diff options
Diffstat (limited to 'arch/arc/kernel')
38 files changed, 1798 insertions, 1392 deletions
diff --git a/arch/arc/kernel/.gitignore b/arch/arc/kernel/.gitignore index c5f676c3c224..bbb90f92d051 100644 --- a/arch/arc/kernel/.gitignore +++ b/arch/arc/kernel/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only vmlinux.lds diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile index 2dc5f4296d44..fa94fff02419 100644 --- a/arch/arc/kernel/Makefile +++ b/arch/arc/kernel/Makefile @@ -1,15 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2 as -# published by the Free Software Foundation. -# Pass UTS_MACHINE for user_regset definition -CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' - -obj-y := arcksyms.o setup.o irq.o reset.o ptrace.o process.o devtree.o +obj-y := head.o arcksyms.o setup.o irq.o reset.o ptrace.o process.o devtree.o obj-y += signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o +obj-y += ctx_sw_asm.o + obj-$(CONFIG_ISA_ARCOMPACT) += entry-compact.o intc-compact.o obj-$(CONFIG_ISA_ARCV2) += entry-arcv2.o intc-arcv2.o @@ -22,15 +19,11 @@ obj-$(CONFIG_ARC_EMUL_UNALIGNED) += unaligned.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_ARC_METAWARE_HLINK) += arc_hostlink.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_ARC_FPU_SAVE_RESTORE) += fpu.o +ifdef CONFIG_ISA_ARCOMPACT CFLAGS_fpu.o += -mdpfp - -ifdef CONFIG_ARC_DW2_UNWIND -CFLAGS_ctx_sw.o += -fno-omit-frame-pointer -obj-y += ctx_sw.o -else -obj-y += ctx_sw_asm.o endif -extra-y := vmlinux.lds head.o +always-$(KBUILD_BUILTIN) := vmlinux.lds diff --git a/arch/arc/kernel/Makefile.syscalls b/arch/arc/kernel/Makefile.syscalls new file mode 100644 index 000000000000..391d30ab7a83 --- /dev/null +++ b/arch/arc/kernel/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += arc time32 renameat stat64 rlimit diff --git a/arch/arc/kernel/arc_hostlink.c b/arch/arc/kernel/arc_hostlink.c index 47b2a17cc52a..08c5196efe0a 100644 --- a/arch/arc/kernel/arc_hostlink.c +++ b/arch/arc/kernel/arc_hostlink.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * arc_hostlink.c: Pseudo-driver for Metaware provided "hostlink" facility * * Allows Linux userland access to host in absence of any peripherals. * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> /* file_operations */ diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c index 000dd041ab42..8851c0a19e09 100644 --- a/arch/arc/kernel/arcksyms.c +++ b/arch/arc/kernel/arcksyms.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * arcksyms.c - Exporting symbols not exportable from their own sources * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * */ #include <linux/module.h> diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c index ecaf34e9235c..2978da85fcb6 100644 --- a/arch/arc/kernel/asm-offsets.c +++ b/arch/arc/kernel/asm-offsets.c @@ -1,10 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ +#define COMPILE_OFFSETS #include <linux/sched.h> #include <linux/mm.h> @@ -15,6 +13,7 @@ #include <asm/hardirq.h> #include <asm/page.h> + int main(void) { DEFINE(TASK_THREAD, offsetof(struct task_struct, thread)); @@ -22,13 +21,13 @@ int main(void) BLANK(); - DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp)); DEFINE(THREAD_CALLEE_REG, offsetof(struct thread_struct, callee_reg)); DEFINE(THREAD_FAULT_ADDR, offsetof(struct thread_struct, fault_address)); BLANK(); + DEFINE(THREAD_INFO_KSP, offsetof(struct thread_info, ksp)); DEFINE(THREAD_INFO_FLAGS, offsetof(struct thread_info, flags)); DEFINE(THREAD_INFO_PREEMPT_COUNT, offsetof(struct thread_info, preempt_count)); @@ -48,7 +47,8 @@ int main(void) BLANK(); DEFINE(PT_status32, offsetof(struct pt_regs, status32)); - DEFINE(PT_event, offsetof(struct pt_regs, event)); + DEFINE(PT_event, offsetof(struct pt_regs, ecr)); + DEFINE(PT_bta, offsetof(struct pt_regs, bta)); DEFINE(PT_sp, offsetof(struct pt_regs, sp)); DEFINE(PT_r0, offsetof(struct pt_regs, r0)); DEFINE(PT_r1, offsetof(struct pt_regs, r1)); @@ -58,11 +58,28 @@ int main(void) DEFINE(PT_r5, offsetof(struct pt_regs, r5)); DEFINE(PT_r6, offsetof(struct pt_regs, r6)); DEFINE(PT_r7, offsetof(struct pt_regs, r7)); + DEFINE(PT_r8, offsetof(struct pt_regs, r8)); + DEFINE(PT_r10, offsetof(struct pt_regs, r10)); + DEFINE(PT_r26, offsetof(struct pt_regs, r26)); DEFINE(PT_ret, offsetof(struct pt_regs, ret)); + DEFINE(PT_blink, offsetof(struct pt_regs, blink)); + OFFSET(PT_fp, pt_regs, fp); + DEFINE(PT_lpe, offsetof(struct pt_regs, lp_end)); + DEFINE(PT_lpc, offsetof(struct pt_regs, lp_count)); +#ifdef CONFIG_ISA_ARCV2 + OFFSET(PT_r12, pt_regs, r12); + OFFSET(PT_r30, pt_regs, r30); +#endif +#ifdef CONFIG_ARC_HAS_ACCL_REGS + OFFSET(PT_r58, pt_regs, r58); + OFFSET(PT_r59, pt_regs, r59); +#endif +#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS + OFFSET(PT_DSP_CTRL, pt_regs, DSP_CTRL); +#endif DEFINE(SZ_CALLEE_REGS, sizeof(struct callee_regs)); DEFINE(SZ_PT_REGS, sizeof(struct pt_regs)); - DEFINE(PT_user_r25, offsetof(struct pt_regs, user_r25)); return 0; } diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c deleted file mode 100644 index 9e1ae9d41925..000000000000 --- a/arch/arc/kernel/ctx_sw.c +++ /dev/null @@ -1,128 +0,0 @@ -/* - * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Vineetg: Aug 2009 - * -"C" version of lowest level context switch asm macro called by schedular - * gcc doesn't generate the dward CFI info for hand written asm, hence can't - * backtrace out of it (e.g. tasks sleeping in kernel). - * So we cheat a bit by writing almost similar code in inline-asm. - * -This is a hacky way of doing things, but there is no other simple way. - * I don't want/intend to extend unwinding code to understand raw asm - */ - -#include <asm/asm-offsets.h> -#include <linux/sched.h> -#include <linux/sched/debug.h> -#ifdef CONFIG_ARC_PLAT_EZNPS -#include <plat/ctop.h> -#endif - -#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) - -struct task_struct *__sched -__switch_to(struct task_struct *prev_task, struct task_struct *next_task) -{ - unsigned int tmp; - unsigned int prev = (unsigned int)prev_task; - unsigned int next = (unsigned int)next_task; - - __asm__ __volatile__( - /* FP/BLINK save generated by gcc (standard function prologue */ - "st.a r13, [sp, -4] \n\t" - "st.a r14, [sp, -4] \n\t" - "st.a r15, [sp, -4] \n\t" - "st.a r16, [sp, -4] \n\t" - "st.a r17, [sp, -4] \n\t" - "st.a r18, [sp, -4] \n\t" - "st.a r19, [sp, -4] \n\t" - "st.a r20, [sp, -4] \n\t" - "st.a r21, [sp, -4] \n\t" - "st.a r22, [sp, -4] \n\t" - "st.a r23, [sp, -4] \n\t" - "st.a r24, [sp, -4] \n\t" -#ifndef CONFIG_ARC_CURR_IN_REG - "st.a r25, [sp, -4] \n\t" -#else - "sub sp, sp, 4 \n\t" /* usual r25 placeholder */ -#endif - - /* set ksp of outgoing task in tsk->thread.ksp */ -#if KSP_WORD_OFF <= 255 - "st.as sp, [%3, %1] \n\t" -#else - /* - * Workaround for NR_CPUS=4k - * %1 is bigger than 255 (S9 offset for st.as) - */ - "add2 r24, %3, %1 \n\t" - "st sp, [r24] \n\t" -#endif - - /* - * setup _current_task with incoming tsk. - * optionally, set r25 to that as well - * For SMP extra work to get to &_current_task[cpu] - * (open coded SET_CURR_TASK_ON_CPU) - */ -#ifndef CONFIG_SMP - "st %2, [@_current_task] \n\t" -#else -#ifdef CONFIG_ARC_PLAT_EZNPS - "lr r24, [%4] \n\t" -#ifndef CONFIG_EZNPS_MTM_EXT - "lsr r24, r24, 4 \n\t" -#endif -#else - "lr r24, [identity] \n\t" - "lsr r24, r24, 8 \n\t" - "bmsk r24, r24, 7 \n\t" -#endif - "add2 r24, @_current_task, r24 \n\t" - "st %2, [r24] \n\t" -#endif -#ifdef CONFIG_ARC_CURR_IN_REG - "mov r25, %2 \n\t" -#endif - - /* get ksp of incoming task from tsk->thread.ksp */ - "ld.as sp, [%2, %1] \n\t" - - /* start loading it's CALLEE reg file */ - -#ifndef CONFIG_ARC_CURR_IN_REG - "ld.ab r25, [sp, 4] \n\t" -#else - "add sp, sp, 4 \n\t" -#endif - "ld.ab r24, [sp, 4] \n\t" - "ld.ab r23, [sp, 4] \n\t" - "ld.ab r22, [sp, 4] \n\t" - "ld.ab r21, [sp, 4] \n\t" - "ld.ab r20, [sp, 4] \n\t" - "ld.ab r19, [sp, 4] \n\t" - "ld.ab r18, [sp, 4] \n\t" - "ld.ab r17, [sp, 4] \n\t" - "ld.ab r16, [sp, 4] \n\t" - "ld.ab r15, [sp, 4] \n\t" - "ld.ab r14, [sp, 4] \n\t" - "ld.ab r13, [sp, 4] \n\t" - - /* last (ret value) = prev : although for ARC it mov r0, r0 */ - "mov %0, %3 \n\t" - - /* FP/BLINK restore generated by gcc (standard func epilogue */ - - : "=r"(tmp) - : "n"(KSP_WORD_OFF), "r"(next), "r"(prev) -#ifdef CONFIG_ARC_PLAT_EZNPS - , "i"(CTOP_AUX_LOGIC_GLOBAL_ID) -#endif - : "blink" - ); - - return (struct task_struct *)tmp; -} diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index 7c1f365ef3d2..48e1f21976ed 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Vineetg: Aug 2009 * -Moved core context switch macro out of entry.S into this file. * -This is the more "natural" hand written assembler @@ -14,50 +11,54 @@ #include <asm/entry.h> /* For the SAVE_* macros */ #include <asm/asm-offsets.h> -#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) - -;################### Low Level Context Switch ########################## +; IN +; - r0: prev task (also current) +; - r1: next task +; OUT +; - r0: prev task (so r0 not touched) .section .sched.text,"ax",@progbits - .align 4 - .global __switch_to - .type __switch_to, @function -__switch_to: - CFI_STARTPROC - - /* Save regs on kernel mode stack of task */ - st.a blink, [sp, -4] - st.a fp, [sp, -4] - SAVE_CALLEE_SAVED_KERNEL +ENTRY_CFI(__switch_to) - /* Save the now KSP in task->thread.ksp */ -#if KSP_WORD_OFF <= 255 - st.as sp, [r0, KSP_WORD_OFF] -#else - /* Workaround for NR_CPUS=4k as ST.as can only take s9 offset */ - add2 r24, r0, KSP_WORD_OFF - st sp, [r24] -#endif - /* - * Return last task in r0 (return reg) - * On ARC, Return reg = First Arg reg = r0. - * Since we already have last task in r0, - * don't need to do anything special to return it - */ + /* save kernel stack frame regs of @prev task */ + push blink + CFI_DEF_CFA_OFFSET 4 + CFI_OFFSET r31, -4 + + push fp + CFI_DEF_CFA_OFFSET 8 + CFI_OFFSET r27, -8 + + mov fp, sp + CFI_DEF_CFA_REGISTER r27 + + /* kernel mode callee regs of @prev */ + SAVE_CALLEE_SAVED_KERNEL /* - * switch to new task, contained in r1 - * Temp reg r3 is required to get the ptr to store val + * save final SP to @prev->thread_info.ksp + * @prev is "current" so thread_info derived from SP */ - SET_CURR_TASK_ON_CPU r1, r3 + GET_CURR_THR_INFO_FROM_SP r10 + st sp, [r10, THREAD_INFO_KSP] + + /* update @next in _current_task[] and GP register caching it */ + SET_CURR_TASK_ON_CPU r1, r10 - /* reload SP with kernel mode stack pointer in task->thread.ksp */ - ld.as sp, [r1, (TASK_THREAD + THREAD_KSP)/4] + /* load SP from @next->thread_info.ksp */ + ld r10, [r1, TASK_THREAD_INFO] + ld sp, [r10, THREAD_INFO_KSP] - /* restore the registers */ + /* restore callee regs, stack frame regs of @next */ RESTORE_CALLEE_SAVED_KERNEL - ld.ab fp, [sp, 4] - ld.ab blink, [sp, 4] - j [blink] + pop fp + CFI_RESTORE r27 + CFI_DEF_CFA r28, 4 + + pop blink + CFI_RESTORE r31 + CFI_DEF_CFA_OFFSET 0 + + j [blink] END_CFI(__switch_to) diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c index 521ef3521a1c..cc6ac7d128aa 100644 --- a/arch/arc/kernel/devtree.c +++ b/arch/arc/kernel/devtree.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com) * * Based on reduced version of METAG - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ @@ -15,6 +12,7 @@ #include <linux/of.h> #include <linux/of_fdt.h> #include <asm/mach_desc.h> +#include <asm/serial.h> #ifdef CONFIG_SERIAL_EARLYCON @@ -32,8 +30,6 @@ static void __init arc_set_early_base_baud(unsigned long dt_root) else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp") || of_flat_dt_is_compatible(dt_root, "snps,hsdk")) arc_base_baud = 33333333; /* Fixed 33MHz clk (AXS10x & HSDK) */ - else if (of_flat_dt_is_compatible(dt_root, "ezchip,arc-nps")) - arc_base_baud = 800000000; /* Fixed 800MHz clk (NPS) */ else arc_base_baud = 50000000; /* Fixed default 50MHz */ } @@ -66,7 +62,7 @@ const struct machine_desc * __init setup_machine_fdt(void *dt) const struct machine_desc *mdesc; unsigned long dt_root; - if (!early_init_dt_scan(dt)) + if (!early_init_dt_scan(dt, __pa(dt))) return NULL; mdesc = of_flat_dt_match_machine(NULL, arch_get_next_mach); diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index 3b7cd4864ba2..ccc7e8c39eb3 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * several functions that help interpret ARC instructions * used for unaligned accesses, kprobes and kgdb * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/types.h> @@ -342,7 +339,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_LDWX_S: /* LDWX_S c, [b, u6] */ state->x = 1; - /* intentional fall-through */ + fallthrough; case op_LDW_S: /* LDW_S c, [b, u6] */ state->zz = 2; @@ -369,7 +366,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_SP: /* LD_S|LDB_S b,[sp,u7], ST_S|STB_S b,[sp,u7] */ /* note: we are ignoring possibility of: * ADD_S, SUB_S, PUSH_S, POP_S as these should not - * cause unaliged exception anyway */ + * cause unaligned exception anyway */ state->write = BITS(state->words[0], 6, 6); state->zz = BITS(state->words[0], 5, 5); if (state->zz) @@ -437,14 +434,31 @@ long __kprobes get_reg(int reg, struct pt_regs *regs, { long *p; +#if defined(CONFIG_ISA_ARCOMPACT) if (reg <= 12) { p = ®s->r0; return p[-reg]; } +#else /* CONFIG_ISA_ARCV2 */ + if (reg <= 11) { + p = ®s->r0; + return p[reg]; + } + if (reg == 12) + return regs->r12; + if (reg == 30) + return regs->r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + if (reg == 58) + return regs->r58; + if (reg == 59) + return regs->r59; +#endif +#endif if (cregs && (reg <= 25)) { p = &cregs->r13; - return p[13-reg]; + return p[13 - reg]; } if (reg == 26) @@ -464,6 +478,7 @@ void __kprobes set_reg(int reg, long val, struct pt_regs *regs, { long *p; +#if defined(CONFIG_ISA_ARCOMPACT) switch (reg) { case 0 ... 12: p = ®s->r0; @@ -472,7 +487,37 @@ void __kprobes set_reg(int reg, long val, struct pt_regs *regs, case 13 ... 25: if (cregs) { p = &cregs->r13; - p[13-reg] = val; + p[13 - reg] = val; + } + break; + case 26: + regs->r26 = val; + break; + case 27: + regs->fp = val; + break; + case 28: + regs->sp = val; + break; + case 31: + regs->blink = val; + break; + default: + break; + } +#else /* CONFIG_ISA_ARCV2 */ + switch (reg) { + case 0 ... 11: + p = ®s->r0; + p[reg] = val; + break; + case 12: + regs->r12 = val; + break; + case 13 ... 25: + if (cregs) { + p = &cregs->r13; + p[13 - reg] = val; } break; case 26: @@ -484,12 +529,24 @@ void __kprobes set_reg(int reg, long val, struct pt_regs *regs, case 28: regs->sp = val; break; + case 30: + regs->r30 = val; + break; case 31: regs->blink = val; break; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + case 58: + regs->r58 = val; + break; + case 59: + regs->r59 = val; + break; +#endif default: break; } +#endif } /* @@ -506,7 +563,6 @@ int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs, { struct disasm_state instr; - memset(&instr, 0, sizeof(struct disasm_state)); disasm_instr(pc, &instr, 0, regs, cregs); *next_pc = pc + instr.instr_len; diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index cc558a25b8fa..e238b5fd3c8c 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -1,18 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * ARCv2 ISA based core Low Level Intr/Traps/Exceptions(non-TLB) Handling * * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ -#include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */ +#include <linux/linkage.h> /* ARC_{ENTRY,EXIT} */ #include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,TRAP...