diff options
Diffstat (limited to 'arch/loongarch/kernel')
26 files changed, 1935 insertions, 59 deletions
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 42be564278fa..fcaa024a685e 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -7,13 +7,27 @@ extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ - elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o + elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ + alternative.o unaligned.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o obj-$(CONFIG_CPU_HAS_FPU) += fpu.o +ifdef CONFIG_FUNCTION_TRACER + ifndef CONFIG_DYNAMIC_FTRACE + obj-y += mcount.o ftrace.o + CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) + else + obj-y += mcount_dyn.o ftrace_dyn.o + CFLAGS_REMOVE_ftrace_dyn.o = $(CC_FLAGS_FTRACE) + endif + CFLAGS_REMOVE_inst.o = $(CC_FLAGS_FTRACE) + CFLAGS_REMOVE_time.o = $(CC_FLAGS_FTRACE) + CFLAGS_REMOVE_perf_event.o = $(CC_FLAGS_FTRACE) +endif + obj-$(CONFIG_MODULES) += module.o module-sections.o obj-$(CONFIG_STACKTRACE) += stacktrace.o diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 8319cc409009..98f431157e4c 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -12,6 +12,7 @@ #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/memblock.h> +#include <linux/of_fdt.h> #include <linux/serial_core.h> #include <asm/io.h> #include <asm/numa.h> @@ -139,20 +140,26 @@ static void __init acpi_process_madt(void) loongson_sysconf.nr_cpus = num_processors; } +#ifndef CONFIG_SUSPEND +int (*acpi_suspend_lowlevel)(void); +#else +int (*acpi_suspend_lowlevel)(void) = loongarch_acpi_suspend; +#endif + void __init acpi_boot_table_init(void) { /* * If acpi_disabled, bail out */ if (acpi_disabled) - return; + goto fdt_earlycon; /* * Initialize the ACPI boot-time table parser. */ if (acpi_table_init()) { disable_acpi(); - return; + goto fdt_earlycon; } loongson_sysconf.boot_cpu_id = read_csr_cpuid(); @@ -164,6 +171,12 @@ void __init acpi_boot_table_init(void) /* Do not enable ACPI SPCR console by default */ acpi_parse_spcr(earlycon_acpi_spcr_enable, false); + + return; + +fdt_earlycon: + if (earlycon_acpi_spcr_enable) + early_init_dt_scan_chosen_stdout(); } #ifdef CONFIG_ACPI_NUMA diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c new file mode 100644 index 000000000000..c5aebeac960b --- /dev/null +++ b/arch/loongarch/kernel/alternative.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/mm.h> +#include <linux/module.h> +#include <asm/alternative.h> +#include <asm/cacheflush.h> +#include <asm/inst.h> +#include <asm/sections.h> + +int __read_mostly alternatives_patched; + +EXPORT_SYMBOL_GPL(alternatives_patched); + +#define MAX_PATCH_SIZE (((u8)(-1)) / LOONGARCH_INSN_SIZE) + +static int __initdata_or_module debug_alternative; + +static int __init debug_alt(char *str) +{ + debug_alternative = 1; + return 1; +} +__setup("debug-alternative", debug_alt); + +#define DPRINTK(fmt, args...) \ +do { \ + if (debug_alternative) \ + printk(KERN_DEBUG "%s: " fmt "\n", __func__, ##args); \ +} while (0) + +#define DUMP_WORDS(buf, count, fmt, args...) \ +do { \ + if (unlikely(debug_alternative)) { \ + int _j; \ + union loongarch_instruction *_buf = buf; \ + \ + if (!(count)) \ + break; \ + \ + printk(KERN_DEBUG fmt, ##args); \ + for (_j = 0; _j < count - 1; _j++) \ + printk(KERN_CONT "<%08x> ", _buf[_j].word); \ + printk(KERN_CONT "<%08x>\n", _buf[_j].word); \ + } \ +} while (0) + +/* Use this to add nops to a buffer, then text_poke the whole buffer. */ +static void __init_or_module add_nops(union loongarch_instruction *insn, int count) +{ + while (count--) { + insn->word = INSN_NOP; + insn++; + } +} + +/* Is the jump addr in local .altinstructions */ +static inline bool in_alt_jump(unsigned long jump, void *start, void *end) +{ + return jump >= (unsigned long)start && jump < (unsigned long)end; +} + +static void __init_or_module recompute_jump(union loongarch_instruction *buf, + union loongarch_instruction *dest, union loongarch_instruction *src, + void *start, void *end) +{ + unsigned int si, si_l, si_h; + unsigned long cur_pc, jump_addr, pc; + long offset; + + cur_pc = (unsigned long)src; + pc = (unsigned long)dest; + + si_l = src->reg0i26_format.immediate_l; + si_h = src->reg0i26_format.immediate_h; + switch (src->reg0i26_format.opcode) { + case b_op: + case bl_op: + jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 27); + if (in_alt_jump(jump_addr, start, end)) + return; + offset = jump_addr - pc; + BUG_ON(offset < -SZ_128M || offset >= SZ_128M); + offset >>= 2; + buf->reg0i26_format.immediate_h = offset >> 16; + buf->reg0i26_format.immediate_l = offset; + return; + } + + si_l = src->reg1i21_format.immediate_l; + si_h = src->reg1i21_format.immediate_h; + switch (src->reg1i21_format.opcode) { + case bceqz_op: /* bceqz_op = bcnez_op */ + BUG_ON(buf->reg1i21_format.rj & BIT(4)); + fallthrough; + case beqz_op: + case bnez_op: + jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 22); + if (in_alt_jump(jump_addr, start, end)) + return; + offset = jump_addr - pc; + BUG_ON(offset < -SZ_4M || offset >= SZ_4M); + offset >>= 2; + buf->reg1i21_format.immediate_h = offset >> 16; + buf->reg1i21_format.immediate_l = offset; + return; + } + + si = src->reg2i16_format.immediate; + switch (src->reg2i16_format.opcode) { + case beq_op: + case bne_op: + case blt_op: + case bge_op: + case bltu_op: + case bgeu_op: + jump_addr = cur_pc + sign_extend(si << 2, 17); + if (in_alt_jump(jump_addr, start, end)) + return; + offset = jump_addr - pc; + BUG_ON(offset < -SZ_128K || offset >= SZ_128K); + offset >>= 2; + buf->reg2i16_format.immediate = offset; + return; + } +} + +static int __init_or_module copy_alt_insns(union loongarch_instruction *buf, + union loongarch_instruction *dest, union loongarch_instruction *src, int nr) +{ + int i; + + for (i = 0; i < nr; i++) { + buf[i].word = src[i].word; + + if (is_pc_ins(&src[i])) { + pr_err("Not support pcrel instruction at present!"); + return -EINVAL; + } + + if (is_branch_ins(&src[i]) && + src[i].reg2i16_format.opcode != jirl_op) { + recompute_jump(&buf[i], &dest[i], &src[i], src, src + nr); + } + } + + return 0; +} + +/* + * text_poke_early - Update instructions on a live kernel at boot time + * + * When you use this code to patch more than one byte of an instruction + * you need to make sure that other CPUs cannot execute this code in parallel. + * Also no thread must be currently preempted in the middle of these + * instructions. And on the local CPU you need to be protected again NMI or MCE + * handlers seeing an inconsistent instruction while you patch. + */ +static void *__init_or_module text_poke_early(union loongarch_instruction *insn, + union loongarch_instruction *buf, unsigned int nr) +{ + int i; + unsigned long flags; + + local_irq_save(flags); + + for (i = 0; i < nr; i++) + insn[i].word = buf[i].word; + + local_irq_restore(flags); + + wbflush(); + flush_icache_range((unsigned long)insn, (unsigned long)(insn + nr)); + + return insn; +} + +/* + * Replace instructions with better alternatives for this CPU type. This runs + * before SMP is initialized to avoid SMP problems with self modifying code. + * This implies that asymmetric systems where APs have less capabilities than + * the boot processor are not handled. Tough. Make sure you disable such + * features by hand. + */ +void __init_or_module apply_alternatives(struct alt_instr *start, struct alt_instr *end) +{ + struct alt_instr *a; + unsigned int nr_instr, nr_repl, nr_insnbuf; + union loongarch_instruction *instr, *replacement; + union loongarch_instruction insnbuf[MAX_PATCH_SIZE]; + + DPRINTK("alt table %px, -> %px", start, end); + /* + * The scan order should be from start to end. A later scanned + * alternative code can overwrite previously scanned alternative code. + * Some kernel functions (e.g. memcpy, memset, etc) use this order to + * patch code. + * + * So be careful if you