - extern char _start; - uintptr_t i; - uintptr_t pa = (uintptr_t) &_start; - pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC); - - va_pa_offset = PAGE_OFFSET - pa; - pfn_base = PFN_DOWN(pa); - - /* Sanity check alignment and size */ - BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0); - BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0); - -#ifndef __PAGETABLE_PMD_FOLDED - trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] = - pfn_pgd(PFN_DOWN((uintptr_t)trampoline_pmd), - __pgprot(_PAGE_TABLE)); - trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot); - - for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) { - size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i; - swapper_pg_dir[o] = - pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i, - __pgprot(_PAGE_TABLE)); - } - for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++) - swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot); -#else - trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] = - pfn_pgd(PFN_DOWN(pa), prot); - - for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) { - size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i; - swapper_pg_dir[o] = - pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot); - } -#endif -} - void __init parse_dtb(unsigned int hartid, void *dtb) { - early_init_dt_scan(__va(dtb)); -} + if (early_init_dt_scan(__va(dtb))) + return; -static void __init setup_bootmem(void) -{ - struct memblock_region *reg; - phys_addr_t mem_size = 0; - - /* Find the memory region containing the kernel */ - for_each_memblock(memory, reg) { - phys_addr_t vmlinux_end = __pa(_end); - phys_addr_t end = reg->base + reg->size; - - if (reg->base <= vmlinux_end && vmlinux_end <= end) { - /* - * Reserve from the start of the region to the end of - * the kernel - */ - memblock_reserve(reg->base, vmlinux_end - reg->base); - mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET); - } - } - BUG_ON(mem_size == 0); - - set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = memblock_end_of_DRAM(); - -#ifdef CONFIG_BLK_DEV_INITRD - setup_initrd(); -#endif /* CONFIG_BLK_DEV_INITRD */ - - early_init_fdt_reserve_self(); - early_init_fdt_scan_reserved_mem(); - memblock_allow_resize(); - memblock_dump_all(); - - for_each_memblock(memory, reg) { - unsigned long start_pfn = memblock_region_memory_base_pfn(reg); - unsigned long end_pfn = memblock_region_memory_end_pfn(reg); - - memblock_set_node(PFN_PHYS(start_pfn), - PFN_PHYS(end_pfn - start_pfn), - &memblock.memory, 0); - } + pr_err("No DTB passed to the kernel\n"); +#ifdef CONFIG_CMDLINE_FORCE + strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + pr_info("Forcing kernel command line to: %s\n", boot_command_line); +#endif } void __init setup_arch(char **cmdline_p) { - *cmdline_p = boot_command_line; - - parse_early_param(); - init_mm.start_code = (unsigned long) _stext; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; init_mm.brk = (unsigned long) _end; + *cmdline_p = boot_command_line; + + parse_early_param(); + setup_bootmem(); paging_init(); unflatten_device_tree(); @@ -224,4 +101,3 @@ void __init setup_arch(char **cmdline_p) riscv_fill_hwcap(); } - diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 57b1383e5ef7..0c41d07ec281 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -23,6 +23,7 @@ #include <linux/smp.h> #include <linux/sched.h> #include <linux/seq_file.h> +#include <linux/delay.h> #include <asm/sbi.h> #include <asm/tlbflush.h> @@ -31,9 +32,19 @@ enum ipi_message_type { IPI_RESCHEDULE, IPI_CALL_FUNC, + IPI_CPU_STOP, IPI_MAX }; +unsigned long __cpuid_to_hartid_map[NR_CPUS] = { + [0 ... NR_CPUS-1] = INVALID_HARTID +}; + +void __init smp_setup_processor_id(void) +{ + cpuid_to_hartid_map(0) = boot_cpu_hartid; +} + /* A collection of single bit ipi messages. */ static struct { unsigned long stats[IPI_MAX] ____cacheline_aligned; @@ -49,7 +60,6 @@ int riscv_hartid_to_cpuid(int hartid) return i; pr_err("Couldn't find cpu id for hartid [%d]\n", hartid); - BUG(); return i; } @@ -66,6 +76,13 @@ int setup_profiling_timer(unsigned int multiplier) return -EINVAL; } +static void ipi_stop(void) +{ + set_cpu_online(smp_processor_id(), false); + while (1) + wait_for_interrupt(); +} + void riscv_software_interrupt(void) { unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits; @@ -94,6 +111,11 @@ void riscv_software_interrupt(void) generic_smp_call_function_interrupt(); } + if (ops & (1 << IPI_CPU_STOP)) { + stats[IPI_CPU_STOP]++; + ipi_stop(); + } + BUG_ON((ops >> IPI_MAX) != 0); /* Order data access and bit testing. */ @@ -121,6 +143,7 @@ send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation) static const char * const ipi_names[] = { [IPI_RESCHEDULE] = "Rescheduling interrupts", [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", }; void show_ipi_stats(struct seq_file *p, int prec) @@ -146,15 +169,29 @@ void arch_send_call_function_single_ipi(int cpu) send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC); } -static void ipi_stop(void *unused) -{ - while (1) - wait_for_interrupt(); -} - void smp_send_stop(void) { - on_each_cpu(ipi_stop, NULL, 1); + unsigned long timeout; + + if (num_online_cpus() > 1) { + cpumask_t mask; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + if (system_state <= SYSTEM_RUNNING) + pr_crit("SMP: stopping secondary CPUs\n"); + send_ipi_message(&mask, IPI_CPU_STOP); + } + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while (num_online_cpus() > 1 && timeout--) + udelay(1); + + if (num_online_cpus() > 1) + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(cpu_online_mask)); } void smp_send_reschedule(int cpu) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index fc185ecabb0a..eb533b5c2c8c 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -39,6 +39,7 @@ void *__cpu_up_stack_pointer[NR_CPUS]; void *__cpu_up_task_pointer[NR_CPUS]; +static DECLARE_COMPLETION(cpu_running); void __init smp_prepare_boot_cpu(void) { @@ -50,30 +51,31 @@ void __init smp_prepare_cpus(unsigned int max_cpus) void __init setup_smp(void) { - struct device_node *dn = NULL; + struct device_node *dn; int hart; bool found_boot_cpu = false; int cpuid = 1; - while ((dn = of_find_node_by_type(dn, "cpu"))) { + for_each_of_cpu_node(dn) { hart = riscv_of_processor_hartid(dn); - if (hart < 0) { - of_node_put(dn); + if (hart < 0) continue; - } if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = 1; - of_node_put(dn); continue; } + if (cpuid >= NR_CPUS) { + pr_warn("Invalid cpuid [%d] for hartid [%d]\n", + cpuid, hart); + break; + } cpuid_to_hartid_map(cpuid) = hart; set_cpu_possible(cpuid, true); set_cpu_present(cpuid, true); cpuid++; - of_node_put(dn); } BUG_ON(!found_boot_cpu); @@ -81,6 +83,7 @@ void __init setup_smp(void) int __cpu_up(unsigned int cpu, struct task_struct *tidle) { + int ret = 0; int hartid = cpuid_to_hartid_map(cpu); tidle->thread_info.cpu = cpu; @@ -96,10 +99,16 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) task_stack_page(tidle) + THREAD_SIZE); WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle); - while (!cpu_online(cpu)) - cpu_relax(); + lockdep_assert_held(&cpu_running); + wait_for_completion_timeout(&cpu_running, + msecs_to_jiffies(1000)); + + if (!cpu_online(cpu)) { + pr_crit("CPU%u: failed to come online\n", cpu); + ret = -EIO; + } - return 0; + return ret; } void __init smp_cpus_done(unsigned int max_cpus) @@ -125,6 +134,7 @@ asmlinkage void __init smp_callin(void) * a local TLB flush right now just in case. */ local_flush_tlb_all(); + complete(&cpu_running); /* * Disable preemption before enabling interrupts, so we don't try to * schedule a CPU that hasn't actually started yet. diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 582cb153eb24..0cd044122234 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -54,7 +54,6 @@ static int __init vdso_init(void) struct page *pg; pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); - ClearPageReserved(pg); vdso_pagelist[i] = pg; } vdso_pagelist[i] = virt_to_page(vdso_data); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index eed1c137f618..fec62b24df89 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -2,9 +2,11 @@ # Symbols present in the vdso vdso-syms = rt_sigreturn +ifdef CONFIG_64BIT vdso-syms += gettimeofday vdso-syms += clock_gettime vdso-syms += clock_getres +endif vdso-syms += getcpu vdso-syms += flush_icache |