} */ #include <asm/errno.h> #include <asm/arcregs.h> #include <asm/irqflags.h> +#include <asm/mmu.h> ; A maximum number of supported interrupts in the core interrupt controller. ; This number is not equal to the maximum interrupt number (256) because @@ -33,7 +31,7 @@ VECTOR res_service ; Reset Vector VECTOR mem_service ; Mem exception VECTOR instr_service ; Instrn Error VECTOR EV_MachineCheck ; Fatal Machine check -VECTOR EV_TLBMissI ; Intruction TLB miss +VECTOR EV_TLBMissI ; Instruction TLB miss VECTOR EV_TLBMissD ; Data TLB miss VECTOR EV_TLBProtV ; Protection Violation VECTOR EV_PrivilegeV ; Privilege Violation @@ -70,7 +68,7 @@ reserved: ENTRY(handle_interrupt) - INTERRUPT_PROLOGUE irq + INTERRUPT_PROLOGUE # irq control APIs local_irq_save/restore/disable/enable fiddle with # global interrupt enable bits in STATUS32 (.IE for 1 prio, .E[] for 2 prio) @@ -78,11 +76,11 @@ ENTRY(handle_interrupt) # query in hard ISR path would return false (since .IE is set) which would # trips genirq interrupt handling asserts. # - # So do a "soft" disable of interrutps here. + # So do a "soft" disable of interrupts here. # # Note this disable is only for consistent book-keeping as further interrupts # will be disabled anyways even w/o this. Hardware tracks active interrupts - # seperately in AUX_IRQ_ACTIVE.active and will not take new interrupts + # separately in AUX_IRQ_ACT.active and will not take new interrupts # unless this one returns (or higher prio becomes pending in 2-prio scheme) IRQ_DISABLE @@ -127,11 +125,6 @@ ENTRY(mem_service) EXCEPTION_PROLOGUE - lr r0, [efa] - mov r1, sp - - FAKE_RET_FROM_EXCPN - bl do_memory_error b ret_from_exception END(mem_service) @@ -140,11 +133,6 @@ ENTRY(EV_Misaligned) EXCEPTION_PROLOGUE - lr r0, [efa] ; Faulting Data address - mov r1, sp - - FAKE_RET_FROM_EXCPN - SAVE_CALLEE_SAVED_USER mov r2, sp ; callee_regs @@ -165,11 +153,6 @@ ENTRY(EV_TLBProtV) EXCEPTION_PROLOGUE - lr r0, [efa] ; Faulting Data address - mov r1, sp ; pt_regs - - FAKE_RET_FROM_EXCPN - mov blink, ret_from_exception b do_page_fault @@ -203,15 +186,18 @@ restore_regs: ld r0, [sp, PT_status32] ; U/K mode at time of entry lr r10, [AUX_IRQ_ACT] - bmsk r11, r10, 15 ; AUX_IRQ_ACT.ACTIVE + bmsk r11, r10, 15 ; extract AUX_IRQ_ACT.active breq r11, 0, .Lexcept_ret ; No intr active, ret from Exception ;####### Return from Intr ####### +.Lisr_ret: + debug_marker_l1: - bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot + ; bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot + btst r0, STATUS_DE_BIT ; Z flag set if bit clear + bnz .Lintr_ret_to_delay_slot ; branch if STATUS_DE_BIT set -.Lisr_ret_fast_path: ; Handle special case #1: (Entry via Exception, Return via IRQ) ; ; Exception in U mode, preempted in kernel, Intr taken (K mode), orig @@ -224,7 +210,7 @@ debug_marker_l1: bset.nz r11, r11, AUX_IRQ_ACT_BIT_U ; NZ means U sr r11, [AUX_IRQ_ACT] - INTERRUPT_EPILOGUE irq + INTERRUPT_EPILOGUE rtie ;####### Return from Exception / pure kernel mode ####### @@ -245,8 +231,8 @@ debug_marker_syscall: ; ; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround ; -; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline -; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly +; Solution is to drop out of interrupt context into pure kernel mode +; and return from pure kernel mode which does right things for delay slot .Lintr_ret_to_delay_slot: debug_marker_ds: @@ -255,48 +241,9 @@ debug_marker_ds: add r2, r2, 1 st r2, [@intr_to_DE_cnt] - ld r2, [sp, PT_ret] - ld r3, [sp, PT_status32] - - ; STAT32 for Int return created from scratch - ; (No delay dlot, disable Further intr in trampoline) - - bic r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK - st r0, [sp, PT_status32] - - mov r1, .Lintr_ret_to_delay_slot_2 - st r1, [sp, PT_ret] - - ; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots - st r2, [sp, 0] - st r3, [sp, 4] - - b .Lisr_ret_fast_path - -.Lintr_ret_to_delay_slot_2: - ; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP - sub sp, sp, SZ_PT_REGS - st r9, [sp, -4] - - ld r9, [sp, 0] - sr r9, [eret] - - ld r9, [sp, 4] - sr r9, [erstatus] - - ; restore AUX_USER_SP if returning to U mode - bbit0 r9, STATUS_U_BIT, 1f - ld r9, [sp, PT_sp] - sr r9, [AUX_USER_SP] - -1: - ld r9, [sp, 8] - sr r9, [erbta] - - ld r9, [sp, -4] - add sp, sp, SZ_PT_REGS - - ; return from pure kernel mode to delay slot - rtie + ; drop out of interrupt context (clear AUX_IRQ_ACT.active) + bmskn r11, r10, 15 + sr r11, [AUX_IRQ_ACT] + b .Lexcept_ret END(ret_from_exception) diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S index f285dbb28066..774c03cc1d1a 100644 --- a/arch/arc/kernel/entry-compact.S +++ b/arch/arc/kernel/entry-compact.S @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARCompact ISA * * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * vineetg: May 2011 * -Userspace unaligned access emulation * @@ -257,18 +254,7 @@ END(handle_interrupt_level1) ENTRY(EV_TLBProtV) - EXCEPTION_PROLOGUE - - mov r2, r9 ; ECR set into r9 already - lr r0, [efa] ; Faulting Data address (not part of pt_regs saved above) - - ; Exception auto-disables further Intr/exceptions. - ; Re-enable them by pretending to return from exception - ; (so rest of handler executes in pure K mode) - - FAKE_RET_FROM_EXCPN - - mov r1, sp ; Handle to pt_regs + EXCEPTION_PROLOGUE ; ECR returned in r10 ;------ (5) Type of Protection Violation? ---------- ; @@ -276,8 +262,7 @@ ENTRY(EV_TLBProtV) ; -Access Violation : 00_23_(00|01|02|03)_00 ; x r w r+w ; -Unaligned Access : 00_23_04_00 - ; - bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f + bbit1 r10, ECR_C_BIT_PROTV_MISALIG_DATA, 4f ;========= (6a) Access Violation Processing ======== bl do_page_fault @@ -306,9 +291,6 @@ END(EV_TLBProtV) ENTRY(call_do_page_fault) EXCEPTION_PROLOGUE - lr r0, [efa] ; Faulting Data address - mov r1, sp - FAKE_RET_FROM_EXCPN mov blink, ret_from_exception b do_page_fault diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 85d9ea4a0acc..3c7e74aba679 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Common Low Level Interrupts/Traps/Exceptions(non-TLB) Handling for ARC * (included from entry-<isa>.S * * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ /*------------------------------------------------------------------ @@ -32,12 +29,24 @@ ENTRY(sys_clone_wrapper) DISCARD_CALLEE_SAVED_USER GET_CURR_THR_INFO_FLAGS r10 - btst r10, TIF_SYSCALL_TRACE - bnz tracesys_exit + and.f 0, r10, _TIF_SYSCALL_WORK + bnz tracesys_exit b .Lret_from_system_call END(sys_clone_wrapper) +ENTRY(sys_clone3_wrapper) + SAVE_CALLEE_SAVED_USER + bl @sys_clone3 + DISCARD_CALLEE_SAVED_USER + + GET_CURR_THR_INFO_FLAGS r10 + and.f 0, r10, _TIF_SYSCALL_WORK + bnz tracesys_exit + + b .Lret_from_system_call +END(sys_clone3_wrapper) + ENTRY(ret_from_fork) ; when the forked child comes here from the __switch_to function ; r0 has the last task pointer. @@ -71,11 +80,6 @@ ENTRY(instr_service) EXCEPTION_PROLOGUE - lr r0, [efa] - mov r1, sp - - FAKE_RET_FROM_EXCPN - bl do_insterror_or_kprobe b ret_from_exception END(instr_service) @@ -86,19 +90,15 @@ END(instr_service) ENTRY(EV_MachineCheck) - EXCEPTION_PROLOGUE + EXCEPTION_PROLOGUE_KEEP_AE ; ECR returned in r10 - lr r2, [ecr] lr r0, [efa] mov r1, sp - ; hardware auto-disables MMU, re-enable it to allow kernel vaddr - ; access for say stack unwinding of modules for crash dumps - lr r3, [ARC_REG_PID] - or r3, r3, MMU_ENABLE - sr r3, [ARC_REG_PID] + ; MC exceptions disable MMU + ARC_MMU_REENABLE r3 - lsr r3, r2, 8 + lsr r3, r10, 8 bmsk r3, r3, 7 brne r3, ECR_C_MCHK_DUP_TLB, 1f @@ -123,11 +123,6 @@ ENTRY(EV_PrivilegeV) EXCEPTION_PROLOGUE - lr r0, [efa] - mov r1, sp - - FAKE_RET_FROM_EXCPN - bl do_privilege_fault b ret_from_exception END(EV_PrivilegeV) @@ -139,11 +134,6 @@ ENTRY(EV_Extension) EXCEPTION_PROLOGUE - lr r0, [efa] - mov r1, sp - - FAKE_RET_FROM_EXCPN - bl do_extension_fault b ret_from_exception END(EV_Extension) @@ -154,22 +144,20 @@ END(EV_Extension) ; syscall Tracing ; --------------------------------------------- tracesys: - ; save EFA in case tracer wants the PC of traced task - ; using ERET won't work since next-PC has already committed - lr r12, [efa] + ; safekeep EFA (r12) if syscall tracer wanted PC + ; for traps, ERET is pre-commit so points to next-PC GET_CURR_TASK_FIELD_PTR TASK_THREAD, r11 st r12, [r11, THREAD_FAULT_ADDR] ; thread.fault_address - ; PRE Sys Call Ptrace hook - mov r0, sp ; pt_regs needed - bl @syscall_trace_entry + ; PRE syscall trace hook + mov r0, sp ; pt_regs + bl @syscall_trace_enter ; Tracing code now returns the syscall num (orig or modif) mov r8, r0 ; Do the Sys Call as we normally would. - ; Validate the Sys Call number - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi tracesys_exit @@ -185,83 +173,74 @@ tracesys: ld r6, [sp, PT_r6] ld r7, [sp, PT_r7] ld.as r9, [sys_call_table, r8] - jl [r9] ; Entry into Sys Call Handler + jl [r9] tracesys_exit: - st r0, [sp, PT_r0] ; sys call return value in pt_regs + st r0, [sp, PT_r0] - ;POST Sys Call Ptrace Hook + ; POST syscall trace hook + mov r0, sp ; pt_regs needed bl @syscall_trace_exit - b ret_from_exception ; NOT ret_from_system_call at is saves r0 which - ; we'd done before calling post hook above + + ; don't call ret_from_system_call as it saves r0, already done above + b ret_from_exception ; --------------------------------------------- ; Breakpoint TRAP ; --------------------------------------------- trap_with_param: + mov r0, r12 ; EFA in case ptracer/gdb wants stop_pc + mov r1, sp ; pt_regs - ; stop_pc info by gdb needs this info - lr r0, [efa] - mov r1, sp - - ; Now that we have read EFA, it is safe to do "fake" rtie - ; and get out of CPU exception mode - FAKE_RET_FROM_EXCPN - - ; Save callee regs in case gdb wants to have a look - ; SP will grow up by size of CALLEE Reg-File - ; NOTE: clobbers r12 + ; save callee regs in case tracer/gdb wants to peek SAVE_CALLEE_SAVED_USER - ; save location of saved Callee Regs @ thread_struct->pc + ; safekeep ref to callee regs GET_CURR_TASK_FIELD_PTR TASK_THREAD, r10 st sp, [r10, THREAD_CALLEE_REG] - ; Call the trap handler + ; call the non syscall trap handler bl do_non_swi_trap - ; unwind stack to discard Callee saved Regs + ; unwind stack to discard callee regs DISCARD_CALLEE_SAVED_USER b ret_from_exception ; --------------------------------------------- ; syscall TRAP -; ABI: (r0-r7) upto 8 args, (r8) syscall number +; ABI: (r0-r7) up to 8 args, (r8) syscall number ; --------------------------------------------- ENTRY(EV_Trap) - EXCEPTION_PROLOGUE + EXCEPTION_PROLOGUE_KEEP_AE - ;============ TRAP 1 :breakpoints - ; Check ECR for trap with arg (PROLOGUE ensures r9 has ECR) - bmsk.f 0, r9, 7 - bnz trap_with_param - - ;============ TRAP (no param): syscall top level + lr r12, [efa] - ; First return from Exception to pure K mode (Exception/IRQs renabled) FAKE_RET_FROM_EXCPN - ; If syscall tracing ongoing, invoke pre-post-hooks + ;============ TRAP N : breakpoints, kprobes etc + bmsk.f 0, r10, 7 + bnz trap_with_param + + ;============ TRAP 0 (no param): syscall + + ; syscall tracing ongoing, invoke pre-post-hooks around syscall GET_CURR_THR_INFO_FLAGS r10 - btst r10, TIF_SYSCALL_TRACE - bnz tracesys ; this never comes back + and.f 0, r10, _TIF_SYSCALL_WORK + bnz tracesys ; this never comes back ;============ Normal syscall case - ; syscall num shd not exceed the total system calls avail - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi .Lret_from_system_call - ; Offset into the syscall_table and call handler ld.as r9,[sys_call_table, r8] - jl [r9] ; Entry into Sys Call Handler + jl [r9] .Lret_from_system_call: - st r0, [sp, PT_r0] ; sys call return value in pt_regs ; fall through to ret_from_exception @@ -304,7 +283,8 @@ resume_user_mode_begin: mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume() GET_CURR_THR_INFO_FLAGS r9 - bbit0 r9, TIF_SIGPENDING, .Lchk_notify_resume + and.f 0, r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL + bz .Lchk_notify_resume ; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs ; in pt_reg since the "C" ABI (kernel code) will automatically @@ -316,7 +296,7 @@ resume_user_mode_begin: ; tracer might call PEEKUSR(CALLEE reg) ; ; NOTE: SP will grow up by size of CALLEE Reg-File - SAVE_CALLEE_SAVED_USER ; clobbers r12 + SAVE_CALLEE_SAVED_USER ; save location of saved Callee Regs @ thread_struct->callee GET_CURR_TASK_FIELD_PTR TASK_THREAD, r10 @@ -340,11 +320,11 @@ resume_user_mode_begin: resume_kernel_mode: ; Disable Interrupts from this point on - ; CONFIG_PREEMPT: This is a must for preempt_schedule_irq() - ; !CONFIG_PREEMPT: To ensure restore_regs is intr safe + ; CONFIG_PREEMPTION: This is a must for preempt_schedule_irq() + ; !CONFIG_PREEMPTION: To ensure restore_regs is intr safe IRQ_DISABLE r9 -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION ; Can't preempt if preemption disabled GET_CURR_THR_INFO_FROM_SP r10 diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c index f352e512cbd1..ec640219d989 100644 --- a/arch/arc/kernel/fpu.c +++ b/arch/arc/kernel/fpu.c @@ -1,15 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fpu.c - save/restore of Floating Point Unit Registers on task switch * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/sched.h> -#include <asm/switch_to.h> +#include <asm/fpu.h> + +#ifdef CONFIG_ISA_ARCOMPACT /* * To save/restore FPU regs, simplest scheme would use LR/SR insns. @@ -53,3 +52,31 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next) : "r" (zero), "r" (*(readfrom + 3)), "r" (*(readfrom + 2)) ); } + +#else + +void fpu_init_task(struct pt_regs *regs) +{ + const unsigned int fwe = 0x80000000; + + /* default rounding mode */ + write_aux_reg(ARC_REG_FPU_CTRL, 0x100); + + /* Initialize to zero: setting requires FWE be set */ + write_aux_reg(ARC_REG_FPU_STATUS, fwe); +} + +void fpu_save_restore(struct task_struct *prev, struct task_struct *next) +{ + struct arc_fpu *save = &prev->thread.fpu; + struct arc_fpu *restore = &next->thread.fpu; + const unsigned int fwe = 0x80000000; + + save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL); + save->status = read_aux_reg(ARC_REG_FPU_STATUS); + + write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl); + write_aux_reg(ARC_REG_FPU_STATUS, (fwe | restore->status)); +} + +#endif diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 8b90d25a15cc..8d541f53fae3 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * ARC CPU startup Code * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Vineetg: Dec 2007 * -Check if we are running on Simulator or on real hardware * to skip certain things during boot on simulator @@ -17,6 +14,8 @@ #include <asm/entry.h> #include <asm/arcregs.h> #include <asm/cache.h> +#include <asm/dsp-impl.h> +#include <asm/irqflags.h> .macro CPU_EARLY_SETUP @@ -47,6 +46,46 @@ sr r5, [ARC_REG_DC_CTRL] 1: + +#ifdef CONFIG_ISA_ARCV2 + ; Unaligned access is disabled at reset, so re-enable early as + ; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access + ; by default + lr r5, [status32] +#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS + bset r5, r5, STATUS_AD_BIT +#else + ; Although disabled at reset, bootloader might have enabled it + bclr r5, r5, STATUS_AD_BIT +#endif + kflag r5 + +#ifdef CONFIG_ARC_LPB_DISABLE + lr r5, [ARC_REG_LPB_BUILD] + breq r5, 0, 1f ; LPB doesn't exist + mov r5, 1 + sr r5, [ARC_REG_LPB_CTRL] +1: +#endif /* CONFIG_ARC_LPB_DISABLE */ + + /* On HSDK, CCMs need to remapped super early */ +#ifdef CONFIG_ARC_SOC_HSDK + mov r6, 0x60000000 + lr r5, [ARC_REG_ICCM_BUILD] + breq r5, 0, 1f + sr r6, [ARC_REG_AUX_ICCM] +1: + lr r5, [ARC_REG_DCCM_BUILD] + breq r5, 0, 2f + sr r6, [ARC_REG_AUX_DCCM] +2: +#endif /* CONFIG_ARC_SOC_HSDK */ + +#endif /* CONFIG_ISA_ARCV2 */ + + ; Config DSP_CTRL properly, so kernel may use integer multiply, + ; multiply-accumulate, and divide operations + DSP_EARLY_INIT .endm .section .init.text, "ax",@progbits @@ -90,15 +129,14 @@ ENTRY(stext) st.ab 0, [r5, 4] 1: -#ifdef CONFIG_ARC_UBOOT_SUPPORT ; Uboot - kernel ABI ; r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2 - ; r1 = magic number (board identity, unused as of now + ; r1 = magic number (always zero as of now) ; r2 = pointer to uboot provided cmdline or external DTB in mem - ; These are handled later in setup_arch() + ; These are handled later in handle_uboot_args() st r0, [@uboot_tag] + st r1, [@uboot_magic] st r2, [@uboot_arg] -#endif ; setup "current" tsk and optionally cache it in dedicated r25 mov r9, @init_task @@ -127,7 +165,7 @@ ENTRY(first_lines_of_secondary) ; setup stack (fp, sp) mov fp, 0 - ; set it's stack base to tsk->thread_info bottom + ; set its stack base to tsk->thread_info bottom GET_TSK_STACK_BASE r0, sp j start_kernel_secondary diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 067ea362fb3e..809edc59af25 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2014 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * */ #include <linux/interrupt.h> @@ -49,16 +45,18 @@ void arc_init_IRQ(void) *(unsigned int *)&ictrl = 0; +#ifndef CONFIG_ARC_IRQ_NO_AUTOSAVE ictrl.save_nr_gpr_pairs = 6; /* r0 to r11 (r12 saved manually) */ ictrl.save_blink = 1; ictrl.save_lp_regs = 1; /* LP_COUNT, LP_START, LP_END */ ictrl.save_u_to_u = 0; /* user ctxt saved on kernel stack */ ictrl.save_idx_regs = 1; /* JLI, LDI, EI */ +#endif WRITE_AUX(AUX_IRQ_CTRL, ictrl); /* - * ARCv2 core intc provides multiple interrupt priorities (upto 16). + * ARCv2 core intc provides multiple interrupt priorities (up to 16). * Typical builds though have only two levels (0-high, 1-low) * Linux by default uses lower prio 1 for most irqs, reserving 0 for * NMI style interrupts in future (say perf) @@ -93,7 +91,7 @@ void arc_init_IRQ(void) /* setup status32, don't enable intr yet as kernel doesn't want */ tmp = read_aux_reg(ARC_REG_STATUS32); - tmp |= STATUS_AD_MASK | (ARCV2_IRQ_DEF_PRIO << 1); + tmp |= ARCV2_IRQ_DEF_PRIO << 1; tmp &= ~STATUS_IE_MASK; asm volatile("kflag %0 \n"::"r"(tmp)); } @@ -110,7 +108,7 @@ static void arcv2_irq_unmask(struct irq_data *data) write_aux_reg(AUX_IRQ_ENABLE, 1); } -void arcv2_irq_enable(struct irq_data *data) +static void arcv2_irq_enable(struct irq_data *data) { /* set default priority */ write_aux_reg(AUX_IRQ_SELECT, data->hwirq); @@ -172,7 +170,7 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent) if (parent) panic("DeviceTree incore intc not a root irq controller\n"); - root_domain = irq_domain_add_linear(intc, nr_cpu_irqs, &arcv2_irq_ops, NULL); + root_domain = irq_domain_create_linear(of_fwnode_handle(intc), nr_cpu_irqs, &arcv2_irq_ops, NULL); if (!root_domain) panic("root irq domain not avail\n"); @@ -180,7 +178,7 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent) * Needed for primary domain lookup to succeed * This is a primary irqchip, and can never have a parent */ - irq_set_default_host(root_domain); + irq_set_default_domain(root_domain); #ifdef CONFIG_SMP irq_create_mapping(root_domain, IPI_IRQ); diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index 47b421fa0147..1b159e9e0234 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * */ #include <linux/interrupt.h> @@ -116,8 +112,9 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent) if (parent) panic("DeviceTree incore intc not a root irq controller\n"); - root_domain = irq_domain_add_linear(intc, NR_CPU_IRQS, - &arc_intc_domain_ops, NULL); + root_domain = irq_domain_create_linear(of_fwnode_handle(intc), + NR_CPU_IRQS, + &arc_intc_domain_ops, NULL); if (!root_domain) panic("root irq domain not avail\n"); @@ -125,7 +122,7 @@ init_onchip_IRQ(struct device_node *intc, struct device_node *parent) * Needed for primary domain lookup to succeed * This is a primary irqchip, and can never have a parent */ - irq_set_default_host(root_domain); + irq_set_default_domain(root_domain); return 0; } @@ -146,7 +143,7 @@ IRQCHIP_DECLARE(arc_intc, "snps,arc700-intc", init_onchip_IRQ); * Time hard-ISR, timer_interrupt( ) calls spin_unlock_irq several times. * Here local_irq_enable( ) shd not re-enable lower priority interrupts * -If called from soft-ISR, it must re-enable all interrupts - * soft ISR are low prioity jobs which can be very slow, thus all IRQs + * soft ISR are low priority jobs which can be very slow, thus all IRQs * must be enabled while they run. * Now hardware context wise we may still be in L2 ISR (not done rtie) * still we must re-enable both L1 and L2 IRQs diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 62b185057c04..dd09b58ff82d 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -1,15 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011-12 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * */ #include <linux/interrupt.h> #include <linux/irqchip.h> #include <asm/mach_desc.h> + +#include <asm/irq_regs.h> #include <asm/smp.h> /* @@ -43,5 +41,11 @@ void __init init_IRQ(void) */ void arch_do_IRQ(unsigned int hwirq, struct pt_regs *regs) { - handle_domain_irq(NULL, hwirq, regs); + struct pt_regs *old_regs; + + irq_enter(); + old_regs = set_irq_regs(regs); + generic_handle_domain_irq(NULL, hwirq); + set_irq_regs(old_regs); + irq_exit(); } diff --git a/arch/arc/kernel/jump_label.c b/arch/arc/kernel/jump_label.c new file mode 100644 index 000000000000..70b74a5d047b --- /dev/null +++ b/arch/arc/kernel/jump_label.