want to change the scan order to any other + * order. + */ + for (a = start; a < end; a++) { + nr_insnbuf = 0; + + instr = (void *)&a->instr_offset + a->instr_offset; + replacement = (void *)&a->replace_offset + a->replace_offset; + + BUG_ON(a->instrlen > sizeof(insnbuf)); + BUG_ON(a->instrlen & 0x3); + BUG_ON(a->replacementlen & 0x3); + + nr_instr = a->instrlen / LOONGARCH_INSN_SIZE; + nr_repl = a->replacementlen / LOONGARCH_INSN_SIZE; + + if (!cpu_has(a->feature)) { + DPRINTK("feat not exist: %d, old: (%px len: %d), repl: (%px, len: %d)", + a->feature, instr, a->instrlen, + replacement, a->replacementlen); + + continue; + } + + DPRINTK("feat: %d, old: (%px len: %d), repl: (%px, len: %d)", + a->feature, instr, a->instrlen, + replacement, a->replacementlen); + + DUMP_WORDS(instr, nr_instr, "%px: old_insn: ", instr); + DUMP_WORDS(replacement, nr_repl, "%px: rpl_insn: ", replacement); + + copy_alt_insns(insnbuf, instr, replacement, nr_repl); + nr_insnbuf = nr_repl; + + if (nr_instr > nr_repl) { + add_nops(insnbuf + nr_repl, nr_instr - nr_repl); + nr_insnbuf += nr_instr - nr_repl; + } + DUMP_WORDS(insnbuf, nr_insnbuf, "%px: final_insn: ", instr); + + text_poke_early(instr, insnbuf, nr_insnbuf); + } +} + +void __init alternative_instructions(void) +{ + apply_alternatives(__alt_instructions, __alt_instructions_end); + + alternatives_patched = 1; +} diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index bdd88eda9513..4bdb203fc66e 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -68,6 +68,9 @@ void output_task_defines(void) OFFSET(TASK_FLAGS, task_struct, flags); OFFSET(TASK_MM, task_struct, mm); OFFSET(TASK_PID, task_struct, pid); +#if defined(CONFIG_STACKPROTECTOR) + OFFSET(TASK_STACK_CANARY, task_struct, stack_canary); +#endif DEFINE(TASK_STRUCT_SIZE, sizeof(struct task_struct)); BLANK(); } @@ -257,3 +260,15 @@ void output_smpboot_defines(void) BLANK(); } #endif + +#ifdef CONFIG_HIBERNATION +void output_pbe_defines(void) +{ + COMMENT(" Linux struct pbe offsets. "); + OFFSET(PBE_ADDRESS, pbe, address); + OFFSET(PBE_ORIG_ADDRESS, pbe, orig_address); + OFFSET(PBE_NEXT, pbe, next); + DEFINE(PBE_SIZE, sizeof(struct pbe)); + BLANK(); +} +#endif diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index d75ce73e8ff8..3d448fef3af4 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -28,16 +28,29 @@ static unsigned long efi_nr_tables; static unsigned long efi_config_table; static unsigned long __initdata boot_memmap = EFI_INVALID_TABLE_ADDR; +static unsigned long __initdata fdt_pointer = EFI_INVALID_TABLE_ADDR; static efi_system_table_t *efi_systab; static efi_config_table_type_t arch_tables[] __initdata = { {LINUX_EFI_BOOT_MEMMAP_GUID, &boot_memmap, "MEMMAP" }, + {DEVICE_TREE_GUID, &fdt_pointer, "FDTPTR" }, {}, }; +void __init *efi_fdt_pointer(void) +{ + if (!efi_systab) + return NULL; + + if (fdt_pointer == EFI_INVALID_TABLE_ADDR) + return NULL; + + return early_memremap_ro(fdt_pointer, SZ_64K); +} + void __init efi_runtime_init(void) { - if (!efi_enabled(EFI_BOOT)) + if (!efi_enabled(EFI_BOOT) || !efi_systab->runtime) return; if (efi_runtime_disabled()) { diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 6d56a463b091..6b3bfb0092e6 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -11,6 +11,7 @@ #include <asm/early_ioremap.h> #include <asm/bootinfo.h> #include <asm/loongson.h> +#include <asm/setup.h> u64 efi_system_table; struct loongson_system_configuration loongson_sysconf; @@ -27,6 +28,7 @@ void __init init_environ(void) clear_bit(EFI_BOOT, &efi.flags); strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE); + strscpy(init_command_line, cmdline, COMMAND_LINE_SIZE); early_memunmap(cmdline, COMMAND_LINE_SIZE); efi_system_table = fw_arg2; diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index 576b3370a296..ccde94140c89 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -8,6 +8,7 @@ */ #include <asm/asm.h> #include <asm/asmmacro.h> +#include <asm/asm-extable.h> #include <asm/asm-offsets.h> #include <asm/errno.h> #include <asm/export.h> @@ -21,9 +22,7 @@ .macro EX insn, reg, src, offs .ex\@: \insn \reg, \src, \offs - .section __ex_table,"a" - PTR .ex\@, fault - .previous + _asm_extable .ex\@, fault .endm .macro sc_save_fp base diff --git a/arch/loongarch/kernel/ftrace.c b/arch/loongarch/kernel/ftrace.c new file mode 100644 index 000000000000..8c3ec1bc7aad --- /dev/null +++ b/arch/loongarch/kernel/ftrace.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Loongson Technology Corporation Limited + */ + +#include <linux/init.h> +#include <linux/ftrace.h> +#include <linux/syscalls.h> +#include <linux/uaccess.h> + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/cacheflush.h> +#include <asm/inst.h> +#include <asm/loongarch.h> +#include <asm/syscall.h> + +#include <asm-generic/sections.h> + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +/* + * As `call _mcount` follows LoongArch psABI, ra-saved operation and + * stack operation can be found before this insn. + */ + +static int ftrace_get_parent_ra_addr(unsigned long insn_addr, int *ra_off) +{ + int limit = 32; + union loongarch_instruction *insn; + + insn = (union loongarch_instruction *)insn_addr; + + do { + insn--; + limit--; + + if (is_ra_save_ins(insn)) + *ra_off = -((1 << 12) - insn->reg2i12_format.immediate); + + } while (!is_stack_alloc_ins(insn) && limit); + + if (!limit) + return -EINVAL; + + return 0; +} + +void prepare_ftrace_return(unsigned long self_addr, + unsigned long callsite_sp, unsigned long old) +{ + int ra_off; + unsigned long return_hooker = (unsigned long)&return_to_handler; + + if (unlikely(ftrace_graph_is_dead())) + return; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + if (ftrace_get_parent_ra_addr(self_addr, &ra_off)) + goto out; + + if (!function_graph_enter(old, self_addr, 0, NULL)) + *(unsigned long *)(callsite_sp + ra_off) = return_hooker; + + return; + +out: + ftrace_graph_stop(); + WARN_ON(1); +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c new file mode 100644 index 000000000000..0f07591cab30 --- /dev/null +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Based on arch/arm64/kernel/ftrace.c + * + * Copyright (C) 2022 Loongson Technology Corporation Limited + */ + +#include <linux/ftrace.h> +#include <linux/uaccess.h> + +#include <asm/inst.h> +#include <asm/module.h> + +static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, bool validate) +{ + u32 replaced; + + if (validate) { + if (larch_insn_read((void *)pc, &replaced)) + return -EFAULT; + + if (replaced != old) + return -EINVAL; + } + + if (larch_insn_patch_text((void *)pc, new)) + return -EPERM; + + return 0; +} + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + +#ifdef CONFIG_MODULES +static inline int __get_mod(struct module **mod, unsigned long addr) +{ + preempt_disable(); + *mod = __module_text_address(addr); + preempt_enable(); + + if (WARN_ON(!