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/jump_label.h> + +#include "asm/cacheflush.h" + +#define JUMPLABEL_ERR "ARC: jump_label: ERROR: " + +/* Halt system on fatal error to make debug easier */ +#define arc_jl_fatal(format...) \ +({ \ + pr_err(JUMPLABEL_ERR format); \ + BUG(); \ +}) + +static inline u32 arc_gen_nop(void) +{ + /* 1x 32bit NOP in middle endian */ + return 0x7000264a; +} + +/* + * Atomic update of patched instruction is only available if this + * instruction doesn't cross L1 cache line boundary. You can read about + * the way we achieve this in arc/include/asm/jump_label.h + */ +static inline void instruction_align_assert(void *addr, int len) +{ + unsigned long a = (unsigned long)addr; + + if ((a >> L1_CACHE_SHIFT) != ((a + len - 1) >> L1_CACHE_SHIFT)) + arc_jl_fatal("instruction (addr %px) cross L1 cache line border", + addr); +} + +/* + * ARCv2 'Branch unconditionally' instruction: + * 00000ssssssssss1SSSSSSSSSSNRtttt + * s S[n:0] lower bits signed immediate (number is bitfield size) + * S S[m:n+1] upper bits signed immediate (number is bitfield size) + * t S[24:21] upper bits signed immediate (branch unconditionally far) + * N N <.d> delay slot mode + * R R Reserved + */ +static inline u32 arc_gen_branch(jump_label_t pc, jump_label_t target) +{ + u32 instruction_l, instruction_r; + u32 pcl = pc & GENMASK(31, 2); + u32 u_offset = target - pcl; + u32 s, S, t; + + /* + * Offset in 32-bit branch instruction must to fit into s25. + * Something is terribly broken if we get such huge offset within one + * function. + */ + if ((s32)u_offset < -16777216 || (s32)u_offset > 16777214) + arc_jl_fatal("gen branch with offset (%d) not fit in s25", + (s32)u_offset); + + /* + * All instructions are aligned by 2 bytes so we should never get offset + * here which is not 2 bytes aligned. + */ + if (u_offset & 0x1) + arc_jl_fatal("gen branch with offset (%d) unaligned to 2 bytes", + (s32)u_offset); + + s = (u_offset >> 1) & GENMASK(9, 0); + S = (u_offset >> 11) & GENMASK(9, 0); + t = (u_offset >> 21) & GENMASK(3, 0); + + /* 00000ssssssssss1 */ + instruction_l = (s << 1) | 0x1; + /* SSSSSSSSSSNRtttt */ + instruction_r = (S << 6) | t; + + return (instruction_r << 16) | (instruction_l & GENMASK(15, 0)); +} + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_t *instr_addr = (jump_label_t *)entry->code; + u32 instr; + + instruction_align_assert(instr_addr, JUMP_LABEL_NOP_SIZE); + + if (type == JUMP_LABEL_JMP) + instr = arc_gen_branch(entry->code, entry->target); + else + instr = arc_gen_nop(); + + WRITE_ONCE(*instr_addr, instr); + flush_icache_range(entry->code, entry->code + JUMP_LABEL_NOP_SIZE); +} + +#ifdef CONFIG_ARC_DBG_JUMP_LABEL +#define SELFTEST_MSG "ARC: instruction generation self-test: " + +struct arc_gen_branch_testdata { + jump_label_t pc; + jump_label_t target_address; + u32 expected_instr; +}; + +static __init int branch_gen_test(const struct arc_gen_branch_testdata *test) +{ + u32 instr_got; + + instr_got = arc_gen_branch(test->pc, test->target_address); + if (instr_got == test->expected_instr) + return 0; + + pr_err(SELFTEST_MSG "FAIL:\n arc_gen_branch(0x%08x, 0x%08x) != 0x%08x, got 0x%08x\n", + test->pc, test->target_address, + test->expected_instr, instr_got); + + return -EFAULT; +} + +/* + * Offset field in branch instruction is not continuous. Test all + * available offset field and sign combinations. Test data is generated + * from real working code. + */ +static const struct arc_gen_branch_testdata arcgenbr_test_data[] __initconst = { + {0x90007548, 0x90007514, 0xffcf07cd}, /* tiny (-52) offs */ + {0x9000c9c0, 0x9000c782, 0xffcf05c3}, /* tiny (-574) offs */ + {0x9000cc1c, 0x9000c782, 0xffcf0367}, /* tiny (-1178) offs */ + {0x9009dce0, 0x9009d106, 0xff8f0427}, /* small (-3034) offs */ + {0x9000f5de, 0x90007d30, 0xfc0f0755}, /* big (-30892) offs */ + {0x900a2444, 0x90035f64, 0xc9cf0321}, /* huge (-443616) offs */ + {0x90007514, 0x9000752c, 0x00000019}, /* tiny (+24) offs */ + {0x9001a578, 0x9001a77a, 0x00000203}, /* tiny (+514) offs */ + {0x90031ed8, 0x90032634, 0x0000075d}, /* tiny (+1884) offs */ + {0x9008c7f2, 0x9008d3f0, 0x00400401}, /* small (+3072) offs */ + {0x9000bb38, 0x9003b340, 0x17c00009}, /* big (+194568) offs */ + {0x90008f44, 0x90578d80, 0xb7c2063d} /* huge (+5701180) offs */ +}; + +static __init int instr_gen_test(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(arcgenbr_test_data); i++) + if (branch_gen_test(&arcgenbr_test_data[i])) + return -EFAULT; + + pr_info(SELFTEST_MSG "OK\n"); + + return 0; +} +early_initcall(instr_gen_test); + +#endif /* CONFIG_ARC_DBG_JUMP_LABEL */ diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index 96bca9963c63..4f2b5951454f 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * kgdb support for ARC * * Copyright (C) 2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/kgdb.h> @@ -143,6 +140,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) regs->ret = addr; + fallthrough; case 'D': case 'k': @@ -177,7 +175,7 @@ void kgdb_trap(struct pt_regs *regs) * with trap_s 4 (compiled) breakpoints, continuation needs to * start after the breakpoint. */ - if (regs->ecr_param == 3) + if (regs->ecr.param == 3) instruction_pointer(regs) -= BREAK_INSTR_SIZE; kgdb_handle_exception(1, SIGTRAP, 0, regs); diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index df35d4c0b0b8..f8e2960832d9 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/types.h> @@ -193,7 +190,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs) } } -int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) +static int +__kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) { struct kprobe *p; struct kprobe_ctlblk *kcb; @@ -244,8 +242,8 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) return 0; } -static int __kprobes arc_post_kprobe_handler(unsigned long addr, - struct pt_regs *regs) +static int +__kprobes arc_post_kprobe_handler(unsigned long addr, struct pt_regs *regs) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -320,22 +318,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned long trapnr) * caused the fault. */ - /* We increment the nmissed count for accounting, - * we can also use npre/npostfault count for accounting - * these specific fault cases. - */ - kprobes_inc_nmissed_count(cur); - - /* - * We come here because instructions in the pre/post - * handler caused the page_fault, this could happen - * if handler tries to access user space by - * copy_from_user(), get_user() etc. Let the - * user-specified handler try to fix it first. - */ - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - /* * In case the user-specified fault handler returned zero, * try to fix up. @@ -382,8 +364,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, static void __used kretprobe_trampoline_holder(void) { - __asm__ __volatile__(".global kretprobe_trampoline\n" - "kretprobe_trampoline:\n" "nop\n"); + __asm__ __volatile__(".global __kretprobe_trampoline\n" + "__kretprobe_trampoline:\n" + "nop\n"); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, @@ -391,66 +374,16 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, { ri->ret_addr = (kprobe_opcode_t *) regs->blink; + ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->blink = (unsigned long)&kretprobe_trampoline; + regs->blink = (unsigned long)&__kretprobe_trampoline; } static int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head, empty_rp; - struct hlist_node *tmp; - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; - - INIT_HLIST_HEAD(&empty_rp); - kretprobe_hash_lock(current, &head, &flags); - - /* - * It is possible to have multiple instances associated with a given - * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more than one return - * return probe was registered for a target function. - * - * We can handle this because: - * - instances are always inserted at the head of the list - * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the - * real return address, and all the rest will point to - * kretprobe_trampoline - */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - if (ri->rp && ri->rp->handler) - ri->rp->handler(ri, regs); - - orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri, &empty_rp); - - if (orig_ret_address != trampoline_address) { - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - } - - kretprobe_assert(ri, orig_ret_address, trampoline_address); - regs->ret = orig_ret_address; - - kretprobe_hash_unlock(current, &flags); - - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } + regs->ret = __kretprobe_trampoline_handler(regs, NULL); /* By returning a non zero value, we are telling the kprobe handler * that we don't want the post_handler to run @@ -459,7 +392,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, } static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -471,7 +404,7 @@ int __init arch_init_kprobes(void) int __kprobes arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *) &kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *) &__kretprobe_trampoline) return 1; return 0; diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 5fe84e481654..02b28a9324f4 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * ARC ARConnect (MultiCore IP) support (formerly known as MCIP) * * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/smp.h> @@ -168,8 +165,6 @@ static void mcip_probe_n_setup(void) IS_AVAIL1(mp.idu, "IDU "), IS_AVAIL1(mp.dbg, "DEBUG "), IS_AVAIL1(mp.gfrc, "GFRC")); - - cpuinfo_arc700[0].extn.gfrc = mp.gfrc; } struct plat_smp_ops plat_smp_ops = { @@ -205,8 +200,8 @@ static void idu_set_dest(unsigned int cmn_irq, unsigned int cpu_mask) __mcip_cmd_data(CMD_IDU_SET_DEST, cmn_irq, cpu_mask); } -static void idu_set_mode(unsigned int cmn_irq, unsigned int lvl, - unsigned int distr) +static void idu_set_mode(unsigned int cmn_irq, bool set_lvl, unsigned int lvl, + bool set_distr, unsigned int distr) { union { unsigned int word; @@ -215,8 +210,11 @@ static void idu_set_mode(unsigned int cmn_irq, unsigned int lvl, }; } data; - data.distr = distr; - data.lvl = lvl; + data.word = __mcip_cmd_read(CMD_IDU_READ_MODE, cmn_irq); + if (set_distr) + data.distr = distr; + if (set_lvl) + data.lvl = lvl; __mcip_cmd_data(CMD_IDU_SET_MODE, cmn_irq, data.word); } @@ -243,6 +241,25 @@ static void idu_irq_unmask(struct irq_data *data) raw_spin_unlock_irqrestore(&mcip_lock, flags); } +static void idu_irq_ack(struct irq_data *data) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + __mcip_cmd(CMD_IDU_ACK_CIRQ, data->hwirq); + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + +static void idu_irq_mask_ack(struct irq_data *data) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + __mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 1); + __mcip_cmd(CMD_IDU_ACK_CIRQ, data->hwirq); + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + static int idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, bool force) @@ -266,13 +283,36 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, else distribution_mode = IDU_M_DISTRI_RR; - idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, distribution_mode); + idu_set_mode(data->hwirq, false, 0, true, distribution_mode); raw_spin_unlock_irqrestore(&mcip_lock, flags); return IRQ_SET_MASK_OK; } +static int idu_irq_set_type(struct irq_data *data, u32 type) +{ + unsigned long flags; + + /* + * ARCv2 IDU HW does not support inverse polarity, so these are the + * only interrupt types supported. + */ + if (type & ~(IRQ_TYPE_EDGE_RISING | IRQ_TYPE_LEVEL_HIGH)) + return -EINVAL; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + idu_set_mode(data->hwirq, true, + type & IRQ_TYPE_EDGE_RISING ? IDU_M_TRIG_EDGE : + IDU_M_TRIG_LEVEL, + false, 0); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); + + return 0; +} + static void idu_irq_enable(struct irq_data *data) { /* @@ -292,7 +332,10 @@ static struct irq_chip idu_irq_chip = { .name = "MCIP IDU Intc", .irq_mask = idu_irq_mask, .irq_unmask = idu_irq_unmask, + .irq_ack = idu_irq_ack, + .irq_mask_ack = idu_irq_mask_ack, .irq_enable = idu_irq_enable, + .irq_set_type = idu_irq_set_type, #ifdef CONFIG_SMP .irq_set_affinity = idu_irq_set_affinity, #endif @@ -307,20 +350,18 @@ static void idu_cascade_isr(struct irq_desc *desc) irq_hw_number_t idu_hwirq = core_hwirq - FIRST_EXT_IRQ; chained_irq_enter(core_chip, desc); - generic_handle_irq(irq_find_mapping(idu_domain, idu_hwirq)); + generic_handle_domain_irq(idu_domain, idu_hwirq); chained_irq_exit(core_chip, desc); } static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq) { irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq); - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); - return 0; } static const struct irq_domain_ops idu_irq_ops = { - .xlate = irq_domain_xlate_onecell, + .xlate = irq_domain_xlate_onetwocell, .map = idu_irq_map, }; @@ -350,7 +391,8 @@ idu_of_init(struct device_node *intc, struct device_node *parent) pr_info("MCIP: IDU supports %u common irqs\n", nr_irqs); - domain = irq_domain_add_linear(intc, nr_irqs, &idu_irq_ops, NULL); + domain = irq_domain_create_linear(of_fwnode_handle(intc), nr_irqs, + &idu_irq_ops, NULL); /* Parent interrupts (core-intc) are already mapped */ diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c index 3d99a6091332..c90c279047bf 100644 --- a/arch/arc/kernel/module.c +++ b/arch/arc/kernel/module.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/module.h> diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 8aec462d90fb..ed6d4f0cd621 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -1,15 +1,10 @@ -/* - * Linux performance counter support for ARC700 series - * - * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com) - * - * This code is inspired by the perf support of various other architectures. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// Linux performance counter support for ARC CPUs. +// This code is inspired by the perf support of various other architectures. +// +// Copyright (C) 2013-2018 Synopsys, Inc. (www.synopsys.com) + #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/module.h> @@ -19,12 +14,193 @@ #include <asm/arcregs.h> #include <asm/stacktrace.h> +/* HW holds 8 symbols + one for null terminator */ +#define ARCPMU_EVENT_NAME_LEN 9 + +/* + * Some ARC pct quirks: + * + * PERF_COUNT_HW_STALLED_CYCLES_BACKEND + * PERF_COUNT_HW_STALLED_CYCLES_FRONTEND + * The ARC 700 can either measure stalls per pipeline stage, or all stalls + * combined; for now we assign all stalls to STALLED_CYCLES_BACKEND + * and all pipeline flushes (e.g. caused by mispredicts, etc.) to + * STALLED_CYCLES_FRONTEND. + * + * We could start multiple performance counters and combine everything + * afterwards, but that makes it complicated. + * + * Note that I$ cache misses aren't counted by either of the two! + */ + +/* + * ARC PCT has hardware conditions with fixed "names" but variable "indexes" + * (based on a specific RTL build) + * Below is the static map between perf generic/arc specific event_id and + * h/w condition names. + * At the time of probe, we loop thru each index and find its name to + * complete the mapping of perf event_id to h/w index as latter is needed + * to program the counter really + */ +static const char * const arc_pmu_ev_hw_map[] = { + /* count cycles */ + [PERF_COUNT_HW_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_REF_CPU_CYCLES] = "crun", + [PERF_COUNT_HW_BUS_CYCLES] = "crun", + + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = "bflush", + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = "bstall", + + /* counts condition */ + [PERF_COUNT_HW_INSTRUCTIONS] = "iall", + /* All jump instructions that are taken */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak", +#ifdef CONFIG_ISA_ARCV2 + [PERF_COUNT_HW_BRANCH_MISSES] = "bpmp", +#else + [PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */ + [PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */ +#endif + [PERF_COUNT_ARC_LDC] = "imemrdc", /* Instr: mem read cached */ + [PERF_COUNT_ARC_STC] = "imemwrc", /* Instr: mem write cached */ + + [PERF_COUNT_ARC_DCLM] = "dclm", /* D-cache Load Miss */ + [PERF_COUNT_ARC_DCSM] = "dcsm", /* D-cache Store Miss */ + [PERF_COUNT_ARC_ICM] = "icm", /* I-cache Miss */ + [PERF_COUNT_ARC_EDTLB] = "edtlb", /* D-TLB Miss */ + [PERF_COUNT_ARC_EITLB] = "eitlb", /* I-TLB Miss */ + + [PERF_COUNT_HW_CACHE_REFERENCES] = "imemrdc", /* Instr: mem read cached */ + [PERF_COUNT_HW_CACHE_MISSES] = "dclm", /* D-cache Load Miss */ +}; + +#define C(_x) PERF_COUNT_HW_CACHE_##_x +#define CACHE_OP_UNSUPPORTED 0xffff + +static const unsigned int arc_pmu_cache_map[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCLM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_ARC_STC, + [C(RESULT_MISS)] = PERF_COUNT_ARC_DCSM, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_ARC_ICM, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_ARC_LDC, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EDTLB, + }, + /* DTLB LD/ST Miss not segregated by h/w*/ + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = PERF_COUNT_ARC_EITLB, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [C(RESULT_MISS)] = PERF_COUNT_HW_BRANCH_MISSES, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, + [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, + }, + }, +}; + +enum arc_pmu_attr_groups { + ARCPMU_ATTR_GR_EVENTS, + ARCPMU_ATTR_GR_FORMATS, + ARCPMU_NR_ATTR_GR +}; + +struct arc_pmu_raw_event_entry { + char name[ARCPMU_EVENT_NAME_LEN]; +}; + struct arc_pmu { struct pmu pmu; unsigned int irq; int n_counters; + int n_events; u64 max_period; int ev_hw_idx[PERF_COUNT_ARC_HW_MAX]; + + struct arc_pmu_raw_event_entry *raw_entry; + struct attribute **attrs; + struct perf_pmu_events_attr *attr; + const struct attribute_group *attr_groups[ARCPMU_NR_ATTR_GR + 1]; }; struct arc_pmu_cpu { @@ -49,6 +225,7 @@ static int callchain_trace(unsigned int addr, void *data) { struct arc_callchain_trace *ctrl = data; struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff; + perf_callchain_store(entry, addr); if (ctrl->depth++ < 3) @@ -57,8 +234,8 @@ static int callchain_trace(unsigned int addr, void *data) return -1; } -void -perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) +void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) { struct arc_callchain_trace ctrl = { .depth = 0, @@ -68,8 +245,8 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re arc_unwind_core(NULL, regs, callchain_trace, &ctrl); } -void -perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) +void perf_callchain_user(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) { /* * User stack can't be unwound trivially with kernel dwarf unwinder @@ -82,10 +259,10 @@ static struct arc_pmu *arc_pmu; static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu); /* read counter #idx; note that counter# != event# on ARC! */ -static uint64_t arc_pmu_read_counter(int idx) +static u64 arc_pmu_read_counter(int idx) { - uint32_t tmp; - uint64_t result; + u32 tmp; + u64 result; /* * ARC supports making 'snapshots' of the counters, so we don't @@ -94,7 +271,7 @@ static uint64_t arc_pmu_read_counter(int idx) write_aux_reg(ARC_REG_PCT_INDEX, idx); tmp = read_aux_reg(ARC_REG_PCT_CONTROL); write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN); - result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32; + result = (u64) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32; result |= read_aux_reg(ARC_REG_PCT_SNAPL); return result; @@ -103,9 +280,9 @@ static uint64_t arc_pmu_read_counter(int idx) static void arc_perf_event_update(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - uint64_t prev_raw_count = local64_read(&hwc->prev_count); - uint64_t new_raw_count = arc_pmu_read_counter(idx); - int64_t delta = new_raw_count - prev_raw_count; + u64 prev_raw_count = local64_read(&hwc->prev_count); + u64 new_raw_count = arc_pmu_read_counter(idx); + s64 delta = new_raw_count - prev_raw_count; /* * We aren't afraid of hwc->prev_count changing beneath our feet @@ -155,7 +332,7 @@ static int arc_pmu_event_init(struct perf_event *event) int ret; if (!is_sampling_event(event)) { - hwc->sample_period = arc_pmu->max_period; + hwc->sample_period = arc_pmu->max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } @@ -192,6 +369,18 @@ static int arc_pmu_event_init(struct perf_event *event) pr_debug("init cache event with h/w %08x \'%s\'\n", (int)hwc->config, arc_pmu_ev_hw_map[ret]); return 0; + + case PERF_TYPE_RAW: + if (event->attr.config >= arc_pmu->n_events) + return -ENOENT; + + hwc->config |= event->attr.config; + pr_debug("init raw event with idx %lld \'%s\'\n", + event->attr.config, + arc_pmu->raw_entry[event->attr.config].name); + + return 0; + default: return -ENOENT; } @@ -200,7 +389,7 @@ static int arc_pmu_event_init(struct perf_event *event) /* starts all counters */ static void arc_pmu_enable(struct pmu *pmu) { - uint32_t tmp; + u32 tmp; tmp = read_aux_reg(ARC_REG_PCT_CONTROL); write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1); } @@ -208,7 +397,7 @@ static void arc_pmu_enable(struct pmu *pmu) /* stops all counters */ static void arc_pmu_disable(struct pmu *pmu) { - uint32_t tmp; + u32 tmp; tmp = read_aux_reg(ARC_REG_PCT_CONTROL); write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0); } @@ -228,7 +417,7 @@ static int arc_pmu_event_set_period(struct perf_event *event) local64_set(&hwc->period_left, left); hwc->last_period = period; overflow = 1; - } else if (unlikely(left <= 0)) { + } else if (unlikely(left <= 0)) { /* left underflowed by less than period. */ left += period; local64_set(&hwc->period_left, left); @@ -246,8 +435,8 @@ static int arc_pmu_event_set_period(struct perf_event *event) write_aux_reg(ARC_REG_PCT_INDEX, idx); /* Write value */ - write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value); - write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32)); + write_aux_reg(ARC_REG_PCT_COUNTL, lower_32_bits(value)); + write_aux_reg(ARC_REG_PCT_COUNTH, upper_32_bits(value)); perf_event_update_userpage(event); @@ -277,7 +466,7 @@ static void arc_pmu_start(struct perf_event *event, int flags) /* Enable interrupt for this counter */ if (is_sampling_event(event)) write_aux_reg(ARC_REG_PCT_INT_CTRL, - read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx)); + read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx)); /* enable ARC pmu here */ write_aux_reg(ARC_REG_PCT_INDEX, idx); /* counter # */ @@ -295,13 +484,13 @@ static void arc_pmu_stop(struct perf_event *event, int flags) * Reset interrupt flag by writing of 1. This is required * to make sure pending interrupt was not left. */ - write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx); + write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx)); write_aux_reg(ARC_REG_PCT_INT_CTRL, - read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx)); + read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~BIT(idx)); } if (!(event->hw.state & PERF_HES_STOPPED)) { - /* stop ARC pmu here */ + /* stop hw counter here */ write_aux_reg(ARC_REG_PCT_INDEX, idx); /* condition code #0 is always "never" */ @@ -334,7 +523,7 @@ static int arc_pmu_add(struct perf_event *event, int flags) { struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu); struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; + int idx; idx = ffz(pmu_cpu->used_mask[0]); if (idx == arc_pmu->n_counters) @@ -349,9 +538,10 @@ static int arc_pmu_add(struct perf_event *event, int flags) if (is_sampling_event(event)) { /* Mimic full counter overflow as other arches do */ - write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period); + write_aux_reg(ARC_REG_PCT_INT_CNTL, + lower_32_bits(arc_pmu->max_period)); write_aux_reg(ARC_REG_PCT_INT_CNTH, - (arc_pmu->max_period >> 32)); + upper_32_bits(arc_pmu->max_period)); } write_aux_reg(ARC_REG_PCT_CONFIG, 0); @@ -392,7 +582,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev) idx = __ffs(active_ints); /* Reset interrupt flag by writing of 1 */ - write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx); + write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx)); /* * On reset of "interrupt active" bit corresponding @@ -400,7 +590,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev) * Now we need to re-enable interrupt for the counter. */ write_aux_reg(ARC_REG_PCT_INT_CTRL, - read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx)); + read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx)); event = pmu_cpu->act_counter[idx]; hwc = &event->hw; @@ -409,12 +599,10 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev) arc_perf_event_update(event, &event->hw, event->hw.idx); perf_sample_data_init(&data, 0, hwc->last_period); - if (arc_pmu_event_set_period(event)) { - if (perf_event_overflow(event, &data, regs)) - arc_pmu_stop(event, 0); - } + if (arc_pmu_event_set_period(event)) + perf_event_overflow(event, &data, regs); - active_ints &= ~(1U << idx); + active_ints &= ~BIT(idx); } while (active_ints); done: @@ -441,19 +629,108 @@ static void arc_cpu_pmu_irq_init(void *data) write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff); } +/* Event field occupies the bottom 15 bits of our config field */ +PMU_FORMAT_ATTR(event, "config:0-14"); +static struct attribute *arc_pmu_format_attrs[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group arc_pmu_format_attr_gr = { + .name = "format", + .attrs = arc_pmu_format_attrs, +}; + +static ssize_t arc_pmu_events_sysfs_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + return sprintf(page, "event=0x%04llx\n", pmu_attr->id); +} + +/* + * We don't add attrs here as we don't have pre-defined list of perf events. + * We will generate and add attrs dynamically in probe() after we read HW + * configuration. + */ +static struct attribute_group arc_pmu_events_attr_gr = { + .name = "events", +}; + +static void arc_pmu_add_raw_event_attr(int j, char *str) +{ + memmove(arc_pmu->raw_entry[j].name, str, ARCPMU_EVENT_NAME_LEN - 1); + arc_pmu->attr[j].attr.attr.name = arc_pmu->raw_entry[j].name; + arc_pmu->attr[j].attr.attr.mode = VERIFY_OCTAL_PERMISSIONS(0444); + arc_pmu->attr[j].attr.show = arc_pmu_events_sysfs_show; + arc_pmu->attr[j].id = j; + arc_pmu->attrs[j] = &(arc_pmu->attr[j].attr.attr); +} + +static int arc_pmu_raw_alloc(struct device *dev) +{ + arc_pmu->attr = devm_kmalloc_array(dev, arc_pmu->n_events + 1, + sizeof(*arc_pmu->attr), GFP_KERNEL | __GFP_ZERO); + if (!arc_pmu->attr) + return -ENOMEM; + + arc_pmu->attrs = devm_kmalloc_array(dev, arc_pmu->n_events + 1, + sizeof(*arc_pmu->attrs), GFP_KERNEL | __GFP_ZERO); + if (!arc_pmu->attrs) + return -ENOMEM; + + arc_pmu->raw_entry = devm_kmalloc_array(dev, arc_pmu->n_events, + sizeof(*arc_pmu->raw_entry), GFP_KERNEL | __GFP_ZERO); + if (!arc_pmu->raw_entry) + return -ENOMEM; + + return 0; +} + +static inline bool event_in_hw_event_map(int i, char *name) +{ + if (!arc_pmu_ev_hw_map[i]) + return false; + + if (!strlen(arc_pmu_ev_hw_map[i])) + return false; + + if (strcmp(arc_pmu_ev_hw_map[i], name)) + return false; + + return true; +} + +static void arc_pmu_map_hw_event(int j, char *str) +{ + int i; + + /* See if HW condition has been mapped to a perf event_id */ + for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) { + if (event_in_hw_event_map(i, str)) { + pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n", + i, str, j); + arc_pmu->ev_hw_idx[i] = j; + } + } +} + static int arc_pmu_device_probe(struct platform_device *pdev) { struct arc_reg_pct_build pct_bcr; struct arc_reg_cc_build cc_bcr; - int i, j, has_interrupts; + int i, has_interrupts, irq = -1; int counter_size; /* in bits */ union cc_name { struct { - uint32_t word0, word1; + u32 word0, word1; char sentinel; } indiv; - char str[9]; + char str[ARCPMU_EVENT_NAME_LEN]; } cc_name; @@ -463,15 +740,22 @@ static int arc_pmu_device_probe(struct platform_device *pdev) return -ENODEV; } BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32); - BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS); + if (WARN_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS)) + return -EINVAL; READ_BCR(ARC_REG_CC_BUILD, cc_bcr); - BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */ + if (WARN(!cc_bcr.v, "Counters exist but No countable conditions?")) + return -EINVAL; arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL); if (!arc_pmu) return -ENOMEM; + arc_pmu->n_events = cc_bcr.c; + + if (arc_pmu_raw_alloc(&pdev->dev)) + return -ENOMEM; + has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0; arc_pmu->n_counters = pct_bcr.c; @@ -481,30 +765,26 @@ static int arc_pmu_device_probe(struct platform_device *pdev) pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n", arc_pmu->n_counters, counter_size, cc_bcr.c, - has_interrupts ? ", [overflow IRQ support]":""); + has_interrupts ? ", [overflow IRQ support]" : ""); - cc_name.str[8] = 0; + cc_name.str[ARCPMU_EVENT_NAME_LEN - 1] = 0; for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++) arc_pmu->ev_hw_idx[i] = -1; /* loop thru all available h/w condition indexes */ - for (j = 0; j < cc_bcr.c; j++) { - write_aux_reg(ARC_REG_CC_INDEX, j); - cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); - cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); - - /* See if it has been mapped to a perf event_id */ - for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) { - if (arc_pmu_ev_hw_map[i] && - !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) && - strlen(arc_pmu_ev_hw_map[i])) { - pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n", - i, cc_name.str, j); - arc_pmu->ev_hw_idx[i] = j; - } - } + for (i = 0; i < cc_bcr.c; i++) { + write_aux_reg(ARC_REG_CC_INDEX, i); + cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0)); + cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1)); + + arc_pmu_map_hw_event(i, cc_name.str); + arc_pmu_add_raw_event_attr(i, cc_name.str); } + arc_pmu_events_attr_gr.attrs = arc_pmu->attrs; + arc_pmu->attr_groups[ARCPMU_ATTR_GR_EVENTS] = &arc_pmu_events_attr_gr; + arc_pmu->attr_groups[ARCPMU_ATTR_GR_FORMATS] = &arc_pmu_format_attr_gr; + arc_pmu->pmu = (struct pmu) { .pmu_enable = arc_pmu_enable, .pmu_disable = arc_pmu_disable, @@ -514,38 +794,44 @@ static int arc_pmu_device_probe(struct platform_device *pdev) .start = arc_pmu_start, .stop = arc_pmu_stop, .read = arc_pmu_read, + .attr_groups = arc_pmu->attr_groups, }; if (has_interrupts) { - int irq = platform_get_irq(pdev, 0); + irq = platform_get_irq(pdev, 0); + if (irq >= 0) { + int ret; - if (irq < 0) { - pr_err("Cannot get IRQ number for the platform\n"); - return -ENODEV; - } + arc_pmu->irq = irq; - arc_pmu->irq = irq; + /* intc map function ensures irq_set_percpu_devid() called */ + ret = request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", + this_cpu_ptr(&arc_pmu_cpu)); - /* intc map function ensures irq_set_percpu_devid() called */ - request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", - this_cpu_ptr(&arc_pmu_cpu)); + if (!ret) + on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); + else + irq = -1; + } - on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); + } - } else + if (irq == -1) arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; - return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW); + /* + * perf parser doesn't really like '-' symbol in events name, so let's + * use '_' in arc pct name as it goes to kernel PMU event prefix. + */ + return perf_pmu_register(&arc_pmu->pmu, "arc_pct", PERF_TYPE_RAW); } -#ifdef CONFIG_OF static const struct of_device_id arc_pmu_match[] = { { .compatible = "snps,arc700-pct" }, { .compatible = "snps,archs-pct" }, {}, }; MODULE_DEVICE_TABLE(of, arc_pmu_match); -#endif static struct platform_driver arc_pmu_driver = { .driver = { diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 641c364fc232..8166d0908713 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Amit Bhor, Kanika Nema: Codito Technologies 2004 */ @@ -23,6 +20,8 @@ #include <linux/elf.h> #include <linux/tick.h> +#include <asm/fpu.h> + SYSCALL_DEFINE1(arc_settls, void *, user_tls_data_ptr) { task_thread_info(current)->thr_ptr = (unsigned int)user_tls_data_ptr; @@ -44,21 +43,21 @@ SYSCALL_DEFINE0(arc_gettls) return task_thread_info(current)->thr_ptr; } -SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) +SYSCALL_DEFINE3(arc_usr_cmpxchg, int __user *, uaddr, int, expected, int, new) { struct pt_regs *regs = current_pt_regs(); u32 uval; int ret; /* - * This is only for old cores lacking LLOCK/SCOND, which by defintion + * This is only for old cores lacking LLOCK/SCOND, which by definition * can't possibly be SMP. Thus doesn't need to be SMP safe. * And this also helps reduce the overhead for serializing in * the UP case */ WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP)); - /* Z indicates to userspace if operation succeded */ + /* Z indicates to userspace if operation succeeded */ regs->status32 &= ~STATUS_Z_MASK; ret = access_ok(uaddr, sizeof(*uaddr)); @@ -91,16 +90,16 @@ fault: if (unlikely(ret != -EFAULT)) goto fail; - down_read(¤t->mm->mmap_sem); - ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr, + mmap_read_lock(current->mm); + ret = fixup_user_fault(current->mm, (unsigned long) uaddr, FAULT_FLAG_WRITE, NULL); - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (likely(!ret)) goto again; fail: - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return ret; } @@ -108,32 +107,24 @@ fail: void arch_cpu_idle(void) { - /* Re-enable interrupts <= default irq priority before commiting SLEEP */ + /* Re-enable interrupts <= default irq priority before committing SLEEP */ const unsigned int arg = 0x10 | ARCV2_IRQ_DEF_PRIO; __asm__ __volatile__( "sleep %0 \n" : :"I"(arg)); /* can't be "r" has to be embedded const */ -} -#elif defined(CONFIG_EZNPS_MTM_EXT) /* ARC700 variant in NPS */ - -void arch_cpu_idle(void) -{ - /* only the calling HW thread needs to sleep */ - __asm__ __volatile__( - ".word %0 \n" - : - :"i"(CTOP_INST_HWSCHD_WFT_IE12)); + raw_local_irq_disable(); } #else /* ARC700 */ void arch_cpu_idle(void) { - /* sleep, but enable both set E1/E2 (levels of interrutps) before committing */ + /* sleep, but enable both set E1/E2 (levels of interrupts) before committing */ __asm__ __volatile__("sleep 0x3 \n"); + raw_local_irq_disable(); } #endif @@ -150,7 +141,7 @@ asmlinkage void ret_from_fork(void); * | unused | * | | * ------------------ - * | r25 | <==== top of Stack (thread.ksp) + * | r25 | <==== top of Stack (thread_info.ksp) * ~ ~ * | --to-- | (CALLEE Regs of kernel mode) * | r13 | @@ -171,13 +162,13 @@ asmlinkage void ret_from_fork(void); * | SP | * | orig_r0 | * | event/ECR | - * | user_r25 | * ------------------ <===== END of PAGE */ -int copy_thread(unsigned long clone_flags, - unsigned long usp, unsigned long kthread_arg, - struct task_struct *p) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + u64 clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long tls = args->tls; struct pt_regs *c_regs; /* child's pt_regs */ unsigned long *childksp; /* to unwind out of __switch_to() */ struct callee_regs *c_callee; /* child's callee regs */ @@ -190,24 +181,24 @@ int copy_thread(unsigned long clone_flags, c_callee = ((struct callee_regs *)childksp) - 1; /* - * __switch_to() uses thread.ksp to start unwinding stack + * __switch_to() uses thread_info.ksp to start unwinding stack * For kernel threads we don't need to create callee regs, the * stack layout nevertheless needs to remain the same. * Also, since __switch_to anyways unwinds callee regs, we use * this to populate kernel thread entry-pt/args into callee regs, * so that ret_from_kernel_thread() becomes simpler. */ - p->thread.ksp = (unsigned long)c_callee; /* THREAD_KSP */ + task_thread_info(p)->ksp = (unsigned long)c_callee; /* THREAD_INFO_KSP */ /* __switch_to expects FP(0), BLINK(return addr) at top */ childksp[0] = 0; /* fp */ childksp[1] = (unsigned long)ret_from_fork; /* blink */ - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(args->fn)) { memset(c_regs, 