(*mod))) + return -EINVAL; + + return 0; +} + +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +{ + struct plt_entry *plt = mod->arch.ftrace_trampolines; + + if (addr == FTRACE_ADDR) + return &plt[FTRACE_PLT_IDX]; + if (addr == FTRACE_REGS_ADDR && + IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return &plt[FTRACE_REGS_PLT_IDX]; + + return NULL; +} + +static unsigned long get_plt_addr(struct module *mod, unsigned long addr) +{ + struct plt_entry *plt; + + plt = get_ftrace_plt(mod, addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)addr); + return -EINVAL; + } + + return (unsigned long)plt; +} +#endif + +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) +{ + u32 old, new; + unsigned long pc; + long offset __maybe_unused; + + pc = rec->ip + LOONGARCH_INSN_SIZE; + +#ifdef CONFIG_MODULES + offset = (long)pc - (long)addr; + + if (offset < -SZ_128M || offset >= SZ_128M) { + int ret; + struct module *mod; + + ret = __get_mod(&mod, pc); + if (ret) + return ret; + + addr = get_plt_addr(mod, addr); + + old_addr = get_plt_addr(mod, old_addr); + } +#endif + + new = larch_insn_gen_bl(pc, addr); + old = larch_insn_gen_bl(pc, old_addr); + + return ftrace_modify_code(pc, old, new, true); +} + +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + u32 new; + unsigned long pc; + + pc = (unsigned long)&ftrace_call; + new = larch_insn_gen_bl(pc, (unsigned long)func); + + return ftrace_modify_code(pc, 0, new, false); +} + +/* + * The compiler has inserted 2 NOPs before the regular function prologue. + * T series registers are available and safe because of LoongArch's psABI. + * + * At runtime, we can replace nop with bl to enable ftrace call and replace bl + * with nop to disable ftrace call. The bl requires us to save the original RA + * value, so it saves RA at t0 here. + * + * Details are: + * + * | Compiled | Disabled | Enabled | + * +------------+------------------------+------------------------+ + * | nop | move t0, ra | move t0, ra | + * | nop | nop | bl ftrace_caller | + * | func_body | func_body | func_body | + * + * The RA value will be recovered by ftrace_regs_entry, and restored into RA + * before returning to the regular function prologue. When a function is not + * being traced, the "move t0, ra" is not harmful. + */ + +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + u32 old, new; + unsigned long pc; + + pc = rec->ip; + old = larch_insn_gen_nop(); + new = larch_insn_gen_move(LOONGARCH_GPR_T0, LOONGARCH_GPR_RA); + + return ftrace_modify_code(pc, old, new, true); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + u32 old, new; + unsigned long pc; + long offset __maybe_unused; + + pc = rec->ip + LOONGARCH_INSN_SIZE; + +#ifdef CONFIG_MODULES + offset = (long)pc - (long)addr; + + if (offset < -SZ_128M || offset >= SZ_128M) { + int ret; + struct module *mod; + + ret = __get_mod(&mod, pc); + if (ret) + return ret; + + addr = get_plt_addr(mod, addr); + } +#endif + + old = larch_insn_gen_nop(); + new = larch_insn_gen_bl(pc, addr); + + return ftrace_modify_code(pc, old, new, true); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) +{ + u32 old, new; + unsigned long pc; + long offset __maybe_unused; + + pc = rec->ip + LOONGARCH_INSN_SIZE; + +#ifdef CONFIG_MODULES + offset = (long)pc - (long)addr; + + if (offset < -SZ_128M || offset >= SZ_128M) { + int ret; + struct module *mod; + + ret = __get_mod(&mod, pc); + if (ret) + return ret; + + addr = get_plt_addr(mod, addr); + } +#endif + + new = larch_insn_gen_nop(); + old = larch_insn_gen_bl(pc, addr); + + return ftrace_modify_code(pc, old, new, true); +} + +void arch_ftrace_update_code(int command) +{ + command |= FTRACE_MAY_SLEEP; + ftrace_modify_all_code(command); +} + +int __init ftrace_dyn_arch_init(void) +{ + return 0; +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent) +{ + unsigned long old; + unsigned long return_hooker = (unsigned long)&return_to_handler; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + if (!function_graph_enter(old, self_addr, 0, parent)) + *parent = return_hooker; +} + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + struct pt_regs *regs = &fregs->regs; + unsigned long *parent = (unsigned long *)®s->regs[1]; + + prepare_ftrace_return(ip, (unsigned long *)parent); +} +#else +static int ftrace_modify_graph_caller(bool enable) +{ + u32 branch, nop; + unsigned long pc, func; + extern void ftrace_graph_call(void); + + pc = (unsigned long)&ftrace_graph_call; + func = (unsigned long)&ftrace_graph_caller; + + nop = larch_insn_gen_nop(); + branch = larch_insn_gen_b(pc, func); + + if (enable) + return ftrace_modify_code(pc, nop, branch, true); + else + return ftrace_modify_code(pc, branch, nop, true); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index b1df0ec34bd1..512579d79b22 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -2,8 +2,135 @@ /* * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/sizes.h> +#include <linux/uaccess.h> + +#include <asm/cacheflush.h> #include <asm/inst.h> +static DEFINE_RAW_SPINLOCK(patch_lock); + +int larch_insn_read(void *addr, u32 *insnp) +{ + int ret; + u32 val; + + ret = copy_from_kernel_nofault(&val, addr, LOONGARCH_INSN_SIZE); + if (!ret) + *insnp = val; + + return ret; +} + +int larch_insn_write(void *addr, u32 insn) +{ + int ret; + unsigned long flags = 0; + + raw_spin_lock_irqsave(&patch_lock, flags); + ret = copy_to_kernel_nofault(addr, &insn, LOONGARCH_INSN_SIZE); + raw_spin_unlock_irqrestore(&patch_lock, flags); + + return ret; +} + +int larch_insn_patch_text(void *addr, u32 insn) +{ + int ret; + u32 *tp = addr; + + if ((unsigned long)tp & 3) + return -EINVAL; + + ret = larch_insn_write(tp, insn); + if (!ret) + flush_icache_range((unsigned long)tp, + (unsigned long)tp + LOONGARCH_INSN_SIZE); + + return ret; +} + +u32 larch_insn_gen_nop(void) +{ + return INSN_NOP; +} + +u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) +{ + long offset = dest - pc; + unsigned int immediate_l, immediate_h; + union loongarch_instruction insn; + + if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) { + pr_warn("The generated b instruction is out of range.\n"); + return INSN_BREAK; + } + + offset >>= 2; + + immediate_l = offset & 0xffff; + offset >>= 16; + immediate_h = offset & 0x3ff; + + insn.reg0i26_format.opcode = b_op; + insn.reg0i26_format.immediate_l = immediate_l; + insn.reg0i26_format.immediate_h = immediate_h; + + return insn.word; +} + +u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest) +{ + long offset = dest - pc; + unsigned int immediate_l, immediate_h; + union loongarch_instruction insn; + + if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) { + pr_warn("The generated bl instruction is out of range.\n"); + return INSN_BREAK; + } + + offset >>= 2; + + immediate_l = offset & 0xffff; + offset >>= 16; + immediate_h = offset & 0x3ff; + + insn.reg0i26_format.opcode = bl_op; + insn.reg0i26_format.immediate_l = immediate_l; + insn.reg0i26_format.immediate_h = immediate_h; + + return insn.word; +} + +u32 larch_insn_gen_or(enum loongarch_gpr rd, enum loongarch_gpr rj, enum loongarch_gpr rk) +{ + union loongarch_instruction insn; + + insn.reg3_format.opcode = or_op; + insn.reg3_format.rd = rd; + insn.reg3_format.rj = rj; + insn.reg3_format.rk = rk; + + return insn.word; +} + +u32 larch_insn_gen_move(enum loongarch_gpr rd, enum loongarch_gpr rj) +{ + return larch_insn_gen_or(rd, rj, 0); +} + +u32 larch_insn_gen_lu12iw(enum loongarch_gpr rd, int imm) +{ + union loongarch_instruction insn; + + insn.reg1i20_format.opcode = lu12iw_op; + insn.reg1i20_format.rd = rd; + insn.reg1i20_format.immediate = imm; + + return insn.word; +} + u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm) { union loongarch_instruction insn; diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S new file mode 100644 index 000000000000..8cdc1563cd33 --- /dev/null +++ b/arch/loongarch/kernel/mcount.