0, sizeof(struct pt_regs)); - c_callee->r13 = kthread_arg; - c_callee->r14 = usp; /* function */ + c_callee->r13 = (unsigned long)args->fn_arg; + c_callee->r14 = (unsigned long)args->fn; return 0; } @@ -234,7 +225,7 @@ int copy_thread(unsigned long clone_flags, * set task's userland tls data ptr from 4th arg * clone C-lib call is difft from clone sys-call */ - task_thread_info(p)->thr_ptr = regs->r3; + task_thread_info(p)->thr_ptr = tls; } else { /* Normal fork case: set parent's TLS ptr in child */ task_thread_info(p)->thr_ptr = @@ -251,23 +242,13 @@ int copy_thread(unsigned long clone_flags, */ c_callee->r25 = task_thread_info(p)->thr_ptr; -#ifdef CONFIG_ARC_CURR_IN_REG - /* - * setup usermode thread pointer #2: - * however for this special use of r25 in kernel, __switch_to() sets - * r25 for kernel needs and only in the final return path is usermode - * r25 setup, from pt_regs->user_r25. So set that up as well - */ - c_regs->user_r25 = c_callee->r25; -#endif - return 0; } /* * Do necessary setup to start up a new user task */ -void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp) +void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long usp) { regs->sp = usp; regs->ret = pc; @@ -279,9 +260,7 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp) */ regs->status32 = STATUS_U_MASK | STATUS_L_MASK | ISA_INIT_STATUS_BITS; -#ifdef CONFIG_EZNPS_MTM_EXT - regs->eflags = 0; -#endif + fpu_init_task(regs); /* bogus seed values for debugging */ regs->lp_start = 0x10; @@ -295,11 +274,6 @@ void flush_thread(void) { } -int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) -{ - return 0; -} - int elf_check_arch(const struct elf32_hdr *x) { unsigned int eflags; @@ -313,7 +287,7 @@ int elf_check_arch(const struct elf32_hdr *x) eflags = x->e_flags; if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) { pr_err("ABI mismatch - you need newer toolchain\n"); - force_sigsegv(SIGSEGV, current); + force_fatal_sig(SIGSEGV); return 0; } diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c index 5ee4676f135d..cad5367b7c37 100644 --- a/arch/arc/kernel/ptrace.c +++ b/arch/arc/kernel/ptrace.c @@ -1,18 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/sched/task_stack.h> #include <linux/regset.h> #include <linux/unistd.h> #include <linux/elf.h> +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +#ifdef CONFIG_ISA_ARCOMPACT +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(bta), + REG_OFFSET_NAME(lp_start), + REG_OFFSET_NAME(lp_end), + REG_OFFSET_NAME(lp_count), + REG_OFFSET_NAME(status32), + REG_OFFSET_NAME(ret), + REG_OFFSET_NAME(blink), + REG_OFFSET_NAME(fp), + REG_OFFSET_NAME(r26), + REG_OFFSET_NAME(r12), + REG_OFFSET_NAME(r11), + REG_OFFSET_NAME(r10), + REG_OFFSET_NAME(r9), + REG_OFFSET_NAME(r8), + REG_OFFSET_NAME(r7), + REG_OFFSET_NAME(r6), + REG_OFFSET_NAME(r5), + REG_OFFSET_NAME(r4), + REG_OFFSET_NAME(r3), + REG_OFFSET_NAME(r2), + REG_OFFSET_NAME(r1), + REG_OFFSET_NAME(r0), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(orig_r0), + REG_OFFSET_NAME(ecr), + REG_OFFSET_END, +}; + +#else + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(orig_r0), + REG_OFFSET_NAME(ecr), + REG_OFFSET_NAME(bta), + REG_OFFSET_NAME(r26), + REG_OFFSET_NAME(fp), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(r12), + REG_OFFSET_NAME(r30), +#ifdef CONFIG_ARC_HAS_ACCL_REGS + REG_OFFSET_NAME(r58), + REG_OFFSET_NAME(r59), +#endif +#ifdef CONFIG_ARC_DSP_SAVE_RESTORE_REGS + REG_OFFSET_NAME(DSP_CTRL), +#endif + REG_OFFSET_NAME(r0), + REG_OFFSET_NAME(r1), + REG_OFFSET_NAME(r2), + REG_OFFSET_NAME(r3), + REG_OFFSET_NAME(r4), + REG_OFFSET_NAME(r5), + REG_OFFSET_NAME(r6), + REG_OFFSET_NAME(r7), + REG_OFFSET_NAME(r8), + REG_OFFSET_NAME(r9), + REG_OFFSET_NAME(r10), + REG_OFFSET_NAME(r11), + REG_OFFSET_NAME(blink), + REG_OFFSET_NAME(lp_end), + REG_OFFSET_NAME(lp_start), + REG_OFFSET_NAME(lp_count), + REG_OFFSET_NAME(ei), + REG_OFFSET_NAME(ldi), + REG_OFFSET_NAME(jli), + REG_OFFSET_NAME(ret), + REG_OFFSET_NAME(status32), + REG_OFFSET_END, +}; +#endif + static struct callee_regs *task_callee_regs(struct task_struct *tsk) { struct callee_regs *tmp = (struct callee_regs *)tsk->thread.callee_reg; @@ -21,88 +101,61 @@ static struct callee_regs *task_callee_regs(struct task_struct *tsk) static int genregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + struct membuf to) { const struct pt_regs *ptregs = task_pt_regs(target); const struct callee_regs *cregs = task_callee_regs(target); - int ret = 0; unsigned int stop_pc_val; -#define REG_O_CHUNK(START, END, PTR) \ - if (!ret) \ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, PTR, \ - offsetof(struct user_regs_struct, START), \ - offsetof(struct user_regs_struct, END)); - -#define REG_O_ONE(LOC, PTR) \ - if (!ret) \ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, PTR, \ - offsetof(struct user_regs_struct, LOC), \ - offsetof(struct user_regs_struct, LOC) + 4); - -#define REG_O_ZERO(LOC) \ - if (!ret) \ - ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, \ - offsetof(struct user_regs_struct, LOC), \ - offsetof(struct user_regs_struct, LOC) + 4); - - REG_O_ZERO(pad); - REG_O_ONE(scratch.bta, &ptregs->bta); - REG_O_ONE(scratch.lp_start, &ptregs->lp_start); - REG_O_ONE(scratch.lp_end, &ptregs->lp_end); - REG_O_ONE(scratch.lp_count, &ptregs->lp_count); - REG_O_ONE(scratch.status32, &ptregs->status32); - REG_O_ONE(scratch.ret, &ptregs->ret); - REG_O_ONE(scratch.blink, &ptregs->blink); - REG_O_ONE(scratch.fp, &ptregs->fp); - REG_O_ONE(scratch.gp, &ptregs->r26); - REG_O_ONE(scratch.r12, &ptregs->r12); - REG_O_ONE(scratch.r11, &ptregs->r11); - REG_O_ONE(scratch.r10, &ptregs->r10); - REG_O_ONE(scratch.r9, &ptregs->r9); - REG_O_ONE(scratch.r8, &ptregs->r8); - REG_O_ONE(scratch.r7, &ptregs->r7); - REG_O_ONE(scratch.r6, &ptregs->r6); - REG_O_ONE(scratch.r5, &ptregs->r5); - REG_O_ONE(scratch.r4, &ptregs->r4); - REG_O_ONE(scratch.r3, &ptregs->r3); - REG_O_ONE(scratch.r2, &ptregs->r2); - REG_O_ONE(scratch.r1, &ptregs->r1); - REG_O_ONE(scratch.r0, &ptregs->r0); - REG_O_ONE(scratch.sp, &ptregs->sp); - - REG_O_ZERO(pad2); - - REG_O_ONE(callee.r25, &cregs->r25); - REG_O_ONE(callee.r24, &cregs->r24); - REG_O_ONE(callee.r23, &cregs->r23); - REG_O_ONE(callee.r22, &cregs->r22); - REG_O_ONE(callee.r21, &cregs->r21); - REG_O_ONE(callee.r20, &cregs->r20); - REG_O_ONE(callee.r19, &cregs->r19); - REG_O_ONE(callee.r18, &cregs->r18); - REG_O_ONE(callee.r17, &cregs->r17); - REG_O_ONE(callee.r16, &cregs->r16); - REG_O_ONE(callee.r15, &cregs->r15); - REG_O_ONE(callee.r14, &cregs->r14); - REG_O_ONE(callee.r13, &cregs->r13); - - REG_O_ONE(efa, &target->thread.fault_address); - - if (!ret) { - if (in_brkpt_trap(ptregs)) { - stop_pc_val = target->thread.fault_address; - pr_debug("\t\tstop_pc (brk-pt)\n"); - } else { - stop_pc_val = ptregs->ret; - pr_debug("\t\tstop_pc (others)\n"); - } - - REG_O_ONE(stop_pc, &stop_pc_val); + membuf_zero(&to, 4); // pad + membuf_store(&to, ptregs->bta); + membuf_store(&to, ptregs->lp_start); + membuf_store(&to, ptregs->lp_end); + membuf_store(&to, ptregs->lp_count); + membuf_store(&to, ptregs->status32); + membuf_store(&to, ptregs->ret); + membuf_store(&to, ptregs->blink); + membuf_store(&to, ptregs->fp); + membuf_store(&to, ptregs->r26); // gp + membuf_store(&to, ptregs->r12); + membuf_store(&to, ptregs->r11); + membuf_store(&to, ptregs->r10); + membuf_store(&to, ptregs->r9); + membuf_store(&to, ptregs->r8); + membuf_store(&to, ptregs->r7); + membuf_store(&to, ptregs->r6); + membuf_store(&to, ptregs->r5); + membuf_store(&to, ptregs->r4); + membuf_store(&to, ptregs->r3); + membuf_store(&to, ptregs->r2); + membuf_store(&to, ptregs->r1); + membuf_store(&to, ptregs->r0); + membuf_store(&to, ptregs->sp); + membuf_zero(&to, 4); // pad2 + membuf_store(&to, cregs->r25); + membuf_store(&to, cregs->r24); + membuf_store(&to, cregs->r23); + membuf_store(&to, cregs->r22); + membuf_store(&to, cregs->r21); + membuf_store(&to, cregs->r20); + membuf_store(&to, cregs->r19); + membuf_store(&to, cregs->r18); + membuf_store(&to, cregs->r17); + membuf_store(&to, cregs->r16); + membuf_store(&to, cregs->r15); + membuf_store(&to, cregs->r14); + membuf_store(&to, cregs->r13); + membuf_store(&to, target->thread.fault_address); // efa + + if (in_brkpt_trap(ptregs)) { + stop_pc_val = target->thread.fault_address; + pr_debug("\t\tstop_pc (brk-pt)\n"); + } else { + stop_pc_val = ptregs->ret; + pr_debug("\t\tstop_pc (others)\n"); } - return ret; + return membuf_store(&to, stop_pc_val); // stop_pc } static int genregs_set(struct task_struct *target, @@ -130,7 +183,7 @@ static int genregs_set(struct task_struct *target, #define REG_IGNORE_ONE(LOC) \ if (!ret) \ - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, \ + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, \ offsetof(struct user_regs_struct, LOC), \ offsetof(struct user_regs_struct, LOC) + 4); @@ -187,25 +240,20 @@ static int genregs_set(struct task_struct *target, #ifdef CONFIG_ISA_ARCV2 static int arcv2regs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) + struct membuf to) { const struct pt_regs *regs = task_pt_regs(target); - int ret, copy_sz; if (IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS)) - copy_sz = sizeof(struct user_regs_arcv2); - else - copy_sz = 4; /* r30 only */ + /* + * itemized copy not needed like above as layout of regs (r30,r58,r59) + * is exactly same in kernel (pt_regs) and userspace (user_regs_arcv2) + */ + return membuf_write(&to, ®s->r30, sizeof(struct user_regs_arcv2)); - /* - * itemized copy not needed like above as layout of regs (r30,r58,r59) - * is exactly same in kernel (pt_regs) and userspace (user_regs_arcv2) - */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, ®s->r30, - 0, copy_sz); - return ret; + membuf_write(&to, ®s->r30, 4); /* r30 only */ + return membuf_zero(&to, sizeof(struct user_regs_arcv2) - 4); } static int arcv2regs_set(struct task_struct *target, @@ -236,27 +284,27 @@ enum arc_getset { static const struct user_regset arc_regsets[] = { [REGSET_CMN] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(unsigned long), .align = sizeof(unsigned long), - .get = genregs_get, + .regset_get = genregs_get, .set = genregs_set, }, #ifdef CONFIG_ISA_ARCV2 [REGSET_ARCV2] = { - .core_note_type = NT_ARC_V2, + USER_REGSET_NOTE_TYPE(ARC_V2), .n = ELF_ARCV2REG, .size = sizeof(unsigned long), .align = sizeof(unsigned long), - .get = arcv2regs_get, + .regset_get = arcv2regs_get, .set = arcv2regs_set, }, #endif }; static const struct user_regset_view user_arc_view = { - .name = UTS_MACHINE, + .name = "arc", .e_machine = EM_ARC_INUSE, .regsets = arc_regsets, .n = ARRAY_SIZE(arc_regsets) @@ -291,15 +339,63 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -asmlinkage int syscall_trace_entry(struct pt_regs *regs) +asmlinkage int syscall_trace_enter(struct pt_regs *regs) { - if (tracehook_report_syscall_entry(regs)) - return ULONG_MAX; + if (test_thread_flag(TIF_SYSCALL_TRACE)) + if (ptrace_report_syscall_entry(regs)) + return ULONG_MAX; + +#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + trace_sys_enter(regs, syscall_get_nr(current, regs)); +#endif return regs->r8; } asmlinkage void syscall_trace_exit(struct pt_regs *regs) { - tracehook_report_syscall_exit(regs, 0); + if (test_thread_flag(TIF_SYSCALL_TRACE)) + ptrace_report_syscall_exit(regs, 0); + +#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + trace_sys_exit(regs, regs_return_value(regs)); +#endif +} + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +const char *regs_query_register_name(unsigned int offset) +{ + const struct pt_regs_offset *roff; + for (roff = regoffset_table; roff->name != NULL; roff++) + if (roff->offset == offset) + return roff->name; + return NULL; +} + +bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return (addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)); +} + +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; } diff --git a/arch/arc/kernel/reset.c b/arch/arc/kernel/reset.c index 2768fa1e39b9..fd6c3eb930ba 100644 --- a/arch/arc/kernel/reset.c +++ b/arch/arc/kernel/reset.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/kernel.h> diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 2e018b8c2e19..7b6a9beba9db 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/seq_file.h> @@ -11,17 +8,19 @@ #include <linux/delay.h> #include <linux/root_dev.h> #include <linux/clk.h> -#include <linux/clk-provider.h> #include <linux/clocksource.h> #include <linux/console.h> #include <linux/module.h> +#include <linux/sizes.h> #include <linux/cpu.h> +#include <linux/of_clk.h> #include <linux/of_fdt.h> #include <linux/of.h> #include <linux/cache.h> #include <uapi/linux/mount.h> #include <asm/sections.h> #include <asm/arcregs.h> +#include <asm/asserts.h> #include <asm/tlb.h> #include <asm/setup.h> #include <asm/page.h> @@ -29,6 +28,8 @@ #include <asm/unwind.h> #include <asm/mach_desc.h> #include <asm/smp.h> +#include <asm/dsp-impl.h> +#include <soc/arc/mcip.h> #define FIX_PTR(x) __asm__ __volatile__(";" : "+r"(x)) @@ -36,396 +37,372 @@ unsigned int intr_to_DE_cnt; /* Part of U-boot ABI: see head.S */ int __initdata uboot_tag; +int __initdata uboot_magic; char __initdata *uboot_arg; const struct machine_desc *machine_desc; struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ -struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; +struct cpuinfo_arc { + int arcver; + unsigned int t0:1, t1:1; + struct { + unsigned long base; + unsigned int sz; + } iccm, dccm; +}; -static const struct id_to_str arc_cpu_rel[] = { -#ifdef CONFIG_ISA_ARCOMPACT - { 0x34, "R4.10"}, - { 0x35, "R4.11"}, -#else - { 0x51, "R2.0" }, - { 0x52, "R2.1" }, - { 0x53, "R3.0" }, - { 0x54, "R3.10a" }, -#endif - { 0x00, NULL } +#ifdef CONFIG_ISA_ARCV2 + +static const struct id_to_str arc_hs_rel[] = { + /* ID.ARCVER, Release */ + { 0x51, "R2.0" }, + { 0x52, "R2.1" }, + { 0x53, "R3.0" }, }; -static const struct id_to_str arc_cpu_nm[] = { -#ifdef CONFIG_ISA_ARCOMPACT - { 0x20, "ARC 600" }, - { 0x30, "ARC 770" }, /* 750 identified seperately */ -#else - { 0x40, "ARC EM" }, - { 0x50, "ARC HS38" }, - { 0x54, "ARC HS48" }, -#endif - { 0x00, "Unknown" } +static const struct id_to_str arc_hs_ver54_rel[] = { + /* UARCH.MAJOR, Release */ + { 0, "R3.10a"}, + { 1, "R3.50a"}, + { 2, "R3.60a"}, + { 3, "R4.00a"}, + { 0xFF, NULL } }; +#endif -static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu) +static int +arcompact_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) { - if (is_isa_arcompact()) { - struct bcr_iccm_arcompact iccm; - struct bcr_dccm_arcompact dccm; + int n = 0; +#ifdef CONFIG_ISA_ARCOMPACT + char *cpu_nm, *isa_nm = "ARCompact"; + struct bcr_fp_arcompact fpu_sp, fpu_dp; + int atomic = 0, be, present; + int bpu_full, bpu_cache, bpu_pred; + struct bcr_bpu_arcompact bpu; + struct bcr_iccm_arcompact iccm; + struct bcr_dccm_arcompact dccm; + struct bcr_generic isa; - READ_BCR(ARC_REG_ICCM_BUILD, iccm); - if (iccm.ver) { - cpu->iccm.sz = 4096 << iccm.sz; /* 8K to 512K */ - cpu->iccm.base_addr = iccm.base << 16; - } + READ_BCR(ARC_REG_ISA_CFG_BCR, isa); - READ_BCR(ARC_REG_DCCM_BUILD, dccm); - if (dccm.ver) { - unsigned long base; - cpu->dccm.sz = 2048 << dccm.sz; /* 2K to 256K */ + if (!isa.ver) /* ISA BCR absent, use Kconfig info */ + atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); + else { + /* ARC700_BUILD only has 2 bits of isa info */ + atomic = isa.info & 1; + } - base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD); - cpu->dccm.base_addr = base & ~0xF; - } - } else { - struct bcr_iccm_arcv2 iccm; - struct bcr_dccm_arcv2 dccm; - unsigned long region; - - READ_BCR(ARC_REG_ICCM_BUILD, iccm); - if (iccm.ver) { - cpu->iccm.sz = 256 << iccm.sz00; /* 512B to 16M */ - if (iccm.sz00 == 0xF && iccm.sz01 > 0) - cpu->iccm.sz <<= iccm.sz01; - - region = read_aux_reg(ARC_REG_AUX_ICCM); - cpu->iccm.base_addr = region & 0xF0000000; - } + be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); - READ_BCR(ARC_REG_DCCM_BUILD, dccm); - if (dccm.ver) { - cpu->dccm.sz = 256 << dccm.sz0; - if (dccm.sz0 == 0xF && dccm.sz1 > 0) - cpu->dccm.sz <<= dccm.sz1; + if (info->arcver < 0x34) + cpu_nm = "ARC750"; + else + cpu_nm = "ARC770"; - region = read_aux_reg(ARC_REG_AUX_DCCM); - cpu->dccm.base_addr = region & 0xF0000000; - } - } -} + n += scnprintf(buf + n, len - n, "processor [%d]\t: %s (%s ISA) %s%s%s\n", + c, cpu_nm, isa_nm, + IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC), + IS_AVAIL1(be, "[Big-Endian]")); -static void read_arc_build_cfg_regs(void) -{ - struct bcr_timer timer; - struct bcr_generic bcr; - struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; - const struct id_to_str *tbl; - struct bcr_isa_arcv2 isa; - - FIX_PTR(cpu); + READ_BCR(ARC_REG_FP_BCR, fpu_sp); + READ_BCR(ARC_REG_DPFP_BCR, fpu_dp); - READ_BCR(AUX_IDENTITY, cpu->core); + if (fpu_sp.ver | fpu_dp.ver) + n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n", + IS_AVAIL1(fpu_sp.ver, "SP "), + IS_AVAIL1(fpu_dp.ver, "DP ")); - for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) { - if (cpu->core.family == tbl->id) { - cpu->details = tbl->str; - break; - } - } + READ_BCR(ARC_REG_BPU_BCR, bpu); + bpu_full = bpu.fam ? 1 : 0; + bpu_cache = 256 << (bpu.ent - 1); + bpu_pred = 256 << (bpu.ent - 1); - for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) { - if ((cpu->core.family & 0xF4) == tbl->id) - break; + n += scnprintf(buf + n, len - n, + "BPU\t\t: %s%s match, cache:%d, Predict Table:%d\n", + IS_AVAIL1(bpu_full, "full"), + IS_AVAIL1(!bpu_full, "partial"), + bpu_cache, bpu_pred); + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + info->iccm.sz = 4096 << iccm.sz; /* 8K to 512K */ + info->iccm.base = iccm.base << 16; } - cpu->name = tbl->str; - READ_BCR(ARC_REG_TIMERS_BCR, timer); - cpu->extn.timer0 = timer.t0; - cpu->extn.timer1 = timer.t1; - cpu->extn.rtc = timer.rtc; - - cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE); + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + unsigned long base; + info->dccm.sz = 2048 << dccm.sz; /* 2K to 256K */ - READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy); + base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD); + info->dccm.base = base & ~0xF; + } - cpu->extn.norm = read_aux_reg(ARC_REG_NORM_BCR) > 1 ? 