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * LoongArch specific _mcount support + * + * Copyright (C) 2022 Loongson Technology Corporation Limited + */ + +#include <asm/export.h> +#include <asm/ftrace.h> +#include <asm/regdef.h> +#include <asm/stackframe.h> + + .text + +#define MCOUNT_S0_OFFSET (0) +#define MCOUNT_RA_OFFSET (SZREG) +#define MCOUNT_STACK_SIZE (2 * SZREG) + + .macro MCOUNT_SAVE_REGS + PTR_ADDI sp, sp, -MCOUNT_STACK_SIZE + PTR_S s0, sp, MCOUNT_S0_OFFSET + PTR_S ra, sp, MCOUNT_RA_OFFSET + move s0, a0 + .endm + + .macro MCOUNT_RESTORE_REGS + move a0, s0 + PTR_L ra, sp, MCOUNT_RA_OFFSET + PTR_L s0, sp, MCOUNT_S0_OFFSET + PTR_ADDI sp, sp, MCOUNT_STACK_SIZE + .endm + +SYM_FUNC_START(_mcount) + la.pcrel t1, ftrace_stub + la.pcrel t2, ftrace_trace_function /* Prepare t2 for (1) */ + PTR_L t2, t2, 0 + beq t1, t2, fgraph_trace + + MCOUNT_SAVE_REGS + + move a0, ra /* arg0: self return address */ + move a1, s0 /* arg1: parent's return address */ + jirl ra, t2, 0 /* (1) call *ftrace_trace_function */ + + MCOUNT_RESTORE_REGS + +fgraph_trace: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + la.pcrel t1, ftrace_stub + la.pcrel t3, ftrace_graph_return + PTR_L t3, t3, 0 + bne t1, t3, ftrace_graph_caller + la.pcrel t1, ftrace_graph_entry_stub + la.pcrel t3, ftrace_graph_entry + PTR_L t3, t3, 0 + bne t1, t3, ftrace_graph_caller +#endif + +SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) + jr ra +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_INNER_LABEL(ftrace_graph_func, SYM_L_GLOBAL) + bl ftrace_stub +#endif +SYM_FUNC_END(_mcount) +EXPORT_SYMBOL(_mcount) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_FUNC_START(ftrace_graph_caller) + MCOUNT_SAVE_REGS + + PTR_ADDI a0, ra, -4 /* arg0: Callsite self return addr */ + PTR_ADDI a1, sp, MCOUNT_STACK_SIZE /* arg1: Callsite sp */ + move a2, s0 /* arg2: Callsite parent ra */ + bl prepare_ftrace_return + + MCOUNT_RESTORE_REGS + jr ra +SYM_FUNC_END(ftrace_graph_caller) + +SYM_FUNC_START(return_to_handler) + PTR_ADDI sp, sp, -2 * SZREG + PTR_S a0, sp, 0 + PTR_S a1, sp, SZREG + + bl ftrace_return_to_handler + + /* Restore the real parent address: a0 -> ra */ + move ra, a0 + + PTR_L a0, sp, 0 + PTR_L a1, sp, SZREG + PTR_ADDI sp, sp, 2 * SZREG + jr ra +SYM_FUNC_END(return_to_handler) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S new file mode 100644 index 000000000000..bbabf06244c2 --- /dev/null +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -0,0 +1,149 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Loongson Technology Corporation Limited + */ + +#include <asm/export.h> +#include <asm/ftrace.h> +#include <asm/regdef.h> +#include <asm/stackframe.h> + + .text +/* + * Due to -fpatchable-function-entry=2: the compiler inserted 2 NOPs before the + * regular C function prologue. When PC arrived here, the last 2 instructions + * are as follows: + * move t0, ra + * bl callsite (for modules, callsite is a tramplione) + * + * modules trampoline is as follows: + * lu12i.w t1, callsite[31:12] + * lu32i.d t1, callsite[51:32] + * lu52i.d t1, t1, callsite[63:52] + * jirl zero, t1, callsite[11:0] >> 2 + * + * See arch/loongarch/kernel/ftrace_dyn.c for details. Here, pay attention to + * that the T series regs are available and safe because each C functions + * follows the LoongArch's psABI as well. + */ + + .macro ftrace_regs_entry allregs=0 + PTR_ADDI sp, sp, -PT_SIZE + PTR_S t0, sp, PT_R1 /* Save parent ra at PT_R1(RA) */ + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S a2, sp, PT_R6 + PTR_S a3, sp, PT_R7 + PTR_S a4, sp, PT_R8 + PTR_S a5, sp, PT_R9 + PTR_S a6, sp, PT_R10 + PTR_S a7, sp, PT_R11 + PTR_S fp, sp, PT_R22 + .if \allregs + PTR_S tp, sp, PT_R2 + PTR_S t0, sp, PT_R12 + PTR_S t1, sp, PT_R13 + PTR_S t2, sp, PT_R14 + PTR_S t3, sp, PT_R15 + PTR_S t4, sp, PT_R16 + PTR_S t5, sp, PT_R17 + PTR_S t6, sp, PT_R18 + PTR_S t7, sp, PT_R19 + PTR_S t8, sp, PT_R20 + PTR_S u0, sp, PT_R21 + PTR_S s0, sp, PT_R23 + PTR_S s1, sp, PT_R24 + PTR_S s2, sp, PT_R25 + PTR_S s3, sp, PT_R26 + PTR_S s4, sp, PT_R27 + PTR_S s5, sp, PT_R28 + PTR_S s6, sp, PT_R29 + PTR_S s7, sp, PT_R30 + PTR_S s8, sp, PT_R31 + /* Clear it for later use as a flag sometimes. */ + PTR_S zero, sp, PT_R0 + .endif + PTR_S ra, sp, PT_ERA /* Save trace function ra at PT_ERA */ + PTR_ADDI t8, sp, PT_SIZE + PTR_S t8, sp, PT_R3 + .endm + +SYM_FUNC_START(ftrace_stub) + jr ra +SYM_FUNC_END(ftrace_stub) + +SYM_CODE_START(ftrace_common) + PTR_ADDI a0, ra, -8 /* arg0: ip */ + move a1, t0 /* arg1: parent_ip */ + la.pcrel t1, function_trace_op + PTR_L a2, t1, 0 /* arg2: op */ + move a3, sp /* arg3: regs */ + +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + bl ftrace_stub +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) + nop /* b ftrace_graph_caller */ +#endif + +/* + * As we didn't use S series regs in this assmembly code and all calls + * are C function which will save S series regs by themselves, there is + * no need to restore S series regs. The T series is available and safe + * at the callsite, so there is no need to restore the T series regs. + */ +ftrace_common_return: + PTR_L ra, sp, PT_R1 + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_L a2, sp, PT_R6 + PTR_L a3, sp, PT_R7 + PTR_L a4, sp, PT_R8 + PTR_L a5, sp, PT_R9 + PTR_L a6, sp, PT_R10 + PTR_L a7, sp, PT_R11 + PTR_L fp, sp, PT_R22 + PTR_L t0, sp, PT_ERA + PTR_ADDI sp, sp, PT_SIZE + jr t0 +SYM_CODE_END(ftrace_common) + +SYM_CODE_START(ftrace_caller) + ftrace_regs_entry allregs=0 + b ftrace_common +SYM_CODE_END(ftrace_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +SYM_CODE_START(ftrace_regs_caller) + ftrace_regs_entry allregs=1 + b ftrace_common +SYM_CODE_END(ftrace_regs_caller) +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_CODE_START(ftrace_graph_caller) + PTR_L a0, sp, PT_ERA + PTR_ADDI a0, a0, -8 /* arg0: self_addr */ + PTR_ADDI a1, sp, PT_R1 /* arg1: parent */ + bl prepare_ftrace_return + b ftrace_common_return +SYM_CODE_END(ftrace_graph_caller) + +SYM_CODE_START(return_to_handler) + /* Save return value regs */ + PTR_ADDI sp, sp, -2 * SZREG + PTR_S a0, sp, 0 + PTR_S a1, sp, SZREG + + move a0, zero + bl ftrace_return_to_handler + move ra, a0 + + /* Restore return value regs */ + PTR_L a0, sp, 0 + PTR_L a1, sp, SZREG + PTR_ADDI sp, sp, 2 * SZREG + + jr ra +SYM_CODE_END(return_to_handler) +#endif diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c index d296a70b758f..d4dbcda1c4b0 100644 --- a/arch/loongarch/kernel/module-sections.c +++ b/arch/loongarch/kernel/module-sections.c @@ -6,18 +6,19 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/ftrace.h> -Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val) +Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr 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); + struct got_entry *got = get_got_entry(val, sechdrs, got_sec); if (got) return (Elf_Addr)got; /* There is no GOT entry for val yet, create a new one. */ - got = (struct got_entry *)got_sec->shdr->sh_addr; + got = (struct got_entry *)sechdrs[got_sec->shndx].sh_addr; got[i] = emit_got_entry(val); got_sec->num_entries++; @@ -33,12 +34,12 @@ Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val) return (Elf_Addr)&got[i]; } -Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Addr val) +Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val) { int nr; struct mod_section *plt_sec = &mod->arch.plt; struct mod_section *plt_idx_sec = &mod->arch.plt_idx; - struct plt_entry *plt = get_plt_entry(val, plt_sec, plt_idx_sec); + struct plt_entry *plt = get_plt_entry(val, sechdrs, plt_sec, plt_idx_sec); struct plt_idx_entry *plt_idx; if (plt) @@ -47,9 +48,9 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Addr val) nr = plt_sec->num_entries; /* There is no duplicate entry, create a new one */ - plt = (struct plt_entry *)plt_sec->shdr->sh_addr; + plt = (struct plt_entry *)sechdrs[plt_sec->shndx].sh_addr; plt[nr] = emit_plt_entry(val); - plt_idx = (struct plt_idx_entry *)plt_idx_sec->shdr->sh_addr; + plt_idx = (struct plt_idx_entry *)sechdrs[plt_idx_sec->shndx].sh_addr; plt_idx[nr] = emit_plt_idx_entry(val); plt_sec->num_entries++; @@ -103,28 +104,31 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { unsigned int i, num_plts = 0, num_gots = 0; + Elf_Shdr *got_sec, *plt_sec, *plt_idx_sec, *tramp = NULL; /* * Find the empty .plt sections. */ for (i = 0; i < ehdr->e_shnum; i++) { if (!strcmp(secstrings + sechdrs[i].sh_name, ".got")) - mod->arch.got.shdr = sechdrs + i; + mod->arch.got.shndx = i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt")) - mod->arch.plt.shdr = sechdrs + i; + mod->arch.plt.shndx = i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt.idx")) - mod->arch.plt_idx.shdr = sechdrs + i; + mod->arch.plt_idx.shndx = i; + else if (!strcmp(secstrings + sechdrs[i].sh_name, ".ftrace_trampoline")) + tramp = sechdrs + i; } - if (!mod->arch.got.shdr) { + if (!mod->arch.got.shndx) { pr_err("%s: module GOT section(s) missing\n", mod->name); return -ENOEXEC; } - if (!mod->arch.plt.shdr) { + if (!mod->arch.plt.shndx) { pr_err("%s: module PLT section(s) missing\n", mod->name); return -ENOEXEC; } - if (!mod->arch.plt_idx.shdr) { + if (!mod->arch.plt_idx.shndx) { pr_err("%s: module PLT.IDX section(s) missing\n", mod->name); return -ENOEXEC; } @@ -145,26 +149,36 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, count_max_entries(relas, num_rela, &num_plts, &num_gots); } - mod->arch.got.shdr->sh_type = SHT_NOBITS; - mod->arch.got.shdr->sh_flags = SHF_ALLOC; - mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES; - mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry); + got_sec = sechdrs + mod->arch.got.shndx; + got_sec->sh_type = SHT_NOBITS; + got_sec->sh_flags = SHF_ALLOC; + got_sec->sh_addralign = L1_CACHE_BYTES; + got_sec->sh_size = (num_gots + 1) * sizeof(struct got_entry); mod->arch.got.num_entries = 0; mod->arch.got.max_entries = num_gots; - mod->arch.plt.shdr->sh_type = SHT_NOBITS; - mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC; - mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES; - mod->arch.plt.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_entry); + plt_sec = sechdrs + mod->arch.plt.shndx; + plt_sec->sh_type = SHT_NOBITS; + plt_sec->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + plt_sec->sh_addralign = L1_CACHE_BYTES; + plt_sec->sh_size = (num_plts + 1) * sizeof(struct plt_entry); mod->arch.plt.num_entries = 0; mod->arch.plt.max_entries = num_plts; - mod->arch.plt_idx.shdr->sh_type = SHT_NOBITS; - mod->arch.plt_idx.shdr->sh_flags = SHF_ALLOC; - mod->arch.plt_idx.shdr->sh_addralign = L1_CACHE_BYTES; - mod->arch.plt_idx.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_idx_entry); + plt_idx_sec = sechdrs + mod->arch.plt_idx.shndx; + plt_idx_sec->sh_type = SHT_NOBITS; + plt_idx_sec->sh_flags = SHF_ALLOC; + plt_idx_sec->sh_addralign = L1_CACHE_BYTES; + plt_idx_sec->sh_size = (num_plts + 1) * sizeof(struct plt_idx_entry); mod->arch.plt_idx.num_entries = 0; mod->arch.plt_idx.max_entries = num_plts; + if (tramp) { + tramp->sh_type = SHT_NOBITS; + tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + tramp->sh_addralign = __alignof__(struct plt_entry); + tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); + } + return 0; } diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c index 097595b2fc14..b8b86088b2dd 100644 --- a/arch/loongarch/kernel/module.c +++ b/arch/loongarch/kernel/module.c @@ -15,8 +15,11 @@ #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/fs.h> +#include <linux/ftrace.h> #include <linux/string.h> #include <linux/kernel.h> +#include <asm/alternative.h> +#include <asm/inst.h> static int rela_stack_push(s64 stack_value, s64 *rela_stack, size_t *rela_stack_top) { @@ -98,16 +101,17 @@ static int apply_r_larch_sop_push_dup(struct module *mod, u32 *location, Elf_Add return 0; } -static int apply_r_larch_sop_push_plt_pcrel(struct module *mod, u32 *location, Elf_Addr v, +static int apply_r_larch_sop_push_plt_pcrel(struct module *mod, + Elf_Shdr *sechdrs, u32 *location, Elf_Addr v, s64 *rela_stack, size_t *rela_stack_top, unsigned int type) { ptrdiff_t offset = (void *)v - (void *)location; if (offset >= SZ_128M) - v = module_emit_plt_entry(mod, v); + v = module_emit_plt_entry(mod, sechdrs, v); if (offset < -SZ_128M) - v = module_emit_plt_entry(mod, v); + v = module_emit_plt_entry(mod, sechdrs, v); return apply_r_larch_sop_push_pcrel(mod, location, v, rela_stack, rela_stack_top, type); } @@ -271,17 +275,18 @@ static int apply_r_larch_add_sub(struct module *mod, u32 *location, Elf_Addr v, } } -static int apply_r_larch_b26(struct module *mod, u32 *location, Elf_Addr v, +static int apply_r_larch_b26(struct module *mod, + Elf_Shdr *sechdrs, u32 *location, Elf_Addr v, s64 *rela_stack, size_t *rela_stack_top, unsigned int type) { ptrdiff_t offset = (void *)v - (void *)location; union loongarch_instruction *insn = (union loongarch_instruction *)location; if (offset >= SZ_128M) - v = module_emit_plt_entry(mod, v); + v = module_emit_plt_entry(mod, sechdrs, v); if (offset < -SZ_128M) - v = module_emit_plt_entry(mod, v); + v = module_emit_plt_entry(mod, sechdrs, v); offset = (void *)v - (void *)location; @@ -338,10 +343,11 @@ static int apply_r_larch_pcala(struct module *mod, u32 *location, Elf_Addr v, return 0; } -static int apply_r_larch_got_pc(struct module *mod, u32 *location, Elf_Addr v, +static int apply_r_larch_got_pc(struct module *mod, + Elf_Shdr *sechdrs, u32 *location, Elf_Addr v, s64 *rela_stack, size_t *rela_stack_top, unsigned int type) { - Elf_Addr got = module_emit_got_entry(mod, v); + Elf_Addr got = module_emit_got_entry(mod, sechdrs, v); if (!got) return -EINVAL; @@ -386,13 +392,10 @@ static reloc_rela_handler reloc_rela_handlers[] = { [R_LARCH_SOP_PUSH_PCREL] = apply_r_larch_sop_push_pcrel, [R_LARCH_SOP_PUSH_ABSOLUTE] = apply_r_larch_sop_push_absolute, [R_LARCH_SOP_PUSH_DUP] = apply_r_larch_sop_push_dup, - [R_LARCH_SOP_PUSH_PLT_PCREL] = apply_r_larch_sop_push_plt_pcrel, [R_LARCH_SOP_SUB ... R_LARCH_SOP_IF_ELSE] = apply_r_larch_sop, [R_LARCH_SOP_POP_32_S_10_5 ... R_LARCH_SOP_POP_32_U] = apply_r_larch_sop_imm_field, [R_LARCH_ADD32 ... R_LARCH_SUB64] = apply_r_larch_add_sub, - [R_LARCH_B26] = apply_r_larch_b26, [R_LARCH_PCALA_HI20...R_LARCH_PCALA64_HI12] = apply_r_larch_pcala, - [R_LARCH_GOT_PC_HI20...R_LARCH_GOT_PC_LO12] = apply_r_larch_got_pc, }; int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, @@ -443,7 +446,22 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, sym->st_value, rel[i].r_addend, (u64)location); v = sym->st_value + rel[i].r_addend; - err = handler(mod, location, v, rela_stack, &rela_stack_top, type); + switch (type) { + case R_LARCH_B26: + err = apply_r_larch_b26(mod, sechdrs, location, + v, rela_stack, &rela_stack_top, type); + break; + case R_LARCH_GOT_PC_HI20...R_LARCH_GOT_PC_LO12: + err = apply_r_larch_got_pc(mod, sechdrs, location, + v, rela_stack, &rela_stack_top, type); + break; + case R_LARCH_SOP_PUSH_PLT_PCREL: + err = apply_r_larch_sop_push_plt_pcrel(mod, sechdrs, location, + v, rela_stack, &rela_stack_top, type); + break; + default: + err = handler(mod, location, v, rela_stack, &rela_stack_top, type); + } if (err) return err; } @@ -456,3 +474,36 @@ void *module_alloc(unsigned long size) return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL, PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); } + +static void module_init_ftrace_plt(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, struct module *mod) +{ +#ifdef CONFIG_DYNAMIC_FTRACE + struct plt_entry *ftrace_plts; + + ftrace_plts = (void *)sechdrs->sh_addr; + + ftrace_plts[FTRACE_PLT_IDX] = emit_plt_entry(FTRACE_ADDR); + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + ftrace_plts[FTRACE_REGS_PLT_IDX] = emit_plt_entry(FTRACE_REGS_ADDR); + + mod->arch.ftrace_trampolines = ftrace_plts; +#endif +} + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, struct module *mod) +{ + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { + if (!strcmp(".altinstructions", secstrs + s->sh_name)) + apply_alternatives((void *)s->sh_addr, (void *)s->sh_addr + s->sh_size); + if (!strcmp(".ftrace_trampoline", secstrs + s->sh_name)) + module_init_ftrace_plt(hdr, s, mod); + } + + return 0; +} diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index eb5d3a4c8a7a..708665895b47 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -388,6 +388,21 @@ static void __init numa_default_distance(void) } } +/* + * fake_numa_init() - For Non-ACPI systems + * Return: 0 on success, -errno on failure. + */ +static int __init fake_numa_init(void) +{ + phys_addr_t start = memblock_start_of_DRAM(); + phys_addr_t end = memblock_end_of_DRAM() - 1; + + node_set(0, numa_nodes_parsed); + pr_info("Faking a node at [mem %pap-%pap]\n", &start, &end); + + return numa_add_memblk(0, start, end + 1); +} + int __init