1 : 0; /* 2,3 */ - cpu->extn.barrel = read_aux_reg(ARC_REG_BARREL_BCR) > 1 ? 1 : 0; /* 2,3 */ - cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0; /* 1,3 */ - cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0; - cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */ - cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 : - IS_ENABLED(CONFIG_ARC_HAS_SWAPE); + /* ARCompact ISA specific sanity checks */ + present = fpu_dp.ver; /* SP has no arch visible regs */ + CHK_OPT_STRICT(CONFIG_ARC_FPU_SAVE_RESTORE, present); +#endif + return n; - READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem); +} - /* Read CCM BCRs for boot reporting even if not enabled in Kconfig */ - read_decode_ccm_bcr(cpu); +static int arcv2_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) +{ + int n = 0; +#ifdef CONFIG_ISA_ARCV2 + const char *release = "", *cpu_nm = "HS38", *isa_nm = "ARCv2"; + int dual_issue = 0, dual_enb = 0, mpy_opt, present; + int bpu_full, bpu_cache, bpu_pred, bpu_ret_stk; + char mpy_nm[16], lpb_nm[32]; + struct bcr_isa_arcv2 isa; + struct bcr_mpy mpy; + struct bcr_fp_arcv2 fpu; + struct bcr_bpu_arcv2 bpu; + struct bcr_lpb lpb; + struct bcr_iccm_arcv2 iccm; + struct bcr_dccm_arcv2 dccm; + struct bcr_erp erp; - read_decode_mmu_bcr(); - read_decode_cache_bcr(); + /* + * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until + * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent + * releases only update it. + */ - if (is_isa_arcompact()) { - struct bcr_fp_arcompact sp, dp; - struct bcr_bpu_arcompact bpu; - - READ_BCR(ARC_REG_FP_BCR, sp); - READ_BCR(ARC_REG_DPFP_BCR, dp); - cpu->extn.fpu_sp = sp.ver ? 1 : 0; - cpu->extn.fpu_dp = dp.ver ? 1 : 0; - - READ_BCR(ARC_REG_BPU_BCR, bpu); - cpu->bpu.ver = bpu.ver; - cpu->bpu.full = bpu.fam ? 1 : 0; - if (bpu.ent) { - cpu->bpu.num_cache = 256 << (bpu.ent - 1); - cpu->bpu.num_pred = 256 << (bpu.ent - 1); - } + if (info->arcver > 0x50 && info->arcver <= 0x53) { + release = arc_hs_rel[info->arcver - 0x51].str; } else { - struct bcr_fp_arcv2 spdp; - struct bcr_bpu_arcv2 bpu; + const struct id_to_str *tbl; + struct bcr_uarch_build uarch; - READ_BCR(ARC_REG_FP_V2_BCR, spdp); - cpu->extn.fpu_sp = spdp.sp ? 1 : 0; - cpu->extn.fpu_dp = spdp.dp ? 1 : 0; + READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch); - READ_BCR(ARC_REG_BPU_BCR, bpu); - cpu->bpu.ver = bpu.ver; - cpu->bpu.full = bpu.ft; - cpu->bpu.num_cache = 256 << bpu.bce; - cpu->bpu.num_pred = 2048 << bpu.pte; - - if (cpu->core.family >= 0x54) { + for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) { + if (uarch.maj == tbl->id) { + release = tbl->str; + break; + } + } + if (uarch.prod == 4) { unsigned int exec_ctrl; + cpu_nm = "HS48"; + dual_issue = 1; + /* if dual issue hardware, is it enabled ? */ READ_BCR(AUX_EXEC_CTRL, exec_ctrl); - cpu->extn.dual_enb = !(exec_ctrl & 1); - - /* dual issue always present for this core */ - cpu->extn.dual = 1; + dual_enb = !(exec_ctrl & 1); } } - READ_BCR(ARC_REG_AP_BCR, bcr); - cpu->extn.ap = bcr.ver ? 1 : 0; - - READ_BCR(ARC_REG_SMART_BCR, bcr); - cpu->extn.smart = bcr.ver ? 1 : 0; - - READ_BCR(ARC_REG_RTT_BCR, bcr); - cpu->extn.rtt = bcr.ver ? 1 : 0; - - cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt; - READ_BCR(ARC_REG_ISA_CFG_BCR, isa); - /* some hacks for lack of feature BCR info in old ARC700 cores */ - if (is_isa_arcompact()) { - if (!isa.ver) /* ISA BCR absent, use Kconfig info */ - cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); - else { - /* ARC700_BUILD only has 2 bits of isa info */ - struct bcr_generic bcr = *(struct bcr_generic *)&isa; - cpu->isa.atomic = bcr.info & 1; - } - - cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); - - /* there's no direct way to distinguish 750 vs. 770 */ - if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3)) - cpu->name = "ARC750"; - } else { - cpu->isa = isa; + n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n", + c, cpu_nm, release, isa_nm, + IS_AVAIL1(isa.be, "[Big-Endian]"), + IS_AVAIL3(dual_issue, dual_enb, " Dual-Issue ")); + + READ_BCR(ARC_REG_MPY_BCR, mpy); + mpy_opt = 2; /* stock MPY/MPYH */ + if (mpy.dsp) /* OPT 7-9 */ + mpy_opt = mpy.dsp + 6; + + scnprintf(mpy_nm, 16, "mpy[opt %d] ", mpy_opt); + + READ_BCR(ARC_REG_FP_V2_BCR, fpu); + + n += scnprintf(buf + n, len - n, "ISA Extn\t: %s%s%s%s%s%s%s%s%s%s%s\n", + IS_AVAIL2(isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC), + IS_AVAIL2(isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64), + IS_AVAIL2(isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS), + IS_AVAIL1(mpy.ver, mpy_nm), + IS_AVAIL1(isa.div_rem, "div_rem "), + IS_AVAIL1((fpu.sp | fpu.dp), " FPU:"), + IS_AVAIL1(fpu.sp, " sp"), + IS_AVAIL1(fpu.dp, " dp")); + + READ_BCR(ARC_REG_BPU_BCR, bpu); + bpu_full = bpu.ft; + bpu_cache = 256 << bpu.bce; + bpu_pred = 2048 << bpu.pte; + bpu_ret_stk = 4 << bpu.rse; + + READ_BCR(ARC_REG_LPB_BUILD, lpb); + if (lpb.ver) { + unsigned int ctl; + ctl = read_aux_reg(ARC_REG_LPB_CTRL); + + scnprintf(lpb_nm, sizeof(lpb_nm), " Loop Buffer:%d %s", + lpb.entries, IS_DISABLED_RUN(!ctl)); } -} - -static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) -{ - struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; - struct bcr_identity *core = &cpu->core; - int i, n = 0, ua = 0; - - FIX_PTR(cpu); n += scnprintf(buf + n, len - n, - "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n", - core->family, core->cpu_id, core->chip_id); - - n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n", - cpu_id, cpu->name, cpu->details, - is_isa_arcompact() ? "ARCompact" : "ARCv2", - IS_AVAIL1(cpu->isa.be, "[Big-Endian]"), - IS_AVAIL3(cpu->extn.dual, cpu->extn.dual_enb, " Dual-Issue ")); - - n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ", - IS_AVAIL1(cpu->extn.timer0, "Timer0 "), - IS_AVAIL1(cpu->extn.timer1, "Timer1 "), - IS_AVAIL2(cpu->extn.rtc, "RTC [UP 64-bit] ", CONFIG_ARC_TIMERS_64BIT), - IS_AVAIL2(cpu->extn.gfrc, "GFRC [SMP 64-bit] ", CONFIG_ARC_TIMERS_64BIT)); - -#ifdef __ARC_UNALIGNED__ - ua = 1; -#endif - n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s%s", - IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC), - IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64), - IS_AVAIL1(cpu->isa.unalign, "unalign "), IS_USED_RUN(ua)); - - if (i) - n += scnprintf(buf + n, len - n, "\n\t\t: "); - - if (cpu->extn_mpy.ver) { - if (cpu->extn_mpy.ver <= 0x2) { /* ARCompact */ - n += scnprintf(buf + n, len - n, "mpy "); - } else { - int opt = 2; /* stock MPY/MPYH */ - - if (cpu->extn_mpy.dsp) /* OPT 7-9 */ - opt = cpu->extn_mpy.dsp + 6; - - n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt); - } + "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d%s\n", + IS_AVAIL1(bpu_full, "full"), + IS_AVAIL1(!bpu_full, "partial"), + bpu_cache, bpu_pred, bpu_ret_stk, + lpb_nm); + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + unsigned long base; + info->iccm.sz = 256 << iccm.sz00; /* 512B to 16M */ + if (iccm.sz00 == 0xF && iccm.sz01 > 0) + info->iccm.sz <<= iccm.sz01; + base = read_aux_reg(ARC_REG_AUX_ICCM); + info->iccm.base = base & 0xF0000000; } - n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", - IS_AVAIL1(cpu->isa.div_rem, "div_rem "), - IS_AVAIL1(cpu->extn.norm, "norm "), - IS_AVAIL1(cpu->extn.barrel, "barrel-shift "), - IS_AVAIL1(cpu->extn.swap, "swap "), - IS_AVAIL1(cpu->extn.minmax, "minmax "), - IS_AVAIL1(cpu->extn.crc, "crc "), - IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE)); + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + unsigned long base; + info->dccm.sz = 256 << dccm.sz0; + if (dccm.sz0 == 0xF && dccm.sz1 > 0) + info->dccm.sz <<= dccm.sz1; + base = read_aux_reg(ARC_REG_AUX_DCCM); + info->dccm.base = base & 0xF0000000; + } - if (cpu->bpu.ver) - n += scnprintf(buf + n, len - n, - "BPU\t\t: %s%s match, cache:%d, Predict Table:%d", - IS_AVAIL1(cpu->bpu.full, "full"), - IS_AVAIL1(!cpu->bpu.full, "partial"), - cpu->bpu.num_cache, cpu->bpu.num_pred); - - if (is_isa_arcv2()) { - struct bcr_lpb lpb; - - READ_BCR(ARC_REG_LPB_BUILD, lpb); - if (lpb.ver) { - unsigned int ctl; - ctl = read_aux_reg(ARC_REG_LPB_CTRL); - - n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s", - lpb.entries, - IS_DISABLED_RUN(!ctl)); - } + /* Error Protection: ECC/Parity */ + READ_BCR(ARC_REG_ERP_BUILD, erp); + if (erp.ver) { + struct ctl_erp ctl; + READ_BCR(ARC_REG_ERP_CTRL, ctl); + /* inverted bits: 0 means enabled */ + n += scnprintf(buf + n, len - n, "Extn [ECC]\t: %s%s%s%s%s%s\n", + IS_AVAIL3(erp.ic, !ctl.dpi, "IC "), + IS_AVAIL3(erp.dc, !ctl.dpd, "DC "), + IS_AVAIL3(erp.mmu, !ctl.mpd, "MMU ")); } - n += scnprintf(buf + n, len - n, "\n"); - return buf; + /* ARCv2 ISA specific sanity checks */ + present = fpu.sp | fpu.dp | mpy.dsp; /* DSP and/or FPU */ + CHK_OPT_STRICT(CONFIG_ARC_HAS_ACCL_REGS, present); + + dsp_config_check(); +#endif + return n; } -static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) +static char *arc_cpu_mumbojumbo(int c, struct cpuinfo_arc *info, char *buf, int len) { - int n = 0; - struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; + struct bcr_identity ident; + struct bcr_timer timer; + struct bcr_generic bcr; + struct mcip_bcr mp; + struct bcr_actionpoint ap; + unsigned long vec_base; + int ap_num, ap_full, smart, rtt, n; - FIX_PTR(cpu); + memset(info, 0, sizeof(struct cpuinfo_arc)); - n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\n", cpu->vec_base); + READ_BCR(AUX_IDENTITY, ident); + info->arcver = ident.family; - if (cpu->extn.fpu_sp || cpu->extn.fpu_dp) - n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n", - IS_AVAIL1(cpu->extn.fpu_sp, "SP "), - IS_AVAIL1(cpu->extn.fpu_dp, "DP ")); + n = scnprintf(buf, len, + "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n", + ident.family, ident.cpu_id, ident.chip_id); - if (cpu->extn.debug) - n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s%s\n", - IS_AVAIL1(cpu->extn.ap, "ActionPoint "), - IS_AVAIL1(cpu->extn.smart, "smaRT "), - IS_AVAIL1(cpu->extn.rtt, "RTT ")); + if (is_isa_arcompact()) { + n += arcompact_mumbojumbo(c, info, buf + n, len - n); + } else if (is_isa_arcv2()){ + n += arcv2_mumbojumbo(c, info, buf + n, len - n); + } - if (cpu->dccm.sz || cpu->iccm.sz) - n += scnprintf(buf + n, len - n, "Extn [CCM]\t: DCCM @ %x, %d KB / ICCM: @ %x, %d KB\n", - cpu->dccm.base_addr, TO_KB(cpu->dccm.sz), - cpu->iccm.base_addr, TO_KB(cpu->iccm.sz)); + n += arc_mmu_mumbojumbo(c, buf + n, len - n); + n += arc_cache_mumbojumbo(c, buf + n, len - n); - if (is_isa_arcv2()) { + READ_BCR(ARC_REG_TIMERS_BCR, timer); + info->t0 = timer.t0; + info->t1 = timer.t1; - /* Error Protection: ECC/Parity */ - struct bcr_erp erp; - READ_BCR(ARC_REG_ERP_BUILD, erp); + READ_BCR(ARC_REG_MCIP_BCR, mp); + vec_base = read_aux_reg(AUX_INTR_VEC_BASE); - if (erp.ver) { - struct ctl_erp ctl; - READ_BCR(ARC_REG_ERP_CTRL, ctl); + n += scnprintf(buf + n, len - n, + "Timers\t\t: %s%s%s%s%s%s\nVector Table\t: %#lx\n", + IS_AVAIL1(timer.t0, "Timer0 "), + IS_AVAIL1(timer.t1, "Timer1 "), + IS_AVAIL2(timer.rtc, "RTC [UP 64-bit] ", CONFIG_ARC_TIMERS_64BIT), + IS_AVAIL2(mp.gfrc, "GFRC [SMP 64-bit] ", CONFIG_ARC_TIMERS_64BIT), + vec_base); + + READ_BCR(ARC_REG_AP_BCR, ap); + if (ap.ver) { + ap_num = 2 << ap.num; + ap_full = !ap.min; + } - /* inverted bits: 0 means enabled */ - n += scnprintf(buf + n, len - n, "Extn [ECC]\t: %s%s%s%s%s%s\n", - IS_AVAIL3(erp.ic, !ctl.dpi, "IC "), - IS_AVAIL3(erp.dc, !ctl.dpd, "DC "), - IS_AVAIL3(erp.mmu, !ctl.mpd, "MMU ")); + READ_BCR(ARC_REG_SMART_BCR, bcr); + smart = bcr.ver ? 1 : 0; + + READ_BCR(ARC_REG_RTT_BCR, bcr); + rtt = bcr.ver ? 1 : 0; + + if (ap.ver | smart | rtt) { + n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s", + IS_AVAIL1(smart, "smaRT "), + IS_AVAIL1(rtt, "RTT ")); + if (ap.ver) { + n += scnprintf(buf + n, len - n, "ActionPoint %d/%s", + ap_num, + ap_full ? "full":"min"); } + n += scnprintf(buf + n, len - n, "\n"); } - n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n", - EF_ARC_OSABI_CURRENT >> 8, - EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ? - "no-legacy-syscalls" : "64-bit data any register aligned"); + if (info->dccm.sz || info->iccm.sz) + n += scnprintf(buf + n, len - n, + "Extn [CCM]\t: DCCM @ %lx, %d KB / ICCM: @ %lx, %d KB\n", + info->dccm.base, TO_KB(info->dccm.sz), + info->iccm.base, TO_KB(info->iccm.sz)); return buf; } -static void arc_chk_core_config(void) +void chk_opt_strict(char *opt_name, bool hw_exists, bool opt_ena) { - struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; - int saved = 0, present = 0; - char *opt_nm = NULL; + if (hw_exists && !opt_ena) + pr_warn(" ! Enable %s for working apps\n", opt_name); + else if (!hw_exists && opt_ena) + panic("Disable %s, hardware NOT present\n", opt_name); +} - if (!cpu->extn.timer0) +void chk_opt_weak(char *opt_name, bool hw_exists, bool opt_ena) +{ + if (!hw_exists && opt_ena) + panic("Disable %s, hardware NOT present\n", opt_name); +} + +/* + * ISA agnostic sanity checks + */ +static void arc_chk_core_config(struct cpuinfo_arc *info) +{ + if (!info->t0) panic("Timer0 is not present!\n"); - if (!cpu->extn.timer1) + if (!info->t1) panic("Timer1 is not present!\n"); #ifdef CONFIG_ARC_HAS_DCCM /* * DCCM can be arbit placed in hardware. - * Make sure it's placement/sz matches what Linux is built with + * Make sure its placement/sz matches what Linux is built with */ - if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr) + if ((unsigned int)__arc_dccm_base != info->dccm.base) panic("Linux built with incorrect DCCM Base address\n"); - if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz) + if (CONFIG_ARC_DCCM_SZ * SZ_1K != info->dccm.sz) panic("Linux built with incorrect DCCM Size\n"); #endif #ifdef CONFIG_ARC_HAS_ICCM - if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz) + if (CONFIG_ARC_ICCM_SZ * SZ_1K != info->iccm.sz) panic("Linux built with incorrect ICCM Size\n"); #endif - - /* - * FP hardware/software config sanity - * -If hardware present, kernel needs to save/restore FPU state - * -If not, it will crash trying to save/restore the non-existant regs - */ - - if (is_isa_arcompact()) { - opt_nm = "CONFIG_ARC_FPU_SAVE_RESTORE"; - saved = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE); - - /* only DPDP checked since SP has no arch visible regs */ - present = cpu->extn.fpu_dp; - } else { - opt_nm = "CONFIG_ARC_HAS_ACCL_REGS"; - saved = IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS); - - /* Accumulator Low:High pair (r58:59) present if DSP MPY or FPU */ - present = cpu->extn_mpy.dsp | cpu->extn.fpu_sp | cpu->extn.fpu_dp; - } - - if (present && !saved) - pr_warn("Enable %s for working apps\n", opt_nm); - else if (!present && saved) - panic("Disable %s, hardware NOT present\n", opt_nm); } /* @@ -436,60 +413,100 @@ static void arc_chk_core_config(void) void setup_processor(void) { + struct cpuinfo_arc info; + int c = smp_processor_id(); char str[512]; - int cpu_id = smp_processor_id(); - read_arc_build_cfg_regs(); - arc_init_IRQ(); + pr_info("%s", arc_cpu_mumbojumbo(c, &info, str, sizeof(str))); + pr_info("%s", arc_platform_smp_cpuinfo()); - pr_info("%s", arc_cpu_mumbojumbo(cpu_id, str, sizeof(str))); + arc_chk_core_config(&info); + arc_init_IRQ(); arc_mmu_init(); arc_cache_init(); - pr_info("%s", arc_extn_mumbojumbo(cpu_id, str, sizeof(str))); - pr_info("%s", arc_platform_smp_cpuinfo()); - - arc_chk_core_config(); } -static inline int is_kernel(unsigned long addr) +static inline bool uboot_arg_invalid(unsigned long addr) { - if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) - return 1; - return 0; + /* + * Check that it is a untranslated address (although MMU is not enabled + * yet, it being a high address ensures this is not by fluke) + */ + if (addr < PAGE_OFFSET) + return true; + + /* Check that address doesn't clobber resident kernel image */ + return addr >= (unsigned long)_stext && addr <= (unsigned long)_end; } -void __init setup_arch(char **cmdline_p) +#define IGNORE_ARGS "Ignore U-boot args: " + +/* uboot_tag values for U-boot - kernel ABI revision 0; see head.S */ +#define UBOOT_TAG_NONE 0 +#define UBOOT_TAG_CMDLINE 1 +#define UBOOT_TAG_DTB 2 +/* We always pass 0 as magic from U-boot */ +#define UBOOT_MAGIC_VALUE 0 + +void __init handle_uboot_args(void) { -#ifdef CONFIG_ARC_UBOOT_SUPPORT - /* make sure that uboot passed pointer to cmdline/dtb is valid */ - if (uboot_tag && is_kernel((unsigned long)uboot_arg)) - panic("Invalid uboot arg\n"); - - /* See if u-boot passed an external Device Tree blob */ - machine_desc = setup_machine_fdt(uboot_arg); /* uboot_tag == 2 */ - if (!machine_desc) -#endif - { - /* No, so try the embedded one */ + bool use_embedded_dtb = true; + bool append_cmdline = false; + + /* check that we know this tag */ + if (uboot_tag != UBOOT_TAG_NONE && + uboot_tag != UBOOT_TAG_CMDLINE && + uboot_tag != UBOOT_TAG_DTB) { + pr_warn(IGNORE_ARGS "invalid uboot tag: '%08x'\n", uboot_tag); + goto ignore_uboot_args; + } + + if (uboot_magic != UBOOT_MAGIC_VALUE) { + pr_warn(IGNORE_ARGS "non zero uboot magic\n"); + goto ignore_uboot_args; + } + + if (uboot_tag != UBOOT_TAG_NONE && + uboot_arg_invalid((unsigned long)uboot_arg)) { + pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg); + goto ignore_uboot_args; + } + + /* see if U-boot passed an external Device Tree blob */ + if (uboot_tag == UBOOT_TAG_DTB) { + machine_desc = setup_machine_fdt((void *)uboot_arg); + + /* external Device Tree blob is invalid - use embedded one */ + use_embedded_dtb = !machine_desc; + } + + if (uboot_tag == UBOOT_TAG_CMDLINE) + append_cmdline = true; + +ignore_uboot_args: + + if (use_embedded_dtb) { machine_desc = setup_machine_fdt(__dtb_start); if (!machine_desc) panic("Embedded DT invalid\n"); + } - /* - * If we are here, it is established that @uboot_arg didn't - * point to DT blob. Instead if u-boot says it is cmdline, - * append to embedded DT cmdline. - * setup_machine_fdt() would have populated @boot_command_line - */ - if (uboot_tag == 1) { - /* Ensure a whitespace between the 2 cmdlines */ - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, uboot_arg, - COMMAND_LINE_SIZE); - } + /* + * NOTE: @boot_command_line is populated by setup_machine_fdt() so this + * append processing can only happen after. + */ + if (append_cmdline) { + /* Ensure a whitespace between the 2 cmdlines */ + strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); + strlcat(boot_command_line, uboot_arg, COMMAND_LINE_SIZE); } +} + +void __init setup_arch(char **cmdline_p) +{ + handle_uboot_args(); /* Save unparsed command line copy for /proc/cmdline */ *cmdline_p = boot_command_line; @@ -514,10 +531,6 @@ void __init setup_arch(char **cmdline_p) */ root_mountflags &= ~MS_RDONLY; -#if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif - arc_unwind_init(); } @@ -559,6 +572,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) char *str; int cpu_id = ptr_to_cpu(v); struct device *cpu_dev = get_cpu_device(cpu_id); + struct cpuinfo_arc info; struct clk *cpu_clk; unsigned long freq = 0; @@ -571,7 +585,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (!str) goto done; - seq_printf(m, arc_cpu_mumbojumbo(cpu_id, str, PAGE_SIZE)); + seq_printf(m, arc_cpu_mumbojumbo(cpu_id, &info, str, PAGE_SIZE)); cpu_clk = clk_get(cpu_dev, NULL); if (IS_ERR(cpu_clk)) { @@ -588,9 +602,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) loops_per_jiffy / (500000 / HZ), (loops_per_jiffy / (5000 / HZ)) % 100); - seq_printf(m, arc_mmu_mumbojumbo(cpu_id, str, PAGE_SIZE)); - seq_printf(m, arc_cache_mumbojumbo(cpu_id, str, PAGE_SIZE)); - seq_printf(m, arc_extn_mumbojumbo(cpu_id, str, PAGE_SIZE)); seq_printf(m, arc_platform_smp_cpuinfo()); free_page((unsigned long)str); diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 1bfb7de696bd..fefa705a8638 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -1,25 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Signal Handling for ARC * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * vineetg: Jan 2010 (Restarting of timer related syscalls) * * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK) * -do_signal() supports TIF_RESTORE_SIGMASK - * -do_signal() no loner needs oldset, required by OLD sys_sigsuspend - * -sys_rt_sigsuspend() now comes from generic code, so discard arch implemen + * -do_signal() no longer needs oldset, required by OLD sys_sigsuspend + * -sys_rt_sigsuspend() now comes from generic code, so discard arch + * implementation * -sys_sigsuspend() no longer needs to fudge ptregs, hence that arg removed * -sys_sigsuspend() no longer loops for do_signal(), sets TIF_xxx and leaves * the job to do_signal() * * vineetg: July 2009 * -Modified Code to support the uClibc provided userland sigreturn stub - * to avoid kernel synthesing it on user stack at runtime, costing TLB + * to avoid kernel synthesizing it on user stack at runtime, costing TLB * probes and Cache line flushes. * * vineetg: July 2009 @@ -52,10 +50,11 @@ #include <linux/personality.h> #include <linux/uaccess.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/sched/task_stack.h> #include <asm/ucontext.h> +#include <asm/entry.h> struct rt_sigframe { struct siginfo info; @@ -64,6 +63,41 @@ struct rt_sigframe { unsigned int sigret_magic; }; +static int save_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) +{ + int err = 0; +#ifndef CONFIG_ISA_ARCOMPACT + struct user_regs_arcv2 v2abi; + + v2abi.r30 = regs->r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + v2abi.r58 = regs->r58; + v2abi.r59 = regs->r59; +#else + v2abi.r58 = v2abi.r59 = 0; +#endif + err = __copy_to_user(&mctx->v2abi, (void const *)&v2abi, sizeof(v2abi)); +#endif + return err; +} + +static int restore_arcv2_regs(struct sigcontext __user *mctx, struct pt_regs *regs) +{ + int err = 0; +#ifndef CONFIG_ISA_ARCOMPACT + struct user_regs_arcv2 v2abi; + + err = __copy_from_user(&v2abi, &mctx->v2abi, sizeof(v2abi)); + + regs->r30 = v2abi.r30; +#ifdef CONFIG_ARC_HAS_ACCL_REGS + regs->r58 = v2abi.r58; + regs->r59 = v2abi.r59; +#endif +#endif + return err; +} + static int stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sigset_t *set) @@ -97,9 +131,13 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), &uregs.scratch, sizeof(sf->uc.uc_mcontext.regs.scratch)); + + if (is_isa_arcv2()) + err |= save_arcv2_regs(&(sf->uc.uc_mcontext), regs); + err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); - return err; + return err ? -EFAULT : 0; } static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) @@ -112,8 +150,12 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) err |= __copy_from_user(&uregs.scratch, &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); + + if (is_isa_arcv2()) + err |= restore_arcv2_regs(&(sf->uc.uc_mcontext), regs); + if (err) - return err; + return -EFAULT; set_current_blocked(&set); regs->bta = uregs.scratch.bta; @@ -197,7 +239,7 @@ SYSCALL_DEFINE0(rt_sigreturn) return regs->r0; badframe: - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return 0; } @@ -262,7 +304,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->r2 = (unsigned long)&sf->uc; /* - * small optim to avoid unconditonally calling do_sigaltstack + * small optim to avoid unconditionally calling do_sigaltstack * in sigreturn path, now that we only have rt_sigreturn */ magic = MAGIC_SIGALTSTK; @@ -279,7 +321,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->ret = (unsigned long)ksig->ka.sa.sa_handler; /* - * handler returns using sigreturn stub provided already by userpsace + * handler returns using sigreturn stub provided already by userspace * If not, nuke the process right away */ if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) @@ -324,7 +366,7 @@ static void arc_restart_syscall(struct k_sigaction *ka, struct pt_regs *regs) regs->r0 = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: /* @@ -365,7 +407,7 @@ void do_signal(struct pt_regs *regs) restart_scall = in_syscall(regs) && syscall_restartable(regs); - if (get_signal(&ksig)) { + if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) { if (restart_scall) { arc_restart_syscall(&ksig.ka, regs); syscall_wont_restart(regs); /* No more restarts */ @@ -394,9 +436,9 @@ void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs) { /* - * ASM glue gaurantees that this is only called when returning to + * ASM glue guarantees that this is only called when returning to * user mode */ - if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + if (test_thread_flag(TIF_NOTIFY_RESUME)) + resume_user_mode_work(regs); } diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 21d86c36692b..b2f2c59279a6 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * RajeshwarR: Dec 11, 2007 * -- Added support for Inter Processor Interrupts * @@ -26,28 +23,22 @@ #include <linux/export.h> #include <linux/of_fdt.h> -#include <asm/processor.h> -#include <asm/setup.h> #include <asm/mach_desc.h> +#include <asm/setup.h> +#include <asm/smp.h> +#include <asm/processor.h> #ifndef CONFIG_ARC_HAS_LLSC arch_spinlock_t smp_atomic_ops_lock = __ARCH_SPIN_LOCK_UNLOCKED; -arch_spinlock_t smp_bitops_lock = __ARCH_SPIN_LOCK_UNLOCKED; EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); -EXPORT_SYMBOL_GPL(smp_bitops_lock); #endif struct plat_smp_ops __weak plat_smp_ops; -/* XXX: per cpu ? Only needed once in early seconday boot */ +/* XXX: per cpu ? Only needed once in early secondary boot */ struct task_struct *secondary_idle_tsk; -/* Called from start_kernel */ -void __init smp_prepare_boot_cpu(void) -{ -} - static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask) { unsigned long dt_root = of_get_flat_dt_root(); @@ -192,7 +183,6 @@ void start_kernel_secondary(void) pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu); local_irq_enable(); - preempt_disable(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } @@ -229,7 +219,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) } if (!cpu_online(cpu)) { - pr_info("Timeout: CPU%u FAILED to comeup !!!\n", cpu); + pr_info("Timeout: CPU%u FAILED to come up !!!\n", cpu); return -1; } @@ -238,14 +228,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) return 0; } -/* - * not supported here - */ -int setup_profiling_timer(unsigned int multiplier) -{ - return -EINVAL; -} - /*****************************************************************************/ /* Inter Processor Interrupt Handling */ /*****************************************************************************/ @@ -280,14 +262,14 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = READ_ONCE(*ipi_data_ptr); + new = old = *ipi_data_ptr; new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); /* * Call the platform specific IPI kick function, but avoid if possible: * Only do so if there's no pending msg from other concurrent sender(s). - * Otherwise, recevier will see this msg as well when it takes the + * Otherwise, receiver will see this msg as well when it takes the * IPI corresponding to that msg. This is true, even if it is already in * IPI handler, because !@old means it has not yet dequeued the msg(s) * so @new msg can be a free-loader @@ -306,7 +288,7 @@ static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg) ipi_send_msg_one(cpu, msg); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { ipi_send_msg_one(cpu, IPI_RESCHEDULE); } @@ -365,7 +347,7 @@ static inline int __do_IPI(unsigned long msg) * arch-common ISR to handle for inter-processor interrupts * Has hooks for platform specific IPI */ -irqreturn_t do_IPI(int irq, void *dev_id) +static irqreturn_t do_IPI(int irq, void *dev_id) { unsigned long pending; unsigned long __maybe_unused copy; @@ -399,7 +381,7 @@ irqreturn_t do_IPI(int irq, void *dev_id) * API called by platform code to hookup arch-common ISR to their IPI IRQ * * Note: If IPI is provided by platform (vs. say ARC MCIP), their intc setup/map - * function needs to call call irq_set_percpu_devid() for IPI IRQ, otherwise + * function needs to call irq_set_percpu_devid() for IPI IRQ, otherwise * request_percpu_irq() below will fail */ static DEFINE_PER_CPU(int, ipi_dev); diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index bf40e06f3fb8..ea99c066ef25 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * stacktrace.c : stacktracing APIs needed by rest of kernel * (wrappers over ARC dwarf based unwinder) * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * vineetg: aug 2009 * -Implemented CONFIG_STACKTRACE APIs, primarily save_stack_trace_tsk( ) * for displaying task's kernel mode call stack in /proc/<pid>/stack @@ -18,7 +15,7 @@ * = specifics of data structs where trace is saved(CONFIG_STACKTRACE etc) * * vineetg: March 2009 - * -Implemented correct versions of thread_saved_pc() and get_wchan() + * -Implemented correct versions of thread_saved_pc() and __get_wchan() * * rajeshwarr: 2008 * -Initial implementation @@ -32,6 +29,7 @@ #include <asm/arcregs.h> #include <asm/unwind.h> +#include <asm/stacktrace.h> #include <asm/switch_to.h> /*------------------------------------------------------------------------- @@ -41,15 +39,27 @@ #ifdef CONFIG_ARC_DW2_UNWIND -static void seed_unwind_frame_info(struct task_struct *tsk, - struct pt_regs *regs, - struct unwind_frame_info *frame_info) +static int +seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, + struct unwind_frame_info *frame_info) { - /* - * synchronous unwinding (e.g. dump_stack) - * - uses current values of SP and friends - */ - if (tsk == NULL && regs == NULL) { + if (regs) { + /* + * Asynchronous unwinding of intr/exception + * - Just uses the pt_regs passed + */ + frame_info->task = tsk; + + frame_info->regs.r27 = regs->fp; + frame_info->regs.r28 = regs->sp; + frame_info->regs.r31 = regs->blink; + frame_info->regs.r63 = regs->ret; + frame_info->call_frame = 0; + } else if (tsk == NULL || tsk == current) { + /* + * synchronous unwinding (e.g. dump_stack) + * - uses current values of SP and friends + */ unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -66,13 +76,17 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r31 = blink; frame_info->regs.r63 = ret; frame_info->call_frame = 0; - } else if (regs == NULL) { + } else { /* - * Asynchronous unwinding of sleeping task - * - Gets SP etc from task's pt_regs (saved bottom of kernel - * mode stack of task) + * Asynchronous unwinding of a likely sleeping task + * - first ensure it is actually sleeping + * - if so, it will be in __switch_to, kernel mode SP of task + * is safe-kept and BLINK at a well known location in there */ + if (task_is_running(tsk)) + return -1; + frame_info->task = tsk; frame_info->regs.r27 = TSK_K_FP(tsk); @@ -93,19 +107,8 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r28 += 60; frame_info->call_frame = 0; - } else { - /* - * Asynchronous unwinding of intr/exception - * - Just uses the pt_regs passed - */ - frame_info->task = tsk; - - frame_info->regs.r27 = regs->fp; - frame_info->regs.r28 = regs->sp; - frame_info->regs.r31 = regs->blink; - frame_info->regs.r63 = regs->ret; - frame_info->call_frame = 0; } + return 0; } #endif @@ -115,11 +118,12 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; - seed_unwind_frame_info(tsk, regs, &frame_info); + if (seed_unwind_frame_info(tsk, regs, &frame_info)) + return 0; while (1) { address = UNW_PC(&frame_info); @@ -135,13 +139,18 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ #else /* On ARC, only Dward based unwinder works. fp based backtracing is * not possible (-fno-omit-frame-pointer) because of the way function - * prelogue is setup (callee regs saved and then fp set and not other + * prologue is setup (callee regs saved and then fp set and not other * way around */ pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); @@ -161,9 +170,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, /* Call-back which plugs into unwinding core to dump the stack in * case of panic/OOPs/BUG etc */ -static int __print_sym(unsigned int address, void *unused) +static int __print_sym(unsigned int address, void *arg) { - printk(" %pS\n", (void *)address); + const char *loglvl = arg; + + printk("%s %pS\n", loglvl, (void *)address); return 0; } @@ -220,24 +231,25 @@ static int __get_first_nonsched(unsigned int address, void *unused) *------------------------------------------------------------------------- */ -noinline void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs) +noinline void show_stacktrace(struct task_struct *tsk, struct pt_regs *regs, + const char *loglvl) { - pr_info("\nStack Trace:\n"); - arc_unwind_core(tsk, regs, __print_sym, NULL); + printk("%s\nStack Trace:\n", loglvl); + arc_unwind_core(tsk, regs, __print_sym, (void *)loglvl); } EXPORT_SYMBOL(show_stacktrace); /* Expected by sched Code */ -void show_stack(struct task_struct *tsk, unsigned long *sp) +void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) { - show_stacktrace(tsk, NULL); + show_stacktrace(tsk, NULL, loglvl); } /* Another API expected by schedular, shows up in "ps" as Wait Channel * Of course just returning schedule( ) would be pointless so unwind until * the function is not in schedular code */ -unsigned int get_wchan(struct task_struct *tsk) +unsigned int __get_wchan(struct task_struct *tsk) { return arc_unwind_core(tsk, NULL, __get_first_nonsched, NULL); } diff --git a/arch/arc/kernel/sys.c b/arch/arc/kernel/sys.c index fddecc76efb7..36a2a95c083b 100644 --- a/arch/arc/kernel/sys.c +++ b/arch/arc/kernel/sys.c @@ -7,11 +7,13 @@ #include <asm/syscalls.h> #define sys_clone sys_clone_wrapper +#define sys_clone3 sys_clone3_wrapper +#define sys_mmap2 sys_mmap_pgoff -#undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) void *sys_call_table[NR_syscalls] = { [0 ... NR_syscalls-1] = sys_ni_syscall, -#include <asm/unistd.h> +#include <asm/syscall_table_32.h> }; diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index a7fcbc0d3943..8d2ea2cbd98b 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Traps/Non-MMU Exception handling for ARC * * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * vineetg: May 2011 * -user-space unaligned access emulation * @@ -19,14 +16,11 @@ #include <linux/ptrace.h> #include <linux/kprobes.h> #include <linux/kgdb.h> +#include <asm/entry.h> #include <asm/setup.