init_numa_memory(void) { int i; @@ -404,7 +419,7 @@ int __init init_numa_memory(void) memset(&numa_meminfo, 0, sizeof(numa_meminfo)); /* Parse SRAT and SLIT if provided by firmware. */ - ret = acpi_numa_init(); + ret = acpi_disabled ? fake_numa_init() : acpi_numa_init(); if (ret < 0) return ret; diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index d61c9f465b95..c583b1ef1f44 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -47,6 +47,12 @@ #include <asm/unwind.h> #include <asm/vdso.h> +#ifdef CONFIG_STACKPROTECTOR +#include <linux/stackprotector.h> +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + /* * Idle related variables and functions */ diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 8c82021eb2f4..1ef8c6383535 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -15,6 +15,7 @@ #include <acpi/reboot.h> #include <asm/idle.h> #include <asm/loongarch.h> +#include <asm/loongson.h> void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); @@ -42,6 +43,10 @@ void machine_power_off(void) preempt_disable(); smp_send_stop(); #endif +#ifdef CONFIG_PM + if (!acpi_disabled) + enable_pci_wakeup(); +#endif do_kernel_power_off(); #ifdef CONFIG_EFI efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index ae436def7ee9..4344502c0b31 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -28,10 +28,16 @@ #include <linux/sizes.h> #include <linux/device.h> #include <linux/dma-map-ops.h> +#include <linux/libfdt.h> +#include <linux/of_fdt.h> +#include <linux/of_address.h> +#include <linux/suspend.h> #include <linux/swiotlb.h> #include <asm/addrspace.h> +#include <asm/alternative.h> #include <asm/bootinfo.h> +#include <asm/bugs.h> #include <asm/cache.h> #include <asm/cpu.h> #include <asm/dma.h> @@ -67,6 +73,7 @@ static const char dmi_empty_string[] = " "; * * These are initialized so they are in the .data section */ +char init_command_line[COMMAND_LINE_SIZE] __initdata; static int num_standard_resources; static struct resource *standard_resources; @@ -80,6 +87,11 @@ const char *get_system_type(void) return "generic-loongson-machine"; } +void __init check_bugs(void) +{ + alternative_instructions(); +} + static const char *dmi_string_parse(const struct dmi_header *dm, u8 s) { const u8 *bp = ((u8 *) dm) + dm->length; @@ -246,6 +258,58 @@ static void __init arch_parse_crashkernel(void) #endif } +static void __init fdt_setup(void) +{ +#ifdef CONFIG_OF_EARLY_FLATTREE + void *fdt_pointer; + + /* ACPI-based systems do not require parsing fdt */ + if (acpi_os_get_root_pointer()) + return; + + /* Look for a device tree configuration table entry */ + fdt_pointer = efi_fdt_pointer(); + if (!fdt_pointer || fdt_check_header(fdt_pointer)) + return; + + early_init_dt_scan(fdt_pointer); + early_init_fdt_reserve_self(); + + max_low_pfn = PFN_PHYS(memblock_end_of_DRAM()); +#endif +} + +static void __init bootcmdline_init(char **cmdline_p) +{ + /* + * If CONFIG_CMDLINE_FORCE is enabled then initializing the command line + * is trivial - we simply use the built-in command line unconditionally & + * unmodified. + */ + if (IS_ENABLED(CONFIG_CMDLINE_FORCE)) { + strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + goto out; + } + +#ifdef CONFIG_OF_FLATTREE + /* + * If CONFIG_CMDLINE_BOOTLOADER is enabled and we are in FDT-based system, + * the boot_command_line will be overwritten by early_init_dt_scan_chosen(). + * So we need to append init_command_line (the original copy of boot_command_line) + * to boot_command_line. + */ + if (initial_boot_params) { + if (boot_command_line[0]) + strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); + + strlcat(boot_command_line, init_command_line, COMMAND_LINE_SIZE); + } +#endif + +out: + *cmdline_p = boot_command_line; +} + void __init platform_init(void) { arch_reserve_vmcore(); @@ -258,6 +322,7 @@ void __init platform_init(void) acpi_gbl_use_default_register_widths = false; acpi_boot_table_init(); #endif + unflatten_and_copy_device_tree(); #ifdef CONFIG_NUMA init_numa_memory(); @@ -290,6 +355,8 @@ static void __init arch_mem_init(char **cmdline_p) check_kernel_sections_mem(); + early_init_fdt_scan_reserved_mem(); + /* * In order to reduce the possibility of kernel panic when failed to * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate @@ -304,6 +371,10 @@ static void __init arch_mem_init(char **cmdline_p) dma_contiguous_reserve(PFN_PHYS(max_low_pfn)); + /* Reserve for hibernation. */ + register_nosave_region(PFN_DOWN(__pa_symbol(&__nosave_begin)), + PFN_UP(__pa_symbol(&__nosave_end))); + memblock_dump_all(); early_memtest(PFN_PHYS(ARCH_PFN_OFFSET), PFN_PHYS(max_low_pfn)); @@ -363,6 +434,81 @@ static void __init resource_init(void) #endif } +static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, + resource_size_t hw_start, resource_size_t size) +{ + int ret = 0; + unsigned long vaddr; + struct logic_pio_hwaddr *range; + + range = kzalloc(sizeof(*range), GFP_ATOMIC); + if (!range) + return -ENOMEM; + + range->fwnode = fwnode; + range->size = size = round_up(size, PAGE_SIZE); + range->hw_start = hw_start; + range->flags = LOGIC_PIO_CPU_MMIO; + + ret = logic_pio_register_range(range); + if (ret) { + kfree(range); + return ret; + } + + /* Legacy ISA must placed at the start of PCI_IOBASE */ + if (range->io_start != 0) { + logic_pio_unregister_range(range); + kfree(range); + return -EINVAL; + } + + vaddr = (unsigned long)(PCI_IOBASE + range->io_start); + ioremap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL)); + + return 0; +} + +static __init int arch_reserve_pio_range(void) +{ + struct device_node *np; + + for_each_node_by_name(np, "isa") { + struct of_range range; + struct of_range_parser parser; + + pr_info("ISA Bridge: %pOF\n", np); + + if (of_range_parser_init(&parser, np)) { + pr_info("Failed to parse resources.\n"); + of_node_put(np); + break; + } + + for_each_of_range(&parser, &range) { + switch (range.flags & IORESOURCE_TYPE_BITS) { + case IORESOURCE_IO: + pr_info(" IO 0x%016llx..0x%016llx -> 0x%016llx\n", + range.cpu_addr, + range.cpu_addr + range.size - 1, + range.bus_addr); + if (add_legacy_isa_io(&np->fwnode, range.cpu_addr, range.size)) + pr_warn("Failed to reserve legacy IO in Logic PIO\n"); + break; + case IORESOURCE_MEM: + pr_info(" MEM 0x%016llx..0x%016llx -> 0x%016llx\n", + range.cpu_addr, + range.cpu_addr + range.size - 1, + range.bus_addr); + break; + } + } + } + + return 0; +} +arch_initcall(arch_reserve_pio_range); + static int __init reserve_memblock_reserved_regions(void) { u64 i, j; @@ -415,12 +561,13 @@ static void __init prefill_possible_map(void) void __init setup_arch(char **cmdline_p) { cpu_probe(); - *cmdline_p = boot_command_line; init_environ(); efi_init(); + fdt_setup(); memblock_init(); pagetable_init(); + bootcmdline_init(cmdline_p); parse_early_param(); reserve_initrd_mem(); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 14508d429ffa..8c6e227cb29d 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -16,6 +16,7 @@ #include <linux/smp.h> #include <linux/threads.h> #include <linux/export.h> +#include <linux/syscore_ops.h> #include <linux/time.h> #include <linux/tracepoint.h> #include <linux/sched/hotplug.h> @@ -180,8 +181,42 @@ irqreturn_t loongson_ipi_interrupt(int irq, void *dev) return IRQ_HANDLED; } +static void __init fdt_smp_setup(void) +{ +#ifdef CONFIG_OF + unsigned int cpu, cpuid; + struct device_node *node = NULL; + + for_each_of_cpu_node(node) { + if (!of_device_is_available(node)) + continue; + + cpuid = of_get_cpu_hwid(node, 0); + if (cpuid >= nr_cpu_ids) + continue; + + if (cpuid == loongson_sysconf.boot_cpu_id) { + cpu = 0; + numa_add_cpu(cpu); + } else { + cpu = cpumask_next_zero(-1, cpu_present_mask); + } + + num_processors++; + set_cpu_possible(cpu, true); + set_cpu_present(cpu, true); + __cpu_number_map[cpuid] = cpu; + __cpu_logical_map[cpu] = cpuid; + } + + loongson_sysconf.nr_cpus = num_processors; +#endif +} + void __init loongson_smp_setup(void) { + fdt_smp_setup(); + cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package; cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package; diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index 202a163cb32f..31dd8199b245 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -23,6 +23,11 @@ SYM_FUNC_START(__switch_to) stptr.d ra, a0, THREAD_REG01 stptr.d a3, a0, THREAD_SCHED_RA stptr.d a4, a0, THREAD_SCHED_CFA +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) + la t7, __stack_chk_guard + LONG_L t8, a1, TASK_STACK_CANARY + LONG_S t8, t7, 0 +#endif move tp, a2 cpu_restore_nonscratch a1 diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 786735dcc8d6..a6576dea590c 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -115,12 +115,17 @@ static unsigned long __init get_loops_per_jiffy(void) return lpj; } -static long init_timeval; +static long init_offset __nosavedata; + +void save_counter(void) +{ + init_offset = drdtime(); +} void sync_counter(void) { /* Ensure counter begin at 0 */ - csr_write64(-init_timeval, LOONGARCH_CSR_CNTC); + csr_write64(init_offset, LOONGARCH_CSR_CNTC); } static int get_timer_irq(void) @@ -219,7 +224,7 @@ void __init time_init(void) else const_clock_freq = calc_const_freq(); - init_timeval = drdtime() - csr_read64(LOONGARCH_CSR_CNTC); + init_offset = -(drdtime() - csr_read64(LOONGARCH_CSR_CNTC)); constant_clockevent_init(); constant_clocksource_init(); diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 1a4dce84ebc6..7ea62faeeadb 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -368,13 +368,40 @@ asmlinkage void noinstr do_ade(struct pt_regs *regs) irqentry_exit(regs, state); } +/* sysctl hooks */ +int unaligned_enabled __read_mostly = 1; /* Enabled by default */ +int no_unaligned_warning __read_mostly = 1; /* Only 1 warning by default */ + asmlinkage void noinstr do_ale(struct pt_regs *regs) { + unsigned int *pc; irqentry_state_t state = irqentry_enter(regs); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr); + + /* + * Did we catch a fault trying to load an instruction? + */ + if (regs->csr_badvaddr == regs->csr_era) + goto sigbus; + if (user_mode(regs) && !test_thread_flag(TIF_FIXADE)) + goto sigbus; + if (!unaligned_enabled) + goto sigbus; + if (!no_unaligned_warning) + show_registers(regs); + + pc = (unsigned int *)exception_era(regs); + + emulate_load_store_insn(regs, (void __user *)regs->csr_badvaddr, pc); + + goto out; + +sigbus: die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); +out: irqentry_exit(regs, state); } diff --git a/arch/loongarch/kernel/unaligned.c b/arch/loongarch/kernel/unaligned.c new file mode 100644 index 000000000000..bdff825d29ef --- /dev/null +++ b/arch/loongarch/kernel/unaligned.c @@ -0,0 +1,499 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handle unaligned accesses by emulation. + * + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + * + * Derived from MIPS: + * Copyright (C) 1996, 1998, 1999, 2002 by Ralf Baechle + * Copyright (C) 1999 Silicon Graphics, Inc. + * Copyright (C) 2014 Imagination Technologies Ltd. + */ +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/signal.h> +#include <linux/debugfs.h> +#include <linux/perf_event.h> + +#include <asm/asm.h> +#include <asm/branch.h> +#include <asm/fpu.h> +#include <asm/inst.h> + +#include "access-helper.h" + +#ifdef CONFIG_DEBUG_FS +static u32 unaligned_instructions_user; +static u32 unaligned_instructions_kernel; +#endif + +static inline unsigned long read_fpr(unsigned int idx) +{ +#define READ_FPR(idx, __value) \ + __asm__ __volatile__("movfr2gr.d %0, $f"#idx"\n\t" : "=r"(__value)); + + unsigned long __value; + + switch (idx) { + case 0: + READ_FPR(0, __value); + break; + case 1: + READ_FPR(1, __value); + break; + case 2: + READ_FPR(2, __value); + break; + case 3: + READ_FPR(3, __value); + break; + case 4: + READ_FPR(4, __value); + break; + case 5: + READ_FPR(5, __value); + break; + case 6: + READ_FPR(6, __value); + break; + case 7: + READ_FPR(7, __value); + break; + case 8: + READ_FPR(8, __value); + break; + case 9: + READ_FPR(9, __value); + break; + case 10: + READ_FPR(10, __value); + break; + case 11: + READ_FPR(11, __value); + break; + case 12: + READ_FPR(12, __value); + break; + case 13: + READ_FPR(13, __value); + break; + case 14: + READ_FPR(14, __value); + break; + case 15: + READ_FPR(15, __value); + break; + case 16: + READ_FPR(16, __value); + break; + case 17: + READ_FPR(17, __value); + break; + case 18: + READ_FPR(18, __value); + break; + case 19: + READ_FPR(19, __value); + break; + case 20: + READ_FPR(20, __value); + break; + case 21: + READ_FPR(21, __value); + break; + case 22: + READ_FPR(22, __value); + break; + case 23: + READ_FPR(23, __value); + break; + case 24: + READ_FPR(24, __value); + break; + case 25: + READ_FPR(25, __value); + break; + case 26: + READ_FPR(26, __value); + break; + case 27: + READ_FPR(27, __value); + break; + case 28: + READ_FPR(28, __value); + break; + case 29: + READ_FPR(29, __value); + break; + case 30: + READ_FPR(30, __value); + break; + case 31: + READ_FPR(31, __value); + break; + default: + panic("unexpected idx '%d'", idx); + } +#undef READ_FPR + return __value; +} + +static inline void write_fpr(unsigned int idx, unsigned long value) +{ +#define WRITE_FPR(idx, value) \ + __asm__ __volatile__("movgr2fr.d $f"#idx", %0\n\t" :: "r"(value)); + + switch (idx) { + case 0: + WRITE_FPR(0, value); + break; + case 1: + WRITE_FPR(1, value); + break; + case 2: + WRITE_FPR(2, value); + break; + case 3: + WRITE_FPR(3, value); + break; + case 4: + WRITE_FPR(4, value); + break; + case 5: + WRITE_FPR(5, value); + break; + case 6: + WRITE_FPR(6, value); + break; + case 7: + WRITE_FPR(7, value); + break; + case 8: + WRITE_FPR(8, value); + break; + case 9: + WRITE_FPR(9, value); + break; + case 10: + WRITE_FPR(10, value); + break; + case 11: + WRITE_FPR(11, value); + break; + case 12: + WRITE_FPR(12, value); + break; + case 13: + WRITE_FPR(13, value); + break; + case 14: + WRITE_FPR(14, value); + break; + case 15: + WRITE_FPR(15, value); + break; + case 16: + WRITE_FPR(16, value); + break; + case 17: + WRITE_FPR(17, value); + break; + case 18: + WRITE_FPR(18, value); + break; + case 19: + WRITE_FPR(19, value); + break; + case 20: + WRITE_FPR(20, value); + break; + case 21: + WRITE_FPR(21, value); + break; + case 22: + WRITE_FPR(22, value); + break; + case 23: + WRITE_FPR(23, value); + break; + case 24: + WRITE_FPR(24, value); + break; + case 25: + WRITE_FPR(25, value); + break; + case 26: + WRITE_FPR(26, value); + break; + case 27: + WRITE_FPR(27, value); + break; + case 28: + WRITE_FPR(28, value); + break; + case 29: + WRITE_FPR(29, value); + break; + case 30: + WRITE_FPR(30, value); + break; + case 31: + WRITE_FPR(31, value); + break; + default: + panic("unexpected idx '%d'", idx); + } +#undef WRITE_FPR +} + +void emulate_load_store_insn(struct pt_regs *regs, void __user *addr, unsigned int *pc) +{ + bool fp = false; + bool sign, write; + bool user = user_mode(regs); + unsigned int res, size = 0; + unsigned long value = 0; + union loongarch_instruction insn; + + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); + + __get_inst(&insn.word, pc, user); + + switch (insn.reg2i12_format.opcode) { + case ldh_op: + size = 2; + sign = true; + write = false; + break; + case ldhu_op: + size = 2; + sign = false; + write = false; + break; + case sth_op: + size = 2; + sign = true; + write = true; + break; + case ldw_op: + size = 4; + sign = true; + write = false; + break; + case ldwu_op: + size = 4; + sign = false; + write = false; + break; + case stw_op: + size = 4; + sign = true; + write = true; + break; + case ldd_op: + size = 8; + sign = true; + write = false; + break; + case std_op: + size = 8; + sign = true; + write = true; + break; + case flds_op: + size = 4; + fp = true; + sign = true; + write = false; + break; + case fsts_op: + size = 