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/kprobes.h> - -void __init trap_init(void) -{ - return; -} +#include "unaligned.h" void die(const char *str, struct pt_regs *regs, unsigned long address) { @@ -50,7 +44,7 @@ unhandled_exception(const char *str, struct pt_regs *regs, tsk->thread.fault_address = (__force unsigned int)addr; - force_sig_fault(signo, si_code, addr, tsk); + force_sig_fault(signo, si_code, addr); } else { /* If not due to copy_(to|from)_user, we are doomed */ @@ -96,7 +90,7 @@ int do_misaligned_access(unsigned long address, struct pt_regs *regs, /* * Entry point for miscll errors such as Nested Exceptions - * -Duplicate TLB entry is handled seperately though + * -Duplicate TLB entry is handled separately though */ void do_machine_check_fault(unsigned long address, struct pt_regs *regs) { @@ -117,9 +111,7 @@ void do_machine_check_fault(unsigned long address, struct pt_regs *regs) */ void do_non_swi_trap(unsigned long address, struct pt_regs *regs) { - unsigned int param = regs->ecr_param; - - switch (param) { + switch (regs->ecr.param) { case 1: trap_is_brkpt(address, regs); break; diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index e8d9fb452346..c380d8c30704 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -1,8 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as */ #include <linux/ptrace.h> @@ -18,51 +16,47 @@ #include <asm/arcregs.h> #include <asm/irqflags.h> -/* - * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25) - * -Prints 3 regs per line and a CR. - * -To continue, callee regs right after scratch, special handling of CR - */ -static noinline void print_reg_file(long *reg_rev, int start_num) -{ - unsigned int i; - char buf[512]; - int n = 0, len = sizeof(buf); - - for (i = start_num; i < start_num + 13; i++) { - n += scnprintf(buf + n, len - n, "r%02u: 0x%08lx\t", - i, (unsigned long)*reg_rev); - - if (((i + 1) % 3) == 0) - n += scnprintf(buf + n, len - n, "\n"); - - /* because pt_regs has regs reversed: r12..r0, r25..r13 */ - if (is_isa_arcv2() && start_num == 0) - reg_rev++; - else - reg_rev--; - } - - if (start_num != 0) - n += scnprintf(buf + n, len - n, "\n\n"); +#define ARC_PATH_MAX 256 - /* To continue printing callee regs on same line as scratch regs */ - if (start_num == 0) - pr_info("%s", buf); - else - pr_cont("%s\n", buf); +static noinline void print_regs_scratch(struct pt_regs *regs) +{ + pr_cont("BTA: 0x%08lx\n SP: 0x%08lx FP: 0x%08lx BLK: %pS\n", + regs->bta, regs->sp, regs->fp, (void *)regs->blink); + pr_cont("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", + regs->lp_start, regs->lp_end, regs->lp_count); + + pr_info("r00: 0x%08lx\tr01: 0x%08lx\tr02: 0x%08lx\n" \ + "r03: 0x%08lx\tr04: 0x%08lx\tr05: 0x%08lx\n" \ + "r06: 0x%08lx\tr07: 0x%08lx\tr08: 0x%08lx\n" \ + "r09: 0x%08lx\tr10: 0x%08lx\tr11: 0x%08lx\n" \ + "r12: 0x%08lx\t", + regs->r0, regs->r1, regs->r2, + regs->r3, regs->r4, regs->r5, + regs->r6, regs->r7, regs->r8, + regs->r9, regs->r10, regs->r11, + regs->r12); } -static void show_callee_regs(struct callee_regs *cregs) +static void print_regs_callee(struct callee_regs *regs) { - print_reg_file(&(cregs->r13), 13); + pr_cont("r13: 0x%08lx\tr14: 0x%08lx\n" \ + "r15: 0x%08lx\tr16: 0x%08lx\tr17: 0x%08lx\n" \ + "r18: 0x%08lx\tr19: 0x%08lx\tr20: 0x%08lx\n" \ + "r21: 0x%08lx\tr22: 0x%08lx\tr23: 0x%08lx\n" \ + "r24: 0x%08lx\tr25: 0x%08lx\n", + regs->r13, regs->r14, + regs->r15, regs->r16, regs->r17, + regs->r18, regs->r19, regs->r20, + regs->r21, regs->r22, regs->r23, + regs->r24, regs->r25); } -static void print_task_path_n_nm(struct task_struct *tsk, char *buf) +static void print_task_path_n_nm(struct task_struct *tsk) { char *path_nm = NULL; struct mm_struct *mm; struct file *exe_file; + char buf[ARC_PATH_MAX]; mm = get_task_mm(tsk); if (!mm) @@ -72,7 +66,7 @@ static void print_task_path_n_nm(struct task_struct *tsk, char *buf) mmput(mm); if (exe_file) { - path_nm = file_path(exe_file, buf, 255); + path_nm = file_path(exe_file, buf, ARC_PATH_MAX-1); fput(exe_file); } @@ -80,36 +74,39 @@ done: pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?"); } -static void show_faulting_vma(unsigned long address, char *buf) +static void show_faulting_vma(unsigned long address) { struct vm_area_struct *vma; - char *nm = buf; struct mm_struct *active_mm = current->active_mm; /* can't use print_vma_addr() yet as it doesn't check for * non-inclusive vma */ - down_read(&active_mm->mmap_sem); - vma = find_vma(active_mm, address); + mmap_read_lock(active_mm); + vma = vma_lookup(active_mm, address); - /* check against the find_vma( ) behaviour which returns the next VMA - * if the container VMA is not found + /* Lookup the vma at the address and report if the container VMA is not + * found */ - if (vma && (vma->vm_start <= address)) { + if (vma) { + char buf[ARC_PATH_MAX]; + char *nm = "anon"; + if (vma->vm_file) { - nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1); + /* XXX: can we use %pD below and get rid of buf? */ + nm = d_path(file_user_path(vma->vm_file), buf, + ARC_PATH_MAX-1); if (IS_ERR(nm)) nm = "?"; } - pr_info(" @off 0x%lx in [%s]\n" - " VMA: 0x%08lx to 0x%08lx\n", + pr_info(" @off 0x%lx in [%s] VMA: 0x%08lx to 0x%08lx\n", vma->vm_start < TASK_UNMAPPED_BASE ? address : address - vma->vm_start, nm, vma->vm_start, vma->vm_end); } else pr_info(" @No matching VMA found\n"); - up_read(&active_mm->mmap_sem); + mmap_read_unlock(active_mm); } static void show_ecr_verbose(struct pt_regs *regs) @@ -117,20 +114,18 @@ static void show_ecr_verbose(struct pt_regs *regs) unsigned int vec, cause_code; unsigned long address; - pr_info("\n[ECR ]: 0x%08lx => ", regs->event); - /* For Data fault, this is data address not instruction addr */ address = current->thread.fault_address; - vec = regs->ecr_vec; - cause_code = regs->ecr_cause; + vec = regs->ecr.vec; + cause_code = regs->ecr.cause; /* For DTLB Miss or ProtV, display the memory involved too */ if (vec == ECR_V_DTLB_MISS) { - pr_cont("Invalid %s @ 0x%08lx by insn @ 0x%08lx\n", + pr_cont("Invalid %s @ 0x%08lx by insn @ %pS\n", (cause_code == 0x01) ? "Read" : ((cause_code == 0x02) ? "Write" : "EX"), - address, regs->ret); + address, (void *)regs->ret); } else if (vec == ECR_V_ITLB_MISS) { pr_cont("Insn could not be fetched\n"); } else if (vec == ECR_V_MACH_CHK) { @@ -140,7 +135,8 @@ static void show_ecr_verbose(struct pt_regs *regs) } else if (vec == ECR_V_PROTV) { if (cause_code == ECR_C_PROTV_INST_FETCH) pr_cont("Execute from Non-exec Page\n"); - else if (cause_code == ECR_C_PROTV_MISALIG_DATA) + else if (cause_code == ECR_C_PROTV_MISALIG_DATA && + IS_ENABLED(CONFIG_ISA_ARCOMPACT)) pr_cont("Misaligned r/w from 0x%08lx\n", address); else pr_cont("%s access not allowed on page\n", @@ -156,9 +152,11 @@ static void show_ecr_verbose(struct pt_regs *regs) pr_cont("Bus Error from Data Mem\n"); else pr_cont("Bus Error, check PRM\n"); + } else if (vec == ECR_V_MISALIGN) { + pr_cont("Misaligned r/w from 0x%08lx\n", address); #endif } else if (vec == ECR_V_TRAP) { - if (regs->ecr_param == 5) + if (regs->ecr.param == 5) pr_cont("gcc generated __builtin_trap\n"); } else { pr_cont("Check Programmer's Manual\n"); @@ -172,57 +170,47 @@ static void show_ecr_verbose(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { struct task_struct *tsk = current; - struct callee_regs *cregs; - char *buf; + struct callee_regs *cregs = (struct callee_regs *)tsk->thread.callee_reg; - buf = (char *)__get_free_page(GFP_KERNEL); - if (!buf) - return; + /* + * generic code calls us with preemption disabled, but some calls + * here could sleep, so re-enable to avoid lockdep splat + */ + preempt_enable(); - print_task_path_n_nm(tsk, buf); + print_task_path_n_nm(tsk); show_regs_print_info(KERN_INFO); show_ecr_verbose(regs); - pr_info("[EFA ]: 0x%08lx\n[BLINK ]: %pS\n[ERET ]: %pS\n", - current->thread.fault_address, - (void *)regs->blink, (void *)regs->ret); - if (user_mode(regs)) - show_faulting_vma(regs->ret, buf); /* faulting code, not data */ + show_faulting_vma(regs->ret); /* faulting code, not data */ + + pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\n", + regs->ecr.full, current->thread.fault_address, regs->ret); - pr_info("[STAT32]: 0x%08lx", regs->status32); + pr_info("STAT32: 0x%08lx", regs->status32); #define STS_BIT(r, bit) r->status32 & STATUS_##bit##_MASK ? #bit" " : "" #ifdef CONFIG_ISA_ARCOMPACT - pr_cont(" : %2s%2s%2s%2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s%2s%2s%2s]", (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE), STS_BIT(regs, A2), STS_BIT(regs, A1), STS_BIT(regs, E2), STS_BIT(regs, E1)); #else - pr_cont(" : %2s%2s%2s%2s\n", + pr_cont(" [%2s%2s%2s%2s] ", STS_BIT(regs, IE), (regs->status32 & STATUS_U_MASK) ? "U " : "K ", STS_BIT(regs, DE), STS_BIT(regs, AE)); #endif - pr_info("BTA: 0x%08lx\t SP: 0x%08lx\t FP: 0x%08lx\n", - regs->bta, regs->sp, regs->fp); - pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n", - regs->lp_start, regs->lp_end, regs->lp_count); - - /* print regs->r0 thru regs->r12 - * Sequential printing was generating horrible code - */ - print_reg_file(&(regs->r0), 0); - /* If Callee regs were saved, display them too */ - cregs = (struct callee_regs *)current->thread.callee_reg; + print_regs_scratch(regs); if (cregs) - show_callee_regs(cregs); + print_regs_callee(cregs); - free_page((unsigned long)buf); + preempt_disable(); } void show_kernel_fault_diag(const char *str, struct pt_regs *regs, @@ -238,5 +226,5 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs, /* Show stack trace if this Fatality happened in kernel mode */ if (!user_mode(regs)) - show_stacktrace(current, regs); + show_stacktrace(current, regs, KERN_DEFAULT); } diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 5f69c3bd59bb..3b2d8b1bd271 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011-2012 Synopsys (www.synopsys.com) * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * vineetg : May 2011 * -Adapted (from .26 to .35) * -original contribution by Tim.yao@amlogic.com - * */ #include <linux/types.h> @@ -16,6 +12,7 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> #include <asm/disasm.h> +#include "unaligned.h" #ifdef CONFIG_CPU_BIG_ENDIAN #define BE 1 @@ -203,7 +200,6 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, struct callee_regs *cregs) { struct disasm_state state; - char buf[TASK_COMM_LEN]; /* handle user mode only and only if enabled by sysadmin */ if (!user_mode(regs) || !unaligned_enabled) @@ -215,11 +211,11 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, " performance significantly\n. To enable further" " logging of such instances, please \n" " echo 0 > /proc/sys/kernel/ignore-unaligned-usertrap\n", - get_task_comm(buf, current), task_pid_nr(current)); + current->comm, task_pid_nr(current)); } else { /* Add rate limiting if it gets down to it */ pr_warn("%s(%d): unaligned access to/from 0x%lx by PC: 0x%lx\n", - get_task_comm(buf, current), task_pid_nr(current), + current->comm, task_pid_nr(current), address, regs->ret); } @@ -241,7 +237,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; - /* clear any remanants of delay slot */ + /* clear any remnants of delay slot */ if (delay_mode(regs)) { regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; diff --git a/arch/arc/kernel/unaligned.h b/arch/arc/kernel/unaligned.h new file mode 100644 index 000000000000..5244453bb85f --- /dev/null +++ b/arch/arc/kernel/unaligned.h @@ -0,0 +1,16 @@ +struct pt_regs; +struct callee_regs; + +#ifdef CONFIG_ARC_EMUL_UNALIGNED +int misaligned_fixup(unsigned long address, struct pt_regs *regs, + struct callee_regs *cregs); +#else +static inline int +misaligned_fixup(unsigned long address, struct pt_regs *regs, + struct callee_regs *cregs) +{ + /* Not fixed */ + return 1; +} +#endif + diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index d34f69eb1a95..789cfb9ea14e 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * Copyright (C) 2002-2006 Novell, Inc. * Jan Beulich <jbeulich@novell.com> * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * A simple API for unwinding kernel stacks. This is used for * debugging and error reporting purposes. The kernel doesn't need * full-blown stack unwinding with all the bells and whistles, so there @@ -22,7 +19,7 @@ #include <linux/uaccess.h> #include <linux/ptrace.h> #include <asm/sections.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/unwind.h> extern char __start_unwind[], __end_unwind[]; @@ -45,10 +42,10 @@ do { \ #define EXTRA_INFO(f) { \ BUILD_BUG_ON_ZERO(offsetof(struct unwind_frame_info, f) \ - % FIELD_SIZEOF(struct unwind_frame_info, f)) \ + % sizeof_field(struct unwind_frame_info, f)) \ + offsetof(struct unwind_frame_info, f) \ - / FIELD_SIZEOF(struct unwind_frame_info, f), \ - FIELD_SIZEOF(struct unwind_frame_info, f) \ + / sizeof_field(struct unwind_frame_info, f), \ + sizeof_field(struct unwind_frame_info, f) \ } #define PTREGS_INFO(f) EXTRA_INFO(regs.f) @@ -181,13 +178,7 @@ static void init_unwind_hdr(struct unwind_table *table, */ static void *__init unw_hdr_alloc_early(unsigned long sz) { - return memblock_alloc_from_nopanic(sz, sizeof(unsigned int), - MAX_DMA_ADDRESS); -} - -static void *unw_hdr_alloc(unsigned long sz) -{ - return kmalloc(sz, GFP_KERNEL); + return memblock_alloc_from(sz, sizeof(unsigned int), MAX_DMA_ADDRESS); } static void init_unwind_table(struct unwind_table *table, const char *name, @@ -196,25 +187,26 @@ static void init_unwind_table(struct unwind_table *table, const char *name, const void *table_start, unsigned long table_size, const u8 *header_start, unsigned long header_size) { - const u8 *ptr = header_start + 4; - const u8 *end = header_start + header_size; - table->core.pc = (unsigned long)core_start; table->core.range = core_size; table->init.pc = (unsigned long)init_start; table->init.range = init_size; table->address = table_start; table->size = table_size; - - /* See if the linker provided table looks valid. */ - if (header_size <= 4 - || header_start[0] != 1 - || (void *)read_pointer(&ptr, end, header_start[1]) != table_start - || header_start[2] == DW_EH_PE_omit - || read_pointer(&ptr, end, header_start[2]) <= 0 - || header_start[3] == DW_EH_PE_omit) - header_start = NULL; - + /* To avoid the pointer addition with NULL pointer.*/ + if (header_start != NULL) { + const u8 *ptr = header_start + 4; + const u8 *end = header_start + header_size; + /* See if the linker provided table looks valid. */ + if (header_size <= 4 + || header_start[0] != 1 + || (void *)read_pointer(&ptr, end, header_start[1]) + != table_start + || header_start[2] == DW_EH_PE_omit + || read_pointer(&ptr, end, header_start[2]) <= 0 + || header_start[3] == DW_EH_PE_omit) + header_start = NULL; + } table->hdrsz = header_size; smp_wmb(); table->header = header_start; @@ -249,26 +241,12 @@ static int cmp_eh_frame_hdr_table_entries(const void *p1, const void *p2) return (e1->start > e2->start) - (e1->start < e2->start); } -static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size) -{ - struct eh_frame_hdr_table_entry *e1 = p1; - struct eh_frame_hdr_table_entry *e2 = p2; - unsigned long v; - - v = e1->start; - e1->start = e2->start; - e2->start = v; - v = e1->fde; - e1->fde = e2->fde; - e2->fde = v; -} - static void init_unwind_hdr(struct unwind_table *table, void *(*alloc) (unsigned long)) { const u8 *ptr; unsigned long tableSize = table->size, hdrSize; - unsigned n; + unsigned int n; const u32 *fde; struct { u8 version; @@ -358,7 +336,7 @@ static void init_unwind_hdr(struct unwind_table *table, sort(header->table, n, sizeof(*header->table), - cmp_eh_frame_hdr_table_entries, swap_eh_frame_hdr_table_entries); + cmp_eh_frame_hdr_table_entries, NULL); table->hdrsz = hdrSize; smp_wmb(); @@ -370,6 +348,10 @@ ret_err: } #ifdef CONFIG_MODULES +static void *unw_hdr_alloc(unsigned long sz) +{ + return kmalloc(sz, GFP_KERNEL); +} static struct unwind_table *last_table; @@ -378,6 +360,8 @@ void *unwind_add_table(struct module *module, const void *table_start, unsigned long table_size) { struct unwind_table *table; + struct module_memory *core_text; + struct module_memory *init_text; if (table_size <= 0) return NULL; @@ -386,11 +370,11 @@ void *unwind_add_table(struct module *module, const void *table_start, if (!table) return NULL; - init_unwind_table(table, module->name, - module->core_layout.base, module->core_layout.size, - module->init_layout.base, module->init_layout.size, - table_start, table_size, - NULL, 0); + core_text = &module->mem[MOD_TEXT]; + init_text = &module->mem[MOD_INIT_TEXT]; + + init_unwind_table(table, module->name, core_text->base, core_text->size, + init_text->base, init_text->size, table_start, table_size, NULL, 0); init_unwind_hdr(table, unw_hdr_alloc); @@ -466,7 +450,7 @@ static uleb128_t get_uleb128(const u8 **pcur, const u8 *end) { const u8 *cur = *pcur; uleb128_t value; - unsigned shift; + unsigned int shift; for (shift = 0, value = 0; cur < end; shift += 7) { if (shift + 7 > 8 * sizeof(value) @@ -487,7 +471,7 @@ static sleb128_t get_sleb128(const u8 **pcur, const u8 *end) { const u8 *cur = *pcur; sleb128_t value; - unsigned shift; + unsigned int shift; for (shift = 0, value = 0; cur < end; shift += 7) { if (shift + 7 > 8 * sizeof(value) @@ -577,6 +561,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end, #else BUILD_BUG_ON(sizeof(u32) != sizeof(value)); #endif + fallthrough; case DW_EH_PE_native: if (end < (const void *)(ptr.pul + 1)) return 0; @@ -612,7 +597,7 @@ static unsigned long read_pointer(const u8 **pLoc, const void *end, static signed fde_pointer_type(const u32 *cie) { const u8 *ptr = (const u8 *)(cie + 2); - unsigned version = *ptr; + unsigned int version = *ptr; if (*++ptr) { const char *aug; @@ -831,7 +816,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc, case DW_CFA_def_cfa: state->cfa.reg = get_uleb128(&ptr.p8, end); unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg); - /*nobreak*/ + fallthrough; case DW_CFA_def_cfa_offset: state->cfa.offs = get_uleb128(&ptr.p8, end); unw_debug("cfa_def_cfa_offset: 0x%lx ", @@ -839,7 +824,7 @@ static int processCFI(const u8 *start, const u8 *end, unsigned long targetLoc, break; case DW_CFA_def_cfa_sf: state->cfa.reg = get_uleb128(&ptr.p8, end); - /*nobreak */ + fallthrough; case DW_CFA_def_cfa_offset_sf: state->cfa.offs = get_sleb128(&ptr.p8, end) * state->dataAlign; @@ -907,7 +892,7 @@ int arc_unwind(struct unwind_frame_info *frame) const u8 *ptr = NULL, *end = NULL; unsigned long pc = UNW_PC(frame) - frame->call_frame; unsigned long startLoc = 0, endLoc = 0, cfa; - unsigned i; + unsigned int i; signed ptrType = -1; uleb128_t retAddrReg = 0; const struct unwind_table *table; @@ -1182,11 +1167,9 @@ int arc_unwind(struct unwind_frame_info *frame) #endif /* update frame */ -#ifndef CONFIG_AS_CFI_SIGNAL_FRAME if (frame->call_frame && !UNW_DEFAULT_RA(state.regs[retAddrReg], state.dataAlign)) frame->call_frame = 0; -#endif cfa = FRAME_REG(state.cfa.reg, unsigned long) + state.cfa.offs; startLoc = min_t(unsigned long, UNW_SP(frame), cfa); endLoc = max_t(unsigned long, UNW_SP(frame), cfa); diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 8fb16bdabdcf..61a1b2b96e1d 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <asm-generic/vmlinux.lds.h> @@ -44,8 +41,8 @@ SECTIONS #endif /* - * The reason for having a seperate subsection .init.ramfs is to - * prevent objump from including it in kernel dumps + * The reason for having a separate subsection .init.ramfs is to + * prevent objdump from including it in kernel dumps * * Reason for having .init.ramfs above .init is to make sure that the * binary blob is tucked away to one side, reducing the displacement @@ -60,7 +57,6 @@ SECTIONS .init.ramfs : { INIT_RAM_FS } . = ALIGN(PAGE_SIZE); - _stext = .; HEAD_TEXT_SECTION INIT_TEXT_SECTION(L1_CACHE_BYTES) @@ -86,11 +82,13 @@ SECTIONS .text : { _text = .; + _stext = .; TEXT_TEXT SCHED_TEXT - CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) } @@ -98,13 +96,13 @@ SECTIONS _etext = .; _sdata = .; - RO_DATA_SECTION(PAGE_SIZE) + RO_DATA(PAGE_SIZE) /* * 1. this is .data essentially * 2. THREAD_SIZE for init.task, must be kernel-stk sz aligned */ - RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) _edata = .; @@ -121,12 +119,11 @@ SECTIONS /DISCARD/ : { *(.eh_frame) } #endif - NOTES - . = ALIGN(PAGE_SIZE); _end = . ; STABS_DEBUG + ELF_DETAILS DISCARDS .arcextmap 0 : { |