4; + fp = true; + sign = true; + write = true; + break; + case fldd_op: + size = 8; + fp = true; + sign = true; + write = false; + break; + case fstd_op: + size = 8; + fp = true; + sign = true; + write = true; + break; + } + + switch (insn.reg2i14_format.opcode) { + case ldptrw_op: + size = 4; + sign = true; + write = false; + break; + case stptrw_op: + size = 4; + sign = true; + write = true; + break; + case ldptrd_op: + size = 8; + sign = true; + write = false; + break; + case stptrd_op: + size = 8; + sign = true; + write = true; + break; + } + + switch (insn.reg3_format.opcode) { + case ldxh_op: + size = 2; + sign = true; + write = false; + break; + case ldxhu_op: + size = 2; + sign = false; + write = false; + break; + case stxh_op: + size = 2; + sign = true; + write = true; + break; + case ldxw_op: + size = 4; + sign = true; + write = false; + break; + case ldxwu_op: + size = 4; + sign = false; + write = false; + break; + case stxw_op: + size = 4; + sign = true; + write = true; + break; + case ldxd_op: + size = 8; + sign = true; + write = false; + break; + case stxd_op: + size = 8; + sign = true; + write = true; + break; + case fldxs_op: + size = 4; + fp = true; + sign = true; + write = false; + break; + case fstxs_op: + size = 4; + fp = true; + sign = true; + write = true; + break; + case fldxd_op: + size = 8; + fp = true; + sign = true; + write = false; + break; + case fstxd_op: + size = 8; + fp = true; + sign = true; + write = true; + break; + } + + if (!size) + goto sigbus; + if (user && !access_ok(addr, size)) + goto sigbus; + + if (!write) { + res = unaligned_read(addr, &value, size, sign); + if (res) + goto fault; + + /* Rd is the same field in any formats */ + if (!fp) + regs->regs[insn.reg3_format.rd] = value; + else { + if (is_fpu_owner()) + write_fpr(insn.reg3_format.rd, value); + else + set_fpr64(¤t->thread.fpu.fpr[insn.reg3_format.rd], 0, value); + } + } else { + /* Rd is the same field in any formats */ + if (!fp) + value = regs->regs[insn.reg3_format.rd]; + else { + if (is_fpu_owner()) + value = read_fpr(insn.reg3_format.rd); + else + value = get_fpr64(¤t->thread.fpu.fpr[insn.reg3_format.rd], 0); + } + + res = unaligned_write(addr, value, size); + if (res) + goto fault; + } + +#ifdef CONFIG_DEBUG_FS + if (user) + unaligned_instructions_user++; + else + unaligned_instructions_kernel++; +#endif + + compute_return_era(regs); + + return; + +fault: + /* Did we have an exception handler installed? */ + if (fixup_exception(regs)) + return; + + die_if_kernel("Unhandled kernel unaligned access", regs); + force_sig(SIGSEGV); + + return; + +sigbus: + die_if_kernel("Unhandled kernel unaligned access", regs); + force_sig(SIGBUS); + + return; +} + +#ifdef CONFIG_DEBUG_FS +static int __init debugfs_unaligned(void) +{ + struct dentry *d; + + d = debugfs_create_dir("loongarch", NULL); + if (!d) + return -ENOMEM; + + debugfs_create_u32("unaligned_instructions_user", + S_IRUGO, d, &unaligned_instructions_user); + debugfs_create_u32("unaligned_instructions_kernel", + S_IRUGO, d, &unaligned_instructions_kernel); + + return 0; +} +arch_initcall(debugfs_unaligned); +#endif diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c index 5afa6064d73e..e2d2e4f3001f 100644 --- a/arch/loongarch/kernel/unwind_guess.c +++ b/arch/loongarch/kernel/unwind_guess.c @@ -3,6 +3,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ #include <linux/kernel.h> +#include <linux/ftrace.h> #include <asm/unwind.h> @@ -53,7 +54,8 @@ bool unwind_next_frame(struct unwind_state *state) state->sp < info->end; state->sp += sizeof(unsigned long)) { addr = *(unsigned long *)(state->sp); - + state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, + addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); if (__kernel_text_address(addr)) return true; } diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 4571c3c87cd4..0f8d1451ebb8 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -2,12 +2,23 @@ /* * Copyright (C) 2022 Loongson Technology Corporation Limited */ +#include <linux/ftrace.h> #include <linux/kallsyms.h> #include <asm/inst.h> #include <asm/ptrace.h> #include <asm/unwind.h> +static inline void unwind_state_fixup(struct unwind_state *state) +{ +#ifdef CONFIG_DYNAMIC_FTRACE + static unsigned long ftrace = (unsigned long)ftrace_call + 4; + + if (state->pc == ftrace) + state->is_ftrace = true; +#endif +} + unsigned long unwind_get_return_address(struct unwind_state *state) { @@ -32,6 +43,8 @@ static bool unwind_by_guess(struct unwind_state *state) state->sp < info->end; state->sp += sizeof(unsigned long)) { addr = *(unsigned long *)(state->sp); + state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, + addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); if (__kernel_text_address(addr)) return true; } @@ -41,15 +54,30 @@ static bool unwind_by_guess(struct unwind_state *state) static bool unwind_by_prologue(struct unwind_state *state) { - struct stack_info *info = &state->stack_info; - union loongarch_instruction *ip, *ip_end; long frame_ra = -1; unsigned long frame_size = 0; unsigned long size, offset, pc = state->pc; + struct pt_regs *regs; + struct stack_info *info = &state->stack_info; + union loongarch_instruction *ip, *ip_end; if (state->sp >= info->end || state->sp < info->begin) return false; + if (state->is_ftrace) { + /* + * As we meet ftrace_regs_entry, reset first flag like first doing + * tracing. Prologue analysis will stop soon because PC is at entry. + */ + regs = (struct pt_regs *)state->sp; + state->first = true; + state->is_ftrace = false; + state->pc = regs->csr_era; + state->ra = regs->regs[1]; + state->sp = regs->regs[3]; + return true; + } + if (!kallsyms_lookup_size_offset(pc, &size, &offset)) return false; @@ -95,7 +123,7 @@ static bool unwind_by_prologue(struct unwind_state *state) state->pc = *(unsigned long *)(state->sp + frame_ra); state->sp = state->sp + frame_size; - return !!__kernel_text_address(state->pc); + goto out; first: state->first = false; @@ -104,7 +132,9 @@ first: state->pc = state->ra; - return !!__kernel_text_address(state->ra); +out: + unwind_state_fixup(state); + return !!__kernel_text_address(state->pc); } void unwind_start(struct unwind_state *state, struct task_struct *task, @@ -147,8 +177,11 @@ bool unwind_next_frame(struct unwind_state *state) break; case UNWINDER_PROLOGUE: - if (unwind_by_prologue(state)) + if (unwind_by_prologue(state)) { + state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, + state->pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); return true; + } if (info->type == STACK_TYPE_IRQ && info->end == state->sp) { @@ -158,10 +191,11 @@ bool unwind_next_frame(struct unwind_state *state) if (user_mode(regs) || !__kernel_text_address(pc)) return false; - state->pc = pc; - state->sp = regs->regs[3]; - state->ra = regs->regs[1]; state->first = true; + state->ra = regs->regs[1]; + state->sp = regs->regs[3]; + state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, + pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); get_stack_info(state->sp, state->task, info); return true; diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index b3309a5e695b..733b16e8d55d 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -4,6 +4,7 @@ #include <asm/thread_info.h> #define PAGE_SIZE _PAGE_SIZE +#define RO_EXCEPTION_TABLE_ALIGN 4 /* * Put .bss..swapper_pg_dir as the first thing in .bss. This will @@ -53,7 +54,17 @@ SECTIONS . = ALIGN(PECOFF_SEGMENT_ALIGN); _etext = .; - EXCEPTION_TABLE(16) + /* + * struct alt_inst entries. From the header (alternative.h): + * "Alternative instructions for different CPU types or capabilities" + * Think locking instructions on spinlocks. + */ + . = ALIGN(4); + .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { + __alt_instructions = .; + *(.altinstructions) + __alt_instructions_end = .; + } .got : ALIGN(16) { *(.got) } .plt : ALIGN(16) { *(.plt) } |